Merge tag 'wireless-drivers-next-for-davem-2017-04-07' of git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/wireless-drivers-next
Kalle Valo says:
====================
wireless-drivers-next patches for 4.12
Lots of bugfixes as usual but also some new features.
Major changes:
ath10k
* improve firmware download time for QCA6174 and QCA9377, especially
helps resume time
ath9k_htc
* add support AirTies 1eda:2315 AR9271 device
rt2x00
* add support MT7620
mwifiex
* enable auto deep sleep mode for USB chipsets
brcmfmac
* add support for network namespaces (WIPHY_FLAG_NETNS_OK)
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/Documentation/ABI/testing/sysfs-class-net-qmi b/Documentation/ABI/testing/sysfs-class-net-qmi
index fa5a00b..7122d62 100644
--- a/Documentation/ABI/testing/sysfs-class-net-qmi
+++ b/Documentation/ABI/testing/sysfs-class-net-qmi
@@ -21,3 +21,30 @@
is responsible for coordination of driver and firmware
link framing mode, changing this setting to 'Y' if the
firmware is configured for 'raw-ip' mode.
+
+What: /sys/class/net/<iface>/qmi/add_mux
+Date: March 2017
+KernelVersion: 4.11
+Contact: Bjørn Mork <bjorn@mork.no>
+Description:
+ Unsigned integer.
+
+ Write a number ranging from 1 to 127 to add a qmap mux
+ based network device, supported by recent Qualcomm based
+ modems.
+
+ The network device will be called qmimux.
+
+ Userspace is in charge of managing the qmux network device
+ activation and data stream setup on the modem side by
+ using the proper QMI protocol requests.
+
+What: /sys/class/net/<iface>/qmi/del_mux
+Date: March 2017
+KernelVersion: 4.11
+Contact: Bjørn Mork <bjorn@mork.no>
+Description:
+ Unsigned integer.
+
+ Write a number ranging from 1 to 127 to delete a previously
+ created qmap mux based network device.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 986e443..facc20a 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -653,6 +653,9 @@
cpuidle.off=1 [CPU_IDLE]
disable the cpuidle sub-system
+ cpufreq.off=1 [CPU_FREQ]
+ disable the cpufreq sub-system
+
cpu_init_udelay=N
[X86] Delay for N microsec between assert and de-assert
of APIC INIT to start processors. This delay occurs
@@ -1183,6 +1186,12 @@
functions that can be changed at run time by the
set_graph_notrace file in the debugfs tracing directory.
+ ftrace_graph_max_depth=<uint>
+ [FTRACE] Used with the function graph tracer. This is
+ the max depth it will trace into a function. This value
+ can be changed at run time by the max_graph_depth file
+ in the tracefs tracing directory. default: 0 (no limit)
+
gamecon.map[2|3]=
[HW,JOY] Multisystem joystick and NES/SNES/PSX pad
support via parallel port (up to 5 devices per port)
@@ -1716,6 +1725,12 @@
kernel and module base offset ASLR (Address Space
Layout Randomization).
+ kasan_multi_shot
+ [KNL] Enforce KASAN (Kernel Address Sanitizer) to print
+ report on every invalid memory access. Without this
+ parameter KASAN will print report only for the first
+ invalid access.
+
keepinitrd [HW,ARM]
kernelcore= [KNL,X86,IA-64,PPC]
diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt
index a71b809..2f66683 100644
--- a/Documentation/arm64/silicon-errata.txt
+++ b/Documentation/arm64/silicon-errata.txt
@@ -68,3 +68,4 @@
| | | | |
| Qualcomm Tech. | Falkor v1 | E1003 | QCOM_FALKOR_ERRATUM_1003 |
| Qualcomm Tech. | Falkor v1 | E1009 | QCOM_FALKOR_ERRATUM_1009 |
+| Qualcomm Tech. | QDF2400 ITS | E0065 | QCOM_QDF2400_ERRATUM_0065 |
diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt
index 3b8449f..49d7c99 100644
--- a/Documentation/cgroup-v2.txt
+++ b/Documentation/cgroup-v2.txt
@@ -1142,16 +1142,17 @@
pids.max
- A read-write single value file which exists on non-root cgroups. The
- default is "max".
+ A read-write single value file which exists on non-root
+ cgroups. The default is "max".
- Hard limit of number of processes.
+ Hard limit of number of processes.
pids.current
- A read-only single value file which exists on all cgroups.
+ A read-only single value file which exists on all cgroups.
- The number of processes currently in the cgroup and its descendants.
+ The number of processes currently in the cgroup and its
+ descendants.
Organisational operations are not blocked by cgroup policies, so it is
possible to have pids.current > pids.max. This can be done by either
diff --git a/Documentation/dev-tools/kcov.rst b/Documentation/dev-tools/kcov.rst
index 2c41b71..44886c9 100644
--- a/Documentation/dev-tools/kcov.rst
+++ b/Documentation/dev-tools/kcov.rst
@@ -10,7 +10,7 @@
to collect more or less stable coverage that is function of syscall inputs.
To achieve this goal it does not collect coverage in soft/hard interrupts
and instrumentation of some inherently non-deterministic parts of kernel is
-disbled (e.g. scheduler, locking).
+disabled (e.g. scheduler, locking).
Usage
-----
diff --git a/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller0.txt b/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller0.txt
index 30c5469..07dbb35 100644
--- a/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller0.txt
+++ b/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller0.txt
@@ -45,7 +45,7 @@
- 1 15 SATA
- 1 16 SATA USB
- 1 17 Main
- - 1 18 SD/MMC
+ - 1 18 SD/MMC/GOP
- 1 21 Slow IO (SPI, NOR, BootROM, I2C, UART)
- 1 22 USB3H0
- 1 23 USB3H1
@@ -65,7 +65,7 @@
"cpm-audio", "cpm-communit", "cpm-nand", "cpm-ppv2", "cpm-sdio",
"cpm-mg-domain", "cpm-mg-core", "cpm-xor1", "cpm-xor0", "cpm-gop-dp", "none",
"cpm-pcie_x10", "cpm-pcie_x11", "cpm-pcie_x4", "cpm-pcie-xor", "cpm-sata",
- "cpm-sata-usb", "cpm-main", "cpm-sd-mmc", "none", "none", "cpm-slow-io",
+ "cpm-sata-usb", "cpm-main", "cpm-sd-mmc-gop", "none", "none", "cpm-slow-io",
"cpm-usb3h0", "cpm-usb3h1", "cpm-usb3dev", "cpm-eip150", "cpm-eip197";
Example:
@@ -78,6 +78,6 @@
gate-clock-output-names = "cpm-audio", "cpm-communit", "cpm-nand", "cpm-ppv2", "cpm-sdio",
"cpm-mg-domain", "cpm-mg-core", "cpm-xor1", "cpm-xor0", "cpm-gop-dp", "none",
"cpm-pcie_x10", "cpm-pcie_x11", "cpm-pcie_x4", "cpm-pcie-xor", "cpm-sata",
- "cpm-sata-usb", "cpm-main", "cpm-sd-mmc", "none", "none", "cpm-slow-io",
+ "cpm-sata-usb", "cpm-main", "cpm-sd-mmc-gop", "none", "none", "cpm-slow-io",
"cpm-usb3h0", "cpm-usb3h1", "cpm-usb3dev", "cpm-eip150", "cpm-eip197";
};
diff --git a/Documentation/devicetree/bindings/display/exynos/exynos_dsim.txt b/Documentation/devicetree/bindings/display/exynos/exynos_dsim.txt
index a782659..ca5204b 100644
--- a/Documentation/devicetree/bindings/display/exynos/exynos_dsim.txt
+++ b/Documentation/devicetree/bindings/display/exynos/exynos_dsim.txt
@@ -4,7 +4,6 @@
- compatible: value should be one of the following
"samsung,exynos3250-mipi-dsi" /* for Exynos3250/3472 SoCs */
"samsung,exynos4210-mipi-dsi" /* for Exynos4 SoCs */
- "samsung,exynos4415-mipi-dsi" /* for Exynos4415 SoC */
"samsung,exynos5410-mipi-dsi" /* for Exynos5410/5420/5440 SoCs */
"samsung,exynos5422-mipi-dsi" /* for Exynos5422/5800 SoCs */
"samsung,exynos5433-mipi-dsi" /* for Exynos5433 SoCs */
diff --git a/Documentation/devicetree/bindings/display/exynos/samsung-fimd.txt b/Documentation/devicetree/bindings/display/exynos/samsung-fimd.txt
index 18645e0..5837402c 100644
--- a/Documentation/devicetree/bindings/display/exynos/samsung-fimd.txt
+++ b/Documentation/devicetree/bindings/display/exynos/samsung-fimd.txt
@@ -11,7 +11,6 @@
"samsung,s5pv210-fimd"; /* for S5PV210 SoC */
"samsung,exynos3250-fimd"; /* for Exynos3250/3472 SoCs */
"samsung,exynos4210-fimd"; /* for Exynos4 SoCs */
- "samsung,exynos4415-fimd"; /* for Exynos4415 SoC */
"samsung,exynos5250-fimd"; /* for Exynos5250 SoCs */
"samsung,exynos5420-fimd"; /* for Exynos5420/5422/5800 SoCs */
diff --git a/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt b/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt
index ea9c1c9..520d61d 100644
--- a/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt
+++ b/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt
@@ -13,7 +13,7 @@
- "rockchip,rk2928-dw-mshc": for Rockchip RK2928 and following,
before RK3288
- "rockchip,rk3288-dw-mshc": for Rockchip RK3288
- - "rockchip,rk1108-dw-mshc", "rockchip,rk3288-dw-mshc": for Rockchip RK1108
+ - "rockchip,rv1108-dw-mshc", "rockchip,rk3288-dw-mshc": for Rockchip RV1108
- "rockchip,rk3036-dw-mshc", "rockchip,rk3288-dw-mshc": for Rockchip RK3036
- "rockchip,rk3368-dw-mshc", "rockchip,rk3288-dw-mshc": for Rockchip RK3368
- "rockchip,rk3399-dw-mshc", "rockchip,rk3288-dw-mshc": for Rockchip RK3399
diff --git a/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt b/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt
index 10587bd..26c77d9 100644
--- a/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt
+++ b/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt
@@ -2,11 +2,14 @@
Required properties:
- compatible: should contain one of "brcm,genet-v1", "brcm,genet-v2",
- "brcm,genet-v3", "brcm,genet-v4".
+ "brcm,genet-v3", "brcm,genet-v4", "brcm,genet-v5".
- reg: address and length of the register set for the device
-- interrupts: must be two cells, the first cell is the general purpose
- interrupt line, while the second cell is the interrupt for the ring
- RX and TX queues operating in ring mode
+- interrupts and/or interrupts-extended: must be two cells, the first cell
+ is the general purpose interrupt line, while the second cell is the
+ interrupt for the ring RX and TX queues operating in ring mode. An
+ optional third interrupt cell for Wake-on-LAN can be specified.
+ See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
+ for information on the property specifics.
- phy-mode: see ethernet.txt file in the same directory
- #address-cells: should be 1
- #size-cells: should be 1
@@ -29,15 +32,15 @@
Required child nodes:
-- mdio bus node: this node should always be present regarless of the PHY
+- mdio bus node: this node should always be present regardless of the PHY
configuration of the GENET instance
MDIO bus node required properties:
- compatible: should contain one of "brcm,genet-mdio-v1", "brcm,genet-mdio-v2"
- "brcm,genet-mdio-v3", "brcm,genet-mdio-v4", the version has to match the
- parent node compatible property (e.g: brcm,genet-v4 pairs with
- brcm,genet-mdio-v4)
+ "brcm,genet-mdio-v3", "brcm,genet-mdio-v4", "brcm,genet-mdio-v5", the version
+ has to match the parent node compatible property (e.g: brcm,genet-v4 pairs
+ with brcm,genet-mdio-v4)
- reg: address and length relative to the parent node base register address
- #address-cells: address cell for MDIO bus addressing, should be 1
- #size-cells: size of the cells for MDIO bus addressing, should be 0
diff --git a/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt b/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt
index ab0bb42..4648948 100644
--- a/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt
+++ b/Documentation/devicetree/bindings/net/brcm,unimac-mdio.txt
@@ -2,8 +2,9 @@
Required properties:
- compatible: should one from "brcm,genet-mdio-v1", "brcm,genet-mdio-v2",
- "brcm,genet-mdio-v3", "brcm,genet-mdio-v4" or "brcm,unimac-mdio"
-- reg: address and length of the regsiter set for the device, first one is the
+ "brcm,genet-mdio-v3", "brcm,genet-mdio-v4", "brcm,genet-mdio-v5" or
+ "brcm,unimac-mdio"
+- reg: address and length of the register set for the device, first one is the
base register, and the second one is optional and for indirect accesses to
larger than 16-bits MDIO transactions
- reg-names: name(s) of the register must be "mdio" and optional "mdio_indir_rw"
diff --git a/Documentation/devicetree/bindings/net/can/holt_hi311x.txt b/Documentation/devicetree/bindings/net/can/holt_hi311x.txt
new file mode 100644
index 0000000..23aa94e
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/can/holt_hi311x.txt
@@ -0,0 +1,24 @@
+* Holt HI-311X stand-alone CAN controller device tree bindings
+
+Required properties:
+ - compatible: Should be one of the following:
+ - "holt,hi3110" for HI-3110
+ - reg: SPI chip select.
+ - clocks: The clock feeding the CAN controller.
+ - interrupt-parent: The parent interrupt controller.
+ - interrupts: Should contain IRQ line for the CAN controller.
+
+Optional properties:
+ - vdd-supply: Regulator that powers the CAN controller.
+ - xceiver-supply: Regulator that powers the CAN transceiver.
+
+Example:
+ can0: can@1 {
+ compatible = "holt,hi3110";
+ reg = <1>;
+ clocks = <&clk32m>;
+ interrupt-parent = <&gpio4>;
+ interrupts = <13 IRQ_TYPE_EDGE_RISING>;
+ vdd-supply = <®5v0>;
+ xceiver-supply = <®5v0>;
+ };
diff --git a/Documentation/devicetree/bindings/net/can/ti_hecc.txt b/Documentation/devicetree/bindings/net/can/ti_hecc.txt
new file mode 100644
index 0000000..e0f0a7c
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/can/ti_hecc.txt
@@ -0,0 +1,32 @@
+Texas Instruments High End CAN Controller (HECC)
+================================================
+
+This file provides information, what the device node
+for the hecc interface contains.
+
+Required properties:
+- compatible: "ti,am3517-hecc"
+- reg: addresses and lengths of the register spaces for 'hecc', 'hecc-ram'
+ and 'mbx'
+- reg-names :"hecc", "hecc-ram", "mbx"
+- interrupts: interrupt mapping for the hecc interrupts sources
+- clocks: clock phandles (see clock bindings for details)
+
+Optional properties:
+- ti,use-hecc1int: if provided configures HECC to produce all interrupts
+ on HECC1INT interrupt line. By default HECC0INT interrupt
+ line will be used.
+- xceiver-supply: regulator that powers the CAN transceiver
+
+Example:
+
+For am3517evm board:
+ hecc: can@5c050000 {
+ compatible = "ti,am3517-hecc";
+ reg = <0x5c050000 0x80>,
+ <0x5c053000 0x180>,
+ <0x5c052000 0x200>;
+ reg-names = "hecc", "hecc-ram", "mbx";
+ interrupts = <24>;
+ clocks = <&hecc_ck>;
+ };
diff --git a/Documentation/devicetree/bindings/net/dsa/mt7530.txt b/Documentation/devicetree/bindings/net/dsa/mt7530.txt
new file mode 100644
index 0000000..a9bc27b
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/dsa/mt7530.txt
@@ -0,0 +1,92 @@
+Mediatek MT7530 Ethernet switch
+================================
+
+Required properties:
+
+- compatible: Must be compatible = "mediatek,mt7530";
+- #address-cells: Must be 1.
+- #size-cells: Must be 0.
+- mediatek,mcm: Boolean; if defined, indicates that either MT7530 is the part
+ on multi-chip module belong to MT7623A has or the remotely standalone
+ chip as the function MT7623N reference board provided for.
+- core-supply: Phandle to the regulator node necessary for the core power.
+- io-supply: Phandle to the regulator node necessary for the I/O power.
+ See Documentation/devicetree/bindings/regulator/mt6323-regulator.txt
+ for details for the regulator setup on these boards.
+
+If the property mediatek,mcm isn't defined, following property is required
+
+- reset-gpios: Should be a gpio specifier for a reset line.
+
+Else, following properties are required
+
+- resets : Phandle pointing to the system reset controller with
+ line index for the ethsys.
+- reset-names : Should be set to "mcm".
+
+Required properties for the child nodes within ports container:
+
+- reg: Port address described must be 6 for CPU port and from 0 to 5 for
+ user ports.
+- phy-mode: String, must be either "trgmii" or "rgmii" for port labeled
+ "cpu".
+
+See Documentation/devicetree/bindings/dsa/dsa.txt for a list of additional
+required, optional properties and how the integrated switch subnodes must
+be specified.
+
+Example:
+
+ &mdio0 {
+ switch@0 {
+ compatible = "mediatek,mt7530";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0>;
+
+ core-supply = <&mt6323_vpa_reg>;
+ io-supply = <&mt6323_vemc3v3_reg>;
+ reset-gpios = <&pio 33 0>;
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0>;
+ port@0 {
+ reg = <0>;
+ label = "lan0";
+ };
+
+ port@1 {
+ reg = <1>;
+ label = "lan1";
+ };
+
+ port@2 {
+ reg = <2>;
+ label = "lan2";
+ };
+
+ port@3 {
+ reg = <3>;
+ label = "lan3";
+ };
+
+ port@4 {
+ reg = <4>;
+ label = "wan";
+ };
+
+ port@6 {
+ reg = <6>;
+ label = "cpu";
+ ethernet = <&gmac0>;
+ phy-mode = "trgmii";
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+ };
+ };
+ };
+ };
+ };
diff --git a/Documentation/devicetree/bindings/net/marvell-pp2.txt b/Documentation/devicetree/bindings/net/marvell-pp2.txt
index 4754364..6b4956b 100644
--- a/Documentation/devicetree/bindings/net/marvell-pp2.txt
+++ b/Documentation/devicetree/bindings/net/marvell-pp2.txt
@@ -1,17 +1,28 @@
-* Marvell Armada 375 Ethernet Controller (PPv2)
+* Marvell Armada 375 Ethernet Controller (PPv2.1)
+ Marvell Armada 7K/8K Ethernet Controller (PPv2.2)
Required properties:
-- compatible: should be "marvell,armada-375-pp2"
+- compatible: should be one of:
+ "marvell,armada-375-pp2"
+ "marvell,armada-7k-pp2"
- reg: addresses and length of the register sets for the device.
- Must contain the following register sets:
+ For "marvell,armada-375-pp2", must contain the following register
+ sets:
- common controller registers
- LMS registers
- In addition, at least one port register set is required.
-- clocks: a pointer to the reference clocks for this device, consequently:
- - main controller clock
- - GOP clock
-- clock-names: names of used clocks, must be "pp_clk" and "gop_clk".
+ - one register area per Ethernet port
+ For "marvell,armada-7k-pp2", must contain the following register
+ sets:
+ - packet processor registers
+ - networking interfaces registers
+
+- clocks: pointers to the reference clocks for this device, consequently:
+ - main controller clock (for both armada-375-pp2 and armada-7k-pp2)
+ - GOP clock (for both armada-375-pp2 and armada-7k-pp2)
+ - MG clock (only for armada-7k-pp2)
+- clock-names: names of used clocks, must be "pp_clk", "gop_clk" and
+ "mg_clk" (the latter only for armada-7k-pp2).
The ethernet ports are represented by subnodes. At least one port is
required.
@@ -19,8 +30,10 @@
Required properties (port):
- interrupts: interrupt for the port
-- port-id: should be '0' or '1' for ethernet ports, and '2' for the
- loopback port
+- port-id: ID of the port from the MAC point of view
+- gop-port-id: only for marvell,armada-7k-pp2, ID of the port from the
+ GOP (Group Of Ports) point of view. This ID is used to index the
+ per-port registers in the second register area.
- phy-mode: See ethernet.txt file in the same directory
Optional properties (port):
@@ -29,7 +42,7 @@
- phy: a phandle to a phy node defining the PHY address (as the reg
property, a single integer).
-Example:
+Example for marvell,armada-375-pp2:
ethernet@f0000 {
compatible = "marvell,armada-375-pp2";
@@ -57,3 +70,30 @@
phy-mode = "gmii";
};
};
+
+Example for marvell,armada-7k-pp2:
+
+cpm_ethernet: ethernet@0 {
+ compatible = "marvell,armada-7k-pp22";
+ reg = <0x0 0x100000>, <0x129000 0xb000>;
+ clocks = <&cpm_syscon0 1 3>, <&cpm_syscon0 1 9>, <&cpm_syscon0 1 5>;
+ clock-names = "pp_clk", "gop_clk", "gp_clk";
+
+ eth0: eth0 {
+ interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;
+ port-id = <0>;
+ gop-port-id = <0>;
+ };
+
+ eth1: eth1 {
+ interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
+ port-id = <1>;
+ gop-port-id = <2>;
+ };
+
+ eth2: eth2 {
+ interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>;
+ port-id = <2>;
+ gop-port-id = <3>;
+ };
+};
diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt
index d3bfc2b..f652b0c 100644
--- a/Documentation/devicetree/bindings/net/stmmac.txt
+++ b/Documentation/devicetree/bindings/net/stmmac.txt
@@ -28,9 +28,9 @@
clocks may be specified in derived bindings.
- clock-names: One name for each entry in the clocks property, the
first one should be "stmmaceth" and the second one should be "pclk".
-- clk_ptp_ref: this is the PTP reference clock; in case of the PTP is
- available this clock is used for programming the Timestamp Addend Register.
- If not passed then the system clock will be used and this is fine on some
+- ptp_ref: this is the PTP reference clock; in case of the PTP is available
+ this clock is used for programming the Timestamp Addend Register. If not
+ passed then the system clock will be used and this is fine on some
platforms.
- tx-fifo-depth: See ethernet.txt file in the same directory
- rx-fifo-depth: See ethernet.txt file in the same directory
@@ -72,7 +72,45 @@
- snps,mb: mixed-burst
- snps,rb: rebuild INCRx Burst
- mdio: with compatible = "snps,dwmac-mdio", create and register mdio bus.
-
+- Multiple RX Queues parameters: below the list of all the parameters to
+ configure the multiple RX queues:
+ - snps,rx-queues-to-use: number of RX queues to be used in the driver
+ - Choose one of these RX scheduling algorithms:
+ - snps,rx-sched-sp: Strict priority
+ - snps,rx-sched-wsp: Weighted Strict priority
+ - For each RX queue
+ - Choose one of these modes:
+ - snps,dcb-algorithm: Queue to be enabled as DCB
+ - snps,avb-algorithm: Queue to be enabled as AVB
+ - snps,map-to-dma-channel: Channel to map
+ - Specifiy specific packet routing:
+ - snps,route-avcp: AV Untagged Control packets
+ - snps,route-ptp: PTP Packets
+ - snps,route-dcbcp: DCB Control Packets
+ - snps,route-up: Untagged Packets
+ - snps,route-multi-broad: Multicast & Broadcast Packets
+ - snps,priority: RX queue priority (Range: 0x0 to 0xF)
+- Multiple TX Queues parameters: below the list of all the parameters to
+ configure the multiple TX queues:
+ - snps,tx-queues-to-use: number of TX queues to be used in the driver
+ - Choose one of these TX scheduling algorithms:
+ - snps,tx-sched-wrr: Weighted Round Robin
+ - snps,tx-sched-wfq: Weighted Fair Queuing
+ - snps,tx-sched-dwrr: Deficit Weighted Round Robin
+ - snps,tx-sched-sp: Strict priority
+ - For each TX queue
+ - snps,weight: TX queue weight (if using a DCB weight algorithm)
+ - Choose one of these modes:
+ - snps,dcb-algorithm: TX queue will be working in DCB
+ - snps,avb-algorithm: TX queue will be working in AVB
+ [Attention] Queue 0 is reserved for legacy traffic
+ and so no AVB is available in this queue.
+ - Configure Credit Base Shaper (if AVB Mode selected):
+ - snps,send_slope: enable Low Power Interface
+ - snps,idle_slope: unlock on WoL
+ - snps,high_credit: max write outstanding req. limit
+ - snps,low_credit: max read outstanding req. limit
+ - snps,priority: TX queue priority (Range: 0x0 to 0xF)
Examples:
stmmac_axi_setup: stmmac-axi-config {
@@ -81,6 +119,35 @@
snps,blen = <256 128 64 32 0 0 0>;
};
+ mtl_rx_setup: rx-queues-config {
+ snps,rx-queues-to-use = <1>;
+ snps,rx-sched-sp;
+ queue0 {
+ snps,dcb-algorithm;
+ snps,map-to-dma-channel = <0x0>;
+ snps,priority = <0x0>;
+ };
+ };
+
+ mtl_tx_setup: tx-queues-config {
+ snps,tx-queues-to-use = <2>;
+ snps,tx-sched-wrr;
+ queue0 {
+ snps,weight = <0x10>;
+ snps,dcb-algorithm;
+ snps,priority = <0x0>;
+ };
+
+ queue1 {
+ snps,avb-algorithm;
+ snps,send_slope = <0x1000>;
+ snps,idle_slope = <0x1000>;
+ snps,high_credit = <0x3E800>;
+ snps,low_credit = <0xFFC18000>;
+ snps,priority = <0x1>;
+ };
+ };
+
gmac0: ethernet@e0800000 {
compatible = "st,spear600-gmac";
reg = <0xe0800000 0x8000>;
@@ -104,4 +171,6 @@
phy1: ethernet-phy@0 {
};
};
+ snps,mtl-rx-config = <&mtl_rx_setup>;
+ snps,mtl-tx-config = <&mtl_tx_setup>;
};
diff --git a/Documentation/devicetree/bindings/phy/brcm,nsp-usb3-phy.txt b/Documentation/devicetree/bindings/phy/brcm,nsp-usb3-phy.txt
deleted file mode 100644
index e68ae5d..0000000
--- a/Documentation/devicetree/bindings/phy/brcm,nsp-usb3-phy.txt
+++ /dev/null
@@ -1,39 +0,0 @@
-Broadcom USB3 phy binding for northstar plus SoC
-The USB3 phy is internal to the SoC and is accessed using mdio interface.
-
-Required mdio bus properties:
-- reg: Should be 0x0 for SoC internal USB3 phy
-- #address-cells: must be 1
-- #size-cells: must be 0
-
-Required USB3 PHY properties:
-- compatible: should be "brcm,nsp-usb3-phy"
-- reg: USB3 Phy address on SoC internal MDIO bus and it should be 0x10.
-- usb3-ctrl-syscon: handler of syscon node defining physical address
- of usb3 control register.
-- #phy-cells: must be 0
-
-Required usb3 control properties:
-- compatible: should be "brcm,nsp-usb3-ctrl"
-- reg: offset and length of the control registers
-
-Example:
-
- mdio@0 {
- reg = <0x0>;
- #address-cells = <1>;
- #size-cells = <0>;
-
- usb3_phy: usb-phy@10 {
- compatible = "brcm,nsp-usb3-phy";
- reg = <0x10>;
- usb3-ctrl-syscon = <&usb3_ctrl>;
- #phy-cells = <0>;
- status = "disabled";
- };
- };
-
- usb3_ctrl: syscon@104408 {
- compatible = "brcm,nsp-usb3-ctrl", "syscon";
- reg = <0x104408 0x3fc>;
- };
diff --git a/Documentation/devicetree/bindings/powerpc/4xx/emac.txt b/Documentation/devicetree/bindings/powerpc/4xx/emac.txt
index 712baf6..44b842b 100644
--- a/Documentation/devicetree/bindings/powerpc/4xx/emac.txt
+++ b/Documentation/devicetree/bindings/powerpc/4xx/emac.txt
@@ -71,6 +71,9 @@
For Axon it can be absent, though my current driver
doesn't handle phy-address yet so for now, keep
0x00ffffff in it.
+ - phy-handle : Used to describe configurations where a external PHY
+ is used. Please refer to:
+ Documentation/devicetree/bindings/net/ethernet.txt
- rx-fifo-size-gige : 1 cell, Rx fifo size in bytes for 1000 Mb/sec
operations (if absent the value is the same as
rx-fifo-size). For Axon, either absent or 2048.
@@ -81,8 +84,22 @@
offload, phandle of the TAH device node.
- tah-channel : 1 cell, optional. If appropriate, channel used on the
TAH engine.
+ - fixed-link : Fixed-link subnode describing a link to a non-MDIO
+ managed entity. See
+ Documentation/devicetree/bindings/net/fixed-link.txt
+ for details.
+ - mdio subnode : When the EMAC has a phy connected to its local
+ mdio, which us supported by the kernel's network
+ PHY library in drivers/net/phy, there must be device
+ tree subnode with the following required properties:
+ - #address-cells: Must be <1>.
+ - #size-cells: Must be <0>.
- Example:
+ For PHY definitions: Please refer to
+ Documentation/devicetree/bindings/net/phy.txt and
+ Documentation/devicetree/bindings/net/ethernet.txt
+
+ Examples:
EMAC0: ethernet@40000800 {
device_type = "network";
@@ -104,6 +121,48 @@
zmii-channel = <0>;
};
+ EMAC1: ethernet@ef600c00 {
+ device_type = "network";
+ compatible = "ibm,emac-apm821xx", "ibm,emac4sync";
+ interrupt-parent = <&EMAC1>;
+ interrupts = <0 1>;
+ #interrupt-cells = <1>;
+ #address-cells = <0>;
+ #size-cells = <0>;
+ interrupt-map = <0 &UIC2 0x10 IRQ_TYPE_LEVEL_HIGH /* Status */
+ 1 &UIC2 0x14 IRQ_TYPE_LEVEL_HIGH /* Wake */>;
+ reg = <0xef600c00 0x000000c4>;
+ local-mac-address = [000000000000]; /* Filled in by U-Boot */
+ mal-device = <&MAL0>;
+ mal-tx-channel = <0>;
+ mal-rx-channel = <0>;
+ cell-index = <0>;
+ max-frame-size = <9000>;
+ rx-fifo-size = <16384>;
+ tx-fifo-size = <2048>;
+ fifo-entry-size = <10>;
+ phy-mode = "rgmii";
+ phy-handle = <&phy0>;
+ phy-map = <0x00000000>;
+ rgmii-device = <&RGMII0>;
+ rgmii-channel = <0>;
+ tah-device = <&TAH0>;
+ tah-channel = <0>;
+ has-inverted-stacr-oc;
+ has-new-stacr-staopc;
+
+ mdio {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ phy0: ethernet-phy@0 {
+ compatible = "ethernet-phy-ieee802.3-c22";
+ reg = <0>;
+ };
+ };
+ };
+
+
ii) McMAL node
Required properties:
@@ -145,4 +204,3 @@
- revision : as provided by the RGMII new version register if
available.
For Axon: 0x0000012a
-
diff --git a/Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt b/Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt
index c3f6546..6a23ad9 100644
--- a/Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt
@@ -45,7 +45,7 @@
Optional Properties:
- reg-names: In addition to the required properties, the following are optional
- "efuse-address" - Contains efuse base address used to pick up ABB info.
- - "ldo-address" - Contains address of ABB LDO overide register address.
+ - "ldo-address" - Contains address of ABB LDO override register.
"efuse-address" is required for this.
- ti,ldovbb-vset-mask - Required if ldo-address is set, mask for LDO override
register to provide override vset value.
diff --git a/Documentation/devicetree/bindings/rng/omap_rng.txt b/Documentation/devicetree/bindings/rng/omap_rng.txt
index 4714772..9cf7876 100644
--- a/Documentation/devicetree/bindings/rng/omap_rng.txt
+++ b/Documentation/devicetree/bindings/rng/omap_rng.txt
@@ -12,7 +12,8 @@
- reg : Offset and length of the register set for the module
- interrupts : the interrupt number for the RNG module.
Used for "ti,omap4-rng" and "inside-secure,safexcel-eip76"
-- clocks: the trng clock source
+- clocks: the trng clock source. Only mandatory for the
+ "inside-secure,safexcel-eip76" compatible.
Example:
/* AM335x */
diff --git a/Documentation/devicetree/bindings/usb/usb251xb.txt b/Documentation/devicetree/bindings/usb/usb251xb.txt
index 0c065f7..3957d4e 100644
--- a/Documentation/devicetree/bindings/usb/usb251xb.txt
+++ b/Documentation/devicetree/bindings/usb/usb251xb.txt
@@ -7,18 +7,18 @@
- compatible : Should be "microchip,usb251xb" or one of the specific types:
"microchip,usb2512b", "microchip,usb2512bi", "microchip,usb2513b",
"microchip,usb2513bi", "microchip,usb2514b", "microchip,usb2514bi"
- - hub-reset-gpios : Should specify the gpio for hub reset
+ - reset-gpios : Should specify the gpio for hub reset
+ - reg : I2C address on the selected bus (default is <0x2C>)
Optional properties :
- - reg : I2C address on the selected bus (default is <0x2C>)
- skip-config : Skip Hub configuration, but only send the USB-Attach command
- - vendor-id : USB Vendor ID of the hub (16 bit, default is 0x0424)
- - product-id : USB Product ID of the hub (16 bit, default depends on type)
- - device-id : USB Device ID of the hub (16 bit, default is 0x0bb3)
- - language-id : USB Language ID (16 bit, default is 0x0000)
- - manufacturer : USB Manufacturer string (max 31 characters long)
- - product : USB Product string (max 31 characters long)
- - serial : USB Serial string (max 31 characters long)
+ - vendor-id : Set USB Vendor ID of the hub (16 bit, default is 0x0424)
+ - product-id : Set USB Product ID of the hub (16 bit, default depends on type)
+ - device-id : Set USB Device ID of the hub (16 bit, default is 0x0bb3)
+ - language-id : Set USB Language ID (16 bit, default is 0x0000)
+ - manufacturer : Set USB Manufacturer string (max 31 characters long)
+ - product : Set USB Product string (max 31 characters long)
+ - serial : Set USB Serial string (max 31 characters long)
- {bus,self}-powered : selects between self- and bus-powered operation (default
is self-powered)
- disable-hi-speed : disable USB Hi-Speed support
@@ -31,8 +31,10 @@
(default is individual)
- dynamic-power-switching : enable auto-switching from self- to bus-powered
operation if the local power source is removed or unavailable
- - oc-delay-{100us,4ms,8ms,16ms} : set over current timer delay (default is 8ms)
- - compound-device : indicated the hub is part of a compound device
+ - oc-delay-us : Delay time (in microseconds) for filtering the over-current
+ sense inputs. Valid values are 100, 4000, 8000 (default) and 16000. If
+ an invalid value is given, the default is used instead.
+ - compound-device : indicate the hub is part of a compound device
- port-mapping-mode : enable port mapping mode
- string-support : enable string descriptor support (required for manufacturer,
product and serial string configuration)
@@ -40,34 +42,15 @@
device connected.
- sp-disabled-ports : Specifies the ports which will be self-power disabled
- bp-disabled-ports : Specifies the ports which will be bus-power disabled
- - max-sp-power : Specifies the maximum current the hub consumes from an
- upstream port when operating as self-powered hub including the power
- consumption of a permanently attached peripheral if the hub is
- configured as a compound device. The value is given in mA in a 0 - 500
- range (default is 2).
- - max-bp-power : Specifies the maximum current the hub consumes from an
- upstream port when operating as bus-powered hub including the power
- consumption of a permanently attached peripheral if the hub is
- configured as a compound device. The value is given in mA in a 0 - 500
- range (default is 100).
- - max-sp-current : Specifies the maximum current the hub consumes from an
- upstream port when operating as self-powered hub EXCLUDING the power
- consumption of a permanently attached peripheral if the hub is
- configured as a compound device. The value is given in mA in a 0 - 500
- range (default is 2).
- - max-bp-current : Specifies the maximum current the hub consumes from an
- upstream port when operating as bus-powered hub EXCLUDING the power
- consumption of a permanently attached peripheral if the hub is
- configured as a compound device. The value is given in mA in a 0 - 500
- range (default is 100).
- - power-on-time : Specifies the time it takes from the time the host initiates
- the power-on sequence to a port until the port has adequate power. The
- value is given in ms in a 0 - 510 range (default is 100ms).
+ - power-on-time-ms : Specifies the time it takes from the time the host
+ initiates the power-on sequence to a port until the port has adequate
+ power. The value is given in ms in a 0 - 510 range (default is 100ms).
Examples:
usb2512b@2c {
compatible = "microchip,usb2512b";
- hub-reset-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
+ reg = <0x2c>;
+ reset-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
};
usb2514b@2c {
diff --git a/Documentation/extcon/intel-int3496.txt b/Documentation/extcon/intel-int3496.txt
index af0b366..8155dbc 100644
--- a/Documentation/extcon/intel-int3496.txt
+++ b/Documentation/extcon/intel-int3496.txt
@@ -20,3 +20,8 @@
Index 2: The output gpio for muxing of the data pins between the USB host and
the USB peripheral controller, write 1 to mux to the peripheral
controller
+
+There is a mapping between indices and GPIO connection IDs as follows
+ id index 0
+ vbus index 1
+ mux index 2
diff --git a/Documentation/gcc-plugins.txt b/Documentation/gcc-plugins.txt
index 891c694..433eaef 100644
--- a/Documentation/gcc-plugins.txt
+++ b/Documentation/gcc-plugins.txt
@@ -18,8 +18,8 @@
gcc-4.7 can be compiled by a C or a C++ compiler,
and versions 4.8+ can only be compiled by a C++ compiler.
-Currently the GCC plugin infrastructure supports only the x86, arm and arm64
-architectures.
+Currently the GCC plugin infrastructure supports only the x86, arm, arm64 and
+powerpc architectures.
This infrastructure was ported from grsecurity [6] and PaX [7].
diff --git a/Documentation/networking/i40e.txt b/Documentation/networking/i40e.txt
index a251bf4..57e616e 100644
--- a/Documentation/networking/i40e.txt
+++ b/Documentation/networking/i40e.txt
@@ -63,6 +63,78 @@
The latest release of ethtool can be found from
https://www.kernel.org/pub/software/network/ethtool
+
+ Flow Director n-ntuple traffic filters (FDir)
+ ---------------------------------------------
+ The driver utilizes the ethtool interface for configuring ntuple filters,
+ via "ethtool -N <device> <filter>".
+
+ The sctp4, ip4, udp4, and tcp4 flow types are supported with the standard
+ fields including src-ip, dst-ip, src-port and dst-port. The driver only
+ supports fully enabling or fully masking the fields, so use of the mask
+ fields for partial matches is not supported.
+
+ Additionally, the driver supports using the action to specify filters for a
+ Virtual Function. You can specify the action as a 64bit value, where the
+ lower 32 bits represents the queue number, while the next 8 bits represent
+ which VF. Note that 0 is the PF, so the VF identifier is offset by 1. For
+ example:
+
+ ... action 0x800000002 ...
+
+ Would indicate to direct traffic for Virtual Function 7 (8 minus 1) on queue
+ 2 of that VF.
+
+ The driver also supports using the user-defined field to specify 2 bytes of
+ arbitrary data to match within the packet payload in addition to the regular
+ fields. The data is specified in the lower 32bits of the user-def field in
+ the following way:
+
+ +----------------------------+---------------------------+
+ | 31 28 24 20 16 | 15 12 8 4 0|
+ +----------------------------+---------------------------+
+ | offset into packet payload | 2 bytes of flexible data |
+ +----------------------------+---------------------------+
+
+ As an example,
+
+ ... user-def 0x4FFFF ....
+
+ means to match the value 0xFFFF 4 bytes into the packet payload. Note that
+ the offset is based on the beginning of the payload, and not the beginning
+ of the packet. Thus
+
+ flow-type tcp4 ... user-def 0x8BEAF ....
+
+ would match TCP/IPv4 packets which have the value 0xBEAF 8bytes into the
+ TCP/IPv4 payload.
+
+ For ICMP, the hardware parses the ICMP header as 4 bytes of header and 4
+ bytes of payload, so if you want to match an ICMP frames payload you may need
+ to add 4 to the offset in order to match the data.
+
+ Furthermore, the offset can only be up to a value of 64, as the hardware
+ will only read up to 64 bytes of data from the payload. It must also be even
+ as the flexible data is 2 bytes long and must be aligned to byte 0 of the
+ packet payload.
+
+ When programming filters, the hardware is limited to using a single input
+ set for each flow type. This means that it is an error to program two
+ different filters with the same type that don't match on the same fields.
+ Thus the second of the following two commands will fail:
+
+ ethtool -N <device> flow-type tcp4 src-ip 192.168.0.7 action 5
+ ethtool -N <device> flow-type tcp4 dst-ip 192.168.15.18 action 1
+
+ This is because the first filter will be accepted and reprogram the input
+ set for TCPv4 filters, but the second filter will be unable to reprogram the
+ input set until all the conflicting TCPv4 filters are first removed.
+
+ Note that the user-defined flexible offset is also considered part of the
+ input set and cannot be programmed separately for multiple filters of the
+ same type. However, the flexible data is not part of the input set and
+ multiple filters may use the same offset but match against different data.
+
Data Center Bridging (DCB)
--------------------------
DCB configuration is not currently supported.
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index fc73eeb..b1c6500 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -73,6 +73,14 @@
0 - disabled
1 - enabled
+fib_multipath_hash_policy - INTEGER
+ Controls which hash policy to use for multipath routes. Only valid
+ for kernels built with CONFIG_IP_ROUTE_MULTIPATH enabled.
+ Default: 0 (Layer 3)
+ Possible values:
+ 0 - Layer 3
+ 1 - Layer 4
+
route/max_size - INTEGER
Maximum number of routes allowed in the kernel. Increase
this when using large numbers of interfaces and/or routes.
@@ -640,11 +648,6 @@
building larger TSO frames.
Default: 3
-tcp_tw_recycle - BOOLEAN
- Enable fast recycling TIME-WAIT sockets. Default value is 0.
- It should not be changed without advice/request of technical
- experts.
-
tcp_tw_reuse - BOOLEAN
Allow to reuse TIME-WAIT sockets for new connections when it is
safe from protocol viewpoint. Default value is 0.
@@ -853,12 +856,21 @@
ip_early_demux - BOOLEAN
Optimize input packet processing down to one demux for
certain kinds of local sockets. Currently we only do this
- for established TCP sockets.
+ for established TCP and connected UDP sockets.
It may add an additional cost for pure routing workloads that
reduces overall throughput, in such case you should disable it.
Default: 1
+tcp_early_demux - BOOLEAN
+ Enable early demux for established TCP sockets.
+ Default: 1
+
+udp_early_demux - BOOLEAN
+ Enable early demux for connected UDP sockets. Disable this if
+ your system could experience more unconnected load.
+ Default: 1
+
icmp_echo_ignore_all - BOOLEAN
If set non-zero, then the kernel will ignore all ICMP ECHO
requests sent to it.
@@ -1006,7 +1018,8 @@
FALSE (router)
forwarding - BOOLEAN
- Enable IP forwarding on this interface.
+ Enable IP forwarding on this interface. This controls whether packets
+ received _on_ this interface can be forwarded.
mc_forwarding - BOOLEAN
Do multicast routing. The kernel needs to be compiled with CONFIG_MROUTE
@@ -1457,11 +1470,20 @@
Functional default: enabled if accept_ra is enabled.
disabled if accept_ra is disabled.
+accept_ra_rt_info_min_plen - INTEGER
+ Minimum prefix length of Route Information in RA.
+
+ Route Information w/ prefix smaller than this variable shall
+ be ignored.
+
+ Functional default: 0 if accept_ra_rtr_pref is enabled.
+ -1 if accept_ra_rtr_pref is disabled.
+
accept_ra_rt_info_max_plen - INTEGER
Maximum prefix length of Route Information in RA.
- Route Information w/ prefix larger than or equal to this
- variable shall be ignored.
+ Route Information w/ prefix larger than this variable shall
+ be ignored.
Functional default: 0 if accept_ra_rtr_pref is enabled.
-1 if accept_ra_rtr_pref is disabled.
diff --git a/Documentation/networking/ipvs-sysctl.txt b/Documentation/networking/ipvs-sysctl.txt
index e6b1c02..0568986 100644
--- a/Documentation/networking/ipvs-sysctl.txt
+++ b/Documentation/networking/ipvs-sysctl.txt
@@ -175,6 +175,14 @@
for VS/NAT when the load balancer receives packets from real
servers but the connection entries don't exist.
+pmtu_disc - BOOLEAN
+ 0 - disabled
+ not 0 - enabled (default)
+
+ By default, reject with FRAG_NEEDED all DF packets that exceed
+ the PMTU, irrespective of the forwarding method. For TUN method
+ the flag can be disabled to fragment such packets.
+
secure_tcp - INTEGER
0 - disabled (default)
@@ -185,15 +193,59 @@
The value definition is the same as that of drop_entry and
drop_packet.
-sync_threshold - INTEGER
- default 3
+sync_threshold - vector of 2 INTEGERs: sync_threshold, sync_period
+ default 3 50
- It sets synchronization threshold, which is the minimum number
- of incoming packets that a connection needs to receive before
- the connection will be synchronized. A connection will be
- synchronized, every time the number of its incoming packets
- modulus 50 equals the threshold. The range of the threshold is
- from 0 to 49.
+ It sets synchronization threshold, which is the minimum number
+ of incoming packets that a connection needs to receive before
+ the connection will be synchronized. A connection will be
+ synchronized, every time the number of its incoming packets
+ modulus sync_period equals the threshold. The range of the
+ threshold is from 0 to sync_period.
+
+ When sync_period and sync_refresh_period are 0, send sync only
+ for state changes or only once when pkts matches sync_threshold
+
+sync_refresh_period - UNSIGNED INTEGER
+ default 0
+
+ In seconds, difference in reported connection timer that triggers
+ new sync message. It can be used to avoid sync messages for the
+ specified period (or half of the connection timeout if it is lower)
+ if connection state is not changed since last sync.
+
+ This is useful for normal connections with high traffic to reduce
+ sync rate. Additionally, retry sync_retries times with period of
+ sync_refresh_period/8.
+
+sync_retries - INTEGER
+ default 0
+
+ Defines sync retries with period of sync_refresh_period/8. Useful
+ to protect against loss of sync messages. The range of the
+ sync_retries is from 0 to 3.
+
+sync_qlen_max - UNSIGNED LONG
+
+ Hard limit for queued sync messages that are not sent yet. It
+ defaults to 1/32 of the memory pages but actually represents
+ number of messages. It will protect us from allocating large
+ parts of memory when the sending rate is lower than the queuing
+ rate.
+
+sync_sock_size - INTEGER
+ default 0
+
+ Configuration of SNDBUF (master) or RCVBUF (slave) socket limit.
+ Default value is 0 (preserve system defaults).
+
+sync_ports - INTEGER
+ default 1
+
+ The number of threads that master and backup servers can use for
+ sync traffic. Every thread will use single UDP port, thread 0 will
+ use the default port 8848 while last thread will use port
+ 8848+sync_ports-1.
snat_reroute - BOOLEAN
0 - disabled
diff --git a/Documentation/networking/mpls-sysctl.txt b/Documentation/networking/mpls-sysctl.txt
index 15d8d16..2f24a19 100644
--- a/Documentation/networking/mpls-sysctl.txt
+++ b/Documentation/networking/mpls-sysctl.txt
@@ -19,6 +19,25 @@
Possible values: 0 - 1048575
Default: 0
+ip_ttl_propagate - BOOL
+ Control whether TTL is propagated from the IPv4/IPv6 header to
+ the MPLS header on imposing labels and propagated from the
+ MPLS header to the IPv4/IPv6 header on popping the last label.
+
+ If disabled, the MPLS transport network will appear as a
+ single hop to transit traffic.
+
+ 0 - disabled / RFC 3443 [Short] Pipe Model
+ 1 - enabled / RFC 3443 Uniform Model (default)
+
+default_ttl - BOOL
+ Default TTL value to use for MPLS packets where it cannot be
+ propagated from an IP header, either because one isn't present
+ or ip_ttl_propagate has been disabled.
+
+ Possible values: 1 - 255
+ Default: 255
+
conf/<interface>/input - BOOL
Control whether packets can be input on this interface.
diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt
index e4991fb..41ef9d8 100644
--- a/Documentation/trace/kprobetrace.txt
+++ b/Documentation/trace/kprobetrace.txt
@@ -12,7 +12,7 @@
functions). Unlike the Tracepoint based event, this can be added and removed
dynamically, on the fly.
-To enable this feature, build your kernel with CONFIG_KPROBE_EVENT=y.
+To enable this feature, build your kernel with CONFIG_KPROBE_EVENTS=y.
Similar to the events tracer, this doesn't need to be activated via
current_tracer. Instead of that, add probe points via
diff --git a/Documentation/trace/uprobetracer.txt b/Documentation/trace/uprobetracer.txt
index fa7b680..bf526a7c 100644
--- a/Documentation/trace/uprobetracer.txt
+++ b/Documentation/trace/uprobetracer.txt
@@ -7,7 +7,7 @@
Overview
--------
Uprobe based trace events are similar to kprobe based trace events.
-To enable this feature, build your kernel with CONFIG_UPROBE_EVENT=y.
+To enable this feature, build your kernel with CONFIG_UPROBE_EVENTS=y.
Similar to the kprobe-event tracer, this doesn't need to be activated via
current_tracer. Instead of that, add probe points via
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 0694509..fd10689 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -951,6 +951,10 @@
slot. When changing an existing slot, it may be moved in the guest
physical memory space, or its flags may be modified. It may not be
resized. Slots may not overlap in guest physical address space.
+Bits 0-15 of "slot" specifies the slot id and this value should be
+less than the maximum number of user memory slots supported per VM.
+The maximum allowed slots can be queried using KVM_CAP_NR_MEMSLOTS,
+if this capability is supported by the architecture.
If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of "slot"
specifies the address space which is being modified. They must be
@@ -3373,6 +3377,69 @@
__u32 pad;
};
+4.104 KVM_X86_GET_MCE_CAP_SUPPORTED
+
+Capability: KVM_CAP_MCE
+Architectures: x86
+Type: system ioctl
+Parameters: u64 mce_cap (out)
+Returns: 0 on success, -1 on error
+
+Returns supported MCE capabilities. The u64 mce_cap parameter
+has the same format as the MSR_IA32_MCG_CAP register. Supported
+capabilities will have the corresponding bits set.
+
+4.105 KVM_X86_SETUP_MCE
+
+Capability: KVM_CAP_MCE
+Architectures: x86
+Type: vcpu ioctl
+Parameters: u64 mcg_cap (in)
+Returns: 0 on success,
+ -EFAULT if u64 mcg_cap cannot be read,
+ -EINVAL if the requested number of banks is invalid,
+ -EINVAL if requested MCE capability is not supported.
+
+Initializes MCE support for use. The u64 mcg_cap parameter
+has the same format as the MSR_IA32_MCG_CAP register and
+specifies which capabilities should be enabled. The maximum
+supported number of error-reporting banks can be retrieved when
+checking for KVM_CAP_MCE. The supported capabilities can be
+retrieved with KVM_X86_GET_MCE_CAP_SUPPORTED.
+
+4.106 KVM_X86_SET_MCE
+
+Capability: KVM_CAP_MCE
+Architectures: x86
+Type: vcpu ioctl
+Parameters: struct kvm_x86_mce (in)
+Returns: 0 on success,
+ -EFAULT if struct kvm_x86_mce cannot be read,
+ -EINVAL if the bank number is invalid,
+ -EINVAL if VAL bit is not set in status field.
+
+Inject a machine check error (MCE) into the guest. The input
+parameter is:
+
+struct kvm_x86_mce {
+ __u64 status;
+ __u64 addr;
+ __u64 misc;
+ __u64 mcg_status;
+ __u8 bank;
+ __u8 pad1[7];
+ __u64 pad2[3];
+};
+
+If the MCE being reported is an uncorrected error, KVM will
+inject it as an MCE exception into the guest. If the guest
+MCG_STATUS register reports that an MCE is in progress, KVM
+causes an KVM_EXIT_SHUTDOWN vmexit.
+
+Otherwise, if the MCE is a corrected error, KVM will just
+store it in the corresponding bank (provided this bank is
+not holding a previously reported uncorrected error).
+
5. The kvm_run structure
------------------------
diff --git a/Documentation/vm/userfaultfd.txt b/Documentation/vm/userfaultfd.txt
index 0e5543a..bb2f945 100644
--- a/Documentation/vm/userfaultfd.txt
+++ b/Documentation/vm/userfaultfd.txt
@@ -172,10 +172,6 @@
manager has to explicitly enable these events by setting appropriate
bits in uffdio_api.features passed to UFFDIO_API ioctl:
-UFFD_FEATURE_EVENT_EXIT - enable notification about exit() of the
-non-cooperative process. When the monitored process exits, the uffd
-manager will get UFFD_EVENT_EXIT.
-
UFFD_FEATURE_EVENT_FORK - enable userfaultfd hooks for fork(). When
this feature is enabled, the userfaultfd context of the parent process
is duplicated into the newly created process. The manager receives
diff --git a/MAINTAINERS b/MAINTAINERS
index c265a5f..5397f54 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -896,12 +896,19 @@
APPLIED MICRO (APM) X-GENE SOC ETHERNET DRIVER
M: Iyappan Subramanian <isubramanian@apm.com>
M: Keyur Chudgar <kchudgar@apm.com>
+M: Quan Nguyen <qnguyen@apm.com>
S: Supported
F: drivers/net/ethernet/apm/xgene/
F: drivers/net/phy/mdio-xgene.c
F: Documentation/devicetree/bindings/net/apm-xgene-enet.txt
F: Documentation/devicetree/bindings/net/apm-xgene-mdio.txt
+APPLIED MICRO (APM) X-GENE SOC ETHERNET (V2) DRIVER
+M: Iyappan Subramanian <isubramanian@apm.com>
+M: Keyur Chudgar <kchudgar@apm.com>
+S: Supported
+F: drivers/net/ethernet/apm/xgene-v2/
+
APPLIED MICRO (APM) X-GENE SOC PMU
M: Tai Nguyen <ttnguyen@apm.com>
S: Supported
@@ -3216,7 +3223,6 @@
CISCO VIC ETHERNET NIC DRIVER
M: Christian Benvenuti <benve@cisco.com>
-M: Sujith Sankar <ssujith@cisco.com>
M: Govindarajulu Varadarajan <_govind@gmx.com>
M: Neel Patel <neepatel@cisco.com>
S: Supported
@@ -4776,6 +4782,12 @@
S: Maintained
F: drivers/edac/mpc85xx_edac.[ch]
+EDAC-PND2
+M: Tony Luck <tony.luck@intel.com>
+L: linux-edac@vger.kernel.org
+S: Maintained
+F: drivers/edac/pnd2_edac.[ch]
+
EDAC-PASEMI
M: Egor Martovetsky <egor@pasemi.com>
L: linux-edac@vger.kernel.org
@@ -4923,6 +4935,7 @@
F: net/bridge/
ETHERNET PHY LIBRARY
+M: Andrew Lunn <andrew@lunn.ch>
M: Florian Fainelli <f.fainelli@gmail.com>
L: netdev@vger.kernel.org
S: Maintained
@@ -7084,9 +7097,9 @@
F: fs/autofs4/
KERNEL BUILD + files below scripts/ (unless maintained elsewhere)
+M: Masahiro Yamada <yamada.masahiro@socionext.com>
M: Michal Marek <mmarek@suse.com>
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild.git for-next
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild.git rc-fixes
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild.git
L: linux-kbuild@vger.kernel.org
S: Maintained
F: Documentation/kbuild/
@@ -7774,13 +7787,6 @@
F: net/mac80211/
F: drivers/net/wireless/mac80211_hwsim.[ch]
-MACVLAN DRIVER
-M: Patrick McHardy <kaber@trash.net>
-L: netdev@vger.kernel.org
-S: Maintained
-F: drivers/net/macvlan.c
-F: include/linux/if_macvlan.h
-
MAILBOX API
M: Jassi Brar <jassisinghbrar@gmail.com>
L: linux-kernel@vger.kernel.org
@@ -7853,6 +7859,8 @@
MARVELL MWIFIEX WIRELESS DRIVER
M: Amitkumar Karwar <akarwar@marvell.com>
M: Nishant Sarmukadam <nishants@marvell.com>
+M: Ganapathi Bhat <gbhat@marvell.com>
+M: Xinming Hu <huxm@marvell.com>
L: linux-wireless@vger.kernel.org
S: Maintained
F: drivers/net/wireless/marvell/mwifiex/
@@ -8307,7 +8315,6 @@
L: linux-usb@vger.kernel.org
S: Maintained
F: drivers/usb/misc/usb251xb.c
-F: include/linux/platform_data/usb251xb.h
F: Documentation/devicetree/bindings/usb/usb251xb.txt
MICROSOFT SURFACE PRO 3 BUTTON DRIVER
@@ -10815,6 +10822,7 @@
F: block/partitions/ibm.c
S390 NETWORK DRIVERS
+M: Julian Wiedmann <jwi@linux.vnet.ibm.com>
M: Ursula Braun <ubraun@linux.vnet.ibm.com>
L: linux-s390@vger.kernel.org
W: http://www.ibm.com/developerworks/linux/linux390/
@@ -10845,6 +10853,7 @@
F: drivers/s390/scsi/zfcp_*
S390 IUCV NETWORK LAYER
+M: Julian Wiedmann <jwi@linux.vnet.ibm.com>
M: Ursula Braun <ubraun@linux.vnet.ibm.com>
L: linux-s390@vger.kernel.org
W: http://www.ibm.com/developerworks/linux/linux390/
@@ -11062,6 +11071,12 @@
F: include/linux/platform_data/dma-dw.h
F: drivers/dma/dw/
+SYNOPSYS DESIGNWARE ENTERPRISE ETHERNET DRIVER
+M: Jie Deng <jiedeng@synopsys.com>
+L: netdev@vger.kernel.org
+S: Supported
+F: drivers/net/ethernet/synopsys/
+
SYNOPSYS DESIGNWARE I2C DRIVER
M: Jarkko Nikula <jarkko.nikula@linux.intel.com>
R: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
@@ -13384,14 +13399,6 @@
S: Maintained
F: drivers/media/platform/vivid/*
-VLAN (802.1Q)
-M: Patrick McHardy <kaber@trash.net>
-L: netdev@vger.kernel.org
-S: Maintained
-F: drivers/net/macvlan.c
-F: include/linux/if_*vlan.h
-F: net/8021q/
-
VLYNQ BUS
M: Florian Fainelli <f.fainelli@gmail.com>
L: openwrt-devel@lists.openwrt.org (subscribers-only)
diff --git a/Makefile b/Makefile
index 4cb6b0a..7acbcb3 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
VERSION = 4
-PATCHLEVEL = 10
+PATCHLEVEL = 11
SUBLEVEL = 0
-EXTRAVERSION =
+EXTRAVERSION = -rc5
NAME = Fearless Coyote
# *DOCUMENTATION*
@@ -372,7 +372,7 @@
CFLAGS_KERNEL =
AFLAGS_KERNEL =
LDFLAGS_vmlinux =
-CFLAGS_GCOV = -fprofile-arcs -ftest-coverage -fno-tree-loop-im -Wno-maybe-uninitialized
+CFLAGS_GCOV := -fprofile-arcs -ftest-coverage -fno-tree-loop-im $(call cc-disable-warning,maybe-uninitialized,)
CFLAGS_KCOV := $(call cc-option,-fsanitize-coverage=trace-pc,)
@@ -653,6 +653,12 @@
# Tell gcc to never replace conditional load with a non-conditional one
KBUILD_CFLAGS += $(call cc-option,--param=allow-store-data-races=0)
+# check for 'asm goto'
+ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y)
+ KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
+ KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
+endif
+
include scripts/Makefile.gcc-plugins
ifdef CONFIG_READABLE_ASM
@@ -798,12 +804,6 @@
# use the deterministic mode of AR if available
KBUILD_ARFLAGS := $(call ar-option,D)
-# check for 'asm goto'
-ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y)
- KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
- KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
-endif
-
include scripts/Makefile.kasan
include scripts/Makefile.extrawarn
include scripts/Makefile.ubsan
diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index afc901b..148d7a3 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -99,4 +99,10 @@
#define SCM_TIMESTAMPING_OPT_STATS 54
+#define SO_MEMINFO 55
+
+#define SO_INCOMING_NAPI_ID 56
+
+#define SO_COOKIE 57
+
#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/arc/boot/dts/skeleton.dtsi b/arch/arc/boot/dts/skeleton.dtsi
index 65808fe..2891cb2 100644
--- a/arch/arc/boot/dts/skeleton.dtsi
+++ b/arch/arc/boot/dts/skeleton.dtsi
@@ -26,6 +26,7 @@
device_type = "cpu";
compatible = "snps,arc770d";
reg = <0>;
+ clocks = <&core_clk>;
};
};
diff --git a/arch/arc/boot/dts/skeleton_hs.dtsi b/arch/arc/boot/dts/skeleton_hs.dtsi
index 2dfe803..5e944d3 100644
--- a/arch/arc/boot/dts/skeleton_hs.dtsi
+++ b/arch/arc/boot/dts/skeleton_hs.dtsi
@@ -21,6 +21,7 @@
device_type = "cpu";
compatible = "snps,archs38";
reg = <0>;
+ clocks = <&core_clk>;
};
};
diff --git a/arch/arc/boot/dts/skeleton_hs_idu.dtsi b/arch/arc/boot/dts/skeleton_hs_idu.dtsi
index 4c11079..54b277d 100644
--- a/arch/arc/boot/dts/skeleton_hs_idu.dtsi
+++ b/arch/arc/boot/dts/skeleton_hs_idu.dtsi
@@ -19,8 +19,27 @@
cpu@0 {
device_type = "cpu";
- compatible = "snps,archs38xN";
+ compatible = "snps,archs38";
reg = <0>;
+ clocks = <&core_clk>;
+ };
+ cpu@1 {
+ device_type = "cpu";
+ compatible = "snps,archs38";
+ reg = <1>;
+ clocks = <&core_clk>;
+ };
+ cpu@2 {
+ device_type = "cpu";
+ compatible = "snps,archs38";
+ reg = <2>;
+ clocks = <&core_clk>;
+ };
+ cpu@3 {
+ device_type = "cpu";
+ compatible = "snps,archs38";
+ reg = <3>;
+ clocks = <&core_clk>;
};
};
diff --git a/arch/arc/boot/dts/vdk_axs10x_mb.dtsi b/arch/arc/boot/dts/vdk_axs10x_mb.dtsi
index f0df59b..459fc65 100644
--- a/arch/arc/boot/dts/vdk_axs10x_mb.dtsi
+++ b/arch/arc/boot/dts/vdk_axs10x_mb.dtsi
@@ -112,13 +112,19 @@
interrupts = <7>;
bus-width = <4>;
};
+ };
- /* Embedded Vision subsystem UIO mappings; only relevant for EV VDK */
- uio_ev: uio@0xD0000000 {
- compatible = "generic-uio";
- reg = <0xD0000000 0x2000 0xD1000000 0x2000 0x90000000 0x10000000 0xC0000000 0x10000000>;
- reg-names = "ev_gsa", "ev_ctrl", "ev_shared_mem", "ev_code_mem";
- interrupts = <23>;
- };
+ /*
+ * Embedded Vision subsystem UIO mappings; only relevant for EV VDK
+ *
+ * This node is intentionally put outside of MB above becase
+ * it maps areas outside of MB's 0xEz-0xFz.
+ */
+ uio_ev: uio@0xD0000000 {
+ compatible = "generic-uio";
+ reg = <0xD0000000 0x2000 0xD1000000 0x2000 0x90000000 0x10000000 0xC0000000 0x10000000>;
+ reg-names = "ev_gsa", "ev_ctrl", "ev_shared_mem", "ev_code_mem";
+ interrupt-parent = <&mb_intc>;
+ interrupts = <23>;
};
};
diff --git a/arch/arc/include/asm/hugepage.h b/arch/arc/include/asm/hugepage.h
index 317ff77..b18fcb6 100644
--- a/arch/arc/include/asm/hugepage.h
+++ b/arch/arc/include/asm/hugepage.h
@@ -11,6 +11,7 @@
#define _ASM_ARC_HUGEPAGE_H
#include <linux/types.h>
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
static inline pte_t pmd_pte(pmd_t pmd)
diff --git a/arch/arc/include/asm/kprobes.h b/arch/arc/include/asm/kprobes.h
index 00bdbe1..2e52d18 100644
--- a/arch/arc/include/asm/kprobes.h
+++ b/arch/arc/include/asm/kprobes.h
@@ -54,9 +54,7 @@ int kprobe_fault_handler(struct pt_regs *regs, unsigned long cause);
void kretprobe_trampoline(void);
void trap_is_kprobe(unsigned long address, struct pt_regs *regs);
#else
-static void trap_is_kprobe(unsigned long address, struct pt_regs *regs)
-{
-}
+#define trap_is_kprobe(address, regs)
#endif /* CONFIG_KPROBES */
#endif /* _ARC_KPROBES_H */
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index e94ca72..ee22d40 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -37,6 +37,7 @@
#include <asm/page.h>
#include <asm/mmu.h>
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
#include <linux/const.h>
diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S
index 2585632..cc558a2 100644
--- a/arch/arc/kernel/entry-arcv2.S
+++ b/arch/arc/kernel/entry-arcv2.S
@@ -100,15 +100,21 @@
;################### Non TLB Exception Handling #############################
ENTRY(EV_SWI)
- flag 1
+ ; TODO: implement this
+ EXCEPTION_PROLOGUE
+ b ret_from_exception
END(EV_SWI)
ENTRY(EV_DivZero)
- flag 1
+ ; TODO: implement this
+ EXCEPTION_PROLOGUE
+ b ret_from_exception
END(EV_DivZero)
ENTRY(EV_DCError)
- flag 1
+ ; TODO: implement this
+ EXCEPTION_PROLOGUE
+ b ret_from_exception
END(EV_DCError)
; ---------------------------------------------
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 3093fa8..fa62404 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -10,6 +10,7 @@
#include <linux/fs.h>
#include <linux/delay.h>
#include <linux/root_dev.h>
+#include <linux/clk.h>
#include <linux/clk-provider.h>
#include <linux/clocksource.h>
#include <linux/console.h>
@@ -488,8 +489,9 @@ static int show_cpuinfo(struct seq_file *m, void *v)
{
char *str;
int cpu_id = ptr_to_cpu(v);
- struct device_node *core_clk = of_find_node_by_name(NULL, "core_clk");
- u32 freq = 0;
+ struct device *cpu_dev = get_cpu_device(cpu_id);
+ struct clk *cpu_clk;
+ unsigned long freq = 0;
if (!cpu_online(cpu_id)) {
seq_printf(m, "processor [%d]\t: Offline\n", cpu_id);
@@ -502,9 +504,15 @@ static int show_cpuinfo(struct seq_file *m, void *v)
seq_printf(m, arc_cpu_mumbojumbo(cpu_id, str, PAGE_SIZE));
- of_property_read_u32(core_clk, "clock-frequency", &freq);
+ cpu_clk = clk_get(cpu_dev, NULL);
+ if (IS_ERR(cpu_clk)) {
+ seq_printf(m, "CPU speed \t: Cannot get clock for processor [%d]\n",
+ cpu_id);
+ } else {
+ freq = clk_get_rate(cpu_clk);
+ }
if (freq)
- seq_printf(m, "CPU speed\t: %u.%02u Mhz\n",
+ seq_printf(m, "CPU speed\t: %lu.%02lu Mhz\n",
freq / 1000000, (freq / 10000) % 100);
seq_printf(m, "Bogo MIPS\t: %lu.%02lu\n",
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index d408fa2..9285629 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -633,6 +633,9 @@ noinline static void slc_entire_op(const int op)
write_aux_reg(ARC_REG_SLC_INVALIDATE, 1);
+ /* Make sure "busy" bit reports correct stataus, see STAR 9001165532 */
+ read_aux_reg(r);
+
/* Important to wait for flush to complete */
while (read_aux_reg(r) & SLC_CTRL_BUSY);
}
diff --git a/arch/arm/boot/dts/am335x-pcm-953.dtsi b/arch/arm/boot/dts/am335x-pcm-953.dtsi
index 02981ea..1ec8e0d 100644
--- a/arch/arm/boot/dts/am335x-pcm-953.dtsi
+++ b/arch/arm/boot/dts/am335x-pcm-953.dtsi
@@ -63,14 +63,14 @@
label = "home";
linux,code = <KEY_HOME>;
gpios = <&gpio3 7 GPIO_ACTIVE_HIGH>;
- gpio-key,wakeup;
+ wakeup-source;
};
button@1 {
label = "menu";
linux,code = <KEY_MENU>;
gpios = <&gpio3 8 GPIO_ACTIVE_HIGH>;
- gpio-key,wakeup;
+ wakeup-source;
};
};
diff --git a/arch/arm/boot/dts/am57xx-idk-common.dtsi b/arch/arm/boot/dts/am57xx-idk-common.dtsi
index 0d341c5..e5ac1d8 100644
--- a/arch/arm/boot/dts/am57xx-idk-common.dtsi
+++ b/arch/arm/boot/dts/am57xx-idk-common.dtsi
@@ -315,6 +315,13 @@
/* ID & VBUS GPIOs provided in board dts */
};
};
+
+ tpic2810: tpic2810@60 {
+ compatible = "ti,tpic2810";
+ reg = <0x60>;
+ gpio-controller;
+ #gpio-cells = <2>;
+ };
};
&mcspi3 {
@@ -330,13 +337,6 @@
spi-max-frequency = <1000000>;
spi-cpol;
};
-
- tpic2810: tpic2810@60 {
- compatible = "ti,tpic2810";
- reg = <0x60>;
- gpio-controller;
- #gpio-cells = <2>;
- };
};
&uart3 {
diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi
index 4fbb089..00de62d 100644
--- a/arch/arm/boot/dts/bcm5301x.dtsi
+++ b/arch/arm/boot/dts/bcm5301x.dtsi
@@ -66,14 +66,14 @@
timer@20200 {
compatible = "arm,cortex-a9-global-timer";
reg = <0x20200 0x100>;
- interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>;
clocks = <&periph_clk>;
};
local-timer@20600 {
compatible = "arm,cortex-a9-twd-timer";
reg = <0x20600 0x100>;
- interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_PPI 13 IRQ_TYPE_EDGE_RISING>;
clocks = <&periph_clk>;
};
diff --git a/arch/arm/boot/dts/bcm953012k.dts b/arch/arm/boot/dts/bcm953012k.dts
index bfd9230..ae31a58 100644
--- a/arch/arm/boot/dts/bcm953012k.dts
+++ b/arch/arm/boot/dts/bcm953012k.dts
@@ -48,15 +48,14 @@
};
memory {
- reg = <0x00000000 0x10000000>;
+ reg = <0x80000000 0x10000000>;
};
};
&uart0 {
- clock-frequency = <62499840>;
+ status = "okay";
};
&uart1 {
- clock-frequency = <62499840>;
status = "okay";
};
diff --git a/arch/arm/boot/dts/bcm958522er.dts b/arch/arm/boot/dts/bcm958522er.dts
index 3f04a40..df05e7f 100644
--- a/arch/arm/boot/dts/bcm958522er.dts
+++ b/arch/arm/boot/dts/bcm958522er.dts
@@ -55,6 +55,7 @@
gpio-restart {
compatible = "gpio-restart";
gpios = <&gpioa 15 GPIO_ACTIVE_LOW>;
+ open-source;
priority = <200>;
};
};
diff --git a/arch/arm/boot/dts/bcm958525er.dts b/arch/arm/boot/dts/bcm958525er.dts
index 9fd5422..4a3ab19 100644
--- a/arch/arm/boot/dts/bcm958525er.dts
+++ b/arch/arm/boot/dts/bcm958525er.dts
@@ -55,6 +55,7 @@
gpio-restart {
compatible = "gpio-restart";
gpios = <&gpioa 15 GPIO_ACTIVE_LOW>;
+ open-source;
priority = <200>;
};
};
diff --git a/arch/arm/boot/dts/bcm958525xmc.dts b/arch/arm/boot/dts/bcm958525xmc.dts
index 41e7fd3..81f7843 100644
--- a/arch/arm/boot/dts/bcm958525xmc.dts
+++ b/arch/arm/boot/dts/bcm958525xmc.dts
@@ -55,6 +55,7 @@
gpio-restart {
compatible = "gpio-restart";
gpios = <&gpioa 31 GPIO_ACTIVE_LOW>;
+ open-source;
priority = <200>;
};
};
diff --git a/arch/arm/boot/dts/bcm958622hr.dts b/arch/arm/boot/dts/bcm958622hr.dts
index 477c486..c88b8fe 100644
--- a/arch/arm/boot/dts/bcm958622hr.dts
+++ b/arch/arm/boot/dts/bcm958622hr.dts
@@ -55,6 +55,7 @@
gpio-restart {
compatible = "gpio-restart";
gpios = <&gpioa 15 GPIO_ACTIVE_LOW>;
+ open-source;
priority = <200>;
};
};
diff --git a/arch/arm/boot/dts/bcm958623hr.dts b/arch/arm/boot/dts/bcm958623hr.dts
index c0a499d..d503fa0 100644
--- a/arch/arm/boot/dts/bcm958623hr.dts
+++ b/arch/arm/boot/dts/bcm958623hr.dts
@@ -55,6 +55,7 @@
gpio-restart {
compatible = "gpio-restart";
gpios = <&gpioa 15 GPIO_ACTIVE_LOW>;
+ open-source;
priority = <200>;
};
};
diff --git a/arch/arm/boot/dts/bcm958625hr.dts b/arch/arm/boot/dts/bcm958625hr.dts
index f7eb585..cc0363b 100644
--- a/arch/arm/boot/dts/bcm958625hr.dts
+++ b/arch/arm/boot/dts/bcm958625hr.dts
@@ -55,6 +55,7 @@
gpio-restart {
compatible = "gpio-restart";
gpios = <&gpioa 15 GPIO_ACTIVE_LOW>;
+ open-source;
priority = <200>;
};
};
diff --git a/arch/arm/boot/dts/bcm988312hr.dts b/arch/arm/boot/dts/bcm988312hr.dts
index 16666324..74e15a3 100644
--- a/arch/arm/boot/dts/bcm988312hr.dts
+++ b/arch/arm/boot/dts/bcm988312hr.dts
@@ -55,6 +55,7 @@
gpio-restart {
compatible = "gpio-restart";
gpios = <&gpioa 15 GPIO_ACTIVE_LOW>;
+ open-source;
priority = <200>;
};
};
diff --git a/arch/arm/boot/dts/imx6sx-udoo-neo.dtsi b/arch/arm/boot/dts/imx6sx-udoo-neo.dtsi
index 49f466f..dcfc975 100644
--- a/arch/arm/boot/dts/imx6sx-udoo-neo.dtsi
+++ b/arch/arm/boot/dts/imx6sx-udoo-neo.dtsi
@@ -121,11 +121,6 @@
};
};
-&cpu0 {
- arm-supply = <&sw1a_reg>;
- soc-supply = <&sw1c_reg>;
-};
-
&fec1 {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_enet1>;
diff --git a/arch/arm/boot/dts/sama5d2.dtsi b/arch/arm/boot/dts/sama5d2.dtsi
index 22332be..528b4e9 100644
--- a/arch/arm/boot/dts/sama5d2.dtsi
+++ b/arch/arm/boot/dts/sama5d2.dtsi
@@ -266,7 +266,7 @@
};
usb1: ohci@00400000 {
- compatible = "atmel,sama5d2-ohci", "usb-ohci";
+ compatible = "atmel,at91rm9200-ohci", "usb-ohci";
reg = <0x00400000 0x100000>;
interrupts = <41 IRQ_TYPE_LEVEL_HIGH 2>;
clocks = <&uhphs_clk>, <&uhphs_clk>, <&uhpck>;
diff --git a/arch/arm/boot/dts/ste-dbx5x0.dtsi b/arch/arm/boot/dts/ste-dbx5x0.dtsi
index 82d8c47..162e1eb 100644
--- a/arch/arm/boot/dts/ste-dbx5x0.dtsi
+++ b/arch/arm/boot/dts/ste-dbx5x0.dtsi
@@ -14,6 +14,7 @@
#include <dt-bindings/mfd/dbx500-prcmu.h>
#include <dt-bindings/arm/ux500_pm_domains.h>
#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/clock/ste-ab8500.h>
#include "skeleton.dtsi"
/ {
@@ -603,6 +604,11 @@
interrupt-controller;
#interrupt-cells = <2>;
+ ab8500_clock: clock-controller {
+ compatible = "stericsson,ab8500-clk";
+ #clock-cells = <1>;
+ };
+
ab8500_gpio: ab8500-gpio {
compatible = "stericsson,ab8500-gpio";
gpio-controller;
@@ -686,6 +692,8 @@
ab8500-pwm {
compatible = "stericsson,ab8500-pwm";
+ clocks = <&ab8500_clock AB8500_SYSCLK_INT>;
+ clock-names = "intclk";
};
ab8500-debugfs {
@@ -700,6 +708,9 @@
V-AMIC2-supply = <&ab8500_ldo_anamic2_reg>;
V-DMIC-supply = <&ab8500_ldo_dmic_reg>;
+ clocks = <&ab8500_clock AB8500_SYSCLK_AUDIO>;
+ clock-names = "audioclk";
+
stericsson,earpeice-cmv = <950>; /* Units in mV. */
};
@@ -1095,6 +1106,14 @@
status = "disabled";
};
+ sound {
+ compatible = "stericsson,snd-soc-mop500";
+ stericsson,cpu-dai = <&msp1 &msp3>;
+ stericsson,audio-codec = <&codec>;
+ clocks = <&prcmu_clk PRCMU_SYSCLK>, <&ab8500_clock AB8500_SYSCLK_ULP>, <&ab8500_clock AB8500_SYSCLK_INT>;
+ clock-names = "sysclk", "ulpclk", "intclk";
+ };
+
msp0: msp@80123000 {
compatible = "stericsson,ux500-msp-i2s";
reg = <0x80123000 0x1000>;
diff --git a/arch/arm/boot/dts/ste-href.dtsi b/arch/arm/boot/dts/ste-href.dtsi
index f37f9e1..9e359e4 100644
--- a/arch/arm/boot/dts/ste-href.dtsi
+++ b/arch/arm/boot/dts/ste-href.dtsi
@@ -186,15 +186,6 @@
status = "okay";
};
- sound {
- compatible = "stericsson,snd-soc-mop500";
-
- stericsson,cpu-dai = <&msp1 &msp3>;
- stericsson,audio-codec = <&codec>;
- clocks = <&prcmu_clk PRCMU_SYSCLK>;
- clock-names = "sysclk";
- };
-
msp0: msp@80123000 {
pinctrl-names = "default";
pinctrl-0 = <&msp0_default_mode>;
diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts
index dd5514d..ade1d0d 100644
--- a/arch/arm/boot/dts/ste-snowball.dts
+++ b/arch/arm/boot/dts/ste-snowball.dts
@@ -159,15 +159,6 @@
"", "", "", "", "", "", "", "";
};
- sound {
- compatible = "stericsson,snd-soc-mop500";
-
- stericsson,cpu-dai = <&msp1 &msp3>;
- stericsson,audio-codec = <&codec>;
- clocks = <&prcmu_clk PRCMU_SYSCLK>;
- clock-names = "sysclk";
- };
-
msp0: msp@80123000 {
pinctrl-names = "default";
pinctrl-0 = <&msp0_default_mode>;
diff --git a/arch/arm/boot/dts/sun7i-a20-lamobo-r1.dts b/arch/arm/boot/dts/sun7i-a20-lamobo-r1.dts
index 72ec0d5..bbf1c8c 100644
--- a/arch/arm/boot/dts/sun7i-a20-lamobo-r1.dts
+++ b/arch/arm/boot/dts/sun7i-a20-lamobo-r1.dts
@@ -167,7 +167,7 @@
reg = <8>;
label = "cpu";
ethernet = <&gmac>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-txid";
fixed-link {
speed = <1000>;
full-duplex;
diff --git a/arch/arm/boot/dts/sun8i-a23-a33.dtsi b/arch/arm/boot/dts/sun8i-a23-a33.dtsi
index a952cc0..8a3ed21 100644
--- a/arch/arm/boot/dts/sun8i-a23-a33.dtsi
+++ b/arch/arm/boot/dts/sun8i-a23-a33.dtsi
@@ -495,7 +495,7 @@
resets = <&ccu RST_BUS_GPU>;
assigned-clocks = <&ccu CLK_GPU>;
- assigned-clock-rates = <408000000>;
+ assigned-clock-rates = <384000000>;
};
gic: interrupt-controller@01c81000 {
diff --git a/arch/arm/boot/dts/sun8i-a33.dtsi b/arch/arm/boot/dts/sun8i-a33.dtsi
index 18c174f..0467fb3 100644
--- a/arch/arm/boot/dts/sun8i-a33.dtsi
+++ b/arch/arm/boot/dts/sun8i-a33.dtsi
@@ -113,8 +113,8 @@
simple-audio-card,mclk-fs = <512>;
simple-audio-card,aux-devs = <&codec_analog>;
simple-audio-card,routing =
- "Left DAC", "Digital Left DAC",
- "Right DAC", "Digital Right DAC";
+ "Left DAC", "AIF1 Slot 0 Left",
+ "Right DAC", "AIF1 Slot 0 Right";
status = "disabled";
simple-audio-card,cpu {
diff --git a/arch/arm/boot/dts/sun8i-reference-design-tablet.dtsi b/arch/arm/boot/dts/sun8i-reference-design-tablet.dtsi
index 7097c18..d6bd158 100644
--- a/arch/arm/boot/dts/sun8i-reference-design-tablet.dtsi
+++ b/arch/arm/boot/dts/sun8i-reference-design-tablet.dtsi
@@ -50,8 +50,6 @@
backlight: backlight {
compatible = "pwm-backlight";
- pinctrl-names = "default";
- pinctrl-0 = <&bl_en_pin>;
pwms = <&pwm 0 50000 PWM_POLARITY_INVERTED>;
brightness-levels = <0 10 20 30 40 50 60 70 80 90 100>;
default-brightness-level = <8>;
@@ -93,11 +91,6 @@
};
&pio {
- bl_en_pin: bl_en_pin@0 {
- pins = "PH6";
- function = "gpio_in";
- };
-
mmc0_cd_pin: mmc0_cd_pin@0 {
pins = "PB4";
function = "gpio_in";
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index f2462a6..decd388 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -188,6 +188,7 @@
CONFIG_WL18XX=m
CONFIG_WLCORE_SPI=m
CONFIG_WLCORE_SDIO=m
+CONFIG_INPUT_MOUSEDEV=m
CONFIG_INPUT_JOYDEV=m
CONFIG_INPUT_EVDEV=m
CONFIG_KEYBOARD_ATKBD=m
diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index e22089f..a3f0b3d 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -209,6 +209,7 @@
#define HSR_EC_IABT_HYP (0x21)
#define HSR_EC_DABT (0x24)
#define HSR_EC_DABT_HYP (0x25)
+#define HSR_EC_MAX (0x3f)
#define HSR_WFI_IS_WFE (_AC(1, UL) << 0)
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index cc495d79..31ee468 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -30,7 +30,6 @@
#define __KVM_HAVE_ARCH_INTC_INITIALIZED
#define KVM_USER_MEM_SLOTS 32
-#define KVM_PRIVATE_MEM_SLOTS 4
#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
#define KVM_HAVE_ONE_REG
#define KVM_HALT_POLL_NS_DEFAULT 500000
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index a8d656d..1c46238 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -20,6 +20,7 @@
#else
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopud.h>
#include <asm/memory.h>
#include <asm/pgtable-hwdef.h>
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index c9a2103..96dba7c 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -221,6 +221,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_MAX_VCPUS:
r = KVM_MAX_VCPUS;
break;
+ case KVM_CAP_NR_MEMSLOTS:
+ r = KVM_USER_MEM_SLOTS;
+ break;
case KVM_CAP_MSI_DEVID:
if (!kvm)
r = -EINVAL;
diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index 4e40d19..96af65a 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -79,7 +79,19 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
return 1;
}
+static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ u32 hsr = kvm_vcpu_get_hsr(vcpu);
+
+ kvm_pr_unimpl("Unknown exception class: hsr: %#08x\n",
+ hsr);
+
+ kvm_inject_undefined(vcpu);
+ return 1;
+}
+
static exit_handle_fn arm_exit_handlers[] = {
+ [0 ... HSR_EC_MAX] = kvm_handle_unknown_ec,
[HSR_EC_WFI] = kvm_handle_wfx,
[HSR_EC_CP15_32] = kvm_handle_cp15_32,
[HSR_EC_CP15_64] = kvm_handle_cp15_64,
@@ -98,13 +110,6 @@ static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
{
u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu);
- if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) ||
- !arm_exit_handlers[hsr_ec]) {
- kvm_err("Unknown exception class: hsr: %#08x\n",
- (unsigned int)kvm_vcpu_get_hsr(vcpu));
- BUG();
- }
-
return arm_exit_handlers[hsr_ec];
}
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index 3d89b79..a277981 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -289,6 +289,22 @@ static void at91_ddr_standby(void)
at91_ramc_write(1, AT91_DDRSDRC_LPR, saved_lpr1);
}
+static void sama5d3_ddr_standby(void)
+{
+ u32 lpr0;
+ u32 saved_lpr0;
+
+ saved_lpr0 = at91_ramc_read(0, AT91_DDRSDRC_LPR);
+ lpr0 = saved_lpr0 & ~AT91_DDRSDRC_LPCB;
+ lpr0 |= AT91_DDRSDRC_LPCB_POWER_DOWN;
+
+ at91_ramc_write(0, AT91_DDRSDRC_LPR, lpr0);
+
+ cpu_do_idle();
+
+ at91_ramc_write(0, AT91_DDRSDRC_LPR, saved_lpr0);
+}
+
/* We manage both DDRAM/SDRAM controllers, we need more than one value to
* remember.
*/
@@ -323,7 +339,7 @@ static const struct of_device_id const ramc_ids[] __initconst = {
{ .compatible = "atmel,at91rm9200-sdramc", .data = at91rm9200_standby },
{ .compatible = "atmel,at91sam9260-sdramc", .data = at91sam9_sdram_standby },
{ .compatible = "atmel,at91sam9g45-ddramc", .data = at91_ddr_standby },
- { .compatible = "atmel,sama5d3-ddramc", .data = at91_ddr_standby },
+ { .compatible = "atmel,sama5d3-ddramc", .data = sama5d3_ddr_standby },
{ /*sentinel*/ }
};
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index 093458b..c89757a 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -241,6 +241,3 @@
onenand-$(CONFIG_MTD_ONENAND_OMAP2) := gpmc-onenand.o
obj-y += $(onenand-m) $(onenand-y)
-
-nand-$(CONFIG_MTD_NAND_OMAP2) := gpmc-nand.o
-obj-y += $(nand-m) $(nand-y)
diff --git a/arch/arm/mach-omap2/gpmc-nand.c b/arch/arm/mach-omap2/gpmc-nand.c
deleted file mode 100644
index f6ac027..0000000
--- a/arch/arm/mach-omap2/gpmc-nand.c
+++ /dev/null
@@ -1,154 +0,0 @@
-/*
- * gpmc-nand.c
- *
- * Copyright (C) 2009 Texas Instruments
- * Vimal Singh <vimalsingh@ti.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
-#include <linux/io.h>
-#include <linux/omap-gpmc.h>
-#include <linux/mtd/nand.h>
-#include <linux/platform_data/mtd-nand-omap2.h>
-
-#include <asm/mach/flash.h>
-
-#include "soc.h"
-
-/* minimum size for IO mapping */
-#define NAND_IO_SIZE 4
-
-static bool gpmc_hwecc_bch_capable(enum omap_ecc ecc_opt)
-{
- /* platforms which support all ECC schemes */
- if (soc_is_am33xx() || soc_is_am43xx() || cpu_is_omap44xx() ||
- soc_is_omap54xx() || soc_is_dra7xx())
- return 1;
-
- if (ecc_opt == OMAP_ECC_BCH4_CODE_HW_DETECTION_SW ||
- ecc_opt == OMAP_ECC_BCH8_CODE_HW_DETECTION_SW) {
- if (cpu_is_omap24xx())
- return 0;
- else if (cpu_is_omap3630() && (GET_OMAP_REVISION() == 0))
- return 0;
- else
- return 1;
- }
-
- /* OMAP3xxx do not have ELM engine, so cannot support ECC schemes
- * which require H/W based ECC error detection */
- if ((cpu_is_omap34xx() || cpu_is_omap3630()) &&
- ((ecc_opt == OMAP_ECC_BCH4_CODE_HW) ||
- (ecc_opt == OMAP_ECC_BCH8_CODE_HW)))
- return 0;
-
- /* legacy platforms support only HAM1 (1-bit Hamming) ECC scheme */
- if (ecc_opt == OMAP_ECC_HAM1_CODE_HW ||
- ecc_opt == OMAP_ECC_HAM1_CODE_SW)
- return 1;
- else
- return 0;
-}
-
-/* This function will go away once the device-tree convertion is complete */
-static void gpmc_set_legacy(struct omap_nand_platform_data *gpmc_nand_data,
- struct gpmc_settings *s)
-{
- /* Enable RD PIN Monitoring Reg */
- if (gpmc_nand_data->dev_ready) {
- s->wait_on_read = true;
- s->wait_on_write = true;
- }
-
- if (gpmc_nand_data->devsize == NAND_BUSWIDTH_16)
- s->device_width = GPMC_DEVWIDTH_16BIT;
- else
- s->device_width = GPMC_DEVWIDTH_8BIT;
-}
-
-int gpmc_nand_init(struct omap_nand_platform_data *gpmc_nand_data,
- struct gpmc_timings *gpmc_t)
-{
- int err = 0;
- struct gpmc_settings s;
- struct platform_device *pdev;
- struct resource gpmc_nand_res[] = {
- { .flags = IORESOURCE_MEM, },
- { .flags = IORESOURCE_IRQ, },
- { .flags = IORESOURCE_IRQ, },
- };
-
- BUG_ON(gpmc_nand_data->cs >= GPMC_CS_NUM);
-
- err = gpmc_cs_request(gpmc_nand_data->cs, NAND_IO_SIZE,
- (unsigned long *)&gpmc_nand_res[0].start);
- if (err < 0) {
- pr_err("omap2-gpmc: Cannot request GPMC CS %d, error %d\n",
- gpmc_nand_data->cs, err);
- return err;
- }
- gpmc_nand_res[0].end = gpmc_nand_res[0].start + NAND_IO_SIZE - 1;
- gpmc_nand_res[1].start = gpmc_get_client_irq(GPMC_IRQ_FIFOEVENTENABLE);
- gpmc_nand_res[2].start = gpmc_get_client_irq(GPMC_IRQ_COUNT_EVENT);
-
- memset(&s, 0, sizeof(struct gpmc_settings));
- gpmc_set_legacy(gpmc_nand_data, &s);
-
- s.device_nand = true;
-
- if (gpmc_t) {
- err = gpmc_cs_set_timings(gpmc_nand_data->cs, gpmc_t, &s);
- if (err < 0) {
- pr_err("omap2-gpmc: Unable to set gpmc timings: %d\n",
- err);
- return err;
- }
- }
-
- err = gpmc_cs_program_settings(gpmc_nand_data->cs, &s);
- if (err < 0)
- goto out_free_cs;
-
- err = gpmc_configure(GPMC_CONFIG_WP, 0);
- if (err < 0)
- goto out_free_cs;
-
- if (!gpmc_hwecc_bch_capable(gpmc_nand_data->ecc_opt)) {
- pr_err("omap2-nand: Unsupported NAND ECC scheme selected\n");
- err = -EINVAL;
- goto out_free_cs;
- }
-
-
- pdev = platform_device_alloc("omap2-nand", gpmc_nand_data->cs);
- if (pdev) {
- err = platform_device_add_resources(pdev, gpmc_nand_res,
- ARRAY_SIZE(gpmc_nand_res));
- if (!err)
- pdev->dev.platform_data = gpmc_nand_data;
- } else {
- err = -ENOMEM;
- }
- if (err)
- goto out_free_pdev;
-
- err = platform_device_add(pdev);
- if (err) {
- dev_err(&pdev->dev, "Unable to register NAND device\n");
- goto out_free_pdev;
- }
-
- return 0;
-
-out_free_pdev:
- platform_device_put(pdev);
-out_free_cs:
- gpmc_cs_free(gpmc_nand_data->cs);
-
- return err;
-}
diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c
index 8633c70..2944af8 100644
--- a/arch/arm/mach-omap2/gpmc-onenand.c
+++ b/arch/arm/mach-omap2/gpmc-onenand.c
@@ -367,7 +367,7 @@ static int gpmc_onenand_setup(void __iomem *onenand_base, int *freq_ptr)
return ret;
}
-void gpmc_onenand_init(struct omap_onenand_platform_data *_onenand_data)
+int gpmc_onenand_init(struct omap_onenand_platform_data *_onenand_data)
{
int err;
struct device *dev = &gpmc_onenand_device.dev;
@@ -393,15 +393,17 @@ void gpmc_onenand_init(struct omap_onenand_platform_data *_onenand_data)
if (err < 0) {
dev_err(dev, "Cannot request GPMC CS %d, error %d\n",
gpmc_onenand_data->cs, err);
- return;
+ return err;
}
gpmc_onenand_resource.end = gpmc_onenand_resource.start +
ONENAND_IO_SIZE - 1;
- if (platform_device_register(&gpmc_onenand_device) < 0) {
+ err = platform_device_register(&gpmc_onenand_device);
+ if (err) {
dev_err(dev, "Unable to register OneNAND device\n");
gpmc_cs_free(gpmc_onenand_data->cs);
- return;
}
+
+ return err;
}
diff --git a/arch/arm/mach-omap2/omap-headsmp.S b/arch/arm/mach-omap2/omap-headsmp.S
index fe36ce2..4c6f14c 100644
--- a/arch/arm/mach-omap2/omap-headsmp.S
+++ b/arch/arm/mach-omap2/omap-headsmp.S
@@ -17,6 +17,7 @@
#include <linux/linkage.h>
#include <linux/init.h>
+#include <asm/assembler.h>
#include "omap44xx.h"
@@ -66,7 +67,7 @@
cmp r0, r4
bne wait_2
ldr r12, =API_HYP_ENTRY
- adr r0, hyp_boot
+ badr r0, hyp_boot
smc #0
hyp_boot:
b omap_secondary_startup
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index 56f917e..1435fee 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -2112,11 +2112,20 @@ static struct omap_hwmod_ocp_if omap3_l4_core__i2c3 = {
};
/* L4 CORE -> SR1 interface */
+static struct omap_hwmod_addr_space omap3_sr1_addr_space[] = {
+ {
+ .pa_start = OMAP34XX_SR1_BASE,
+ .pa_end = OMAP34XX_SR1_BASE + SZ_1K - 1,
+ .flags = ADDR_TYPE_RT,
+ },
+ { },
+};
static struct omap_hwmod_ocp_if omap34xx_l4_core__sr1 = {
.master = &omap3xxx_l4_core_hwmod,
.slave = &omap34xx_sr1_hwmod,
.clk = "sr_l4_ick",
+ .addr = omap3_sr1_addr_space,
.user = OCP_USER_MPU,
};
@@ -2124,15 +2133,25 @@ static struct omap_hwmod_ocp_if omap36xx_l4_core__sr1 = {
.master = &omap3xxx_l4_core_hwmod,
.slave = &omap36xx_sr1_hwmod,
.clk = "sr_l4_ick",
+ .addr = omap3_sr1_addr_space,
.user = OCP_USER_MPU,
};
/* L4 CORE -> SR1 interface */
+static struct omap_hwmod_addr_space omap3_sr2_addr_space[] = {
+ {
+ .pa_start = OMAP34XX_SR2_BASE,
+ .pa_end = OMAP34XX_SR2_BASE + SZ_1K - 1,
+ .flags = ADDR_TYPE_RT,
+ },
+ { },
+};
static struct omap_hwmod_ocp_if omap34xx_l4_core__sr2 = {
.master = &omap3xxx_l4_core_hwmod,
.slave = &omap34xx_sr2_hwmod,
.clk = "sr_l4_ick",
+ .addr = omap3_sr2_addr_space,
.user = OCP_USER_MPU,
};
@@ -2140,6 +2159,7 @@ static struct omap_hwmod_ocp_if omap36xx_l4_core__sr2 = {
.master = &omap3xxx_l4_core_hwmod,
.slave = &omap36xx_sr2_hwmod,
.clk = "sr_l4_ick",
+ .addr = omap3_sr2_addr_space,
.user = OCP_USER_MPU,
};
@@ -3111,16 +3131,20 @@ static struct omap_hwmod_ocp_if *omap3xxx_dss_hwmod_ocp_ifs[] __initdata = {
* Return: 0 if device named @dev_name is not likely to be accessible,
* or 1 if it is likely to be accessible.
*/
-static int __init omap3xxx_hwmod_is_hs_ip_block_usable(struct device_node *bus,
- const char *dev_name)
+static bool __init omap3xxx_hwmod_is_hs_ip_block_usable(struct device_node *bus,
+ const char *dev_name)
{
+ struct device_node *node;
+ bool available;
+
if (!bus)
- return (omap_type() == OMAP2_DEVICE_TYPE_GP) ? 1 : 0;
+ return omap_type() == OMAP2_DEVICE_TYPE_GP;
- if (of_device_is_available(of_find_node_by_name(bus, dev_name)))
- return 1;
+ node = of_get_child_by_name(bus, dev_name);
+ available = of_device_is_available(node);
+ of_node_put(node);
- return 0;
+ return available;
}
int __init omap3xxx_hwmod_init(void)
@@ -3189,15 +3213,20 @@ int __init omap3xxx_hwmod_init(void)
if (h_sham && omap3xxx_hwmod_is_hs_ip_block_usable(bus, "sham")) {
r = omap_hwmod_register_links(h_sham);
- if (r < 0)
+ if (r < 0) {
+ of_node_put(bus);
return r;
+ }
}
if (h_aes && omap3xxx_hwmod_is_hs_ip_block_usable(bus, "aes")) {
r = omap_hwmod_register_links(h_aes);
- if (r < 0)
+ if (r < 0) {
+ of_node_put(bus);
return r;
+ }
}
+ of_node_put(bus);
/*
* Register hwmod links specific to certain ES levels of a
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 3c2cb5d..0bb0e9c 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -411,3 +411,4 @@
394 common pkey_mprotect sys_pkey_mprotect
395 common pkey_alloc sys_pkey_alloc
396 common pkey_free sys_pkey_free
+397 common statx sys_statx
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index ce18c91..f0325d9 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -198,6 +198,8 @@ static const struct dma_map_ops xen_swiotlb_dma_ops = {
.unmap_page = xen_swiotlb_unmap_page,
.dma_supported = xen_swiotlb_dma_supported,
.set_dma_mask = xen_swiotlb_set_dma_mask,
+ .mmap = xen_swiotlb_dma_mmap,
+ .get_sgtable = xen_swiotlb_get_sgtable,
};
int __init xen_mm_init(void)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index a39029b..3741859 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -508,6 +508,16 @@
If unsure, say Y.
+config QCOM_QDF2400_ERRATUM_0065
+ bool "QDF2400 E0065: Incorrect GITS_TYPER.ITT_Entry_size"
+ default y
+ help
+ On Qualcomm Datacenter Technologies QDF2400 SoC, ITS hardware reports
+ ITE size incorrectly. The GITS_TYPER.ITT_Entry_size field should have
+ been indicated as 16Bytes (0xf), not 8Bytes (0x7).
+
+ If unsure, say Y.
+
endmenu
@@ -1063,6 +1073,10 @@
def_bool y
depends on COMPAT && SYSVIPC
+config KEYS_COMPAT
+ def_bool y
+ depends on COMPAT && KEYS
+
endmenu
menu "Power management options"
diff --git a/arch/arm64/boot/dts/broadcom/ns2.dtsi b/arch/arm64/boot/dts/broadcom/ns2.dtsi
index 9f9e203..bcb03fc 100644
--- a/arch/arm64/boot/dts/broadcom/ns2.dtsi
+++ b/arch/arm64/boot/dts/broadcom/ns2.dtsi
@@ -114,6 +114,7 @@
pcie0: pcie@20020000 {
compatible = "brcm,iproc-pcie";
reg = <0 0x20020000 0 0x1000>;
+ dma-coherent;
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0>;
@@ -144,6 +145,7 @@
pcie4: pcie@50020000 {
compatible = "brcm,iproc-pcie";
reg = <0 0x50020000 0 0x1000>;
+ dma-coherent;
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0>;
@@ -174,6 +176,7 @@
pcie8: pcie@60c00000 {
compatible = "brcm,iproc-pcie-paxc";
reg = <0 0x60c00000 0 0x1000>;
+ dma-coherent;
linux,pci-domain = <8>;
bus-range = <0x0 0x1>;
@@ -203,6 +206,7 @@
<0x61030000 0x100>;
reg-names = "amac_base", "idm_base", "nicpm_base";
interrupts = <GIC_SPI 341 IRQ_TYPE_LEVEL_HIGH>;
+ dma-coherent;
phy-handle = <&gphy0>;
phy-mode = "rgmii";
status = "disabled";
@@ -213,6 +217,7 @@
reg = <0x612c0000 0x445>; /* PDC FS0 regs */
interrupts = <GIC_SPI 187 IRQ_TYPE_LEVEL_HIGH>;
#mbox-cells = <1>;
+ dma-coherent;
brcm,rx-status-len = <32>;
brcm,use-bcm-hdr;
};
@@ -222,6 +227,7 @@
reg = <0x612e0000 0x445>; /* PDC FS1 regs */
interrupts = <GIC_SPI 189 IRQ_TYPE_LEVEL_HIGH>;
#mbox-cells = <1>;
+ dma-coherent;
brcm,rx-status-len = <32>;
brcm,use-bcm-hdr;
};
@@ -231,6 +237,7 @@
reg = <0x61300000 0x445>; /* PDC FS2 regs */
interrupts = <GIC_SPI 191 IRQ_TYPE_LEVEL_HIGH>;
#mbox-cells = <1>;
+ dma-coherent;
brcm,rx-status-len = <32>;
brcm,use-bcm-hdr;
};
@@ -240,6 +247,7 @@
reg = <0x61320000 0x445>; /* PDC FS3 regs */
interrupts = <GIC_SPI 193 IRQ_TYPE_LEVEL_HIGH>;
#mbox-cells = <1>;
+ dma-coherent;
brcm,rx-status-len = <32>;
brcm,use-bcm-hdr;
};
@@ -644,6 +652,7 @@
sata: ahci@663f2000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
reg = <0x663f2000 0x1000>;
+ dma-coherent;
reg-names = "ahci";
interrupts = <GIC_SPI 438 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
@@ -667,6 +676,7 @@
compatible = "brcm,sdhci-iproc-cygnus";
reg = <0x66420000 0x100>;
interrupts = <GIC_SPI 421 IRQ_TYPE_LEVEL_HIGH>;
+ dma-coherent;
bus-width = <8>;
clocks = <&genpll_sw BCM_NS2_GENPLL_SW_SDIO_CLK>;
status = "disabled";
@@ -676,6 +686,7 @@
compatible = "brcm,sdhci-iproc-cygnus";
reg = <0x66430000 0x100>;
interrupts = <GIC_SPI 422 IRQ_TYPE_LEVEL_HIGH>;
+ dma-coherent;
bus-width = <8>;
clocks = <&genpll_sw BCM_NS2_GENPLL_SW_SDIO_CLK>;
status = "disabled";
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 05310ad..f31c48d 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -251,7 +251,7 @@ static inline bool system_supports_fpsimd(void)
static inline bool system_uses_ttbr0_pan(void)
{
return IS_ENABLED(CONFIG_ARM64_SW_TTBR0_PAN) &&
- !cpus_have_cap(ARM64_HAS_PAN);
+ !cpus_have_const_cap(ARM64_HAS_PAN);
}
#endif /* __ASSEMBLY__ */
diff --git a/arch/arm64/include/asm/current.h b/arch/arm64/include/asm/current.h
index 86c4041..f6580d4 100644
--- a/arch/arm64/include/asm/current.h
+++ b/arch/arm64/include/asm/current.h
@@ -3,8 +3,6 @@
#include <linux/compiler.h>
-#include <asm/sysreg.h>
-
#ifndef __ASSEMBLY__
struct task_struct;
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index f21fd38..e7705e7 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -30,8 +30,7 @@
#define __KVM_HAVE_ARCH_INTC_INITIALIZED
-#define KVM_USER_MEM_SLOTS 32
-#define KVM_PRIVATE_MEM_SLOTS 4
+#define KVM_USER_MEM_SLOTS 512
#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
#define KVM_HALT_POLL_NS_DEFAULT 500000
diff --git a/arch/arm64/include/asm/pgtable-types.h b/arch/arm64/include/asm/pgtable-types.h
index 69b2fd4..345a072 100644
--- a/arch/arm64/include/asm/pgtable-types.h
+++ b/arch/arm64/include/asm/pgtable-types.h
@@ -55,9 +55,13 @@ typedef struct { pteval_t pgprot; } pgprot_t;
#define __pgprot(x) ((pgprot_t) { (x) } )
#if CONFIG_PGTABLE_LEVELS == 2
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
#elif CONFIG_PGTABLE_LEVELS == 3
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopud.h>
+#elif CONFIG_PGTABLE_LEVELS == 4
+#include <asm-generic/5level-fixup.h>
#endif
#endif /* __ASM_PGTABLE_TYPES_H */
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index e78ac26..bdbeb06 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -44,7 +44,7 @@
#define __ARM_NR_compat_cacheflush (__ARM_NR_COMPAT_BASE+2)
#define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE+5)
-#define __NR_compat_syscalls 394
+#define __NR_compat_syscalls 398
#endif
#define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index b7e8ef1..c66b51a 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -809,6 +809,14 @@ __SYSCALL(__NR_copy_file_range, sys_copy_file_range)
__SYSCALL(__NR_preadv2, compat_sys_preadv2)
#define __NR_pwritev2 393
__SYSCALL(__NR_pwritev2, compat_sys_pwritev2)
+#define __NR_pkey_mprotect 394
+__SYSCALL(__NR_pkey_mprotect, sys_pkey_mprotect)
+#define __NR_pkey_alloc 395
+__SYSCALL(__NR_pkey_alloc, sys_pkey_alloc)
+#define __NR_pkey_free 396
+__SYSCALL(__NR_pkey_free, sys_pkey_free)
+#define __NR_statx 397
+__SYSCALL(__NR_statx, sys_statx)
/*
* Please add new compat syscalls above this comment and update
diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
index 75a0f8a..fd69108 100644
--- a/arch/arm64/kernel/cpuidle.c
+++ b/arch/arm64/kernel/cpuidle.c
@@ -30,7 +30,7 @@ int arm_cpuidle_init(unsigned int cpu)
}
/**
- * cpu_suspend() - function to enter a low-power idle state
+ * arm_cpuidle_suspend() - function to enter a low-power idle state
* @arg: argument to pass to CPU suspend operations
*
* Return: 0 on success, -EOPNOTSUPP if CPU suspend hook not initialized, CPU
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index 769f24e..d7e90d9 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -131,11 +131,15 @@ u64 __init kaslr_early_init(u64 dt_phys, u64 modulo_offset)
/*
* The kernel Image should not extend across a 1GB/32MB/512MB alignment
* boundary (for 4KB/16KB/64KB granule kernels, respectively). If this
- * happens, increase the KASLR offset by the size of the kernel image.
+ * happens, increase the KASLR offset by the size of the kernel image
+ * rounded up by SWAPPER_BLOCK_SIZE.
*/
if ((((u64)_text + offset + modulo_offset) >> SWAPPER_TABLE_SHIFT) !=
- (((u64)_end + offset + modulo_offset) >> SWAPPER_TABLE_SHIFT))
- offset = (offset + (u64)(_end - _text)) & mask;
+ (((u64)_end + offset + modulo_offset) >> SWAPPER_TABLE_SHIFT)) {
+ u64 kimg_sz = _end - _text;
+ offset = (offset + round_up(kimg_sz, SWAPPER_BLOCK_SIZE))
+ & mask;
+ }
if (IS_ENABLED(CONFIG_KASAN))
/*
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 2a07aae..c5c4594 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -372,12 +372,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr)
return 0;
}
-int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
- unsigned long val, void *data)
-{
- return NOTIFY_DONE;
-}
-
static void __kprobes kprobe_handler(struct pt_regs *regs)
{
struct kprobe *p, *cur_kprobe;
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index ef1caae..9b10365 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -944,7 +944,7 @@ static bool have_cpu_die(void)
#ifdef CONFIG_HOTPLUG_CPU
int any_cpu = raw_smp_processor_id();
- if (cpu_ops[any_cpu]->cpu_die)
+ if (cpu_ops[any_cpu] && cpu_ops[any_cpu]->cpu_die)
return true;
#endif
return false;
diff --git a/arch/arm64/kernel/vdso/.gitignore b/arch/arm64/kernel/vdso/.gitignore
index b8cc94e..f8b69d8 100644
--- a/arch/arm64/kernel/vdso/.gitignore
+++ b/arch/arm64/kernel/vdso/.gitignore
@@ -1,2 +1 @@
vdso.lds
-vdso-offsets.h
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 1bfe30d..fa1b18e 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -135,7 +135,19 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
return ret;
}
+static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ u32 hsr = kvm_vcpu_get_hsr(vcpu);
+
+ kvm_pr_unimpl("Unknown exception class: hsr: %#08x -- %s\n",
+ hsr, esr_get_class_string(hsr));
+
+ kvm_inject_undefined(vcpu);
+ return 1;
+}
+
static exit_handle_fn arm_exit_handlers[] = {
+ [0 ... ESR_ELx_EC_MAX] = kvm_handle_unknown_ec,
[ESR_ELx_EC_WFx] = kvm_handle_wfx,
[ESR_ELx_EC_CP15_32] = kvm_handle_cp15_32,
[ESR_ELx_EC_CP15_64] = kvm_handle_cp15_64,
@@ -162,13 +174,6 @@ static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
u32 hsr = kvm_vcpu_get_hsr(vcpu);
u8 hsr_ec = ESR_ELx_EC(hsr);
- if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) ||
- !arm_exit_handlers[hsr_ec]) {
- kvm_err("Unknown exception class: hsr: %#08x -- %s\n",
- hsr, esr_get_class_string(hsr));
- BUG();
- }
-
return arm_exit_handlers[hsr_ec];
}
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index e8e7ba2..9e1d2b7 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -18,14 +18,62 @@
#include <asm/kvm_hyp.h>
#include <asm/tlbflush.h>
+static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm)
+{
+ u64 val;
+
+ /*
+ * With VHE enabled, we have HCR_EL2.{E2H,TGE} = {1,1}, and
+ * most TLB operations target EL2/EL0. In order to affect the
+ * guest TLBs (EL1/EL0), we need to change one of these two
+ * bits. Changing E2H is impossible (goodbye TTBR1_EL2), so
+ * let's flip TGE before executing the TLB operation.
+ */
+ write_sysreg(kvm->arch.vttbr, vttbr_el2);
+ val = read_sysreg(hcr_el2);
+ val &= ~HCR_TGE;
+ write_sysreg(val, hcr_el2);
+ isb();
+}
+
+static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm)
+{
+ write_sysreg(kvm->arch.vttbr, vttbr_el2);
+ isb();
+}
+
+static hyp_alternate_select(__tlb_switch_to_guest,
+ __tlb_switch_to_guest_nvhe,
+ __tlb_switch_to_guest_vhe,
+ ARM64_HAS_VIRT_HOST_EXTN);
+
+static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm)
+{
+ /*
+ * We're done with the TLB operation, let's restore the host's
+ * view of HCR_EL2.
+ */
+ write_sysreg(0, vttbr_el2);
+ write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
+}
+
+static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm)
+{
+ write_sysreg(0, vttbr_el2);
+}
+
+static hyp_alternate_select(__tlb_switch_to_host,
+ __tlb_switch_to_host_nvhe,
+ __tlb_switch_to_host_vhe,
+ ARM64_HAS_VIRT_HOST_EXTN);
+
void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
{
dsb(ishst);
/* Switch to requested VMID */
kvm = kern_hyp_va(kvm);
- write_sysreg(kvm->arch.vttbr, vttbr_el2);
- isb();
+ __tlb_switch_to_guest()(kvm);
/*
* We could do so much better if we had the VA as well.
@@ -46,7 +94,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
dsb(ish);
isb();
- write_sysreg(0, vttbr_el2);
+ __tlb_switch_to_host()(kvm);
}
void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
@@ -55,14 +103,13 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
/* Switch to requested VMID */
kvm = kern_hyp_va(kvm);
- write_sysreg(kvm->arch.vttbr, vttbr_el2);
- isb();
+ __tlb_switch_to_guest()(kvm);
__tlbi(vmalls12e1is);
dsb(ish);
isb();
- write_sysreg(0, vttbr_el2);
+ __tlb_switch_to_host()(kvm);
}
void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
@@ -70,14 +117,13 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm);
/* Switch to requested VMID */
- write_sysreg(kvm->arch.vttbr, vttbr_el2);
- isb();
+ __tlb_switch_to_guest()(kvm);
__tlbi(vmalle1);
dsb(nsh);
isb();
- write_sysreg(0, vttbr_el2);
+ __tlb_switch_to_host()(kvm);
}
void __hyp_text __kvm_flush_vm_context(void)
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index 55d1e92..687a358 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -162,7 +162,7 @@ void __init kasan_init(void)
clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
vmemmap_populate(kimg_shadow_start, kimg_shadow_end,
- pfn_to_nid(virt_to_pfn(_text)));
+ pfn_to_nid(virt_to_pfn(lm_alias(_text))));
/*
* vmemmap_populate() has populated the shadow region that covers the
diff --git a/arch/avr32/include/asm/pgtable-2level.h b/arch/avr32/include/asm/pgtable-2level.h
index 425dd56..d5b1c63 100644
--- a/arch/avr32/include/asm/pgtable-2level.h
+++ b/arch/avr32/include/asm/pgtable-2level.h
@@ -8,6 +8,7 @@
#ifndef __ASM_AVR32_PGTABLE_2LEVEL_H
#define __ASM_AVR32_PGTABLE_2LEVEL_H
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
/*
diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h
index 5a65042..2434d08 100644
--- a/arch/avr32/include/uapi/asm/socket.h
+++ b/arch/avr32/include/uapi/asm/socket.h
@@ -92,4 +92,10 @@
#define SCM_TIMESTAMPING_OPT_STATS 54
+#define SO_MEMINFO 55
+
+#define SO_INCOMING_NAPI_ID 56
+
+#define SO_COOKIE 57
+
#endif /* _UAPI__ASM_AVR32_SOCKET_H */
diff --git a/arch/avr32/oprofile/backtrace.c b/arch/avr32/oprofile/backtrace.c
index 75d9ad6..29cf2f1 100644
--- a/arch/avr32/oprofile/backtrace.c
+++ b/arch/avr32/oprofile/backtrace.c
@@ -14,7 +14,7 @@
*/
#include <linux/oprofile.h>
-#include <linux/sched.h>
+#include <linux/ptrace.h>
#include <linux/uaccess.h>
/* The first two words of each frame on the stack look like this if we have
diff --git a/arch/c6x/kernel/ptrace.c b/arch/c6x/kernel/ptrace.c
index a27e1f0..8801dc9 100644
--- a/arch/c6x/kernel/ptrace.c
+++ b/arch/c6x/kernel/ptrace.c
@@ -70,46 +70,6 @@ static int gpr_get(struct task_struct *target,
0, sizeof(*regs));
}
-static int gpr_set(struct task_struct *target,
- const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
-{
- int ret;
- struct pt_regs *regs = task_pt_regs(target);
-
- /* Don't copyin TSR or CSR */
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- ®s,
- 0, PT_TSR * sizeof(long));
- if (ret)
- return ret;
-
- ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
- PT_TSR * sizeof(long),
- (PT_TSR + 1) * sizeof(long));
- if (ret)
- return ret;
-
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- ®s,
- (PT_TSR + 1) * sizeof(long),
- PT_CSR * sizeof(long));
- if (ret)
- return ret;
-
- ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
- PT_CSR * sizeof(long),
- (PT_CSR + 1) * sizeof(long));
- if (ret)
- return ret;
-
- ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- ®s,
- (PT_CSR + 1) * sizeof(long), -1);
- return ret;
-}
-
enum c6x_regset {
REGSET_GPR,
};
@@ -121,7 +81,6 @@ static const struct user_regset c6x_regsets[] = {
.size = sizeof(u32),
.align = sizeof(u32),
.get = gpr_get,
- .set = gpr_set
},
};
diff --git a/arch/cris/arch-v32/drivers/cryptocop.c b/arch/cris/arch-v32/drivers/cryptocop.c
index ae6903d..14970f1 100644
--- a/arch/cris/arch-v32/drivers/cryptocop.c
+++ b/arch/cris/arch-v32/drivers/cryptocop.c
@@ -2086,7 +2086,7 @@ static void cryptocop_job_queue_close(void)
dma_in_cfg.en = regk_dma_no;
REG_WR(dma, IN_DMA_INST, rw_cfg, dma_in_cfg);
- /* Disble the cryptocop. */
+ /* Disable the cryptocop. */
rw_cfg = REG_RD(strcop, regi_strcop, rw_cfg);
rw_cfg.en = 0;
REG_WR(strcop, regi_strcop, rw_cfg, rw_cfg);
diff --git a/arch/cris/include/asm/pgtable.h b/arch/cris/include/asm/pgtable.h
index 2a3210b..fa3a730 100644
--- a/arch/cris/include/asm/pgtable.h
+++ b/arch/cris/include/asm/pgtable.h
@@ -6,6 +6,7 @@
#define _CRIS_PGTABLE_H
#include <asm/page.h>
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
#ifndef __ASSEMBLY__
diff --git a/arch/frv/include/asm/pgtable.h b/arch/frv/include/asm/pgtable.h
index a0513d4..ab6e7e9 100644
--- a/arch/frv/include/asm/pgtable.h
+++ b/arch/frv/include/asm/pgtable.h
@@ -16,6 +16,7 @@
#ifndef _ASM_PGTABLE_H
#define _ASM_PGTABLE_H
+#include <asm-generic/5level-fixup.h>
#include <asm/mem-layout.h>
#include <asm/setup.h>
#include <asm/processor.h>
diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h
index 81e0353..1ccf456 100644
--- a/arch/frv/include/uapi/asm/socket.h
+++ b/arch/frv/include/uapi/asm/socket.h
@@ -92,5 +92,11 @@
#define SCM_TIMESTAMPING_OPT_STATS 54
+#define SO_MEMINFO 55
+
+#define SO_INCOMING_NAPI_ID 56
+
+#define SO_COOKIE 57
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/h8300/include/asm/pgtable.h b/arch/h8300/include/asm/pgtable.h
index 8341db6..7d265d2 100644
--- a/arch/h8300/include/asm/pgtable.h
+++ b/arch/h8300/include/asm/pgtable.h
@@ -1,5 +1,6 @@
#ifndef _H8300_PGTABLE_H
#define _H8300_PGTABLE_H
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopud.h>
#include <asm-generic/pgtable.h>
#define pgtable_cache_init() do { } while (0)
diff --git a/arch/h8300/kernel/ptrace.c b/arch/h8300/kernel/ptrace.c
index 9207554..0dc1c8f 100644
--- a/arch/h8300/kernel/ptrace.c
+++ b/arch/h8300/kernel/ptrace.c
@@ -95,7 +95,8 @@ static int regs_get(struct task_struct *target,
long *reg = (long *)®s;
/* build user regs in buffer */
- for (r = 0; r < ARRAY_SIZE(register_offset); r++)
+ BUILD_BUG_ON(sizeof(regs) % sizeof(long) != 0);
+ for (r = 0; r < sizeof(regs) / sizeof(long); r++)
*reg++ = h8300_get_reg(target, r);
return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
@@ -113,7 +114,8 @@ static int regs_set(struct task_struct *target,
long *reg;
/* build user regs in buffer */
- for (reg = (long *)®s, r = 0; r < ARRAY_SIZE(register_offset); r++)
+ BUILD_BUG_ON(sizeof(regs) % sizeof(long) != 0);
+ for (reg = (long *)®s, r = 0; r < sizeof(regs) / sizeof(long); r++)
*reg++ = h8300_get_reg(target, r);
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
@@ -122,7 +124,7 @@ static int regs_set(struct task_struct *target,
return ret;
/* write back to pt_regs */
- for (reg = (long *)®s, r = 0; r < ARRAY_SIZE(register_offset); r++)
+ for (reg = (long *)®s, r = 0; r < sizeof(regs) / sizeof(long); r++)
h8300_put_reg(target, r, *reg++);
return 0;
}
diff --git a/arch/h8300/kernel/ptrace_h.c b/arch/h8300/kernel/ptrace_h.c
index fe3b567..f5ff3b7 100644
--- a/arch/h8300/kernel/ptrace_h.c
+++ b/arch/h8300/kernel/ptrace_h.c
@@ -9,7 +9,7 @@
*/
#include <linux/linkage.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
#include <asm/ptrace.h>
#define BREAKINST 0x5730 /* trapa #3 */
diff --git a/arch/hexagon/include/asm/pgtable.h b/arch/hexagon/include/asm/pgtable.h
index 49eab81..24a9177 100644
--- a/arch/hexagon/include/asm/pgtable.h
+++ b/arch/hexagon/include/asm/pgtable.h
@@ -26,6 +26,7 @@
*/
#include <linux/swap.h>
#include <asm/page.h>
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
/* A handy thing to have if one has the RAM. Declared in head.S */
diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h
index 384794e..6cc22c8d 100644
--- a/arch/ia64/include/asm/pgtable.h
+++ b/arch/ia64/include/asm/pgtable.h
@@ -587,8 +587,10 @@ extern struct page *zero_page_memmap_ptr;
#if CONFIG_PGTABLE_LEVELS == 3
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopud.h>
#endif
+#include <asm-generic/5level-fixup.h>
#include <asm-generic/pgtable.h>
#endif /* _ASM_IA64_PGTABLE_H */
diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h
index 57feb0c..2c3f4b4 100644
--- a/arch/ia64/include/uapi/asm/socket.h
+++ b/arch/ia64/include/uapi/asm/socket.h
@@ -101,4 +101,10 @@
#define SCM_TIMESTAMPING_OPT_STATS 54
+#define SO_MEMINFO 55
+
+#define SO_INCOMING_NAPI_ID 56
+
+#define SO_COOKIE 57
+
#endif /* _ASM_IA64_SOCKET_H */
diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h
index 5853f8e9..ae6548d 100644
--- a/arch/m32r/include/uapi/asm/socket.h
+++ b/arch/m32r/include/uapi/asm/socket.h
@@ -92,4 +92,10 @@
#define SCM_TIMESTAMPING_OPT_STATS 54
+#define SO_MEMINFO 55
+
+#define SO_INCOMING_NAPI_ID 56
+
+#define SO_COOKIE 57
+
#endif /* _ASM_M32R_SOCKET_H */
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 048bf07..531cb9e 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -25,6 +25,7 @@
# CONFIG_EFI_PARTITION is not set
CONFIG_SYSV68_PARTITION=y
CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
CONFIG_KEXEC=y
CONFIG_BOOTINFO_PROC=y
CONFIG_M68020=y
@@ -60,6 +61,7 @@
CONFIG_NET_FOU_IP_TUNNELS=y
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
CONFIG_INET_IPCOMP=m
CONFIG_INET_XFRM_MODE_TRANSPORT=m
CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -71,6 +73,7 @@
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
CONFIG_INET6_IPCOMP=m
CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
@@ -101,6 +104,7 @@
CONFIG_NFT_CT=m
CONFIG_NFT_SET_RBTREE=m
CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
@@ -298,6 +302,8 @@
CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
CONFIG_NET_DEVLINK=m
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -371,6 +377,7 @@
CONFIG_MACVLAN=m
CONFIG_MACVTAP=m
CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
CONFIG_VXLAN=m
CONFIG_GENEVE=m
CONFIG_GTP=m
@@ -383,6 +390,7 @@
# CONFIG_NET_VENDOR_AMAZON is not set
CONFIG_A2065=y
CONFIG_ARIADNE=y
+# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
@@ -404,7 +412,6 @@
# CONFIG_NET_VENDOR_SOLARFLARE is not set
# CONFIG_NET_VENDOR_SMSC is not set
# CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
@@ -564,6 +571,8 @@
CONFIG_DLM=m
# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
CONFIG_ASYNC_RAID6_TEST=m
CONFIG_TEST_HEXDUMP=m
CONFIG_TEST_STRING_HELPERS=m
@@ -594,6 +603,7 @@
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
CONFIG_CRYPTO_XCBC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -605,6 +615,7 @@
CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_ANUBIS=m
CONFIG_CRYPTO_BLOWFISH=m
CONFIG_CRYPTO_CAMELLIA=m
@@ -629,4 +640,5 @@
CONFIG_CRYPTO_USER_API_RNG=m
CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index d4de249..ca91d39 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -26,6 +26,7 @@
# CONFIG_EFI_PARTITION is not set
CONFIG_SYSV68_PARTITION=y
CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
CONFIG_KEXEC=y
CONFIG_BOOTINFO_PROC=y
CONFIG_M68020=y
@@ -58,6 +59,7 @@
CONFIG_NET_FOU_IP_TUNNELS=y
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
CONFIG_INET_IPCOMP=m
CONFIG_INET_XFRM_MODE_TRANSPORT=m
CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -69,6 +71,7 @@
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
CONFIG_INET6_IPCOMP=m
CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
@@ -99,6 +102,7 @@
CONFIG_NFT_CT=m
CONFIG_NFT_SET_RBTREE=m
CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
@@ -296,6 +300,8 @@
CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
CONFIG_NET_DEVLINK=m
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -353,6 +359,7 @@
CONFIG_MACVLAN=m
CONFIG_MACVTAP=m
CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
CONFIG_VXLAN=m
CONFIG_GENEVE=m
CONFIG_GTP=m
@@ -362,6 +369,7 @@
CONFIG_VETH=m
# CONFIG_NET_VENDOR_ALACRITECH is not set
# CONFIG_NET_VENDOR_AMAZON is not set
+# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
@@ -378,7 +386,6 @@
# CONFIG_NET_VENDOR_SEEQ is not set
# CONFIG_NET_VENDOR_SOLARFLARE is not set
# CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
@@ -523,6 +530,8 @@
CONFIG_DLM=m
# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
CONFIG_ASYNC_RAID6_TEST=m
CONFIG_TEST_HEXDUMP=m
CONFIG_TEST_STRING_HELPERS=m
@@ -553,6 +562,7 @@
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
CONFIG_CRYPTO_XCBC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -564,6 +574,7 @@
CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_ANUBIS=m
CONFIG_CRYPTO_BLOWFISH=m
CONFIG_CRYPTO_CAMELLIA=m
@@ -588,4 +599,5 @@
CONFIG_CRYPTO_USER_API_RNG=m
CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index fc0fd3f..23a3d8a 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -25,6 +25,7 @@
# CONFIG_EFI_PARTITION is not set
CONFIG_SYSV68_PARTITION=y
CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
CONFIG_KEXEC=y
CONFIG_BOOTINFO_PROC=y
CONFIG_M68020=y
@@ -58,6 +59,7 @@
CONFIG_NET_FOU_IP_TUNNELS=y
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
CONFIG_INET_IPCOMP=m
CONFIG_INET_XFRM_MODE_TRANSPORT=m
CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -69,6 +71,7 @@
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
CONFIG_INET6_IPCOMP=m
CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
@@ -99,6 +102,7 @@
CONFIG_NFT_CT=m
CONFIG_NFT_SET_RBTREE=m
CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
@@ -296,6 +300,8 @@
CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
CONFIG_NET_DEVLINK=m
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -362,6 +368,7 @@
CONFIG_MACVLAN=m
CONFIG_MACVTAP=m
CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
CONFIG_VXLAN=m
CONFIG_GENEVE=m
CONFIG_GTP=m
@@ -372,6 +379,7 @@
# CONFIG_NET_VENDOR_ALACRITECH is not set
# CONFIG_NET_VENDOR_AMAZON is not set
CONFIG_ATARILANCE=y
+# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
@@ -389,7 +397,6 @@
# CONFIG_NET_VENDOR_SOLARFLARE is not set
CONFIG_SMC91X=y
# CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
@@ -544,6 +551,8 @@
CONFIG_DLM=m
# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
CONFIG_ASYNC_RAID6_TEST=m
CONFIG_TEST_HEXDUMP=m
CONFIG_TEST_STRING_HELPERS=m
@@ -574,6 +583,7 @@
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
CONFIG_CRYPTO_XCBC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -585,6 +595,7 @@
CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_ANUBIS=m
CONFIG_CRYPTO_BLOWFISH=m
CONFIG_CRYPTO_CAMELLIA=m
@@ -609,4 +620,5 @@
CONFIG_CRYPTO_USER_API_RNG=m
CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 52e984a..95deb95 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -25,6 +25,7 @@
CONFIG_SUN_PARTITION=y
# CONFIG_EFI_PARTITION is not set
CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
CONFIG_KEXEC=y
CONFIG_BOOTINFO_PROC=y
CONFIG_M68040=y
@@ -56,6 +57,7 @@
CONFIG_NET_FOU_IP_TUNNELS=y
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
CONFIG_INET_IPCOMP=m
CONFIG_INET_XFRM_MODE_TRANSPORT=m
CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -67,6 +69,7 @@
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
CONFIG_INET6_IPCOMP=m
CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
@@ -97,6 +100,7 @@
CONFIG_NFT_CT=m
CONFIG_NFT_SET_RBTREE=m
CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
@@ -294,6 +298,8 @@
CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
CONFIG_NET_DEVLINK=m
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -352,6 +358,7 @@
CONFIG_MACVLAN=m
CONFIG_MACVTAP=m
CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
CONFIG_VXLAN=m
CONFIG_GENEVE=m
CONFIG_GTP=m
@@ -361,6 +368,7 @@
CONFIG_VETH=m
# CONFIG_NET_VENDOR_ALACRITECH is not set
# CONFIG_NET_VENDOR_AMAZON is not set
+# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
@@ -377,7 +385,6 @@
# CONFIG_NET_VENDOR_SEEQ is not set
# CONFIG_NET_VENDOR_SOLARFLARE is not set
# CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
@@ -515,6 +522,8 @@
CONFIG_DLM=m
# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
CONFIG_ASYNC_RAID6_TEST=m
CONFIG_TEST_HEXDUMP=m
CONFIG_TEST_STRING_HELPERS=m
@@ -545,6 +554,7 @@
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
CONFIG_CRYPTO_XCBC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -556,6 +566,7 @@
CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_ANUBIS=m
CONFIG_CRYPTO_BLOWFISH=m
CONFIG_CRYPTO_CAMELLIA=m
@@ -580,4 +591,5 @@
CONFIG_CRYPTO_USER_API_RNG=m
CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index aaeed44..afae695 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -26,6 +26,7 @@
# CONFIG_EFI_PARTITION is not set
CONFIG_SYSV68_PARTITION=y
CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
CONFIG_KEXEC=y
CONFIG_BOOTINFO_PROC=y
CONFIG_M68020=y
@@ -58,6 +59,7 @@
CONFIG_NET_FOU_IP_TUNNELS=y
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
CONFIG_INET_IPCOMP=m
CONFIG_INET_XFRM_MODE_TRANSPORT=m
CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -69,6 +71,7 @@
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
CONFIG_INET6_IPCOMP=m
CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
@@ -99,6 +102,7 @@
CONFIG_NFT_CT=m
CONFIG_NFT_SET_RBTREE=m
CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
@@ -296,6 +300,8 @@
CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
CONFIG_NET_DEVLINK=m
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -353,6 +359,7 @@
CONFIG_MACVLAN=m
CONFIG_MACVTAP=m
CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
CONFIG_VXLAN=m
CONFIG_GENEVE=m
CONFIG_GTP=m
@@ -363,6 +370,7 @@
# CONFIG_NET_VENDOR_ALACRITECH is not set
# CONFIG_NET_VENDOR_AMAZON is not set
CONFIG_HPLANCE=y
+# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
@@ -379,7 +387,6 @@
# CONFIG_NET_VENDOR_SEEQ is not set
# CONFIG_NET_VENDOR_SOLARFLARE is not set
# CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
@@ -525,6 +532,8 @@
CONFIG_DLM=m
# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
CONFIG_ASYNC_RAID6_TEST=m
CONFIG_TEST_HEXDUMP=m
CONFIG_TEST_STRING_HELPERS=m
@@ -555,6 +564,7 @@
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
CONFIG_CRYPTO_XCBC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -566,6 +576,7 @@
CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_ANUBIS=m
CONFIG_CRYPTO_BLOWFISH=m
CONFIG_CRYPTO_CAMELLIA=m
@@ -590,4 +601,5 @@
CONFIG_CRYPTO_USER_API_RNG=m
CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 3bbc9b2..b010734 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -25,6 +25,7 @@
# CONFIG_EFI_PARTITION is not set
CONFIG_SYSV68_PARTITION=y
CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
CONFIG_KEXEC=y
CONFIG_BOOTINFO_PROC=y
CONFIG_M68020=y
@@ -57,6 +58,7 @@
CONFIG_NET_FOU_IP_TUNNELS=y
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
CONFIG_INET_IPCOMP=m
CONFIG_INET_XFRM_MODE_TRANSPORT=m
CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -68,6 +70,7 @@
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
CONFIG_INET6_IPCOMP=m
CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
@@ -98,6 +101,7 @@
CONFIG_NFT_CT=m
CONFIG_NFT_SET_RBTREE=m
CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
@@ -298,6 +302,8 @@
CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
CONFIG_NET_DEVLINK=m
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -369,6 +375,7 @@
CONFIG_MACVLAN=m
CONFIG_MACVTAP=m
CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
CONFIG_VXLAN=m
CONFIG_GENEVE=m
CONFIG_GTP=m
@@ -379,6 +386,7 @@
# CONFIG_NET_VENDOR_ALACRITECH is not set
# CONFIG_NET_VENDOR_AMAZON is not set
CONFIG_MACMACE=y
+# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
@@ -398,7 +406,6 @@
# CONFIG_NET_VENDOR_SOLARFLARE is not set
# CONFIG_NET_VENDOR_SMSC is not set
# CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
@@ -547,6 +554,8 @@
CONFIG_DLM=m
# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
CONFIG_ASYNC_RAID6_TEST=m
CONFIG_TEST_HEXDUMP=m
CONFIG_TEST_STRING_HELPERS=m
@@ -577,6 +586,7 @@
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
CONFIG_CRYPTO_XCBC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -588,6 +598,7 @@
CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_ANUBIS=m
CONFIG_CRYPTO_BLOWFISH=m
CONFIG_CRYPTO_CAMELLIA=m
@@ -612,4 +623,5 @@
CONFIG_CRYPTO_USER_API_RNG=m
CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 8f2c0de..0e41454 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -21,6 +21,7 @@
CONFIG_UNIXWARE_DISKLABEL=y
# CONFIG_EFI_PARTITION is not set
CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
CONFIG_KEXEC=y
CONFIG_BOOTINFO_PROC=y
CONFIG_M68020=y
@@ -67,6 +68,7 @@
CONFIG_NET_FOU_IP_TUNNELS=y
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
CONFIG_INET_IPCOMP=m
CONFIG_INET_XFRM_MODE_TRANSPORT=m
CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -78,6 +80,7 @@
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
CONFIG_INET6_IPCOMP=m
CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
@@ -108,6 +111,7 @@
CONFIG_NFT_CT=m
CONFIG_NFT_SET_RBTREE=m
CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
@@ -308,6 +312,8 @@
CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
CONFIG_NET_DEVLINK=m
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -402,6 +408,7 @@
CONFIG_MACVLAN=m
CONFIG_MACVTAP=m
CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
CONFIG_VXLAN=m
CONFIG_GENEVE=m
CONFIG_GTP=m
@@ -419,6 +426,7 @@
CONFIG_MVME147_NET=y
CONFIG_SUN3LANCE=y
CONFIG_MACMACE=y
+# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
@@ -444,7 +452,6 @@
# CONFIG_NET_VENDOR_SOLARFLARE is not set
CONFIG_SMC91X=y
# CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PLIP=m
@@ -627,6 +634,8 @@
CONFIG_DLM=m
# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
CONFIG_ASYNC_RAID6_TEST=m
CONFIG_TEST_HEXDUMP=m
CONFIG_TEST_STRING_HELPERS=m
@@ -657,6 +666,7 @@
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
CONFIG_CRYPTO_XCBC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -668,6 +678,7 @@
CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_ANUBIS=m
CONFIG_CRYPTO_BLOWFISH=m
CONFIG_CRYPTO_CAMELLIA=m
@@ -692,4 +703,5 @@
CONFIG_CRYPTO_USER_API_RNG=m
CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index c743dd2..b2e687a 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -25,6 +25,7 @@
CONFIG_SUN_PARTITION=y
# CONFIG_EFI_PARTITION is not set
CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
CONFIG_KEXEC=y
CONFIG_BOOTINFO_PROC=y
CONFIG_M68030=y
@@ -55,6 +56,7 @@
CONFIG_NET_FOU_IP_TUNNELS=y
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
CONFIG_INET_IPCOMP=m
CONFIG_INET_XFRM_MODE_TRANSPORT=m
CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -66,6 +68,7 @@
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
CONFIG_INET6_IPCOMP=m
CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
@@ -96,6 +99,7 @@
CONFIG_NFT_CT=m
CONFIG_NFT_SET_RBTREE=m
CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
@@ -293,6 +297,8 @@
CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
CONFIG_NET_DEVLINK=m
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -351,6 +357,7 @@
CONFIG_MACVLAN=m
CONFIG_MACVTAP=m
CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
CONFIG_VXLAN=m
CONFIG_GENEVE=m
CONFIG_GTP=m
@@ -361,6 +368,7 @@
# CONFIG_NET_VENDOR_ALACRITECH is not set
# CONFIG_NET_VENDOR_AMAZON is not set
CONFIG_MVME147_NET=y
+# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
@@ -377,7 +385,6 @@
# CONFIG_NET_VENDOR_SEEQ is not set
# CONFIG_NET_VENDOR_SOLARFLARE is not set
# CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
@@ -515,6 +522,8 @@
CONFIG_DLM=m
# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
CONFIG_ASYNC_RAID6_TEST=m
CONFIG_TEST_HEXDUMP=m
CONFIG_TEST_STRING_HELPERS=m
@@ -545,6 +554,7 @@
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
CONFIG_CRYPTO_XCBC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -556,6 +566,7 @@
CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_ANUBIS=m
CONFIG_CRYPTO_BLOWFISH=m
CONFIG_CRYPTO_CAMELLIA=m
@@ -580,4 +591,5 @@
CONFIG_CRYPTO_USER_API_RNG=m
CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 2ccaca8..cbd8ee2 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -25,6 +25,7 @@
CONFIG_SUN_PARTITION=y
# CONFIG_EFI_PARTITION is not set
CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
CONFIG_KEXEC=y
CONFIG_BOOTINFO_PROC=y
CONFIG_M68040=y
@@ -56,6 +57,7 @@
CONFIG_NET_FOU_IP_TUNNELS=y
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
CONFIG_INET_IPCOMP=m
CONFIG_INET_XFRM_MODE_TRANSPORT=m
CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -67,6 +69,7 @@
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
CONFIG_INET6_IPCOMP=m
CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
@@ -97,6 +100,7 @@
CONFIG_NFT_CT=m
CONFIG_NFT_SET_RBTREE=m
CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
@@ -294,6 +298,8 @@
CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
CONFIG_NET_DEVLINK=m
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -352,6 +358,7 @@
CONFIG_MACVLAN=m
CONFIG_MACVTAP=m
CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
CONFIG_VXLAN=m
CONFIG_GENEVE=m
CONFIG_GTP=m
@@ -361,6 +368,7 @@
CONFIG_VETH=m
# CONFIG_NET_VENDOR_ALACRITECH is not set
# CONFIG_NET_VENDOR_AMAZON is not set
+# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
@@ -377,7 +385,6 @@
# CONFIG_NET_VENDOR_SEEQ is not set
# CONFIG_NET_VENDOR_SOLARFLARE is not set
# CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
@@ -515,6 +522,8 @@
CONFIG_DLM=m
# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
CONFIG_ASYNC_RAID6_TEST=m
CONFIG_TEST_HEXDUMP=m
CONFIG_TEST_STRING_HELPERS=m
@@ -545,6 +554,7 @@
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
CONFIG_CRYPTO_XCBC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -556,6 +566,7 @@
CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_ANUBIS=m
CONFIG_CRYPTO_BLOWFISH=m
CONFIG_CRYPTO_CAMELLIA=m
@@ -580,4 +591,5 @@
CONFIG_CRYPTO_USER_API_RNG=m
CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 5599f3f..1e82cc9 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -26,6 +26,7 @@
# CONFIG_EFI_PARTITION is not set
CONFIG_SYSV68_PARTITION=y
CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
CONFIG_KEXEC=y
CONFIG_BOOTINFO_PROC=y
CONFIG_M68040=y
@@ -56,6 +57,7 @@
CONFIG_NET_FOU_IP_TUNNELS=y
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
CONFIG_INET_IPCOMP=m
CONFIG_INET_XFRM_MODE_TRANSPORT=m
CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -67,6 +69,7 @@
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
CONFIG_INET6_IPCOMP=m
CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
@@ -97,6 +100,7 @@
CONFIG_NFT_CT=m
CONFIG_NFT_SET_RBTREE=m
CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
@@ -294,6 +298,8 @@
CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
CONFIG_NET_DEVLINK=m
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -358,6 +364,7 @@
CONFIG_MACVLAN=m
CONFIG_MACVTAP=m
CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
CONFIG_VXLAN=m
CONFIG_GENEVE=m
CONFIG_GTP=m
@@ -369,6 +376,7 @@
# CONFIG_NET_VENDOR_ALACRITECH is not set
# CONFIG_NET_VENDOR_AMAZON is not set
# CONFIG_NET_VENDOR_AMD is not set
+# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
@@ -388,7 +396,6 @@
# CONFIG_NET_VENDOR_SOLARFLARE is not set
# CONFIG_NET_VENDOR_SMSC is not set
# CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PLIP=m
@@ -538,6 +545,8 @@
CONFIG_DLM=m
# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
CONFIG_ASYNC_RAID6_TEST=m
CONFIG_TEST_HEXDUMP=m
CONFIG_TEST_STRING_HELPERS=m
@@ -568,6 +577,7 @@
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
CONFIG_CRYPTO_XCBC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -579,6 +589,7 @@
CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_ANUBIS=m
CONFIG_CRYPTO_BLOWFISH=m
CONFIG_CRYPTO_CAMELLIA=m
@@ -603,4 +614,5 @@
CONFIG_CRYPTO_USER_API_RNG=m
CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index 313bf0a..f9e77f5 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -25,6 +25,7 @@
# CONFIG_EFI_PARTITION is not set
CONFIG_SYSV68_PARTITION=y
CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
CONFIG_KEXEC=y
CONFIG_BOOTINFO_PROC=y
CONFIG_SUN3=y
@@ -53,6 +54,7 @@
CONFIG_NET_FOU_IP_TUNNELS=y
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
CONFIG_INET_IPCOMP=m
CONFIG_INET_XFRM_MODE_TRANSPORT=m
CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -64,6 +66,7 @@
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
CONFIG_INET6_IPCOMP=m
CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
@@ -94,6 +97,7 @@
CONFIG_NFT_CT=m
CONFIG_NFT_SET_RBTREE=m
CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
@@ -291,6 +295,8 @@
CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
CONFIG_NET_DEVLINK=m
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -349,6 +355,7 @@
CONFIG_MACVLAN=m
CONFIG_MACVTAP=m
CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
CONFIG_VXLAN=m
CONFIG_GENEVE=m
CONFIG_GTP=m
@@ -359,6 +366,7 @@
# CONFIG_NET_VENDOR_ALACRITECH is not set
# CONFIG_NET_VENDOR_AMAZON is not set
CONFIG_SUN3LANCE=y
+# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_EZCHIP is not set
@@ -375,7 +383,6 @@
# CONFIG_NET_VENDOR_SOLARFLARE is not set
# CONFIG_NET_VENDOR_STMICRO is not set
# CONFIG_NET_VENDOR_SUN is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
@@ -517,6 +524,8 @@
CONFIG_DLM=m
# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
CONFIG_ASYNC_RAID6_TEST=m
CONFIG_TEST_HEXDUMP=m
CONFIG_TEST_STRING_HELPERS=m
@@ -546,6 +555,7 @@
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
CONFIG_CRYPTO_XCBC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -557,6 +567,7 @@
CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_ANUBIS=m
CONFIG_CRYPTO_BLOWFISH=m
CONFIG_CRYPTO_CAMELLIA=m
@@ -581,4 +592,5 @@
CONFIG_CRYPTO_USER_API_RNG=m
CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 38b6136..3c394fc 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -25,6 +25,7 @@
# CONFIG_EFI_PARTITION is not set
CONFIG_SYSV68_PARTITION=y
CONFIG_IOSCHED_DEADLINE=m
+CONFIG_MQ_IOSCHED_DEADLINE=m
CONFIG_KEXEC=y
CONFIG_BOOTINFO_PROC=y
CONFIG_SUN3X=y
@@ -53,6 +54,7 @@
CONFIG_NET_FOU_IP_TUNNELS=y
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
+CONFIG_INET_ESP_OFFLOAD=m
CONFIG_INET_IPCOMP=m
CONFIG_INET_XFRM_MODE_TRANSPORT=m
CONFIG_INET_XFRM_MODE_TUNNEL=m
@@ -64,6 +66,7 @@
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
+CONFIG_INET6_ESP_OFFLOAD=m
CONFIG_INET6_IPCOMP=m
CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
@@ -94,6 +97,7 @@
CONFIG_NFT_CT=m
CONFIG_NFT_SET_RBTREE=m
CONFIG_NFT_SET_HASH=m
+CONFIG_NFT_SET_BITMAP=m
CONFIG_NFT_COUNTER=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
@@ -291,6 +295,8 @@
CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
+CONFIG_PSAMPLE=m
+CONFIG_NET_IFE=m
CONFIG_NET_DEVLINK=m
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -349,6 +355,7 @@
CONFIG_MACVLAN=m
CONFIG_MACVTAP=m
CONFIG_IPVLAN=m
+CONFIG_IPVTAP=m
CONFIG_VXLAN=m
CONFIG_GENEVE=m
CONFIG_GTP=m
@@ -359,6 +366,7 @@
# CONFIG_NET_VENDOR_ALACRITECH is not set
# CONFIG_NET_VENDOR_AMAZON is not set
CONFIG_SUN3LANCE=y
+# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
@@ -375,7 +383,6 @@
# CONFIG_NET_VENDOR_SEEQ is not set
# CONFIG_NET_VENDOR_SOLARFLARE is not set
# CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
@@ -517,6 +524,8 @@
CONFIG_DLM=m
# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
CONFIG_MAGIC_SYSRQ=y
+CONFIG_WW_MUTEX_SELFTEST=m
+CONFIG_ATOMIC64_SELFTEST=m
CONFIG_ASYNC_RAID6_TEST=m
CONFIG_TEST_HEXDUMP=m
CONFIG_TEST_STRING_HELPERS=m
@@ -547,6 +556,7 @@
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_CMAC=m
CONFIG_CRYPTO_XCBC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_MICHAEL_MIC=m
@@ -558,6 +568,7 @@
CONFIG_CRYPTO_SHA3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_ANUBIS=m
CONFIG_CRYPTO_BLOWFISH=m
CONFIG_CRYPTO_CAMELLIA=m
@@ -582,4 +593,5 @@
CONFIG_CRYPTO_USER_API_RNG=m
CONFIG_CRYPTO_USER_API_AEAD=m
# CONFIG_CRYPTO_HW is not set
+CONFIG_CRC32_SELFTEST=m
CONFIG_XZ_DEC_TEST=m
diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h
index b4a9b0d..dda58cf 100644
--- a/arch/m68k/include/asm/bitops.h
+++ b/arch/m68k/include/asm/bitops.h
@@ -148,7 +148,7 @@ static inline void bfchg_mem_change_bit(int nr, volatile unsigned long *vaddr)
#define __change_bit(nr, vaddr) change_bit(nr, vaddr)
-static inline int test_bit(int nr, const unsigned long *vaddr)
+static inline int test_bit(int nr, const volatile unsigned long *vaddr)
{
return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
}
diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h
index a857d82..aab1edd 100644
--- a/arch/m68k/include/asm/unistd.h
+++ b/arch/m68k/include/asm/unistd.h
@@ -4,7 +4,7 @@
#include <uapi/asm/unistd.h>
-#define NR_syscalls 379
+#define NR_syscalls 380
#define __ARCH_WANT_OLD_READDIR
#define __ARCH_WANT_OLD_STAT
diff --git a/arch/m68k/include/uapi/asm/unistd.h b/arch/m68k/include/uapi/asm/unistd.h
index 9fe674bf..25589f5 100644
--- a/arch/m68k/include/uapi/asm/unistd.h
+++ b/arch/m68k/include/uapi/asm/unistd.h
@@ -384,5 +384,6 @@
#define __NR_copy_file_range 376
#define __NR_preadv2 377
#define __NR_pwritev2 378
+#define __NR_statx 379
#endif /* _UAPI_ASM_M68K_UNISTD_H_ */
diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S
index d6fd6d9..8c9fcfa 100644
--- a/arch/m68k/kernel/syscalltable.S
+++ b/arch/m68k/kernel/syscalltable.S
@@ -399,3 +399,4 @@
.long sys_copy_file_range
.long sys_preadv2
.long sys_pwritev2
+ .long sys_statx
diff --git a/arch/metag/include/asm/pgtable.h b/arch/metag/include/asm/pgtable.h
index ffa3a3a..0c151e5 100644
--- a/arch/metag/include/asm/pgtable.h
+++ b/arch/metag/include/asm/pgtable.h
@@ -6,6 +6,7 @@
#define _METAG_PGTABLE_H
#include <asm/pgtable-bits.h>
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
/* Invalid regions on Meta: 0x00000000-0x001FFFFF and 0xFFFF0000-0xFFFFFFFF */
diff --git a/arch/metag/kernel/ptrace.c b/arch/metag/kernel/ptrace.c
index 5fd16ee..e615603 100644
--- a/arch/metag/kernel/ptrace.c
+++ b/arch/metag/kernel/ptrace.c
@@ -26,6 +26,16 @@
* user_regset definitions.
*/
+static unsigned long user_txstatus(const struct pt_regs *regs)
+{
+ unsigned long data = (unsigned long)regs->ctx.Flags;
+
+ if (regs->ctx.SaveMask & TBICTX_CBUF_BIT)
+ data |= USER_GP_REGS_STATUS_CATCH_BIT;
+
+ return data;
+}
+
int metag_gp_regs_copyout(const struct pt_regs *regs,
unsigned int pos, unsigned int count,
void *kbuf, void __user *ubuf)
@@ -64,9 +74,7 @@ int metag_gp_regs_copyout(const struct pt_regs *regs,
if (ret)
goto out;
/* TXSTATUS */
- data = (unsigned long)regs->ctx.Flags;
- if (regs->ctx.SaveMask & TBICTX_CBUF_BIT)
- data |= USER_GP_REGS_STATUS_CATCH_BIT;
+ data = user_txstatus(regs);
ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
&data, 4*25, 4*26);
if (ret)
@@ -121,6 +129,7 @@ int metag_gp_regs_copyin(struct pt_regs *regs,
if (ret)
goto out;
/* TXSTATUS */
+ data = user_txstatus(regs);
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
&data, 4*25, 4*26);
if (ret)
@@ -246,6 +255,8 @@ int metag_rp_state_copyin(struct pt_regs *regs,
unsigned long long *ptr;
int ret, i;
+ if (count < 4*13)
+ return -EINVAL;
/* Read the entire pipeline before making any changes */
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
&rp, 0, 4*13);
@@ -305,7 +316,7 @@ static int metag_tls_set(struct task_struct *target,
const void *kbuf, const void __user *ubuf)
{
int ret;
- void __user *tls;
+ void __user *tls = target->thread.tls_ptr;
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1);
if (ret)
diff --git a/arch/microblaze/include/asm/page.h b/arch/microblaze/include/asm/page.h
index fd85087..d506bb0 100644
--- a/arch/microblaze/include/asm/page.h
+++ b/arch/microblaze/include/asm/page.h
@@ -95,7 +95,8 @@ typedef struct { unsigned long pgd; } pgd_t;
# else /* CONFIG_MMU */
typedef struct { unsigned long ste[64]; } pmd_t;
typedef struct { pmd_t pue[1]; } pud_t;
-typedef struct { pud_t pge[1]; } pgd_t;
+typedef struct { pud_t p4e[1]; } p4d_t;
+typedef struct { p4d_t pge[1]; } pgd_t;
# endif /* CONFIG_MMU */
# define pte_val(x) ((x).pte)
diff --git a/arch/mips/cavium-octeon/cpu.c b/arch/mips/cavium-octeon/cpu.c
index a5b4279..036d56c 100644
--- a/arch/mips/cavium-octeon/cpu.c
+++ b/arch/mips/cavium-octeon/cpu.c
@@ -10,7 +10,9 @@
#include <linux/irqflags.h>
#include <linux/notifier.h>
#include <linux/prefetch.h>
+#include <linux/ptrace.h>
#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
#include <asm/cop2.h>
#include <asm/current.h>
diff --git a/arch/mips/cavium-octeon/crypto/octeon-crypto.c b/arch/mips/cavium-octeon/crypto/octeon-crypto.c
index 4d22365..cfb4a14 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-crypto.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-crypto.c
@@ -9,6 +9,7 @@
#include <asm/cop2.h>
#include <linux/export.h>
#include <linux/interrupt.h>
+#include <linux/sched/task_stack.h>
#include "octeon-crypto.h"
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index 4b94b7f..3de7865 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -12,6 +12,7 @@
#include <linux/kernel_stat.h>
#include <linux/sched.h>
#include <linux/sched/hotplug.h>
+#include <linux/sched/task_stack.h>
#include <linux/init.h>
#include <linux/export.h>
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index 321752b..f94455f 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -12,6 +12,7 @@
#include <linux/sched.h>
#include <linux/sched/task_stack.h>
+#include <linux/ptrace.h>
#include <linux/thread_info.h>
#include <linux/bitops.h>
diff --git a/arch/mips/include/asm/pgtable-32.h b/arch/mips/include/asm/pgtable-32.h
index d21f3da..6f94bed 100644
--- a/arch/mips/include/asm/pgtable-32.h
+++ b/arch/mips/include/asm/pgtable-32.h
@@ -16,6 +16,7 @@
#include <asm/cachectl.h>
#include <asm/fixmap.h>
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
extern int temp_tlb_entry;
diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h
index 514cbc0..130a2a6 100644
--- a/arch/mips/include/asm/pgtable-64.h
+++ b/arch/mips/include/asm/pgtable-64.h
@@ -17,6 +17,7 @@
#include <asm/cachectl.h>
#include <asm/fixmap.h>
+#define __ARCH_USE_5LEVEL_HACK
#if defined(CONFIG_PAGE_SIZE_64KB) && !defined(CONFIG_MIPS_VA_BITS_48)
#include <asm-generic/pgtable-nopmd.h>
#else
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index 566ecdc..3418ec9 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -110,4 +110,10 @@
#define SCM_TIMESTAMPING_OPT_STATS 54
+#define SO_MEMINFO 55
+
+#define SO_INCOMING_NAPI_ID 56
+
+#define SO_COOKIE 57
+
#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 3396012..6931fe7 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -456,7 +456,8 @@ static int fpr_set(struct task_struct *target,
&target->thread.fpu,
0, sizeof(elf_fpregset_t));
- for (i = 0; i < NUM_FPU_REGS; i++) {
+ BUILD_BUG_ON(sizeof(fpr_val) != sizeof(elf_fpreg_t));
+ for (i = 0; i < NUM_FPU_REGS && count >= sizeof(elf_fpreg_t); i++) {
err = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
&fpr_val, i * sizeof(elf_fpreg_t),
(i + 1) * sizeof(elf_fpreg_t));
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index 3daa2ca..1b070a7 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -11,6 +11,7 @@
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/sched/hotplug.h>
+#include <linux/sched/task_stack.h>
#include <linux/mm.h>
#include <linux/delay.h>
#include <linux/smp.h>
diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c
index e077ea3..e398cbc 100644
--- a/arch/mips/kernel/smp-mt.c
+++ b/arch/mips/kernel/smp-mt.c
@@ -23,6 +23,7 @@
#include <linux/interrupt.h>
#include <linux/irqchip/mips-gic.h>
#include <linux/compiler.h>
+#include <linux/sched/task_stack.h>
#include <linux/smp.h>
#include <linux/atomic.h>
diff --git a/arch/mips/loongson64/loongson-3/cop2-ex.c b/arch/mips/loongson64/loongson-3/cop2-ex.c
index ea13764..621d6af 100644
--- a/arch/mips/loongson64/loongson-3/cop2-ex.c
+++ b/arch/mips/loongson64/loongson-3/cop2-ex.c
@@ -13,6 +13,7 @@
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/notifier.h>
+#include <linux/ptrace.h>
#include <asm/fpu.h>
#include <asm/cop2.h>
diff --git a/arch/mips/netlogic/common/smp.c b/arch/mips/netlogic/common/smp.c
index 10d86d5..bddf1ef 100644
--- a/arch/mips/netlogic/common/smp.c
+++ b/arch/mips/netlogic/common/smp.c
@@ -35,6 +35,7 @@
#include <linux/kernel.h>
#include <linux/delay.h>
#include <linux/init.h>
+#include <linux/sched/task_stack.h>
#include <linux/smp.h>
#include <linux/irq.h>
diff --git a/arch/mips/netlogic/xlp/cop2-ex.c b/arch/mips/netlogic/xlp/cop2-ex.c
index 52bc5de..21e439b 100644
--- a/arch/mips/netlogic/xlp/cop2-ex.c
+++ b/arch/mips/netlogic/xlp/cop2-ex.c
@@ -9,11 +9,14 @@
* Copyright (C) 2009 Wind River Systems,
* written by Ralf Baechle <ralf@linux-mips.org>
*/
+#include <linux/capability.h>
#include <linux/init.h>
#include <linux/irqflags.h>
#include <linux/notifier.h>
#include <linux/prefetch.h>
+#include <linux/ptrace.h>
#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
#include <asm/cop2.h>
#include <asm/current.h>
diff --git a/arch/mips/sgi-ip22/ip28-berr.c b/arch/mips/sgi-ip22/ip28-berr.c
index 1f2a5bc..75460e1 100644
--- a/arch/mips/sgi-ip22/ip28-berr.c
+++ b/arch/mips/sgi-ip22/ip28-berr.c
@@ -9,6 +9,7 @@
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/sched/debug.h>
+#include <linux/sched/signal.h>
#include <linux/seq_file.h>
#include <asm/addrspace.h>
diff --git a/arch/mips/sgi-ip27/ip27-berr.c b/arch/mips/sgi-ip27/ip27-berr.c
index d12879e..83efe03 100644
--- a/arch/mips/sgi-ip27/ip27-berr.c
+++ b/arch/mips/sgi-ip27/ip27-berr.c
@@ -12,7 +12,9 @@
#include <linux/signal.h> /* for SIGBUS */
#include <linux/sched.h> /* schow_regs(), force_sig() */
#include <linux/sched/debug.h>
+#include <linux/sched/signal.h>
+#include <asm/ptrace.h>
#include <asm/sn/addrs.h>
#include <asm/sn/arch.h>
#include <asm/sn/sn0/hub.h>
diff --git a/arch/mips/sgi-ip27/ip27-smp.c b/arch/mips/sgi-ip27/ip27-smp.c
index f5ed45e..4cd47d2 100644
--- a/arch/mips/sgi-ip27/ip27-smp.c
+++ b/arch/mips/sgi-ip27/ip27-smp.c
@@ -8,10 +8,13 @@
*/
#include <linux/init.h>
#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
#include <linux/topology.h>
#include <linux/nodemask.h>
+
#include <asm/page.h>
#include <asm/processor.h>
+#include <asm/ptrace.h>
#include <asm/sn/arch.h>
#include <asm/sn/gda.h>
#include <asm/sn/intr.h>
diff --git a/arch/mips/sgi-ip32/ip32-berr.c b/arch/mips/sgi-ip32/ip32-berr.c
index 57d8c74..c1f12a9 100644
--- a/arch/mips/sgi-ip32/ip32-berr.c
+++ b/arch/mips/sgi-ip32/ip32-berr.c
@@ -11,6 +11,7 @@
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/sched/debug.h>
+#include <linux/sched/signal.h>
#include <asm/traps.h>
#include <linux/uaccess.h>
#include <asm/addrspace.h>
diff --git a/arch/mips/sgi-ip32/ip32-reset.c b/arch/mips/sgi-ip32/ip32-reset.c
index 8bd415c..b3b442d 100644
--- a/arch/mips/sgi-ip32/ip32-reset.c
+++ b/arch/mips/sgi-ip32/ip32-reset.c
@@ -13,6 +13,7 @@
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sched.h>
+#include <linux/sched/signal.h>
#include <linux/notifier.h>
#include <linux/delay.h>
#include <linux/rtc/ds1685.h>
diff --git a/arch/mn10300/include/asm/page.h b/arch/mn10300/include/asm/page.h
index 3810a6f..dfe730a 100644
--- a/arch/mn10300/include/asm/page.h
+++ b/arch/mn10300/include/asm/page.h
@@ -57,6 +57,7 @@ typedef struct page *pgtable_t;
#define __pgd(x) ((pgd_t) { (x) })
#define __pgprot(x) ((pgprot_t) { (x) })
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
#endif /* !__ASSEMBLY__ */
diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h
index 0e12527..4526e92 100644
--- a/arch/mn10300/include/uapi/asm/socket.h
+++ b/arch/mn10300/include/uapi/asm/socket.h
@@ -92,4 +92,10 @@
#define SCM_TIMESTAMPING_OPT_STATS 54
+#define SO_MEMINFO 55
+
+#define SO_INCOMING_NAPI_ID 56
+
+#define SO_COOKIE 57
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/nios2/include/asm/pgtable.h b/arch/nios2/include/asm/pgtable.h
index 298393c..db4f7d1 100644
--- a/arch/nios2/include/asm/pgtable.h
+++ b/arch/nios2/include/asm/pgtable.h
@@ -22,6 +22,7 @@
#include <asm/tlbflush.h>
#include <asm/pgtable-bits.h>
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
#define FIRST_USER_ADDRESS 0UL
diff --git a/arch/nios2/kernel/prom.c b/arch/nios2/kernel/prom.c
index 367c542..3901b80 100644
--- a/arch/nios2/kernel/prom.c
+++ b/arch/nios2/kernel/prom.c
@@ -48,6 +48,13 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
return alloc_bootmem_align(size, align);
}
+int __init early_init_dt_reserve_memory_arch(phys_addr_t base, phys_addr_t size,
+ bool nomap)
+{
+ reserve_bootmem(base, size, BOOTMEM_DEFAULT);
+ return 0;
+}
+
void __init early_init_devtree(void *params)
{
__be32 *dtb = (u32 *)__dtb_start;
diff --git a/arch/nios2/kernel/setup.c b/arch/nios2/kernel/setup.c
index 6e57ffa..6044d9b 100644
--- a/arch/nios2/kernel/setup.c
+++ b/arch/nios2/kernel/setup.c
@@ -201,6 +201,9 @@ void __init setup_arch(char **cmdline_p)
}
#endif /* CONFIG_BLK_DEV_INITRD */
+ early_init_fdt_reserve_self();
+ early_init_fdt_scan_reserved_mem();
+
unflatten_and_copy_device_tree();
setup_cpuinfo();
diff --git a/arch/openrisc/include/asm/cmpxchg.h b/arch/openrisc/include/asm/cmpxchg.h
index 5fcb9ac..f0a5d8b 100644
--- a/arch/openrisc/include/asm/cmpxchg.h
+++ b/arch/openrisc/include/asm/cmpxchg.h
@@ -77,7 +77,11 @@ static inline unsigned long __xchg(unsigned long val, volatile void *ptr,
return val;
}
-#define xchg(ptr, with) \
- ((typeof(*(ptr)))__xchg((unsigned long)(with), (ptr), sizeof(*(ptr))))
+#define xchg(ptr, with) \
+ ({ \
+ (__typeof__(*(ptr))) __xchg((unsigned long)(with), \
+ (ptr), \
+ sizeof(*(ptr))); \
+ })
#endif /* __ASM_OPENRISC_CMPXCHG_H */
diff --git a/arch/openrisc/include/asm/pgtable.h b/arch/openrisc/include/asm/pgtable.h
index 3567aa7..ff97374 100644
--- a/arch/openrisc/include/asm/pgtable.h
+++ b/arch/openrisc/include/asm/pgtable.h
@@ -25,6 +25,7 @@
#ifndef __ASM_OPENRISC_PGTABLE_H
#define __ASM_OPENRISC_PGTABLE_H
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
#ifndef __ASSEMBLY__
diff --git a/arch/openrisc/include/asm/uaccess.h b/arch/openrisc/include/asm/uaccess.h
index 140faa1..1311e6b 100644
--- a/arch/openrisc/include/asm/uaccess.h
+++ b/arch/openrisc/include/asm/uaccess.h
@@ -211,7 +211,7 @@ do { \
case 1: __get_user_asm(x, ptr, retval, "l.lbz"); break; \
case 2: __get_user_asm(x, ptr, retval, "l.lhz"); break; \
case 4: __get_user_asm(x, ptr, retval, "l.lwz"); break; \
- case 8: __get_user_asm2(x, ptr, retval); \
+ case 8: __get_user_asm2(x, ptr, retval); break; \
default: (x) = __get_user_bad(); \
} \
} while (0)
diff --git a/arch/openrisc/kernel/or32_ksyms.c b/arch/openrisc/kernel/or32_ksyms.c
index 5c4695d..ee3e604 100644
--- a/arch/openrisc/kernel/or32_ksyms.c
+++ b/arch/openrisc/kernel/or32_ksyms.c
@@ -30,6 +30,7 @@
#include <asm/hardirq.h>
#include <asm/delay.h>
#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
#define DECLARE_EXPORT(name) extern void name(void); EXPORT_SYMBOL(name)
@@ -42,6 +43,9 @@ DECLARE_EXPORT(__muldi3);
DECLARE_EXPORT(__ashrdi3);
DECLARE_EXPORT(__ashldi3);
DECLARE_EXPORT(__lshrdi3);
+DECLARE_EXPORT(__ucmpdi2);
+EXPORT_SYMBOL(empty_zero_page);
EXPORT_SYMBOL(__copy_tofrom_user);
+EXPORT_SYMBOL(__clear_user);
EXPORT_SYMBOL(memset);
diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c
index 828a291..f8da545 100644
--- a/arch/openrisc/kernel/process.c
+++ b/arch/openrisc/kernel/process.c
@@ -90,6 +90,7 @@ void arch_cpu_idle(void)
}
void (*pm_power_off) (void) = machine_power_off;
+EXPORT_SYMBOL(pm_power_off);
/*
* When a process does an "exec", machine state like FPU and debug
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index 19c9c3c..c7e15cc 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -43,28 +43,9 @@ static inline void flush_kernel_dcache_page(struct page *page)
#define flush_kernel_dcache_range(start,size) \
flush_kernel_dcache_range_asm((start), (start)+(size));
-/* vmap range flushes and invalidates. Architecturally, we don't need
- * the invalidate, because the CPU should refuse to speculate once an
- * area has been flushed, so invalidate is left empty */
-static inline void flush_kernel_vmap_range(void *vaddr, int size)
-{
- unsigned long start = (unsigned long)vaddr;
- flush_kernel_dcache_range_asm(start, start + size);
-}
-static inline void invalidate_kernel_vmap_range(void *vaddr, int size)
-{
- unsigned long start = (unsigned long)vaddr;
- void *cursor = vaddr;
-
- for ( ; cursor < vaddr + size; cursor += PAGE_SIZE) {
- struct page *page = vmalloc_to_page(cursor);
-
- if (test_and_clear_bit(PG_dcache_dirty, &page->flags))
- flush_kernel_dcache_page(page);
- }
- flush_kernel_dcache_range_asm(start, start + size);
-}
+void flush_kernel_vmap_range(void *vaddr, int size);
+void invalidate_kernel_vmap_range(void *vaddr, int size);
#define flush_cache_vmap(start, end) flush_cache_all()
#define flush_cache_vunmap(start, end) flush_cache_all()
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index fb4382c..8442727 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -32,7 +32,8 @@
* that put_user is the same as __put_user, etc.
*/
-#define access_ok(type, uaddr, size) (1)
+#define access_ok(type, uaddr, size) \
+ ( (uaddr) == (uaddr) )
#define put_user __put_user
#define get_user __get_user
@@ -64,6 +65,15 @@ struct exception_table_entry {
".previous\n"
/*
+ * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() creates a special exception table entry
+ * (with lowest bit set) for which the fault handler in fixup_exception() will
+ * load -EFAULT into %r8 for a read or write fault, and zeroes the target
+ * register in case of a read fault in get_user().
+ */
+#define ASM_EXCEPTIONTABLE_ENTRY_EFAULT( fault_addr, except_addr )\
+ ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr + 1)
+
+/*
* The page fault handler stores, in a per-cpu area, the following information
* if a fixup routine is available.
*/
@@ -90,7 +100,7 @@ struct exception_data {
#define __get_user(x, ptr) \
({ \
register long __gu_err __asm__ ("r8") = 0; \
- register long __gu_val __asm__ ("r9") = 0; \
+ register long __gu_val; \
\
load_sr2(); \
switch (sizeof(*(ptr))) { \
@@ -106,22 +116,23 @@ struct exception_data {
})
#define __get_user_asm(ldx, ptr) \
- __asm__("\n1:\t" ldx "\t0(%%sr2,%2),%0\n\t" \
- ASM_EXCEPTIONTABLE_ENTRY(1b, fixup_get_user_skip_1)\
+ __asm__("1: " ldx " 0(%%sr2,%2),%0\n" \
+ "9:\n" \
+ ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \
: "=r"(__gu_val), "=r"(__gu_err) \
- : "r"(ptr), "1"(__gu_err) \
- : "r1");
+ : "r"(ptr), "1"(__gu_err));
#if !defined(CONFIG_64BIT)
#define __get_user_asm64(ptr) \
- __asm__("\n1:\tldw 0(%%sr2,%2),%0" \
- "\n2:\tldw 4(%%sr2,%2),%R0\n\t" \
- ASM_EXCEPTIONTABLE_ENTRY(1b, fixup_get_user_skip_2)\
- ASM_EXCEPTIONTABLE_ENTRY(2b, fixup_get_user_skip_1)\
+ __asm__(" copy %%r0,%R0\n" \
+ "1: ldw 0(%%sr2,%2),%0\n" \
+ "2: ldw 4(%%sr2,%2),%R0\n" \
+ "9:\n" \
+ ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \
+ ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b) \
: "=r"(__gu_val), "=r"(__gu_err) \
- : "r"(ptr), "1"(__gu_err) \
- : "r1");
+ : "r"(ptr), "1"(__gu_err));
#endif /* !defined(CONFIG_64BIT) */
@@ -147,32 +158,31 @@ struct exception_data {
* The "__put_user/kernel_asm()" macros tell gcc they read from memory
* instead of writing. This is because they do not write to any memory
* gcc knows about, so there are no aliasing issues. These macros must
- * also be aware that "fixup_put_user_skip_[12]" are executed in the
- * context of the fault, and any registers used there must be listed
- * as clobbers. In this case only "r1" is used by the current routines.
- * r8/r9 are already listed as err/val.
+ * also be aware that fixups are executed in the context of the fault,
+ * and any registers used there must be listed as clobbers.
+ * r8 is already listed as err.
*/
#define __put_user_asm(stx, x, ptr) \
__asm__ __volatile__ ( \
- "\n1:\t" stx "\t%2,0(%%sr2,%1)\n\t" \
- ASM_EXCEPTIONTABLE_ENTRY(1b, fixup_put_user_skip_1)\
+ "1: " stx " %2,0(%%sr2,%1)\n" \
+ "9:\n" \
+ ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \
: "=r"(__pu_err) \
- : "r"(ptr), "r"(x), "0"(__pu_err) \
- : "r1")
+ : "r"(ptr), "r"(x), "0"(__pu_err))
#if !defined(CONFIG_64BIT)
#define __put_user_asm64(__val, ptr) do { \
__asm__ __volatile__ ( \
- "\n1:\tstw %2,0(%%sr2,%1)" \
- "\n2:\tstw %R2,4(%%sr2,%1)\n\t" \
- ASM_EXCEPTIONTABLE_ENTRY(1b, fixup_put_user_skip_2)\
- ASM_EXCEPTIONTABLE_ENTRY(2b, fixup_put_user_skip_1)\
+ "1: stw %2,0(%%sr2,%1)\n" \
+ "2: stw %R2,4(%%sr2,%1)\n" \
+ "9:\n" \
+ ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \
+ ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b) \
: "=r"(__pu_err) \
- : "r"(ptr), "r"(__val), "0"(__pu_err) \
- : "r1"); \
+ : "r"(ptr), "r"(__val), "0"(__pu_err)); \
} while (0)
#endif /* !defined(CONFIG_64BIT) */
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index 7a109b7..5147018 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -91,4 +91,10 @@
#define SCM_TIMESTAMPING_OPT_STATS 0x402F
+#define SO_MEMINFO 0x4030
+
+#define SO_INCOMING_NAPI_ID 0x4031
+
+#define SO_COOKIE 0x4032
+
#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h
index 6b0741e..667c994 100644
--- a/arch/parisc/include/uapi/asm/unistd.h
+++ b/arch/parisc/include/uapi/asm/unistd.h
@@ -362,8 +362,9 @@
#define __NR_copy_file_range (__NR_Linux + 346)
#define __NR_preadv2 (__NR_Linux + 347)
#define __NR_pwritev2 (__NR_Linux + 348)
+#define __NR_statx (__NR_Linux + 349)
-#define __NR_Linux_syscalls (__NR_pwritev2 + 1)
+#define __NR_Linux_syscalls (__NR_statx + 1)
#define __IGNORE_select /* newselect */
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 0dc72d5..c32a090 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -616,3 +616,25 @@ flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long
__flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
}
}
+
+void flush_kernel_vmap_range(void *vaddr, int size)
+{
+ unsigned long start = (unsigned long)vaddr;
+
+ if ((unsigned long)size > parisc_cache_flush_threshold)
+ flush_data_cache();
+ else
+ flush_kernel_dcache_range_asm(start, start + size);
+}
+EXPORT_SYMBOL(flush_kernel_vmap_range);
+
+void invalidate_kernel_vmap_range(void *vaddr, int size)
+{
+ unsigned long start = (unsigned long)vaddr;
+
+ if ((unsigned long)size > parisc_cache_flush_threshold)
+ flush_data_cache();
+ else
+ flush_kernel_dcache_range_asm(start, start + size);
+}
+EXPORT_SYMBOL(invalidate_kernel_vmap_range);
diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c
index a0ecdb4..c66c943 100644
--- a/arch/parisc/kernel/module.c
+++ b/arch/parisc/kernel/module.c
@@ -620,6 +620,10 @@ int apply_relocate_add(Elf_Shdr *sechdrs,
*/
*loc = fsel(val, addend);
break;
+ case R_PARISC_SECREL32:
+ /* 32-bit section relative address. */
+ *loc = fsel(val, addend);
+ break;
case R_PARISC_DPREL21L:
/* left 21 bit of relative address */
val = lrsel(val - dp, addend);
@@ -807,6 +811,10 @@ int apply_relocate_add(Elf_Shdr *sechdrs,
*/
*loc = fsel(val, addend);
break;
+ case R_PARISC_SECREL32:
+ /* 32-bit section relative address. */
+ *loc = fsel(val, addend);
+ break;
case R_PARISC_FPTR64:
/* 64-bit function address */
if(in_local(me, (void *)(val + addend))) {
diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c
index 7484b3d..c6d6272 100644
--- a/arch/parisc/kernel/parisc_ksyms.c
+++ b/arch/parisc/kernel/parisc_ksyms.c
@@ -47,16 +47,6 @@ EXPORT_SYMBOL(__cmpxchg_u64);
EXPORT_SYMBOL(lclear_user);
EXPORT_SYMBOL(lstrnlen_user);
-/* Global fixups - defined as int to avoid creation of function pointers */
-extern int fixup_get_user_skip_1;
-extern int fixup_get_user_skip_2;
-extern int fixup_put_user_skip_1;
-extern int fixup_put_user_skip_2;
-EXPORT_SYMBOL(fixup_get_user_skip_1);
-EXPORT_SYMBOL(fixup_get_user_skip_2);
-EXPORT_SYMBOL(fixup_put_user_skip_1);
-EXPORT_SYMBOL(fixup_put_user_skip_2);
-
#ifndef CONFIG_64BIT
/* Needed so insmod can set dp value */
extern int $global$;
diff --git a/arch/parisc/kernel/perf.c b/arch/parisc/kernel/perf.c
index e282a51..6017a5a 100644
--- a/arch/parisc/kernel/perf.c
+++ b/arch/parisc/kernel/perf.c
@@ -39,7 +39,7 @@
* the PDC INTRIGUE calls. This is done to eliminate bugs introduced
* in various PDC revisions. The code is much more maintainable
* and reliable this way vs having to debug on every version of PDC
- * on every box.
+ * on every box.
*/
#include <linux/capability.h>
@@ -195,8 +195,8 @@ static int perf_config(uint32_t *image_ptr);
static int perf_release(struct inode *inode, struct file *file);
static int perf_open(struct inode *inode, struct file *file);
static ssize_t perf_read(struct file *file, char __user *buf, size_t cnt, loff_t *ppos);
-static ssize_t perf_write(struct file *file, const char __user *buf, size_t count,
- loff_t *ppos);
+static ssize_t perf_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos);
static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
static void perf_start_counters(void);
static int perf_stop_counters(uint32_t *raddr);
@@ -222,7 +222,7 @@ extern void perf_intrigue_disable_perf_counters (void);
/*
* configure:
*
- * Configure the cpu with a given data image. First turn off the counters,
+ * Configure the cpu with a given data image. First turn off the counters,
* then download the image, then turn the counters back on.
*/
static int perf_config(uint32_t *image_ptr)
@@ -234,7 +234,7 @@ static int perf_config(uint32_t *image_ptr)
error = perf_stop_counters(raddr);
if (error != 0) {
printk("perf_config: perf_stop_counters = %ld\n", error);
- return -EINVAL;
+ return -EINVAL;
}
printk("Preparing to write image\n");
@@ -242,7 +242,7 @@ printk("Preparing to write image\n");
error = perf_write_image((uint64_t *)image_ptr);
if (error != 0) {
printk("perf_config: DOWNLOAD = %ld\n", error);
- return -EINVAL;
+ return -EINVAL;
}
printk("Preparing to start counters\n");
@@ -254,7 +254,7 @@ printk("Preparing to start counters\n");
}
/*
- * Open the device and initialize all of its memory. The device is only
+ * Open the device and initialize all of its memory. The device is only
* opened once, but can be "queried" by multiple processes that know its
* file descriptor.
*/
@@ -298,19 +298,19 @@ static ssize_t perf_read(struct file *file, char __user *buf, size_t cnt, loff_t
* called on the processor that the download should happen
* on.
*/
-static ssize_t perf_write(struct file *file, const char __user *buf, size_t count,
- loff_t *ppos)
+static ssize_t perf_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
{
size_t image_size;
uint32_t image_type;
uint32_t interface_type;
uint32_t test;
- if (perf_processor_interface == ONYX_INTF)
+ if (perf_processor_interface == ONYX_INTF)
image_size = PCXU_IMAGE_SIZE;
- else if (perf_processor_interface == CUDA_INTF)
+ else if (perf_processor_interface == CUDA_INTF)
image_size = PCXW_IMAGE_SIZE;
- else
+ else
return -EFAULT;
if (!capable(CAP_SYS_ADMIN))
@@ -330,22 +330,22 @@ static ssize_t perf_write(struct file *file, const char __user *buf, size_t coun
/* First check the machine type is correct for
the requested image */
- if (((perf_processor_interface == CUDA_INTF) &&
- (interface_type != CUDA_INTF)) ||
- ((perf_processor_interface == ONYX_INTF) &&
- (interface_type != ONYX_INTF)))
+ if (((perf_processor_interface == CUDA_INTF) &&
+ (interface_type != CUDA_INTF)) ||
+ ((perf_processor_interface == ONYX_INTF) &&
+ (interface_type != ONYX_INTF)))
return -EINVAL;
/* Next check to make sure the requested image
is valid */
- if (((interface_type == CUDA_INTF) &&
+ if (((interface_type == CUDA_INTF) &&
(test >= MAX_CUDA_IMAGES)) ||
- ((interface_type == ONYX_INTF) &&
- (test >= MAX_ONYX_IMAGES)))
+ ((interface_type == ONYX_INTF) &&
+ (test >= MAX_ONYX_IMAGES)))
return -EINVAL;
/* Copy the image into the processor */
- if (interface_type == CUDA_INTF)
+ if (interface_type == CUDA_INTF)
return perf_config(cuda_images[test]);
else
return perf_config(onyx_images[test]);
@@ -359,7 +359,7 @@ static ssize_t perf_write(struct file *file, const char __user *buf, size_t coun
static void perf_patch_images(void)
{
#if 0 /* FIXME!! */
-/*
+/*
* NOTE: this routine is VERY specific to the current TLB image.
* If the image is changed, this routine might also need to be changed.
*/
@@ -367,9 +367,9 @@ static void perf_patch_images(void)
extern void $i_dtlb_miss_2_0();
extern void PA2_0_iva();
- /*
+ /*
* We can only use the lower 32-bits, the upper 32-bits should be 0
- * anyway given this is in the kernel
+ * anyway given this is in the kernel
*/
uint32_t itlb_addr = (uint32_t)&($i_itlb_miss_2_0);
uint32_t dtlb_addr = (uint32_t)&($i_dtlb_miss_2_0);
@@ -377,21 +377,21 @@ static void perf_patch_images(void)
if (perf_processor_interface == ONYX_INTF) {
/* clear last 2 bytes */
- onyx_images[TLBMISS][15] &= 0xffffff00;
+ onyx_images[TLBMISS][15] &= 0xffffff00;
/* set 2 bytes */
onyx_images[TLBMISS][15] |= (0x000000ff&((dtlb_addr) >> 24));
onyx_images[TLBMISS][16] = (dtlb_addr << 8)&0xffffff00;
onyx_images[TLBMISS][17] = itlb_addr;
/* clear last 2 bytes */
- onyx_images[TLBHANDMISS][15] &= 0xffffff00;
+ onyx_images[TLBHANDMISS][15] &= 0xffffff00;
/* set 2 bytes */
onyx_images[TLBHANDMISS][15] |= (0x000000ff&((dtlb_addr) >> 24));
onyx_images[TLBHANDMISS][16] = (dtlb_addr << 8)&0xffffff00;
onyx_images[TLBHANDMISS][17] = itlb_addr;
/* clear last 2 bytes */
- onyx_images[BIG_CPI][15] &= 0xffffff00;
+ onyx_images[BIG_CPI][15] &= 0xffffff00;
/* set 2 bytes */
onyx_images[BIG_CPI][15] |= (0x000000ff&((dtlb_addr) >> 24));
onyx_images[BIG_CPI][16] = (dtlb_addr << 8)&0xffffff00;
@@ -404,24 +404,24 @@ static void perf_patch_images(void)
} else if (perf_processor_interface == CUDA_INTF) {
/* Cuda interface */
- cuda_images[TLBMISS][16] =
+ cuda_images[TLBMISS][16] =
(cuda_images[TLBMISS][16]&0xffff0000) |
((dtlb_addr >> 8)&0x0000ffff);
- cuda_images[TLBMISS][17] =
+ cuda_images[TLBMISS][17] =
((dtlb_addr << 24)&0xff000000) | ((itlb_addr >> 16)&0x000000ff);
cuda_images[TLBMISS][18] = (itlb_addr << 16)&0xffff0000;
- cuda_images[TLBHANDMISS][16] =
+ cuda_images[TLBHANDMISS][16] =
(cuda_images[TLBHANDMISS][16]&0xffff0000) |
((dtlb_addr >> 8)&0x0000ffff);
- cuda_images[TLBHANDMISS][17] =
+ cuda_images[TLBHANDMISS][17] =
((dtlb_addr << 24)&0xff000000) | ((itlb_addr >> 16)&0x000000ff);
cuda_images[TLBHANDMISS][18] = (itlb_addr << 16)&0xffff0000;
- cuda_images[BIG_CPI][16] =
+ cuda_images[BIG_CPI][16] =
(cuda_images[BIG_CPI][16]&0xffff0000) |
((dtlb_addr >> 8)&0x0000ffff);
- cuda_images[BIG_CPI][17] =
+ cuda_images[BIG_CPI][17] =
((dtlb_addr << 24)&0xff000000) | ((itlb_addr >> 16)&0x000000ff);
cuda_images[BIG_CPI][18] = (itlb_addr << 16)&0xffff0000;
} else {
@@ -433,7 +433,7 @@ static void perf_patch_images(void)
/*
* ioctl routine
- * All routines effect the processor that they are executed on. Thus you
+ * All routines effect the processor that they are executed on. Thus you
* must be running on the processor that you wish to change.
*/
@@ -459,7 +459,7 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
}
/* copy out the Counters */
- if (copy_to_user((void __user *)arg, raddr,
+ if (copy_to_user((void __user *)arg, raddr,
sizeof (raddr)) != 0) {
error = -EFAULT;
break;
@@ -487,7 +487,7 @@ static const struct file_operations perf_fops = {
.open = perf_open,
.release = perf_release
};
-
+
static struct miscdevice perf_dev = {
MISC_DYNAMIC_MINOR,
PA_PERF_DEV,
@@ -595,7 +595,7 @@ static int perf_stop_counters(uint32_t *raddr)
/* OR sticky2 (bit 1496) to counter2 bit 32 */
tmp64 |= (userbuf[23] >> 8) & 0x0000000080000000;
raddr[2] = (uint32_t)tmp64;
-
+
/* Counter3 is bits 1497 to 1528 */
tmp64 = (userbuf[23] >> 7) & 0x00000000ffffffff;
/* OR sticky3 (bit 1529) to counter3 bit 32 */
@@ -617,7 +617,7 @@ static int perf_stop_counters(uint32_t *raddr)
userbuf[22] = 0;
userbuf[23] = 0;
- /*
+ /*
* Write back the zeroed bytes + the image given
* the read was destructive.
*/
@@ -625,13 +625,13 @@ static int perf_stop_counters(uint32_t *raddr)
} else {
/*
- * Read RDR-15 which contains the counters and sticky bits
+ * Read RDR-15 which contains the counters and sticky bits
*/
if (!perf_rdr_read_ubuf(15, userbuf)) {
return -13;
}
- /*
+ /*
* Clear out the counters
*/
perf_rdr_clear(15);
@@ -644,7 +644,7 @@ static int perf_stop_counters(uint32_t *raddr)
raddr[2] = (uint32_t)((userbuf[1] >> 32) & 0x00000000ffffffffUL);
raddr[3] = (uint32_t)(userbuf[1] & 0x00000000ffffffffUL);
}
-
+
return 0;
}
@@ -682,7 +682,7 @@ static int perf_rdr_read_ubuf(uint32_t rdr_num, uint64_t *buffer)
i = tentry->num_words;
while (i--) {
buffer[i] = 0;
- }
+ }
/* Check for bits an even number of 64 */
if ((xbits = width & 0x03f) != 0) {
@@ -808,18 +808,22 @@ static int perf_write_image(uint64_t *memaddr)
}
runway = ioremap_nocache(cpu_device->hpa.start, 4096);
+ if (!runway) {
+ pr_err("perf_write_image: ioremap failed!\n");
+ return -ENOMEM;
+ }
/* Merge intrigue bits into Runway STATUS 0 */
tmp64 = __raw_readq(runway + RUNWAY_STATUS) & 0xffecfffffffffffful;
- __raw_writeq(tmp64 | (*memaddr++ & 0x0013000000000000ul),
+ __raw_writeq(tmp64 | (*memaddr++ & 0x0013000000000000ul),
runway + RUNWAY_STATUS);
-
+
/* Write RUNWAY DEBUG registers */
for (i = 0; i < 8; i++) {
__raw_writeq(*memaddr++, runway + RUNWAY_DEBUG);
}
- return 0;
+ return 0;
}
/*
@@ -843,7 +847,7 @@ printk("perf_rdr_write\n");
perf_rdr_shift_out_U(rdr_num, buffer[i]);
} else {
perf_rdr_shift_out_W(rdr_num, buffer[i]);
- }
+ }
}
printk("perf_rdr_write done\n");
}
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 06f7ca7..4516a5b 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -142,6 +142,10 @@ void machine_power_off(void)
printk(KERN_EMERG "System shut down completed.\n"
"Please power this system off now.");
+
+ /* prevent soft lockup/stalled CPU messages for endless loop. */
+ rcu_sysrq_start();
+ for (;;);
}
void (*pm_power_off)(void) = machine_power_off;
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 3cfef1d..44aeaa9 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -444,6 +444,7 @@
ENTRY_SAME(copy_file_range)
ENTRY_COMP(preadv2)
ENTRY_COMP(pwritev2)
+ ENTRY_SAME(statx)
.ifne (. - 90b) - (__NR_Linux_syscalls * (91b - 90b))
diff --git a/arch/parisc/lib/Makefile b/arch/parisc/lib/Makefile
index 8fa92b8..f2dac4d 100644
--- a/arch/parisc/lib/Makefile
+++ b/arch/parisc/lib/Makefile
@@ -2,7 +2,7 @@
# Makefile for parisc-specific library files
#
-lib-y := lusercopy.o bitops.o checksum.o io.o memset.o fixup.o memcpy.o \
+lib-y := lusercopy.o bitops.o checksum.o io.o memset.o memcpy.o \
ucmpdi2.o delay.o
obj-y := iomap.o
diff --git a/arch/parisc/lib/fixup.S b/arch/parisc/lib/fixup.S
deleted file mode 100644
index a5b72f2..0000000
--- a/arch/parisc/lib/fixup.S
+++ /dev/null
@@ -1,98 +0,0 @@
-/*
- * Linux/PA-RISC Project (http://www.parisc-linux.org/)
- *
- * Copyright (C) 2004 Randolph Chung <tausq@debian.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Fixup routines for kernel exception handling.
- */
-#include <asm/asm-offsets.h>
-#include <asm/assembly.h>
-#include <asm/errno.h>
-#include <linux/linkage.h>
-
-#ifdef CONFIG_SMP
- .macro get_fault_ip t1 t2
- loadgp
- addil LT%__per_cpu_offset,%r27
- LDREG RT%__per_cpu_offset(%r1),\t1
- /* t2 = smp_processor_id() */
- mfctl 30,\t2
- ldw TI_CPU(\t2),\t2
-#ifdef CONFIG_64BIT
- extrd,u \t2,63,32,\t2
-#endif
- /* t2 = &__per_cpu_offset[smp_processor_id()]; */
- LDREGX \t2(\t1),\t2
- addil LT%exception_data,%r27
- LDREG RT%exception_data(%r1),\t1
- /* t1 = this_cpu_ptr(&exception_data) */
- add,l \t1,\t2,\t1
- /* %r27 = t1->fault_gp - restore gp */
- LDREG EXCDATA_GP(\t1), %r27
- /* t1 = t1->fault_ip */
- LDREG EXCDATA_IP(\t1), \t1
- .endm
-#else
- .macro get_fault_ip t1 t2
- loadgp
- /* t1 = this_cpu_ptr(&exception_data) */
- addil LT%exception_data,%r27
- LDREG RT%exception_data(%r1),\t2
- /* %r27 = t2->fault_gp - restore gp */
- LDREG EXCDATA_GP(\t2), %r27
- /* t1 = t2->fault_ip */
- LDREG EXCDATA_IP(\t2), \t1
- .endm
-#endif
-
- .level LEVEL
-
- .text
- .section .fixup, "ax"
-
- /* get_user() fixups, store -EFAULT in r8, and 0 in r9 */
-ENTRY_CFI(fixup_get_user_skip_1)
- get_fault_ip %r1,%r8
- ldo 4(%r1), %r1
- ldi -EFAULT, %r8
- bv %r0(%r1)
- copy %r0, %r9
-ENDPROC_CFI(fixup_get_user_skip_1)
-
-ENTRY_CFI(fixup_get_user_skip_2)
- get_fault_ip %r1,%r8
- ldo 8(%r1), %r1
- ldi -EFAULT, %r8
- bv %r0(%r1)
- copy %r0, %r9
-ENDPROC_CFI(fixup_get_user_skip_2)
-
- /* put_user() fixups, store -EFAULT in r8 */
-ENTRY_CFI(fixup_put_user_skip_1)
- get_fault_ip %r1,%r8
- ldo 4(%r1), %r1
- bv %r0(%r1)
- ldi -EFAULT, %r8
-ENDPROC_CFI(fixup_put_user_skip_1)
-
-ENTRY_CFI(fixup_put_user_skip_2)
- get_fault_ip %r1,%r8
- ldo 8(%r1), %r1
- bv %r0(%r1)
- ldi -EFAULT, %r8
-ENDPROC_CFI(fixup_put_user_skip_2)
-
diff --git a/arch/parisc/lib/lusercopy.S b/arch/parisc/lib/lusercopy.S
index 56845de..f01188c 100644
--- a/arch/parisc/lib/lusercopy.S
+++ b/arch/parisc/lib/lusercopy.S
@@ -5,6 +5,8 @@
* Copyright (C) 2000 Richard Hirst <rhirst with parisc-linux.org>
* Copyright (C) 2001 Matthieu Delahaye <delahaym at esiee.fr>
* Copyright (C) 2003 Randolph Chung <tausq with parisc-linux.org>
+ * Copyright (C) 2017 Helge Deller <deller@gmx.de>
+ * Copyright (C) 2017 John David Anglin <dave.anglin@bell.net>
*
*
* This program is free software; you can redistribute it and/or modify
@@ -132,4 +134,320 @@
.procend
+
+
+/*
+ * unsigned long pa_memcpy(void *dstp, const void *srcp, unsigned long len)
+ *
+ * Inputs:
+ * - sr1 already contains space of source region
+ * - sr2 already contains space of destination region
+ *
+ * Returns:
+ * - number of bytes that could not be copied.
+ * On success, this will be zero.
+ *
+ * This code is based on a C-implementation of a copy routine written by
+ * Randolph Chung, which in turn was derived from the glibc.
+ *
+ * Several strategies are tried to try to get the best performance for various
+ * conditions. In the optimal case, we copy by loops that copy 32- or 16-bytes
+ * at a time using general registers. Unaligned copies are handled either by
+ * aligning the destination and then using shift-and-write method, or in a few
+ * cases by falling back to a byte-at-a-time copy.
+ *
+ * Testing with various alignments and buffer sizes shows that this code is
+ * often >10x faster than a simple byte-at-a-time copy, even for strangely
+ * aligned operands. It is interesting to note that the glibc version of memcpy
+ * (written in C) is actually quite fast already. This routine is able to beat
+ * it by 30-40% for aligned copies because of the loop unrolling, but in some
+ * cases the glibc version is still slightly faster. This lends more
+ * credibility that gcc can generate very good code as long as we are careful.
+ *
+ * Possible optimizations:
+ * - add cache prefetching
+ * - try not to use the post-increment address modifiers; they may create
+ * additional interlocks. Assumption is that those were only efficient on old
+ * machines (pre PA8000 processors)
+ */
+
+ dst = arg0
+ src = arg1
+ len = arg2
+ end = arg3
+ t1 = r19
+ t2 = r20
+ t3 = r21
+ t4 = r22
+ srcspc = sr1
+ dstspc = sr2
+
+ t0 = r1
+ a1 = t1
+ a2 = t2
+ a3 = t3
+ a0 = t4
+
+ save_src = ret0
+ save_dst = ret1
+ save_len = r31
+
+ENTRY_CFI(pa_memcpy)
+ .proc
+ .callinfo NO_CALLS
+ .entry
+
+ /* Last destination address */
+ add dst,len,end
+
+ /* short copy with less than 16 bytes? */
+ cmpib,>>=,n 15,len,.Lbyte_loop
+
+ /* same alignment? */
+ xor src,dst,t0
+ extru t0,31,2,t1
+ cmpib,<>,n 0,t1,.Lunaligned_copy
+
+#ifdef CONFIG_64BIT
+ /* only do 64-bit copies if we can get aligned. */
+ extru t0,31,3,t1
+ cmpib,<>,n 0,t1,.Lalign_loop32
+
+ /* loop until we are 64-bit aligned */
+.Lalign_loop64:
+ extru dst,31,3,t1
+ cmpib,=,n 0,t1,.Lcopy_loop_16
+20: ldb,ma 1(srcspc,src),t1
+21: stb,ma t1,1(dstspc,dst)
+ b .Lalign_loop64
+ ldo -1(len),len
+
+ ASM_EXCEPTIONTABLE_ENTRY(20b,.Lcopy_done)
+ ASM_EXCEPTIONTABLE_ENTRY(21b,.Lcopy_done)
+
+ ldi 31,t0
+.Lcopy_loop_16:
+ cmpb,COND(>>=),n t0,len,.Lword_loop
+
+10: ldd 0(srcspc,src),t1
+11: ldd 8(srcspc,src),t2
+ ldo 16(src),src
+12: std,ma t1,8(dstspc,dst)
+13: std,ma t2,8(dstspc,dst)
+14: ldd 0(srcspc,src),t1
+15: ldd 8(srcspc,src),t2
+ ldo 16(src),src
+16: std,ma t1,8(dstspc,dst)
+17: std,ma t2,8(dstspc,dst)
+
+ ASM_EXCEPTIONTABLE_ENTRY(10b,.Lcopy_done)
+ ASM_EXCEPTIONTABLE_ENTRY(11b,.Lcopy16_fault)
+ ASM_EXCEPTIONTABLE_ENTRY(12b,.Lcopy_done)
+ ASM_EXCEPTIONTABLE_ENTRY(13b,.Lcopy_done)
+ ASM_EXCEPTIONTABLE_ENTRY(14b,.Lcopy_done)
+ ASM_EXCEPTIONTABLE_ENTRY(15b,.Lcopy16_fault)
+ ASM_EXCEPTIONTABLE_ENTRY(16b,.Lcopy_done)
+ ASM_EXCEPTIONTABLE_ENTRY(17b,.Lcopy_done)
+
+ b .Lcopy_loop_16
+ ldo -32(len),len
+
+.Lword_loop:
+ cmpib,COND(>>=),n 3,len,.Lbyte_loop
+20: ldw,ma 4(srcspc,src),t1
+21: stw,ma t1,4(dstspc,dst)
+ b .Lword_loop
+ ldo -4(len),len
+
+ ASM_EXCEPTIONTABLE_ENTRY(20b,.Lcopy_done)
+ ASM_EXCEPTIONTABLE_ENTRY(21b,.Lcopy_done)
+
+#endif /* CONFIG_64BIT */
+
+ /* loop until we are 32-bit aligned */
+.Lalign_loop32:
+ extru dst,31,2,t1
+ cmpib,=,n 0,t1,.Lcopy_loop_4
+20: ldb,ma 1(srcspc,src),t1
+21: stb,ma t1,1(dstspc,dst)
+ b .Lalign_loop32
+ ldo -1(len),len
+
+ ASM_EXCEPTIONTABLE_ENTRY(20b,.Lcopy_done)
+ ASM_EXCEPTIONTABLE_ENTRY(21b,.Lcopy_done)
+
+
+.Lcopy_loop_4:
+ cmpib,COND(>>=),n 15,len,.Lbyte_loop
+
+10: ldw 0(srcspc,src),t1
+11: ldw 4(srcspc,src),t2
+12: stw,ma t1,4(dstspc,dst)
+13: stw,ma t2,4(dstspc,dst)
+14: ldw 8(srcspc,src),t1
+15: ldw 12(srcspc,src),t2
+ ldo 16(src),src
+16: stw,ma t1,4(dstspc,dst)
+17: stw,ma t2,4(dstspc,dst)
+
+ ASM_EXCEPTIONTABLE_ENTRY(10b,.Lcopy_done)
+ ASM_EXCEPTIONTABLE_ENTRY(11b,.Lcopy8_fault)
+ ASM_EXCEPTIONTABLE_ENTRY(12b,.Lcopy_done)
+ ASM_EXCEPTIONTABLE_ENTRY(13b,.Lcopy_done)
+ ASM_EXCEPTIONTABLE_ENTRY(14b,.Lcopy_done)
+ ASM_EXCEPTIONTABLE_ENTRY(15b,.Lcopy8_fault)
+ ASM_EXCEPTIONTABLE_ENTRY(16b,.Lcopy_done)
+ ASM_EXCEPTIONTABLE_ENTRY(17b,.Lcopy_done)
+
+ b .Lcopy_loop_4
+ ldo -16(len),len
+
+.Lbyte_loop:
+ cmpclr,COND(<>) len,%r0,%r0
+ b,n .Lcopy_done
+20: ldb 0(srcspc,src),t1
+ ldo 1(src),src
+21: stb,ma t1,1(dstspc,dst)
+ b .Lbyte_loop
+ ldo -1(len),len
+
+ ASM_EXCEPTIONTABLE_ENTRY(20b,.Lcopy_done)
+ ASM_EXCEPTIONTABLE_ENTRY(21b,.Lcopy_done)
+
+.Lcopy_done:
+ bv %r0(%r2)
+ sub end,dst,ret0
+
+
+ /* src and dst are not aligned the same way. */
+ /* need to go the hard way */
+.Lunaligned_copy:
+ /* align until dst is 32bit-word-aligned */
+ extru dst,31,2,t1
+ cmpib,COND(=),n 0,t1,.Lcopy_dstaligned
+20: ldb 0(srcspc,src),t1
+ ldo 1(src),src
+21: stb,ma t1,1(dstspc,dst)
+ b .Lunaligned_copy
+ ldo -1(len),len
+
+ ASM_EXCEPTIONTABLE_ENTRY(20b,.Lcopy_done)
+ ASM_EXCEPTIONTABLE_ENTRY(21b,.Lcopy_done)
+
+.Lcopy_dstaligned:
+
+ /* store src, dst and len in safe place */
+ copy src,save_src
+ copy dst,save_dst
+ copy len,save_len
+
+ /* len now needs give number of words to copy */
+ SHRREG len,2,len
+
+ /*
+ * Copy from a not-aligned src to an aligned dst using shifts.
+ * Handles 4 words per loop.
+ */
+
+ depw,z src,28,2,t0
+ subi 32,t0,t0
+ mtsar t0
+ extru len,31,2,t0
+ cmpib,= 2,t0,.Lcase2
+ /* Make src aligned by rounding it down. */
+ depi 0,31,2,src
+
+ cmpiclr,<> 3,t0,%r0
+ b,n .Lcase3
+ cmpiclr,<> 1,t0,%r0
+ b,n .Lcase1
+.Lcase0:
+ cmpb,= %r0,len,.Lcda_finish
+ nop
+
+1: ldw,ma 4(srcspc,src), a3
+ ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+1: ldw,ma 4(srcspc,src), a0
+ ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+ b,n .Ldo3
+.Lcase1:
+1: ldw,ma 4(srcspc,src), a2
+ ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+1: ldw,ma 4(srcspc,src), a3
+ ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+ ldo -1(len),len
+ cmpb,=,n %r0,len,.Ldo0
+.Ldo4:
+1: ldw,ma 4(srcspc,src), a0
+ ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+ shrpw a2, a3, %sar, t0
+1: stw,ma t0, 4(dstspc,dst)
+ ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcopy_done)
+.Ldo3:
+1: ldw,ma 4(srcspc,src), a1
+ ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+ shrpw a3, a0, %sar, t0
+1: stw,ma t0, 4(dstspc,dst)
+ ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcopy_done)
+.Ldo2:
+1: ldw,ma 4(srcspc,src), a2
+ ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+ shrpw a0, a1, %sar, t0
+1: stw,ma t0, 4(dstspc,dst)
+ ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcopy_done)
+.Ldo1:
+1: ldw,ma 4(srcspc,src), a3
+ ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+ shrpw a1, a2, %sar, t0
+1: stw,ma t0, 4(dstspc,dst)
+ ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcopy_done)
+ ldo -4(len),len
+ cmpb,<> %r0,len,.Ldo4
+ nop
+.Ldo0:
+ shrpw a2, a3, %sar, t0
+1: stw,ma t0, 4(dstspc,dst)
+ ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcopy_done)
+
+.Lcda_rdfault:
+.Lcda_finish:
+ /* calculate new src, dst and len and jump to byte-copy loop */
+ sub dst,save_dst,t0
+ add save_src,t0,src
+ b .Lbyte_loop
+ sub save_len,t0,len
+
+.Lcase3:
+1: ldw,ma 4(srcspc,src), a0
+ ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+1: ldw,ma 4(srcspc,src), a1
+ ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+ b .Ldo2
+ ldo 1(len),len
+.Lcase2:
+1: ldw,ma 4(srcspc,src), a1
+ ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+1: ldw,ma 4(srcspc,src), a2
+ ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
+ b .Ldo1
+ ldo 2(len),len
+
+
+ /* fault exception fixup handlers: */
+#ifdef CONFIG_64BIT
+.Lcopy16_fault:
+10: b .Lcopy_done
+ std,ma t1,8(dstspc,dst)
+ ASM_EXCEPTIONTABLE_ENTRY(10b,.Lcopy_done)
+#endif
+
+.Lcopy8_fault:
+10: b .Lcopy_done
+ stw,ma t1,4(dstspc,dst)
+ ASM_EXCEPTIONTABLE_ENTRY(10b,.Lcopy_done)
+
+ .exit
+ENDPROC_CFI(pa_memcpy)
+ .procend
+
.end
diff --git a/arch/parisc/lib/memcpy.c b/arch/parisc/lib/memcpy.c
index f82ff10..b3d47ec 100644
--- a/arch/parisc/lib/memcpy.c
+++ b/arch/parisc/lib/memcpy.c
@@ -2,7 +2,7 @@
* Optimized memory copy routines.
*
* Copyright (C) 2004 Randolph Chung <tausq@debian.org>
- * Copyright (C) 2013 Helge Deller <deller@gmx.de>
+ * Copyright (C) 2013-2017 Helge Deller <deller@gmx.de>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -21,474 +21,21 @@
* Portions derived from the GNU C Library
* Copyright (C) 1991, 1997, 2003 Free Software Foundation, Inc.
*
- * Several strategies are tried to try to get the best performance for various
- * conditions. In the optimal case, we copy 64-bytes in an unrolled loop using
- * fp regs. This is followed by loops that copy 32- or 16-bytes at a time using
- * general registers. Unaligned copies are handled either by aligning the
- * destination and then using shift-and-write method, or in a few cases by
- * falling back to a byte-at-a-time copy.
- *
- * I chose to implement this in C because it is easier to maintain and debug,
- * and in my experiments it appears that the C code generated by gcc (3.3/3.4
- * at the time of writing) is fairly optimal. Unfortunately some of the
- * semantics of the copy routine (exception handling) is difficult to express
- * in C, so we have to play some tricks to get it to work.
- *
- * All the loads and stores are done via explicit asm() code in order to use
- * the right space registers.
- *
- * Testing with various alignments and buffer sizes shows that this code is
- * often >10x faster than a simple byte-at-a-time copy, even for strangely
- * aligned operands. It is interesting to note that the glibc version
- * of memcpy (written in C) is actually quite fast already. This routine is
- * able to beat it by 30-40% for aligned copies because of the loop unrolling,
- * but in some cases the glibc version is still slightly faster. This lends
- * more credibility that gcc can generate very good code as long as we are
- * careful.
- *
- * TODO:
- * - cache prefetching needs more experimentation to get optimal settings
- * - try not to use the post-increment address modifiers; they create additional
- * interlocks
- * - replace byte-copy loops with stybs sequences
*/
-#ifdef __KERNEL__
#include <linux/module.h>
#include <linux/compiler.h>
#include <linux/uaccess.h>
-#define s_space "%%sr1"
-#define d_space "%%sr2"
-#else
-#include "memcpy.h"
-#define s_space "%%sr0"
-#define d_space "%%sr0"
-#define pa_memcpy new2_copy
-#endif
DECLARE_PER_CPU(struct exception_data, exception_data);
-#define preserve_branch(label) do { \
- volatile int dummy = 0; \
- /* The following branch is never taken, it's just here to */ \
- /* prevent gcc from optimizing away our exception code. */ \
- if (unlikely(dummy != dummy)) \
- goto label; \
-} while (0)
-
#define get_user_space() (segment_eq(get_fs(), KERNEL_DS) ? 0 : mfsp(3))
#define get_kernel_space() (0)
-#define MERGE(w0, sh_1, w1, sh_2) ({ \
- unsigned int _r; \
- asm volatile ( \
- "mtsar %3\n" \
- "shrpw %1, %2, %%sar, %0\n" \
- : "=r"(_r) \
- : "r"(w0), "r"(w1), "r"(sh_2) \
- ); \
- _r; \
-})
-#define THRESHOLD 16
-
-#ifdef DEBUG_MEMCPY
-#define DPRINTF(fmt, args...) do { printk(KERN_DEBUG "%s:%d:%s ", __FILE__, __LINE__, __func__ ); printk(KERN_DEBUG fmt, ##args ); } while (0)
-#else
-#define DPRINTF(fmt, args...)
-#endif
-
-#define def_load_ai_insn(_insn,_sz,_tt,_s,_a,_t,_e) \
- __asm__ __volatile__ ( \
- "1:\t" #_insn ",ma " #_sz "(" _s ",%1), %0\n\t" \
- ASM_EXCEPTIONTABLE_ENTRY(1b,_e) \
- : _tt(_t), "+r"(_a) \
- : \
- : "r8")
-
-#define def_store_ai_insn(_insn,_sz,_tt,_s,_a,_t,_e) \
- __asm__ __volatile__ ( \
- "1:\t" #_insn ",ma %1, " #_sz "(" _s ",%0)\n\t" \
- ASM_EXCEPTIONTABLE_ENTRY(1b,_e) \
- : "+r"(_a) \
- : _tt(_t) \
- : "r8")
-
-#define ldbma(_s, _a, _t, _e) def_load_ai_insn(ldbs,1,"=r",_s,_a,_t,_e)
-#define stbma(_s, _t, _a, _e) def_store_ai_insn(stbs,1,"r",_s,_a,_t,_e)
-#define ldwma(_s, _a, _t, _e) def_load_ai_insn(ldw,4,"=r",_s,_a,_t,_e)
-#define stwma(_s, _t, _a, _e) def_store_ai_insn(stw,4,"r",_s,_a,_t,_e)
-#define flddma(_s, _a, _t, _e) def_load_ai_insn(fldd,8,"=f",_s,_a,_t,_e)
-#define fstdma(_s, _t, _a, _e) def_store_ai_insn(fstd,8,"f",_s,_a,_t,_e)
-
-#define def_load_insn(_insn,_tt,_s,_o,_a,_t,_e) \
- __asm__ __volatile__ ( \
- "1:\t" #_insn " " #_o "(" _s ",%1), %0\n\t" \
- ASM_EXCEPTIONTABLE_ENTRY(1b,_e) \
- : _tt(_t) \
- : "r"(_a) \
- : "r8")
-
-#define def_store_insn(_insn,_tt,_s,_t,_o,_a,_e) \
- __asm__ __volatile__ ( \
- "1:\t" #_insn " %0, " #_o "(" _s ",%1)\n\t" \
- ASM_EXCEPTIONTABLE_ENTRY(1b,_e) \
- : \
- : _tt(_t), "r"(_a) \
- : "r8")
-
-#define ldw(_s,_o,_a,_t,_e) def_load_insn(ldw,"=r",_s,_o,_a,_t,_e)
-#define stw(_s,_t,_o,_a,_e) def_store_insn(stw,"r",_s,_t,_o,_a,_e)
-
-#ifdef CONFIG_PREFETCH
-static inline void prefetch_src(const void *addr)
-{
- __asm__("ldw 0(" s_space ",%0), %%r0" : : "r" (addr));
-}
-
-static inline void prefetch_dst(const void *addr)
-{
- __asm__("ldd 0(" d_space ",%0), %%r0" : : "r" (addr));
-}
-#else
-#define prefetch_src(addr) do { } while(0)
-#define prefetch_dst(addr) do { } while(0)
-#endif
-
-#define PA_MEMCPY_OK 0
-#define PA_MEMCPY_LOAD_ERROR 1
-#define PA_MEMCPY_STORE_ERROR 2
-
-/* Copy from a not-aligned src to an aligned dst, using shifts. Handles 4 words
- * per loop. This code is derived from glibc.
- */
-static noinline unsigned long copy_dstaligned(unsigned long dst,
- unsigned long src, unsigned long len)
-{
- /* gcc complains that a2 and a3 may be uninitialized, but actually
- * they cannot be. Initialize a2/a3 to shut gcc up.
- */
- register unsigned int a0, a1, a2 = 0, a3 = 0;
- int sh_1, sh_2;
-
- /* prefetch_src((const void *)src); */
-
- /* Calculate how to shift a word read at the memory operation
- aligned srcp to make it aligned for copy. */
- sh_1 = 8 * (src % sizeof(unsigned int));
- sh_2 = 8 * sizeof(unsigned int) - sh_1;
-
- /* Make src aligned by rounding it down. */
- src &= -sizeof(unsigned int);
-
- switch (len % 4)
- {
- case 2:
- /* a1 = ((unsigned int *) src)[0];
- a2 = ((unsigned int *) src)[1]; */
- ldw(s_space, 0, src, a1, cda_ldw_exc);
- ldw(s_space, 4, src, a2, cda_ldw_exc);
- src -= 1 * sizeof(unsigned int);
- dst -= 3 * sizeof(unsigned int);
- len += 2;
- goto do1;
- case 3:
- /* a0 = ((unsigned int *) src)[0];
- a1 = ((unsigned int *) src)[1]; */
- ldw(s_space, 0, src, a0, cda_ldw_exc);
- ldw(s_space, 4, src, a1, cda_ldw_exc);
- src -= 0 * sizeof(unsigned int);
- dst -= 2 * sizeof(unsigned int);
- len += 1;
- goto do2;
- case 0:
- if (len == 0)
- return PA_MEMCPY_OK;
- /* a3 = ((unsigned int *) src)[0];
- a0 = ((unsigned int *) src)[1]; */
- ldw(s_space, 0, src, a3, cda_ldw_exc);
- ldw(s_space, 4, src, a0, cda_ldw_exc);
- src -=-1 * sizeof(unsigned int);
- dst -= 1 * sizeof(unsigned int);
- len += 0;
- goto do3;
- case 1:
- /* a2 = ((unsigned int *) src)[0];
- a3 = ((unsigned int *) src)[1]; */
- ldw(s_space, 0, src, a2, cda_ldw_exc);
- ldw(s_space, 4, src, a3, cda_ldw_exc);
- src -=-2 * sizeof(unsigned int);
- dst -= 0 * sizeof(unsigned int);
- len -= 1;
- if (len == 0)
- goto do0;
- goto do4; /* No-op. */
- }
-
- do
- {
- /* prefetch_src((const void *)(src + 4 * sizeof(unsigned int))); */
-do4:
- /* a0 = ((unsigned int *) src)[0]; */
- ldw(s_space, 0, src, a0, cda_ldw_exc);
- /* ((unsigned int *) dst)[0] = MERGE (a2, sh_1, a3, sh_2); */
- stw(d_space, MERGE (a2, sh_1, a3, sh_2), 0, dst, cda_stw_exc);
-do3:
- /* a1 = ((unsigned int *) src)[1]; */
- ldw(s_space, 4, src, a1, cda_ldw_exc);
- /* ((unsigned int *) dst)[1] = MERGE (a3, sh_1, a0, sh_2); */
- stw(d_space, MERGE (a3, sh_1, a0, sh_2), 4, dst, cda_stw_exc);
-do2:
- /* a2 = ((unsigned int *) src)[2]; */
- ldw(s_space, 8, src, a2, cda_ldw_exc);
- /* ((unsigned int *) dst)[2] = MERGE (a0, sh_1, a1, sh_2); */
- stw(d_space, MERGE (a0, sh_1, a1, sh_2), 8, dst, cda_stw_exc);
-do1:
- /* a3 = ((unsigned int *) src)[3]; */
- ldw(s_space, 12, src, a3, cda_ldw_exc);
- /* ((unsigned int *) dst)[3] = MERGE (a1, sh_1, a2, sh_2); */
- stw(d_space, MERGE (a1, sh_1, a2, sh_2), 12, dst, cda_stw_exc);
-
- src += 4 * sizeof(unsigned int);
- dst += 4 * sizeof(unsigned int);
- len -= 4;
- }
- while (len != 0);
-
-do0:
- /* ((unsigned int *) dst)[0] = MERGE (a2, sh_1, a3, sh_2); */
- stw(d_space, MERGE (a2, sh_1, a3, sh_2), 0, dst, cda_stw_exc);
-
- preserve_branch(handle_load_error);
- preserve_branch(handle_store_error);
-
- return PA_MEMCPY_OK;
-
-handle_load_error:
- __asm__ __volatile__ ("cda_ldw_exc:\n");
- return PA_MEMCPY_LOAD_ERROR;
-
-handle_store_error:
- __asm__ __volatile__ ("cda_stw_exc:\n");
- return PA_MEMCPY_STORE_ERROR;
-}
-
-
-/* Returns PA_MEMCPY_OK, PA_MEMCPY_LOAD_ERROR or PA_MEMCPY_STORE_ERROR.
- * In case of an access fault the faulty address can be read from the per_cpu
- * exception data struct. */
-static noinline unsigned long pa_memcpy_internal(void *dstp, const void *srcp,
- unsigned long len)
-{
- register unsigned long src, dst, t1, t2, t3;
- register unsigned char *pcs, *pcd;
- register unsigned int *pws, *pwd;
- register double *pds, *pdd;
- unsigned long ret;
-
- src = (unsigned long)srcp;
- dst = (unsigned long)dstp;
- pcs = (unsigned char *)srcp;
- pcd = (unsigned char *)dstp;
-
- /* prefetch_src((const void *)srcp); */
-
- if (len < THRESHOLD)
- goto byte_copy;
-
- /* Check alignment */
- t1 = (src ^ dst);
- if (unlikely(t1 & (sizeof(double)-1)))
- goto unaligned_copy;
-
- /* src and dst have same alignment. */
-
- /* Copy bytes till we are double-aligned. */
- t2 = src & (sizeof(double) - 1);
- if (unlikely(t2 != 0)) {
- t2 = sizeof(double) - t2;
- while (t2 && len) {
- /* *pcd++ = *pcs++; */
- ldbma(s_space, pcs, t3, pmc_load_exc);
- len--;
- stbma(d_space, t3, pcd, pmc_store_exc);
- t2--;
- }
- }
-
- pds = (double *)pcs;
- pdd = (double *)pcd;
-
-#if 0
- /* Copy 8 doubles at a time */
- while (len >= 8*sizeof(double)) {
- register double r1, r2, r3, r4, r5, r6, r7, r8;
- /* prefetch_src((char *)pds + L1_CACHE_BYTES); */
- flddma(s_space, pds, r1, pmc_load_exc);
- flddma(s_space, pds, r2, pmc_load_exc);
- flddma(s_space, pds, r3, pmc_load_exc);
- flddma(s_space, pds, r4, pmc_load_exc);
- fstdma(d_space, r1, pdd, pmc_store_exc);
- fstdma(d_space, r2, pdd, pmc_store_exc);
- fstdma(d_space, r3, pdd, pmc_store_exc);
- fstdma(d_space, r4, pdd, pmc_store_exc);
-
-#if 0
- if (L1_CACHE_BYTES <= 32)
- prefetch_src((char *)pds + L1_CACHE_BYTES);
-#endif
- flddma(s_space, pds, r5, pmc_load_exc);
- flddma(s_space, pds, r6, pmc_load_exc);
- flddma(s_space, pds, r7, pmc_load_exc);
- flddma(s_space, pds, r8, pmc_load_exc);
- fstdma(d_space, r5, pdd, pmc_store_exc);
- fstdma(d_space, r6, pdd, pmc_store_exc);
- fstdma(d_space, r7, pdd, pmc_store_exc);
- fstdma(d_space, r8, pdd, pmc_store_exc);
- len -= 8*sizeof(double);
- }
-#endif
-
- pws = (unsigned int *)pds;
- pwd = (unsigned int *)pdd;
-
-word_copy:
- while (len >= 8*sizeof(unsigned int)) {
- register unsigned int r1,r2,r3,r4,r5,r6,r7,r8;
- /* prefetch_src((char *)pws + L1_CACHE_BYTES); */
- ldwma(s_space, pws, r1, pmc_load_exc);
- ldwma(s_space, pws, r2, pmc_load_exc);
- ldwma(s_space, pws, r3, pmc_load_exc);
- ldwma(s_space, pws, r4, pmc_load_exc);
- stwma(d_space, r1, pwd, pmc_store_exc);
- stwma(d_space, r2, pwd, pmc_store_exc);
- stwma(d_space, r3, pwd, pmc_store_exc);
- stwma(d_space, r4, pwd, pmc_store_exc);
-
- ldwma(s_space, pws, r5, pmc_load_exc);
- ldwma(s_space, pws, r6, pmc_load_exc);
- ldwma(s_space, pws, r7, pmc_load_exc);
- ldwma(s_space, pws, r8, pmc_load_exc);
- stwma(d_space, r5, pwd, pmc_store_exc);
- stwma(d_space, r6, pwd, pmc_store_exc);
- stwma(d_space, r7, pwd, pmc_store_exc);
- stwma(d_space, r8, pwd, pmc_store_exc);
- len -= 8*sizeof(unsigned int);
- }
-
- while (len >= 4*sizeof(unsigned int)) {
- register unsigned int r1,r2,r3,r4;
- ldwma(s_space, pws, r1, pmc_load_exc);
- ldwma(s_space, pws, r2, pmc_load_exc);
- ldwma(s_space, pws, r3, pmc_load_exc);
- ldwma(s_space, pws, r4, pmc_load_exc);
- stwma(d_space, r1, pwd, pmc_store_exc);
- stwma(d_space, r2, pwd, pmc_store_exc);
- stwma(d_space, r3, pwd, pmc_store_exc);
- stwma(d_space, r4, pwd, pmc_store_exc);
- len -= 4*sizeof(unsigned int);
- }
-
- pcs = (unsigned char *)pws;
- pcd = (unsigned char *)pwd;
-
-byte_copy:
- while (len) {
- /* *pcd++ = *pcs++; */
- ldbma(s_space, pcs, t3, pmc_load_exc);
- stbma(d_space, t3, pcd, pmc_store_exc);
- len--;
- }
-
- return PA_MEMCPY_OK;
-
-unaligned_copy:
- /* possibly we are aligned on a word, but not on a double... */
- if (likely((t1 & (sizeof(unsigned int)-1)) == 0)) {
- t2 = src & (sizeof(unsigned int) - 1);
-
- if (unlikely(t2 != 0)) {
- t2 = sizeof(unsigned int) - t2;
- while (t2) {
- /* *pcd++ = *pcs++; */
- ldbma(s_space, pcs, t3, pmc_load_exc);
- stbma(d_space, t3, pcd, pmc_store_exc);
- len--;
- t2--;
- }
- }
-
- pws = (unsigned int *)pcs;
- pwd = (unsigned int *)pcd;
- goto word_copy;
- }
-
- /* Align the destination. */
- if (unlikely((dst & (sizeof(unsigned int) - 1)) != 0)) {
- t2 = sizeof(unsigned int) - (dst & (sizeof(unsigned int) - 1));
- while (t2) {
- /* *pcd++ = *pcs++; */
- ldbma(s_space, pcs, t3, pmc_load_exc);
- stbma(d_space, t3, pcd, pmc_store_exc);
- len--;
- t2--;
- }
- dst = (unsigned long)pcd;
- src = (unsigned long)pcs;
- }
-
- ret = copy_dstaligned(dst, src, len / sizeof(unsigned int));
- if (ret)
- return ret;
-
- pcs += (len & -sizeof(unsigned int));
- pcd += (len & -sizeof(unsigned int));
- len %= sizeof(unsigned int);
-
- preserve_branch(handle_load_error);
- preserve_branch(handle_store_error);
-
- goto byte_copy;
-
-handle_load_error:
- __asm__ __volatile__ ("pmc_load_exc:\n");
- return PA_MEMCPY_LOAD_ERROR;
-
-handle_store_error:
- __asm__ __volatile__ ("pmc_store_exc:\n");
- return PA_MEMCPY_STORE_ERROR;
-}
-
-
/* Returns 0 for success, otherwise, returns number of bytes not transferred. */
-static unsigned long pa_memcpy(void *dstp, const void *srcp, unsigned long len)
-{
- unsigned long ret, fault_addr, reference;
- struct exception_data *d;
+extern unsigned long pa_memcpy(void *dst, const void *src,
+ unsigned long len);
- ret = pa_memcpy_internal(dstp, srcp, len);
- if (likely(ret == PA_MEMCPY_OK))
- return 0;
-
- /* if a load or store fault occured we can get the faulty addr */
- d = this_cpu_ptr(&exception_data);
- fault_addr = d->fault_addr;
-
- /* error in load or store? */
- if (ret == PA_MEMCPY_LOAD_ERROR)
- reference = (unsigned long) srcp;
- else
- reference = (unsigned long) dstp;
-
- DPRINTF("pa_memcpy: fault type = %lu, len=%lu fault_addr=%lu ref=%lu\n",
- ret, len, fault_addr, reference);
-
- if (fault_addr >= reference)
- return len - (fault_addr - reference);
- else
- return len;
-}
-
-#ifdef __KERNEL__
unsigned long __copy_to_user(void __user *dst, const void *src,
unsigned long len)
{
@@ -537,5 +84,3 @@ long probe_kernel_read(void *dst, const void *src, size_t size)
return __probe_kernel_read(dst, src, size);
}
-
-#endif
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index deab89a..32ec221 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -150,6 +150,23 @@ int fixup_exception(struct pt_regs *regs)
d->fault_space = regs->isr;
d->fault_addr = regs->ior;
+ /*
+ * Fix up get_user() and put_user().
+ * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() sets the least-significant
+ * bit in the relative address of the fixup routine to indicate
+ * that %r8 should be loaded with -EFAULT to report a userspace
+ * access error.
+ */
+ if (fix->fixup & 1) {
+ regs->gr[8] = -EFAULT;
+
+ /* zero target register for get_user() */
+ if (parisc_acctyp(0, regs->iir) == VM_READ) {
+ int treg = regs->iir & 0x1f;
+ regs->gr[treg] = 0;
+ }
+ }
+
regs->iaoq[0] = (unsigned long)&fix->fixup + fix->fixup;
regs->iaoq[0] &= ~3;
/*
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 4940917..97a8bc8 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -80,93 +80,99 @@
config PPC
bool
default y
- select BUILDTIME_EXTABLE_SORT
+ #
+ # Please keep this list sorted alphabetically.
+ #
+ select ARCH_HAS_DEVMEM_IS_ALLOWED
+ select ARCH_HAS_DMA_SET_COHERENT_MASK
+ select ARCH_HAS_ELF_RANDOMIZE
+ select ARCH_HAS_GCOV_PROFILE_ALL
+ select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE
+ select ARCH_HAS_SG_CHAIN
+ select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
+ select ARCH_HAS_UBSAN_SANITIZE_ALL
+ select ARCH_HAVE_NMI_SAFE_CMPXCHG
select ARCH_MIGHT_HAVE_PC_PARPORT
select ARCH_MIGHT_HAVE_PC_SERIO
+ select ARCH_SUPPORTS_ATOMIC_RMW
+ select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
+ select ARCH_USE_BUILTIN_BSWAP
+ select ARCH_USE_CMPXCHG_LOCKREF if PPC64
+ select ARCH_WANT_IPC_PARSE_VERSION
select BINFMT_ELF
- select ARCH_HAS_ELF_RANDOMIZE
+ select BUILDTIME_EXTABLE_SORT
+ select CLONE_BACKWARDS
+ select DCACHE_WORD_ACCESS if PPC64 && CPU_LITTLE_ENDIAN
+ select EDAC_ATOMIC_SCRUB
+ select EDAC_SUPPORT
+ select GENERIC_ATOMIC64 if PPC32
+ select GENERIC_CLOCKEVENTS
+ select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+ select GENERIC_CMOS_UPDATE
+ select GENERIC_CPU_AUTOPROBE
+ select GENERIC_IRQ_SHOW
+ select GENERIC_IRQ_SHOW_LEVEL
+ select GENERIC_SMP_IDLE_THREAD
+ select GENERIC_STRNCPY_FROM_USER
+ select GENERIC_STRNLEN_USER
+ select GENERIC_TIME_VSYSCALL_OLD
+ select HAVE_ARCH_AUDITSYSCALL
+ select HAVE_ARCH_HARDENED_USERCOPY
+ select HAVE_ARCH_JUMP_LABEL
+ select HAVE_ARCH_KGDB
+ select HAVE_ARCH_SECCOMP_FILTER
+ select HAVE_ARCH_TRACEHOOK
+ select HAVE_CBPF_JIT if !PPC64
+ select HAVE_CONTEXT_TRACKING if PPC64
+ select HAVE_DEBUG_KMEMLEAK
+ select HAVE_DEBUG_STACKOVERFLOW
+ select HAVE_DMA_API_DEBUG
+ select HAVE_DYNAMIC_FTRACE
+ select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL
+ select HAVE_EBPF_JIT if PPC64
+ select HAVE_EFFICIENT_UNALIGNED_ACCESS if !(CPU_LITTLE_ENDIAN && POWER7_CPU)
+ select HAVE_FTRACE_MCOUNT_RECORD
+ select HAVE_FUNCTION_GRAPH_TRACER
+ select HAVE_FUNCTION_TRACER
+ select HAVE_GCC_PLUGINS
+ select HAVE_GENERIC_RCU_GUP
+ select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
+ select HAVE_IDE
+ select HAVE_IOREMAP_PROT
+ select HAVE_IRQ_EXIT_ON_IRQ_STACK
+ select HAVE_KERNEL_GZIP
+ select HAVE_KPROBES
+ select HAVE_KRETPROBES
+ select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS
+ select HAVE_MEMBLOCK
+ select HAVE_MEMBLOCK_NODE_MAP
+ select HAVE_MOD_ARCH_SPECIFIC
+ select HAVE_NMI if PERF_EVENTS
+ select HAVE_OPROFILE
+ select HAVE_OPTPROBES if PPC64
+ select HAVE_PERF_EVENTS
+ select HAVE_PERF_EVENTS_NMI if PPC64
+ select HAVE_PERF_REGS
+ select HAVE_PERF_USER_STACK_DUMP
+ select HAVE_RCU_TABLE_FREE if SMP
+ select HAVE_REGS_AND_STACK_ACCESS_API
+ select HAVE_SYSCALL_TRACEPOINTS
+ select HAVE_VIRT_CPU_ACCOUNTING
+ select IRQ_DOMAIN
+ select IRQ_FORCED_THREADING
+ select MODULES_USE_ELF_RELA
+ select NO_BOOTMEM
select OF
select OF_EARLY_FLATTREE
select OF_RESERVED_MEM
- select HAVE_FTRACE_MCOUNT_RECORD
- select HAVE_DYNAMIC_FTRACE
- select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL
- select HAVE_FUNCTION_TRACER
- select HAVE_FUNCTION_GRAPH_TRACER
- select HAVE_GCC_PLUGINS
- select SYSCTL_EXCEPTION_TRACE
- select VIRT_TO_BUS if !PPC64
- select HAVE_IDE
- select HAVE_IOREMAP_PROT
- select HAVE_EFFICIENT_UNALIGNED_ACCESS if !(CPU_LITTLE_ENDIAN && POWER7_CPU)
- select HAVE_KPROBES
- select HAVE_OPTPROBES if PPC64
- select HAVE_ARCH_KGDB
- select HAVE_KRETPROBES
- select HAVE_ARCH_TRACEHOOK
- select HAVE_MEMBLOCK
- select HAVE_MEMBLOCK_NODE_MAP
- select HAVE_DMA_API_DEBUG
- select HAVE_OPROFILE
- select HAVE_DEBUG_KMEMLEAK
- select ARCH_HAS_SG_CHAIN
- select GENERIC_ATOMIC64 if PPC32
- select HAVE_PERF_EVENTS
- select HAVE_PERF_REGS
- select HAVE_PERF_USER_STACK_DUMP
- select HAVE_REGS_AND_STACK_ACCESS_API
- select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
- select ARCH_WANT_IPC_PARSE_VERSION
- select SPARSE_IRQ
- select IRQ_DOMAIN
- select GENERIC_IRQ_SHOW
- select GENERIC_IRQ_SHOW_LEVEL
- select IRQ_FORCED_THREADING
- select HAVE_RCU_TABLE_FREE if SMP
- select HAVE_SYSCALL_TRACEPOINTS
- select HAVE_CBPF_JIT if !PPC64
- select HAVE_EBPF_JIT if PPC64
- select HAVE_ARCH_JUMP_LABEL
- select ARCH_HAVE_NMI_SAFE_CMPXCHG
- select ARCH_HAS_GCOV_PROFILE_ALL
- select GENERIC_SMP_IDLE_THREAD
- select GENERIC_CMOS_UPDATE
- select GENERIC_TIME_VSYSCALL_OLD
- select GENERIC_CLOCKEVENTS
- select GENERIC_CLOCKEVENTS_BROADCAST if SMP
- select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
- select GENERIC_STRNCPY_FROM_USER
- select GENERIC_STRNLEN_USER
- select HAVE_MOD_ARCH_SPECIFIC
- select MODULES_USE_ELF_RELA
- select CLONE_BACKWARDS
- select ARCH_USE_BUILTIN_BSWAP
+ select OLD_SIGACTION if PPC32
select OLD_SIGSUSPEND
- select OLD_SIGACTION if PPC32
- select HAVE_DEBUG_STACKOVERFLOW
- select HAVE_IRQ_EXIT_ON_IRQ_STACK
- select ARCH_USE_CMPXCHG_LOCKREF if PPC64
- select HAVE_ARCH_AUDITSYSCALL
- select ARCH_SUPPORTS_ATOMIC_RMW
- select DCACHE_WORD_ACCESS if PPC64 && CPU_LITTLE_ENDIAN
- select NO_BOOTMEM
- select HAVE_GENERIC_RCU_GUP
- select HAVE_PERF_EVENTS_NMI if PPC64
- select HAVE_NMI if PERF_EVENTS
- select EDAC_SUPPORT
- select EDAC_ATOMIC_SCRUB
- select ARCH_HAS_DMA_SET_COHERENT_MASK
- select ARCH_HAS_DEVMEM_IS_ALLOWED
- select HAVE_ARCH_SECCOMP_FILTER
- select ARCH_HAS_UBSAN_SANITIZE_ALL
- select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
- select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS
- select GENERIC_CPU_AUTOPROBE
- select HAVE_VIRT_CPU_ACCOUNTING
- select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE
- select HAVE_ARCH_HARDENED_USERCOPY
- select HAVE_KERNEL_GZIP
- select HAVE_CONTEXT_TRACKING if PPC64
+ select SPARSE_IRQ
+ select SYSCTL_EXCEPTION_TRACE
+ select VIRT_TO_BUS if !PPC64
+ #
+ # Please keep this list sorted alphabetically.
+ #
config GENERIC_CSUM
def_bool n
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 31286fa..19b0d1a 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -72,8 +72,15 @@
MULTIPLEWORD := -mmultiple
endif
-cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mbig-endian)
+ifdef CONFIG_PPC64
+cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mabi=elfv1)
+cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mcall-aixdesc)
+aflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mabi=elfv1)
+aflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mabi=elfv2
+endif
+
cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mlittle-endian
+cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mbig-endian)
ifneq ($(cc-name),clang)
cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mno-strict-align
endif
@@ -113,7 +120,9 @@
CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2,$(call cc-option,-mcall-aixdesc))
AFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2)
else
+CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv1)
CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcall-aixdesc)
+AFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv1)
endif
CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc))
CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mno-pointers-to-nested-functions)
diff --git a/arch/powerpc/boot/zImage.lds.S b/arch/powerpc/boot/zImage.lds.S
index 861e721..f080abf 100644
--- a/arch/powerpc/boot/zImage.lds.S
+++ b/arch/powerpc/boot/zImage.lds.S
@@ -68,6 +68,7 @@
}
#ifdef CONFIG_PPC64_BOOT_WRAPPER
+ . = ALIGN(256);
.got :
{
__toc_start = .;
diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
index 9fa046d..4119945 100644
--- a/arch/powerpc/crypto/crc32c-vpmsum_glue.c
+++ b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
@@ -52,7 +52,7 @@ static int crc32c_vpmsum_cra_init(struct crypto_tfm *tfm)
{
u32 *key = crypto_tfm_ctx(tfm);
- *key = 0;
+ *key = ~0;
return 0;
}
diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h
index 73eb794..bc5fdfd 100644
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -51,6 +51,10 @@
#define PPC_BIT(bit) (1UL << PPC_BITLSHIFT(bit))
#define PPC_BITMASK(bs, be) ((PPC_BIT(bs) - PPC_BIT(be)) | PPC_BIT(bs))
+/* Put a PPC bit into a "normal" bit position */
+#define PPC_BITEXTRACT(bits, ppc_bit, dst_bit) \
+ ((((bits) >> PPC_BITLSHIFT(ppc_bit)) & 1) << (dst_bit))
+
#include <asm/barrier.h>
/* Macro for generating the ***_bits() functions */
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 0122236..26ed228 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -1,6 +1,7 @@
#ifndef _ASM_POWERPC_BOOK3S_32_PGTABLE_H
#define _ASM_POWERPC_BOOK3S_32_PGTABLE_H
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
#include <asm/book3s/32/hash.h>
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 1eeeb72..8f4d419 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -1,9 +1,12 @@
#ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_H_
#define _ASM_POWERPC_BOOK3S_64_PGTABLE_H_
+#include <asm-generic/5level-fixup.h>
+
#ifndef __ASSEMBLY__
#include <linux/mmdebug.h>
#endif
+
/*
* Common bits between hash and Radix page table
*/
@@ -347,23 +350,58 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
__r; \
})
+static inline int __pte_write(pte_t pte)
+{
+ return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE));
+}
+
+#ifdef CONFIG_NUMA_BALANCING
+#define pte_savedwrite pte_savedwrite
+static inline bool pte_savedwrite(pte_t pte)
+{
+ /*
+ * Saved write ptes are prot none ptes that doesn't have
+ * privileged bit sit. We mark prot none as one which has
+ * present and pviliged bit set and RWX cleared. To mark
+ * protnone which used to have _PAGE_WRITE set we clear
+ * the privileged bit.
+ */
+ return !(pte_raw(pte) & cpu_to_be64(_PAGE_RWX | _PAGE_PRIVILEGED));
+}
+#else
+#define pte_savedwrite pte_savedwrite
+static inline bool pte_savedwrite(pte_t pte)
+{
+ return false;
+}
+#endif
+
+static inline int pte_write(pte_t pte)
+{
+ return __pte_write(pte) || pte_savedwrite(pte);
+}
+
#define __HAVE_ARCH_PTEP_SET_WRPROTECT
static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
{
- if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_WRITE)) == 0)
- return;
-
- pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
+ if (__pte_write(*ptep))
+ pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
+ else if (unlikely(pte_savedwrite(*ptep)))
+ pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 0);
}
static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
- if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_WRITE)) == 0)
- return;
-
- pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1);
+ /*
+ * We should not find protnone for hugetlb, but this complete the
+ * interface.
+ */
+ if (__pte_write(*ptep))
+ pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1);
+ else if (unlikely(pte_savedwrite(*ptep)))
+ pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 1);
}
#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
@@ -397,11 +435,6 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
pte_update(mm, addr, ptep, ~0UL, 0, 0);
}
-static inline int pte_write(pte_t pte)
-{
- return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE));
-}
-
static inline int pte_dirty(pte_t pte)
{
return !!(pte_raw(pte) & cpu_to_be64(_PAGE_DIRTY));
@@ -465,19 +498,12 @@ static inline pte_t pte_clear_savedwrite(pte_t pte)
VM_BUG_ON(!pte_protnone(pte));
return __pte(pte_val(pte) | _PAGE_PRIVILEGED);
}
-
-#define pte_savedwrite pte_savedwrite
-static inline bool pte_savedwrite(pte_t pte)
+#else
+#define pte_clear_savedwrite pte_clear_savedwrite
+static inline pte_t pte_clear_savedwrite(pte_t pte)
{
- /*
- * Saved write ptes are prot none ptes that doesn't have
- * privileged bit sit. We mark prot none as one which has
- * present and pviliged bit set and RWX cleared. To mark
- * protnone which used to have _PAGE_WRITE set we clear
- * the privileged bit.
- */
- VM_BUG_ON(!pte_protnone(pte));
- return !(pte_raw(pte) & cpu_to_be64(_PAGE_RWX | _PAGE_PRIVILEGED));
+ VM_WARN_ON(1);
+ return __pte(pte_val(pte) & ~_PAGE_WRITE);
}
#endif /* CONFIG_NUMA_BALANCING */
@@ -506,6 +532,8 @@ static inline unsigned long pte_pfn(pte_t pte)
/* Generic modifiers for PTE bits */
static inline pte_t pte_wrprotect(pte_t pte)
{
+ if (unlikely(pte_savedwrite(pte)))
+ return pte_clear_savedwrite(pte);
return __pte(pte_val(pte) & ~_PAGE_WRITE);
}
@@ -926,6 +954,7 @@ static inline int pmd_protnone(pmd_t pmd)
#define __HAVE_ARCH_PMD_WRITE
#define pmd_write(pmd) pte_write(pmd_pte(pmd))
+#define __pmd_write(pmd) __pte_write(pmd_pte(pmd))
#define pmd_savedwrite(pmd) pte_savedwrite(pmd_pte(pmd))
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -982,11 +1011,10 @@ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp)
{
-
- if ((pmd_raw(*pmdp) & cpu_to_be64(_PAGE_WRITE)) == 0)
- return;
-
- pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0);
+ if (__pmd_write((*pmdp)))
+ pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0);
+ else if (unlikely(pmd_savedwrite(*pmdp)))
+ pmd_hugepage_update(mm, addr, pmdp, 0, _PAGE_PRIVILEGED);
}
static inline int pmd_trans_huge(pmd_t pmd)
diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index 4e63787..842124b 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -112,7 +112,7 @@ static inline __wsum csum_add(__wsum csum, __wsum addend)
#ifdef __powerpc64__
res += (__force u64)addend;
- return (__force __wsum)((u32)res + (res >> 32));
+ return (__force __wsum) from64to32(res);
#else
asm("addc %0,%0,%1;"
"addze %0,%0;"
diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h
index fd321eb4..1557315 100644
--- a/arch/powerpc/include/asm/cpuidle.h
+++ b/arch/powerpc/include/asm/cpuidle.h
@@ -70,8 +70,8 @@ static inline void report_invalid_psscr_val(u64 psscr_val, int err)
std r0,0(r1); \
ptesync; \
ld r0,0(r1); \
-1: cmpd cr0,r0,r0; \
- bne 1b; \
+236: cmpd cr0,r0,r0; \
+ bne 236b; \
IDLE_INST; \
#define IDLE_STATE_ENTER_SEQ_NORET(IDLE_INST) \
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index 93b9b84..09bde6e 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -144,8 +144,8 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
#define ARCH_DLINFO_CACHE_GEOMETRY \
NEW_AUX_ENT(AT_L1I_CACHESIZE, ppc64_caches.l1i.size); \
NEW_AUX_ENT(AT_L1I_CACHEGEOMETRY, get_cache_geometry(l1i)); \
- NEW_AUX_ENT(AT_L1D_CACHESIZE, ppc64_caches.l1i.size); \
- NEW_AUX_ENT(AT_L1D_CACHEGEOMETRY, get_cache_geometry(l1i)); \
+ NEW_AUX_ENT(AT_L1D_CACHESIZE, ppc64_caches.l1d.size); \
+ NEW_AUX_ENT(AT_L1D_CACHEGEOMETRY, get_cache_geometry(l1d)); \
NEW_AUX_ENT(AT_L2_CACHESIZE, ppc64_caches.l2.size); \
NEW_AUX_ENT(AT_L2_CACHEGEOMETRY, get_cache_geometry(l2)); \
NEW_AUX_ENT(AT_L3_CACHESIZE, ppc64_caches.l3.size); \
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index f97d8cb..ed62efe 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -66,6 +66,55 @@
#define P8_DSISR_MC_SLB_ERRORS (P7_DSISR_MC_SLB_ERRORS | \
P8_DSISR_MC_ERAT_MULTIHIT_SEC)
+
+/*
+ * Machine Check bits on power9
+ */
+#define P9_SRR1_MC_LOADSTORE(srr1) (((srr1) >> PPC_BITLSHIFT(42)) & 1)
+
+#define P9_SRR1_MC_IFETCH(srr1) ( \
+ PPC_BITEXTRACT(srr1, 45, 0) | \
+ PPC_BITEXTRACT(srr1, 44, 1) | \
+ PPC_BITEXTRACT(srr1, 43, 2) | \
+ PPC_BITEXTRACT(srr1, 36, 3) )
+
+/* 0 is reserved */
+#define P9_SRR1_MC_IFETCH_UE 1
+#define P9_SRR1_MC_IFETCH_SLB_PARITY 2
+#define P9_SRR1_MC_IFETCH_SLB_MULTIHIT 3
+#define P9_SRR1_MC_IFETCH_ERAT_MULTIHIT 4
+#define P9_SRR1_MC_IFETCH_TLB_MULTIHIT 5
+#define P9_SRR1_MC_IFETCH_UE_TLB_RELOAD 6
+/* 7 is reserved */
+#define P9_SRR1_MC_IFETCH_LINK_TIMEOUT 8
+#define P9_SRR1_MC_IFETCH_LINK_TABLEWALK_TIMEOUT 9
+/* 10 ? */
+#define P9_SRR1_MC_IFETCH_RA 11
+#define P9_SRR1_MC_IFETCH_RA_TABLEWALK 12
+#define P9_SRR1_MC_IFETCH_RA_ASYNC_STORE 13
+#define P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT 14
+#define P9_SRR1_MC_IFETCH_RA_TABLEWALK_FOREIGN 15
+
+/* DSISR bits for machine check (On Power9) */
+#define P9_DSISR_MC_UE (PPC_BIT(48))
+#define P9_DSISR_MC_UE_TABLEWALK (PPC_BIT(49))
+#define P9_DSISR_MC_LINK_LOAD_TIMEOUT (PPC_BIT(50))
+#define P9_DSISR_MC_LINK_TABLEWALK_TIMEOUT (PPC_BIT(51))
+#define P9_DSISR_MC_ERAT_MULTIHIT (PPC_BIT(52))
+#define P9_DSISR_MC_TLB_MULTIHIT_MFTLB (PPC_BIT(53))
+#define P9_DSISR_MC_USER_TLBIE (PPC_BIT(54))
+#define P9_DSISR_MC_SLB_PARITY_MFSLB (PPC_BIT(55))
+#define P9_DSISR_MC_SLB_MULTIHIT_MFSLB (PPC_BIT(56))
+#define P9_DSISR_MC_RA_LOAD (PPC_BIT(57))
+#define P9_DSISR_MC_RA_TABLEWALK (PPC_BIT(58))
+#define P9_DSISR_MC_RA_TABLEWALK_FOREIGN (PPC_BIT(59))
+#define P9_DSISR_MC_RA_FOREIGN (PPC_BIT(60))
+
+/* SLB error bits */
+#define P9_DSISR_MC_SLB_ERRORS (P9_DSISR_MC_ERAT_MULTIHIT | \
+ P9_DSISR_MC_SLB_PARITY_MFSLB | \
+ P9_DSISR_MC_SLB_MULTIHIT_MFSLB)
+
enum MCE_Version {
MCE_V1 = 1,
};
@@ -93,6 +142,9 @@ enum MCE_ErrorType {
MCE_ERROR_TYPE_SLB = 2,
MCE_ERROR_TYPE_ERAT = 3,
MCE_ERROR_TYPE_TLB = 4,
+ MCE_ERROR_TYPE_USER = 5,
+ MCE_ERROR_TYPE_RA = 6,
+ MCE_ERROR_TYPE_LINK = 7,
};
enum MCE_UeErrorType {
@@ -121,6 +173,32 @@ enum MCE_TlbErrorType {
MCE_TLB_ERROR_MULTIHIT = 2,
};
+enum MCE_UserErrorType {
+ MCE_USER_ERROR_INDETERMINATE = 0,
+ MCE_USER_ERROR_TLBIE = 1,
+};
+
+enum MCE_RaErrorType {
+ MCE_RA_ERROR_INDETERMINATE = 0,
+ MCE_RA_ERROR_IFETCH = 1,
+ MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH = 2,
+ MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN = 3,
+ MCE_RA_ERROR_LOAD = 4,
+ MCE_RA_ERROR_STORE = 5,
+ MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE = 6,
+ MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN = 7,
+ MCE_RA_ERROR_LOAD_STORE_FOREIGN = 8,
+};
+
+enum MCE_LinkErrorType {
+ MCE_LINK_ERROR_INDETERMINATE = 0,
+ MCE_LINK_ERROR_IFETCH_TIMEOUT = 1,
+ MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT = 2,
+ MCE_LINK_ERROR_LOAD_TIMEOUT = 3,
+ MCE_LINK_ERROR_STORE_TIMEOUT = 4,
+ MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT = 5,
+};
+
struct machine_check_event {
enum MCE_Version version:8; /* 0x00 */
uint8_t in_use; /* 0x01 */
@@ -166,6 +244,30 @@ struct machine_check_event {
uint64_t effective_address;
uint8_t reserved_2[16];
} tlb_error;
+
+ struct {
+ enum MCE_UserErrorType user_error_type:8;
+ uint8_t effective_address_provided;
+ uint8_t reserved_1[6];
+ uint64_t effective_address;
+ uint8_t reserved_2[16];
+ } user_error;
+
+ struct {
+ enum MCE_RaErrorType ra_error_type:8;
+ uint8_t effective_address_provided;
+ uint8_t reserved_1[6];
+ uint64_t effective_address;
+ uint8_t reserved_2[16];
+ } ra_error;
+
+ struct {
+ enum MCE_LinkErrorType link_error_type:8;
+ uint8_t effective_address_provided;
+ uint8_t reserved_1[6];
+ uint64_t effective_address;
+ uint8_t reserved_2[16];
+ } link_error;
} u;
};
@@ -176,8 +278,12 @@ struct mce_error_info {
enum MCE_SlbErrorType slb_error_type:8;
enum MCE_EratErrorType erat_error_type:8;
enum MCE_TlbErrorType tlb_error_type:8;
+ enum MCE_UserErrorType user_error_type:8;
+ enum MCE_RaErrorType ra_error_type:8;
+ enum MCE_LinkErrorType link_error_type:8;
} u;
- uint8_t reserved[2];
+ enum MCE_Severity severity:8;
+ enum MCE_Initiator initiator:8;
};
#define MAX_MC_EVT 100
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index ba9921b..5134ade 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -1,6 +1,7 @@
#ifndef _ASM_POWERPC_NOHASH_32_PGTABLE_H
#define _ASM_POWERPC_NOHASH_32_PGTABLE_H
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
#ifndef __ASSEMBLY__
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable-4k.h b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h
index d0db987..9f4de0a 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable-4k.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h
@@ -1,5 +1,8 @@
#ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H
#define _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H
+
+#include <asm-generic/5level-fixup.h>
+
/*
* Entries per page directory level. The PTE level must use a 64b record
* for each page table entry. The PMD and PGD level use a 32b record for
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable-64k.h b/arch/powerpc/include/asm/nohash/64/pgtable-64k.h
index 55b28ef..1facb58 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable-64k.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable-64k.h
@@ -1,6 +1,7 @@
#ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H
#define _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopud.h>
diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
index 0cd8a38..e5805ad 100644
--- a/arch/powerpc/include/asm/nohash/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/pgtable.h
@@ -230,7 +230,7 @@ static inline int hugepd_ok(hugepd_t hpd)
return ((hpd_val(hpd) & 0x4) != 0);
#else
/* We clear the top bit to indicate hugepd */
- return ((hpd_val(hpd) & PD_HUGE) == 0);
+ return (hpd_val(hpd) && (hpd_val(hpd) & PD_HUGE) == 0);
#endif
}
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index d99bd44..e7d6d86 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -284,6 +284,13 @@
#define PPC_INST_BRANCH_COND 0x40800000
#define PPC_INST_LBZCIX 0x7c0006aa
#define PPC_INST_STBCIX 0x7c0007aa
+#define PPC_INST_LWZX 0x7c00002e
+#define PPC_INST_LFSX 0x7c00042e
+#define PPC_INST_STFSX 0x7c00052e
+#define PPC_INST_LFDX 0x7c0004ae
+#define PPC_INST_STFDX 0x7c0005ae
+#define PPC_INST_LVX 0x7c0000ce
+#define PPC_INST_STVX 0x7c0001ce
/* macros to insert fields into opcodes */
#define ___PPC_RA(a) (((a) & 0x1f) << 16)
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index 4a90634..35c00d7 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -160,12 +160,18 @@ struct of_drconf_cell {
#define OV5_PFO_HW_ENCR 0x1120 /* PFO Encryption Accelerator */
#define OV5_SUB_PROCESSORS 0x1501 /* 1,2,or 4 Sub-Processors supported */
#define OV5_XIVE_EXPLOIT 0x1701 /* XIVE exploitation supported */
-#define OV5_MMU_RADIX_300 0x1880 /* ISA v3.00 radix MMU supported */
-#define OV5_MMU_HASH_300 0x1840 /* ISA v3.00 hash MMU supported */
-#define OV5_MMU_SEGM_RADIX 0x1820 /* radix mode (no segmentation) */
-#define OV5_MMU_PROC_TBL 0x1810 /* hcall selects SLB or proc table */
-#define OV5_MMU_SLB 0x1800 /* always use SLB */
-#define OV5_MMU_GTSE 0x1808 /* Guest translation shootdown */
+/* MMU Base Architecture */
+#define OV5_MMU_SUPPORT 0x18C0 /* MMU Mode Support Mask */
+#define OV5_MMU_HASH 0x1800 /* Hash MMU Only */
+#define OV5_MMU_RADIX 0x1840 /* Radix MMU Only */
+#define OV5_MMU_EITHER 0x1880 /* Hash or Radix Supported */
+#define OV5_MMU_DYNAMIC 0x18C0 /* Hash or Radix Can Switch Later */
+#define OV5_NMMU 0x1820 /* Nest MMU Available */
+/* Hash Table Extensions */
+#define OV5_HASH_SEG_TBL 0x1980 /* In Memory Segment Tables Available */
+#define OV5_HASH_GTSE 0x1940 /* Guest Translation Shoot Down Avail */
+/* Radix Table Extensions */
+#define OV5_RADIX_GTSE 0x1A40 /* Guest Translation Shoot Down Avail */
/* Option Vector 6: IBM PAPR hints */
#define OV6_LINUX 0x02 /* Linux is our OS */
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 4b369d8..1c94708 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -387,3 +387,4 @@ SYSCALL(copy_file_range)
COMPAT_SYS_SPU(preadv2)
COMPAT_SYS_SPU(pwritev2)
SYSCALL(kexec_file_load)
+SYSCALL(statx)
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index eb1acee..9ba11db 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -12,7 +12,7 @@
#include <uapi/asm/unistd.h>
-#define NR_syscalls 383
+#define NR_syscalls 384
#define __NR__exit __NR_exit
diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h
index 44583a5..58e2ec0 100644
--- a/arch/powerpc/include/uapi/asm/socket.h
+++ b/arch/powerpc/include/uapi/asm/socket.h
@@ -99,4 +99,10 @@
#define SCM_TIMESTAMPING_OPT_STATS 54
+#define SO_MEMINFO 55
+
+#define SO_INCOMING_NAPI_ID 56
+
+#define SO_COOKIE 57
+
#endif /* _ASM_POWERPC_SOCKET_H */
diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h
index 2f26335..b85f142 100644
--- a/arch/powerpc/include/uapi/asm/unistd.h
+++ b/arch/powerpc/include/uapi/asm/unistd.h
@@ -393,5 +393,6 @@
#define __NR_preadv2 380
#define __NR_pwritev2 381
#define __NR_kexec_file_load 382
+#define __NR_statx 383
#endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index bb7a189..e79b9da 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -77,6 +77,7 @@ extern void __flush_tlb_power8(unsigned int action);
extern void __flush_tlb_power9(unsigned int action);
extern long __machine_check_early_realmode_p7(struct pt_regs *regs);
extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
+extern long __machine_check_early_realmode_p9(struct pt_regs *regs);
#endif /* CONFIG_PPC64 */
#if defined(CONFIG_E500)
extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec);
@@ -540,6 +541,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.cpu_setup = __setup_cpu_power9,
.cpu_restore = __restore_cpu_power9,
.flush_tlb = __flush_tlb_power9,
+ .machine_check_early = __machine_check_early_realmode_p9,
.platform = "power9",
},
{ /* Power9 */
@@ -559,6 +561,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.cpu_setup = __setup_cpu_power9,
.cpu_restore = __restore_cpu_power9,
.flush_tlb = __flush_tlb_power9,
+ .machine_check_early = __machine_check_early_realmode_p9,
.platform = "power9",
},
{ /* Cell Broadband Engine */
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 5f61cc0..6fd0821 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -276,19 +276,21 @@
*/
andis. r4,r3,PSSCR_EC_ESL_MASK_SHIFTED
clrldi r3,r3,60 /* r3 = Bits[60:63] = Requested Level (RL) */
- bne 1f
+ bne .Lhandle_esl_ec_set
IDLE_STATE_ENTER_SEQ(PPC_STOP)
li r3,0 /* Since we didn't lose state, return 0 */
b pnv_wakeup_noloss
+
+.Lhandle_esl_ec_set:
/*
* Check if the requested state is a deep idle state.
*/
-1: LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
+ LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
ld r4,ADDROFF(pnv_first_deep_stop_state)(r5)
cmpd r3,r4
- bge 2f
+ bge .Lhandle_deep_stop
IDLE_STATE_ENTER_SEQ_NORET(PPC_STOP)
-2:
+.Lhandle_deep_stop:
/*
* Entering deep idle state.
* Clear thread bit in PACA_CORE_IDLE_STATE, save SPRs to
@@ -447,9 +449,23 @@
_GLOBAL(pnv_wakeup_tb_loss)
ld r1,PACAR1(r13)
/*
- * Before entering any idle state, the NVGPRs are saved in the stack
- * and they are restored before switching to the process context. Hence
- * until they are restored, they are free to be used.
+ * Before entering any idle state, the NVGPRs are saved in the stack.
+ * If there was a state loss, or PACA_NAPSTATELOST was set, then the
+ * NVGPRs are restored. If we are here, it is likely that state is lost,
+ * but not guaranteed -- neither ISA207 nor ISA300 tests to reach
+ * here are the same as the test to restore NVGPRS:
+ * PACA_THREAD_IDLE_STATE test for ISA207, PSSCR test for ISA300,
+ * and SRR1 test for restoring NVGPRs.
+ *
+ * We are about to clobber NVGPRs now, so set NAPSTATELOST to
+ * guarantee they will always be restored. This might be tightened
+ * with careful reading of specs (particularly for ISA300) but this
+ * is already a slow wakeup path and it's simpler to be safe.
+ */
+ li r0,1
+ stb r0,PACA_NAPSTATELOST(r13)
+
+ /*
*
* Save SRR1 and LR in NVGPRs as they might be clobbered in
* opal_call() (called in CHECK_HMI_INTERRUPT). SRR1 is required
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index c6923ff..a1475e6 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -58,6 +58,15 @@ static void mce_set_error_info(struct machine_check_event *mce,
case MCE_ERROR_TYPE_TLB:
mce->u.tlb_error.tlb_error_type = mce_err->u.tlb_error_type;
break;
+ case MCE_ERROR_TYPE_USER:
+ mce->u.user_error.user_error_type = mce_err->u.user_error_type;
+ break;
+ case MCE_ERROR_TYPE_RA:
+ mce->u.ra_error.ra_error_type = mce_err->u.ra_error_type;
+ break;
+ case MCE_ERROR_TYPE_LINK:
+ mce->u.link_error.link_error_type = mce_err->u.link_error_type;
+ break;
case MCE_ERROR_TYPE_UNKNOWN:
default:
break;
@@ -90,13 +99,14 @@ void save_mce_event(struct pt_regs *regs, long handled,
mce->gpr3 = regs->gpr[3];
mce->in_use = 1;
- mce->initiator = MCE_INITIATOR_CPU;
/* Mark it recovered if we have handled it and MSR(RI=1). */
if (handled && (regs->msr & MSR_RI))
mce->disposition = MCE_DISPOSITION_RECOVERED;
else
mce->disposition = MCE_DISPOSITION_NOT_RECOVERED;
- mce->severity = MCE_SEV_ERROR_SYNC;
+
+ mce->initiator = mce_err->initiator;
+ mce->severity = mce_err->severity;
/*
* Populate the mce error_type and type-specific error_type.
@@ -115,6 +125,15 @@ void save_mce_event(struct pt_regs *regs, long handled,
} else if (mce->error_type == MCE_ERROR_TYPE_ERAT) {
mce->u.erat_error.effective_address_provided = true;
mce->u.erat_error.effective_address = addr;
+ } else if (mce->error_type == MCE_ERROR_TYPE_USER) {
+ mce->u.user_error.effective_address_provided = true;
+ mce->u.user_error.effective_address = addr;
+ } else if (mce->error_type == MCE_ERROR_TYPE_RA) {
+ mce->u.ra_error.effective_address_provided = true;
+ mce->u.ra_error.effective_address = addr;
+ } else if (mce->error_type == MCE_ERROR_TYPE_LINK) {
+ mce->u.link_error.effective_address_provided = true;
+ mce->u.link_error.effective_address = addr;
} else if (mce->error_type == MCE_ERROR_TYPE_UE) {
mce->u.ue_error.effective_address_provided = true;
mce->u.ue_error.effective_address = addr;
@@ -239,6 +258,29 @@ void machine_check_print_event_info(struct machine_check_event *evt)
"Parity",
"Multihit",
};
+ static const char *mc_user_types[] = {
+ "Indeterminate",
+ "tlbie(l) invalid",
+ };
+ static const char *mc_ra_types[] = {
+ "Indeterminate",
+ "Instruction fetch (bad)",
+ "Page table walk ifetch (bad)",
+ "Page table walk ifetch (foreign)",
+ "Load (bad)",
+ "Store (bad)",
+ "Page table walk Load/Store (bad)",
+ "Page table walk Load/Store (foreign)",
+ "Load/Store (foreign)",
+ };
+ static const char *mc_link_types[] = {
+ "Indeterminate",
+ "Instruction fetch (timeout)",
+ "Page table walk ifetch (timeout)",
+ "Load (timeout)",
+ "Store (timeout)",
+ "Page table walk Load/Store (timeout)",
+ };
/* Print things out */
if (evt->version != MCE_V1) {
@@ -315,6 +357,36 @@ void machine_check_print_event_info(struct machine_check_event *evt)
printk("%s Effective address: %016llx\n",
level, evt->u.tlb_error.effective_address);
break;
+ case MCE_ERROR_TYPE_USER:
+ subtype = evt->u.user_error.user_error_type <
+ ARRAY_SIZE(mc_user_types) ?
+ mc_user_types[evt->u.user_error.user_error_type]
+ : "Unknown";
+ printk("%s Error type: User [%s]\n", level, subtype);
+ if (evt->u.user_error.effective_address_provided)
+ printk("%s Effective address: %016llx\n",
+ level, evt->u.user_error.effective_address);
+ break;
+ case MCE_ERROR_TYPE_RA:
+ subtype = evt->u.ra_error.ra_error_type <
+ ARRAY_SIZE(mc_ra_types) ?
+ mc_ra_types[evt->u.ra_error.ra_error_type]
+ : "Unknown";
+ printk("%s Error type: Real address [%s]\n", level, subtype);
+ if (evt->u.ra_error.effective_address_provided)
+ printk("%s Effective address: %016llx\n",
+ level, evt->u.ra_error.effective_address);
+ break;
+ case MCE_ERROR_TYPE_LINK:
+ subtype = evt->u.link_error.link_error_type <
+ ARRAY_SIZE(mc_link_types) ?
+ mc_link_types[evt->u.link_error.link_error_type]
+ : "Unknown";
+ printk("%s Error type: Link [%s]\n", level, subtype);
+ if (evt->u.link_error.effective_address_provided)
+ printk("%s Effective address: %016llx\n",
+ level, evt->u.link_error.effective_address);
+ break;
default:
case MCE_ERROR_TYPE_UNKNOWN:
printk("%s Error type: Unknown\n", level);
@@ -341,6 +413,18 @@ uint64_t get_mce_fault_addr(struct machine_check_event *evt)
if (evt->u.tlb_error.effective_address_provided)
return evt->u.tlb_error.effective_address;
break;
+ case MCE_ERROR_TYPE_USER:
+ if (evt->u.user_error.effective_address_provided)
+ return evt->u.user_error.effective_address;
+ break;
+ case MCE_ERROR_TYPE_RA:
+ if (evt->u.ra_error.effective_address_provided)
+ return evt->u.ra_error.effective_address;
+ break;
+ case MCE_ERROR_TYPE_LINK:
+ if (evt->u.link_error.effective_address_provided)
+ return evt->u.link_error.effective_address;
+ break;
default:
case MCE_ERROR_TYPE_UNKNOWN:
break;
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index 7353991..763d6f5 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -116,6 +116,51 @@ static void flush_and_reload_slb(void)
}
#endif
+static void flush_erat(void)
+{
+ asm volatile(PPC_INVALIDATE_ERAT : : :"memory");
+}
+
+#define MCE_FLUSH_SLB 1
+#define MCE_FLUSH_TLB 2
+#define MCE_FLUSH_ERAT 3
+
+static int mce_flush(int what)
+{
+#ifdef CONFIG_PPC_STD_MMU_64
+ if (what == MCE_FLUSH_SLB) {
+ flush_and_reload_slb();
+ return 1;
+ }
+#endif
+ if (what == MCE_FLUSH_ERAT) {
+ flush_erat();
+ return 1;
+ }
+ if (what == MCE_FLUSH_TLB) {
+ if (cur_cpu_spec && cur_cpu_spec->flush_tlb) {
+ cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_GLOBAL);
+ return 1;
+ }
+ }
+
+ return 0;
+}
+
+static int mce_handle_flush_derrors(uint64_t dsisr, uint64_t slb, uint64_t tlb, uint64_t erat)
+{
+ if ((dsisr & slb) && mce_flush(MCE_FLUSH_SLB))
+ dsisr &= ~slb;
+ if ((dsisr & erat) && mce_flush(MCE_FLUSH_ERAT))
+ dsisr &= ~erat;
+ if ((dsisr & tlb) && mce_flush(MCE_FLUSH_TLB))
+ dsisr &= ~tlb;
+ /* Any other errors we don't understand? */
+ if (dsisr)
+ return 0;
+ return 1;
+}
+
static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits)
{
long handled = 1;
@@ -281,6 +326,9 @@ long __machine_check_early_realmode_p7(struct pt_regs *regs)
long handled = 1;
struct mce_error_info mce_error_info = { 0 };
+ mce_error_info.severity = MCE_SEV_ERROR_SYNC;
+ mce_error_info.initiator = MCE_INITIATOR_CPU;
+
srr1 = regs->msr;
nip = regs->nip;
@@ -352,6 +400,9 @@ long __machine_check_early_realmode_p8(struct pt_regs *regs)
long handled = 1;
struct mce_error_info mce_error_info = { 0 };
+ mce_error_info.severity = MCE_SEV_ERROR_SYNC;
+ mce_error_info.initiator = MCE_INITIATOR_CPU;
+
srr1 = regs->msr;
nip = regs->nip;
@@ -372,3 +423,189 @@ long __machine_check_early_realmode_p8(struct pt_regs *regs)
save_mce_event(regs, handled, &mce_error_info, nip, addr);
return handled;
}
+
+static int mce_handle_derror_p9(struct pt_regs *regs)
+{
+ uint64_t dsisr = regs->dsisr;
+
+ return mce_handle_flush_derrors(dsisr,
+ P9_DSISR_MC_SLB_PARITY_MFSLB |
+ P9_DSISR_MC_SLB_MULTIHIT_MFSLB,
+
+ P9_DSISR_MC_TLB_MULTIHIT_MFTLB,
+
+ P9_DSISR_MC_ERAT_MULTIHIT);
+}
+
+static int mce_handle_ierror_p9(struct pt_regs *regs)
+{
+ uint64_t srr1 = regs->msr;
+
+ switch (P9_SRR1_MC_IFETCH(srr1)) {
+ case P9_SRR1_MC_IFETCH_SLB_PARITY:
+ case P9_SRR1_MC_IFETCH_SLB_MULTIHIT:
+ return mce_flush(MCE_FLUSH_SLB);
+ case P9_SRR1_MC_IFETCH_TLB_MULTIHIT:
+ return mce_flush(MCE_FLUSH_TLB);
+ case P9_SRR1_MC_IFETCH_ERAT_MULTIHIT:
+ return mce_flush(MCE_FLUSH_ERAT);
+ default:
+ return 0;
+ }
+}
+
+static void mce_get_derror_p9(struct pt_regs *regs,
+ struct mce_error_info *mce_err, uint64_t *addr)
+{
+ uint64_t dsisr = regs->dsisr;
+
+ mce_err->severity = MCE_SEV_ERROR_SYNC;
+ mce_err->initiator = MCE_INITIATOR_CPU;
+
+ if (dsisr & P9_DSISR_MC_USER_TLBIE)
+ *addr = regs->nip;
+ else
+ *addr = regs->dar;
+
+ if (dsisr & P9_DSISR_MC_UE) {
+ mce_err->error_type = MCE_ERROR_TYPE_UE;
+ mce_err->u.ue_error_type = MCE_UE_ERROR_LOAD_STORE;
+ } else if (dsisr & P9_DSISR_MC_UE_TABLEWALK) {
+ mce_err->error_type = MCE_ERROR_TYPE_UE;
+ mce_err->u.ue_error_type = MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE;
+ } else if (dsisr & P9_DSISR_MC_LINK_LOAD_TIMEOUT) {
+ mce_err->error_type = MCE_ERROR_TYPE_LINK;
+ mce_err->u.link_error_type = MCE_LINK_ERROR_LOAD_TIMEOUT;
+ } else if (dsisr & P9_DSISR_MC_LINK_TABLEWALK_TIMEOUT) {
+ mce_err->error_type = MCE_ERROR_TYPE_LINK;
+ mce_err->u.link_error_type = MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT;
+ } else if (dsisr & P9_DSISR_MC_ERAT_MULTIHIT) {
+ mce_err->error_type = MCE_ERROR_TYPE_ERAT;
+ mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
+ } else if (dsisr & P9_DSISR_MC_TLB_MULTIHIT_MFTLB) {
+ mce_err->error_type = MCE_ERROR_TYPE_TLB;
+ mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
+ } else if (dsisr & P9_DSISR_MC_USER_TLBIE) {
+ mce_err->error_type = MCE_ERROR_TYPE_USER;
+ mce_err->u.user_error_type = MCE_USER_ERROR_TLBIE;
+ } else if (dsisr & P9_DSISR_MC_SLB_PARITY_MFSLB) {
+ mce_err->error_type = MCE_ERROR_TYPE_SLB;
+ mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY;
+ } else if (dsisr & P9_DSISR_MC_SLB_MULTIHIT_MFSLB) {
+ mce_err->error_type = MCE_ERROR_TYPE_SLB;
+ mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
+ } else if (dsisr & P9_DSISR_MC_RA_LOAD) {
+ mce_err->error_type = MCE_ERROR_TYPE_RA;
+ mce_err->u.ra_error_type = MCE_RA_ERROR_LOAD;
+ } else if (dsisr & P9_DSISR_MC_RA_TABLEWALK) {
+ mce_err->error_type = MCE_ERROR_TYPE_RA;
+ mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE;
+ } else if (dsisr & P9_DSISR_MC_RA_TABLEWALK_FOREIGN) {
+ mce_err->error_type = MCE_ERROR_TYPE_RA;
+ mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN;
+ } else if (dsisr & P9_DSISR_MC_RA_FOREIGN) {
+ mce_err->error_type = MCE_ERROR_TYPE_RA;
+ mce_err->u.ra_error_type = MCE_RA_ERROR_LOAD_STORE_FOREIGN;
+ }
+}
+
+static void mce_get_ierror_p9(struct pt_regs *regs,
+ struct mce_error_info *mce_err, uint64_t *addr)
+{
+ uint64_t srr1 = regs->msr;
+
+ switch (P9_SRR1_MC_IFETCH(srr1)) {
+ case P9_SRR1_MC_IFETCH_RA_ASYNC_STORE:
+ case P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT:
+ mce_err->severity = MCE_SEV_FATAL;
+ break;
+ default:
+ mce_err->severity = MCE_SEV_ERROR_SYNC;
+ break;
+ }
+
+ mce_err->initiator = MCE_INITIATOR_CPU;
+
+ *addr = regs->nip;
+
+ switch (P9_SRR1_MC_IFETCH(srr1)) {
+ case P9_SRR1_MC_IFETCH_UE:
+ mce_err->error_type = MCE_ERROR_TYPE_UE;
+ mce_err->u.ue_error_type = MCE_UE_ERROR_IFETCH;
+ break;
+ case P9_SRR1_MC_IFETCH_SLB_PARITY:
+ mce_err->error_type = MCE_ERROR_TYPE_SLB;
+ mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY;
+ break;
+ case P9_SRR1_MC_IFETCH_SLB_MULTIHIT:
+ mce_err->error_type = MCE_ERROR_TYPE_SLB;
+ mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
+ break;
+ case P9_SRR1_MC_IFETCH_ERAT_MULTIHIT:
+ mce_err->error_type = MCE_ERROR_TYPE_ERAT;
+ mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
+ break;
+ case P9_SRR1_MC_IFETCH_TLB_MULTIHIT:
+ mce_err->error_type = MCE_ERROR_TYPE_TLB;
+ mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
+ break;
+ case P9_SRR1_MC_IFETCH_UE_TLB_RELOAD:
+ mce_err->error_type = MCE_ERROR_TYPE_UE;
+ mce_err->u.ue_error_type = MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH;
+ break;
+ case P9_SRR1_MC_IFETCH_LINK_TIMEOUT:
+ mce_err->error_type = MCE_ERROR_TYPE_LINK;
+ mce_err->u.link_error_type = MCE_LINK_ERROR_IFETCH_TIMEOUT;
+ break;
+ case P9_SRR1_MC_IFETCH_LINK_TABLEWALK_TIMEOUT:
+ mce_err->error_type = MCE_ERROR_TYPE_LINK;
+ mce_err->u.link_error_type = MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT;
+ break;
+ case P9_SRR1_MC_IFETCH_RA:
+ mce_err->error_type = MCE_ERROR_TYPE_RA;
+ mce_err->u.ra_error_type = MCE_RA_ERROR_IFETCH;
+ break;
+ case P9_SRR1_MC_IFETCH_RA_TABLEWALK:
+ mce_err->error_type = MCE_ERROR_TYPE_RA;
+ mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH;
+ break;
+ case P9_SRR1_MC_IFETCH_RA_ASYNC_STORE:
+ mce_err->error_type = MCE_ERROR_TYPE_RA;
+ mce_err->u.ra_error_type = MCE_RA_ERROR_STORE;
+ break;
+ case P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT:
+ mce_err->error_type = MCE_ERROR_TYPE_LINK;
+ mce_err->u.link_error_type = MCE_LINK_ERROR_STORE_TIMEOUT;
+ break;
+ case P9_SRR1_MC_IFETCH_RA_TABLEWALK_FOREIGN:
+ mce_err->error_type = MCE_ERROR_TYPE_RA;
+ mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN;
+ break;
+ default:
+ break;
+ }
+}
+
+long __machine_check_early_realmode_p9(struct pt_regs *regs)
+{
+ uint64_t nip, addr;
+ long handled;
+ struct mce_error_info mce_error_info = { 0 };
+
+ nip = regs->nip;
+
+ if (P9_SRR1_MC_LOADSTORE(regs->msr)) {
+ handled = mce_handle_derror_p9(regs);
+ mce_get_derror_p9(regs, &mce_error_info, &addr);
+ } else {
+ handled = mce_handle_ierror_p9(regs);
+ mce_get_ierror_p9(regs, &mce_error_info, &addr);
+ }
+
+ /* Handle UE error. */
+ if (mce_error_info.error_type == MCE_ERROR_TYPE_UE)
+ handled = mce_handle_ue_error(regs);
+
+ save_mce_event(regs, handled, &mce_error_info, nip, addr);
+ return handled;
+}
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index a394454..1c1b44e 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -168,6 +168,14 @@ static unsigned long __initdata prom_tce_alloc_start;
static unsigned long __initdata prom_tce_alloc_end;
#endif
+static bool __initdata prom_radix_disable;
+
+struct platform_support {
+ bool hash_mmu;
+ bool radix_mmu;
+ bool radix_gtse;
+};
+
/* Platforms codes are now obsolete in the kernel. Now only used within this
* file and ultimately gone too. Feel free to change them if you need, they
* are not shared with anything outside of this file anymore
@@ -626,6 +634,12 @@ static void __init early_cmdline_parse(void)
prom_memory_limit = ALIGN(prom_memory_limit, 0x1000000);
#endif
}
+
+ opt = strstr(prom_cmd_line, "disable_radix");
+ if (opt) {
+ prom_debug("Radix disabled from cmdline\n");
+ prom_radix_disable = true;
+ }
}
#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
@@ -695,6 +709,8 @@ struct option_vector5 {
u8 byte22;
u8 intarch;
u8 mmu;
+ u8 hash_ext;
+ u8 radix_ext;
} __packed;
struct option_vector6 {
@@ -850,8 +866,9 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = {
.reserved3 = 0,
.subprocessors = 1,
.intarch = 0,
- .mmu = OV5_FEAT(OV5_MMU_RADIX_300) | OV5_FEAT(OV5_MMU_HASH_300) |
- OV5_FEAT(OV5_MMU_PROC_TBL) | OV5_FEAT(OV5_MMU_GTSE),
+ .mmu = 0,
+ .hash_ext = 0,
+ .radix_ext = 0,
},
/* option vector 6: IBM PAPR hints */
@@ -990,6 +1007,92 @@ static int __init prom_count_smt_threads(void)
}
+static void __init prom_parse_mmu_model(u8 val,
+ struct platform_support *support)
+{
+ switch (val) {
+ case OV5_FEAT(OV5_MMU_DYNAMIC):
+ case OV5_FEAT(OV5_MMU_EITHER): /* Either Available */
+ prom_debug("MMU - either supported\n");
+ support->radix_mmu = !prom_radix_disable;
+ support->hash_mmu = true;
+ break;
+ case OV5_FEAT(OV5_MMU_RADIX): /* Only Radix */
+ prom_debug("MMU - radix only\n");
+ if (prom_radix_disable) {
+ /*
+ * If we __have__ to do radix, we're better off ignoring
+ * the command line rather than not booting.
+ */
+ prom_printf("WARNING: Ignoring cmdline option disable_radix\n");
+ }
+ support->radix_mmu = true;
+ break;
+ case OV5_FEAT(OV5_MMU_HASH):
+ prom_debug("MMU - hash only\n");
+ support->hash_mmu = true;
+ break;
+ default:
+ prom_debug("Unknown mmu support option: 0x%x\n", val);
+ break;
+ }
+}
+
+static void __init prom_parse_platform_support(u8 index, u8 val,
+ struct platform_support *support)
+{
+ switch (index) {
+ case OV5_INDX(OV5_MMU_SUPPORT): /* MMU Model */
+ prom_parse_mmu_model(val & OV5_FEAT(OV5_MMU_SUPPORT), support);
+ break;
+ case OV5_INDX(OV5_RADIX_GTSE): /* Radix Extensions */
+ if (val & OV5_FEAT(OV5_RADIX_GTSE)) {
+ prom_debug("Radix - GTSE supported\n");
+ support->radix_gtse = true;
+ }
+ break;
+ }
+}
+
+static void __init prom_check_platform_support(void)
+{
+ struct platform_support supported = {
+ .hash_mmu = false,
+ .radix_mmu = false,
+ .radix_gtse = false
+ };
+ int prop_len = prom_getproplen(prom.chosen,
+ "ibm,arch-vec-5-platform-support");
+ if (prop_len > 1) {
+ int i;
+ u8 vec[prop_len];
+ prom_debug("Found ibm,arch-vec-5-platform-support, len: %d\n",
+ prop_len);
+ prom_getprop(prom.chosen, "ibm,arch-vec-5-platform-support",
+ &vec, sizeof(vec));
+ for (i = 0; i < prop_len; i += 2) {
+ prom_debug("%d: index = 0x%x val = 0x%x\n", i / 2
+ , vec[i]
+ , vec[i + 1]);
+ prom_parse_platform_support(vec[i], vec[i + 1],
+ &supported);
+ }
+ }
+
+ if (supported.radix_mmu && supported.radix_gtse) {
+ /* Radix preferred - but we require GTSE for now */
+ prom_debug("Asking for radix with GTSE\n");
+ ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_RADIX);
+ ibm_architecture_vec.vec5.radix_ext = OV5_FEAT(OV5_RADIX_GTSE);
+ } else if (supported.hash_mmu) {
+ /* Default to hash mmu (if we can) */
+ prom_debug("Asking for hash\n");
+ ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_HASH);
+ } else {
+ /* We're probably on a legacy hypervisor */
+ prom_debug("Assuming legacy hash support\n");
+ }
+}
static void __init prom_send_capabilities(void)
{
@@ -997,6 +1100,9 @@ static void __init prom_send_capabilities(void)
prom_arg_t ret;
u32 cores;
+ /* Check ibm,arch-vec-5-platform-support and fixup vec5 if required */
+ prom_check_platform_support();
+
root = call_prom("open", 1, 1, ADDR("/"));
if (root != 0) {
/* We need to tell the FW about the number of cores we support.
@@ -2993,6 +3099,11 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
*/
prom_check_initrd(r3, r4);
+ /*
+ * Do early parsing of command line
+ */
+ early_cmdline_parse();
+
#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
/*
* On pSeries, inform the firmware about our capabilities
@@ -3009,11 +3120,6 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
copy_and_flush(0, kbase, 0x100, 0);
/*
- * Do early parsing of command line
- */
- early_cmdline_parse();
-
- /*
* Initialize memory management within prom_init
*/
prom_init_mem();
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index adf2084..9cfaa8b 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -408,7 +408,10 @@ static void init_cache_info(struct ppc_cache_info *info, u32 size, u32 lsize,
info->line_size = lsize;
info->block_size = bsize;
info->log_block_size = __ilog2(bsize);
- info->blocks_per_page = PAGE_SIZE / bsize;
+ if (bsize)
+ info->blocks_per_page = PAGE_SIZE / bsize;
+ else
+ info->blocks_per_page = 0;
if (sets == 0)
info->assoc = 0xffff;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index f3158fb..8c68145 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -601,7 +601,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
hva, NULL, NULL);
if (ptep) {
pte = kvmppc_read_update_linux_pte(ptep, 1);
- if (pte_write(pte))
+ if (__pte_write(pte))
write_ok = 1;
}
local_irq_restore(flags);
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 6fca970..ce6f212 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -256,7 +256,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
}
pte = kvmppc_read_update_linux_pte(ptep, writing);
if (pte_present(pte) && !pte_protnone(pte)) {
- if (writing && !pte_write(pte))
+ if (writing && !__pte_write(pte))
/* make the actual HPTE be read-only */
ptel = hpte_make_readonly(ptel);
is_ci = pte_ci(pte);
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 0e649d7..2b5e090 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -20,6 +20,7 @@
obj64-$(CONFIG_SMP) += locks.o
obj64-$(CONFIG_ALTIVEC) += vmx-helper.o
+obj64-$(CONFIG_KPROBES_SANITY_TEST) += test_emulate_step.o
obj-y += checksum_$(BITS).o checksum_wrappers.o
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 846dba2..9c542ec 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -1799,8 +1799,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
goto instr_done;
case LARX:
- if (regs->msr & MSR_LE)
- return 0;
if (op.ea & (size - 1))
break; /* can't handle misaligned */
if (!address_ok(regs, op.ea, size))
@@ -1823,8 +1821,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
goto ldst_done;
case STCX:
- if (regs->msr & MSR_LE)
- return 0;
if (op.ea & (size - 1))
break; /* can't handle misaligned */
if (!address_ok(regs, op.ea, size))
@@ -1849,8 +1845,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
goto ldst_done;
case LOAD:
- if (regs->msr & MSR_LE)
- return 0;
err = read_mem(®s->gpr[op.reg], op.ea, size, regs);
if (!err) {
if (op.type & SIGNEXT)
@@ -1862,8 +1856,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
#ifdef CONFIG_PPC_FPU
case LOAD_FP:
- if (regs->msr & MSR_LE)
- return 0;
if (size == 4)
err = do_fp_load(op.reg, do_lfs, op.ea, size, regs);
else
@@ -1872,15 +1864,11 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
#endif
#ifdef CONFIG_ALTIVEC
case LOAD_VMX:
- if (regs->msr & MSR_LE)
- return 0;
err = do_vec_load(op.reg, do_lvx, op.ea & ~0xfUL, regs);
goto ldst_done;
#endif
#ifdef CONFIG_VSX
case LOAD_VSX:
- if (regs->msr & MSR_LE)
- return 0;
err = do_vsx_load(op.reg, do_lxvd2x, op.ea, regs);
goto ldst_done;
#endif
@@ -1903,8 +1891,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
goto instr_done;
case STORE:
- if (regs->msr & MSR_LE)
- return 0;
if ((op.type & UPDATE) && size == sizeof(long) &&
op.reg == 1 && op.update_reg == 1 &&
!(regs->msr & MSR_PR) &&
@@ -1917,8 +1903,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
#ifdef CONFIG_PPC_FPU
case STORE_FP:
- if (regs->msr & MSR_LE)
- return 0;
if (size == 4)
err = do_fp_store(op.reg, do_stfs, op.ea, size, regs);
else
@@ -1927,15 +1911,11 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
#endif
#ifdef CONFIG_ALTIVEC
case STORE_VMX:
- if (regs->msr & MSR_LE)
- return 0;
err = do_vec_store(op.reg, do_stvx, op.ea & ~0xfUL, regs);
goto ldst_done;
#endif
#ifdef CONFIG_VSX
case STORE_VSX:
- if (regs->msr & MSR_LE)
- return 0;
err = do_vsx_store(op.reg, do_stxvd2x, op.ea, regs);
goto ldst_done;
#endif
diff --git a/arch/powerpc/lib/test_emulate_step.c b/arch/powerpc/lib/test_emulate_step.c
new file mode 100644
index 0000000..2534c14
--- /dev/null
+++ b/arch/powerpc/lib/test_emulate_step.c
@@ -0,0 +1,434 @@
+/*
+ * Simple sanity test for emulate_step load/store instructions.
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) "emulate_step_test: " fmt
+
+#include <linux/ptrace.h>
+#include <asm/sstep.h>
+#include <asm/ppc-opcode.h>
+
+#define IMM_L(i) ((uintptr_t)(i) & 0xffff)
+
+/*
+ * Defined with TEST_ prefix so it does not conflict with other
+ * definitions.
+ */
+#define TEST_LD(r, base, i) (PPC_INST_LD | ___PPC_RT(r) | \
+ ___PPC_RA(base) | IMM_L(i))
+#define TEST_LWZ(r, base, i) (PPC_INST_LWZ | ___PPC_RT(r) | \
+ ___PPC_RA(base) | IMM_L(i))
+#define TEST_LWZX(t, a, b) (PPC_INST_LWZX | ___PPC_RT(t) | \
+ ___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STD(r, base, i) (PPC_INST_STD | ___PPC_RS(r) | \
+ ___PPC_RA(base) | ((i) & 0xfffc))
+#define TEST_LDARX(t, a, b, eh) (PPC_INST_LDARX | ___PPC_RT(t) | \
+ ___PPC_RA(a) | ___PPC_RB(b) | \
+ __PPC_EH(eh))
+#define TEST_STDCX(s, a, b) (PPC_INST_STDCX | ___PPC_RS(s) | \
+ ___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LFSX(t, a, b) (PPC_INST_LFSX | ___PPC_RT(t) | \
+ ___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STFSX(s, a, b) (PPC_INST_STFSX | ___PPC_RS(s) | \
+ ___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LFDX(t, a, b) (PPC_INST_LFDX | ___PPC_RT(t) | \
+ ___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STFDX(s, a, b) (PPC_INST_STFDX | ___PPC_RS(s) | \
+ ___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LVX(t, a, b) (PPC_INST_LVX | ___PPC_RT(t) | \
+ ___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STVX(s, a, b) (PPC_INST_STVX | ___PPC_RS(s) | \
+ ___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LXVD2X(s, a, b) (PPC_INST_LXVD2X | VSX_XX1((s), R##a, R##b))
+#define TEST_STXVD2X(s, a, b) (PPC_INST_STXVD2X | VSX_XX1((s), R##a, R##b))
+
+
+static void __init init_pt_regs(struct pt_regs *regs)
+{
+ static unsigned long msr;
+ static bool msr_cached;
+
+ memset(regs, 0, sizeof(struct pt_regs));
+
+ if (likely(msr_cached)) {
+ regs->msr = msr;
+ return;
+ }
+
+ asm volatile("mfmsr %0" : "=r"(regs->msr));
+
+ regs->msr |= MSR_FP;
+ regs->msr |= MSR_VEC;
+ regs->msr |= MSR_VSX;
+
+ msr = regs->msr;
+ msr_cached = true;
+}
+
+static void __init show_result(char *ins, char *result)
+{
+ pr_info("%-14s : %s\n", ins, result);
+}
+
+static void __init test_ld(void)
+{
+ struct pt_regs regs;
+ unsigned long a = 0x23;
+ int stepped = -1;
+
+ init_pt_regs(®s);
+ regs.gpr[3] = (unsigned long) &a;
+
+ /* ld r5, 0(r3) */
+ stepped = emulate_step(®s, TEST_LD(5, 3, 0));
+
+ if (stepped == 1 && regs.gpr[5] == a)
+ show_result("ld", "PASS");
+ else
+ show_result("ld", "FAIL");
+}
+
+static void __init test_lwz(void)
+{
+ struct pt_regs regs;
+ unsigned int a = 0x4545;
+ int stepped = -1;
+
+ init_pt_regs(®s);
+ regs.gpr[3] = (unsigned long) &a;
+
+ /* lwz r5, 0(r3) */
+ stepped = emulate_step(®s, TEST_LWZ(5, 3, 0));
+
+ if (stepped == 1 && regs.gpr[5] == a)
+ show_result("lwz", "PASS");
+ else
+ show_result("lwz", "FAIL");
+}
+
+static void __init test_lwzx(void)
+{
+ struct pt_regs regs;
+ unsigned int a[3] = {0x0, 0x0, 0x1234};
+ int stepped = -1;
+
+ init_pt_regs(®s);
+ regs.gpr[3] = (unsigned long) a;
+ regs.gpr[4] = 8;
+ regs.gpr[5] = 0x8765;
+
+ /* lwzx r5, r3, r4 */
+ stepped = emulate_step(®s, TEST_LWZX(5, 3, 4));
+ if (stepped == 1 && regs.gpr[5] == a[2])
+ show_result("lwzx", "PASS");
+ else
+ show_result("lwzx", "FAIL");
+}
+
+static void __init test_std(void)
+{
+ struct pt_regs regs;
+ unsigned long a = 0x1234;
+ int stepped = -1;
+
+ init_pt_regs(®s);
+ regs.gpr[3] = (unsigned long) &a;
+ regs.gpr[5] = 0x5678;
+
+ /* std r5, 0(r3) */
+ stepped = emulate_step(®s, TEST_STD(5, 3, 0));
+ if (stepped == 1 || regs.gpr[5] == a)
+ show_result("std", "PASS");
+ else
+ show_result("std", "FAIL");
+}
+
+static void __init test_ldarx_stdcx(void)
+{
+ struct pt_regs regs;
+ unsigned long a = 0x1234;
+ int stepped = -1;
+ unsigned long cr0_eq = 0x1 << 29; /* eq bit of CR0 */
+
+ init_pt_regs(®s);
+ asm volatile("mfcr %0" : "=r"(regs.ccr));
+
+
+ /*** ldarx ***/
+
+ regs.gpr[3] = (unsigned long) &a;
+ regs.gpr[4] = 0;
+ regs.gpr[5] = 0x5678;
+
+ /* ldarx r5, r3, r4, 0 */
+ stepped = emulate_step(®s, TEST_LDARX(5, 3, 4, 0));
+
+ /*
+ * Don't touch 'a' here. Touching 'a' can do Load/store
+ * of 'a' which result in failure of subsequent stdcx.
+ * Instead, use hardcoded value for comparison.
+ */
+ if (stepped <= 0 || regs.gpr[5] != 0x1234) {
+ show_result("ldarx / stdcx.", "FAIL (ldarx)");
+ return;
+ }
+
+
+ /*** stdcx. ***/
+
+ regs.gpr[5] = 0x9ABC;
+
+ /* stdcx. r5, r3, r4 */
+ stepped = emulate_step(®s, TEST_STDCX(5, 3, 4));
+
+ /*
+ * Two possible scenarios that indicates successful emulation
+ * of stdcx. :
+ * 1. Reservation is active and store is performed. In this
+ * case cr0.eq bit will be set to 1.
+ * 2. Reservation is not active and store is not performed.
+ * In this case cr0.eq bit will be set to 0.
+ */
+ if (stepped == 1 && ((regs.gpr[5] == a && (regs.ccr & cr0_eq))
+ || (regs.gpr[5] != a && !(regs.ccr & cr0_eq))))
+ show_result("ldarx / stdcx.", "PASS");
+ else
+ show_result("ldarx / stdcx.", "FAIL (stdcx.)");
+}
+
+#ifdef CONFIG_PPC_FPU
+static void __init test_lfsx_stfsx(void)
+{
+ struct pt_regs regs;
+ union {
+ float a;
+ int b;
+ } c;
+ int cached_b;
+ int stepped = -1;
+
+ init_pt_regs(®s);
+
+
+ /*** lfsx ***/
+
+ c.a = 123.45;
+ cached_b = c.b;
+
+ regs.gpr[3] = (unsigned long) &c.a;
+ regs.gpr[4] = 0;
+
+ /* lfsx frt10, r3, r4 */
+ stepped = emulate_step(®s, TEST_LFSX(10, 3, 4));
+
+ if (stepped == 1)
+ show_result("lfsx", "PASS");
+ else
+ show_result("lfsx", "FAIL");
+
+
+ /*** stfsx ***/
+
+ c.a = 678.91;
+
+ /* stfsx frs10, r3, r4 */
+ stepped = emulate_step(®s, TEST_STFSX(10, 3, 4));
+
+ if (stepped == 1 && c.b == cached_b)
+ show_result("stfsx", "PASS");
+ else
+ show_result("stfsx", "FAIL");
+}
+
+static void __init test_lfdx_stfdx(void)
+{
+ struct pt_regs regs;
+ union {
+ double a;
+ long b;
+ } c;
+ long cached_b;
+ int stepped = -1;
+
+ init_pt_regs(®s);
+
+
+ /*** lfdx ***/
+
+ c.a = 123456.78;
+ cached_b = c.b;
+
+ regs.gpr[3] = (unsigned long) &c.a;
+ regs.gpr[4] = 0;
+
+ /* lfdx frt10, r3, r4 */
+ stepped = emulate_step(®s, TEST_LFDX(10, 3, 4));
+
+ if (stepped == 1)
+ show_result("lfdx", "PASS");
+ else
+ show_result("lfdx", "FAIL");
+
+
+ /*** stfdx ***/
+
+ c.a = 987654.32;
+
+ /* stfdx frs10, r3, r4 */
+ stepped = emulate_step(®s, TEST_STFDX(10, 3, 4));
+
+ if (stepped == 1 && c.b == cached_b)
+ show_result("stfdx", "PASS");
+ else
+ show_result("stfdx", "FAIL");
+}
+#else
+static void __init test_lfsx_stfsx(void)
+{
+ show_result("lfsx", "SKIP (CONFIG_PPC_FPU is not set)");
+ show_result("stfsx", "SKIP (CONFIG_PPC_FPU is not set)");
+}
+
+static void __init test_lfdx_stfdx(void)
+{
+ show_result("lfdx", "SKIP (CONFIG_PPC_FPU is not set)");
+ show_result("stfdx", "SKIP (CONFIG_PPC_FPU is not set)");
+}
+#endif /* CONFIG_PPC_FPU */
+
+#ifdef CONFIG_ALTIVEC
+static void __init test_lvx_stvx(void)
+{
+ struct pt_regs regs;
+ union {
+ vector128 a;
+ u32 b[4];
+ } c;
+ u32 cached_b[4];
+ int stepped = -1;
+
+ init_pt_regs(®s);
+
+
+ /*** lvx ***/
+
+ cached_b[0] = c.b[0] = 923745;
+ cached_b[1] = c.b[1] = 2139478;
+ cached_b[2] = c.b[2] = 9012;
+ cached_b[3] = c.b[3] = 982134;
+
+ regs.gpr[3] = (unsigned long) &c.a;
+ regs.gpr[4] = 0;
+
+ /* lvx vrt10, r3, r4 */
+ stepped = emulate_step(®s, TEST_LVX(10, 3, 4));
+
+ if (stepped == 1)
+ show_result("lvx", "PASS");
+ else
+ show_result("lvx", "FAIL");
+
+
+ /*** stvx ***/
+
+ c.b[0] = 4987513;
+ c.b[1] = 84313948;
+ c.b[2] = 71;
+ c.b[3] = 498532;
+
+ /* stvx vrs10, r3, r4 */
+ stepped = emulate_step(®s, TEST_STVX(10, 3, 4));
+
+ if (stepped == 1 && cached_b[0] == c.b[0] && cached_b[1] == c.b[1] &&
+ cached_b[2] == c.b[2] && cached_b[3] == c.b[3])
+ show_result("stvx", "PASS");
+ else
+ show_result("stvx", "FAIL");
+}
+#else
+static void __init test_lvx_stvx(void)
+{
+ show_result("lvx", "SKIP (CONFIG_ALTIVEC is not set)");
+ show_result("stvx", "SKIP (CONFIG_ALTIVEC is not set)");
+}
+#endif /* CONFIG_ALTIVEC */
+
+#ifdef CONFIG_VSX
+static void __init test_lxvd2x_stxvd2x(void)
+{
+ struct pt_regs regs;
+ union {
+ vector128 a;
+ u32 b[4];
+ } c;
+ u32 cached_b[4];
+ int stepped = -1;
+
+ init_pt_regs(®s);
+
+
+ /*** lxvd2x ***/
+
+ cached_b[0] = c.b[0] = 18233;
+ cached_b[1] = c.b[1] = 34863571;
+ cached_b[2] = c.b[2] = 834;
+ cached_b[3] = c.b[3] = 6138911;
+
+ regs.gpr[3] = (unsigned long) &c.a;
+ regs.gpr[4] = 0;
+
+ /* lxvd2x vsr39, r3, r4 */
+ stepped = emulate_step(®s, TEST_LXVD2X(39, 3, 4));
+
+ if (stepped == 1)
+ show_result("lxvd2x", "PASS");
+ else
+ show_result("lxvd2x", "FAIL");
+
+
+ /*** stxvd2x ***/
+
+ c.b[0] = 21379463;
+ c.b[1] = 87;
+ c.b[2] = 374234;
+ c.b[3] = 4;
+
+ /* stxvd2x vsr39, r3, r4 */
+ stepped = emulate_step(®s, TEST_STXVD2X(39, 3, 4));
+
+ if (stepped == 1 && cached_b[0] == c.b[0] && cached_b[1] == c.b[1] &&
+ cached_b[2] == c.b[2] && cached_b[3] == c.b[3])
+ show_result("stxvd2x", "PASS");
+ else
+ show_result("stxvd2x", "FAIL");
+}
+#else
+static void __init test_lxvd2x_stxvd2x(void)
+{
+ show_result("lxvd2x", "SKIP (CONFIG_VSX is not set)");
+ show_result("stxvd2x", "SKIP (CONFIG_VSX is not set)");
+}
+#endif /* CONFIG_VSX */
+
+static int __init test_emulate_step(void)
+{
+ test_ld();
+ test_lwz();
+ test_lwzx();
+ test_std();
+ test_ldarx_stdcx();
+ test_lfsx_stfsx();
+ test_lfdx_stfdx();
+ test_lvx_stvx();
+ test_lxvd2x_stxvd2x();
+
+ return 0;
+}
+late_initcall(test_emulate_step);
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 6aa3b76..c22f207 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -356,25 +356,48 @@ static void early_check_vec5(void)
unsigned long root, chosen;
int size;
const u8 *vec5;
+ u8 mmu_supported;
root = of_get_flat_dt_root();
chosen = of_get_flat_dt_subnode_by_name(root, "chosen");
- if (chosen == -FDT_ERR_NOTFOUND)
- return;
- vec5 = of_get_flat_dt_prop(chosen, "ibm,architecture-vec-5", &size);
- if (!vec5)
- return;
- if (size <= OV5_INDX(OV5_MMU_RADIX_300) ||
- !(vec5[OV5_INDX(OV5_MMU_RADIX_300)] & OV5_FEAT(OV5_MMU_RADIX_300)))
- /* Hypervisor doesn't support radix */
+ if (chosen == -FDT_ERR_NOTFOUND) {
cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
+ return;
+ }
+ vec5 = of_get_flat_dt_prop(chosen, "ibm,architecture-vec-5", &size);
+ if (!vec5) {
+ cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
+ return;
+ }
+ if (size <= OV5_INDX(OV5_MMU_SUPPORT)) {
+ cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
+ return;
+ }
+
+ /* Check for supported configuration */
+ mmu_supported = vec5[OV5_INDX(OV5_MMU_SUPPORT)] &
+ OV5_FEAT(OV5_MMU_SUPPORT);
+ if (mmu_supported == OV5_FEAT(OV5_MMU_RADIX)) {
+ /* Hypervisor only supports radix - check enabled && GTSE */
+ if (!early_radix_enabled()) {
+ pr_warn("WARNING: Ignoring cmdline option disable_radix\n");
+ }
+ if (!(vec5[OV5_INDX(OV5_RADIX_GTSE)] &
+ OV5_FEAT(OV5_RADIX_GTSE))) {
+ pr_warn("WARNING: Hypervisor doesn't support RADIX with GTSE\n");
+ }
+ /* Do radix anyway - the hypervisor said we had to */
+ cur_cpu_spec->mmu_features |= MMU_FTR_TYPE_RADIX;
+ } else if (mmu_supported == OV5_FEAT(OV5_MMU_HASH)) {
+ /* Hypervisor only supports hash - disable radix */
+ cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
+ }
}
void __init mmu_early_init_devtree(void)
{
/* Disable radix mode based on kernel command line. */
- /* We don't yet have the machinery to do radix as a guest. */
- if (disable_radix || !(mfmsr() & MSR_HV))
+ if (disable_radix)
cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
/*
@@ -383,7 +406,7 @@ void __init mmu_early_init_devtree(void)
* even though the ibm,architecture-vec-5 property created by
* skiboot doesn't have the necessary bits set.
*/
- if (early_radix_enabled() && !(mfmsr() & MSR_HV))
+ if (!(mfmsr() & MSR_HV))
early_check_vec5();
if (early_radix_enabled())
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index 2a590a9..c28165d 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -186,6 +186,10 @@ static void __init radix_init_pgtable(void)
*/
register_process_table(__pa(process_tb), 0, PRTB_SIZE_SHIFT - 12);
pr_info("Process table %p and radix root for kernel: %p\n", process_tb, init_mm.pgd);
+ asm volatile("ptesync" : : : "memory");
+ asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : :
+ "r" (TLBIEL_INVAL_SET_LPID), "r" (0));
+ asm volatile("eieio; tlbsync; ptesync" : : : "memory");
}
static void __init radix_init_partition_table(void)
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 595dd71..2ff1324 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -188,6 +188,8 @@ static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp)
sdsync = POWER7P_MMCRA_SDAR_VALID;
else if (ppmu->flags & PPMU_ALT_SIPR)
sdsync = POWER6_MMCRA_SDSYNC;
+ else if (ppmu->flags & PPMU_NO_SIAR)
+ sdsync = MMCRA_SAMPLE_ENABLE;
else
sdsync = MMCRA_SDSYNC;
diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
index e79fb5f..cd951fd 100644
--- a/arch/powerpc/perf/isa207-common.c
+++ b/arch/powerpc/perf/isa207-common.c
@@ -65,12 +65,41 @@ static bool is_event_valid(u64 event)
return !(event & ~valid_mask);
}
-static u64 mmcra_sdar_mode(u64 event)
+static inline bool is_event_marked(u64 event)
{
- if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1))
- return p9_SDAR_MODE(event) << MMCRA_SDAR_MODE_SHIFT;
+ if (event & EVENT_IS_MARKED)
+ return true;
- return MMCRA_SDAR_MODE_TLB;
+ return false;
+}
+
+static void mmcra_sdar_mode(u64 event, unsigned long *mmcra)
+{
+ /*
+ * MMCRA[SDAR_MODE] specifices how the SDAR should be updated in
+ * continous sampling mode.
+ *
+ * Incase of Power8:
+ * MMCRA[SDAR_MODE] will be programmed as "0b01" for continous sampling
+ * mode and will be un-changed when setting MMCRA[63] (Marked events).
+ *
+ * Incase of Power9:
+ * Marked event: MMCRA[SDAR_MODE] will be set to 0b00 ('No Updates'),
+ * or if group already have any marked events.
+ * Non-Marked events (for DD1):
+ * MMCRA[SDAR_MODE] will be set to 0b01
+ * For rest
+ * MMCRA[SDAR_MODE] will be set from event code.
+ */
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ if (is_event_marked(event) || (*mmcra & MMCRA_SAMPLE_ENABLE))
+ *mmcra &= MMCRA_SDAR_MODE_NO_UPDATES;
+ else if (!cpu_has_feature(CPU_FTR_POWER9_DD1))
+ *mmcra |= p9_SDAR_MODE(event) << MMCRA_SDAR_MODE_SHIFT;
+ else if (cpu_has_feature(CPU_FTR_POWER9_DD1))
+ *mmcra |= MMCRA_SDAR_MODE_TLB;
+ } else
+ *mmcra |= MMCRA_SDAR_MODE_TLB;
}
static u64 thresh_cmp_val(u64 value)
@@ -180,7 +209,7 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
value |= CNST_L1_QUAL_VAL(cache);
}
- if (event & EVENT_IS_MARKED) {
+ if (is_event_marked(event)) {
mask |= CNST_SAMPLE_MASK;
value |= CNST_SAMPLE_VAL(event >> EVENT_SAMPLE_SHIFT);
}
@@ -276,7 +305,7 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
}
/* In continuous sampling mode, update SDAR on TLB miss */
- mmcra |= mmcra_sdar_mode(event[i]);
+ mmcra_sdar_mode(event[i], &mmcra);
if (event[i] & EVENT_IS_L1) {
cache = event[i] >> EVENT_CACHE_SEL_SHIFT;
@@ -285,7 +314,7 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
mmcr1 |= (cache & 1) << MMCR1_DC_QUAL_SHIFT;
}
- if (event[i] & EVENT_IS_MARKED) {
+ if (is_event_marked(event[i])) {
mmcra |= MMCRA_SAMPLE_ENABLE;
val = (event[i] >> EVENT_SAMPLE_SHIFT) & EVENT_SAMPLE_MASK;
diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h
index cf9bd899..899210f 100644
--- a/arch/powerpc/perf/isa207-common.h
+++ b/arch/powerpc/perf/isa207-common.h
@@ -246,6 +246,7 @@
#define MMCRA_THR_CMP_SHIFT 32
#define MMCRA_SDAR_MODE_SHIFT 42
#define MMCRA_SDAR_MODE_TLB (1ull << MMCRA_SDAR_MODE_SHIFT)
+#define MMCRA_SDAR_MODE_NO_UPDATES ~(0x3ull << MMCRA_SDAR_MODE_SHIFT)
#define MMCRA_IFM_SHIFT 30
/* MMCR1 Threshold Compare bit constant for power9 */
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 6693f75..da8a0f7 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -39,8 +39,8 @@
BEGIN_FTR_SECTION; \
b 1f; \
END_FTR_SECTION(0, 1); \
- ld r12,opal_tracepoint_refcount@toc(r2); \
- cmpdi r12,0; \
+ ld r11,opal_tracepoint_refcount@toc(r2); \
+ cmpdi r11,0; \
bne- LABEL; \
1:
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 86d9fde..e0f856b 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -395,7 +395,6 @@ static int opal_recover_mce(struct pt_regs *regs,
struct machine_check_event *evt)
{
int recovered = 0;
- uint64_t ea = get_mce_fault_addr(evt);
if (!(regs->msr & MSR_RI)) {
/* If MSR_RI isn't set, we cannot recover */
@@ -404,26 +403,18 @@ static int opal_recover_mce(struct pt_regs *regs,
} else if (evt->disposition == MCE_DISPOSITION_RECOVERED) {
/* Platform corrected itself */
recovered = 1;
- } else if (ea && !is_kernel_addr(ea)) {
+ } else if (evt->severity == MCE_SEV_FATAL) {
+ /* Fatal machine check */
+ pr_err("Machine check interrupt is fatal\n");
+ recovered = 0;
+ } else if ((evt->severity == MCE_SEV_ERROR_SYNC) &&
+ (user_mode(regs) && !is_global_init(current))) {
/*
- * Faulting address is not in kernel text. We should be fine.
- * We need to find which process uses this address.
* For now, kill the task if we have received exception when
* in userspace.
*
* TODO: Queue up this address for hwpoisioning later.
*/
- if (user_mode(regs) && !is_global_init(current)) {
- _exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
- recovered = 1;
- } else
- recovered = 0;
- } else if (user_mode(regs) && !is_global_init(current) &&
- evt->severity == MCE_SEV_ERROR_SYNC) {
- /*
- * If we have received a synchronous error when in userspace
- * kill the task.
- */
_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
recovered = 1;
}
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 6901a06..e367382 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1775,17 +1775,20 @@ static u64 pnv_pci_ioda_dma_get_required_mask(struct pci_dev *pdev)
}
static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe,
- struct pci_bus *bus)
+ struct pci_bus *bus,
+ bool add_to_group)
{
struct pci_dev *dev;
list_for_each_entry(dev, &bus->devices, bus_list) {
set_iommu_table_base(&dev->dev, pe->table_group.tables[0]);
set_dma_offset(&dev->dev, pe->tce_bypass_base);
- iommu_add_device(&dev->dev);
+ if (add_to_group)
+ iommu_add_device(&dev->dev);
if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
- pnv_ioda_setup_bus_dma(pe, dev->subordinate);
+ pnv_ioda_setup_bus_dma(pe, dev->subordinate,
+ add_to_group);
}
}
@@ -2191,7 +2194,7 @@ static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb,
set_iommu_table_base(&pe->pdev->dev, tbl);
iommu_add_device(&pe->pdev->dev);
} else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
- pnv_ioda_setup_bus_dma(pe, pe->pbus);
+ pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
return;
fail:
@@ -2426,6 +2429,8 @@ static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
pnv_pci_ioda2_set_bypass(pe, false);
pnv_pci_ioda2_unset_window(&pe->table_group, 0);
+ if (pe->pbus)
+ pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
pnv_ioda2_table_free(tbl);
}
@@ -2435,6 +2440,8 @@ static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group)
table_group);
pnv_pci_ioda2_setup_default_config(pe);
+ if (pe->pbus)
+ pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
}
static struct iommu_table_group_ops pnv_pci_ioda2_ops = {
@@ -2624,6 +2631,9 @@ static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
level_shift = entries_shift + 3;
level_shift = max_t(unsigned, level_shift, PAGE_SHIFT);
+ if ((level_shift - 3) * levels + page_shift >= 60)
+ return -EINVAL;
+
/* Allocate TCE table */
addr = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift,
levels, tce_table_size, &offset, &total_allocated);
@@ -2728,7 +2738,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
if (pe->flags & PNV_IODA_PE_DEV)
iommu_add_device(&pe->pdev->dev);
else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
- pnv_ioda_setup_bus_dma(pe, pe->pbus);
+ pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
}
#ifdef CONFIG_PCI_MSI
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 251060c..8b1fe89 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -751,7 +751,9 @@ void __init hpte_init_pseries(void)
mmu_hash_ops.flush_hash_range = pSeries_lpar_flush_hash_range;
mmu_hash_ops.hpte_clear_all = pseries_hpte_clear_all;
mmu_hash_ops.hugepage_invalidate = pSeries_lpar_hugepage_invalidate;
- mmu_hash_ops.resize_hpt = pseries_lpar_resize_hpt;
+
+ if (firmware_has_feature(FW_FEATURE_HPT_RESIZE))
+ mmu_hash_ops.resize_hpt = pseries_lpar_resize_hpt;
}
void radix_init_pseries(void)
diff --git a/arch/powerpc/purgatory/trampoline.S b/arch/powerpc/purgatory/trampoline.S
index f9760cc..3696ea6 100644
--- a/arch/powerpc/purgatory/trampoline.S
+++ b/arch/powerpc/purgatory/trampoline.S
@@ -116,13 +116,13 @@
.data
.balign 8
-.globl sha256_digest
-sha256_digest:
+.globl purgatory_sha256_digest
+purgatory_sha256_digest:
.skip 32
- .size sha256_digest, . - sha256_digest
+ .size purgatory_sha256_digest, . - purgatory_sha256_digest
.balign 8
-.globl sha_regions
-sha_regions:
+.globl purgatory_sha_regions
+purgatory_sha_regions:
.skip 8 * 2 * 16
- .size sha_regions, . - sha_regions
+ .size purgatory_sha_regions, . - purgatory_sha_regions
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index ada29ea..f523ac8 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -274,7 +274,9 @@ static int axon_ram_probe(struct platform_device *device)
if (bank->disk->major > 0)
unregister_blkdev(bank->disk->major,
bank->disk->disk_name);
- del_gendisk(bank->disk);
+ if (bank->disk->flags & GENHD_FL_UP)
+ del_gendisk(bank->disk);
+ put_disk(bank->disk);
}
device->dev.platform_data = NULL;
if (bank->io_addr != 0)
@@ -299,6 +301,7 @@ axon_ram_remove(struct platform_device *device)
device_remove_file(&device->dev, &dev_attr_ecc);
free_irq(bank->irq_id, device);
del_gendisk(bank->disk);
+ put_disk(bank->disk);
iounmap((void __iomem *) bank->io_addr);
kfree(bank);
diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c
index f9670ea..b53f80f 100644
--- a/arch/powerpc/sysdev/xics/icp-opal.c
+++ b/arch/powerpc/sysdev/xics/icp-opal.c
@@ -91,6 +91,16 @@ static unsigned int icp_opal_get_irq(void)
static void icp_opal_set_cpu_priority(unsigned char cppr)
{
+ /*
+ * Here be dragons. The caller has asked to allow only IPI's and not
+ * external interrupts. But OPAL XIVE doesn't support that. So instead
+ * of allowing no interrupts allow all. That's still not right, but
+ * currently the only caller who does this is xics_migrate_irqs_away()
+ * and it works in that case.
+ */
+ if (cppr >= DEFAULT_PRIORITY)
+ cppr = LOWEST_PRIORITY;
+
xics_set_base_cppr(cppr);
opal_int_set_cppr(cppr);
iosync();
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index 69d858e..23efe4e 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -20,6 +20,7 @@
#include <linux/of.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
+#include <linux/delay.h>
#include <asm/prom.h>
#include <asm/io.h>
@@ -198,9 +199,6 @@ void xics_migrate_irqs_away(void)
/* Remove ourselves from the global interrupt queue */
xics_set_cpu_giq(xics_default_distrib_server, 0);
- /* Allow IPIs again... */
- icp_ops->set_priority(DEFAULT_PRIORITY);
-
for_each_irq_desc(virq, desc) {
struct irq_chip *chip;
long server;
@@ -255,6 +253,19 @@ void xics_migrate_irqs_away(void)
unlock:
raw_spin_unlock_irqrestore(&desc->lock, flags);
}
+
+ /* Allow "sufficient" time to drop any inflight IRQ's */
+ mdelay(5);
+
+ /*
+ * Allow IPIs again. This is done at the very end, after migrating all
+ * interrupts, the expectation is that we'll only get woken up by an IPI
+ * interrupt beyond this point, but leave externals masked just to be
+ * safe. If we're using icp-opal this may actually allow all
+ * interrupts anyway, but that should be OK.
+ */
+ icp_ops->set_priority(DEFAULT_PRIORITY);
+
}
#endif /* CONFIG_HOTPLUG_CPU */
diff --git a/arch/s390/boot/compressed/misc.c b/arch/s390/boot/compressed/misc.c
index fa95041..33ca293 100644
--- a/arch/s390/boot/compressed/misc.c
+++ b/arch/s390/boot/compressed/misc.c
@@ -141,31 +141,34 @@ static void check_ipl_parmblock(void *start, unsigned long size)
unsigned long decompress_kernel(void)
{
- unsigned long output_addr;
- unsigned char *output;
+ void *output, *kernel_end;
- output_addr = ((unsigned long) &_end + HEAP_SIZE + 4095UL) & -4096UL;
- check_ipl_parmblock((void *) 0, output_addr + SZ__bss_start);
- memset(&_bss, 0, &_ebss - &_bss);
- free_mem_ptr = (unsigned long)&_end;
- free_mem_end_ptr = free_mem_ptr + HEAP_SIZE;
- output = (unsigned char *) output_addr;
+ output = (void *) ALIGN((unsigned long) &_end + HEAP_SIZE, PAGE_SIZE);
+ kernel_end = output + SZ__bss_start;
+ check_ipl_parmblock((void *) 0, (unsigned long) kernel_end);
#ifdef CONFIG_BLK_DEV_INITRD
/*
* Move the initrd right behind the end of the decompressed
- * kernel image.
+ * kernel image. This also prevents initrd corruption caused by
+ * bss clearing since kernel_end will always be located behind the
+ * current bss section..
*/
- if (INITRD_START && INITRD_SIZE &&
- INITRD_START < (unsigned long) output + SZ__bss_start) {
- check_ipl_parmblock(output + SZ__bss_start,
- INITRD_START + INITRD_SIZE);
- memmove(output + SZ__bss_start,
- (void *) INITRD_START, INITRD_SIZE);
- INITRD_START = (unsigned long) output + SZ__bss_start;
+ if (INITRD_START && INITRD_SIZE && kernel_end > (void *) INITRD_START) {
+ check_ipl_parmblock(kernel_end, INITRD_SIZE);
+ memmove(kernel_end, (void *) INITRD_START, INITRD_SIZE);
+ INITRD_START = (unsigned long) kernel_end;
}
#endif
+ /*
+ * Clear bss section. free_mem_ptr and free_mem_end_ptr need to be
+ * initialized afterwards since they reside in bss.
+ */
+ memset(&_bss, 0, &_ebss - &_bss);
+ free_mem_ptr = (unsigned long) &_end;
+ free_mem_end_ptr = free_mem_ptr + HEAP_SIZE;
+
puts("Uncompressing Linux... ");
__decompress(input_data, input_len, NULL, NULL, output, 0, NULL, error);
puts("Ok, booting the kernel.\n");
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index 143b1e0..4b176fe 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -609,7 +609,7 @@
CONFIG_FTRACE_SYSCALLS=y
CONFIG_STACK_TRACER=y
CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
CONFIG_FUNCTION_PROFILER=y
CONFIG_HIST_TRIGGERS=y
CONFIG_TRACE_ENUM_MAP_FILE=y
diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig
index f05d2d6..0de46cc 100644
--- a/arch/s390/configs/gcov_defconfig
+++ b/arch/s390/configs/gcov_defconfig
@@ -560,7 +560,7 @@
CONFIG_FTRACE_SYSCALLS=y
CONFIG_STACK_TRACER=y
CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
CONFIG_FUNCTION_PROFILER=y
CONFIG_HIST_TRIGGERS=y
CONFIG_TRACE_ENUM_MAP_FILE=y
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index 2358bf3..e167557 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -558,7 +558,7 @@
CONFIG_FTRACE_SYSCALLS=y
CONFIG_STACK_TRACER=y
CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
CONFIG_FUNCTION_PROFILER=y
CONFIG_HIST_TRIGGERS=y
CONFIG_TRACE_ENUM_MAP_FILE=y
diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c
index d69ea49..716b172 100644
--- a/arch/s390/crypto/paes_s390.c
+++ b/arch/s390/crypto/paes_s390.c
@@ -474,8 +474,11 @@ static int ctr_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier,
ret = blkcipher_walk_done(desc, walk, nbytes - n);
}
if (k < n) {
- if (__ctr_paes_set_key(ctx) != 0)
+ if (__ctr_paes_set_key(ctx) != 0) {
+ if (locked)
+ spin_unlock(&ctrblk_lock);
return blkcipher_walk_done(desc, walk, -EIO);
+ }
}
}
if (locked)
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 68bfd09..97189db 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -179,7 +179,7 @@
CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
CONFIG_STACK_TRACER=y
CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
CONFIG_FUNCTION_PROFILER=y
CONFIG_TRACE_ENUM_MAP_FILE=y
CONFIG_KPROBES_SANITY_TEST=y
diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h
index d1c407d..9072bf6 100644
--- a/arch/s390/include/asm/cputime.h
+++ b/arch/s390/include/asm/cputime.h
@@ -8,31 +8,27 @@
#define _S390_CPUTIME_H
#include <linux/types.h>
-#include <asm/div64.h>
+#include <asm/timex.h>
#define CPUTIME_PER_USEC 4096ULL
#define CPUTIME_PER_SEC (CPUTIME_PER_USEC * USEC_PER_SEC)
/* We want to use full resolution of the CPU timer: 2**-12 micro-seconds. */
-typedef unsigned long long __nocast cputime_t;
-typedef unsigned long long __nocast cputime64_t;
-
#define cmpxchg_cputime(ptr, old, new) cmpxchg64(ptr, old, new)
-static inline unsigned long __div(unsigned long long n, unsigned long base)
+/*
+ * Convert cputime to microseconds.
+ */
+static inline u64 cputime_to_usecs(const u64 cputime)
{
- return n / base;
+ return cputime >> 12;
}
/*
- * Convert cputime to microseconds and back.
+ * Convert cputime to nanoseconds.
*/
-static inline unsigned int cputime_to_usecs(const cputime_t cputime)
-{
- return (__force unsigned long long) cputime >> 12;
-}
-
+#define cputime_to_nsecs(cputime) tod_to_ns(cputime)
u64 arch_cpu_idle_time(int cpu);
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 7ed1972..93e37b1 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -24,6 +24,7 @@
* the S390 page table tree.
*/
#ifndef __ASSEMBLY__
+#include <asm-generic/5level-fixup.h>
#include <linux/sched.h>
#include <linux/mm_types.h>
#include <linux/page-flags.h>
diff --git a/arch/s390/include/asm/sections.h b/arch/s390/include/asm/sections.h
index 5ce29fe..fbd9116 100644
--- a/arch/s390/include/asm/sections.h
+++ b/arch/s390/include/asm/sections.h
@@ -4,6 +4,5 @@
#include <asm-generic/sections.h>
extern char _eshared[], _ehead[];
-extern char __start_ro_after_init[], __end_ro_after_init[];
#endif
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index 354344d..1185351 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -206,20 +206,16 @@ static inline unsigned long long get_tod_clock_monotonic(void)
* ns = (todval * 125) >> 9;
*
* In order to avoid an overflow with the multiplication we can rewrite this.
- * With a split todval == 2^32 * th + tl (th upper 32 bits, tl lower 32 bits)
+ * With a split todval == 2^9 * th + tl (th upper 55 bits, tl lower 9 bits)
* we end up with
*
- * ns = ((2^32 * th + tl) * 125 ) >> 9;
- * -> ns = (2^23 * th * 125) + ((tl * 125) >> 9);
+ * ns = ((2^9 * th + tl) * 125 ) >> 9;
+ * -> ns = (th * 125) + ((tl * 125) >> 9);
*
*/
static inline unsigned long long tod_to_ns(unsigned long long todval)
{
- unsigned long long ns;
-
- ns = ((todval >> 32) << 23) * 125;
- ns += ((todval & 0xffffffff) * 125) >> 9;
- return ns;
+ return ((todval >> 9) * 125) + (((todval & 0x1ff) * 125) >> 9);
}
#endif
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 136932f..3ea1554 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -147,7 +147,7 @@ unsigned long __must_check __copy_to_user(void __user *to, const void *from,
" jg 2b\n" \
".popsection\n" \
EX_TABLE(0b,3b) EX_TABLE(1b,3b) \
- : "=d" (__rc), "=Q" (*(to)) \
+ : "=d" (__rc), "+Q" (*(to)) \
: "d" (size), "Q" (*(from)), \
"d" (__reg0), "K" (-EFAULT) \
: "cc"); \
diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
index b24a64c..e8e5ecf 100644
--- a/arch/s390/include/uapi/asm/socket.h
+++ b/arch/s390/include/uapi/asm/socket.h
@@ -98,4 +98,10 @@
#define SCM_TIMESTAMPING_OPT_STATS 54
+#define SO_MEMINFO 55
+
+#define SO_INCOMING_NAPI_ID 56
+
+#define SO_COOKIE 57
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h
index 4384bc7..152de9b 100644
--- a/arch/s390/include/uapi/asm/unistd.h
+++ b/arch/s390/include/uapi/asm/unistd.h
@@ -313,7 +313,9 @@
#define __NR_copy_file_range 375
#define __NR_preadv2 376
#define __NR_pwritev2 377
-#define NR_syscalls 378
+/* Number 378 is reserved for guarded storage */
+#define __NR_statx 379
+#define NR_syscalls 380
/*
* There are some system calls that are not present on 64 bit, some
diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c
index ae2cda5..e89cc2e 100644
--- a/arch/s390/kernel/compat_wrapper.c
+++ b/arch/s390/kernel/compat_wrapper.c
@@ -178,3 +178,4 @@ COMPAT_SYSCALL_WRAP3(getpeername, int, fd, struct sockaddr __user *, usockaddr,
COMPAT_SYSCALL_WRAP6(sendto, int, fd, void __user *, buff, size_t, len, unsigned int, flags, struct sockaddr __user *, addr, int, addr_len);
COMPAT_SYSCALL_WRAP3(mlock2, unsigned long, start, size_t, len, int, flags);
COMPAT_SYSCALL_WRAP6(copy_file_range, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags);
+COMPAT_SYSCALL_WRAP5(statx, int, dfd, const char __user *, path, unsigned, flags, unsigned, mask, struct statx __user *, buffer);
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index dff2152..6a7d737 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -490,7 +490,7 @@
jnz .Lpgm_svcper # -> single stepped svc
1: CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC
aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
- j 3f
+ j 4f
2: UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER
lg %r15,__LC_KERNEL_STACK
lgr %r14,%r12
@@ -499,8 +499,8 @@
tm __LC_PGM_ILC+2,0x02 # check for transaction abort
jz 3f
mvc __THREAD_trap_tdb(256,%r14),0(%r13)
-3: la %r11,STACK_FRAME_OVERHEAD(%r15)
- stg %r10,__THREAD_last_break(%r14)
+3: stg %r10,__THREAD_last_break(%r14)
+4: la %r11,STACK_FRAME_OVERHEAD(%r15)
stmg %r0,%r7,__PT_R0(%r11)
mvc __PT_R8(64,%r11),__LC_SAVE_AREA_SYNC
stmg %r8,%r9,__PT_PSW(%r11)
@@ -509,14 +509,14 @@
xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
stg %r10,__PT_ARGS(%r11)
tm __LC_PGM_ILC+3,0x80 # check for per exception
- jz 4f
+ jz 5f
tmhh %r8,0x0001 # kernel per event ?
jz .Lpgm_kprobe
oi __PT_FLAGS+7(%r11),_PIF_PER_TRAP
mvc __THREAD_per_address(8,%r14),__LC_PER_ADDRESS
mvc __THREAD_per_cause(2,%r14),__LC_PER_CODE
mvc __THREAD_per_paid(1,%r14),__LC_PER_ACCESS_ID
-4: REENABLE_IRQS
+5: REENABLE_IRQS
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
larl %r1,pgm_check_table
llgh %r10,__PT_INT_CODE+2(%r11)
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index b67dafb..e545ffe 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -564,6 +564,8 @@ static struct kset *ipl_kset;
static void __ipl_run(void *unused)
{
+ if (MACHINE_IS_LPAR && ipl_info.type == IPL_TYPE_CCW)
+ diag308(DIAG308_LOAD_NORMAL_DUMP, NULL);
diag308(DIAG308_LOAD_CLEAR, NULL);
if (MACHINE_IS_VM)
__cpcmd("IPL", NULL, 0, NULL);
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 20cd339..f29e41c 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -124,7 +124,10 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long new_stackp,
clear_tsk_thread_flag(p, TIF_SINGLE_STEP);
/* Initialize per thread user and system timer values */
p->thread.user_timer = 0;
+ p->thread.guest_timer = 0;
p->thread.system_timer = 0;
+ p->thread.hardirq_timer = 0;
+ p->thread.softirq_timer = 0;
frame->sf.back_chain = 0;
/* new return point is ret_from_fork */
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 47a973b..5dab859 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -909,13 +909,11 @@ void __init smp_prepare_boot_cpu(void)
{
struct pcpu *pcpu = pcpu_devices;
+ WARN_ON(!cpu_present(0) || !cpu_online(0));
pcpu->state = CPU_STATE_CONFIGURED;
- pcpu->address = stap();
pcpu->lowcore = (struct lowcore *)(unsigned long) store_prefix();
S390_lowcore.percpu_offset = __per_cpu_offset[0];
smp_cpu_set_polarization(0, POLARIZATION_UNKNOWN);
- set_cpu_present(0, true);
- set_cpu_online(0, true);
}
void __init smp_cpus_done(unsigned int max_cpus)
@@ -924,6 +922,7 @@ void __init smp_cpus_done(unsigned int max_cpus)
void __init smp_setup_processor_id(void)
{
+ pcpu_devices[0].address = stap();
S390_lowcore.cpu_nr = 0;
S390_lowcore.spinlock_lockval = arch_spin_lockval(0);
}
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
index 9b59e62..2659b5c 100644
--- a/arch/s390/kernel/syscalls.S
+++ b/arch/s390/kernel/syscalls.S
@@ -386,3 +386,5 @@
SYSCALL(sys_copy_file_range,compat_sys_copy_file_range) /* 375 */
SYSCALL(sys_preadv2,compat_sys_preadv2)
SYSCALL(sys_pwritev2,compat_sys_pwritev2)
+NI_SYSCALL
+SYSCALL(sys_statx,compat_sys_statx)
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 5ccf953..72307f1 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -63,11 +63,9 @@
. = ALIGN(PAGE_SIZE);
__start_ro_after_init = .;
- __start_data_ro_after_init = .;
.data..ro_after_init : {
*(.data..ro_after_init)
}
- __end_data_ro_after_init = .;
EXCEPTION_TABLE(16)
. = ALIGN(PAGE_SIZE);
__end_ro_after_init = .;
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index c14fc90..072d84b 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -111,7 +111,7 @@ static inline u64 scale_vtime(u64 vtime)
}
static void account_system_index_scaled(struct task_struct *p,
- cputime_t cputime, cputime_t scaled,
+ u64 cputime, u64 scaled,
enum cpu_usage_stat index)
{
p->stimescaled += cputime_to_nsecs(scaled);
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index b48dc5f..463e5ef 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -608,12 +608,29 @@ void ptep_zap_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr)
{
spinlock_t *ptl;
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
pgste_t pgste;
pte_t *ptep;
pte_t pte;
bool dirty;
- ptep = get_locked_pte(mm, addr, &ptl);
+ pgd = pgd_offset(mm, addr);
+ pud = pud_alloc(mm, pgd, addr);
+ if (!pud)
+ return false;
+ pmd = pmd_alloc(mm, pud, addr);
+ if (!pmd)
+ return false;
+ /* We can't run guests backed by huge pages, but userspace can
+ * still set them up and then try to migrate them without any
+ * migration support.
+ */
+ if (pmd_large(*pmd))
+ return true;
+
+ ptep = pte_alloc_map_lock(mm, pmd, addr, &ptl);
if (unlikely(!ptep))
return false;
diff --git a/arch/score/include/asm/pgtable.h b/arch/score/include/asm/pgtable.h
index 0553e5c..46ff8fd 100644
--- a/arch/score/include/asm/pgtable.h
+++ b/arch/score/include/asm/pgtable.h
@@ -2,6 +2,7 @@
#define _ASM_SCORE_PGTABLE_H
#include <linux/const.h>
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
#include <asm/fixmap.h>
diff --git a/arch/score/kernel/traps.c b/arch/score/kernel/traps.c
index e359ec6..12daf45 100644
--- a/arch/score/kernel/traps.c
+++ b/arch/score/kernel/traps.c
@@ -24,6 +24,7 @@
*/
#include <linux/extable.h>
+#include <linux/ptrace.h>
#include <linux/sched/mm.h>
#include <linux/sched/signal.h>
#include <linux/sched/debug.h>
diff --git a/arch/score/mm/extable.c b/arch/score/mm/extable.c
index ec87135..6736a3a 100644
--- a/arch/score/mm/extable.c
+++ b/arch/score/mm/extable.c
@@ -24,6 +24,8 @@
*/
#include <linux/extable.h>
+#include <linux/ptrace.h>
+#include <asm/extable.h>
int fixup_exception(struct pt_regs *regs)
{
diff --git a/arch/sh/boards/mach-cayman/setup.c b/arch/sh/boards/mach-cayman/setup.c
index 340fd40..9c292c2 100644
--- a/arch/sh/boards/mach-cayman/setup.c
+++ b/arch/sh/boards/mach-cayman/setup.c
@@ -128,7 +128,6 @@ static int __init smsc_superio_setup(void)
SMSC_SUPERIO_WRITE_INDEXED(1, SMSC_PRIMARY_INT_INDEX);
SMSC_SUPERIO_WRITE_INDEXED(12, SMSC_SECONDARY_INT_INDEX);
-#ifdef CONFIG_IDE
/*
* Only IDE1 exists on the Cayman
*/
@@ -158,7 +157,6 @@ static int __init smsc_superio_setup(void)
SMSC_SUPERIO_WRITE_INDEXED(0x01, 0xc5); /* GP45 = IDE1_IRQ */
SMSC_SUPERIO_WRITE_INDEXED(0x00, 0xc6); /* GP46 = nIOROP */
SMSC_SUPERIO_WRITE_INDEXED(0x00, 0xc7); /* GP47 = nIOWOP */
-#endif
/* Exit the configuration state */
outb(SMSC_EXIT_CONFIG_KEY, SMSC_CONFIG_PORT_ADDR);
diff --git a/arch/sh/include/asm/pgtable-2level.h b/arch/sh/include/asm/pgtable-2level.h
index 19bd89d..f75cf43 100644
--- a/arch/sh/include/asm/pgtable-2level.h
+++ b/arch/sh/include/asm/pgtable-2level.h
@@ -1,6 +1,7 @@
#ifndef __ASM_SH_PGTABLE_2LEVEL_H
#define __ASM_SH_PGTABLE_2LEVEL_H
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
/*
diff --git a/arch/sh/include/asm/pgtable-3level.h b/arch/sh/include/asm/pgtable-3level.h
index 249a985..9b1e776 100644
--- a/arch/sh/include/asm/pgtable-3level.h
+++ b/arch/sh/include/asm/pgtable-3level.h
@@ -1,6 +1,7 @@
#ifndef __ASM_SH_PGTABLE_3LEVEL_H
#define __ASM_SH_PGTABLE_3LEVEL_H
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopud.h>
/*
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 56e49c8..8a59852 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -12,6 +12,7 @@
* the SpitFire page tables.
*/
+#include <asm-generic/5level-fixup.h>
#include <linux/compiler.h>
#include <linux/const.h>
#include <asm/types.h>
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index a25dc32..3f4ad19 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -88,6 +88,12 @@
#define SCM_TIMESTAMPING_OPT_STATS 0x0038
+#define SO_MEMINFO 0x0039
+
+#define SO_INCOMING_NAPI_ID 0x003a
+
+#define SO_COOKIE 0x003b
+
/* Security levels - as per NRL IPv6 - don't actually do anything */
#define SO_SECURITY_AUTHENTICATION 0x5001
#define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002
diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c
index df9e731..fc5124c 100644
--- a/arch/sparc/kernel/ptrace_64.c
+++ b/arch/sparc/kernel/ptrace_64.c
@@ -351,7 +351,7 @@ static int genregs64_set(struct task_struct *target,
}
if (!ret) {
- unsigned long y;
+ unsigned long y = regs->y;
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
&y,
diff --git a/arch/tile/include/asm/pgtable_32.h b/arch/tile/include/asm/pgtable_32.h
index d26a422..5f8c615 100644
--- a/arch/tile/include/asm/pgtable_32.h
+++ b/arch/tile/include/asm/pgtable_32.h
@@ -74,6 +74,7 @@ extern unsigned long VMALLOC_RESERVE /* = CONFIG_VMALLOC_RESERVE */;
#define MAXMEM (_VMALLOC_START - PAGE_OFFSET)
/* We have no pmd or pud since we are strictly a two-level page table */
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
static inline int pud_huge_page(pud_t pud) { return 0; }
diff --git a/arch/tile/include/asm/pgtable_64.h b/arch/tile/include/asm/pgtable_64.h
index e96cec5..96fe58b 100644
--- a/arch/tile/include/asm/pgtable_64.h
+++ b/arch/tile/include/asm/pgtable_64.h
@@ -59,6 +59,7 @@
#ifndef __ASSEMBLY__
/* We have no pud since we are a three-level page table. */
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopud.h>
/*
diff --git a/arch/um/include/asm/pgtable-2level.h b/arch/um/include/asm/pgtable-2level.h
index cfbe597..179c0ea 100644
--- a/arch/um/include/asm/pgtable-2level.h
+++ b/arch/um/include/asm/pgtable-2level.h
@@ -8,6 +8,7 @@
#ifndef __UM_PGTABLE_2LEVEL_H
#define __UM_PGTABLE_2LEVEL_H
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
/* PGDIR_SHIFT determines what a third-level page table entry can map */
diff --git a/arch/um/include/asm/pgtable-3level.h b/arch/um/include/asm/pgtable-3level.h
index bae8523..c4d876d 100644
--- a/arch/um/include/asm/pgtable-3level.h
+++ b/arch/um/include/asm/pgtable-3level.h
@@ -7,6 +7,7 @@
#ifndef __UM_PGTABLE_3LEVEL_H
#define __UM_PGTABLE_3LEVEL_H
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopud.h>
/* PGDIR_SHIFT determines what a third-level page table entry can map */
diff --git a/arch/unicore32/include/asm/pgtable.h b/arch/unicore32/include/asm/pgtable.h
index 818d0f5..a4f2bef 100644
--- a/arch/unicore32/include/asm/pgtable.h
+++ b/arch/unicore32/include/asm/pgtable.h
@@ -12,6 +12,7 @@
#ifndef __UNICORE_PGTABLE_H__
#define __UNICORE_PGTABLE_H__
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
#include <asm/cpu-single.h>
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 2d44933..a94a4d1 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -120,10 +120,6 @@
# -funit-at-a-time shrinks the kernel .text considerably
# unfortunately it makes reading oopses harder.
KBUILD_CFLAGS += $(call cc-option,-funit-at-a-time)
-
- # this works around some issues with generating unwind tables in older gccs
- # newer gccs do it by default
- KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args)
endif
ifdef CONFIG_X86_X32
@@ -147,6 +143,37 @@
KBUILD_CFLAGS += $(call cc-option,-fno-builtin-memcpy)
endif
+#
+# If the function graph tracer is used with mcount instead of fentry,
+# '-maccumulate-outgoing-args' is needed to prevent a GCC bug
+# (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=42109)
+#
+ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ ifndef CONFIG_HAVE_FENTRY
+ ACCUMULATE_OUTGOING_ARGS := 1
+ else
+ ifeq ($(call cc-option-yn, -mfentry), n)
+ ACCUMULATE_OUTGOING_ARGS := 1
+ endif
+ endif
+endif
+
+#
+# Jump labels need '-maccumulate-outgoing-args' for gcc < 4.5.2 to prevent a
+# GCC bug (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46226). There's no way
+# to test for this bug at compile-time because the test case needs to execute,
+# which is a no-go for cross compilers. So check the GCC version instead.
+#
+ifdef CONFIG_JUMP_LABEL
+ ifneq ($(ACCUMULATE_OUTGOING_ARGS), 1)
+ ACCUMULATE_OUTGOING_ARGS = $(call cc-if-fullversion, -lt, 040502, 1)
+ endif
+endif
+
+ifeq ($(ACCUMULATE_OUTGOING_ARGS), 1)
+ KBUILD_CFLAGS += -maccumulate-outgoing-args
+endif
+
# Stackpointer is addressed different for 32 bit and 64 bit x86
sp-$(CONFIG_X86_32) := esp
sp-$(CONFIG_X86_64) := rsp
diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu
index 6647ed4..a45eb15 100644
--- a/arch/x86/Makefile_32.cpu
+++ b/arch/x86/Makefile_32.cpu
@@ -45,24 +45,6 @@
# cpu entries
cflags-$(CONFIG_X86_GENERIC) += $(call tune,generic,$(call tune,i686))
-# Work around the pentium-mmx code generator madness of gcc4.4.x which
-# does stack alignment by generating horrible code _before_ the mcount
-# prologue (push %ebp, mov %esp, %ebp) which breaks the function graph
-# tracer assumptions. For i686, generic, core2 this is set by the
-# compiler anyway
-ifeq ($(CONFIG_FUNCTION_GRAPH_TRACER), y)
-ADD_ACCUMULATE_OUTGOING_ARGS := y
-endif
-
-# Work around to a bug with asm goto with first implementations of it
-# in gcc causing gcc to mess up the push and pop of the stack in some
-# uses of asm goto.
-ifeq ($(CONFIG_JUMP_LABEL), y)
-ADD_ACCUMULATE_OUTGOING_ARGS := y
-endif
-
-cflags-$(ADD_ACCUMULATE_OUTGOING_ARGS) += $(call cc-option,-maccumulate-outgoing-args)
-
# Bug fix for binutils: this option is required in order to keep
# binutils from generating NOPL instructions against our will.
ifneq ($(CONFIG_X86_P6_NOP),y)
diff --git a/arch/x86/boot/compressed/error.c b/arch/x86/boot/compressed/error.c
index 6248740..3192202 100644
--- a/arch/x86/boot/compressed/error.c
+++ b/arch/x86/boot/compressed/error.c
@@ -4,6 +4,7 @@
* memcpy() and memmove() are defined for the compressed boot environment.
*/
#include "misc.h"
+#include "error.h"
void warn(char *m)
{
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 7ef4a09..6205d3b 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -176,6 +176,7 @@
CONFIG_SKY2=y
CONFIG_FORCEDETH=y
CONFIG_8139TOO=y
+CONFIG_R8169=y
CONFIG_FDDI=y
CONFIG_INPUT_POLLDEV=y
# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index afb222b..c84584b 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -604,7 +604,7 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, int idx,
return &amd_f15_PMC20;
}
case AMD_EVENT_NB:
- /* moved to perf_event_amd_uncore.c */
+ /* moved to uncore.c */
return &emptyconstraint;
default:
return &emptyconstraint;
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 349d4d1..580b60f 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2101,8 +2101,8 @@ static int x86_pmu_event_init(struct perf_event *event)
static void refresh_pce(void *ignored)
{
- if (current->mm)
- load_mm_cr4(current->mm);
+ if (current->active_mm)
+ load_mm_cr4(current->active_mm);
}
static void x86_pmu_event_mapped(struct perf_event *event)
@@ -2110,6 +2110,18 @@ static void x86_pmu_event_mapped(struct perf_event *event)
if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED))
return;
+ /*
+ * This function relies on not being called concurrently in two
+ * tasks in the same mm. Otherwise one task could observe
+ * perf_rdpmc_allowed > 1 and return all the way back to
+ * userspace with CR4.PCE clear while another task is still
+ * doing on_each_cpu_mask() to propagate CR4.PCE.
+ *
+ * For now, this can't happen because all callers hold mmap_sem
+ * for write. If this changes, we'll need a different solution.
+ */
+ lockdep_assert_held_exclusive(¤t->mm->mmap_sem);
+
if (atomic_inc_return(¤t->mm->context.perf_rdpmc_allowed) == 1)
on_each_cpu_mask(mm_cpumask(current->mm), refresh_pce, NULL, 1);
}
@@ -2244,6 +2256,7 @@ void arch_perf_update_userpage(struct perf_event *event,
struct perf_event_mmap_page *userpg, u64 now)
{
struct cyc2ns_data *data;
+ u64 offset;
userpg->cap_user_time = 0;
userpg->cap_user_time_zero = 0;
@@ -2251,11 +2264,13 @@ void arch_perf_update_userpage(struct perf_event *event,
!!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED);
userpg->pmc_width = x86_pmu.cntval_bits;
- if (!sched_clock_stable())
+ if (!using_native_sched_clock() || !sched_clock_stable())
return;
data = cyc2ns_read_begin();
+ offset = data->cyc2ns_offset + __sched_clock_offset;
+
/*
* Internal timekeeping for enabled/running/stopped times
* is always in the local_clock domain.
@@ -2263,7 +2278,7 @@ void arch_perf_update_userpage(struct perf_event *event,
userpg->cap_user_time = 1;
userpg->time_mult = data->cyc2ns_mul;
userpg->time_shift = data->cyc2ns_shift;
- userpg->time_offset = data->cyc2ns_offset - now;
+ userpg->time_offset = offset - now;
/*
* cap_user_time_zero doesn't make sense when we're using a different
@@ -2271,7 +2286,7 @@ void arch_perf_update_userpage(struct perf_event *event,
*/
if (!event->attr.use_clockid) {
userpg->cap_user_time_zero = 1;
- userpg->time_zero = data->cyc2ns_offset;
+ userpg->time_zero = offset;
}
cyc2ns_read_end(data);
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index aff4b5b..238ae32 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -1,5 +1,5 @@
/*
- * perf_event_intel_cstate.c: support cstate residency counters
+ * Support cstate residency counters
*
* Copyright (C) 2015, Intel Corp.
* Author: Kan Liang (kan.liang@intel.com)
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 22054ca..9d05c7e 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -1,5 +1,5 @@
/*
- * perf_event_intel_rapl.c: support Intel RAPL energy consumption counters
+ * Support Intel RAPL energy consumption counters
* Copyright (C) 2013 Google, Inc., Stephane Eranian
*
* Intel RAPL interface is specified in the IA-32 Manual Vol3b
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index ad986c1..df5989f 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -360,7 +360,7 @@ extern struct list_head pci2phy_map_head;
extern struct pci_extra_dev *uncore_extra_pci_dev;
extern struct event_constraint uncore_constraint_empty;
-/* perf_event_intel_uncore_snb.c */
+/* uncore_snb.c */
int snb_uncore_pci_init(void);
int ivb_uncore_pci_init(void);
int hsw_uncore_pci_init(void);
@@ -371,7 +371,7 @@ void nhm_uncore_cpu_init(void);
void skl_uncore_cpu_init(void);
int snb_pci2phy_map_init(int devid);
-/* perf_event_intel_uncore_snbep.c */
+/* uncore_snbep.c */
int snbep_uncore_pci_init(void);
void snbep_uncore_cpu_init(void);
int ivbep_uncore_pci_init(void);
@@ -385,5 +385,5 @@ void knl_uncore_cpu_init(void);
int skx_uncore_pci_init(void);
void skx_uncore_cpu_init(void);
-/* perf_event_intel_uncore_nhmex.c */
+/* uncore_nhmex.c */
void nhmex_uncore_cpu_init(void);
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index db64baf0..8bef70e 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -158,13 +158,13 @@ void hyperv_init(void)
clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
return;
}
+register_msr_cs:
#endif
/*
* For 32 bit guests just use the MSR based mechanism for reading
* the partition counter.
*/
-register_msr_cs:
hyperv_cs = &hyperv_cs_msr;
if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100);
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 4e77723..b04bb6d 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -289,7 +289,8 @@
#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */
#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */
#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
-#define X86_FEATURE_RDPID (16*32+ 22) /* RDPID instruction */
+#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */
+#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */
/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index d74747b..c4eda79 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -46,6 +46,7 @@ struct kvm_page_track_notifier_node {
};
void kvm_page_track_init(struct kvm *kvm);
+void kvm_page_track_cleanup(struct kvm *kvm);
void kvm_page_track_free_memslot(struct kvm_memory_slot *free,
struct kvm_memory_slot *dont);
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 72277b1..50d35e3 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -121,12 +121,9 @@ static inline void native_pmd_clear(pmd_t *pmd)
*(tmp + 1) = 0;
}
-#if !defined(CONFIG_SMP) || (defined(CONFIG_HIGHMEM64G) && \
- defined(CONFIG_PARAVIRT))
static inline void native_pud_clear(pud_t *pudp)
{
}
-#endif
static inline void pud_clear(pud_t *pudp)
{
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 1cfb36b..585ee0d 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -62,7 +62,7 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page);
# define set_pud(pudp, pud) native_set_pud(pudp, pud)
#endif
-#ifndef __PAGETABLE_PMD_FOLDED
+#ifndef __PAGETABLE_PUD_FOLDED
#define pud_clear(pud) native_pud_clear(pud)
#endif
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 8b4de22..6248433 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -273,6 +273,8 @@ static inline pgdval_t pgd_flags(pgd_t pgd)
}
#if CONFIG_PGTABLE_LEVELS > 3
+#include <asm-generic/5level-fixup.h>
+
typedef struct { pudval_t pud; } pud_t;
static inline pud_t native_make_pud(pmdval_t val)
@@ -285,6 +287,7 @@ static inline pudval_t native_pud_val(pud_t pud)
return pud.pud;
}
#else
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopud.h>
static inline pudval_t native_pud_val(pud_t pud)
@@ -306,6 +309,7 @@ static inline pmdval_t native_pmd_val(pmd_t pmd)
return pmd.pmd;
}
#else
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
static inline pmdval_t native_pmd_val(pmd_t pmd)
diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h
index 34684ad..b3b09b9 100644
--- a/arch/x86/include/asm/pkeys.h
+++ b/arch/x86/include/asm/pkeys.h
@@ -46,6 +46,15 @@ extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
static inline
bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey)
{
+ /*
+ * "Allocated" pkeys are those that have been returned
+ * from pkey_alloc(). pkey 0 is special, and never
+ * returned from pkey_alloc().
+ */
+ if (pkey <= 0)
+ return false;
+ if (pkey >= arch_max_pkey())
+ return false;
return mm_pkey_allocation_map(mm) & (1U << pkey);
}
@@ -82,12 +91,6 @@ int mm_pkey_alloc(struct mm_struct *mm)
static inline
int mm_pkey_free(struct mm_struct *mm, int pkey)
{
- /*
- * pkey 0 is special, always allocated and can never
- * be freed.
- */
- if (!pkey)
- return -EINVAL;
if (!mm_pkey_is_allocated(mm, pkey))
return -EINVAL;
diff --git a/arch/x86/include/asm/purgatory.h b/arch/x86/include/asm/purgatory.h
new file mode 100644
index 0000000..d7da272
--- /dev/null
+++ b/arch/x86/include/asm/purgatory.h
@@ -0,0 +1,20 @@
+#ifndef _ASM_X86_PURGATORY_H
+#define _ASM_X86_PURGATORY_H
+
+#ifndef __ASSEMBLY__
+#include <linux/purgatory.h>
+
+extern void purgatory(void);
+/*
+ * These forward declarations serve two purposes:
+ *
+ * 1) Make sparse happy when checking arch/purgatory
+ * 2) Document that these are required to be global so the symbol
+ * lookup in kexec works
+ */
+extern unsigned long purgatory_backup_dest;
+extern unsigned long purgatory_backup_src;
+extern unsigned long purgatory_backup_sz;
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_PURGATORY_H */
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index a04eabd..27e9f9d 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -12,6 +12,8 @@ extern int recalibrate_cpu_khz(void);
extern int no_timer_check;
+extern bool using_native_sched_clock(void);
+
/*
* We use the full linear equation: f(x) = a + b*x, in order to allow
* a continuous function in the face of dynamic freq changes.
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 6fa8594..fc5abff 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -188,7 +188,7 @@ static inline void __native_flush_tlb_single(unsigned long addr)
static inline void __flush_tlb_all(void)
{
- if (static_cpu_has(X86_FEATURE_PGE))
+ if (boot_cpu_has(X86_FEATURE_PGE))
__flush_tlb_global();
else
__flush_tlb();
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 72e8300..9cffb44 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -485,15 +485,17 @@ static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr)
if (paddr < uv_hub_info->lowmem_remap_top)
paddr |= uv_hub_info->lowmem_remap_base;
- paddr |= uv_hub_info->gnode_upper;
- if (m_val)
+
+ if (m_val) {
+ paddr |= uv_hub_info->gnode_upper;
paddr = ((paddr << uv_hub_info->m_shift)
>> uv_hub_info->m_shift) |
((paddr >> uv_hub_info->m_val)
<< uv_hub_info->n_lshift);
- else
+ } else {
paddr |= uv_soc_phys_ram_to_nasid(paddr)
<< uv_hub_info->gpa_shift;
+ }
return paddr;
}
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 5138dac..07244ea 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -58,7 +58,7 @@ struct setup_header {
__u32 header;
__u16 version;
__u32 realmode_swtch;
- __u16 start_sys;
+ __u16 start_sys_seg;
__u16 kernel_version;
__u8 type_of_loader;
__u8 loadflags;
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index ae32838..b2879cc23 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -179,10 +179,15 @@ static int acpi_register_lapic(int id, u32 acpiid, u8 enabled)
return -EINVAL;
}
+ if (!enabled) {
+ ++disabled_cpus;
+ return -EINVAL;
+ }
+
if (boot_cpu_physical_apicid != -1U)
ver = boot_cpu_apic_version;
- cpu = __generic_processor_info(id, ver, enabled);
+ cpu = generic_processor_info(id, ver);
if (cpu >= 0)
early_per_cpu(x86_cpu_to_acpiid, cpu) = acpiid;
@@ -710,7 +715,7 @@ static void __init acpi_set_irq_model_ioapic(void)
#ifdef CONFIG_ACPI_HOTPLUG_CPU
#include <acpi/processor.h>
-int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
+static int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
{
#ifdef CONFIG_ACPI_NUMA
int nid;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 4261b32..8ccb7ef 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1610,24 +1610,15 @@ static inline void try_to_enable_x2apic(int remap_mode) { }
static inline void __x2apic_enable(void) { }
#endif /* !CONFIG_X86_X2APIC */
-static int __init try_to_enable_IR(void)
-{
-#ifdef CONFIG_X86_IO_APIC
- if (!x2apic_enabled() && skip_ioapic_setup) {
- pr_info("Not enabling interrupt remapping due to skipped IO-APIC setup\n");
- return -1;
- }
-#endif
- return irq_remapping_enable();
-}
-
void __init enable_IR_x2apic(void)
{
unsigned long flags;
int ret, ir_stat;
- if (skip_ioapic_setup)
+ if (skip_ioapic_setup) {
+ pr_info("Not enabling interrupt remapping due to skipped IO-APIC setup\n");
return;
+ }
ir_stat = irq_remapping_prepare();
if (ir_stat < 0 && !x2apic_supported())
@@ -1645,7 +1636,7 @@ void __init enable_IR_x2apic(void)
/* If irq_remapping_prepare() succeeded, try to enable it */
if (ir_stat >= 0)
- ir_stat = try_to_enable_IR();
+ ir_stat = irq_remapping_enable();
/* ir_stat contains the remap mode or an error code */
try_to_enable_x2apic(ir_stat);
@@ -2062,17 +2053,17 @@ static int allocate_logical_cpuid(int apicid)
/* Allocate a new cpuid. */
if (nr_logical_cpuids >= nr_cpu_ids) {
- WARN_ONCE(1, "Only %d processors supported."
+ WARN_ONCE(1, "APIC: NR_CPUS/possible_cpus limit of %i reached. "
"Processor %d/0x%x and the rest are ignored.\n",
- nr_cpu_ids - 1, nr_logical_cpuids, apicid);
- return -1;
+ nr_cpu_ids, nr_logical_cpuids, apicid);
+ return -EINVAL;
}
cpuid_to_apicid[nr_logical_cpuids] = apicid;
return nr_logical_cpuids++;
}
-int __generic_processor_info(int apicid, int version, bool enabled)
+int generic_processor_info(int apicid, int version)
{
int cpu, max = nr_cpu_ids;
bool boot_cpu_detected = physid_isset(boot_cpu_physical_apicid,
@@ -2130,11 +2121,9 @@ int __generic_processor_info(int apicid, int version, bool enabled)
if (num_processors >= nr_cpu_ids) {
int thiscpu = max + disabled_cpus;
- if (enabled) {
- pr_warning("APIC: NR_CPUS/possible_cpus limit of %i "
- "reached. Processor %d/0x%x ignored.\n",
- max, thiscpu, apicid);
- }
+ pr_warning("APIC: NR_CPUS/possible_cpus limit of %i "
+ "reached. Processor %d/0x%x ignored.\n",
+ max, thiscpu, apicid);
disabled_cpus++;
return -EINVAL;
@@ -2186,23 +2175,13 @@ int __generic_processor_info(int apicid, int version, bool enabled)
apic->x86_32_early_logical_apicid(cpu);
#endif
set_cpu_possible(cpu, true);
-
- if (enabled) {
- num_processors++;
- physid_set(apicid, phys_cpu_present_map);
- set_cpu_present(cpu, true);
- } else {
- disabled_cpus++;
- }
+ physid_set(apicid, phys_cpu_present_map);
+ set_cpu_present(cpu, true);
+ num_processors++;
return cpu;
}
-int generic_processor_info(int apicid, int version)
-{
- return __generic_processor_info(apicid, version, true);
-}
-
int hard_smp_processor_id(void)
{
return read_apic_id();
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index e9f8f8c..86f20cc 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -1105,7 +1105,8 @@ void __init uv_init_hub_info(struct uv_hub_info_s *hi)
node_id.v = uv_read_local_mmr(UVH_NODE_ID);
uv_cpuid.gnode_shift = max_t(unsigned int, uv_cpuid.gnode_shift, mn.n_val);
hi->gnode_extra = (node_id.s.node_id & ~((1 << uv_cpuid.gnode_shift) - 1)) >> 1;
- hi->gnode_upper = (unsigned long)hi->gnode_extra << mn.m_val;
+ if (mn.m_val)
+ hi->gnode_upper = (u64)hi->gnode_extra << mn.m_val;
if (uv_gp_table) {
hi->global_mmr_base = uv_gp_table->mmr_base;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 35a5d5d..c36140d 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -556,10 +556,6 @@ static void early_init_amd(struct cpuinfo_x86 *c)
if (c->x86_power & (1 << 8)) {
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
- if (check_tsc_unstable())
- clear_sched_clock_stable();
- } else {
- clear_sched_clock_stable();
}
/* Bit 12 of 8000_0007 edx is accumulated power mechanism. */
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index adc0ebd..43955ee 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -105,8 +105,6 @@ static void early_init_centaur(struct cpuinfo_x86 *c)
#ifdef CONFIG_X86_64
set_cpu_cap(c, X86_FEATURE_SYSENTER32);
#endif
-
- clear_sched_clock_stable();
}
static void init_centaur(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b11b38c..58094a1 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -88,7 +88,6 @@ static void default_init(struct cpuinfo_x86 *c)
strcpy(c->x86_model_id, "386");
}
#endif
- clear_sched_clock_stable();
}
static const struct cpu_dev default_cpu = {
@@ -1077,8 +1076,6 @@ static void identify_cpu(struct cpuinfo_x86 *c)
*/
if (this_cpu->c_init)
this_cpu->c_init(c);
- else
- clear_sched_clock_stable();
/* Disable the PN if appropriate */
squash_the_stupid_serial_number(c);
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 0a3bc19..a70fd61 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -185,7 +185,6 @@ static void early_init_cyrix(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_CYRIX_ARR);
break;
}
- clear_sched_clock_stable();
}
static void init_cyrix(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index fe0a615..0631977 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -162,10 +162,6 @@ static void early_init_intel(struct cpuinfo_x86 *c)
if (c->x86_power & (1 << 8)) {
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
- if (check_tsc_unstable())
- clear_sched_clock_stable();
- } else {
- clear_sched_clock_stable();
}
/* Penwell and Cloverview have the TSC which doesn't sleep on S3 */
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 0bbe0f3..9ac2a5c 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -28,7 +28,6 @@
#include <linux/sched/signal.h>
#include <linux/sched/task.h>
#include <linux/slab.h>
-#include <linux/cpu.h>
#include <linux/task_work.h>
#include <uapi/linux/magic.h>
@@ -728,7 +727,7 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn)
if (atomic_dec_and_test(&rdtgrp->waitcount) &&
(rdtgrp->flags & RDT_DELETED)) {
kernfs_unbreak_active_protection(kn);
- kernfs_put(kn);
+ kernfs_put(rdtgrp->kn);
kfree(rdtgrp);
} else {
kernfs_unbreak_active_protection(kn);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 8e9725c..5accfbd 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -54,6 +54,8 @@
static DEFINE_MUTEX(mce_chrdev_read_mutex);
+static int mce_chrdev_open_count; /* #times opened */
+
#define mce_log_get_idx_check(p) \
({ \
RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \
@@ -598,6 +600,10 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
if (atomic_read(&num_notifiers) > 2)
return NOTIFY_DONE;
+ /* Don't print when mcelog is running */
+ if (mce_chrdev_open_count > 0)
+ return NOTIFY_DONE;
+
__print_mce(m);
return NOTIFY_DONE;
@@ -1828,7 +1834,6 @@ void mcheck_cpu_clear(struct cpuinfo_x86 *c)
*/
static DEFINE_SPINLOCK(mce_chrdev_state_lock);
-static int mce_chrdev_open_count; /* #times opened */
static int mce_chrdev_open_exclu; /* already open exclusive? */
static int mce_chrdev_open(struct inode *inode, struct file *file)
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 524cc57..6e4a047 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -60,7 +60,7 @@ static const char * const th_names[] = {
"load_store",
"insn_fetch",
"combined_unit",
- "",
+ "decode_unit",
"northbridge",
"execution_unit",
};
diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c
index 8457b49..d77d07a 100644
--- a/arch/x86/kernel/cpu/transmeta.c
+++ b/arch/x86/kernel/cpu/transmeta.c
@@ -16,8 +16,6 @@ static void early_init_transmeta(struct cpuinfo_x86 *c)
if (xlvl >= 0x80860001)
c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001);
}
-
- clear_sched_clock_stable();
}
static void init_transmeta(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 891f4da..22403a2 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -30,7 +30,6 @@
#include <asm/hypervisor.h>
#include <asm/timer.h>
#include <asm/apic.h>
-#include <asm/timer.h>
#undef pr_fmt
#define pr_fmt(fmt) "vmware: " fmt
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 8639bb2..cbd73eb 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -29,6 +29,12 @@
#include <asm/ftrace.h>
#include <asm/nops.h>
+#if defined(CONFIG_FUNCTION_GRAPH_TRACER) && \
+ !defined(CC_USING_FENTRY) && \
+ !defined(CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE)
+# error The following combination is not supported: ((compiler missing -mfentry) || (CONFIG_X86_32 and !CONFIG_DYNAMIC_FTRACE)) && CONFIG_FUNCTION_GRAPH_TRACER && CONFIG_CC_OPTIMIZE_FOR_SIZE
+#endif
+
#ifdef CONFIG_DYNAMIC_FTRACE
int ftrace_arch_code_modify_prepare(void)
@@ -535,7 +541,7 @@ static void run_sync(void)
{
int enable_irqs = irqs_disabled();
- /* We may be called with interrupts disbled (on bootup). */
+ /* We may be called with interrupts disabled (on bootup). */
if (enable_irqs)
local_irq_enable();
on_each_cpu(do_sync_core, NULL, 1);
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 54a2372..b5785c1 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -4,6 +4,7 @@
* Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
*/
+#define DISABLE_BRANCH_PROFILING
#include <linux/init.h>
#include <linux/linkage.h>
#include <linux/types.h>
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index dc6ba5b..89ff7af 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -354,7 +354,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer)
irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq));
irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
- disable_irq(hdev->irq);
+ disable_hardirq(hdev->irq);
irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
enable_irq(hdev->irq);
}
diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index bdb83e4..38b6458 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -167,7 +167,7 @@ static int __init boot_params_kdebugfs_init(void)
struct dentry *dbp, *version, *data;
int error = -ENOMEM;
- dbp = debugfs_create_dir("boot_params", NULL);
+ dbp = debugfs_create_dir("boot_params", arch_debugfs_dir);
if (!dbp)
return -ENOMEM;
diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h
index c6ee63f..d688826 100644
--- a/arch/x86/kernel/kprobes/common.h
+++ b/arch/x86/kernel/kprobes/common.h
@@ -67,7 +67,7 @@
#endif
/* Ensure if the instruction can be boostable */
-extern int can_boost(kprobe_opcode_t *instruction);
+extern int can_boost(kprobe_opcode_t *instruction, void *addr);
/* Recover instruction if given address is probed */
extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf,
unsigned long addr);
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 6384eb7..993fa4f 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -167,12 +167,12 @@ NOKPROBE_SYMBOL(skip_prefixes);
* Returns non-zero if opcode is boostable.
* RIP relative instructions are adjusted at copying time in 64 bits mode
*/
-int can_boost(kprobe_opcode_t *opcodes)
+int can_boost(kprobe_opcode_t *opcodes, void *addr)
{
kprobe_opcode_t opcode;
kprobe_opcode_t *orig_opcodes = opcodes;
- if (search_exception_tables((unsigned long)opcodes))
+ if (search_exception_tables((unsigned long)addr))
return 0; /* Page fault may occur on this address. */
retry:
@@ -417,7 +417,7 @@ static int arch_copy_kprobe(struct kprobe *p)
* __copy_instruction can modify the displacement of the instruction,
* but it doesn't affect boostable check.
*/
- if (can_boost(p->ainsn.insn))
+ if (can_boost(p->ainsn.insn, p->addr))
p->ainsn.boostable = 0;
else
p->ainsn.boostable = -1;
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 3d1bee9..3e7c6e5 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -178,7 +178,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src)
while (len < RELATIVEJUMP_SIZE) {
ret = __copy_instruction(dest + len, src + len);
- if (!ret || !can_boost(dest + len))
+ if (!ret || !can_boost(dest + len, src + len))
return -EINVAL;
len += ret;
}
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 307b1f4..857cdbd 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -194,19 +194,22 @@ static int arch_update_purgatory(struct kimage *image)
/* Setup copying of backup region */
if (image->type == KEXEC_TYPE_CRASH) {
- ret = kexec_purgatory_get_set_symbol(image, "backup_dest",
+ ret = kexec_purgatory_get_set_symbol(image,
+ "purgatory_backup_dest",
&image->arch.backup_load_addr,
sizeof(image->arch.backup_load_addr), 0);
if (ret)
return ret;
- ret = kexec_purgatory_get_set_symbol(image, "backup_src",
+ ret = kexec_purgatory_get_set_symbol(image,
+ "purgatory_backup_src",
&image->arch.backup_src_start,
sizeof(image->arch.backup_src_start), 0);
if (ret)
return ret;
- ret = kexec_purgatory_get_set_symbol(image, "backup_sz",
+ ret = kexec_purgatory_get_set_symbol(image,
+ "purgatory_backup_sz",
&image->arch.backup_src_sz,
sizeof(image->arch.backup_src_sz), 0);
if (ret)
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index f088ea4..a723ae94 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -166,11 +166,9 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action)
spin_lock_irqsave(&desc->lock, flags);
/*
- * most handlers of type NMI_UNKNOWN never return because
- * they just assume the NMI is theirs. Just a sanity check
- * to manage expectations
+ * Indicate if there are multiple registrations on the
+ * internal NMI handler call chains (SERR and IO_CHECK).
*/
- WARN_ON_ONCE(type == NMI_UNKNOWN && !list_empty(&desc->head));
WARN_ON_ONCE(type == NMI_SERR && !list_empty(&desc->head));
WARN_ON_ONCE(type == NMI_IO_CHECK && !list_empty(&desc->head));
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index e244c19..067f981 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -223,6 +223,22 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
DMI_MATCH(DMI_BOARD_NAME, "P4S800"),
},
},
+ { /* Handle problems with rebooting on ASUS EeeBook X205TA */
+ .callback = set_acpi_reboot,
+ .ident = "ASUS EeeBook X205TA",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "X205TA"),
+ },
+ },
+ { /* Handle problems with rebooting on ASUS EeeBook X205TAW */
+ .callback = set_acpi_reboot,
+ .ident = "ASUS EeeBook X205TAW",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "X205TAW"),
+ },
+ },
/* Certec */
{ /* Handle problems with rebooting on Certec BPC600 */
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 46bcda4..714dfba 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -327,9 +327,16 @@ unsigned long long sched_clock(void)
{
return paravirt_sched_clock();
}
+
+bool using_native_sched_clock(void)
+{
+ return pv_time_ops.sched_clock == native_sched_clock;
+}
#else
unsigned long long
sched_clock(void) __attribute__((alias("native_sched_clock")));
+
+bool using_native_sched_clock(void) { return true; }
#endif
int check_tsc_unstable(void)
@@ -1112,8 +1119,10 @@ static void tsc_cs_mark_unstable(struct clocksource *cs)
{
if (tsc_unstable)
return;
+
tsc_unstable = 1;
- clear_sched_clock_stable();
+ if (using_native_sched_clock())
+ clear_sched_clock_stable();
disable_sched_clock_irqtime();
pr_info("Marking TSC unstable due to clocksource watchdog\n");
}
@@ -1135,18 +1144,20 @@ static struct clocksource clocksource_tsc = {
void mark_tsc_unstable(char *reason)
{
- if (!tsc_unstable) {
- tsc_unstable = 1;
+ if (tsc_unstable)
+ return;
+
+ tsc_unstable = 1;
+ if (using_native_sched_clock())
clear_sched_clock_stable();
- disable_sched_clock_irqtime();
- pr_info("Marking TSC unstable due to %s\n", reason);
- /* Change only the rating, when not registered */
- if (clocksource_tsc.mult)
- clocksource_mark_unstable(&clocksource_tsc);
- else {
- clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE;
- clocksource_tsc.rating = 0;
- }
+ disable_sched_clock_irqtime();
+ pr_info("Marking TSC unstable due to %s\n", reason);
+ /* Change only the rating, when not registered */
+ if (clocksource_tsc.mult) {
+ clocksource_mark_unstable(&clocksource_tsc);
+ } else {
+ clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE;
+ clocksource_tsc.rating = 0;
}
}
@@ -1322,6 +1333,8 @@ static int __init init_tsc_clocksource(void)
* the refined calibration and directly register it as a clocksource.
*/
if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) {
+ if (boot_cpu_has(X86_FEATURE_ART))
+ art_related_clocksource = &clocksource_tsc;
clocksource_register_khz(&clocksource_tsc, tsc_khz);
return 0;
}
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index 478d15d..0833926 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -82,19 +82,43 @@ static size_t regs_size(struct pt_regs *regs)
return sizeof(*regs);
}
+#ifdef CONFIG_X86_32
+#define GCC_REALIGN_WORDS 3
+#else
+#define GCC_REALIGN_WORDS 1
+#endif
+
static bool is_last_task_frame(struct unwind_state *state)
{
- unsigned long bp = (unsigned long)state->bp;
- unsigned long regs = (unsigned long)task_pt_regs(state->task);
+ unsigned long *last_bp = (unsigned long *)task_pt_regs(state->task) - 2;
+ unsigned long *aligned_bp = last_bp - GCC_REALIGN_WORDS;
/*
* We have to check for the last task frame at two different locations
* because gcc can occasionally decide to realign the stack pointer and
- * change the offset of the stack frame by a word in the prologue of a
- * function called by head/entry code.
+ * change the offset of the stack frame in the prologue of a function
+ * called by head/entry code. Examples:
+ *
+ * <start_secondary>:
+ * push %edi
+ * lea 0x8(%esp),%edi
+ * and $0xfffffff8,%esp
+ * pushl -0x4(%edi)
+ * push %ebp
+ * mov %esp,%ebp
+ *
+ * <x86_64_start_kernel>:
+ * lea 0x8(%rsp),%r10
+ * and $0xfffffffffffffff0,%rsp
+ * pushq -0x8(%r10)
+ * push %rbp
+ * mov %rsp,%rbp
+ *
+ * Note that after aligning the stack, it pushes a duplicate copy of
+ * the return address before pushing the frame pointer.
*/
- return bp == regs - FRAME_HEADER_SIZE ||
- bp == regs - FRAME_HEADER_SIZE - sizeof(long);
+ return (state->bp == last_bp ||
+ (state->bp == aligned_bp && *(aligned_bp+1) == *(last_bp+1)));
}
/*
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index 73ea24d..047b17a 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -657,6 +657,9 @@ void kvm_pic_destroy(struct kvm *kvm)
{
struct kvm_pic *vpic = kvm->arch.vpic;
+ if (!vpic)
+ return;
+
kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_master);
kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_slave);
kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_eclr);
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 6e219e5..289270a 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -635,6 +635,9 @@ void kvm_ioapic_destroy(struct kvm *kvm)
{
struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+ if (!ioapic)
+ return;
+
cancel_delayed_work_sync(&ioapic->eoi_inject);
kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev);
kvm->arch.vioapic = NULL;
diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c
index 37942e4..60168cd 100644
--- a/arch/x86/kvm/page_track.c
+++ b/arch/x86/kvm/page_track.c
@@ -160,6 +160,14 @@ bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn,
return !!ACCESS_ONCE(slot->arch.gfn_track[mode][index]);
}
+void kvm_page_track_cleanup(struct kvm *kvm)
+{
+ struct kvm_page_track_notifier_head *head;
+
+ head = &kvm->arch.track_notifier_head;
+ cleanup_srcu_struct(&head->track_srcu);
+}
+
void kvm_page_track_init(struct kvm *kvm)
{
struct kvm_page_track_notifier_head *head;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index d1efe2c..5fba706 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1379,6 +1379,9 @@ static void avic_vm_destroy(struct kvm *kvm)
unsigned long flags;
struct kvm_arch *vm_data = &kvm->arch;
+ if (!avic)
+ return;
+
avic_free_vm_id(vm_data->avic_vm_id);
if (vm_data->avic_logical_id_table_page)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 283aa86..2ee00db 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1239,6 +1239,11 @@ static inline bool cpu_has_vmx_invvpid_global(void)
return vmx_capability.vpid & VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT;
}
+static inline bool cpu_has_vmx_invvpid(void)
+{
+ return vmx_capability.vpid & VMX_VPID_INVVPID_BIT;
+}
+
static inline bool cpu_has_vmx_ept(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
@@ -2753,7 +2758,6 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
SECONDARY_EXEC_RDTSCP |
SECONDARY_EXEC_DESC |
SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
- SECONDARY_EXEC_ENABLE_VPID |
SECONDARY_EXEC_APIC_REGISTER_VIRT |
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
SECONDARY_EXEC_WBINVD_EXITING |
@@ -2781,10 +2785,12 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
* though it is treated as global context. The alternative is
* not failing the single-context invvpid, and it is worse.
*/
- if (enable_vpid)
+ if (enable_vpid) {
+ vmx->nested.nested_vmx_secondary_ctls_high |=
+ SECONDARY_EXEC_ENABLE_VPID;
vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT |
VMX_VPID_EXTENT_SUPPORTED_MASK;
- else
+ } else
vmx->nested.nested_vmx_vpid_caps = 0;
if (enable_unrestricted_guest)
@@ -4024,6 +4030,12 @@ static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
__vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid);
}
+static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu)
+{
+ if (enable_ept)
+ vmx_flush_tlb(vcpu);
+}
+
static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
{
ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits;
@@ -6517,8 +6529,10 @@ static __init int hardware_setup(void)
if (boot_cpu_has(X86_FEATURE_NX))
kvm_enable_efer_bits(EFER_NX);
- if (!cpu_has_vmx_vpid())
+ if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() ||
+ !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global()))
enable_vpid = 0;
+
if (!cpu_has_vmx_shadow_vmcs())
enable_shadow_vmcs = 0;
if (enable_shadow_vmcs)
@@ -7258,9 +7272,8 @@ static int handle_vmoff(struct kvm_vcpu *vcpu)
static int handle_vmclear(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ u32 zero = 0;
gpa_t vmptr;
- struct vmcs12 *vmcs12;
- struct page *page;
if (!nested_vmx_check_permission(vcpu))
return 1;
@@ -7271,22 +7284,9 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
if (vmptr == vmx->nested.current_vmptr)
nested_release_vmcs12(vmx);
- page = nested_get_page(vcpu, vmptr);
- if (page == NULL) {
- /*
- * For accurate processor emulation, VMCLEAR beyond available
- * physical memory should do nothing at all. However, it is
- * possible that a nested vmx bug, not a guest hypervisor bug,
- * resulted in this case, so let's shut down before doing any
- * more damage:
- */
- kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
- return 1;
- }
- vmcs12 = kmap(page);
- vmcs12->launch_state = 0;
- kunmap(page);
- nested_release_page(page);
+ kvm_vcpu_write_guest(vcpu,
+ vmptr + offsetof(struct vmcs12, launch_state),
+ &zero, sizeof(zero));
nested_free_vmcs02(vmx, vmptr);
@@ -8515,7 +8515,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
&& kvm_vmx_exit_handlers[exit_reason])
return kvm_vmx_exit_handlers[exit_reason](vcpu);
else {
- WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_reason);
+ vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n",
+ exit_reason);
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
}
@@ -8561,6 +8562,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
} else {
sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+ vmx_flush_tlb_ept_only(vcpu);
}
vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);
@@ -8586,8 +8588,10 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
*/
if (!is_guest_mode(vcpu) ||
!nested_cpu_has2(get_vmcs12(&vmx->vcpu),
- SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
vmcs_write64(APIC_ACCESS_ADDR, hpa);
+ vmx_flush_tlb_ept_only(vcpu);
+ }
}
static void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
@@ -9694,10 +9698,8 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
return false;
page = nested_get_page(vcpu, vmcs12->msr_bitmap);
- if (!page) {
- WARN_ON(1);
+ if (!page)
return false;
- }
msr_bitmap_l1 = (unsigned long *)kmap(page);
memset(msr_bitmap_l0, 0xff, PAGE_SIZE);
@@ -9990,7 +9992,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 exec_control;
- bool nested_ept_enabled = false;
vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
@@ -10137,8 +10138,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
vmcs12->guest_intr_status);
}
- nested_ept_enabled = (exec_control & SECONDARY_EXEC_ENABLE_EPT) != 0;
-
/*
* Write an illegal value to APIC_ACCESS_ADDR. Later,
* nested_get_vmcs12_pages will either fix it up or
@@ -10271,6 +10270,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
if (nested_cpu_has_ept(vmcs12)) {
kvm_mmu_unload(vcpu);
nested_ept_init_mmu_context(vcpu);
+ } else if (nested_cpu_has2(vmcs12,
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+ vmx_flush_tlb_ept_only(vcpu);
}
/*
@@ -10298,12 +10300,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
vmx_set_efer(vcpu, vcpu->arch.efer);
/* Shadow page tables on either EPT or shadow page tables. */
- if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_ept_enabled,
+ if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12),
entry_failure_code))
return 1;
- kvm_mmu_reset_context(vcpu);
-
if (!enable_ept)
vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested;
@@ -11072,6 +11072,10 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
vmx->nested.change_vmcs01_virtual_x2apic_mode = false;
vmx_set_virtual_x2apic_mode(vcpu,
vcpu->arch.apic_base & X2APIC_ENABLE);
+ } else if (!nested_cpu_has_ept(vmcs12) &&
+ nested_cpu_has2(vmcs12,
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+ vmx_flush_tlb_ept_only(vcpu);
}
/* This is needed for same reason as it was needed in prepare_vmcs02 */
@@ -11121,8 +11125,10 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
*/
static void vmx_leave_nested(struct kvm_vcpu *vcpu)
{
- if (is_guest_mode(vcpu))
+ if (is_guest_mode(vcpu)) {
+ to_vmx(vcpu)->nested.nested_run_pending = 0;
nested_vmx_vmexit(vcpu, -1, 0, 0);
+ }
free_nested(to_vmx(vcpu));
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1faf620..ccbd45e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8153,11 +8153,12 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
if (kvm_x86_ops->vm_destroy)
kvm_x86_ops->vm_destroy(kvm);
kvm_iommu_unmap_guest(kvm);
- kfree(kvm->arch.vpic);
- kfree(kvm->arch.vioapic);
+ kvm_pic_destroy(kvm);
+ kvm_ioapic_destroy(kvm);
kvm_free_vcpus(kvm);
kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
kvm_mmu_uninit_vm(kvm);
+ kvm_page_track_cleanup(kvm);
}
void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
@@ -8566,11 +8567,11 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
{
struct x86_exception fault;
- trace_kvm_async_pf_ready(work->arch.token, work->gva);
if (work->wakeup_all)
work->arch.token = ~0; /* broadcast wakeup */
else
kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
+ trace_kvm_async_pf_ready(work->arch.token, work->gva);
if ((vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) &&
!apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) {
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 779782f..9a53a06 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -290,7 +290,7 @@
_ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
+ _ASM_EXTABLE_FAULT(.L_cache_w2, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail)
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 99c7805..1f3b6ef 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -106,32 +106,35 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
unsigned long end, int write, struct page **pages, int *nr)
{
struct dev_pagemap *pgmap = NULL;
- int nr_start = *nr;
- pte_t *ptep;
+ int nr_start = *nr, ret = 0;
+ pte_t *ptep, *ptem;
- ptep = pte_offset_map(&pmd, addr);
+ /*
+ * Keep the original mapped PTE value (ptem) around since we
+ * might increment ptep off the end of the page when finishing
+ * our loop iteration.
+ */
+ ptem = ptep = pte_offset_map(&pmd, addr);
do {
pte_t pte = gup_get_pte(ptep);
struct page *page;
/* Similar to the PMD case, NUMA hinting must take slow path */
- if (pte_protnone(pte)) {
- pte_unmap(ptep);
- return 0;
- }
+ if (pte_protnone(pte))
+ break;
+
+ if (!pte_allows_gup(pte_val(pte), write))
+ break;
if (pte_devmap(pte)) {
pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
if (unlikely(!pgmap)) {
undo_dev_pagemap(nr, nr_start, pages);
- pte_unmap(ptep);
- return 0;
+ break;
}
- } else if (!pte_allows_gup(pte_val(pte), write) ||
- pte_special(pte)) {
- pte_unmap(ptep);
- return 0;
- }
+ } else if (pte_special(pte))
+ break;
+
VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
page = pte_page(pte);
get_page(page);
@@ -141,9 +144,11 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
(*nr)++;
} while (ptep++, addr += PAGE_SIZE, addr != end);
- pte_unmap(ptep - 1);
+ if (addr == end)
+ ret = 1;
+ pte_unmap(ptem);
- return 1;
+ return ret;
}
static inline void get_head_page_multiple(struct page *page, int nr)
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 8d63d7a..4c90cfd 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -1,3 +1,4 @@
+#define DISABLE_BRANCH_PROFILING
#define pr_fmt(fmt) "kasan: " fmt
#include <linux/bootmem.h>
#include <linux/kasan.h>
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 887e571..aed2064 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -48,7 +48,7 @@ static const unsigned long vaddr_start = __PAGE_OFFSET_BASE;
#if defined(CONFIG_X86_ESPFIX64)
static const unsigned long vaddr_end = ESPFIX_BASE_ADDR;
#elif defined(CONFIG_EFI)
-static const unsigned long vaddr_end = EFI_VA_START;
+static const unsigned long vaddr_end = EFI_VA_END;
#else
static const unsigned long vaddr_end = __START_KERNEL_map;
#endif
@@ -105,7 +105,7 @@ void __init kernel_randomize_memory(void)
*/
BUILD_BUG_ON(vaddr_start >= vaddr_end);
BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_ESPFIX64) &&
- vaddr_end >= EFI_VA_START);
+ vaddr_end >= EFI_VA_END);
BUILD_BUG_ON((IS_ENABLED(CONFIG_X86_ESPFIX64) ||
IS_ENABLED(CONFIG_EFI)) &&
vaddr_end >= __START_KERNEL_map);
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index 5126dfd..cd44ae7 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -590,7 +590,7 @@ static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm,
* we might run off the end of the bounds table if we are on
* a 64-bit kernel and try to get 8 bytes.
*/
-int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret,
+static int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret,
long __user *bd_entry_ptr)
{
u32 bd_entry_32;
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 0cb52ae..190e718 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -735,6 +735,15 @@ void pcibios_disable_device (struct pci_dev *dev)
pcibios_disable_irq(dev);
}
+#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
+void pcibios_release_device(struct pci_dev *dev)
+{
+ if (atomic_dec_return(&dev->enable_cnt) >= 0)
+ pcibios_disable_device(dev);
+
+}
+#endif
+
int pci_ext_cfg_avail(void)
{
if (raw_pci_ext_ops)
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index e1fb269..292ab03 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -234,23 +234,14 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
return 1;
for_each_pci_msi_entry(msidesc, dev) {
- __pci_read_msi_msg(msidesc, &msg);
- pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) |
- ((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff);
- if (msg.data != XEN_PIRQ_MSI_DATA ||
- xen_irq_from_pirq(pirq) < 0) {
- pirq = xen_allocate_pirq_msi(dev, msidesc);
- if (pirq < 0) {
- irq = -ENODEV;
- goto error;
- }
- xen_msi_compose_msg(dev, pirq, &msg);
- __pci_write_msi_msg(msidesc, &msg);
- dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq);
- } else {
- dev_dbg(&dev->dev,
- "xen: msi already bound to pirq=%d\n", pirq);
+ pirq = xen_allocate_pirq_msi(dev, msidesc);
+ if (pirq < 0) {
+ irq = -ENODEV;
+ goto error;
}
+ xen_msi_compose_msg(dev, pirq, &msg);
+ __pci_write_msi_msg(msidesc, &msg);
+ dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq);
irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq,
(type == PCI_CAP_ID_MSI) ? nvec : 1,
(type == PCI_CAP_ID_MSIX) ?
diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile
index a7dbec4..3dbde04 100644
--- a/arch/x86/platform/intel-mid/device_libs/Makefile
+++ b/arch/x86/platform/intel-mid/device_libs/Makefile
@@ -26,5 +26,6 @@
obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_tca6416.o
# MISC Devices
obj-$(subst m,y,$(CONFIG_KEYBOARD_GPIO)) += platform_gpio_keys.o
+obj-$(subst m,y,$(CONFIG_INTEL_MID_POWER_BUTTON)) += platform_mrfld_power_btn.o
obj-$(subst m,y,$(CONFIG_RTC_DRV_CMOS)) += platform_mrfld_rtc.o
obj-$(subst m,y,$(CONFIG_INTEL_MID_WATCHDOG)) += platform_mrfld_wdt.o
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_power_btn.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_power_btn.c
new file mode 100644
index 0000000..a6c3705
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_power_btn.c
@@ -0,0 +1,82 @@
+/*
+ * Intel Merrifield power button support
+ *
+ * (C) Copyright 2017 Intel Corporation
+ *
+ * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/init.h>
+#include <linux/ioport.h>
+#include <linux/platform_device.h>
+#include <linux/sfi.h>
+
+#include <asm/intel-mid.h>
+#include <asm/intel_scu_ipc.h>
+
+static struct resource mrfld_power_btn_resources[] = {
+ {
+ .flags = IORESOURCE_IRQ,
+ },
+};
+
+static struct platform_device mrfld_power_btn_dev = {
+ .name = "msic_power_btn",
+ .id = PLATFORM_DEVID_NONE,
+ .num_resources = ARRAY_SIZE(mrfld_power_btn_resources),
+ .resource = mrfld_power_btn_resources,
+};
+
+static int mrfld_power_btn_scu_status_change(struct notifier_block *nb,
+ unsigned long code, void *data)
+{
+ if (code == SCU_DOWN) {
+ platform_device_unregister(&mrfld_power_btn_dev);
+ return 0;
+ }
+
+ return platform_device_register(&mrfld_power_btn_dev);
+}
+
+static struct notifier_block mrfld_power_btn_scu_notifier = {
+ .notifier_call = mrfld_power_btn_scu_status_change,
+};
+
+static int __init register_mrfld_power_btn(void)
+{
+ if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER)
+ return -ENODEV;
+
+ /*
+ * We need to be sure that the SCU IPC is ready before
+ * PMIC power button device can be registered:
+ */
+ intel_scu_notifier_add(&mrfld_power_btn_scu_notifier);
+
+ return 0;
+}
+arch_initcall(register_mrfld_power_btn);
+
+static void __init *mrfld_power_btn_platform_data(void *info)
+{
+ struct resource *res = mrfld_power_btn_resources;
+ struct sfi_device_table_entry *pentry = info;
+
+ res->start = res->end = pentry->irq;
+ return NULL;
+}
+
+static const struct devs_id mrfld_power_btn_dev_id __initconst = {
+ .name = "bcove_power_btn",
+ .type = SFI_DEV_TYPE_IPC,
+ .delay = 1,
+ .msic = 1,
+ .get_platform_data = &mrfld_power_btn_platform_data,
+};
+
+sfi_device(mrfld_power_btn_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
index 86edd1e9..9e304e2 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
@@ -19,7 +19,7 @@
#include <asm/intel_scu_ipc.h>
#include <asm/io_apic.h>
-#define TANGIER_EXT_TIMER0_MSI 15
+#define TANGIER_EXT_TIMER0_MSI 12
static struct platform_device wdt_dev = {
.name = "intel_mid_wdt",
diff --git a/arch/x86/platform/intel-mid/mfld.c b/arch/x86/platform/intel-mid/mfld.c
index e793fe5..e42978d 100644
--- a/arch/x86/platform/intel-mid/mfld.c
+++ b/arch/x86/platform/intel-mid/mfld.c
@@ -17,16 +17,6 @@
#include "intel_mid_weak_decls.h"
-static void penwell_arch_setup(void);
-/* penwell arch ops */
-static struct intel_mid_ops penwell_ops = {
- .arch_setup = penwell_arch_setup,
-};
-
-static void mfld_power_off(void)
-{
-}
-
static unsigned long __init mfld_calibrate_tsc(void)
{
unsigned long fast_calibrate;
@@ -63,9 +53,12 @@ static unsigned long __init mfld_calibrate_tsc(void)
static void __init penwell_arch_setup(void)
{
x86_platform.calibrate_tsc = mfld_calibrate_tsc;
- pm_power_off = mfld_power_off;
}
+static struct intel_mid_ops penwell_ops = {
+ .arch_setup = penwell_arch_setup,
+};
+
void *get_penwell_ops(void)
{
return &penwell_ops;
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 766d4d3..f25982c 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1847,7 +1847,6 @@ static void pq_init(int node, int pnode)
ops.write_payload_first(pnode, first);
ops.write_payload_last(pnode, last);
- ops.write_g_sw_ack(pnode, 0xffffUL);
/* in effect, all msg_type's are set to MSG_NOOP */
memset(pqp, 0, sizeof(struct bau_pq_entry) * DEST_Q_SIZE);
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 555b9fa..7dbdb78 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -8,6 +8,7 @@
LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib -z nodefaultlib
targets += purgatory.ro
+KASAN_SANITIZE := n
KCOV_INSTRUMENT := n
# Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That
diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c
index 25e068b..470edad 100644
--- a/arch/x86/purgatory/purgatory.c
+++ b/arch/x86/purgatory/purgatory.c
@@ -10,21 +10,19 @@
* Version 2. See the file COPYING for more details.
*/
+#include <linux/bug.h>
+#include <asm/purgatory.h>
+
#include "sha256.h"
#include "../boot/string.h"
-struct sha_region {
- unsigned long start;
- unsigned long len;
-};
+unsigned long purgatory_backup_dest __section(.kexec-purgatory);
+unsigned long purgatory_backup_src __section(.kexec-purgatory);
+unsigned long purgatory_backup_sz __section(.kexec-purgatory);
-unsigned long backup_dest = 0;
-unsigned long backup_src = 0;
-unsigned long backup_sz = 0;
+u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE] __section(.kexec-purgatory);
-u8 sha256_digest[SHA256_DIGEST_SIZE] = { 0 };
-
-struct sha_region sha_regions[16] = {};
+struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX] __section(.kexec-purgatory);
/*
* On x86, second kernel requries first 640K of memory to boot. Copy
@@ -33,26 +31,28 @@ struct sha_region sha_regions[16] = {};
*/
static int copy_backup_region(void)
{
- if (backup_dest)
- memcpy((void *)backup_dest, (void *)backup_src, backup_sz);
-
+ if (purgatory_backup_dest) {
+ memcpy((void *)purgatory_backup_dest,
+ (void *)purgatory_backup_src, purgatory_backup_sz);
+ }
return 0;
}
-int verify_sha256_digest(void)
+static int verify_sha256_digest(void)
{
- struct sha_region *ptr, *end;
+ struct kexec_sha_region *ptr, *end;
u8 digest[SHA256_DIGEST_SIZE];
struct sha256_state sctx;
sha256_init(&sctx);
- end = &sha_regions[sizeof(sha_regions)/sizeof(sha_regions[0])];
- for (ptr = sha_regions; ptr < end; ptr++)
+ end = purgatory_sha_regions + ARRAY_SIZE(purgatory_sha_regions);
+
+ for (ptr = purgatory_sha_regions; ptr < end; ptr++)
sha256_update(&sctx, (uint8_t *)(ptr->start), ptr->len);
sha256_final(&sctx, digest);
- if (memcmp(digest, sha256_digest, sizeof(digest)))
+ if (memcmp(digest, purgatory_sha256_digest, sizeof(digest)))
return 1;
return 0;
diff --git a/arch/x86/purgatory/setup-x86_64.S b/arch/x86/purgatory/setup-x86_64.S
index fe3c91b..dfae9b9 100644
--- a/arch/x86/purgatory/setup-x86_64.S
+++ b/arch/x86/purgatory/setup-x86_64.S
@@ -9,6 +9,7 @@
* This source code is licensed under the GNU General Public License,
* Version 2. See the file COPYING for more details.
*/
+#include <asm/purgatory.h>
.text
.globl purgatory_start
diff --git a/arch/x86/purgatory/sha256.h b/arch/x86/purgatory/sha256.h
index bd15a41..2867d98 100644
--- a/arch/x86/purgatory/sha256.h
+++ b/arch/x86/purgatory/sha256.h
@@ -10,7 +10,6 @@
#ifndef SHA256_H
#define SHA256_H
-
#include <linux/types.h>
#include <crypto/sha.h>
diff --git a/arch/xtensa/include/asm/page.h b/arch/xtensa/include/asm/page.h
index 976b1d7..4ddbfd5 100644
--- a/arch/xtensa/include/asm/page.h
+++ b/arch/xtensa/include/asm/page.h
@@ -164,8 +164,21 @@ void copy_user_highpage(struct page *to, struct page *from,
#define ARCH_PFN_OFFSET (PHYS_OFFSET >> PAGE_SHIFT)
+#ifdef CONFIG_MMU
+static inline unsigned long ___pa(unsigned long va)
+{
+ unsigned long off = va - PAGE_OFFSET;
+
+ if (off >= XCHAL_KSEG_SIZE)
+ off -= XCHAL_KSEG_SIZE;
+
+ return off + PHYS_OFFSET;
+}
+#define __pa(x) ___pa((unsigned long)(x))
+#else
#define __pa(x) \
((unsigned long) (x) - PAGE_OFFSET + PHYS_OFFSET)
+#endif
#define __va(x) \
((void *)((unsigned long) (x) - PHYS_OFFSET + PAGE_OFFSET))
#define pfn_valid(pfn) \
diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h
index 8aa0e0d..30dd5b2 100644
--- a/arch/xtensa/include/asm/pgtable.h
+++ b/arch/xtensa/include/asm/pgtable.h
@@ -11,6 +11,7 @@
#ifndef _XTENSA_PGTABLE_H
#define _XTENSA_PGTABLE_H
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
#include <asm/page.h>
#include <asm/kmem_layout.h>
diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h
index 9fdbe1f..1eb6d2f 100644
--- a/arch/xtensa/include/uapi/asm/socket.h
+++ b/arch/xtensa/include/uapi/asm/socket.h
@@ -103,4 +103,10 @@
#define SCM_TIMESTAMPING_OPT_STATS 54
+#define SO_MEMINFO 55
+
+#define SO_INCOMING_NAPI_ID 56
+
+#define SO_COOKIE 57
+
#endif /* _XTENSA_SOCKET_H */
diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h
index cd400af..6be7eb2 100644
--- a/arch/xtensa/include/uapi/asm/unistd.h
+++ b/arch/xtensa/include/uapi/asm/unistd.h
@@ -774,7 +774,10 @@ __SYSCALL(349, sys_pkey_alloc, 2)
#define __NR_pkey_free 350
__SYSCALL(350, sys_pkey_free, 1)
-#define __NR_syscall_count 351
+#define __NR_statx 351
+__SYSCALL(351, sys_statx, 5)
+
+#define __NR_syscall_count 352
/*
* sysxtensa syscall handler
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index c82c43b..bae697a 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -483,10 +483,8 @@ void show_regs(struct pt_regs * regs)
static int show_trace_cb(struct stackframe *frame, void *data)
{
- if (kernel_text_address(frame->pc)) {
- pr_cont(" [<%08lx>]", frame->pc);
- print_symbol(" %s\n", frame->pc);
- }
+ if (kernel_text_address(frame->pc))
+ pr_cont(" [<%08lx>] %pB\n", frame->pc, (void *)frame->pc);
return 0;
}
diff --git a/block/bio.c b/block/bio.c
index 5eec5e0..e75878f 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -376,10 +376,14 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
bio_list_init(&punt);
bio_list_init(&nopunt);
- while ((bio = bio_list_pop(current->bio_list)))
+ while ((bio = bio_list_pop(¤t->bio_list[0])))
bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
+ current->bio_list[0] = nopunt;
- *current->bio_list = nopunt;
+ bio_list_init(&nopunt);
+ while ((bio = bio_list_pop(¤t->bio_list[1])))
+ bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
+ current->bio_list[1] = nopunt;
spin_lock(&bs->rescue_lock);
bio_list_merge(&bs->rescue_list, &punt);
@@ -466,7 +470,9 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
* we retry with the original gfp_flags.
*/
- if (current->bio_list && !bio_list_empty(current->bio_list))
+ if (current->bio_list &&
+ (!bio_list_empty(¤t->bio_list[0]) ||
+ !bio_list_empty(¤t->bio_list[1])))
gfp_mask &= ~__GFP_DIRECT_RECLAIM;
p = mempool_alloc(bs->bio_pool, gfp_mask);
diff --git a/block/blk-core.c b/block/blk-core.c
index 1086dac..d772c22 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -578,8 +578,6 @@ void blk_cleanup_queue(struct request_queue *q)
q->queue_lock = &q->__queue_lock;
spin_unlock_irq(lock);
- put_disk_devt(q->disk_devt);
-
/* @q is and will stay empty, shutdown and put */
blk_put_queue(q);
}
@@ -1975,7 +1973,14 @@ generic_make_request_checks(struct bio *bio)
*/
blk_qc_t generic_make_request(struct bio *bio)
{
- struct bio_list bio_list_on_stack;
+ /*
+ * bio_list_on_stack[0] contains bios submitted by the current
+ * make_request_fn.
+ * bio_list_on_stack[1] contains bios that were submitted before
+ * the current make_request_fn, but that haven't been processed
+ * yet.
+ */
+ struct bio_list bio_list_on_stack[2];
blk_qc_t ret = BLK_QC_T_NONE;
if (!generic_make_request_checks(bio))
@@ -1992,7 +1997,7 @@ blk_qc_t generic_make_request(struct bio *bio)
* should be added at the tail
*/
if (current->bio_list) {
- bio_list_add(current->bio_list, bio);
+ bio_list_add(¤t->bio_list[0], bio);
goto out;
}
@@ -2011,23 +2016,39 @@ blk_qc_t generic_make_request(struct bio *bio)
* bio_list, and call into ->make_request() again.
*/
BUG_ON(bio->bi_next);
- bio_list_init(&bio_list_on_stack);
- current->bio_list = &bio_list_on_stack;
+ bio_list_init(&bio_list_on_stack[0]);
+ current->bio_list = bio_list_on_stack;
do {
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
if (likely(blk_queue_enter(q, false) == 0)) {
+ struct bio_list lower, same;
+
+ /* Create a fresh bio_list for all subordinate requests */
+ bio_list_on_stack[1] = bio_list_on_stack[0];
+ bio_list_init(&bio_list_on_stack[0]);
ret = q->make_request_fn(q, bio);
blk_queue_exit(q);
- bio = bio_list_pop(current->bio_list);
+ /* sort new bios into those for a lower level
+ * and those for the same level
+ */
+ bio_list_init(&lower);
+ bio_list_init(&same);
+ while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL)
+ if (q == bdev_get_queue(bio->bi_bdev))
+ bio_list_add(&same, bio);
+ else
+ bio_list_add(&lower, bio);
+ /* now assemble so we handle the lowest level first */
+ bio_list_merge(&bio_list_on_stack[0], &lower);
+ bio_list_merge(&bio_list_on_stack[0], &same);
+ bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
} else {
- struct bio *bio_next = bio_list_pop(current->bio_list);
-
bio_io_error(bio);
- bio = bio_next;
}
+ bio = bio_list_pop(&bio_list_on_stack[0]);
} while (bio);
current->bio_list = NULL; /* deactivate */
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 295e696..d745ab8 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -17,6 +17,15 @@ static void blk_mq_sysfs_release(struct kobject *kobj)
{
}
+static void blk_mq_hw_sysfs_release(struct kobject *kobj)
+{
+ struct blk_mq_hw_ctx *hctx = container_of(kobj, struct blk_mq_hw_ctx,
+ kobj);
+ free_cpumask_var(hctx->cpumask);
+ kfree(hctx->ctxs);
+ kfree(hctx);
+}
+
struct blk_mq_ctx_sysfs_entry {
struct attribute attr;
ssize_t (*show)(struct blk_mq_ctx *, char *);
@@ -200,7 +209,7 @@ static struct kobj_type blk_mq_ctx_ktype = {
static struct kobj_type blk_mq_hw_ktype = {
.sysfs_ops = &blk_mq_hw_sysfs_ops,
.default_attrs = default_hw_ctx_attrs,
- .release = blk_mq_sysfs_release,
+ .release = blk_mq_hw_sysfs_release,
};
static void blk_mq_unregister_hctx(struct blk_mq_hw_ctx *hctx)
@@ -242,24 +251,15 @@ static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx)
static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx;
- struct blk_mq_ctx *ctx;
- int i, j;
+ int i;
- queue_for_each_hw_ctx(q, hctx, i) {
+ queue_for_each_hw_ctx(q, hctx, i)
blk_mq_unregister_hctx(hctx);
- hctx_for_each_ctx(hctx, ctx, j)
- kobject_put(&ctx->kobj);
-
- kobject_put(&hctx->kobj);
- }
-
blk_mq_debugfs_unregister_hctxs(q);
kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
kobject_del(&q->mq_kobj);
- kobject_put(&q->mq_kobj);
-
kobject_put(&dev->kobj);
q->mq_sysfs_init_done = false;
@@ -277,7 +277,19 @@ void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx)
kobject_init(&hctx->kobj, &blk_mq_hw_ktype);
}
-static void blk_mq_sysfs_init(struct request_queue *q)
+void blk_mq_sysfs_deinit(struct request_queue *q)
+{
+ struct blk_mq_ctx *ctx;
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ ctx = per_cpu_ptr(q->queue_ctx, cpu);
+ kobject_put(&ctx->kobj);
+ }
+ kobject_put(&q->mq_kobj);
+}
+
+void blk_mq_sysfs_init(struct request_queue *q)
{
struct blk_mq_ctx *ctx;
int cpu;
@@ -297,8 +309,6 @@ int blk_mq_register_dev(struct device *dev, struct request_queue *q)
blk_mq_disable_hotplug();
- blk_mq_sysfs_init(q);
-
ret = kobject_add(&q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq");
if (ret < 0)
goto out;
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index e48bc2c..9d97bfc 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -295,6 +295,9 @@ int blk_mq_reinit_tagset(struct blk_mq_tag_set *set)
for (i = 0; i < set->nr_hw_queues; i++) {
struct blk_mq_tags *tags = set->tags[i];
+ if (!tags)
+ continue;
+
for (j = 0; j < tags->nr_tags; j++) {
if (!tags->static_rqs[j])
continue;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index b2fd175..6b6e7bc 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -697,17 +697,8 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
{
struct blk_mq_timeout_data *data = priv;
- if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) {
- /*
- * If a request wasn't started before the queue was
- * marked dying, kill it here or it'll go unnoticed.
- */
- if (unlikely(blk_queue_dying(rq->q))) {
- rq->errors = -EIO;
- blk_mq_end_request(rq, rq->errors);
- }
+ if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
return;
- }
if (time_after_eq(jiffies, rq->deadline)) {
if (!blk_mark_rq_complete(rq))
@@ -978,7 +969,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
struct request *rq;
LIST_HEAD(driver_list);
struct list_head *dptr;
- int queued, ret = BLK_MQ_RQ_QUEUE_OK;
+ int errors, queued, ret = BLK_MQ_RQ_QUEUE_OK;
/*
* Start off with dptr being NULL, so we start the first request
@@ -989,7 +980,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
/*
* Now process all the entries, sending them to the driver.
*/
- queued = 0;
+ errors = queued = 0;
while (!list_empty(list)) {
struct blk_mq_queue_data bd;
@@ -1046,6 +1037,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
default:
pr_err("blk-mq: bad return on queue: %d\n", ret);
case BLK_MQ_RQ_QUEUE_ERROR:
+ errors++;
rq->errors = -EIO;
blk_mq_end_request(rq, rq->errors);
break;
@@ -1097,7 +1089,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
blk_mq_run_hw_queue(hctx, true);
}
- return queued != 0;
+ return (queued + errors) != 0;
}
static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
@@ -1434,7 +1426,8 @@ static blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, struct request *rq)
return blk_tag_to_qc_t(rq->internal_tag, hctx->queue_num, true);
}
-static void blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie)
+static void blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie,
+ bool may_sleep)
{
struct request_queue *q = rq->q;
struct blk_mq_queue_data bd = {
@@ -1475,7 +1468,7 @@ static void blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie)
}
insert:
- blk_mq_sched_insert_request(rq, false, true, true, false);
+ blk_mq_sched_insert_request(rq, false, true, false, may_sleep);
}
/*
@@ -1569,11 +1562,11 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
if (!(data.hctx->flags & BLK_MQ_F_BLOCKING)) {
rcu_read_lock();
- blk_mq_try_issue_directly(old_rq, &cookie);
+ blk_mq_try_issue_directly(old_rq, &cookie, false);
rcu_read_unlock();
} else {
srcu_idx = srcu_read_lock(&data.hctx->queue_rq_srcu);
- blk_mq_try_issue_directly(old_rq, &cookie);
+ blk_mq_try_issue_directly(old_rq, &cookie, true);
srcu_read_unlock(&data.hctx->queue_rq_srcu, srcu_idx);
}
goto done;
@@ -1955,16 +1948,6 @@ static void blk_mq_exit_hw_queues(struct request_queue *q,
}
}
-static void blk_mq_free_hw_queues(struct request_queue *q,
- struct blk_mq_tag_set *set)
-{
- struct blk_mq_hw_ctx *hctx;
- unsigned int i;
-
- queue_for_each_hw_ctx(q, hctx, i)
- free_cpumask_var(hctx->cpumask);
-}
-
static int blk_mq_init_hctx(struct request_queue *q,
struct blk_mq_tag_set *set,
struct blk_mq_hw_ctx *hctx, unsigned hctx_idx)
@@ -2045,7 +2028,6 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
struct blk_mq_ctx *__ctx = per_cpu_ptr(q->queue_ctx, i);
struct blk_mq_hw_ctx *hctx;
- memset(__ctx, 0, sizeof(*__ctx));
__ctx->cpu = i;
spin_lock_init(&__ctx->lock);
INIT_LIST_HEAD(&__ctx->rq_list);
@@ -2257,15 +2239,19 @@ void blk_mq_release(struct request_queue *q)
queue_for_each_hw_ctx(q, hctx, i) {
if (!hctx)
continue;
- kfree(hctx->ctxs);
- kfree(hctx);
+ kobject_put(&hctx->kobj);
}
q->mq_map = NULL;
kfree(q->queue_hw_ctx);
- /* ctx kobj stays in queue_ctx */
+ /*
+ * release .mq_kobj and sw queue's kobject now because
+ * both share lifetime with request queue.
+ */
+ blk_mq_sysfs_deinit(q);
+
free_percpu(q->queue_ctx);
}
@@ -2330,10 +2316,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
if (hctx->tags)
blk_mq_free_map_and_requests(set, j);
blk_mq_exit_hctx(q, set, hctx, j);
- free_cpumask_var(hctx->cpumask);
kobject_put(&hctx->kobj);
- kfree(hctx->ctxs);
- kfree(hctx);
hctxs[j] = NULL;
}
@@ -2352,6 +2335,9 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
if (!q->queue_ctx)
goto err_exit;
+ /* init q->mq_kobj and sw queues' kobjects */
+ blk_mq_sysfs_init(q);
+
q->queue_hw_ctx = kzalloc_node(nr_cpu_ids * sizeof(*(q->queue_hw_ctx)),
GFP_KERNEL, set->numa_node);
if (!q->queue_hw_ctx)
@@ -2442,7 +2428,6 @@ void blk_mq_free_queue(struct request_queue *q)
blk_mq_del_queue_tag_set(q);
blk_mq_exit_hw_queues(q, set, set->nr_hw_queues);
- blk_mq_free_hw_queues(q, set);
}
/* Basically redo blk_mq_init_queue with queue frozen */
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 088ced0..b79f9a7 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -77,6 +77,8 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
/*
* sysfs helpers
*/
+extern void blk_mq_sysfs_init(struct request_queue *q);
+extern void blk_mq_sysfs_deinit(struct request_queue *q);
extern int blk_mq_sysfs_register(struct request_queue *q);
extern void blk_mq_sysfs_unregister(struct request_queue *q);
extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
diff --git a/block/blk-stat.c b/block/blk-stat.c
index 9b43efb..186fcb9 100644
--- a/block/blk-stat.c
+++ b/block/blk-stat.c
@@ -30,11 +30,11 @@ static void blk_stat_flush_batch(struct blk_rq_stat *stat)
static void blk_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src)
{
+ blk_stat_flush_batch(src);
+
if (!src->nr_samples)
return;
- blk_stat_flush_batch(src);
-
dst->min = min(dst->min, src->min);
dst->max = max(dst->max, src->max);
diff --git a/block/genhd.c b/block/genhd.c
index b26a5ea..a9c516a 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -572,20 +572,6 @@ static void register_disk(struct device *parent, struct gendisk *disk)
disk_part_iter_exit(&piter);
}
-void put_disk_devt(struct disk_devt *disk_devt)
-{
- if (disk_devt && atomic_dec_and_test(&disk_devt->count))
- disk_devt->release(disk_devt);
-}
-EXPORT_SYMBOL(put_disk_devt);
-
-void get_disk_devt(struct disk_devt *disk_devt)
-{
- if (disk_devt)
- atomic_inc(&disk_devt->count);
-}
-EXPORT_SYMBOL(get_disk_devt);
-
/**
* device_add_disk - add partitioning information to kernel list
* @parent: parent device for the disk
@@ -626,13 +612,6 @@ void device_add_disk(struct device *parent, struct gendisk *disk)
disk_alloc_events(disk);
- /*
- * Take a reference on the devt and assign it to queue since it
- * must not be reallocated while the bdi is registered
- */
- disk->queue->disk_devt = disk->disk_devt;
- get_disk_devt(disk->disk_devt);
-
/* Register BDI before referencing it from bdev */
bdi = disk->queue->backing_dev_info;
bdi_register_owner(bdi, disk_to_dev(disk));
@@ -681,12 +660,16 @@ void del_gendisk(struct gendisk *disk)
disk->flags &= ~GENHD_FL_UP;
sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
- /*
- * Unregister bdi before releasing device numbers (as they can get
- * reused and we'd get clashes in sysfs).
- */
- bdi_unregister(disk->queue->backing_dev_info);
- blk_unregister_queue(disk);
+ if (disk->queue) {
+ /*
+ * Unregister bdi before releasing device numbers (as they can
+ * get reused and we'd get clashes in sysfs).
+ */
+ bdi_unregister(disk->queue->backing_dev_info);
+ blk_unregister_queue(disk);
+ } else {
+ WARN_ON(1);
+ }
blk_unregister_region(disk_devt(disk), disk->minors);
part_stat_set_all(&disk->part0, 0);
diff --git a/block/sed-opal.c b/block/sed-opal.c
index 1e18dca..14035f8 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -1023,7 +1023,6 @@ static int finalize_and_send(struct opal_dev *dev, cont_fn cont)
static int gen_key(struct opal_dev *dev, void *data)
{
- const u8 *method;
u8 uid[OPAL_UID_LENGTH];
int err = 0;
@@ -1031,7 +1030,6 @@ static int gen_key(struct opal_dev *dev, void *data)
set_comid(dev, dev->comid);
memcpy(uid, dev->prev_data, min(sizeof(uid), dev->prev_d_len));
- method = opalmethod[OPAL_GENKEY];
kfree(dev->prev_data);
dev->prev_data = NULL;
@@ -1669,7 +1667,6 @@ static int add_user_to_lr(struct opal_dev *dev, void *data)
static int lock_unlock_locking_range(struct opal_dev *dev, void *data)
{
u8 lr_buffer[OPAL_UID_LENGTH];
- const u8 *method;
struct opal_lock_unlock *lkul = data;
u8 read_locked = 1, write_locked = 1;
int err = 0;
@@ -1677,7 +1674,6 @@ static int lock_unlock_locking_range(struct opal_dev *dev, void *data)
clear_opal_cmd(dev);
set_comid(dev, dev->comid);
- method = opalmethod[OPAL_SET];
if (build_locking_range(lr_buffer, sizeof(lr_buffer),
lkul->session.opal_key.lr) < 0)
return -ERANGE;
@@ -1733,14 +1729,12 @@ static int lock_unlock_locking_range_sum(struct opal_dev *dev, void *data)
{
u8 lr_buffer[OPAL_UID_LENGTH];
u8 read_locked = 1, write_locked = 1;
- const u8 *method;
struct opal_lock_unlock *lkul = data;
int ret;
clear_opal_cmd(dev);
set_comid(dev, dev->comid);
- method = opalmethod[OPAL_SET];
if (build_locking_range(lr_buffer, sizeof(lr_buffer),
lkul->session.opal_key.lr) < 0)
return -ERANGE;
@@ -2133,7 +2127,7 @@ static int opal_add_user_to_lr(struct opal_dev *dev,
pr_err("Locking state was not RO or RW\n");
return -EINVAL;
}
- if (lk_unlk->session.who < OPAL_USER1 &&
+ if (lk_unlk->session.who < OPAL_USER1 ||
lk_unlk->session.who > OPAL_USER9) {
pr_err("Authority was not within the range of users: %d\n",
lk_unlk->session.who);
@@ -2316,7 +2310,7 @@ static int opal_activate_user(struct opal_dev *dev,
int ret;
/* We can't activate Admin1 it's active as manufactured */
- if (opal_session->who < OPAL_USER1 &&
+ if (opal_session->who < OPAL_USER1 ||
opal_session->who > OPAL_USER9) {
pr_err("Who was not a valid user: %d\n", opal_session->who);
return -EINVAL;
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index f5e18c2..690deca 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -266,7 +266,7 @@ static int alg_setsockopt(struct socket *sock, int level, int optname,
return err;
}
-int af_alg_accept(struct sock *sk, struct socket *newsock)
+int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern)
{
struct alg_sock *ask = alg_sk(sk);
const struct af_alg_type *type;
@@ -281,7 +281,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock)
if (!type)
goto unlock;
- sk2 = sk_alloc(sock_net(sk), PF_ALG, GFP_KERNEL, &alg_proto, 0);
+ sk2 = sk_alloc(sock_net(sk), PF_ALG, GFP_KERNEL, &alg_proto, kern);
err = -ENOMEM;
if (!sk2)
goto unlock;
@@ -323,9 +323,10 @@ int af_alg_accept(struct sock *sk, struct socket *newsock)
}
EXPORT_SYMBOL_GPL(af_alg_accept);
-static int alg_accept(struct socket *sock, struct socket *newsock, int flags)
+static int alg_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
- return af_alg_accept(sock->sk, newsock);
+ return af_alg_accept(sock->sk, newsock, kern);
}
static const struct proto_ops alg_proto_ops = {
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 54fc90e..5e92bd2 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -239,7 +239,8 @@ static int hash_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
return err ?: len;
}
-static int hash_accept(struct socket *sock, struct socket *newsock, int flags)
+static int hash_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sock *sk = sock->sk;
struct alg_sock *ask = alg_sk(sk);
@@ -260,7 +261,7 @@ static int hash_accept(struct socket *sock, struct socket *newsock, int flags)
if (err)
return err;
- err = af_alg_accept(ask->parent, newsock);
+ err = af_alg_accept(ask->parent, newsock, kern);
if (err)
return err;
@@ -378,7 +379,7 @@ static int hash_recvmsg_nokey(struct socket *sock, struct msghdr *msg,
}
static int hash_accept_nokey(struct socket *sock, struct socket *newsock,
- int flags)
+ int flags, bool kern)
{
int err;
@@ -386,7 +387,7 @@ static int hash_accept_nokey(struct socket *sock, struct socket *newsock,
if (err)
return err;
- return hash_accept(sock, newsock, flags);
+ return hash_accept(sock, newsock, flags, kern);
}
static struct proto_ops algif_hash_ops_nokey = {
diff --git a/crypto/lrw.c b/crypto/lrw.c
index ecd8474..3ea095a 100644
--- a/crypto/lrw.c
+++ b/crypto/lrw.c
@@ -286,8 +286,11 @@ static int init_crypt(struct skcipher_request *req, crypto_completion_t done)
subreq->cryptlen = LRW_BUFFER_SIZE;
if (req->cryptlen > LRW_BUFFER_SIZE) {
- subreq->cryptlen = min(req->cryptlen, (unsigned)PAGE_SIZE);
- rctx->ext = kmalloc(subreq->cryptlen, gfp);
+ unsigned int n = min(req->cryptlen, (unsigned int)PAGE_SIZE);
+
+ rctx->ext = kmalloc(n, gfp);
+ if (rctx->ext)
+ subreq->cryptlen = n;
}
rctx->src = req->src;
diff --git a/crypto/xts.c b/crypto/xts.c
index baeb34d..c976bfac 100644
--- a/crypto/xts.c
+++ b/crypto/xts.c
@@ -230,8 +230,11 @@ static int init_crypt(struct skcipher_request *req, crypto_completion_t done)
subreq->cryptlen = XTS_BUFFER_SIZE;
if (req->cryptlen > XTS_BUFFER_SIZE) {
- subreq->cryptlen = min(req->cryptlen, (unsigned)PAGE_SIZE);
- rctx->ext = kmalloc(subreq->cryptlen, gfp);
+ unsigned int n = min(req->cryptlen, (unsigned int)PAGE_SIZE);
+
+ rctx->ext = kmalloc(n, gfp);
+ if (rctx->ext)
+ subreq->cryptlen = n;
}
rctx->src = req->src;
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index a391bbc..d94f92f 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -2,7 +2,6 @@
# Makefile for the Linux ACPI interpreter
#
-ccflags-y := -Os
ccflags-$(CONFIG_ACPI_DEBUG) += -DACPI_DEBUG_OUTPUT
#
diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c
index b4c1a6a..03250e1f 100644
--- a/drivers/acpi/acpi_platform.c
+++ b/drivers/acpi/acpi_platform.c
@@ -25,9 +25,11 @@
ACPI_MODULE_NAME("platform");
static const struct acpi_device_id forbidden_id_list[] = {
- {"PNP0000", 0}, /* PIC */
- {"PNP0100", 0}, /* Timer */
- {"PNP0200", 0}, /* AT DMA Controller */
+ {"PNP0000", 0}, /* PIC */
+ {"PNP0100", 0}, /* Timer */
+ {"PNP0200", 0}, /* AT DMA Controller */
+ {"ACPI0009", 0}, /* IOxAPIC */
+ {"ACPI000A", 0}, /* IOAPIC */
{"", 0},
};
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index 4467a80..0143135 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -182,11 +182,6 @@ int __weak arch_register_cpu(int cpu)
void __weak arch_unregister_cpu(int cpu) {}
-int __weak acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
-{
- return -ENODEV;
-}
-
static int acpi_processor_hotadd_init(struct acpi_processor *pr)
{
unsigned long long sta;
@@ -285,6 +280,13 @@ static int acpi_processor_get_info(struct acpi_device *device)
pr->acpi_id = value;
}
+ if (acpi_duplicate_processor_id(pr->acpi_id)) {
+ dev_err(&device->dev,
+ "Failed to get unique processor _UID (0x%x)\n",
+ pr->acpi_id);
+ return -ENODEV;
+ }
+
pr->phys_id = acpi_get_phys_id(pr->handle, device_declaration,
pr->acpi_id);
if (invalid_phys_cpuid(pr->phys_id))
@@ -585,7 +587,7 @@ static struct acpi_scan_handler processor_container_handler = {
static int nr_unique_ids __initdata;
/* The number of the duplicate processor IDs */
-static int nr_duplicate_ids __initdata;
+static int nr_duplicate_ids;
/* Used to store the unique processor IDs */
static int unique_processor_ids[] __initdata = {
@@ -593,7 +595,7 @@ static int unique_processor_ids[] __initdata = {
};
/* Used to store the duplicate processor IDs */
-static int duplicate_processor_ids[] __initdata = {
+static int duplicate_processor_ids[] = {
[0 ... NR_CPUS - 1] = -1,
};
@@ -638,28 +640,53 @@ static acpi_status __init acpi_processor_ids_walk(acpi_handle handle,
void **rv)
{
acpi_status status;
+ acpi_object_type acpi_type;
+ unsigned long long uid;
union acpi_object object = { 0 };
struct acpi_buffer buffer = { sizeof(union acpi_object), &object };
- status = acpi_evaluate_object(handle, NULL, NULL, &buffer);
+ status = acpi_get_type(handle, &acpi_type);
if (ACPI_FAILURE(status))
- acpi_handle_info(handle, "Not get the processor object\n");
- else
- processor_validated_ids_update(object.processor.proc_id);
+ return false;
- return AE_OK;
+ switch (acpi_type) {
+ case ACPI_TYPE_PROCESSOR:
+ status = acpi_evaluate_object(handle, NULL, NULL, &buffer);
+ if (ACPI_FAILURE(status))
+ goto err;
+ uid = object.processor.proc_id;
+ break;
+
+ case ACPI_TYPE_DEVICE:
+ status = acpi_evaluate_integer(handle, "_UID", NULL, &uid);
+ if (ACPI_FAILURE(status))
+ goto err;
+ break;
+ default:
+ goto err;
+ }
+
+ processor_validated_ids_update(uid);
+ return true;
+
+err:
+ acpi_handle_info(handle, "Invalid processor object\n");
+ return false;
+
}
-static void __init acpi_processor_check_duplicates(void)
+void __init acpi_processor_check_duplicates(void)
{
- /* Search all processor nodes in ACPI namespace */
+ /* check the correctness for all processors in ACPI namespace */
acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT,
ACPI_UINT32_MAX,
acpi_processor_ids_walk,
NULL, NULL, NULL);
+ acpi_get_devices(ACPI_PROCESSOR_DEVICE_HID, acpi_processor_ids_walk,
+ NULL, NULL);
}
-bool __init acpi_processor_validate_proc_id(int proc_id)
+bool acpi_duplicate_processor_id(int proc_id)
{
int i;
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index b192b42a8..79b3c9c 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -1073,6 +1073,7 @@ static int ghes_remove(struct platform_device *ghes_dev)
if (list_empty(&ghes_sci))
unregister_acpi_hed_notifier(&ghes_notifier_sci);
mutex_unlock(&ghes_list_mutex);
+ synchronize_rcu();
break;
case ACPI_HEST_NOTIFY_NMI:
ghes_nmi_remove(ghes);
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 80cb5eb..34fbe02 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -1249,7 +1249,6 @@ static int __init acpi_init(void)
acpi_wakeup_device_init();
acpi_debugger_init();
acpi_setup_sb_notify_handler();
- acpi_set_processor_mapping();
return 0;
}
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 219b90b..f159001 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -41,8 +41,10 @@ void acpi_gpe_apply_masked_gpes(void);
void acpi_container_init(void);
void acpi_memory_hotplug_init(void);
#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
+void pci_ioapic_remove(struct acpi_pci_root *root);
int acpi_ioapic_remove(struct acpi_pci_root *root);
#else
+static inline void pci_ioapic_remove(struct acpi_pci_root *root) { return; }
static inline int acpi_ioapic_remove(struct acpi_pci_root *root) { return 0; }
#endif
#ifdef CONFIG_ACPI_DOCK
diff --git a/drivers/acpi/ioapic.c b/drivers/acpi/ioapic.c
index 6d7ce6e..7e4fbf9 100644
--- a/drivers/acpi/ioapic.c
+++ b/drivers/acpi/ioapic.c
@@ -45,6 +45,12 @@ static acpi_status setup_res(struct acpi_resource *acpi_res, void *data)
struct resource *res = data;
struct resource_win win;
+ /*
+ * We might assign this to 'res' later, make sure all pointers are
+ * cleared before the resource is added to the global list
+ */
+ memset(&win, 0, sizeof(win));
+
res->flags = 0;
if (acpi_dev_filter_resource_type(acpi_res, IORESOURCE_MEM))
return AE_OK;
@@ -206,6 +212,23 @@ int acpi_ioapic_add(acpi_handle root_handle)
return ACPI_SUCCESS(status) && ACPI_SUCCESS(retval) ? 0 : -ENODEV;
}
+void pci_ioapic_remove(struct acpi_pci_root *root)
+{
+ struct acpi_pci_ioapic *ioapic, *tmp;
+
+ mutex_lock(&ioapic_list_lock);
+ list_for_each_entry_safe(ioapic, tmp, &ioapic_list, list) {
+ if (root->device->handle != ioapic->root_handle)
+ continue;
+ if (ioapic->pdev) {
+ pci_release_region(ioapic->pdev, 0);
+ pci_disable_device(ioapic->pdev);
+ pci_dev_put(ioapic->pdev);
+ }
+ }
+ mutex_unlock(&ioapic_list_lock);
+}
+
int acpi_ioapic_remove(struct acpi_pci_root *root)
{
int retval = 0;
@@ -215,15 +238,8 @@ int acpi_ioapic_remove(struct acpi_pci_root *root)
list_for_each_entry_safe(ioapic, tmp, &ioapic_list, list) {
if (root->device->handle != ioapic->root_handle)
continue;
-
if (acpi_unregister_ioapic(ioapic->handle, ioapic->gsi_base))
retval = -EBUSY;
-
- if (ioapic->pdev) {
- pci_release_region(ioapic->pdev, 0);
- pci_disable_device(ioapic->pdev);
- pci_dev_put(ioapic->pdev);
- }
if (ioapic->res.flags && ioapic->res.parent)
release_resource(&ioapic->res);
list_del(&ioapic->list);
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index bf601d4..919be0a 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -648,12 +648,12 @@ static void acpi_pci_root_remove(struct acpi_device *device)
pci_stop_root_bus(root->bus);
- WARN_ON(acpi_ioapic_remove(root));
-
+ pci_ioapic_remove(root);
device_set_run_wake(root->bus->bridge, false);
pci_acpi_remove_bus_pm_notifier(device);
pci_remove_root_bus(root->bus);
+ WARN_ON(acpi_ioapic_remove(root));
dmar_device_remove(device->handle);
diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c
index 611a558..b933061 100644
--- a/drivers/acpi/processor_core.c
+++ b/drivers/acpi/processor_core.c
@@ -32,12 +32,12 @@ static struct acpi_table_madt *get_madt_table(void)
}
static int map_lapic_id(struct acpi_subtable_header *entry,
- u32 acpi_id, phys_cpuid_t *apic_id, bool ignore_disabled)
+ u32 acpi_id, phys_cpuid_t *apic_id)
{
struct acpi_madt_local_apic *lapic =
container_of(entry, struct acpi_madt_local_apic, header);
- if (ignore_disabled && !(lapic->lapic_flags & ACPI_MADT_ENABLED))
+ if (!(lapic->lapic_flags & ACPI_MADT_ENABLED))
return -ENODEV;
if (lapic->processor_id != acpi_id)
@@ -48,13 +48,12 @@ static int map_lapic_id(struct acpi_subtable_header *entry,
}
static int map_x2apic_id(struct acpi_subtable_header *entry,
- int device_declaration, u32 acpi_id, phys_cpuid_t *apic_id,
- bool ignore_disabled)
+ int device_declaration, u32 acpi_id, phys_cpuid_t *apic_id)
{
struct acpi_madt_local_x2apic *apic =
container_of(entry, struct acpi_madt_local_x2apic, header);
- if (ignore_disabled && !(apic->lapic_flags & ACPI_MADT_ENABLED))
+ if (!(apic->lapic_flags & ACPI_MADT_ENABLED))
return -ENODEV;
if (device_declaration && (apic->uid == acpi_id)) {
@@ -66,13 +65,12 @@ static int map_x2apic_id(struct acpi_subtable_header *entry,
}
static int map_lsapic_id(struct acpi_subtable_header *entry,
- int device_declaration, u32 acpi_id, phys_cpuid_t *apic_id,
- bool ignore_disabled)
+ int device_declaration, u32 acpi_id, phys_cpuid_t *apic_id)
{
struct acpi_madt_local_sapic *lsapic =
container_of(entry, struct acpi_madt_local_sapic, header);
- if (ignore_disabled && !(lsapic->lapic_flags & ACPI_MADT_ENABLED))
+ if (!(lsapic->lapic_flags & ACPI_MADT_ENABLED))
return -ENODEV;
if (device_declaration) {
@@ -89,13 +87,12 @@ static int map_lsapic_id(struct acpi_subtable_header *entry,
* Retrieve the ARM CPU physical identifier (MPIDR)
*/
static int map_gicc_mpidr(struct acpi_subtable_header *entry,
- int device_declaration, u32 acpi_id, phys_cpuid_t *mpidr,
- bool ignore_disabled)
+ int device_declaration, u32 acpi_id, phys_cpuid_t *mpidr)
{
struct acpi_madt_generic_interrupt *gicc =
container_of(entry, struct acpi_madt_generic_interrupt, header);
- if (ignore_disabled && !(gicc->flags & ACPI_MADT_ENABLED))
+ if (!(gicc->flags & ACPI_MADT_ENABLED))
return -ENODEV;
/* device_declaration means Device object in DSDT, in the
@@ -112,7 +109,7 @@ static int map_gicc_mpidr(struct acpi_subtable_header *entry,
}
static phys_cpuid_t map_madt_entry(struct acpi_table_madt *madt,
- int type, u32 acpi_id, bool ignore_disabled)
+ int type, u32 acpi_id)
{
unsigned long madt_end, entry;
phys_cpuid_t phys_id = PHYS_CPUID_INVALID; /* CPU hardware ID */
@@ -130,20 +127,16 @@ static phys_cpuid_t map_madt_entry(struct acpi_table_madt *madt,
struct acpi_subtable_header *header =
(struct acpi_subtable_header *)entry;
if (header->type == ACPI_MADT_TYPE_LOCAL_APIC) {
- if (!map_lapic_id(header, acpi_id, &phys_id,
- ignore_disabled))
+ if (!map_lapic_id(header, acpi_id, &phys_id))
break;
} else if (header->type == ACPI_MADT_TYPE_LOCAL_X2APIC) {
- if (!map_x2apic_id(header, type, acpi_id, &phys_id,
- ignore_disabled))
+ if (!map_x2apic_id(header, type, acpi_id, &phys_id))
break;
} else if (header->type == ACPI_MADT_TYPE_LOCAL_SAPIC) {
- if (!map_lsapic_id(header, type, acpi_id, &phys_id,
- ignore_disabled))
+ if (!map_lsapic_id(header, type, acpi_id, &phys_id))
break;
} else if (header->type == ACPI_MADT_TYPE_GENERIC_INTERRUPT) {
- if (!map_gicc_mpidr(header, type, acpi_id, &phys_id,
- ignore_disabled))
+ if (!map_gicc_mpidr(header, type, acpi_id, &phys_id))
break;
}
entry += header->length;
@@ -161,15 +154,14 @@ phys_cpuid_t __init acpi_map_madt_entry(u32 acpi_id)
if (!madt)
return PHYS_CPUID_INVALID;
- rv = map_madt_entry(madt, 1, acpi_id, true);
+ rv = map_madt_entry(madt, 1, acpi_id);
acpi_put_table((struct acpi_table_header *)madt);
return rv;
}
-static phys_cpuid_t map_mat_entry(acpi_handle handle, int type, u32 acpi_id,
- bool ignore_disabled)
+static phys_cpuid_t map_mat_entry(acpi_handle handle, int type, u32 acpi_id)
{
struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
union acpi_object *obj;
@@ -190,38 +182,30 @@ static phys_cpuid_t map_mat_entry(acpi_handle handle, int type, u32 acpi_id,
header = (struct acpi_subtable_header *)obj->buffer.pointer;
if (header->type == ACPI_MADT_TYPE_LOCAL_APIC)
- map_lapic_id(header, acpi_id, &phys_id, ignore_disabled);
+ map_lapic_id(header, acpi_id, &phys_id);
else if (header->type == ACPI_MADT_TYPE_LOCAL_SAPIC)
- map_lsapic_id(header, type, acpi_id, &phys_id, ignore_disabled);
+ map_lsapic_id(header, type, acpi_id, &phys_id);
else if (header->type == ACPI_MADT_TYPE_LOCAL_X2APIC)
- map_x2apic_id(header, type, acpi_id, &phys_id, ignore_disabled);
+ map_x2apic_id(header, type, acpi_id, &phys_id);
else if (header->type == ACPI_MADT_TYPE_GENERIC_INTERRUPT)
- map_gicc_mpidr(header, type, acpi_id, &phys_id,
- ignore_disabled);
+ map_gicc_mpidr(header, type, acpi_id, &phys_id);
exit:
kfree(buffer.pointer);
return phys_id;
}
-static phys_cpuid_t __acpi_get_phys_id(acpi_handle handle, int type,
- u32 acpi_id, bool ignore_disabled)
+phys_cpuid_t acpi_get_phys_id(acpi_handle handle, int type, u32 acpi_id)
{
phys_cpuid_t phys_id;
- phys_id = map_mat_entry(handle, type, acpi_id, ignore_disabled);
+ phys_id = map_mat_entry(handle, type, acpi_id);
if (invalid_phys_cpuid(phys_id))
- phys_id = map_madt_entry(get_madt_table(), type, acpi_id,
- ignore_disabled);
+ phys_id = map_madt_entry(get_madt_table(), type, acpi_id);
return phys_id;
}
-phys_cpuid_t acpi_get_phys_id(acpi_handle handle, int type, u32 acpi_id)
-{
- return __acpi_get_phys_id(handle, type, acpi_id, true);
-}
-
int acpi_map_cpuid(phys_cpuid_t phys_id, u32 acpi_id)
{
#ifdef CONFIG_SMP
@@ -278,79 +262,6 @@ int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id)
}
EXPORT_SYMBOL_GPL(acpi_get_cpuid);
-#ifdef CONFIG_ACPI_HOTPLUG_CPU
-static bool __init
-map_processor(acpi_handle handle, phys_cpuid_t *phys_id, int *cpuid)
-{
- int type, id;
- u32 acpi_id;
- acpi_status status;
- acpi_object_type acpi_type;
- unsigned long long tmp;
- union acpi_object object = { 0 };
- struct acpi_buffer buffer = { sizeof(union acpi_object), &object };
-
- status = acpi_get_type(handle, &acpi_type);
- if (ACPI_FAILURE(status))
- return false;
-
- switch (acpi_type) {
- case ACPI_TYPE_PROCESSOR:
- status = acpi_evaluate_object(handle, NULL, NULL, &buffer);
- if (ACPI_FAILURE(status))
- return false;
- acpi_id = object.processor.proc_id;
-
- /* validate the acpi_id */
- if(acpi_processor_validate_proc_id(acpi_id))
- return false;
- break;
- case ACPI_TYPE_DEVICE:
- status = acpi_evaluate_integer(handle, "_UID", NULL, &tmp);
- if (ACPI_FAILURE(status))
- return false;
- acpi_id = tmp;
- break;
- default:
- return false;
- }
-
- type = (acpi_type == ACPI_TYPE_DEVICE) ? 1 : 0;
-
- *phys_id = __acpi_get_phys_id(handle, type, acpi_id, false);
- id = acpi_map_cpuid(*phys_id, acpi_id);
-
- if (id < 0)
- return false;
- *cpuid = id;
- return true;
-}
-
-static acpi_status __init
-set_processor_node_mapping(acpi_handle handle, u32 lvl, void *context,
- void **rv)
-{
- phys_cpuid_t phys_id;
- int cpu_id;
-
- if (!map_processor(handle, &phys_id, &cpu_id))
- return AE_ERROR;
-
- acpi_map_cpu2node(handle, cpu_id, phys_id);
- return AE_OK;
-}
-
-void __init acpi_set_processor_mapping(void)
-{
- /* Set persistent cpu <-> node mapping for all processors. */
- acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT,
- ACPI_UINT32_MAX, set_processor_node_mapping,
- NULL, NULL, NULL);
-}
-#else
-void __init acpi_set_processor_mapping(void) {}
-#endif /* CONFIG_ACPI_HOTPLUG_CPU */
-
#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
static int get_ioapic_id(struct acpi_subtable_header *entry, u32 gsi_base,
u64 *phys_addr, int *ioapic_id)
diff --git a/drivers/acpi/spcr.c b/drivers/acpi/spcr.c
index 01c9466..3afa8c1 100644
--- a/drivers/acpi/spcr.c
+++ b/drivers/acpi/spcr.c
@@ -30,7 +30,7 @@ static bool qdf2400_erratum_44_present(struct acpi_table_header *h)
return true;
if (!memcmp(h->oem_table_id, "QDF2400 ", ACPI_OEM_TABLE_ID_SIZE) &&
- h->oem_revision == 0)
+ h->oem_revision == 1)
return true;
return false;
diff --git a/drivers/ata/ahci_qoriq.c b/drivers/ata/ahci_qoriq.c
index 85d8332..4c96f3a 100644
--- a/drivers/ata/ahci_qoriq.c
+++ b/drivers/ata/ahci_qoriq.c
@@ -177,7 +177,8 @@ static int ahci_qoriq_phy_init(struct ahci_host_priv *hpriv)
case AHCI_LS1043A:
if (!qpriv->ecc_addr)
return -EINVAL;
- writel(ECC_DIS_ARMV8_CH2, qpriv->ecc_addr);
+ writel(readl(qpriv->ecc_addr) | ECC_DIS_ARMV8_CH2,
+ qpriv->ecc_addr);
writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1);
writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS);
if (qpriv->is_dmacoherent)
@@ -194,7 +195,8 @@ static int ahci_qoriq_phy_init(struct ahci_host_priv *hpriv)
case AHCI_LS1046A:
if (!qpriv->ecc_addr)
return -EINVAL;
- writel(ECC_DIS_ARMV8_CH2, qpriv->ecc_addr);
+ writel(readl(qpriv->ecc_addr) | ECC_DIS_ARMV8_CH2,
+ qpriv->ecc_addr);
writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1);
writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS);
if (qpriv->is_dmacoherent)
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index 2bd92dc..274d6d7 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -1482,7 +1482,6 @@ unsigned int ata_sff_qc_issue(struct ata_queued_cmd *qc)
break;
default:
- WARN_ON_ONCE(1);
return AC_ERR_SYSTEM;
}
diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c
index 4669823..19e6e53 100644
--- a/drivers/ata/libata-transport.c
+++ b/drivers/ata/libata-transport.c
@@ -224,7 +224,6 @@ static DECLARE_TRANSPORT_CLASS(ata_port_class,
static void ata_tport_release(struct device *dev)
{
- put_device(dev->parent);
}
/**
@@ -284,7 +283,7 @@ int ata_tport_add(struct device *parent,
device_initialize(dev);
dev->type = &ata_port_type;
- dev->parent = get_device(parent);
+ dev->parent = parent;
dev->release = ata_tport_release;
dev_set_name(dev, "ata%d", ap->print_id);
transport_setup_device(dev);
@@ -348,7 +347,6 @@ static DECLARE_TRANSPORT_CLASS(ata_link_class,
static void ata_tlink_release(struct device *dev)
{
- put_device(dev->parent);
}
/**
@@ -410,7 +408,7 @@ int ata_tlink_add(struct ata_link *link)
int error;
device_initialize(dev);
- dev->parent = get_device(&ap->tdev);
+ dev->parent = &ap->tdev;
dev->release = ata_tlink_release;
if (ata_is_host_link(link))
dev_set_name(dev, "link%d", ap->print_id);
@@ -589,7 +587,6 @@ static DECLARE_TRANSPORT_CLASS(ata_dev_class,
static void ata_tdev_release(struct device *dev)
{
- put_device(dev->parent);
}
/**
@@ -662,7 +659,7 @@ static int ata_tdev_add(struct ata_device *ata_dev)
int error;
device_initialize(dev);
- dev->parent = get_device(&link->tdev);
+ dev->parent = &link->tdev;
dev->release = ata_tdev_release;
if (ata_is_host_link(link))
dev_set_name(dev, "dev%d.%d", ap->print_id,ata_dev->devno);
diff --git a/drivers/atm/ambassador.c b/drivers/atm/ambassador.c
index 4a61079..906705e 100644
--- a/drivers/atm/ambassador.c
+++ b/drivers/atm/ambassador.c
@@ -2267,9 +2267,8 @@ static int amb_probe(struct pci_dev *pci_dev,
dev->atm_dev->ci_range.vpi_bits = NUM_VPI_BITS;
dev->atm_dev->ci_range.vci_bits = NUM_VCI_BITS;
- init_timer(&dev->housekeeping);
- dev->housekeeping.function = do_housekeeping;
- dev->housekeeping.data = (unsigned long) dev;
+ setup_timer(&dev->housekeeping, do_housekeeping,
+ (unsigned long)dev);
mod_timer(&dev->housekeeping, jiffies);
// enable host interrupts
diff --git a/drivers/auxdisplay/img-ascii-lcd.c b/drivers/auxdisplay/img-ascii-lcd.c
index bf43b5d..83f1439 100644
--- a/drivers/auxdisplay/img-ascii-lcd.c
+++ b/drivers/auxdisplay/img-ascii-lcd.c
@@ -218,6 +218,7 @@ static const struct of_device_id img_ascii_lcd_matches[] = {
{ .compatible = "img,boston-lcd", .data = &boston_config },
{ .compatible = "mti,malta-lcd", .data = &malta_config },
{ .compatible = "mti,sead3-lcd", .data = &sead3_config },
+ { /* sentinel */ }
};
/**
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 684bda4..6bb60fb 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -639,11 +639,6 @@ int lock_device_hotplug_sysfs(void)
return restart_syscall();
}
-void assert_held_device_hotplug(void)
-{
- lockdep_assert_held(&device_hotplug_lock);
-}
-
#ifdef CONFIG_BLOCK
static inline int device_is_not_partition(struct device *dev)
{
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 7e4287b..d8a2356 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -47,6 +47,8 @@ static DEFINE_MUTEX(nbd_index_mutex);
struct nbd_sock {
struct socket *sock;
struct mutex tx_lock;
+ struct request *pending;
+ int sent;
};
#define NBD_TIMEDOUT 0
@@ -124,7 +126,8 @@ static const char *nbdcmd_to_ascii(int cmd)
static int nbd_size_clear(struct nbd_device *nbd, struct block_device *bdev)
{
- bd_set_size(bdev, 0);
+ if (bdev->bd_openers <= 1)
+ bd_set_size(bdev, 0);
set_capacity(nbd->disk, 0);
kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
@@ -190,7 +193,7 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
dev_err(nbd_to_dev(nbd), "Connection timed out, shutting down connection\n");
set_bit(NBD_TIMEDOUT, &nbd->runtime_flags);
- req->errors++;
+ req->errors = -EIO;
mutex_lock(&nbd->config_lock);
sock_shutdown(nbd);
@@ -202,7 +205,7 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
* Send or receive packet.
*/
static int sock_xmit(struct nbd_device *nbd, int index, int send,
- struct iov_iter *iter, int msg_flags)
+ struct iov_iter *iter, int msg_flags, int *sent)
{
struct socket *sock = nbd->socks[index]->sock;
int result;
@@ -237,6 +240,8 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send,
result = -EPIPE; /* short read */
break;
}
+ if (sent)
+ *sent += result;
} while (msg_data_left(&msg));
tsk_restore_flags(current, pflags, PF_MEMALLOC);
@@ -248,6 +253,7 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send,
static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
{
struct request *req = blk_mq_rq_from_pdu(cmd);
+ struct nbd_sock *nsock = nbd->socks[index];
int result;
struct nbd_request request = {.magic = htonl(NBD_REQUEST_MAGIC)};
struct kvec iov = {.iov_base = &request, .iov_len = sizeof(request)};
@@ -256,6 +262,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
struct bio *bio;
u32 type;
u32 tag = blk_mq_unique_tag(req);
+ int sent = nsock->sent, skip = 0;
iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request));
@@ -283,6 +290,17 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
return -EIO;
}
+ /* We did a partial send previously, and we at least sent the whole
+ * request struct, so just go and send the rest of the pages in the
+ * request.
+ */
+ if (sent) {
+ if (sent >= sizeof(request)) {
+ skip = sent - sizeof(request);
+ goto send_pages;
+ }
+ iov_iter_advance(&from, sent);
+ }
request.type = htonl(type);
if (type != NBD_CMD_FLUSH) {
request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9);
@@ -294,15 +312,27 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
cmd, nbdcmd_to_ascii(type),
(unsigned long long)blk_rq_pos(req) << 9, blk_rq_bytes(req));
result = sock_xmit(nbd, index, 1, &from,
- (type == NBD_CMD_WRITE) ? MSG_MORE : 0);
+ (type == NBD_CMD_WRITE) ? MSG_MORE : 0, &sent);
if (result <= 0) {
+ if (result == -ERESTARTSYS) {
+ /* If we havne't sent anything we can just return BUSY,
+ * however if we have sent something we need to make
+ * sure we only allow this req to be sent until we are
+ * completely done.
+ */
+ if (sent) {
+ nsock->pending = req;
+ nsock->sent = sent;
+ }
+ return BLK_MQ_RQ_QUEUE_BUSY;
+ }
dev_err_ratelimited(disk_to_dev(nbd->disk),
"Send control failed (result %d)\n", result);
return -EIO;
}
-
+send_pages:
if (type != NBD_CMD_WRITE)
- return 0;
+ goto out;
bio = req->bio;
while (bio) {
@@ -318,8 +348,25 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
cmd, bvec.bv_len);
iov_iter_bvec(&from, ITER_BVEC | WRITE,
&bvec, 1, bvec.bv_len);
- result = sock_xmit(nbd, index, 1, &from, flags);
+ if (skip) {
+ if (skip >= iov_iter_count(&from)) {
+ skip -= iov_iter_count(&from);
+ continue;
+ }
+ iov_iter_advance(&from, skip);
+ skip = 0;
+ }
+ result = sock_xmit(nbd, index, 1, &from, flags, &sent);
if (result <= 0) {
+ if (result == -ERESTARTSYS) {
+ /* We've already sent the header, we
+ * have no choice but to set pending and
+ * return BUSY.
+ */
+ nsock->pending = req;
+ nsock->sent = sent;
+ return BLK_MQ_RQ_QUEUE_BUSY;
+ }
dev_err(disk_to_dev(nbd->disk),
"Send data failed (result %d)\n",
result);
@@ -336,6 +383,9 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
}
bio = next;
}
+out:
+ nsock->pending = NULL;
+ nsock->sent = 0;
return 0;
}
@@ -353,7 +403,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
reply.magic = 0;
iov_iter_kvec(&to, READ | ITER_KVEC, &iov, 1, sizeof(reply));
- result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL);
+ result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL);
if (result <= 0) {
if (!test_bit(NBD_DISCONNECTED, &nbd->runtime_flags) &&
!test_bit(NBD_DISCONNECT_REQUESTED, &nbd->runtime_flags))
@@ -383,7 +433,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
if (ntohl(reply.error)) {
dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n",
ntohl(reply.error));
- req->errors++;
+ req->errors = -EIO;
return cmd;
}
@@ -395,11 +445,11 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
rq_for_each_segment(bvec, req, iter) {
iov_iter_bvec(&to, ITER_BVEC | READ,
&bvec, 1, bvec.bv_len);
- result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL);
+ result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL);
if (result <= 0) {
dev_err(disk_to_dev(nbd->disk), "Receive data failed (result %d)\n",
result);
- req->errors++;
+ req->errors = -EIO;
return cmd;
}
dev_dbg(nbd_to_dev(nbd), "request %p: got %d bytes data\n",
@@ -469,7 +519,7 @@ static void nbd_clear_req(struct request *req, void *data, bool reserved)
if (!blk_mq_request_started(req))
return;
cmd = blk_mq_rq_to_pdu(req);
- req->errors++;
+ req->errors = -EIO;
nbd_end_request(cmd);
}
@@ -482,22 +532,23 @@ static void nbd_clear_que(struct nbd_device *nbd)
}
-static void nbd_handle_cmd(struct nbd_cmd *cmd, int index)
+static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
{
struct request *req = blk_mq_rq_from_pdu(cmd);
struct nbd_device *nbd = cmd->nbd;
struct nbd_sock *nsock;
+ int ret;
if (index >= nbd->num_connections) {
dev_err_ratelimited(disk_to_dev(nbd->disk),
"Attempted send on invalid socket\n");
- goto error_out;
+ return -EINVAL;
}
if (test_bit(NBD_DISCONNECTED, &nbd->runtime_flags)) {
dev_err_ratelimited(disk_to_dev(nbd->disk),
"Attempted send on closed socket\n");
- goto error_out;
+ return -EINVAL;
}
req->errors = 0;
@@ -508,29 +559,30 @@ static void nbd_handle_cmd(struct nbd_cmd *cmd, int index)
mutex_unlock(&nsock->tx_lock);
dev_err_ratelimited(disk_to_dev(nbd->disk),
"Attempted send on closed socket\n");
- goto error_out;
+ return -EINVAL;
}
- if (nbd_send_cmd(nbd, cmd, index) != 0) {
- dev_err_ratelimited(disk_to_dev(nbd->disk),
- "Request send failed\n");
- req->errors++;
- nbd_end_request(cmd);
+ /* Handle the case that we have a pending request that was partially
+ * transmitted that _has_ to be serviced first. We need to call requeue
+ * here so that it gets put _after_ the request that is already on the
+ * dispatch list.
+ */
+ if (unlikely(nsock->pending && nsock->pending != req)) {
+ blk_mq_requeue_request(req, true);
+ ret = 0;
+ goto out;
}
-
+ ret = nbd_send_cmd(nbd, cmd, index);
+out:
mutex_unlock(&nsock->tx_lock);
-
- return;
-
-error_out:
- req->errors++;
- nbd_end_request(cmd);
+ return ret;
}
static int nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
struct nbd_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
+ int ret;
/*
* Since we look at the bio's to send the request over the network we
@@ -543,10 +595,20 @@ static int nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
*/
init_completion(&cmd->send_complete);
blk_mq_start_request(bd->rq);
- nbd_handle_cmd(cmd, hctx->queue_num);
+
+ /* We can be called directly from the user space process, which means we
+ * could possibly have signals pending so our sendmsg will fail. In
+ * this case we need to return that we are busy, otherwise error out as
+ * appropriate.
+ */
+ ret = nbd_handle_cmd(cmd, hctx->queue_num);
+ if (ret < 0)
+ ret = BLK_MQ_RQ_QUEUE_ERROR;
+ if (!ret)
+ ret = BLK_MQ_RQ_QUEUE_OK;
complete(&cmd->send_complete);
- return BLK_MQ_RQ_QUEUE_OK;
+ return ret;
}
static int nbd_add_socket(struct nbd_device *nbd, struct block_device *bdev,
@@ -581,6 +643,8 @@ static int nbd_add_socket(struct nbd_device *nbd, struct block_device *bdev,
mutex_init(&nsock->tx_lock);
nsock->sock = sock;
+ nsock->pending = NULL;
+ nsock->sent = 0;
socks[nbd->num_connections++] = nsock;
if (max_part)
@@ -602,6 +666,8 @@ static void nbd_reset(struct nbd_device *nbd)
static void nbd_bdev_reset(struct block_device *bdev)
{
+ if (bdev->bd_openers > 1)
+ return;
set_device_ro(bdev, false);
bdev->bd_inode->i_size = 0;
if (max_part > 0) {
@@ -634,7 +700,7 @@ static void send_disconnects(struct nbd_device *nbd)
for (i = 0; i < nbd->num_connections; i++) {
iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request));
- ret = sock_xmit(nbd, i, 1, &from, 0);
+ ret = sock_xmit(nbd, i, 1, &from, 0, NULL);
if (ret <= 0)
dev_err(disk_to_dev(nbd->disk),
"Send disconnect failed %d\n", ret);
@@ -665,7 +731,8 @@ static int nbd_clear_sock(struct nbd_device *nbd, struct block_device *bdev)
{
sock_shutdown(nbd);
nbd_clear_que(nbd);
- kill_bdev(bdev);
+
+ __invalidate_device(bdev, true);
nbd_bdev_reset(bdev);
/*
* We want to give the run thread a chance to wait for everybody
@@ -781,7 +848,10 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
nbd_size_set(nbd, bdev, nbd->blksize, arg);
return 0;
case NBD_SET_TIMEOUT:
- nbd->tag_set.timeout = arg * HZ;
+ if (arg) {
+ nbd->tag_set.timeout = arg * HZ;
+ blk_queue_rq_timeout(nbd->disk->queue, arg * HZ);
+ }
return 0;
case NBD_SET_FLAGS:
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index 10aed84..939641d 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -50,7 +50,7 @@
the slower the port i/o. In some cases, setting
this to zero will speed up the device. (default -1)
- major You may use this parameter to overide the
+ major You may use this parameter to override the
default major number (46) that this driver
will use. Be sure to change the device
name as well.
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 644ba08..9cfd2e0 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -61,7 +61,7 @@
first drive found.
- major You may use this parameter to overide the
+ major You may use this parameter to override the
default major number (45) that this driver
will use. Be sure to change the device
name as well.
diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c
index ed93e8b..14c5d32 100644
--- a/drivers/block/paride/pf.c
+++ b/drivers/block/paride/pf.c
@@ -59,7 +59,7 @@
the slower the port i/o. In some cases, setting
this to zero will speed up the device. (default -1)
- major You may use this parameter to overide the
+ major You may use this parameter to override the
default major number (47) that this driver
will use. Be sure to change the device
name as well.
diff --git a/drivers/block/paride/pg.c b/drivers/block/paride/pg.c
index 5db955f..3b5882b 100644
--- a/drivers/block/paride/pg.c
+++ b/drivers/block/paride/pg.c
@@ -84,7 +84,7 @@
the slower the port i/o. In some cases, setting
this to zero will speed up the device. (default -1)
- major You may use this parameter to overide the
+ major You may use this parameter to override the
default major number (97) that this driver
will use. Be sure to change the device
name as well.
diff --git a/drivers/block/paride/pt.c b/drivers/block/paride/pt.c
index 61fc6824..e815312 100644
--- a/drivers/block/paride/pt.c
+++ b/drivers/block/paride/pt.c
@@ -61,7 +61,7 @@
the slower the port i/o. In some cases, setting
this to zero will speed up the device. (default -1)
- major You may use this parameter to overide the
+ major You may use this parameter to override the
default major number (96) that this driver
will use. Be sure to change the device
name as well.
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 4d68077..517838b 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -120,10 +120,11 @@ static int atomic_dec_return_safe(atomic_t *v)
/* Feature bits */
-#define RBD_FEATURE_LAYERING (1<<0)
-#define RBD_FEATURE_STRIPINGV2 (1<<1)
-#define RBD_FEATURE_EXCLUSIVE_LOCK (1<<2)
-#define RBD_FEATURE_DATA_POOL (1<<7)
+#define RBD_FEATURE_LAYERING (1ULL<<0)
+#define RBD_FEATURE_STRIPINGV2 (1ULL<<1)
+#define RBD_FEATURE_EXCLUSIVE_LOCK (1ULL<<2)
+#define RBD_FEATURE_DATA_POOL (1ULL<<7)
+
#define RBD_FEATURES_ALL (RBD_FEATURE_LAYERING | \
RBD_FEATURE_STRIPINGV2 | \
RBD_FEATURE_EXCLUSIVE_LOCK | \
@@ -499,16 +500,23 @@ static bool rbd_is_lock_owner(struct rbd_device *rbd_dev)
return is_lock_owner;
}
+static ssize_t rbd_supported_features_show(struct bus_type *bus, char *buf)
+{
+ return sprintf(buf, "0x%llx\n", RBD_FEATURES_SUPPORTED);
+}
+
static BUS_ATTR(add, S_IWUSR, NULL, rbd_add);
static BUS_ATTR(remove, S_IWUSR, NULL, rbd_remove);
static BUS_ATTR(add_single_major, S_IWUSR, NULL, rbd_add_single_major);
static BUS_ATTR(remove_single_major, S_IWUSR, NULL, rbd_remove_single_major);
+static BUS_ATTR(supported_features, S_IRUGO, rbd_supported_features_show, NULL);
static struct attribute *rbd_bus_attrs[] = {
&bus_attr_add.attr,
&bus_attr_remove.attr,
&bus_attr_add_single_major.attr,
&bus_attr_remove_single_major.attr,
+ &bus_attr_supported_features.attr,
NULL,
};
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index e27d89a..dceb5ed 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1189,6 +1189,8 @@ static int zram_add(void)
blk_queue_io_min(zram->disk->queue, PAGE_SIZE);
blk_queue_io_opt(zram->disk->queue, PAGE_SIZE);
zram->disk->queue->limits.discard_granularity = PAGE_SIZE;
+ zram->disk->queue->limits.max_sectors = SECTORS_PER_PAGE;
+ zram->disk->queue->limits.chunk_sectors = 0;
blk_queue_max_discard_sectors(zram->disk->queue, UINT_MAX);
/*
* zram_bio_discard() will clear all logical blocks if logical block
diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig
index c2c14a1..a6a9dd4 100644
--- a/drivers/bluetooth/Kconfig
+++ b/drivers/bluetooth/Kconfig
@@ -344,7 +344,8 @@
config BT_QCOMSMD
tristate "Qualcomm SMD based HCI support"
- depends on (QCOM_SMD && QCOM_WCNSS_CTRL) || COMPILE_TEST
+ depends on RPMSG || (COMPILE_TEST && RPMSG=n)
+ depends on QCOM_WCNSS_CTRL || (COMPILE_TEST && QCOM_WCNSS_CTRL=n)
select BT_QCA
help
Qualcomm SMD based HCI driver.
diff --git a/drivers/bluetooth/btqcomsmd.c b/drivers/bluetooth/btqcomsmd.c
index 8d4868a..ef730c1 100644
--- a/drivers/bluetooth/btqcomsmd.c
+++ b/drivers/bluetooth/btqcomsmd.c
@@ -14,7 +14,7 @@
#include <linux/module.h>
#include <linux/slab.h>
-#include <linux/soc/qcom/smd.h>
+#include <linux/rpmsg.h>
#include <linux/soc/qcom/wcnss_ctrl.h>
#include <linux/platform_device.h>
@@ -26,8 +26,8 @@
struct btqcomsmd {
struct hci_dev *hdev;
- struct qcom_smd_channel *acl_channel;
- struct qcom_smd_channel *cmd_channel;
+ struct rpmsg_endpoint *acl_channel;
+ struct rpmsg_endpoint *cmd_channel;
};
static int btqcomsmd_recv(struct hci_dev *hdev, unsigned int type,
@@ -48,19 +48,19 @@ static int btqcomsmd_recv(struct hci_dev *hdev, unsigned int type,
return hci_recv_frame(hdev, skb);
}
-static int btqcomsmd_acl_callback(struct qcom_smd_channel *channel,
- const void *data, size_t count)
+static int btqcomsmd_acl_callback(struct rpmsg_device *rpdev, void *data,
+ int count, void *priv, u32 addr)
{
- struct btqcomsmd *btq = qcom_smd_get_drvdata(channel);
+ struct btqcomsmd *btq = priv;
btq->hdev->stat.byte_rx += count;
return btqcomsmd_recv(btq->hdev, HCI_ACLDATA_PKT, data, count);
}
-static int btqcomsmd_cmd_callback(struct qcom_smd_channel *channel,
- const void *data, size_t count)
+static int btqcomsmd_cmd_callback(struct rpmsg_device *rpdev, void *data,
+ int count, void *priv, u32 addr)
{
- struct btqcomsmd *btq = qcom_smd_get_drvdata(channel);
+ struct btqcomsmd *btq = priv;
return btqcomsmd_recv(btq->hdev, HCI_EVENT_PKT, data, count);
}
@@ -72,12 +72,12 @@ static int btqcomsmd_send(struct hci_dev *hdev, struct sk_buff *skb)
switch (hci_skb_pkt_type(skb)) {
case HCI_ACLDATA_PKT:
- ret = qcom_smd_send(btq->acl_channel, skb->data, skb->len);
+ ret = rpmsg_send(btq->acl_channel, skb->data, skb->len);
hdev->stat.acl_tx++;
hdev->stat.byte_tx += skb->len;
break;
case HCI_COMMAND_PKT:
- ret = qcom_smd_send(btq->cmd_channel, skb->data, skb->len);
+ ret = rpmsg_send(btq->cmd_channel, skb->data, skb->len);
hdev->stat.cmd_tx++;
break;
default:
@@ -114,18 +114,15 @@ static int btqcomsmd_probe(struct platform_device *pdev)
wcnss = dev_get_drvdata(pdev->dev.parent);
btq->acl_channel = qcom_wcnss_open_channel(wcnss, "APPS_RIVA_BT_ACL",
- btqcomsmd_acl_callback);
+ btqcomsmd_acl_callback, btq);
if (IS_ERR(btq->acl_channel))
return PTR_ERR(btq->acl_channel);
btq->cmd_channel = qcom_wcnss_open_channel(wcnss, "APPS_RIVA_BT_CMD",
- btqcomsmd_cmd_callback);
+ btqcomsmd_cmd_callback, btq);
if (IS_ERR(btq->cmd_channel))
return PTR_ERR(btq->cmd_channel);
- qcom_smd_set_drvdata(btq->acl_channel, btq);
- qcom_smd_set_drvdata(btq->cmd_channel, btq);
-
hdev = hci_alloc_dev();
if (!hdev)
return -ENOMEM;
@@ -158,6 +155,9 @@ static int btqcomsmd_remove(struct platform_device *pdev)
hci_unregister_dev(btq->hdev);
hci_free_dev(btq->hdev);
+ rpmsg_destroy_ept(btq->cmd_channel);
+ rpmsg_destroy_ept(btq->acl_channel);
+
return 0;
}
diff --git a/drivers/char/hw_random/amd-rng.c b/drivers/char/hw_random/amd-rng.c
index 4a99ac7..9959c76 100644
--- a/drivers/char/hw_random/amd-rng.c
+++ b/drivers/char/hw_random/amd-rng.c
@@ -55,6 +55,7 @@ MODULE_DEVICE_TABLE(pci, pci_tbl);
struct amd768_priv {
void __iomem *iobase;
struct pci_dev *pcidev;
+ u32 pmbase;
};
static int amd_rng_read(struct hwrng *rng, void *buf, size_t max, bool wait)
@@ -148,33 +149,58 @@ static int __init mod_init(void)
if (pmbase == 0)
return -EIO;
- priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+ priv = kzalloc(sizeof(*priv), GFP_KERNEL);
if (!priv)
return -ENOMEM;
- if (!devm_request_region(&pdev->dev, pmbase + PMBASE_OFFSET,
- PMBASE_SIZE, DRV_NAME)) {
+ if (!request_region(pmbase + PMBASE_OFFSET, PMBASE_SIZE, DRV_NAME)) {
dev_err(&pdev->dev, DRV_NAME " region 0x%x already in use!\n",
pmbase + 0xF0);
- return -EBUSY;
+ err = -EBUSY;
+ goto out;
}
- priv->iobase = devm_ioport_map(&pdev->dev, pmbase + PMBASE_OFFSET,
- PMBASE_SIZE);
+ priv->iobase = ioport_map(pmbase + PMBASE_OFFSET, PMBASE_SIZE);
if (!priv->iobase) {
pr_err(DRV_NAME "Cannot map ioport\n");
- return -ENOMEM;
+ err = -EINVAL;
+ goto err_iomap;
}
amd_rng.priv = (unsigned long)priv;
+ priv->pmbase = pmbase;
priv->pcidev = pdev;
pr_info(DRV_NAME " detected\n");
- return devm_hwrng_register(&pdev->dev, &amd_rng);
+ err = hwrng_register(&amd_rng);
+ if (err) {
+ pr_err(DRV_NAME " registering failed (%d)\n", err);
+ goto err_hwrng;
+ }
+ return 0;
+
+err_hwrng:
+ ioport_unmap(priv->iobase);
+err_iomap:
+ release_region(pmbase + PMBASE_OFFSET, PMBASE_SIZE);
+out:
+ kfree(priv);
+ return err;
}
static void __exit mod_exit(void)
{
+ struct amd768_priv *priv;
+
+ priv = (struct amd768_priv *)amd_rng.priv;
+
+ hwrng_unregister(&amd_rng);
+
+ ioport_unmap(priv->iobase);
+
+ release_region(priv->pmbase + PMBASE_OFFSET, PMBASE_SIZE);
+
+ kfree(priv);
}
module_init(mod_init);
diff --git a/drivers/char/hw_random/geode-rng.c b/drivers/char/hw_random/geode-rng.c
index e7a2459..e1d421a 100644
--- a/drivers/char/hw_random/geode-rng.c
+++ b/drivers/char/hw_random/geode-rng.c
@@ -31,6 +31,9 @@
#include <linux/module.h>
#include <linux/pci.h>
+
+#define PFX KBUILD_MODNAME ": "
+
#define GEODE_RNG_DATA_REG 0x50
#define GEODE_RNG_STATUS_REG 0x54
@@ -82,6 +85,7 @@ static struct hwrng geode_rng = {
static int __init mod_init(void)
{
+ int err = -ENODEV;
struct pci_dev *pdev = NULL;
const struct pci_device_id *ent;
void __iomem *mem;
@@ -89,27 +93,43 @@ static int __init mod_init(void)
for_each_pci_dev(pdev) {
ent = pci_match_id(pci_tbl, pdev);
- if (ent) {
- rng_base = pci_resource_start(pdev, 0);
- if (rng_base == 0)
- return -ENODEV;
-
- mem = devm_ioremap(&pdev->dev, rng_base, 0x58);
- if (!mem)
- return -ENOMEM;
- geode_rng.priv = (unsigned long)mem;
-
- pr_info("AMD Geode RNG detected\n");
- return devm_hwrng_register(&pdev->dev, &geode_rng);
- }
+ if (ent)
+ goto found;
}
-
/* Device not found. */
- return -ENODEV;
+ goto out;
+
+found:
+ rng_base = pci_resource_start(pdev, 0);
+ if (rng_base == 0)
+ goto out;
+ err = -ENOMEM;
+ mem = ioremap(rng_base, 0x58);
+ if (!mem)
+ goto out;
+ geode_rng.priv = (unsigned long)mem;
+
+ pr_info("AMD Geode RNG detected\n");
+ err = hwrng_register(&geode_rng);
+ if (err) {
+ pr_err(PFX "RNG registering failed (%d)\n",
+ err);
+ goto err_unmap;
+ }
+out:
+ return err;
+
+err_unmap:
+ iounmap(mem);
+ goto out;
}
static void __exit mod_exit(void)
{
+ void __iomem *mem = (void __iomem *)geode_rng.priv;
+
+ hwrng_unregister(&geode_rng);
+ iounmap(mem);
}
module_init(mod_init);
diff --git a/drivers/char/hw_random/omap-rng.c b/drivers/char/hw_random/omap-rng.c
index 3ad86fd..b1ad125 100644
--- a/drivers/char/hw_random/omap-rng.c
+++ b/drivers/char/hw_random/omap-rng.c
@@ -397,9 +397,8 @@ static int of_get_omap_rng_device_details(struct omap_rng_dev *priv,
irq, err);
return err;
}
- omap_rng_write(priv, RNG_INTMASK_REG, RNG_SHUTDOWN_OFLO_MASK);
- priv->clk = of_clk_get(pdev->dev.of_node, 0);
+ priv->clk = devm_clk_get(&pdev->dev, NULL);
if (IS_ERR(priv->clk) && PTR_ERR(priv->clk) == -EPROBE_DEFER)
return -EPROBE_DEFER;
if (!IS_ERR(priv->clk)) {
@@ -408,6 +407,19 @@ static int of_get_omap_rng_device_details(struct omap_rng_dev *priv,
dev_err(&pdev->dev, "unable to enable the clk, "
"err = %d\n", err);
}
+
+ /*
+ * On OMAP4, enabling the shutdown_oflo interrupt is
+ * done in the interrupt mask register. There is no
+ * such register on EIP76, and it's enabled by the
+ * same bit in the control register
+ */
+ if (priv->pdata->regs[RNG_INTMASK_REG])
+ omap_rng_write(priv, RNG_INTMASK_REG,
+ RNG_SHUTDOWN_OFLO_MASK);
+ else
+ omap_rng_write(priv, RNG_CONTROL_REG,
+ RNG_SHUTDOWN_OFLO_MASK);
}
return 0;
}
diff --git a/drivers/char/nwbutton.c b/drivers/char/nwbutton.c
index a5b1eb2..e6d0d27 100644
--- a/drivers/char/nwbutton.c
+++ b/drivers/char/nwbutton.c
@@ -6,7 +6,7 @@
#include <linux/module.h>
#include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
#include <linux/interrupt.h>
#include <linux/time.h>
#include <linux/timer.h>
diff --git a/drivers/char/ppdev.c b/drivers/char/ppdev.c
index 2a558c7..3e73bcd 100644
--- a/drivers/char/ppdev.c
+++ b/drivers/char/ppdev.c
@@ -84,11 +84,14 @@ struct pp_struct {
struct ieee1284_info state;
struct ieee1284_info saved_state;
long default_inactivity;
+ int index;
};
/* should we use PARDEVICE_MAX here? */
static struct device *devices[PARPORT_MAX];
+static DEFINE_IDA(ida_index);
+
/* pp_struct.flags bitfields */
#define PP_CLAIMED (1<<0)
#define PP_EXCL (1<<1)
@@ -290,7 +293,7 @@ static int register_device(int minor, struct pp_struct *pp)
struct pardevice *pdev = NULL;
char *name;
struct pardev_cb ppdev_cb;
- int rc = 0;
+ int rc = 0, index;
name = kasprintf(GFP_KERNEL, CHRDEV "%x", minor);
if (name == NULL)
@@ -303,20 +306,23 @@ static int register_device(int minor, struct pp_struct *pp)
goto err;
}
+ index = ida_simple_get(&ida_index, 0, 0, GFP_KERNEL);
memset(&ppdev_cb, 0, sizeof(ppdev_cb));
ppdev_cb.irq_func = pp_irq;
ppdev_cb.flags = (pp->flags & PP_EXCL) ? PARPORT_FLAG_EXCL : 0;
ppdev_cb.private = pp;
- pdev = parport_register_dev_model(port, name, &ppdev_cb, minor);
+ pdev = parport_register_dev_model(port, name, &ppdev_cb, index);
parport_put_port(port);
if (!pdev) {
pr_warn("%s: failed to register device!\n", name);
rc = -ENXIO;
+ ida_simple_remove(&ida_index, index);
goto err;
}
pp->pdev = pdev;
+ pp->index = index;
dev_dbg(&pdev->dev, "registered pardevice\n");
err:
kfree(name);
@@ -755,6 +761,7 @@ static int pp_release(struct inode *inode, struct file *file)
if (pp->pdev) {
parport_unregister_device(pp->pdev);
+ ida_simple_remove(&ida_index, pp->index);
pp->pdev = NULL;
pr_debug(CHRDEV "%x: unregistered pardevice\n", minor);
}
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 1ef2640..0ab0249 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -313,13 +313,6 @@ static int random_read_wakeup_bits = 64;
static int random_write_wakeup_bits = 28 * OUTPUT_POOL_WORDS;
/*
- * The minimum number of seconds between urandom pool reseeding. We
- * do this to limit the amount of entropy that can be drained from the
- * input pool even if there are heavy demands on /dev/urandom.
- */
-static int random_min_urandom_seed = 60;
-
-/*
* Originally, we used a primitive polynomial of degree .poolwords
* over GF(2). The taps for various sizes are defined below. They
* were chosen to be evenly spaced except for the last tap, which is 1
@@ -409,7 +402,6 @@ static struct poolinfo {
*/
static DECLARE_WAIT_QUEUE_HEAD(random_read_wait);
static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);
-static DECLARE_WAIT_QUEUE_HEAD(urandom_init_wait);
static struct fasync_struct *fasync;
static DEFINE_SPINLOCK(random_ready_list_lock);
@@ -467,7 +459,6 @@ struct entropy_store {
int entropy_count;
int entropy_total;
unsigned int initialized:1;
- unsigned int limit:1;
unsigned int last_data_init:1;
__u8 last_data[EXTRACT_SIZE];
};
@@ -485,7 +476,6 @@ static __u32 blocking_pool_data[OUTPUT_POOL_WORDS] __latent_entropy;
static struct entropy_store input_pool = {
.poolinfo = &poolinfo_table[0],
.name = "input",
- .limit = 1,
.lock = __SPIN_LOCK_UNLOCKED(input_pool.lock),
.pool = input_pool_data
};
@@ -493,7 +483,6 @@ static struct entropy_store input_pool = {
static struct entropy_store blocking_pool = {
.poolinfo = &poolinfo_table[1],
.name = "blocking",
- .limit = 1,
.pull = &input_pool,
.lock = __SPIN_LOCK_UNLOCKED(blocking_pool.lock),
.pool = blocking_pool_data,
@@ -855,13 +844,6 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
spin_unlock_irqrestore(&primary_crng.lock, flags);
}
-static inline void maybe_reseed_primary_crng(void)
-{
- if (crng_init > 2 &&
- time_after(jiffies, primary_crng.init_time + CRNG_RESEED_INTERVAL))
- crng_reseed(&primary_crng, &input_pool);
-}
-
static inline void crng_wait_ready(void)
{
wait_event_interruptible(crng_init_wait, crng_ready());
@@ -1220,15 +1202,6 @@ static void xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
r->entropy_count > r->poolinfo->poolfracbits)
return;
- if (r->limit == 0 && random_min_urandom_seed) {
- unsigned long now = jiffies;
-
- if (time_before(now,
- r->last_pulled + random_min_urandom_seed * HZ))
- return;
- r->last_pulled = now;
- }
-
_xfer_secondary_pool(r, nbytes);
}
@@ -1236,8 +1209,6 @@ static void _xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
{
__u32 tmp[OUTPUT_POOL_WORDS];
- /* For /dev/random's pool, always leave two wakeups' worth */
- int rsvd_bytes = r->limit ? 0 : random_read_wakeup_bits / 4;
int bytes = nbytes;
/* pull at least as much as a wakeup */
@@ -1248,7 +1219,7 @@ static void _xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
trace_xfer_secondary_pool(r->name, bytes * 8, nbytes * 8,
ENTROPY_BITS(r), ENTROPY_BITS(r->pull));
bytes = extract_entropy(r->pull, tmp, bytes,
- random_read_wakeup_bits / 8, rsvd_bytes);
+ random_read_wakeup_bits / 8, 0);
mix_pool_bytes(r, tmp, bytes);
credit_entropy_bits(r, bytes*8);
}
@@ -1276,7 +1247,7 @@ static void push_to_pool(struct work_struct *work)
static size_t account(struct entropy_store *r, size_t nbytes, int min,
int reserved)
{
- int entropy_count, orig;
+ int entropy_count, orig, have_bytes;
size_t ibytes, nfrac;
BUG_ON(r->entropy_count > r->poolinfo->poolfracbits);
@@ -1285,14 +1256,12 @@ static size_t account(struct entropy_store *r, size_t nbytes, int min,
retry:
entropy_count = orig = ACCESS_ONCE(r->entropy_count);
ibytes = nbytes;
- /* If limited, never pull more than available */
- if (r->limit) {
- int have_bytes = entropy_count >> (ENTROPY_SHIFT + 3);
+ /* never pull more than available */
+ have_bytes = entropy_count >> (ENTROPY_SHIFT + 3);
- if ((have_bytes -= reserved) < 0)
- have_bytes = 0;
- ibytes = min_t(size_t, ibytes, have_bytes);
- }
+ if ((have_bytes -= reserved) < 0)
+ have_bytes = 0;
+ ibytes = min_t(size_t, ibytes, have_bytes);
if (ibytes < min)
ibytes = 0;
@@ -1912,6 +1881,7 @@ SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count,
static int min_read_thresh = 8, min_write_thresh;
static int max_read_thresh = OUTPUT_POOL_WORDS * 32;
static int max_write_thresh = INPUT_POOL_WORDS * 32;
+static int random_min_urandom_seed = 60;
static char sysctl_bootid[16];
/*
@@ -2042,63 +2012,64 @@ struct ctl_table random_table[] = {
};
#endif /* CONFIG_SYSCTL */
-static u32 random_int_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned;
-
-int random_int_secret_init(void)
-{
- get_random_bytes(random_int_secret, sizeof(random_int_secret));
- return 0;
-}
-
-static DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash)
- __aligned(sizeof(unsigned long));
+struct batched_entropy {
+ union {
+ u64 entropy_u64[CHACHA20_BLOCK_SIZE / sizeof(u64)];
+ u32 entropy_u32[CHACHA20_BLOCK_SIZE / sizeof(u32)];
+ };
+ unsigned int position;
+};
/*
- * Get a random word for internal kernel use only. Similar to urandom but
- * with the goal of minimal entropy pool depletion. As a result, the random
- * value is not cryptographically secure but for several uses the cost of
- * depleting entropy is too high
+ * Get a random word for internal kernel use only. The quality of the random
+ * number is either as good as RDRAND or as good as /dev/urandom, with the
+ * goal of being quite fast and not depleting entropy.
*/
-unsigned int get_random_int(void)
+static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64);
+u64 get_random_u64(void)
{
- __u32 *hash;
- unsigned int ret;
+ u64 ret;
+ struct batched_entropy *batch;
+
+#if BITS_PER_LONG == 64
+ if (arch_get_random_long((unsigned long *)&ret))
+ return ret;
+#else
+ if (arch_get_random_long((unsigned long *)&ret) &&
+ arch_get_random_long((unsigned long *)&ret + 1))
+ return ret;
+#endif
+
+ batch = &get_cpu_var(batched_entropy_u64);
+ if (batch->position % ARRAY_SIZE(batch->entropy_u64) == 0) {
+ extract_crng((u8 *)batch->entropy_u64);
+ batch->position = 0;
+ }
+ ret = batch->entropy_u64[batch->position++];
+ put_cpu_var(batched_entropy_u64);
+ return ret;
+}
+EXPORT_SYMBOL(get_random_u64);
+
+static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u32);
+u32 get_random_u32(void)
+{
+ u32 ret;
+ struct batched_entropy *batch;
if (arch_get_random_int(&ret))
return ret;
- hash = get_cpu_var(get_random_int_hash);
-
- hash[0] += current->pid + jiffies + random_get_entropy();
- md5_transform(hash, random_int_secret);
- ret = hash[0];
- put_cpu_var(get_random_int_hash);
-
+ batch = &get_cpu_var(batched_entropy_u32);
+ if (batch->position % ARRAY_SIZE(batch->entropy_u32) == 0) {
+ extract_crng((u8 *)batch->entropy_u32);
+ batch->position = 0;
+ }
+ ret = batch->entropy_u32[batch->position++];
+ put_cpu_var(batched_entropy_u32);
return ret;
}
-EXPORT_SYMBOL(get_random_int);
-
-/*
- * Same as get_random_int(), but returns unsigned long.
- */
-unsigned long get_random_long(void)
-{
- __u32 *hash;
- unsigned long ret;
-
- if (arch_get_random_long(&ret))
- return ret;
-
- hash = get_cpu_var(get_random_int_hash);
-
- hash[0] += current->pid + jiffies + random_get_entropy();
- md5_transform(hash, random_int_secret);
- ret = *(unsigned long *)hash;
- put_cpu_var(get_random_int_hash);
-
- return ret;
-}
-EXPORT_SYMBOL(get_random_long);
+EXPORT_SYMBOL(get_random_u32);
/**
* randomize_page - Generate a random, page aligned address
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 0fb39fe..67201f6 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -2502,7 +2502,7 @@ struct clk *__clk_create_clk(struct clk_hw *hw, const char *dev_id,
clk->core = hw->core;
clk->dev_id = dev_id;
- clk->con_id = con_id;
+ clk->con_id = kstrdup_const(con_id, GFP_KERNEL);
clk->max_rate = ULONG_MAX;
clk_prepare_lock();
@@ -2518,6 +2518,7 @@ void __clk_free_clk(struct clk *clk)
hlist_del(&clk->clks_node);
clk_prepare_unlock();
+ kfree_const(clk->con_id);
kfree(clk);
}
diff --git a/drivers/clk/rockchip/clk-rk3036.c b/drivers/clk/rockchip/clk-rk3036.c
index 924f560..00d4150 100644
--- a/drivers/clk/rockchip/clk-rk3036.c
+++ b/drivers/clk/rockchip/clk-rk3036.c
@@ -127,7 +127,7 @@ PNAME(mux_ddrphy_p) = { "dpll_ddr", "gpll_ddr" };
PNAME(mux_pll_src_3plls_p) = { "apll", "dpll", "gpll" };
PNAME(mux_timer_p) = { "xin24m", "pclk_peri_src" };
-PNAME(mux_pll_src_apll_dpll_gpll_usb480m_p) = { "apll", "dpll", "gpll" "usb480m" };
+PNAME(mux_pll_src_apll_dpll_gpll_usb480m_p) = { "apll", "dpll", "gpll", "usb480m" };
PNAME(mux_mmc_src_p) = { "apll", "dpll", "gpll", "xin24m" };
PNAME(mux_i2s_pre_p) = { "i2s_src", "i2s_frac", "ext_i2s", "xin12m" };
@@ -450,6 +450,13 @@ static void __init rk3036_clk_init(struct device_node *np)
return;
}
+ /*
+ * Make uart_pll_clk a child of the gpll, as all other sources are
+ * not that usable / stable.
+ */
+ writel_relaxed(HIWORD_UPDATE(0x2, 0x3, 10),
+ reg_base + RK2928_CLKSEL_CON(13));
+
ctx = rockchip_clk_init(np, reg_base, CLK_NR_CLKS);
if (IS_ERR(ctx)) {
pr_err("%s: rockchip clk init failed\n", __func__);
diff --git a/drivers/clk/sunxi-ng/Kconfig b/drivers/clk/sunxi-ng/Kconfig
index 695bbf9..72109d2 100644
--- a/drivers/clk/sunxi-ng/Kconfig
+++ b/drivers/clk/sunxi-ng/Kconfig
@@ -80,6 +80,7 @@
select SUNXI_CCU_DIV
select SUNXI_CCU_NK
select SUNXI_CCU_NKM
+ select SUNXI_CCU_NKMP
select SUNXI_CCU_NM
select SUNXI_CCU_MP
select SUNXI_CCU_PHASE
diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
index e3c084c..f54114c 100644
--- a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
+++ b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
@@ -566,7 +566,7 @@ static SUNXI_CCU_M_WITH_GATE(gpu_clk, "gpu", "pll-gpu",
0x1a0, 0, 3, BIT(31), CLK_SET_RATE_PARENT);
/* Fixed Factor clocks */
-static CLK_FIXED_FACTOR(osc12M_clk, "osc12M", "osc24M", 1, 2, 0);
+static CLK_FIXED_FACTOR(osc12M_clk, "osc12M", "osc24M", 2, 1, 0);
/* We hardcode the divider to 4 for now */
static CLK_FIXED_FACTOR(pll_audio_clk, "pll-audio",
diff --git a/drivers/clk/sunxi-ng/ccu-sun6i-a31.c b/drivers/clk/sunxi-ng/ccu-sun6i-a31.c
index 4c9a920..89e68d2 100644
--- a/drivers/clk/sunxi-ng/ccu-sun6i-a31.c
+++ b/drivers/clk/sunxi-ng/ccu-sun6i-a31.c
@@ -608,7 +608,7 @@ static SUNXI_CCU_M_WITH_MUX_GATE(hdmi_clk, "hdmi", lcd_ch1_parents,
0x150, 0, 4, 24, 2, BIT(31),
CLK_SET_RATE_PARENT);
-static SUNXI_CCU_GATE(hdmi_ddc_clk, "hdmi-ddc", "osc24M", 0x150, BIT(31), 0);
+static SUNXI_CCU_GATE(hdmi_ddc_clk, "hdmi-ddc", "osc24M", 0x150, BIT(30), 0);
static SUNXI_CCU_GATE(ps_clk, "ps", "lcd1-ch1", 0x140, BIT(31), 0);
diff --git a/drivers/clk/sunxi-ng/ccu_mp.c b/drivers/clk/sunxi-ng/ccu_mp.c
index 22c2ca7..b583f18 100644
--- a/drivers/clk/sunxi-ng/ccu_mp.c
+++ b/drivers/clk/sunxi-ng/ccu_mp.c
@@ -85,6 +85,10 @@ static unsigned long ccu_mp_recalc_rate(struct clk_hw *hw,
unsigned int m, p;
u32 reg;
+ /* Adjust parent_rate according to pre-dividers */
+ ccu_mux_helper_adjust_parent_for_prediv(&cmp->common, &cmp->mux,
+ -1, &parent_rate);
+
reg = readl(cmp->common.base + cmp->common.reg);
m = reg >> cmp->m.shift;
@@ -117,6 +121,10 @@ static int ccu_mp_set_rate(struct clk_hw *hw, unsigned long rate,
unsigned int m, p;
u32 reg;
+ /* Adjust parent_rate according to pre-dividers */
+ ccu_mux_helper_adjust_parent_for_prediv(&cmp->common, &cmp->mux,
+ -1, &parent_rate);
+
max_m = cmp->m.max ?: 1 << cmp->m.width;
max_p = cmp->p.max ?: 1 << ((1 << cmp->p.width) - 1);
diff --git a/drivers/clk/sunxi-ng/ccu_nkmp.c b/drivers/clk/sunxi-ng/ccu_nkmp.c
index a2b40a0..488055e 100644
--- a/drivers/clk/sunxi-ng/ccu_nkmp.c
+++ b/drivers/clk/sunxi-ng/ccu_nkmp.c
@@ -107,7 +107,7 @@ static unsigned long ccu_nkmp_recalc_rate(struct clk_hw *hw,
p = reg >> nkmp->p.shift;
p &= (1 << nkmp->p.width) - 1;
- return parent_rate * n * k >> p / m;
+ return (parent_rate * n * k >> p) / m;
}
static long ccu_nkmp_round_rate(struct clk_hw *hw, unsigned long rate,
diff --git a/drivers/clocksource/clkevt-probe.c b/drivers/clocksource/clkevt-probe.c
index 8c30fec..eb89b50 100644
--- a/drivers/clocksource/clkevt-probe.c
+++ b/drivers/clocksource/clkevt-probe.c
@@ -17,7 +17,7 @@
#include <linux/init.h>
#include <linux/of.h>
-#include <linux/clockchip.h>
+#include <linux/clockchips.h>
extern struct of_device_id __clkevt_of_table[];
diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c
index 745844e..d4ca996 100644
--- a/drivers/clocksource/tcb_clksrc.c
+++ b/drivers/clocksource/tcb_clksrc.c
@@ -10,7 +10,6 @@
#include <linux/io.h>
#include <linux/platform_device.h>
#include <linux/atmel_tc.h>
-#include <linux/sched_clock.h>
/*
@@ -57,14 +56,9 @@ static u64 tc_get_cycles(struct clocksource *cs)
return (upper << 16) | lower;
}
-static u32 tc_get_cv32(void)
-{
- return __raw_readl(tcaddr + ATMEL_TC_REG(0, CV));
-}
-
static u64 tc_get_cycles32(struct clocksource *cs)
{
- return tc_get_cv32();
+ return __raw_readl(tcaddr + ATMEL_TC_REG(0, CV));
}
static struct clocksource clksrc = {
@@ -75,11 +69,6 @@ static struct clocksource clksrc = {
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
};
-static u64 notrace tc_read_sched_clock(void)
-{
- return tc_get_cv32();
-}
-
#ifdef CONFIG_GENERIC_CLOCKEVENTS
struct tc_clkevt_device {
@@ -350,9 +339,6 @@ static int __init tcb_clksrc_init(void)
clksrc.read = tc_get_cycles32;
/* setup ony channel 0 */
tcb_setup_single_chan(tc, best_divisor_idx);
-
- /* register sched_clock on chips with single 32 bit counter */
- sched_clock_register(tc_read_sched_clock, 32, divided_rate);
} else {
/* tclib will give us three clocks no matter what the
* underlying platform supports.
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index a475432..bc96d42 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -680,9 +680,11 @@ static ssize_t show_cpuinfo_cur_freq(struct cpufreq_policy *policy,
char *buf)
{
unsigned int cur_freq = __cpufreq_get(policy);
- if (!cur_freq)
- return sprintf(buf, "<unknown>");
- return sprintf(buf, "%u\n", cur_freq);
+
+ if (cur_freq)
+ return sprintf(buf, "%u\n", cur_freq);
+
+ return sprintf(buf, "<unknown>\n");
}
/**
@@ -916,11 +918,19 @@ static struct kobj_type ktype_cpufreq = {
.release = cpufreq_sysfs_release,
};
-static int add_cpu_dev_symlink(struct cpufreq_policy *policy,
- struct device *dev)
+static void add_cpu_dev_symlink(struct cpufreq_policy *policy, unsigned int cpu)
{
+ struct device *dev = get_cpu_device(cpu);
+
+ if (!dev)
+ return;
+
+ if (cpumask_test_and_set_cpu(cpu, policy->real_cpus))
+ return;
+
dev_dbg(dev, "%s: Adding symlink\n", __func__);
- return sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq");
+ if (sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq"))
+ dev_err(dev, "cpufreq symlink creation failed\n");
}
static void remove_cpu_dev_symlink(struct cpufreq_policy *policy,
@@ -1178,10 +1188,13 @@ static int cpufreq_online(unsigned int cpu)
policy->user_policy.min = policy->min;
policy->user_policy.max = policy->max;
- write_lock_irqsave(&cpufreq_driver_lock, flags);
- for_each_cpu(j, policy->related_cpus)
+ for_each_cpu(j, policy->related_cpus) {
per_cpu(cpufreq_cpu_data, j) = policy;
- write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+ add_cpu_dev_symlink(policy, j);
+ }
+ } else {
+ policy->min = policy->user_policy.min;
+ policy->max = policy->user_policy.max;
}
if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
@@ -1270,13 +1283,15 @@ static int cpufreq_online(unsigned int cpu)
if (cpufreq_driver->exit)
cpufreq_driver->exit(policy);
+
+ for_each_cpu(j, policy->real_cpus)
+ remove_cpu_dev_symlink(policy, get_cpu_device(j));
+
out_free_policy:
cpufreq_policy_free(policy);
return ret;
}
-static int cpufreq_offline(unsigned int cpu);
-
/**
* cpufreq_add_dev - the cpufreq interface for a CPU device.
* @dev: CPU device.
@@ -1298,16 +1313,10 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
/* Create sysfs link on CPU registration */
policy = per_cpu(cpufreq_cpu_data, cpu);
- if (!policy || cpumask_test_and_set_cpu(cpu, policy->real_cpus))
- return 0;
+ if (policy)
+ add_cpu_dev_symlink(policy, cpu);
- ret = add_cpu_dev_symlink(policy, dev);
- if (ret) {
- cpumask_clear_cpu(cpu, policy->real_cpus);
- cpufreq_offline(cpu);
- }
-
- return ret;
+ return 0;
}
static int cpufreq_offline(unsigned int cpu)
@@ -2532,4 +2541,5 @@ static int __init cpufreq_core_init(void)
return 0;
}
+module_param(off, int, 0444);
core_initcall(cpufreq_core_init);
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index b1fbaa3..283491f 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -84,6 +84,11 @@ static inline u64 div_ext_fp(u64 x, u64 y)
return div64_u64(x << EXT_FRAC_BITS, y);
}
+static inline int32_t percent_ext_fp(int percent)
+{
+ return div_ext_fp(percent, 100);
+}
+
/**
* struct sample - Store performance sample
* @core_avg_perf: Ratio of APERF/MPERF which is the actual average
@@ -359,9 +364,7 @@ static bool driver_registered __read_mostly;
static bool acpi_ppc;
#endif
-static struct perf_limits performance_limits;
-static struct perf_limits powersave_limits;
-static struct perf_limits *limits;
+static struct perf_limits global;
static void intel_pstate_init_limits(struct perf_limits *limits)
{
@@ -372,13 +375,6 @@ static void intel_pstate_init_limits(struct perf_limits *limits)
limits->max_sysfs_pct = 100;
}
-static void intel_pstate_set_performance_limits(struct perf_limits *limits)
-{
- intel_pstate_init_limits(limits);
- limits->min_perf_pct = 100;
- limits->min_perf = int_ext_tofp(1);
-}
-
static DEFINE_MUTEX(intel_pstate_driver_lock);
static DEFINE_MUTEX(intel_pstate_limits_lock);
@@ -501,7 +497,7 @@ static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy)
* correct max turbo frequency based on the turbo state.
* Also need to convert to MHz as _PSS freq is in MHz.
*/
- if (!limits->turbo_disabled)
+ if (!global.turbo_disabled)
cpu->acpi_perf_data.states[0].core_frequency =
policy->cpuinfo.max_freq / 1000;
cpu->valid_pss_table = true;
@@ -620,7 +616,7 @@ static inline void update_turbo_state(void)
cpu = all_cpu_data[0];
rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
- limits->turbo_disabled =
+ global.turbo_disabled =
(misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE ||
cpu->pstate.max_pstate == cpu->pstate.turbo_pstate);
}
@@ -844,12 +840,11 @@ static struct freq_attr *hwp_cpufreq_attrs[] = {
static void intel_pstate_hwp_set(struct cpufreq_policy *policy)
{
- int min, hw_min, max, hw_max, cpu, range, adj_range;
- struct perf_limits *perf_limits = limits;
+ int min, hw_min, max, hw_max, cpu;
+ struct perf_limits *perf_limits = &global;
u64 value, cap;
for_each_cpu(cpu, policy->cpus) {
- int max_perf_pct, min_perf_pct;
struct cpudata *cpu_data = all_cpu_data[cpu];
s16 epp;
@@ -858,24 +853,22 @@ static void intel_pstate_hwp_set(struct cpufreq_policy *policy)
rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap);
hw_min = HWP_LOWEST_PERF(cap);
- if (limits->no_turbo)
+ if (global.no_turbo)
hw_max = HWP_GUARANTEED_PERF(cap);
else
hw_max = HWP_HIGHEST_PERF(cap);
- range = hw_max - hw_min;
- max_perf_pct = perf_limits->max_perf_pct;
- min_perf_pct = perf_limits->min_perf_pct;
+ max = fp_ext_toint(hw_max * perf_limits->max_perf);
+ if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE)
+ min = max;
+ else
+ min = fp_ext_toint(hw_max * perf_limits->min_perf);
rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value);
- adj_range = min_perf_pct * range / 100;
- min = hw_min + adj_range;
+
value &= ~HWP_MIN_PERF(~0L);
value |= HWP_MIN_PERF(min);
- adj_range = max_perf_pct * range / 100;
- max = hw_min + adj_range;
-
value &= ~HWP_MAX_PERF(~0L);
value |= HWP_MAX_PERF(max);
@@ -979,6 +972,7 @@ static void intel_pstate_update_policies(void)
static int pid_param_set(void *data, u64 val)
{
*(u32 *)data = val;
+ pid_params.sample_rate_ns = pid_params.sample_rate_ms * NSEC_PER_MSEC;
intel_pstate_reset_all_pid();
return 0;
}
@@ -1050,7 +1044,7 @@ static void intel_pstate_debug_hide_params(void)
static ssize_t show_##file_name \
(struct kobject *kobj, struct attribute *attr, char *buf) \
{ \
- return sprintf(buf, "%u\n", limits->object); \
+ return sprintf(buf, "%u\n", global.object); \
}
static ssize_t intel_pstate_show_status(char *buf);
@@ -1141,10 +1135,10 @@ static ssize_t show_no_turbo(struct kobject *kobj,
}
update_turbo_state();
- if (limits->turbo_disabled)
- ret = sprintf(buf, "%u\n", limits->turbo_disabled);
+ if (global.turbo_disabled)
+ ret = sprintf(buf, "%u\n", global.turbo_disabled);
else
- ret = sprintf(buf, "%u\n", limits->no_turbo);
+ ret = sprintf(buf, "%u\n", global.no_turbo);
mutex_unlock(&intel_pstate_driver_lock);
@@ -1171,14 +1165,14 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
mutex_lock(&intel_pstate_limits_lock);
update_turbo_state();
- if (limits->turbo_disabled) {
+ if (global.turbo_disabled) {
pr_warn("Turbo disabled by BIOS or unavailable on processor\n");
mutex_unlock(&intel_pstate_limits_lock);
mutex_unlock(&intel_pstate_driver_lock);
return -EPERM;
}
- limits->no_turbo = clamp_t(int, input, 0, 1);
+ global.no_turbo = clamp_t(int, input, 0, 1);
mutex_unlock(&intel_pstate_limits_lock);
@@ -1208,14 +1202,11 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
mutex_lock(&intel_pstate_limits_lock);
- limits->max_sysfs_pct = clamp_t(int, input, 0 , 100);
- limits->max_perf_pct = min(limits->max_policy_pct,
- limits->max_sysfs_pct);
- limits->max_perf_pct = max(limits->min_policy_pct,
- limits->max_perf_pct);
- limits->max_perf_pct = max(limits->min_perf_pct,
- limits->max_perf_pct);
- limits->max_perf = div_ext_fp(limits->max_perf_pct, 100);
+ global.max_sysfs_pct = clamp_t(int, input, 0 , 100);
+ global.max_perf_pct = min(global.max_policy_pct, global.max_sysfs_pct);
+ global.max_perf_pct = max(global.min_policy_pct, global.max_perf_pct);
+ global.max_perf_pct = max(global.min_perf_pct, global.max_perf_pct);
+ global.max_perf = percent_ext_fp(global.max_perf_pct);
mutex_unlock(&intel_pstate_limits_lock);
@@ -1245,14 +1236,11 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
mutex_lock(&intel_pstate_limits_lock);
- limits->min_sysfs_pct = clamp_t(int, input, 0 , 100);
- limits->min_perf_pct = max(limits->min_policy_pct,
- limits->min_sysfs_pct);
- limits->min_perf_pct = min(limits->max_policy_pct,
- limits->min_perf_pct);
- limits->min_perf_pct = min(limits->max_perf_pct,
- limits->min_perf_pct);
- limits->min_perf = div_ext_fp(limits->min_perf_pct, 100);
+ global.min_sysfs_pct = clamp_t(int, input, 0 , 100);
+ global.min_perf_pct = max(global.min_policy_pct, global.min_sysfs_pct);
+ global.min_perf_pct = min(global.max_policy_pct, global.min_perf_pct);
+ global.min_perf_pct = min(global.max_perf_pct, global.min_perf_pct);
+ global.min_perf = percent_ext_fp(global.min_perf_pct);
mutex_unlock(&intel_pstate_limits_lock);
@@ -1377,7 +1365,7 @@ static u64 atom_get_val(struct cpudata *cpudata, int pstate)
u32 vid;
val = (u64)pstate << 8;
- if (limits->no_turbo && !limits->turbo_disabled)
+ if (global.no_turbo && !global.turbo_disabled)
val |= (u64)1 << 32;
vid_fp = cpudata->vid.min + mul_fp(
@@ -1547,7 +1535,7 @@ static u64 core_get_val(struct cpudata *cpudata, int pstate)
u64 val;
val = (u64)pstate << 8;
- if (limits->no_turbo && !limits->turbo_disabled)
+ if (global.no_turbo && !global.turbo_disabled)
val |= (u64)1 << 32;
return val;
@@ -1673,9 +1661,9 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
int max_perf = cpu->pstate.turbo_pstate;
int max_perf_adj;
int min_perf;
- struct perf_limits *perf_limits = limits;
+ struct perf_limits *perf_limits = &global;
- if (limits->no_turbo || limits->turbo_disabled)
+ if (global.no_turbo || global.turbo_disabled)
max_perf = cpu->pstate.max_pstate;
if (per_cpu_limits)
@@ -1810,7 +1798,7 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
sample->busy_scaled = busy_frac * 100;
- target = limits->no_turbo || limits->turbo_disabled ?
+ target = global.no_turbo || global.turbo_disabled ?
cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
target += target >> 2;
target = mul_fp(target, busy_frac);
@@ -1874,13 +1862,11 @@ static int intel_pstate_prepare_request(struct cpudata *cpu, int pstate)
intel_pstate_get_min_max(cpu, &min_perf, &max_perf);
pstate = clamp_t(int, pstate, min_perf, max_perf);
- trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
return pstate;
}
static void intel_pstate_update_pstate(struct cpudata *cpu, int pstate)
{
- pstate = intel_pstate_prepare_request(cpu, pstate);
if (pstate == cpu->pstate.current_pstate)
return;
@@ -1900,6 +1886,8 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
update_turbo_state();
+ target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
+ trace_cpu_frequency(target_pstate * cpu->pstate.scaling, cpu->cpu);
intel_pstate_update_pstate(cpu, target_pstate);
sample = &cpu->sample;
@@ -2070,36 +2058,34 @@ static void intel_pstate_clear_update_util_hook(unsigned int cpu)
static void intel_pstate_update_perf_limits(struct cpufreq_policy *policy,
struct perf_limits *limits)
{
+ int32_t max_policy_perf, min_policy_perf;
- limits->max_policy_pct = DIV_ROUND_UP(policy->max * 100,
- policy->cpuinfo.max_freq);
- limits->max_policy_pct = clamp_t(int, limits->max_policy_pct, 0, 100);
+ max_policy_perf = div_ext_fp(policy->max, policy->cpuinfo.max_freq);
+ max_policy_perf = clamp_t(int32_t, max_policy_perf, 0, int_ext_tofp(1));
if (policy->max == policy->min) {
- limits->min_policy_pct = limits->max_policy_pct;
+ min_policy_perf = max_policy_perf;
} else {
- limits->min_policy_pct = DIV_ROUND_UP(policy->min * 100,
- policy->cpuinfo.max_freq);
- limits->min_policy_pct = clamp_t(int, limits->min_policy_pct,
- 0, 100);
+ min_policy_perf = div_ext_fp(policy->min,
+ policy->cpuinfo.max_freq);
+ min_policy_perf = clamp_t(int32_t, min_policy_perf,
+ 0, max_policy_perf);
}
- /* Normalize user input to [min_policy_pct, max_policy_pct] */
- limits->min_perf_pct = max(limits->min_policy_pct,
- limits->min_sysfs_pct);
- limits->min_perf_pct = min(limits->max_policy_pct,
- limits->min_perf_pct);
- limits->max_perf_pct = min(limits->max_policy_pct,
- limits->max_sysfs_pct);
- limits->max_perf_pct = max(limits->min_policy_pct,
- limits->max_perf_pct);
+ /* Normalize user input to [min_perf, max_perf] */
+ limits->min_perf = max(min_policy_perf,
+ percent_ext_fp(limits->min_sysfs_pct));
+ limits->min_perf = min(limits->min_perf, max_policy_perf);
+ limits->max_perf = min(max_policy_perf,
+ percent_ext_fp(limits->max_sysfs_pct));
+ limits->max_perf = max(min_policy_perf, limits->max_perf);
- /* Make sure min_perf_pct <= max_perf_pct */
- limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct);
+ /* Make sure min_perf <= max_perf */
+ limits->min_perf = min(limits->min_perf, limits->max_perf);
- limits->min_perf = div_ext_fp(limits->min_perf_pct, 100);
- limits->max_perf = div_ext_fp(limits->max_perf_pct, 100);
limits->max_perf = round_up(limits->max_perf, EXT_FRAC_BITS);
limits->min_perf = round_up(limits->min_perf, EXT_FRAC_BITS);
+ limits->max_perf_pct = fp_ext_toint(limits->max_perf * 100);
+ limits->min_perf_pct = fp_ext_toint(limits->min_perf * 100);
pr_debug("cpu:%d max_perf_pct:%d min_perf_pct:%d\n", policy->cpu,
limits->max_perf_pct, limits->min_perf_pct);
@@ -2108,7 +2094,7 @@ static void intel_pstate_update_perf_limits(struct cpufreq_policy *policy,
static int intel_pstate_set_policy(struct cpufreq_policy *policy)
{
struct cpudata *cpu;
- struct perf_limits *perf_limits = NULL;
+ struct perf_limits *perf_limits = &global;
if (!policy->cpuinfo.max_freq)
return -ENODEV;
@@ -2131,28 +2117,8 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
mutex_lock(&intel_pstate_limits_lock);
- if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
- if (!perf_limits) {
- limits = &performance_limits;
- perf_limits = limits;
- }
- if (policy->max >= policy->cpuinfo.max_freq &&
- !limits->no_turbo) {
- pr_debug("set performance\n");
- intel_pstate_set_performance_limits(perf_limits);
- goto out;
- }
- } else {
- pr_debug("set powersave\n");
- if (!perf_limits) {
- limits = &powersave_limits;
- perf_limits = limits;
- }
-
- }
-
intel_pstate_update_perf_limits(policy, perf_limits);
- out:
+
if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) {
/*
* NOHZ_FULL CPUs need this as the governor callback may not
@@ -2174,16 +2140,9 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
static int intel_pstate_verify_policy(struct cpufreq_policy *policy)
{
struct cpudata *cpu = all_cpu_data[policy->cpu];
- struct perf_limits *perf_limits;
-
- if (policy->policy == CPUFREQ_POLICY_PERFORMANCE)
- perf_limits = &performance_limits;
- else
- perf_limits = &powersave_limits;
update_turbo_state();
- policy->cpuinfo.max_freq = perf_limits->turbo_disabled ||
- perf_limits->no_turbo ?
+ policy->cpuinfo.max_freq = global.turbo_disabled || global.no_turbo ?
cpu->pstate.max_freq :
cpu->pstate.turbo_freq;
@@ -2198,9 +2157,9 @@ static int intel_pstate_verify_policy(struct cpufreq_policy *policy)
unsigned int max_freq, min_freq;
max_freq = policy->cpuinfo.max_freq *
- limits->max_sysfs_pct / 100;
+ global.max_sysfs_pct / 100;
min_freq = policy->cpuinfo.max_freq *
- limits->min_sysfs_pct / 100;
+ global.min_sysfs_pct / 100;
cpufreq_verify_within_limits(policy, min_freq, max_freq);
}
@@ -2243,13 +2202,8 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy)
cpu = all_cpu_data[policy->cpu];
- /*
- * We need sane value in the cpu->perf_limits, so inherit from global
- * perf_limits limits, which are seeded with values based on the
- * CONFIG_CPU_FREQ_DEFAULT_GOV_*, during boot up.
- */
if (per_cpu_limits)
- memcpy(cpu->perf_limits, limits, sizeof(struct perf_limits));
+ intel_pstate_init_limits(cpu->perf_limits);
policy->min = cpu->pstate.min_pstate * cpu->pstate.scaling;
policy->max = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
@@ -2257,7 +2211,7 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy)
/* cpuinfo and default policy values */
policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling;
update_turbo_state();
- policy->cpuinfo.max_freq = limits->turbo_disabled ?
+ policy->cpuinfo.max_freq = global.turbo_disabled ?
cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
policy->cpuinfo.max_freq *= cpu->pstate.scaling;
@@ -2277,7 +2231,7 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
return ret;
policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
- if (limits->min_perf_pct == 100 && limits->max_perf_pct == 100)
+ if (IS_ENABLED(CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE))
policy->policy = CPUFREQ_POLICY_PERFORMANCE;
else
policy->policy = CPUFREQ_POLICY_POWERSAVE;
@@ -2301,46 +2255,16 @@ static struct cpufreq_driver intel_pstate = {
static int intel_cpufreq_verify_policy(struct cpufreq_policy *policy)
{
struct cpudata *cpu = all_cpu_data[policy->cpu];
- struct perf_limits *perf_limits = limits;
update_turbo_state();
- policy->cpuinfo.max_freq = limits->turbo_disabled ?
+ policy->cpuinfo.max_freq = global.no_turbo || global.turbo_disabled ?
cpu->pstate.max_freq : cpu->pstate.turbo_freq;
cpufreq_verify_within_cpu_limits(policy);
- if (per_cpu_limits)
- perf_limits = cpu->perf_limits;
-
- mutex_lock(&intel_pstate_limits_lock);
-
- intel_pstate_update_perf_limits(policy, perf_limits);
-
- mutex_unlock(&intel_pstate_limits_lock);
-
return 0;
}
-static unsigned int intel_cpufreq_turbo_update(struct cpudata *cpu,
- struct cpufreq_policy *policy,
- unsigned int target_freq)
-{
- unsigned int max_freq;
-
- update_turbo_state();
-
- max_freq = limits->no_turbo || limits->turbo_disabled ?
- cpu->pstate.max_freq : cpu->pstate.turbo_freq;
- policy->cpuinfo.max_freq = max_freq;
- if (policy->max > max_freq)
- policy->max = max_freq;
-
- if (target_freq > max_freq)
- target_freq = max_freq;
-
- return target_freq;
-}
-
static int intel_cpufreq_target(struct cpufreq_policy *policy,
unsigned int target_freq,
unsigned int relation)
@@ -2349,8 +2273,10 @@ static int intel_cpufreq_target(struct cpufreq_policy *policy,
struct cpufreq_freqs freqs;
int target_pstate;
+ update_turbo_state();
+
freqs.old = policy->cur;
- freqs.new = intel_cpufreq_turbo_update(cpu, policy, target_freq);
+ freqs.new = target_freq;
cpufreq_freq_transition_begin(policy, &freqs);
switch (relation) {
@@ -2370,6 +2296,7 @@ static int intel_cpufreq_target(struct cpufreq_policy *policy,
wrmsrl_on_cpu(policy->cpu, MSR_IA32_PERF_CTL,
pstate_funcs.get_val(cpu, target_pstate));
}
+ freqs.new = target_pstate * cpu->pstate.scaling;
cpufreq_freq_transition_end(policy, &freqs, false);
return 0;
@@ -2381,10 +2308,12 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy,
struct cpudata *cpu = all_cpu_data[policy->cpu];
int target_pstate;
- target_freq = intel_cpufreq_turbo_update(cpu, policy, target_freq);
+ update_turbo_state();
+
target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling);
+ target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
intel_pstate_update_pstate(cpu, target_pstate);
- return target_freq;
+ return target_pstate * cpu->pstate.scaling;
}
static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
@@ -2435,10 +2364,7 @@ static int intel_pstate_register_driver(void)
{
int ret;
- intel_pstate_init_limits(&powersave_limits);
- intel_pstate_set_performance_limits(&performance_limits);
- limits = IS_ENABLED(CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE) ?
- &performance_limits : &powersave_limits;
+ intel_pstate_init_limits(&global);
ret = cpufreq_register_driver(intel_pstate_driver);
if (ret) {
diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index 3705930..cda8f62 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -175,6 +175,24 @@ static int powernv_cpuidle_driver_init(void)
drv->state_count += 1;
}
+ /*
+ * On the PowerNV platform cpu_present may be less than cpu_possible in
+ * cases when firmware detects the CPU, but it is not available to the
+ * OS. If CONFIG_HOTPLUG_CPU=n, then such CPUs are not hotplugable at
+ * run time and hence cpu_devices are not created for those CPUs by the
+ * generic topology_init().
+ *
+ * drv->cpumask defaults to cpu_possible_mask in
+ * __cpuidle_driver_init(). This breaks cpuidle on PowerNV where
+ * cpu_devices are not created for CPUs in cpu_possible_mask that
+ * cannot be hot-added later at run time.
+ *
+ * Trying cpuidle_register_device() on a CPU without a cpu_device is
+ * incorrect, so pass a correct CPU mask to the generic cpuidle driver.
+ */
+
+ drv->cpumask = (struct cpumask *)cpu_present_mask;
+
return 0;
}
diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c
index c5adc8c..ae948b1 100644
--- a/drivers/cpuidle/sysfs.c
+++ b/drivers/cpuidle/sysfs.c
@@ -615,6 +615,18 @@ int cpuidle_add_sysfs(struct cpuidle_device *dev)
struct device *cpu_dev = get_cpu_device((unsigned long)dev->cpu);
int error;
+ /*
+ * Return if cpu_device is not setup for this CPU.
+ *
+ * This could happen if the arch did not set up cpu_device
+ * since this CPU is not in cpu_present mask and the
+ * driver did not send a correct CPU mask during registration.
+ * Without this check we would end up passing bogus
+ * value for &cpu_dev->kobj in kobject_init_and_add()
+ */
+ if (!cpu_dev)
+ return -ENODEV;
+
kdev = kzalloc(sizeof(*kdev), GFP_KERNEL);
if (!kdev)
return -ENOMEM;
diff --git a/drivers/crypto/ccp/ccp-dev-v5.c b/drivers/crypto/ccp/ccp-dev-v5.c
index 41cc853..fc08b4e 100644
--- a/drivers/crypto/ccp/ccp-dev-v5.c
+++ b/drivers/crypto/ccp/ccp-dev-v5.c
@@ -1015,6 +1015,7 @@ const struct ccp_vdata ccpv5a = {
const struct ccp_vdata ccpv5b = {
.version = CCP_VERSION(5, 0),
+ .dma_chan_attr = DMA_PRIVATE,
.setup = ccp5other_config,
.perform = &ccp5_actions,
.bar = 2,
diff --git a/drivers/crypto/ccp/ccp-dev.c b/drivers/crypto/ccp/ccp-dev.c
index 511ab04..92d1c69 100644
--- a/drivers/crypto/ccp/ccp-dev.c
+++ b/drivers/crypto/ccp/ccp-dev.c
@@ -283,11 +283,14 @@ EXPORT_SYMBOL_GPL(ccp_version);
*/
int ccp_enqueue_cmd(struct ccp_cmd *cmd)
{
- struct ccp_device *ccp = ccp_get_device();
+ struct ccp_device *ccp;
unsigned long flags;
unsigned int i;
int ret;
+ /* Some commands might need to be sent to a specific device */
+ ccp = cmd->ccp ? cmd->ccp : ccp_get_device();
+
if (!ccp)
return -ENODEV;
diff --git a/drivers/crypto/ccp/ccp-dev.h b/drivers/crypto/ccp/ccp-dev.h
index 2b5c01f..aa36f3f 100644
--- a/drivers/crypto/ccp/ccp-dev.h
+++ b/drivers/crypto/ccp/ccp-dev.h
@@ -179,6 +179,10 @@
/* ------------------------ General CCP Defines ------------------------ */
+#define CCP_DMA_DFLT 0x0
+#define CCP_DMA_PRIV 0x1
+#define CCP_DMA_PUB 0x2
+
#define CCP_DMAPOOL_MAX_SIZE 64
#define CCP_DMAPOOL_ALIGN BIT(5)
@@ -636,6 +640,7 @@ struct ccp_actions {
/* Structure to hold CCP version-specific values */
struct ccp_vdata {
const unsigned int version;
+ const unsigned int dma_chan_attr;
void (*setup)(struct ccp_device *);
const struct ccp_actions *perform;
const unsigned int bar;
diff --git a/drivers/crypto/ccp/ccp-dmaengine.c b/drivers/crypto/ccp/ccp-dmaengine.c
index e5d9278..e00be01 100644
--- a/drivers/crypto/ccp/ccp-dmaengine.c
+++ b/drivers/crypto/ccp/ccp-dmaengine.c
@@ -10,6 +10,7 @@
* published by the Free Software Foundation.
*/
+#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/dmaengine.h>
#include <linux/spinlock.h>
@@ -25,6 +26,37 @@
(mask == 0) ? 64 : fls64(mask); \
})
+/* The CCP as a DMA provider can be configured for public or private
+ * channels. Default is specified in the vdata for the device (PCI ID).
+ * This module parameter will override for all channels on all devices:
+ * dma_chan_attr = 0x2 to force all channels public
+ * = 0x1 to force all channels private
+ * = 0x0 to defer to the vdata setting
+ * = any other value: warning, revert to 0x0
+ */
+static unsigned int dma_chan_attr = CCP_DMA_DFLT;
+module_param(dma_chan_attr, uint, 0444);
+MODULE_PARM_DESC(dma_chan_attr, "Set DMA channel visibility: 0 (default) = device defaults, 1 = make private, 2 = make public");
+
+unsigned int ccp_get_dma_chan_attr(struct ccp_device *ccp)
+{
+ switch (dma_chan_attr) {
+ case CCP_DMA_DFLT:
+ return ccp->vdata->dma_chan_attr;
+
+ case CCP_DMA_PRIV:
+ return DMA_PRIVATE;
+
+ case CCP_DMA_PUB:
+ return 0;
+
+ default:
+ dev_info_once(ccp->dev, "Invalid value for dma_chan_attr: %d\n",
+ dma_chan_attr);
+ return ccp->vdata->dma_chan_attr;
+ }
+}
+
static void ccp_free_cmd_resources(struct ccp_device *ccp,
struct list_head *list)
{
@@ -390,6 +422,7 @@ static struct ccp_dma_desc *ccp_create_desc(struct dma_chan *dma_chan,
goto err;
ccp_cmd = &cmd->ccp_cmd;
+ ccp_cmd->ccp = chan->ccp;
ccp_pt = &ccp_cmd->u.passthru_nomap;
ccp_cmd->flags = CCP_CMD_MAY_BACKLOG;
ccp_cmd->flags |= CCP_CMD_PASSTHRU_NO_DMA_MAP;
@@ -674,6 +707,15 @@ int ccp_dmaengine_register(struct ccp_device *ccp)
dma_cap_set(DMA_SG, dma_dev->cap_mask);
dma_cap_set(DMA_INTERRUPT, dma_dev->cap_mask);
+ /* The DMA channels for this device can be set to public or private,
+ * and overridden by the module parameter dma_chan_attr.
+ * Default: according to the value in vdata (dma_chan_attr=0)
+ * dma_chan_attr=0x1: all channels private (override vdata)
+ * dma_chan_attr=0x2: all channels public (override vdata)
+ */
+ if (ccp_get_dma_chan_attr(ccp) == DMA_PRIVATE)
+ dma_cap_set(DMA_PRIVATE, dma_dev->cap_mask);
+
INIT_LIST_HEAD(&dma_dev->channels);
for (i = 0; i < ccp->cmd_q_count; i++) {
chan = ccp->ccp_dma_chan + i;
diff --git a/drivers/crypto/s5p-sss.c b/drivers/crypto/s5p-sss.c
index dce1af0..1b9da3d 100644
--- a/drivers/crypto/s5p-sss.c
+++ b/drivers/crypto/s5p-sss.c
@@ -270,7 +270,7 @@ static void s5p_sg_copy_buf(void *buf, struct scatterlist *sg,
scatterwalk_done(&walk, out, 0);
}
-static void s5p_aes_complete(struct s5p_aes_dev *dev, int err)
+static void s5p_sg_done(struct s5p_aes_dev *dev)
{
if (dev->sg_dst_cpy) {
dev_dbg(dev->dev,
@@ -281,8 +281,11 @@ static void s5p_aes_complete(struct s5p_aes_dev *dev, int err)
}
s5p_free_sg_cpy(dev, &dev->sg_src_cpy);
s5p_free_sg_cpy(dev, &dev->sg_dst_cpy);
+}
- /* holding a lock outside */
+/* Calls the completion. Cannot be called with dev->lock hold. */
+static void s5p_aes_complete(struct s5p_aes_dev *dev, int err)
+{
dev->req->base.complete(&dev->req->base, err);
dev->busy = false;
}
@@ -368,51 +371,44 @@ static int s5p_set_indata(struct s5p_aes_dev *dev, struct scatterlist *sg)
}
/*
- * Returns true if new transmitting (output) data is ready and its
- * address+length have to be written to device (by calling
- * s5p_set_dma_outdata()). False otherwise.
+ * Returns -ERRNO on error (mapping of new data failed).
+ * On success returns:
+ * - 0 if there is no more data,
+ * - 1 if new transmitting (output) data is ready and its address+length
+ * have to be written to device (by calling s5p_set_dma_outdata()).
*/
-static bool s5p_aes_tx(struct s5p_aes_dev *dev)
+static int s5p_aes_tx(struct s5p_aes_dev *dev)
{
- int err = 0;
- bool ret = false;
+ int ret = 0;
s5p_unset_outdata(dev);
if (!sg_is_last(dev->sg_dst)) {
- err = s5p_set_outdata(dev, sg_next(dev->sg_dst));
- if (err)
- s5p_aes_complete(dev, err);
- else
- ret = true;
- } else {
- s5p_aes_complete(dev, err);
-
- dev->busy = true;
- tasklet_schedule(&dev->tasklet);
+ ret = s5p_set_outdata(dev, sg_next(dev->sg_dst));
+ if (!ret)
+ ret = 1;
}
return ret;
}
/*
- * Returns true if new receiving (input) data is ready and its
- * address+length have to be written to device (by calling
- * s5p_set_dma_indata()). False otherwise.
+ * Returns -ERRNO on error (mapping of new data failed).
+ * On success returns:
+ * - 0 if there is no more data,
+ * - 1 if new receiving (input) data is ready and its address+length
+ * have to be written to device (by calling s5p_set_dma_indata()).
*/
-static bool s5p_aes_rx(struct s5p_aes_dev *dev)
+static int s5p_aes_rx(struct s5p_aes_dev *dev/*, bool *set_dma*/)
{
- int err;
- bool ret = false;
+ int ret = 0;
s5p_unset_indata(dev);
if (!sg_is_last(dev->sg_src)) {
- err = s5p_set_indata(dev, sg_next(dev->sg_src));
- if (err)
- s5p_aes_complete(dev, err);
- else
- ret = true;
+ ret = s5p_set_indata(dev, sg_next(dev->sg_src));
+ if (!ret)
+ ret = 1;
}
return ret;
@@ -422,33 +418,73 @@ static irqreturn_t s5p_aes_interrupt(int irq, void *dev_id)
{
struct platform_device *pdev = dev_id;
struct s5p_aes_dev *dev = platform_get_drvdata(pdev);
- bool set_dma_tx = false;
- bool set_dma_rx = false;
+ int err_dma_tx = 0;
+ int err_dma_rx = 0;
+ bool tx_end = false;
unsigned long flags;
uint32_t status;
+ int err;
spin_lock_irqsave(&dev->lock, flags);
+ /*
+ * Handle rx or tx interrupt. If there is still data (scatterlist did not
+ * reach end), then map next scatterlist entry.
+ * In case of such mapping error, s5p_aes_complete() should be called.
+ *
+ * If there is no more data in tx scatter list, call s5p_aes_complete()
+ * and schedule new tasklet.
+ */
status = SSS_READ(dev, FCINTSTAT);
if (status & SSS_FCINTSTAT_BRDMAINT)
- set_dma_rx = s5p_aes_rx(dev);
- if (status & SSS_FCINTSTAT_BTDMAINT)
- set_dma_tx = s5p_aes_tx(dev);
+ err_dma_rx = s5p_aes_rx(dev);
+
+ if (status & SSS_FCINTSTAT_BTDMAINT) {
+ if (sg_is_last(dev->sg_dst))
+ tx_end = true;
+ err_dma_tx = s5p_aes_tx(dev);
+ }
SSS_WRITE(dev, FCINTPEND, status);
- /*
- * Writing length of DMA block (either receiving or transmitting)
- * will start the operation immediately, so this should be done
- * at the end (even after clearing pending interrupts to not miss the
- * interrupt).
- */
- if (set_dma_tx)
- s5p_set_dma_outdata(dev, dev->sg_dst);
- if (set_dma_rx)
- s5p_set_dma_indata(dev, dev->sg_src);
+ if (err_dma_rx < 0) {
+ err = err_dma_rx;
+ goto error;
+ }
+ if (err_dma_tx < 0) {
+ err = err_dma_tx;
+ goto error;
+ }
+ if (tx_end) {
+ s5p_sg_done(dev);
+
+ spin_unlock_irqrestore(&dev->lock, flags);
+
+ s5p_aes_complete(dev, 0);
+ dev->busy = true;
+ tasklet_schedule(&dev->tasklet);
+ } else {
+ /*
+ * Writing length of DMA block (either receiving or
+ * transmitting) will start the operation immediately, so this
+ * should be done at the end (even after clearing pending
+ * interrupts to not miss the interrupt).
+ */
+ if (err_dma_tx == 1)
+ s5p_set_dma_outdata(dev, dev->sg_dst);
+ if (err_dma_rx == 1)
+ s5p_set_dma_indata(dev, dev->sg_src);
+
+ spin_unlock_irqrestore(&dev->lock, flags);
+ }
+
+ return IRQ_HANDLED;
+
+error:
+ s5p_sg_done(dev);
spin_unlock_irqrestore(&dev->lock, flags);
+ s5p_aes_complete(dev, err);
return IRQ_HANDLED;
}
@@ -597,8 +633,9 @@ static void s5p_aes_crypt_start(struct s5p_aes_dev *dev, unsigned long mode)
s5p_unset_indata(dev);
indata_error:
- s5p_aes_complete(dev, err);
+ s5p_sg_done(dev);
spin_unlock_irqrestore(&dev->lock, flags);
+ s5p_aes_complete(dev, err);
}
static void s5p_tasklet_cb(unsigned long data)
@@ -805,8 +842,9 @@ static int s5p_aes_probe(struct platform_device *pdev)
dev_warn(dev, "feed control interrupt is not available.\n");
goto err_irq;
}
- err = devm_request_irq(dev, pdata->irq_fc, s5p_aes_interrupt,
- IRQF_SHARED, pdev->name, pdev);
+ err = devm_request_threaded_irq(dev, pdata->irq_fc, NULL,
+ s5p_aes_interrupt, IRQF_ONESHOT,
+ pdev->name, pdev);
if (err < 0) {
dev_warn(dev, "feed control interrupt is not available.\n");
goto err_irq;
diff --git a/drivers/crypto/ux500/cryp/cryp.c b/drivers/crypto/ux500/cryp/cryp.c
index 43a0c8a..00a16ab 100644
--- a/drivers/crypto/ux500/cryp/cryp.c
+++ b/drivers/crypto/ux500/cryp/cryp.c
@@ -82,7 +82,7 @@ void cryp_activity(struct cryp_device_data *device_data,
void cryp_flush_inoutfifo(struct cryp_device_data *device_data)
{
/*
- * We always need to disble the hardware before trying to flush the
+ * We always need to disable the hardware before trying to flush the
* FIFO. This is something that isn't written in the design
* specification, but we have been informed by the hardware designers
* that this must be done.
diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index 8d9829f..80c6db279 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -427,6 +427,7 @@ static int __dax_dev_pte_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
int rc = VM_FAULT_SIGBUS;
phys_addr_t phys;
pfn_t pfn;
+ unsigned int fault_size = PAGE_SIZE;
if (check_vma(dax_dev, vmf->vma, __func__))
return VM_FAULT_SIGBUS;
@@ -437,9 +438,12 @@ static int __dax_dev_pte_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
return VM_FAULT_SIGBUS;
}
+ if (fault_size != dax_region->align)
+ return VM_FAULT_SIGBUS;
+
phys = pgoff_to_phys(dax_dev, vmf->pgoff, PAGE_SIZE);
if (phys == -1) {
- dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__,
+ dev_dbg(dev, "%s: pgoff_to_phys(%#lx) failed\n", __func__,
vmf->pgoff);
return VM_FAULT_SIGBUS;
}
@@ -464,6 +468,7 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
phys_addr_t phys;
pgoff_t pgoff;
pfn_t pfn;
+ unsigned int fault_size = PMD_SIZE;
if (check_vma(dax_dev, vmf->vma, __func__))
return VM_FAULT_SIGBUS;
@@ -480,10 +485,20 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
return VM_FAULT_SIGBUS;
}
+ if (fault_size < dax_region->align)
+ return VM_FAULT_SIGBUS;
+ else if (fault_size > dax_region->align)
+ return VM_FAULT_FALLBACK;
+
+ /* if we are outside of the VMA */
+ if (pmd_addr < vmf->vma->vm_start ||
+ (pmd_addr + PMD_SIZE) > vmf->vma->vm_end)
+ return VM_FAULT_SIGBUS;
+
pgoff = linear_page_index(vmf->vma, pmd_addr);
phys = pgoff_to_phys(dax_dev, pgoff, PMD_SIZE);
if (phys == -1) {
- dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__,
+ dev_dbg(dev, "%s: pgoff_to_phys(%#lx) failed\n", __func__,
pgoff);
return VM_FAULT_SIGBUS;
}
@@ -503,6 +518,8 @@ static int __dax_dev_pud_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
phys_addr_t phys;
pgoff_t pgoff;
pfn_t pfn;
+ unsigned int fault_size = PUD_SIZE;
+
if (check_vma(dax_dev, vmf->vma, __func__))
return VM_FAULT_SIGBUS;
@@ -519,10 +536,20 @@ static int __dax_dev_pud_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
return VM_FAULT_SIGBUS;
}
+ if (fault_size < dax_region->align)
+ return VM_FAULT_SIGBUS;
+ else if (fault_size > dax_region->align)
+ return VM_FAULT_FALLBACK;
+
+ /* if we are outside of the VMA */
+ if (pud_addr < vmf->vma->vm_start ||
+ (pud_addr + PUD_SIZE) > vmf->vma->vm_end)
+ return VM_FAULT_SIGBUS;
+
pgoff = linear_page_index(vmf->vma, pud_addr);
phys = pgoff_to_phys(dax_dev, pgoff, PUD_SIZE);
if (phys == -1) {
- dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__,
+ dev_dbg(dev, "%s: pgoff_to_phys(%#lx) failed\n", __func__,
pgoff);
return VM_FAULT_SIGBUS;
}
diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c
index e18dc59..6204cc3 100644
--- a/drivers/dma/bcm2835-dma.c
+++ b/drivers/dma/bcm2835-dma.c
@@ -251,8 +251,11 @@ static void bcm2835_dma_create_cb_set_length(
*/
/* have we filled in period_length yet? */
- if (*total_len + control_block->length < period_len)
+ if (*total_len + control_block->length < period_len) {
+ /* update number of bytes in this period so far */
+ *total_len += control_block->length;
return;
+ }
/* calculate the length that remains to reach period_length */
control_block->length = period_len - *total_len;
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 24e0221..d9118ec 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -1108,12 +1108,14 @@ static struct dmaengine_unmap_pool *__get_unmap_pool(int nr)
switch (order) {
case 0 ... 1:
return &unmap_pool[0];
+#if IS_ENABLED(CONFIG_DMA_ENGINE_RAID)
case 2 ... 4:
return &unmap_pool[1];
case 5 ... 7:
return &unmap_pool[2];
case 8:
return &unmap_pool[3];
+#endif
default:
BUG();
return NULL;
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 82d85cce..4773f28 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -43,6 +43,7 @@
config EDAC_DEBUG
bool "Debugging"
+ select DEBUG_FS
help
This turns on debugging information for the entire EDAC subsystem.
You do so by inserting edac_module with "edac_debug_level=x." Valid
@@ -259,6 +260,15 @@
Support for error detection and correction the Intel
Skylake server Integrated Memory Controllers.
+config EDAC_PND2
+ tristate "Intel Pondicherry2"
+ depends on EDAC_MM_EDAC && PCI && X86_64 && X86_MCE_INTEL
+ help
+ Support for error detection and correction on the Intel
+ Pondicherry2 Integrated Memory Controller. This SoC IP is
+ first used on the Apollo Lake platform and Denverton
+ micro-server but may appear on others in the future.
+
config EDAC_MPC85XX
tristate "Freescale MPC83xx / MPC85xx"
depends on EDAC_MM_EDAC && FSL_SOC
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index 88e472e..587107e 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -32,6 +32,7 @@
obj-$(CONFIG_EDAC_I7CORE) += i7core_edac.o
obj-$(CONFIG_EDAC_SBRIDGE) += sb_edac.o
obj-$(CONFIG_EDAC_SKX) += skx_edac.o
+obj-$(CONFIG_EDAC_PND2) += pnd2_edac.o
obj-$(CONFIG_EDAC_E7XXX) += e7xxx_edac.o
obj-$(CONFIG_EDAC_E752X) += e752x_edac.o
obj-$(CONFIG_EDAC_I82443BXGX) += i82443bxgx_edac.o
diff --git a/drivers/edac/i5000_edac.c b/drivers/edac/i5000_edac.c
index 1670d27..f683919 100644
--- a/drivers/edac/i5000_edac.c
+++ b/drivers/edac/i5000_edac.c
@@ -1293,7 +1293,7 @@ static int i5000_init_csrows(struct mem_ctl_info *mci)
dimm->mtype = MEM_FB_DDR2;
/* ask what device type on this row */
- if (MTR_DRAM_WIDTH(mtr))
+ if (MTR_DRAM_WIDTH(mtr) == 8)
dimm->dtype = DEV_X8;
else
dimm->dtype = DEV_X4;
diff --git a/drivers/edac/i5400_edac.c b/drivers/edac/i5400_edac.c
index abf6ef2..37a9ba7 100644
--- a/drivers/edac/i5400_edac.c
+++ b/drivers/edac/i5400_edac.c
@@ -1207,13 +1207,14 @@ static int i5400_init_dimms(struct mem_ctl_info *mci)
dimm->nr_pages = size_mb << 8;
dimm->grain = 8;
- dimm->dtype = MTR_DRAM_WIDTH(mtr) ? DEV_X8 : DEV_X4;
+ dimm->dtype = MTR_DRAM_WIDTH(mtr) == 8 ?
+ DEV_X8 : DEV_X4;
dimm->mtype = MEM_FB_DDR2;
/*
* The eccc mechanism is SDDC (aka SECC), with
* is similar to Chipkill.
*/
- dimm->edac_mode = MTR_DRAM_WIDTH(mtr) ?
+ dimm->edac_mode = MTR_DRAM_WIDTH(mtr) == 8 ?
EDAC_S8ECD8ED : EDAC_S4ECD4ED;
ndimms++;
}
diff --git a/drivers/edac/pnd2_edac.c b/drivers/edac/pnd2_edac.c
new file mode 100644
index 0000000..928e0db
--- /dev/null
+++ b/drivers/edac/pnd2_edac.c
@@ -0,0 +1,1546 @@
+/*
+ * Driver for Pondicherry2 memory controller.
+ *
+ * Copyright (c) 2016, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * [Derived from sb_edac.c]
+ *
+ * Translation of system physical addresses to DIMM addresses
+ * is a two stage process:
+ *
+ * First the Pondicherry 2 memory controller handles slice and channel interleaving
+ * in "sys2pmi()". This is (almost) completley common between platforms.
+ *
+ * Then a platform specific dunit (DIMM unit) completes the process to provide DIMM,
+ * rank, bank, row and column using the appropriate "dunit_ops" functions/parameters.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/pci_ids.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/edac.h>
+#include <linux/mmzone.h>
+#include <linux/smp.h>
+#include <linux/bitmap.h>
+#include <linux/math64.h>
+#include <linux/mod_devicetable.h>
+#include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
+#include <asm/processor.h>
+#include <asm/mce.h>
+
+#include "edac_mc.h"
+#include "edac_module.h"
+#include "pnd2_edac.h"
+
+#define APL_NUM_CHANNELS 4
+#define DNV_NUM_CHANNELS 2
+#define DNV_MAX_DIMMS 2 /* Max DIMMs per channel */
+
+enum type {
+ APL,
+ DNV, /* All requests go to PMI CH0 on each slice (CH1 disabled) */
+};
+
+struct dram_addr {
+ int chan;
+ int dimm;
+ int rank;
+ int bank;
+ int row;
+ int col;
+};
+
+struct pnd2_pvt {
+ int dimm_geom[APL_NUM_CHANNELS];
+ u64 tolm, tohm;
+};
+
+/*
+ * System address space is divided into multiple regions with
+ * different interleave rules in each. The as0/as1 regions
+ * have no interleaving at all. The as2 region is interleaved
+ * between two channels. The mot region is magic and may overlap
+ * other regions, with its interleave rules taking precedence.
+ * Addresses not in any of these regions are interleaved across
+ * all four channels.
+ */
+static struct region {
+ u64 base;
+ u64 limit;
+ u8 enabled;
+} mot, as0, as1, as2;
+
+static struct dunit_ops {
+ char *name;
+ enum type type;
+ int pmiaddr_shift;
+ int pmiidx_shift;
+ int channels;
+ int dimms_per_channel;
+ int (*rd_reg)(int port, int off, int op, void *data, size_t sz, char *name);
+ int (*get_registers)(void);
+ int (*check_ecc)(void);
+ void (*mk_region)(char *name, struct region *rp, void *asym);
+ void (*get_dimm_config)(struct mem_ctl_info *mci);
+ int (*pmi2mem)(struct mem_ctl_info *mci, u64 pmiaddr, u32 pmiidx,
+ struct dram_addr *daddr, char *msg);
+} *ops;
+
+static struct mem_ctl_info *pnd2_mci;
+
+#define PND2_MSG_SIZE 256
+
+/* Debug macros */
+#define pnd2_printk(level, fmt, arg...) \
+ edac_printk(level, "pnd2", fmt, ##arg)
+
+#define pnd2_mc_printk(mci, level, fmt, arg...) \
+ edac_mc_chipset_printk(mci, level, "pnd2", fmt, ##arg)
+
+#define MOT_CHAN_INTLV_BIT_1SLC_2CH 12
+#define MOT_CHAN_INTLV_BIT_2SLC_2CH 13
+#define SELECTOR_DISABLED (-1)
+#define _4GB (1ul << 32)
+
+#define PMI_ADDRESS_WIDTH 31
+#define PND_MAX_PHYS_BIT 39
+
+#define APL_ASYMSHIFT 28
+#define DNV_ASYMSHIFT 31
+#define CH_HASH_MASK_LSB 6
+#define SLICE_HASH_MASK_LSB 6
+#define MOT_SLC_INTLV_BIT 12
+#define LOG2_PMI_ADDR_GRANULARITY 5
+#define MOT_SHIFT 24
+
+#define GET_BITFIELD(v, lo, hi) (((v) & GENMASK_ULL(hi, lo)) >> (lo))
+#define U64_LSHIFT(val, s) ((u64)(val) << (s))
+
+#ifdef CONFIG_X86_INTEL_SBI_APL
+#include "linux/platform_data/sbi_apl.h"
+int sbi_send(int port, int off, int op, u32 *data)
+{
+ struct sbi_apl_message sbi_arg;
+ int ret, read = 0;
+
+ memset(&sbi_arg, 0, sizeof(sbi_arg));
+
+ if (op == 0 || op == 4 || op == 6)
+ read = 1;
+ else
+ sbi_arg.data = *data;
+
+ sbi_arg.opcode = op;
+ sbi_arg.port_address = port;
+ sbi_arg.register_offset = off;
+ ret = sbi_apl_commit(&sbi_arg);
+ if (ret || sbi_arg.status)
+ edac_dbg(2, "sbi_send status=%d ret=%d data=%x\n",
+ sbi_arg.status, ret, sbi_arg.data);
+
+ if (ret == 0)
+ ret = sbi_arg.status;
+
+ if (ret == 0 && read)
+ *data = sbi_arg.data;
+
+ return ret;
+}
+#else
+int sbi_send(int port, int off, int op, u32 *data)
+{
+ return -EUNATCH;
+}
+#endif
+
+static int apl_rd_reg(int port, int off, int op, void *data, size_t sz, char *name)
+{
+ int ret = 0;
+
+ edac_dbg(2, "Read %s port=%x off=%x op=%x\n", name, port, off, op);
+ switch (sz) {
+ case 8:
+ ret = sbi_send(port, off + 4, op, (u32 *)(data + 4));
+ case 4:
+ ret = sbi_send(port, off, op, (u32 *)data);
+ pnd2_printk(KERN_DEBUG, "%s=%x%08x ret=%d\n", name,
+ sz == 8 ? *((u32 *)(data + 4)) : 0, *((u32 *)data), ret);
+ break;
+ }
+
+ return ret;
+}
+
+static u64 get_mem_ctrl_hub_base_addr(void)
+{
+ struct b_cr_mchbar_lo_pci lo;
+ struct b_cr_mchbar_hi_pci hi;
+ struct pci_dev *pdev;
+
+ pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x1980, NULL);
+ if (pdev) {
+ pci_read_config_dword(pdev, 0x48, (u32 *)&lo);
+ pci_read_config_dword(pdev, 0x4c, (u32 *)&hi);
+ pci_dev_put(pdev);
+ } else {
+ return 0;
+ }
+
+ if (!lo.enable) {
+ edac_dbg(2, "MMIO via memory controller hub base address is disabled!\n");
+ return 0;
+ }
+
+ return U64_LSHIFT(hi.base, 32) | U64_LSHIFT(lo.base, 15);
+}
+
+static u64 get_sideband_reg_base_addr(void)
+{
+ struct pci_dev *pdev;
+ u32 hi, lo;
+
+ pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x19dd, NULL);
+ if (pdev) {
+ pci_read_config_dword(pdev, 0x10, &lo);
+ pci_read_config_dword(pdev, 0x14, &hi);
+ pci_dev_put(pdev);
+ return (U64_LSHIFT(hi, 32) | U64_LSHIFT(lo, 0));
+ } else {
+ return 0xfd000000;
+ }
+}
+
+static int dnv_rd_reg(int port, int off, int op, void *data, size_t sz, char *name)
+{
+ struct pci_dev *pdev;
+ char *base;
+ u64 addr;
+
+ if (op == 4) {
+ pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x1980, NULL);
+ if (!pdev)
+ return -ENODEV;
+
+ pci_read_config_dword(pdev, off, data);
+ pci_dev_put(pdev);
+ } else {
+ /* MMIO via memory controller hub base address */
+ if (op == 0 && port == 0x4c) {
+ addr = get_mem_ctrl_hub_base_addr();
+ if (!addr)
+ return -ENODEV;
+ } else {
+ /* MMIO via sideband register base address */
+ addr = get_sideband_reg_base_addr();
+ if (!addr)
+ return -ENODEV;
+ addr += (port << 16);
+ }
+
+ base = ioremap((resource_size_t)addr, 0x10000);
+ if (!base)
+ return -ENODEV;
+
+ if (sz == 8)
+ *(u32 *)(data + 4) = *(u32 *)(base + off + 4);
+ *(u32 *)data = *(u32 *)(base + off);
+
+ iounmap(base);
+ }
+
+ edac_dbg(2, "Read %s=%.8x_%.8x\n", name,
+ (sz == 8) ? *(u32 *)(data + 4) : 0, *(u32 *)data);
+
+ return 0;
+}
+
+#define RD_REGP(regp, regname, port) \
+ ops->rd_reg(port, \
+ regname##_offset, \
+ regname##_r_opcode, \
+ regp, sizeof(struct regname), \
+ #regname)
+
+#define RD_REG(regp, regname) \
+ ops->rd_reg(regname ## _port, \
+ regname##_offset, \
+ regname##_r_opcode, \
+ regp, sizeof(struct regname), \
+ #regname)
+
+static u64 top_lm, top_hm;
+static bool two_slices;
+static bool two_channels; /* Both PMI channels in one slice enabled */
+
+static u8 sym_chan_mask;
+static u8 asym_chan_mask;
+static u8 chan_mask;
+
+static int slice_selector = -1;
+static int chan_selector = -1;
+static u64 slice_hash_mask;
+static u64 chan_hash_mask;
+
+static void mk_region(char *name, struct region *rp, u64 base, u64 limit)
+{
+ rp->enabled = 1;
+ rp->base = base;
+ rp->limit = limit;
+ edac_dbg(2, "Region:%s [%llx, %llx]\n", name, base, limit);
+}
+
+static void mk_region_mask(char *name, struct region *rp, u64 base, u64 mask)
+{
+ if (mask == 0) {
+ pr_info(FW_BUG "MOT mask cannot be zero\n");
+ return;
+ }
+ if (mask != GENMASK_ULL(PND_MAX_PHYS_BIT, __ffs(mask))) {
+ pr_info(FW_BUG "MOT mask not power of two\n");
+ return;
+ }
+ if (base & ~mask) {
+ pr_info(FW_BUG "MOT region base/mask alignment error\n");
+ return;
+ }
+ rp->base = base;
+ rp->limit = (base | ~mask) & GENMASK_ULL(PND_MAX_PHYS_BIT, 0);
+ rp->enabled = 1;
+ edac_dbg(2, "Region:%s [%llx, %llx]\n", name, base, rp->limit);
+}
+
+static bool in_region(struct region *rp, u64 addr)
+{
+ if (!rp->enabled)
+ return false;
+
+ return rp->base <= addr && addr <= rp->limit;
+}
+
+static int gen_sym_mask(struct b_cr_slice_channel_hash *p)
+{
+ int mask = 0;
+
+ if (!p->slice_0_mem_disabled)
+ mask |= p->sym_slice0_channel_enabled;
+
+ if (!p->slice_1_disabled)
+ mask |= p->sym_slice1_channel_enabled << 2;
+
+ if (p->ch_1_disabled || p->enable_pmi_dual_data_mode)
+ mask &= 0x5;
+
+ return mask;
+}
+
+static int gen_asym_mask(struct b_cr_slice_channel_hash *p,
+ struct b_cr_asym_mem_region0_mchbar *as0,
+ struct b_cr_asym_mem_region1_mchbar *as1,
+ struct b_cr_asym_2way_mem_region_mchbar *as2way)
+{
+ const int intlv[] = { 0x5, 0xA, 0x3, 0xC };
+ int mask = 0;
+
+ if (as2way->asym_2way_interleave_enable)
+ mask = intlv[as2way->asym_2way_intlv_mode];
+ if (as0->slice0_asym_enable)
+ mask |= (1 << as0->slice0_asym_channel_select);
+ if (as1->slice1_asym_enable)
+ mask |= (4 << as1->slice1_asym_channel_select);
+ if (p->slice_0_mem_disabled)
+ mask &= 0xc;
+ if (p->slice_1_disabled)
+ mask &= 0x3;
+ if (p->ch_1_disabled || p->enable_pmi_dual_data_mode)
+ mask &= 0x5;
+
+ return mask;
+}
+
+static struct b_cr_tolud_pci tolud;
+static struct b_cr_touud_lo_pci touud_lo;
+static struct b_cr_touud_hi_pci touud_hi;
+static struct b_cr_asym_mem_region0_mchbar asym0;
+static struct b_cr_asym_mem_region1_mchbar asym1;
+static struct b_cr_asym_2way_mem_region_mchbar asym_2way;
+static struct b_cr_mot_out_base_mchbar mot_base;
+static struct b_cr_mot_out_mask_mchbar mot_mask;
+static struct b_cr_slice_channel_hash chash;
+
+/* Apollo Lake dunit */
+/*
+ * Validated on board with just two DIMMs in the [0] and [2] positions
+ * in this array. Other port number matches documentation, but caution
+ * advised.
+ */
+static const int apl_dports[APL_NUM_CHANNELS] = { 0x18, 0x10, 0x11, 0x19 };
+static struct d_cr_drp0 drp0[APL_NUM_CHANNELS];
+
+/* Denverton dunit */
+static const int dnv_dports[DNV_NUM_CHANNELS] = { 0x10, 0x12 };
+static struct d_cr_dsch dsch;
+static struct d_cr_ecc_ctrl ecc_ctrl[DNV_NUM_CHANNELS];
+static struct d_cr_drp drp[DNV_NUM_CHANNELS];
+static struct d_cr_dmap dmap[DNV_NUM_CHANNELS];
+static struct d_cr_dmap1 dmap1[DNV_NUM_CHANNELS];
+static struct d_cr_dmap2 dmap2[DNV_NUM_CHANNELS];
+static struct d_cr_dmap3 dmap3[DNV_NUM_CHANNELS];
+static struct d_cr_dmap4 dmap4[DNV_NUM_CHANNELS];
+static struct d_cr_dmap5 dmap5[DNV_NUM_CHANNELS];
+
+static void apl_mk_region(char *name, struct region *rp, void *asym)
+{
+ struct b_cr_asym_mem_region0_mchbar *a = asym;
+
+ mk_region(name, rp,
+ U64_LSHIFT(a->slice0_asym_base, APL_ASYMSHIFT),
+ U64_LSHIFT(a->slice0_asym_limit, APL_ASYMSHIFT) +
+ GENMASK_ULL(APL_ASYMSHIFT - 1, 0));
+}
+
+static void dnv_mk_region(char *name, struct region *rp, void *asym)
+{
+ struct b_cr_asym_mem_region_denverton *a = asym;
+
+ mk_region(name, rp,
+ U64_LSHIFT(a->slice_asym_base, DNV_ASYMSHIFT),
+ U64_LSHIFT(a->slice_asym_limit, DNV_ASYMSHIFT) +
+ GENMASK_ULL(DNV_ASYMSHIFT - 1, 0));
+}
+
+static int apl_get_registers(void)
+{
+ int i;
+
+ if (RD_REG(&asym_2way, b_cr_asym_2way_mem_region_mchbar))
+ return -ENODEV;
+
+ for (i = 0; i < APL_NUM_CHANNELS; i++)
+ if (RD_REGP(&drp0[i], d_cr_drp0, apl_dports[i]))
+ return -ENODEV;
+
+ return 0;
+}
+
+static int dnv_get_registers(void)
+{
+ int i;
+
+ if (RD_REG(&dsch, d_cr_dsch))
+ return -ENODEV;
+
+ for (i = 0; i < DNV_NUM_CHANNELS; i++)
+ if (RD_REGP(&ecc_ctrl[i], d_cr_ecc_ctrl, dnv_dports[i]) ||
+ RD_REGP(&drp[i], d_cr_drp, dnv_dports[i]) ||
+ RD_REGP(&dmap[i], d_cr_dmap, dnv_dports[i]) ||
+ RD_REGP(&dmap1[i], d_cr_dmap1, dnv_dports[i]) ||
+ RD_REGP(&dmap2[i], d_cr_dmap2, dnv_dports[i]) ||
+ RD_REGP(&dmap3[i], d_cr_dmap3, dnv_dports[i]) ||
+ RD_REGP(&dmap4[i], d_cr_dmap4, dnv_dports[i]) ||
+ RD_REGP(&dmap5[i], d_cr_dmap5, dnv_dports[i]))
+ return -ENODEV;
+
+ return 0;
+}
+
+/*
+ * Read all the h/w config registers once here (they don't
+ * change at run time. Figure out which address ranges have
+ * which interleave characteristics.
+ */
+static int get_registers(void)
+{
+ const int intlv[] = { 10, 11, 12, 12 };
+
+ if (RD_REG(&tolud, b_cr_tolud_pci) ||
+ RD_REG(&touud_lo, b_cr_touud_lo_pci) ||
+ RD_REG(&touud_hi, b_cr_touud_hi_pci) ||
+ RD_REG(&asym0, b_cr_asym_mem_region0_mchbar) ||
+ RD_REG(&asym1, b_cr_asym_mem_region1_mchbar) ||
+ RD_REG(&mot_base, b_cr_mot_out_base_mchbar) ||
+ RD_REG(&mot_mask, b_cr_mot_out_mask_mchbar) ||
+ RD_REG(&chash, b_cr_slice_channel_hash))
+ return -ENODEV;
+
+ if (ops->get_registers())
+ return -ENODEV;
+
+ if (ops->type == DNV) {
+ /* PMI channel idx (always 0) for asymmetric region */
+ asym0.slice0_asym_channel_select = 0;
+ asym1.slice1_asym_channel_select = 0;
+ /* PMI channel bitmap (always 1) for symmetric region */
+ chash.sym_slice0_channel_enabled = 0x1;
+ chash.sym_slice1_channel_enabled = 0x1;
+ }
+
+ if (asym0.slice0_asym_enable)
+ ops->mk_region("as0", &as0, &asym0);
+
+ if (asym1.slice1_asym_enable)
+ ops->mk_region("as1", &as1, &asym1);
+
+ if (asym_2way.asym_2way_interleave_enable) {
+ mk_region("as2way", &as2,
+ U64_LSHIFT(asym_2way.asym_2way_base, APL_ASYMSHIFT),
+ U64_LSHIFT(asym_2way.asym_2way_limit, APL_ASYMSHIFT) +
+ GENMASK_ULL(APL_ASYMSHIFT - 1, 0));
+ }
+
+ if (mot_base.imr_en) {
+ mk_region_mask("mot", &mot,
+ U64_LSHIFT(mot_base.mot_out_base, MOT_SHIFT),
+ U64_LSHIFT(mot_mask.mot_out_mask, MOT_SHIFT));
+ }
+
+ top_lm = U64_LSHIFT(tolud.tolud, 20);
+ top_hm = U64_LSHIFT(touud_hi.touud, 32) | U64_LSHIFT(touud_lo.touud, 20);
+
+ two_slices = !chash.slice_1_disabled &&
+ !chash.slice_0_mem_disabled &&
+ (chash.sym_slice0_channel_enabled != 0) &&
+ (chash.sym_slice1_channel_enabled != 0);
+ two_channels = !chash.ch_1_disabled &&
+ !chash.enable_pmi_dual_data_mode &&
+ ((chash.sym_slice0_channel_enabled == 3) ||
+ (chash.sym_slice1_channel_enabled == 3));
+
+ sym_chan_mask = gen_sym_mask(&chash);
+ asym_chan_mask = gen_asym_mask(&chash, &asym0, &asym1, &asym_2way);
+ chan_mask = sym_chan_mask | asym_chan_mask;
+
+ if (two_slices && !two_channels) {
+ if (chash.hvm_mode)
+ slice_selector = 29;
+ else
+ slice_selector = intlv[chash.interleave_mode];
+ } else if (!two_slices && two_channels) {
+ if (chash.hvm_mode)
+ chan_selector = 29;
+ else
+ chan_selector = intlv[chash.interleave_mode];
+ } else if (two_slices && two_channels) {
+ if (chash.hvm_mode) {
+ slice_selector = 29;
+ chan_selector = 30;
+ } else {
+ slice_selector = intlv[chash.interleave_mode];
+ chan_selector = intlv[chash.interleave_mode] + 1;
+ }
+ }
+
+ if (two_slices) {
+ if (!chash.hvm_mode)
+ slice_hash_mask = chash.slice_hash_mask << SLICE_HASH_MASK_LSB;
+ if (!two_channels)
+ slice_hash_mask |= BIT_ULL(slice_selector);
+ }
+
+ if (two_channels) {
+ if (!chash.hvm_mode)
+ chan_hash_mask = chash.ch_hash_mask << CH_HASH_MASK_LSB;
+ if (!two_slices)
+ chan_hash_mask |= BIT_ULL(chan_selector);
+ }
+
+ return 0;
+}
+
+/* Get a contiguous memory address (remove the MMIO gap) */
+static u64 remove_mmio_gap(u64 sys)
+{
+ return (sys < _4GB) ? sys : sys - (_4GB - top_lm);
+}
+
+/* Squeeze out one address bit, shift upper part down to fill gap */
+static void remove_addr_bit(u64 *addr, int bitidx)
+{
+ u64 mask;
+
+ if (bitidx == -1)
+ return;
+
+ mask = (1ull << bitidx) - 1;
+ *addr = ((*addr >> 1) & ~mask) | (*addr & mask);
+}
+
+/* XOR all the bits from addr specified in mask */
+static int hash_by_mask(u64 addr, u64 mask)
+{
+ u64 result = addr & mask;
+
+ result = (result >> 32) ^ result;
+ result = (result >> 16) ^ result;
+ result = (result >> 8) ^ result;
+ result = (result >> 4) ^ result;
+ result = (result >> 2) ^ result;
+ result = (result >> 1) ^ result;
+
+ return (int)result & 1;
+}
+
+/*
+ * First stage decode. Take the system address and figure out which
+ * second stage will deal with it based on interleave modes.
+ */
+static int sys2pmi(const u64 addr, u32 *pmiidx, u64 *pmiaddr, char *msg)
+{
+ u64 contig_addr, contig_base, contig_offset, contig_base_adj;
+ int mot_intlv_bit = two_slices ? MOT_CHAN_INTLV_BIT_2SLC_2CH :
+ MOT_CHAN_INTLV_BIT_1SLC_2CH;
+ int slice_intlv_bit_rm = SELECTOR_DISABLED;
+ int chan_intlv_bit_rm = SELECTOR_DISABLED;
+ /* Determine if address is in the MOT region. */
+ bool mot_hit = in_region(&mot, addr);
+ /* Calculate the number of symmetric regions enabled. */
+ int sym_channels = hweight8(sym_chan_mask);
+
+ /*
+ * The amount we need to shift the asym base can be determined by the
+ * number of enabled symmetric channels.
+ * NOTE: This can only work because symmetric memory is not supposed
+ * to do a 3-way interleave.
+ */
+ int sym_chan_shift = sym_channels >> 1;
+
+ /* Give up if address is out of range, or in MMIO gap */
+ if (addr >= (1ul << PND_MAX_PHYS_BIT) ||
+ (addr >= top_lm && addr < _4GB) || addr >= top_hm) {
+ snprintf(msg, PND2_MSG_SIZE, "Error address 0x%llx is not DRAM", addr);
+ return -EINVAL;
+ }
+
+ /* Get a contiguous memory address (remove the MMIO gap) */
+ contig_addr = remove_mmio_gap(addr);
+
+ if (in_region(&as0, addr)) {
+ *pmiidx = asym0.slice0_asym_channel_select;
+
+ contig_base = remove_mmio_gap(as0.base);
+ contig_offset = contig_addr - contig_base;
+ contig_base_adj = (contig_base >> sym_chan_shift) *
+ ((chash.sym_slice0_channel_enabled >> (*pmiidx & 1)) & 1);
+ contig_addr = contig_offset + ((sym_channels > 0) ? contig_base_adj : 0ull);
+ } else if (in_region(&as1, addr)) {
+ *pmiidx = 2u + asym1.slice1_asym_channel_select;
+
+ contig_base = remove_mmio_gap(as1.base);
+ contig_offset = contig_addr - contig_base;
+ contig_base_adj = (contig_base >> sym_chan_shift) *
+ ((chash.sym_slice1_channel_enabled >> (*pmiidx & 1)) & 1);
+ contig_addr = contig_offset + ((sym_channels > 0) ? contig_base_adj : 0ull);
+ } else if (in_region(&as2, addr) && (asym_2way.asym_2way_intlv_mode == 0x3ul)) {
+ bool channel1;
+
+ mot_intlv_bit = MOT_CHAN_INTLV_BIT_1SLC_2CH;
+ *pmiidx = (asym_2way.asym_2way_intlv_mode & 1) << 1;
+ channel1 = mot_hit ? ((bool)((addr >> mot_intlv_bit) & 1)) :
+ hash_by_mask(contig_addr, chan_hash_mask);
+ *pmiidx |= (u32)channel1;
+
+ contig_base = remove_mmio_gap(as2.base);
+ chan_intlv_bit_rm = mot_hit ? mot_intlv_bit : chan_selector;
+ contig_offset = contig_addr - contig_base;
+ remove_addr_bit(&contig_offset, chan_intlv_bit_rm);
+ contig_addr = (contig_base >> sym_chan_shift) + contig_offset;
+ } else {
+ /* Otherwise we're in normal, boring symmetric mode. */
+ *pmiidx = 0u;
+
+ if (two_slices) {
+ bool slice1;
+
+ if (mot_hit) {
+ slice_intlv_bit_rm = MOT_SLC_INTLV_BIT;
+ slice1 = (addr >> MOT_SLC_INTLV_BIT) & 1;
+ } else {
+ slice_intlv_bit_rm = slice_selector;
+ slice1 = hash_by_mask(addr, slice_hash_mask);
+ }
+
+ *pmiidx = (u32)slice1 << 1;
+ }
+
+ if (two_channels) {
+ bool channel1;
+
+ mot_intlv_bit = two_slices ? MOT_CHAN_INTLV_BIT_2SLC_2CH :
+ MOT_CHAN_INTLV_BIT_1SLC_2CH;
+
+ if (mot_hit) {
+ chan_intlv_bit_rm = mot_intlv_bit;
+ channel1 = (addr >> mot_intlv_bit) & 1;
+ } else {
+ chan_intlv_bit_rm = chan_selector;
+ channel1 = hash_by_mask(contig_addr, chan_hash_mask);
+ }
+
+ *pmiidx |= (u32)channel1;
+ }
+ }
+
+ /* Remove the chan_selector bit first */
+ remove_addr_bit(&contig_addr, chan_intlv_bit_rm);
+ /* Remove the slice bit (we remove it second because it must be lower */
+ remove_addr_bit(&contig_addr, slice_intlv_bit_rm);
+ *pmiaddr = contig_addr;
+
+ return 0;
+}
+
+/* Translate PMI address to memory (rank, row, bank, column) */
+#define C(n) (0x10 | (n)) /* column */
+#define B(n) (0x20 | (n)) /* bank */
+#define R(n) (0x40 | (n)) /* row */
+#define RS (0x80) /* rank */
+
+/* addrdec values */
+#define AMAP_1KB 0
+#define AMAP_2KB 1
+#define AMAP_4KB 2
+#define AMAP_RSVD 3
+
+/* dden values */
+#define DEN_4Gb 0
+#define DEN_8Gb 2
+
+/* dwid values */
+#define X8 0
+#define X16 1
+
+static struct dimm_geometry {
+ u8 addrdec;
+ u8 dden;
+ u8 dwid;
+ u8 rowbits, colbits;
+ u16 bits[PMI_ADDRESS_WIDTH];
+} dimms[] = {
+ {
+ .addrdec = AMAP_1KB, .dden = DEN_4Gb, .dwid = X16,
+ .rowbits = 15, .colbits = 10,
+ .bits = {
+ C(2), C(3), C(4), C(5), C(6), B(0), B(1), B(2), R(0),
+ R(1), R(2), R(3), R(4), R(5), R(6), R(7), R(8), R(9),
+ R(10), C(7), C(8), C(9), R(11), RS, R(12), R(13), R(14),
+ 0, 0, 0, 0
+ }
+ },
+ {
+ .addrdec = AMAP_1KB, .dden = DEN_4Gb, .dwid = X8,
+ .rowbits = 16, .colbits = 10,
+ .bits = {
+ C(2), C(3), C(4), C(5), C(6), B(0), B(1), B(2), R(0),
+ R(1), R(2), R(3), R(4), R(5), R(6), R(7), R(8), R(9),
+ R(10), C(7), C(8), C(9), R(11), RS, R(12), R(13), R(14),
+ R(15), 0, 0, 0
+ }
+ },
+ {
+ .addrdec = AMAP_1KB, .dden = DEN_8Gb, .dwid = X16,
+ .rowbits = 16, .colbits = 10,
+ .bits = {
+ C(2), C(3), C(4), C(5), C(6), B(0), B(1), B(2), R(0),
+ R(1), R(2), R(3), R(4), R(5), R(6), R(7), R(8), R(9),
+ R(10), C(7), C(8), C(9), R(11), RS, R(12), R(13), R(14),
+ R(15), 0, 0, 0
+ }
+ },
+ {
+ .addrdec = AMAP_1KB, .dden = DEN_8Gb, .dwid = X8,
+ .rowbits = 16, .colbits = 11,
+ .bits = {
+ C(2), C(3), C(4), C(5), C(6), B(0), B(1), B(2), R(0),
+ R(1), R(2), R(3), R(4), R(5), R(6), R(7), R(8), R(9),
+ R(10), C(7), C(8), C(9), R(11), RS, C(11), R(12), R(13),
+ R(14), R(15), 0, 0
+ }
+ },
+ {
+ .addrdec = AMAP_2KB, .dden = DEN_4Gb, .dwid = X16,
+ .rowbits = 15, .colbits = 10,
+ .bits = {
+ C(2), C(3), C(4), C(5), C(6), C(7), B(0), B(1), B(2),
+ R(0), R(1), R(2), R(3), R(4), R(5), R(6), R(7), R(8),
+ R(9), R(10), C(8), C(9), R(11), RS, R(12), R(13), R(14),
+ 0, 0, 0, 0
+ }
+ },
+ {
+ .addrdec = AMAP_2KB, .dden = DEN_4Gb, .dwid = X8,
+ .rowbits = 16, .colbits = 10,
+ .bits = {
+ C(2), C(3), C(4), C(5), C(6), C(7), B(0), B(1), B(2),
+ R(0), R(1), R(2), R(3), R(4), R(5), R(6), R(7), R(8),
+ R(9), R(10), C(8), C(9), R(11), RS, R(12), R(13), R(14),
+ R(15), 0, 0, 0
+ }
+ },
+ {
+ .addrdec = AMAP_2KB, .dden = DEN_8Gb, .dwid = X16,
+ .rowbits = 16, .colbits = 10,
+ .bits = {
+ C(2), C(3), C(4), C(5), C(6), C(7), B(0), B(1), B(2),
+ R(0), R(1), R(2), R(3), R(4), R(5), R(6), R(7), R(8),
+ R(9), R(10), C(8), C(9), R(11), RS, R(12), R(13), R(14),
+ R(15), 0, 0, 0
+ }
+ },
+ {
+ .addrdec = AMAP_2KB, .dden = DEN_8Gb, .dwid = X8,
+ .rowbits = 16, .colbits = 11,
+ .bits = {
+ C(2), C(3), C(4), C(5), C(6), C(7), B(0), B(1), B(2),
+ R(0), R(1), R(2), R(3), R(4), R(5), R(6), R(7), R(8),
+ R(9), R(10), C(8), C(9), R(11), RS, C(11), R(12), R(13),
+ R(14), R(15), 0, 0
+ }
+ },
+ {
+ .addrdec = AMAP_4KB, .dden = DEN_4Gb, .dwid = X16,
+ .rowbits = 15, .colbits = 10,
+ .bits = {
+ C(2), C(3), C(4), C(5), C(6), C(7), C(8), B(0), B(1),
+ B(2), R(0), R(1), R(2), R(3), R(4), R(5), R(6), R(7),
+ R(8), R(9), R(10), C(9), R(11), RS, R(12), R(13), R(14),
+ 0, 0, 0, 0
+ }
+ },
+ {
+ .addrdec = AMAP_4KB, .dden = DEN_4Gb, .dwid = X8,
+ .rowbits = 16, .colbits = 10,
+ .bits = {
+ C(2), C(3), C(4), C(5), C(6), C(7), C(8), B(0), B(1),
+ B(2), R(0), R(1), R(2), R(3), R(4), R(5), R(6), R(7),
+ R(8), R(9), R(10), C(9), R(11), RS, R(12), R(13), R(14),
+ R(15), 0, 0, 0
+ }
+ },
+ {
+ .addrdec = AMAP_4KB, .dden = DEN_8Gb, .dwid = X16,
+ .rowbits = 16, .colbits = 10,
+ .bits = {
+ C(2), C(3), C(4), C(5), C(6), C(7), C(8), B(0), B(1),
+ B(2), R(0), R(1), R(2), R(3), R(4), R(5), R(6), R(7),
+ R(8), R(9), R(10), C(9), R(11), RS, R(12), R(13), R(14),
+ R(15), 0, 0, 0
+ }
+ },
+ {
+ .addrdec = AMAP_4KB, .dden = DEN_8Gb, .dwid = X8,
+ .rowbits = 16, .colbits = 11,
+ .bits = {
+ C(2), C(3), C(4), C(5), C(6), C(7), C(8), B(0), B(1),
+ B(2), R(0), R(1), R(2), R(3), R(4), R(5), R(6), R(7),
+ R(8), R(9), R(10), C(9), R(11), RS, C(11), R(12), R(13),
+ R(14), R(15), 0, 0
+ }
+ }
+};
+
+static int bank_hash(u64 pmiaddr, int idx, int shft)
+{
+ int bhash = 0;
+
+ switch (idx) {
+ case 0:
+ bhash ^= ((pmiaddr >> (12 + shft)) ^ (pmiaddr >> (9 + shft))) & 1;
+ break;
+ case 1:
+ bhash ^= (((pmiaddr >> (10 + shft)) ^ (pmiaddr >> (8 + shft))) & 1) << 1;
+ bhash ^= ((pmiaddr >> 22) & 1) << 1;
+ break;
+ case 2:
+ bhash ^= (((pmiaddr >> (13 + shft)) ^ (pmiaddr >> (11 + shft))) & 1) << 2;
+ break;
+ }
+
+ return bhash;
+}
+
+static int rank_hash(u64 pmiaddr)
+{
+ return ((pmiaddr >> 16) ^ (pmiaddr >> 10)) & 1;
+}
+
+/* Second stage decode. Compute rank, bank, row & column. */
+static int apl_pmi2mem(struct mem_ctl_info *mci, u64 pmiaddr, u32 pmiidx,
+ struct dram_addr *daddr, char *msg)
+{
+ struct d_cr_drp0 *cr_drp0 = &drp0[pmiidx];
+ struct pnd2_pvt *pvt = mci->pvt_info;
+ int g = pvt->dimm_geom[pmiidx];
+ struct dimm_geometry *d = &dimms[g];
+ int column = 0, bank = 0, row = 0, rank = 0;
+ int i, idx, type, skiprs = 0;
+
+ for (i = 0; i < PMI_ADDRESS_WIDTH; i++) {
+ int bit = (pmiaddr >> i) & 1;
+
+ if (i + skiprs >= PMI_ADDRESS_WIDTH) {
+ snprintf(msg, PND2_MSG_SIZE, "Bad dimm_geometry[] table\n");
+ return -EINVAL;
+ }
+
+ type = d->bits[i + skiprs] & ~0xf;
+ idx = d->bits[i + skiprs] & 0xf;
+
+ /*
+ * On single rank DIMMs ignore the rank select bit
+ * and shift remainder of "bits[]" down one place.
+ */
+ if (type == RS && (cr_drp0->rken0 + cr_drp0->rken1) == 1) {
+ skiprs = 1;
+ type = d->bits[i + skiprs] & ~0xf;
+ idx = d->bits[i + skiprs] & 0xf;
+ }
+
+ switch (type) {
+ case C(0):
+ column |= (bit << idx);
+ break;
+ case B(0):
+ bank |= (bit << idx);
+ if (cr_drp0->bahen)
+ bank ^= bank_hash(pmiaddr, idx, d->addrdec);
+ break;
+ case R(0):
+ row |= (bit << idx);
+ break;
+ case RS:
+ rank = bit;
+ if (cr_drp0->rsien)
+ rank ^= rank_hash(pmiaddr);
+ break;
+ default:
+ if (bit) {
+ snprintf(msg, PND2_MSG_SIZE, "Bad translation\n");
+ return -EINVAL;
+ }
+ goto done;
+ }
+ }
+
+done:
+ daddr->col = column;
+ daddr->bank = bank;
+ daddr->row = row;
+ daddr->rank = rank;
+ daddr->dimm = 0;
+
+ return 0;
+}
+
+/* Pluck bit "in" from pmiaddr and return value shifted to bit "out" */
+#define dnv_get_bit(pmi, in, out) ((int)(((pmi) >> (in)) & 1u) << (out))
+
+static int dnv_pmi2mem(struct mem_ctl_info *mci, u64 pmiaddr, u32 pmiidx,
+ struct dram_addr *daddr, char *msg)
+{
+ /* Rank 0 or 1 */
+ daddr->rank = dnv_get_bit(pmiaddr, dmap[pmiidx].rs0 + 13, 0);
+ /* Rank 2 or 3 */
+ daddr->rank |= dnv_get_bit(pmiaddr, dmap[pmiidx].rs1 + 13, 1);
+
+ /*
+ * Normally ranks 0,1 are DIMM0, and 2,3 are DIMM1, but we
+ * flip them if DIMM1 is larger than DIMM0.
+ */
+ daddr->dimm = (daddr->rank >= 2) ^ drp[pmiidx].dimmflip;
+
+ daddr->bank = dnv_get_bit(pmiaddr, dmap[pmiidx].ba0 + 6, 0);
+ daddr->bank |= dnv_get_bit(pmiaddr, dmap[pmiidx].ba1 + 6, 1);
+ daddr->bank |= dnv_get_bit(pmiaddr, dmap[pmiidx].bg0 + 6, 2);
+ if (dsch.ddr4en)
+ daddr->bank |= dnv_get_bit(pmiaddr, dmap[pmiidx].bg1 + 6, 3);
+ if (dmap1[pmiidx].bxor) {
+ if (dsch.ddr4en) {
+ daddr->bank ^= dnv_get_bit(pmiaddr, dmap3[pmiidx].row6 + 6, 0);
+ daddr->bank ^= dnv_get_bit(pmiaddr, dmap3[pmiidx].row7 + 6, 1);
+ if (dsch.chan_width == 0)
+ /* 64/72 bit dram channel width */
+ daddr->bank ^= dnv_get_bit(pmiaddr, dmap5[pmiidx].ca3 + 6, 2);
+ else
+ /* 32/40 bit dram channel width */
+ daddr->bank ^= dnv_get_bit(pmiaddr, dmap5[pmiidx].ca4 + 6, 2);
+ daddr->bank ^= dnv_get_bit(pmiaddr, dmap2[pmiidx].row2 + 6, 3);
+ } else {
+ daddr->bank ^= dnv_get_bit(pmiaddr, dmap2[pmiidx].row2 + 6, 0);
+ daddr->bank ^= dnv_get_bit(pmiaddr, dmap3[pmiidx].row6 + 6, 1);
+ if (dsch.chan_width == 0)
+ daddr->bank ^= dnv_get_bit(pmiaddr, dmap5[pmiidx].ca3 + 6, 2);
+ else
+ daddr->bank ^= dnv_get_bit(pmiaddr, dmap5[pmiidx].ca4 + 6, 2);
+ }
+ }
+
+ daddr->row = dnv_get_bit(pmiaddr, dmap2[pmiidx].row0 + 6, 0);
+ daddr->row |= dnv_get_bit(pmiaddr, dmap2[pmiidx].row1 + 6, 1);
+ daddr->row |= dnv_get_bit(pmiaddr, dmap2[pmiidx].row2 + 6, 2);
+ daddr->row |= dnv_get_bit(pmiaddr, dmap2[pmiidx].row3 + 6, 3);
+ daddr->row |= dnv_get_bit(pmiaddr, dmap2[pmiidx].row4 + 6, 4);
+ daddr->row |= dnv_get_bit(pmiaddr, dmap2[pmiidx].row5 + 6, 5);
+ daddr->row |= dnv_get_bit(pmiaddr, dmap3[pmiidx].row6 + 6, 6);
+ daddr->row |= dnv_get_bit(pmiaddr, dmap3[pmiidx].row7 + 6, 7);
+ daddr->row |= dnv_get_bit(pmiaddr, dmap3[pmiidx].row8 + 6, 8);
+ daddr->row |= dnv_get_bit(pmiaddr, dmap3[pmiidx].row9 + 6, 9);
+ daddr->row |= dnv_get_bit(pmiaddr, dmap3[pmiidx].row10 + 6, 10);
+ daddr->row |= dnv_get_bit(pmiaddr, dmap3[pmiidx].row11 + 6, 11);
+ daddr->row |= dnv_get_bit(pmiaddr, dmap4[pmiidx].row12 + 6, 12);
+ daddr->row |= dnv_get_bit(pmiaddr, dmap4[pmiidx].row13 + 6, 13);
+ if (dmap4[pmiidx].row14 != 31)
+ daddr->row |= dnv_get_bit(pmiaddr, dmap4[pmiidx].row14 + 6, 14);
+ if (dmap4[pmiidx].row15 != 31)
+ daddr->row |= dnv_get_bit(pmiaddr, dmap4[pmiidx].row15 + 6, 15);
+ if (dmap4[pmiidx].row16 != 31)
+ daddr->row |= dnv_get_bit(pmiaddr, dmap4[pmiidx].row16 + 6, 16);
+ if (dmap4[pmiidx].row17 != 31)
+ daddr->row |= dnv_get_bit(pmiaddr, dmap4[pmiidx].row17 + 6, 17);
+
+ daddr->col = dnv_get_bit(pmiaddr, dmap5[pmiidx].ca3 + 6, 3);
+ daddr->col |= dnv_get_bit(pmiaddr, dmap5[pmiidx].ca4 + 6, 4);
+ daddr->col |= dnv_get_bit(pmiaddr, dmap5[pmiidx].ca5 + 6, 5);
+ daddr->col |= dnv_get_bit(pmiaddr, dmap5[pmiidx].ca6 + 6, 6);
+ daddr->col |= dnv_get_bit(pmiaddr, dmap5[pmiidx].ca7 + 6, 7);
+ daddr->col |= dnv_get_bit(pmiaddr, dmap5[pmiidx].ca8 + 6, 8);
+ daddr->col |= dnv_get_bit(pmiaddr, dmap5[pmiidx].ca9 + 6, 9);
+ if (!dsch.ddr4en && dmap1[pmiidx].ca11 != 0x3f)
+ daddr->col |= dnv_get_bit(pmiaddr, dmap1[pmiidx].ca11 + 13, 11);
+
+ return 0;
+}
+
+static int check_channel(int ch)
+{
+ if (drp0[ch].dramtype != 0) {
+ pnd2_printk(KERN_INFO, "Unsupported DIMM in channel %d\n", ch);
+ return 1;
+ } else if (drp0[ch].eccen == 0) {
+ pnd2_printk(KERN_INFO, "ECC disabled on channel %d\n", ch);
+ return 1;
+ }
+ return 0;
+}
+
+static int apl_check_ecc_active(void)
+{
+ int i, ret = 0;
+
+ /* Check dramtype and ECC mode for each present DIMM */
+ for (i = 0; i < APL_NUM_CHANNELS; i++)
+ if (chan_mask & BIT(i))
+ ret += check_channel(i);
+ return ret ? -EINVAL : 0;
+}
+
+#define DIMMS_PRESENT(d) ((d)->rken0 + (d)->rken1 + (d)->rken2 + (d)->rken3)
+
+static int check_unit(int ch)
+{
+ struct d_cr_drp *d = &drp[ch];
+
+ if (DIMMS_PRESENT(d) && !ecc_ctrl[ch].eccen) {
+ pnd2_printk(KERN_INFO, "ECC disabled on channel %d\n", ch);
+ return 1;
+ }
+ return 0;
+}
+
+static int dnv_check_ecc_active(void)
+{
+ int i, ret = 0;
+
+ for (i = 0; i < DNV_NUM_CHANNELS; i++)
+ ret += check_unit(i);
+ return ret ? -EINVAL : 0;
+}
+
+static int get_memory_error_data(struct mem_ctl_info *mci, u64 addr,
+ struct dram_addr *daddr, char *msg)
+{
+ u64 pmiaddr;
+ u32 pmiidx;
+ int ret;
+
+ ret = sys2pmi(addr, &pmiidx, &pmiaddr, msg);
+ if (ret)
+ return ret;
+
+ pmiaddr >>= ops->pmiaddr_shift;
+ /* pmi channel idx to dimm channel idx */
+ pmiidx >>= ops->pmiidx_shift;
+ daddr->chan = pmiidx;
+
+ ret = ops->pmi2mem(mci, pmiaddr, pmiidx, daddr, msg);
+ if (ret)
+ return ret;
+
+ edac_dbg(0, "SysAddr=%llx PmiAddr=%llx Channel=%d DIMM=%d Rank=%d Bank=%d Row=%d Column=%d\n",
+ addr, pmiaddr, daddr->chan, daddr->dimm, daddr->rank, daddr->bank, daddr->row, daddr->col);
+
+ return 0;
+}
+
+static void pnd2_mce_output_error(struct mem_ctl_info *mci, const struct mce *m,
+ struct dram_addr *daddr)
+{
+ enum hw_event_mc_err_type tp_event;
+ char *optype, msg[PND2_MSG_SIZE];
+ bool ripv = m->mcgstatus & MCG_STATUS_RIPV;
+ bool overflow = m->status & MCI_STATUS_OVER;
+ bool uc_err = m->status & MCI_STATUS_UC;
+ bool recov = m->status & MCI_STATUS_S;
+ u32 core_err_cnt = GET_BITFIELD(m->status, 38, 52);
+ u32 mscod = GET_BITFIELD(m->status, 16, 31);
+ u32 errcode = GET_BITFIELD(m->status, 0, 15);
+ u32 optypenum = GET_BITFIELD(m->status, 4, 6);
+ int rc;
+
+ tp_event = uc_err ? (ripv ? HW_EVENT_ERR_FATAL : HW_EVENT_ERR_UNCORRECTED) :
+ HW_EVENT_ERR_CORRECTED;
+
+ /*
+ * According with Table 15-9 of the Intel Architecture spec vol 3A,
+ * memory errors should fit in this mask:
+ * 000f 0000 1mmm cccc (binary)
+ * where:
+ * f = Correction Report Filtering Bit. If 1, subsequent errors
+ * won't be shown
+ * mmm = error type
+ * cccc = channel
+ * If the mask doesn't match, report an error to the parsing logic
+ */
+ if (!((errcode & 0xef80) == 0x80)) {
+ optype = "Can't parse: it is not a mem";
+ } else {
+ switch (optypenum) {
+ case 0:
+ optype = "generic undef request error";
+ break;
+ case 1:
+ optype = "memory read error";
+ break;
+ case 2:
+ optype = "memory write error";
+ break;
+ case 3:
+ optype = "addr/cmd error";
+ break;
+ case 4:
+ optype = "memory scrubbing error";
+ break;
+ default:
+ optype = "reserved";
+ break;
+ }
+ }
+
+ /* Only decode errors with an valid address (ADDRV) */
+ if (!(m->status & MCI_STATUS_ADDRV))
+ return;
+
+ rc = get_memory_error_data(mci, m->addr, daddr, msg);
+ if (rc)
+ goto address_error;
+
+ snprintf(msg, sizeof(msg),
+ "%s%s err_code:%04x:%04x channel:%d DIMM:%d rank:%d row:%d bank:%d col:%d",
+ overflow ? " OVERFLOW" : "", (uc_err && recov) ? " recoverable" : "", mscod,
+ errcode, daddr->chan, daddr->dimm, daddr->rank, daddr->row, daddr->bank, daddr->col);
+
+ edac_dbg(0, "%s\n", msg);
+
+ /* Call the helper to output message */
+ edac_mc_handle_error(tp_event, mci, core_err_cnt, m->addr >> PAGE_SHIFT,
+ m->addr & ~PAGE_MASK, 0, daddr->chan, daddr->dimm, -1, optype, msg);
+
+ return;
+
+address_error:
+ edac_mc_handle_error(tp_event, mci, core_err_cnt, 0, 0, 0, -1, -1, -1, msg, "");
+}
+
+static void apl_get_dimm_config(struct mem_ctl_info *mci)
+{
+ struct pnd2_pvt *pvt = mci->pvt_info;
+ struct dimm_info *dimm;
+ struct d_cr_drp0 *d;
+ u64 capacity;
+ int i, g;
+
+ for (i = 0; i < APL_NUM_CHANNELS; i++) {
+ if (!(chan_mask & BIT(i)))
+ continue;
+
+ dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, i, 0, 0);
+ if (!dimm) {
+ edac_dbg(0, "No allocated DIMM for channel %d\n", i);
+ continue;
+ }
+
+ d = &drp0[i];
+ for (g = 0; g < ARRAY_SIZE(dimms); g++)
+ if (dimms[g].addrdec == d->addrdec &&
+ dimms[g].dden == d->dden &&
+ dimms[g].dwid == d->dwid)
+ break;
+
+ if (g == ARRAY_SIZE(dimms)) {
+ edac_dbg(0, "Channel %d: unrecognized DIMM\n", i);
+ continue;
+ }
+
+ pvt->dimm_geom[i] = g;
+ capacity = (d->rken0 + d->rken1) * 8 * (1ul << dimms[g].rowbits) *
+ (1ul << dimms[g].colbits);
+ edac_dbg(0, "Channel %d: %lld MByte DIMM\n", i, capacity >> (20 - 3));
+ dimm->nr_pages = MiB_TO_PAGES(capacity >> (20 - 3));
+ dimm->grain = 32;
+ dimm->dtype = (d->dwid == 0) ? DEV_X8 : DEV_X16;
+ dimm->mtype = MEM_DDR3;
+ dimm->edac_mode = EDAC_SECDED;
+ snprintf(dimm->label, sizeof(dimm->label), "Slice#%d_Chan#%d", i / 2, i % 2);
+ }
+}
+
+static const int dnv_dtypes[] = {
+ DEV_X8, DEV_X4, DEV_X16, DEV_UNKNOWN
+};
+
+static void dnv_get_dimm_config(struct mem_ctl_info *mci)
+{
+ int i, j, ranks_of_dimm[DNV_MAX_DIMMS], banks, rowbits, colbits, memtype;
+ struct dimm_info *dimm;
+ struct d_cr_drp *d;
+ u64 capacity;
+
+ if (dsch.ddr4en) {
+ memtype = MEM_DDR4;
+ banks = 16;
+ colbits = 10;
+ } else {
+ memtype = MEM_DDR3;
+ banks = 8;
+ }
+
+ for (i = 0; i < DNV_NUM_CHANNELS; i++) {
+ if (dmap4[i].row14 == 31)
+ rowbits = 14;
+ else if (dmap4[i].row15 == 31)
+ rowbits = 15;
+ else if (dmap4[i].row16 == 31)
+ rowbits = 16;
+ else if (dmap4[i].row17 == 31)
+ rowbits = 17;
+ else
+ rowbits = 18;
+
+ if (memtype == MEM_DDR3) {
+ if (dmap1[i].ca11 != 0x3f)
+ colbits = 12;
+ else
+ colbits = 10;
+ }
+
+ d = &drp[i];
+ /* DIMM0 is present if rank0 and/or rank1 is enabled */
+ ranks_of_dimm[0] = d->rken0 + d->rken1;
+ /* DIMM1 is present if rank2 and/or rank3 is enabled */
+ ranks_of_dimm[1] = d->rken2 + d->rken3;
+
+ for (j = 0; j < DNV_MAX_DIMMS; j++) {
+ if (!ranks_of_dimm[j])
+ continue;
+
+ dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, i, j, 0);
+ if (!dimm) {
+ edac_dbg(0, "No allocated DIMM for channel %d DIMM %d\n", i, j);
+ continue;
+ }
+
+ capacity = ranks_of_dimm[j] * banks * (1ul << rowbits) * (1ul << colbits);
+ edac_dbg(0, "Channel %d DIMM %d: %lld MByte DIMM\n", i, j, capacity >> (20 - 3));
+ dimm->nr_pages = MiB_TO_PAGES(capacity >> (20 - 3));
+ dimm->grain = 32;
+ dimm->dtype = dnv_dtypes[j ? d->dimmdwid0 : d->dimmdwid1];
+ dimm->mtype = memtype;
+ dimm->edac_mode = EDAC_SECDED;
+ snprintf(dimm->label, sizeof(dimm->label), "Chan#%d_DIMM#%d", i, j);
+ }
+ }
+}
+
+static int pnd2_register_mci(struct mem_ctl_info **ppmci)
+{
+ struct edac_mc_layer layers[2];
+ struct mem_ctl_info *mci;
+ struct pnd2_pvt *pvt;
+ int rc;
+
+ rc = ops->check_ecc();
+ if (rc < 0)
+ return rc;
+
+ /* Allocate a new MC control structure */
+ layers[0].type = EDAC_MC_LAYER_CHANNEL;
+ layers[0].size = ops->channels;
+ layers[0].is_virt_csrow = false;
+ layers[1].type = EDAC_MC_LAYER_SLOT;
+ layers[1].size = ops->dimms_per_channel;
+ layers[1].is_virt_csrow = true;
+ mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, sizeof(*pvt));
+ if (!mci)
+ return -ENOMEM;
+
+ pvt = mci->pvt_info;
+ memset(pvt, 0, sizeof(*pvt));
+
+ mci->mod_name = "pnd2_edac.c";
+ mci->dev_name = ops->name;
+ mci->ctl_name = "Pondicherry2";
+
+ /* Get dimm basic config and the memory layout */
+ ops->get_dimm_config(mci);
+
+ if (edac_mc_add_mc(mci)) {
+ edac_dbg(0, "MC: failed edac_mc_add_mc()\n");
+ edac_mc_free(mci);
+ return -EINVAL;
+ }
+
+ *ppmci = mci;
+
+ return 0;
+}
+
+static void pnd2_unregister_mci(struct mem_ctl_info *mci)
+{
+ if (unlikely(!mci || !mci->pvt_info)) {
+ pnd2_printk(KERN_ERR, "Couldn't find mci handler\n");
+ return;
+ }
+
+ /* Remove MC sysfs nodes */
+ edac_mc_del_mc(NULL);
+ edac_dbg(1, "%s: free mci struct\n", mci->ctl_name);
+ edac_mc_free(mci);
+}
+
+/*
+ * Callback function registered with core kernel mce code.
+ * Called once for each logged error.
+ */
+static int pnd2_mce_check_error(struct notifier_block *nb, unsigned long val, void *data)
+{
+ struct mce *mce = (struct mce *)data;
+ struct mem_ctl_info *mci;
+ struct dram_addr daddr;
+ char *type;
+
+ if (get_edac_report_status() == EDAC_REPORTING_DISABLED)
+ return NOTIFY_DONE;
+
+ mci = pnd2_mci;
+ if (!mci)
+ return NOTIFY_DONE;
+
+ /*
+ * Just let mcelog handle it if the error is
+ * outside the memory controller. A memory error
+ * is indicated by bit 7 = 1 and bits = 8-11,13-15 = 0.
+ * bit 12 has an special meaning.
+ */
+ if ((mce->status & 0xefff) >> 7 != 1)
+ return NOTIFY_DONE;
+
+ if (mce->mcgstatus & MCG_STATUS_MCIP)
+ type = "Exception";
+ else
+ type = "Event";
+
+ pnd2_mc_printk(mci, KERN_INFO, "HANDLING MCE MEMORY ERROR\n");
+ pnd2_mc_printk(mci, KERN_INFO, "CPU %u: Machine Check %s: %llx Bank %u: %llx\n",
+ mce->extcpu, type, mce->mcgstatus, mce->bank, mce->status);
+ pnd2_mc_printk(mci, KERN_INFO, "TSC %llx ", mce->tsc);
+ pnd2_mc_printk(mci, KERN_INFO, "ADDR %llx ", mce->addr);
+ pnd2_mc_printk(mci, KERN_INFO, "MISC %llx ", mce->misc);
+ pnd2_mc_printk(mci, KERN_INFO, "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n",
+ mce->cpuvendor, mce->cpuid, mce->time, mce->socketid, mce->apicid);
+
+ pnd2_mce_output_error(mci, mce, &daddr);
+
+ /* Advice mcelog that the error were handled */
+ return NOTIFY_STOP;
+}
+
+static struct notifier_block pnd2_mce_dec = {
+ .notifier_call = pnd2_mce_check_error,
+};
+
+#ifdef CONFIG_EDAC_DEBUG
+/*
+ * Write an address to this file to exercise the address decode
+ * logic in this driver.
+ */
+static u64 pnd2_fake_addr;
+#define PND2_BLOB_SIZE 1024
+static char pnd2_result[PND2_BLOB_SIZE];
+static struct dentry *pnd2_test;
+static struct debugfs_blob_wrapper pnd2_blob = {
+ .data = pnd2_result,
+ .size = 0
+};
+
+static int debugfs_u64_set(void *data, u64 val)
+{
+ struct dram_addr daddr;
+ struct mce m;
+
+ *(u64 *)data = val;
+ m.mcgstatus = 0;
+ /* ADDRV + MemRd + Unknown channel */
+ m.status = MCI_STATUS_ADDRV + 0x9f;
+ m.addr = val;
+ pnd2_mce_output_error(pnd2_mci, &m, &daddr);
+ snprintf(pnd2_blob.data, PND2_BLOB_SIZE,
+ "SysAddr=%llx Channel=%d DIMM=%d Rank=%d Bank=%d Row=%d Column=%d\n",
+ m.addr, daddr.chan, daddr.dimm, daddr.rank, daddr.bank, daddr.row, daddr.col);
+ pnd2_blob.size = strlen(pnd2_blob.data);
+
+ return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n");
+
+static void setup_pnd2_debug(void)
+{
+ pnd2_test = edac_debugfs_create_dir("pnd2_test");
+ edac_debugfs_create_file("pnd2_debug_addr", 0200, pnd2_test,
+ &pnd2_fake_addr, &fops_u64_wo);
+ debugfs_create_blob("pnd2_debug_results", 0400, pnd2_test, &pnd2_blob);
+}
+
+static void teardown_pnd2_debug(void)
+{
+ debugfs_remove_recursive(pnd2_test);
+}
+#else
+static void setup_pnd2_debug(void) {}
+static void teardown_pnd2_debug(void) {}
+#endif /* CONFIG_EDAC_DEBUG */
+
+
+static int pnd2_probe(void)
+{
+ int rc;
+
+ edac_dbg(2, "\n");
+ rc = get_registers();
+ if (rc)
+ return rc;
+
+ return pnd2_register_mci(&pnd2_mci);
+}
+
+static void pnd2_remove(void)
+{
+ edac_dbg(0, "\n");
+ pnd2_unregister_mci(pnd2_mci);
+}
+
+static struct dunit_ops apl_ops = {
+ .name = "pnd2/apl",
+ .type = APL,
+ .pmiaddr_shift = LOG2_PMI_ADDR_GRANULARITY,
+ .pmiidx_shift = 0,
+ .channels = APL_NUM_CHANNELS,
+ .dimms_per_channel = 1,
+ .rd_reg = apl_rd_reg,
+ .get_registers = apl_get_registers,
+ .check_ecc = apl_check_ecc_active,
+ .mk_region = apl_mk_region,
+ .get_dimm_config = apl_get_dimm_config,
+ .pmi2mem = apl_pmi2mem,
+};
+
+static struct dunit_ops dnv_ops = {
+ .name = "pnd2/dnv",
+ .type = DNV,
+ .pmiaddr_shift = 0,
+ .pmiidx_shift = 1,
+ .channels = DNV_NUM_CHANNELS,
+ .dimms_per_channel = 2,
+ .rd_reg = dnv_rd_reg,
+ .get_registers = dnv_get_registers,
+ .check_ecc = dnv_check_ecc_active,
+ .mk_region = dnv_mk_region,
+ .get_dimm_config = dnv_get_dimm_config,
+ .pmi2mem = dnv_pmi2mem,
+};
+
+static const struct x86_cpu_id pnd2_cpuids[] = {
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT, 0, (kernel_ulong_t)&apl_ops },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_DENVERTON, 0, (kernel_ulong_t)&dnv_ops },
+ { }
+};
+MODULE_DEVICE_TABLE(x86cpu, pnd2_cpuids);
+
+static int __init pnd2_init(void)
+{
+ const struct x86_cpu_id *id;
+ int rc;
+
+ edac_dbg(2, "\n");
+
+ id = x86_match_cpu(pnd2_cpuids);
+ if (!id)
+ return -ENODEV;
+
+ ops = (struct dunit_ops *)id->driver_data;
+
+ /* Ensure that the OPSTATE is set correctly for POLL or NMI */
+ opstate_init();
+
+ rc = pnd2_probe();
+ if (rc < 0) {
+ pnd2_printk(KERN_ERR, "Failed to register device with error %d.\n", rc);
+ return rc;
+ }
+
+ if (!pnd2_mci)
+ return -ENODEV;
+
+ mce_register_decode_chain(&pnd2_mce_dec);
+ setup_pnd2_debug();
+
+ return 0;
+}
+
+static void __exit pnd2_exit(void)
+{
+ edac_dbg(2, "\n");
+ teardown_pnd2_debug();
+ mce_unregister_decode_chain(&pnd2_mce_dec);
+ pnd2_remove();
+}
+
+module_init(pnd2_init);
+module_exit(pnd2_exit);
+
+module_param(edac_op_state, int, 0444);
+MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI");
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Tony Luck");
+MODULE_DESCRIPTION("MC Driver for Intel SoC using Pondicherry memory controller");
diff --git a/drivers/edac/pnd2_edac.h b/drivers/edac/pnd2_edac.h
new file mode 100644
index 0000000..61b6e79
--- /dev/null
+++ b/drivers/edac/pnd2_edac.h
@@ -0,0 +1,301 @@
+/*
+ * Register bitfield descriptions for Pondicherry2 memory controller.
+ *
+ * Copyright (c) 2016, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef _PND2_REGS_H
+#define _PND2_REGS_H
+
+struct b_cr_touud_lo_pci {
+ u32 lock : 1;
+ u32 reserved_1 : 19;
+ u32 touud : 12;
+};
+
+#define b_cr_touud_lo_pci_port 0x4c
+#define b_cr_touud_lo_pci_offset 0xa8
+#define b_cr_touud_lo_pci_r_opcode 0x04
+
+struct b_cr_touud_hi_pci {
+ u32 touud : 7;
+ u32 reserved_0 : 25;
+};
+
+#define b_cr_touud_hi_pci_port 0x4c
+#define b_cr_touud_hi_pci_offset 0xac
+#define b_cr_touud_hi_pci_r_opcode 0x04
+
+struct b_cr_tolud_pci {
+ u32 lock : 1;
+ u32 reserved_0 : 19;
+ u32 tolud : 12;
+};
+
+#define b_cr_tolud_pci_port 0x4c
+#define b_cr_tolud_pci_offset 0xbc
+#define b_cr_tolud_pci_r_opcode 0x04
+
+struct b_cr_mchbar_lo_pci {
+ u32 enable : 1;
+ u32 pad_3_1 : 3;
+ u32 pad_14_4: 11;
+ u32 base: 17;
+};
+
+struct b_cr_mchbar_hi_pci {
+ u32 base : 7;
+ u32 pad_31_7 : 25;
+};
+
+/* Symmetric region */
+struct b_cr_slice_channel_hash {
+ u64 slice_1_disabled : 1;
+ u64 hvm_mode : 1;
+ u64 interleave_mode : 2;
+ u64 slice_0_mem_disabled : 1;
+ u64 reserved_0 : 1;
+ u64 slice_hash_mask : 14;
+ u64 reserved_1 : 11;
+ u64 enable_pmi_dual_data_mode : 1;
+ u64 ch_1_disabled : 1;
+ u64 reserved_2 : 1;
+ u64 sym_slice0_channel_enabled : 2;
+ u64 sym_slice1_channel_enabled : 2;
+ u64 ch_hash_mask : 14;
+ u64 reserved_3 : 11;
+ u64 lock : 1;
+};
+
+#define b_cr_slice_channel_hash_port 0x4c
+#define b_cr_slice_channel_hash_offset 0x4c58
+#define b_cr_slice_channel_hash_r_opcode 0x06
+
+struct b_cr_mot_out_base_mchbar {
+ u32 reserved_0 : 14;
+ u32 mot_out_base : 15;
+ u32 reserved_1 : 1;
+ u32 tr_en : 1;
+ u32 imr_en : 1;
+};
+
+#define b_cr_mot_out_base_mchbar_port 0x4c
+#define b_cr_mot_out_base_mchbar_offset 0x6af0
+#define b_cr_mot_out_base_mchbar_r_opcode 0x00
+
+struct b_cr_mot_out_mask_mchbar {
+ u32 reserved_0 : 14;
+ u32 mot_out_mask : 15;
+ u32 reserved_1 : 1;
+ u32 ia_iwb_en : 1;
+ u32 gt_iwb_en : 1;
+};
+
+#define b_cr_mot_out_mask_mchbar_port 0x4c
+#define b_cr_mot_out_mask_mchbar_offset 0x6af4
+#define b_cr_mot_out_mask_mchbar_r_opcode 0x00
+
+struct b_cr_asym_mem_region0_mchbar {
+ u32 pad : 4;
+ u32 slice0_asym_base : 11;
+ u32 pad_18_15 : 4;
+ u32 slice0_asym_limit : 11;
+ u32 slice0_asym_channel_select : 1;
+ u32 slice0_asym_enable : 1;
+};
+
+#define b_cr_asym_mem_region0_mchbar_port 0x4c
+#define b_cr_asym_mem_region0_mchbar_offset 0x6e40
+#define b_cr_asym_mem_region0_mchbar_r_opcode 0x00
+
+struct b_cr_asym_mem_region1_mchbar {
+ u32 pad : 4;
+ u32 slice1_asym_base : 11;
+ u32 pad_18_15 : 4;
+ u32 slice1_asym_limit : 11;
+ u32 slice1_asym_channel_select : 1;
+ u32 slice1_asym_enable : 1;
+};
+
+#define b_cr_asym_mem_region1_mchbar_port 0x4c
+#define b_cr_asym_mem_region1_mchbar_offset 0x6e44
+#define b_cr_asym_mem_region1_mchbar_r_opcode 0x00
+
+/* Some bit fields moved in above two structs on Denverton */
+struct b_cr_asym_mem_region_denverton {
+ u32 pad : 4;
+ u32 slice_asym_base : 8;
+ u32 pad_19_12 : 8;
+ u32 slice_asym_limit : 8;
+ u32 pad_28_30 : 3;
+ u32 slice_asym_enable : 1;
+};
+
+struct b_cr_asym_2way_mem_region_mchbar {
+ u32 pad : 2;
+ u32 asym_2way_intlv_mode : 2;
+ u32 asym_2way_base : 11;
+ u32 pad_16_15 : 2;
+ u32 asym_2way_limit : 11;
+ u32 pad_30_28 : 3;
+ u32 asym_2way_interleave_enable : 1;
+};
+
+#define b_cr_asym_2way_mem_region_mchbar_port 0x4c
+#define b_cr_asym_2way_mem_region_mchbar_offset 0x6e50
+#define b_cr_asym_2way_mem_region_mchbar_r_opcode 0x00
+
+/* Apollo Lake d-unit */
+
+struct d_cr_drp0 {
+ u32 rken0 : 1;
+ u32 rken1 : 1;
+ u32 ddmen : 1;
+ u32 rsvd3 : 1;
+ u32 dwid : 2;
+ u32 dden : 3;
+ u32 rsvd13_9 : 5;
+ u32 rsien : 1;
+ u32 bahen : 1;
+ u32 rsvd18_16 : 3;
+ u32 caswizzle : 2;
+ u32 eccen : 1;
+ u32 dramtype : 3;
+ u32 blmode : 3;
+ u32 addrdec : 2;
+ u32 dramdevice_pr : 2;
+};
+
+#define d_cr_drp0_offset 0x1400
+#define d_cr_drp0_r_opcode 0x00
+
+/* Denverton d-unit */
+
+struct d_cr_dsch {
+ u32 ch0en : 1;
+ u32 ch1en : 1;
+ u32 ddr4en : 1;
+ u32 coldwake : 1;
+ u32 newbypdis : 1;
+ u32 chan_width : 1;
+ u32 rsvd6_6 : 1;
+ u32 ooodis : 1;
+ u32 rsvd18_8 : 11;
+ u32 ic : 1;
+ u32 rsvd31_20 : 12;
+};
+
+#define d_cr_dsch_port 0x16
+#define d_cr_dsch_offset 0x0
+#define d_cr_dsch_r_opcode 0x0
+
+struct d_cr_ecc_ctrl {
+ u32 eccen : 1;
+ u32 rsvd31_1 : 31;
+};
+
+#define d_cr_ecc_ctrl_offset 0x180
+#define d_cr_ecc_ctrl_r_opcode 0x0
+
+struct d_cr_drp {
+ u32 rken0 : 1;
+ u32 rken1 : 1;
+ u32 rken2 : 1;
+ u32 rken3 : 1;
+ u32 dimmdwid0 : 2;
+ u32 dimmdden0 : 2;
+ u32 dimmdwid1 : 2;
+ u32 dimmdden1 : 2;
+ u32 rsvd15_12 : 4;
+ u32 dimmflip : 1;
+ u32 rsvd31_17 : 15;
+};
+
+#define d_cr_drp_offset 0x158
+#define d_cr_drp_r_opcode 0x0
+
+struct d_cr_dmap {
+ u32 ba0 : 5;
+ u32 ba1 : 5;
+ u32 bg0 : 5; /* if ddr3, ba2 = bg0 */
+ u32 bg1 : 5; /* if ddr3, ba3 = bg1 */
+ u32 rs0 : 5;
+ u32 rs1 : 5;
+ u32 rsvd : 2;
+};
+
+#define d_cr_dmap_offset 0x174
+#define d_cr_dmap_r_opcode 0x0
+
+struct d_cr_dmap1 {
+ u32 ca11 : 6;
+ u32 bxor : 1;
+ u32 rsvd : 25;
+};
+
+#define d_cr_dmap1_offset 0xb4
+#define d_cr_dmap1_r_opcode 0x0
+
+struct d_cr_dmap2 {
+ u32 row0 : 5;
+ u32 row1 : 5;
+ u32 row2 : 5;
+ u32 row3 : 5;
+ u32 row4 : 5;
+ u32 row5 : 5;
+ u32 rsvd : 2;
+};
+
+#define d_cr_dmap2_offset 0x148
+#define d_cr_dmap2_r_opcode 0x0
+
+struct d_cr_dmap3 {
+ u32 row6 : 5;
+ u32 row7 : 5;
+ u32 row8 : 5;
+ u32 row9 : 5;
+ u32 row10 : 5;
+ u32 row11 : 5;
+ u32 rsvd : 2;
+};
+
+#define d_cr_dmap3_offset 0x14c
+#define d_cr_dmap3_r_opcode 0x0
+
+struct d_cr_dmap4 {
+ u32 row12 : 5;
+ u32 row13 : 5;
+ u32 row14 : 5;
+ u32 row15 : 5;
+ u32 row16 : 5;
+ u32 row17 : 5;
+ u32 rsvd : 2;
+};
+
+#define d_cr_dmap4_offset 0x150
+#define d_cr_dmap4_r_opcode 0x0
+
+struct d_cr_dmap5 {
+ u32 ca3 : 4;
+ u32 ca4 : 4;
+ u32 ca5 : 4;
+ u32 ca6 : 4;
+ u32 ca7 : 4;
+ u32 ca8 : 4;
+ u32 ca9 : 4;
+ u32 rsvd : 4;
+};
+
+#define d_cr_dmap5_offset 0x154
+#define d_cr_dmap5_r_opcode 0x0
+
+#endif /* _PND2_REGS_H */
diff --git a/drivers/edac/xgene_edac.c b/drivers/edac/xgene_edac.c
index 6c270d9..6692460 100644
--- a/drivers/edac/xgene_edac.c
+++ b/drivers/edac/xgene_edac.c
@@ -1596,7 +1596,7 @@ static void xgene_edac_pa_report(struct edac_device_ctl_info *edac_dev)
reg = readl(ctx->dev_csr + IOBPATRANSERRINTSTS);
if (!reg)
goto chk_iob_axi0;
- dev_err(edac_dev->dev, "IOB procesing agent (PA) transaction error\n");
+ dev_err(edac_dev->dev, "IOB processing agent (PA) transaction error\n");
if (reg & IOBPA_RDATA_CORRUPT_MASK)
dev_err(edac_dev->dev, "IOB PA read data RAM error\n");
if (reg & IOBPA_M_RDATA_CORRUPT_MASK)
diff --git a/drivers/extcon/Kconfig b/drivers/extcon/Kconfig
index 96bbae5..fc09c76 100644
--- a/drivers/extcon/Kconfig
+++ b/drivers/extcon/Kconfig
@@ -44,7 +44,7 @@
config EXTCON_INTEL_INT3496
tristate "Intel INT3496 ACPI device extcon driver"
- depends on GPIOLIB && ACPI
+ depends on GPIOLIB && ACPI && (X86 || COMPILE_TEST)
help
Say Y here to enable extcon support for USB OTG ports controlled by
an Intel INT3496 ACPI device.
diff --git a/drivers/extcon/extcon-intel-int3496.c b/drivers/extcon/extcon-intel-int3496.c
index a3131b0..9d17984 100644
--- a/drivers/extcon/extcon-intel-int3496.c
+++ b/drivers/extcon/extcon-intel-int3496.c
@@ -45,6 +45,17 @@ static const unsigned int int3496_cable[] = {
EXTCON_NONE,
};
+static const struct acpi_gpio_params id_gpios = { INT3496_GPIO_USB_ID, 0, false };
+static const struct acpi_gpio_params vbus_gpios = { INT3496_GPIO_VBUS_EN, 0, false };
+static const struct acpi_gpio_params mux_gpios = { INT3496_GPIO_USB_MUX, 0, false };
+
+static const struct acpi_gpio_mapping acpi_int3496_default_gpios[] = {
+ { "id-gpios", &id_gpios, 1 },
+ { "vbus-gpios", &vbus_gpios, 1 },
+ { "mux-gpios", &mux_gpios, 1 },
+ { },
+};
+
static void int3496_do_usb_id(struct work_struct *work)
{
struct int3496_data *data =
@@ -83,6 +94,13 @@ static int int3496_probe(struct platform_device *pdev)
struct int3496_data *data;
int ret;
+ ret = acpi_dev_add_driver_gpios(ACPI_COMPANION(dev),
+ acpi_int3496_default_gpios);
+ if (ret) {
+ dev_err(dev, "can't add GPIO ACPI mapping\n");
+ return ret;
+ }
+
data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
if (!data)
return -ENOMEM;
@@ -90,30 +108,27 @@ static int int3496_probe(struct platform_device *pdev)
data->dev = dev;
INIT_DELAYED_WORK(&data->work, int3496_do_usb_id);
- data->gpio_usb_id = devm_gpiod_get_index(dev, "id",
- INT3496_GPIO_USB_ID,
- GPIOD_IN);
+ data->gpio_usb_id = devm_gpiod_get(dev, "id", GPIOD_IN);
if (IS_ERR(data->gpio_usb_id)) {
ret = PTR_ERR(data->gpio_usb_id);
dev_err(dev, "can't request USB ID GPIO: %d\n", ret);
return ret;
+ } else if (gpiod_get_direction(data->gpio_usb_id) != GPIOF_DIR_IN) {
+ dev_warn(dev, FW_BUG "USB ID GPIO not in input mode, fixing\n");
+ gpiod_direction_input(data->gpio_usb_id);
}
data->usb_id_irq = gpiod_to_irq(data->gpio_usb_id);
- if (data->usb_id_irq <= 0) {
+ if (data->usb_id_irq < 0) {
dev_err(dev, "can't get USB ID IRQ: %d\n", data->usb_id_irq);
- return -EINVAL;
+ return data->usb_id_irq;
}
- data->gpio_vbus_en = devm_gpiod_get_index(dev, "vbus en",
- INT3496_GPIO_VBUS_EN,
- GPIOD_ASIS);
+ data->gpio_vbus_en = devm_gpiod_get(dev, "vbus", GPIOD_ASIS);
if (IS_ERR(data->gpio_vbus_en))
dev_info(dev, "can't request VBUS EN GPIO\n");
- data->gpio_usb_mux = devm_gpiod_get_index(dev, "usb mux",
- INT3496_GPIO_USB_MUX,
- GPIOD_ASIS);
+ data->gpio_usb_mux = devm_gpiod_get(dev, "mux", GPIOD_ASIS);
if (IS_ERR(data->gpio_usb_mux))
dev_info(dev, "can't request USB MUX GPIO\n");
@@ -154,6 +169,8 @@ static int int3496_remove(struct platform_device *pdev)
devm_free_irq(&pdev->dev, data->usb_id_irq, data);
cancel_delayed_work_sync(&data->work);
+ acpi_dev_remove_driver_gpios(ACPI_COMPANION(&pdev->dev));
+
return 0;
}
diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c
index 349dc3e..974c5a3 100644
--- a/drivers/firmware/efi/arm-runtime.c
+++ b/drivers/firmware/efi/arm-runtime.c
@@ -65,6 +65,7 @@ static bool __init efi_virtmap_init(void)
bool systab_found;
efi_mm.pgd = pgd_alloc(&efi_mm);
+ mm_init_cpumask(&efi_mm);
init_new_context(NULL, &efi_mm);
systab_found = false;
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index e7d4040..b372aad 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -389,7 +389,6 @@ int __init efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md)
return 0;
}
}
- pr_err_once("requested map not found.\n");
return -ENOENT;
}
diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c
index 08b0268..8554d7a 100644
--- a/drivers/firmware/efi/esrt.c
+++ b/drivers/firmware/efi/esrt.c
@@ -254,7 +254,7 @@ void __init efi_esrt_init(void)
rc = efi_mem_desc_lookup(efi.esrt, &md);
if (rc < 0) {
- pr_err("ESRT header is not in the memory map.\n");
+ pr_warn("ESRT header is not in the memory map.\n");
return;
}
diff --git a/drivers/firmware/efi/libstub/secureboot.c b/drivers/firmware/efi/libstub/secureboot.c
index 6def402..5da36e5 100644
--- a/drivers/firmware/efi/libstub/secureboot.c
+++ b/drivers/firmware/efi/libstub/secureboot.c
@@ -45,6 +45,8 @@ enum efi_secureboot_mode efi_get_secureboot(efi_system_table_t *sys_table_arg)
size = sizeof(secboot);
status = get_efi_var(efi_SecureBoot_name, &efi_variable_guid,
NULL, &size, &secboot);
+ if (status == EFI_NOT_FOUND)
+ return efi_secureboot_mode_disabled;
if (status != EFI_SUCCESS)
goto out_efi_err;
@@ -78,7 +80,5 @@ enum efi_secureboot_mode efi_get_secureboot(efi_system_table_t *sys_table_arg)
out_efi_err:
pr_efi_err(sys_table_arg, "Could not determine UEFI Secure Boot status.\n");
- if (status == EFI_NOT_FOUND)
- return efi_secureboot_mode_disabled;
return efi_secureboot_mode_unknown;
}
diff --git a/drivers/gpio/gpio-altera-a10sr.c b/drivers/gpio/gpio-altera-a10sr.c
index 9e1a138..16a8951 100644
--- a/drivers/gpio/gpio-altera-a10sr.c
+++ b/drivers/gpio/gpio-altera-a10sr.c
@@ -96,7 +96,7 @@ static int altr_a10sr_gpio_probe(struct platform_device *pdev)
gpio->regmap = a10sr->regmap;
gpio->gp = altr_a10sr_gc;
-
+ gpio->gp.parent = pdev->dev.parent;
gpio->gp.of_node = pdev->dev.of_node;
ret = devm_gpiochip_add_data(&pdev->dev, &gpio->gp, gpio);
diff --git a/drivers/gpio/gpio-altera.c b/drivers/gpio/gpio-altera.c
index 5bddbd5..3fe6a21 100644
--- a/drivers/gpio/gpio-altera.c
+++ b/drivers/gpio/gpio-altera.c
@@ -90,21 +90,18 @@ static int altera_gpio_irq_set_type(struct irq_data *d,
altera_gc = gpiochip_get_data(irq_data_get_irq_chip_data(d));
- if (type == IRQ_TYPE_NONE)
+ if (type == IRQ_TYPE_NONE) {
+ irq_set_handler_locked(d, handle_bad_irq);
return 0;
- if (type == IRQ_TYPE_LEVEL_HIGH &&
- altera_gc->interrupt_trigger == IRQ_TYPE_LEVEL_HIGH)
+ }
+ if (type == altera_gc->interrupt_trigger) {
+ if (type == IRQ_TYPE_LEVEL_HIGH)
+ irq_set_handler_locked(d, handle_level_irq);
+ else
+ irq_set_handler_locked(d, handle_simple_irq);
return 0;
- if (type == IRQ_TYPE_EDGE_RISING &&
- altera_gc->interrupt_trigger == IRQ_TYPE_EDGE_RISING)
- return 0;
- if (type == IRQ_TYPE_EDGE_FALLING &&
- altera_gc->interrupt_trigger == IRQ_TYPE_EDGE_FALLING)
- return 0;
- if (type == IRQ_TYPE_EDGE_BOTH &&
- altera_gc->interrupt_trigger == IRQ_TYPE_EDGE_BOTH)
- return 0;
-
+ }
+ irq_set_handler_locked(d, handle_bad_irq);
return -EINVAL;
}
@@ -230,7 +227,6 @@ static void altera_gpio_irq_edge_handler(struct irq_desc *desc)
chained_irq_exit(chip, desc);
}
-
static void altera_gpio_irq_leveL_high_handler(struct irq_desc *desc)
{
struct altera_gpio_chip *altera_gc;
@@ -310,7 +306,7 @@ static int altera_gpio_probe(struct platform_device *pdev)
altera_gc->interrupt_trigger = reg;
ret = gpiochip_irqchip_add(&altera_gc->mmchip.gc, &altera_irq_chip, 0,
- handle_simple_irq, IRQ_TYPE_NONE);
+ handle_bad_irq, IRQ_TYPE_NONE);
if (ret) {
dev_err(&pdev->dev, "could not add irqchip\n");
diff --git a/drivers/gpio/gpio-mcp23s08.c b/drivers/gpio/gpio-mcp23s08.c
index bdb6923..2a57d024 100644
--- a/drivers/gpio/gpio-mcp23s08.c
+++ b/drivers/gpio/gpio-mcp23s08.c
@@ -270,8 +270,10 @@ mcp23s08_direction_output(struct gpio_chip *chip, unsigned offset, int value)
static irqreturn_t mcp23s08_irq(int irq, void *data)
{
struct mcp23s08 *mcp = data;
- int intcap, intf, i;
+ int intcap, intf, i, gpio, gpio_orig, intcap_mask;
unsigned int child_irq;
+ bool intf_set, intcap_changed, gpio_bit_changed,
+ defval_changed, gpio_set;
mutex_lock(&mcp->lock);
if (mcp_read(mcp, MCP_INTF, &intf) < 0) {
@@ -287,14 +289,67 @@ static irqreturn_t mcp23s08_irq(int irq, void *data)
}
mcp->cache[MCP_INTCAP] = intcap;
+
+ /* This clears the interrupt(configurable on S18) */
+ if (mcp_read(mcp, MCP_GPIO, &gpio) < 0) {
+ mutex_unlock(&mcp->lock);
+ return IRQ_HANDLED;
+ }
+ gpio_orig = mcp->cache[MCP_GPIO];
+ mcp->cache[MCP_GPIO] = gpio;
mutex_unlock(&mcp->lock);
+ if (mcp->cache[MCP_INTF] == 0) {
+ /* There is no interrupt pending */
+ return IRQ_HANDLED;
+ }
+
+ dev_dbg(mcp->chip.parent,
+ "intcap 0x%04X intf 0x%04X gpio_orig 0x%04X gpio 0x%04X\n",
+ intcap, intf, gpio_orig, gpio);
for (i = 0; i < mcp->chip.ngpio; i++) {
- if ((BIT(i) & mcp->cache[MCP_INTF]) &&
- ((BIT(i) & intcap & mcp->irq_rise) ||
- (mcp->irq_fall & ~intcap & BIT(i)) ||
- (BIT(i) & mcp->cache[MCP_INTCON]))) {
+ /* We must check all of the inputs on the chip,
+ * otherwise we may not notice a change on >=2 pins.
+ *
+ * On at least the mcp23s17, INTCAP is only updated
+ * one byte at a time(INTCAPA and INTCAPB are
+ * not written to at the same time - only on a per-bank
+ * basis).
+ *
+ * INTF only contains the single bit that caused the
+ * interrupt per-bank. On the mcp23s17, there is
+ * INTFA and INTFB. If two pins are changed on the A
+ * side at the same time, INTF will only have one bit
+ * set. If one pin on the A side and one pin on the B
+ * side are changed at the same time, INTF will have
+ * two bits set. Thus, INTF can't be the only check
+ * to see if the input has changed.
+ */
+
+ intf_set = BIT(i) & mcp->cache[MCP_INTF];
+ if (i < 8 && intf_set)
+ intcap_mask = 0x00FF;
+ else if (i >= 8 && intf_set)
+ intcap_mask = 0xFF00;
+ else
+ intcap_mask = 0x00;
+
+ intcap_changed = (intcap_mask &
+ (BIT(i) & mcp->cache[MCP_INTCAP])) !=
+ (intcap_mask & (BIT(i) & gpio_orig));
+ gpio_set = BIT(i) & mcp->cache[MCP_GPIO];
+ gpio_bit_changed = (BIT(i) & gpio_orig) !=
+ (BIT(i) & mcp->cache[MCP_GPIO]);
+ defval_changed = (BIT(i) & mcp->cache[MCP_INTCON]) &&
+ ((BIT(i) & mcp->cache[MCP_GPIO]) !=
+ (BIT(i) & mcp->cache[MCP_DEFVAL]));
+
+ if (((gpio_bit_changed || intcap_changed) &&
+ (BIT(i) & mcp->irq_rise) && gpio_set) ||
+ ((gpio_bit_changed || intcap_changed) &&
+ (BIT(i) & mcp->irq_fall) && !gpio_set) ||
+ defval_changed) {
child_irq = irq_find_mapping(mcp->chip.irqdomain, i);
handle_nested_irq(child_irq);
}
diff --git a/drivers/gpio/gpio-mockup.c b/drivers/gpio/gpio-mockup.c
index 06dac72..d993386 100644
--- a/drivers/gpio/gpio-mockup.c
+++ b/drivers/gpio/gpio-mockup.c
@@ -197,7 +197,7 @@ static ssize_t gpio_mockup_event_write(struct file *file,
struct seq_file *sfile;
struct gpio_desc *desc;
struct gpio_chip *gc;
- int status, val;
+ int val;
char buf;
sfile = file->private_data;
@@ -206,9 +206,8 @@ static ssize_t gpio_mockup_event_write(struct file *file,
chip = priv->chip;
gc = &chip->gc;
- status = copy_from_user(&buf, usr_buf, 1);
- if (status)
- return status;
+ if (copy_from_user(&buf, usr_buf, 1))
+ return -EFAULT;
if (buf == '0')
val = 0;
diff --git a/drivers/gpio/gpio-xgene.c b/drivers/gpio/gpio-xgene.c
index 40a8881..f1c6ec1 100644
--- a/drivers/gpio/gpio-xgene.c
+++ b/drivers/gpio/gpio-xgene.c
@@ -42,9 +42,7 @@ struct xgene_gpio {
struct gpio_chip chip;
void __iomem *base;
spinlock_t lock;
-#ifdef CONFIG_PM
u32 set_dr_val[XGENE_MAX_GPIO_BANKS];
-#endif
};
static int xgene_gpio_get(struct gpio_chip *gc, unsigned int offset)
@@ -138,8 +136,7 @@ static int xgene_gpio_dir_out(struct gpio_chip *gc,
return 0;
}
-#ifdef CONFIG_PM
-static int xgene_gpio_suspend(struct device *dev)
+static __maybe_unused int xgene_gpio_suspend(struct device *dev)
{
struct xgene_gpio *gpio = dev_get_drvdata(dev);
unsigned long bank_offset;
@@ -152,7 +149,7 @@ static int xgene_gpio_suspend(struct device *dev)
return 0;
}
-static int xgene_gpio_resume(struct device *dev)
+static __maybe_unused int xgene_gpio_resume(struct device *dev)
{
struct xgene_gpio *gpio = dev_get_drvdata(dev);
unsigned long bank_offset;
@@ -166,10 +163,6 @@ static int xgene_gpio_resume(struct device *dev)
}
static SIMPLE_DEV_PM_OPS(xgene_gpio_pm, xgene_gpio_suspend, xgene_gpio_resume);
-#define XGENE_GPIO_PM_OPS (&xgene_gpio_pm)
-#else
-#define XGENE_GPIO_PM_OPS NULL
-#endif
static int xgene_gpio_probe(struct platform_device *pdev)
{
@@ -241,7 +234,7 @@ static struct platform_driver xgene_gpio_driver = {
.name = "xgene-gpio",
.of_match_table = xgene_gpio_of_match,
.acpi_match_table = ACPI_PTR(xgene_gpio_acpi_match),
- .pm = XGENE_GPIO_PM_OPS,
+ .pm = &xgene_gpio_pm,
},
.probe = xgene_gpio_probe,
};
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 9b37a36..2bd683e 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -266,6 +266,9 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares,
goto fail_free_event;
}
+ if (agpio->wake_capable == ACPI_WAKE_CAPABLE)
+ enable_irq_wake(irq);
+
list_add_tail(&event->node, &acpi_gpio->events);
return AE_OK;
@@ -339,6 +342,9 @@ void acpi_gpiochip_free_interrupts(struct gpio_chip *chip)
list_for_each_entry_safe_reverse(event, ep, &acpi_gpio->events, node) {
struct gpio_desc *desc;
+ if (irqd_is_wakeup_set(irq_get_irq_data(event->irq)))
+ disable_irq_wake(event->irq);
+
free_irq(event->irq, event);
desc = event->desc;
if (WARN_ON(IS_ERR(desc)))
@@ -571,8 +577,10 @@ struct gpio_desc *acpi_find_gpio(struct device *dev,
}
desc = acpi_get_gpiod_by_index(adev, propname, idx, &info);
- if (!IS_ERR(desc) || (PTR_ERR(desc) == -EPROBE_DEFER))
+ if (!IS_ERR(desc))
break;
+ if (PTR_ERR(desc) == -EPROBE_DEFER)
+ return ERR_CAST(desc);
}
/* Then from plain _CRS GPIOs */
diff --git a/drivers/gpu/drm/amd/acp/Makefile b/drivers/gpu/drm/amd/acp/Makefile
index 8363cb5..8a08e81 100644
--- a/drivers/gpu/drm/amd/acp/Makefile
+++ b/drivers/gpu/drm/amd/acp/Makefile
@@ -3,6 +3,4 @@
# of AMDSOC/AMDGPU drm driver.
# It provides the HW control for ACP related functionalities.
-subdir-ccflags-y += -I$(AMDACPPATH)/ -I$(AMDACPPATH)/include
-
AMD_ACP_FILES := $(AMDACPPATH)/acp_hw.o
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index d2d0f60..99424cb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -240,6 +240,8 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
for (; i >= 0; i--)
drm_free_large(p->chunks[i].kdata);
kfree(p->chunks);
+ p->chunks = NULL;
+ p->nchunks = 0;
put_ctx:
amdgpu_ctx_put(p->ctx);
free_chunk:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 6abb238..de0cf33 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -475,7 +475,7 @@ static int amdgpu_wb_init(struct amdgpu_device *adev)
int r;
if (adev->wb.wb_obj == NULL) {
- r = amdgpu_bo_create_kernel(adev, AMDGPU_MAX_WB * 4,
+ r = amdgpu_bo_create_kernel(adev, AMDGPU_MAX_WB * sizeof(uint32_t),
PAGE_SIZE, AMDGPU_GEM_DOMAIN_GTT,
&adev->wb.wb_obj, &adev->wb.gpu_addr,
(void **)&adev->wb.wb);
@@ -488,7 +488,7 @@ static int amdgpu_wb_init(struct amdgpu_device *adev)
memset(&adev->wb.used, 0, sizeof(adev->wb.used));
/* clear wb memory */
- memset((char *)adev->wb.wb, 0, AMDGPU_GPU_PAGE_SIZE);
+ memset((char *)adev->wb.wb, 0, AMDGPU_MAX_WB * sizeof(uint32_t));
}
return 0;
@@ -2094,8 +2094,11 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
}
r = amdgpu_late_init(adev);
- if (r)
+ if (r) {
+ if (fbcon)
+ console_unlock();
return r;
+ }
/* pin cursors */
list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
@@ -2587,7 +2590,7 @@ static ssize_t amdgpu_debugfs_regs_read(struct file *f, char __user *buf,
use_bank = 0;
}
- *pos &= 0x3FFFF;
+ *pos &= (1UL << 22) - 1;
if (use_bank) {
if ((sh_bank != 0xFFFFFFFF && sh_bank >= adev->gfx.config.max_sh_per_se) ||
@@ -2663,7 +2666,7 @@ static ssize_t amdgpu_debugfs_regs_write(struct file *f, const char __user *buf,
use_bank = 0;
}
- *pos &= 0x3FFFF;
+ *pos &= (1UL << 22) - 1;
if (use_bank) {
if ((sh_bank != 0xFFFFFFFF && sh_bank >= adev->gfx.config.max_sh_per_se) ||
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 75fc376..b76cd69 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -59,9 +59,10 @@
* - 3.7.0 - Add support for VCE clock list packet
* - 3.8.0 - Add support raster config init in the kernel
* - 3.9.0 - Add support for memory query info about VRAM and GTT.
+ * - 3.10.0 - Add support for new fences ioctl, new gem ioctl flags
*/
#define KMS_DRIVER_MAJOR 3
-#define KMS_DRIVER_MINOR 9
+#define KMS_DRIVER_MINOR 10
#define KMS_DRIVER_PATCHLEVEL 0
int amdgpu_vram_limit = 0;
@@ -420,6 +421,7 @@ static const struct pci_device_id pciidlist[] = {
{0x1002, 0x6985, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12},
{0x1002, 0x6986, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12},
{0x1002, 0x6987, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12},
+ {0x1002, 0x6995, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12},
{0x1002, 0x699F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12},
{0, 0, 0}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 51d7594..106cf83 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -202,6 +202,27 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
bool kernel = false;
int r;
+ /* reject invalid gem flags */
+ if (args->in.domain_flags & ~(AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
+ AMDGPU_GEM_CREATE_NO_CPU_ACCESS |
+ AMDGPU_GEM_CREATE_CPU_GTT_USWC |
+ AMDGPU_GEM_CREATE_VRAM_CLEARED|
+ AMDGPU_GEM_CREATE_SHADOW |
+ AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)) {
+ r = -EINVAL;
+ goto error_unlock;
+ }
+ /* reject invalid gem domains */
+ if (args->in.domains & ~(AMDGPU_GEM_DOMAIN_CPU |
+ AMDGPU_GEM_DOMAIN_GTT |
+ AMDGPU_GEM_DOMAIN_VRAM |
+ AMDGPU_GEM_DOMAIN_GDS |
+ AMDGPU_GEM_DOMAIN_GWS |
+ AMDGPU_GEM_DOMAIN_OA)) {
+ r = -EINVAL;
+ goto error_unlock;
+ }
+
/* create a gem object to contain this object in */
if (args->in.domains & (AMDGPU_GEM_DOMAIN_GDS |
AMDGPU_GEM_DOMAIN_GWS | AMDGPU_GEM_DOMAIN_OA)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 31375bd..011800f 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -788,7 +788,7 @@ static int sdma_v3_0_start(struct amdgpu_device *adev)
}
}
- /* disble sdma engine before programing it */
+ /* disable sdma engine before programing it */
sdma_v3_0_ctx_switch_enable(adev, false);
sdma_v3_0_enable(adev, false);
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
index f55e45b..c5dec21 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
@@ -3464,6 +3464,16 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev,
(adev->pdev->device == 0x6667)) {
max_sclk = 75000;
}
+ } else if (adev->asic_type == CHIP_OLAND) {
+ if ((adev->pdev->revision == 0xC7) ||
+ (adev->pdev->revision == 0x80) ||
+ (adev->pdev->revision == 0x81) ||
+ (adev->pdev->revision == 0x83) ||
+ (adev->pdev->revision == 0x87) ||
+ (adev->pdev->device == 0x6604) ||
+ (adev->pdev->device == 0x6605)) {
+ max_sclk = 75000;
+ }
}
if (rps->vce_active) {
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 50bdb24..4a785d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -1051,7 +1051,7 @@ static int vi_common_early_init(void *handle)
/* rev0 hardware requires workarounds to support PG */
adev->pg_flags = 0;
if (adev->rev_id != 0x00) {
- adev->pg_flags |= AMD_PG_SUPPORT_GFX_PG |
+ adev->pg_flags |=
AMD_PG_SUPPORT_GFX_SMG |
AMD_PG_SUPPORT_GFX_PIPELINE |
AMD_PG_SUPPORT_CP |
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
index 8cf71f3..261b828 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
@@ -178,7 +178,7 @@ int smu7_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate)
if (bgate) {
cgs_set_powergating_state(hwmgr->device,
AMD_IP_BLOCK_TYPE_VCE,
- AMD_PG_STATE_UNGATE);
+ AMD_PG_STATE_GATE);
cgs_set_clockgating_state(hwmgr->device,
AMD_IP_BLOCK_TYPE_VCE,
AMD_CG_STATE_GATE);
diff --git a/drivers/gpu/drm/arm/malidp_crtc.c b/drivers/gpu/drm/arm/malidp_crtc.c
index 08e6a71..294b536 100644
--- a/drivers/gpu/drm/arm/malidp_crtc.c
+++ b/drivers/gpu/drm/arm/malidp_crtc.c
@@ -63,8 +63,7 @@ static void malidp_crtc_enable(struct drm_crtc *crtc)
clk_prepare_enable(hwdev->pxlclk);
- /* mclk needs to be set to the same or higher rate than pxlclk */
- clk_set_rate(hwdev->mclk, crtc->state->adjusted_mode.crtc_clock * 1000);
+ /* We rely on firmware to set mclk to a sensible level. */
clk_set_rate(hwdev->pxlclk, crtc->state->adjusted_mode.crtc_clock * 1000);
hwdev->modeset(hwdev, &vm);
diff --git a/drivers/gpu/drm/arm/malidp_hw.c b/drivers/gpu/drm/arm/malidp_hw.c
index 488aedf..9f55130 100644
--- a/drivers/gpu/drm/arm/malidp_hw.c
+++ b/drivers/gpu/drm/arm/malidp_hw.c
@@ -83,7 +83,7 @@ static const struct malidp_layer malidp550_layers[] = {
{ DE_VIDEO1, MALIDP550_DE_LV1_BASE, MALIDP550_DE_LV1_PTR_BASE, MALIDP_DE_LV_STRIDE0 },
{ DE_GRAPHICS1, MALIDP550_DE_LG_BASE, MALIDP550_DE_LG_PTR_BASE, MALIDP_DE_LG_STRIDE },
{ DE_VIDEO2, MALIDP550_DE_LV2_BASE, MALIDP550_DE_LV2_PTR_BASE, MALIDP_DE_LV_STRIDE0 },
- { DE_SMART, MALIDP550_DE_LS_BASE, MALIDP550_DE_LS_PTR_BASE, 0 },
+ { DE_SMART, MALIDP550_DE_LS_BASE, MALIDP550_DE_LS_PTR_BASE, MALIDP550_DE_LS_R1_STRIDE },
};
#define MALIDP_DE_DEFAULT_PREFETCH_START 5
diff --git a/drivers/gpu/drm/arm/malidp_planes.c b/drivers/gpu/drm/arm/malidp_planes.c
index 414aada..d5aec08 100644
--- a/drivers/gpu/drm/arm/malidp_planes.c
+++ b/drivers/gpu/drm/arm/malidp_planes.c
@@ -37,6 +37,8 @@
#define LAYER_V_VAL(x) (((x) & 0x1fff) << 16)
#define MALIDP_LAYER_COMP_SIZE 0x010
#define MALIDP_LAYER_OFFSET 0x014
+#define MALIDP550_LS_ENABLE 0x01c
+#define MALIDP550_LS_R1_IN_SIZE 0x020
/*
* This 4-entry look-up-table is used to determine the full 8-bit alpha value
@@ -242,6 +244,11 @@ static void malidp_de_plane_update(struct drm_plane *plane,
LAYER_V_VAL(plane->state->crtc_y),
mp->layer->base + MALIDP_LAYER_OFFSET);
+ if (mp->layer->id == DE_SMART)
+ malidp_hw_write(mp->hwdev,
+ LAYER_H_VAL(src_w) | LAYER_V_VAL(src_h),
+ mp->layer->base + MALIDP550_LS_R1_IN_SIZE);
+
/* first clear the rotation bits */
val = malidp_hw_read(mp->hwdev, mp->layer->base + MALIDP_LAYER_CONTROL);
val &= ~LAYER_ROT_MASK;
@@ -330,9 +337,16 @@ int malidp_de_planes_init(struct drm_device *drm)
plane->hwdev = malidp->dev;
plane->layer = &map->layers[i];
- /* Skip the features which the SMART layer doesn't have */
- if (id == DE_SMART)
+ if (id == DE_SMART) {
+ /*
+ * Enable the first rectangle in the SMART layer to be
+ * able to use it as a drm plane.
+ */
+ malidp_hw_write(malidp->dev, 1,
+ plane->layer->base + MALIDP550_LS_ENABLE);
+ /* Skip the features which the SMART layer doesn't have. */
continue;
+ }
drm_plane_create_rotation_property(&plane->base, DRM_ROTATE_0, flags);
malidp_hw_write(malidp->dev, MALIDP_ALPHA_LUT,
diff --git a/drivers/gpu/drm/arm/malidp_regs.h b/drivers/gpu/drm/arm/malidp_regs.h
index aff6d4a..b816067 100644
--- a/drivers/gpu/drm/arm/malidp_regs.h
+++ b/drivers/gpu/drm/arm/malidp_regs.h
@@ -84,6 +84,7 @@
/* Stride register offsets relative to Lx_BASE */
#define MALIDP_DE_LG_STRIDE 0x18
#define MALIDP_DE_LV_STRIDE0 0x18
+#define MALIDP550_DE_LS_R1_STRIDE 0x28
/* macros to set values into registers */
#define MALIDP_DE_H_FRONTPORCH(x) (((x) & 0xfff) << 0)
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index c8baab9..ba58f1b 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -148,6 +148,9 @@ static const struct edid_quirk {
/* Panel in Samsung NP700G7A-S01PL notebook reports 6bpc */
{ "SEC", 0xd033, EDID_QUIRK_FORCE_8BPC },
+
+ /* Rotel RSX-1058 forwards sink's EDID but only does HDMI 1.1*/
+ { "ETR", 13896, EDID_QUIRK_FORCE_8BPC },
};
/*
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index f6d4d97..324a688 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -1260,9 +1260,9 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var,
* to KMS, hence fail if different settings are requested.
*/
if (var->bits_per_pixel != fb->format->cpp[0] * 8 ||
- var->xres != fb->width || var->yres != fb->height ||
- var->xres_virtual != fb->width || var->yres_virtual != fb->height) {
- DRM_DEBUG("fb userspace requested width/height/bpp different than current fb "
+ var->xres > fb->width || var->yres > fb->height ||
+ var->xres_virtual > fb->width || var->yres_virtual > fb->height) {
+ DRM_DEBUG("fb requested width/height/bpp can't fit in current fb "
"request %dx%d-%d (virtual %dx%d) > %dx%d-%d\n",
var->xres, var->yres, var->bits_per_pixel,
var->xres_virtual, var->yres_virtual,
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
index 130d7d5..da48819 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
@@ -1311,6 +1311,8 @@ int etnaviv_gpu_submit(struct etnaviv_gpu *gpu,
goto out_pm_put;
}
+ mutex_lock(&gpu->lock);
+
fence = etnaviv_gpu_fence_alloc(gpu);
if (!fence) {
event_free(gpu, event);
@@ -1318,8 +1320,6 @@ int etnaviv_gpu_submit(struct etnaviv_gpu *gpu,
goto out_pm_put;
}
- mutex_lock(&gpu->lock);
-
gpu->event[event].fence = fence;
submit->fence = fence->seqno;
gpu->active_fence = submit->fence;
diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index 0fd6f7a..c0e8d33 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -68,6 +68,8 @@ struct decon_context {
unsigned long flags;
unsigned long out_type;
int first_win;
+ spinlock_t vblank_lock;
+ u32 frame_id;
};
static const uint32_t decon_formats[] = {
@@ -103,7 +105,7 @@ static int decon_enable_vblank(struct exynos_drm_crtc *crtc)
if (ctx->out_type & IFTYPE_I80)
val |= VIDINTCON0_FRAMEDONE;
else
- val |= VIDINTCON0_INTFRMEN;
+ val |= VIDINTCON0_INTFRMEN | VIDINTCON0_FRAMESEL_FP;
writel(val, ctx->addr + DECON_VIDINTCON0);
}
@@ -122,14 +124,56 @@ static void decon_disable_vblank(struct exynos_drm_crtc *crtc)
writel(0, ctx->addr + DECON_VIDINTCON0);
}
+/* return number of starts/ends of frame transmissions since reset */
+static u32 decon_get_frame_count(struct decon_context *ctx, bool end)
+{
+ u32 frm, pfrm, status, cnt = 2;
+
+ /* To get consistent result repeat read until frame id is stable.
+ * Usually the loop will be executed once, in rare cases when the loop
+ * is executed at frame change time 2nd pass will be needed.
+ */
+ frm = readl(ctx->addr + DECON_CRFMID);
+ do {
+ status = readl(ctx->addr + DECON_VIDCON1);
+ pfrm = frm;
+ frm = readl(ctx->addr + DECON_CRFMID);
+ } while (frm != pfrm && --cnt);
+
+ /* CRFMID is incremented on BPORCH in case of I80 and on VSYNC in case
+ * of RGB, it should be taken into account.
+ */
+ if (!frm)
+ return 0;
+
+ switch (status & (VIDCON1_VSTATUS_MASK | VIDCON1_I80_ACTIVE)) {
+ case VIDCON1_VSTATUS_VS:
+ if (!(ctx->out_type & IFTYPE_I80))
+ --frm;
+ break;
+ case VIDCON1_VSTATUS_BP:
+ --frm;
+ break;
+ case VIDCON1_I80_ACTIVE:
+ case VIDCON1_VSTATUS_AC:
+ if (end)
+ --frm;
+ break;
+ default:
+ break;
+ }
+
+ return frm;
+}
+
static void decon_setup_trigger(struct decon_context *ctx)
{
if (!(ctx->out_type & (IFTYPE_I80 | I80_HW_TRG)))
return;
if (!(ctx->out_type & I80_HW_TRG)) {
- writel(TRIGCON_TE_AUTO_MASK | TRIGCON_SWTRIGEN
- | TRIGCON_TE_AUTO_MASK | TRIGCON_SWTRIGEN,
+ writel(TRIGCON_TRIGEN_PER_F | TRIGCON_TRIGEN_F |
+ TRIGCON_TE_AUTO_MASK | TRIGCON_SWTRIGEN,
ctx->addr + DECON_TRIGCON);
return;
}
@@ -365,11 +409,14 @@ static void decon_disable_plane(struct exynos_drm_crtc *crtc,
static void decon_atomic_flush(struct exynos_drm_crtc *crtc)
{
struct decon_context *ctx = crtc->ctx;
+ unsigned long flags;
int i;
if (test_bit(BIT_SUSPENDED, &ctx->flags))
return;
+ spin_lock_irqsave(&ctx->vblank_lock, flags);
+
for (i = ctx->first_win; i < WINDOWS_NR; i++)
decon_shadow_protect_win(ctx, i, false);
@@ -378,11 +425,18 @@ static void decon_atomic_flush(struct exynos_drm_crtc *crtc)
if (ctx->out_type & IFTYPE_I80)
set_bit(BIT_WIN_UPDATED, &ctx->flags);
+
+ ctx->frame_id = decon_get_frame_count(ctx, true);
+
+ exynos_crtc_handle_event(crtc);
+
+ spin_unlock_irqrestore(&ctx->vblank_lock, flags);
}
static void decon_swreset(struct decon_context *ctx)
{
unsigned int tries;
+ unsigned long flags;
writel(0, ctx->addr + DECON_VIDCON0);
for (tries = 2000; tries; --tries) {
@@ -400,6 +454,10 @@ static void decon_swreset(struct decon_context *ctx)
WARN(tries == 0, "failed to software reset DECON\n");
+ spin_lock_irqsave(&ctx->vblank_lock, flags);
+ ctx->frame_id = 0;
+ spin_unlock_irqrestore(&ctx->vblank_lock, flags);
+
if (!(ctx->out_type & IFTYPE_HDMI))
return;
@@ -578,6 +636,24 @@ static const struct component_ops decon_component_ops = {
.unbind = decon_unbind,
};
+static void decon_handle_vblank(struct decon_context *ctx)
+{
+ u32 frm;
+
+ spin_lock(&ctx->vblank_lock);
+
+ frm = decon_get_frame_count(ctx, true);
+
+ if (frm != ctx->frame_id) {
+ /* handle only if incremented, take care of wrap-around */
+ if ((s32)(frm - ctx->frame_id) > 0)
+ drm_crtc_handle_vblank(&ctx->crtc->base);
+ ctx->frame_id = frm;
+ }
+
+ spin_unlock(&ctx->vblank_lock);
+}
+
static irqreturn_t decon_irq_handler(int irq, void *dev_id)
{
struct decon_context *ctx = dev_id;
@@ -598,7 +674,7 @@ static irqreturn_t decon_irq_handler(int irq, void *dev_id)
(VIDOUT_INTERLACE_EN_F | VIDOUT_INTERLACE_FIELD_F))
return IRQ_HANDLED;
}
- drm_crtc_handle_vblank(&ctx->crtc->base);
+ decon_handle_vblank(ctx);
}
out:
@@ -671,6 +747,7 @@ static int exynos5433_decon_probe(struct platform_device *pdev)
__set_bit(BIT_SUSPENDED, &ctx->flags);
ctx->dev = dev;
ctx->out_type = (unsigned long)of_device_get_match_data(dev);
+ spin_lock_init(&ctx->vblank_lock);
if (ctx->out_type & IFTYPE_HDMI) {
ctx->first_win = 1;
@@ -678,7 +755,7 @@ static int exynos5433_decon_probe(struct platform_device *pdev)
ctx->out_type |= IFTYPE_I80;
}
- if (ctx->out_type | I80_HW_TRG) {
+ if (ctx->out_type & I80_HW_TRG) {
ctx->sysreg = syscon_regmap_lookup_by_phandle(dev->of_node,
"samsung,disp-sysreg");
if (IS_ERR(ctx->sysreg)) {
diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index f9ab19e..4881180 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -526,6 +526,7 @@ static void decon_atomic_flush(struct exynos_drm_crtc *crtc)
for (i = 0; i < WINDOWS_NR; i++)
decon_shadow_protect_win(ctx, i, false);
+ exynos_crtc_handle_event(crtc);
}
static void decon_init(struct decon_context *ctx)
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
index 5367b66..c65f450 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
@@ -85,24 +85,9 @@ static void exynos_crtc_atomic_flush(struct drm_crtc *crtc,
struct drm_crtc_state *old_crtc_state)
{
struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc);
- struct drm_pending_vblank_event *event;
- unsigned long flags;
if (exynos_crtc->ops->atomic_flush)
exynos_crtc->ops->atomic_flush(exynos_crtc);
-
- event = crtc->state->event;
- if (event) {
- crtc->state->event = NULL;
-
- spin_lock_irqsave(&crtc->dev->event_lock, flags);
- if (drm_crtc_vblank_get(crtc) == 0)
- drm_crtc_arm_vblank_event(crtc, event);
- else
- drm_crtc_send_vblank_event(crtc, event);
- spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
- }
-
}
static const struct drm_crtc_helper_funcs exynos_crtc_helper_funcs = {
@@ -114,6 +99,24 @@ static const struct drm_crtc_helper_funcs exynos_crtc_helper_funcs = {
.atomic_flush = exynos_crtc_atomic_flush,
};
+void exynos_crtc_handle_event(struct exynos_drm_crtc *exynos_crtc)
+{
+ struct drm_crtc *crtc = &exynos_crtc->base;
+ struct drm_pending_vblank_event *event = crtc->state->event;
+ unsigned long flags;
+
+ if (event) {
+ crtc->state->event = NULL;
+ spin_lock_irqsave(&crtc->dev->event_lock, flags);
+ if (drm_crtc_vblank_get(crtc) == 0)
+ drm_crtc_arm_vblank_event(crtc, event);
+ else
+ drm_crtc_send_vblank_event(crtc, event);
+ spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+ }
+
+}
+
static void exynos_drm_crtc_destroy(struct drm_crtc *crtc)
{
struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.h b/drivers/gpu/drm/exynos/exynos_drm_crtc.h
index 6a581a8..abd5d6c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.h
@@ -40,4 +40,6 @@ int exynos_drm_crtc_get_pipe_from_type(struct drm_device *drm_dev,
*/
void exynos_drm_crtc_te_handler(struct drm_crtc *crtc);
+void exynos_crtc_handle_event(struct exynos_drm_crtc *exynos_crtc);
+
#endif
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index 812e2ec..d7ef263 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -86,7 +86,7 @@
#define DSIM_SYNC_INFORM (1 << 27)
#define DSIM_EOT_DISABLE (1 << 28)
#define DSIM_MFLUSH_VS (1 << 29)
-/* This flag is valid only for exynos3250/3472/4415/5260/5430 */
+/* This flag is valid only for exynos3250/3472/5260/5430 */
#define DSIM_CLKLANE_STOP (1 << 30)
/* DSIM_ESCMODE */
@@ -473,17 +473,6 @@ static const struct exynos_dsi_driver_data exynos4_dsi_driver_data = {
.reg_values = reg_values,
};
-static const struct exynos_dsi_driver_data exynos4415_dsi_driver_data = {
- .reg_ofs = exynos_reg_ofs,
- .plltmr_reg = 0x58,
- .has_clklane_stop = 1,
- .num_clks = 2,
- .max_freq = 1000,
- .wait_for_reset = 1,
- .num_bits_resol = 11,
- .reg_values = reg_values,
-};
-
static const struct exynos_dsi_driver_data exynos5_dsi_driver_data = {
.reg_ofs = exynos_reg_ofs,
.plltmr_reg = 0x58,
@@ -521,8 +510,6 @@ static const struct of_device_id exynos_dsi_of_match[] = {
.data = &exynos3_dsi_driver_data },
{ .compatible = "samsung,exynos4210-mipi-dsi",
.data = &exynos4_dsi_driver_data },
- { .compatible = "samsung,exynos4415-mipi-dsi",
- .data = &exynos4415_dsi_driver_data },
{ .compatible = "samsung,exynos5410-mipi-dsi",
.data = &exynos5_dsi_driver_data },
{ .compatible = "samsung,exynos5422-mipi-dsi",
@@ -979,7 +966,7 @@ static void exynos_dsi_send_to_fifo(struct exynos_dsi *dsi,
bool first = !xfer->tx_done;
u32 reg;
- dev_dbg(dev, "< xfer %p: tx len %u, done %u, rx len %u, done %u\n",
+ dev_dbg(dev, "< xfer %pK: tx len %u, done %u, rx len %u, done %u\n",
xfer, length, xfer->tx_done, xfer->rx_len, xfer->rx_done);
if (length > DSI_TX_FIFO_SIZE)
@@ -1177,7 +1164,7 @@ static bool exynos_dsi_transfer_finish(struct exynos_dsi *dsi)
spin_unlock_irqrestore(&dsi->transfer_lock, flags);
dev_dbg(dsi->dev,
- "> xfer %p, tx_len %zu, tx_done %u, rx_len %u, rx_done %u\n",
+ "> xfer %pK, tx_len %zu, tx_done %u, rx_len %u, rx_done %u\n",
xfer, xfer->packet.payload_length, xfer->tx_done, xfer->rx_len,
xfer->rx_done);
@@ -1348,9 +1335,12 @@ static int exynos_dsi_register_te_irq(struct exynos_dsi *dsi)
int te_gpio_irq;
dsi->te_gpio = of_get_named_gpio(dsi->panel_node, "te-gpios", 0);
+ if (dsi->te_gpio == -ENOENT)
+ return 0;
+
if (!gpio_is_valid(dsi->te_gpio)) {
- dev_err(dsi->dev, "no te-gpios specified\n");
ret = dsi->te_gpio;
+ dev_err(dsi->dev, "cannot get te-gpios, %d\n", ret);
goto out;
}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
index 95871577..5b18b5c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -1695,7 +1695,7 @@ static int fimc_probe(struct platform_device *pdev)
goto err_put_clk;
}
- DRM_DEBUG_KMS("id[%d]ippdrv[%p]\n", ctx->id, ippdrv);
+ DRM_DEBUG_KMS("id[%d]ippdrv[%pK]\n", ctx->id, ippdrv);
spin_lock_init(&ctx->lock);
platform_set_drvdata(pdev, ctx);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index a9fa444..3f04d72 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -71,10 +71,10 @@
#define TRIGCON 0x1A4
#define TRGMODE_ENABLE (1 << 0)
#define SWTRGCMD_ENABLE (1 << 1)
-/* Exynos3250, 3472, 4415, 5260 5410, 5420 and 5422 only supported. */
+/* Exynos3250, 3472, 5260 5410, 5420 and 5422 only supported. */
#define HWTRGEN_ENABLE (1 << 3)
#define HWTRGMASK_ENABLE (1 << 4)
-/* Exynos3250, 3472, 4415, 5260, 5420 and 5422 only supported. */
+/* Exynos3250, 3472, 5260, 5420 and 5422 only supported. */
#define HWTRIGEN_PER_ENABLE (1 << 31)
/* display mode change control register except exynos4 */
@@ -138,18 +138,6 @@ static struct fimd_driver_data exynos4_fimd_driver_data = {
.has_vtsel = 1,
};
-static struct fimd_driver_data exynos4415_fimd_driver_data = {
- .timing_base = 0x20000,
- .lcdblk_offset = 0x210,
- .lcdblk_vt_shift = 10,
- .lcdblk_bypass_shift = 1,
- .trg_type = I80_HW_TRG,
- .has_shadowcon = 1,
- .has_vidoutcon = 1,
- .has_vtsel = 1,
- .has_trigger_per_te = 1,
-};
-
static struct fimd_driver_data exynos5_fimd_driver_data = {
.timing_base = 0x20000,
.lcdblk_offset = 0x214,
@@ -210,8 +198,6 @@ static const struct of_device_id fimd_driver_dt_match[] = {
.data = &exynos3_fimd_driver_data },
{ .compatible = "samsung,exynos4210-fimd",
.data = &exynos4_fimd_driver_data },
- { .compatible = "samsung,exynos4415-fimd",
- .data = &exynos4415_fimd_driver_data },
{ .compatible = "samsung,exynos5250-fimd",
.data = &exynos5_fimd_driver_data },
{ .compatible = "samsung,exynos5420-fimd",
@@ -257,7 +243,7 @@ static int fimd_enable_vblank(struct exynos_drm_crtc *crtc)
val |= VIDINTCON0_INT_FRAME;
val &= ~VIDINTCON0_FRAMESEL0_MASK;
- val |= VIDINTCON0_FRAMESEL0_VSYNC;
+ val |= VIDINTCON0_FRAMESEL0_FRONTPORCH;
val &= ~VIDINTCON0_FRAMESEL1_MASK;
val |= VIDINTCON0_FRAMESEL1_NONE;
}
@@ -723,6 +709,8 @@ static void fimd_atomic_flush(struct exynos_drm_crtc *crtc)
for (i = 0; i < WINDOWS_NR; i++)
fimd_shadow_protect_win(ctx, i, false);
+
+ exynos_crtc_handle_event(crtc);
}
static void fimd_update_plane(struct exynos_drm_crtc *crtc,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index 4c28f7f..55a1579 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -218,7 +218,7 @@ static struct exynos_drm_gem *exynos_drm_gem_init(struct drm_device *dev,
return ERR_PTR(ret);
}
- DRM_DEBUG_KMS("created file object = %p\n", obj->filp);
+ DRM_DEBUG_KMS("created file object = %pK\n", obj->filp);
return exynos_gem;
}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
index bef5798..0506b2b 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
@@ -1723,7 +1723,7 @@ static int gsc_probe(struct platform_device *pdev)
return ret;
}
- DRM_DEBUG_KMS("id[%d]ippdrv[%p]\n", ctx->id, ippdrv);
+ DRM_DEBUG_KMS("id[%d]ippdrv[%pK]\n", ctx->id, ippdrv);
mutex_init(&ctx->lock);
platform_set_drvdata(pdev, ctx);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
index 9c84ee7..3edda18 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
@@ -208,7 +208,7 @@ static struct exynos_drm_ippdrv *ipp_find_drv_by_handle(u32 prop_id)
* e.g PAUSE state, queue buf, command control.
*/
list_for_each_entry(ippdrv, &exynos_drm_ippdrv_list, drv_list) {
- DRM_DEBUG_KMS("count[%d]ippdrv[%p]\n", count++, ippdrv);
+ DRM_DEBUG_KMS("count[%d]ippdrv[%pK]\n", count++, ippdrv);
mutex_lock(&ippdrv->cmd_lock);
list_for_each_entry(c_node, &ippdrv->cmd_list, list) {
@@ -388,7 +388,7 @@ int exynos_drm_ipp_set_property(struct drm_device *drm_dev, void *data,
}
property->prop_id = ret;
- DRM_DEBUG_KMS("created prop_id[%d]cmd[%d]ippdrv[%p]\n",
+ DRM_DEBUG_KMS("created prop_id[%d]cmd[%d]ippdrv[%pK]\n",
property->prop_id, property->cmd, ippdrv);
/* stored property information and ippdrv in private data */
@@ -518,7 +518,7 @@ static int ipp_put_mem_node(struct drm_device *drm_dev,
{
int i;
- DRM_DEBUG_KMS("node[%p]\n", m_node);
+ DRM_DEBUG_KMS("node[%pK]\n", m_node);
if (!m_node) {
DRM_ERROR("invalid dequeue node.\n");
@@ -562,7 +562,7 @@ static struct drm_exynos_ipp_mem_node
m_node->buf_id = qbuf->buf_id;
INIT_LIST_HEAD(&m_node->list);
- DRM_DEBUG_KMS("m_node[%p]ops_id[%d]\n", m_node, qbuf->ops_id);
+ DRM_DEBUG_KMS("m_node[%pK]ops_id[%d]\n", m_node, qbuf->ops_id);
DRM_DEBUG_KMS("prop_id[%d]buf_id[%d]\n", qbuf->prop_id, m_node->buf_id);
for_each_ipp_planar(i) {
@@ -659,7 +659,7 @@ static void ipp_put_event(struct drm_exynos_ipp_cmd_node *c_node,
mutex_lock(&c_node->event_lock);
list_for_each_entry_safe(e, te, &c_node->event_list, base.link) {
- DRM_DEBUG_KMS("count[%d]e[%p]\n", count++, e);
+ DRM_DEBUG_KMS("count[%d]e[%pK]\n", count++, e);
/*
* qbuf == NULL condition means all event deletion.
@@ -750,7 +750,7 @@ static struct drm_exynos_ipp_mem_node
/* find memory node from memory list */
list_for_each_entry(m_node, head, list) {
- DRM_DEBUG_KMS("count[%d]m_node[%p]\n", count++, m_node);
+ DRM_DEBUG_KMS("count[%d]m_node[%pK]\n", count++, m_node);
/* compare buffer id */
if (m_node->buf_id == qbuf->buf_id)
@@ -767,7 +767,7 @@ static int ipp_set_mem_node(struct exynos_drm_ippdrv *ippdrv,
struct exynos_drm_ipp_ops *ops = NULL;
int ret = 0;
- DRM_DEBUG_KMS("node[%p]\n", m_node);
+ DRM_DEBUG_KMS("node[%pK]\n", m_node);
if (!m_node) {
DRM_ERROR("invalid queue node.\n");
@@ -1232,7 +1232,7 @@ static int ipp_start_property(struct exynos_drm_ippdrv *ippdrv,
m_node = list_first_entry(head,
struct drm_exynos_ipp_mem_node, list);
- DRM_DEBUG_KMS("m_node[%p]\n", m_node);
+ DRM_DEBUG_KMS("m_node[%pK]\n", m_node);
ret = ipp_set_mem_node(ippdrv, c_node, m_node);
if (ret) {
@@ -1601,7 +1601,7 @@ static int ipp_subdrv_probe(struct drm_device *drm_dev, struct device *dev)
}
ippdrv->prop_list.ipp_id = ret;
- DRM_DEBUG_KMS("count[%d]ippdrv[%p]ipp_id[%d]\n",
+ DRM_DEBUG_KMS("count[%d]ippdrv[%pK]ipp_id[%d]\n",
count++, ippdrv, ret);
/* store parent device for node */
@@ -1659,7 +1659,7 @@ static int ipp_subdrv_open(struct drm_device *drm_dev, struct device *dev,
file_priv->ipp_dev = dev;
- DRM_DEBUG_KMS("done priv[%p]\n", dev);
+ DRM_DEBUG_KMS("done priv[%pK]\n", dev);
return 0;
}
@@ -1676,7 +1676,7 @@ static void ipp_subdrv_close(struct drm_device *drm_dev, struct device *dev,
mutex_lock(&ippdrv->cmd_lock);
list_for_each_entry_safe(c_node, tc_node,
&ippdrv->cmd_list, list) {
- DRM_DEBUG_KMS("count[%d]ippdrv[%p]\n",
+ DRM_DEBUG_KMS("count[%d]ippdrv[%pK]\n",
count++, ippdrv);
if (c_node->filp == file) {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
index 6591e40..79282a8 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
@@ -748,7 +748,7 @@ static int rotator_probe(struct platform_device *pdev)
goto err_ippdrv_register;
}
- DRM_DEBUG_KMS("ippdrv[%p]\n", ippdrv);
+ DRM_DEBUG_KMS("ippdrv[%pK]\n", ippdrv);
platform_set_drvdata(pdev, rot);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index 57fe514..5d9a62a 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -170,6 +170,7 @@ static const struct exynos_drm_crtc_ops vidi_crtc_ops = {
.enable_vblank = vidi_enable_vblank,
.disable_vblank = vidi_disable_vblank,
.update_plane = vidi_update_plane,
+ .atomic_flush = exynos_crtc_handle_event,
};
static void vidi_fake_vblank_timer(unsigned long arg)
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index 72143ac..25edb63 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -1012,6 +1012,7 @@ static void mixer_atomic_flush(struct exynos_drm_crtc *crtc)
return;
mixer_vsync_set_update(mixer_ctx, true);
+ exynos_crtc_handle_event(crtc);
}
static void mixer_enable(struct exynos_drm_crtc *crtc)
diff --git a/drivers/gpu/drm/i915/gvt/aperture_gm.c b/drivers/gpu/drm/i915/gvt/aperture_gm.c
index 3b6caac..325618d 100644
--- a/drivers/gpu/drm/i915/gvt/aperture_gm.c
+++ b/drivers/gpu/drm/i915/gvt/aperture_gm.c
@@ -242,7 +242,7 @@ static int alloc_resource(struct intel_vgpu *vgpu,
const char *item;
if (!param->low_gm_sz || !param->high_gm_sz || !param->fence_sz) {
- gvt_err("Invalid vGPU creation params\n");
+ gvt_vgpu_err("Invalid vGPU creation params\n");
return -EINVAL;
}
@@ -285,9 +285,9 @@ static int alloc_resource(struct intel_vgpu *vgpu,
return 0;
no_enough_resource:
- gvt_err("vgpu%d: fail to allocate resource %s\n", vgpu->id, item);
- gvt_err("vgpu%d: request %luMB avail %luMB max %luMB taken %luMB\n",
- vgpu->id, BYTES_TO_MB(request), BYTES_TO_MB(avail),
+ gvt_vgpu_err("fail to allocate resource %s\n", item);
+ gvt_vgpu_err("request %luMB avail %luMB max %luMB taken %luMB\n",
+ BYTES_TO_MB(request), BYTES_TO_MB(avail),
BYTES_TO_MB(max), BYTES_TO_MB(taken));
return -ENOSPC;
}
diff --git a/drivers/gpu/drm/i915/gvt/cfg_space.c b/drivers/gpu/drm/i915/gvt/cfg_space.c
index 4a6a2ed..b7d7721 100644
--- a/drivers/gpu/drm/i915/gvt/cfg_space.c
+++ b/drivers/gpu/drm/i915/gvt/cfg_space.c
@@ -41,6 +41,54 @@ enum {
INTEL_GVT_PCI_BAR_MAX,
};
+/* bitmap for writable bits (RW or RW1C bits, but cannot co-exist in one
+ * byte) byte by byte in standard pci configuration space. (not the full
+ * 256 bytes.)
+ */
+static const u8 pci_cfg_space_rw_bmp[PCI_INTERRUPT_LINE + 4] = {
+ [PCI_COMMAND] = 0xff, 0x07,
+ [PCI_STATUS] = 0x00, 0xf9, /* the only one RW1C byte */
+ [PCI_CACHE_LINE_SIZE] = 0xff,
+ [PCI_BASE_ADDRESS_0 ... PCI_CARDBUS_CIS - 1] = 0xff,
+ [PCI_ROM_ADDRESS] = 0x01, 0xf8, 0xff, 0xff,
+ [PCI_INTERRUPT_LINE] = 0xff,
+};
+
+/**
+ * vgpu_pci_cfg_mem_write - write virtual cfg space memory
+ *
+ * Use this function to write virtual cfg space memory.
+ * For standard cfg space, only RW bits can be changed,
+ * and we emulates the RW1C behavior of PCI_STATUS register.
+ */
+static void vgpu_pci_cfg_mem_write(struct intel_vgpu *vgpu, unsigned int off,
+ u8 *src, unsigned int bytes)
+{
+ u8 *cfg_base = vgpu_cfg_space(vgpu);
+ u8 mask, new, old;
+ int i = 0;
+
+ for (; i < bytes && (off + i < sizeof(pci_cfg_space_rw_bmp)); i++) {
+ mask = pci_cfg_space_rw_bmp[off + i];
+ old = cfg_base[off + i];
+ new = src[i] & mask;
+
+ /**
+ * The PCI_STATUS high byte has RW1C bits, here
+ * emulates clear by writing 1 for these bits.
+ * Writing a 0b to RW1C bits has no effect.
+ */
+ if (off + i == PCI_STATUS + 1)
+ new = (~new & old) & mask;
+
+ cfg_base[off + i] = (old & ~mask) | new;
+ }
+
+ /* For other configuration space directly copy as it is. */
+ if (i < bytes)
+ memcpy(cfg_base + off + i, src + i, bytes - i);
+}
+
/**
* intel_vgpu_emulate_cfg_read - emulate vGPU configuration space read
*
@@ -123,7 +171,7 @@ static int emulate_pci_command_write(struct intel_vgpu *vgpu,
u8 changed = old ^ new;
int ret;
- memcpy(vgpu_cfg_space(vgpu) + offset, p_data, bytes);
+ vgpu_pci_cfg_mem_write(vgpu, offset, p_data, bytes);
if (!(changed & PCI_COMMAND_MEMORY))
return 0;
@@ -237,6 +285,9 @@ int intel_vgpu_emulate_cfg_write(struct intel_vgpu *vgpu, unsigned int offset,
{
int ret;
+ if (vgpu->failsafe)
+ return 0;
+
if (WARN_ON(bytes > 4))
return -EINVAL;
@@ -274,10 +325,10 @@ int intel_vgpu_emulate_cfg_write(struct intel_vgpu *vgpu, unsigned int offset,
if (ret)
return ret;
- memcpy(vgpu_cfg_space(vgpu) + offset, p_data, bytes);
+ vgpu_pci_cfg_mem_write(vgpu, offset, p_data, bytes);
break;
default:
- memcpy(vgpu_cfg_space(vgpu) + offset, p_data, bytes);
+ vgpu_pci_cfg_mem_write(vgpu, offset, p_data, bytes);
break;
}
return 0;
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index b9c8e24..2b92cc8 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -668,7 +668,7 @@ static inline void print_opcode(u32 cmd, int ring_id)
if (d_info == NULL)
return;
- gvt_err("opcode=0x%x %s sub_ops:",
+ gvt_dbg_cmd("opcode=0x%x %s sub_ops:",
cmd >> (32 - d_info->op_len), d_info->name);
for (i = 0; i < d_info->nr_sub_op; i++)
@@ -693,23 +693,23 @@ static void parser_exec_state_dump(struct parser_exec_state *s)
int cnt = 0;
int i;
- gvt_err(" vgpu%d RING%d: ring_start(%08lx) ring_end(%08lx)"
+ gvt_dbg_cmd(" vgpu%d RING%d: ring_start(%08lx) ring_end(%08lx)"
" ring_head(%08lx) ring_tail(%08lx)\n", s->vgpu->id,
s->ring_id, s->ring_start, s->ring_start + s->ring_size,
s->ring_head, s->ring_tail);
- gvt_err(" %s %s ip_gma(%08lx) ",
+ gvt_dbg_cmd(" %s %s ip_gma(%08lx) ",
s->buf_type == RING_BUFFER_INSTRUCTION ?
"RING_BUFFER" : "BATCH_BUFFER",
s->buf_addr_type == GTT_BUFFER ?
"GTT" : "PPGTT", s->ip_gma);
if (s->ip_va == NULL) {
- gvt_err(" ip_va(NULL)");
+ gvt_dbg_cmd(" ip_va(NULL)");
return;
}
- gvt_err(" ip_va=%p: %08x %08x %08x %08x\n",
+ gvt_dbg_cmd(" ip_va=%p: %08x %08x %08x %08x\n",
s->ip_va, cmd_val(s, 0), cmd_val(s, 1),
cmd_val(s, 2), cmd_val(s, 3));
@@ -817,6 +817,25 @@ static bool is_shadowed_mmio(unsigned int offset)
return ret;
}
+static inline bool is_force_nonpriv_mmio(unsigned int offset)
+{
+ return (offset >= 0x24d0 && offset < 0x2500);
+}
+
+static int force_nonpriv_reg_handler(struct parser_exec_state *s,
+ unsigned int offset, unsigned int index)
+{
+ struct intel_gvt *gvt = s->vgpu->gvt;
+ unsigned int data = cmd_val(s, index + 1);
+
+ if (!intel_gvt_in_force_nonpriv_whitelist(gvt, data)) {
+ gvt_err("Unexpected forcenonpriv 0x%x LRI write, value=0x%x\n",
+ offset, data);
+ return -EINVAL;
+ }
+ return 0;
+}
+
static int cmd_reg_handler(struct parser_exec_state *s,
unsigned int offset, unsigned int index, char *cmd)
{
@@ -824,23 +843,26 @@ static int cmd_reg_handler(struct parser_exec_state *s,
struct intel_gvt *gvt = vgpu->gvt;
if (offset + 4 > gvt->device_info.mmio_size) {
- gvt_err("%s access to (%x) outside of MMIO range\n",
+ gvt_vgpu_err("%s access to (%x) outside of MMIO range\n",
cmd, offset);
return -EINVAL;
}
if (!intel_gvt_mmio_is_cmd_access(gvt, offset)) {
- gvt_err("vgpu%d: %s access to non-render register (%x)\n",
- s->vgpu->id, cmd, offset);
+ gvt_vgpu_err("%s access to non-render register (%x)\n",
+ cmd, offset);
return 0;
}
if (is_shadowed_mmio(offset)) {
- gvt_err("vgpu%d: found access of shadowed MMIO %x\n",
- s->vgpu->id, offset);
+ gvt_vgpu_err("found access of shadowed MMIO %x\n", offset);
return 0;
}
+ if (is_force_nonpriv_mmio(offset) &&
+ force_nonpriv_reg_handler(s, offset, index))
+ return -EINVAL;
+
if (offset == i915_mmio_reg_offset(DERRMR) ||
offset == i915_mmio_reg_offset(FORCEWAKE_MT)) {
/* Writing to HW VGT_PVINFO_PAGE offset will be discarded */
@@ -1008,7 +1030,7 @@ static int cmd_handler_pipe_control(struct parser_exec_state *s)
ret = cmd_reg_handler(s, 0x2358, 1, "pipe_ctrl");
else if (post_sync == 1) {
/* check ggtt*/
- if ((cmd_val(s, 2) & (1 << 2))) {
+ if ((cmd_val(s, 1) & PIPE_CONTROL_GLOBAL_GTT_IVB)) {
gma = cmd_val(s, 2) & GENMASK(31, 3);
if (gmadr_bytes == 8)
gma |= (cmd_gma_hi(s, 3)) << 32;
@@ -1129,6 +1151,7 @@ static int skl_decode_mi_display_flip(struct parser_exec_state *s,
struct mi_display_flip_command_info *info)
{
struct drm_i915_private *dev_priv = s->vgpu->gvt->dev_priv;
+ struct intel_vgpu *vgpu = s->vgpu;
u32 dword0 = cmd_val(s, 0);
u32 dword1 = cmd_val(s, 1);
u32 dword2 = cmd_val(s, 2);
@@ -1167,7 +1190,7 @@ static int skl_decode_mi_display_flip(struct parser_exec_state *s,
break;
default:
- gvt_err("unknown plane code %d\n", plane);
+ gvt_vgpu_err("unknown plane code %d\n", plane);
return -EINVAL;
}
@@ -1274,25 +1297,26 @@ static int update_plane_mmio_from_mi_display_flip(
static int cmd_handler_mi_display_flip(struct parser_exec_state *s)
{
struct mi_display_flip_command_info info;
+ struct intel_vgpu *vgpu = s->vgpu;
int ret;
int i;
int len = cmd_length(s);
ret = decode_mi_display_flip(s, &info);
if (ret) {
- gvt_err("fail to decode MI display flip command\n");
+ gvt_vgpu_err("fail to decode MI display flip command\n");
return ret;
}
ret = check_mi_display_flip(s, &info);
if (ret) {
- gvt_err("invalid MI display flip command\n");
+ gvt_vgpu_err("invalid MI display flip command\n");
return ret;
}
ret = update_plane_mmio_from_mi_display_flip(s, &info);
if (ret) {
- gvt_err("fail to update plane mmio\n");
+ gvt_vgpu_err("fail to update plane mmio\n");
return ret;
}
@@ -1350,7 +1374,8 @@ static inline int cmd_address_audit(struct parser_exec_state *s,
int ret;
if (op_size > max_surface_size) {
- gvt_err("command address audit fail name %s\n", s->info->name);
+ gvt_vgpu_err("command address audit fail name %s\n",
+ s->info->name);
return -EINVAL;
}
@@ -1367,7 +1392,7 @@ static inline int cmd_address_audit(struct parser_exec_state *s,
}
return 0;
err:
- gvt_err("cmd_parser: Malicious %s detected, addr=0x%lx, len=%d!\n",
+ gvt_vgpu_err("cmd_parser: Malicious %s detected, addr=0x%lx, len=%d!\n",
s->info->name, guest_gma, op_size);
pr_err("cmd dump: ");
@@ -1412,8 +1437,10 @@ static int cmd_handler_mi_store_data_imm(struct parser_exec_state *s)
static inline int unexpected_cmd(struct parser_exec_state *s)
{
- gvt_err("vgpu%d: Unexpected %s in command buffer!\n",
- s->vgpu->id, s->info->name);
+ struct intel_vgpu *vgpu = s->vgpu;
+
+ gvt_vgpu_err("Unexpected %s in command buffer!\n", s->info->name);
+
return -EINVAL;
}
@@ -1516,7 +1543,7 @@ static int copy_gma_to_hva(struct intel_vgpu *vgpu, struct intel_vgpu_mm *mm,
while (gma != end_gma) {
gpa = intel_vgpu_gma_to_gpa(mm, gma);
if (gpa == INTEL_GVT_INVALID_ADDR) {
- gvt_err("invalid gma address: %lx\n", gma);
+ gvt_vgpu_err("invalid gma address: %lx\n", gma);
return -EFAULT;
}
@@ -1557,6 +1584,7 @@ static uint32_t find_bb_size(struct parser_exec_state *s)
uint32_t bb_size = 0;
uint32_t cmd_len = 0;
bool met_bb_end = false;
+ struct intel_vgpu *vgpu = s->vgpu;
u32 cmd;
/* get the start gm address of the batch buffer */
@@ -1565,7 +1593,7 @@ static uint32_t find_bb_size(struct parser_exec_state *s)
info = get_cmd_info(s->vgpu->gvt, cmd, s->ring_id);
if (info == NULL) {
- gvt_err("unknown cmd 0x%x, opcode=0x%x\n",
+ gvt_vgpu_err("unknown cmd 0x%x, opcode=0x%x\n",
cmd, get_opcode(cmd, s->ring_id));
return -EINVAL;
}
@@ -1574,7 +1602,7 @@ static uint32_t find_bb_size(struct parser_exec_state *s)
gma, gma + 4, &cmd);
info = get_cmd_info(s->vgpu->gvt, cmd, s->ring_id);
if (info == NULL) {
- gvt_err("unknown cmd 0x%x, opcode=0x%x\n",
+ gvt_vgpu_err("unknown cmd 0x%x, opcode=0x%x\n",
cmd, get_opcode(cmd, s->ring_id));
return -EINVAL;
}
@@ -1599,6 +1627,7 @@ static uint32_t find_bb_size(struct parser_exec_state *s)
static int perform_bb_shadow(struct parser_exec_state *s)
{
struct intel_shadow_bb_entry *entry_obj;
+ struct intel_vgpu *vgpu = s->vgpu;
unsigned long gma = 0;
uint32_t bb_size;
void *dst = NULL;
@@ -1633,7 +1662,7 @@ static int perform_bb_shadow(struct parser_exec_state *s)
ret = i915_gem_object_set_to_cpu_domain(entry_obj->obj, false);
if (ret) {
- gvt_err("failed to set shadow batch to CPU\n");
+ gvt_vgpu_err("failed to set shadow batch to CPU\n");
goto unmap_src;
}
@@ -1645,7 +1674,7 @@ static int perform_bb_shadow(struct parser_exec_state *s)
gma, gma + bb_size,
dst);
if (ret) {
- gvt_err("fail to copy guest ring buffer\n");
+ gvt_vgpu_err("fail to copy guest ring buffer\n");
goto unmap_src;
}
@@ -1676,15 +1705,16 @@ static int cmd_handler_mi_batch_buffer_start(struct parser_exec_state *s)
{
bool second_level;
int ret = 0;
+ struct intel_vgpu *vgpu = s->vgpu;
if (s->buf_type == BATCH_BUFFER_2ND_LEVEL) {
- gvt_err("Found MI_BATCH_BUFFER_START in 2nd level BB\n");
+ gvt_vgpu_err("Found MI_BATCH_BUFFER_START in 2nd level BB\n");
return -EINVAL;
}
second_level = BATCH_BUFFER_2ND_LEVEL_BIT(cmd_val(s, 0)) == 1;
if (second_level && (s->buf_type != BATCH_BUFFER_INSTRUCTION)) {
- gvt_err("Jumping to 2nd level BB from RB is not allowed\n");
+ gvt_vgpu_err("Jumping to 2nd level BB from RB is not allowed\n");
return -EINVAL;
}
@@ -1702,7 +1732,7 @@ static int cmd_handler_mi_batch_buffer_start(struct parser_exec_state *s)
if (batch_buffer_needs_scan(s)) {
ret = perform_bb_shadow(s);
if (ret < 0)
- gvt_err("invalid shadow batch buffer\n");
+ gvt_vgpu_err("invalid shadow batch buffer\n");
} else {
/* emulate a batch buffer end to do return right */
ret = cmd_handler_mi_batch_buffer_end(s);
@@ -2429,6 +2459,7 @@ static int cmd_parser_exec(struct parser_exec_state *s)
int ret = 0;
cycles_t t0, t1, t2;
struct parser_exec_state s_before_advance_custom;
+ struct intel_vgpu *vgpu = s->vgpu;
t0 = get_cycles();
@@ -2436,7 +2467,7 @@ static int cmd_parser_exec(struct parser_exec_state *s)
info = get_cmd_info(s->vgpu->gvt, cmd, s->ring_id);
if (info == NULL) {
- gvt_err("unknown cmd 0x%x, opcode=0x%x\n",
+ gvt_vgpu_err("unknown cmd 0x%x, opcode=0x%x\n",
cmd, get_opcode(cmd, s->ring_id));
return -EINVAL;
}
@@ -2452,7 +2483,7 @@ static int cmd_parser_exec(struct parser_exec_state *s)
if (info->handler) {
ret = info->handler(s);
if (ret < 0) {
- gvt_err("%s handler error\n", info->name);
+ gvt_vgpu_err("%s handler error\n", info->name);
return ret;
}
}
@@ -2463,7 +2494,7 @@ static int cmd_parser_exec(struct parser_exec_state *s)
if (!(info->flag & F_IP_ADVANCE_CUSTOM)) {
ret = cmd_advance_default(s);
if (ret) {
- gvt_err("%s IP advance error\n", info->name);
+ gvt_vgpu_err("%s IP advance error\n", info->name);
return ret;
}
}
@@ -2486,6 +2517,7 @@ static int command_scan(struct parser_exec_state *s,
unsigned long gma_head, gma_tail, gma_bottom;
int ret = 0;
+ struct intel_vgpu *vgpu = s->vgpu;
gma_head = rb_start + rb_head;
gma_tail = rb_start + rb_tail;
@@ -2497,7 +2529,7 @@ static int command_scan(struct parser_exec_state *s,
if (s->buf_type == RING_BUFFER_INSTRUCTION) {
if (!(s->ip_gma >= rb_start) ||
!(s->ip_gma < gma_bottom)) {
- gvt_err("ip_gma %lx out of ring scope."
+ gvt_vgpu_err("ip_gma %lx out of ring scope."
"(base:0x%lx, bottom: 0x%lx)\n",
s->ip_gma, rb_start,
gma_bottom);
@@ -2505,7 +2537,7 @@ static int command_scan(struct parser_exec_state *s,
return -EINVAL;
}
if (gma_out_of_range(s->ip_gma, gma_head, gma_tail)) {
- gvt_err("ip_gma %lx out of range."
+ gvt_vgpu_err("ip_gma %lx out of range."
"base 0x%lx head 0x%lx tail 0x%lx\n",
s->ip_gma, rb_start,
rb_head, rb_tail);
@@ -2515,7 +2547,7 @@ static int command_scan(struct parser_exec_state *s,
}
ret = cmd_parser_exec(s);
if (ret) {
- gvt_err("cmd parser error\n");
+ gvt_vgpu_err("cmd parser error\n");
parser_exec_state_dump(s);
break;
}
@@ -2639,7 +2671,7 @@ static int shadow_workload_ring_buffer(struct intel_vgpu_workload *workload)
gma_head, gma_top,
workload->shadow_ring_buffer_va);
if (ret) {
- gvt_err("fail to copy guest ring buffer\n");
+ gvt_vgpu_err("fail to copy guest ring buffer\n");
return ret;
}
copy_len = gma_top - gma_head;
@@ -2651,7 +2683,7 @@ static int shadow_workload_ring_buffer(struct intel_vgpu_workload *workload)
gma_head, gma_tail,
workload->shadow_ring_buffer_va + copy_len);
if (ret) {
- gvt_err("fail to copy guest ring buffer\n");
+ gvt_vgpu_err("fail to copy guest ring buffer\n");
return ret;
}
ring->tail += workload->rb_len;
@@ -2662,16 +2694,17 @@ static int shadow_workload_ring_buffer(struct intel_vgpu_workload *workload)
int intel_gvt_scan_and_shadow_workload(struct intel_vgpu_workload *workload)
{
int ret;
+ struct intel_vgpu *vgpu = workload->vgpu;
ret = shadow_workload_ring_buffer(workload);
if (ret) {
- gvt_err("fail to shadow workload ring_buffer\n");
+ gvt_vgpu_err("fail to shadow workload ring_buffer\n");
return ret;
}
ret = scan_workload(workload);
if (ret) {
- gvt_err("scan workload error\n");
+ gvt_vgpu_err("scan workload error\n");
return ret;
}
return 0;
@@ -2681,6 +2714,7 @@ static int shadow_indirect_ctx(struct intel_shadow_wa_ctx *wa_ctx)
{
int ctx_size = wa_ctx->indirect_ctx.size;
unsigned long guest_gma = wa_ctx->indirect_ctx.guest_gma;
+ struct intel_vgpu *vgpu = wa_ctx->workload->vgpu;
struct drm_i915_gem_object *obj;
int ret = 0;
void *map;
@@ -2694,14 +2728,14 @@ static int shadow_indirect_ctx(struct intel_shadow_wa_ctx *wa_ctx)
/* get the va of the shadow batch buffer */
map = i915_gem_object_pin_map(obj, I915_MAP_WB);
if (IS_ERR(map)) {
- gvt_err("failed to vmap shadow indirect ctx\n");
+ gvt_vgpu_err("failed to vmap shadow indirect ctx\n");
ret = PTR_ERR(map);
goto put_obj;
}
ret = i915_gem_object_set_to_cpu_domain(obj, false);
if (ret) {
- gvt_err("failed to set shadow indirect ctx to CPU\n");
+ gvt_vgpu_err("failed to set shadow indirect ctx to CPU\n");
goto unmap_src;
}
@@ -2710,7 +2744,7 @@ static int shadow_indirect_ctx(struct intel_shadow_wa_ctx *wa_ctx)
guest_gma, guest_gma + ctx_size,
map);
if (ret) {
- gvt_err("fail to copy guest indirect ctx\n");
+ gvt_vgpu_err("fail to copy guest indirect ctx\n");
goto unmap_src;
}
@@ -2744,13 +2778,14 @@ static int combine_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
int intel_gvt_scan_and_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
{
int ret;
+ struct intel_vgpu *vgpu = wa_ctx->workload->vgpu;
if (wa_ctx->indirect_ctx.size == 0)
return 0;
ret = shadow_indirect_ctx(wa_ctx);
if (ret) {
- gvt_err("fail to shadow indirect ctx\n");
+ gvt_vgpu_err("fail to shadow indirect ctx\n");
return ret;
}
@@ -2758,7 +2793,7 @@ int intel_gvt_scan_and_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
ret = scan_wa_ctx(wa_ctx);
if (ret) {
- gvt_err("scan wa ctx error\n");
+ gvt_vgpu_err("scan wa ctx error\n");
return ret;
}
diff --git a/drivers/gpu/drm/i915/gvt/debug.h b/drivers/gpu/drm/i915/gvt/debug.h
index 68cba7b..b0cff4d 100644
--- a/drivers/gpu/drm/i915/gvt/debug.h
+++ b/drivers/gpu/drm/i915/gvt/debug.h
@@ -27,6 +27,14 @@
#define gvt_err(fmt, args...) \
DRM_ERROR("gvt: "fmt, ##args)
+#define gvt_vgpu_err(fmt, args...) \
+do { \
+ if (IS_ERR_OR_NULL(vgpu)) \
+ DRM_DEBUG_DRIVER("gvt: "fmt, ##args); \
+ else \
+ DRM_DEBUG_DRIVER("gvt: vgpu %d: "fmt, vgpu->id, ##args);\
+} while (0)
+
#define gvt_dbg_core(fmt, args...) \
DRM_DEBUG_DRIVER("gvt: core: "fmt, ##args)
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index 6d8fde8..5419ae6 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -83,44 +83,80 @@ static int pipe_is_enabled(struct intel_vgpu *vgpu, int pipe)
return 0;
}
+static unsigned char virtual_dp_monitor_edid[GVT_EDID_NUM][EDID_SIZE] = {
+ {
+/* EDID with 1024x768 as its resolution */
+ /*Header*/
+ 0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00,
+ /* Vendor & Product Identification */
+ 0x22, 0xf0, 0x54, 0x29, 0x00, 0x00, 0x00, 0x00, 0x04, 0x17,
+ /* Version & Revision */
+ 0x01, 0x04,
+ /* Basic Display Parameters & Features */
+ 0xa5, 0x34, 0x20, 0x78, 0x23,
+ /* Color Characteristics */
+ 0xfc, 0x81, 0xa4, 0x55, 0x4d, 0x9d, 0x25, 0x12, 0x50, 0x54,
+ /* Established Timings: maximum resolution is 1024x768 */
+ 0x21, 0x08, 0x00,
+ /* Standard Timings. All invalid */
+ 0x00, 0xc0, 0x00, 0xc0, 0x00, 0x40, 0x00, 0x80, 0x00, 0x00,
+ 0x00, 0x40, 0x00, 0x00, 0x00, 0x01,
+ /* 18 Byte Data Blocks 1: invalid */
+ 0x00, 0x00, 0x80, 0xa0, 0x70, 0xb0,
+ 0x23, 0x40, 0x30, 0x20, 0x36, 0x00, 0x06, 0x44, 0x21, 0x00, 0x00, 0x1a,
+ /* 18 Byte Data Blocks 2: invalid */
+ 0x00, 0x00, 0x00, 0xfd, 0x00, 0x18, 0x3c, 0x18, 0x50, 0x11, 0x00, 0x0a,
+ 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
+ /* 18 Byte Data Blocks 3: invalid */
+ 0x00, 0x00, 0x00, 0xfc, 0x00, 0x48,
+ 0x50, 0x20, 0x5a, 0x52, 0x32, 0x34, 0x34, 0x30, 0x77, 0x0a, 0x20, 0x20,
+ /* 18 Byte Data Blocks 4: invalid */
+ 0x00, 0x00, 0x00, 0xff, 0x00, 0x43, 0x4e, 0x34, 0x33, 0x30, 0x34, 0x30,
+ 0x44, 0x58, 0x51, 0x0a, 0x20, 0x20,
+ /* Extension Block Count */
+ 0x00,
+ /* Checksum */
+ 0xef,
+ },
+ {
/* EDID with 1920x1200 as its resolution */
-static unsigned char virtual_dp_monitor_edid[] = {
- /*Header*/
- 0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00,
- /* Vendor & Product Identification */
- 0x22, 0xf0, 0x54, 0x29, 0x00, 0x00, 0x00, 0x00, 0x04, 0x17,
- /* Version & Revision */
- 0x01, 0x04,
- /* Basic Display Parameters & Features */
- 0xa5, 0x34, 0x20, 0x78, 0x23,
- /* Color Characteristics */
- 0xfc, 0x81, 0xa4, 0x55, 0x4d, 0x9d, 0x25, 0x12, 0x50, 0x54,
- /* Established Timings: maximum resolution is 1024x768 */
- 0x21, 0x08, 0x00,
- /*
- * Standard Timings.
- * below new resolutions can be supported:
- * 1920x1080, 1280x720, 1280x960, 1280x1024,
- * 1440x900, 1600x1200, 1680x1050
- */
- 0xd1, 0xc0, 0x81, 0xc0, 0x81, 0x40, 0x81, 0x80, 0x95, 0x00,
- 0xa9, 0x40, 0xb3, 0x00, 0x01, 0x01,
- /* 18 Byte Data Blocks 1: max resolution is 1920x1200 */
- 0x28, 0x3c, 0x80, 0xa0, 0x70, 0xb0,
- 0x23, 0x40, 0x30, 0x20, 0x36, 0x00, 0x06, 0x44, 0x21, 0x00, 0x00, 0x1a,
- /* 18 Byte Data Blocks 2: invalid */
- 0x00, 0x00, 0x00, 0xfd, 0x00, 0x18, 0x3c, 0x18, 0x50, 0x11, 0x00, 0x0a,
- 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
- /* 18 Byte Data Blocks 3: invalid */
- 0x00, 0x00, 0x00, 0xfc, 0x00, 0x48,
- 0x50, 0x20, 0x5a, 0x52, 0x32, 0x34, 0x34, 0x30, 0x77, 0x0a, 0x20, 0x20,
- /* 18 Byte Data Blocks 4: invalid */
- 0x00, 0x00, 0x00, 0xff, 0x00, 0x43, 0x4e, 0x34, 0x33, 0x30, 0x34, 0x30,
- 0x44, 0x58, 0x51, 0x0a, 0x20, 0x20,
- /* Extension Block Count */
- 0x00,
- /* Checksum */
- 0x45,
+ /*Header*/
+ 0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00,
+ /* Vendor & Product Identification */
+ 0x22, 0xf0, 0x54, 0x29, 0x00, 0x00, 0x00, 0x00, 0x04, 0x17,
+ /* Version & Revision */
+ 0x01, 0x04,
+ /* Basic Display Parameters & Features */
+ 0xa5, 0x34, 0x20, 0x78, 0x23,
+ /* Color Characteristics */
+ 0xfc, 0x81, 0xa4, 0x55, 0x4d, 0x9d, 0x25, 0x12, 0x50, 0x54,
+ /* Established Timings: maximum resolution is 1024x768 */
+ 0x21, 0x08, 0x00,
+ /*
+ * Standard Timings.
+ * below new resolutions can be supported:
+ * 1920x1080, 1280x720, 1280x960, 1280x1024,
+ * 1440x900, 1600x1200, 1680x1050
+ */
+ 0xd1, 0xc0, 0x81, 0xc0, 0x81, 0x40, 0x81, 0x80, 0x95, 0x00,
+ 0xa9, 0x40, 0xb3, 0x00, 0x01, 0x01,
+ /* 18 Byte Data Blocks 1: max resolution is 1920x1200 */
+ 0x28, 0x3c, 0x80, 0xa0, 0x70, 0xb0,
+ 0x23, 0x40, 0x30, 0x20, 0x36, 0x00, 0x06, 0x44, 0x21, 0x00, 0x00, 0x1a,
+ /* 18 Byte Data Blocks 2: invalid */
+ 0x00, 0x00, 0x00, 0xfd, 0x00, 0x18, 0x3c, 0x18, 0x50, 0x11, 0x00, 0x0a,
+ 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
+ /* 18 Byte Data Blocks 3: invalid */
+ 0x00, 0x00, 0x00, 0xfc, 0x00, 0x48,
+ 0x50, 0x20, 0x5a, 0x52, 0x32, 0x34, 0x34, 0x30, 0x77, 0x0a, 0x20, 0x20,
+ /* 18 Byte Data Blocks 4: invalid */
+ 0x00, 0x00, 0x00, 0xff, 0x00, 0x43, 0x4e, 0x34, 0x33, 0x30, 0x34, 0x30,
+ 0x44, 0x58, 0x51, 0x0a, 0x20, 0x20,
+ /* Extension Block Count */
+ 0x00,
+ /* Checksum */
+ 0x45,
+ },
};
#define DPCD_HEADER_SIZE 0xb
@@ -140,14 +176,20 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
vgpu_vreg(vgpu, SDEISR) &= ~(SDE_PORTA_HOTPLUG_SPT |
SDE_PORTE_HOTPLUG_SPT);
- if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B))
+ if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
vgpu_vreg(vgpu, SDEISR) |= SDE_PORTB_HOTPLUG_CPT;
+ vgpu_vreg(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDIB_DETECTED;
+ }
- if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C))
+ if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
vgpu_vreg(vgpu, SDEISR) |= SDE_PORTC_HOTPLUG_CPT;
+ vgpu_vreg(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDIC_DETECTED;
+ }
- if (intel_vgpu_has_monitor_on_port(vgpu, PORT_D))
+ if (intel_vgpu_has_monitor_on_port(vgpu, PORT_D)) {
vgpu_vreg(vgpu, SDEISR) |= SDE_PORTD_HOTPLUG_CPT;
+ vgpu_vreg(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDID_DETECTED;
+ }
if (IS_SKYLAKE(dev_priv) &&
intel_vgpu_has_monitor_on_port(vgpu, PORT_E)) {
@@ -160,6 +202,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
GEN8_PORT_DP_A_HOTPLUG;
else
vgpu_vreg(vgpu, SDEISR) |= SDE_PORTA_HOTPLUG_SPT;
+
+ vgpu_vreg(vgpu, DDI_BUF_CTL(PORT_A)) |= DDI_INIT_DISPLAY_DETECTED;
}
}
@@ -175,10 +219,13 @@ static void clean_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num)
}
static int setup_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num,
- int type)
+ int type, unsigned int resolution)
{
struct intel_vgpu_port *port = intel_vgpu_port(vgpu, port_num);
+ if (WARN_ON(resolution >= GVT_EDID_NUM))
+ return -EINVAL;
+
port->edid = kzalloc(sizeof(*(port->edid)), GFP_KERNEL);
if (!port->edid)
return -ENOMEM;
@@ -189,7 +236,7 @@ static int setup_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num,
return -ENOMEM;
}
- memcpy(port->edid->edid_block, virtual_dp_monitor_edid,
+ memcpy(port->edid->edid_block, virtual_dp_monitor_edid[resolution],
EDID_SIZE);
port->edid->data_valid = true;
@@ -322,16 +369,18 @@ void intel_vgpu_clean_display(struct intel_vgpu *vgpu)
* Zero on success, negative error code if failed.
*
*/
-int intel_vgpu_init_display(struct intel_vgpu *vgpu)
+int intel_vgpu_init_display(struct intel_vgpu *vgpu, u64 resolution)
{
struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
intel_vgpu_init_i2c_edid(vgpu);
if (IS_SKYLAKE(dev_priv))
- return setup_virtual_dp_monitor(vgpu, PORT_D, GVT_DP_D);
+ return setup_virtual_dp_monitor(vgpu, PORT_D, GVT_DP_D,
+ resolution);
else
- return setup_virtual_dp_monitor(vgpu, PORT_B, GVT_DP_B);
+ return setup_virtual_dp_monitor(vgpu, PORT_B, GVT_DP_B,
+ resolution);
}
/**
diff --git a/drivers/gpu/drm/i915/gvt/display.h b/drivers/gpu/drm/i915/gvt/display.h
index 8b234ea..d73de22 100644
--- a/drivers/gpu/drm/i915/gvt/display.h
+++ b/drivers/gpu/drm/i915/gvt/display.h
@@ -154,10 +154,28 @@ struct intel_vgpu_port {
int type;
};
+enum intel_vgpu_edid {
+ GVT_EDID_1024_768,
+ GVT_EDID_1920_1200,
+ GVT_EDID_NUM,
+};
+
+static inline char *vgpu_edid_str(enum intel_vgpu_edid id)
+{
+ switch (id) {
+ case GVT_EDID_1024_768:
+ return "1024x768";
+ case GVT_EDID_1920_1200:
+ return "1920x1200";
+ default:
+ return "";
+ }
+}
+
void intel_gvt_emulate_vblank(struct intel_gvt *gvt);
void intel_gvt_check_vblank_emulation(struct intel_gvt *gvt);
-int intel_vgpu_init_display(struct intel_vgpu *vgpu);
+int intel_vgpu_init_display(struct intel_vgpu *vgpu, u64 resolution);
void intel_vgpu_reset_display(struct intel_vgpu *vgpu);
void intel_vgpu_clean_display(struct intel_vgpu *vgpu);
diff --git a/drivers/gpu/drm/i915/gvt/edid.c b/drivers/gpu/drm/i915/gvt/edid.c
index bda85df..42cd09ec 100644
--- a/drivers/gpu/drm/i915/gvt/edid.c
+++ b/drivers/gpu/drm/i915/gvt/edid.c
@@ -52,16 +52,16 @@ static unsigned char edid_get_byte(struct intel_vgpu *vgpu)
unsigned char chr = 0;
if (edid->state == I2C_NOT_SPECIFIED || !edid->slave_selected) {
- gvt_err("Driver tries to read EDID without proper sequence!\n");
+ gvt_vgpu_err("Driver tries to read EDID without proper sequence!\n");
return 0;
}
if (edid->current_edid_read >= EDID_SIZE) {
- gvt_err("edid_get_byte() exceeds the size of EDID!\n");
+ gvt_vgpu_err("edid_get_byte() exceeds the size of EDID!\n");
return 0;
}
if (!edid->edid_available) {
- gvt_err("Reading EDID but EDID is not available!\n");
+ gvt_vgpu_err("Reading EDID but EDID is not available!\n");
return 0;
}
@@ -72,7 +72,7 @@ static unsigned char edid_get_byte(struct intel_vgpu *vgpu)
chr = edid_data->edid_block[edid->current_edid_read];
edid->current_edid_read++;
} else {
- gvt_err("No EDID available during the reading?\n");
+ gvt_vgpu_err("No EDID available during the reading?\n");
}
return chr;
}
@@ -223,7 +223,7 @@ static int gmbus1_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
vgpu_vreg(vgpu, PCH_GMBUS2) |= GMBUS_ACTIVE;
break;
default:
- gvt_err("Unknown/reserved GMBUS cycle detected!\n");
+ gvt_vgpu_err("Unknown/reserved GMBUS cycle detected!\n");
break;
}
/*
@@ -292,8 +292,7 @@ static int gmbus3_mmio_read(struct intel_vgpu *vgpu, unsigned int offset,
*/
} else {
memcpy(p_data, &vgpu_vreg(vgpu, offset), bytes);
- gvt_err("vgpu%d: warning: gmbus3 read with nothing returned\n",
- vgpu->id);
+ gvt_vgpu_err("warning: gmbus3 read with nothing returned\n");
}
return 0;
}
@@ -496,7 +495,8 @@ void intel_gvt_i2c_handle_aux_ch_write(struct intel_vgpu *vgpu,
unsigned char val = edid_get_byte(vgpu);
aux_data_for_write = (val << 16);
- }
+ } else
+ aux_data_for_write = (0xff << 16);
}
/* write the return value in AUX_CH_DATA reg which includes:
* ACK of I2C_WRITE
diff --git a/drivers/gpu/drm/i915/gvt/execlist.c b/drivers/gpu/drm/i915/gvt/execlist.c
index 46eb9fd..f1f426a 100644
--- a/drivers/gpu/drm/i915/gvt/execlist.c
+++ b/drivers/gpu/drm/i915/gvt/execlist.c
@@ -172,6 +172,7 @@ static int emulate_execlist_ctx_schedule_out(
struct intel_vgpu_execlist *execlist,
struct execlist_ctx_descriptor_format *ctx)
{
+ struct intel_vgpu *vgpu = execlist->vgpu;
struct intel_vgpu_execlist_slot *running = execlist->running_slot;
struct intel_vgpu_execlist_slot *pending = execlist->pending_slot;
struct execlist_ctx_descriptor_format *ctx0 = &running->ctx[0];
@@ -183,7 +184,7 @@ static int emulate_execlist_ctx_schedule_out(
gvt_dbg_el("schedule out context id %x\n", ctx->context_id);
if (WARN_ON(!same_context(ctx, execlist->running_context))) {
- gvt_err("schedule out context is not running context,"
+ gvt_vgpu_err("schedule out context is not running context,"
"ctx id %x running ctx id %x\n",
ctx->context_id,
execlist->running_context->context_id);
@@ -254,7 +255,7 @@ static struct intel_vgpu_execlist_slot *get_next_execlist_slot(
status.udw = vgpu_vreg(vgpu, status_reg + 4);
if (status.execlist_queue_full) {
- gvt_err("virtual execlist slots are full\n");
+ gvt_vgpu_err("virtual execlist slots are full\n");
return NULL;
}
@@ -270,11 +271,12 @@ static int emulate_execlist_schedule_in(struct intel_vgpu_execlist *execlist,
struct execlist_ctx_descriptor_format *ctx0, *ctx1;
struct execlist_context_status_format status;
+ struct intel_vgpu *vgpu = execlist->vgpu;
gvt_dbg_el("emulate schedule-in\n");
if (!slot) {
- gvt_err("no available execlist slot\n");
+ gvt_vgpu_err("no available execlist slot\n");
return -EINVAL;
}
@@ -375,7 +377,6 @@ static void prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload)
vma = i915_gem_object_ggtt_pin(entry_obj->obj, NULL, 0, 4, 0);
if (IS_ERR(vma)) {
- gvt_err("Cannot pin\n");
return;
}
@@ -428,7 +429,6 @@ static void prepare_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
vma = i915_gem_object_ggtt_pin(wa_ctx->indirect_ctx.obj, NULL,
0, CACHELINE_BYTES, 0);
if (IS_ERR(vma)) {
- gvt_err("Cannot pin indirect ctx obj\n");
return;
}
@@ -561,6 +561,7 @@ static int prepare_mm(struct intel_vgpu_workload *workload)
{
struct execlist_ctx_descriptor_format *desc = &workload->ctx_desc;
struct intel_vgpu_mm *mm;
+ struct intel_vgpu *vgpu = workload->vgpu;
int page_table_level;
u32 pdp[8];
@@ -569,7 +570,7 @@ static int prepare_mm(struct intel_vgpu_workload *workload)
} else if (desc->addressing_mode == 3) { /* legacy 64 bit */
page_table_level = 4;
} else {
- gvt_err("Advanced Context mode(SVM) is not supported!\n");
+ gvt_vgpu_err("Advanced Context mode(SVM) is not supported!\n");
return -EINVAL;
}
@@ -583,7 +584,7 @@ static int prepare_mm(struct intel_vgpu_workload *workload)
mm = intel_vgpu_create_mm(workload->vgpu, INTEL_GVT_MM_PPGTT,
pdp, page_table_level, 0);
if (IS_ERR(mm)) {
- gvt_err("fail to create mm object.\n");
+ gvt_vgpu_err("fail to create mm object.\n");
return PTR_ERR(mm);
}
}
@@ -609,7 +610,7 @@ static int submit_context(struct intel_vgpu *vgpu, int ring_id,
ring_context_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm,
(u32)((desc->lrca + 1) << GTT_PAGE_SHIFT));
if (ring_context_gpa == INTEL_GVT_INVALID_ADDR) {
- gvt_err("invalid guest context LRCA: %x\n", desc->lrca);
+ gvt_vgpu_err("invalid guest context LRCA: %x\n", desc->lrca);
return -EINVAL;
}
@@ -724,8 +725,7 @@ int intel_vgpu_submit_execlist(struct intel_vgpu *vgpu, int ring_id)
continue;
if (!desc[i]->privilege_access) {
- gvt_err("vgpu%d: unexpected GGTT elsp submission\n",
- vgpu->id);
+ gvt_vgpu_err("unexpected GGTT elsp submission\n");
return -EINVAL;
}
@@ -735,15 +735,13 @@ int intel_vgpu_submit_execlist(struct intel_vgpu *vgpu, int ring_id)
}
if (!valid_desc_bitmap) {
- gvt_err("vgpu%d: no valid desc in a elsp submission\n",
- vgpu->id);
+ gvt_vgpu_err("no valid desc in a elsp submission\n");
return -EINVAL;
}
if (!test_bit(0, (void *)&valid_desc_bitmap) &&
test_bit(1, (void *)&valid_desc_bitmap)) {
- gvt_err("vgpu%d: weird elsp submission, desc 0 is not valid\n",
- vgpu->id);
+ gvt_vgpu_err("weird elsp submission, desc 0 is not valid\n");
return -EINVAL;
}
@@ -752,8 +750,7 @@ int intel_vgpu_submit_execlist(struct intel_vgpu *vgpu, int ring_id)
ret = submit_context(vgpu, ring_id, &valid_desc[i],
emulate_schedule_in);
if (ret) {
- gvt_err("vgpu%d: fail to schedule workload\n",
- vgpu->id);
+ gvt_vgpu_err("fail to schedule workload\n");
return ret;
}
emulate_schedule_in = false;
diff --git a/drivers/gpu/drm/i915/gvt/firmware.c b/drivers/gpu/drm/i915/gvt/firmware.c
index 1cb29b2..933a7c2 100644
--- a/drivers/gpu/drm/i915/gvt/firmware.c
+++ b/drivers/gpu/drm/i915/gvt/firmware.c
@@ -80,7 +80,7 @@ static int expose_firmware_sysfs(struct intel_gvt *gvt)
int ret;
size = sizeof(*h) + info->mmio_size + info->cfg_space_size - 1;
- firmware = vmalloc(size);
+ firmware = vzalloc(size);
if (!firmware)
return -ENOMEM;
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 28c9234..b832bea 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -49,8 +49,8 @@ bool intel_gvt_ggtt_validate_range(struct intel_vgpu *vgpu, u64 addr, u32 size)
{
if ((!vgpu_gmadr_is_valid(vgpu, addr)) || (size
&& !vgpu_gmadr_is_valid(vgpu, addr + size - 1))) {
- gvt_err("vgpu%d: invalid range gmadr 0x%llx size 0x%x\n",
- vgpu->id, addr, size);
+ gvt_vgpu_err("invalid range gmadr 0x%llx size 0x%x\n",
+ addr, size);
return false;
}
return true;
@@ -430,7 +430,7 @@ static int gtt_entry_p2m(struct intel_vgpu *vgpu, struct intel_gvt_gtt_entry *p,
mfn = intel_gvt_hypervisor_gfn_to_mfn(vgpu, gfn);
if (mfn == INTEL_GVT_INVALID_ADDR) {
- gvt_err("fail to translate gfn: 0x%lx\n", gfn);
+ gvt_vgpu_err("fail to translate gfn: 0x%lx\n", gfn);
return -ENXIO;
}
@@ -611,7 +611,7 @@ static inline int init_shadow_page(struct intel_vgpu *vgpu,
daddr = dma_map_page(kdev, p->page, 0, 4096, PCI_DMA_BIDIRECTIONAL);
if (dma_mapping_error(kdev, daddr)) {
- gvt_err("fail to map dma addr\n");
+ gvt_vgpu_err("fail to map dma addr\n");
return -EINVAL;
}
@@ -735,7 +735,7 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_alloc_shadow_page(
if (reclaim_one_mm(vgpu->gvt))
goto retry;
- gvt_err("fail to allocate ppgtt shadow page\n");
+ gvt_vgpu_err("fail to allocate ppgtt shadow page\n");
return ERR_PTR(-ENOMEM);
}
@@ -750,14 +750,14 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_alloc_shadow_page(
*/
ret = init_shadow_page(vgpu, &spt->shadow_page, type);
if (ret) {
- gvt_err("fail to initialize shadow page for spt\n");
+ gvt_vgpu_err("fail to initialize shadow page for spt\n");
goto err;
}
ret = intel_vgpu_init_guest_page(vgpu, &spt->guest_page,
gfn, ppgtt_write_protection_handler, NULL);
if (ret) {
- gvt_err("fail to initialize guest page for spt\n");
+ gvt_vgpu_err("fail to initialize guest page for spt\n");
goto err;
}
@@ -776,8 +776,7 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_find_shadow_page(
if (p)
return shadow_page_to_ppgtt_spt(p);
- gvt_err("vgpu%d: fail to find ppgtt shadow page: 0x%lx\n",
- vgpu->id, mfn);
+ gvt_vgpu_err("fail to find ppgtt shadow page: 0x%lx\n", mfn);
return NULL;
}
@@ -827,8 +826,8 @@ static int ppgtt_invalidate_shadow_page_by_shadow_entry(struct intel_vgpu *vgpu,
}
s = ppgtt_find_shadow_page(vgpu, ops->get_pfn(e));
if (!s) {
- gvt_err("vgpu%d: fail to find shadow page: mfn: 0x%lx\n",
- vgpu->id, ops->get_pfn(e));
+ gvt_vgpu_err("fail to find shadow page: mfn: 0x%lx\n",
+ ops->get_pfn(e));
return -ENXIO;
}
return ppgtt_invalidate_shadow_page(s);
@@ -836,6 +835,7 @@ static int ppgtt_invalidate_shadow_page_by_shadow_entry(struct intel_vgpu *vgpu,
static int ppgtt_invalidate_shadow_page(struct intel_vgpu_ppgtt_spt *spt)
{
+ struct intel_vgpu *vgpu = spt->vgpu;
struct intel_gvt_gtt_entry e;
unsigned long index;
int ret;
@@ -854,7 +854,7 @@ static int ppgtt_invalidate_shadow_page(struct intel_vgpu_ppgtt_spt *spt)
for_each_present_shadow_entry(spt, &e, index) {
if (!gtt_type_is_pt(get_next_pt_type(e.type))) {
- gvt_err("GVT doesn't support pse bit for now\n");
+ gvt_vgpu_err("GVT doesn't support pse bit for now\n");
return -EINVAL;
}
ret = ppgtt_invalidate_shadow_page_by_shadow_entry(
@@ -868,8 +868,8 @@ static int ppgtt_invalidate_shadow_page(struct intel_vgpu_ppgtt_spt *spt)
ppgtt_free_shadow_page(spt);
return 0;
fail:
- gvt_err("vgpu%d: fail: shadow page %p shadow entry 0x%llx type %d\n",
- spt->vgpu->id, spt, e.val64, e.type);
+ gvt_vgpu_err("fail: shadow page %p shadow entry 0x%llx type %d\n",
+ spt, e.val64, e.type);
return ret;
}
@@ -914,8 +914,8 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_populate_shadow_page_by_guest_entry(
}
return s;
fail:
- gvt_err("vgpu%d: fail: shadow page %p guest entry 0x%llx type %d\n",
- vgpu->id, s, we->val64, we->type);
+ gvt_vgpu_err("fail: shadow page %p guest entry 0x%llx type %d\n",
+ s, we->val64, we->type);
return ERR_PTR(ret);
}
@@ -953,7 +953,7 @@ static int ppgtt_populate_shadow_page(struct intel_vgpu_ppgtt_spt *spt)
for_each_present_guest_entry(spt, &ge, i) {
if (!gtt_type_is_pt(get_next_pt_type(ge.type))) {
- gvt_err("GVT doesn't support pse bit now\n");
+ gvt_vgpu_err("GVT doesn't support pse bit now\n");
ret = -EINVAL;
goto fail;
}
@@ -969,8 +969,8 @@ static int ppgtt_populate_shadow_page(struct intel_vgpu_ppgtt_spt *spt)
}
return 0;
fail:
- gvt_err("vgpu%d: fail: shadow page %p guest entry 0x%llx type %d\n",
- vgpu->id, spt, ge.val64, ge.type);
+ gvt_vgpu_err("fail: shadow page %p guest entry 0x%llx type %d\n",
+ spt, ge.val64, ge.type);
return ret;
}
@@ -999,7 +999,7 @@ static int ppgtt_handle_guest_entry_removal(struct intel_vgpu_guest_page *gpt,
struct intel_vgpu_ppgtt_spt *s =
ppgtt_find_shadow_page(vgpu, ops->get_pfn(&e));
if (!s) {
- gvt_err("fail to find guest page\n");
+ gvt_vgpu_err("fail to find guest page\n");
ret = -ENXIO;
goto fail;
}
@@ -1011,8 +1011,8 @@ static int ppgtt_handle_guest_entry_removal(struct intel_vgpu_guest_page *gpt,
ppgtt_set_shadow_entry(spt, &e, index);
return 0;
fail:
- gvt_err("vgpu%d: fail: shadow page %p guest entry 0x%llx type %d\n",
- vgpu->id, spt, e.val64, e.type);
+ gvt_vgpu_err("fail: shadow page %p guest entry 0x%llx type %d\n",
+ spt, e.val64, e.type);
return ret;
}
@@ -1046,8 +1046,8 @@ static int ppgtt_handle_guest_entry_add(struct intel_vgpu_guest_page *gpt,
}
return 0;
fail:
- gvt_err("vgpu%d: fail: spt %p guest entry 0x%llx type %d\n", vgpu->id,
- spt, we->val64, we->type);
+ gvt_vgpu_err("fail: spt %p guest entry 0x%llx type %d\n",
+ spt, we->val64, we->type);
return ret;
}
@@ -1250,8 +1250,8 @@ static int ppgtt_handle_guest_write_page_table(
}
return 0;
fail:
- gvt_err("vgpu%d: fail: shadow page %p guest entry 0x%llx type %d.\n",
- vgpu->id, spt, we->val64, we->type);
+ gvt_vgpu_err("fail: shadow page %p guest entry 0x%llx type %d.\n",
+ spt, we->val64, we->type);
return ret;
}
@@ -1493,7 +1493,7 @@ static int shadow_mm(struct intel_vgpu_mm *mm)
spt = ppgtt_populate_shadow_page_by_guest_entry(vgpu, &ge);
if (IS_ERR(spt)) {
- gvt_err("fail to populate guest root pointer\n");
+ gvt_vgpu_err("fail to populate guest root pointer\n");
ret = PTR_ERR(spt);
goto fail;
}
@@ -1566,7 +1566,7 @@ struct intel_vgpu_mm *intel_vgpu_create_mm(struct intel_vgpu *vgpu,
ret = gtt->mm_alloc_page_table(mm);
if (ret) {
- gvt_err("fail to allocate page table for mm\n");
+ gvt_vgpu_err("fail to allocate page table for mm\n");
goto fail;
}
@@ -1584,7 +1584,7 @@ struct intel_vgpu_mm *intel_vgpu_create_mm(struct intel_vgpu *vgpu,
}
return mm;
fail:
- gvt_err("fail to create mm\n");
+ gvt_vgpu_err("fail to create mm\n");
if (mm)
intel_gvt_mm_unreference(mm);
return ERR_PTR(ret);
@@ -1760,7 +1760,7 @@ unsigned long intel_vgpu_gma_to_gpa(struct intel_vgpu_mm *mm, unsigned long gma)
mm->page_table_level, gma, gpa);
return gpa;
err:
- gvt_err("invalid mm type: %d gma %lx\n", mm->type, gma);
+ gvt_vgpu_err("invalid mm type: %d gma %lx\n", mm->type, gma);
return INTEL_GVT_INVALID_ADDR;
}
@@ -1825,11 +1825,8 @@ static int emulate_gtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
gma = g_gtt_index << GTT_PAGE_SHIFT;
/* the VM may configure the whole GM space when ballooning is used */
- if (WARN_ONCE(!vgpu_gmadr_is_valid(vgpu, gma),
- "vgpu%d: found oob ggtt write, offset %x\n",
- vgpu->id, off)) {
+ if (!vgpu_gmadr_is_valid(vgpu, gma))
return 0;
- }
ggtt_get_guest_entry(ggtt_mm, &e, g_gtt_index);
@@ -1839,13 +1836,16 @@ static int emulate_gtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
if (ops->test_present(&e)) {
ret = gtt_entry_p2m(vgpu, &e, &m);
if (ret) {
- gvt_err("vgpu%d: fail to translate guest gtt entry\n",
- vgpu->id);
- return ret;
+ gvt_vgpu_err("fail to translate guest gtt entry\n");
+ /* guest driver may read/write the entry when partial
+ * update the entry in this situation p2m will fail
+ * settting the shadow entry to point to a scratch page
+ */
+ ops->set_pfn(&m, gvt->gtt.scratch_ggtt_mfn);
}
} else {
m = e;
- m.val64 = 0;
+ ops->set_pfn(&m, gvt->gtt.scratch_ggtt_mfn);
}
ggtt_set_shadow_entry(ggtt_mm, &m, g_gtt_index);
@@ -1896,14 +1896,14 @@ static int alloc_scratch_pages(struct intel_vgpu *vgpu,
scratch_pt = (void *)get_zeroed_page(GFP_KERNEL);
if (!scratch_pt) {
- gvt_err("fail to allocate scratch page\n");
+ gvt_vgpu_err("fail to allocate scratch page\n");
return -ENOMEM;
}
daddr = dma_map_page(dev, virt_to_page(scratch_pt), 0,
4096, PCI_DMA_BIDIRECTIONAL);
if (dma_mapping_error(dev, daddr)) {
- gvt_err("fail to dmamap scratch_pt\n");
+ gvt_vgpu_err("fail to dmamap scratch_pt\n");
__free_page(virt_to_page(scratch_pt));
return -ENOMEM;
}
@@ -2006,7 +2006,7 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu)
ggtt_mm = intel_vgpu_create_mm(vgpu, INTEL_GVT_MM_GGTT,
NULL, 1, 0);
if (IS_ERR(ggtt_mm)) {
- gvt_err("fail to create mm for ggtt.\n");
+ gvt_vgpu_err("fail to create mm for ggtt.\n");
return PTR_ERR(ggtt_mm);
}
@@ -2015,6 +2015,22 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu)
return create_scratch_page_tree(vgpu);
}
+static void intel_vgpu_free_mm(struct intel_vgpu *vgpu, int type)
+{
+ struct list_head *pos, *n;
+ struct intel_vgpu_mm *mm;
+
+ list_for_each_safe(pos, n, &vgpu->gtt.mm_list_head) {
+ mm = container_of(pos, struct intel_vgpu_mm, list);
+ if (mm->type == type) {
+ vgpu->gvt->gtt.mm_free_page_table(mm);
+ list_del(&mm->list);
+ list_del(&mm->lru_list);
+ kfree(mm);
+ }
+ }
+}
+
/**
* intel_vgpu_clean_gtt - clean up per-vGPU graphics memory virulization
* @vgpu: a vGPU
@@ -2027,19 +2043,11 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu)
*/
void intel_vgpu_clean_gtt(struct intel_vgpu *vgpu)
{
- struct list_head *pos, *n;
- struct intel_vgpu_mm *mm;
-
ppgtt_free_all_shadow_page(vgpu);
release_scratch_page_tree(vgpu);
- list_for_each_safe(pos, n, &vgpu->gtt.mm_list_head) {
- mm = container_of(pos, struct intel_vgpu_mm, list);
- vgpu->gvt->gtt.mm_free_page_table(mm);
- list_del(&mm->list);
- list_del(&mm->lru_list);
- kfree(mm);
- }
+ intel_vgpu_free_mm(vgpu, INTEL_GVT_MM_PPGTT);
+ intel_vgpu_free_mm(vgpu, INTEL_GVT_MM_GGTT);
}
static void clean_spt_oos(struct intel_gvt *gvt)
@@ -2071,7 +2079,6 @@ static int setup_spt_oos(struct intel_gvt *gvt)
for (i = 0; i < preallocated_oos_pages; i++) {
oos_page = kzalloc(sizeof(*oos_page), GFP_KERNEL);
if (!oos_page) {
- gvt_err("fail to pre-allocate oos page\n");
ret = -ENOMEM;
goto fail;
}
@@ -2161,7 +2168,7 @@ int intel_vgpu_g2v_create_ppgtt_mm(struct intel_vgpu *vgpu,
mm = intel_vgpu_create_mm(vgpu, INTEL_GVT_MM_PPGTT,
pdp, page_table_level, 0);
if (IS_ERR(mm)) {
- gvt_err("fail to create mm\n");
+ gvt_vgpu_err("fail to create mm\n");
return PTR_ERR(mm);
}
}
@@ -2191,7 +2198,7 @@ int intel_vgpu_g2v_destroy_ppgtt_mm(struct intel_vgpu *vgpu,
mm = intel_vgpu_find_ppgtt_mm(vgpu, page_table_level, pdp);
if (!mm) {
- gvt_err("fail to find ppgtt instance.\n");
+ gvt_vgpu_err("fail to find ppgtt instance.\n");
return -EINVAL;
}
intel_gvt_mm_unreference(mm);
@@ -2322,6 +2329,13 @@ void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu, bool dmlr)
int i;
ppgtt_free_all_shadow_page(vgpu);
+
+ /* Shadow pages are only created when there is no page
+ * table tracking data, so remove page tracking data after
+ * removing the shadow pages.
+ */
+ intel_vgpu_free_mm(vgpu, INTEL_GVT_MM_PPGTT);
+
if (!dmlr)
return;
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index e227caf..6dfc48b 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -143,6 +143,8 @@ struct intel_vgpu {
int id;
unsigned long handle; /* vGPU handle used by hypervisor MPT modules */
bool active;
+ bool pv_notified;
+ bool failsafe;
bool resetting;
void *sched_data;
@@ -160,7 +162,6 @@ struct intel_vgpu {
atomic_t running_workload_num;
DECLARE_BITMAP(tlb_handle_pending, I915_NUM_ENGINES);
struct i915_gem_context *shadow_ctx;
- struct notifier_block shadow_ctx_notifier_block;
#if IS_ENABLED(CONFIG_DRM_I915_GVT_KVMGT)
struct {
@@ -203,18 +204,18 @@ struct intel_gvt_firmware {
};
struct intel_gvt_opregion {
- void __iomem *opregion_va;
+ void *opregion_va;
u32 opregion_pa;
};
#define NR_MAX_INTEL_VGPU_TYPES 20
struct intel_vgpu_type {
char name[16];
- unsigned int max_instance;
unsigned int avail_instance;
unsigned int low_gm_size;
unsigned int high_gm_size;
unsigned int fence;
+ enum intel_vgpu_edid resolution;
};
struct intel_gvt {
@@ -231,6 +232,7 @@ struct intel_gvt {
struct intel_gvt_gtt gtt;
struct intel_gvt_opregion opregion;
struct intel_gvt_workload_scheduler scheduler;
+ struct notifier_block shadow_ctx_notifier_block[I915_NUM_ENGINES];
DECLARE_HASHTABLE(cmd_table, GVT_CMD_HASH_BITS);
struct intel_vgpu_type *types;
unsigned int num_types;
@@ -317,6 +319,7 @@ struct intel_vgpu_creation_params {
__u64 low_gm_sz; /* in MB */
__u64 high_gm_sz; /* in MB */
__u64 fence_sz;
+ __u64 resolution;
__s32 primary;
__u64 vgpu_id;
};
@@ -449,6 +452,11 @@ struct intel_gvt_ops {
};
+enum {
+ GVT_FAILSAFE_UNSUPPORTED_GUEST,
+ GVT_FAILSAFE_INSUFFICIENT_RESOURCE,
+};
+
#include "mpt.h"
#endif
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 1d45062..6da9ae1 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -121,6 +121,7 @@ static int new_mmio_info(struct intel_gvt *gvt,
info->size = size;
info->length = (i + 4) < end ? 4 : (end - i);
info->addr_mask = addr_mask;
+ info->ro_mask = ro_mask;
info->device = device;
info->read = read ? read : intel_vgpu_default_mmio_read;
info->write = write ? write : intel_vgpu_default_mmio_write;
@@ -150,15 +151,42 @@ static int render_mmio_to_ring_id(struct intel_gvt *gvt, unsigned int reg)
#define fence_num_to_offset(num) \
(num * 8 + i915_mmio_reg_offset(FENCE_REG_GEN6_LO(0)))
+
+static void enter_failsafe_mode(struct intel_vgpu *vgpu, int reason)
+{
+ switch (reason) {
+ case GVT_FAILSAFE_UNSUPPORTED_GUEST:
+ pr_err("Detected your guest driver doesn't support GVT-g.\n");
+ break;
+ case GVT_FAILSAFE_INSUFFICIENT_RESOURCE:
+ pr_err("Graphics resource is not enough for the guest\n");
+ default:
+ break;
+ }
+ pr_err("Now vgpu %d will enter failsafe mode.\n", vgpu->id);
+ vgpu->failsafe = true;
+}
+
static int sanitize_fence_mmio_access(struct intel_vgpu *vgpu,
unsigned int fence_num, void *p_data, unsigned int bytes)
{
if (fence_num >= vgpu_fence_sz(vgpu)) {
- gvt_err("vgpu%d: found oob fence register access\n",
- vgpu->id);
- gvt_err("vgpu%d: total fence num %d access fence num %d\n",
- vgpu->id, vgpu_fence_sz(vgpu), fence_num);
+
+ /* When guest access oob fence regs without access
+ * pv_info first, we treat guest not supporting GVT,
+ * and we will let vgpu enter failsafe mode.
+ */
+ if (!vgpu->pv_notified)
+ enter_failsafe_mode(vgpu,
+ GVT_FAILSAFE_UNSUPPORTED_GUEST);
+
+ if (!vgpu->mmio.disable_warn_untrack) {
+ gvt_vgpu_err("found oob fence register access\n");
+ gvt_vgpu_err("total fence %d, access fence %d\n",
+ vgpu_fence_sz(vgpu), fence_num);
+ }
memset(p_data, 0, bytes);
+ return -EINVAL;
}
return 0;
}
@@ -219,7 +247,7 @@ static int mul_force_wake_write(struct intel_vgpu *vgpu,
break;
default:
/*should not hit here*/
- gvt_err("invalid forcewake offset 0x%x\n", offset);
+ gvt_vgpu_err("invalid forcewake offset 0x%x\n", offset);
return -EINVAL;
}
} else {
@@ -369,6 +397,74 @@ static int pipeconf_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
return 0;
}
+/* ascendingly sorted */
+static i915_reg_t force_nonpriv_white_list[] = {
+ GEN9_CS_DEBUG_MODE1, //_MMIO(0x20ec)
+ GEN9_CTX_PREEMPT_REG,//_MMIO(0x2248)
+ GEN8_CS_CHICKEN1,//_MMIO(0x2580)
+ _MMIO(0x2690),
+ _MMIO(0x2694),
+ _MMIO(0x2698),
+ _MMIO(0x4de0),
+ _MMIO(0x4de4),
+ _MMIO(0x4dfc),
+ GEN7_COMMON_SLICE_CHICKEN1,//_MMIO(0x7010)
+ _MMIO(0x7014),
+ HDC_CHICKEN0,//_MMIO(0x7300)
+ GEN8_HDC_CHICKEN1,//_MMIO(0x7304)
+ _MMIO(0x7700),
+ _MMIO(0x7704),
+ _MMIO(0x7708),
+ _MMIO(0x770c),
+ _MMIO(0xb110),
+ GEN8_L3SQCREG4,//_MMIO(0xb118)
+ _MMIO(0xe100),
+ _MMIO(0xe18c),
+ _MMIO(0xe48c),
+ _MMIO(0xe5f4),
+};
+
+/* a simple bsearch */
+static inline bool in_whitelist(unsigned int reg)
+{
+ int left = 0, right = ARRAY_SIZE(force_nonpriv_white_list);
+ i915_reg_t *array = force_nonpriv_white_list;
+
+ while (left < right) {
+ int mid = (left + right)/2;
+
+ if (reg > array[mid].reg)
+ left = mid + 1;
+ else if (reg < array[mid].reg)
+ right = mid;
+ else
+ return true;
+ }
+ return false;
+}
+
+static int force_nonpriv_write(struct intel_vgpu *vgpu,
+ unsigned int offset, void *p_data, unsigned int bytes)
+{
+ u32 reg_nonpriv = *(u32 *)p_data;
+ int ret = -EINVAL;
+
+ if ((bytes != 4) || ((offset & (bytes - 1)) != 0)) {
+ gvt_err("vgpu(%d) Invalid FORCE_NONPRIV offset %x(%dB)\n",
+ vgpu->id, offset, bytes);
+ return ret;
+ }
+
+ if (in_whitelist(reg_nonpriv)) {
+ ret = intel_vgpu_default_mmio_write(vgpu, offset, p_data,
+ bytes);
+ } else {
+ gvt_err("vgpu(%d) Invalid FORCE_NONPRIV write %x\n",
+ vgpu->id, reg_nonpriv);
+ }
+ return ret;
+}
+
static int ddi_buf_ctl_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
void *p_data, unsigned int bytes)
{
@@ -432,7 +528,7 @@ static int check_fdi_rx_train_status(struct intel_vgpu *vgpu,
fdi_tx_train_bits = FDI_LINK_TRAIN_PATTERN_2;
fdi_iir_check_bits = FDI_RX_SYMBOL_LOCK;
} else {
- gvt_err("Invalid train pattern %d\n", train_pattern);
+ gvt_vgpu_err("Invalid train pattern %d\n", train_pattern);
return -EINVAL;
}
@@ -490,7 +586,7 @@ static int update_fdi_rx_iir_status(struct intel_vgpu *vgpu,
else if (FDI_RX_IMR_TO_PIPE(offset) != INVALID_INDEX)
index = FDI_RX_IMR_TO_PIPE(offset);
else {
- gvt_err("Unsupport registers %x\n", offset);
+ gvt_vgpu_err("Unsupport registers %x\n", offset);
return -EINVAL;
}
@@ -720,7 +816,7 @@ static int dp_aux_ch_ctl_mmio_write(struct intel_vgpu *vgpu,
u32 data;
if (!dpy_is_valid_port(port_index)) {
- gvt_err("GVT(%d): Unsupported DP port access!\n", vgpu->id);
+ gvt_vgpu_err("Unsupported DP port access!\n");
return 0;
}
@@ -874,6 +970,14 @@ static int dp_aux_ch_ctl_mmio_write(struct intel_vgpu *vgpu,
return 0;
}
+static int mbctl_write(struct intel_vgpu *vgpu, unsigned int offset,
+ void *p_data, unsigned int bytes)
+{
+ *(u32 *)p_data &= (~GEN6_MBCTL_ENABLE_BOOT_FETCH);
+ write_vreg(vgpu, offset, p_data, bytes);
+ return 0;
+}
+
static int vga_control_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
void *p_data, unsigned int bytes)
{
@@ -918,8 +1022,7 @@ static void write_virtual_sbi_register(struct intel_vgpu *vgpu,
if (i == num) {
if (num == SBI_REG_MAX) {
- gvt_err("vgpu%d: SBI caching meets maximum limits\n",
- vgpu->id);
+ gvt_vgpu_err("SBI caching meets maximum limits\n");
return;
}
display->sbi.number++;
@@ -999,8 +1102,9 @@ static int pvinfo_mmio_read(struct intel_vgpu *vgpu, unsigned int offset,
break;
}
if (invalid_read)
- gvt_err("invalid pvinfo read: [%x:%x] = %x\n",
+ gvt_vgpu_err("invalid pvinfo read: [%x:%x] = %x\n",
offset, bytes, *(u32 *)p_data);
+ vgpu->pv_notified = true;
return 0;
}
@@ -1026,7 +1130,7 @@ static int handle_g2v_notification(struct intel_vgpu *vgpu, int notification)
case 1: /* Remove this in guest driver. */
break;
default:
- gvt_err("Invalid PV notification %d\n", notification);
+ gvt_vgpu_err("Invalid PV notification %d\n", notification);
}
return ret;
}
@@ -1039,7 +1143,7 @@ static int send_display_ready_uevent(struct intel_vgpu *vgpu, int ready)
char vmid_str[20];
char display_ready_str[20];
- snprintf(display_ready_str, 20, "GVT_DISPLAY_READY=%d\n", ready);
+ snprintf(display_ready_str, 20, "GVT_DISPLAY_READY=%d", ready);
env[0] = display_ready_str;
snprintf(vmid_str, 20, "VMID=%d", vgpu->id);
@@ -1078,8 +1182,11 @@ static int pvinfo_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
case _vgtif_reg(execlist_context_descriptor_lo):
case _vgtif_reg(execlist_context_descriptor_hi):
break;
+ case _vgtif_reg(rsv5[0])..._vgtif_reg(rsv5[3]):
+ enter_failsafe_mode(vgpu, GVT_FAILSAFE_INSUFFICIENT_RESOURCE);
+ break;
default:
- gvt_err("invalid pvinfo write offset %x bytes %x data %x\n",
+ gvt_vgpu_err("invalid pvinfo write offset %x bytes %x data %x\n",
offset, bytes, data);
break;
}
@@ -1203,26 +1310,37 @@ static int mailbox_write(struct intel_vgpu *vgpu, unsigned int offset,
u32 *data0 = &vgpu_vreg(vgpu, GEN6_PCODE_DATA);
switch (cmd) {
- case 0x6:
- /**
- * "Read memory latency" command on gen9.
- * Below memory latency values are read
- * from skylake platform.
- */
- if (!*data0)
- *data0 = 0x1e1a1100;
- else
- *data0 = 0x61514b3d;
+ case GEN9_PCODE_READ_MEM_LATENCY:
+ if (IS_SKYLAKE(vgpu->gvt->dev_priv)) {
+ /**
+ * "Read memory latency" command on gen9.
+ * Below memory latency values are read
+ * from skylake platform.
+ */
+ if (!*data0)
+ *data0 = 0x1e1a1100;
+ else
+ *data0 = 0x61514b3d;
+ }
break;
- case 0x5:
+ case SKL_PCODE_CDCLK_CONTROL:
+ if (IS_SKYLAKE(vgpu->gvt->dev_priv))
+ *data0 = SKL_CDCLK_READY_FOR_CHANGE;
+ break;
+ case GEN6_PCODE_READ_RC6VIDS:
*data0 |= 0x1;
break;
}
gvt_dbg_core("VM(%d) write %x to mailbox, return data0 %x\n",
vgpu->id, value, *data0);
-
- value &= ~(1 << 31);
+ /**
+ * PCODE_READY clear means ready for pcode read/write,
+ * PCODE_ERROR_MASK clear means no error happened. In GVT-g we
+ * always emulate as pcode read/write success and ready for access
+ * anytime, since we don't touch real physical registers here.
+ */
+ value &= ~(GEN6_PCODE_READY | GEN6_PCODE_ERROR_MASK);
return intel_vgpu_default_mmio_write(vgpu, offset, &value, bytes);
}
@@ -1302,7 +1420,8 @@ static int elsp_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
if (execlist->elsp_dwords.index == 3) {
ret = intel_vgpu_submit_execlist(vgpu, ring_id);
if(ret)
- gvt_err("fail submit workload on ring %d\n", ring_id);
+ gvt_vgpu_err("fail submit workload on ring %d\n",
+ ring_id);
}
++execlist->elsp_dwords.index;
@@ -1318,6 +1437,17 @@ static int ring_mode_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
bool enable_execlist;
write_vreg(vgpu, offset, p_data, bytes);
+
+ /* when PPGTT mode enabled, we will check if guest has called
+ * pvinfo, if not, we will treat this guest as non-gvtg-aware
+ * guest, and stop emulating its cfg space, mmio, gtt, etc.
+ */
+ if (((data & _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE)) ||
+ (data & _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE)))
+ && !vgpu->pv_notified) {
+ enter_failsafe_mode(vgpu, GVT_FAILSAFE_UNSUPPORTED_GUEST);
+ return 0;
+ }
if ((data & _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE))
|| (data & _MASKED_BIT_DISABLE(GFX_RUN_LIST_ENABLE))) {
enable_execlist = !!(data & GFX_RUN_LIST_ENABLE);
@@ -1400,6 +1530,9 @@ static int ring_reset_ctl_write(struct intel_vgpu *vgpu,
#define MMIO_GM(reg, d, r, w) \
MMIO_F(reg, 4, F_GMADR, 0xFFFFF000, 0, d, r, w)
+#define MMIO_GM_RDR(reg, d, r, w) \
+ MMIO_F(reg, 4, F_GMADR | F_CMD_ACCESS, 0xFFFFF000, 0, d, r, w)
+
#define MMIO_RO(reg, d, f, rm, r, w) \
MMIO_F(reg, 4, F_RO | f, 0, rm, d, r, w)
@@ -1419,6 +1552,9 @@ static int ring_reset_ctl_write(struct intel_vgpu *vgpu,
#define MMIO_RING_GM(prefix, d, r, w) \
MMIO_RING_F(prefix, 4, F_GMADR, 0xFFFF0000, 0, d, r, w)
+#define MMIO_RING_GM_RDR(prefix, d, r, w) \
+ MMIO_RING_F(prefix, 4, F_GMADR | F_CMD_ACCESS, 0xFFFF0000, 0, d, r, w)
+
#define MMIO_RING_RO(prefix, d, f, rm, r, w) \
MMIO_RING_F(prefix, 4, F_RO | f, 0, rm, d, r, w)
@@ -1427,73 +1563,81 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
struct drm_i915_private *dev_priv = gvt->dev_priv;
int ret;
- MMIO_RING_DFH(RING_IMR, D_ALL, 0, NULL, intel_vgpu_reg_imr_handler);
+ MMIO_RING_DFH(RING_IMR, D_ALL, F_CMD_ACCESS, NULL,
+ intel_vgpu_reg_imr_handler);
MMIO_DFH(SDEIMR, D_ALL, 0, NULL, intel_vgpu_reg_imr_handler);
MMIO_DFH(SDEIER, D_ALL, 0, NULL, intel_vgpu_reg_ier_handler);
MMIO_DFH(SDEIIR, D_ALL, 0, NULL, intel_vgpu_reg_iir_handler);
MMIO_D(SDEISR, D_ALL);
- MMIO_RING_D(RING_HWSTAM, D_ALL);
+ MMIO_RING_DFH(RING_HWSTAM, D_ALL, F_CMD_ACCESS, NULL, NULL);
- MMIO_GM(RENDER_HWS_PGA_GEN7, D_ALL, NULL, NULL);
- MMIO_GM(BSD_HWS_PGA_GEN7, D_ALL, NULL, NULL);
- MMIO_GM(BLT_HWS_PGA_GEN7, D_ALL, NULL, NULL);
- MMIO_GM(VEBOX_HWS_PGA_GEN7, D_ALL, NULL, NULL);
+ MMIO_GM_RDR(RENDER_HWS_PGA_GEN7, D_ALL, NULL, NULL);
+ MMIO_GM_RDR(BSD_HWS_PGA_GEN7, D_ALL, NULL, NULL);
+ MMIO_GM_RDR(BLT_HWS_PGA_GEN7, D_ALL, NULL, NULL);
+ MMIO_GM_RDR(VEBOX_HWS_PGA_GEN7, D_ALL, NULL, NULL);
#define RING_REG(base) (base + 0x28)
- MMIO_RING_D(RING_REG, D_ALL);
+ MMIO_RING_DFH(RING_REG, D_ALL, F_CMD_ACCESS, NULL, NULL);
#undef RING_REG
#define RING_REG(base) (base + 0x134)
- MMIO_RING_D(RING_REG, D_ALL);
+ MMIO_RING_DFH(RING_REG, D_ALL, F_CMD_ACCESS, NULL, NULL);
#undef RING_REG
- MMIO_GM(0x2148, D_ALL, NULL, NULL);
- MMIO_GM(CCID, D_ALL, NULL, NULL);
- MMIO_GM(0x12198, D_ALL, NULL, NULL);
+ MMIO_GM_RDR(0x2148, D_ALL, NULL, NULL);
+ MMIO_GM_RDR(CCID, D_ALL, NULL, NULL);
+ MMIO_GM_RDR(0x12198, D_ALL, NULL, NULL);
MMIO_D(GEN7_CXT_SIZE, D_ALL);
- MMIO_RING_D(RING_TAIL, D_ALL);
- MMIO_RING_D(RING_HEAD, D_ALL);
- MMIO_RING_D(RING_CTL, D_ALL);
- MMIO_RING_D(RING_ACTHD, D_ALL);
- MMIO_RING_GM(RING_START, D_ALL, NULL, NULL);
+ MMIO_RING_DFH(RING_TAIL, D_ALL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_RING_DFH(RING_HEAD, D_ALL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_RING_DFH(RING_CTL, D_ALL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_RING_DFH(RING_ACTHD, D_ALL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_RING_GM_RDR(RING_START, D_ALL, NULL, NULL);
/* RING MODE */
#define RING_REG(base) (base + 0x29c)
- MMIO_RING_DFH(RING_REG, D_ALL, F_MODE_MASK, NULL, ring_mode_mmio_write);
+ MMIO_RING_DFH(RING_REG, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL,
+ ring_mode_mmio_write);
#undef RING_REG
- MMIO_RING_DFH(RING_MI_MODE, D_ALL, F_MODE_MASK, NULL, NULL);
- MMIO_RING_DFH(RING_INSTPM, D_ALL, F_MODE_MASK, NULL, NULL);
+ MMIO_RING_DFH(RING_MI_MODE, D_ALL, F_MODE_MASK | F_CMD_ACCESS,
+ NULL, NULL);
+ MMIO_RING_DFH(RING_INSTPM, D_ALL, F_MODE_MASK | F_CMD_ACCESS,
+ NULL, NULL);
MMIO_RING_DFH(RING_TIMESTAMP, D_ALL, F_CMD_ACCESS,
ring_timestamp_mmio_read, NULL);
MMIO_RING_DFH(RING_TIMESTAMP_UDW, D_ALL, F_CMD_ACCESS,
ring_timestamp_mmio_read, NULL);
- MMIO_DFH(GEN7_GT_MODE, D_ALL, F_MODE_MASK, NULL, NULL);
- MMIO_DFH(CACHE_MODE_0_GEN7, D_ALL, F_MODE_MASK, NULL, NULL);
+ MMIO_DFH(GEN7_GT_MODE, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(CACHE_MODE_0_GEN7, D_ALL, F_MODE_MASK | F_CMD_ACCESS,
+ NULL, NULL);
MMIO_DFH(CACHE_MODE_1, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(CACHE_MODE_0, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x2124, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
- MMIO_DFH(0x20dc, D_ALL, F_MODE_MASK, NULL, NULL);
- MMIO_DFH(_3D_CHICKEN3, D_ALL, F_MODE_MASK, NULL, NULL);
- MMIO_DFH(0x2088, D_ALL, F_MODE_MASK, NULL, NULL);
- MMIO_DFH(0x20e4, D_ALL, F_MODE_MASK, NULL, NULL);
- MMIO_DFH(0x2470, D_ALL, F_MODE_MASK, NULL, NULL);
- MMIO_D(GAM_ECOCHK, D_ALL);
- MMIO_DFH(GEN7_COMMON_SLICE_CHICKEN1, D_ALL, F_MODE_MASK, NULL, NULL);
+ MMIO_DFH(0x20dc, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(_3D_CHICKEN3, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x2088, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x20e4, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x2470, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(GAM_ECOCHK, D_ALL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(GEN7_COMMON_SLICE_CHICKEN1, D_ALL, F_MODE_MASK | F_CMD_ACCESS,
+ NULL, NULL);
MMIO_DFH(COMMON_SLICE_CHICKEN2, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
- MMIO_D(0x9030, D_ALL);
- MMIO_D(0x20a0, D_ALL);
- MMIO_D(0x2420, D_ALL);
- MMIO_D(0x2430, D_ALL);
- MMIO_D(0x2434, D_ALL);
- MMIO_D(0x2438, D_ALL);
- MMIO_D(0x243c, D_ALL);
- MMIO_DFH(0x7018, D_ALL, F_MODE_MASK, NULL, NULL);
+ MMIO_DFH(0x9030, D_ALL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x20a0, D_ALL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x2420, D_ALL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x2430, D_ALL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x2434, D_ALL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x2438, D_ALL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x243c, D_ALL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x7018, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
MMIO_DFH(HALF_SLICE_CHICKEN3, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
- MMIO_DFH(0xe100, D_ALL, F_MODE_MASK, NULL, NULL);
+ MMIO_DFH(GEN7_HALF_SLICE_CHICKEN1, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
/* display */
MMIO_F(0x60220, 0x20, 0, 0, 0, D_ALL, NULL, NULL);
@@ -2022,8 +2166,8 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
MMIO_D(FORCEWAKE_ACK, D_ALL);
MMIO_D(GEN6_GT_CORE_STATUS, D_ALL);
MMIO_D(GEN6_GT_THREAD_STATUS_REG, D_ALL);
- MMIO_D(GTFIFODBG, D_ALL);
- MMIO_D(GTFIFOCTL, D_ALL);
+ MMIO_DFH(GTFIFODBG, D_ALL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(GTFIFOCTL, D_ALL, F_CMD_ACCESS, NULL, NULL);
MMIO_DH(FORCEWAKE_MT, D_PRE_SKL, NULL, mul_force_wake_write);
MMIO_DH(FORCEWAKE_ACK_HSW, D_HSW | D_BDW, NULL, NULL);
MMIO_D(ECOBUS, D_ALL);
@@ -2080,7 +2224,7 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
MMIO_F(0x4f000, 0x90, 0, 0, 0, D_ALL, NULL, NULL);
- MMIO_D(GEN6_PCODE_MAILBOX, D_PRE_SKL);
+ MMIO_D(GEN6_PCODE_MAILBOX, D_PRE_BDW);
MMIO_D(GEN6_PCODE_DATA, D_ALL);
MMIO_D(0x13812c, D_ALL);
MMIO_DH(GEN7_ERR_INT, D_ALL, NULL, NULL);
@@ -2102,7 +2246,7 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
MMIO_D(0x7180, D_ALL);
MMIO_D(0x7408, D_ALL);
MMIO_D(0x7c00, D_ALL);
- MMIO_D(GEN6_MBCTL, D_ALL);
+ MMIO_DH(GEN6_MBCTL, D_ALL, NULL, mbctl_write);
MMIO_D(0x911c, D_ALL);
MMIO_D(0x9120, D_ALL);
MMIO_DFH(GEN7_UCGCTL4, D_ALL, F_CMD_ACCESS, NULL, NULL);
@@ -2159,36 +2303,35 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
MMIO_D(0x1a054, D_ALL);
MMIO_D(0x44070, D_ALL);
-
- MMIO_D(0x215c, D_HSW_PLUS);
+ MMIO_DFH(0x215c, D_HSW_PLUS, F_CMD_ACCESS, NULL, NULL);
MMIO_DFH(0x2178, D_ALL, F_CMD_ACCESS, NULL, NULL);
MMIO_DFH(0x217c, D_ALL, F_CMD_ACCESS, NULL, NULL);
MMIO_DFH(0x12178, D_ALL, F_CMD_ACCESS, NULL, NULL);
MMIO_DFH(0x1217c, D_ALL, F_CMD_ACCESS, NULL, NULL);
- MMIO_F(0x2290, 8, 0, 0, 0, D_HSW_PLUS, NULL, NULL);
- MMIO_D(GEN7_OACONTROL, D_HSW);
+ MMIO_F(0x2290, 8, F_CMD_ACCESS, 0, 0, D_HSW_PLUS, NULL, NULL);
+ MMIO_DFH(GEN7_OACONTROL, D_HSW, F_CMD_ACCESS, NULL, NULL);
MMIO_D(0x2b00, D_BDW_PLUS);
MMIO_D(0x2360, D_BDW_PLUS);
- MMIO_F(0x5200, 32, 0, 0, 0, D_ALL, NULL, NULL);
- MMIO_F(0x5240, 32, 0, 0, 0, D_ALL, NULL, NULL);
- MMIO_F(0x5280, 16, 0, 0, 0, D_ALL, NULL, NULL);
+ MMIO_F(0x5200, 32, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+ MMIO_F(0x5240, 32, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+ MMIO_F(0x5280, 16, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
MMIO_DFH(0x1c17c, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
MMIO_DFH(0x1c178, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
- MMIO_D(BCS_SWCTRL, D_ALL);
+ MMIO_DFH(BCS_SWCTRL, D_ALL, F_CMD_ACCESS, NULL, NULL);
- MMIO_F(HS_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
- MMIO_F(DS_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
- MMIO_F(IA_VERTICES_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
- MMIO_F(IA_PRIMITIVES_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
- MMIO_F(VS_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
- MMIO_F(GS_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
- MMIO_F(GS_PRIMITIVES_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
- MMIO_F(CL_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
- MMIO_F(CL_PRIMITIVES_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
- MMIO_F(PS_INVOCATION_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
- MMIO_F(PS_DEPTH_COUNT, 8, 0, 0, 0, D_ALL, NULL, NULL);
+ MMIO_F(HS_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+ MMIO_F(DS_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+ MMIO_F(IA_VERTICES_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+ MMIO_F(IA_PRIMITIVES_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+ MMIO_F(VS_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+ MMIO_F(GS_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+ MMIO_F(GS_PRIMITIVES_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+ MMIO_F(CL_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+ MMIO_F(CL_PRIMITIVES_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+ MMIO_F(PS_INVOCATION_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
+ MMIO_F(PS_DEPTH_COUNT, 8, F_CMD_ACCESS, 0, 0, D_ALL, NULL, NULL);
MMIO_DH(0x4260, D_BDW_PLUS, NULL, gvt_reg_tlb_control_handler);
MMIO_DH(0x4264, D_BDW_PLUS, NULL, gvt_reg_tlb_control_handler);
MMIO_DH(0x4268, D_BDW_PLUS, NULL, gvt_reg_tlb_control_handler);
@@ -2196,6 +2339,17 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
MMIO_DH(0x4270, D_BDW_PLUS, NULL, gvt_reg_tlb_control_handler);
MMIO_DFH(0x4094, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(ARB_MODE, D_ALL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+ MMIO_RING_GM_RDR(RING_BBADDR, D_ALL, NULL, NULL);
+ MMIO_DFH(0x2220, D_ALL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x12220, D_ALL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x22220, D_ALL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_RING_DFH(RING_SYNC_1, D_ALL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_RING_DFH(RING_SYNC_0, D_ALL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x22178, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x1a178, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x1a17c, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x2217c, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
return 0;
}
@@ -2204,7 +2358,7 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
struct drm_i915_private *dev_priv = gvt->dev_priv;
int ret;
- MMIO_DH(RING_IMR(GEN8_BSD2_RING_BASE), D_BDW_PLUS, NULL,
+ MMIO_DFH(RING_IMR(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS, NULL,
intel_vgpu_reg_imr_handler);
MMIO_DH(GEN8_GT_IMR(0), D_BDW_PLUS, NULL, intel_vgpu_reg_imr_handler);
@@ -2269,24 +2423,31 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
MMIO_DH(GEN8_MASTER_IRQ, D_BDW_PLUS, NULL,
intel_vgpu_reg_master_irq_handler);
- MMIO_D(RING_HWSTAM(GEN8_BSD2_RING_BASE), D_BDW_PLUS);
- MMIO_D(0x1c134, D_BDW_PLUS);
+ MMIO_DFH(RING_HWSTAM(GEN8_BSD2_RING_BASE), D_BDW_PLUS,
+ F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x1c134, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
- MMIO_D(RING_TAIL(GEN8_BSD2_RING_BASE), D_BDW_PLUS);
- MMIO_D(RING_HEAD(GEN8_BSD2_RING_BASE), D_BDW_PLUS);
- MMIO_GM(RING_START(GEN8_BSD2_RING_BASE), D_BDW_PLUS, NULL, NULL);
- MMIO_D(RING_CTL(GEN8_BSD2_RING_BASE), D_BDW_PLUS);
- MMIO_D(RING_ACTHD(GEN8_BSD2_RING_BASE), D_BDW_PLUS);
- MMIO_D(RING_ACTHD_UDW(GEN8_BSD2_RING_BASE), D_BDW_PLUS);
- MMIO_DFH(0x1c29c, D_BDW_PLUS, F_MODE_MASK, NULL, ring_mode_mmio_write);
- MMIO_DFH(RING_MI_MODE(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_MODE_MASK,
- NULL, NULL);
- MMIO_DFH(RING_INSTPM(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_MODE_MASK,
- NULL, NULL);
+ MMIO_DFH(RING_TAIL(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS,
+ NULL, NULL);
+ MMIO_DFH(RING_HEAD(GEN8_BSD2_RING_BASE), D_BDW_PLUS,
+ F_CMD_ACCESS, NULL, NULL);
+ MMIO_GM_RDR(RING_START(GEN8_BSD2_RING_BASE), D_BDW_PLUS, NULL, NULL);
+ MMIO_DFH(RING_CTL(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS,
+ NULL, NULL);
+ MMIO_DFH(RING_ACTHD(GEN8_BSD2_RING_BASE), D_BDW_PLUS,
+ F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(RING_ACTHD_UDW(GEN8_BSD2_RING_BASE), D_BDW_PLUS,
+ F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x1c29c, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL,
+ ring_mode_mmio_write);
+ MMIO_DFH(RING_MI_MODE(GEN8_BSD2_RING_BASE), D_BDW_PLUS,
+ F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(RING_INSTPM(GEN8_BSD2_RING_BASE), D_BDW_PLUS,
+ F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
MMIO_DFH(RING_TIMESTAMP(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS,
ring_timestamp_mmio_read, NULL);
- MMIO_RING_D(RING_ACTHD_UDW, D_BDW_PLUS);
+ MMIO_RING_DFH(RING_ACTHD_UDW, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
#define RING_REG(base) (base + 0xd0)
MMIO_RING_F(RING_REG, 4, F_RO, 0,
@@ -2303,13 +2464,16 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
#undef RING_REG
#define RING_REG(base) (base + 0x234)
- MMIO_RING_F(RING_REG, 8, F_RO, 0, ~0, D_BDW_PLUS, NULL, NULL);
- MMIO_F(RING_REG(GEN8_BSD2_RING_BASE), 4, F_RO, 0, ~0LL, D_BDW_PLUS, NULL, NULL);
+ MMIO_RING_F(RING_REG, 8, F_RO | F_CMD_ACCESS, 0, ~0, D_BDW_PLUS,
+ NULL, NULL);
+ MMIO_F(RING_REG(GEN8_BSD2_RING_BASE), 4, F_RO | F_CMD_ACCESS, 0,
+ ~0LL, D_BDW_PLUS, NULL, NULL);
#undef RING_REG
#define RING_REG(base) (base + 0x244)
- MMIO_RING_D(RING_REG, D_BDW_PLUS);
- MMIO_D(RING_REG(GEN8_BSD2_RING_BASE), D_BDW_PLUS);
+ MMIO_RING_DFH(RING_REG, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(RING_REG(GEN8_BSD2_RING_BASE), D_BDW_PLUS, F_CMD_ACCESS,
+ NULL, NULL);
#undef RING_REG
#define RING_REG(base) (base + 0x370)
@@ -2331,6 +2495,8 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
MMIO_D(GEN7_MISCCPCTL, D_BDW_PLUS);
MMIO_D(0x1c054, D_BDW_PLUS);
+ MMIO_DH(GEN6_PCODE_MAILBOX, D_BDW_PLUS, NULL, mailbox_write);
+
MMIO_D(GEN8_PRIVATE_PAT_LO, D_BDW_PLUS);
MMIO_D(GEN8_PRIVATE_PAT_HI, D_BDW_PLUS);
@@ -2341,14 +2507,14 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
MMIO_F(RING_REG(GEN8_BSD2_RING_BASE), 32, 0, 0, 0, D_BDW_PLUS, NULL, NULL);
#undef RING_REG
- MMIO_RING_GM(RING_HWS_PGA, D_BDW_PLUS, NULL, NULL);
- MMIO_GM(0x1c080, D_BDW_PLUS, NULL, NULL);
+ MMIO_RING_GM_RDR(RING_HWS_PGA, D_BDW_PLUS, NULL, NULL);
+ MMIO_GM_RDR(RING_HWS_PGA(GEN8_BSD2_RING_BASE), D_BDW_PLUS, NULL, NULL);
MMIO_DFH(HDC_CHICKEN0, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
- MMIO_D(CHICKEN_PIPESL_1(PIPE_A), D_BDW);
- MMIO_D(CHICKEN_PIPESL_1(PIPE_B), D_BDW);
- MMIO_D(CHICKEN_PIPESL_1(PIPE_C), D_BDW);
+ MMIO_D(CHICKEN_PIPESL_1(PIPE_A), D_BDW_PLUS);
+ MMIO_D(CHICKEN_PIPESL_1(PIPE_B), D_BDW_PLUS);
+ MMIO_D(CHICKEN_PIPESL_1(PIPE_C), D_BDW_PLUS);
MMIO_D(WM_MISC, D_BDW);
MMIO_D(BDW_EDP_PSR_BASE, D_BDW);
@@ -2362,27 +2528,31 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
MMIO_D(GEN8_EU_DISABLE1, D_BDW_PLUS);
MMIO_D(GEN8_EU_DISABLE2, D_BDW_PLUS);
- MMIO_D(0xfdc, D_BDW);
- MMIO_DFH(GEN8_ROW_CHICKEN, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
- MMIO_D(GEN7_ROW_CHICKEN2, D_BDW_PLUS);
- MMIO_D(GEN8_UCGCTL6, D_BDW_PLUS);
+ MMIO_D(0xfdc, D_BDW_PLUS);
+ MMIO_DFH(GEN8_ROW_CHICKEN, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS,
+ NULL, NULL);
+ MMIO_DFH(GEN7_ROW_CHICKEN2, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS,
+ NULL, NULL);
+ MMIO_DFH(GEN8_UCGCTL6, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
- MMIO_D(0xb1f0, D_BDW);
- MMIO_D(0xb1c0, D_BDW);
+ MMIO_DFH(0xb1f0, D_BDW, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0xb1c0, D_BDW, F_CMD_ACCESS, NULL, NULL);
MMIO_DFH(GEN8_L3SQCREG4, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
- MMIO_D(0xb100, D_BDW);
- MMIO_D(0xb10c, D_BDW);
+ MMIO_DFH(0xb100, D_BDW, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0xb10c, D_BDW, F_CMD_ACCESS, NULL, NULL);
MMIO_D(0xb110, D_BDW);
- MMIO_DFH(0x24d0, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
- MMIO_DFH(0x24d4, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
- MMIO_DFH(0x24d8, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
- MMIO_DFH(0x24dc, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+ MMIO_F(0x24d0, 48, F_CMD_ACCESS, 0, 0, D_BDW_PLUS,
+ NULL, force_nonpriv_write);
- MMIO_D(0x83a4, D_BDW);
+ MMIO_D(0x22040, D_BDW_PLUS);
+ MMIO_D(0x44484, D_BDW_PLUS);
+ MMIO_D(0x4448c, D_BDW_PLUS);
+
+ MMIO_DFH(0x83a4, D_BDW, F_CMD_ACCESS, NULL, NULL);
MMIO_D(GEN8_L3_LRA_1_GPGPU, D_BDW_PLUS);
- MMIO_D(0x8430, D_BDW);
+ MMIO_DFH(0x8430, D_BDW, F_CMD_ACCESS, NULL, NULL);
MMIO_D(0x110000, D_BDW_PLUS);
@@ -2394,10 +2564,19 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
MMIO_DFH(0xe194, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
MMIO_DFH(0xe188, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
MMIO_DFH(HALF_SLICE_CHICKEN2, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
- MMIO_DFH(0x2580, D_BDW_PLUS, F_MODE_MASK, NULL, NULL);
+ MMIO_DFH(0x2580, D_BDW_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
- MMIO_D(0x2248, D_BDW);
+ MMIO_DFH(0x2248, D_BDW, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0xe220, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0xe230, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0xe240, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0xe260, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0xe270, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0xe280, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0xe2a0, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0xe2b0, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0xe2c0, D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL);
return 0;
}
@@ -2420,7 +2599,6 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
MMIO_D(HSW_PWR_WELL_BIOS, D_SKL);
MMIO_DH(HSW_PWR_WELL_DRIVER, D_SKL, NULL, skl_power_well_ctl_write);
- MMIO_DH(GEN6_PCODE_MAILBOX, D_SKL, NULL, mailbox_write);
MMIO_D(0xa210, D_SKL_PLUS);
MMIO_D(GEN9_MEDIA_PG_IDLE_HYSTERESIS, D_SKL_PLUS);
MMIO_D(GEN9_RENDER_PG_IDLE_HYSTERESIS, D_SKL_PLUS);
@@ -2578,16 +2756,16 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
MMIO_F(0xb020, 0x80, F_CMD_ACCESS, 0, 0, D_SKL, NULL, NULL);
MMIO_D(0xd08, D_SKL);
- MMIO_D(0x20e0, D_SKL);
- MMIO_D(0x20ec, D_SKL);
+ MMIO_DFH(0x20e0, D_SKL, F_MODE_MASK, NULL, NULL);
+ MMIO_DFH(0x20ec, D_SKL, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
/* TRTT */
- MMIO_D(0x4de0, D_SKL);
- MMIO_D(0x4de4, D_SKL);
- MMIO_D(0x4de8, D_SKL);
- MMIO_D(0x4dec, D_SKL);
- MMIO_D(0x4df0, D_SKL);
- MMIO_DH(0x4df4, D_SKL, NULL, gen9_trtte_write);
+ MMIO_DFH(0x4de0, D_SKL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x4de4, D_SKL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x4de8, D_SKL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x4dec, D_SKL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x4df0, D_SKL, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(0x4df4, D_SKL, F_CMD_ACCESS, NULL, gen9_trtte_write);
MMIO_DH(0x4dfc, D_SKL, NULL, gen9_trtt_chicken_write);
MMIO_D(0x45008, D_SKL);
@@ -2611,7 +2789,7 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
MMIO_D(0x65f08, D_SKL);
MMIO_D(0x320f0, D_SKL);
- MMIO_D(_REG_VCS2_EXCC, D_SKL);
+ MMIO_DFH(_REG_VCS2_EXCC, D_SKL, F_CMD_ACCESS, NULL, NULL);
MMIO_D(0x70034, D_SKL);
MMIO_D(0x71034, D_SKL);
MMIO_D(0x72034, D_SKL);
@@ -2624,6 +2802,9 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
MMIO_D(_PLANE_KEYMSK_1(PIPE_C), D_SKL);
MMIO_D(0x44500, D_SKL);
+ MMIO_DFH(GEN9_CSFE_CHICKEN1_RCS, D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(GEN8_HDC_CHICKEN1, D_SKL, F_MODE_MASK | F_CMD_ACCESS,
+ NULL, NULL);
return 0;
}
@@ -2813,3 +2994,20 @@ int intel_vgpu_default_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
write_vreg(vgpu, offset, p_data, bytes);
return 0;
}
+
+/**
+ * intel_gvt_in_force_nonpriv_whitelist - if a mmio is in whitelist to be
+ * force-nopriv register
+ *
+ * @gvt: a GVT device
+ * @offset: register offset
+ *
+ * Returns:
+ * True if the register is in force-nonpriv whitelist;
+ * False if outside;
+ */
+bool intel_gvt_in_force_nonpriv_whitelist(struct intel_gvt *gvt,
+ unsigned int offset)
+{
+ return in_whitelist(offset);
+}
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 0f7f5d9..d641214 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -96,10 +96,10 @@ static int gvt_dma_map_iova(struct intel_vgpu *vgpu, kvm_pfn_t pfn,
struct device *dev = &vgpu->gvt->dev_priv->drm.pdev->dev;
dma_addr_t daddr;
- page = pfn_to_page(pfn);
- if (is_error_page(page))
+ if (unlikely(!pfn_valid(pfn)))
return -EFAULT;
+ page = pfn_to_page(pfn);
daddr = dma_map_page(dev, page, 0, PAGE_SIZE,
PCI_DMA_BIDIRECTIONAL);
if (dma_mapping_error(dev, daddr))
@@ -295,10 +295,10 @@ static ssize_t description_show(struct kobject *kobj, struct device *dev,
return 0;
return sprintf(buf, "low_gm_size: %dMB\nhigh_gm_size: %dMB\n"
- "fence: %d\n",
- BYTES_TO_MB(type->low_gm_size),
- BYTES_TO_MB(type->high_gm_size),
- type->fence);
+ "fence: %d\nresolution: %s\n",
+ BYTES_TO_MB(type->low_gm_size),
+ BYTES_TO_MB(type->high_gm_size),
+ type->fence, vgpu_edid_str(type->resolution));
}
static MDEV_TYPE_ATTR_RO(available_instances);
@@ -426,7 +426,7 @@ static void kvmgt_protect_table_del(struct kvmgt_guest_info *info,
static int intel_vgpu_create(struct kobject *kobj, struct mdev_device *mdev)
{
- struct intel_vgpu *vgpu;
+ struct intel_vgpu *vgpu = NULL;
struct intel_vgpu_type *type;
struct device *pdev;
void *gvt;
@@ -437,7 +437,7 @@ static int intel_vgpu_create(struct kobject *kobj, struct mdev_device *mdev)
type = intel_gvt_find_vgpu_type(gvt, kobject_name(kobj));
if (!type) {
- gvt_err("failed to find type %s to create\n",
+ gvt_vgpu_err("failed to find type %s to create\n",
kobject_name(kobj));
ret = -EINVAL;
goto out;
@@ -446,7 +446,7 @@ static int intel_vgpu_create(struct kobject *kobj, struct mdev_device *mdev)
vgpu = intel_gvt_ops->vgpu_create(gvt, type);
if (IS_ERR_OR_NULL(vgpu)) {
ret = vgpu == NULL ? -EFAULT : PTR_ERR(vgpu);
- gvt_err("failed to create intel vgpu: %d\n", ret);
+ gvt_vgpu_err("failed to create intel vgpu: %d\n", ret);
goto out;
}
@@ -526,7 +526,8 @@ static int intel_vgpu_open(struct mdev_device *mdev)
ret = vfio_register_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY, &events,
&vgpu->vdev.iommu_notifier);
if (ret != 0) {
- gvt_err("vfio_register_notifier for iommu failed: %d\n", ret);
+ gvt_vgpu_err("vfio_register_notifier for iommu failed: %d\n",
+ ret);
goto out;
}
@@ -534,7 +535,8 @@ static int intel_vgpu_open(struct mdev_device *mdev)
ret = vfio_register_notifier(mdev_dev(mdev), VFIO_GROUP_NOTIFY, &events,
&vgpu->vdev.group_notifier);
if (ret != 0) {
- gvt_err("vfio_register_notifier for group failed: %d\n", ret);
+ gvt_vgpu_err("vfio_register_notifier for group failed: %d\n",
+ ret);
goto undo_iommu;
}
@@ -635,7 +637,7 @@ static ssize_t intel_vgpu_rw(struct mdev_device *mdev, char *buf,
if (index >= VFIO_PCI_NUM_REGIONS) {
- gvt_err("invalid index: %u\n", index);
+ gvt_vgpu_err("invalid index: %u\n", index);
return -EINVAL;
}
@@ -669,7 +671,7 @@ static ssize_t intel_vgpu_rw(struct mdev_device *mdev, char *buf,
case VFIO_PCI_VGA_REGION_INDEX:
case VFIO_PCI_ROM_REGION_INDEX:
default:
- gvt_err("unsupported region: %u\n", index);
+ gvt_vgpu_err("unsupported region: %u\n", index);
}
return ret == 0 ? count : ret;
@@ -861,7 +863,7 @@ static int intel_vgpu_set_msi_trigger(struct intel_vgpu *vgpu,
trigger = eventfd_ctx_fdget(fd);
if (IS_ERR(trigger)) {
- gvt_err("eventfd_ctx_fdget failed\n");
+ gvt_vgpu_err("eventfd_ctx_fdget failed\n");
return PTR_ERR(trigger);
}
vgpu->vdev.msi_trigger = trigger;
@@ -1120,7 +1122,7 @@ static long intel_vgpu_ioctl(struct mdev_device *mdev, unsigned int cmd,
ret = vfio_set_irqs_validate_and_prepare(&hdr, max,
VFIO_PCI_NUM_IRQS, &data_size);
if (ret) {
- gvt_err("intel:vfio_set_irqs_validate_and_prepare failed\n");
+ gvt_vgpu_err("intel:vfio_set_irqs_validate_and_prepare failed\n");
return -EINVAL;
}
if (data_size) {
@@ -1310,7 +1312,7 @@ static int kvmgt_guest_init(struct mdev_device *mdev)
kvm = vgpu->vdev.kvm;
if (!kvm || kvm->mm != current->mm) {
- gvt_err("KVM is required to use Intel vGPU\n");
+ gvt_vgpu_err("KVM is required to use Intel vGPU\n");
return -ESRCH;
}
@@ -1324,6 +1326,7 @@ static int kvmgt_guest_init(struct mdev_device *mdev)
vgpu->handle = (unsigned long)info;
info->vgpu = vgpu;
info->kvm = kvm;
+ kvm_get_kvm(info->kvm);
kvmgt_protect_table_init(info);
gvt_cache_init(vgpu);
@@ -1337,12 +1340,15 @@ static int kvmgt_guest_init(struct mdev_device *mdev)
static bool kvmgt_guest_exit(struct kvmgt_guest_info *info)
{
+ struct intel_vgpu *vgpu = info->vgpu;
+
if (!info) {
- gvt_err("kvmgt_guest_info invalid\n");
+ gvt_vgpu_err("kvmgt_guest_info invalid\n");
return false;
}
kvm_page_track_unregister_notifier(info->kvm, &info->track_node);
+ kvm_put_kvm(info->kvm);
kvmgt_protect_table_destroy(info);
gvt_cache_destroy(info->vgpu);
vfree(info);
@@ -1383,12 +1389,14 @@ static unsigned long kvmgt_gfn_to_pfn(unsigned long handle, unsigned long gfn)
unsigned long iova, pfn;
struct kvmgt_guest_info *info;
struct device *dev;
+ struct intel_vgpu *vgpu;
int rc;
if (!handle_valid(handle))
return INTEL_GVT_INVALID_ADDR;
info = (struct kvmgt_guest_info *)handle;
+ vgpu = info->vgpu;
iova = gvt_cache_find(info->vgpu, gfn);
if (iova != INTEL_GVT_INVALID_ADDR)
return iova;
@@ -1397,13 +1405,14 @@ static unsigned long kvmgt_gfn_to_pfn(unsigned long handle, unsigned long gfn)
dev = mdev_dev(info->vgpu->vdev.mdev);
rc = vfio_pin_pages(dev, &gfn, 1, IOMMU_READ | IOMMU_WRITE, &pfn);
if (rc != 1) {
- gvt_err("vfio_pin_pages failed for gfn 0x%lx: %d\n", gfn, rc);
+ gvt_vgpu_err("vfio_pin_pages failed for gfn 0x%lx: %d\n",
+ gfn, rc);
return INTEL_GVT_INVALID_ADDR;
}
/* transfer to host iova for GFX to use DMA */
rc = gvt_dma_map_iova(info->vgpu, pfn, &iova);
if (rc) {
- gvt_err("gvt_dma_map_iova failed for gfn: 0x%lx\n", gfn);
+ gvt_vgpu_err("gvt_dma_map_iova failed for gfn: 0x%lx\n", gfn);
vfio_unpin_pages(dev, &gfn, 1);
return INTEL_GVT_INVALID_ADDR;
}
@@ -1417,7 +1426,7 @@ static int kvmgt_rw_gpa(unsigned long handle, unsigned long gpa,
{
struct kvmgt_guest_info *info;
struct kvm *kvm;
- int ret;
+ int idx, ret;
bool kthread = current->mm == NULL;
if (!handle_valid(handle))
@@ -1429,8 +1438,10 @@ static int kvmgt_rw_gpa(unsigned long handle, unsigned long gpa,
if (kthread)
use_mm(kvm->mm);
+ idx = srcu_read_lock(&kvm->srcu);
ret = write ? kvm_write_guest(kvm, gpa, buf, len) :
kvm_read_guest(kvm, gpa, buf, len);
+ srcu_read_unlock(&kvm->srcu, idx);
if (kthread)
unuse_mm(kvm->mm);
diff --git a/drivers/gpu/drm/i915/gvt/mmio.c b/drivers/gpu/drm/i915/gvt/mmio.c
index 4df078b..1ba3bdb 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.c
+++ b/drivers/gpu/drm/i915/gvt/mmio.c
@@ -57,6 +57,58 @@ int intel_vgpu_gpa_to_mmio_offset(struct intel_vgpu *vgpu, u64 gpa)
(reg >= gvt->device_info.gtt_start_offset \
&& reg < gvt->device_info.gtt_start_offset + gvt_ggtt_sz(gvt))
+static void failsafe_emulate_mmio_rw(struct intel_vgpu *vgpu, uint64_t pa,
+ void *p_data, unsigned int bytes, bool read)
+{
+ struct intel_gvt *gvt = NULL;
+ void *pt = NULL;
+ unsigned int offset = 0;
+
+ if (!vgpu || !p_data)
+ return;
+
+ gvt = vgpu->gvt;
+ mutex_lock(&gvt->lock);
+ offset = intel_vgpu_gpa_to_mmio_offset(vgpu, pa);
+ if (reg_is_mmio(gvt, offset)) {
+ if (read)
+ intel_vgpu_default_mmio_read(vgpu, offset, p_data,
+ bytes);
+ else
+ intel_vgpu_default_mmio_write(vgpu, offset, p_data,
+ bytes);
+ } else if (reg_is_gtt(gvt, offset) &&
+ vgpu->gtt.ggtt_mm->virtual_page_table) {
+ offset -= gvt->device_info.gtt_start_offset;
+ pt = vgpu->gtt.ggtt_mm->virtual_page_table + offset;
+ if (read)
+ memcpy(p_data, pt, bytes);
+ else
+ memcpy(pt, p_data, bytes);
+
+ } else if (atomic_read(&vgpu->gtt.n_write_protected_guest_page)) {
+ struct intel_vgpu_guest_page *gp;
+
+ /* Since we enter the failsafe mode early during guest boot,
+ * guest may not have chance to set up its ppgtt table, so
+ * there should not be any wp pages for guest. Keep the wp
+ * related code here in case we need to handle it in furture.
+ */
+ gp = intel_vgpu_find_guest_page(vgpu, pa >> PAGE_SHIFT);
+ if (gp) {
+ /* remove write protection to prevent furture traps */
+ intel_vgpu_clean_guest_page(vgpu, gp);
+ if (read)
+ intel_gvt_hypervisor_read_gpa(vgpu, pa,
+ p_data, bytes);
+ else
+ intel_gvt_hypervisor_write_gpa(vgpu, pa,
+ p_data, bytes);
+ }
+ }
+ mutex_unlock(&gvt->lock);
+}
+
/**
* intel_vgpu_emulate_mmio_read - emulate MMIO read
* @vgpu: a vGPU
@@ -75,6 +127,11 @@ int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, uint64_t pa,
unsigned int offset = 0;
int ret = -EINVAL;
+
+ if (vgpu->failsafe) {
+ failsafe_emulate_mmio_rw(vgpu, pa, p_data, bytes, true);
+ return 0;
+ }
mutex_lock(&gvt->lock);
if (atomic_read(&vgpu->gtt.n_write_protected_guest_page)) {
@@ -85,10 +142,10 @@ int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, uint64_t pa,
ret = intel_gvt_hypervisor_read_gpa(vgpu, pa,
p_data, bytes);
if (ret) {
- gvt_err("vgpu%d: guest page read error %d, "
+ gvt_vgpu_err("guest page read error %d, "
"gfn 0x%lx, pa 0x%llx, var 0x%x, len %d\n",
- vgpu->id, ret,
- gp->gfn, pa, *(u32 *)p_data, bytes);
+ ret, gp->gfn, pa, *(u32 *)p_data,
+ bytes);
}
mutex_unlock(&gvt->lock);
return ret;
@@ -143,14 +200,13 @@ int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, uint64_t pa,
ret = intel_vgpu_default_mmio_read(vgpu, offset, p_data, bytes);
if (!vgpu->mmio.disable_warn_untrack) {
- gvt_err("vgpu%d: read untracked MMIO %x(%dB) val %x\n",
- vgpu->id, offset, bytes, *(u32 *)p_data);
+ gvt_vgpu_err("read untracked MMIO %x(%dB) val %x\n",
+ offset, bytes, *(u32 *)p_data);
if (offset == 0x206c) {
- gvt_err("------------------------------------------\n");
- gvt_err("vgpu%d: likely triggers a gfx reset\n",
- vgpu->id);
- gvt_err("------------------------------------------\n");
+ gvt_vgpu_err("------------------------------------------\n");
+ gvt_vgpu_err("likely triggers a gfx reset\n");
+ gvt_vgpu_err("------------------------------------------\n");
vgpu->mmio.disable_warn_untrack = true;
}
}
@@ -163,8 +219,8 @@ int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, uint64_t pa,
mutex_unlock(&gvt->lock);
return 0;
err:
- gvt_err("vgpu%d: fail to emulate MMIO read %08x len %d\n",
- vgpu->id, offset, bytes);
+ gvt_vgpu_err("fail to emulate MMIO read %08x len %d\n",
+ offset, bytes);
mutex_unlock(&gvt->lock);
return ret;
}
@@ -188,6 +244,11 @@ int intel_vgpu_emulate_mmio_write(struct intel_vgpu *vgpu, uint64_t pa,
u32 old_vreg = 0, old_sreg = 0;
int ret = -EINVAL;
+ if (vgpu->failsafe) {
+ failsafe_emulate_mmio_rw(vgpu, pa, p_data, bytes, false);
+ return 0;
+ }
+
mutex_lock(&gvt->lock);
if (atomic_read(&vgpu->gtt.n_write_protected_guest_page)) {
@@ -197,10 +258,11 @@ int intel_vgpu_emulate_mmio_write(struct intel_vgpu *vgpu, uint64_t pa,
if (gp) {
ret = gp->handler(gp, pa, p_data, bytes);
if (ret) {
- gvt_err("vgpu%d: guest page write error %d, "
- "gfn 0x%lx, pa 0x%llx, var 0x%x, len %d\n",
- vgpu->id, ret,
- gp->gfn, pa, *(u32 *)p_data, bytes);
+ gvt_err("guest page write error %d, "
+ "gfn 0x%lx, pa 0x%llx, "
+ "var 0x%x, len %d\n",
+ ret, gp->gfn, pa,
+ *(u32 *)p_data, bytes);
}
mutex_unlock(&gvt->lock);
return ret;
@@ -236,7 +298,7 @@ int intel_vgpu_emulate_mmio_write(struct intel_vgpu *vgpu, uint64_t pa,
mmio = intel_gvt_find_mmio_info(gvt, rounddown(offset, 4));
if (!mmio && !vgpu->mmio.disable_warn_untrack)
- gvt_err("vgpu%d: write untracked MMIO %x len %d val %x\n",
+ gvt_dbg_mmio("vgpu%d: write untracked MMIO %x len %d val %x\n",
vgpu->id, offset, bytes, *(u32 *)p_data);
if (!intel_gvt_mmio_is_unalign(gvt, offset)) {
@@ -267,8 +329,8 @@ int intel_vgpu_emulate_mmio_write(struct intel_vgpu *vgpu, uint64_t pa,
/* all register bits are RO. */
if (ro_mask == ~(u64)0) {
- gvt_err("vgpu%d: try to write RO reg %x\n",
- vgpu->id, offset);
+ gvt_vgpu_err("try to write RO reg %x\n",
+ offset);
ret = 0;
goto out;
}
@@ -298,8 +360,8 @@ int intel_vgpu_emulate_mmio_write(struct intel_vgpu *vgpu, uint64_t pa,
mutex_unlock(&gvt->lock);
return 0;
err:
- gvt_err("vgpu%d: fail to emulate MMIO write %08x len %d\n",
- vgpu->id, offset, bytes);
+ gvt_vgpu_err("fail to emulate MMIO write %08x len %d\n", offset,
+ bytes);
mutex_unlock(&gvt->lock);
return ret;
}
@@ -322,6 +384,8 @@ void intel_vgpu_reset_mmio(struct intel_vgpu *vgpu)
/* set the bit 0:2(Core C-State ) to C0 */
vgpu_vreg(vgpu, GEN6_GT_CORE_STATUS) = 0;
+
+ vgpu->mmio.disable_warn_untrack = false;
}
/**
diff --git a/drivers/gpu/drm/i915/gvt/mmio.h b/drivers/gpu/drm/i915/gvt/mmio.h
index 3bc620f..a3a0270 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.h
+++ b/drivers/gpu/drm/i915/gvt/mmio.h
@@ -107,4 +107,7 @@ int intel_vgpu_default_mmio_read(struct intel_vgpu *vgpu, unsigned int offset,
void *p_data, unsigned int bytes);
int intel_vgpu_default_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
void *p_data, unsigned int bytes);
+
+bool intel_gvt_in_force_nonpriv_whitelist(struct intel_gvt *gvt,
+ unsigned int offset);
#endif
diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c
index d9fb41a..3117991 100644
--- a/drivers/gpu/drm/i915/gvt/opregion.c
+++ b/drivers/gpu/drm/i915/gvt/opregion.c
@@ -27,7 +27,6 @@
static int init_vgpu_opregion(struct intel_vgpu *vgpu, u32 gpa)
{
- void __iomem *host_va = vgpu->gvt->opregion.opregion_va;
u8 *buf;
int i;
@@ -43,8 +42,8 @@ static int init_vgpu_opregion(struct intel_vgpu *vgpu, u32 gpa)
if (!vgpu_opregion(vgpu)->va)
return -ENOMEM;
- memcpy_fromio(vgpu_opregion(vgpu)->va, host_va,
- INTEL_GVT_OPREGION_SIZE);
+ memcpy(vgpu_opregion(vgpu)->va, vgpu->gvt->opregion.opregion_va,
+ INTEL_GVT_OPREGION_SIZE);
for (i = 0; i < INTEL_GVT_OPREGION_PAGES; i++)
vgpu_opregion(vgpu)->gfn[i] = (gpa >> PAGE_SHIFT) + i;
@@ -68,14 +67,15 @@ static int map_vgpu_opregion(struct intel_vgpu *vgpu, bool map)
mfn = intel_gvt_hypervisor_virt_to_mfn(vgpu_opregion(vgpu)->va
+ i * PAGE_SIZE);
if (mfn == INTEL_GVT_INVALID_ADDR) {
- gvt_err("fail to get MFN from VA\n");
+ gvt_vgpu_err("fail to get MFN from VA\n");
return -EINVAL;
}
ret = intel_gvt_hypervisor_map_gfn_to_mfn(vgpu,
vgpu_opregion(vgpu)->gfn[i],
mfn, 1, map);
if (ret) {
- gvt_err("fail to map GFN to MFN, errno: %d\n", ret);
+ gvt_vgpu_err("fail to map GFN to MFN, errno: %d\n",
+ ret);
return ret;
}
}
@@ -288,7 +288,7 @@ int intel_vgpu_emulate_opregion_request(struct intel_vgpu *vgpu, u32 swsci)
parm = vgpu_opregion(vgpu)->va + INTEL_GVT_OPREGION_PARM;
if (!(swsci & SWSCI_SCI_SELECT)) {
- gvt_err("vgpu%d: requesting SMI service\n", vgpu->id);
+ gvt_vgpu_err("requesting SMI service\n");
return 0;
}
/* ignore non 0->1 trasitions */
@@ -301,9 +301,8 @@ int intel_vgpu_emulate_opregion_request(struct intel_vgpu *vgpu, u32 swsci)
func = GVT_OPREGION_FUNC(*scic);
subfunc = GVT_OPREGION_SUBFUNC(*scic);
if (!querying_capabilities(*scic)) {
- gvt_err("vgpu%d: requesting runtime service: func \"%s\","
+ gvt_vgpu_err("requesting runtime service: func \"%s\","
" subfunc \"%s\"\n",
- vgpu->id,
opregion_func_name(func),
opregion_subfunc_name(subfunc));
/*
diff --git a/drivers/gpu/drm/i915/gvt/render.c b/drivers/gpu/drm/i915/gvt/render.c
index 2b3a642..0beb835 100644
--- a/drivers/gpu/drm/i915/gvt/render.c
+++ b/drivers/gpu/drm/i915/gvt/render.c
@@ -53,6 +53,14 @@ static struct render_mmio gen8_render_mmio_list[] = {
{RCS, _MMIO(0x24d4), 0, false},
{RCS, _MMIO(0x24d8), 0, false},
{RCS, _MMIO(0x24dc), 0, false},
+ {RCS, _MMIO(0x24e0), 0, false},
+ {RCS, _MMIO(0x24e4), 0, false},
+ {RCS, _MMIO(0x24e8), 0, false},
+ {RCS, _MMIO(0x24ec), 0, false},
+ {RCS, _MMIO(0x24f0), 0, false},
+ {RCS, _MMIO(0x24f4), 0, false},
+ {RCS, _MMIO(0x24f8), 0, false},
+ {RCS, _MMIO(0x24fc), 0, false},
{RCS, _MMIO(0x7004), 0xffff, true},
{RCS, _MMIO(0x7008), 0xffff, true},
{RCS, _MMIO(0x7000), 0xffff, true},
@@ -76,6 +84,14 @@ static struct render_mmio gen9_render_mmio_list[] = {
{RCS, _MMIO(0x24d4), 0, false},
{RCS, _MMIO(0x24d8), 0, false},
{RCS, _MMIO(0x24dc), 0, false},
+ {RCS, _MMIO(0x24e0), 0, false},
+ {RCS, _MMIO(0x24e4), 0, false},
+ {RCS, _MMIO(0x24e8), 0, false},
+ {RCS, _MMIO(0x24ec), 0, false},
+ {RCS, _MMIO(0x24f0), 0, false},
+ {RCS, _MMIO(0x24f4), 0, false},
+ {RCS, _MMIO(0x24f8), 0, false},
+ {RCS, _MMIO(0x24fc), 0, false},
{RCS, _MMIO(0x7004), 0xffff, true},
{RCS, _MMIO(0x7008), 0xffff, true},
{RCS, _MMIO(0x7000), 0xffff, true},
@@ -151,7 +167,7 @@ static void handle_tlb_pending_event(struct intel_vgpu *vgpu, int ring_id)
I915_WRITE_FW(reg, 0x1);
if (wait_for_atomic((I915_READ_FW(reg) == 0), 50))
- gvt_err("timeout in invalidate ring (%d) tlb\n", ring_id);
+ gvt_vgpu_err("timeout in invalidate ring (%d) tlb\n", ring_id);
else
vgpu_vreg(vgpu, regs[ring_id]) = 0;
@@ -191,7 +207,7 @@ static void load_mocs(struct intel_vgpu *vgpu, int ring_id)
l3_offset.reg = 0xb020;
for (i = 0; i < 32; i++) {
gen9_render_mocs_L3[i] = I915_READ(l3_offset);
- I915_WRITE(l3_offset, vgpu_vreg(vgpu, offset));
+ I915_WRITE(l3_offset, vgpu_vreg(vgpu, l3_offset));
POSTING_READ(l3_offset);
l3_offset.reg += 4;
}
diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.c b/drivers/gpu/drm/i915/gvt/sched_policy.c
index 06c9584..34b9acd 100644
--- a/drivers/gpu/drm/i915/gvt/sched_policy.c
+++ b/drivers/gpu/drm/i915/gvt/sched_policy.c
@@ -101,7 +101,7 @@ struct tbs_sched_data {
struct list_head runq_head;
};
-#define GVT_DEFAULT_TIME_SLICE (1 * HZ / 1000)
+#define GVT_DEFAULT_TIME_SLICE (msecs_to_jiffies(1))
static void tbs_sched_func(struct work_struct *work)
{
@@ -223,7 +223,7 @@ static void tbs_sched_start_schedule(struct intel_vgpu *vgpu)
return;
list_add_tail(&vgpu_data->list, &sched_data->runq_head);
- schedule_delayed_work(&sched_data->work, sched_data->period);
+ schedule_delayed_work(&sched_data->work, 0);
}
static void tbs_sched_stop_schedule(struct intel_vgpu *vgpu)
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index d6b6d0e..a447824 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -84,7 +84,7 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
(u32)((workload->ctx_desc.lrca + i) <<
GTT_PAGE_SHIFT));
if (context_gpa == INTEL_GVT_INVALID_ADDR) {
- gvt_err("Invalid guest context descriptor\n");
+ gvt_vgpu_err("Invalid guest context descriptor\n");
return -EINVAL;
}
@@ -127,18 +127,24 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
return 0;
}
+static inline bool is_gvt_request(struct drm_i915_gem_request *req)
+{
+ return i915_gem_context_force_single_submission(req->ctx);
+}
+
static int shadow_context_status_change(struct notifier_block *nb,
unsigned long action, void *data)
{
- struct intel_vgpu *vgpu = container_of(nb,
- struct intel_vgpu, shadow_ctx_notifier_block);
- struct drm_i915_gem_request *req =
- (struct drm_i915_gem_request *)data;
- struct intel_gvt_workload_scheduler *scheduler =
- &vgpu->gvt->scheduler;
+ struct drm_i915_gem_request *req = (struct drm_i915_gem_request *)data;
+ struct intel_gvt *gvt = container_of(nb, struct intel_gvt,
+ shadow_ctx_notifier_block[req->engine->id]);
+ struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
struct intel_vgpu_workload *workload =
scheduler->current_workload[req->engine->id];
+ if (!is_gvt_request(req) || unlikely(!workload))
+ return NOTIFY_OK;
+
switch (action) {
case INTEL_CONTEXT_SCHEDULE_IN:
intel_gvt_load_render_mmio(workload->vgpu,
@@ -148,6 +154,15 @@ static int shadow_context_status_change(struct notifier_block *nb,
case INTEL_CONTEXT_SCHEDULE_OUT:
intel_gvt_restore_render_mmio(workload->vgpu,
workload->ring_id);
+ /* If the status is -EINPROGRESS means this workload
+ * doesn't meet any issue during dispatching so when
+ * get the SCHEDULE_OUT set the status to be zero for
+ * good. If the status is NOT -EINPROGRESS means there
+ * is something wrong happened during dispatching and
+ * the status should not be set to zero
+ */
+ if (workload->status == -EINPROGRESS)
+ workload->status = 0;
atomic_set(&workload->shadow_ctx_active, 0);
break;
default:
@@ -163,7 +178,9 @@ static int dispatch_workload(struct intel_vgpu_workload *workload)
int ring_id = workload->ring_id;
struct i915_gem_context *shadow_ctx = workload->vgpu->shadow_ctx;
struct drm_i915_private *dev_priv = workload->vgpu->gvt->dev_priv;
+ struct intel_engine_cs *engine = dev_priv->engine[ring_id];
struct drm_i915_gem_request *rq;
+ struct intel_vgpu *vgpu = workload->vgpu;
int ret;
gvt_dbg_sched("ring id %d prepare to dispatch workload %p\n",
@@ -175,9 +192,24 @@ static int dispatch_workload(struct intel_vgpu_workload *workload)
mutex_lock(&dev_priv->drm.struct_mutex);
+ /* pin shadow context by gvt even the shadow context will be pinned
+ * when i915 alloc request. That is because gvt will update the guest
+ * context from shadow context when workload is completed, and at that
+ * moment, i915 may already unpined the shadow context to make the
+ * shadow_ctx pages invalid. So gvt need to pin itself. After update
+ * the guest context, gvt can unpin the shadow_ctx safely.
+ */
+ ret = engine->context_pin(engine, shadow_ctx);
+ if (ret) {
+ gvt_vgpu_err("fail to pin shadow context\n");
+ workload->status = ret;
+ mutex_unlock(&dev_priv->drm.struct_mutex);
+ return ret;
+ }
+
rq = i915_gem_request_alloc(dev_priv->engine[ring_id], shadow_ctx);
if (IS_ERR(rq)) {
- gvt_err("fail to allocate gem request\n");
+ gvt_vgpu_err("fail to allocate gem request\n");
ret = PTR_ERR(rq);
goto out;
}
@@ -190,9 +222,12 @@ static int dispatch_workload(struct intel_vgpu_workload *workload)
if (ret)
goto out;
- ret = intel_gvt_scan_and_shadow_wa_ctx(&workload->wa_ctx);
- if (ret)
- goto out;
+ if ((workload->ring_id == RCS) &&
+ (workload->wa_ctx.indirect_ctx.size != 0)) {
+ ret = intel_gvt_scan_and_shadow_wa_ctx(&workload->wa_ctx);
+ if (ret)
+ goto out;
+ }
ret = populate_shadow_context(workload);
if (ret)
@@ -215,6 +250,9 @@ static int dispatch_workload(struct intel_vgpu_workload *workload)
if (!IS_ERR_OR_NULL(rq))
i915_add_request_no_flush(rq);
+ else
+ engine->context_unpin(engine, shadow_ctx);
+
mutex_unlock(&dev_priv->drm.struct_mutex);
return ret;
}
@@ -310,7 +348,7 @@ static void update_guest_context(struct intel_vgpu_workload *workload)
(u32)((workload->ctx_desc.lrca + i) <<
GTT_PAGE_SHIFT));
if (context_gpa == INTEL_GVT_INVALID_ADDR) {
- gvt_err("invalid guest context descriptor\n");
+ gvt_vgpu_err("invalid guest context descriptor\n");
return;
}
@@ -359,15 +397,31 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
workload = scheduler->current_workload[ring_id];
vgpu = workload->vgpu;
- if (!workload->status && !vgpu->resetting) {
+ /* For the workload w/ request, needs to wait for the context
+ * switch to make sure request is completed.
+ * For the workload w/o request, directly complete the workload.
+ */
+ if (workload->req) {
+ struct drm_i915_private *dev_priv =
+ workload->vgpu->gvt->dev_priv;
+ struct intel_engine_cs *engine =
+ dev_priv->engine[workload->ring_id];
wait_event(workload->shadow_ctx_status_wq,
!atomic_read(&workload->shadow_ctx_active));
- update_guest_context(workload);
+ i915_gem_request_put(fetch_and_zero(&workload->req));
- for_each_set_bit(event, workload->pending_events,
- INTEL_GVT_EVENT_MAX)
- intel_vgpu_trigger_virtual_event(vgpu, event);
+ if (!workload->status && !vgpu->resetting) {
+ update_guest_context(workload);
+
+ for_each_set_bit(event, workload->pending_events,
+ INTEL_GVT_EVENT_MAX)
+ intel_vgpu_trigger_virtual_event(vgpu, event);
+ }
+ mutex_lock(&dev_priv->drm.struct_mutex);
+ /* unpin shadow ctx as the shadow_ctx update is done */
+ engine->context_unpin(engine, workload->vgpu->shadow_ctx);
+ mutex_unlock(&dev_priv->drm.struct_mutex);
}
gvt_dbg_sched("ring id %d complete workload %p status %d\n",
@@ -397,7 +451,7 @@ static int workload_thread(void *priv)
int ring_id = p->ring_id;
struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
struct intel_vgpu_workload *workload = NULL;
- long lret;
+ struct intel_vgpu *vgpu = NULL;
int ret;
bool need_force_wake = IS_SKYLAKE(gvt->dev_priv);
DEFINE_WAIT_FUNC(wait, woken_wake_function);
@@ -440,29 +494,19 @@ static int workload_thread(void *priv)
mutex_unlock(&gvt->lock);
if (ret) {
- gvt_err("fail to dispatch workload, skip\n");
+ vgpu = workload->vgpu;
+ gvt_vgpu_err("fail to dispatch workload, skip\n");
goto complete;
}
gvt_dbg_sched("ring id %d wait workload %p\n",
workload->ring_id, workload);
-
- lret = i915_wait_request(workload->req,
- 0, MAX_SCHEDULE_TIMEOUT);
- if (lret < 0) {
- workload->status = lret;
- gvt_err("fail to wait workload, skip\n");
- } else {
- workload->status = 0;
- }
+ i915_wait_request(workload->req, 0, MAX_SCHEDULE_TIMEOUT);
complete:
gvt_dbg_sched("will complete workload %p, status: %d\n",
workload, workload->status);
- if (workload->req)
- i915_gem_request_put(fetch_and_zero(&workload->req));
-
complete_current_workload(gvt, ring_id);
if (need_force_wake)
@@ -493,15 +537,16 @@ void intel_gvt_wait_vgpu_idle(struct intel_vgpu *vgpu)
void intel_gvt_clean_workload_scheduler(struct intel_gvt *gvt)
{
struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
- int i;
+ struct intel_engine_cs *engine;
+ enum intel_engine_id i;
gvt_dbg_core("clean workload scheduler\n");
- for (i = 0; i < I915_NUM_ENGINES; i++) {
- if (scheduler->thread[i]) {
- kthread_stop(scheduler->thread[i]);
- scheduler->thread[i] = NULL;
- }
+ for_each_engine(engine, gvt->dev_priv, i) {
+ atomic_notifier_chain_unregister(
+ &engine->context_status_notifier,
+ &gvt->shadow_ctx_notifier_block[i]);
+ kthread_stop(scheduler->thread[i]);
}
}
@@ -509,18 +554,15 @@ int intel_gvt_init_workload_scheduler(struct intel_gvt *gvt)
{
struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
struct workload_thread_param *param = NULL;
+ struct intel_engine_cs *engine;
+ enum intel_engine_id i;
int ret;
- int i;
gvt_dbg_core("init workload scheduler\n");
init_waitqueue_head(&scheduler->workload_complete_wq);
- for (i = 0; i < I915_NUM_ENGINES; i++) {
- /* check ring mask at init time */
- if (!HAS_ENGINE(gvt->dev_priv, i))
- continue;
-
+ for_each_engine(engine, gvt->dev_priv, i) {
init_waitqueue_head(&scheduler->waitq[i]);
param = kzalloc(sizeof(*param), GFP_KERNEL);
@@ -539,6 +581,11 @@ int intel_gvt_init_workload_scheduler(struct intel_gvt *gvt)
ret = PTR_ERR(scheduler->thread[i]);
goto err;
}
+
+ gvt->shadow_ctx_notifier_block[i].notifier_call =
+ shadow_context_status_change;
+ atomic_notifier_chain_register(&engine->context_status_notifier,
+ &gvt->shadow_ctx_notifier_block[i]);
}
return 0;
err:
@@ -550,9 +597,6 @@ int intel_gvt_init_workload_scheduler(struct intel_gvt *gvt)
void intel_vgpu_clean_gvt_context(struct intel_vgpu *vgpu)
{
- atomic_notifier_chain_unregister(&vgpu->shadow_ctx->status_notifier,
- &vgpu->shadow_ctx_notifier_block);
-
i915_gem_context_put_unlocked(vgpu->shadow_ctx);
}
@@ -567,10 +611,5 @@ int intel_vgpu_init_gvt_context(struct intel_vgpu *vgpu)
vgpu->shadow_ctx->engine[RCS].initialised = true;
- vgpu->shadow_ctx_notifier_block.notifier_call =
- shadow_context_status_change;
-
- atomic_notifier_chain_register(&vgpu->shadow_ctx->status_notifier,
- &vgpu->shadow_ctx_notifier_block);
return 0;
}
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 95a97aa..41cfa5c 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -64,6 +64,20 @@ void populate_pvinfo_page(struct intel_vgpu *vgpu)
WARN_ON(sizeof(struct vgt_if) != VGT_PVINFO_SIZE);
}
+static struct {
+ unsigned int low_mm;
+ unsigned int high_mm;
+ unsigned int fence;
+ enum intel_vgpu_edid edid;
+ char *name;
+} vgpu_types[] = {
+/* Fixed vGPU type table */
+ { MB_TO_BYTES(64), MB_TO_BYTES(512), 4, GVT_EDID_1024_768, "8" },
+ { MB_TO_BYTES(128), MB_TO_BYTES(512), 4, GVT_EDID_1920_1200, "4" },
+ { MB_TO_BYTES(256), MB_TO_BYTES(1024), 4, GVT_EDID_1920_1200, "2" },
+ { MB_TO_BYTES(512), MB_TO_BYTES(2048), 4, GVT_EDID_1920_1200, "1" },
+};
+
/**
* intel_gvt_init_vgpu_types - initialize vGPU type list
* @gvt : GVT device
@@ -78,9 +92,8 @@ int intel_gvt_init_vgpu_types(struct intel_gvt *gvt)
unsigned int min_low;
/* vGPU type name is defined as GVTg_Vx_y which contains
- * physical GPU generation type and 'y' means maximum vGPU
- * instances user can create on one physical GPU for this
- * type.
+ * physical GPU generation type (e.g V4 as BDW server, V5 as
+ * SKL server).
*
* Depend on physical SKU resource, might see vGPU types like
* GVTg_V4_8, GVTg_V4_4, GVTg_V4_2, etc. We can create
@@ -92,7 +105,7 @@ int intel_gvt_init_vgpu_types(struct intel_gvt *gvt)
*/
low_avail = gvt_aperture_sz(gvt) - HOST_LOW_GM_SIZE;
high_avail = gvt_hidden_sz(gvt) - HOST_HIGH_GM_SIZE;
- num_types = 4;
+ num_types = sizeof(vgpu_types) / sizeof(vgpu_types[0]);
gvt->types = kzalloc(num_types * sizeof(struct intel_vgpu_type),
GFP_KERNEL);
@@ -101,28 +114,29 @@ int intel_gvt_init_vgpu_types(struct intel_gvt *gvt)
min_low = MB_TO_BYTES(32);
for (i = 0; i < num_types; ++i) {
- if (low_avail / min_low == 0)
+ if (low_avail / vgpu_types[i].low_mm == 0)
break;
- gvt->types[i].low_gm_size = min_low;
- gvt->types[i].high_gm_size = max((min_low<<3), MB_TO_BYTES(384U));
- gvt->types[i].fence = 4;
- gvt->types[i].max_instance = min(low_avail / min_low,
- high_avail / gvt->types[i].high_gm_size);
- gvt->types[i].avail_instance = gvt->types[i].max_instance;
+
+ gvt->types[i].low_gm_size = vgpu_types[i].low_mm;
+ gvt->types[i].high_gm_size = vgpu_types[i].high_mm;
+ gvt->types[i].fence = vgpu_types[i].fence;
+ gvt->types[i].resolution = vgpu_types[i].edid;
+ gvt->types[i].avail_instance = min(low_avail / vgpu_types[i].low_mm,
+ high_avail / vgpu_types[i].high_mm);
if (IS_GEN8(gvt->dev_priv))
- sprintf(gvt->types[i].name, "GVTg_V4_%u",
- gvt->types[i].max_instance);
+ sprintf(gvt->types[i].name, "GVTg_V4_%s",
+ vgpu_types[i].name);
else if (IS_GEN9(gvt->dev_priv))
- sprintf(gvt->types[i].name, "GVTg_V5_%u",
- gvt->types[i].max_instance);
+ sprintf(gvt->types[i].name, "GVTg_V5_%s",
+ vgpu_types[i].name);
- min_low <<= 1;
- gvt_dbg_core("type[%d]: %s max %u avail %u low %u high %u fence %u\n",
- i, gvt->types[i].name, gvt->types[i].max_instance,
+ gvt_dbg_core("type[%d]: %s avail %u low %u high %u fence %u res %s\n",
+ i, gvt->types[i].name,
gvt->types[i].avail_instance,
gvt->types[i].low_gm_size,
- gvt->types[i].high_gm_size, gvt->types[i].fence);
+ gvt->types[i].high_gm_size, gvt->types[i].fence,
+ vgpu_edid_str(gvt->types[i].resolution));
}
gvt->num_types = i;
@@ -138,7 +152,7 @@ static void intel_gvt_update_vgpu_types(struct intel_gvt *gvt)
{
int i;
unsigned int low_gm_avail, high_gm_avail, fence_avail;
- unsigned int low_gm_min, high_gm_min, fence_min, total_min;
+ unsigned int low_gm_min, high_gm_min, fence_min;
/* Need to depend on maxium hw resource size but keep on
* static config for now.
@@ -154,12 +168,11 @@ static void intel_gvt_update_vgpu_types(struct intel_gvt *gvt)
low_gm_min = low_gm_avail / gvt->types[i].low_gm_size;
high_gm_min = high_gm_avail / gvt->types[i].high_gm_size;
fence_min = fence_avail / gvt->types[i].fence;
- total_min = min(min(low_gm_min, high_gm_min), fence_min);
- gvt->types[i].avail_instance = min(gvt->types[i].max_instance,
- total_min);
+ gvt->types[i].avail_instance = min(min(low_gm_min, high_gm_min),
+ fence_min);
- gvt_dbg_core("update type[%d]: %s max %u avail %u low %u high %u fence %u\n",
- i, gvt->types[i].name, gvt->types[i].max_instance,
+ gvt_dbg_core("update type[%d]: %s avail %u low %u high %u fence %u\n",
+ i, gvt->types[i].name,
gvt->types[i].avail_instance, gvt->types[i].low_gm_size,
gvt->types[i].high_gm_size, gvt->types[i].fence);
}
@@ -248,7 +261,7 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt,
if (ret)
goto out_detach_hypervisor_vgpu;
- ret = intel_vgpu_init_display(vgpu);
+ ret = intel_vgpu_init_display(vgpu, param->resolution);
if (ret)
goto out_clean_gtt;
@@ -312,6 +325,7 @@ struct intel_vgpu *intel_gvt_create_vgpu(struct intel_gvt *gvt,
param.low_gm_sz = type->low_gm_size;
param.high_gm_sz = type->high_gm_size;
param.fence_sz = type->fence;
+ param.resolution = type->resolution;
/* XXX current param based on MB */
param.low_gm_sz = BYTES_TO_MB(param.low_gm_sz);
@@ -387,8 +401,12 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
populate_pvinfo_page(vgpu);
intel_vgpu_reset_display(vgpu);
- if (dmlr)
+ if (dmlr) {
intel_vgpu_reset_cfg_space(vgpu);
+ /* only reset the failsafe mode when dmlr reset */
+ vgpu->failsafe = false;
+ vgpu->pv_notified = false;
+ }
}
vgpu->resetting = false;
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index e703556..1c75402 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -248,6 +248,7 @@ static int i915_getparam(struct drm_device *dev, void *data,
case I915_PARAM_IRQ_ACTIVE:
case I915_PARAM_ALLOW_BATCHBUFFER:
case I915_PARAM_LAST_DISPATCH:
+ case I915_PARAM_HAS_EXEC_CONSTANTS:
/* Reject all old ums/dri params. */
return -ENODEV;
case I915_PARAM_CHIPSET_ID:
@@ -274,9 +275,6 @@ static int i915_getparam(struct drm_device *dev, void *data,
case I915_PARAM_HAS_BSD2:
value = !!dev_priv->engine[VCS2];
break;
- case I915_PARAM_HAS_EXEC_CONSTANTS:
- value = INTEL_GEN(dev_priv) >= 4;
- break;
case I915_PARAM_HAS_LLC:
value = HAS_LLC(dev_priv);
break;
@@ -1788,7 +1786,7 @@ void i915_reset(struct drm_i915_private *dev_priv)
goto error;
}
- i915_gem_reset_finish(dev_priv);
+ i915_gem_reset(dev_priv);
intel_overlay_reset(dev_priv);
/* Ok, now get things going again... */
@@ -1814,6 +1812,7 @@ void i915_reset(struct drm_i915_private *dev_priv)
i915_queue_hangcheck(dev_priv);
wakeup:
+ i915_gem_reset_finish(dev_priv);
enable_irq(dev_priv->drm.irq);
wake_up_bit(&error->flags, I915_RESET_IN_PROGRESS);
return;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 0a4b42d..1e53c31 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -293,6 +293,7 @@ enum plane_id {
PLANE_PRIMARY,
PLANE_SPRITE0,
PLANE_SPRITE1,
+ PLANE_SPRITE2,
PLANE_CURSOR,
I915_MAX_PLANES,
};
@@ -1324,7 +1325,7 @@ struct intel_gen6_power_mgmt {
unsigned boosts;
/* manual wa residency calculations */
- struct intel_rps_ei up_ei, down_ei;
+ struct intel_rps_ei ei;
/*
* Protects RPS/RC6 register access and PCU communication.
@@ -2063,8 +2064,6 @@ struct drm_i915_private {
const struct intel_device_info info;
- int relative_constants_mode;
-
void __iomem *regs;
struct intel_uncore uncore;
@@ -3341,6 +3340,7 @@ static inline u32 i915_reset_count(struct i915_gpu_error *error)
}
int i915_gem_reset_prepare(struct drm_i915_private *dev_priv);
+void i915_gem_reset(struct drm_i915_private *dev_priv);
void i915_gem_reset_finish(struct drm_i915_private *dev_priv);
void i915_gem_set_wedged(struct drm_i915_private *dev_priv);
void i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 6908123..67b1fc5 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1434,6 +1434,12 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
trace_i915_gem_object_pwrite(obj, args->offset, args->size);
+ ret = -ENODEV;
+ if (obj->ops->pwrite)
+ ret = obj->ops->pwrite(obj, args);
+ if (ret != -ENODEV)
+ goto err;
+
ret = i915_gem_object_wait(obj,
I915_WAIT_INTERRUPTIBLE |
I915_WAIT_ALL,
@@ -2119,6 +2125,7 @@ i915_gem_object_truncate(struct drm_i915_gem_object *obj)
*/
shmem_truncate_range(file_inode(obj->base.filp), 0, (loff_t)-1);
obj->mm.madv = __I915_MADV_PURGED;
+ obj->mm.pages = ERR_PTR(-EFAULT);
}
/* Try to discard unwanted pages */
@@ -2218,7 +2225,9 @@ void __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
__i915_gem_object_reset_page_iter(obj);
- obj->ops->put_pages(obj, pages);
+ if (!IS_ERR(pages))
+ obj->ops->put_pages(obj, pages);
+
unlock:
mutex_unlock(&obj->mm.lock);
}
@@ -2437,7 +2446,7 @@ int __i915_gem_object_get_pages(struct drm_i915_gem_object *obj)
if (err)
return err;
- if (unlikely(!obj->mm.pages)) {
+ if (unlikely(IS_ERR_OR_NULL(obj->mm.pages))) {
err = ____i915_gem_object_get_pages(obj);
if (err)
goto unlock;
@@ -2515,7 +2524,7 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
pinned = true;
if (!atomic_inc_not_zero(&obj->mm.pages_pin_count)) {
- if (unlikely(!obj->mm.pages)) {
+ if (unlikely(IS_ERR_OR_NULL(obj->mm.pages))) {
ret = ____i915_gem_object_get_pages(obj);
if (ret)
goto err_unlock;
@@ -2563,6 +2572,75 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
goto out_unlock;
}
+static int
+i915_gem_object_pwrite_gtt(struct drm_i915_gem_object *obj,
+ const struct drm_i915_gem_pwrite *arg)
+{
+ struct address_space *mapping = obj->base.filp->f_mapping;
+ char __user *user_data = u64_to_user_ptr(arg->data_ptr);
+ u64 remain, offset;
+ unsigned int pg;
+
+ /* Before we instantiate/pin the backing store for our use, we
+ * can prepopulate the shmemfs filp efficiently using a write into
+ * the pagecache. We avoid the penalty of instantiating all the
+ * pages, important if the user is just writing to a few and never
+ * uses the object on the GPU, and using a direct write into shmemfs
+ * allows it to avoid the cost of retrieving a page (either swapin
+ * or clearing-before-use) before it is overwritten.
+ */
+ if (READ_ONCE(obj->mm.pages))
+ return -ENODEV;
+
+ /* Before the pages are instantiated the object is treated as being
+ * in the CPU domain. The pages will be clflushed as required before
+ * use, and we can freely write into the pages directly. If userspace
+ * races pwrite with any other operation; corruption will ensue -
+ * that is userspace's prerogative!
+ */
+
+ remain = arg->size;
+ offset = arg->offset;
+ pg = offset_in_page(offset);
+
+ do {
+ unsigned int len, unwritten;
+ struct page *page;
+ void *data, *vaddr;
+ int err;
+
+ len = PAGE_SIZE - pg;
+ if (len > remain)
+ len = remain;
+
+ err = pagecache_write_begin(obj->base.filp, mapping,
+ offset, len, 0,
+ &page, &data);
+ if (err < 0)
+ return err;
+
+ vaddr = kmap(page);
+ unwritten = copy_from_user(vaddr + pg, user_data, len);
+ kunmap(page);
+
+ err = pagecache_write_end(obj->base.filp, mapping,
+ offset, len, len - unwritten,
+ page, data);
+ if (err < 0)
+ return err;
+
+ if (unwritten)
+ return -EFAULT;
+
+ remain -= len;
+ user_data += len;
+ offset += len;
+ pg = 0;
+ } while (remain);
+
+ return 0;
+}
+
static bool ban_context(const struct i915_gem_context *ctx)
{
return (i915_gem_context_is_bannable(ctx) &&
@@ -2641,7 +2719,16 @@ int i915_gem_reset_prepare(struct drm_i915_private *dev_priv)
for_each_engine(engine, dev_priv, id) {
struct drm_i915_gem_request *request;
+ /* Prevent request submission to the hardware until we have
+ * completed the reset in i915_gem_reset_finish(). If a request
+ * is completed by one engine, it may then queue a request
+ * to a second via its engine->irq_tasklet *just* as we are
+ * calling engine->init_hw() and also writing the ELSP.
+ * Turning off the engine->irq_tasklet until the reset is over
+ * prevents the race.
+ */
tasklet_kill(&engine->irq_tasklet);
+ tasklet_disable(&engine->irq_tasklet);
if (engine_stalled(engine)) {
request = i915_gem_find_active_request(engine);
@@ -2756,7 +2843,7 @@ static void i915_gem_reset_engine(struct intel_engine_cs *engine)
engine->reset_hw(engine, request);
}
-void i915_gem_reset_finish(struct drm_i915_private *dev_priv)
+void i915_gem_reset(struct drm_i915_private *dev_priv)
{
struct intel_engine_cs *engine;
enum intel_engine_id id;
@@ -2778,6 +2865,17 @@ void i915_gem_reset_finish(struct drm_i915_private *dev_priv)
}
}
+void i915_gem_reset_finish(struct drm_i915_private *dev_priv)
+{
+ struct intel_engine_cs *engine;
+ enum intel_engine_id id;
+
+ lockdep_assert_held(&dev_priv->drm.struct_mutex);
+
+ for_each_engine(engine, dev_priv, id)
+ tasklet_enable(&engine->irq_tasklet);
+}
+
static void nop_submit_request(struct drm_i915_gem_request *request)
{
dma_fence_set_error(&request->fence, -EIO);
@@ -3029,6 +3127,16 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
args->timeout_ns -= ktime_to_ns(ktime_sub(ktime_get(), start));
if (args->timeout_ns < 0)
args->timeout_ns = 0;
+
+ /*
+ * Apparently ktime isn't accurate enough and occasionally has a
+ * bit of mismatch in the jiffies<->nsecs<->ktime loop. So patch
+ * things up to make the test happy. We allow up to 1 jiffy.
+ *
+ * This is a regression from the timespec->ktime conversion.
+ */
+ if (ret == -ETIME && !nsecs_to_jiffies(args->timeout_ns))
+ args->timeout_ns = 0;
}
i915_gem_object_put(obj);
@@ -3974,8 +4082,11 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
static const struct drm_i915_gem_object_ops i915_gem_object_ops = {
.flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE |
I915_GEM_OBJECT_IS_SHRINKABLE,
+
.get_pages = i915_gem_object_get_pages_gtt,
.put_pages = i915_gem_object_put_pages_gtt,
+
+ .pwrite = i915_gem_object_pwrite_gtt,
};
struct drm_i915_gem_object *
@@ -4583,8 +4694,6 @@ i915_gem_load_init(struct drm_i915_private *dev_priv)
init_waitqueue_head(&dev_priv->gpu_error.wait_queue);
init_waitqueue_head(&dev_priv->gpu_error.reset_queue);
- dev_priv->relative_constants_mode = I915_EXEC_CONSTANTS_REL_GENERAL;
-
init_waitqueue_head(&dev_priv->pending_flip_queue);
dev_priv->mm.interruptible = true;
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 17f90c6..e2d83b6 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -311,7 +311,6 @@ __create_hw_context(struct drm_i915_private *dev_priv,
ctx->ring_size = 4 * PAGE_SIZE;
ctx->desc_template = GEN8_CTX_ADDRESSING_MODE(dev_priv) <<
GEN8_CTX_ADDRESSING_MODE_SHIFT;
- ATOMIC_INIT_NOTIFIER_HEAD(&ctx->status_notifier);
/* GuC requires the ring to be placed above GUC_WOPCM_TOP. If GuC is not
* present or not in use we still need a small bias as ring wraparound
diff --git a/drivers/gpu/drm/i915/i915_gem_context.h b/drivers/gpu/drm/i915/i915_gem_context.h
index 0ac750b..e9c008f 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/i915_gem_context.h
@@ -160,9 +160,6 @@ struct i915_gem_context {
/** desc_template: invariant fields for the HW context descriptor */
u32 desc_template;
- /** status_notifier: list of callbacks for context-switch changes */
- struct atomic_notifier_head status_notifier;
-
/** guilty_count: How many times this context has caused a GPU hang. */
unsigned int guilty_count;
/**
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index c181b1b..3be2503 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -293,12 +293,12 @@ int i915_gem_evict_for_node(struct i915_address_space *vm,
* those as well to make room for our guard pages.
*/
if (check_color) {
- if (vma->node.start + vma->node.size == node->start) {
- if (vma->node.color == node->color)
+ if (node->start + node->size == target->start) {
+ if (node->color == target->color)
continue;
}
- if (vma->node.start == node->start + node->size) {
- if (vma->node.color == node->color)
+ if (node->start == target->start + target->size) {
+ if (node->color == target->color)
continue;
}
}
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index d02cfae..30e0675 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1408,10 +1408,7 @@ execbuf_submit(struct i915_execbuffer_params *params,
struct drm_i915_gem_execbuffer2 *args,
struct list_head *vmas)
{
- struct drm_i915_private *dev_priv = params->request->i915;
u64 exec_start, exec_len;
- int instp_mode;
- u32 instp_mask;
int ret;
ret = i915_gem_execbuffer_move_to_gpu(params->request, vmas);
@@ -1422,56 +1419,11 @@ execbuf_submit(struct i915_execbuffer_params *params,
if (ret)
return ret;
- instp_mode = args->flags & I915_EXEC_CONSTANTS_MASK;
- instp_mask = I915_EXEC_CONSTANTS_MASK;
- switch (instp_mode) {
- case I915_EXEC_CONSTANTS_REL_GENERAL:
- case I915_EXEC_CONSTANTS_ABSOLUTE:
- case I915_EXEC_CONSTANTS_REL_SURFACE:
- if (instp_mode != 0 && params->engine->id != RCS) {
- DRM_DEBUG("non-0 rel constants mode on non-RCS\n");
- return -EINVAL;
- }
-
- if (instp_mode != dev_priv->relative_constants_mode) {
- if (INTEL_INFO(dev_priv)->gen < 4) {
- DRM_DEBUG("no rel constants on pre-gen4\n");
- return -EINVAL;
- }
-
- if (INTEL_INFO(dev_priv)->gen > 5 &&
- instp_mode == I915_EXEC_CONSTANTS_REL_SURFACE) {
- DRM_DEBUG("rel surface constants mode invalid on gen5+\n");
- return -EINVAL;
- }
-
- /* The HW changed the meaning on this bit on gen6 */
- if (INTEL_INFO(dev_priv)->gen >= 6)
- instp_mask &= ~I915_EXEC_CONSTANTS_REL_SURFACE;
- }
- break;
- default:
- DRM_DEBUG("execbuf with unknown constants: %d\n", instp_mode);
+ if (args->flags & I915_EXEC_CONSTANTS_MASK) {
+ DRM_DEBUG("I915_EXEC_CONSTANTS_* unsupported\n");
return -EINVAL;
}
- if (params->engine->id == RCS &&
- instp_mode != dev_priv->relative_constants_mode) {
- struct intel_ring *ring = params->request->ring;
-
- ret = intel_ring_begin(params->request, 4);
- if (ret)
- return ret;
-
- intel_ring_emit(ring, MI_NOOP);
- intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
- intel_ring_emit_reg(ring, INSTPM);
- intel_ring_emit(ring, instp_mask << 16 | instp_mode);
- intel_ring_advance(ring);
-
- dev_priv->relative_constants_mode = instp_mode;
- }
-
if (args->flags & I915_EXEC_GEN7_SOL_RESET) {
ret = i915_reset_gen7_sol_offsets(params->request);
if (ret)
diff --git a/drivers/gpu/drm/i915/i915_gem_object.h b/drivers/gpu/drm/i915/i915_gem_object.h
index bf90b07..76b80a0 100644
--- a/drivers/gpu/drm/i915/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/i915_gem_object.h
@@ -54,6 +54,9 @@ struct drm_i915_gem_object_ops {
struct sg_table *(*get_pages)(struct drm_i915_gem_object *);
void (*put_pages)(struct drm_i915_gem_object *, struct sg_table *);
+ int (*pwrite)(struct drm_i915_gem_object *,
+ const struct drm_i915_gem_pwrite *);
+
int (*dmabuf_export)(struct drm_i915_gem_object *);
void (*release)(struct drm_i915_gem_object *);
};
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index 401006b..d5d2b4c 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -263,7 +263,7 @@ unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv)
I915_SHRINK_BOUND |
I915_SHRINK_UNBOUND |
I915_SHRINK_ACTIVE);
- rcu_barrier(); /* wait until our RCU delayed slab frees are completed */
+ synchronize_rcu(); /* wait for our earlier RCU delayed slab frees */
return freed;
}
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index e6ffef2..b6c886a 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1046,68 +1046,51 @@ static void vlv_c0_read(struct drm_i915_private *dev_priv,
ei->media_c0 = I915_READ(VLV_MEDIA_C0_COUNT);
}
-static bool vlv_c0_above(struct drm_i915_private *dev_priv,
- const struct intel_rps_ei *old,
- const struct intel_rps_ei *now,
- int threshold)
-{
- u64 time, c0;
- unsigned int mul = 100;
-
- if (old->cz_clock == 0)
- return false;
-
- if (I915_READ(VLV_COUNTER_CONTROL) & VLV_COUNT_RANGE_HIGH)
- mul <<= 8;
-
- time = now->cz_clock - old->cz_clock;
- time *= threshold * dev_priv->czclk_freq;
-
- /* Workload can be split between render + media, e.g. SwapBuffers
- * being blitted in X after being rendered in mesa. To account for
- * this we need to combine both engines into our activity counter.
- */
- c0 = now->render_c0 - old->render_c0;
- c0 += now->media_c0 - old->media_c0;
- c0 *= mul * VLV_CZ_CLOCK_TO_MILLI_SEC;
-
- return c0 >= time;
-}
-
void gen6_rps_reset_ei(struct drm_i915_private *dev_priv)
{
- vlv_c0_read(dev_priv, &dev_priv->rps.down_ei);
- dev_priv->rps.up_ei = dev_priv->rps.down_ei;
+ memset(&dev_priv->rps.ei, 0, sizeof(dev_priv->rps.ei));
}
static u32 vlv_wa_c0_ei(struct drm_i915_private *dev_priv, u32 pm_iir)
{
+ const struct intel_rps_ei *prev = &dev_priv->rps.ei;
struct intel_rps_ei now;
u32 events = 0;
- if ((pm_iir & (GEN6_PM_RP_DOWN_EI_EXPIRED | GEN6_PM_RP_UP_EI_EXPIRED)) == 0)
+ if ((pm_iir & GEN6_PM_RP_UP_EI_EXPIRED) == 0)
return 0;
vlv_c0_read(dev_priv, &now);
if (now.cz_clock == 0)
return 0;
- if (pm_iir & GEN6_PM_RP_DOWN_EI_EXPIRED) {
- if (!vlv_c0_above(dev_priv,
- &dev_priv->rps.down_ei, &now,
- dev_priv->rps.down_threshold))
- events |= GEN6_PM_RP_DOWN_THRESHOLD;
- dev_priv->rps.down_ei = now;
+ if (prev->cz_clock) {
+ u64 time, c0;
+ unsigned int mul;
+
+ mul = VLV_CZ_CLOCK_TO_MILLI_SEC * 100; /* scale to threshold% */
+ if (I915_READ(VLV_COUNTER_CONTROL) & VLV_COUNT_RANGE_HIGH)
+ mul <<= 8;
+
+ time = now.cz_clock - prev->cz_clock;
+ time *= dev_priv->czclk_freq;
+
+ /* Workload can be split between render + media,
+ * e.g. SwapBuffers being blitted in X after being rendered in
+ * mesa. To account for this we need to combine both engines
+ * into our activity counter.
+ */
+ c0 = now.render_c0 - prev->render_c0;
+ c0 += now.media_c0 - prev->media_c0;
+ c0 *= mul;
+
+ if (c0 > time * dev_priv->rps.up_threshold)
+ events = GEN6_PM_RP_UP_THRESHOLD;
+ else if (c0 < time * dev_priv->rps.down_threshold)
+ events = GEN6_PM_RP_DOWN_THRESHOLD;
}
- if (pm_iir & GEN6_PM_RP_UP_EI_EXPIRED) {
- if (vlv_c0_above(dev_priv,
- &dev_priv->rps.up_ei, &now,
- dev_priv->rps.up_threshold))
- events |= GEN6_PM_RP_UP_THRESHOLD;
- dev_priv->rps.up_ei = now;
- }
-
+ dev_priv->rps.ei = now;
return events;
}
@@ -4228,7 +4211,7 @@ void intel_irq_init(struct drm_i915_private *dev_priv)
/* Let's track the enabled rps events */
if (IS_VALLEYVIEW(dev_priv))
/* WaGsvRC0ResidencyMethod:vlv */
- dev_priv->pm_rps_events = GEN6_PM_RP_DOWN_EI_EXPIRED | GEN6_PM_RP_UP_EI_EXPIRED;
+ dev_priv->pm_rps_events = GEN6_PM_RP_UP_EI_EXPIRED;
else
dev_priv->pm_rps_events = GEN6_PM_RPS_EVENTS;
@@ -4266,6 +4249,16 @@ void intel_irq_init(struct drm_i915_private *dev_priv)
if (!IS_GEN2(dev_priv))
dev->vblank_disable_immediate = true;
+ /* Most platforms treat the display irq block as an always-on
+ * power domain. vlv/chv can disable it at runtime and need
+ * special care to avoid writing any of the display block registers
+ * outside of the power domain. We defer setting up the display irqs
+ * in this case to the runtime pm.
+ */
+ dev_priv->display_irqs_enabled = true;
+ if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+ dev_priv->display_irqs_enabled = false;
+
dev->driver->get_vblank_timestamp = i915_get_vblank_timestamp;
dev->driver->get_scanout_position = i915_get_crtc_scanoutpos;
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 155906e..df20e9b 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -512,10 +512,36 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
return ret;
}
+static void
+i915_vma_remove(struct i915_vma *vma)
+{
+ struct drm_i915_gem_object *obj = vma->obj;
+
+ GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
+ GEM_BUG_ON(vma->flags & (I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND));
+
+ drm_mm_remove_node(&vma->node);
+ list_move_tail(&vma->vm_link, &vma->vm->unbound_list);
+
+ /* Since the unbound list is global, only move to that list if
+ * no more VMAs exist.
+ */
+ if (--obj->bind_count == 0)
+ list_move_tail(&obj->global_link,
+ &to_i915(obj->base.dev)->mm.unbound_list);
+
+ /* And finally now the object is completely decoupled from this vma,
+ * we can drop its hold on the backing storage and allow it to be
+ * reaped by the shrinker.
+ */
+ i915_gem_object_unpin_pages(obj);
+ GEM_BUG_ON(atomic_read(&obj->mm.pages_pin_count) < obj->bind_count);
+}
+
int __i915_vma_do_pin(struct i915_vma *vma,
u64 size, u64 alignment, u64 flags)
{
- unsigned int bound = vma->flags;
+ const unsigned int bound = vma->flags;
int ret;
lockdep_assert_held(&vma->vm->i915->drm.struct_mutex);
@@ -524,18 +550,18 @@ int __i915_vma_do_pin(struct i915_vma *vma,
if (WARN_ON(bound & I915_VMA_PIN_OVERFLOW)) {
ret = -EBUSY;
- goto err;
+ goto err_unpin;
}
if ((bound & I915_VMA_BIND_MASK) == 0) {
ret = i915_vma_insert(vma, size, alignment, flags);
if (ret)
- goto err;
+ goto err_unpin;
}
ret = i915_vma_bind(vma, vma->obj->cache_level, flags);
if (ret)
- goto err;
+ goto err_remove;
if ((bound ^ vma->flags) & I915_VMA_GLOBAL_BIND)
__i915_vma_set_map_and_fenceable(vma);
@@ -544,7 +570,12 @@ int __i915_vma_do_pin(struct i915_vma *vma,
GEM_BUG_ON(i915_vma_misplaced(vma, size, alignment, flags));
return 0;
-err:
+err_remove:
+ if ((bound & I915_VMA_BIND_MASK) == 0) {
+ GEM_BUG_ON(vma->pages);
+ i915_vma_remove(vma);
+ }
+err_unpin:
__i915_vma_unpin(vma);
return ret;
}
@@ -657,9 +688,6 @@ int i915_vma_unbind(struct i915_vma *vma)
}
vma->flags &= ~(I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND);
- drm_mm_remove_node(&vma->node);
- list_move_tail(&vma->vm_link, &vma->vm->unbound_list);
-
if (vma->pages != obj->mm.pages) {
GEM_BUG_ON(!vma->pages);
sg_free_table(vma->pages);
@@ -667,18 +695,7 @@ int i915_vma_unbind(struct i915_vma *vma)
}
vma->pages = NULL;
- /* Since the unbound list is global, only move to that list if
- * no more VMAs exist. */
- if (--obj->bind_count == 0)
- list_move_tail(&obj->global_link,
- &to_i915(obj->base.dev)->mm.unbound_list);
-
- /* And finally now the object is completely decoupled from this vma,
- * we can drop its hold on the backing storage and allow it to be
- * reaped by the shrinker.
- */
- i915_gem_object_unpin_pages(obj);
- GEM_BUG_ON(atomic_read(&obj->mm.pages_pin_count) < obj->bind_count);
+ i915_vma_remove(vma);
destroy:
if (unlikely(i915_vma_is_closed(vma)))
diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c
index 0085bc7..de219b7 100644
--- a/drivers/gpu/drm/i915/intel_csr.c
+++ b/drivers/gpu/drm/i915/intel_csr.c
@@ -35,7 +35,6 @@
*/
#define I915_CSR_GLK "i915/glk_dmc_ver1_01.bin"
-MODULE_FIRMWARE(I915_CSR_GLK);
#define GLK_CSR_VERSION_REQUIRED CSR_VERSION(1, 1)
#define I915_CSR_KBL "i915/kbl_dmc_ver1_01.bin"
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 0134167..ed1f4f2 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3669,10 +3669,6 @@ static void intel_update_pipe_config(struct intel_crtc *crtc,
/* drm_atomic_helper_update_legacy_modeset_state might not be called. */
crtc->base.mode = crtc->base.state->mode;
- DRM_DEBUG_KMS("Updating pipe size %ix%i -> %ix%i\n",
- old_crtc_state->pipe_src_w, old_crtc_state->pipe_src_h,
- pipe_config->pipe_src_w, pipe_config->pipe_src_h);
-
/*
* Update pipe size and adjust fitter if needed: the reason for this is
* that in compute_mode_changes we check the native mode (not the pfit
@@ -4796,23 +4792,17 @@ static void skylake_pfit_enable(struct intel_crtc *crtc)
struct intel_crtc_scaler_state *scaler_state =
&crtc->config->scaler_state;
- DRM_DEBUG_KMS("for crtc_state = %p\n", crtc->config);
-
if (crtc->config->pch_pfit.enabled) {
int id;
- if (WARN_ON(crtc->config->scaler_state.scaler_id < 0)) {
- DRM_ERROR("Requesting pfit without getting a scaler first\n");
+ if (WARN_ON(crtc->config->scaler_state.scaler_id < 0))
return;
- }
id = scaler_state->scaler_id;
I915_WRITE(SKL_PS_CTRL(pipe, id), PS_SCALER_EN |
PS_FILTER_MEDIUM | scaler_state->scalers[id].mode);
I915_WRITE(SKL_PS_WIN_POS(pipe, id), crtc->config->pch_pfit.pos);
I915_WRITE(SKL_PS_WIN_SZ(pipe, id), crtc->config->pch_pfit.size);
-
- DRM_DEBUG_KMS("for crtc_state = %p scaler_id = %d\n", crtc->config, id);
}
}
@@ -14379,6 +14369,24 @@ static void skl_update_crtcs(struct drm_atomic_state *state,
} while (progress);
}
+static void intel_atomic_helper_free_state(struct drm_i915_private *dev_priv)
+{
+ struct intel_atomic_state *state, *next;
+ struct llist_node *freed;
+
+ freed = llist_del_all(&dev_priv->atomic_helper.free_list);
+ llist_for_each_entry_safe(state, next, freed, freed)
+ drm_atomic_state_put(&state->base);
+}
+
+static void intel_atomic_helper_free_state_worker(struct work_struct *work)
+{
+ struct drm_i915_private *dev_priv =
+ container_of(work, typeof(*dev_priv), atomic_helper.free_work);
+
+ intel_atomic_helper_free_state(dev_priv);
+}
+
static void intel_atomic_commit_tail(struct drm_atomic_state *state)
{
struct drm_device *dev = state->dev;
@@ -14545,6 +14553,8 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state)
* can happen also when the device is completely off.
*/
intel_uncore_arm_unclaimed_mmio_detection(dev_priv);
+
+ intel_atomic_helper_free_state(dev_priv);
}
static void intel_atomic_commit_work(struct work_struct *work)
@@ -14946,17 +14956,19 @@ static void intel_begin_crtc_commit(struct drm_crtc *crtc,
to_intel_atomic_state(old_crtc_state->state);
bool modeset = needs_modeset(crtc->state);
+ if (!modeset &&
+ (intel_cstate->base.color_mgmt_changed ||
+ intel_cstate->update_pipe)) {
+ intel_color_set_csc(crtc->state);
+ intel_color_load_luts(crtc->state);
+ }
+
/* Perform vblank evasion around commit operation */
intel_pipe_update_start(intel_crtc);
if (modeset)
goto out;
- if (crtc->state->color_mgmt_changed || to_intel_crtc_state(crtc->state)->update_pipe) {
- intel_color_set_csc(crtc->state);
- intel_color_load_luts(crtc->state);
- }
-
if (intel_cstate->update_pipe)
intel_update_pipe_config(intel_crtc, old_intel_cstate);
else if (INTEL_GEN(dev_priv) >= 9)
@@ -16599,18 +16611,6 @@ static void sanitize_watermarks(struct drm_device *dev)
drm_modeset_acquire_fini(&ctx);
}
-static void intel_atomic_helper_free_state(struct work_struct *work)
-{
- struct drm_i915_private *dev_priv =
- container_of(work, typeof(*dev_priv), atomic_helper.free_work);
- struct intel_atomic_state *state, *next;
- struct llist_node *freed;
-
- freed = llist_del_all(&dev_priv->atomic_helper.free_list);
- llist_for_each_entry_safe(state, next, freed, freed)
- drm_atomic_state_put(&state->base);
-}
-
int intel_modeset_init(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = to_i915(dev);
@@ -16631,7 +16631,7 @@ int intel_modeset_init(struct drm_device *dev)
dev->mode_config.funcs = &intel_mode_funcs;
INIT_WORK(&dev_priv->atomic_helper.free_work,
- intel_atomic_helper_free_state);
+ intel_atomic_helper_free_state_worker);
intel_init_quirks(dev);
@@ -16696,12 +16696,11 @@ int intel_modeset_init(struct drm_device *dev)
}
}
- intel_update_czclk(dev_priv);
- intel_update_cdclk(dev_priv);
- dev_priv->atomic_cdclk_freq = dev_priv->cdclk_freq;
-
intel_shared_dpll_init(dev);
+ intel_update_czclk(dev_priv);
+ intel_modeset_init_hw(dev);
+
if (dev_priv->max_cdclk_freq == 0)
intel_update_max_cdclk(dev_priv);
@@ -17258,8 +17257,6 @@ void intel_modeset_gem_init(struct drm_device *dev)
intel_init_gt_powersave(dev_priv);
- intel_modeset_init_hw(dev);
-
intel_setup_overlay(dev_priv);
}
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 371acf10..ab1be5c 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -105,6 +105,8 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
/* Nothing to do here, execute in order of dependencies */
engine->schedule = NULL;
+ ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier);
+
dev_priv->engine[id] = engine;
return 0;
}
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index 1b8ba2e..2d449fb 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -357,14 +357,13 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
bool *enabled, int width, int height)
{
struct drm_i915_private *dev_priv = to_i915(fb_helper->dev);
- unsigned long conn_configured, mask;
+ unsigned long conn_configured, conn_seq, mask;
unsigned int count = min(fb_helper->connector_count, BITS_PER_LONG);
int i, j;
bool *save_enabled;
bool fallback = true;
int num_connectors_enabled = 0;
int num_connectors_detected = 0;
- int pass = 0;
save_enabled = kcalloc(count, sizeof(bool), GFP_KERNEL);
if (!save_enabled)
@@ -374,6 +373,7 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
mask = BIT(count) - 1;
conn_configured = 0;
retry:
+ conn_seq = conn_configured;
for (i = 0; i < count; i++) {
struct drm_fb_helper_connector *fb_conn;
struct drm_connector *connector;
@@ -387,7 +387,7 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
if (conn_configured & BIT(i))
continue;
- if (pass == 0 && !connector->has_tile)
+ if (conn_seq == 0 && !connector->has_tile)
continue;
if (connector->status == connector_status_connected)
@@ -498,10 +498,8 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
conn_configured |= BIT(i);
}
- if ((conn_configured & mask) != mask) {
- pass++;
+ if ((conn_configured & mask) != mask && conn_configured != conn_seq)
goto retry;
- }
/*
* If the BIOS didn't enable everything it could, fall back to have the
diff --git a/drivers/gpu/drm/i915/intel_gvt.c b/drivers/gpu/drm/i915/intel_gvt.c
index d23c0fc..8c04eca 100644
--- a/drivers/gpu/drm/i915/intel_gvt.c
+++ b/drivers/gpu/drm/i915/intel_gvt.c
@@ -77,6 +77,11 @@ int intel_gvt_init(struct drm_i915_private *dev_priv)
goto bail;
}
+ if (!i915.enable_execlists) {
+ DRM_INFO("GPU guest virtualisation [GVT-g] disabled due to disabled execlist submission [i915.enable_execlists module parameter]\n");
+ goto bail;
+ }
+
/*
* We're not in host or fail to find a MPT module, disable GVT-g
*/
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index ebae2bd..24b2fa5 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -1298,16 +1298,34 @@ intel_hdmi_mode_valid(struct drm_connector *connector,
static bool hdmi_12bpc_possible(struct intel_crtc_state *crtc_state)
{
- struct drm_device *dev = crtc_state->base.crtc->dev;
+ struct drm_i915_private *dev_priv =
+ to_i915(crtc_state->base.crtc->dev);
+ struct drm_atomic_state *state = crtc_state->base.state;
+ struct drm_connector_state *connector_state;
+ struct drm_connector *connector;
+ int i;
- if (HAS_GMCH_DISPLAY(to_i915(dev)))
+ if (HAS_GMCH_DISPLAY(dev_priv))
return false;
/*
* HDMI 12bpc affects the clocks, so it's only possible
* when not cloning with other encoder types.
*/
- return crtc_state->output_types == 1 << INTEL_OUTPUT_HDMI;
+ if (crtc_state->output_types != 1 << INTEL_OUTPUT_HDMI)
+ return false;
+
+ for_each_connector_in_state(state, connector, connector_state, i) {
+ const struct drm_display_info *info = &connector->display_info;
+
+ if (connector_state->crtc != crtc_state->base.crtc)
+ continue;
+
+ if ((info->edid_hdmi_dc_modes & DRM_EDID_HDMI_DC_36) == 0)
+ return false;
+ }
+
+ return true;
}
bool intel_hdmi_compute_config(struct intel_encoder *encoder,
diff --git a/drivers/gpu/drm/i915/intel_hotplug.c b/drivers/gpu/drm/i915/intel_hotplug.c
index b62e3f8..54208be 100644
--- a/drivers/gpu/drm/i915/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/intel_hotplug.c
@@ -219,7 +219,7 @@ static void intel_hpd_irq_storm_reenable_work(struct work_struct *work)
}
}
}
- if (dev_priv->display.hpd_irq_setup)
+ if (dev_priv->display_irqs_enabled && dev_priv->display.hpd_irq_setup)
dev_priv->display.hpd_irq_setup(dev_priv);
spin_unlock_irq(&dev_priv->irq_lock);
@@ -425,7 +425,7 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
}
}
- if (storm_detected)
+ if (storm_detected && dev_priv->display_irqs_enabled)
dev_priv->display.hpd_irq_setup(dev_priv);
spin_unlock(&dev_priv->irq_lock);
@@ -471,10 +471,12 @@ void intel_hpd_init(struct drm_i915_private *dev_priv)
* Interrupt setup is already guaranteed to be single-threaded, this is
* just to make the assert_spin_locked checks happy.
*/
- spin_lock_irq(&dev_priv->irq_lock);
- if (dev_priv->display.hpd_irq_setup)
- dev_priv->display.hpd_irq_setup(dev_priv);
- spin_unlock_irq(&dev_priv->irq_lock);
+ if (dev_priv->display_irqs_enabled && dev_priv->display.hpd_irq_setup) {
+ spin_lock_irq(&dev_priv->irq_lock);
+ if (dev_priv->display_irqs_enabled)
+ dev_priv->display.hpd_irq_setup(dev_priv);
+ spin_unlock_irq(&dev_priv->irq_lock);
+ }
}
static void i915_hpd_poll_init_work(struct work_struct *work)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index ebf8023..471af3b 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -345,7 +345,8 @@ execlists_context_status_change(struct drm_i915_gem_request *rq,
if (!IS_ENABLED(CONFIG_DRM_I915_GVT))
return;
- atomic_notifier_call_chain(&rq->ctx->status_notifier, status, rq);
+ atomic_notifier_call_chain(&rq->engine->context_status_notifier,
+ status, rq);
}
static void
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 249623d..6a29784 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4891,6 +4891,12 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
break;
}
+ /* When byt can survive without system hang with dynamic
+ * sw freq adjustments, this restriction can be lifted.
+ */
+ if (IS_VALLEYVIEW(dev_priv))
+ goto skip_hw_write;
+
I915_WRITE(GEN6_RP_UP_EI,
GT_INTERVAL_FROM_US(dev_priv, ei_up));
I915_WRITE(GEN6_RP_UP_THRESHOLD,
@@ -4911,6 +4917,7 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
GEN6_RP_UP_BUSY_AVG |
GEN6_RP_DOWN_IDLE_AVG);
+skip_hw_write:
dev_priv->rps.power = new_power;
dev_priv->rps.up_threshold = threshold_up;
dev_priv->rps.down_threshold = threshold_down;
@@ -4921,8 +4928,9 @@ static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val)
{
u32 mask = 0;
+ /* We use UP_EI_EXPIRED interupts for both up/down in manual mode */
if (val > dev_priv->rps.min_freq_softlimit)
- mask |= GEN6_PM_RP_DOWN_EI_EXPIRED | GEN6_PM_RP_DOWN_THRESHOLD | GEN6_PM_RP_DOWN_TIMEOUT;
+ mask |= GEN6_PM_RP_UP_EI_EXPIRED | GEN6_PM_RP_DOWN_THRESHOLD | GEN6_PM_RP_DOWN_TIMEOUT;
if (val < dev_priv->rps.max_freq_softlimit)
mask |= GEN6_PM_RP_UP_EI_EXPIRED | GEN6_PM_RP_UP_THRESHOLD;
@@ -5032,7 +5040,7 @@ void gen6_rps_busy(struct drm_i915_private *dev_priv)
{
mutex_lock(&dev_priv->rps.hw_lock);
if (dev_priv->rps.enabled) {
- if (dev_priv->pm_rps_events & (GEN6_PM_RP_DOWN_EI_EXPIRED | GEN6_PM_RP_UP_EI_EXPIRED))
+ if (dev_priv->pm_rps_events & GEN6_PM_RP_UP_EI_EXPIRED)
gen6_rps_reset_ei(dev_priv);
I915_WRITE(GEN6_PMINTRMSK,
gen6_rps_pm_mask(dev_priv, dev_priv->rps.cur_freq));
@@ -7916,10 +7924,10 @@ static bool skl_pcode_try_request(struct drm_i915_private *dev_priv, u32 mbox,
* @timeout_base_ms: timeout for polling with preemption enabled
*
* Keep resending the @request to @mbox until PCODE acknowledges it, PCODE
- * reports an error or an overall timeout of @timeout_base_ms+10 ms expires.
+ * reports an error or an overall timeout of @timeout_base_ms+50 ms expires.
* The request is acknowledged once the PCODE reply dword equals @reply after
* applying @reply_mask. Polling is first attempted with preemption enabled
- * for @timeout_base_ms and if this times out for another 10 ms with
+ * for @timeout_base_ms and if this times out for another 50 ms with
* preemption disabled.
*
* Returns 0 on success, %-ETIMEDOUT in case of a timeout, <0 in case of some
@@ -7955,14 +7963,15 @@ int skl_pcode_request(struct drm_i915_private *dev_priv, u32 mbox, u32 request,
* worst case) _and_ PCODE was busy for some reason even after a
* (queued) request and @timeout_base_ms delay. As a workaround retry
* the poll with preemption disabled to maximize the number of
- * requests. Increase the timeout from @timeout_base_ms to 10ms to
+ * requests. Increase the timeout from @timeout_base_ms to 50ms to
* account for interrupts that could reduce the number of these
- * requests.
+ * requests, and for any quirks of the PCODE firmware that delays
+ * the request completion.
*/
DRM_DEBUG_KMS("PCODE timeout, retrying with preemption disabled\n");
WARN_ON_ONCE(timeout_base_ms > 3);
preempt_disable();
- ret = wait_for_atomic(COND, 10);
+ ret = wait_for_atomic(COND, 50);
preempt_enable();
out:
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 91bc4ab..6c5f995 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2024,6 +2024,8 @@ static int intel_ring_context_pin(struct intel_engine_cs *engine,
ret = context_pin(ctx, flags);
if (ret)
goto error;
+
+ ce->state->obj->mm.dirty = true;
}
/* The kernel context is only used as a placeholder for flushing the
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 79c2b8d..13dccb1 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -403,6 +403,9 @@ struct intel_engine_cs {
*/
struct i915_gem_context *legacy_active_context;
+ /* status_notifier: list of callbacks for context-switch changes */
+ struct atomic_notifier_head context_status_notifier;
+
struct intel_engine_hangcheck hangcheck;
bool needs_cmd_parser;
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 9ef5468..9481ca9 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -254,9 +254,6 @@ skl_update_plane(struct drm_plane *drm_plane,
int scaler_id = plane_state->scaler_id;
const struct intel_scaler *scaler;
- DRM_DEBUG_KMS("plane = %d PS_PLANE_SEL(plane) = 0x%x\n",
- plane_id, PS_PLANE_SEL(plane_id));
-
scaler = &crtc_state->scaler_state.scalers[scaler_id];
I915_WRITE(SKL_PS_CTRL(pipe, scaler_id),
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index abe0888..b7ff592 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -119,6 +119,8 @@ fw_domains_get(struct drm_i915_private *dev_priv, enum forcewake_domains fw_doma
for_each_fw_domain_masked(d, fw_domains, dev_priv)
fw_domain_wait_ack(d);
+
+ dev_priv->uncore.fw_domains_active |= fw_domains;
}
static void
@@ -130,6 +132,8 @@ fw_domains_put(struct drm_i915_private *dev_priv, enum forcewake_domains fw_doma
fw_domain_put(d);
fw_domain_posting_read(d);
}
+
+ dev_priv->uncore.fw_domains_active &= ~fw_domains;
}
static void
@@ -240,10 +244,8 @@ intel_uncore_fw_release_timer(struct hrtimer *timer)
if (WARN_ON(domain->wake_count == 0))
domain->wake_count++;
- if (--domain->wake_count == 0) {
+ if (--domain->wake_count == 0)
dev_priv->uncore.funcs.force_wake_put(dev_priv, domain->mask);
- dev_priv->uncore.fw_domains_active &= ~domain->mask;
- }
spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
@@ -454,10 +456,8 @@ static void __intel_uncore_forcewake_get(struct drm_i915_private *dev_priv,
fw_domains &= ~domain->mask;
}
- if (fw_domains) {
+ if (fw_domains)
dev_priv->uncore.funcs.force_wake_get(dev_priv, fw_domains);
- dev_priv->uncore.fw_domains_active |= fw_domains;
- }
}
/**
@@ -968,7 +968,6 @@ static noinline void ___force_wake_auto(struct drm_i915_private *dev_priv,
fw_domain_arm_timer(domain);
dev_priv->uncore.funcs.force_wake_get(dev_priv, fw_domains);
- dev_priv->uncore.fw_domains_active |= fw_domains;
}
static inline void __force_wake_auto(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 4414cf7..36602ac 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -1,4 +1,4 @@
-/* Copyright (c) 2016 The Linux Foundation. All rights reserved.
+/* Copyright (c) 2016-2017 The Linux Foundation. All rights reserved.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 and
@@ -534,7 +534,7 @@ static void a5xx_destroy(struct msm_gpu *gpu)
}
if (a5xx_gpu->gpmu_bo) {
- if (a5xx_gpu->gpmu_bo)
+ if (a5xx_gpu->gpmu_iova)
msm_gem_put_iova(a5xx_gpu->gpmu_bo, gpu->id);
drm_gem_object_unreference_unlocked(a5xx_gpu->gpmu_bo);
}
@@ -860,7 +860,9 @@ static const struct adreno_gpu_funcs funcs = {
.idle = a5xx_idle,
.irq = a5xx_irq,
.destroy = a5xx_destroy,
+#ifdef CONFIG_DEBUG_FS
.show = a5xx_show,
+#endif
},
.get_timestamp = a5xx_get_timestamp,
};
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index c9bd1e6..5ae6542 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -418,18 +418,27 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
return 0;
}
-void adreno_gpu_cleanup(struct adreno_gpu *gpu)
+void adreno_gpu_cleanup(struct adreno_gpu *adreno_gpu)
{
- if (gpu->memptrs_bo) {
- if (gpu->memptrs)
- msm_gem_put_vaddr(gpu->memptrs_bo);
+ struct msm_gpu *gpu = &adreno_gpu->base;
- if (gpu->memptrs_iova)
- msm_gem_put_iova(gpu->memptrs_bo, gpu->base.id);
+ if (adreno_gpu->memptrs_bo) {
+ if (adreno_gpu->memptrs)
+ msm_gem_put_vaddr(adreno_gpu->memptrs_bo);
- drm_gem_object_unreference_unlocked(gpu->memptrs_bo);
+ if (adreno_gpu->memptrs_iova)
+ msm_gem_put_iova(adreno_gpu->memptrs_bo, gpu->id);
+
+ drm_gem_object_unreference_unlocked(adreno_gpu->memptrs_bo);
}
- release_firmware(gpu->pm4);
- release_firmware(gpu->pfp);
- msm_gpu_cleanup(&gpu->base);
+ release_firmware(adreno_gpu->pm4);
+ release_firmware(adreno_gpu->pfp);
+
+ msm_gpu_cleanup(gpu);
+
+ if (gpu->aspace) {
+ gpu->aspace->mmu->funcs->detach(gpu->aspace->mmu,
+ iommu_ports, ARRAY_SIZE(iommu_ports));
+ msm_gem_address_space_destroy(gpu->aspace);
+ }
}
diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index 921270e..a879ffa 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -171,7 +171,7 @@ dsi_mgr_phy_enable(int id,
}
}
} else {
- msm_dsi_host_reset_phy(mdsi->host);
+ msm_dsi_host_reset_phy(msm_dsi->host);
ret = enable_phy(msm_dsi, src_pll_id, &shared_timings[id]);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_audio.c b/drivers/gpu/drm/msm/hdmi/hdmi_audio.c
index a54d3bb..8177e85 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_audio.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_audio.c
@@ -18,13 +18,6 @@
#include <linux/hdmi.h>
#include "hdmi.h"
-
-/* Supported HDMI Audio channels */
-#define MSM_HDMI_AUDIO_CHANNEL_2 0
-#define MSM_HDMI_AUDIO_CHANNEL_4 1
-#define MSM_HDMI_AUDIO_CHANNEL_6 2
-#define MSM_HDMI_AUDIO_CHANNEL_8 3
-
/* maps MSM_HDMI_AUDIO_CHANNEL_n consts used by audio driver to # of channels: */
static int nchannels[] = { 2, 4, 6, 8 };
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_pipe.h b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_pipe.h
index 611da7a..2389019 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_pipe.h
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_pipe.h
@@ -18,7 +18,8 @@
#ifndef __MDP5_PIPE_H__
#define __MDP5_PIPE_H__
-#define SSPP_MAX (SSPP_RGB3 + 1) /* TODO: Add SSPP_MAX in mdp5.xml.h */
+/* TODO: Add SSPP_MAX in mdp5.xml.h */
+#define SSPP_MAX (SSPP_CURSOR1 + 1)
/* represents a hw pipe, which is dynamically assigned to a plane */
struct mdp5_hw_pipe {
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 59811f2..68e509b 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -812,6 +812,12 @@ struct drm_gem_object *msm_gem_new(struct drm_device *dev,
size = PAGE_ALIGN(size);
+ /* Disallow zero sized objects as they make the underlying
+ * infrastructure grumpy
+ */
+ if (size == 0)
+ return ERR_PTR(-EINVAL);
+
ret = msm_gem_new_impl(dev, size, flags, NULL, &obj);
if (ret)
goto fail;
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 99e05aa..af5b6ba 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -706,9 +706,6 @@ void msm_gpu_cleanup(struct msm_gpu *gpu)
msm_ringbuffer_destroy(gpu->rb);
}
- if (gpu->aspace)
- msm_gem_address_space_destroy(gpu->aspace);
-
if (gpu->fctx)
msm_fence_context_free(gpu->fctx);
}
diff --git a/drivers/gpu/drm/mxsfb/mxsfb_crtc.c b/drivers/gpu/drm/mxsfb/mxsfb_crtc.c
index e10a4ed..1144e0c 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_crtc.c
+++ b/drivers/gpu/drm/mxsfb/mxsfb_crtc.c
@@ -65,13 +65,11 @@ static int mxsfb_set_pixel_fmt(struct mxsfb_drm_private *mxsfb)
switch (format) {
case DRM_FORMAT_RGB565:
dev_dbg(drm->dev, "Setting up RGB565 mode\n");
- ctrl |= CTRL_SET_BUS_WIDTH(STMLCDIF_16BIT);
ctrl |= CTRL_SET_WORD_LENGTH(0);
ctrl1 |= CTRL1_SET_BYTE_PACKAGING(0xf);
break;
case DRM_FORMAT_XRGB8888:
dev_dbg(drm->dev, "Setting up XRGB8888 mode\n");
- ctrl |= CTRL_SET_BUS_WIDTH(STMLCDIF_24BIT);
ctrl |= CTRL_SET_WORD_LENGTH(3);
/* Do not use packed pixels = one pixel per word instead. */
ctrl1 |= CTRL1_SET_BYTE_PACKAGING(0x7);
@@ -87,6 +85,36 @@ static int mxsfb_set_pixel_fmt(struct mxsfb_drm_private *mxsfb)
return 0;
}
+static void mxsfb_set_bus_fmt(struct mxsfb_drm_private *mxsfb)
+{
+ struct drm_crtc *crtc = &mxsfb->pipe.crtc;
+ struct drm_device *drm = crtc->dev;
+ u32 bus_format = MEDIA_BUS_FMT_RGB888_1X24;
+ u32 reg;
+
+ reg = readl(mxsfb->base + LCDC_CTRL);
+
+ if (mxsfb->connector.display_info.num_bus_formats)
+ bus_format = mxsfb->connector.display_info.bus_formats[0];
+
+ reg &= ~CTRL_BUS_WIDTH_MASK;
+ switch (bus_format) {
+ case MEDIA_BUS_FMT_RGB565_1X16:
+ reg |= CTRL_SET_BUS_WIDTH(STMLCDIF_16BIT);
+ break;
+ case MEDIA_BUS_FMT_RGB666_1X18:
+ reg |= CTRL_SET_BUS_WIDTH(STMLCDIF_18BIT);
+ break;
+ case MEDIA_BUS_FMT_RGB888_1X24:
+ reg |= CTRL_SET_BUS_WIDTH(STMLCDIF_24BIT);
+ break;
+ default:
+ dev_err(drm->dev, "Unknown media bus format %d\n", bus_format);
+ break;
+ }
+ writel(reg, mxsfb->base + LCDC_CTRL);
+}
+
static void mxsfb_enable_controller(struct mxsfb_drm_private *mxsfb)
{
u32 reg;
@@ -168,13 +196,22 @@ static void mxsfb_crtc_mode_set_nofb(struct mxsfb_drm_private *mxsfb)
vdctrl0 |= VDCTRL0_HSYNC_ACT_HIGH;
if (m->flags & DRM_MODE_FLAG_PVSYNC)
vdctrl0 |= VDCTRL0_VSYNC_ACT_HIGH;
- if (bus_flags & DRM_BUS_FLAG_DE_HIGH)
+ /* Make sure Data Enable is high active by default */
+ if (!(bus_flags & DRM_BUS_FLAG_DE_LOW))
vdctrl0 |= VDCTRL0_ENABLE_ACT_HIGH;
- if (bus_flags & DRM_BUS_FLAG_PIXDATA_NEGEDGE)
+ /*
+ * DRM_BUS_FLAG_PIXDATA_ defines are controller centric,
+ * controllers VDCTRL0_DOTCLK is display centric.
+ * Drive on positive edge -> display samples on falling edge
+ * DRM_BUS_FLAG_PIXDATA_POSEDGE -> VDCTRL0_DOTCLK_ACT_FALLING
+ */
+ if (bus_flags & DRM_BUS_FLAG_PIXDATA_POSEDGE)
vdctrl0 |= VDCTRL0_DOTCLK_ACT_FALLING;
writel(vdctrl0, mxsfb->base + LCDC_VDCTRL0);
+ mxsfb_set_bus_fmt(mxsfb);
+
/* Frame length in lines. */
writel(m->crtc_vtotal, mxsfb->base + LCDC_VDCTRL1);
@@ -184,8 +221,8 @@ static void mxsfb_crtc_mode_set_nofb(struct mxsfb_drm_private *mxsfb)
VDCTRL2_SET_HSYNC_PERIOD(m->crtc_htotal),
mxsfb->base + LCDC_VDCTRL2);
- writel(SET_HOR_WAIT_CNT(m->crtc_hblank_end - m->crtc_hsync_end) |
- SET_VERT_WAIT_CNT(m->crtc_vblank_end - m->crtc_vsync_end),
+ writel(SET_HOR_WAIT_CNT(m->crtc_htotal - m->crtc_hsync_start) |
+ SET_VERT_WAIT_CNT(m->crtc_vtotal - m->crtc_vsync_start),
mxsfb->base + LCDC_VDCTRL3);
writel(SET_DOTCLK_H_VALID_DATA_CNT(m->hdisplay),
diff --git a/drivers/gpu/drm/mxsfb/mxsfb_drv.c b/drivers/gpu/drm/mxsfb/mxsfb_drv.c
index cdfbe02..ff6d6a6 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_drv.c
+++ b/drivers/gpu/drm/mxsfb/mxsfb_drv.c
@@ -102,14 +102,18 @@ static void mxsfb_pipe_enable(struct drm_simple_display_pipe *pipe,
{
struct mxsfb_drm_private *mxsfb = drm_pipe_to_mxsfb_drm_private(pipe);
+ drm_panel_prepare(mxsfb->panel);
mxsfb_crtc_enable(mxsfb);
+ drm_panel_enable(mxsfb->panel);
}
static void mxsfb_pipe_disable(struct drm_simple_display_pipe *pipe)
{
struct mxsfb_drm_private *mxsfb = drm_pipe_to_mxsfb_drm_private(pipe);
+ drm_panel_disable(mxsfb->panel);
mxsfb_crtc_disable(mxsfb);
+ drm_panel_unprepare(mxsfb->panel);
}
static void mxsfb_pipe_update(struct drm_simple_display_pipe *pipe,
diff --git a/drivers/gpu/drm/mxsfb/mxsfb_out.c b/drivers/gpu/drm/mxsfb/mxsfb_out.c
index fa8d173..b8e8142 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_out.c
+++ b/drivers/gpu/drm/mxsfb/mxsfb_out.c
@@ -112,6 +112,7 @@ static int mxsfb_attach_endpoint(struct drm_device *drm,
int mxsfb_create_output(struct drm_device *drm)
{
+ struct mxsfb_drm_private *mxsfb = drm->dev_private;
struct device_node *ep_np = NULL;
struct of_endpoint ep;
int ret;
@@ -127,5 +128,8 @@ int mxsfb_create_output(struct drm_device *drm)
}
}
+ if (!mxsfb->panel)
+ return -EPROBE_DEFER;
+
return 0;
}
diff --git a/drivers/gpu/drm/mxsfb/mxsfb_regs.h b/drivers/gpu/drm/mxsfb/mxsfb_regs.h
index 31d62cd..66a6ba9 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_regs.h
+++ b/drivers/gpu/drm/mxsfb/mxsfb_regs.h
@@ -44,6 +44,7 @@
#define CTRL_DATA_SELECT (1 << 16)
#define CTRL_SET_BUS_WIDTH(x) (((x) & 0x3) << 10)
#define CTRL_GET_BUS_WIDTH(x) (((x) >> 10) & 0x3)
+#define CTRL_BUS_WIDTH_MASK (0x3 << 10)
#define CTRL_SET_WORD_LENGTH(x) (((x) & 0x3) << 8)
#define CTRL_GET_WORD_LENGTH(x) (((x) >> 8) & 0x3)
#define CTRL_MASTER (1 << 5)
diff --git a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
index af267c3..ee5883f 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
@@ -147,9 +147,6 @@ static int omap_gem_dmabuf_mmap(struct dma_buf *buffer,
struct drm_gem_object *obj = buffer->priv;
int ret = 0;
- if (WARN_ON(!obj->filp))
- return -EINVAL;
-
ret = drm_gem_mmap_obj(obj, omap_gem_mmap_size(obj), vma);
if (ret < 0)
return ret;
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 684f170..aaa3e80 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -213,8 +213,8 @@ static void radeon_evict_flags(struct ttm_buffer_object *bo,
rbo->placement.num_busy_placement = 0;
for (i = 0; i < rbo->placement.num_placement; i++) {
if (rbo->placements[i].flags & TTM_PL_FLAG_VRAM) {
- if (rbo->placements[0].fpfn < fpfn)
- rbo->placements[0].fpfn = fpfn;
+ if (rbo->placements[i].fpfn < fpfn)
+ rbo->placements[i].fpfn = fpfn;
} else {
rbo->placement.busy_placement =
&rbo->placements[i];
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index d12b897..c7af9fd 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2984,6 +2984,16 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
(rdev->pdev->device == 0x6667)) {
max_sclk = 75000;
}
+ } else if (rdev->family == CHIP_OLAND) {
+ if ((rdev->pdev->revision == 0xC7) ||
+ (rdev->pdev->revision == 0x80) ||
+ (rdev->pdev->revision == 0x81) ||
+ (rdev->pdev->revision == 0x83) ||
+ (rdev->pdev->revision == 0x87) ||
+ (rdev->pdev->device == 0x6604) ||
+ (rdev->pdev->device == 0x6605)) {
+ max_sclk = 75000;
+ }
}
if (rps->vce_active) {
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
index b5bfbe5..b0ff304 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
@@ -32,6 +32,10 @@ void rcar_du_vsp_enable(struct rcar_du_crtc *crtc)
{
const struct drm_display_mode *mode = &crtc->crtc.state->adjusted_mode;
struct rcar_du_device *rcdu = crtc->group->dev;
+ struct vsp1_du_lif_config cfg = {
+ .width = mode->hdisplay,
+ .height = mode->vdisplay,
+ };
struct rcar_du_plane_state state = {
.state = {
.crtc = &crtc->crtc,
@@ -66,12 +70,12 @@ void rcar_du_vsp_enable(struct rcar_du_crtc *crtc)
*/
crtc->group->need_restart = true;
- vsp1_du_setup_lif(crtc->vsp->vsp, mode->hdisplay, mode->vdisplay);
+ vsp1_du_setup_lif(crtc->vsp->vsp, &cfg);
}
void rcar_du_vsp_disable(struct rcar_du_crtc *crtc)
{
- vsp1_du_setup_lif(crtc->vsp->vsp, 0, 0);
+ vsp1_du_setup_lif(crtc->vsp->vsp, NULL);
}
void rcar_du_vsp_atomic_begin(struct rcar_du_crtc *crtc)
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
index f80bf93..d745e8b 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
@@ -464,6 +464,7 @@ static void tilcdc_crtc_enable(struct drm_crtc *crtc)
{
struct drm_device *dev = crtc->dev;
struct tilcdc_crtc *tilcdc_crtc = to_tilcdc_crtc(crtc);
+ unsigned long flags;
WARN_ON(!drm_modeset_is_locked(&crtc->mutex));
mutex_lock(&tilcdc_crtc->enable_lock);
@@ -484,7 +485,17 @@ static void tilcdc_crtc_enable(struct drm_crtc *crtc)
tilcdc_write_mask(dev, LCDC_RASTER_CTRL_REG,
LCDC_PALETTE_LOAD_MODE(DATA_ONLY),
LCDC_PALETTE_LOAD_MODE_MASK);
+
+ /* There is no real chance for a race here as the time stamp
+ * is taken before the raster DMA is started. The spin-lock is
+ * taken to have a memory barrier after taking the time-stamp
+ * and to avoid a context switch between taking the stamp and
+ * enabling the raster.
+ */
+ spin_lock_irqsave(&tilcdc_crtc->irq_lock, flags);
+ tilcdc_crtc->last_vblank = ktime_get();
tilcdc_set(dev, LCDC_RASTER_CTRL_REG, LCDC_RASTER_ENABLE);
+ spin_unlock_irqrestore(&tilcdc_crtc->irq_lock, flags);
drm_crtc_vblank_on(crtc);
@@ -539,7 +550,6 @@ static void tilcdc_crtc_off(struct drm_crtc *crtc, bool shutdown)
}
drm_flip_work_commit(&tilcdc_crtc->unref_work, priv->wq);
- tilcdc_crtc->last_vblank = 0;
tilcdc_crtc->enabled = false;
mutex_unlock(&tilcdc_crtc->enable_lock);
@@ -602,7 +612,6 @@ int tilcdc_crtc_update_fb(struct drm_crtc *crtc,
{
struct tilcdc_crtc *tilcdc_crtc = to_tilcdc_crtc(crtc);
struct drm_device *dev = crtc->dev;
- unsigned long flags;
WARN_ON(!drm_modeset_is_locked(&crtc->mutex));
@@ -614,28 +623,30 @@ int tilcdc_crtc_update_fb(struct drm_crtc *crtc,
drm_framebuffer_reference(fb);
crtc->primary->fb = fb;
+ tilcdc_crtc->event = event;
- spin_lock_irqsave(&tilcdc_crtc->irq_lock, flags);
+ mutex_lock(&tilcdc_crtc->enable_lock);
- if (crtc->hwmode.vrefresh && ktime_to_ns(tilcdc_crtc->last_vblank)) {
+ if (tilcdc_crtc->enabled) {
+ unsigned long flags;
ktime_t next_vblank;
s64 tdiff;
- next_vblank = ktime_add_us(tilcdc_crtc->last_vblank,
- 1000000 / crtc->hwmode.vrefresh);
+ spin_lock_irqsave(&tilcdc_crtc->irq_lock, flags);
+ next_vblank = ktime_add_us(tilcdc_crtc->last_vblank,
+ 1000000 / crtc->hwmode.vrefresh);
tdiff = ktime_to_us(ktime_sub(next_vblank, ktime_get()));
if (tdiff < TILCDC_VBLANK_SAFETY_THRESHOLD_US)
tilcdc_crtc->next_fb = fb;
+ else
+ set_scanout(crtc, fb);
+
+ spin_unlock_irqrestore(&tilcdc_crtc->irq_lock, flags);
}
- if (tilcdc_crtc->next_fb != fb)
- set_scanout(crtc, fb);
-
- tilcdc_crtc->event = event;
-
- spin_unlock_irqrestore(&tilcdc_crtc->irq_lock, flags);
+ mutex_unlock(&tilcdc_crtc->enable_lock);
return 0;
}
@@ -1036,5 +1047,5 @@ int tilcdc_crtc_create(struct drm_device *dev)
fail:
tilcdc_crtc_destroy(crtc);
- return -ENOMEM;
+ return ret;
}
diff --git a/drivers/gpu/drm/ttm/ttm_object.c b/drivers/gpu/drm/ttm/ttm_object.c
index fdb451e..26a7ad0 100644
--- a/drivers/gpu/drm/ttm/ttm_object.c
+++ b/drivers/gpu/drm/ttm/ttm_object.c
@@ -179,7 +179,7 @@ int ttm_base_object_init(struct ttm_object_file *tfile,
if (unlikely(ret != 0))
goto out_err0;
- ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL);
+ ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL, false);
if (unlikely(ret != 0))
goto out_err1;
@@ -318,7 +318,8 @@ EXPORT_SYMBOL(ttm_ref_object_exists);
int ttm_ref_object_add(struct ttm_object_file *tfile,
struct ttm_base_object *base,
- enum ttm_ref_type ref_type, bool *existed)
+ enum ttm_ref_type ref_type, bool *existed,
+ bool require_existed)
{
struct drm_open_hash *ht = &tfile->ref_hash[ref_type];
struct ttm_ref_object *ref;
@@ -345,6 +346,9 @@ int ttm_ref_object_add(struct ttm_object_file *tfile,
}
rcu_read_unlock();
+ if (require_existed)
+ return -EPERM;
+
ret = ttm_mem_global_alloc(mem_glob, sizeof(*ref),
false, false);
if (unlikely(ret != 0))
@@ -449,10 +453,10 @@ void ttm_object_file_release(struct ttm_object_file **p_tfile)
ttm_ref_object_release(&ref->kref);
}
+ spin_unlock(&tfile->lock);
for (i = 0; i < TTM_REF_NUM; ++i)
drm_ht_remove(&tfile->ref_hash[i]);
- spin_unlock(&tfile->lock);
ttm_object_file_unref(&tfile);
}
EXPORT_SYMBOL(ttm_object_file_release);
@@ -529,9 +533,7 @@ void ttm_object_device_release(struct ttm_object_device **p_tdev)
*p_tdev = NULL;
- spin_lock(&tdev->object_lock);
drm_ht_remove(&tdev->object_hash);
- spin_unlock(&tdev->object_lock);
kfree(tdev);
}
@@ -635,7 +637,7 @@ int ttm_prime_fd_to_handle(struct ttm_object_file *tfile,
prime = (struct ttm_prime_object *) dma_buf->priv;
base = &prime->base;
*handle = base->hash.key;
- ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL);
+ ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL, false);
dma_buf_put(dma_buf);
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index 0c06844..9fcf05c 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -846,6 +846,17 @@ static void vc4_crtc_destroy_state(struct drm_crtc *crtc,
drm_atomic_helper_crtc_destroy_state(crtc, state);
}
+static void
+vc4_crtc_reset(struct drm_crtc *crtc)
+{
+ if (crtc->state)
+ __drm_atomic_helper_crtc_destroy_state(crtc->state);
+
+ crtc->state = kzalloc(sizeof(struct vc4_crtc_state), GFP_KERNEL);
+ if (crtc->state)
+ crtc->state->crtc = crtc;
+}
+
static const struct drm_crtc_funcs vc4_crtc_funcs = {
.set_config = drm_atomic_helper_set_config,
.destroy = vc4_crtc_destroy,
@@ -853,7 +864,7 @@ static const struct drm_crtc_funcs vc4_crtc_funcs = {
.set_property = NULL,
.cursor_set = NULL, /* handled by drm_mode_cursor_universal */
.cursor_move = NULL, /* handled by drm_mode_cursor_universal */
- .reset = drm_atomic_helper_crtc_reset,
+ .reset = vc4_crtc_reset,
.atomic_duplicate_state = vc4_crtc_duplicate_state,
.atomic_destroy_state = vc4_crtc_destroy_state,
.gamma_set = vc4_crtc_gamma_set,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
index 6541dd8..6b2708b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
@@ -538,7 +538,7 @@ int vmw_fence_create(struct vmw_fence_manager *fman,
struct vmw_fence_obj **p_fence)
{
struct vmw_fence_obj *fence;
- int ret;
+ int ret;
fence = kzalloc(sizeof(*fence), GFP_KERNEL);
if (unlikely(fence == NULL))
@@ -701,6 +701,41 @@ void vmw_fence_fifo_up(struct vmw_fence_manager *fman)
}
+/**
+ * vmw_fence_obj_lookup - Look up a user-space fence object
+ *
+ * @tfile: A struct ttm_object_file identifying the caller.
+ * @handle: A handle identifying the fence object.
+ * @return: A struct vmw_user_fence base ttm object on success or
+ * an error pointer on failure.
+ *
+ * The fence object is looked up and type-checked. The caller needs
+ * to have opened the fence object first, but since that happens on
+ * creation and fence objects aren't shareable, that's not an
+ * issue currently.
+ */
+static struct ttm_base_object *
+vmw_fence_obj_lookup(struct ttm_object_file *tfile, u32 handle)
+{
+ struct ttm_base_object *base = ttm_base_object_lookup(tfile, handle);
+
+ if (!base) {
+ pr_err("Invalid fence object handle 0x%08lx.\n",
+ (unsigned long)handle);
+ return ERR_PTR(-EINVAL);
+ }
+
+ if (base->refcount_release != vmw_user_fence_base_release) {
+ pr_err("Invalid fence object handle 0x%08lx.\n",
+ (unsigned long)handle);
+ ttm_base_object_unref(&base);
+ return ERR_PTR(-EINVAL);
+ }
+
+ return base;
+}
+
+
int vmw_fence_obj_wait_ioctl(struct drm_device *dev, void *data,
struct drm_file *file_priv)
{
@@ -726,13 +761,9 @@ int vmw_fence_obj_wait_ioctl(struct drm_device *dev, void *data,
arg->kernel_cookie = jiffies + wait_timeout;
}
- base = ttm_base_object_lookup(tfile, arg->handle);
- if (unlikely(base == NULL)) {
- printk(KERN_ERR "Wait invalid fence object handle "
- "0x%08lx.\n",
- (unsigned long)arg->handle);
- return -EINVAL;
- }
+ base = vmw_fence_obj_lookup(tfile, arg->handle);
+ if (IS_ERR(base))
+ return PTR_ERR(base);
fence = &(container_of(base, struct vmw_user_fence, base)->fence);
@@ -771,13 +802,9 @@ int vmw_fence_obj_signaled_ioctl(struct drm_device *dev, void *data,
struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
struct vmw_private *dev_priv = vmw_priv(dev);
- base = ttm_base_object_lookup(tfile, arg->handle);
- if (unlikely(base == NULL)) {
- printk(KERN_ERR "Fence signaled invalid fence object handle "
- "0x%08lx.\n",
- (unsigned long)arg->handle);
- return -EINVAL;
- }
+ base = vmw_fence_obj_lookup(tfile, arg->handle);
+ if (IS_ERR(base))
+ return PTR_ERR(base);
fence = &(container_of(base, struct vmw_user_fence, base)->fence);
fman = fman_from_fence(fence);
@@ -1024,6 +1051,7 @@ int vmw_fence_event_ioctl(struct drm_device *dev, void *data,
(struct drm_vmw_fence_event_arg *) data;
struct vmw_fence_obj *fence = NULL;
struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv);
+ struct ttm_object_file *tfile = vmw_fp->tfile;
struct drm_vmw_fence_rep __user *user_fence_rep =
(struct drm_vmw_fence_rep __user *)(unsigned long)
arg->fence_rep;
@@ -1037,24 +1065,18 @@ int vmw_fence_event_ioctl(struct drm_device *dev, void *data,
*/
if (arg->handle) {
struct ttm_base_object *base =
- ttm_base_object_lookup_for_ref(dev_priv->tdev,
- arg->handle);
+ vmw_fence_obj_lookup(tfile, arg->handle);
- if (unlikely(base == NULL)) {
- DRM_ERROR("Fence event invalid fence object handle "
- "0x%08lx.\n",
- (unsigned long)arg->handle);
- return -EINVAL;
- }
+ if (IS_ERR(base))
+ return PTR_ERR(base);
+
fence = &(container_of(base, struct vmw_user_fence,
base)->fence);
(void) vmw_fence_obj_reference(fence);
if (user_fence_rep != NULL) {
- bool existed;
-
ret = ttm_ref_object_add(vmw_fp->tfile, base,
- TTM_REF_USAGE, &existed);
+ TTM_REF_USAGE, NULL, false);
if (unlikely(ret != 0)) {
DRM_ERROR("Failed to reference a fence "
"object.\n");
@@ -1097,8 +1119,7 @@ int vmw_fence_event_ioctl(struct drm_device *dev, void *data,
return 0;
out_no_create:
if (user_fence_rep != NULL)
- ttm_ref_object_base_unref(vmw_fpriv(file_priv)->tfile,
- handle, TTM_REF_USAGE);
+ ttm_ref_object_base_unref(tfile, handle, TTM_REF_USAGE);
out_no_ref_obj:
vmw_fence_obj_unreference(&fence);
return ret;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
index b8c6a03..5ec24fd 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
@@ -114,8 +114,6 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data,
param->value = dev_priv->has_dx;
break;
default:
- DRM_ERROR("Illegal vmwgfx get param request: %d\n",
- param->param);
return -EINVAL;
}
@@ -186,7 +184,7 @@ int vmw_get_cap_3d_ioctl(struct drm_device *dev, void *data,
bool gb_objects = !!(dev_priv->capabilities & SVGA_CAP_GBOBJECTS);
struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv);
- if (unlikely(arg->pad64 != 0)) {
+ if (unlikely(arg->pad64 != 0 || arg->max_size == 0)) {
DRM_ERROR("Illegal GET_3D_CAP argument.\n");
return -EINVAL;
}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 65b3f03..bf23153 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -589,7 +589,7 @@ static int vmw_user_dmabuf_synccpu_grab(struct vmw_user_dma_buffer *user_bo,
return ret;
ret = ttm_ref_object_add(tfile, &user_bo->prime.base,
- TTM_REF_SYNCCPU_WRITE, &existed);
+ TTM_REF_SYNCCPU_WRITE, &existed, false);
if (ret != 0 || existed)
ttm_bo_synccpu_write_release(&user_bo->dma.base);
@@ -773,7 +773,7 @@ int vmw_user_dmabuf_reference(struct ttm_object_file *tfile,
*handle = user_bo->prime.base.hash.key;
return ttm_ref_object_add(tfile, &user_bo->prime.base,
- TTM_REF_USAGE, NULL);
+ TTM_REF_USAGE, NULL, false);
}
/*
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index b445ce9..05fa092 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -713,11 +713,14 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
128;
num_sizes = 0;
- for (i = 0; i < DRM_VMW_MAX_SURFACE_FACES; ++i)
+ for (i = 0; i < DRM_VMW_MAX_SURFACE_FACES; ++i) {
+ if (req->mip_levels[i] > DRM_VMW_MAX_MIP_LEVELS)
+ return -EINVAL;
num_sizes += req->mip_levels[i];
+ }
- if (num_sizes > DRM_VMW_MAX_SURFACE_FACES *
- DRM_VMW_MAX_MIP_LEVELS)
+ if (num_sizes > DRM_VMW_MAX_SURFACE_FACES * DRM_VMW_MAX_MIP_LEVELS ||
+ num_sizes == 0)
return -EINVAL;
size = vmw_user_surface_size + 128 +
@@ -891,17 +894,16 @@ vmw_surface_handle_reference(struct vmw_private *dev_priv,
uint32_t handle;
struct ttm_base_object *base;
int ret;
+ bool require_exist = false;
if (handle_type == DRM_VMW_HANDLE_PRIME) {
ret = ttm_prime_fd_to_handle(tfile, u_handle, &handle);
if (unlikely(ret != 0))
return ret;
} else {
- if (unlikely(drm_is_render_client(file_priv))) {
- DRM_ERROR("Render client refused legacy "
- "surface reference.\n");
- return -EACCES;
- }
+ if (unlikely(drm_is_render_client(file_priv)))
+ require_exist = true;
+
if (ACCESS_ONCE(vmw_fpriv(file_priv)->locked_master)) {
DRM_ERROR("Locked master refused legacy "
"surface reference.\n");
@@ -929,17 +931,14 @@ vmw_surface_handle_reference(struct vmw_private *dev_priv,
/*
* Make sure the surface creator has the same
- * authenticating master.
+ * authenticating master, or is already registered with us.
*/
if (drm_is_primary_client(file_priv) &&
- user_srf->master != file_priv->master) {
- DRM_ERROR("Trying to reference surface outside of"
- " master domain.\n");
- ret = -EACCES;
- goto out_bad_resource;
- }
+ user_srf->master != file_priv->master)
+ require_exist = true;
- ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL);
+ ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL,
+ require_exist);
if (unlikely(ret != 0)) {
DRM_ERROR("Could not add a reference to a surface.\n");
goto out_bad_resource;
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 1aeb80e..8c54cb8 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -175,11 +175,11 @@
Support for Cherry Cymotion keyboard.
config HID_CHICONY
- tristate "Chicony Tactical pad"
+ tristate "Chicony devices"
depends on HID
default !EXPERT
---help---
- Support for Chicony Tactical pad.
+ Support for Chicony Tactical pad and special keys on Chicony keyboards.
config HID_CORSAIR
tristate "Corsair devices"
@@ -190,6 +190,7 @@
Supported devices:
- Vengeance K90
+ - Scimitar PRO RGB
config HID_PRODIKEYS
tristate "Prodikeys PC-MIDI Keyboard support"
diff --git a/drivers/hid/hid-chicony.c b/drivers/hid/hid-chicony.c
index bc3cec1..f04ed9a 100644
--- a/drivers/hid/hid-chicony.c
+++ b/drivers/hid/hid-chicony.c
@@ -86,6 +86,7 @@ static const struct hid_device_id ch_devices[] = {
{ HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_WIRELESS2) },
{ HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_AK1D) },
{ HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_ACER_SWITCH12) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_JESS, USB_DEVICE_ID_JESS_ZEN_AIO_KBD) },
{ }
};
MODULE_DEVICE_TABLE(hid, ch_devices);
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index e9e87d3..63ec199 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1870,6 +1870,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
{ HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_AK1D) },
{ HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_ACER_SWITCH12) },
{ HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K90) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_SCIMITAR_PRO_RGB) },
{ HID_USB_DEVICE(USB_VENDOR_ID_CREATIVELABS, USB_DEVICE_ID_PRODIKEYS_PCMIDI) },
{ HID_USB_DEVICE(USB_VENDOR_ID_CYGNAL, USB_DEVICE_ID_CYGNAL_CP2112) },
{ HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_BARCODE_1) },
@@ -1910,6 +1911,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A081) },
{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A0C2) },
{ HID_USB_DEVICE(USB_VENDOR_ID_HUION, USB_DEVICE_ID_HUION_TABLET) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_JESS, USB_DEVICE_ID_JESS_ZEN_AIO_KBD) },
{ HID_USB_DEVICE(USB_VENDOR_ID_JESS2, USB_DEVICE_ID_JESS2_COLOR_RUMBLE_PAD) },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ION, USB_DEVICE_ID_ICADE) },
{ HID_USB_DEVICE(USB_VENDOR_ID_KENSINGTON, USB_DEVICE_ID_KS_SLIMBLADE) },
@@ -2110,6 +2112,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
{ HID_USB_DEVICE(USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_SIRIUS_BATTERY_FREE_TABLET) },
{ HID_USB_DEVICE(USB_VENDOR_ID_X_TENSIONS, USB_DEVICE_ID_SPEEDLINK_VAD_CEZANNE) },
{ HID_USB_DEVICE(USB_VENDOR_ID_XIN_MO, USB_DEVICE_ID_XIN_MO_DUAL_ARCADE) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_XIN_MO, USB_DEVICE_ID_THT_2P_ARCADE) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ZEROPLUS, 0x0005) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ZEROPLUS, 0x0030) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ZYDACRON, USB_DEVICE_ID_ZYDACRON_REMOTE_CONTROL) },
diff --git a/drivers/hid/hid-corsair.c b/drivers/hid/hid-corsair.c
index c0303f6..9ba5d98 100644
--- a/drivers/hid/hid-corsair.c
+++ b/drivers/hid/hid-corsair.c
@@ -3,8 +3,10 @@
*
* Supported devices:
* - Vengeance K90 Keyboard
+ * - Scimitar PRO RGB Gaming Mouse
*
* Copyright (c) 2015 Clement Vuchener
+ * Copyright (c) 2017 Oscar Campos
*/
/*
@@ -670,10 +672,51 @@ static int corsair_input_mapping(struct hid_device *dev,
return 0;
}
+/*
+ * The report descriptor of Corsair Scimitar RGB Pro gaming mouse is
+ * non parseable as they define two consecutive Logical Minimum for
+ * the Usage Page (Consumer) in rdescs bytes 75 and 77 being 77 0x16
+ * that should be obviousy 0x26 for Logical Magimum of 16 bits. This
+ * prevents poper parsing of the report descriptor due Logical
+ * Minimum being larger than Logical Maximum.
+ *
+ * This driver fixes the report descriptor for:
+ * - USB ID b1c:1b3e, sold as Scimitar RGB Pro Gaming mouse
+ */
+
+static __u8 *corsair_mouse_report_fixup(struct hid_device *hdev, __u8 *rdesc,
+ unsigned int *rsize)
+{
+ struct usb_interface *intf = to_usb_interface(hdev->dev.parent);
+
+ if (intf->cur_altsetting->desc.bInterfaceNumber == 1) {
+ /*
+ * Corsair Scimitar RGB Pro report descriptor is broken and
+ * defines two different Logical Minimum for the Consumer
+ * Application. The byte 77 should be a 0x26 defining a 16
+ * bits integer for the Logical Maximum but it is a 0x16
+ * instead (Logical Minimum)
+ */
+ switch (hdev->product) {
+ case USB_DEVICE_ID_CORSAIR_SCIMITAR_PRO_RGB:
+ if (*rsize >= 172 && rdesc[75] == 0x15 && rdesc[77] == 0x16
+ && rdesc[78] == 0xff && rdesc[79] == 0x0f) {
+ hid_info(hdev, "Fixing up report descriptor\n");
+ rdesc[77] = 0x26;
+ }
+ break;
+ }
+
+ }
+ return rdesc;
+}
+
static const struct hid_device_id corsair_devices[] = {
{ HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K90),
.driver_data = CORSAIR_USE_K90_MACRO |
CORSAIR_USE_K90_BACKLIGHT },
+ { HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR,
+ USB_DEVICE_ID_CORSAIR_SCIMITAR_PRO_RGB) },
{}
};
@@ -686,10 +729,14 @@ static struct hid_driver corsair_driver = {
.event = corsair_event,
.remove = corsair_remove,
.input_mapping = corsair_input_mapping,
+ .report_fixup = corsair_mouse_report_fixup,
};
module_hid_driver(corsair_driver);
MODULE_LICENSE("GPL");
+/* Original K90 driver author */
MODULE_AUTHOR("Clement Vuchener");
+/* Scimitar PRO RGB driver author */
+MODULE_AUTHOR("Oscar Campos");
MODULE_DESCRIPTION("HID driver for Corsair devices");
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 86c95d3..4e2648c 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -278,6 +278,9 @@
#define USB_DEVICE_ID_CORSAIR_K70RGB 0x1b13
#define USB_DEVICE_ID_CORSAIR_STRAFE 0x1b15
#define USB_DEVICE_ID_CORSAIR_K65RGB 0x1b17
+#define USB_DEVICE_ID_CORSAIR_K70RGB_RAPIDFIRE 0x1b38
+#define USB_DEVICE_ID_CORSAIR_K65RGB_RAPIDFIRE 0x1b39
+#define USB_DEVICE_ID_CORSAIR_SCIMITAR_PRO_RGB 0x1b3e
#define USB_VENDOR_ID_CREATIVELABS 0x041e
#define USB_DEVICE_ID_CREATIVE_SB_OMNI_SURROUND_51 0x322c
@@ -557,6 +560,7 @@
#define USB_VENDOR_ID_JESS 0x0c45
#define USB_DEVICE_ID_JESS_YUREX 0x1010
+#define USB_DEVICE_ID_JESS_ZEN_AIO_KBD 0x5112
#define USB_VENDOR_ID_JESS2 0x0f30
#define USB_DEVICE_ID_JESS2_COLOR_RUMBLE_PAD 0x0111
@@ -1078,6 +1082,7 @@
#define USB_VENDOR_ID_XIN_MO 0x16c0
#define USB_DEVICE_ID_XIN_MO_DUAL_ARCADE 0x05e1
+#define USB_DEVICE_ID_THT_2P_ARCADE 0x75e1
#define USB_VENDOR_ID_XIROKU 0x1477
#define USB_DEVICE_ID_XIROKU_SPX 0x1006
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index f405b07..740996f 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -2632,6 +2632,8 @@ static int sony_input_configured(struct hid_device *hdev,
sony_leds_remove(sc);
if (sc->quirks & SONY_BATTERY_SUPPORT)
sony_battery_remove(sc);
+ if (sc->touchpad)
+ sony_unregister_touchpad(sc);
sony_cancel_work_sync(sc);
kfree(sc->output_report_dmabuf);
sony_remove_dev_list(sc);
diff --git a/drivers/hid/hid-xinmo.c b/drivers/hid/hid-xinmo.c
index 7df5227..9ad7731 100644
--- a/drivers/hid/hid-xinmo.c
+++ b/drivers/hid/hid-xinmo.c
@@ -46,6 +46,7 @@ static int xinmo_event(struct hid_device *hdev, struct hid_field *field,
static const struct hid_device_id xinmo_devices[] = {
{ HID_USB_DEVICE(USB_VENDOR_ID_XIN_MO, USB_DEVICE_ID_XIN_MO_DUAL_ARCADE) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_XIN_MO, USB_DEVICE_ID_THT_2P_ARCADE) },
{ }
};
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index d6847a6..a69a3c8 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -80,6 +80,9 @@ static const struct hid_blacklist {
{ USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K70RGB, HID_QUIRK_NO_INIT_REPORTS },
{ USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K65RGB, HID_QUIRK_NO_INIT_REPORTS },
{ USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_STRAFE, HID_QUIRK_NO_INIT_REPORTS | HID_QUIRK_ALWAYS_POLL },
+ { USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K70RGB_RAPIDFIRE, HID_QUIRK_NO_INIT_REPORTS | HID_QUIRK_ALWAYS_POLL },
+ { USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K65RGB_RAPIDFIRE, HID_QUIRK_NO_INIT_REPORTS | HID_QUIRK_ALWAYS_POLL },
+ { USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_SCIMITAR_PRO_RGB, HID_QUIRK_NO_INIT_REPORTS | HID_QUIRK_ALWAYS_POLL },
{ USB_VENDOR_ID_CREATIVELABS, USB_DEVICE_ID_CREATIVE_SB_OMNI_SURROUND_51, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_DMI, USB_DEVICE_ID_DMI_ENC, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_WIIU, HID_QUIRK_MULTI_INPUT },
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index be8f7e2..e2666ef 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -2165,6 +2165,14 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless)
wacom_update_name(wacom, wireless ? " (WL)" : "");
+ /* pen only Bamboo neither support touch nor pad */
+ if ((features->type == BAMBOO_PEN) &&
+ ((features->device_type & WACOM_DEVICETYPE_TOUCH) ||
+ (features->device_type & WACOM_DEVICETYPE_PAD))) {
+ error = -ENODEV;
+ goto fail;
+ }
+
error = wacom_add_shared_data(hdev);
if (error)
goto fail;
@@ -2208,14 +2216,8 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless)
/* touch only Bamboo doesn't support pen */
if ((features->type == BAMBOO_TOUCH) &&
(features->device_type & WACOM_DEVICETYPE_PEN)) {
- error = -ENODEV;
- goto fail_quirks;
- }
-
- /* pen only Bamboo neither support touch nor pad */
- if ((features->type == BAMBOO_PEN) &&
- ((features->device_type & WACOM_DEVICETYPE_TOUCH) ||
- (features->device_type & WACOM_DEVICETYPE_PAD))) {
+ cancel_delayed_work_sync(&wacom->init_work);
+ _wacom_query_tablet_data(wacom);
error = -ENODEV;
goto fail_quirks;
}
@@ -2579,7 +2581,9 @@ static void wacom_remove(struct hid_device *hdev)
/* make sure we don't trigger the LEDs */
wacom_led_groups_release(wacom);
- wacom_release_resources(wacom);
+
+ if (wacom->wacom_wac.features.type != REMOTE)
+ wacom_release_resources(wacom);
hid_set_drvdata(hdev, NULL);
}
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 4aa3de9..94250c2 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -1959,8 +1959,10 @@ static void wacom_wac_pen_usage_mapping(struct hid_device *hdev,
input_set_capability(input, EV_KEY, BTN_TOOL_BRUSH);
input_set_capability(input, EV_KEY, BTN_TOOL_PENCIL);
input_set_capability(input, EV_KEY, BTN_TOOL_AIRBRUSH);
- input_set_capability(input, EV_KEY, BTN_TOOL_MOUSE);
- input_set_capability(input, EV_KEY, BTN_TOOL_LENS);
+ if (!(features->device_type & WACOM_DEVICETYPE_DIRECT)) {
+ input_set_capability(input, EV_KEY, BTN_TOOL_MOUSE);
+ input_set_capability(input, EV_KEY, BTN_TOOL_LENS);
+ }
break;
case WACOM_HID_WD_FINGERWHEEL:
wacom_map_usage(input, usage, field, EV_ABS, ABS_WHEEL, 0);
@@ -4197,10 +4199,10 @@ static const struct wacom_features wacom_features_0x343 =
WACOM_DTU_OFFSET, WACOM_DTU_OFFSET };
static const struct wacom_features wacom_features_0x360 =
{ "Wacom Intuos Pro M", 44800, 29600, 8191, 63,
- INTUOSP2_BT, WACOM_INTUOS_RES, WACOM_INTUOS_RES, 9, .touch_max = 10 };
+ INTUOSP2_BT, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES, 9, .touch_max = 10 };
static const struct wacom_features wacom_features_0x361 =
{ "Wacom Intuos Pro L", 62200, 43200, 8191, 63,
- INTUOSP2_BT, WACOM_INTUOS_RES, WACOM_INTUOS_RES, 9, .touch_max = 10 };
+ INTUOSP2_BT, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES, 9, .touch_max = 10 };
static const struct wacom_features wacom_features_HID_ANY_ID =
{ "Wacom HID", .type = HID_GENERIC, .oVid = HID_ANY_ID, .oPid = HID_ANY_ID };
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 81a80c8..321b883 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -502,12 +502,15 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
wait_for_completion(&info->waitevent);
- if (channel->rescind) {
- ret = -ENODEV;
- goto post_msg_err;
- }
-
post_msg_err:
+ /*
+ * If the channel has been rescinded;
+ * we will be awakened by the rescind
+ * handler; set the error code to zero so we don't leak memory.
+ */
+ if (channel->rescind)
+ ret = 0;
+
spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
list_del(&info->msglistentry);
spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
@@ -530,20 +533,18 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
int ret;
/*
- * vmbus_on_event(), running in the tasklet, can race
+ * vmbus_on_event(), running in the per-channel tasklet, can race
* with vmbus_close_internal() in the case of SMP guest, e.g., when
* the former is accessing channel->inbound.ring_buffer, the latter
- * could be freeing the ring_buffer pages.
- *
- * To resolve the race, we can serialize them by disabling the
- * tasklet when the latter is running here.
+ * could be freeing the ring_buffer pages, so here we must stop it
+ * first.
*/
- hv_event_tasklet_disable(channel);
+ tasklet_disable(&channel->callback_event);
/*
* In case a device driver's probe() fails (e.g.,
* util_probe() -> vmbus_open() returns -ENOMEM) and the device is
- * rescinded later (e.g., we dynamically disble an Integrated Service
+ * rescinded later (e.g., we dynamically disable an Integrated Service
* in Hyper-V Manager), the driver's remove() invokes vmbus_close():
* here we should skip most of the below cleanup work.
*/
@@ -605,8 +606,6 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
get_order(channel->ringbuffer_pagecount * PAGE_SIZE));
out:
- hv_event_tasklet_enable(channel);
-
return ret;
}
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index f33465d..fbcb063 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -350,7 +350,8 @@ static struct vmbus_channel *alloc_channel(void)
static void free_channel(struct vmbus_channel *channel)
{
tasklet_kill(&channel->callback_event);
- kfree(channel);
+
+ kfree_rcu(channel, rcu);
}
static void percpu_channel_enq(void *arg)
@@ -359,14 +360,14 @@ static void percpu_channel_enq(void *arg)
struct hv_per_cpu_context *hv_cpu
= this_cpu_ptr(hv_context.cpu_context);
- list_add_tail(&channel->percpu_list, &hv_cpu->chan_list);
+ list_add_tail_rcu(&channel->percpu_list, &hv_cpu->chan_list);
}
static void percpu_channel_deq(void *arg)
{
struct vmbus_channel *channel = arg;
- list_del(&channel->percpu_list);
+ list_del_rcu(&channel->percpu_list);
}
@@ -381,19 +382,6 @@ static void vmbus_release_relid(u32 relid)
true);
}
-void hv_event_tasklet_disable(struct vmbus_channel *channel)
-{
- tasklet_disable(&channel->callback_event);
-}
-
-void hv_event_tasklet_enable(struct vmbus_channel *channel)
-{
- tasklet_enable(&channel->callback_event);
-
- /* In case there is any pending event */
- tasklet_schedule(&channel->callback_event);
-}
-
void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
{
unsigned long flags;
@@ -402,7 +390,6 @@ void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
BUG_ON(!channel->rescind);
BUG_ON(!mutex_is_locked(&vmbus_connection.channel_mutex));
- hv_event_tasklet_disable(channel);
if (channel->target_cpu != get_cpu()) {
put_cpu();
smp_call_function_single(channel->target_cpu,
@@ -411,7 +398,6 @@ void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
percpu_channel_deq(channel);
put_cpu();
}
- hv_event_tasklet_enable(channel);
if (channel->primary_channel == NULL) {
list_del(&channel->listentry);
@@ -505,7 +491,6 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
init_vp_index(newchannel, dev_type);
- hv_event_tasklet_disable(newchannel);
if (newchannel->target_cpu != get_cpu()) {
put_cpu();
smp_call_function_single(newchannel->target_cpu,
@@ -515,7 +500,6 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
percpu_channel_enq(newchannel);
put_cpu();
}
- hv_event_tasklet_enable(newchannel);
/*
* This state is used to indicate a successful open
@@ -565,7 +549,6 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
list_del(&newchannel->listentry);
mutex_unlock(&vmbus_connection.channel_mutex);
- hv_event_tasklet_disable(newchannel);
if (newchannel->target_cpu != get_cpu()) {
put_cpu();
smp_call_function_single(newchannel->target_cpu,
@@ -574,7 +557,6 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
percpu_channel_deq(newchannel);
put_cpu();
}
- hv_event_tasklet_enable(newchannel);
vmbus_release_relid(newchannel->offermsg.child_relid);
@@ -814,6 +796,7 @@ static void vmbus_onoffer(struct vmbus_channel_message_header *hdr)
/* Allocate the channel object and save this offer. */
newchannel = alloc_channel();
if (!newchannel) {
+ vmbus_release_relid(offer->child_relid);
pr_err("Unable to allocate channel object\n");
return;
}
diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c
index 9aee601..a5596a6 100644
--- a/drivers/hv/hv_fcopy.c
+++ b/drivers/hv/hv_fcopy.c
@@ -71,7 +71,6 @@ static DECLARE_WORK(fcopy_send_work, fcopy_send_data);
static const char fcopy_devname[] = "vmbus/hv_fcopy";
static u8 *recv_buffer;
static struct hvutil_transport *hvt;
-static struct completion release_event;
/*
* This state maintains the version number registered by the daemon.
*/
@@ -331,7 +330,6 @@ static void fcopy_on_reset(void)
if (cancel_delayed_work_sync(&fcopy_timeout_work))
fcopy_respond_to_host(HV_E_FAIL);
- complete(&release_event);
}
int hv_fcopy_init(struct hv_util_service *srv)
@@ -339,7 +337,6 @@ int hv_fcopy_init(struct hv_util_service *srv)
recv_buffer = srv->recv_buffer;
fcopy_transaction.recv_channel = srv->channel;
- init_completion(&release_event);
/*
* When this driver loads, the user level daemon that
* processes the host requests may not yet be running.
@@ -361,5 +358,4 @@ void hv_fcopy_deinit(void)
fcopy_transaction.state = HVUTIL_DEVICE_DYING;
cancel_delayed_work_sync(&fcopy_timeout_work);
hvutil_transport_destroy(hvt);
- wait_for_completion(&release_event);
}
diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c
index de26371..a1adfe2 100644
--- a/drivers/hv/hv_kvp.c
+++ b/drivers/hv/hv_kvp.c
@@ -101,7 +101,6 @@ static DECLARE_WORK(kvp_sendkey_work, kvp_send_key);
static const char kvp_devname[] = "vmbus/hv_kvp";
static u8 *recv_buffer;
static struct hvutil_transport *hvt;
-static struct completion release_event;
/*
* Register the kernel component with the user-level daemon.
* As part of this registration, pass the LIC version number.
@@ -714,7 +713,6 @@ static void kvp_on_reset(void)
if (cancel_delayed_work_sync(&kvp_timeout_work))
kvp_respond_to_host(NULL, HV_E_FAIL);
kvp_transaction.state = HVUTIL_DEVICE_INIT;
- complete(&release_event);
}
int
@@ -723,7 +721,6 @@ hv_kvp_init(struct hv_util_service *srv)
recv_buffer = srv->recv_buffer;
kvp_transaction.recv_channel = srv->channel;
- init_completion(&release_event);
/*
* When this driver loads, the user level daemon that
* processes the host requests may not yet be running.
@@ -747,5 +744,4 @@ void hv_kvp_deinit(void)
cancel_delayed_work_sync(&kvp_timeout_work);
cancel_work_sync(&kvp_sendkey_work);
hvutil_transport_destroy(hvt);
- wait_for_completion(&release_event);
}
diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c
index bcc03f0..e659d1b 100644
--- a/drivers/hv/hv_snapshot.c
+++ b/drivers/hv/hv_snapshot.c
@@ -79,7 +79,6 @@ static int dm_reg_value;
static const char vss_devname[] = "vmbus/hv_vss";
static __u8 *recv_buffer;
static struct hvutil_transport *hvt;
-static struct completion release_event;
static void vss_timeout_func(struct work_struct *dummy);
static void vss_handle_request(struct work_struct *dummy);
@@ -361,13 +360,11 @@ static void vss_on_reset(void)
if (cancel_delayed_work_sync(&vss_timeout_work))
vss_respond_to_host(HV_E_FAIL);
vss_transaction.state = HVUTIL_DEVICE_INIT;
- complete(&release_event);
}
int
hv_vss_init(struct hv_util_service *srv)
{
- init_completion(&release_event);
if (vmbus_proto_version < VERSION_WIN8_1) {
pr_warn("Integration service 'Backup (volume snapshot)'"
" not supported on this host version.\n");
@@ -400,5 +397,4 @@ void hv_vss_deinit(void)
cancel_delayed_work_sync(&vss_timeout_work);
cancel_work_sync(&vss_handle_request_work);
hvutil_transport_destroy(hvt);
- wait_for_completion(&release_event);
}
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index 3042eaa..186b100 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -590,6 +590,8 @@ static int hv_timesync_init(struct hv_util_service *srv)
if (!hyperv_cs)
return -ENODEV;
+ spin_lock_init(&host_ts.lock);
+
INIT_WORK(&wrk.work, hv_set_host_time);
/*
diff --git a/drivers/hv/hv_utils_transport.c b/drivers/hv/hv_utils_transport.c
index c235a95..4402a71 100644
--- a/drivers/hv/hv_utils_transport.c
+++ b/drivers/hv/hv_utils_transport.c
@@ -182,10 +182,11 @@ static int hvt_op_release(struct inode *inode, struct file *file)
* connects back.
*/
hvt_reset(hvt);
- mutex_unlock(&hvt->lock);
if (mode_old == HVUTIL_TRANSPORT_DESTROY)
- hvt_transport_free(hvt);
+ complete(&hvt->release);
+
+ mutex_unlock(&hvt->lock);
return 0;
}
@@ -304,6 +305,7 @@ struct hvutil_transport *hvutil_transport_init(const char *name,
init_waitqueue_head(&hvt->outmsg_q);
mutex_init(&hvt->lock);
+ init_completion(&hvt->release);
spin_lock(&hvt_list_lock);
list_add(&hvt->list, &hvt_list);
@@ -351,6 +353,8 @@ void hvutil_transport_destroy(struct hvutil_transport *hvt)
if (hvt->cn_id.idx > 0 && hvt->cn_id.val > 0)
cn_del_callback(&hvt->cn_id);
- if (mode_old != HVUTIL_TRANSPORT_CHARDEV)
- hvt_transport_free(hvt);
+ if (mode_old == HVUTIL_TRANSPORT_CHARDEV)
+ wait_for_completion(&hvt->release);
+
+ hvt_transport_free(hvt);
}
diff --git a/drivers/hv/hv_utils_transport.h b/drivers/hv/hv_utils_transport.h
index d98f522..79afb62 100644
--- a/drivers/hv/hv_utils_transport.h
+++ b/drivers/hv/hv_utils_transport.h
@@ -41,6 +41,7 @@ struct hvutil_transport {
int outmsg_len; /* its length */
wait_queue_head_t outmsg_q; /* poll/read wait queue */
struct mutex lock; /* protects struct members */
+ struct completion release; /* synchronize with fd release */
};
struct hvutil_transport *hvutil_transport_init(const char *name,
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index da6b59b..8370b9dc 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -939,8 +939,10 @@ static void vmbus_chan_sched(struct hv_per_cpu_context *hv_cpu)
if (relid == 0)
continue;
+ rcu_read_lock();
+
/* Find channel based on relid */
- list_for_each_entry(channel, &hv_cpu->chan_list, percpu_list) {
+ list_for_each_entry_rcu(channel, &hv_cpu->chan_list, percpu_list) {
if (channel->offermsg.child_relid != relid)
continue;
@@ -956,6 +958,8 @@ static void vmbus_chan_sched(struct hv_per_cpu_context *hv_cpu)
tasklet_schedule(&channel->callback_event);
}
}
+
+ rcu_read_unlock();
}
}
diff --git a/drivers/hwmon/asus_atk0110.c b/drivers/hwmon/asus_atk0110.c
index cccef87..975c43d 100644
--- a/drivers/hwmon/asus_atk0110.c
+++ b/drivers/hwmon/asus_atk0110.c
@@ -646,6 +646,9 @@ static int atk_read_value(struct atk_sensor_data *sensor, u64 *value)
else
err = atk_read_value_new(sensor, value);
+ if (err)
+ return err;
+
sensor->is_valid = true;
sensor->last_updated = jiffies;
sensor->cached_value = *value;
diff --git a/drivers/hwmon/it87.c b/drivers/hwmon/it87.c
index efb01c2..4dfc723 100644
--- a/drivers/hwmon/it87.c
+++ b/drivers/hwmon/it87.c
@@ -3198,7 +3198,7 @@ static int __init sm_it87_init(void)
{
int sioaddr[2] = { REG_2E, REG_4E };
struct it87_sio_data sio_data;
- unsigned short isa_address;
+ unsigned short isa_address[2];
bool found = false;
int i, err;
@@ -3208,15 +3208,29 @@ static int __init sm_it87_init(void)
for (i = 0; i < ARRAY_SIZE(sioaddr); i++) {
memset(&sio_data, 0, sizeof(struct it87_sio_data));
- isa_address = 0;
- err = it87_find(sioaddr[i], &isa_address, &sio_data);
- if (err || isa_address == 0)
+ isa_address[i] = 0;
+ err = it87_find(sioaddr[i], &isa_address[i], &sio_data);
+ if (err || isa_address[i] == 0)
continue;
+ /*
+ * Don't register second chip if its ISA address matches
+ * the first chip's ISA address.
+ */
+ if (i && isa_address[i] == isa_address[0])
+ break;
- err = it87_device_add(i, isa_address, &sio_data);
+ err = it87_device_add(i, isa_address[i], &sio_data);
if (err)
goto exit_dev_unregister;
+
found = true;
+
+ /*
+ * IT8705F may respond on both SIO addresses.
+ * Stop probing after finding one.
+ */
+ if (sio_data.type == it87)
+ break;
}
if (!found) {
diff --git a/drivers/hwmon/max31790.c b/drivers/hwmon/max31790.c
index c1b9275..281491c 100644
--- a/drivers/hwmon/max31790.c
+++ b/drivers/hwmon/max31790.c
@@ -311,7 +311,7 @@ static int max31790_write_pwm(struct device *dev, u32 attr, int channel,
data->pwm[channel] = val << 8;
err = i2c_smbus_write_word_swapped(client,
MAX31790_REG_PWMOUT(channel),
- val);
+ data->pwm[channel]);
break;
case hwmon_pwm_enable:
fan_config = data->fan_config[channel];
diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c
index cdd9b3b..7563ece 100644
--- a/drivers/hwtracing/intel_th/core.c
+++ b/drivers/hwtracing/intel_th/core.c
@@ -221,8 +221,10 @@ static int intel_th_output_activate(struct intel_th_device *thdev)
else
intel_th_trace_enable(thdev);
- if (ret)
+ if (ret) {
pm_runtime_put(&thdev->dev);
+ module_put(thdrv->driver.owner);
+ }
return ret;
}
diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index 0bba384..590cf90 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -85,6 +85,16 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa2a6),
.driver_data = (kernel_ulong_t)0,
},
+ {
+ /* Denverton */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x19e1),
+ .driver_data = (kernel_ulong_t)0,
+ },
+ {
+ /* Gemini Lake */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x318e),
+ .driver_data = (kernel_ulong_t)0,
+ },
{ 0 },
};
diff --git a/drivers/i2c/busses/i2c-brcmstb.c b/drivers/i2c/busses/i2c-brcmstb.c
index 0652281..78792b4 100644
--- a/drivers/i2c/busses/i2c-brcmstb.c
+++ b/drivers/i2c/busses/i2c-brcmstb.c
@@ -465,6 +465,7 @@ static int brcmstb_i2c_xfer(struct i2c_adapter *adapter,
u8 *tmp_buf;
int len = 0;
int xfersz = brcmstb_i2c_get_xfersz(dev);
+ u32 cond, cond_per_msg;
if (dev->is_suspended)
return -EBUSY;
@@ -481,10 +482,11 @@ static int brcmstb_i2c_xfer(struct i2c_adapter *adapter,
pmsg->buf ? pmsg->buf[0] : '0', pmsg->len);
if (i < (num - 1) && (msgs[i + 1].flags & I2C_M_NOSTART))
- brcmstb_set_i2c_start_stop(dev, ~(COND_START_STOP));
+ cond = ~COND_START_STOP;
else
- brcmstb_set_i2c_start_stop(dev,
- COND_RESTART | COND_NOSTOP);
+ cond = COND_RESTART | COND_NOSTOP;
+
+ brcmstb_set_i2c_start_stop(dev, cond);
/* Send slave address */
if (!(pmsg->flags & I2C_M_NOSTART)) {
@@ -497,13 +499,24 @@ static int brcmstb_i2c_xfer(struct i2c_adapter *adapter,
}
}
+ cond_per_msg = cond;
+
/* Perform data transfer */
while (len) {
bytes_to_xfer = min(len, xfersz);
- if (len <= xfersz && i == (num - 1))
- brcmstb_set_i2c_start_stop(dev,
- ~(COND_START_STOP));
+ if (len <= xfersz) {
+ if (i == (num - 1))
+ cond_per_msg = cond_per_msg &
+ ~(COND_RESTART | COND_NOSTOP);
+ else
+ cond_per_msg = cond;
+ } else {
+ cond_per_msg = (cond_per_msg & ~COND_RESTART) |
+ COND_NOSTOP;
+ }
+
+ brcmstb_set_i2c_start_stop(dev, cond_per_msg);
rc = brcmstb_i2c_xfer_bsc_data(dev, tmp_buf,
bytes_to_xfer, pmsg);
@@ -512,6 +525,8 @@ static int brcmstb_i2c_xfer(struct i2c_adapter *adapter,
len -= bytes_to_xfer;
tmp_buf += bytes_to_xfer;
+
+ cond_per_msg = COND_NOSTART | COND_NOSTOP;
}
}
diff --git a/drivers/i2c/busses/i2c-designware-core.h b/drivers/i2c/busses/i2c-designware-core.h
index c1db3a5..d9aaf17 100644
--- a/drivers/i2c/busses/i2c-designware-core.h
+++ b/drivers/i2c/busses/i2c-designware-core.h
@@ -88,6 +88,7 @@ struct dw_i2c_dev {
void __iomem *base;
struct completion cmd_complete;
struct clk *clk;
+ struct reset_control *rst;
u32 (*get_clk_rate_khz) (struct dw_i2c_dev *dev);
struct dw_pci_controller *controller;
int cmd_err;
diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c
index 6ce4313..79c4b4e 100644
--- a/drivers/i2c/busses/i2c-designware-platdrv.c
+++ b/drivers/i2c/busses/i2c-designware-platdrv.c
@@ -38,6 +38,7 @@
#include <linux/pm_runtime.h>
#include <linux/property.h>
#include <linux/io.h>
+#include <linux/reset.h>
#include <linux/slab.h>
#include <linux/acpi.h>
#include <linux/platform_data/i2c-designware.h>
@@ -199,6 +200,14 @@ static int dw_i2c_plat_probe(struct platform_device *pdev)
dev->irq = irq;
platform_set_drvdata(pdev, dev);
+ dev->rst = devm_reset_control_get_optional_exclusive(&pdev->dev, NULL);
+ if (IS_ERR(dev->rst)) {
+ if (PTR_ERR(dev->rst) == -EPROBE_DEFER)
+ return -EPROBE_DEFER;
+ } else {
+ reset_control_deassert(dev->rst);
+ }
+
if (pdata) {
dev->clk_freq = pdata->i2c_scl_freq;
} else {
@@ -235,12 +244,13 @@ static int dw_i2c_plat_probe(struct platform_device *pdev)
&& dev->clk_freq != 1000000 && dev->clk_freq != 3400000) {
dev_err(&pdev->dev,
"Only 100kHz, 400kHz, 1MHz and 3.4MHz supported");
- return -EINVAL;
+ r = -EINVAL;
+ goto exit_reset;
}
r = i2c_dw_eval_lock_support(dev);
if (r)
- return r;
+ goto exit_reset;
dev->functionality = I2C_FUNC_10BIT_ADDR | DW_IC_DEFAULT_FUNCTIONALITY;
@@ -286,10 +296,18 @@ static int dw_i2c_plat_probe(struct platform_device *pdev)
}
r = i2c_dw_probe(dev);
- if (r && !dev->pm_runtime_disabled)
- pm_runtime_disable(&pdev->dev);
+ if (r)
+ goto exit_probe;
return r;
+
+exit_probe:
+ if (!dev->pm_runtime_disabled)
+ pm_runtime_disable(&pdev->dev);
+exit_reset:
+ if (!IS_ERR_OR_NULL(dev->rst))
+ reset_control_assert(dev->rst);
+ return r;
}
static int dw_i2c_plat_remove(struct platform_device *pdev)
@@ -306,6 +324,8 @@ static int dw_i2c_plat_remove(struct platform_device *pdev)
pm_runtime_put_sync(&pdev->dev);
if (!dev->pm_runtime_disabled)
pm_runtime_disable(&pdev->dev);
+ if (!IS_ERR_OR_NULL(dev->rst))
+ reset_control_assert(dev->rst);
return 0;
}
diff --git a/drivers/i2c/busses/i2c-exynos5.c b/drivers/i2c/busses/i2c-exynos5.c
index cbd93ce..736a824 100644
--- a/drivers/i2c/busses/i2c-exynos5.c
+++ b/drivers/i2c/busses/i2c-exynos5.c
@@ -457,7 +457,6 @@ static irqreturn_t exynos5_i2c_irq(int irqno, void *dev_id)
int_status = readl(i2c->regs + HSI2C_INT_STATUS);
writel(int_status, i2c->regs + HSI2C_INT_STATUS);
- trans_status = readl(i2c->regs + HSI2C_TRANS_STATUS);
/* handle interrupt related to the transfer status */
if (i2c->variant->hw == HSI2C_EXYNOS7) {
@@ -482,11 +481,13 @@ static irqreturn_t exynos5_i2c_irq(int irqno, void *dev_id)
goto stop;
}
+ trans_status = readl(i2c->regs + HSI2C_TRANS_STATUS);
if ((trans_status & HSI2C_MASTER_ST_MASK) == HSI2C_MASTER_ST_LOSE) {
i2c->state = -EAGAIN;
goto stop;
}
} else if (int_status & HSI2C_INT_I2C) {
+ trans_status = readl(i2c->regs + HSI2C_TRANS_STATUS);
if (trans_status & HSI2C_NO_DEV_ACK) {
dev_dbg(i2c->dev, "No ACK from device\n");
i2c->state = -ENXIO;
diff --git a/drivers/i2c/busses/i2c-meson.c b/drivers/i2c/busses/i2c-meson.c
index 2aa61bb..73b97c7 100644
--- a/drivers/i2c/busses/i2c-meson.c
+++ b/drivers/i2c/busses/i2c-meson.c
@@ -175,7 +175,7 @@ static void meson_i2c_put_data(struct meson_i2c *i2c, char *buf, int len)
wdata1 |= *buf++ << ((i - 4) * 8);
writel(wdata0, i2c->regs + REG_TOK_WDATA0);
- writel(wdata0, i2c->regs + REG_TOK_WDATA1);
+ writel(wdata1, i2c->regs + REG_TOK_WDATA1);
dev_dbg(i2c->dev, "%s: data %08x %08x len %d\n", __func__,
wdata0, wdata1, len);
diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c
index 4a7d9bc..45d6171 100644
--- a/drivers/i2c/busses/i2c-mt65xx.c
+++ b/drivers/i2c/busses/i2c-mt65xx.c
@@ -172,14 +172,6 @@ static const struct i2c_adapter_quirks mt6577_i2c_quirks = {
.max_comb_2nd_msg_len = 31,
};
-static const struct i2c_adapter_quirks mt8173_i2c_quirks = {
- .max_num_msgs = 65535,
- .max_write_len = 65535,
- .max_read_len = 65535,
- .max_comb_1st_msg_len = 65535,
- .max_comb_2nd_msg_len = 65535,
-};
-
static const struct mtk_i2c_compatible mt6577_compat = {
.quirks = &mt6577_i2c_quirks,
.pmic_i2c = 0,
@@ -199,7 +191,6 @@ static const struct mtk_i2c_compatible mt6589_compat = {
};
static const struct mtk_i2c_compatible mt8173_compat = {
- .quirks = &mt8173_i2c_quirks,
.pmic_i2c = 0,
.dcm = 1,
.auto_restart = 1,
diff --git a/drivers/i2c/busses/i2c-riic.c b/drivers/i2c/busses/i2c-riic.c
index 8f11d34..c811af4c 100644
--- a/drivers/i2c/busses/i2c-riic.c
+++ b/drivers/i2c/busses/i2c-riic.c
@@ -218,8 +218,12 @@ static irqreturn_t riic_tend_isr(int irq, void *data)
}
if (riic->is_last || riic->err) {
- riic_clear_set_bit(riic, 0, ICIER_SPIE, RIIC_ICIER);
+ riic_clear_set_bit(riic, ICIER_TEIE, ICIER_SPIE, RIIC_ICIER);
writeb(ICCR2_SP, riic->base + RIIC_ICCR2);
+ } else {
+ /* Transfer is complete, but do not send STOP */
+ riic_clear_set_bit(riic, ICIER_TEIE, 0, RIIC_ICIER);
+ complete(&riic->msg_done);
}
return IRQ_HANDLED;
diff --git a/drivers/i2c/i2c-mux.c b/drivers/i2c/i2c-mux.c
index 83768e8..2178266 100644
--- a/drivers/i2c/i2c-mux.c
+++ b/drivers/i2c/i2c-mux.c
@@ -429,6 +429,7 @@ void i2c_mux_del_adapters(struct i2c_mux_core *muxc)
while (muxc->num_adapters) {
struct i2c_adapter *adap = muxc->adapter[--muxc->num_adapters];
struct i2c_mux_priv *priv = adap->algo_data;
+ struct device_node *np = adap->dev.of_node;
muxc->adapter[muxc->num_adapters] = NULL;
@@ -438,6 +439,7 @@ void i2c_mux_del_adapters(struct i2c_mux_core *muxc)
sysfs_remove_link(&priv->adap.dev.kobj, "mux_device");
i2c_del_adapter(adap);
+ of_node_put(np);
kfree(priv);
}
}
diff --git a/drivers/i2c/muxes/i2c-mux-pca954x.c b/drivers/i2c/muxes/i2c-mux-pca954x.c
index dfc1c0e..ad31d21 100644
--- a/drivers/i2c/muxes/i2c-mux-pca954x.c
+++ b/drivers/i2c/muxes/i2c-mux-pca954x.c
@@ -35,7 +35,6 @@
* warranty of any kind, whether express or implied.
*/
-#include <linux/acpi.h>
#include <linux/device.h>
#include <linux/gpio/consumer.h>
#include <linux/i2c.h>
@@ -117,6 +116,10 @@ static const struct chip_desc chips[] = {
.has_irq = 1,
.muxtype = pca954x_isswi,
},
+ [pca_9546] = {
+ .nchans = 4,
+ .muxtype = pca954x_isswi,
+ },
[pca_9547] = {
.nchans = 8,
.enable = 0x8,
@@ -134,28 +137,13 @@ static const struct i2c_device_id pca954x_id[] = {
{ "pca9543", pca_9543 },
{ "pca9544", pca_9544 },
{ "pca9545", pca_9545 },
- { "pca9546", pca_9545 },
+ { "pca9546", pca_9546 },
{ "pca9547", pca_9547 },
{ "pca9548", pca_9548 },
{ }
};
MODULE_DEVICE_TABLE(i2c, pca954x_id);
-#ifdef CONFIG_ACPI
-static const struct acpi_device_id pca954x_acpi_ids[] = {
- { .id = "PCA9540", .driver_data = pca_9540 },
- { .id = "PCA9542", .driver_data = pca_9542 },
- { .id = "PCA9543", .driver_data = pca_9543 },
- { .id = "PCA9544", .driver_data = pca_9544 },
- { .id = "PCA9545", .driver_data = pca_9545 },
- { .id = "PCA9546", .driver_data = pca_9545 },
- { .id = "PCA9547", .driver_data = pca_9547 },
- { .id = "PCA9548", .driver_data = pca_9548 },
- { }
-};
-MODULE_DEVICE_TABLE(acpi, pca954x_acpi_ids);
-#endif
-
#ifdef CONFIG_OF
static const struct of_device_id pca954x_of_match[] = {
{ .compatible = "nxp,pca9540", .data = &chips[pca_9540] },
@@ -393,17 +381,8 @@ static int pca954x_probe(struct i2c_client *client,
match = of_match_device(of_match_ptr(pca954x_of_match), &client->dev);
if (match)
data->chip = of_device_get_match_data(&client->dev);
- else if (id)
+ else
data->chip = &chips[id->driver_data];
- else {
- const struct acpi_device_id *acpi_id;
-
- acpi_id = acpi_match_device(ACPI_PTR(pca954x_acpi_ids),
- &client->dev);
- if (!acpi_id)
- return -ENODEV;
- data->chip = &chips[acpi_id->driver_data];
- }
data->last_chan = 0; /* force the first selection */
@@ -492,7 +471,6 @@ static struct i2c_driver pca954x_driver = {
.name = "pca954x",
.pm = &pca954x_pm,
.of_match_table = of_match_ptr(pca954x_of_match),
- .acpi_match_table = ACPI_PTR(pca954x_acpi_ids),
},
.probe = pca954x_probe,
.remove = pca954x_remove,
diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c
index ad9dec3..4282cec 100644
--- a/drivers/iio/adc/ti_am335x_adc.c
+++ b/drivers/iio/adc/ti_am335x_adc.c
@@ -169,7 +169,9 @@ static irqreturn_t tiadc_irq_h(int irq, void *private)
{
struct iio_dev *indio_dev = private;
struct tiadc_device *adc_dev = iio_priv(indio_dev);
- unsigned int status, config;
+ unsigned int status, config, adc_fsm;
+ unsigned short count = 0;
+
status = tiadc_readl(adc_dev, REG_IRQSTATUS);
/*
@@ -183,6 +185,15 @@ static irqreturn_t tiadc_irq_h(int irq, void *private)
tiadc_writel(adc_dev, REG_CTRL, config);
tiadc_writel(adc_dev, REG_IRQSTATUS, IRQENB_FIFO1OVRRUN
| IRQENB_FIFO1UNDRFLW | IRQENB_FIFO1THRES);
+
+ /* wait for idle state.
+ * ADC needs to finish the current conversion
+ * before disabling the module
+ */
+ do {
+ adc_fsm = tiadc_readl(adc_dev, REG_ADCFSM);
+ } while (adc_fsm != 0x10 && count++ < 100);
+
tiadc_writel(adc_dev, REG_CTRL, (config | CNTRLREG_TSCSSENB));
return IRQ_HANDLED;
} else if (status & IRQENB_FIFO1THRES) {
diff --git a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
index a3cce3a..ecf592d 100644
--- a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
+++ b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
@@ -51,8 +51,6 @@ static int _hid_sensor_power_state(struct hid_sensor_common *st, bool state)
st->report_state.report_id,
st->report_state.index,
HID_USAGE_SENSOR_PROP_REPORTING_STATE_ALL_EVENTS_ENUM);
-
- poll_value = hid_sensor_read_poll_value(st);
} else {
int val;
@@ -89,7 +87,9 @@ static int _hid_sensor_power_state(struct hid_sensor_common *st, bool state)
sensor_hub_get_feature(st->hsdev, st->power_state.report_id,
st->power_state.index,
sizeof(state_val), &state_val);
- if (state && poll_value)
+ if (state)
+ poll_value = hid_sensor_read_poll_value(st);
+ if (poll_value > 0)
msleep_interruptible(poll_value * 2);
return 0;
diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
index 78532ce..81b572d 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
@@ -193,8 +193,8 @@ int st_lsm6dsx_update_watermark(struct st_lsm6dsx_sensor *sensor, u16 watermark)
if (err < 0)
goto out;
- fifo_watermark = ((data & ~ST_LSM6DSX_FIFO_TH_MASK) << 8) |
- (fifo_watermark & ST_LSM6DSX_FIFO_TH_MASK);
+ fifo_watermark = ((data << 8) & ~ST_LSM6DSX_FIFO_TH_MASK) |
+ (fifo_watermark & ST_LSM6DSX_FIFO_TH_MASK);
wdata = cpu_to_le16(fifo_watermark);
err = hw->tf->write(hw->dev, ST_LSM6DSX_REG_FIFO_THL_ADDR,
diff --git a/drivers/iio/magnetometer/ak8974.c b/drivers/iio/magnetometer/ak8974.c
index 6dd8cbd..e13370d 100644
--- a/drivers/iio/magnetometer/ak8974.c
+++ b/drivers/iio/magnetometer/ak8974.c
@@ -763,7 +763,7 @@ static int ak8974_probe(struct i2c_client *i2c,
return ret;
}
-static int __exit ak8974_remove(struct i2c_client *i2c)
+static int ak8974_remove(struct i2c_client *i2c)
{
struct iio_dev *indio_dev = i2c_get_clientdata(i2c);
struct ak8974 *ak8974 = iio_priv(indio_dev);
@@ -845,7 +845,7 @@ static struct i2c_driver ak8974_driver = {
.of_match_table = of_match_ptr(ak8974_of_match),
},
.probe = ak8974_probe,
- .remove = __exit_p(ak8974_remove),
+ .remove = ak8974_remove,
.id_table = ak8974_id,
};
module_i2c_driver(ak8974_driver);
diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c
index e955101..f2ae75f 100644
--- a/drivers/infiniband/core/cq.c
+++ b/drivers/infiniband/core/cq.c
@@ -29,7 +29,13 @@ static int __ib_process_cq(struct ib_cq *cq, int budget)
{
int i, n, completed = 0;
- while ((n = ib_poll_cq(cq, IB_POLL_BATCH, cq->wc)) > 0) {
+ /*
+ * budget might be (-1) if the caller does not
+ * want to bound this call, thus we need unsigned
+ * minimum here.
+ */
+ while ((n = ib_poll_cq(cq, min_t(u32, IB_POLL_BATCH,
+ budget - completed), cq->wc)) > 0) {
for (i = 0; i < n; i++) {
struct ib_wc *wc = &cq->wc[i];
@@ -196,7 +202,7 @@ void ib_free_cq(struct ib_cq *cq)
irq_poll_disable(&cq->iop);
break;
case IB_POLL_WORKQUEUE:
- flush_work(&cq->work);
+ cancel_work_sync(&cq->work);
break;
default:
WARN_ON_ONCE(1);
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 593d2ce..7c9e34d 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -336,12 +336,26 @@ int ib_register_device(struct ib_device *device,
struct device *parent = device->dev.parent;
WARN_ON_ONCE(!parent);
- if (!device->dev.dma_ops)
- device->dev.dma_ops = parent->dma_ops;
- if (!device->dev.dma_mask)
- device->dev.dma_mask = parent->dma_mask;
- if (!device->dev.coherent_dma_mask)
- device->dev.coherent_dma_mask = parent->coherent_dma_mask;
+ WARN_ON_ONCE(device->dma_device);
+ if (device->dev.dma_ops) {
+ /*
+ * The caller provided custom DMA operations. Copy the
+ * DMA-related fields that are used by e.g. dma_alloc_coherent()
+ * into device->dev.
+ */
+ device->dma_device = &device->dev;
+ if (!device->dev.dma_mask)
+ device->dev.dma_mask = parent->dma_mask;
+ if (!device->dev.coherent_dma_mask)
+ device->dev.coherent_dma_mask =
+ parent->coherent_dma_mask;
+ } else {
+ /*
+ * The caller did not provide custom DMA operations. Use the
+ * DMA mapping operations of the parent device.
+ */
+ device->dma_device = parent;
+ }
mutex_lock(&device_mutex);
@@ -1015,8 +1029,7 @@ static int __init ib_core_init(void)
return -ENOMEM;
ib_comp_wq = alloc_workqueue("ib-comp-wq",
- WQ_UNBOUND | WQ_HIGHPRI | WQ_MEM_RECLAIM,
- WQ_UNBOUND_MAX_ACTIVE);
+ WQ_HIGHPRI | WQ_MEM_RECLAIM | WQ_SYSFS, 0);
if (!ib_comp_wq) {
ret = -ENOMEM;
goto err;
diff --git a/drivers/infiniband/hw/i40iw/i40iw_utils.c b/drivers/infiniband/hw/i40iw/i40iw_utils.c
index 0f5d43d..70c3e9e 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_utils.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_utils.c
@@ -160,6 +160,9 @@ int i40iw_inetaddr_event(struct notifier_block *notifier,
return NOTIFY_DONE;
iwdev = &hdl->device;
+ if (iwdev->init_state < INET_NOTIFIER)
+ return NOTIFY_DONE;
+
netdev = iwdev->ldev->netdev;
upper_dev = netdev_master_upper_dev_get(netdev);
if (netdev != event_netdev)
@@ -214,6 +217,9 @@ int i40iw_inet6addr_event(struct notifier_block *notifier,
return NOTIFY_DONE;
iwdev = &hdl->device;
+ if (iwdev->init_state < INET_NOTIFIER)
+ return NOTIFY_DONE;
+
netdev = iwdev->ldev->netdev;
if (netdev != event_netdev)
return NOTIFY_DONE;
@@ -260,6 +266,8 @@ int i40iw_net_event(struct notifier_block *notifier, unsigned long event, void *
if (!iwhdl)
return NOTIFY_DONE;
iwdev = &iwhdl->device;
+ if (iwdev->init_state < INET_NOTIFIER)
+ return NOTIFY_DONE;
p = (__be32 *)neigh->primary_key;
i40iw_copy_ip_ntohl(local_ipaddr, p);
if (neigh->nud_state & NUD_VALID) {
diff --git a/drivers/infiniband/hw/nes/nes.h b/drivers/infiniband/hw/nes/nes.h
index 85acd08..3f9e56e 100644
--- a/drivers/infiniband/hw/nes/nes.h
+++ b/drivers/infiniband/hw/nes/nes.h
@@ -36,6 +36,7 @@
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
+#include <linux/interrupt.h>
#include <linux/spinlock.h>
#include <linux/kernel.h>
#include <linux/delay.h>
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index bc9fb14..c52edea 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -372,7 +372,7 @@ static int _ocrdma_pd_mgr_put_bitmap(struct ocrdma_dev *dev, u16 pd_id,
return 0;
}
-static u8 ocrdma_put_pd_num(struct ocrdma_dev *dev, u16 pd_id,
+static int ocrdma_put_pd_num(struct ocrdma_dev *dev, u16 pd_id,
bool dpp_pool)
{
int status;
diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c
index b9b47e5..ced0461 100644
--- a/drivers/infiniband/hw/qedr/main.c
+++ b/drivers/infiniband/hw/qedr/main.c
@@ -587,9 +587,8 @@ void qedr_affiliated_event(void *context, u8 e_code, void *fw_handle)
#define EVENT_TYPE_CQ 1
#define EVENT_TYPE_QP 2
struct qedr_dev *dev = (struct qedr_dev *)context;
- union event_ring_data *data = fw_handle;
- u64 roce_handle64 = ((u64)data->roce_handle.hi << 32) +
- data->roce_handle.lo;
+ struct regpair *async_handle = (struct regpair *)fw_handle;
+ u64 roce_handle64 = ((u64) async_handle->hi << 32) + async_handle->lo;
u8 event_type = EVENT_TYPE_NOT_DEFINED;
struct ib_event event;
struct ib_cq *ibcq;
diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h
index bb32e47..5cb9195 100644
--- a/drivers/infiniband/hw/qedr/qedr.h
+++ b/drivers/infiniband/hw/qedr/qedr.h
@@ -38,7 +38,8 @@
#include <linux/qed/qed_chain.h>
#include <linux/qed/qed_roce_if.h>
#include <linux/qed/qede_roce.h>
-#include "qedr_hsi.h"
+#include <linux/qed/roce_common.h>
+#include "qedr_hsi_rdma.h"
#define QEDR_MODULE_VERSION "8.10.10.0"
#define QEDR_NODE_DESC "QLogic 579xx RoCE HCA"
diff --git a/drivers/infiniband/hw/qedr/qedr_cm.c b/drivers/infiniband/hw/qedr/qedr_cm.c
index 6996328..a6280ce 100644
--- a/drivers/infiniband/hw/qedr/qedr_cm.c
+++ b/drivers/infiniband/hw/qedr/qedr_cm.c
@@ -43,14 +43,11 @@
#include <rdma/ib_addr.h>
#include <rdma/ib_cache.h>
-#include "qedr_hsi.h"
#include <linux/qed/qed_if.h>
#include <linux/qed/qed_roce_if.h>
#include "qedr.h"
-#include "qedr_hsi.h"
#include "verbs.h"
#include <rdma/qedr-abi.h>
-#include "qedr_hsi.h"
#include "qedr_cm.h"
void qedr_inc_sw_gsi_cons(struct qedr_qp_hwq_info *info)
diff --git a/drivers/infiniband/hw/qedr/qedr_hsi.h b/drivers/infiniband/hw/qedr/qedr_hsi.h
deleted file mode 100644
index 66d2752..0000000
--- a/drivers/infiniband/hw/qedr/qedr_hsi.h
+++ /dev/null
@@ -1,56 +0,0 @@
-/* QLogic qedr NIC Driver
- * Copyright (c) 2015-2016 QLogic Corporation
- *
- * This software is available to you under a choice of one of two
- * licenses. You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- * Redistribution and use in source and binary forms, with or
- * without modification, are permitted provided that the following
- * conditions are met:
- *
- * - Redistributions of source code must retain the above
- * copyright notice, this list of conditions and the following
- * disclaimer.
- *
- * - Redistributions in binary form must reproduce the above
- * copyright notice, this list of conditions and the following
- * disclaimer in the documentation and /or other materials
- * provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-#ifndef __QED_HSI_ROCE__
-#define __QED_HSI_ROCE__
-
-#include <linux/qed/common_hsi.h>
-#include <linux/qed/roce_common.h>
-#include "qedr_hsi_rdma.h"
-
-/* Affiliated asynchronous events / errors enumeration */
-enum roce_async_events_type {
- ROCE_ASYNC_EVENT_NONE = 0,
- ROCE_ASYNC_EVENT_COMM_EST = 1,
- ROCE_ASYNC_EVENT_SQ_DRAINED,
- ROCE_ASYNC_EVENT_SRQ_LIMIT,
- ROCE_ASYNC_EVENT_LAST_WQE_REACHED,
- ROCE_ASYNC_EVENT_CQ_ERR,
- ROCE_ASYNC_EVENT_LOCAL_INVALID_REQUEST_ERR,
- ROCE_ASYNC_EVENT_LOCAL_CATASTROPHIC_ERR,
- ROCE_ASYNC_EVENT_LOCAL_ACCESS_ERR,
- ROCE_ASYNC_EVENT_QP_CATASTROPHIC_ERR,
- ROCE_ASYNC_EVENT_CQ_OVERFLOW_ERR,
- ROCE_ASYNC_EVENT_SRQ_EMPTY,
- MAX_ROCE_ASYNC_EVENTS_TYPE
-};
-
-#endif /* __QED_HSI_ROCE__ */
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 6b3bb32..2091902 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -43,7 +43,8 @@
#include <rdma/ib_addr.h>
#include <rdma/ib_cache.h>
-#include "qedr_hsi.h"
+#include <linux/qed/common_hsi.h>
+#include "qedr_hsi_rdma.h"
#include <linux/qed/qed_if.h>
#include "qedr.h"
#include "verbs.h"
diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c
index 12c4208..af9f596 100644
--- a/drivers/infiniband/hw/qib/qib_iba7322.c
+++ b/drivers/infiniband/hw/qib/qib_iba7322.c
@@ -7068,7 +7068,7 @@ static void qib_7322_txchk_change(struct qib_devdata *dd, u32 start,
unsigned long flags;
while (wait) {
- unsigned long shadow;
+ unsigned long shadow = 0;
int cstart, previ = -1;
/*
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
index 3cd96c1..9fbe22d 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
@@ -69,6 +69,9 @@
*/
#define PCI_DEVICE_ID_VMWARE_PVRDMA 0x0820
+#define PVRDMA_NUM_RING_PAGES 4
+#define PVRDMA_QP_NUM_HEADER_PAGES 1
+
struct pvrdma_dev;
struct pvrdma_page_dir {
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h
index e69d6f3..09078cc 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h
@@ -132,7 +132,7 @@ enum pvrdma_pci_resource {
enum pvrdma_device_ctl {
PVRDMA_DEVICE_CTL_ACTIVATE, /* Activate device. */
- PVRDMA_DEVICE_CTL_QUIESCE, /* Quiesce device. */
+ PVRDMA_DEVICE_CTL_UNQUIESCE, /* Unquiesce device. */
PVRDMA_DEVICE_CTL_RESET, /* Reset device. */
};
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
index 100bea5..34ebc76 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
@@ -56,7 +56,7 @@
#include "pvrdma.h"
#define DRV_NAME "vmw_pvrdma"
-#define DRV_VERSION "1.0.0.0-k"
+#define DRV_VERSION "1.0.1.0-k"
static DEFINE_MUTEX(pvrdma_device_list_lock);
static LIST_HEAD(pvrdma_device_list);
@@ -660,7 +660,16 @@ static void pvrdma_netdevice_event_handle(struct pvrdma_dev *dev,
pvrdma_dispatch_event(dev, 1, IB_EVENT_PORT_ERR);
break;
case NETDEV_UP:
- pvrdma_dispatch_event(dev, 1, IB_EVENT_PORT_ACTIVE);
+ pvrdma_write_reg(dev, PVRDMA_REG_CTL,
+ PVRDMA_DEVICE_CTL_UNQUIESCE);
+
+ mb();
+
+ if (pvrdma_read_reg(dev, PVRDMA_REG_ERR))
+ dev_err(&dev->pdev->dev,
+ "failed to activate device during link up\n");
+ else
+ pvrdma_dispatch_event(dev, 1, IB_EVENT_PORT_ACTIVE);
break;
default:
dev_dbg(&dev->pdev->dev, "ignore netdevice event %ld on %s\n",
@@ -858,7 +867,7 @@ static int pvrdma_pci_probe(struct pci_dev *pdev,
dev->dsr->resp_slot_dma = (u64)slot_dma;
/* Async event ring */
- dev->dsr->async_ring_pages.num_pages = 4;
+ dev->dsr->async_ring_pages.num_pages = PVRDMA_NUM_RING_PAGES;
ret = pvrdma_page_dir_init(dev, &dev->async_pdir,
dev->dsr->async_ring_pages.num_pages, true);
if (ret)
@@ -867,7 +876,7 @@ static int pvrdma_pci_probe(struct pci_dev *pdev,
dev->dsr->async_ring_pages.pdir_dma = dev->async_pdir.dir_dma;
/* CQ notification ring */
- dev->dsr->cq_ring_pages.num_pages = 4;
+ dev->dsr->cq_ring_pages.num_pages = PVRDMA_NUM_RING_PAGES;
ret = pvrdma_page_dir_init(dev, &dev->cq_pdir,
dev->dsr->cq_ring_pages.num_pages, true);
if (ret)
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
index dbbfd35..30062aa 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
@@ -170,8 +170,9 @@ static int pvrdma_set_sq_size(struct pvrdma_dev *dev, struct ib_qp_cap *req_cap,
sizeof(struct pvrdma_sge) *
qp->sq.max_sg);
/* Note: one extra page for the header. */
- qp->npages_send = 1 + (qp->sq.wqe_cnt * qp->sq.wqe_size +
- PAGE_SIZE - 1) / PAGE_SIZE;
+ qp->npages_send = PVRDMA_QP_NUM_HEADER_PAGES +
+ (qp->sq.wqe_cnt * qp->sq.wqe_size + PAGE_SIZE - 1) /
+ PAGE_SIZE;
return 0;
}
@@ -288,7 +289,7 @@ struct ib_qp *pvrdma_create_qp(struct ib_pd *pd,
qp->npages = qp->npages_send + qp->npages_recv;
/* Skip header page. */
- qp->sq.offset = PAGE_SIZE;
+ qp->sq.offset = PVRDMA_QP_NUM_HEADER_PAGES * PAGE_SIZE;
/* Recv queue pages are after send pages. */
qp->rq.offset = qp->npages_send * PAGE_SIZE;
@@ -341,7 +342,7 @@ struct ib_qp *pvrdma_create_qp(struct ib_pd *pd,
cmd->qp_type = ib_qp_type_to_pvrdma(init_attr->qp_type);
cmd->access_flags = IB_ACCESS_LOCAL_WRITE;
cmd->total_chunks = qp->npages;
- cmd->send_chunks = qp->npages_send - 1;
+ cmd->send_chunks = qp->npages_send - PVRDMA_QP_NUM_HEADER_PAGES;
cmd->pdir_dma = qp->pdir.dir_dma;
dev_dbg(&dev->pdev->dev, "create queuepair with %d, %d, %d, %d\n",
@@ -554,13 +555,13 @@ int pvrdma_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
return ret;
}
-static inline void *get_sq_wqe(struct pvrdma_qp *qp, int n)
+static inline void *get_sq_wqe(struct pvrdma_qp *qp, unsigned int n)
{
return pvrdma_page_dir_get_ptr(&qp->pdir,
qp->sq.offset + n * qp->sq.wqe_size);
}
-static inline void *get_rq_wqe(struct pvrdma_qp *qp, int n)
+static inline void *get_rq_wqe(struct pvrdma_qp *qp, unsigned int n)
{
return pvrdma_page_dir_get_ptr(&qp->pdir,
qp->rq.offset + n * qp->rq.wqe_size);
@@ -598,9 +599,7 @@ int pvrdma_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
unsigned long flags;
struct pvrdma_sq_wqe_hdr *wqe_hdr;
struct pvrdma_sge *sge;
- int i, index;
- int nreq;
- int ret;
+ int i, ret;
/*
* In states lower than RTS, we can fail immediately. In other states,
@@ -613,9 +612,8 @@ int pvrdma_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
spin_lock_irqsave(&qp->sq.lock, flags);
- index = pvrdma_idx(&qp->sq.ring->prod_tail, qp->sq.wqe_cnt);
- for (nreq = 0; wr; nreq++, wr = wr->next) {
- unsigned int tail;
+ while (wr) {
+ unsigned int tail = 0;
if (unlikely(!pvrdma_idx_ring_has_space(
qp->sq.ring, qp->sq.wqe_cnt, &tail))) {
@@ -680,7 +678,7 @@ int pvrdma_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
}
}
- wqe_hdr = (struct pvrdma_sq_wqe_hdr *)get_sq_wqe(qp, index);
+ wqe_hdr = (struct pvrdma_sq_wqe_hdr *)get_sq_wqe(qp, tail);
memset(wqe_hdr, 0, sizeof(*wqe_hdr));
wqe_hdr->wr_id = wr->wr_id;
wqe_hdr->num_sge = wr->num_sge;
@@ -771,12 +769,11 @@ int pvrdma_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
/* Make sure wqe is written before index update */
smp_wmb();
- index++;
- if (unlikely(index >= qp->sq.wqe_cnt))
- index = 0;
/* Update shared sq ring */
pvrdma_idx_ring_inc(&qp->sq.ring->prod_tail,
qp->sq.wqe_cnt);
+
+ wr = wr->next;
}
ret = 0;
@@ -806,7 +803,6 @@ int pvrdma_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
struct pvrdma_qp *qp = to_vqp(ibqp);
struct pvrdma_rq_wqe_hdr *wqe_hdr;
struct pvrdma_sge *sge;
- int index, nreq;
int ret = 0;
int i;
@@ -821,9 +817,8 @@ int pvrdma_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
spin_lock_irqsave(&qp->rq.lock, flags);
- index = pvrdma_idx(&qp->rq.ring->prod_tail, qp->rq.wqe_cnt);
- for (nreq = 0; wr; nreq++, wr = wr->next) {
- unsigned int tail;
+ while (wr) {
+ unsigned int tail = 0;
if (unlikely(wr->num_sge > qp->rq.max_sg ||
wr->num_sge < 0)) {
@@ -843,7 +838,7 @@ int pvrdma_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
goto out;
}
- wqe_hdr = (struct pvrdma_rq_wqe_hdr *)get_rq_wqe(qp, index);
+ wqe_hdr = (struct pvrdma_rq_wqe_hdr *)get_rq_wqe(qp, tail);
wqe_hdr->wr_id = wr->wr_id;
wqe_hdr->num_sge = wr->num_sge;
wqe_hdr->total_len = 0;
@@ -859,12 +854,11 @@ int pvrdma_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
/* Make sure wqe is written before index update */
smp_wmb();
- index++;
- if (unlikely(index >= qp->rq.wqe_cnt))
- index = 0;
/* Update shared rq ring */
pvrdma_idx_ring_inc(&qp->rq.ring->prod_tail,
qp->rq.wqe_cnt);
+
+ wr = wr->next;
}
spin_unlock_irqrestore(&qp->rq.lock, flags);
diff --git a/drivers/infiniband/sw/rdmavt/mmap.c b/drivers/infiniband/sw/rdmavt/mmap.c
index e202b81..6b712ee 100644
--- a/drivers/infiniband/sw/rdmavt/mmap.c
+++ b/drivers/infiniband/sw/rdmavt/mmap.c
@@ -170,9 +170,9 @@ struct rvt_mmap_info *rvt_create_mmap_info(struct rvt_dev_info *rdi,
spin_lock_irq(&rdi->mmap_offset_lock);
if (rdi->mmap_offset == 0)
- rdi->mmap_offset = PAGE_SIZE;
+ rdi->mmap_offset = ALIGN(PAGE_SIZE, SHMLBA);
ip->offset = rdi->mmap_offset;
- rdi->mmap_offset += size;
+ rdi->mmap_offset += ALIGN(size, SHMLBA);
spin_unlock_irq(&rdi->mmap_offset_lock);
INIT_LIST_HEAD(&ip->pending_mmaps);
diff --git a/drivers/infiniband/sw/rxe/Kconfig b/drivers/infiniband/sw/rxe/Kconfig
index 7d1ac27..6332ded 100644
--- a/drivers/infiniband/sw/rxe/Kconfig
+++ b/drivers/infiniband/sw/rxe/Kconfig
@@ -22,4 +22,4 @@
To configure and work with soft-RoCE driver please use the
following wiki page under "configure Soft-RoCE (RXE)" section:
- https://github.com/SoftRoCE/rxe-dev/wiki/rxe-dev:-Home
+ https://github.com/linux-rdma/rdma-core/blob/master/Documentation/rxe.md
diff --git a/drivers/infiniband/sw/rxe/rxe_mmap.c b/drivers/infiniband/sw/rxe/rxe_mmap.c
index c572a4c..bd812e0 100644
--- a/drivers/infiniband/sw/rxe/rxe_mmap.c
+++ b/drivers/infiniband/sw/rxe/rxe_mmap.c
@@ -156,10 +156,10 @@ struct rxe_mmap_info *rxe_create_mmap_info(struct rxe_dev *rxe,
spin_lock_bh(&rxe->mmap_offset_lock);
if (rxe->mmap_offset == 0)
- rxe->mmap_offset = PAGE_SIZE;
+ rxe->mmap_offset = ALIGN(PAGE_SIZE, SHMLBA);
ip->info.offset = rxe->mmap_offset;
- rxe->mmap_offset += size;
+ rxe->mmap_offset += ALIGN(size, SHMLBA);
spin_unlock_bh(&rxe->mmap_offset_lock);
diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index dbfde0d..9f95f50 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -729,11 +729,11 @@ int rxe_requester(void *arg)
ret = rxe_xmit_packet(to_rdev(qp->ibqp.device), qp, &pkt, skb);
if (ret) {
qp->need_req_skb = 1;
- kfree_skb(skb);
rollback_state(wqe, qp, &rollback_wqe, rollback_psn);
if (ret == -EAGAIN) {
+ kfree_skb(skb);
rxe_run_task(&qp->req.task, 1);
goto exit;
}
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index d404a8a..c9dd385 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -813,18 +813,17 @@ static enum resp_states execute(struct rxe_qp *qp, struct rxe_pkt_info *pkt)
WARN_ON_ONCE(1);
}
- /* We successfully processed this new request. */
- qp->resp.msn++;
-
/* next expected psn, read handles this separately */
qp->resp.psn = (pkt->psn + 1) & BTH_PSN_MASK;
qp->resp.opcode = pkt->opcode;
qp->resp.status = IB_WC_SUCCESS;
- if (pkt->mask & RXE_COMP_MASK)
+ if (pkt->mask & RXE_COMP_MASK) {
+ /* We successfully processed this new request. */
+ qp->resp.msn++;
return RESPST_COMPLETE;
- else if (qp_type(qp) == IB_QPT_RC)
+ } else if (qp_type(qp) == IB_QPT_RC)
return RESPST_ACKNOWLEDGE;
else
return RESPST_CLEANUP;
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h
index 9d0b22a..c1ae4ae 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.h
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.h
@@ -430,6 +430,7 @@ struct iser_fr_desc {
struct list_head list;
struct iser_reg_resources rsc;
struct iser_pi_context *pi_ctx;
+ struct list_head all_list;
};
/**
@@ -443,6 +444,7 @@ struct iser_fr_pool {
struct list_head list;
spinlock_t lock;
int size;
+ struct list_head all_list;
};
/**
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index 30b622f..c538a38 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -362,6 +362,7 @@ int iser_alloc_fastreg_pool(struct ib_conn *ib_conn,
int i, ret;
INIT_LIST_HEAD(&fr_pool->list);
+ INIT_LIST_HEAD(&fr_pool->all_list);
spin_lock_init(&fr_pool->lock);
fr_pool->size = 0;
for (i = 0; i < cmds_max; i++) {
@@ -373,6 +374,7 @@ int iser_alloc_fastreg_pool(struct ib_conn *ib_conn,
}
list_add_tail(&desc->list, &fr_pool->list);
+ list_add_tail(&desc->all_list, &fr_pool->all_list);
fr_pool->size++;
}
@@ -392,13 +394,13 @@ void iser_free_fastreg_pool(struct ib_conn *ib_conn)
struct iser_fr_desc *desc, *tmp;
int i = 0;
- if (list_empty(&fr_pool->list))
+ if (list_empty(&fr_pool->all_list))
return;
iser_info("freeing conn %p fr pool\n", ib_conn);
- list_for_each_entry_safe(desc, tmp, &fr_pool->list, list) {
- list_del(&desc->list);
+ list_for_each_entry_safe(desc, tmp, &fr_pool->all_list, all_list) {
+ list_del(&desc->all_list);
iser_free_reg_res(&desc->rsc);
if (desc->pi_ctx)
iser_free_pi_ctx(desc->pi_ctx);
diff --git a/drivers/input/joystick/iforce/iforce-usb.c b/drivers/input/joystick/iforce/iforce-usb.c
index d96aa27..db64adf 100644
--- a/drivers/input/joystick/iforce/iforce-usb.c
+++ b/drivers/input/joystick/iforce/iforce-usb.c
@@ -141,6 +141,9 @@ static int iforce_usb_probe(struct usb_interface *intf,
interface = intf->cur_altsetting;
+ if (interface->desc.bNumEndpoints < 2)
+ return -ENODEV;
+
epirq = &interface->endpoint[0].desc;
epout = &interface->endpoint[1].desc;
diff --git a/drivers/input/misc/cm109.c b/drivers/input/misc/cm109.c
index 9cc6d05..23c191a 100644
--- a/drivers/input/misc/cm109.c
+++ b/drivers/input/misc/cm109.c
@@ -700,6 +700,10 @@ static int cm109_usb_probe(struct usb_interface *intf,
int error = -ENOMEM;
interface = intf->cur_altsetting;
+
+ if (interface->desc.bNumEndpoints < 1)
+ return -ENODEV;
+
endpoint = &interface->endpoint[0].desc;
if (!usb_endpoint_is_int_in(endpoint))
diff --git a/drivers/input/misc/ims-pcu.c b/drivers/input/misc/ims-pcu.c
index 9c0ea36..f4e8fbe 100644
--- a/drivers/input/misc/ims-pcu.c
+++ b/drivers/input/misc/ims-pcu.c
@@ -1667,6 +1667,10 @@ static int ims_pcu_parse_cdc_data(struct usb_interface *intf, struct ims_pcu *pc
return -EINVAL;
alt = pcu->ctrl_intf->cur_altsetting;
+
+ if (alt->desc.bNumEndpoints < 1)
+ return -ENODEV;
+
pcu->ep_ctrl = &alt->endpoint[0].desc;
pcu->max_ctrl_size = usb_endpoint_maxp(pcu->ep_ctrl);
diff --git a/drivers/input/misc/yealink.c b/drivers/input/misc/yealink.c
index 79c964c..6e7ff95 100644
--- a/drivers/input/misc/yealink.c
+++ b/drivers/input/misc/yealink.c
@@ -875,6 +875,10 @@ static int usb_probe(struct usb_interface *intf, const struct usb_device_id *id)
int ret, pipe, i;
interface = intf->cur_altsetting;
+
+ if (interface->desc.bNumEndpoints < 1)
+ return -ENODEV;
+
endpoint = &interface->endpoint[0].desc;
if (!usb_endpoint_is_int_in(endpoint))
return -ENODEV;
diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index 72b28eb..f210e19 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -1282,10 +1282,8 @@ static int alps_decode_ss4_v2(struct alps_fields *f,
/* handle buttons */
if (pkt_id == SS4_PACKET_ID_STICK) {
f->ts_left = !!(SS4_BTN_V2(p) & 0x01);
- if (!(priv->flags & ALPS_BUTTONPAD)) {
- f->ts_right = !!(SS4_BTN_V2(p) & 0x02);
- f->ts_middle = !!(SS4_BTN_V2(p) & 0x04);
- }
+ f->ts_right = !!(SS4_BTN_V2(p) & 0x02);
+ f->ts_middle = !!(SS4_BTN_V2(p) & 0x04);
} else {
f->left = !!(SS4_BTN_V2(p) & 0x01);
if (!(priv->flags & ALPS_BUTTONPAD)) {
@@ -2462,14 +2460,34 @@ static int alps_update_device_area_ss4_v2(unsigned char otp[][4],
int num_y_electrode;
int x_pitch, y_pitch, x_phys, y_phys;
- num_x_electrode = SS4_NUMSENSOR_XOFFSET + (otp[1][0] & 0x0F);
- num_y_electrode = SS4_NUMSENSOR_YOFFSET + ((otp[1][0] >> 4) & 0x0F);
+ if (IS_SS4PLUS_DEV(priv->dev_id)) {
+ num_x_electrode =
+ SS4PLUS_NUMSENSOR_XOFFSET + (otp[0][2] & 0x0F);
+ num_y_electrode =
+ SS4PLUS_NUMSENSOR_YOFFSET + ((otp[0][2] >> 4) & 0x0F);
- priv->x_max = (num_x_electrode - 1) * SS4_COUNT_PER_ELECTRODE;
- priv->y_max = (num_y_electrode - 1) * SS4_COUNT_PER_ELECTRODE;
+ priv->x_max =
+ (num_x_electrode - 1) * SS4PLUS_COUNT_PER_ELECTRODE;
+ priv->y_max =
+ (num_y_electrode - 1) * SS4PLUS_COUNT_PER_ELECTRODE;
- x_pitch = ((otp[1][2] >> 2) & 0x07) + SS4_MIN_PITCH_MM;
- y_pitch = ((otp[1][2] >> 5) & 0x07) + SS4_MIN_PITCH_MM;
+ x_pitch = (otp[0][1] & 0x0F) + SS4PLUS_MIN_PITCH_MM;
+ y_pitch = ((otp[0][1] >> 4) & 0x0F) + SS4PLUS_MIN_PITCH_MM;
+
+ } else {
+ num_x_electrode =
+ SS4_NUMSENSOR_XOFFSET + (otp[1][0] & 0x0F);
+ num_y_electrode =
+ SS4_NUMSENSOR_YOFFSET + ((otp[1][0] >> 4) & 0x0F);
+
+ priv->x_max =
+ (num_x_electrode - 1) * SS4_COUNT_PER_ELECTRODE;
+ priv->y_max =
+ (num_y_electrode - 1) * SS4_COUNT_PER_ELECTRODE;
+
+ x_pitch = ((otp[1][2] >> 2) & 0x07) + SS4_MIN_PITCH_MM;
+ y_pitch = ((otp[1][2] >> 5) & 0x07) + SS4_MIN_PITCH_MM;
+ }
x_phys = x_pitch * (num_x_electrode - 1); /* In 0.1 mm units */
y_phys = y_pitch * (num_y_electrode - 1); /* In 0.1 mm units */
@@ -2485,7 +2503,10 @@ static int alps_update_btn_info_ss4_v2(unsigned char otp[][4],
{
unsigned char is_btnless;
- is_btnless = (otp[1][1] >> 3) & 0x01;
+ if (IS_SS4PLUS_DEV(priv->dev_id))
+ is_btnless = (otp[1][0] >> 1) & 0x01;
+ else
+ is_btnless = (otp[1][1] >> 3) & 0x01;
if (is_btnless)
priv->flags |= ALPS_BUTTONPAD;
@@ -2493,6 +2514,21 @@ static int alps_update_btn_info_ss4_v2(unsigned char otp[][4],
return 0;
}
+static int alps_update_dual_info_ss4_v2(unsigned char otp[][4],
+ struct alps_data *priv)
+{
+ bool is_dual = false;
+
+ if (IS_SS4PLUS_DEV(priv->dev_id))
+ is_dual = (otp[0][0] >> 4) & 0x01;
+
+ if (is_dual)
+ priv->flags |= ALPS_DUALPOINT |
+ ALPS_DUALPOINT_WITH_PRESSURE;
+
+ return 0;
+}
+
static int alps_set_defaults_ss4_v2(struct psmouse *psmouse,
struct alps_data *priv)
{
@@ -2508,6 +2544,8 @@ static int alps_set_defaults_ss4_v2(struct psmouse *psmouse,
alps_update_btn_info_ss4_v2(otp, priv);
+ alps_update_dual_info_ss4_v2(otp, priv);
+
return 0;
}
@@ -2753,10 +2791,6 @@ static int alps_set_protocol(struct psmouse *psmouse,
if (alps_set_defaults_ss4_v2(psmouse, priv))
return -EIO;
- if (priv->fw_ver[1] == 0x1)
- priv->flags |= ALPS_DUALPOINT |
- ALPS_DUALPOINT_WITH_PRESSURE;
-
break;
}
@@ -2827,10 +2861,7 @@ static int alps_identify(struct psmouse *psmouse, struct alps_data *priv)
ec[2] >= 0x90 && ec[2] <= 0x9d) {
protocol = &alps_v3_protocol_data;
} else if (e7[0] == 0x73 && e7[1] == 0x03 &&
- e7[2] == 0x14 && ec[1] == 0x02) {
- protocol = &alps_v8_protocol_data;
- } else if (e7[0] == 0x73 && e7[1] == 0x03 &&
- e7[2] == 0x28 && ec[1] == 0x01) {
+ (e7[2] == 0x14 || e7[2] == 0x28)) {
protocol = &alps_v8_protocol_data;
} else {
psmouse_dbg(psmouse,
@@ -2840,7 +2871,8 @@ static int alps_identify(struct psmouse *psmouse, struct alps_data *priv)
}
if (priv) {
- /* Save the Firmware version */
+ /* Save Device ID and Firmware version */
+ memcpy(priv->dev_id, e7, 3);
memcpy(priv->fw_ver, ec, 3);
error = alps_set_protocol(psmouse, priv, protocol);
if (error)
diff --git a/drivers/input/mouse/alps.h b/drivers/input/mouse/alps.h
index 6d279aa..4334f28 100644
--- a/drivers/input/mouse/alps.h
+++ b/drivers/input/mouse/alps.h
@@ -54,6 +54,16 @@ enum SS4_PACKET_ID {
#define SS4_MASK_NORMAL_BUTTONS 0x07
+#define SS4PLUS_COUNT_PER_ELECTRODE 128
+#define SS4PLUS_NUMSENSOR_XOFFSET 16
+#define SS4PLUS_NUMSENSOR_YOFFSET 5
+#define SS4PLUS_MIN_PITCH_MM 37
+
+#define IS_SS4PLUS_DEV(_b) (((_b[0]) == 0x73) && \
+ ((_b[1]) == 0x03) && \
+ ((_b[2]) == 0x28) \
+ )
+
#define SS4_IS_IDLE_V2(_b) (((_b[0]) == 0x18) && \
((_b[1]) == 0x10) && \
((_b[2]) == 0x00) && \
@@ -283,6 +293,7 @@ struct alps_data {
int addr_command;
u16 proto_version;
u8 byte0, mask0;
+ u8 dev_id[3];
u8 fw_ver[3];
int flags;
int x_max;
diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index 352050e..d5ab9dd 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -218,17 +218,19 @@ static int elan_query_product(struct elan_tp_data *data)
static int elan_check_ASUS_special_fw(struct elan_tp_data *data)
{
- if (data->ic_type != 0x0E)
- return false;
-
- switch (data->product_id) {
- case 0x05 ... 0x07:
- case 0x09:
- case 0x13:
+ if (data->ic_type == 0x0E) {
+ switch (data->product_id) {
+ case 0x05 ... 0x07:
+ case 0x09:
+ case 0x13:
+ return true;
+ }
+ } else if (data->ic_type == 0x08 && data->product_id == 0x26) {
+ /* ASUS EeeBook X205TA */
return true;
- default:
- return false;
}
+
+ return false;
}
static int __elan_initialize(struct elan_tp_data *data)
diff --git a/drivers/input/rmi4/rmi_f30.c b/drivers/input/rmi4/rmi_f30.c
index 1986786..34dfee5 100644
--- a/drivers/input/rmi4/rmi_f30.c
+++ b/drivers/input/rmi4/rmi_f30.c
@@ -170,6 +170,10 @@ static int rmi_f30_config(struct rmi_function *fn)
rmi_get_platform_data(fn->rmi_dev);
int error;
+ /* can happen if f30_data.disable is set */
+ if (!f30)
+ return 0;
+
if (pdata->f30_data.trackstick_buttons) {
/* Try [re-]establish link to F03. */
f30->f03 = rmi_find_function(fn->rmi_dev, 0x03);
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index 05afd16..312bd6c 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -120,6 +120,13 @@ static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = {
},
},
{
+ /* Dell Embedded Box PC 3000 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Embedded Box PC 3000"),
+ },
+ },
+ {
/* OQO Model 01 */
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "OQO"),
@@ -513,6 +520,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = {
DMI_MATCH(DMI_PRODUCT_NAME, "IC4I"),
},
},
+ {
+ /* TUXEDO BU1406 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Notebook"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "N24_25BU"),
+ },
+ },
{ }
};
diff --git a/drivers/input/tablet/hanwang.c b/drivers/input/tablet/hanwang.c
index cd85205..df4bea9 100644
--- a/drivers/input/tablet/hanwang.c
+++ b/drivers/input/tablet/hanwang.c
@@ -340,6 +340,9 @@ static int hanwang_probe(struct usb_interface *intf, const struct usb_device_id
int error;
int i;
+ if (intf->cur_altsetting->desc.bNumEndpoints < 1)
+ return -ENODEV;
+
hanwang = kzalloc(sizeof(struct hanwang), GFP_KERNEL);
input_dev = input_allocate_device();
if (!hanwang || !input_dev) {
diff --git a/drivers/input/tablet/kbtab.c b/drivers/input/tablet/kbtab.c
index e850d7e..4d9d649 100644
--- a/drivers/input/tablet/kbtab.c
+++ b/drivers/input/tablet/kbtab.c
@@ -122,6 +122,9 @@ static int kbtab_probe(struct usb_interface *intf, const struct usb_device_id *i
struct input_dev *input_dev;
int error = -ENOMEM;
+ if (intf->cur_altsetting->desc.bNumEndpoints < 1)
+ return -ENODEV;
+
kbtab = kzalloc(sizeof(struct kbtab), GFP_KERNEL);
input_dev = input_allocate_device();
if (!kbtab || !input_dev)
diff --git a/drivers/input/touchscreen/sur40.c b/drivers/input/touchscreen/sur40.c
index aefb6e1..4c0eeca 100644
--- a/drivers/input/touchscreen/sur40.c
+++ b/drivers/input/touchscreen/sur40.c
@@ -527,6 +527,9 @@ static int sur40_probe(struct usb_interface *interface,
if (iface_desc->desc.bInterfaceClass != 0xFF)
return -ENODEV;
+ if (iface_desc->desc.bNumEndpoints < 5)
+ return -ENODEV;
+
/* Use endpoint #4 (0x86). */
endpoint = &iface_desc->endpoint[4].desc;
if (endpoint->bEndpointAddress != TOUCH_ENDPOINT)
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 98940d1..b17536d6 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -3202,7 +3202,7 @@ static void amd_iommu_get_resv_regions(struct device *dev,
region = iommu_alloc_resv_region(MSI_RANGE_START,
MSI_RANGE_END - MSI_RANGE_START + 1,
- 0, IOMMU_RESV_RESERVED);
+ 0, IOMMU_RESV_MSI);
if (!region)
return;
list_add_tail(®ion->list, head);
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 5806a6a..591bb96 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -1888,7 +1888,7 @@ static void arm_smmu_get_resv_regions(struct device *dev,
int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
region = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH,
- prot, IOMMU_RESV_MSI);
+ prot, IOMMU_RESV_SW_MSI);
if (!region)
return;
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index abf6496..b493c99 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -1608,7 +1608,7 @@ static void arm_smmu_get_resv_regions(struct device *dev,
int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
region = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH,
- prot, IOMMU_RESV_MSI);
+ prot, IOMMU_RESV_SW_MSI);
if (!region)
return;
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index a7e0821..c01bfcd 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -512,7 +512,13 @@ static void sysmmu_tlb_invalidate_flpdcache(struct sysmmu_drvdata *data,
spin_lock_irqsave(&data->lock, flags);
if (data->active && data->version >= MAKE_MMU_VER(3, 3)) {
clk_enable(data->clk_master);
- __sysmmu_tlb_invalidate_entry(data, iova, 1);
+ if (sysmmu_block(data)) {
+ if (data->version >= MAKE_MMU_VER(5, 0))
+ __sysmmu_tlb_invalidate(data);
+ else
+ __sysmmu_tlb_invalidate_entry(data, iova, 1);
+ sysmmu_unblock(data);
+ }
clk_disable(data->clk_master);
}
spin_unlock_irqrestore(&data->lock, flags);
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 238ad34..d412a31 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -916,7 +916,7 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf
* which we used for the IOMMU lookup. Strictly speaking
* we could do this for all PCI devices; we only need to
* get the BDF# from the scope table for ACPI matches. */
- if (pdev->is_virtfn)
+ if (pdev && pdev->is_virtfn)
goto got_pdev;
*bus = drhd->devices[i].bus;
@@ -5249,7 +5249,7 @@ static void intel_iommu_get_resv_regions(struct device *device,
reg = iommu_alloc_resv_region(IOAPIC_RANGE_START,
IOAPIC_RANGE_END - IOAPIC_RANGE_START + 1,
- 0, IOMMU_RESV_RESERVED);
+ 0, IOMMU_RESV_MSI);
if (!reg)
return;
list_add_tail(®->list, head);
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 1c049e2..8d6ca28 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -422,8 +422,12 @@ static int __arm_v7s_map(struct arm_v7s_io_pgtable *data, unsigned long iova,
pte |= ARM_V7S_ATTR_NS_TABLE;
__arm_v7s_set_pte(ptep, pte, 1, cfg);
- } else {
+ } else if (ARM_V7S_PTE_IS_TABLE(pte, lvl)) {
cptep = iopte_deref(pte, lvl);
+ } else {
+ /* We require an unmap first */
+ WARN_ON(!selftest_running);
+ return -EEXIST;
}
/* Rinse, repeat */
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index feacc54..f9bc6eb 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -335,8 +335,12 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_NS)
pte |= ARM_LPAE_PTE_NSTABLE;
__arm_lpae_set_pte(ptep, pte, cfg);
- } else {
+ } else if (!iopte_leaf(pte, lvl)) {
cptep = iopte_deref(pte, data);
+ } else {
+ /* We require an unmap first */
+ WARN_ON(!selftest_running);
+ return -EEXIST;
}
/* Rinse, repeat */
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 8ea14f4..3b67144 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -72,6 +72,7 @@ static const char * const iommu_group_resv_type_string[] = {
[IOMMU_RESV_DIRECT] = "direct",
[IOMMU_RESV_RESERVED] = "reserved",
[IOMMU_RESV_MSI] = "msi",
+ [IOMMU_RESV_SW_MSI] = "msi",
};
#define IOMMU_GROUP_ATTR(_name, _mode, _show, _store) \
@@ -1743,8 +1744,8 @@ void iommu_put_resv_regions(struct device *dev, struct list_head *list)
}
struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start,
- size_t length,
- int prot, int type)
+ size_t length, int prot,
+ enum iommu_resv_type type)
{
struct iommu_resv_region *region;
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 125528f..8162121 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -262,6 +262,7 @@
config MVEBU_ODMI
bool
+ select GENERIC_MSI_IRQ_DOMAIN
config MVEBU_PIC
bool
diff --git a/drivers/irqchip/irq-crossbar.c b/drivers/irqchip/irq-crossbar.c
index 1eef56a..f966012 100644
--- a/drivers/irqchip/irq-crossbar.c
+++ b/drivers/irqchip/irq-crossbar.c
@@ -198,7 +198,8 @@ static const struct irq_domain_ops crossbar_domain_ops = {
static int __init crossbar_of_init(struct device_node *node)
{
- int i, size, max = 0, reserved = 0, entry;
+ u32 max = 0, entry, reg_size;
+ int i, size, reserved = 0;
const __be32 *irqsr;
int ret = -ENOMEM;
@@ -275,9 +276,9 @@ static int __init crossbar_of_init(struct device_node *node)
if (!cb->register_offsets)
goto err_irq_map;
- of_property_read_u32(node, "ti,reg-size", &size);
+ of_property_read_u32(node, "ti,reg-size", ®_size);
- switch (size) {
+ switch (reg_size) {
case 1:
cb->write = crossbar_writeb;
break;
@@ -303,7 +304,7 @@ static int __init crossbar_of_init(struct device_node *node)
continue;
cb->register_offsets[i] = reserved;
- reserved += size;
+ reserved += reg_size;
}
of_property_read_u32(node, "ti,irqs-safe-map", &cb->safe_map);
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 2320100..f77f840 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -1601,6 +1601,14 @@ static void __maybe_unused its_enable_quirk_cavium_23144(void *data)
its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_23144;
}
+static void __maybe_unused its_enable_quirk_qdf2400_e0065(void *data)
+{
+ struct its_node *its = data;
+
+ /* On QDF2400, the size of the ITE is 16Bytes */
+ its->ite_size = 16;
+}
+
static const struct gic_quirk its_quirks[] = {
#ifdef CONFIG_CAVIUM_ERRATUM_22375
{
@@ -1618,6 +1626,14 @@ static const struct gic_quirk its_quirks[] = {
.init = its_enable_quirk_cavium_23144,
},
#endif
+#ifdef CONFIG_QCOM_QDF2400_ERRATUM_0065
+ {
+ .desc = "ITS: QDF2400 erratum 0065",
+ .iidr = 0x00001070, /* QDF2400 ITS rev 1.x */
+ .mask = 0xffffffff,
+ .init = its_enable_quirk_qdf2400_e0065,
+ },
+#endif
{
}
};
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index 11d12bc..cd20df1 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -991,8 +991,12 @@ static void __init gic_map_single_int(struct device_node *node,
static void __init gic_map_interrupts(struct device_node *node)
{
+ gic_map_single_int(node, GIC_LOCAL_INT_WD);
+ gic_map_single_int(node, GIC_LOCAL_INT_COMPARE);
gic_map_single_int(node, GIC_LOCAL_INT_TIMER);
gic_map_single_int(node, GIC_LOCAL_INT_PERFCTR);
+ gic_map_single_int(node, GIC_LOCAL_INT_SWINT0);
+ gic_map_single_int(node, GIC_LOCAL_INT_SWINT1);
gic_map_single_int(node, GIC_LOCAL_INT_FDC);
}
diff --git a/drivers/isdn/capi/kcapi.c b/drivers/isdn/capi/kcapi.c
index 1dfd108..9ca691d 100644
--- a/drivers/isdn/capi/kcapi.c
+++ b/drivers/isdn/capi/kcapi.c
@@ -1032,6 +1032,7 @@ static int old_capi_manufacturer(unsigned int cmd, void __user *data)
sizeof(avmb1_carddef))))
return -EFAULT;
cdef.cardtype = AVM_CARDTYPE_B1;
+ cdef.cardnr = 0;
} else {
if ((retval = copy_from_user(&cdef, data,
sizeof(avmb1_extcarddef))))
diff --git a/drivers/isdn/divert/isdn_divert.c b/drivers/isdn/divert/isdn_divert.c
index 50749a7..060d357 100644
--- a/drivers/isdn/divert/isdn_divert.c
+++ b/drivers/isdn/divert/isdn_divert.c
@@ -157,10 +157,8 @@ int cf_command(int drvid, int mode,
/* allocate mem for information struct */
if (!(cs = kmalloc(sizeof(struct call_struc), GFP_ATOMIC)))
return (-ENOMEM); /* no memory */
- init_timer(&cs->timer);
+ setup_timer(&cs->timer, deflect_timer_expire, (ulong)cs);
cs->info[0] = '\0';
- cs->timer.function = deflect_timer_expire;
- cs->timer.data = (ulong) cs; /* pointer to own structure */
cs->ics.driver = drvid;
cs->ics.command = ISDN_CMD_PROT_IO; /* protocol specific io */
cs->ics.arg = DSS1_CMD_INVOKE; /* invoke supplementary service */
@@ -452,10 +450,9 @@ static int isdn_divert_icall(isdn_ctrl *ic)
return (0); /* no external deflection needed */
if (!(cs = kmalloc(sizeof(struct call_struc), GFP_ATOMIC)))
return (0); /* no memory */
- init_timer(&cs->timer);
+ setup_timer(&cs->timer, deflect_timer_expire,
+ (ulong)cs);
cs->info[0] = '\0';
- cs->timer.function = deflect_timer_expire;
- cs->timer.data = (ulong) cs; /* pointer to own structure */
cs->ics = *ic; /* copy incoming data */
if (!cs->ics.parm.setup.phone[0]) strcpy(cs->ics.parm.setup.phone, "0");
diff --git a/drivers/isdn/gigaset/bas-gigaset.c b/drivers/isdn/gigaset/bas-gigaset.c
index 11e13c5..2da3ff6 100644
--- a/drivers/isdn/gigaset/bas-gigaset.c
+++ b/drivers/isdn/gigaset/bas-gigaset.c
@@ -2317,6 +2317,9 @@ static int gigaset_probe(struct usb_interface *interface,
return -ENODEV;
}
+ if (hostif->desc.bNumEndpoints < 1)
+ return -ENODEV;
+
dev_info(&udev->dev,
"%s: Device matched (Vendor: 0x%x, Product: 0x%x)\n",
__func__, le16_to_cpu(udev->descriptor.idVendor),
diff --git a/drivers/isdn/hardware/eicon/divasi.c b/drivers/isdn/hardware/eicon/divasi.c
index cb88090..c610495 100644
--- a/drivers/isdn/hardware/eicon/divasi.c
+++ b/drivers/isdn/hardware/eicon/divasi.c
@@ -300,9 +300,8 @@ static int um_idi_open_adapter(struct file *file, int adapter_nr)
p_os = (diva_um_idi_os_context_t *) diva_um_id_get_os_context(e);
init_waitqueue_head(&p_os->read_wait);
init_waitqueue_head(&p_os->close_wait);
- init_timer(&p_os->diva_timer_id);
- p_os->diva_timer_id.function = (void *) diva_um_timer_function;
- p_os->diva_timer_id.data = (unsigned long) p_os;
+ setup_timer(&p_os->diva_timer_id, (void *)diva_um_timer_function,
+ (unsigned long)p_os);
p_os->aborted = 0;
p_os->adapter_nr = adapter_nr;
return (1);
diff --git a/drivers/isdn/hardware/mISDN/Kconfig b/drivers/isdn/hardware/mISDN/Kconfig
index 09df54f..fda912b 100644
--- a/drivers/isdn/hardware/mISDN/Kconfig
+++ b/drivers/isdn/hardware/mISDN/Kconfig
@@ -13,7 +13,7 @@
config MISDN_HFCMULTI
tristate "Support for HFC multiport cards (HFC-4S/8S/E1)"
- depends on PCI || 8xx
+ depends on PCI || CPM1
depends on MISDN
help
Enable support for cards with Cologne Chip AG's HFC multiport
@@ -27,8 +27,8 @@
bool "Support for XHFC embedded board in HFC multiport driver"
depends on MISDN
depends on MISDN_HFCMULTI
- depends on 8xx
- default 8xx
+ depends on CPM1
+ default CPM1
help
Enable support for the XHFC embedded solution from Speech Design.
diff --git a/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h b/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h
index 0eafe9f..8a25474 100644
--- a/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h
+++ b/drivers/isdn/hardware/mISDN/hfc_multi_8xx.h
@@ -6,7 +6,7 @@
*
*/
-#include <asm/8xx_immap.h>
+#include <asm/cpm1.h>
/* Change this to the value used by your board */
#ifndef IMAP_ADDR
diff --git a/drivers/isdn/hardware/mISDN/hfcmulti.c b/drivers/isdn/hardware/mISDN/hfcmulti.c
index 480c2d7..961c07e 100644
--- a/drivers/isdn/hardware/mISDN/hfcmulti.c
+++ b/drivers/isdn/hardware/mISDN/hfcmulti.c
@@ -3878,9 +3878,8 @@ hfcmulti_initmode(struct dchannel *dch)
if (hc->dnum[pt]) {
mode_hfcmulti(hc, dch->slot, dch->dev.D.protocol,
-1, 0, -1, 0);
- dch->timer.function = (void *) hfcmulti_dbusy_timer;
- dch->timer.data = (long) dch;
- init_timer(&dch->timer);
+ setup_timer(&dch->timer, (void *)hfcmulti_dbusy_timer,
+ (long)dch);
}
for (i = 1; i <= 31; i++) {
if (!((1 << i) & hc->bmask[pt])) /* skip unused chan */
@@ -3986,9 +3985,8 @@ hfcmulti_initmode(struct dchannel *dch)
hc->chan[i].slot_rx = -1;
hc->chan[i].conf = -1;
mode_hfcmulti(hc, i, dch->dev.D.protocol, -1, 0, -1, 0);
- dch->timer.function = (void *) hfcmulti_dbusy_timer;
- dch->timer.data = (long) dch;
- init_timer(&dch->timer);
+ setup_timer(&dch->timer, (void *)hfcmulti_dbusy_timer,
+ (long)dch);
hc->chan[i - 2].slot_tx = -1;
hc->chan[i - 2].slot_rx = -1;
hc->chan[i - 2].conf = -1;
diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c
index ff48da6..5dc246d 100644
--- a/drivers/isdn/hardware/mISDN/hfcpci.c
+++ b/drivers/isdn/hardware/mISDN/hfcpci.c
@@ -1717,9 +1717,8 @@ static void
inithfcpci(struct hfc_pci *hc)
{
printk(KERN_DEBUG "inithfcpci: entered\n");
- hc->dch.timer.function = (void *) hfcpci_dbusy_timer;
- hc->dch.timer.data = (long) &hc->dch;
- init_timer(&hc->dch.timer);
+ setup_timer(&hc->dch.timer, (void *)hfcpci_dbusy_timer,
+ (long)&hc->dch);
hc->chanlimit = 2;
mode_hfcpci(&hc->bch[0], 1, -1);
mode_hfcpci(&hc->bch[1], 2, -1);
@@ -2044,9 +2043,7 @@ setup_hw(struct hfc_pci *hc)
Write_hfc(hc, HFCPCI_INT_M1, hc->hw.int_m1);
/* At this point the needed PCI config is done */
/* fifos are still not enabled */
- hc->hw.timer.function = (void *) hfcpci_Timer;
- hc->hw.timer.data = (long) hc;
- init_timer(&hc->hw.timer);
+ setup_timer(&hc->hw.timer, (void *)hfcpci_Timer, (long)hc);
/* default PCM master */
test_and_set_bit(HFC_CFG_MASTER, &hc->cfg);
return 0;
diff --git a/drivers/isdn/hardware/mISDN/mISDNipac.c b/drivers/isdn/hardware/mISDN/mISDNipac.c
index 77dec28..6742b0d 100644
--- a/drivers/isdn/hardware/mISDN/mISDNipac.c
+++ b/drivers/isdn/hardware/mISDN/mISDNipac.c
@@ -796,9 +796,8 @@ isac_init(struct isac_hw *isac)
}
isac->mon_tx = NULL;
isac->mon_rx = NULL;
- isac->dch.timer.function = (void *) dbusy_timer_handler;
- isac->dch.timer.data = (long)isac;
- init_timer(&isac->dch.timer);
+ setup_timer(&isac->dch.timer, (void *)dbusy_timer_handler,
+ (long)isac);
isac->mocr = 0xaa;
if (isac->type & IPAC_TYPE_ISACX) {
/* Disable all IRQ */
diff --git a/drivers/isdn/hardware/mISDN/mISDNisar.c b/drivers/isdn/hardware/mISDN/mISDNisar.c
index feafa91..5b07859 100644
--- a/drivers/isdn/hardware/mISDN/mISDNisar.c
+++ b/drivers/isdn/hardware/mISDN/mISDNisar.c
@@ -1635,13 +1635,11 @@ init_isar(struct isar_hw *isar)
}
if (isar->version != 1)
return -EINVAL;
- isar->ch[0].ftimer.function = &ftimer_handler;
- isar->ch[0].ftimer.data = (long)&isar->ch[0];
- init_timer(&isar->ch[0].ftimer);
+ setup_timer(&isar->ch[0].ftimer, &ftimer_handler,
+ (long)&isar->ch[0]);
test_and_set_bit(FLG_INITIALIZED, &isar->ch[0].bch.Flags);
- isar->ch[1].ftimer.function = &ftimer_handler;
- isar->ch[1].ftimer.data = (long)&isar->ch[1];
- init_timer(&isar->ch[1].ftimer);
+ setup_timer(&isar->ch[1].ftimer, &ftimer_handler,
+ (long)&isar->ch[1]);
test_and_set_bit(FLG_INITIALIZED, &isar->ch[1].bch.Flags);
return 0;
}
diff --git a/drivers/isdn/hardware/mISDN/w6692.c b/drivers/isdn/hardware/mISDN/w6692.c
index 3b067ea..3052c83 100644
--- a/drivers/isdn/hardware/mISDN/w6692.c
+++ b/drivers/isdn/hardware/mISDN/w6692.c
@@ -852,9 +852,8 @@ static void initW6692(struct w6692_hw *card)
{
u8 val;
- card->dch.timer.function = (void *)dbusy_timer_handler;
- card->dch.timer.data = (u_long)&card->dch;
- init_timer(&card->dch.timer);
+ setup_timer(&card->dch.timer, (void *)dbusy_timer_handler,
+ (u_long)&card->dch);
w6692_mode(&card->bc[0], ISDN_P_NONE);
w6692_mode(&card->bc[1], ISDN_P_NONE);
WriteW6692(card, W_D_CTL, 0x00);
diff --git a/drivers/isdn/hisax/amd7930_fn.c b/drivers/isdn/hisax/amd7930_fn.c
index 36817e0..3a4c2f9 100644
--- a/drivers/isdn/hisax/amd7930_fn.c
+++ b/drivers/isdn/hisax/amd7930_fn.c
@@ -789,7 +789,5 @@ void Amd7930_init(struct IsdnCardState *cs)
void setup_Amd7930(struct IsdnCardState *cs)
{
INIT_WORK(&cs->tqueue, Amd7930_bh);
- cs->dbusytimer.function = (void *) dbusy_timer_handler;
- cs->dbusytimer.data = (long) cs;
- init_timer(&cs->dbusytimer);
+ setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs);
}
diff --git a/drivers/isdn/hisax/arcofi.c b/drivers/isdn/hisax/arcofi.c
index 29ec2df..9826bad 100644
--- a/drivers/isdn/hisax/arcofi.c
+++ b/drivers/isdn/hisax/arcofi.c
@@ -125,9 +125,7 @@ clear_arcofi(struct IsdnCardState *cs) {
void
init_arcofi(struct IsdnCardState *cs) {
- cs->dc.isac.arcofitimer.function = (void *) arcofi_timer;
- cs->dc.isac.arcofitimer.data = (long) cs;
- init_timer(&cs->dc.isac.arcofitimer);
+ setup_timer(&cs->dc.isac.arcofitimer, (void *)arcofi_timer, (long)cs);
init_waitqueue_head(&cs->dc.isac.arcofi_wait);
test_and_set_bit(HW_ARCOFI, &cs->HW_Flags);
}
diff --git a/drivers/isdn/hisax/diva.c b/drivers/isdn/hisax/diva.c
index 4fc90de..079336e 100644
--- a/drivers/isdn/hisax/diva.c
+++ b/drivers/isdn/hisax/diva.c
@@ -976,9 +976,8 @@ static int setup_diva_common(struct IsdnCardState *cs)
printk(KERN_INFO "Diva: IPACX Design Id: %x\n",
MemReadISAC_IPACX(cs, IPACX_ID) & 0x3F);
} else { /* DIVA 2.0 */
- cs->hw.diva.tl.function = (void *) diva_led_handler;
- cs->hw.diva.tl.data = (long) cs;
- init_timer(&cs->hw.diva.tl);
+ setup_timer(&cs->hw.diva.tl, (void *)diva_led_handler,
+ (long)cs);
cs->readisac = &ReadISAC;
cs->writeisac = &WriteISAC;
cs->readisacfifo = &ReadISACfifo;
diff --git a/drivers/isdn/hisax/elsa.c b/drivers/isdn/hisax/elsa.c
index d8ef64d..03bc5d5 100644
--- a/drivers/isdn/hisax/elsa.c
+++ b/drivers/isdn/hisax/elsa.c
@@ -1147,9 +1147,7 @@ static int setup_elsa_common(struct IsdnCard *card)
init_arcofi(cs);
#endif
setup_isac(cs);
- cs->hw.elsa.tl.function = (void *) elsa_led_handler;
- cs->hw.elsa.tl.data = (long) cs;
- init_timer(&cs->hw.elsa.tl);
+ setup_timer(&cs->hw.elsa.tl, (void *)elsa_led_handler, (long)cs);
/* Teste Timer */
if (cs->hw.elsa.timer) {
byteout(cs->hw.elsa.trig, 0xff);
diff --git a/drivers/isdn/hisax/fsm.c b/drivers/isdn/hisax/fsm.c
index c7a9471..d63266f 100644
--- a/drivers/isdn/hisax/fsm.c
+++ b/drivers/isdn/hisax/fsm.c
@@ -98,13 +98,11 @@ void
FsmInitTimer(struct FsmInst *fi, struct FsmTimer *ft)
{
ft->fi = fi;
- ft->tl.function = (void *) FsmExpireTimer;
- ft->tl.data = (long) ft;
#if FSM_TIMER_DEBUG
if (ft->fi->debug)
ft->fi->printdebug(ft->fi, "FsmInitTimer %lx", (long) ft);
#endif
- init_timer(&ft->tl);
+ setup_timer(&ft->tl, (void *)FsmExpireTimer, (long)ft);
}
void
diff --git a/drivers/isdn/hisax/hfc4s8s_l1.c b/drivers/isdn/hisax/hfc4s8s_l1.c
index e034ed8..90f051c 100644
--- a/drivers/isdn/hisax/hfc4s8s_l1.c
+++ b/drivers/isdn/hisax/hfc4s8s_l1.c
@@ -1396,9 +1396,8 @@ setup_instance(hfc4s8s_hw *hw)
l1p = hw->l1 + i;
spin_lock_init(&l1p->lock);
l1p->hw = hw;
- l1p->l1_timer.function = (void *) hfc_l1_timer;
- l1p->l1_timer.data = (long) (l1p);
- init_timer(&l1p->l1_timer);
+ setup_timer(&l1p->l1_timer, (void *)hfc_l1_timer,
+ (long)(l1p));
l1p->st_num = i;
skb_queue_head_init(&l1p->d_tx_queue);
l1p->d_if.ifc.priv = hw->l1 + i;
diff --git a/drivers/isdn/hisax/hfc_2bds0.c b/drivers/isdn/hisax/hfc_2bds0.c
index a756e5c..ad8597a 100644
--- a/drivers/isdn/hisax/hfc_2bds0.c
+++ b/drivers/isdn/hisax/hfc_2bds0.c
@@ -1073,8 +1073,6 @@ set_cs_func(struct IsdnCardState *cs)
cs->writeisacfifo = &dummyf;
cs->BC_Read_Reg = &ReadReg;
cs->BC_Write_Reg = &WriteReg;
- cs->dbusytimer.function = (void *) hfc_dbusy_timer;
- cs->dbusytimer.data = (long) cs;
- init_timer(&cs->dbusytimer);
+ setup_timer(&cs->dbusytimer, (void *)hfc_dbusy_timer, (long)cs);
INIT_WORK(&cs->tqueue, hfcd_bh);
}
diff --git a/drivers/isdn/hisax/hfc_pci.c b/drivers/isdn/hisax/hfc_pci.c
index 90449e1..f9ca35c 100644
--- a/drivers/isdn/hisax/hfc_pci.c
+++ b/drivers/isdn/hisax/hfc_pci.c
@@ -1582,9 +1582,7 @@ inithfcpci(struct IsdnCardState *cs)
cs->bcs[1].BC_SetStack = setstack_2b;
cs->bcs[0].BC_Close = close_hfcpci;
cs->bcs[1].BC_Close = close_hfcpci;
- cs->dbusytimer.function = (void *) hfcpci_dbusy_timer;
- cs->dbusytimer.data = (long) cs;
- init_timer(&cs->dbusytimer);
+ setup_timer(&cs->dbusytimer, (void *)hfcpci_dbusy_timer, (long)cs);
mode_hfcpci(cs->bcs, 0, 0);
mode_hfcpci(cs->bcs + 1, 0, 1);
}
@@ -1746,9 +1744,7 @@ setup_hfcpci(struct IsdnCard *card)
cs->BC_Write_Reg = NULL;
cs->irq_func = &hfcpci_interrupt;
cs->irq_flags |= IRQF_SHARED;
- cs->hw.hfcpci.timer.function = (void *) hfcpci_Timer;
- cs->hw.hfcpci.timer.data = (long) cs;
- init_timer(&cs->hw.hfcpci.timer);
+ setup_timer(&cs->hw.hfcpci.timer, (void *)hfcpci_Timer, (long)cs);
cs->cardmsg = &hfcpci_card_msg;
cs->auxcmd = &hfcpci_auxcmd;
diff --git a/drivers/isdn/hisax/hfc_sx.c b/drivers/isdn/hisax/hfc_sx.c
index 13b2151..3aef8e1 100644
--- a/drivers/isdn/hisax/hfc_sx.c
+++ b/drivers/isdn/hisax/hfc_sx.c
@@ -1495,9 +1495,7 @@ int setup_hfcsx(struct IsdnCard *card)
} else
return (0); /* no valid card type */
- cs->dbusytimer.function = (void *) hfcsx_dbusy_timer;
- cs->dbusytimer.data = (long) cs;
- init_timer(&cs->dbusytimer);
+ setup_timer(&cs->dbusytimer, (void *)hfcsx_dbusy_timer, (long)cs);
INIT_WORK(&cs->tqueue, hfcsx_bh);
cs->readisac = NULL;
cs->writeisac = NULL;
@@ -1507,11 +1505,9 @@ int setup_hfcsx(struct IsdnCard *card)
cs->BC_Write_Reg = NULL;
cs->irq_func = &hfcsx_interrupt;
- cs->hw.hfcsx.timer.function = (void *) hfcsx_Timer;
- cs->hw.hfcsx.timer.data = (long) cs;
cs->hw.hfcsx.b_fifo_size = 0; /* fifo size still unknown */
cs->hw.hfcsx.cirm = ccd_sp_irqtab[cs->irq & 0xF]; /* RAM not evaluated */
- init_timer(&cs->hw.hfcsx.timer);
+ setup_timer(&cs->hw.hfcsx.timer, (void *)hfcsx_Timer, (long)cs);
reset_hfcsx(cs);
cs->cardmsg = &hfcsx_card_msg;
diff --git a/drivers/isdn/hisax/hfc_usb.c b/drivers/isdn/hisax/hfc_usb.c
index 678bd52..6dbd1f1 100644
--- a/drivers/isdn/hisax/hfc_usb.c
+++ b/drivers/isdn/hisax/hfc_usb.c
@@ -1165,14 +1165,10 @@ hfc_usb_init(hfcusb_data *hfc)
hfc->old_led_state = 0;
/* init the t3 timer */
- init_timer(&hfc->t3_timer);
- hfc->t3_timer.data = (long) hfc;
- hfc->t3_timer.function = (void *) l1_timer_expire_t3;
+ setup_timer(&hfc->t3_timer, (void *)l1_timer_expire_t3, (long)hfc);
/* init the t4 timer */
- init_timer(&hfc->t4_timer);
- hfc->t4_timer.data = (long) hfc;
- hfc->t4_timer.function = (void *) l1_timer_expire_t4;
+ setup_timer(&hfc->t4_timer, (void *)l1_timer_expire_t4, (long)hfc);
/* init the background machinery for control requests */
hfc->ctrl_read.bRequestType = 0xc0;
diff --git a/drivers/isdn/hisax/hfcscard.c b/drivers/isdn/hisax/hfcscard.c
index 394da64..4672870 100644
--- a/drivers/isdn/hisax/hfcscard.c
+++ b/drivers/isdn/hisax/hfcscard.c
@@ -253,9 +253,7 @@ int setup_hfcs(struct IsdnCard *card)
outb(0x57, cs->hw.hfcD.addr | 1);
}
set_cs_func(cs);
- cs->hw.hfcD.timer.function = (void *) hfcs_Timer;
- cs->hw.hfcD.timer.data = (long) cs;
- init_timer(&cs->hw.hfcD.timer);
+ setup_timer(&cs->hw.hfcD.timer, (void *)hfcs_Timer, (long)cs);
cs->cardmsg = &hfcs_card_msg;
cs->irq_func = &hfcs_interrupt;
return (1);
diff --git a/drivers/isdn/hisax/icc.c b/drivers/isdn/hisax/icc.c
index 96d1df0..c7c3797 100644
--- a/drivers/isdn/hisax/icc.c
+++ b/drivers/isdn/hisax/icc.c
@@ -676,7 +676,5 @@ clear_pending_icc_ints(struct IsdnCardState *cs)
void setup_icc(struct IsdnCardState *cs)
{
INIT_WORK(&cs->tqueue, icc_bh);
- cs->dbusytimer.function = (void *) dbusy_timer_handler;
- cs->dbusytimer.data = (long) cs;
- init_timer(&cs->dbusytimer);
+ setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs);
}
diff --git a/drivers/isdn/hisax/ipacx.c b/drivers/isdn/hisax/ipacx.c
index 9cc26b4..43effe7 100644
--- a/drivers/isdn/hisax/ipacx.c
+++ b/drivers/isdn/hisax/ipacx.c
@@ -424,9 +424,7 @@ dch_init(struct IsdnCardState *cs)
cs->setstack_d = dch_setstack;
- cs->dbusytimer.function = (void *) dbusy_timer_handler;
- cs->dbusytimer.data = (long) cs;
- init_timer(&cs->dbusytimer);
+ setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs);
cs->writeisac(cs, IPACX_TR_CONF0, 0x00); // clear LDD
cs->writeisac(cs, IPACX_TR_CONF2, 0x00); // enable transmitter
diff --git a/drivers/isdn/hisax/isac.c b/drivers/isdn/hisax/isac.c
index df7e05c..4273b45 100644
--- a/drivers/isdn/hisax/isac.c
+++ b/drivers/isdn/hisax/isac.c
@@ -677,7 +677,5 @@ void clear_pending_isac_ints(struct IsdnCardState *cs)
void setup_isac(struct IsdnCardState *cs)
{
INIT_WORK(&cs->tqueue, isac_bh);
- cs->dbusytimer.function = (void *) dbusy_timer_handler;
- cs->dbusytimer.data = (long) cs;
- init_timer(&cs->dbusytimer);
+ setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs);
}
diff --git a/drivers/isdn/hisax/isar.c b/drivers/isdn/hisax/isar.c
index f4956c7..0dc60b2 100644
--- a/drivers/isdn/hisax/isar.c
+++ b/drivers/isdn/hisax/isar.c
@@ -1902,10 +1902,8 @@ void initisar(struct IsdnCardState *cs)
cs->bcs[1].BC_SetStack = setstack_isar;
cs->bcs[0].BC_Close = close_isarstate;
cs->bcs[1].BC_Close = close_isarstate;
- cs->bcs[0].hw.isar.ftimer.function = (void *) ftimer_handler;
- cs->bcs[0].hw.isar.ftimer.data = (long) &cs->bcs[0];
- init_timer(&cs->bcs[0].hw.isar.ftimer);
- cs->bcs[1].hw.isar.ftimer.function = (void *) ftimer_handler;
- cs->bcs[1].hw.isar.ftimer.data = (long) &cs->bcs[1];
- init_timer(&cs->bcs[1].hw.isar.ftimer);
+ setup_timer(&cs->bcs[0].hw.isar.ftimer, (void *)ftimer_handler,
+ (long)&cs->bcs[0]);
+ setup_timer(&cs->bcs[1].hw.isar.ftimer, (void *)ftimer_handler,
+ (long)&cs->bcs[1]);
}
diff --git a/drivers/isdn/hisax/isdnl3.c b/drivers/isdn/hisax/isdnl3.c
index c754706..569ce52 100644
--- a/drivers/isdn/hisax/isdnl3.c
+++ b/drivers/isdn/hisax/isdnl3.c
@@ -169,9 +169,7 @@ void
L3InitTimer(struct l3_process *pc, struct L3Timer *t)
{
t->pc = pc;
- t->tl.function = (void *) L3ExpireTimer;
- t->tl.data = (long) t;
- init_timer(&t->tl);
+ setup_timer(&t->tl, (void *)L3ExpireTimer, (long)t);
}
void
diff --git a/drivers/isdn/hisax/st5481_b.c b/drivers/isdn/hisax/st5481_b.c
index 4098491..f64a360 100644
--- a/drivers/isdn/hisax/st5481_b.c
+++ b/drivers/isdn/hisax/st5481_b.c
@@ -239,7 +239,7 @@ static void st5481B_mode(struct st5481_bcs *bcs, int mode)
}
}
} else {
- // Disble B channel interrupts
+ // Disable B channel interrupts
st5481_usb_device_ctrl_msg(adapter, FFMSK_B1+(bcs->channel * 2), 0, NULL, NULL);
// Disable B channel FIFOs
diff --git a/drivers/isdn/hisax/teleint.c b/drivers/isdn/hisax/teleint.c
index bf64754..950399f 100644
--- a/drivers/isdn/hisax/teleint.c
+++ b/drivers/isdn/hisax/teleint.c
@@ -278,9 +278,7 @@ int setup_TeleInt(struct IsdnCard *card)
cs->bcs[0].hw.hfc.send = NULL;
cs->bcs[1].hw.hfc.send = NULL;
cs->hw.hfc.fifosize = 7 * 1024 + 512;
- cs->hw.hfc.timer.function = (void *) TeleInt_Timer;
- cs->hw.hfc.timer.data = (long) cs;
- init_timer(&cs->hw.hfc.timer);
+ setup_timer(&cs->hw.hfc.timer, (void *)TeleInt_Timer, (long)cs);
if (!request_region(cs->hw.hfc.addr, 2, "TeleInt isdn")) {
printk(KERN_WARNING
"HiSax: TeleInt config port %x-%x already in use\n",
diff --git a/drivers/isdn/hisax/w6692.c b/drivers/isdn/hisax/w6692.c
index a858955..c99f0ec 100644
--- a/drivers/isdn/hisax/w6692.c
+++ b/drivers/isdn/hisax/w6692.c
@@ -901,9 +901,8 @@ static void initW6692(struct IsdnCardState *cs, int part)
if (part & 1) {
cs->setstack_d = setstack_W6692;
cs->DC_Close = DC_Close_W6692;
- cs->dbusytimer.function = (void *) dbusy_timer_handler;
- cs->dbusytimer.data = (long) cs;
- init_timer(&cs->dbusytimer);
+ setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler,
+ (long)cs);
resetW6692(cs);
ph_command(cs, W_L1CMD_RST);
cs->dc.w6692.ph_state = W_L1CMD_RST;
diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c
index 9c1e8ad..d07dd51 100644
--- a/drivers/isdn/i4l/isdn_ppp.c
+++ b/drivers/isdn/i4l/isdn_ppp.c
@@ -2370,9 +2370,8 @@ static struct ippp_ccp_reset_state *isdn_ppp_ccp_reset_alloc_state(struct ippp_s
rs->state = CCPResetIdle;
rs->is = is;
rs->id = id;
- init_timer(&rs->timer);
- rs->timer.data = (unsigned long)rs;
- rs->timer.function = isdn_ppp_ccp_timer_callback;
+ setup_timer(&rs->timer, isdn_ppp_ccp_timer_callback,
+ (unsigned long)rs);
is->reset->rs[id] = rs;
}
return rs;
diff --git a/drivers/isdn/i4l/isdn_tty.c b/drivers/isdn/i4l/isdn_tty.c
index 1b16955..ddd8207 100644
--- a/drivers/isdn/i4l/isdn_tty.c
+++ b/drivers/isdn/i4l/isdn_tty.c
@@ -1812,9 +1812,8 @@ isdn_tty_modem_init(void)
info->isdn_channel = -1;
info->drv_index = -1;
info->xmit_size = ISDN_SERIAL_XMIT_SIZE;
- init_timer(&info->nc_timer);
- info->nc_timer.function = isdn_tty_modem_do_ncarrier;
- info->nc_timer.data = (unsigned long) info;
+ setup_timer(&info->nc_timer, isdn_tty_modem_do_ncarrier,
+ (unsigned long)info);
skb_queue_head_init(&info->xmit_queue);
#ifdef CONFIG_ISDN_AUDIO
skb_queue_head_init(&info->dtmf_queue);
diff --git a/drivers/isdn/mISDN/dsp_core.c b/drivers/isdn/mISDN/dsp_core.c
index 9b85295..880e9d3 100644
--- a/drivers/isdn/mISDN/dsp_core.c
+++ b/drivers/isdn/mISDN/dsp_core.c
@@ -1092,9 +1092,7 @@ dspcreate(struct channel_req *crq)
ndsp->pcm_bank_tx = -1;
ndsp->hfc_conf = -1; /* current conference number */
/* set tone timer */
- ndsp->tone.tl.function = (void *)dsp_tone_timeout;
- ndsp->tone.tl.data = (long) ndsp;
- init_timer(&ndsp->tone.tl);
+ setup_timer(&ndsp->tone.tl, (void *)dsp_tone_timeout, (long)ndsp);
if (dtmfthreshold < 20 || dtmfthreshold > 500)
dtmfthreshold = 200;
diff --git a/drivers/isdn/mISDN/fsm.c b/drivers/isdn/mISDN/fsm.c
index 26477d4..78fc5d5 100644
--- a/drivers/isdn/mISDN/fsm.c
+++ b/drivers/isdn/mISDN/fsm.c
@@ -110,13 +110,11 @@ void
mISDN_FsmInitTimer(struct FsmInst *fi, struct FsmTimer *ft)
{
ft->fi = fi;
- ft->tl.function = (void *) FsmExpireTimer;
- ft->tl.data = (long) ft;
#if FSM_TIMER_DEBUG
if (ft->fi->debug)
ft->fi->printdebug(ft->fi, "mISDN_FsmInitTimer %lx", (long) ft);
#endif
- init_timer(&ft->tl);
+ setup_timer(&ft->tl, (void *)FsmExpireTimer, (long)ft);
}
EXPORT_SYMBOL(mISDN_FsmInitTimer);
diff --git a/drivers/isdn/mISDN/l1oip_core.c b/drivers/isdn/mISDN/l1oip_core.c
index 6ceca7d..6be2041 100644
--- a/drivers/isdn/mISDN/l1oip_core.c
+++ b/drivers/isdn/mISDN/l1oip_core.c
@@ -1443,9 +1443,7 @@ init_card(struct l1oip *hc, int pri, int bundle)
hc->keep_tl.expires = jiffies + 2 * HZ; /* two seconds first time */
add_timer(&hc->keep_tl);
- hc->timeout_tl.function = (void *)l1oip_timeout;
- hc->timeout_tl.data = (ulong)hc;
- init_timer(&hc->timeout_tl);
+ setup_timer(&hc->timeout_tl, (void *)l1oip_timeout, (ulong)hc);
hc->timeout_on = 0; /* state that we have timer off */
return 0;
diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c
index 3f041b1..f757cef2 100644
--- a/drivers/macintosh/macio_asic.c
+++ b/drivers/macintosh/macio_asic.c
@@ -392,6 +392,7 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip,
* To get all the fields, copy all archdata
*/
dev->ofdev.dev.archdata = chip->lbus.pdev->dev.archdata;
+ dev->ofdev.dev.dma_ops = chip->lbus.pdev->dev.dma_ops;
#endif /* CONFIG_PCI */
#ifdef DEBUG
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index a126919..5d13930 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -4,7 +4,6 @@
#include <linux/blkdev.h>
#include <linux/errno.h>
-#include <linux/blkdev.h>
#include <linux/kernel.h>
#include <linux/sched/clock.h>
#include <linux/llist.h>
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index f4ffd1e..dfb7597 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -989,26 +989,29 @@ static void flush_current_bio_list(struct blk_plug_cb *cb, bool from_schedule)
struct dm_offload *o = container_of(cb, struct dm_offload, cb);
struct bio_list list;
struct bio *bio;
+ int i;
INIT_LIST_HEAD(&o->cb.list);
if (unlikely(!current->bio_list))
return;
- list = *current->bio_list;
- bio_list_init(current->bio_list);
+ for (i = 0; i < 2; i++) {
+ list = current->bio_list[i];
+ bio_list_init(¤t->bio_list[i]);
- while ((bio = bio_list_pop(&list))) {
- struct bio_set *bs = bio->bi_pool;
- if (unlikely(!bs) || bs == fs_bio_set) {
- bio_list_add(current->bio_list, bio);
- continue;
+ while ((bio = bio_list_pop(&list))) {
+ struct bio_set *bs = bio->bi_pool;
+ if (unlikely(!bs) || bs == fs_bio_set) {
+ bio_list_add(¤t->bio_list[i], bio);
+ continue;
+ }
+
+ spin_lock(&bs->rescue_lock);
+ bio_list_add(&bs->rescue_list, bio);
+ queue_work(bs->rescue_workqueue, &bs->rescue_work);
+ spin_unlock(&bs->rescue_lock);
}
-
- spin_lock(&bs->rescue_lock);
- bio_list_add(&bs->rescue_list, bio);
- queue_work(bs->rescue_workqueue, &bs->rescue_work);
- spin_unlock(&bs->rescue_lock);
}
}
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 2b13117..321ecac 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -777,7 +777,6 @@ static int gather_all_resync_info(struct mddev *mddev, int total_slots)
bm_lockres->flags |= DLM_LKF_NOQUEUE;
ret = dlm_lock_sync(bm_lockres, DLM_LOCK_PW);
if (ret == -EAGAIN) {
- memset(bm_lockres->lksb.sb_lvbptr, '\0', LVB_SIZE);
s = read_resync_info(mddev, bm_lockres);
if (s) {
pr_info("%s:%d Resync[%llu..%llu] in progress on %d\n",
@@ -974,6 +973,7 @@ static int leave(struct mddev *mddev)
lockres_free(cinfo->bitmap_lockres);
unlock_all_bitmaps(mddev);
dlm_release_lockspace(cinfo->lockspace, 2);
+ kfree(cinfo);
return 0;
}
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 548d1b8..f6ae1d6 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -440,14 +440,6 @@ void md_flush_request(struct mddev *mddev, struct bio *bio)
}
EXPORT_SYMBOL(md_flush_request);
-void md_unplug(struct blk_plug_cb *cb, bool from_schedule)
-{
- struct mddev *mddev = cb->data;
- md_wakeup_thread(mddev->thread);
- kfree(cb);
-}
-EXPORT_SYMBOL(md_unplug);
-
static inline struct mddev *mddev_get(struct mddev *mddev)
{
atomic_inc(&mddev->active);
@@ -1887,7 +1879,7 @@ super_1_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
}
sb = page_address(rdev->sb_page);
sb->data_size = cpu_to_le64(num_sectors);
- sb->super_offset = rdev->sb_start;
+ sb->super_offset = cpu_to_le64(rdev->sb_start);
sb->sb_csum = calc_sb_1_csum(sb);
do {
md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
@@ -2295,7 +2287,7 @@ static bool does_sb_need_changing(struct mddev *mddev)
/* Check if any mddev parameters have changed */
if ((mddev->dev_sectors != le64_to_cpu(sb->size)) ||
(mddev->reshape_position != le64_to_cpu(sb->reshape_position)) ||
- (mddev->layout != le64_to_cpu(sb->layout)) ||
+ (mddev->layout != le32_to_cpu(sb->layout)) ||
(mddev->raid_disks != le32_to_cpu(sb->raid_disks)) ||
(mddev->chunk_sectors != le32_to_cpu(sb->chunksize)))
return true;
@@ -6458,11 +6450,10 @@ static int set_array_info(struct mddev *mddev, mdu_array_info_t *info)
mddev->layout = info->layout;
mddev->chunk_sectors = info->chunk_size >> 9;
- mddev->max_disks = MD_SB_DISKS;
-
if (mddev->persistent) {
- mddev->flags = 0;
- mddev->sb_flags = 0;
+ mddev->max_disks = MD_SB_DISKS;
+ mddev->flags = 0;
+ mddev->sb_flags = 0;
}
set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
@@ -6533,8 +6524,12 @@ static int update_size(struct mddev *mddev, sector_t num_sectors)
return -ENOSPC;
}
rv = mddev->pers->resize(mddev, num_sectors);
- if (!rv)
- revalidate_disk(mddev->gendisk);
+ if (!rv) {
+ if (mddev->queue) {
+ set_capacity(mddev->gendisk, mddev->array_sectors);
+ revalidate_disk(mddev->gendisk);
+ }
+ }
return rv;
}
diff --git a/drivers/md/md.h b/drivers/md/md.h
index b8859cb..dde8ecb 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -676,16 +676,10 @@ extern void mddev_resume(struct mddev *mddev);
extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
struct mddev *mddev);
-extern void md_unplug(struct blk_plug_cb *cb, bool from_schedule);
extern void md_reload_sb(struct mddev *mddev, int raid_disk);
extern void md_update_sb(struct mddev *mddev, int force);
extern void md_kick_rdev_from_array(struct md_rdev * rdev);
struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr);
-static inline int mddev_check_plugged(struct mddev *mddev)
-{
- return !!blk_check_plugged(md_unplug, mddev,
- sizeof(struct blk_plug_cb));
-}
static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev)
{
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index fbc2d78..a34f587 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1027,7 +1027,7 @@ static int get_unqueued_pending(struct r1conf *conf)
static void freeze_array(struct r1conf *conf, int extra)
{
/* Stop sync I/O and normal I/O and wait for everything to
- * go quite.
+ * go quiet.
* This is called in two situations:
* 1) management command handlers (reshape, remove disk, quiesce).
* 2) one normal I/O request failed.
@@ -1587,9 +1587,30 @@ static void raid1_make_request(struct mddev *mddev, struct bio *bio)
split = bio;
}
- if (bio_data_dir(split) == READ)
+ if (bio_data_dir(split) == READ) {
raid1_read_request(mddev, split);
- else
+
+ /*
+ * If a bio is splitted, the first part of bio will
+ * pass barrier but the bio is queued in
+ * current->bio_list (see generic_make_request). If
+ * there is a raise_barrier() called here, the second
+ * part of bio can't pass barrier. But since the first
+ * part bio isn't dispatched to underlaying disks yet,
+ * the barrier is never released, hence raise_barrier
+ * will alays wait. We have a deadlock.
+ * Note, this only happens in read path. For write
+ * path, the first part of bio is dispatched in a
+ * schedule() call (because of blk plug) or offloaded
+ * to raid10d.
+ * Quitting from the function immediately can change
+ * the bio order queued in bio_list and avoid the deadlock.
+ */
+ if (split != bio) {
+ generic_make_request(bio);
+ break;
+ }
+ } else
raid1_write_request(mddev, split);
} while (split != bio);
}
@@ -3246,8 +3267,6 @@ static int raid1_resize(struct mddev *mddev, sector_t sectors)
return ret;
}
md_set_array_sectors(mddev, newsize);
- set_capacity(mddev->gendisk, mddev->array_sectors);
- revalidate_disk(mddev->gendisk);
if (sectors > mddev->dev_sectors &&
mddev->recovery_cp > mddev->dev_sectors) {
mddev->recovery_cp = mddev->dev_sectors;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 063c43d..e89a8d7 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -974,7 +974,8 @@ static void wait_barrier(struct r10conf *conf)
!conf->barrier ||
(atomic_read(&conf->nr_pending) &&
current->bio_list &&
- !bio_list_empty(current->bio_list)),
+ (!bio_list_empty(¤t->bio_list[0]) ||
+ !bio_list_empty(¤t->bio_list[1]))),
conf->resync_lock);
conf->nr_waiting--;
if (!conf->nr_waiting)
@@ -1477,11 +1478,24 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
mbio->bi_bdev = (void*)rdev;
atomic_inc(&r10_bio->remaining);
+
+ cb = blk_check_plugged(raid10_unplug, mddev,
+ sizeof(*plug));
+ if (cb)
+ plug = container_of(cb, struct raid10_plug_cb,
+ cb);
+ else
+ plug = NULL;
spin_lock_irqsave(&conf->device_lock, flags);
- bio_list_add(&conf->pending_bio_list, mbio);
- conf->pending_count++;
+ if (plug) {
+ bio_list_add(&plug->pending, mbio);
+ plug->pending_cnt++;
+ } else {
+ bio_list_add(&conf->pending_bio_list, mbio);
+ conf->pending_count++;
+ }
spin_unlock_irqrestore(&conf->device_lock, flags);
- if (!mddev_check_plugged(mddev))
+ if (!plug)
md_wakeup_thread(mddev->thread);
}
}
@@ -1571,7 +1585,25 @@ static void raid10_make_request(struct mddev *mddev, struct bio *bio)
split = bio;
}
+ /*
+ * If a bio is splitted, the first part of bio will pass
+ * barrier but the bio is queued in current->bio_list (see
+ * generic_make_request). If there is a raise_barrier() called
+ * here, the second part of bio can't pass barrier. But since
+ * the first part bio isn't dispatched to underlaying disks
+ * yet, the barrier is never released, hence raise_barrier will
+ * alays wait. We have a deadlock.
+ * Note, this only happens in read path. For write path, the
+ * first part of bio is dispatched in a schedule() call
+ * (because of blk plug) or offloaded to raid10d.
+ * Quitting from the function immediately can change the bio
+ * order queued in bio_list and avoid the deadlock.
+ */
__make_request(mddev, split);
+ if (split != bio && bio_data_dir(bio) == READ) {
+ generic_make_request(bio);
+ break;
+ }
} while (split != bio);
/* In case raid10d snuck in to freeze_array */
@@ -3943,10 +3975,6 @@ static int raid10_resize(struct mddev *mddev, sector_t sectors)
return ret;
}
md_set_array_sectors(mddev, size);
- if (mddev->queue) {
- set_capacity(mddev->gendisk, mddev->array_sectors);
- revalidate_disk(mddev->gendisk);
- }
if (sectors > mddev->dev_sectors &&
mddev->recovery_cp > oldsize) {
mddev->recovery_cp = oldsize;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 4fb09b3..ed5cd70 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1401,7 +1401,8 @@ static int set_syndrome_sources(struct page **srcs,
(test_bit(R5_Wantdrain, &dev->flags) ||
test_bit(R5_InJournal, &dev->flags))) ||
(srctype == SYNDROME_SRC_WRITTEN &&
- dev->written)) {
+ (dev->written ||
+ test_bit(R5_InJournal, &dev->flags)))) {
if (test_bit(R5_InJournal, &dev->flags))
srcs[slot] = sh->dev[i].orig_page;
else
@@ -7605,8 +7606,6 @@ static int raid5_resize(struct mddev *mddev, sector_t sectors)
return ret;
}
md_set_array_sectors(mddev, newsize);
- set_capacity(mddev->gendisk, mddev->array_sectors);
- revalidate_disk(mddev->gendisk);
if (sectors > mddev->dev_sectors &&
mddev->recovery_cp > mddev->dev_sectors) {
mddev->recovery_cp = mddev->dev_sectors;
diff --git a/drivers/media/dvb-frontends/drx39xyj/drx_driver.h b/drivers/media/dvb-frontends/drx39xyj/drx_driver.h
index 7a681d82..4442e47 100644
--- a/drivers/media/dvb-frontends/drx39xyj/drx_driver.h
+++ b/drivers/media/dvb-frontends/drx39xyj/drx_driver.h
@@ -256,8 +256,7 @@ int drxbsp_tuner_default_i2c_write_read(struct tuner_instance *tuner,
*
* The actual DAP implementation may be restricted to only one of the modes.
* A compiler warning or error will be generated if the DAP implementation
-* overides or cannot handle the mode defined below.
-*
+* overrides or cannot handle the mode defined below.
*/
#ifndef DRXDAP_SINGLE_MASTER
#define DRXDAP_SINGLE_MASTER 1
@@ -272,7 +271,7 @@ int drxbsp_tuner_default_i2c_write_read(struct tuner_instance *tuner,
*
* This maximum size may be restricted by the actual DAP implementation.
* A compiler warning or error will be generated if the DAP implementation
-* overides or cannot handle the chunksize defined below.
+* overrides or cannot handle the chunksize defined below.
*
* Beware that the DAP uses DRXDAP_MAX_WCHUNKSIZE to create a temporary data
* buffer. Do not undefine or choose too large, unless your system is able to
@@ -292,8 +291,7 @@ int drxbsp_tuner_default_i2c_write_read(struct tuner_instance *tuner,
*
* This maximum size may be restricted by the actual DAP implementation.
* A compiler warning or error will be generated if the DAP implementation
-* overides or cannot handle the chunksize defined below.
-*
+* overrides or cannot handle the chunksize defined below.
*/
#ifndef DRXDAP_MAX_RCHUNKSIZE
#define DRXDAP_MAX_RCHUNKSIZE 60
diff --git a/drivers/media/platform/coda/imx-vdoa.c b/drivers/media/platform/coda/imx-vdoa.c
index 67fd8ff..669a4c8 100644
--- a/drivers/media/platform/coda/imx-vdoa.c
+++ b/drivers/media/platform/coda/imx-vdoa.c
@@ -321,7 +321,7 @@ static const struct of_device_id vdoa_dt_ids[] = {
};
MODULE_DEVICE_TABLE(of, vdoa_dt_ids);
-static const struct platform_driver vdoa_driver = {
+static struct platform_driver vdoa_driver = {
.probe = vdoa_probe,
.remove = vdoa_remove,
.driver = {
diff --git a/drivers/media/platform/exynos-gsc/gsc-core.c b/drivers/media/platform/exynos-gsc/gsc-core.c
index cbb0376..0f0c389 100644
--- a/drivers/media/platform/exynos-gsc/gsc-core.c
+++ b/drivers/media/platform/exynos-gsc/gsc-core.c
@@ -861,9 +861,7 @@ int gsc_prepare_addr(struct gsc_ctx *ctx, struct vb2_buffer *vb,
if ((frame->fmt->pixelformat == V4L2_PIX_FMT_VYUY) ||
(frame->fmt->pixelformat == V4L2_PIX_FMT_YVYU) ||
- (frame->fmt->pixelformat == V4L2_PIX_FMT_NV61) ||
(frame->fmt->pixelformat == V4L2_PIX_FMT_YVU420) ||
- (frame->fmt->pixelformat == V4L2_PIX_FMT_NV21) ||
(frame->fmt->pixelformat == V4L2_PIX_FMT_YVU420M))
swap(addr->cb, addr->cr);
diff --git a/drivers/media/platform/sti/bdisp/bdisp-v4l2.c b/drivers/media/platform/sti/bdisp/bdisp-v4l2.c
index 8236081..7918b92 100644
--- a/drivers/media/platform/sti/bdisp/bdisp-v4l2.c
+++ b/drivers/media/platform/sti/bdisp/bdisp-v4l2.c
@@ -632,8 +632,8 @@ static int bdisp_open(struct file *file)
error_ctrls:
bdisp_ctrls_delete(ctx);
-error_fh:
v4l2_fh_del(&ctx->fh);
+error_fh:
v4l2_fh_exit(&ctx->fh);
bdisp_hw_free_nodes(ctx);
mem_ctx:
diff --git a/drivers/media/platform/vsp1/vsp1_drm.c b/drivers/media/platform/vsp1/vsp1_drm.c
index b4b583f..b4c0f10 100644
--- a/drivers/media/platform/vsp1/vsp1_drm.c
+++ b/drivers/media/platform/vsp1/vsp1_drm.c
@@ -54,12 +54,11 @@ EXPORT_SYMBOL_GPL(vsp1_du_init);
/**
* vsp1_du_setup_lif - Setup the output part of the VSP pipeline
* @dev: the VSP device
- * @width: output frame width in pixels
- * @height: output frame height in pixels
+ * @cfg: the LIF configuration
*
- * Configure the output part of VSP DRM pipeline for the given frame @width and
- * @height. This sets up formats on the BRU source pad, the WPF0 sink and source
- * pads, and the LIF sink pad.
+ * Configure the output part of VSP DRM pipeline for the given frame @cfg.width
+ * and @cfg.height. This sets up formats on the BRU source pad, the WPF0 sink
+ * and source pads, and the LIF sink pad.
*
* As the media bus code on the BRU source pad is conditioned by the
* configuration of the BRU sink 0 pad, we also set up the formats on all BRU
@@ -69,8 +68,7 @@ EXPORT_SYMBOL_GPL(vsp1_du_init);
*
* Return 0 on success or a negative error code on failure.
*/
-int vsp1_du_setup_lif(struct device *dev, unsigned int width,
- unsigned int height)
+int vsp1_du_setup_lif(struct device *dev, const struct vsp1_du_lif_config *cfg)
{
struct vsp1_device *vsp1 = dev_get_drvdata(dev);
struct vsp1_pipeline *pipe = &vsp1->drm->pipe;
@@ -79,11 +77,8 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int width,
unsigned int i;
int ret;
- dev_dbg(vsp1->dev, "%s: configuring LIF with format %ux%u\n",
- __func__, width, height);
-
- if (width == 0 || height == 0) {
- /* Zero width or height means the CRTC is being disabled, stop
+ if (!cfg) {
+ /* NULL configuration means the CRTC is being disabled, stop
* the pipeline and turn the light off.
*/
ret = vsp1_pipeline_stop(pipe);
@@ -108,6 +103,9 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int width,
return 0;
}
+ dev_dbg(vsp1->dev, "%s: configuring LIF with format %ux%u\n",
+ __func__, cfg->width, cfg->height);
+
/* Configure the format at the BRU sinks and propagate it through the
* pipeline.
*/
@@ -117,8 +115,8 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int width,
for (i = 0; i < bru->entity.source_pad; ++i) {
format.pad = i;
- format.format.width = width;
- format.format.height = height;
+ format.format.width = cfg->width;
+ format.format.height = cfg->height;
format.format.code = MEDIA_BUS_FMT_ARGB8888_1X32;
format.format.field = V4L2_FIELD_NONE;
@@ -133,8 +131,8 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int width,
}
format.pad = bru->entity.source_pad;
- format.format.width = width;
- format.format.height = height;
+ format.format.width = cfg->width;
+ format.format.height = cfg->height;
format.format.code = MEDIA_BUS_FMT_ARGB8888_1X32;
format.format.field = V4L2_FIELD_NONE;
@@ -180,7 +178,8 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int width,
/* Verify that the format at the output of the pipeline matches the
* requested frame size and media bus code.
*/
- if (format.format.width != width || format.format.height != height ||
+ if (format.format.width != cfg->width ||
+ format.format.height != cfg->height ||
format.format.code != MEDIA_BUS_FMT_ARGB8888_1X32) {
dev_dbg(vsp1->dev, "%s: format mismatch\n", __func__);
return -EPIPE;
diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c
index 393dcca..1688893 100644
--- a/drivers/media/rc/lirc_dev.c
+++ b/drivers/media/rc/lirc_dev.c
@@ -436,6 +436,8 @@ int lirc_dev_fop_open(struct inode *inode, struct file *file)
return -ERESTARTSYS;
ir = irctls[iminor(inode)];
+ mutex_unlock(&lirc_dev_lock);
+
if (!ir) {
retval = -ENODEV;
goto error;
@@ -476,8 +478,6 @@ int lirc_dev_fop_open(struct inode *inode, struct file *file)
}
error:
- mutex_unlock(&lirc_dev_lock);
-
nonseekable_open(inode, file);
return retval;
diff --git a/drivers/media/rc/nuvoton-cir.c b/drivers/media/rc/nuvoton-cir.c
index b109f82..ec4b25b 100644
--- a/drivers/media/rc/nuvoton-cir.c
+++ b/drivers/media/rc/nuvoton-cir.c
@@ -176,12 +176,13 @@ static void nvt_write_wakeup_codes(struct rc_dev *dev,
{
u8 tolerance, config;
struct nvt_dev *nvt = dev->priv;
+ unsigned long flags;
int i;
/* hardcode the tolerance to 10% */
tolerance = DIV_ROUND_UP(count, 10);
- spin_lock(&nvt->lock);
+ spin_lock_irqsave(&nvt->lock, flags);
nvt_clear_cir_wake_fifo(nvt);
nvt_cir_wake_reg_write(nvt, count, CIR_WAKE_FIFO_CMP_DEEP);
@@ -203,7 +204,7 @@ static void nvt_write_wakeup_codes(struct rc_dev *dev,
nvt_cir_wake_reg_write(nvt, config, CIR_WAKE_IRCON);
- spin_unlock(&nvt->lock);
+ spin_unlock_irqrestore(&nvt->lock, flags);
}
static ssize_t wakeup_data_show(struct device *dev,
diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c
index 2424946..d845336 100644
--- a/drivers/media/rc/rc-main.c
+++ b/drivers/media/rc/rc-main.c
@@ -1663,6 +1663,7 @@ static int rc_setup_rx_device(struct rc_dev *dev)
{
int rc;
struct rc_map *rc_map;
+ u64 rc_type;
if (!dev->map_name)
return -EINVAL;
@@ -1677,15 +1678,18 @@ static int rc_setup_rx_device(struct rc_dev *dev)
if (rc)
return rc;
- if (dev->change_protocol) {
- u64 rc_type = (1ll << rc_map->rc_type);
+ rc_type = BIT_ULL(rc_map->rc_type);
+ if (dev->change_protocol) {
rc = dev->change_protocol(dev, &rc_type);
if (rc < 0)
goto out_table;
dev->enabled_protocols = rc_type;
}
+ if (dev->driver_type == RC_DRIVER_IR_RAW)
+ ir_raw_load_modules(&rc_type);
+
set_bit(EV_KEY, dev->input_dev->evbit);
set_bit(EV_REP, dev->input_dev->evbit);
set_bit(EV_MSC, dev->input_dev->evbit);
@@ -1777,12 +1781,6 @@ int rc_register_device(struct rc_dev *dev)
dev->input_name ?: "Unspecified device", path ?: "N/A");
kfree(path);
- if (dev->driver_type != RC_DRIVER_IR_RAW_TX) {
- rc = rc_setup_rx_device(dev);
- if (rc)
- goto out_dev;
- }
-
if (dev->driver_type == RC_DRIVER_IR_RAW ||
dev->driver_type == RC_DRIVER_IR_RAW_TX) {
if (!raw_init) {
@@ -1791,7 +1789,13 @@ int rc_register_device(struct rc_dev *dev)
}
rc = ir_raw_event_register(dev);
if (rc < 0)
- goto out_rx;
+ goto out_dev;
+ }
+
+ if (dev->driver_type != RC_DRIVER_IR_RAW_TX) {
+ rc = rc_setup_rx_device(dev);
+ if (rc)
+ goto out_raw;
}
/* Allow the RC sysfs nodes to be accessible */
@@ -1803,8 +1807,8 @@ int rc_register_device(struct rc_dev *dev)
return 0;
-out_rx:
- rc_free_rx_device(dev);
+out_raw:
+ ir_raw_event_unregister(dev);
out_dev:
device_del(&dev->dev);
out_unlock:
diff --git a/drivers/media/rc/serial_ir.c b/drivers/media/rc/serial_ir.c
index 923fb22..41b54e4 100644
--- a/drivers/media/rc/serial_ir.c
+++ b/drivers/media/rc/serial_ir.c
@@ -487,10 +487,69 @@ static void serial_ir_timeout(unsigned long arg)
ir_raw_event_handle(serial_ir.rcdev);
}
+/* Needed by serial_ir_probe() */
+static int serial_ir_tx(struct rc_dev *dev, unsigned int *txbuf,
+ unsigned int count);
+static int serial_ir_tx_duty_cycle(struct rc_dev *dev, u32 cycle);
+static int serial_ir_tx_carrier(struct rc_dev *dev, u32 carrier);
+static int serial_ir_open(struct rc_dev *rcdev);
+static void serial_ir_close(struct rc_dev *rcdev);
+
static int serial_ir_probe(struct platform_device *dev)
{
+ struct rc_dev *rcdev;
int i, nlow, nhigh, result;
+ rcdev = devm_rc_allocate_device(&dev->dev, RC_DRIVER_IR_RAW);
+ if (!rcdev)
+ return -ENOMEM;
+
+ if (hardware[type].send_pulse && hardware[type].send_space)
+ rcdev->tx_ir = serial_ir_tx;
+ if (hardware[type].set_send_carrier)
+ rcdev->s_tx_carrier = serial_ir_tx_carrier;
+ if (hardware[type].set_duty_cycle)
+ rcdev->s_tx_duty_cycle = serial_ir_tx_duty_cycle;
+
+ switch (type) {
+ case IR_HOMEBREW:
+ rcdev->input_name = "Serial IR type home-brew";
+ break;
+ case IR_IRDEO:
+ rcdev->input_name = "Serial IR type IRdeo";
+ break;
+ case IR_IRDEO_REMOTE:
+ rcdev->input_name = "Serial IR type IRdeo remote";
+ break;
+ case IR_ANIMAX:
+ rcdev->input_name = "Serial IR type AnimaX";
+ break;
+ case IR_IGOR:
+ rcdev->input_name = "Serial IR type IgorPlug";
+ break;
+ }
+
+ rcdev->input_phys = KBUILD_MODNAME "/input0";
+ rcdev->input_id.bustype = BUS_HOST;
+ rcdev->input_id.vendor = 0x0001;
+ rcdev->input_id.product = 0x0001;
+ rcdev->input_id.version = 0x0100;
+ rcdev->open = serial_ir_open;
+ rcdev->close = serial_ir_close;
+ rcdev->dev.parent = &serial_ir.pdev->dev;
+ rcdev->allowed_protocols = RC_BIT_ALL_IR_DECODER;
+ rcdev->driver_name = KBUILD_MODNAME;
+ rcdev->map_name = RC_MAP_RC6_MCE;
+ rcdev->min_timeout = 1;
+ rcdev->timeout = IR_DEFAULT_TIMEOUT;
+ rcdev->max_timeout = 10 * IR_DEFAULT_TIMEOUT;
+ rcdev->rx_resolution = 250000;
+
+ serial_ir.rcdev = rcdev;
+
+ setup_timer(&serial_ir.timeout_timer, serial_ir_timeout,
+ (unsigned long)&serial_ir);
+
result = devm_request_irq(&dev->dev, irq, serial_ir_irq_handler,
share_irq ? IRQF_SHARED : 0,
KBUILD_MODNAME, &hardware);
@@ -516,9 +575,6 @@ static int serial_ir_probe(struct platform_device *dev)
return -EBUSY;
}
- setup_timer(&serial_ir.timeout_timer, serial_ir_timeout,
- (unsigned long)&serial_ir);
-
result = hardware_init_port();
if (result < 0)
return result;
@@ -552,7 +608,8 @@ static int serial_ir_probe(struct platform_device *dev)
sense ? "low" : "high");
dev_dbg(&dev->dev, "Interrupt %d, port %04x obtained\n", irq, io);
- return 0;
+
+ return devm_rc_register_device(&dev->dev, rcdev);
}
static int serial_ir_open(struct rc_dev *rcdev)
@@ -723,7 +780,6 @@ static void serial_ir_exit(void)
static int __init serial_ir_init_module(void)
{
- struct rc_dev *rcdev;
int result;
switch (type) {
@@ -754,63 +810,9 @@ static int __init serial_ir_init_module(void)
sense = !!sense;
result = serial_ir_init();
- if (result)
- return result;
-
- rcdev = devm_rc_allocate_device(&serial_ir.pdev->dev, RC_DRIVER_IR_RAW);
- if (!rcdev) {
- result = -ENOMEM;
- goto serial_cleanup;
- }
-
- if (hardware[type].send_pulse && hardware[type].send_space)
- rcdev->tx_ir = serial_ir_tx;
- if (hardware[type].set_send_carrier)
- rcdev->s_tx_carrier = serial_ir_tx_carrier;
- if (hardware[type].set_duty_cycle)
- rcdev->s_tx_duty_cycle = serial_ir_tx_duty_cycle;
-
- switch (type) {
- case IR_HOMEBREW:
- rcdev->input_name = "Serial IR type home-brew";
- break;
- case IR_IRDEO:
- rcdev->input_name = "Serial IR type IRdeo";
- break;
- case IR_IRDEO_REMOTE:
- rcdev->input_name = "Serial IR type IRdeo remote";
- break;
- case IR_ANIMAX:
- rcdev->input_name = "Serial IR type AnimaX";
- break;
- case IR_IGOR:
- rcdev->input_name = "Serial IR type IgorPlug";
- break;
- }
-
- rcdev->input_phys = KBUILD_MODNAME "/input0";
- rcdev->input_id.bustype = BUS_HOST;
- rcdev->input_id.vendor = 0x0001;
- rcdev->input_id.product = 0x0001;
- rcdev->input_id.version = 0x0100;
- rcdev->open = serial_ir_open;
- rcdev->close = serial_ir_close;
- rcdev->dev.parent = &serial_ir.pdev->dev;
- rcdev->allowed_protocols = RC_BIT_ALL_IR_DECODER;
- rcdev->driver_name = KBUILD_MODNAME;
- rcdev->map_name = RC_MAP_RC6_MCE;
- rcdev->min_timeout = 1;
- rcdev->timeout = IR_DEFAULT_TIMEOUT;
- rcdev->max_timeout = 10 * IR_DEFAULT_TIMEOUT;
- rcdev->rx_resolution = 250000;
-
- serial_ir.rcdev = rcdev;
-
- result = rc_register_device(rcdev);
-
if (!result)
return 0;
-serial_cleanup:
+
serial_ir_exit();
return result;
}
@@ -818,7 +820,6 @@ static int __init serial_ir_init_module(void)
static void __exit serial_ir_exit_module(void)
{
del_timer_sync(&serial_ir.timeout_timer);
- rc_unregister_device(serial_ir.rcdev);
serial_ir_exit();
}
diff --git a/drivers/media/usb/dvb-usb/dvb-usb-firmware.c b/drivers/media/usb/dvb-usb/dvb-usb-firmware.c
index ab98660..04033ef 100644
--- a/drivers/media/usb/dvb-usb/dvb-usb-firmware.c
+++ b/drivers/media/usb/dvb-usb/dvb-usb-firmware.c
@@ -36,16 +36,18 @@ static int usb_cypress_writemem(struct usb_device *udev,u16 addr,u8 *data, u8 le
int usb_cypress_load_firmware(struct usb_device *udev, const struct firmware *fw, int type)
{
struct hexline *hx;
- u8 reset;
- int ret,pos=0;
+ u8 *buf;
+ int ret, pos = 0;
+ u16 cpu_cs_register = cypress[type].cpu_cs_register;
- hx = kmalloc(sizeof(*hx), GFP_KERNEL);
- if (!hx)
+ buf = kmalloc(sizeof(*hx), GFP_KERNEL);
+ if (!buf)
return -ENOMEM;
+ hx = (struct hexline *)buf;
/* stop the CPU */
- reset = 1;
- if ((ret = usb_cypress_writemem(udev,cypress[type].cpu_cs_register,&reset,1)) != 1)
+ buf[0] = 1;
+ if (usb_cypress_writemem(udev, cpu_cs_register, buf, 1) != 1)
err("could not stop the USB controller CPU.");
while ((ret = dvb_usb_get_hexline(fw, hx, &pos)) > 0) {
@@ -61,21 +63,21 @@ int usb_cypress_load_firmware(struct usb_device *udev, const struct firmware *fw
}
if (ret < 0) {
err("firmware download failed at %d with %d",pos,ret);
- kfree(hx);
+ kfree(buf);
return ret;
}
if (ret == 0) {
/* restart the CPU */
- reset = 0;
- if (ret || usb_cypress_writemem(udev,cypress[type].cpu_cs_register,&reset,1) != 1) {
+ buf[0] = 0;
+ if (usb_cypress_writemem(udev, cpu_cs_register, buf, 1) != 1) {
err("could not restart the USB controller CPU.");
ret = -EINVAL;
}
} else
ret = -EIO;
- kfree(hx);
+ kfree(buf);
return ret;
}
diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c
index 6ca502d..4f42d57 100644
--- a/drivers/media/usb/dvb-usb/dw2102.c
+++ b/drivers/media/usb/dvb-usb/dw2102.c
@@ -68,6 +68,7 @@
struct dw2102_state {
u8 initialized;
u8 last_lock;
+ u8 data[MAX_XFER_SIZE + 4];
struct i2c_client *i2c_client_demod;
struct i2c_client *i2c_client_tuner;
@@ -661,62 +662,72 @@ static int su3000_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[],
int num)
{
struct dvb_usb_device *d = i2c_get_adapdata(adap);
- u8 obuf[0x40], ibuf[0x40];
+ struct dw2102_state *state;
if (!d)
return -ENODEV;
+
+ state = d->priv;
+
if (mutex_lock_interruptible(&d->i2c_mutex) < 0)
return -EAGAIN;
+ if (mutex_lock_interruptible(&d->data_mutex) < 0) {
+ mutex_unlock(&d->i2c_mutex);
+ return -EAGAIN;
+ }
switch (num) {
case 1:
switch (msg[0].addr) {
case SU3000_STREAM_CTRL:
- obuf[0] = msg[0].buf[0] + 0x36;
- obuf[1] = 3;
- obuf[2] = 0;
- if (dvb_usb_generic_rw(d, obuf, 3, ibuf, 0, 0) < 0)
+ state->data[0] = msg[0].buf[0] + 0x36;
+ state->data[1] = 3;
+ state->data[2] = 0;
+ if (dvb_usb_generic_rw(d, state->data, 3,
+ state->data, 0, 0) < 0)
err("i2c transfer failed.");
break;
case DW2102_RC_QUERY:
- obuf[0] = 0x10;
- if (dvb_usb_generic_rw(d, obuf, 1, ibuf, 2, 0) < 0)
+ state->data[0] = 0x10;
+ if (dvb_usb_generic_rw(d, state->data, 1,
+ state->data, 2, 0) < 0)
err("i2c transfer failed.");
- msg[0].buf[1] = ibuf[0];
- msg[0].buf[0] = ibuf[1];
+ msg[0].buf[1] = state->data[0];
+ msg[0].buf[0] = state->data[1];
break;
default:
/* always i2c write*/
- obuf[0] = 0x08;
- obuf[1] = msg[0].addr;
- obuf[2] = msg[0].len;
+ state->data[0] = 0x08;
+ state->data[1] = msg[0].addr;
+ state->data[2] = msg[0].len;
- memcpy(&obuf[3], msg[0].buf, msg[0].len);
+ memcpy(&state->data[3], msg[0].buf, msg[0].len);
- if (dvb_usb_generic_rw(d, obuf, msg[0].len + 3,
- ibuf, 1, 0) < 0)
+ if (dvb_usb_generic_rw(d, state->data, msg[0].len + 3,
+ state->data, 1, 0) < 0)
err("i2c transfer failed.");
}
break;
case 2:
/* always i2c read */
- obuf[0] = 0x09;
- obuf[1] = msg[0].len;
- obuf[2] = msg[1].len;
- obuf[3] = msg[0].addr;
- memcpy(&obuf[4], msg[0].buf, msg[0].len);
+ state->data[0] = 0x09;
+ state->data[1] = msg[0].len;
+ state->data[2] = msg[1].len;
+ state->data[3] = msg[0].addr;
+ memcpy(&state->data[4], msg[0].buf, msg[0].len);
- if (dvb_usb_generic_rw(d, obuf, msg[0].len + 4,
- ibuf, msg[1].len + 1, 0) < 0)
+ if (dvb_usb_generic_rw(d, state->data, msg[0].len + 4,
+ state->data, msg[1].len + 1, 0) < 0)
err("i2c transfer failed.");
- memcpy(msg[1].buf, &ibuf[1], msg[1].len);
+ memcpy(msg[1].buf, &state->data[1], msg[1].len);
break;
default:
warn("more than 2 i2c messages at a time is not handled yet.");
break;
}
+ mutex_unlock(&d->data_mutex);
mutex_unlock(&d->i2c_mutex);
return num;
}
@@ -844,17 +855,23 @@ static int su3000_streaming_ctrl(struct dvb_usb_adapter *adap, int onoff)
static int su3000_power_ctrl(struct dvb_usb_device *d, int i)
{
struct dw2102_state *state = (struct dw2102_state *)d->priv;
- u8 obuf[] = {0xde, 0};
+ int ret = 0;
info("%s: %d, initialized %d", __func__, i, state->initialized);
if (i && !state->initialized) {
+ mutex_lock(&d->data_mutex);
+
+ state->data[0] = 0xde;
+ state->data[1] = 0;
+
state->initialized = 1;
/* reset board */
- return dvb_usb_generic_rw(d, obuf, 2, NULL, 0, 0);
+ ret = dvb_usb_generic_rw(d, state->data, 2, NULL, 0, 0);
+ mutex_unlock(&d->data_mutex);
}
- return 0;
+ return ret;
}
static int su3000_read_mac_address(struct dvb_usb_device *d, u8 mac[6])
@@ -1309,49 +1326,57 @@ static int prof_7500_frontend_attach(struct dvb_usb_adapter *d)
return 0;
}
-static int su3000_frontend_attach(struct dvb_usb_adapter *d)
+static int su3000_frontend_attach(struct dvb_usb_adapter *adap)
{
- u8 obuf[3] = { 0xe, 0x80, 0 };
- u8 ibuf[] = { 0 };
+ struct dvb_usb_device *d = adap->dev;
+ struct dw2102_state *state = d->priv;
- if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+ mutex_lock(&d->data_mutex);
+
+ state->data[0] = 0xe;
+ state->data[1] = 0x80;
+ state->data[2] = 0;
+
+ if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
err("command 0x0e transfer failed.");
- obuf[0] = 0xe;
- obuf[1] = 0x02;
- obuf[2] = 1;
+ state->data[0] = 0xe;
+ state->data[1] = 0x02;
+ state->data[2] = 1;
- if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+ if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
err("command 0x0e transfer failed.");
msleep(300);
- obuf[0] = 0xe;
- obuf[1] = 0x83;
- obuf[2] = 0;
+ state->data[0] = 0xe;
+ state->data[1] = 0x83;
+ state->data[2] = 0;
- if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+ if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
err("command 0x0e transfer failed.");
- obuf[0] = 0xe;
- obuf[1] = 0x83;
- obuf[2] = 1;
+ state->data[0] = 0xe;
+ state->data[1] = 0x83;
+ state->data[2] = 1;
- if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+ if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
err("command 0x0e transfer failed.");
- obuf[0] = 0x51;
+ state->data[0] = 0x51;
- if (dvb_usb_generic_rw(d->dev, obuf, 1, ibuf, 1, 0) < 0)
+ if (dvb_usb_generic_rw(d, state->data, 1, state->data, 1, 0) < 0)
err("command 0x51 transfer failed.");
- d->fe_adap[0].fe = dvb_attach(ds3000_attach, &su3000_ds3000_config,
- &d->dev->i2c_adap);
- if (d->fe_adap[0].fe == NULL)
+ mutex_unlock(&d->data_mutex);
+
+ adap->fe_adap[0].fe = dvb_attach(ds3000_attach, &su3000_ds3000_config,
+ &d->i2c_adap);
+ if (adap->fe_adap[0].fe == NULL)
return -EIO;
- if (dvb_attach(ts2020_attach, d->fe_adap[0].fe,
+ if (dvb_attach(ts2020_attach, adap->fe_adap[0].fe,
&dw2104_ts2020_config,
- &d->dev->i2c_adap)) {
+ &d->i2c_adap)) {
info("Attached DS3000/TS2020!");
return 0;
}
@@ -1360,47 +1385,55 @@ static int su3000_frontend_attach(struct dvb_usb_adapter *d)
return -EIO;
}
-static int t220_frontend_attach(struct dvb_usb_adapter *d)
+static int t220_frontend_attach(struct dvb_usb_adapter *adap)
{
- u8 obuf[3] = { 0xe, 0x87, 0 };
- u8 ibuf[] = { 0 };
+ struct dvb_usb_device *d = adap->dev;
+ struct dw2102_state *state = d->priv;
- if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+ mutex_lock(&d->data_mutex);
+
+ state->data[0] = 0xe;
+ state->data[1] = 0x87;
+ state->data[2] = 0x0;
+
+ if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
err("command 0x0e transfer failed.");
- obuf[0] = 0xe;
- obuf[1] = 0x86;
- obuf[2] = 1;
+ state->data[0] = 0xe;
+ state->data[1] = 0x86;
+ state->data[2] = 1;
- if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+ if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
err("command 0x0e transfer failed.");
- obuf[0] = 0xe;
- obuf[1] = 0x80;
- obuf[2] = 0;
+ state->data[0] = 0xe;
+ state->data[1] = 0x80;
+ state->data[2] = 0;
- if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+ if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
err("command 0x0e transfer failed.");
msleep(50);
- obuf[0] = 0xe;
- obuf[1] = 0x80;
- obuf[2] = 1;
+ state->data[0] = 0xe;
+ state->data[1] = 0x80;
+ state->data[2] = 1;
- if (dvb_usb_generic_rw(d->dev, obuf, 3, ibuf, 1, 0) < 0)
+ if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
err("command 0x0e transfer failed.");
- obuf[0] = 0x51;
+ state->data[0] = 0x51;
- if (dvb_usb_generic_rw(d->dev, obuf, 1, ibuf, 1, 0) < 0)
+ if (dvb_usb_generic_rw(d, state->data, 1, state->data, 1, 0) < 0)
err("command 0x51 transfer failed.");
- d->fe_adap[0].fe = dvb_attach(cxd2820r_attach, &cxd2820r_config,
- &d->dev->i2c_adap, NULL);
- if (d->fe_adap[0].fe != NULL) {
- if (dvb_attach(tda18271_attach, d->fe_adap[0].fe, 0x60,
- &d->dev->i2c_adap, &tda18271_config)) {
+ mutex_unlock(&d->data_mutex);
+
+ adap->fe_adap[0].fe = dvb_attach(cxd2820r_attach, &cxd2820r_config,
+ &d->i2c_adap, NULL);
+ if (adap->fe_adap[0].fe != NULL) {
+ if (dvb_attach(tda18271_attach, adap->fe_adap[0].fe, 0x60,
+ &d->i2c_adap, &tda18271_config)) {
info("Attached TDA18271HD/CXD2820R!");
return 0;
}
@@ -1410,23 +1443,30 @@ static int t220_frontend_attach(struct dvb_usb_adapter *d)
return -EIO;
}
-static int m88rs2000_frontend_attach(struct dvb_usb_adapter *d)
+static int m88rs2000_frontend_attach(struct dvb_usb_adapter *adap)
{
- u8 obuf[] = { 0x51 };
- u8 ibuf[] = { 0 };
+ struct dvb_usb_device *d = adap->dev;
+ struct dw2102_state *state = d->priv;
- if (dvb_usb_generic_rw(d->dev, obuf, 1, ibuf, 1, 0) < 0)
+ mutex_lock(&d->data_mutex);
+
+ state->data[0] = 0x51;
+
+ if (dvb_usb_generic_rw(d, state->data, 1, state->data, 1, 0) < 0)
err("command 0x51 transfer failed.");
- d->fe_adap[0].fe = dvb_attach(m88rs2000_attach, &s421_m88rs2000_config,
- &d->dev->i2c_adap);
+ mutex_unlock(&d->data_mutex);
- if (d->fe_adap[0].fe == NULL)
+ adap->fe_adap[0].fe = dvb_attach(m88rs2000_attach,
+ &s421_m88rs2000_config,
+ &d->i2c_adap);
+
+ if (adap->fe_adap[0].fe == NULL)
return -EIO;
- if (dvb_attach(ts2020_attach, d->fe_adap[0].fe,
+ if (dvb_attach(ts2020_attach, adap->fe_adap[0].fe,
&dw2104_ts2020_config,
- &d->dev->i2c_adap)) {
+ &d->i2c_adap)) {
info("Attached RS2000/TS2020!");
return 0;
}
@@ -1439,44 +1479,50 @@ static int tt_s2_4600_frontend_attach(struct dvb_usb_adapter *adap)
{
struct dvb_usb_device *d = adap->dev;
struct dw2102_state *state = d->priv;
- u8 obuf[3] = { 0xe, 0x80, 0 };
- u8 ibuf[] = { 0 };
struct i2c_adapter *i2c_adapter;
struct i2c_client *client;
struct i2c_board_info board_info;
struct m88ds3103_platform_data m88ds3103_pdata = {};
struct ts2020_config ts2020_config = {};
- if (dvb_usb_generic_rw(d, obuf, 3, ibuf, 1, 0) < 0)
+ mutex_lock(&d->data_mutex);
+
+ state->data[0] = 0xe;
+ state->data[1] = 0x80;
+ state->data[2] = 0x0;
+
+ if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
err("command 0x0e transfer failed.");
- obuf[0] = 0xe;
- obuf[1] = 0x02;
- obuf[2] = 1;
+ state->data[0] = 0xe;
+ state->data[1] = 0x02;
+ state->data[2] = 1;
- if (dvb_usb_generic_rw(d, obuf, 3, ibuf, 1, 0) < 0)
+ if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
err("command 0x0e transfer failed.");
msleep(300);
- obuf[0] = 0xe;
- obuf[1] = 0x83;
- obuf[2] = 0;
+ state->data[0] = 0xe;
+ state->data[1] = 0x83;
+ state->data[2] = 0;
- if (dvb_usb_generic_rw(d, obuf, 3, ibuf, 1, 0) < 0)
+ if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
err("command 0x0e transfer failed.");
- obuf[0] = 0xe;
- obuf[1] = 0x83;
- obuf[2] = 1;
+ state->data[0] = 0xe;
+ state->data[1] = 0x83;
+ state->data[2] = 1;
- if (dvb_usb_generic_rw(d, obuf, 3, ibuf, 1, 0) < 0)
+ if (dvb_usb_generic_rw(d, state->data, 3, state->data, 1, 0) < 0)
err("command 0x0e transfer failed.");
- obuf[0] = 0x51;
+ state->data[0] = 0x51;
- if (dvb_usb_generic_rw(d, obuf, 1, ibuf, 1, 0) < 0)
+ if (dvb_usb_generic_rw(d, state->data, 1, state->data, 1, 0) < 0)
err("command 0x51 transfer failed.");
+ mutex_unlock(&d->data_mutex);
+
/* attach demod */
m88ds3103_pdata.clk = 27000000;
m88ds3103_pdata.i2c_wr_max = 33;
diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c
index 5457c36..bf0fe01 100644
--- a/drivers/memory/omap-gpmc.c
+++ b/drivers/memory/omap-gpmc.c
@@ -1947,9 +1947,7 @@ static int gpmc_probe_onenand_child(struct platform_device *pdev,
if (!of_property_read_u32(child, "dma-channel", &val))
gpmc_onenand_data->dma_channel = val;
- gpmc_onenand_init(gpmc_onenand_data);
-
- return 0;
+ return gpmc_onenand_init(gpmc_onenand_data);
}
#else
static int gpmc_probe_onenand_child(struct platform_device *pdev,
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 91f6459..b27ea98 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -1792,15 +1792,14 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,
/* If we're permanently dead, give up. */
if (state == pci_channel_io_perm_failure) {
- /* Tell the AFU drivers; but we don't care what they
- * say, we're going away.
- */
for (i = 0; i < adapter->slices; i++) {
afu = adapter->afu[i];
- /* Only participate in EEH if we are on a virtual PHB */
- if (afu->phb == NULL)
- return PCI_ERS_RESULT_NONE;
- cxl_vphb_error_detected(afu, state);
+ /*
+ * Tell the AFU drivers; but we don't care what they
+ * say, we're going away.
+ */
+ if (afu->phb != NULL)
+ cxl_vphb_error_detected(afu, state);
}
return PCI_ERS_RESULT_DISCONNECT;
}
diff --git a/drivers/misc/mei/bus-fixup.c b/drivers/misc/mei/bus-fixup.c
index 3600c99..29f2dae 100644
--- a/drivers/misc/mei/bus-fixup.c
+++ b/drivers/misc/mei/bus-fixup.c
@@ -112,11 +112,9 @@ struct mkhi_msg {
static int mei_osver(struct mei_cl_device *cldev)
{
- int ret;
const size_t size = sizeof(struct mkhi_msg_hdr) +
sizeof(struct mkhi_fwcaps) +
sizeof(struct mei_os_ver);
- size_t length = 8;
char buf[size];
struct mkhi_msg *req;
struct mkhi_fwcaps *fwcaps;
@@ -137,15 +135,7 @@ static int mei_osver(struct mei_cl_device *cldev)
os_ver = (struct mei_os_ver *)fwcaps->data;
os_ver->os_type = OSTYPE_LINUX;
- ret = __mei_cl_send(cldev->cl, buf, size, mode);
- if (ret < 0)
- return ret;
-
- ret = __mei_cl_recv(cldev->cl, buf, length, 0);
- if (ret < 0)
- return ret;
-
- return 0;
+ return __mei_cl_send(cldev->cl, buf, size, mode);
}
static void mei_mkhi_fix(struct mei_cl_device *cldev)
@@ -160,7 +150,7 @@ static void mei_mkhi_fix(struct mei_cl_device *cldev)
return;
ret = mei_osver(cldev);
- if (ret)
+ if (ret < 0)
dev_err(&cldev->dev, "OS version command failed %d\n", ret);
mei_cldev_disable(cldev);
diff --git a/drivers/misc/mei/init.c b/drivers/misc/mei/init.c
index cfb1cdf..13c55b8 100644
--- a/drivers/misc/mei/init.c
+++ b/drivers/misc/mei/init.c
@@ -124,8 +124,6 @@ int mei_reset(struct mei_device *dev)
mei_clear_interrupts(dev);
- mei_synchronize_irq(dev);
-
/* we're already in reset, cancel the init timer
* if the reset was called due the hbm protocol error
* we need to call it before hw start
@@ -304,6 +302,9 @@ static void mei_reset_work(struct work_struct *work)
container_of(work, struct mei_device, reset_work);
int ret;
+ mei_clear_interrupts(dev);
+ mei_synchronize_irq(dev);
+
mutex_lock(&dev->device_lock);
ret = mei_reset(dev);
@@ -328,6 +329,9 @@ void mei_stop(struct mei_device *dev)
mei_cancel_work(dev);
+ mei_clear_interrupts(dev);
+ mei_synchronize_irq(dev);
+
mutex_lock(&dev->device_lock);
dev->dev_state = MEI_DEV_POWER_DOWN;
diff --git a/drivers/misc/sgi-gru/grufault.c b/drivers/misc/sgi-gru/grufault.c
index 6fb773d..93be82f 100644
--- a/drivers/misc/sgi-gru/grufault.c
+++ b/drivers/misc/sgi-gru/grufault.c
@@ -219,15 +219,20 @@ static int atomic_pte_lookup(struct vm_area_struct *vma, unsigned long vaddr,
int write, unsigned long *paddr, int *pageshift)
{
pgd_t *pgdp;
- pmd_t *pmdp;
+ p4d_t *p4dp;
pud_t *pudp;
+ pmd_t *pmdp;
pte_t pte;
pgdp = pgd_offset(vma->vm_mm, vaddr);
if (unlikely(pgd_none(*pgdp)))
goto err;
- pudp = pud_offset(pgdp, vaddr);
+ p4dp = p4d_offset(pgdp, vaddr);
+ if (unlikely(p4d_none(*p4dp)))
+ goto err;
+
+ pudp = pud_offset(p4dp, vaddr);
if (unlikely(pud_none(*pudp)))
goto err;
diff --git a/drivers/misc/vmw_vmci/vmci_guest.c b/drivers/misc/vmw_vmci/vmci_guest.c
index 9d65954..dad5abe 100644
--- a/drivers/misc/vmw_vmci/vmci_guest.c
+++ b/drivers/misc/vmw_vmci/vmci_guest.c
@@ -566,10 +566,10 @@ static int vmci_guest_probe_device(struct pci_dev *pdev,
*/
error = pci_alloc_irq_vectors(pdev, VMCI_MAX_INTRS, VMCI_MAX_INTRS,
PCI_IRQ_MSIX);
- if (error) {
+ if (error < 0) {
error = pci_alloc_irq_vectors(pdev, 1, 1,
PCI_IRQ_MSIX | PCI_IRQ_MSI | PCI_IRQ_LEGACY);
- if (error)
+ if (error < 0)
goto err_remove_bitmap;
} else {
vmci_dev->exclusive_vectors = true;
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 1621fa0..ff3da96 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -1560,11 +1560,8 @@ static bool mmc_blk_rw_cmd_err(struct mmc_blk_data *md, struct mmc_card *card,
struct mmc_blk_request *brq, struct request *req,
bool old_req_pending)
{
- struct mmc_queue_req *mq_rq;
bool req_pending;
- mq_rq = container_of(brq, struct mmc_queue_req, brq);
-
/*
* If this is an SD card and we're writing, we can first
* mark the known good sectors as ok.
@@ -1701,7 +1698,8 @@ static void mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *new_req)
case MMC_BLK_CMD_ERR:
req_pending = mmc_blk_rw_cmd_err(md, card, brq, old_req, req_pending);
if (mmc_blk_reset(md, card->host, type)) {
- mmc_blk_rw_cmd_abort(card, old_req);
+ if (req_pending)
+ mmc_blk_rw_cmd_abort(card, old_req);
mmc_blk_rw_try_restart(mq, new_req);
return;
}
@@ -1817,6 +1815,7 @@ void mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
mmc_blk_issue_flush(mq, req);
} else {
mmc_blk_issue_rw_rq(mq, req);
+ card->host->context_info.is_waiting_last_req = false;
}
out:
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 7fd7228..b502601 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1730,7 +1730,7 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
err = mmc_select_hs400(card);
if (err)
goto free_card;
- } else {
+ } else if (!mmc_card_hs400es(card)) {
/* Select the desired bus width optionally */
err = mmc_select_bus_width(card);
if (err > 0 && mmc_card_hs(card)) {
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index 8e32580..b235d8d 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -580,7 +580,7 @@ static void msdc_set_mclk(struct msdc_host *host, unsigned char timing, u32 hz)
}
}
sdr_set_field(host->base + MSDC_CFG, MSDC_CFG_CKMOD | MSDC_CFG_CKDIV,
- (mode << 8) | (div % 0xff));
+ (mode << 8) | div);
sdr_set_bits(host->base + MSDC_CFG, MSDC_CFG_CKPDN);
while (!(readl(host->base + MSDC_CFG) & MSDC_CFG_CKSTB))
cpu_relax();
@@ -1559,7 +1559,7 @@ static int msdc_drv_probe(struct platform_device *pdev)
host->src_clk_freq = clk_get_rate(host->src_clk);
/* Set host parameters to mmc */
mmc->ops = &mt_msdc_ops;
- mmc->f_min = host->src_clk_freq / (4 * 255);
+ mmc->f_min = DIV_ROUND_UP(host->src_clk_freq, 4 * 255);
mmc->caps |= MMC_CAP_ERASE | MMC_CAP_CMD23;
/* MMC core transfer sizes tunable parameters */
diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c
index 410a55b..1cfd7f9 100644
--- a/drivers/mmc/host/sdhci-of-arasan.c
+++ b/drivers/mmc/host/sdhci-of-arasan.c
@@ -28,13 +28,9 @@
#include "sdhci-pltfm.h"
#include <linux/of.h>
-#define SDHCI_ARASAN_CLK_CTRL_OFFSET 0x2c
#define SDHCI_ARASAN_VENDOR_REGISTER 0x78
#define VENDOR_ENHANCED_STROBE BIT(0)
-#define CLK_CTRL_TIMEOUT_SHIFT 16
-#define CLK_CTRL_TIMEOUT_MASK (0xf << CLK_CTRL_TIMEOUT_SHIFT)
-#define CLK_CTRL_TIMEOUT_MIN_EXP 13
#define PHY_CLK_TOO_SLOW_HZ 400000
@@ -163,15 +159,15 @@ static int sdhci_arasan_syscon_write(struct sdhci_host *host,
static unsigned int sdhci_arasan_get_timeout_clock(struct sdhci_host *host)
{
- u32 div;
unsigned long freq;
struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
- div = readl(host->ioaddr + SDHCI_ARASAN_CLK_CTRL_OFFSET);
- div = (div & CLK_CTRL_TIMEOUT_MASK) >> CLK_CTRL_TIMEOUT_SHIFT;
+ /* SDHCI timeout clock is in kHz */
+ freq = DIV_ROUND_UP(clk_get_rate(pltfm_host->clk), 1000);
- freq = clk_get_rate(pltfm_host->clk);
- freq /= 1 << (CLK_CTRL_TIMEOUT_MIN_EXP + div);
+ /* or in MHz */
+ if (host->caps & SDHCI_TIMEOUT_CLK_UNIT)
+ freq = DIV_ROUND_UP(freq, 1000);
return freq;
}
diff --git a/drivers/mmc/host/sdhci-of-at91.c b/drivers/mmc/host/sdhci-of-at91.c
index 2f9ad21..d5430ed 100644
--- a/drivers/mmc/host/sdhci-of-at91.c
+++ b/drivers/mmc/host/sdhci-of-at91.c
@@ -29,6 +29,8 @@
#include "sdhci-pltfm.h"
+#define SDMMC_MC1R 0x204
+#define SDMMC_MC1R_DDR BIT(3)
#define SDMMC_CACR 0x230
#define SDMMC_CACR_CAPWREN BIT(0)
#define SDMMC_CACR_KEY (0x46 << 8)
@@ -85,11 +87,37 @@ static void sdhci_at91_set_clock(struct sdhci_host *host, unsigned int clock)
sdhci_writew(host, clk, SDHCI_CLOCK_CONTROL);
}
+/*
+ * In this specific implementation of the SDHCI controller, the power register
+ * needs to have a valid voltage set even when the power supply is managed by
+ * an external regulator.
+ */
+static void sdhci_at91_set_power(struct sdhci_host *host, unsigned char mode,
+ unsigned short vdd)
+{
+ if (!IS_ERR(host->mmc->supply.vmmc)) {
+ struct mmc_host *mmc = host->mmc;
+
+ spin_unlock_irq(&host->lock);
+ mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, vdd);
+ spin_lock_irq(&host->lock);
+ }
+ sdhci_set_power_noreg(host, mode, vdd);
+}
+
+void sdhci_at91_set_uhs_signaling(struct sdhci_host *host, unsigned int timing)
+{
+ if (timing == MMC_TIMING_MMC_DDR52)
+ sdhci_writeb(host, SDMMC_MC1R_DDR, SDMMC_MC1R);
+ sdhci_set_uhs_signaling(host, timing);
+}
+
static const struct sdhci_ops sdhci_at91_sama5d2_ops = {
.set_clock = sdhci_at91_set_clock,
.set_bus_width = sdhci_set_bus_width,
.reset = sdhci_reset,
- .set_uhs_signaling = sdhci_set_uhs_signaling,
+ .set_uhs_signaling = sdhci_at91_set_uhs_signaling,
+ .set_power = sdhci_at91_set_power,
};
static const struct sdhci_pltfm_data soc_data_sama5d2 = {
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index 982b3e3..86560d5 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -451,6 +451,8 @@ static void sdhci_intel_set_power(struct sdhci_host *host, unsigned char mode,
if (mode == MMC_POWER_OFF)
return;
+ spin_unlock_irq(&host->lock);
+
/*
* Bus power might not enable after D3 -> D0 transition due to the
* present state not yet having propagated. Retry for up to 2ms.
@@ -463,6 +465,8 @@ static void sdhci_intel_set_power(struct sdhci_host *host, unsigned char mode,
reg |= SDHCI_POWER_ON;
sdhci_writeb(host, reg, SDHCI_POWER_CONTROL);
}
+
+ spin_lock_irq(&host->lock);
}
static const struct sdhci_ops sdhci_intel_byt_ops = {
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 6fdd7a7..63bc33a 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -1362,7 +1362,9 @@ void sdhci_enable_clk(struct sdhci_host *host, u16 clk)
return;
}
timeout--;
- mdelay(1);
+ spin_unlock_irq(&host->lock);
+ usleep_range(900, 1100);
+ spin_lock_irq(&host->lock);
}
clk |= SDHCI_CLOCK_CARD_EN;
@@ -1828,6 +1830,9 @@ static void sdhci_enable_sdio_irq(struct mmc_host *mmc, int enable)
struct sdhci_host *host = mmc_priv(mmc);
unsigned long flags;
+ if (enable)
+ pm_runtime_get_noresume(host->mmc->parent);
+
spin_lock_irqsave(&host->lock, flags);
if (enable)
host->flags |= SDHCI_SDIO_IRQ_ENABLED;
@@ -1836,6 +1841,9 @@ static void sdhci_enable_sdio_irq(struct mmc_host *mmc, int enable)
sdhci_enable_sdio_irq_nolock(host, enable);
spin_unlock_irqrestore(&host->lock, flags);
+
+ if (!enable)
+ pm_runtime_put_noidle(host->mmc->parent);
}
static int sdhci_start_signal_voltage_switch(struct mmc_host *mmc,
diff --git a/drivers/mmc/host/ushc.c b/drivers/mmc/host/ushc.c
index d2c386f..1d84335 100644
--- a/drivers/mmc/host/ushc.c
+++ b/drivers/mmc/host/ushc.c
@@ -426,6 +426,9 @@ static int ushc_probe(struct usb_interface *intf, const struct usb_device_id *id
struct ushc_data *ushc;
int ret;
+ if (intf->cur_altsetting->desc.bNumEndpoints < 1)
+ return -ENODEV;
+
mmc = mmc_alloc_host(sizeof(struct ushc_data), &intf->dev);
if (mmc == NULL)
return -ENOMEM;
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index 1ae872b..747645c 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -186,7 +186,7 @@ static inline int write_enable(struct spi_nor *nor)
}
/*
- * Send write disble instruction to the chip.
+ * Send write disable instruction to the chip.
*/
static inline int write_disable(struct spi_nor *nor)
{
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 98ed4d9..57fc47a 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -18,7 +18,7 @@
obj-$(CONFIG_MDIO) += mdio.o
obj-$(CONFIG_NET) += Space.o loopback.o
obj-$(CONFIG_NETCONSOLE) += netconsole.o
-obj-$(CONFIG_PHYLIB) += phy/
+obj-y += phy/
obj-$(CONFIG_RIONET) += rionet.o
obj-$(CONFIG_NET_TEAM) += team/
obj-$(CONFIG_TUN) += tun.o
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index edc70ff..c5fd425 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -92,6 +92,7 @@ enum ad_link_speed_type {
AD_LINK_SPEED_2500MBPS,
AD_LINK_SPEED_10000MBPS,
AD_LINK_SPEED_20000MBPS,
+ AD_LINK_SPEED_25000MBPS,
AD_LINK_SPEED_40000MBPS,
AD_LINK_SPEED_56000MBPS,
AD_LINK_SPEED_100000MBPS,
@@ -260,6 +261,7 @@ static inline int __check_agg_selection_timer(struct port *port)
* %AD_LINK_SPEED_2500MBPS,
* %AD_LINK_SPEED_10000MBPS
* %AD_LINK_SPEED_20000MBPS
+ * %AD_LINK_SPEED_25000MBPS
* %AD_LINK_SPEED_40000MBPS
* %AD_LINK_SPEED_56000MBPS
* %AD_LINK_SPEED_100000MBPS
@@ -302,6 +304,10 @@ static u16 __get_link_speed(struct port *port)
speed = AD_LINK_SPEED_20000MBPS;
break;
+ case SPEED_25000:
+ speed = AD_LINK_SPEED_25000MBPS;
+ break;
+
case SPEED_40000:
speed = AD_LINK_SPEED_40000MBPS;
break;
@@ -707,6 +713,9 @@ static u32 __get_agg_bandwidth(struct aggregator *aggregator)
case AD_LINK_SPEED_20000MBPS:
bandwidth = nports * 20000;
break;
+ case AD_LINK_SPEED_25000MBPS:
+ bandwidth = nports * 25000;
+ break;
case AD_LINK_SPEED_40000MBPS:
bandwidth = nports * 40000;
break;
@@ -1052,8 +1061,7 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port)
port->sm_rx_state = AD_RX_INITIALIZE;
port->sm_vars |= AD_PORT_CHURNED;
/* check if port is not enabled */
- } else if (!(port->sm_vars & AD_PORT_BEGIN)
- && !port->is_enabled && !(port->sm_vars & AD_PORT_MOVED))
+ } else if (!(port->sm_vars & AD_PORT_BEGIN) && !port->is_enabled)
port->sm_rx_state = AD_RX_PORT_DISABLED;
/* check if new lacpdu arrived */
else if (lacpdu && ((port->sm_rx_state == AD_RX_EXPIRED) ||
@@ -1081,11 +1089,8 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port)
/* if no lacpdu arrived and no timer is on */
switch (port->sm_rx_state) {
case AD_RX_PORT_DISABLED:
- if (port->sm_vars & AD_PORT_MOVED)
- port->sm_rx_state = AD_RX_INITIALIZE;
- else if (port->is_enabled
- && (port->sm_vars
- & AD_PORT_LACP_ENABLED))
+ if (port->is_enabled &&
+ (port->sm_vars & AD_PORT_LACP_ENABLED))
port->sm_rx_state = AD_RX_EXPIRED;
else if (port->is_enabled
&& ((port->sm_vars
@@ -1115,7 +1120,6 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port)
port->sm_vars &= ~AD_PORT_SELECTED;
__record_default(port);
port->actor_oper_port_state &= ~AD_STATE_EXPIRED;
- port->sm_vars &= ~AD_PORT_MOVED;
port->sm_rx_state = AD_RX_PORT_DISABLED;
/* Fall Through */
@@ -2442,9 +2446,9 @@ void bond_3ad_adapter_speed_duplex_changed(struct slave *slave)
spin_lock_bh(&slave->bond->mode_lock);
ad_update_actor_keys(port, false);
+ spin_unlock_bh(&slave->bond->mode_lock);
netdev_dbg(slave->bond->dev, "Port %d slave %s changed speed/duplex\n",
port->actor_port_number, slave->dev->name);
- spin_unlock_bh(&slave->bond->mode_lock);
}
/**
@@ -2488,12 +2492,12 @@ void bond_3ad_handle_link_change(struct slave *slave, char link)
agg = __get_first_agg(port);
ad_agg_selection_logic(agg, &dummy);
+ spin_unlock_bh(&slave->bond->mode_lock);
+
netdev_dbg(slave->bond->dev, "Port %d changed link status to %s\n",
port->actor_port_number,
link == BOND_LINK_UP ? "UP" : "DOWN");
- spin_unlock_bh(&slave->bond->mode_lock);
-
/* RTNL is held and mode_lock is released so it's safe
* to update slave_array here.
*/
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index c80b023..7d7a3ce 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -687,7 +687,8 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
/* the arp must be sent on the selected rx channel */
tx_slave = rlb_choose_channel(skb, bond);
if (tx_slave)
- ether_addr_copy(arp->mac_src, tx_slave->dev->dev_addr);
+ bond_hw_addr_copy(arp->mac_src, tx_slave->dev->dev_addr,
+ tx_slave->dev->addr_len);
netdev_dbg(bond->dev, "Server sent ARP Reply packet\n");
} else if (arp->op_code == htons(ARPOP_REQUEST)) {
/* Create an entry in the rx_hashtbl for this client as a
@@ -1017,22 +1018,23 @@ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[],
rcu_read_unlock();
}
-static int alb_set_slave_mac_addr(struct slave *slave, u8 addr[])
+static int alb_set_slave_mac_addr(struct slave *slave, u8 addr[],
+ unsigned int len)
{
struct net_device *dev = slave->dev;
- struct sockaddr s_addr;
+ struct sockaddr_storage ss;
if (BOND_MODE(slave->bond) == BOND_MODE_TLB) {
- memcpy(dev->dev_addr, addr, dev->addr_len);
+ memcpy(dev->dev_addr, addr, len);
return 0;
}
/* for rlb each slave must have a unique hw mac addresses so that
* each slave will receive packets destined to a different mac
*/
- memcpy(s_addr.sa_data, addr, dev->addr_len);
- s_addr.sa_family = dev->type;
- if (dev_set_mac_address(dev, &s_addr)) {
+ memcpy(ss.__data, addr, len);
+ ss.ss_family = dev->type;
+ if (dev_set_mac_address(dev, (struct sockaddr *)&ss)) {
netdev_err(slave->bond->dev, "dev_set_mac_address of dev %s failed! ALB mode requires that the base driver support setting the hw address also when the network device's interface is open\n",
dev->name);
return -EOPNOTSUPP;
@@ -1046,11 +1048,14 @@ static int alb_set_slave_mac_addr(struct slave *slave, u8 addr[])
*/
static void alb_swap_mac_addr(struct slave *slave1, struct slave *slave2)
{
- u8 tmp_mac_addr[ETH_ALEN];
+ u8 tmp_mac_addr[MAX_ADDR_LEN];
- ether_addr_copy(tmp_mac_addr, slave1->dev->dev_addr);
- alb_set_slave_mac_addr(slave1, slave2->dev->dev_addr);
- alb_set_slave_mac_addr(slave2, tmp_mac_addr);
+ bond_hw_addr_copy(tmp_mac_addr, slave1->dev->dev_addr,
+ slave1->dev->addr_len);
+ alb_set_slave_mac_addr(slave1, slave2->dev->dev_addr,
+ slave2->dev->addr_len);
+ alb_set_slave_mac_addr(slave2, tmp_mac_addr,
+ slave1->dev->addr_len);
}
@@ -1177,7 +1182,8 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav
/* Try setting slave mac to bond address and fall-through
* to code handling that situation below...
*/
- alb_set_slave_mac_addr(slave, bond->dev->dev_addr);
+ alb_set_slave_mac_addr(slave, bond->dev->dev_addr,
+ bond->dev->addr_len);
}
/* The slave's address is equal to the address of the bond.
@@ -1202,7 +1208,8 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav
}
if (free_mac_slave) {
- alb_set_slave_mac_addr(slave, free_mac_slave->perm_hwaddr);
+ alb_set_slave_mac_addr(slave, free_mac_slave->perm_hwaddr,
+ free_mac_slave->dev->addr_len);
netdev_warn(bond->dev, "the hw address of slave %s is in use by the bond; giving it the hw address of %s\n",
slave->dev->name, free_mac_slave->dev->name);
@@ -1234,8 +1241,8 @@ static int alb_set_mac_address(struct bonding *bond, void *addr)
{
struct slave *slave, *rollback_slave;
struct list_head *iter;
- struct sockaddr sa;
- char tmp_addr[ETH_ALEN];
+ struct sockaddr_storage ss;
+ char tmp_addr[MAX_ADDR_LEN];
int res;
if (bond->alb_info.rlb_enabled)
@@ -1243,12 +1250,14 @@ static int alb_set_mac_address(struct bonding *bond, void *addr)
bond_for_each_slave(bond, slave, iter) {
/* save net_device's current hw address */
- ether_addr_copy(tmp_addr, slave->dev->dev_addr);
+ bond_hw_addr_copy(tmp_addr, slave->dev->dev_addr,
+ slave->dev->addr_len);
res = dev_set_mac_address(slave->dev, addr);
/* restore net_device's hw address */
- ether_addr_copy(slave->dev->dev_addr, tmp_addr);
+ bond_hw_addr_copy(slave->dev->dev_addr, tmp_addr,
+ slave->dev->addr_len);
if (res)
goto unwind;
@@ -1257,16 +1266,19 @@ static int alb_set_mac_address(struct bonding *bond, void *addr)
return 0;
unwind:
- memcpy(sa.sa_data, bond->dev->dev_addr, bond->dev->addr_len);
- sa.sa_family = bond->dev->type;
+ memcpy(ss.__data, bond->dev->dev_addr, bond->dev->addr_len);
+ ss.ss_family = bond->dev->type;
/* unwind from head to the slave that failed */
bond_for_each_slave(bond, rollback_slave, iter) {
if (rollback_slave == slave)
break;
- ether_addr_copy(tmp_addr, rollback_slave->dev->dev_addr);
- dev_set_mac_address(rollback_slave->dev, &sa);
- ether_addr_copy(rollback_slave->dev->dev_addr, tmp_addr);
+ bond_hw_addr_copy(tmp_addr, rollback_slave->dev->dev_addr,
+ rollback_slave->dev->addr_len);
+ dev_set_mac_address(rollback_slave->dev,
+ (struct sockaddr *)&ss);
+ bond_hw_addr_copy(rollback_slave->dev->dev_addr, tmp_addr,
+ rollback_slave->dev->addr_len);
}
return res;
@@ -1582,7 +1594,8 @@ int bond_alb_init_slave(struct bonding *bond, struct slave *slave)
{
int res;
- res = alb_set_slave_mac_addr(slave, slave->perm_hwaddr);
+ res = alb_set_slave_mac_addr(slave, slave->perm_hwaddr,
+ slave->dev->addr_len);
if (res)
return res;
@@ -1696,17 +1709,20 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave
* and thus filter bond->dev_addr's packets, so force bond's mac
*/
if (BOND_MODE(bond) == BOND_MODE_TLB) {
- struct sockaddr sa;
- u8 tmp_addr[ETH_ALEN];
+ struct sockaddr_storage ss;
+ u8 tmp_addr[MAX_ADDR_LEN];
- ether_addr_copy(tmp_addr, new_slave->dev->dev_addr);
+ bond_hw_addr_copy(tmp_addr, new_slave->dev->dev_addr,
+ new_slave->dev->addr_len);
- memcpy(sa.sa_data, bond->dev->dev_addr, bond->dev->addr_len);
- sa.sa_family = bond->dev->type;
+ bond_hw_addr_copy(ss.__data, bond->dev->dev_addr,
+ bond->dev->addr_len);
+ ss.ss_family = bond->dev->type;
/* we don't care if it can't change its mac, best effort */
- dev_set_mac_address(new_slave->dev, &sa);
+ dev_set_mac_address(new_slave->dev, (struct sockaddr *)&ss);
- ether_addr_copy(new_slave->dev->dev_addr, tmp_addr);
+ bond_hw_addr_copy(new_slave->dev->dev_addr, tmp_addr,
+ new_slave->dev->addr_len);
}
/* curr_active_slave must be set before calling alb_swap_mac_addr */
@@ -1716,7 +1732,8 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave
alb_fasten_mac_swap(bond, swap_slave, new_slave);
} else {
/* set the new_slave to the bond mac address */
- alb_set_slave_mac_addr(new_slave, bond->dev->dev_addr);
+ alb_set_slave_mac_addr(new_slave, bond->dev->dev_addr,
+ bond->dev->addr_len);
alb_send_learning_packets(new_slave, bond->dev->dev_addr,
false);
}
@@ -1726,19 +1743,19 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave
int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr)
{
struct bonding *bond = netdev_priv(bond_dev);
- struct sockaddr *sa = addr;
+ struct sockaddr_storage *ss = addr;
struct slave *curr_active;
struct slave *swap_slave;
int res;
- if (!is_valid_ether_addr(sa->sa_data))
+ if (!is_valid_ether_addr(ss->__data))
return -EADDRNOTAVAIL;
res = alb_set_mac_address(bond, addr);
if (res)
return res;
- memcpy(bond_dev->dev_addr, sa->sa_data, bond_dev->addr_len);
+ bond_hw_addr_copy(bond_dev->dev_addr, ss->__data, bond_dev->addr_len);
/* If there is no curr_active_slave there is nothing else to do.
* Otherwise we'll need to pass the new address to it and handle
@@ -1754,7 +1771,8 @@ int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr)
alb_swap_mac_addr(swap_slave, curr_active);
alb_fasten_mac_swap(bond, swap_slave, curr_active);
} else {
- alb_set_slave_mac_addr(curr_active, bond_dev->dev_addr);
+ alb_set_slave_mac_addr(curr_active, bond_dev->dev_addr,
+ bond_dev->addr_len);
alb_send_learning_packets(curr_active,
bond_dev->dev_addr, false);
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 8a4ba8b..aba7352 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -201,12 +201,6 @@ atomic_t netpoll_block_tx = ATOMIC_INIT(0);
unsigned int bond_net_id __read_mostly;
-static __be32 arp_target[BOND_MAX_ARP_TARGETS];
-static int arp_ip_count;
-static int bond_mode = BOND_MODE_ROUNDROBIN;
-static int xmit_hashtype = BOND_XMIT_POLICY_LAYER2;
-static int lacp_fast;
-
/*-------------------------- Forward declarations ---------------------------*/
static int bond_init(struct net_device *bond_dev);
@@ -371,9 +365,10 @@ int bond_set_carrier(struct bonding *bond)
/* Get link speed and duplex from the slave's base driver
* using ethtool. If for some reason the call fails or the
* values are invalid, set speed and duplex to -1,
- * and return.
+ * and return. Return 1 if speed or duplex settings are
+ * UNKNOWN; 0 otherwise.
*/
-static void bond_update_speed_duplex(struct slave *slave)
+static int bond_update_speed_duplex(struct slave *slave)
{
struct net_device *slave_dev = slave->dev;
struct ethtool_link_ksettings ecmd;
@@ -384,23 +379,21 @@ static void bond_update_speed_duplex(struct slave *slave)
res = __ethtool_get_link_ksettings(slave_dev, &ecmd);
if (res < 0)
- return;
-
+ return 1;
if (ecmd.base.speed == 0 || ecmd.base.speed == ((__u32)-1))
- return;
-
+ return 1;
switch (ecmd.base.duplex) {
case DUPLEX_FULL:
case DUPLEX_HALF:
break;
default:
- return;
+ return 1;
}
slave->speed = ecmd.base.speed;
slave->duplex = ecmd.base.duplex;
- return;
+ return 0;
}
const char *bond_slave_link_status(s8 link)
@@ -652,8 +645,8 @@ static void bond_do_fail_over_mac(struct bonding *bond,
struct slave *new_active,
struct slave *old_active)
{
- u8 tmp_mac[ETH_ALEN];
- struct sockaddr saddr;
+ u8 tmp_mac[MAX_ADDR_LEN];
+ struct sockaddr_storage ss;
int rv;
switch (bond->params.fail_over_mac) {
@@ -673,16 +666,20 @@ static void bond_do_fail_over_mac(struct bonding *bond,
old_active = bond_get_old_active(bond, new_active);
if (old_active) {
- ether_addr_copy(tmp_mac, new_active->dev->dev_addr);
- ether_addr_copy(saddr.sa_data,
- old_active->dev->dev_addr);
- saddr.sa_family = new_active->dev->type;
+ bond_hw_addr_copy(tmp_mac, new_active->dev->dev_addr,
+ new_active->dev->addr_len);
+ bond_hw_addr_copy(ss.__data,
+ old_active->dev->dev_addr,
+ old_active->dev->addr_len);
+ ss.ss_family = new_active->dev->type;
} else {
- ether_addr_copy(saddr.sa_data, bond->dev->dev_addr);
- saddr.sa_family = bond->dev->type;
+ bond_hw_addr_copy(ss.__data, bond->dev->dev_addr,
+ bond->dev->addr_len);
+ ss.ss_family = bond->dev->type;
}
- rv = dev_set_mac_address(new_active->dev, &saddr);
+ rv = dev_set_mac_address(new_active->dev,
+ (struct sockaddr *)&ss);
if (rv) {
netdev_err(bond->dev, "Error %d setting MAC of slave %s\n",
-rv, new_active->dev->name);
@@ -692,10 +689,12 @@ static void bond_do_fail_over_mac(struct bonding *bond,
if (!old_active)
goto out;
- ether_addr_copy(saddr.sa_data, tmp_mac);
- saddr.sa_family = old_active->dev->type;
+ bond_hw_addr_copy(ss.__data, tmp_mac,
+ new_active->dev->addr_len);
+ ss.ss_family = old_active->dev->type;
- rv = dev_set_mac_address(old_active->dev, &saddr);
+ rv = dev_set_mac_address(old_active->dev,
+ (struct sockaddr *)&ss);
if (rv)
netdev_err(bond->dev, "Error %d setting MAC of slave %s\n",
-rv, new_active->dev->name);
@@ -1191,7 +1190,8 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
kfree_skb(skb);
return RX_HANDLER_CONSUMED;
}
- ether_addr_copy(eth_hdr(skb)->h_dest, bond->dev->dev_addr);
+ bond_hw_addr_copy(eth_hdr(skb)->h_dest, bond->dev->dev_addr,
+ bond->dev->addr_len);
}
return ret;
@@ -1330,7 +1330,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
struct bonding *bond = netdev_priv(bond_dev);
const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
struct slave *new_slave = NULL, *prev_slave;
- struct sockaddr addr;
+ struct sockaddr_storage ss;
int link_reporting;
int res = 0, i;
@@ -1481,16 +1481,17 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
* that need it, and for restoring it upon release, and then
* set it to the master's address
*/
- ether_addr_copy(new_slave->perm_hwaddr, slave_dev->dev_addr);
+ bond_hw_addr_copy(new_slave->perm_hwaddr, slave_dev->dev_addr,
+ slave_dev->addr_len);
if (!bond->params.fail_over_mac ||
BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
/* Set slave to master's mac address. The application already
* set the master's mac address to that of the first slave
*/
- memcpy(addr.sa_data, bond_dev->dev_addr, bond_dev->addr_len);
- addr.sa_family = slave_dev->type;
- res = dev_set_mac_address(slave_dev, &addr);
+ memcpy(ss.__data, bond_dev->dev_addr, bond_dev->addr_len);
+ ss.ss_family = slave_dev->type;
+ res = dev_set_mac_address(slave_dev, (struct sockaddr *)&ss);
if (res) {
netdev_dbg(bond_dev, "Error %d calling set_mac_address\n", res);
goto err_restore_mtu;
@@ -1565,7 +1566,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
new_slave->delay = 0;
new_slave->link_failure_count = 0;
- bond_update_speed_duplex(new_slave);
+ if (bond_update_speed_duplex(new_slave))
+ new_slave->link = BOND_LINK_DOWN;
new_slave->last_rx = jiffies -
(msecs_to_jiffies(bond->params.arp_interval) + 1);
@@ -1773,9 +1775,10 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
* MAC if this slave's MAC is in use by the bond, or at
* least print a warning.
*/
- ether_addr_copy(addr.sa_data, new_slave->perm_hwaddr);
- addr.sa_family = slave_dev->type;
- dev_set_mac_address(slave_dev, &addr);
+ bond_hw_addr_copy(ss.__data, new_slave->perm_hwaddr,
+ new_slave->dev->addr_len);
+ ss.ss_family = slave_dev->type;
+ dev_set_mac_address(slave_dev, (struct sockaddr *)&ss);
}
err_restore_mtu:
@@ -1818,7 +1821,7 @@ static int __bond_release_one(struct net_device *bond_dev,
{
struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave, *oldcurrent;
- struct sockaddr addr;
+ struct sockaddr_storage ss;
int old_flags = bond_dev->flags;
netdev_features_t old_features = bond_dev->features;
@@ -1953,9 +1956,10 @@ static int __bond_release_one(struct net_device *bond_dev,
if (bond->params.fail_over_mac != BOND_FOM_ACTIVE ||
BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
/* restore original ("permanent") mac address */
- ether_addr_copy(addr.sa_data, slave->perm_hwaddr);
- addr.sa_family = slave_dev->type;
- dev_set_mac_address(slave_dev, &addr);
+ bond_hw_addr_copy(ss.__data, slave->perm_hwaddr,
+ slave->dev->addr_len);
+ ss.ss_family = slave_dev->type;
+ dev_set_mac_address(slave_dev, (struct sockaddr *)&ss);
}
dev_set_mtu(slave_dev, slave->original_mtu);
@@ -2039,8 +2043,7 @@ static int bond_miimon_inspect(struct bonding *bond)
if (link_state)
continue;
- bond_set_slave_link_state(slave, BOND_LINK_FAIL,
- BOND_SLAVE_NOTIFY_LATER);
+ bond_propose_link_state(slave, BOND_LINK_FAIL);
slave->delay = bond->params.downdelay;
if (slave->delay) {
netdev_info(bond->dev, "link status down for %sinterface %s, disabling it in %d ms\n",
@@ -2055,8 +2058,7 @@ static int bond_miimon_inspect(struct bonding *bond)
case BOND_LINK_FAIL:
if (link_state) {
/* recovered before downdelay expired */
- bond_set_slave_link_state(slave, BOND_LINK_UP,
- BOND_SLAVE_NOTIFY_LATER);
+ bond_propose_link_state(slave, BOND_LINK_UP);
slave->last_link_up = jiffies;
netdev_info(bond->dev, "link status up again after %d ms for interface %s\n",
(bond->params.downdelay - slave->delay) *
@@ -2078,8 +2080,7 @@ static int bond_miimon_inspect(struct bonding *bond)
if (!link_state)
continue;
- bond_set_slave_link_state(slave, BOND_LINK_BACK,
- BOND_SLAVE_NOTIFY_LATER);
+ bond_propose_link_state(slave, BOND_LINK_BACK);
slave->delay = bond->params.updelay;
if (slave->delay) {
@@ -2092,9 +2093,7 @@ static int bond_miimon_inspect(struct bonding *bond)
/*FALLTHRU*/
case BOND_LINK_BACK:
if (!link_state) {
- bond_set_slave_link_state(slave,
- BOND_LINK_DOWN,
- BOND_SLAVE_NOTIFY_LATER);
+ bond_propose_link_state(slave, BOND_LINK_DOWN);
netdev_info(bond->dev, "link status down again after %d ms for interface %s\n",
(bond->params.updelay - slave->delay) *
bond->params.miimon,
@@ -2132,7 +2131,13 @@ static void bond_miimon_commit(struct bonding *bond)
continue;
case BOND_LINK_UP:
- bond_update_speed_duplex(slave);
+ if (bond_update_speed_duplex(slave)) {
+ slave->link = BOND_LINK_DOWN;
+ netdev_warn(bond->dev,
+ "failed to get link speed/duplex for %s\n",
+ slave->dev->name);
+ continue;
+ }
bond_set_slave_link_state(slave, BOND_LINK_UP,
BOND_SLAVE_NOTIFY_NOW);
slave->last_link_up = jiffies;
@@ -2231,6 +2236,8 @@ static void bond_mii_monitor(struct work_struct *work)
mii_work.work);
bool should_notify_peers = false;
unsigned long delay;
+ struct slave *slave;
+ struct list_head *iter;
delay = msecs_to_jiffies(bond->params.miimon);
@@ -2251,6 +2258,9 @@ static void bond_mii_monitor(struct work_struct *work)
goto re_arm;
}
+ bond_for_each_slave(bond, slave, iter) {
+ bond_commit_link_state(slave, BOND_SLAVE_NOTIFY_LATER);
+ }
bond_miimon_commit(bond);
rtnl_unlock(); /* might sleep, hold no other locks */
@@ -2575,10 +2585,8 @@ static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act,
* arp is transmitted to generate traffic. see activebackup_arp_monitor for
* arp monitoring in active backup mode.
*/
-static void bond_loadbalance_arp_mon(struct work_struct *work)
+static void bond_loadbalance_arp_mon(struct bonding *bond)
{
- struct bonding *bond = container_of(work, struct bonding,
- arp_work.work);
struct slave *slave, *oldcurrent;
struct list_head *iter;
int do_failover = 0, slave_state_changed = 0;
@@ -2916,10 +2924,8 @@ static bool bond_ab_arp_probe(struct bonding *bond)
return should_notify_rtnl;
}
-static void bond_activebackup_arp_mon(struct work_struct *work)
+static void bond_activebackup_arp_mon(struct bonding *bond)
{
- struct bonding *bond = container_of(work, struct bonding,
- arp_work.work);
bool should_notify_peers = false;
bool should_notify_rtnl = false;
int delta_in_ticks;
@@ -2972,6 +2978,17 @@ static void bond_activebackup_arp_mon(struct work_struct *work)
}
}
+static void bond_arp_monitor(struct work_struct *work)
+{
+ struct bonding *bond = container_of(work, struct bonding,
+ arp_work.work);
+
+ if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP)
+ bond_activebackup_arp_mon(bond);
+ else
+ bond_loadbalance_arp_mon(bond);
+}
+
/*-------------------------- netdev event handling --------------------------*/
/* Change device name */
@@ -3228,10 +3245,7 @@ static void bond_work_init_all(struct bonding *bond)
bond_resend_igmp_join_requests_delayed);
INIT_DELAYED_WORK(&bond->alb_work, bond_alb_monitor);
INIT_DELAYED_WORK(&bond->mii_work, bond_mii_monitor);
- if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP)
- INIT_DELAYED_WORK(&bond->arp_work, bond_activebackup_arp_mon);
- else
- INIT_DELAYED_WORK(&bond->arp_work, bond_loadbalance_arp_mon);
+ INIT_DELAYED_WORK(&bond->arp_work, bond_arp_monitor);
INIT_DELAYED_WORK(&bond->ad_work, bond_3ad_state_machine_handler);
INIT_DELAYED_WORK(&bond->slave_arr_work, bond_slave_arr_handler);
}
@@ -3266,8 +3280,6 @@ static int bond_open(struct net_device *bond_dev)
}
}
- bond_work_init_all(bond);
-
if (bond_is_lb(bond)) {
/* bond_alb_initialize must be called before the timer
* is started.
@@ -3327,12 +3339,17 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res,
for (i = 0; i < sizeof(*_res) / sizeof(u64); i++) {
u64 nv = new[i];
u64 ov = old[i];
+ s64 delta = nv - ov;
/* detects if this particular field is 32bit only */
if (((nv | ov) >> 32) == 0)
- res[i] += (u32)nv - (u32)ov;
- else
- res[i] += nv - ov;
+ delta = (s64)(s32)((u32)nv - (u32)ov);
+
+ /* filter anomalies, some drivers reset their stats
+ * at down/up events.
+ */
+ if (delta > 0)
+ res[i] += delta;
}
}
@@ -3619,7 +3636,7 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
{
struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave, *rollback_slave;
- struct sockaddr *sa = addr, tmp_sa;
+ struct sockaddr_storage *ss = addr, tmp_ss;
struct list_head *iter;
int res = 0;
@@ -3636,7 +3653,7 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP)
return 0;
- if (!is_valid_ether_addr(sa->sa_data))
+ if (!is_valid_ether_addr(ss->__data))
return -EADDRNOTAVAIL;
bond_for_each_slave(bond, slave, iter) {
@@ -3655,12 +3672,12 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
}
/* success */
- memcpy(bond_dev->dev_addr, sa->sa_data, bond_dev->addr_len);
+ memcpy(bond_dev->dev_addr, ss->__data, bond_dev->addr_len);
return 0;
unwind:
- memcpy(tmp_sa.sa_data, bond_dev->dev_addr, bond_dev->addr_len);
- tmp_sa.sa_family = bond_dev->type;
+ memcpy(tmp_ss.__data, bond_dev->dev_addr, bond_dev->addr_len);
+ tmp_ss.ss_family = bond_dev->type;
/* unwind from head to the slave that failed */
bond_for_each_slave(bond, rollback_slave, iter) {
@@ -3669,7 +3686,8 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
if (rollback_slave == slave)
break;
- tmp_res = dev_set_mac_address(rollback_slave->dev, &tmp_sa);
+ tmp_res = dev_set_mac_address(rollback_slave->dev,
+ (struct sockaddr *)&tmp_ss);
if (tmp_res) {
netdev_dbg(bond_dev, "unwind err %d dev %s\n",
tmp_res, rollback_slave->dev->name);
@@ -4252,6 +4270,12 @@ static int bond_check_params(struct bond_params *params)
int arp_all_targets_value;
u16 ad_actor_sys_prio = 0;
u16 ad_user_port_key = 0;
+ __be32 arp_target[BOND_MAX_ARP_TARGETS];
+ int arp_ip_count;
+ int bond_mode = BOND_MODE_ROUNDROBIN;
+ int xmit_hashtype = BOND_XMIT_POLICY_LAYER2;
+ int lacp_fast = 0;
+ int tlb_dynamic_lb = 0;
/* Convert string parameters. */
if (mode) {
@@ -4564,6 +4588,17 @@ static int bond_check_params(struct bond_params *params)
}
ad_user_port_key = valptr->value;
+ if (bond_mode == BOND_MODE_TLB) {
+ bond_opt_initstr(&newval, "default");
+ valptr = bond_opt_parse(bond_opt_get(BOND_OPT_TLB_DYNAMIC_LB),
+ &newval);
+ if (!valptr) {
+ pr_err("Error: No tlb_dynamic_lb default value");
+ return -EINVAL;
+ }
+ tlb_dynamic_lb = valptr->value;
+ }
+
if (lp_interval == 0) {
pr_warn("Warning: ip_interval must be between 1 and %d, so it was reset to %d\n",
INT_MAX, BOND_ALB_DEFAULT_LP_INTERVAL);
@@ -4591,7 +4626,7 @@ static int bond_check_params(struct bond_params *params)
params->min_links = min_links;
params->lp_interval = lp_interval;
params->packets_per_slave = packets_per_slave;
- params->tlb_dynamic_lb = 1; /* Default value */
+ params->tlb_dynamic_lb = tlb_dynamic_lb;
params->ad_actor_sys_prio = ad_actor_sys_prio;
eth_zero_addr(params->ad_actor_system);
params->ad_user_port_key = ad_user_port_key;
@@ -4687,6 +4722,8 @@ int bond_create(struct net *net, const char *name)
netif_carrier_off(bond_dev);
+ bond_work_init_all(bond);
+
rtnl_unlock();
if (res < 0)
bond_destructor(bond_dev);
diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c
index f514fe5..d8d4ada 100644
--- a/drivers/net/bonding/bond_procfs.c
+++ b/drivers/net/bonding/bond_procfs.c
@@ -183,7 +183,8 @@ static void bond_info_show_slave(struct seq_file *seq,
seq_printf(seq, "Link Failure Count: %u\n",
slave->link_failure_count);
- seq_printf(seq, "Permanent HW addr: %pM\n", slave->perm_hwaddr);
+ seq_printf(seq, "Permanent HW addr: %*phC\n",
+ slave->dev->addr_len, slave->perm_hwaddr);
seq_printf(seq, "Slave queue ID: %d\n", slave->queue_id);
if (BOND_MODE(bond) == BOND_MODE_8023AD) {
diff --git a/drivers/net/can/spi/Kconfig b/drivers/net/can/spi/Kconfig
index 148cae5..8f2e0dd 100644
--- a/drivers/net/can/spi/Kconfig
+++ b/drivers/net/can/spi/Kconfig
@@ -1,6 +1,12 @@
menu "CAN SPI interfaces"
depends on SPI
+config CAN_HI311X
+ tristate "Holt HI311x SPI CAN controllers"
+ depends on CAN_DEV && SPI && HAS_DMA
+ ---help---
+ Driver for the Holt HI311x SPI CAN controllers.
+
config CAN_MCP251X
tristate "Microchip MCP251x SPI CAN controllers"
depends on HAS_DMA
diff --git a/drivers/net/can/spi/Makefile b/drivers/net/can/spi/Makefile
index 0e86040..f59fa37 100644
--- a/drivers/net/can/spi/Makefile
+++ b/drivers/net/can/spi/Makefile
@@ -3,4 +3,5 @@
#
+obj-$(CONFIG_CAN_HI311X) += hi311x.o
obj-$(CONFIG_CAN_MCP251X) += mcp251x.o
diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c
new file mode 100644
index 0000000..5590c55
--- /dev/null
+++ b/drivers/net/can/spi/hi311x.c
@@ -0,0 +1,1076 @@
+/* CAN bus driver for Holt HI3110 CAN Controller with SPI Interface
+ *
+ * Copyright(C) Timesys Corporation 2016
+ *
+ * Based on Microchip 251x CAN Controller (mcp251x) Linux kernel driver
+ * Copyright 2009 Christian Pellegrin EVOL S.r.l.
+ * Copyright 2007 Raymarine UK, Ltd. All Rights Reserved.
+ * Copyright 2006 Arcom Control Systems Ltd.
+ *
+ * Based on CAN bus driver for the CCAN controller written by
+ * - Sascha Hauer, Marc Kleine-Budde, Pengutronix
+ * - Simon Kallweit, intefo AG
+ * Copyright 2007
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/can/core.h>
+#include <linux/can/dev.h>
+#include <linux/can/led.h>
+#include <linux/clk.h>
+#include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/freezer.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/consumer.h>
+#include <linux/slab.h>
+#include <linux/spi/spi.h>
+#include <linux/uaccess.h>
+
+#define HI3110_MASTER_RESET 0x56
+#define HI3110_READ_CTRL0 0xD2
+#define HI3110_READ_CTRL1 0xD4
+#define HI3110_READ_STATF 0xE2
+#define HI3110_WRITE_CTRL0 0x14
+#define HI3110_WRITE_CTRL1 0x16
+#define HI3110_WRITE_INTE 0x1C
+#define HI3110_WRITE_BTR0 0x18
+#define HI3110_WRITE_BTR1 0x1A
+#define HI3110_READ_BTR0 0xD6
+#define HI3110_READ_BTR1 0xD8
+#define HI3110_READ_INTF 0xDE
+#define HI3110_READ_ERR 0xDC
+#define HI3110_READ_FIFO_WOTIME 0x48
+#define HI3110_WRITE_FIFO 0x12
+#define HI3110_READ_MESSTAT 0xDA
+#define HI3110_READ_REC 0xEA
+#define HI3110_READ_TEC 0xEC
+
+#define HI3110_CTRL0_MODE_MASK (7 << 5)
+#define HI3110_CTRL0_NORMAL_MODE (0 << 5)
+#define HI3110_CTRL0_LOOPBACK_MODE (1 << 5)
+#define HI3110_CTRL0_MONITOR_MODE (2 << 5)
+#define HI3110_CTRL0_SLEEP_MODE (3 << 5)
+#define HI3110_CTRL0_INIT_MODE (4 << 5)
+
+#define HI3110_CTRL1_TXEN BIT(7)
+
+#define HI3110_INT_RXTMP BIT(7)
+#define HI3110_INT_RXFIFO BIT(6)
+#define HI3110_INT_TXCPLT BIT(5)
+#define HI3110_INT_BUSERR BIT(4)
+#define HI3110_INT_MCHG BIT(3)
+#define HI3110_INT_WAKEUP BIT(2)
+#define HI3110_INT_F1MESS BIT(1)
+#define HI3110_INT_F0MESS BIT(0)
+
+#define HI3110_ERR_BUSOFF BIT(7)
+#define HI3110_ERR_TXERRP BIT(6)
+#define HI3110_ERR_RXERRP BIT(5)
+#define HI3110_ERR_BITERR BIT(4)
+#define HI3110_ERR_FRMERR BIT(3)
+#define HI3110_ERR_CRCERR BIT(2)
+#define HI3110_ERR_ACKERR BIT(1)
+#define HI3110_ERR_STUFERR BIT(0)
+#define HI3110_ERR_PROTOCOL_MASK (0x1F)
+#define HI3110_ERR_PASSIVE_MASK (0x60)
+
+#define HI3110_STAT_RXFMTY BIT(1)
+#define HI3110_STAT_BUSOFF BIT(2)
+#define HI3110_STAT_ERRP BIT(3)
+#define HI3110_STAT_ERRW BIT(4)
+
+#define HI3110_BTR0_SJW_SHIFT 6
+#define HI3110_BTR0_BRP_SHIFT 0
+
+#define HI3110_BTR1_SAMP_3PERBIT (1 << 7)
+#define HI3110_BTR1_SAMP_1PERBIT (0 << 7)
+#define HI3110_BTR1_TSEG2_SHIFT 4
+#define HI3110_BTR1_TSEG1_SHIFT 0
+
+#define HI3110_FIFO_WOTIME_TAG_OFF 0
+#define HI3110_FIFO_WOTIME_ID_OFF 1
+#define HI3110_FIFO_WOTIME_DLC_OFF 5
+#define HI3110_FIFO_WOTIME_DAT_OFF 6
+
+#define HI3110_FIFO_WOTIME_TAG_IDE BIT(7)
+#define HI3110_FIFO_WOTIME_ID_RTR BIT(0)
+
+#define HI3110_FIFO_TAG_OFF 0
+#define HI3110_FIFO_ID_OFF 1
+#define HI3110_FIFO_STD_DLC_OFF 3
+#define HI3110_FIFO_STD_DATA_OFF 4
+#define HI3110_FIFO_EXT_DLC_OFF 5
+#define HI3110_FIFO_EXT_DATA_OFF 6
+
+#define HI3110_CAN_MAX_DATA_LEN 8
+#define HI3110_RX_BUF_LEN 15
+#define HI3110_TX_STD_BUF_LEN 12
+#define HI3110_TX_EXT_BUF_LEN 14
+#define HI3110_CAN_FRAME_MAX_BITS 128
+#define HI3110_EFF_FLAGS 0x18 /* IDE + SRR */
+
+#define HI3110_TX_ECHO_SKB_MAX 1
+
+#define HI3110_OST_DELAY_MS (10)
+
+#define DEVICE_NAME "hi3110"
+
+static int hi3110_enable_dma = 1; /* Enable SPI DMA. Default: 1 (On) */
+module_param(hi3110_enable_dma, int, 0444);
+MODULE_PARM_DESC(hi3110_enable_dma, "Enable SPI DMA. Default: 1 (On)");
+
+static const struct can_bittiming_const hi3110_bittiming_const = {
+ .name = DEVICE_NAME,
+ .tseg1_min = 2,
+ .tseg1_max = 16,
+ .tseg2_min = 2,
+ .tseg2_max = 8,
+ .sjw_max = 4,
+ .brp_min = 1,
+ .brp_max = 64,
+ .brp_inc = 1,
+};
+
+enum hi3110_model {
+ CAN_HI3110_HI3110 = 0x3110,
+};
+
+struct hi3110_priv {
+ struct can_priv can;
+ struct net_device *net;
+ struct spi_device *spi;
+ enum hi3110_model model;
+
+ struct mutex hi3110_lock; /* SPI device lock */
+
+ u8 *spi_tx_buf;
+ u8 *spi_rx_buf;
+ dma_addr_t spi_tx_dma;
+ dma_addr_t spi_rx_dma;
+
+ struct sk_buff *tx_skb;
+ int tx_len;
+
+ struct workqueue_struct *wq;
+ struct work_struct tx_work;
+ struct work_struct restart_work;
+
+ int force_quit;
+ int after_suspend;
+#define HI3110_AFTER_SUSPEND_UP 1
+#define HI3110_AFTER_SUSPEND_DOWN 2
+#define HI3110_AFTER_SUSPEND_POWER 4
+#define HI3110_AFTER_SUSPEND_RESTART 8
+ int restart_tx;
+ struct regulator *power;
+ struct regulator *transceiver;
+ struct clk *clk;
+};
+
+static void hi3110_clean(struct net_device *net)
+{
+ struct hi3110_priv *priv = netdev_priv(net);
+
+ if (priv->tx_skb || priv->tx_len)
+ net->stats.tx_errors++;
+ if (priv->tx_skb)
+ dev_kfree_skb(priv->tx_skb);
+ if (priv->tx_len)
+ can_free_echo_skb(priv->net, 0);
+ priv->tx_skb = NULL;
+ priv->tx_len = 0;
+}
+
+/* Note about handling of error return of hi3110_spi_trans: accessing
+ * registers via SPI is not really different conceptually than using
+ * normal I/O assembler instructions, although it's much more
+ * complicated from a practical POV. So it's not advisable to always
+ * check the return value of this function. Imagine that every
+ * read{b,l}, write{b,l} and friends would be bracketed in "if ( < 0)
+ * error();", it would be a great mess (well there are some situation
+ * when exception handling C++ like could be useful after all). So we
+ * just check that transfers are OK at the beginning of our
+ * conversation with the chip and to avoid doing really nasty things
+ * (like injecting bogus packets in the network stack).
+ */
+static int hi3110_spi_trans(struct spi_device *spi, int len)
+{
+ struct hi3110_priv *priv = spi_get_drvdata(spi);
+ struct spi_transfer t = {
+ .tx_buf = priv->spi_tx_buf,
+ .rx_buf = priv->spi_rx_buf,
+ .len = len,
+ .cs_change = 0,
+ };
+ struct spi_message m;
+ int ret;
+
+ spi_message_init(&m);
+
+ if (hi3110_enable_dma) {
+ t.tx_dma = priv->spi_tx_dma;
+ t.rx_dma = priv->spi_rx_dma;
+ m.is_dma_mapped = 1;
+ }
+
+ spi_message_add_tail(&t, &m);
+
+ ret = spi_sync(spi, &m);
+
+ if (ret)
+ dev_err(&spi->dev, "spi transfer failed: ret = %d\n", ret);
+ return ret;
+}
+
+static u8 hi3110_cmd(struct spi_device *spi, u8 command)
+{
+ struct hi3110_priv *priv = spi_get_drvdata(spi);
+
+ priv->spi_tx_buf[0] = command;
+ dev_dbg(&spi->dev, "hi3110_cmd: %02X\n", command);
+
+ return hi3110_spi_trans(spi, 1);
+}
+
+static u8 hi3110_read(struct spi_device *spi, u8 command)
+{
+ struct hi3110_priv *priv = spi_get_drvdata(spi);
+ u8 val = 0;
+
+ priv->spi_tx_buf[0] = command;
+ hi3110_spi_trans(spi, 2);
+ val = priv->spi_rx_buf[1];
+
+ return val;
+}
+
+static void hi3110_write(struct spi_device *spi, u8 reg, u8 val)
+{
+ struct hi3110_priv *priv = spi_get_drvdata(spi);
+
+ priv->spi_tx_buf[0] = reg;
+ priv->spi_tx_buf[1] = val;
+ hi3110_spi_trans(spi, 2);
+}
+
+static void hi3110_hw_tx_frame(struct spi_device *spi, u8 *buf, int len)
+{
+ struct hi3110_priv *priv = spi_get_drvdata(spi);
+
+ priv->spi_tx_buf[0] = HI3110_WRITE_FIFO;
+ memcpy(priv->spi_tx_buf + 1, buf, len);
+ hi3110_spi_trans(spi, len + 1);
+}
+
+static void hi3110_hw_tx(struct spi_device *spi, struct can_frame *frame)
+{
+ u8 buf[HI3110_TX_EXT_BUF_LEN];
+
+ buf[HI3110_FIFO_TAG_OFF] = 0;
+
+ if (frame->can_id & CAN_EFF_FLAG) {
+ /* Extended frame */
+ buf[HI3110_FIFO_ID_OFF] = (frame->can_id & CAN_EFF_MASK) >> 21;
+ buf[HI3110_FIFO_ID_OFF + 1] =
+ (((frame->can_id & CAN_EFF_MASK) >> 13) & 0xe0) |
+ HI3110_EFF_FLAGS |
+ (((frame->can_id & CAN_EFF_MASK) >> 15) & 0x07);
+ buf[HI3110_FIFO_ID_OFF + 2] =
+ (frame->can_id & CAN_EFF_MASK) >> 7;
+ buf[HI3110_FIFO_ID_OFF + 3] =
+ ((frame->can_id & CAN_EFF_MASK) << 1) |
+ ((frame->can_id & CAN_RTR_FLAG) ? 1 : 0);
+
+ buf[HI3110_FIFO_EXT_DLC_OFF] = frame->can_dlc;
+
+ memcpy(buf + HI3110_FIFO_EXT_DATA_OFF,
+ frame->data, frame->can_dlc);
+
+ hi3110_hw_tx_frame(spi, buf, HI3110_TX_EXT_BUF_LEN -
+ (HI3110_CAN_MAX_DATA_LEN - frame->can_dlc));
+ } else {
+ /* Standard frame */
+ buf[HI3110_FIFO_ID_OFF] = (frame->can_id & CAN_SFF_MASK) >> 3;
+ buf[HI3110_FIFO_ID_OFF + 1] =
+ ((frame->can_id & CAN_SFF_MASK) << 5) |
+ ((frame->can_id & CAN_RTR_FLAG) ? (1 << 4) : 0);
+
+ buf[HI3110_FIFO_STD_DLC_OFF] = frame->can_dlc;
+
+ memcpy(buf + HI3110_FIFO_STD_DATA_OFF,
+ frame->data, frame->can_dlc);
+
+ hi3110_hw_tx_frame(spi, buf, HI3110_TX_STD_BUF_LEN -
+ (HI3110_CAN_MAX_DATA_LEN - frame->can_dlc));
+ }
+}
+
+static void hi3110_hw_rx_frame(struct spi_device *spi, u8 *buf)
+{
+ struct hi3110_priv *priv = spi_get_drvdata(spi);
+
+ priv->spi_tx_buf[0] = HI3110_READ_FIFO_WOTIME;
+ hi3110_spi_trans(spi, HI3110_RX_BUF_LEN);
+ memcpy(buf, priv->spi_rx_buf + 1, HI3110_RX_BUF_LEN - 1);
+}
+
+static void hi3110_hw_rx(struct spi_device *spi)
+{
+ struct hi3110_priv *priv = spi_get_drvdata(spi);
+ struct sk_buff *skb;
+ struct can_frame *frame;
+ u8 buf[HI3110_RX_BUF_LEN - 1];
+
+ skb = alloc_can_skb(priv->net, &frame);
+ if (!skb) {
+ priv->net->stats.rx_dropped++;
+ return;
+ }
+
+ hi3110_hw_rx_frame(spi, buf);
+ if (buf[HI3110_FIFO_WOTIME_TAG_OFF] & HI3110_FIFO_WOTIME_TAG_IDE) {
+ /* IDE is recessive (1), indicating extended 29-bit frame */
+ frame->can_id = CAN_EFF_FLAG;
+ frame->can_id |=
+ (buf[HI3110_FIFO_WOTIME_ID_OFF] << 21) |
+ (((buf[HI3110_FIFO_WOTIME_ID_OFF + 1] & 0xE0) >> 5) << 18) |
+ ((buf[HI3110_FIFO_WOTIME_ID_OFF + 1] & 0x07) << 15) |
+ (buf[HI3110_FIFO_WOTIME_ID_OFF + 2] << 7) |
+ (buf[HI3110_FIFO_WOTIME_ID_OFF + 3] >> 1);
+ } else {
+ /* IDE is dominant (0), frame indicating standard 11-bit */
+ frame->can_id =
+ (buf[HI3110_FIFO_WOTIME_ID_OFF] << 3) |
+ ((buf[HI3110_FIFO_WOTIME_ID_OFF + 1] & 0xE0) >> 5);
+ }
+
+ /* Data length */
+ frame->can_dlc = get_can_dlc(buf[HI3110_FIFO_WOTIME_DLC_OFF] & 0x0F);
+
+ if (buf[HI3110_FIFO_WOTIME_ID_OFF + 3] & HI3110_FIFO_WOTIME_ID_RTR)
+ frame->can_id |= CAN_RTR_FLAG;
+ else
+ memcpy(frame->data, buf + HI3110_FIFO_WOTIME_DAT_OFF,
+ frame->can_dlc);
+
+ priv->net->stats.rx_packets++;
+ priv->net->stats.rx_bytes += frame->can_dlc;
+
+ can_led_event(priv->net, CAN_LED_EVENT_RX);
+
+ netif_rx_ni(skb);
+}
+
+static void hi3110_hw_sleep(struct spi_device *spi)
+{
+ hi3110_write(spi, HI3110_WRITE_CTRL0, HI3110_CTRL0_SLEEP_MODE);
+}
+
+static netdev_tx_t hi3110_hard_start_xmit(struct sk_buff *skb,
+ struct net_device *net)
+{
+ struct hi3110_priv *priv = netdev_priv(net);
+ struct spi_device *spi = priv->spi;
+
+ if (priv->tx_skb || priv->tx_len) {
+ dev_err(&spi->dev, "hard_xmit called while tx busy\n");
+ return NETDEV_TX_BUSY;
+ }
+
+ if (can_dropped_invalid_skb(net, skb))
+ return NETDEV_TX_OK;
+
+ netif_stop_queue(net);
+ priv->tx_skb = skb;
+ queue_work(priv->wq, &priv->tx_work);
+
+ return NETDEV_TX_OK;
+}
+
+static int hi3110_do_set_mode(struct net_device *net, enum can_mode mode)
+{
+ struct hi3110_priv *priv = netdev_priv(net);
+
+ switch (mode) {
+ case CAN_MODE_START:
+ hi3110_clean(net);
+ /* We have to delay work since SPI I/O may sleep */
+ priv->can.state = CAN_STATE_ERROR_ACTIVE;
+ priv->restart_tx = 1;
+ if (priv->can.restart_ms == 0)
+ priv->after_suspend = HI3110_AFTER_SUSPEND_RESTART;
+ queue_work(priv->wq, &priv->restart_work);
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
+
+static int hi3110_get_berr_counter(const struct net_device *net,
+ struct can_berr_counter *bec)
+{
+ struct hi3110_priv *priv = netdev_priv(net);
+ struct spi_device *spi = priv->spi;
+
+ bec->txerr = hi3110_read(spi, HI3110_READ_TEC);
+ bec->rxerr = hi3110_read(spi, HI3110_READ_REC);
+
+ return 0;
+}
+
+static int hi3110_set_normal_mode(struct spi_device *spi)
+{
+ struct hi3110_priv *priv = spi_get_drvdata(spi);
+ u8 reg = 0;
+
+ hi3110_write(spi, HI3110_WRITE_INTE, HI3110_INT_BUSERR |
+ HI3110_INT_RXFIFO | HI3110_INT_TXCPLT);
+
+ /* Enable TX */
+ hi3110_write(spi, HI3110_WRITE_CTRL1, HI3110_CTRL1_TXEN);
+
+ if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK)
+ reg = HI3110_CTRL0_LOOPBACK_MODE;
+ else if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
+ reg = HI3110_CTRL0_MONITOR_MODE;
+ else
+ reg = HI3110_CTRL0_NORMAL_MODE;
+
+ hi3110_write(spi, HI3110_WRITE_CTRL0, reg);
+
+ /* Wait for the device to enter the mode */
+ mdelay(HI3110_OST_DELAY_MS);
+ reg = hi3110_read(spi, HI3110_READ_CTRL0);
+ if ((reg & HI3110_CTRL0_MODE_MASK) != reg)
+ return -EBUSY;
+
+ priv->can.state = CAN_STATE_ERROR_ACTIVE;
+ return 0;
+}
+
+static int hi3110_do_set_bittiming(struct net_device *net)
+{
+ struct hi3110_priv *priv = netdev_priv(net);
+ struct can_bittiming *bt = &priv->can.bittiming;
+ struct spi_device *spi = priv->spi;
+
+ hi3110_write(spi, HI3110_WRITE_BTR0,
+ ((bt->sjw - 1) << HI3110_BTR0_SJW_SHIFT) |
+ ((bt->brp - 1) << HI3110_BTR0_BRP_SHIFT));
+
+ hi3110_write(spi, HI3110_WRITE_BTR1,
+ (priv->can.ctrlmode &
+ CAN_CTRLMODE_3_SAMPLES ?
+ HI3110_BTR1_SAMP_3PERBIT : HI3110_BTR1_SAMP_1PERBIT) |
+ ((bt->phase_seg1 + bt->prop_seg - 1)
+ << HI3110_BTR1_TSEG1_SHIFT) |
+ ((bt->phase_seg2 - 1) << HI3110_BTR1_TSEG2_SHIFT));
+
+ dev_dbg(&spi->dev, "BT: 0x%02x 0x%02x\n",
+ hi3110_read(spi, HI3110_READ_BTR0),
+ hi3110_read(spi, HI3110_READ_BTR1));
+
+ return 0;
+}
+
+static int hi3110_setup(struct net_device *net)
+{
+ hi3110_do_set_bittiming(net);
+ return 0;
+}
+
+static int hi3110_hw_reset(struct spi_device *spi)
+{
+ u8 reg;
+ int ret;
+
+ /* Wait for oscillator startup timer after power up */
+ mdelay(HI3110_OST_DELAY_MS);
+
+ ret = hi3110_cmd(spi, HI3110_MASTER_RESET);
+ if (ret)
+ return ret;
+
+ /* Wait for oscillator startup timer after reset */
+ mdelay(HI3110_OST_DELAY_MS);
+
+ reg = hi3110_read(spi, HI3110_READ_CTRL0);
+ if ((reg & HI3110_CTRL0_MODE_MASK) != HI3110_CTRL0_INIT_MODE)
+ return -ENODEV;
+
+ /* As per the datasheet it appears the error flags are
+ * not cleared on reset. Explicitly clear them by performing a read
+ */
+ hi3110_read(spi, HI3110_READ_ERR);
+
+ return 0;
+}
+
+static int hi3110_hw_probe(struct spi_device *spi)
+{
+ u8 statf;
+
+ hi3110_hw_reset(spi);
+
+ /* Confirm correct operation by checking against reset values
+ * in datasheet
+ */
+ statf = hi3110_read(spi, HI3110_READ_STATF);
+
+ dev_dbg(&spi->dev, "statf: %02X\n", statf);
+
+ if (statf != 0x82)
+ return -ENODEV;
+
+ return 0;
+}
+
+static int hi3110_power_enable(struct regulator *reg, int enable)
+{
+ if (IS_ERR_OR_NULL(reg))
+ return 0;
+
+ if (enable)
+ return regulator_enable(reg);
+ else
+ return regulator_disable(reg);
+}
+
+static int hi3110_stop(struct net_device *net)
+{
+ struct hi3110_priv *priv = netdev_priv(net);
+ struct spi_device *spi = priv->spi;
+
+ close_candev(net);
+
+ priv->force_quit = 1;
+ free_irq(spi->irq, priv);
+ destroy_workqueue(priv->wq);
+ priv->wq = NULL;
+
+ mutex_lock(&priv->hi3110_lock);
+
+ /* Disable transmit, interrupts and clear flags */
+ hi3110_write(spi, HI3110_WRITE_CTRL1, 0x0);
+ hi3110_write(spi, HI3110_WRITE_INTE, 0x0);
+ hi3110_read(spi, HI3110_READ_INTF);
+
+ hi3110_clean(net);
+
+ hi3110_hw_sleep(spi);
+
+ hi3110_power_enable(priv->transceiver, 0);
+
+ priv->can.state = CAN_STATE_STOPPED;
+
+ mutex_unlock(&priv->hi3110_lock);
+
+ can_led_event(net, CAN_LED_EVENT_STOP);
+
+ return 0;
+}
+
+static void hi3110_tx_work_handler(struct work_struct *ws)
+{
+ struct hi3110_priv *priv = container_of(ws, struct hi3110_priv,
+ tx_work);
+ struct spi_device *spi = priv->spi;
+ struct net_device *net = priv->net;
+ struct can_frame *frame;
+
+ mutex_lock(&priv->hi3110_lock);
+ if (priv->tx_skb) {
+ if (priv->can.state == CAN_STATE_BUS_OFF) {
+ hi3110_clean(net);
+ } else {
+ frame = (struct can_frame *)priv->tx_skb->data;
+ hi3110_hw_tx(spi, frame);
+ priv->tx_len = 1 + frame->can_dlc;
+ can_put_echo_skb(priv->tx_skb, net, 0);
+ priv->tx_skb = NULL;
+ }
+ }
+ mutex_unlock(&priv->hi3110_lock);
+}
+
+static void hi3110_restart_work_handler(struct work_struct *ws)
+{
+ struct hi3110_priv *priv = container_of(ws, struct hi3110_priv,
+ restart_work);
+ struct spi_device *spi = priv->spi;
+ struct net_device *net = priv->net;
+
+ mutex_lock(&priv->hi3110_lock);
+ if (priv->after_suspend) {
+ hi3110_hw_reset(spi);
+ hi3110_setup(net);
+ if (priv->after_suspend & HI3110_AFTER_SUSPEND_RESTART) {
+ hi3110_set_normal_mode(spi);
+ } else if (priv->after_suspend & HI3110_AFTER_SUSPEND_UP) {
+ netif_device_attach(net);
+ hi3110_clean(net);
+ hi3110_set_normal_mode(spi);
+ netif_wake_queue(net);
+ } else {
+ hi3110_hw_sleep(spi);
+ }
+ priv->after_suspend = 0;
+ priv->force_quit = 0;
+ }
+
+ if (priv->restart_tx) {
+ priv->restart_tx = 0;
+ hi3110_hw_reset(spi);
+ hi3110_setup(net);
+ hi3110_clean(net);
+ hi3110_set_normal_mode(spi);
+ netif_wake_queue(net);
+ }
+ mutex_unlock(&priv->hi3110_lock);
+}
+
+static irqreturn_t hi3110_can_ist(int irq, void *dev_id)
+{
+ struct hi3110_priv *priv = dev_id;
+ struct spi_device *spi = priv->spi;
+ struct net_device *net = priv->net;
+
+ mutex_lock(&priv->hi3110_lock);
+
+ while (!priv->force_quit) {
+ enum can_state new_state;
+ u8 intf, eflag, statf;
+
+ while (!(HI3110_STAT_RXFMTY &
+ (statf = hi3110_read(spi, HI3110_READ_STATF)))) {
+ hi3110_hw_rx(spi);
+ }
+
+ intf = hi3110_read(spi, HI3110_READ_INTF);
+ eflag = hi3110_read(spi, HI3110_READ_ERR);
+ /* Update can state */
+ if (eflag & HI3110_ERR_BUSOFF)
+ new_state = CAN_STATE_BUS_OFF;
+ else if (eflag & HI3110_ERR_PASSIVE_MASK)
+ new_state = CAN_STATE_ERROR_PASSIVE;
+ else if (statf & HI3110_STAT_ERRW)
+ new_state = CAN_STATE_ERROR_WARNING;
+ else
+ new_state = CAN_STATE_ERROR_ACTIVE;
+
+ if (new_state != priv->can.state) {
+ struct can_frame *cf;
+ struct sk_buff *skb;
+ enum can_state rx_state, tx_state;
+ u8 rxerr, txerr;
+
+ skb = alloc_can_err_skb(net, &cf);
+ if (!skb)
+ break;
+
+ txerr = hi3110_read(spi, HI3110_READ_TEC);
+ rxerr = hi3110_read(spi, HI3110_READ_REC);
+ cf->data[6] = txerr;
+ cf->data[7] = rxerr;
+ tx_state = txerr >= rxerr ? new_state : 0;
+ rx_state = txerr <= rxerr ? new_state : 0;
+ can_change_state(net, cf, tx_state, rx_state);
+ netif_rx_ni(skb);
+
+ if (new_state == CAN_STATE_BUS_OFF) {
+ can_bus_off(net);
+ if (priv->can.restart_ms == 0) {
+ priv->force_quit = 1;
+ hi3110_hw_sleep(spi);
+ break;
+ }
+ }
+ }
+
+ /* Update bus errors */
+ if ((intf & HI3110_INT_BUSERR) &&
+ (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING)) {
+ struct can_frame *cf;
+ struct sk_buff *skb;
+
+ /* Check for protocol errors */
+ if (eflag & HI3110_ERR_PROTOCOL_MASK) {
+ skb = alloc_can_err_skb(net, &cf);
+ if (!skb)
+ break;
+
+ cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR;
+ priv->can.can_stats.bus_error++;
+ priv->net->stats.rx_errors++;
+ if (eflag & HI3110_ERR_BITERR)
+ cf->data[2] |= CAN_ERR_PROT_BIT;
+ else if (eflag & HI3110_ERR_FRMERR)
+ cf->data[2] |= CAN_ERR_PROT_FORM;
+ else if (eflag & HI3110_ERR_STUFERR)
+ cf->data[2] |= CAN_ERR_PROT_STUFF;
+ else if (eflag & HI3110_ERR_CRCERR)
+ cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ;
+ else if (eflag & HI3110_ERR_ACKERR)
+ cf->data[3] |= CAN_ERR_PROT_LOC_ACK;
+
+ cf->data[6] = hi3110_read(spi, HI3110_READ_TEC);
+ cf->data[7] = hi3110_read(spi, HI3110_READ_REC);
+ netdev_dbg(priv->net, "Bus Error\n");
+ netif_rx_ni(skb);
+ }
+ }
+
+ if (intf == 0)
+ break;
+
+ if (intf & HI3110_INT_TXCPLT) {
+ net->stats.tx_packets++;
+ net->stats.tx_bytes += priv->tx_len - 1;
+ can_led_event(net, CAN_LED_EVENT_TX);
+ if (priv->tx_len) {
+ can_get_echo_skb(net, 0);
+ priv->tx_len = 0;
+ }
+ netif_wake_queue(net);
+ }
+ }
+ mutex_unlock(&priv->hi3110_lock);
+ return IRQ_HANDLED;
+}
+
+static int hi3110_open(struct net_device *net)
+{
+ struct hi3110_priv *priv = netdev_priv(net);
+ struct spi_device *spi = priv->spi;
+ unsigned long flags = IRQF_ONESHOT | IRQF_TRIGGER_RISING;
+ int ret;
+
+ ret = open_candev(net);
+ if (ret)
+ return ret;
+
+ mutex_lock(&priv->hi3110_lock);
+ hi3110_power_enable(priv->transceiver, 1);
+
+ priv->force_quit = 0;
+ priv->tx_skb = NULL;
+ priv->tx_len = 0;
+
+ ret = request_threaded_irq(spi->irq, NULL, hi3110_can_ist,
+ flags, DEVICE_NAME, priv);
+ if (ret) {
+ dev_err(&spi->dev, "failed to acquire irq %d\n", spi->irq);
+ goto out_close;
+ }
+
+ priv->wq = alloc_workqueue("hi3110_wq", WQ_FREEZABLE | WQ_MEM_RECLAIM,
+ 0);
+ if (!priv->wq) {
+ ret = -ENOMEM;
+ goto out_free_irq;
+ }
+ INIT_WORK(&priv->tx_work, hi3110_tx_work_handler);
+ INIT_WORK(&priv->restart_work, hi3110_restart_work_handler);
+
+ ret = hi3110_hw_reset(spi);
+ if (ret)
+ goto out_free_wq;
+
+ ret = hi3110_setup(net);
+ if (ret)
+ goto out_free_wq;
+
+ ret = hi3110_set_normal_mode(spi);
+ if (ret)
+ goto out_free_wq;
+
+ can_led_event(net, CAN_LED_EVENT_OPEN);
+ netif_wake_queue(net);
+ mutex_unlock(&priv->hi3110_lock);
+
+ return 0;
+
+ out_free_wq:
+ destroy_workqueue(priv->wq);
+ out_free_irq:
+ free_irq(spi->irq, priv);
+ hi3110_hw_sleep(spi);
+ out_close:
+ hi3110_power_enable(priv->transceiver, 0);
+ close_candev(net);
+ mutex_unlock(&priv->hi3110_lock);
+ return ret;
+}
+
+static const struct net_device_ops hi3110_netdev_ops = {
+ .ndo_open = hi3110_open,
+ .ndo_stop = hi3110_stop,
+ .ndo_start_xmit = hi3110_hard_start_xmit,
+};
+
+static const struct of_device_id hi3110_of_match[] = {
+ {
+ .compatible = "holt,hi3110",
+ .data = (void *)CAN_HI3110_HI3110,
+ },
+ { }
+};
+MODULE_DEVICE_TABLE(of, hi3110_of_match);
+
+static const struct spi_device_id hi3110_id_table[] = {
+ {
+ .name = "hi3110",
+ .driver_data = (kernel_ulong_t)CAN_HI3110_HI3110,
+ },
+ { }
+};
+MODULE_DEVICE_TABLE(spi, hi3110_id_table);
+
+static int hi3110_can_probe(struct spi_device *spi)
+{
+ const struct of_device_id *of_id = of_match_device(hi3110_of_match,
+ &spi->dev);
+ struct net_device *net;
+ struct hi3110_priv *priv;
+ struct clk *clk;
+ int freq, ret;
+
+ clk = devm_clk_get(&spi->dev, NULL);
+ if (IS_ERR(clk)) {
+ dev_err(&spi->dev, "no CAN clock source defined\n");
+ return PTR_ERR(clk);
+ }
+ freq = clk_get_rate(clk);
+
+ /* Sanity check */
+ if (freq > 40000000)
+ return -ERANGE;
+
+ /* Allocate can/net device */
+ net = alloc_candev(sizeof(struct hi3110_priv), HI3110_TX_ECHO_SKB_MAX);
+ if (!net)
+ return -ENOMEM;
+
+ if (!IS_ERR(clk)) {
+ ret = clk_prepare_enable(clk);
+ if (ret)
+ goto out_free;
+ }
+
+ net->netdev_ops = &hi3110_netdev_ops;
+ net->flags |= IFF_ECHO;
+
+ priv = netdev_priv(net);
+ priv->can.bittiming_const = &hi3110_bittiming_const;
+ priv->can.do_set_mode = hi3110_do_set_mode;
+ priv->can.do_get_berr_counter = hi3110_get_berr_counter;
+ priv->can.clock.freq = freq / 2;
+ priv->can.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES |
+ CAN_CTRLMODE_LOOPBACK |
+ CAN_CTRLMODE_LISTENONLY |
+ CAN_CTRLMODE_BERR_REPORTING;
+
+ if (of_id)
+ priv->model = (enum hi3110_model)of_id->data;
+ else
+ priv->model = spi_get_device_id(spi)->driver_data;
+ priv->net = net;
+ priv->clk = clk;
+
+ spi_set_drvdata(spi, priv);
+
+ /* Configure the SPI bus */
+ spi->bits_per_word = 8;
+ ret = spi_setup(spi);
+ if (ret)
+ goto out_clk;
+
+ priv->power = devm_regulator_get_optional(&spi->dev, "vdd");
+ priv->transceiver = devm_regulator_get_optional(&spi->dev, "xceiver");
+ if ((PTR_ERR(priv->power) == -EPROBE_DEFER) ||
+ (PTR_ERR(priv->transceiver) == -EPROBE_DEFER)) {
+ ret = -EPROBE_DEFER;
+ goto out_clk;
+ }
+
+ ret = hi3110_power_enable(priv->power, 1);
+ if (ret)
+ goto out_clk;
+
+ priv->spi = spi;
+ mutex_init(&priv->hi3110_lock);
+
+ /* If requested, allocate DMA buffers */
+ if (hi3110_enable_dma) {
+ spi->dev.coherent_dma_mask = ~0;
+
+ /* Minimum coherent DMA allocation is PAGE_SIZE, so allocate
+ * that much and share it between Tx and Rx DMA buffers.
+ */
+ priv->spi_tx_buf = dmam_alloc_coherent(&spi->dev,
+ PAGE_SIZE,
+ &priv->spi_tx_dma,
+ GFP_DMA);
+
+ if (priv->spi_tx_buf) {
+ priv->spi_rx_buf = (priv->spi_tx_buf + (PAGE_SIZE / 2));
+ priv->spi_rx_dma = (dma_addr_t)(priv->spi_tx_dma +
+ (PAGE_SIZE / 2));
+ } else {
+ /* Fall back to non-DMA */
+ hi3110_enable_dma = 0;
+ }
+ }
+
+ /* Allocate non-DMA buffers */
+ if (!hi3110_enable_dma) {
+ priv->spi_tx_buf = devm_kzalloc(&spi->dev, HI3110_RX_BUF_LEN,
+ GFP_KERNEL);
+ if (!priv->spi_tx_buf) {
+ ret = -ENOMEM;
+ goto error_probe;
+ }
+ priv->spi_rx_buf = devm_kzalloc(&spi->dev, HI3110_RX_BUF_LEN,
+ GFP_KERNEL);
+
+ if (!priv->spi_rx_buf) {
+ ret = -ENOMEM;
+ goto error_probe;
+ }
+ }
+
+ SET_NETDEV_DEV(net, &spi->dev);
+
+ ret = hi3110_hw_probe(spi);
+ if (ret) {
+ if (ret == -ENODEV)
+ dev_err(&spi->dev, "Cannot initialize %x. Wrong wiring?\n",
+ priv->model);
+ goto error_probe;
+ }
+ hi3110_hw_sleep(spi);
+
+ ret = register_candev(net);
+ if (ret)
+ goto error_probe;
+
+ devm_can_led_init(net);
+ netdev_info(net, "%x successfully initialized.\n", priv->model);
+
+ return 0;
+
+ error_probe:
+ hi3110_power_enable(priv->power, 0);
+
+ out_clk:
+ if (!IS_ERR(clk))
+ clk_disable_unprepare(clk);
+
+ out_free:
+ free_candev(net);
+
+ dev_err(&spi->dev, "Probe failed, err=%d\n", -ret);
+ return ret;
+}
+
+static int hi3110_can_remove(struct spi_device *spi)
+{
+ struct hi3110_priv *priv = spi_get_drvdata(spi);
+ struct net_device *net = priv->net;
+
+ unregister_candev(net);
+
+ hi3110_power_enable(priv->power, 0);
+
+ if (!IS_ERR(priv->clk))
+ clk_disable_unprepare(priv->clk);
+
+ free_candev(net);
+
+ return 0;
+}
+
+static int __maybe_unused hi3110_can_suspend(struct device *dev)
+{
+ struct spi_device *spi = to_spi_device(dev);
+ struct hi3110_priv *priv = spi_get_drvdata(spi);
+ struct net_device *net = priv->net;
+
+ priv->force_quit = 1;
+ disable_irq(spi->irq);
+
+ /* Note: at this point neither IST nor workqueues are running.
+ * open/stop cannot be called anyway so locking is not needed
+ */
+ if (netif_running(net)) {
+ netif_device_detach(net);
+
+ hi3110_hw_sleep(spi);
+ hi3110_power_enable(priv->transceiver, 0);
+ priv->after_suspend = HI3110_AFTER_SUSPEND_UP;
+ } else {
+ priv->after_suspend = HI3110_AFTER_SUSPEND_DOWN;
+ }
+
+ if (!IS_ERR_OR_NULL(priv->power)) {
+ regulator_disable(priv->power);
+ priv->after_suspend |= HI3110_AFTER_SUSPEND_POWER;
+ }
+
+ return 0;
+}
+
+static int __maybe_unused hi3110_can_resume(struct device *dev)
+{
+ struct spi_device *spi = to_spi_device(dev);
+ struct hi3110_priv *priv = spi_get_drvdata(spi);
+
+ if (priv->after_suspend & HI3110_AFTER_SUSPEND_POWER)
+ hi3110_power_enable(priv->power, 1);
+
+ if (priv->after_suspend & HI3110_AFTER_SUSPEND_UP) {
+ hi3110_power_enable(priv->transceiver, 1);
+ queue_work(priv->wq, &priv->restart_work);
+ } else {
+ priv->after_suspend = 0;
+ }
+
+ priv->force_quit = 0;
+ enable_irq(spi->irq);
+ return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(hi3110_can_pm_ops, hi3110_can_suspend, hi3110_can_resume);
+
+static struct spi_driver hi3110_can_driver = {
+ .driver = {
+ .name = DEVICE_NAME,
+ .of_match_table = hi3110_of_match,
+ .pm = &hi3110_can_pm_ops,
+ },
+ .id_table = hi3110_id_table,
+ .probe = hi3110_can_probe,
+ .remove = hi3110_can_remove,
+};
+
+module_spi_driver(hi3110_can_driver);
+
+MODULE_AUTHOR("Akshay Bhat <akshay.bhat@timesys.com>");
+MODULE_AUTHOR("Casey Fitzpatrick <casey.fitzpatrick@timesys.com>");
+MODULE_DESCRIPTION("Holt HI-3110 CAN driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index 6749b18..b8aac53 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -17,25 +17,6 @@
*
*/
-/*
- * Your platform definitions should specify module ram offsets and interrupt
- * number to use as follows:
- *
- * static struct ti_hecc_platform_data am3517_evm_hecc_pdata = {
- * .scc_hecc_offset = 0,
- * .scc_ram_offset = 0x3000,
- * .hecc_ram_offset = 0x3000,
- * .mbx_offset = 0x2000,
- * .int_line = 0,
- * .revision = 1,
- * .transceiver_switch = hecc_phy_control,
- * };
- *
- * Please see include/linux/can/platform/ti_hecc.h for description of
- * above fields.
- *
- */
-
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/types.h>
@@ -46,11 +27,13 @@
#include <linux/platform_device.h>
#include <linux/clk.h>
#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/regulator/consumer.h>
#include <linux/can/dev.h>
#include <linux/can/error.h>
#include <linux/can/led.h>
-#include <linux/can/platform/ti_hecc.h>
#define DRV_NAME "ti_hecc"
#define HECC_MODULE_VERSION "0.7"
@@ -214,15 +197,14 @@ struct ti_hecc_priv {
struct net_device *ndev;
struct clk *clk;
void __iomem *base;
- u32 scc_ram_offset;
- u32 hecc_ram_offset;
- u32 mbx_offset;
- u32 int_line;
+ void __iomem *hecc_ram;
+ void __iomem *mbx;
+ bool use_hecc1int;
spinlock_t mbx_lock; /* CANME register needs protection */
u32 tx_head;
u32 tx_tail;
u32 rx_next;
- void (*transceiver_switch)(int);
+ struct regulator *reg_xceiver;
};
static inline int get_tx_head_mb(struct ti_hecc_priv *priv)
@@ -242,20 +224,18 @@ static inline int get_tx_head_prio(struct ti_hecc_priv *priv)
static inline void hecc_write_lam(struct ti_hecc_priv *priv, u32 mbxno, u32 val)
{
- __raw_writel(val, priv->base + priv->hecc_ram_offset + mbxno * 4);
+ __raw_writel(val, priv->hecc_ram + mbxno * 4);
}
static inline void hecc_write_mbx(struct ti_hecc_priv *priv, u32 mbxno,
u32 reg, u32 val)
{
- __raw_writel(val, priv->base + priv->mbx_offset + mbxno * 0x10 +
- reg);
+ __raw_writel(val, priv->mbx + mbxno * 0x10 + reg);
}
static inline u32 hecc_read_mbx(struct ti_hecc_priv *priv, u32 mbxno, u32 reg)
{
- return __raw_readl(priv->base + priv->mbx_offset + mbxno * 0x10 +
- reg);
+ return __raw_readl(priv->mbx + mbxno * 0x10 + reg);
}
static inline void hecc_write(struct ti_hecc_priv *priv, u32 reg, u32 val)
@@ -311,11 +291,16 @@ static int ti_hecc_set_btc(struct ti_hecc_priv *priv)
return 0;
}
-static void ti_hecc_transceiver_switch(const struct ti_hecc_priv *priv,
- int on)
+static int ti_hecc_transceiver_switch(const struct ti_hecc_priv *priv,
+ int on)
{
- if (priv->transceiver_switch)
- priv->transceiver_switch(on);
+ if (!priv->reg_xceiver)
+ return 0;
+
+ if (on)
+ return regulator_enable(priv->reg_xceiver);
+ else
+ return regulator_disable(priv->reg_xceiver);
}
static void ti_hecc_reset(struct net_device *ndev)
@@ -409,7 +394,7 @@ static void ti_hecc_start(struct net_device *ndev)
/* Prevent message over-write & Enable interrupts */
hecc_write(priv, HECC_CANOPC, HECC_SET_REG);
- if (priv->int_line) {
+ if (priv->use_hecc1int) {
hecc_write(priv, HECC_CANMIL, HECC_SET_REG);
hecc_write(priv, HECC_CANGIM, HECC_CANGIM_DEF_MASK |
HECC_CANGIM_I1EN | HECC_CANGIM_SIL);
@@ -760,7 +745,7 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id)
unsigned long ack, flags;
int_status = hecc_read(priv,
- (priv->int_line) ? HECC_CANGIF1 : HECC_CANGIF0);
+ (priv->use_hecc1int) ? HECC_CANGIF1 : HECC_CANGIF0);
if (!int_status)
return IRQ_NONE;
@@ -806,7 +791,7 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id)
}
/* clear all interrupt conditions - read back to avoid spurious ints */
- if (priv->int_line) {
+ if (priv->use_hecc1int) {
hecc_write(priv, HECC_CANGIF1, HECC_SET_REG);
int_status = hecc_read(priv, HECC_CANGIF1);
} else {
@@ -872,58 +857,87 @@ static const struct net_device_ops ti_hecc_netdev_ops = {
.ndo_change_mtu = can_change_mtu,
};
+static const struct of_device_id ti_hecc_dt_ids[] = {
+ {
+ .compatible = "ti,am3517-hecc",
+ },
+ { }
+};
+MODULE_DEVICE_TABLE(of, ti_hecc_dt_ids);
+
static int ti_hecc_probe(struct platform_device *pdev)
{
struct net_device *ndev = (struct net_device *)0;
struct ti_hecc_priv *priv;
- struct ti_hecc_platform_data *pdata;
- struct resource *mem, *irq;
- void __iomem *addr;
+ struct device_node *np = pdev->dev.of_node;
+ struct resource *res, *irq;
+ struct regulator *reg_xceiver;
int err = -ENODEV;
- pdata = dev_get_platdata(&pdev->dev);
- if (!pdata) {
- dev_err(&pdev->dev, "No platform data\n");
- goto probe_exit;
+ if (!IS_ENABLED(CONFIG_OF) || !np)
+ return -EINVAL;
+
+ reg_xceiver = devm_regulator_get(&pdev->dev, "xceiver");
+ if (PTR_ERR(reg_xceiver) == -EPROBE_DEFER)
+ return -EPROBE_DEFER;
+ else if (IS_ERR(reg_xceiver))
+ reg_xceiver = NULL;
+
+ ndev = alloc_candev(sizeof(struct ti_hecc_priv), HECC_MAX_TX_MBOX);
+ if (!ndev) {
+ dev_err(&pdev->dev, "alloc_candev failed\n");
+ return -ENOMEM;
+ }
+ priv = netdev_priv(ndev);
+
+ /* handle hecc memory */
+ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "hecc");
+ if (!res) {
+ dev_err(&pdev->dev, "can't get IORESOURCE_MEM hecc\n");
+ return -EINVAL;
}
- mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!mem) {
- dev_err(&pdev->dev, "No mem resources\n");
- goto probe_exit;
+ priv->base = devm_ioremap_resource(&pdev->dev, res);
+ if (!priv->base) {
+ dev_err(&pdev->dev, "hecc ioremap failed\n");
+ return -ENOMEM;
}
+
+ /* handle hecc-ram memory */
+ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "hecc-ram");
+ if (!res) {
+ dev_err(&pdev->dev, "can't get IORESOURCE_MEM hecc-ram\n");
+ return -EINVAL;
+ }
+
+ priv->hecc_ram = devm_ioremap_resource(&pdev->dev, res);
+ if (!priv->hecc_ram) {
+ dev_err(&pdev->dev, "hecc-ram ioremap failed\n");
+ return -ENOMEM;
+ }
+
+ /* handle mbx memory */
+ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "mbx");
+ if (!res) {
+ dev_err(&pdev->dev, "can't get IORESOURCE_MEM mbx\n");
+ return -EINVAL;
+ }
+
+ priv->mbx = devm_ioremap_resource(&pdev->dev, res);
+ if (!priv->mbx) {
+ dev_err(&pdev->dev, "mbx ioremap failed\n");
+ return -ENOMEM;
+ }
+
irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
if (!irq) {
dev_err(&pdev->dev, "No irq resource\n");
goto probe_exit;
}
- if (!request_mem_region(mem->start, resource_size(mem), pdev->name)) {
- dev_err(&pdev->dev, "HECC region already claimed\n");
- err = -EBUSY;
- goto probe_exit;
- }
- addr = ioremap(mem->start, resource_size(mem));
- if (!addr) {
- dev_err(&pdev->dev, "ioremap failed\n");
- err = -ENOMEM;
- goto probe_exit_free_region;
- }
- ndev = alloc_candev(sizeof(struct ti_hecc_priv), HECC_MAX_TX_MBOX);
- if (!ndev) {
- dev_err(&pdev->dev, "alloc_candev failed\n");
- err = -ENOMEM;
- goto probe_exit_iounmap;
- }
-
- priv = netdev_priv(ndev);
priv->ndev = ndev;
- priv->base = addr;
- priv->scc_ram_offset = pdata->scc_ram_offset;
- priv->hecc_ram_offset = pdata->hecc_ram_offset;
- priv->mbx_offset = pdata->mbx_offset;
- priv->int_line = pdata->int_line;
- priv->transceiver_switch = pdata->transceiver_switch;
+ priv->reg_xceiver = reg_xceiver;
+ priv->use_hecc1int = of_property_read_bool(np, "ti,use-hecc1int");
priv->can.bittiming_const = &ti_hecc_bittiming_const;
priv->can.do_set_mode = ti_hecc_do_set_mode;
@@ -971,32 +985,23 @@ static int ti_hecc_probe(struct platform_device *pdev)
clk_put(priv->clk);
probe_exit_candev:
free_candev(ndev);
-probe_exit_iounmap:
- iounmap(addr);
-probe_exit_free_region:
- release_mem_region(mem->start, resource_size(mem));
probe_exit:
return err;
}
static int ti_hecc_remove(struct platform_device *pdev)
{
- struct resource *res;
struct net_device *ndev = platform_get_drvdata(pdev);
struct ti_hecc_priv *priv = netdev_priv(ndev);
unregister_candev(ndev);
clk_disable_unprepare(priv->clk);
clk_put(priv->clk);
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- iounmap(priv->base);
- release_mem_region(res->start, resource_size(res));
free_candev(ndev);
return 0;
}
-
#ifdef CONFIG_PM
static int ti_hecc_suspend(struct platform_device *pdev, pm_message_t state)
{
@@ -1045,6 +1050,7 @@ static int ti_hecc_resume(struct platform_device *pdev)
static struct platform_driver ti_hecc_driver = {
.driver = {
.name = DRV_NAME,
+ .of_match_table = ti_hecc_dt_ids,
},
.probe = ti_hecc_probe,
.remove = ti_hecc_remove,
diff --git a/drivers/net/cris/eth_v10.c b/drivers/net/cris/eth_v10.c
index 91c876a..da02041 100644
--- a/drivers/net/cris/eth_v10.c
+++ b/drivers/net/cris/eth_v10.c
@@ -1412,31 +1412,39 @@ e100_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
return rc;
}
-static int e100_get_settings(struct net_device *dev,
- struct ethtool_cmd *cmd)
+static int e100_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
struct net_local *np = netdev_priv(dev);
+ u32 supported;
int err;
spin_lock_irq(&np->lock);
- err = mii_ethtool_gset(&np->mii_if, cmd);
+ err = mii_ethtool_get_link_ksettings(&np->mii_if, cmd);
spin_unlock_irq(&np->lock);
/* The PHY may support 1000baseT, but the Etrax100 does not. */
- cmd->supported &= ~(SUPPORTED_1000baseT_Half
- | SUPPORTED_1000baseT_Full);
+ ethtool_convert_link_mode_to_legacy_u32(&supported,
+ cmd->link_modes.supported);
+
+ supported &= ~(SUPPORTED_1000baseT_Half | SUPPORTED_1000baseT_Full);
+
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ supported);
+
return err;
}
-static int e100_set_settings(struct net_device *dev,
- struct ethtool_cmd *ecmd)
+static int e100_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *ecmd)
{
- if (ecmd->autoneg == AUTONEG_ENABLE) {
+ if (ecmd->base.autoneg == AUTONEG_ENABLE) {
e100_set_duplex(dev, autoneg);
e100_set_speed(dev, 0);
} else {
- e100_set_duplex(dev, ecmd->duplex == DUPLEX_HALF ? half : full);
- e100_set_speed(dev, ecmd->speed == SPEED_10 ? 10: 100);
+ e100_set_duplex(dev, ecmd->base.duplex == DUPLEX_HALF ?
+ half : full);
+ e100_set_speed(dev, ecmd->base.speed == SPEED_10 ? 10 : 100);
}
return 0;
@@ -1459,11 +1467,11 @@ static int e100_nway_reset(struct net_device *dev)
}
static const struct ethtool_ops e100_ethtool_ops = {
- .get_settings = e100_get_settings,
- .set_settings = e100_set_settings,
.get_drvinfo = e100_get_drvinfo,
.nway_reset = e100_nway_reset,
.get_link = ethtool_op_get_link,
+ .get_link_ksettings = e100_get_link_ksettings,
+ .set_link_ksettings = e100_set_link_ksettings,
};
static int
diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig
index 0659846..31a2b22 100644
--- a/drivers/net/dsa/Kconfig
+++ b/drivers/net/dsa/Kconfig
@@ -11,7 +11,7 @@
config NET_DSA_BCM_SF2
tristate "Broadcom Starfighter 2 Ethernet switch support"
- depends on HAS_IOMEM && NET_DSA
+ depends on HAS_IOMEM && NET_DSA && OF_MDIO
select NET_DSA_TAG_BRCM
select FIXED_PHY
select BCM7XXX_PHY
@@ -34,4 +34,20 @@
This enables support for the Qualcomm Atheros QCA8K Ethernet
switch chips.
+config NET_DSA_LOOP
+ tristate "DSA mock-up Ethernet switch chip support"
+ depends on NET_DSA
+ select FIXED_PHY
+ ---help---
+ This enables support for a fake mock-up switch chip which
+ exercises the DSA APIs.
+
+config NET_DSA_MT7530
+ tristate "Mediatek MT7530 Ethernet switch support"
+ depends on NET_DSA
+ select NET_DSA_TAG_MTK
+ ---help---
+ This enables support for the Mediatek MT7530 Ethernet switch
+ chip.
+
endmenu
diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile
index a3c9416..2ae07f4 100644
--- a/drivers/net/dsa/Makefile
+++ b/drivers/net/dsa/Makefile
@@ -2,6 +2,7 @@
obj-$(CONFIG_NET_DSA_BCM_SF2) += bcm-sf2.o
bcm-sf2-objs := bcm_sf2.o bcm_sf2_cfp.o
obj-$(CONFIG_NET_DSA_QCA8K) += qca8k.o
-
+obj-$(CONFIG_NET_DSA_MT7530) += mt7530.o
obj-y += b53/
obj-y += mv88e6xxx/
+obj-$(CONFIG_NET_DSA_LOOP) += dsa_loop.o dsa_loop_bdinfo.o
diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index 346dd9a..2fb32d6 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -10,10 +10,11 @@
*/
#include <linux/list.h>
-#include <net/dsa.h>
#include <linux/ethtool.h>
#include <linux/if_ether.h>
#include <linux/in.h>
+#include <linux/netdevice.h>
+#include <net/dsa.h>
#include <linux/bitmap.h>
#include "bcm_sf2.h"
diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c
new file mode 100644
index 0000000..f0fc4de
--- /dev/null
+++ b/drivers/net/dsa/dsa_loop.c
@@ -0,0 +1,328 @@
+/*
+ * Distributed Switch Architecture loopback driver
+ *
+ * Copyright (C) 2016, Florian Fainelli <f.fainelli@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/platform_device.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+#include <linux/phy_fixed.h>
+#include <linux/export.h>
+#include <linux/workqueue.h>
+#include <linux/module.h>
+#include <linux/if_bridge.h>
+#include <net/switchdev.h>
+#include <net/dsa.h>
+
+#include "dsa_loop.h"
+
+struct dsa_loop_vlan {
+ u16 members;
+ u16 untagged;
+};
+
+#define DSA_LOOP_VLANS 5
+
+struct dsa_loop_priv {
+ struct mii_bus *bus;
+ unsigned int port_base;
+ struct dsa_loop_vlan vlans[DSA_LOOP_VLANS];
+ struct net_device *netdev;
+ u16 pvid;
+};
+
+static struct phy_device *phydevs[PHY_MAX_ADDR];
+
+static enum dsa_tag_protocol dsa_loop_get_protocol(struct dsa_switch *ds)
+{
+ dev_dbg(ds->dev, "%s\n", __func__);
+
+ return DSA_TAG_PROTO_NONE;
+}
+
+static int dsa_loop_setup(struct dsa_switch *ds)
+{
+ dev_dbg(ds->dev, "%s\n", __func__);
+
+ return 0;
+}
+
+static int dsa_loop_set_addr(struct dsa_switch *ds, u8 *addr)
+{
+ dev_dbg(ds->dev, "%s\n", __func__);
+
+ return 0;
+}
+
+static int dsa_loop_phy_read(struct dsa_switch *ds, int port, int regnum)
+{
+ struct dsa_loop_priv *ps = ds->priv;
+ struct mii_bus *bus = ps->bus;
+
+ dev_dbg(ds->dev, "%s\n", __func__);
+
+ return mdiobus_read_nested(bus, ps->port_base + port, regnum);
+}
+
+static int dsa_loop_phy_write(struct dsa_switch *ds, int port,
+ int regnum, u16 value)
+{
+ struct dsa_loop_priv *ps = ds->priv;
+ struct mii_bus *bus = ps->bus;
+
+ dev_dbg(ds->dev, "%s\n", __func__);
+
+ return mdiobus_write_nested(bus, ps->port_base + port, regnum, value);
+}
+
+static int dsa_loop_port_bridge_join(struct dsa_switch *ds, int port,
+ struct net_device *bridge)
+{
+ dev_dbg(ds->dev, "%s\n", __func__);
+
+ return 0;
+}
+
+static void dsa_loop_port_bridge_leave(struct dsa_switch *ds, int port,
+ struct net_device *bridge)
+{
+ dev_dbg(ds->dev, "%s\n", __func__);
+}
+
+static void dsa_loop_port_stp_state_set(struct dsa_switch *ds, int port,
+ u8 state)
+{
+ dev_dbg(ds->dev, "%s\n", __func__);
+}
+
+static int dsa_loop_port_vlan_filtering(struct dsa_switch *ds, int port,
+ bool vlan_filtering)
+{
+ dev_dbg(ds->dev, "%s\n", __func__);
+
+ return 0;
+}
+
+static int dsa_loop_port_vlan_prepare(struct dsa_switch *ds, int port,
+ const struct switchdev_obj_port_vlan *vlan,
+ struct switchdev_trans *trans)
+{
+ struct dsa_loop_priv *ps = ds->priv;
+ struct mii_bus *bus = ps->bus;
+
+ dev_dbg(ds->dev, "%s\n", __func__);
+
+ /* Just do a sleeping operation to make lockdep checks effective */
+ mdiobus_read(bus, ps->port_base + port, MII_BMSR);
+
+ if (vlan->vid_end > DSA_LOOP_VLANS)
+ return -ERANGE;
+
+ return 0;
+}
+
+static void dsa_loop_port_vlan_add(struct dsa_switch *ds, int port,
+ const struct switchdev_obj_port_vlan *vlan,
+ struct switchdev_trans *trans)
+{
+ bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+ bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
+ struct dsa_loop_priv *ps = ds->priv;
+ struct mii_bus *bus = ps->bus;
+ struct dsa_loop_vlan *vl;
+ u16 vid;
+
+ dev_dbg(ds->dev, "%s\n", __func__);
+
+ /* Just do a sleeping operation to make lockdep checks effective */
+ mdiobus_read(bus, ps->port_base + port, MII_BMSR);
+
+ for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+ vl = &ps->vlans[vid];
+
+ vl->members |= BIT(port);
+ if (untagged)
+ vl->untagged |= BIT(port);
+ else
+ vl->untagged &= ~BIT(port);
+ }
+
+ if (pvid)
+ ps->pvid = vid;
+}
+
+static int dsa_loop_port_vlan_del(struct dsa_switch *ds, int port,
+ const struct switchdev_obj_port_vlan *vlan)
+{
+ bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+ struct dsa_loop_priv *ps = ds->priv;
+ struct mii_bus *bus = ps->bus;
+ struct dsa_loop_vlan *vl;
+ u16 vid, pvid = ps->pvid;
+
+ dev_dbg(ds->dev, "%s\n", __func__);
+
+ /* Just do a sleeping operation to make lockdep checks effective */
+ mdiobus_read(bus, ps->port_base + port, MII_BMSR);
+
+ for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+ vl = &ps->vlans[vid];
+
+ vl->members &= ~BIT(port);
+ if (untagged)
+ vl->untagged &= ~BIT(port);
+
+ if (pvid == vid)
+ pvid = 1;
+ }
+ ps->pvid = pvid;
+
+ return 0;
+}
+
+static int dsa_loop_port_vlan_dump(struct dsa_switch *ds, int port,
+ struct switchdev_obj_port_vlan *vlan,
+ int (*cb)(struct switchdev_obj *obj))
+{
+ struct dsa_loop_priv *ps = ds->priv;
+ struct mii_bus *bus = ps->bus;
+ struct dsa_loop_vlan *vl;
+ u16 vid, vid_start = 0;
+ int err = 0;
+
+ dev_dbg(ds->dev, "%s\n", __func__);
+
+ /* Just do a sleeping operation to make lockdep checks effective */
+ mdiobus_read(bus, ps->port_base + port, MII_BMSR);
+
+ for (vid = vid_start; vid < DSA_LOOP_VLANS; vid++) {
+ vl = &ps->vlans[vid];
+
+ if (!(vl->members & BIT(port)))
+ continue;
+
+ vlan->vid_begin = vlan->vid_end = vid;
+ vlan->flags = 0;
+
+ if (vl->untagged & BIT(port))
+ vlan->flags |= BRIDGE_VLAN_INFO_UNTAGGED;
+ if (ps->pvid == vid)
+ vlan->flags |= BRIDGE_VLAN_INFO_PVID;
+
+ err = cb(&vlan->obj);
+ if (err)
+ break;
+ }
+
+ return err;
+}
+
+static struct dsa_switch_ops dsa_loop_driver = {
+ .get_tag_protocol = dsa_loop_get_protocol,
+ .setup = dsa_loop_setup,
+ .set_addr = dsa_loop_set_addr,
+ .phy_read = dsa_loop_phy_read,
+ .phy_write = dsa_loop_phy_write,
+ .port_bridge_join = dsa_loop_port_bridge_join,
+ .port_bridge_leave = dsa_loop_port_bridge_leave,
+ .port_stp_state_set = dsa_loop_port_stp_state_set,
+ .port_vlan_filtering = dsa_loop_port_vlan_filtering,
+ .port_vlan_prepare = dsa_loop_port_vlan_prepare,
+ .port_vlan_add = dsa_loop_port_vlan_add,
+ .port_vlan_del = dsa_loop_port_vlan_del,
+ .port_vlan_dump = dsa_loop_port_vlan_dump,
+};
+
+static int dsa_loop_drv_probe(struct mdio_device *mdiodev)
+{
+ struct dsa_loop_pdata *pdata = mdiodev->dev.platform_data;
+ struct dsa_loop_priv *ps;
+ struct dsa_switch *ds;
+
+ if (!pdata)
+ return -ENODEV;
+
+ dev_info(&mdiodev->dev, "%s: 0x%0x\n",
+ pdata->name, pdata->enabled_ports);
+
+ ds = dsa_switch_alloc(&mdiodev->dev, DSA_MAX_PORTS);
+ if (!ds)
+ return -ENOMEM;
+
+ ps = devm_kzalloc(&mdiodev->dev, sizeof(*ps), GFP_KERNEL);
+ ps->netdev = dev_get_by_name(&init_net, pdata->netdev);
+ if (!ps->netdev)
+ return -EPROBE_DEFER;
+
+ pdata->cd.netdev[DSA_LOOP_CPU_PORT] = &ps->netdev->dev;
+
+ ds->dev = &mdiodev->dev;
+ ds->ops = &dsa_loop_driver;
+ ds->priv = ps;
+ ps->bus = mdiodev->bus;
+
+ dev_set_drvdata(&mdiodev->dev, ds);
+
+ return dsa_register_switch(ds, ds->dev);
+}
+
+static void dsa_loop_drv_remove(struct mdio_device *mdiodev)
+{
+ struct dsa_switch *ds = dev_get_drvdata(&mdiodev->dev);
+ struct dsa_loop_priv *ps = ds->priv;
+
+ dsa_unregister_switch(ds);
+ dev_put(ps->netdev);
+}
+
+static struct mdio_driver dsa_loop_drv = {
+ .mdiodrv.driver = {
+ .name = "dsa-loop",
+ },
+ .probe = dsa_loop_drv_probe,
+ .remove = dsa_loop_drv_remove,
+};
+
+#define NUM_FIXED_PHYS (DSA_LOOP_NUM_PORTS - 2)
+
+static void unregister_fixed_phys(void)
+{
+ unsigned int i;
+
+ for (i = 0; i < NUM_FIXED_PHYS; i++)
+ if (phydevs[i])
+ fixed_phy_unregister(phydevs[i]);
+}
+
+static int __init dsa_loop_init(void)
+{
+ struct fixed_phy_status status = {
+ .link = 1,
+ .speed = SPEED_100,
+ .duplex = DUPLEX_FULL,
+ };
+ unsigned int i;
+
+ for (i = 0; i < NUM_FIXED_PHYS; i++)
+ phydevs[i] = fixed_phy_register(PHY_POLL, &status, -1, NULL);
+
+ return mdio_driver_register(&dsa_loop_drv);
+}
+module_init(dsa_loop_init);
+
+static void __exit dsa_loop_exit(void)
+{
+ mdio_driver_unregister(&dsa_loop_drv);
+ unregister_fixed_phys();
+}
+module_exit(dsa_loop_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Florian Fainelli");
+MODULE_DESCRIPTION("DSA loopback driver");
diff --git a/drivers/net/dsa/dsa_loop.h b/drivers/net/dsa/dsa_loop.h
new file mode 100644
index 0000000..dc39687
--- /dev/null
+++ b/drivers/net/dsa/dsa_loop.h
@@ -0,0 +1,19 @@
+#ifndef __DSA_LOOP_H
+#define __DSA_LOOP_H
+
+struct dsa_chip_data;
+
+struct dsa_loop_pdata {
+ /* Must be first, such that dsa_register_switch() can access this
+ * without gory pointer manipulations
+ */
+ struct dsa_chip_data cd;
+ const char *name;
+ unsigned int enabled_ports;
+ const char *netdev;
+};
+
+#define DSA_LOOP_NUM_PORTS 6
+#define DSA_LOOP_CPU_PORT (DSA_LOOP_NUM_PORTS - 1)
+
+#endif /* __DSA_LOOP_H */
diff --git a/drivers/net/dsa/dsa_loop_bdinfo.c b/drivers/net/dsa/dsa_loop_bdinfo.c
new file mode 100644
index 0000000..fb8d5dc
--- /dev/null
+++ b/drivers/net/dsa/dsa_loop_bdinfo.c
@@ -0,0 +1,34 @@
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/phy.h>
+#include <net/dsa.h>
+
+#include "dsa_loop.h"
+
+static struct dsa_loop_pdata dsa_loop_pdata = {
+ .cd = {
+ .port_names[0] = "lan1",
+ .port_names[1] = "lan2",
+ .port_names[2] = "lan3",
+ .port_names[3] = "lan4",
+ .port_names[DSA_LOOP_CPU_PORT] = "cpu",
+ },
+ .name = "DSA mockup driver",
+ .enabled_ports = 0x1f,
+ .netdev = "eth0",
+};
+
+static const struct mdio_board_info bdinfo = {
+ .bus_id = "fixed-0",
+ .modalias = "dsa-loop",
+ .mdio_addr = 31,
+ .platform_data = &dsa_loop_pdata,
+};
+
+static int __init dsa_loop_bdinfo_init(void)
+{
+ return mdiobus_register_board_info(&bdinfo, 1);
+}
+arch_initcall(dsa_loop_bdinfo_init)
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
new file mode 100644
index 0000000..a4f3b0b
--- /dev/null
+++ b/drivers/net/dsa/mt7530.c
@@ -0,0 +1,1125 @@
+/*
+ * Mediatek MT7530 DSA Switch driver
+ * Copyright (C) 2017 Sean Wang <sean.wang@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+#include <linux/etherdevice.h>
+#include <linux/if_bridge.h>
+#include <linux/iopoll.h>
+#include <linux/mdio.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/of_gpio.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
+#include <linux/of_platform.h>
+#include <linux/phy.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+#include <linux/reset.h>
+#include <net/dsa.h>
+#include <net/switchdev.h>
+
+#include "mt7530.h"
+
+/* String, offset, and register size in bytes if different from 4 bytes */
+static const struct mt7530_mib_desc mt7530_mib[] = {
+ MIB_DESC(1, 0x00, "TxDrop"),
+ MIB_DESC(1, 0x04, "TxCrcErr"),
+ MIB_DESC(1, 0x08, "TxUnicast"),
+ MIB_DESC(1, 0x0c, "TxMulticast"),
+ MIB_DESC(1, 0x10, "TxBroadcast"),
+ MIB_DESC(1, 0x14, "TxCollision"),
+ MIB_DESC(1, 0x18, "TxSingleCollision"),
+ MIB_DESC(1, 0x1c, "TxMultipleCollision"),
+ MIB_DESC(1, 0x20, "TxDeferred"),
+ MIB_DESC(1, 0x24, "TxLateCollision"),
+ MIB_DESC(1, 0x28, "TxExcessiveCollistion"),
+ MIB_DESC(1, 0x2c, "TxPause"),
+ MIB_DESC(1, 0x30, "TxPktSz64"),
+ MIB_DESC(1, 0x34, "TxPktSz65To127"),
+ MIB_DESC(1, 0x38, "TxPktSz128To255"),
+ MIB_DESC(1, 0x3c, "TxPktSz256To511"),
+ MIB_DESC(1, 0x40, "TxPktSz512To1023"),
+ MIB_DESC(1, 0x44, "Tx1024ToMax"),
+ MIB_DESC(2, 0x48, "TxBytes"),
+ MIB_DESC(1, 0x60, "RxDrop"),
+ MIB_DESC(1, 0x64, "RxFiltering"),
+ MIB_DESC(1, 0x6c, "RxMulticast"),
+ MIB_DESC(1, 0x70, "RxBroadcast"),
+ MIB_DESC(1, 0x74, "RxAlignErr"),
+ MIB_DESC(1, 0x78, "RxCrcErr"),
+ MIB_DESC(1, 0x7c, "RxUnderSizeErr"),
+ MIB_DESC(1, 0x80, "RxFragErr"),
+ MIB_DESC(1, 0x84, "RxOverSzErr"),
+ MIB_DESC(1, 0x88, "RxJabberErr"),
+ MIB_DESC(1, 0x8c, "RxPause"),
+ MIB_DESC(1, 0x90, "RxPktSz64"),
+ MIB_DESC(1, 0x94, "RxPktSz65To127"),
+ MIB_DESC(1, 0x98, "RxPktSz128To255"),
+ MIB_DESC(1, 0x9c, "RxPktSz256To511"),
+ MIB_DESC(1, 0xa0, "RxPktSz512To1023"),
+ MIB_DESC(1, 0xa4, "RxPktSz1024ToMax"),
+ MIB_DESC(2, 0xa8, "RxBytes"),
+ MIB_DESC(1, 0xb0, "RxCtrlDrop"),
+ MIB_DESC(1, 0xb4, "RxIngressDrop"),
+ MIB_DESC(1, 0xb8, "RxArlDrop"),
+};
+
+static int
+mt7623_trgmii_write(struct mt7530_priv *priv, u32 reg, u32 val)
+{
+ int ret;
+
+ ret = regmap_write(priv->ethernet, TRGMII_BASE(reg), val);
+ if (ret < 0)
+ dev_err(priv->dev,
+ "failed to priv write register\n");
+ return ret;
+}
+
+static u32
+mt7623_trgmii_read(struct mt7530_priv *priv, u32 reg)
+{
+ int ret;
+ u32 val;
+
+ ret = regmap_read(priv->ethernet, TRGMII_BASE(reg), &val);
+ if (ret < 0) {
+ dev_err(priv->dev,
+ "failed to priv read register\n");
+ return ret;
+ }
+
+ return val;
+}
+
+static void
+mt7623_trgmii_rmw(struct mt7530_priv *priv, u32 reg,
+ u32 mask, u32 set)
+{
+ u32 val;
+
+ val = mt7623_trgmii_read(priv, reg);
+ val &= ~mask;
+ val |= set;
+ mt7623_trgmii_write(priv, reg, val);
+}
+
+static void
+mt7623_trgmii_set(struct mt7530_priv *priv, u32 reg, u32 val)
+{
+ mt7623_trgmii_rmw(priv, reg, 0, val);
+}
+
+static void
+mt7623_trgmii_clear(struct mt7530_priv *priv, u32 reg, u32 val)
+{
+ mt7623_trgmii_rmw(priv, reg, val, 0);
+}
+
+static int
+core_read_mmd_indirect(struct mt7530_priv *priv, int prtad, int devad)
+{
+ struct mii_bus *bus = priv->bus;
+ int value, ret;
+
+ /* Write the desired MMD Devad */
+ ret = bus->write(bus, 0, MII_MMD_CTRL, devad);
+ if (ret < 0)
+ goto err;
+
+ /* Write the desired MMD register address */
+ ret = bus->write(bus, 0, MII_MMD_DATA, prtad);
+ if (ret < 0)
+ goto err;
+
+ /* Select the Function : DATA with no post increment */
+ ret = bus->write(bus, 0, MII_MMD_CTRL, (devad | MII_MMD_CTRL_NOINCR));
+ if (ret < 0)
+ goto err;
+
+ /* Read the content of the MMD's selected register */
+ value = bus->read(bus, 0, MII_MMD_DATA);
+
+ return value;
+err:
+ dev_err(&bus->dev, "failed to read mmd register\n");
+
+ return ret;
+}
+
+static int
+core_write_mmd_indirect(struct mt7530_priv *priv, int prtad,
+ int devad, u32 data)
+{
+ struct mii_bus *bus = priv->bus;
+ int ret;
+
+ /* Write the desired MMD Devad */
+ ret = bus->write(bus, 0, MII_MMD_CTRL, devad);
+ if (ret < 0)
+ goto err;
+
+ /* Write the desired MMD register address */
+ ret = bus->write(bus, 0, MII_MMD_DATA, prtad);
+ if (ret < 0)
+ goto err;
+
+ /* Select the Function : DATA with no post increment */
+ ret = bus->write(bus, 0, MII_MMD_CTRL, (devad | MII_MMD_CTRL_NOINCR));
+ if (ret < 0)
+ goto err;
+
+ /* Write the data into MMD's selected register */
+ ret = bus->write(bus, 0, MII_MMD_DATA, data);
+err:
+ if (ret < 0)
+ dev_err(&bus->dev,
+ "failed to write mmd register\n");
+ return ret;
+}
+
+static void
+core_write(struct mt7530_priv *priv, u32 reg, u32 val)
+{
+ struct mii_bus *bus = priv->bus;
+
+ mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
+
+ core_write_mmd_indirect(priv, reg, MDIO_MMD_VEND2, val);
+
+ mutex_unlock(&bus->mdio_lock);
+}
+
+static void
+core_rmw(struct mt7530_priv *priv, u32 reg, u32 mask, u32 set)
+{
+ struct mii_bus *bus = priv->bus;
+ u32 val;
+
+ mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
+
+ val = core_read_mmd_indirect(priv, reg, MDIO_MMD_VEND2);
+ val &= ~mask;
+ val |= set;
+ core_write_mmd_indirect(priv, reg, MDIO_MMD_VEND2, val);
+
+ mutex_unlock(&bus->mdio_lock);
+}
+
+static void
+core_set(struct mt7530_priv *priv, u32 reg, u32 val)
+{
+ core_rmw(priv, reg, 0, val);
+}
+
+static void
+core_clear(struct mt7530_priv *priv, u32 reg, u32 val)
+{
+ core_rmw(priv, reg, val, 0);
+}
+
+static int
+mt7530_mii_write(struct mt7530_priv *priv, u32 reg, u32 val)
+{
+ struct mii_bus *bus = priv->bus;
+ u16 page, r, lo, hi;
+ int ret;
+
+ page = (reg >> 6) & 0x3ff;
+ r = (reg >> 2) & 0xf;
+ lo = val & 0xffff;
+ hi = val >> 16;
+
+ /* MT7530 uses 31 as the pseudo port */
+ ret = bus->write(bus, 0x1f, 0x1f, page);
+ if (ret < 0)
+ goto err;
+
+ ret = bus->write(bus, 0x1f, r, lo);
+ if (ret < 0)
+ goto err;
+
+ ret = bus->write(bus, 0x1f, 0x10, hi);
+err:
+ if (ret < 0)
+ dev_err(&bus->dev,
+ "failed to write mt7530 register\n");
+ return ret;
+}
+
+static u32
+mt7530_mii_read(struct mt7530_priv *priv, u32 reg)
+{
+ struct mii_bus *bus = priv->bus;
+ u16 page, r, lo, hi;
+ int ret;
+
+ page = (reg >> 6) & 0x3ff;
+ r = (reg >> 2) & 0xf;
+
+ /* MT7530 uses 31 as the pseudo port */
+ ret = bus->write(bus, 0x1f, 0x1f, page);
+ if (ret < 0) {
+ dev_err(&bus->dev,
+ "failed to read mt7530 register\n");
+ return ret;
+ }
+
+ lo = bus->read(bus, 0x1f, r);
+ hi = bus->read(bus, 0x1f, 0x10);
+
+ return (hi << 16) | (lo & 0xffff);
+}
+
+static void
+mt7530_write(struct mt7530_priv *priv, u32 reg, u32 val)
+{
+ struct mii_bus *bus = priv->bus;
+
+ mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
+
+ mt7530_mii_write(priv, reg, val);
+
+ mutex_unlock(&bus->mdio_lock);
+}
+
+static u32
+_mt7530_read(struct mt7530_dummy_poll *p)
+{
+ struct mii_bus *bus = p->priv->bus;
+ u32 val;
+
+ mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
+
+ val = mt7530_mii_read(p->priv, p->reg);
+
+ mutex_unlock(&bus->mdio_lock);
+
+ return val;
+}
+
+static u32
+mt7530_read(struct mt7530_priv *priv, u32 reg)
+{
+ struct mt7530_dummy_poll p;
+
+ INIT_MT7530_DUMMY_POLL(&p, priv, reg);
+ return _mt7530_read(&p);
+}
+
+static void
+mt7530_rmw(struct mt7530_priv *priv, u32 reg,
+ u32 mask, u32 set)
+{
+ struct mii_bus *bus = priv->bus;
+ u32 val;
+
+ mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
+
+ val = mt7530_mii_read(priv, reg);
+ val &= ~mask;
+ val |= set;
+ mt7530_mii_write(priv, reg, val);
+
+ mutex_unlock(&bus->mdio_lock);
+}
+
+static void
+mt7530_set(struct mt7530_priv *priv, u32 reg, u32 val)
+{
+ mt7530_rmw(priv, reg, 0, val);
+}
+
+static void
+mt7530_clear(struct mt7530_priv *priv, u32 reg, u32 val)
+{
+ mt7530_rmw(priv, reg, val, 0);
+}
+
+static int
+mt7530_fdb_cmd(struct mt7530_priv *priv, enum mt7530_fdb_cmd cmd, u32 *rsp)
+{
+ u32 val;
+ int ret;
+ struct mt7530_dummy_poll p;
+
+ /* Set the command operating upon the MAC address entries */
+ val = ATC_BUSY | ATC_MAT(0) | cmd;
+ mt7530_write(priv, MT7530_ATC, val);
+
+ INIT_MT7530_DUMMY_POLL(&p, priv, MT7530_ATC);
+ ret = readx_poll_timeout(_mt7530_read, &p, val,
+ !(val & ATC_BUSY), 20, 20000);
+ if (ret < 0) {
+ dev_err(priv->dev, "reset timeout\n");
+ return ret;
+ }
+
+ /* Additional sanity for read command if the specified
+ * entry is invalid
+ */
+ val = mt7530_read(priv, MT7530_ATC);
+ if ((cmd == MT7530_FDB_READ) && (val & ATC_INVALID))
+ return -EINVAL;
+
+ if (rsp)
+ *rsp = val;
+
+ return 0;
+}
+
+static void
+mt7530_fdb_read(struct mt7530_priv *priv, struct mt7530_fdb *fdb)
+{
+ u32 reg[3];
+ int i;
+
+ /* Read from ARL table into an array */
+ for (i = 0; i < 3; i++) {
+ reg[i] = mt7530_read(priv, MT7530_TSRA1 + (i * 4));
+
+ dev_dbg(priv->dev, "%s(%d) reg[%d]=0x%x\n",
+ __func__, __LINE__, i, reg[i]);
+ }
+
+ fdb->vid = (reg[1] >> CVID) & CVID_MASK;
+ fdb->aging = (reg[2] >> AGE_TIMER) & AGE_TIMER_MASK;
+ fdb->port_mask = (reg[2] >> PORT_MAP) & PORT_MAP_MASK;
+ fdb->mac[0] = (reg[0] >> MAC_BYTE_0) & MAC_BYTE_MASK;
+ fdb->mac[1] = (reg[0] >> MAC_BYTE_1) & MAC_BYTE_MASK;
+ fdb->mac[2] = (reg[0] >> MAC_BYTE_2) & MAC_BYTE_MASK;
+ fdb->mac[3] = (reg[0] >> MAC_BYTE_3) & MAC_BYTE_MASK;
+ fdb->mac[4] = (reg[1] >> MAC_BYTE_4) & MAC_BYTE_MASK;
+ fdb->mac[5] = (reg[1] >> MAC_BYTE_5) & MAC_BYTE_MASK;
+ fdb->noarp = ((reg[2] >> ENT_STATUS) & ENT_STATUS_MASK) == STATIC_ENT;
+}
+
+static void
+mt7530_fdb_write(struct mt7530_priv *priv, u16 vid,
+ u8 port_mask, const u8 *mac,
+ u8 aging, u8 type)
+{
+ u32 reg[3] = { 0 };
+ int i;
+
+ reg[1] |= vid & CVID_MASK;
+ reg[2] |= (aging & AGE_TIMER_MASK) << AGE_TIMER;
+ reg[2] |= (port_mask & PORT_MAP_MASK) << PORT_MAP;
+ /* STATIC_ENT indicate that entry is static wouldn't
+ * be aged out and STATIC_EMP specified as erasing an
+ * entry
+ */
+ reg[2] |= (type & ENT_STATUS_MASK) << ENT_STATUS;
+ reg[1] |= mac[5] << MAC_BYTE_5;
+ reg[1] |= mac[4] << MAC_BYTE_4;
+ reg[0] |= mac[3] << MAC_BYTE_3;
+ reg[0] |= mac[2] << MAC_BYTE_2;
+ reg[0] |= mac[1] << MAC_BYTE_1;
+ reg[0] |= mac[0] << MAC_BYTE_0;
+
+ /* Write array into the ARL table */
+ for (i = 0; i < 3; i++)
+ mt7530_write(priv, MT7530_ATA1 + (i * 4), reg[i]);
+}
+
+static int
+mt7530_pad_clk_setup(struct dsa_switch *ds, int mode)
+{
+ struct mt7530_priv *priv = ds->priv;
+ u32 ncpo1, ssc_delta, trgint, i;
+
+ switch (mode) {
+ case PHY_INTERFACE_MODE_RGMII:
+ trgint = 0;
+ ncpo1 = 0x0c80;
+ ssc_delta = 0x87;
+ break;
+ case PHY_INTERFACE_MODE_TRGMII:
+ trgint = 1;
+ ncpo1 = 0x1400;
+ ssc_delta = 0x57;
+ break;
+ default:
+ dev_err(priv->dev, "xMII mode %d not supported\n", mode);
+ return -EINVAL;
+ }
+
+ mt7530_rmw(priv, MT7530_P6ECR, P6_INTF_MODE_MASK,
+ P6_INTF_MODE(trgint));
+
+ /* Lower Tx Driving for TRGMII path */
+ for (i = 0 ; i < NUM_TRGMII_CTRL ; i++)
+ mt7530_write(priv, MT7530_TRGMII_TD_ODT(i),
+ TD_DM_DRVP(8) | TD_DM_DRVN(8));
+
+ /* Setup core clock for MT7530 */
+ if (!trgint) {
+ /* Disable MT7530 core clock */
+ core_clear(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN);
+
+ /* Disable PLL, since phy_device has not yet been created
+ * provided for phy_[read,write]_mmd_indirect is called, we
+ * provide our own core_write_mmd_indirect to complete this
+ * function.
+ */
+ core_write_mmd_indirect(priv,
+ CORE_GSWPLL_GRP1,
+ MDIO_MMD_VEND2,
+ 0);
+
+ /* Set core clock into 500Mhz */
+ core_write(priv, CORE_GSWPLL_GRP2,
+ RG_GSWPLL_POSDIV_500M(1) |
+ RG_GSWPLL_FBKDIV_500M(25));
+
+ /* Enable PLL */
+ core_write(priv, CORE_GSWPLL_GRP1,
+ RG_GSWPLL_EN_PRE |
+ RG_GSWPLL_POSDIV_200M(2) |
+ RG_GSWPLL_FBKDIV_200M(32));
+
+ /* Enable MT7530 core clock */
+ core_set(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN);
+ }
+
+ /* Setup the MT7530 TRGMII Tx Clock */
+ core_set(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN);
+ core_write(priv, CORE_PLL_GROUP5, RG_LCDDS_PCW_NCPO1(ncpo1));
+ core_write(priv, CORE_PLL_GROUP6, RG_LCDDS_PCW_NCPO0(0));
+ core_write(priv, CORE_PLL_GROUP10, RG_LCDDS_SSC_DELTA(ssc_delta));
+ core_write(priv, CORE_PLL_GROUP11, RG_LCDDS_SSC_DELTA1(ssc_delta));
+ core_write(priv, CORE_PLL_GROUP4,
+ RG_SYSPLL_DDSFBK_EN | RG_SYSPLL_BIAS_EN |
+ RG_SYSPLL_BIAS_LPF_EN);
+ core_write(priv, CORE_PLL_GROUP2,
+ RG_SYSPLL_EN_NORMAL | RG_SYSPLL_VODEN |
+ RG_SYSPLL_POSDIV(1));
+ core_write(priv, CORE_PLL_GROUP7,
+ RG_LCDDS_PCW_NCPO_CHG | RG_LCCDS_C(3) |
+ RG_LCDDS_PWDB | RG_LCDDS_ISO_EN);
+ core_set(priv, CORE_TRGMII_GSW_CLK_CG,
+ REG_GSWCK_EN | REG_TRGMIICK_EN);
+
+ if (!trgint)
+ for (i = 0 ; i < NUM_TRGMII_CTRL; i++)
+ mt7530_rmw(priv, MT7530_TRGMII_RD(i),
+ RD_TAP_MASK, RD_TAP(16));
+ else
+ mt7623_trgmii_set(priv, GSW_INTF_MODE, INTF_MODE_TRGMII);
+
+ return 0;
+}
+
+static int
+mt7623_pad_clk_setup(struct dsa_switch *ds)
+{
+ struct mt7530_priv *priv = ds->priv;
+ int i;
+
+ for (i = 0 ; i < NUM_TRGMII_CTRL; i++)
+ mt7623_trgmii_write(priv, GSW_TRGMII_TD_ODT(i),
+ TD_DM_DRVP(8) | TD_DM_DRVN(8));
+
+ mt7623_trgmii_set(priv, GSW_TRGMII_RCK_CTRL, RX_RST | RXC_DQSISEL);
+ mt7623_trgmii_clear(priv, GSW_TRGMII_RCK_CTRL, RX_RST);
+
+ return 0;
+}
+
+static void
+mt7530_mib_reset(struct dsa_switch *ds)
+{
+ struct mt7530_priv *priv = ds->priv;
+
+ mt7530_write(priv, MT7530_MIB_CCR, CCR_MIB_FLUSH);
+ mt7530_write(priv, MT7530_MIB_CCR, CCR_MIB_ACTIVATE);
+}
+
+static void
+mt7530_port_set_status(struct mt7530_priv *priv, int port, int enable)
+{
+ u32 mask = PMCR_TX_EN | PMCR_RX_EN;
+
+ if (enable)
+ mt7530_set(priv, MT7530_PMCR_P(port), mask);
+ else
+ mt7530_clear(priv, MT7530_PMCR_P(port), mask);
+}
+
+static int mt7530_phy_read(struct dsa_switch *ds, int port, int regnum)
+{
+ struct mt7530_priv *priv = ds->priv;
+
+ return mdiobus_read_nested(priv->bus, port, regnum);
+}
+
+int mt7530_phy_write(struct dsa_switch *ds, int port, int regnum, u16 val)
+{
+ struct mt7530_priv *priv = ds->priv;
+
+ return mdiobus_write_nested(priv->bus, port, regnum, val);
+}
+
+static void
+mt7530_get_strings(struct dsa_switch *ds, int port, uint8_t *data)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(mt7530_mib); i++)
+ strncpy(data + i * ETH_GSTRING_LEN, mt7530_mib[i].name,
+ ETH_GSTRING_LEN);
+}
+
+static void
+mt7530_get_ethtool_stats(struct dsa_switch *ds, int port,
+ uint64_t *data)
+{
+ struct mt7530_priv *priv = ds->priv;
+ const struct mt7530_mib_desc *mib;
+ u32 reg, i;
+ u64 hi;
+
+ for (i = 0; i < ARRAY_SIZE(mt7530_mib); i++) {
+ mib = &mt7530_mib[i];
+ reg = MT7530_PORT_MIB_COUNTER(port) + mib->offset;
+
+ data[i] = mt7530_read(priv, reg);
+ if (mib->size == 2) {
+ hi = mt7530_read(priv, reg + 4);
+ data[i] |= hi << 32;
+ }
+ }
+}
+
+static int
+mt7530_get_sset_count(struct dsa_switch *ds)
+{
+ return ARRAY_SIZE(mt7530_mib);
+}
+
+static void mt7530_adjust_link(struct dsa_switch *ds, int port,
+ struct phy_device *phydev)
+{
+ struct mt7530_priv *priv = ds->priv;
+
+ if (phy_is_pseudo_fixed_link(phydev)) {
+ dev_dbg(priv->dev, "phy-mode for master device = %x\n",
+ phydev->interface);
+
+ /* Setup TX circuit incluing relevant PAD and driving */
+ mt7530_pad_clk_setup(ds, phydev->interface);
+
+ /* Setup RX circuit, relevant PAD and driving on the host
+ * which must be placed after the setup on the device side is
+ * all finished.
+ */
+ mt7623_pad_clk_setup(ds);
+ }
+}
+
+static int
+mt7530_cpu_port_enable(struct mt7530_priv *priv,
+ int port)
+{
+ /* Enable Mediatek header mode on the cpu port */
+ mt7530_write(priv, MT7530_PVC_P(port),
+ PORT_SPEC_TAG);
+
+ /* Setup the MAC by default for the cpu port */
+ mt7530_write(priv, MT7530_PMCR_P(port), PMCR_CPUP_LINK);
+
+ /* Disable auto learning on the cpu port */
+ mt7530_set(priv, MT7530_PSC_P(port), SA_DIS);
+
+ /* Unknown unicast frame fordwarding to the cpu port */
+ mt7530_set(priv, MT7530_MFC, UNU_FFP(BIT(port)));
+
+ /* CPU port gets connected to all user ports of
+ * the switch
+ */
+ mt7530_write(priv, MT7530_PCR_P(port),
+ PCR_MATRIX(priv->ds->enabled_port_mask));
+
+ return 0;
+}
+
+static int
+mt7530_port_enable(struct dsa_switch *ds, int port,
+ struct phy_device *phy)
+{
+ struct mt7530_priv *priv = ds->priv;
+
+ mutex_lock(&priv->reg_mutex);
+
+ /* Setup the MAC for the user port */
+ mt7530_write(priv, MT7530_PMCR_P(port), PMCR_USERP_LINK);
+
+ /* Allow the user port gets connected to the cpu port and also
+ * restore the port matrix if the port is the member of a certain
+ * bridge.
+ */
+ priv->ports[port].pm |= PCR_MATRIX(BIT(MT7530_CPU_PORT));
+ priv->ports[port].enable = true;
+ mt7530_rmw(priv, MT7530_PCR_P(port), PCR_MATRIX_MASK,
+ priv->ports[port].pm);
+ mt7530_port_set_status(priv, port, 1);
+
+ mutex_unlock(&priv->reg_mutex);
+
+ return 0;
+}
+
+static void
+mt7530_port_disable(struct dsa_switch *ds, int port,
+ struct phy_device *phy)
+{
+ struct mt7530_priv *priv = ds->priv;
+
+ mutex_lock(&priv->reg_mutex);
+
+ /* Clear up all port matrix which could be restored in the next
+ * enablement for the port.
+ */
+ priv->ports[port].enable = false;
+ mt7530_rmw(priv, MT7530_PCR_P(port), PCR_MATRIX_MASK,
+ PCR_MATRIX_CLR);
+ mt7530_port_set_status(priv, port, 0);
+
+ mutex_unlock(&priv->reg_mutex);
+}
+
+static void
+mt7530_stp_state_set(struct dsa_switch *ds, int port, u8 state)
+{
+ struct mt7530_priv *priv = ds->priv;
+ u32 stp_state;
+
+ switch (state) {
+ case BR_STATE_DISABLED:
+ stp_state = MT7530_STP_DISABLED;
+ break;
+ case BR_STATE_BLOCKING:
+ stp_state = MT7530_STP_BLOCKING;
+ break;
+ case BR_STATE_LISTENING:
+ stp_state = MT7530_STP_LISTENING;
+ break;
+ case BR_STATE_LEARNING:
+ stp_state = MT7530_STP_LEARNING;
+ break;
+ case BR_STATE_FORWARDING:
+ default:
+ stp_state = MT7530_STP_FORWARDING;
+ break;
+ }
+
+ mt7530_rmw(priv, MT7530_SSP_P(port), FID_PST_MASK, stp_state);
+}
+
+static int
+mt7530_port_bridge_join(struct dsa_switch *ds, int port,
+ struct net_device *bridge)
+{
+ struct mt7530_priv *priv = ds->priv;
+ u32 port_bitmap = BIT(MT7530_CPU_PORT);
+ int i;
+
+ mutex_lock(&priv->reg_mutex);
+
+ for (i = 0; i < MT7530_NUM_PORTS; i++) {
+ /* Add this port to the port matrix of the other ports in the
+ * same bridge. If the port is disabled, port matrix is kept
+ * and not being setup until the port becomes enabled.
+ */
+ if (ds->enabled_port_mask & BIT(i) && i != port) {
+ if (ds->ports[i].bridge_dev != bridge)
+ continue;
+ if (priv->ports[i].enable)
+ mt7530_set(priv, MT7530_PCR_P(i),
+ PCR_MATRIX(BIT(port)));
+ priv->ports[i].pm |= PCR_MATRIX(BIT(port));
+
+ port_bitmap |= BIT(i);
+ }
+ }
+
+ /* Add the all other ports to this port matrix. */
+ if (priv->ports[port].enable)
+ mt7530_rmw(priv, MT7530_PCR_P(port),
+ PCR_MATRIX_MASK, PCR_MATRIX(port_bitmap));
+ priv->ports[port].pm |= PCR_MATRIX(port_bitmap);
+
+ mutex_unlock(&priv->reg_mutex);
+
+ return 0;
+}
+
+static void
+mt7530_port_bridge_leave(struct dsa_switch *ds, int port,
+ struct net_device *bridge)
+{
+ struct mt7530_priv *priv = ds->priv;
+ int i;
+
+ mutex_lock(&priv->reg_mutex);
+
+ for (i = 0; i < MT7530_NUM_PORTS; i++) {
+ /* Remove this port from the port matrix of the other ports
+ * in the same bridge. If the port is disabled, port matrix
+ * is kept and not being setup until the port becomes enabled.
+ */
+ if (ds->enabled_port_mask & BIT(i) && i != port) {
+ if (ds->ports[i].bridge_dev != bridge)
+ continue;
+ if (priv->ports[i].enable)
+ mt7530_clear(priv, MT7530_PCR_P(i),
+ PCR_MATRIX(BIT(port)));
+ priv->ports[i].pm &= ~PCR_MATRIX(BIT(port));
+ }
+ }
+
+ /* Set the cpu port to be the only one in the port matrix of
+ * this port.
+ */
+ if (priv->ports[port].enable)
+ mt7530_rmw(priv, MT7530_PCR_P(port), PCR_MATRIX_MASK,
+ PCR_MATRIX(BIT(MT7530_CPU_PORT)));
+ priv->ports[port].pm = PCR_MATRIX(BIT(MT7530_CPU_PORT));
+
+ mutex_unlock(&priv->reg_mutex);
+}
+
+static int
+mt7530_port_fdb_prepare(struct dsa_switch *ds, int port,
+ const struct switchdev_obj_port_fdb *fdb,
+ struct switchdev_trans *trans)
+{
+ struct mt7530_priv *priv = ds->priv;
+ int ret;
+
+ /* Because auto-learned entrie shares the same FDB table.
+ * an entry is reserved with no port_mask to make sure fdb_add
+ * is called while the entry is still available.
+ */
+ mutex_lock(&priv->reg_mutex);
+ mt7530_fdb_write(priv, fdb->vid, 0, fdb->addr, -1, STATIC_ENT);
+ ret = mt7530_fdb_cmd(priv, MT7530_FDB_WRITE, 0);
+ mutex_unlock(&priv->reg_mutex);
+
+ return ret;
+}
+
+static void
+mt7530_port_fdb_add(struct dsa_switch *ds, int port,
+ const struct switchdev_obj_port_fdb *fdb,
+ struct switchdev_trans *trans)
+{
+ struct mt7530_priv *priv = ds->priv;
+ u8 port_mask = BIT(port);
+
+ mutex_lock(&priv->reg_mutex);
+ mt7530_fdb_write(priv, fdb->vid, port_mask, fdb->addr, -1, STATIC_ENT);
+ mt7530_fdb_cmd(priv, MT7530_FDB_WRITE, 0);
+ mutex_unlock(&priv->reg_mutex);
+}
+
+static int
+mt7530_port_fdb_del(struct dsa_switch *ds, int port,
+ const struct switchdev_obj_port_fdb *fdb)
+{
+ struct mt7530_priv *priv = ds->priv;
+ int ret;
+ u8 port_mask = BIT(port);
+
+ mutex_lock(&priv->reg_mutex);
+ mt7530_fdb_write(priv, fdb->vid, port_mask, fdb->addr, -1, STATIC_EMP);
+ ret = mt7530_fdb_cmd(priv, MT7530_FDB_WRITE, 0);
+ mutex_unlock(&priv->reg_mutex);
+
+ return ret;
+}
+
+static int
+mt7530_port_fdb_dump(struct dsa_switch *ds, int port,
+ struct switchdev_obj_port_fdb *fdb,
+ int (*cb)(struct switchdev_obj *obj))
+{
+ struct mt7530_priv *priv = ds->priv;
+ struct mt7530_fdb _fdb = { 0 };
+ int cnt = MT7530_NUM_FDB_RECORDS;
+ int ret = 0;
+ u32 rsp = 0;
+
+ mutex_lock(&priv->reg_mutex);
+
+ ret = mt7530_fdb_cmd(priv, MT7530_FDB_START, &rsp);
+ if (ret < 0)
+ goto err;
+
+ do {
+ if (rsp & ATC_SRCH_HIT) {
+ mt7530_fdb_read(priv, &_fdb);
+ if (_fdb.port_mask & BIT(port)) {
+ ether_addr_copy(fdb->addr, _fdb.mac);
+ fdb->vid = _fdb.vid;
+ fdb->ndm_state = _fdb.noarp ?
+ NUD_NOARP : NUD_REACHABLE;
+ ret = cb(&fdb->obj);
+ if (ret < 0)
+ break;
+ }
+ }
+ } while (--cnt &&
+ !(rsp & ATC_SRCH_END) &&
+ !mt7530_fdb_cmd(priv, MT7530_FDB_NEXT, &rsp));
+err:
+ mutex_unlock(&priv->reg_mutex);
+
+ return 0;
+}
+
+static enum dsa_tag_protocol
+mtk_get_tag_protocol(struct dsa_switch *ds)
+{
+ struct mt7530_priv *priv = ds->priv;
+
+ if (!dsa_is_cpu_port(ds, MT7530_CPU_PORT)) {
+ dev_warn(priv->dev,
+ "port not matched with tagging CPU port\n");
+ return DSA_TAG_PROTO_NONE;
+ } else {
+ return DSA_TAG_PROTO_MTK;
+ }
+}
+
+static int
+mt7530_setup(struct dsa_switch *ds)
+{
+ struct mt7530_priv *priv = ds->priv;
+ int ret, i;
+ u32 id, val;
+ struct device_node *dn;
+ struct mt7530_dummy_poll p;
+
+ /* The parent node of master_netdev which holds the common system
+ * controller also is the container for two GMACs nodes representing
+ * as two netdev instances.
+ */
+ dn = ds->master_netdev->dev.of_node->parent;
+ priv->ethernet = syscon_node_to_regmap(dn);
+ if (IS_ERR(priv->ethernet))
+ return PTR_ERR(priv->ethernet);
+
+ regulator_set_voltage(priv->core_pwr, 1000000, 1000000);
+ ret = regulator_enable(priv->core_pwr);
+ if (ret < 0) {
+ dev_err(priv->dev,
+ "Failed to enable core power: %d\n", ret);
+ return ret;
+ }
+
+ regulator_set_voltage(priv->io_pwr, 3300000, 3300000);
+ ret = regulator_enable(priv->io_pwr);
+ if (ret < 0) {
+ dev_err(priv->dev, "Failed to enable io pwr: %d\n",
+ ret);
+ return ret;
+ }
+
+ /* Reset whole chip through gpio pin or memory-mapped registers for
+ * different type of hardware
+ */
+ if (priv->mcm) {
+ reset_control_assert(priv->rstc);
+ usleep_range(1000, 1100);
+ reset_control_deassert(priv->rstc);
+ } else {
+ gpiod_set_value_cansleep(priv->reset, 0);
+ usleep_range(1000, 1100);
+ gpiod_set_value_cansleep(priv->reset, 1);
+ }
+
+ /* Waiting for MT7530 got to stable */
+ INIT_MT7530_DUMMY_POLL(&p, priv, MT7530_HWTRAP);
+ ret = readx_poll_timeout(_mt7530_read, &p, val, val != 0,
+ 20, 1000000);
+ if (ret < 0) {
+ dev_err(priv->dev, "reset timeout\n");
+ return ret;
+ }
+
+ id = mt7530_read(priv, MT7530_CREV);
+ id >>= CHIP_NAME_SHIFT;
+ if (id != MT7530_ID) {
+ dev_err(priv->dev, "chip %x can't be supported\n", id);
+ return -ENODEV;
+ }
+
+ /* Reset the switch through internal reset */
+ mt7530_write(priv, MT7530_SYS_CTRL,
+ SYS_CTRL_PHY_RST | SYS_CTRL_SW_RST |
+ SYS_CTRL_REG_RST);
+
+ /* Enable Port 6 only; P5 as GMAC5 which currently is not supported */
+ val = mt7530_read(priv, MT7530_MHWTRAP);
+ val &= ~MHWTRAP_P6_DIS & ~MHWTRAP_PHY_ACCESS;
+ val |= MHWTRAP_MANUAL;
+ mt7530_write(priv, MT7530_MHWTRAP, val);
+
+ /* Enable and reset MIB counters */
+ mt7530_mib_reset(ds);
+
+ mt7530_clear(priv, MT7530_MFC, UNU_FFP_MASK);
+
+ for (i = 0; i < MT7530_NUM_PORTS; i++) {
+ /* Disable forwarding by default on all ports */
+ mt7530_rmw(priv, MT7530_PCR_P(i), PCR_MATRIX_MASK,
+ PCR_MATRIX_CLR);
+
+ if (dsa_is_cpu_port(ds, i))
+ mt7530_cpu_port_enable(priv, i);
+ else
+ mt7530_port_disable(ds, i, NULL);
+ }
+
+ /* Flush the FDB table */
+ ret = mt7530_fdb_cmd(priv, MT7530_FDB_FLUSH, 0);
+ if (ret < 0)
+ return ret;
+
+ return 0;
+}
+
+static struct dsa_switch_ops mt7530_switch_ops = {
+ .get_tag_protocol = mtk_get_tag_protocol,
+ .setup = mt7530_setup,
+ .get_strings = mt7530_get_strings,
+ .phy_read = mt7530_phy_read,
+ .phy_write = mt7530_phy_write,
+ .get_ethtool_stats = mt7530_get_ethtool_stats,
+ .get_sset_count = mt7530_get_sset_count,
+ .adjust_link = mt7530_adjust_link,
+ .port_enable = mt7530_port_enable,
+ .port_disable = mt7530_port_disable,
+ .port_stp_state_set = mt7530_stp_state_set,
+ .port_bridge_join = mt7530_port_bridge_join,
+ .port_bridge_leave = mt7530_port_bridge_leave,
+ .port_fdb_prepare = mt7530_port_fdb_prepare,
+ .port_fdb_add = mt7530_port_fdb_add,
+ .port_fdb_del = mt7530_port_fdb_del,
+ .port_fdb_dump = mt7530_port_fdb_dump,
+};
+
+static int
+mt7530_probe(struct mdio_device *mdiodev)
+{
+ struct mt7530_priv *priv;
+ struct device_node *dn;
+
+ dn = mdiodev->dev.of_node;
+
+ priv = devm_kzalloc(&mdiodev->dev, sizeof(*priv), GFP_KERNEL);
+ if (!priv)
+ return -ENOMEM;
+
+ priv->ds = dsa_switch_alloc(&mdiodev->dev, DSA_MAX_PORTS);
+ if (!priv->ds)
+ return -ENOMEM;
+
+ /* Use medatek,mcm property to distinguish hardware type that would
+ * casues a little bit differences on power-on sequence.
+ */
+ priv->mcm = of_property_read_bool(dn, "mediatek,mcm");
+ if (priv->mcm) {
+ dev_info(&mdiodev->dev, "MT7530 adapts as multi-chip module\n");
+
+ priv->rstc = devm_reset_control_get(&mdiodev->dev, "mcm");
+ if (IS_ERR(priv->rstc)) {
+ dev_err(&mdiodev->dev, "Couldn't get our reset line\n");
+ return PTR_ERR(priv->rstc);
+ }
+ }
+
+ priv->core_pwr = devm_regulator_get(&mdiodev->dev, "core");
+ if (IS_ERR(priv->core_pwr))
+ return PTR_ERR(priv->core_pwr);
+
+ priv->io_pwr = devm_regulator_get(&mdiodev->dev, "io");
+ if (IS_ERR(priv->io_pwr))
+ return PTR_ERR(priv->io_pwr);
+
+ /* Not MCM that indicates switch works as the remote standalone
+ * integrated circuit so the GPIO pin would be used to complete
+ * the reset, otherwise memory-mapped register accessing used
+ * through syscon provides in the case of MCM.
+ */
+ if (!priv->mcm) {
+ priv->reset = devm_gpiod_get_optional(&mdiodev->dev, "reset",
+ GPIOD_OUT_LOW);
+ if (IS_ERR(priv->reset)) {
+ dev_err(&mdiodev->dev, "Couldn't get our reset line\n");
+ return PTR_ERR(priv->reset);
+ }
+ }
+
+ priv->bus = mdiodev->bus;
+ priv->dev = &mdiodev->dev;
+ priv->ds->priv = priv;
+ priv->ds->ops = &mt7530_switch_ops;
+ mutex_init(&priv->reg_mutex);
+ dev_set_drvdata(&mdiodev->dev, priv);
+
+ return dsa_register_switch(priv->ds, &mdiodev->dev);
+}
+
+static void
+mt7530_remove(struct mdio_device *mdiodev)
+{
+ struct mt7530_priv *priv = dev_get_drvdata(&mdiodev->dev);
+ int ret = 0;
+
+ ret = regulator_disable(priv->core_pwr);
+ if (ret < 0)
+ dev_err(priv->dev,
+ "Failed to disable core power: %d\n", ret);
+
+ ret = regulator_disable(priv->io_pwr);
+ if (ret < 0)
+ dev_err(priv->dev, "Failed to disable io pwr: %d\n",
+ ret);
+
+ dsa_unregister_switch(priv->ds);
+ mutex_destroy(&priv->reg_mutex);
+}
+
+static const struct of_device_id mt7530_of_match[] = {
+ { .compatible = "mediatek,mt7530" },
+ { /* sentinel */ },
+};
+
+static struct mdio_driver mt7530_mdio_driver = {
+ .probe = mt7530_probe,
+ .remove = mt7530_remove,
+ .mdiodrv.driver = {
+ .name = "mt7530",
+ .of_match_table = mt7530_of_match,
+ },
+};
+
+mdio_module_driver(mt7530_mdio_driver);
+
+MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
+MODULE_DESCRIPTION("Driver for Mediatek MT7530 Switch");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:mediatek-mt7530");
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
new file mode 100644
index 0000000..b83d76b
--- /dev/null
+++ b/drivers/net/dsa/mt7530.h
@@ -0,0 +1,402 @@
+/*
+ * Copyright (C) 2017 Sean Wang <sean.wang@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __MT7530_H
+#define __MT7530_H
+
+#define MT7530_NUM_PORTS 7
+#define MT7530_CPU_PORT 6
+#define MT7530_NUM_FDB_RECORDS 2048
+
+#define NUM_TRGMII_CTRL 5
+
+#define TRGMII_BASE(x) (0x10000 + (x))
+
+/* Registers to ethsys access */
+#define ETHSYS_CLKCFG0 0x2c
+#define ETHSYS_TRGMII_CLK_SEL362_5 BIT(11)
+
+#define SYSC_REG_RSTCTRL 0x34
+#define RESET_MCM BIT(2)
+
+/* Registers to mac forward control for unknown frames */
+#define MT7530_MFC 0x10
+#define BC_FFP(x) (((x) & 0xff) << 24)
+#define UNM_FFP(x) (((x) & 0xff) << 16)
+#define UNU_FFP(x) (((x) & 0xff) << 8)
+#define UNU_FFP_MASK UNU_FFP(~0)
+
+/* Registers for address table access */
+#define MT7530_ATA1 0x74
+#define STATIC_EMP 0
+#define STATIC_ENT 3
+#define MT7530_ATA2 0x78
+
+/* Register for address table write data */
+#define MT7530_ATWD 0x7c
+
+/* Register for address table control */
+#define MT7530_ATC 0x80
+#define ATC_HASH (((x) & 0xfff) << 16)
+#define ATC_BUSY BIT(15)
+#define ATC_SRCH_END BIT(14)
+#define ATC_SRCH_HIT BIT(13)
+#define ATC_INVALID BIT(12)
+#define ATC_MAT(x) (((x) & 0xf) << 8)
+#define ATC_MAT_MACTAB ATC_MAT(0)
+
+enum mt7530_fdb_cmd {
+ MT7530_FDB_READ = 0,
+ MT7530_FDB_WRITE = 1,
+ MT7530_FDB_FLUSH = 2,
+ MT7530_FDB_START = 4,
+ MT7530_FDB_NEXT = 5,
+};
+
+/* Registers for table search read address */
+#define MT7530_TSRA1 0x84
+#define MAC_BYTE_0 24
+#define MAC_BYTE_1 16
+#define MAC_BYTE_2 8
+#define MAC_BYTE_3 0
+#define MAC_BYTE_MASK 0xff
+
+#define MT7530_TSRA2 0x88
+#define MAC_BYTE_4 24
+#define MAC_BYTE_5 16
+#define CVID 0
+#define CVID_MASK 0xfff
+
+#define MT7530_ATRD 0x8C
+#define AGE_TIMER 24
+#define AGE_TIMER_MASK 0xff
+#define PORT_MAP 4
+#define PORT_MAP_MASK 0xff
+#define ENT_STATUS 2
+#define ENT_STATUS_MASK 0x3
+
+/* Register for vlan table control */
+#define MT7530_VTCR 0x90
+#define VTCR_BUSY BIT(31)
+#define VTCR_FUNC (((x) & 0xf) << 12)
+#define VTCR_FUNC_RD_VID 0x1
+#define VTCR_FUNC_WR_VID 0x2
+#define VTCR_FUNC_INV_VID 0x3
+#define VTCR_FUNC_VAL_VID 0x4
+#define VTCR_VID ((x) & 0xfff)
+
+/* Register for setup vlan and acl write data */
+#define MT7530_VAWD1 0x94
+#define PORT_STAG BIT(31)
+#define IVL_MAC BIT(30)
+#define PORT_MEM(x) (((x) & 0xff) << 16)
+#define VALID BIT(1)
+
+#define MT7530_VAWD2 0x98
+
+/* Register for port STP state control */
+#define MT7530_SSP_P(x) (0x2000 + ((x) * 0x100))
+#define FID_PST(x) ((x) & 0x3)
+#define FID_PST_MASK FID_PST(0x3)
+
+enum mt7530_stp_state {
+ MT7530_STP_DISABLED = 0,
+ MT7530_STP_BLOCKING = 1,
+ MT7530_STP_LISTENING = 1,
+ MT7530_STP_LEARNING = 2,
+ MT7530_STP_FORWARDING = 3
+};
+
+/* Register for port control */
+#define MT7530_PCR_P(x) (0x2004 + ((x) * 0x100))
+#define PORT_VLAN(x) ((x) & 0x3)
+#define PCR_MATRIX(x) (((x) & 0xff) << 16)
+#define PORT_PRI(x) (((x) & 0x7) << 24)
+#define EG_TAG(x) (((x) & 0x3) << 28)
+#define PCR_MATRIX_MASK PCR_MATRIX(0xff)
+#define PCR_MATRIX_CLR PCR_MATRIX(0)
+
+/* Register for port security control */
+#define MT7530_PSC_P(x) (0x200c + ((x) * 0x100))
+#define SA_DIS BIT(4)
+
+/* Register for port vlan control */
+#define MT7530_PVC_P(x) (0x2010 + ((x) * 0x100))
+#define PORT_SPEC_TAG BIT(5)
+#define VLAN_ATTR(x) (((x) & 0x3) << 6)
+#define STAG_VPID (((x) & 0xffff) << 16)
+
+/* Register for port port-and-protocol based vlan 1 control */
+#define MT7530_PPBV1_P(x) (0x2014 + ((x) * 0x100))
+
+/* Register for port MAC control register */
+#define MT7530_PMCR_P(x) (0x3000 + ((x) * 0x100))
+#define PMCR_IFG_XMIT(x) (((x) & 0x3) << 18)
+#define PMCR_MAC_MODE BIT(16)
+#define PMCR_FORCE_MODE BIT(15)
+#define PMCR_TX_EN BIT(14)
+#define PMCR_RX_EN BIT(13)
+#define PMCR_BACKOFF_EN BIT(9)
+#define PMCR_BACKPR_EN BIT(8)
+#define PMCR_TX_FC_EN BIT(5)
+#define PMCR_RX_FC_EN BIT(4)
+#define PMCR_FORCE_SPEED_1000 BIT(3)
+#define PMCR_FORCE_FDX BIT(1)
+#define PMCR_FORCE_LNK BIT(0)
+#define PMCR_COMMON_LINK (PMCR_IFG_XMIT(1) | PMCR_MAC_MODE | \
+ PMCR_BACKOFF_EN | PMCR_BACKPR_EN | \
+ PMCR_TX_EN | PMCR_RX_EN | \
+ PMCR_TX_FC_EN | PMCR_RX_FC_EN)
+#define PMCR_CPUP_LINK (PMCR_COMMON_LINK | PMCR_FORCE_MODE | \
+ PMCR_FORCE_SPEED_1000 | \
+ PMCR_FORCE_FDX | \
+ PMCR_FORCE_LNK)
+#define PMCR_USERP_LINK PMCR_COMMON_LINK
+#define PMCR_FIXED_LINK (PMCR_IFG_XMIT(1) | PMCR_MAC_MODE | \
+ PMCR_FORCE_MODE | PMCR_TX_EN | \
+ PMCR_RX_EN | PMCR_BACKPR_EN | \
+ PMCR_BACKOFF_EN | \
+ PMCR_FORCE_SPEED_1000 | \
+ PMCR_FORCE_FDX | \
+ PMCR_FORCE_LNK)
+#define PMCR_FIXED_LINK_FC (PMCR_FIXED_LINK | \
+ PMCR_TX_FC_EN | PMCR_RX_FC_EN)
+
+#define MT7530_PMSR_P(x) (0x3008 + (x) * 0x100)
+
+/* Register for MIB */
+#define MT7530_PORT_MIB_COUNTER(x) (0x4000 + (x) * 0x100)
+#define MT7530_MIB_CCR 0x4fe0
+#define CCR_MIB_ENABLE BIT(31)
+#define CCR_RX_OCT_CNT_GOOD BIT(7)
+#define CCR_RX_OCT_CNT_BAD BIT(6)
+#define CCR_TX_OCT_CNT_GOOD BIT(5)
+#define CCR_TX_OCT_CNT_BAD BIT(4)
+#define CCR_MIB_FLUSH (CCR_RX_OCT_CNT_GOOD | \
+ CCR_RX_OCT_CNT_BAD | \
+ CCR_TX_OCT_CNT_GOOD | \
+ CCR_TX_OCT_CNT_BAD)
+#define CCR_MIB_ACTIVATE (CCR_MIB_ENABLE | \
+ CCR_RX_OCT_CNT_GOOD | \
+ CCR_RX_OCT_CNT_BAD | \
+ CCR_TX_OCT_CNT_GOOD | \
+ CCR_TX_OCT_CNT_BAD)
+/* Register for system reset */
+#define MT7530_SYS_CTRL 0x7000
+#define SYS_CTRL_PHY_RST BIT(2)
+#define SYS_CTRL_SW_RST BIT(1)
+#define SYS_CTRL_REG_RST BIT(0)
+
+/* Register for hw trap status */
+#define MT7530_HWTRAP 0x7800
+
+/* Register for hw trap modification */
+#define MT7530_MHWTRAP 0x7804
+#define MHWTRAP_MANUAL BIT(16)
+#define MHWTRAP_P5_MAC_SEL BIT(13)
+#define MHWTRAP_P6_DIS BIT(8)
+#define MHWTRAP_P5_RGMII_MODE BIT(7)
+#define MHWTRAP_P5_DIS BIT(6)
+#define MHWTRAP_PHY_ACCESS BIT(5)
+
+/* Register for TOP signal control */
+#define MT7530_TOP_SIG_CTRL 0x7808
+#define TOP_SIG_CTRL_NORMAL (BIT(17) | BIT(16))
+
+#define MT7530_IO_DRV_CR 0x7810
+#define P5_IO_CLK_DRV(x) ((x) & 0x3)
+#define P5_IO_DATA_DRV(x) (((x) & 0x3) << 4)
+
+#define MT7530_P6ECR 0x7830
+#define P6_INTF_MODE_MASK 0x3
+#define P6_INTF_MODE(x) ((x) & 0x3)
+
+/* Registers for TRGMII on the both side */
+#define MT7530_TRGMII_RCK_CTRL 0x7a00
+#define GSW_TRGMII_RCK_CTRL 0x300
+#define RX_RST BIT(31)
+#define RXC_DQSISEL BIT(30)
+#define DQSI1_TAP_MASK (0x7f << 8)
+#define DQSI0_TAP_MASK 0x7f
+#define DQSI1_TAP(x) (((x) & 0x7f) << 8)
+#define DQSI0_TAP(x) ((x) & 0x7f)
+
+#define MT7530_TRGMII_RCK_RTT 0x7a04
+#define GSW_TRGMII_RCK_RTT 0x304
+#define DQS1_GATE BIT(31)
+#define DQS0_GATE BIT(30)
+
+#define MT7530_TRGMII_RD(x) (0x7a10 + (x) * 8)
+#define GSW_TRGMII_RD(x) (0x310 + (x) * 8)
+#define BSLIP_EN BIT(31)
+#define EDGE_CHK BIT(30)
+#define RD_TAP_MASK 0x7f
+#define RD_TAP(x) ((x) & 0x7f)
+
+#define GSW_TRGMII_TXCTRL 0x340
+#define MT7530_TRGMII_TXCTRL 0x7a40
+#define TRAIN_TXEN BIT(31)
+#define TXC_INV BIT(30)
+#define TX_RST BIT(28)
+
+#define MT7530_TRGMII_TD_ODT(i) (0x7a54 + 8 * (i))
+#define GSW_TRGMII_TD_ODT(i) (0x354 + 8 * (i))
+#define TD_DM_DRVP(x) ((x) & 0xf)
+#define TD_DM_DRVN(x) (((x) & 0xf) << 4)
+
+#define GSW_INTF_MODE 0x390
+#define INTF_MODE_TRGMII BIT(1)
+
+#define MT7530_TRGMII_TCK_CTRL 0x7a78
+#define TCK_TAP(x) (((x) & 0xf) << 8)
+
+#define MT7530_P5RGMIIRXCR 0x7b00
+#define CSR_RGMII_EDGE_ALIGN BIT(8)
+#define CSR_RGMII_RXC_0DEG_CFG(x) ((x) & 0xf)
+
+#define MT7530_P5RGMIITXCR 0x7b04
+#define CSR_RGMII_TXC_CFG(x) ((x) & 0x1f)
+
+#define MT7530_CREV 0x7ffc
+#define CHIP_NAME_SHIFT 16
+#define MT7530_ID 0x7530
+
+/* Registers for core PLL access through mmd indirect */
+#define CORE_PLL_GROUP2 0x401
+#define RG_SYSPLL_EN_NORMAL BIT(15)
+#define RG_SYSPLL_VODEN BIT(14)
+#define RG_SYSPLL_LF BIT(13)
+#define RG_SYSPLL_RST_DLY(x) (((x) & 0x3) << 12)
+#define RG_SYSPLL_LVROD_EN BIT(10)
+#define RG_SYSPLL_PREDIV(x) (((x) & 0x3) << 8)
+#define RG_SYSPLL_POSDIV(x) (((x) & 0x3) << 5)
+#define RG_SYSPLL_FBKSEL BIT(4)
+#define RT_SYSPLL_EN_AFE_OLT BIT(0)
+
+#define CORE_PLL_GROUP4 0x403
+#define RG_SYSPLL_DDSFBK_EN BIT(12)
+#define RG_SYSPLL_BIAS_EN BIT(11)
+#define RG_SYSPLL_BIAS_LPF_EN BIT(10)
+
+#define CORE_PLL_GROUP5 0x404
+#define RG_LCDDS_PCW_NCPO1(x) ((x) & 0xffff)
+
+#define CORE_PLL_GROUP6 0x405
+#define RG_LCDDS_PCW_NCPO0(x) ((x) & 0xffff)
+
+#define CORE_PLL_GROUP7 0x406
+#define RG_LCDDS_PWDB BIT(15)
+#define RG_LCDDS_ISO_EN BIT(13)
+#define RG_LCCDS_C(x) (((x) & 0x7) << 4)
+#define RG_LCDDS_PCW_NCPO_CHG BIT(3)
+
+#define CORE_PLL_GROUP10 0x409
+#define RG_LCDDS_SSC_DELTA(x) ((x) & 0xfff)
+
+#define CORE_PLL_GROUP11 0x40a
+#define RG_LCDDS_SSC_DELTA1(x) ((x) & 0xfff)
+
+#define CORE_GSWPLL_GRP1 0x40d
+#define RG_GSWPLL_PREDIV(x) (((x) & 0x3) << 14)
+#define RG_GSWPLL_POSDIV_200M(x) (((x) & 0x3) << 12)
+#define RG_GSWPLL_EN_PRE BIT(11)
+#define RG_GSWPLL_FBKSEL BIT(10)
+#define RG_GSWPLL_BP BIT(9)
+#define RG_GSWPLL_BR BIT(8)
+#define RG_GSWPLL_FBKDIV_200M(x) ((x) & 0xff)
+
+#define CORE_GSWPLL_GRP2 0x40e
+#define RG_GSWPLL_POSDIV_500M(x) (((x) & 0x3) << 8)
+#define RG_GSWPLL_FBKDIV_500M(x) ((x) & 0xff)
+
+#define CORE_TRGMII_GSW_CLK_CG 0x410
+#define REG_GSWCK_EN BIT(0)
+#define REG_TRGMIICK_EN BIT(1)
+
+#define MIB_DESC(_s, _o, _n) \
+ { \
+ .size = (_s), \
+ .offset = (_o), \
+ .name = (_n), \
+ }
+
+struct mt7530_mib_desc {
+ unsigned int size;
+ unsigned int offset;
+ const char *name;
+};
+
+struct mt7530_fdb {
+ u16 vid;
+ u8 port_mask;
+ u8 aging;
+ u8 mac[6];
+ bool noarp;
+};
+
+struct mt7530_port {
+ bool enable;
+ u32 pm;
+};
+
+/* struct mt7530_priv - This is the main data structure for holding the state
+ * of the driver
+ * @dev: The device pointer
+ * @ds: The pointer to the dsa core structure
+ * @bus: The bus used for the device and built-in PHY
+ * @rstc: The pointer to reset control used by MCM
+ * @ethernet: The regmap used for access TRGMII-based registers
+ * @core_pwr: The power supplied into the core
+ * @io_pwr: The power supplied into the I/O
+ * @reset: The descriptor for GPIO line tied to its reset pin
+ * @mcm: Flag for distinguishing if standalone IC or module
+ * coupling
+ * @ports: Holding the state among ports
+ * @reg_mutex: The lock for protecting among process accessing
+ * registers
+ */
+struct mt7530_priv {
+ struct device *dev;
+ struct dsa_switch *ds;
+ struct mii_bus *bus;
+ struct reset_control *rstc;
+ struct regmap *ethernet;
+ struct regulator *core_pwr;
+ struct regulator *io_pwr;
+ struct gpio_desc *reset;
+ bool mcm;
+
+ struct mt7530_port ports[MT7530_NUM_PORTS];
+ /* protect among processes for registers access*/
+ struct mutex reg_mutex;
+};
+
+struct mt7530_hw_stats {
+ const char *string;
+ u16 reg;
+ u8 sizeof_stat;
+};
+
+struct mt7530_dummy_poll {
+ struct mt7530_priv *priv;
+ u32 reg;
+};
+
+static inline void INIT_MT7530_DUMMY_POLL(struct mt7530_dummy_poll *p,
+ struct mt7530_priv *priv, u32 reg)
+{
+ p->priv = priv;
+ p->reg = reg;
+}
+
+#endif /* __MT7530_H */
diff --git a/drivers/net/dsa/mv88e6xxx/Makefile b/drivers/net/dsa/mv88e6xxx/Makefile
index c36be31..31d37a9 100644
--- a/drivers/net/dsa/mv88e6xxx/Makefile
+++ b/drivers/net/dsa/mv88e6xxx/Makefile
@@ -1,5 +1,6 @@
obj-$(CONFIG_NET_DSA_MV88E6XXX) += mv88e6xxx.o
mv88e6xxx-objs := chip.o
mv88e6xxx-objs += global1.o
+mv88e6xxx-objs += global1_atu.o
mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_GLOBAL2) += global2.o
mv88e6xxx-objs += port.o
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 03dc886..44ba8cf 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -8,6 +8,9 @@
*
* Copyright (c) 2016 Andrew Lunn <andrew@lunn.ch>
*
+ * Copyright (c) 2016-2017 Savoir-faire Linux Inc.
+ * Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ *
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
@@ -687,11 +690,6 @@ static bool mv88e6xxx_6165_family(struct mv88e6xxx_chip *chip)
return chip->info->family == MV88E6XXX_FAMILY_6165;
}
-static bool mv88e6xxx_6320_family(struct mv88e6xxx_chip *chip)
-{
- return chip->info->family == MV88E6XXX_FAMILY_6320;
-}
-
static bool mv88e6xxx_6341_family(struct mv88e6xxx_chip *chip)
{
return chip->info->family == MV88E6XXX_FAMILY_6341;
@@ -1066,11 +1064,6 @@ static void mv88e6xxx_get_regs(struct dsa_switch *ds, int port,
mutex_unlock(&chip->reg_lock);
}
-static int _mv88e6xxx_atu_wait(struct mv88e6xxx_chip *chip)
-{
- return mv88e6xxx_g1_wait(chip, GLOBAL_ATU_OP, GLOBAL_ATU_OP_BUSY);
-}
-
static int mv88e6xxx_get_eee(struct dsa_switch *ds, int port,
struct ethtool_eee *e)
{
@@ -1130,143 +1123,42 @@ static int mv88e6xxx_set_eee(struct dsa_switch *ds, int port,
return err;
}
-static int _mv88e6xxx_atu_cmd(struct mv88e6xxx_chip *chip, u16 fid, u16 cmd)
+static u16 mv88e6xxx_port_vlan(struct mv88e6xxx_chip *chip, int dev, int port)
{
- u16 val;
- int err;
-
- if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_G1_ATU_FID)) {
- err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_FID, fid);
- if (err)
- return err;
- } else if (mv88e6xxx_num_databases(chip) == 256) {
- /* ATU DBNum[7:4] are located in ATU Control 15:12 */
- err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val);
- if (err)
- return err;
-
- err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL,
- (val & 0xfff) | ((fid << 8) & 0xf000));
- if (err)
- return err;
-
- /* ATU DBNum[3:0] are located in ATU Operation 3:0 */
- cmd |= fid & 0xf;
- }
-
- err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_OP, cmd);
- if (err)
- return err;
-
- return _mv88e6xxx_atu_wait(chip);
-}
-
-static int _mv88e6xxx_atu_data_write(struct mv88e6xxx_chip *chip,
- struct mv88e6xxx_atu_entry *entry)
-{
- u16 data = entry->state & GLOBAL_ATU_DATA_STATE_MASK;
-
- if (entry->state != GLOBAL_ATU_DATA_STATE_UNUSED) {
- unsigned int mask, shift;
-
- if (entry->trunk) {
- data |= GLOBAL_ATU_DATA_TRUNK;
- mask = GLOBAL_ATU_DATA_TRUNK_ID_MASK;
- shift = GLOBAL_ATU_DATA_TRUNK_ID_SHIFT;
- } else {
- mask = GLOBAL_ATU_DATA_PORT_VECTOR_MASK;
- shift = GLOBAL_ATU_DATA_PORT_VECTOR_SHIFT;
- }
-
- data |= (entry->portv_trunkid << shift) & mask;
- }
-
- return mv88e6xxx_g1_write(chip, GLOBAL_ATU_DATA, data);
-}
-
-static int _mv88e6xxx_atu_flush_move(struct mv88e6xxx_chip *chip,
- struct mv88e6xxx_atu_entry *entry,
- bool static_too)
-{
- int op;
- int err;
-
- err = _mv88e6xxx_atu_wait(chip);
- if (err)
- return err;
-
- err = _mv88e6xxx_atu_data_write(chip, entry);
- if (err)
- return err;
-
- if (entry->fid) {
- op = static_too ? GLOBAL_ATU_OP_FLUSH_MOVE_ALL_DB :
- GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC_DB;
- } else {
- op = static_too ? GLOBAL_ATU_OP_FLUSH_MOVE_ALL :
- GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC;
- }
-
- return _mv88e6xxx_atu_cmd(chip, entry->fid, op);
-}
-
-static int _mv88e6xxx_atu_flush(struct mv88e6xxx_chip *chip,
- u16 fid, bool static_too)
-{
- struct mv88e6xxx_atu_entry entry = {
- .fid = fid,
- .state = 0, /* EntryState bits must be 0 */
- };
-
- return _mv88e6xxx_atu_flush_move(chip, &entry, static_too);
-}
-
-static int _mv88e6xxx_atu_move(struct mv88e6xxx_chip *chip, u16 fid,
- int from_port, int to_port, bool static_too)
-{
- struct mv88e6xxx_atu_entry entry = {
- .trunk = false,
- .fid = fid,
- };
-
- /* EntryState bits must be 0xF */
- entry.state = GLOBAL_ATU_DATA_STATE_MASK;
-
- /* ToPort and FromPort are respectively in PortVec bits 7:4 and 3:0 */
- entry.portv_trunkid = (to_port & 0x0f) << 4;
- entry.portv_trunkid |= from_port & 0x0f;
-
- return _mv88e6xxx_atu_flush_move(chip, &entry, static_too);
-}
-
-static int _mv88e6xxx_atu_remove(struct mv88e6xxx_chip *chip, u16 fid,
- int port, bool static_too)
-{
- /* Destination port 0xF means remove the entries */
- return _mv88e6xxx_atu_move(chip, fid, port, 0x0f, static_too);
-}
-
-static int _mv88e6xxx_port_based_vlan_map(struct mv88e6xxx_chip *chip, int port)
-{
- struct dsa_switch *ds = chip->ds;
- struct net_device *bridge = ds->ports[port].bridge_dev;
- u16 output_ports = 0;
+ struct dsa_switch *ds = NULL;
+ struct net_device *br;
+ u16 pvlan;
int i;
- /* allow CPU port or DSA link(s) to send frames to every port */
- if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)) {
- output_ports = ~0;
- } else {
- for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) {
- /* allow sending frames to every group member */
- if (bridge && ds->ports[i].bridge_dev == bridge)
- output_ports |= BIT(i);
+ if (dev < DSA_MAX_SWITCHES)
+ ds = chip->ds->dst->ds[dev];
- /* allow sending frames to CPU port and DSA link(s) */
- if (dsa_is_cpu_port(ds, i) || dsa_is_dsa_port(ds, i))
- output_ports |= BIT(i);
- }
- }
+ /* Prevent frames from unknown switch or port */
+ if (!ds || port >= ds->num_ports)
+ return 0;
+
+ /* Frames from DSA links and CPU ports can egress any local port */
+ if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port))
+ return mv88e6xxx_port_mask(chip);
+
+ br = ds->ports[port].bridge_dev;
+ pvlan = 0;
+
+ /* Frames from user ports can egress any local DSA links and CPU ports,
+ * as well as any local member of their bridge group.
+ */
+ for (i = 0; i < mv88e6xxx_num_ports(chip); ++i)
+ if (dsa_is_cpu_port(chip->ds, i) ||
+ dsa_is_dsa_port(chip->ds, i) ||
+ (br && chip->ds->ports[i].bridge_dev == br))
+ pvlan |= BIT(i);
+
+ return pvlan;
+}
+
+static int mv88e6xxx_port_vlan_map(struct mv88e6xxx_chip *chip, int port)
+{
+ u16 output_ports = mv88e6xxx_port_vlan(chip, chip->ds->index, port);
/* prevent frames from going back out of the port they came in on */
output_ports &= ~BIT(port);
@@ -1306,13 +1198,68 @@ static void mv88e6xxx_port_stp_state_set(struct dsa_switch *ds, int port,
netdev_err(ds->ports[port].netdev, "failed to update state\n");
}
+static int mv88e6xxx_atu_setup(struct mv88e6xxx_chip *chip)
+{
+ int err;
+
+ err = mv88e6xxx_g1_atu_flush(chip, 0, true);
+ if (err)
+ return err;
+
+ err = mv88e6xxx_g1_atu_set_learn2all(chip, true);
+ if (err)
+ return err;
+
+ return mv88e6xxx_g1_atu_set_age_time(chip, 300000);
+}
+
+static int mv88e6xxx_pvt_map(struct mv88e6xxx_chip *chip, int dev, int port)
+{
+ u16 pvlan = 0;
+
+ if (!mv88e6xxx_has_pvt(chip))
+ return -EOPNOTSUPP;
+
+ /* Skip the local source device, which uses in-chip port VLAN */
+ if (dev != chip->ds->index)
+ pvlan = mv88e6xxx_port_vlan(chip, dev, port);
+
+ return mv88e6xxx_g2_pvt_write(chip, dev, port, pvlan);
+}
+
+static int mv88e6xxx_pvt_setup(struct mv88e6xxx_chip *chip)
+{
+ int dev, port;
+ int err;
+
+ if (!mv88e6xxx_has_pvt(chip))
+ return 0;
+
+ /* Clear 5 Bit Port for usage with Marvell Link Street devices:
+ * use 4 bits for the Src_Port/Src_Trunk and 5 bits for the Src_Dev.
+ */
+ err = mv88e6xxx_g2_misc_4_bit_port(chip);
+ if (err)
+ return err;
+
+ for (dev = 0; dev < MV88E6XXX_MAX_PVT_SWITCHES; ++dev) {
+ for (port = 0; port < MV88E6XXX_MAX_PVT_PORTS; ++port) {
+ err = mv88e6xxx_pvt_map(chip, dev, port);
+ if (err)
+ return err;
+ }
+ }
+
+ return 0;
+}
+
static void mv88e6xxx_port_fast_age(struct dsa_switch *ds, int port)
{
struct mv88e6xxx_chip *chip = ds->priv;
int err;
mutex_lock(&chip->reg_lock);
- err = _mv88e6xxx_atu_remove(chip, 0, port, false);
+ err = mv88e6xxx_g1_atu_remove(chip, 0, port, false);
mutex_unlock(&chip->reg_lock);
if (err)
@@ -1662,7 +1609,7 @@ static int _mv88e6xxx_stu_loadpurge(struct mv88e6xxx_chip *chip,
return _mv88e6xxx_vtu_cmd(chip, GLOBAL_VTU_OP_STU_LOAD_PURGE);
}
-static int _mv88e6xxx_fid_new(struct mv88e6xxx_chip *chip, u16 *fid)
+static int mv88e6xxx_atu_new(struct mv88e6xxx_chip *chip, u16 *fid)
{
DECLARE_BITMAP(fid_bitmap, MV88E6XXX_N_FID);
struct mv88e6xxx_vtu_entry vlan;
@@ -1703,7 +1650,7 @@ static int _mv88e6xxx_fid_new(struct mv88e6xxx_chip *chip, u16 *fid)
return -ENOSPC;
/* Clear the database */
- return _mv88e6xxx_atu_flush(chip, *fid, true);
+ return mv88e6xxx_g1_atu_flush(chip, *fid, true);
}
static int _mv88e6xxx_vtu_new(struct mv88e6xxx_chip *chip, u16 vid,
@@ -1716,7 +1663,7 @@ static int _mv88e6xxx_vtu_new(struct mv88e6xxx_chip *chip, u16 vid,
};
int i, err;
- err = _mv88e6xxx_fid_new(chip, &vlan.fid);
+ err = mv88e6xxx_atu_new(chip, &vlan.fid);
if (err)
return err;
@@ -1964,7 +1911,7 @@ static int _mv88e6xxx_port_vlan_del(struct mv88e6xxx_chip *chip,
if (err)
return err;
- return _mv88e6xxx_atu_remove(chip, vlan.fid, port, false);
+ return mv88e6xxx_g1_atu_remove(chip, vlan.fid, port, false);
}
static int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port,
@@ -2001,96 +1948,6 @@ static int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port,
return err;
}
-static int _mv88e6xxx_atu_mac_write(struct mv88e6xxx_chip *chip,
- const unsigned char *addr)
-{
- int i, err;
-
- for (i = 0; i < 3; i++) {
- err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_MAC_01 + i,
- (addr[i * 2] << 8) | addr[i * 2 + 1]);
- if (err)
- return err;
- }
-
- return 0;
-}
-
-static int _mv88e6xxx_atu_mac_read(struct mv88e6xxx_chip *chip,
- unsigned char *addr)
-{
- u16 val;
- int i, err;
-
- for (i = 0; i < 3; i++) {
- err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_MAC_01 + i, &val);
- if (err)
- return err;
-
- addr[i * 2] = val >> 8;
- addr[i * 2 + 1] = val & 0xff;
- }
-
- return 0;
-}
-
-static int _mv88e6xxx_atu_load(struct mv88e6xxx_chip *chip,
- struct mv88e6xxx_atu_entry *entry)
-{
- int ret;
-
- ret = _mv88e6xxx_atu_wait(chip);
- if (ret < 0)
- return ret;
-
- ret = _mv88e6xxx_atu_mac_write(chip, entry->mac);
- if (ret < 0)
- return ret;
-
- ret = _mv88e6xxx_atu_data_write(chip, entry);
- if (ret < 0)
- return ret;
-
- return _mv88e6xxx_atu_cmd(chip, entry->fid, GLOBAL_ATU_OP_LOAD_DB);
-}
-
-static int _mv88e6xxx_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid,
- struct mv88e6xxx_atu_entry *entry);
-
-static int mv88e6xxx_atu_get(struct mv88e6xxx_chip *chip, int fid,
- const u8 *addr, struct mv88e6xxx_atu_entry *entry)
-{
- struct mv88e6xxx_atu_entry next;
- int err;
-
- memcpy(next.mac, addr, ETH_ALEN);
- eth_addr_dec(next.mac);
-
- err = _mv88e6xxx_atu_mac_write(chip, next.mac);
- if (err)
- return err;
-
- do {
- err = _mv88e6xxx_atu_getnext(chip, fid, &next);
- if (err)
- return err;
-
- if (next.state == GLOBAL_ATU_DATA_STATE_UNUSED)
- break;
-
- if (ether_addr_equal(next.mac, addr)) {
- *entry = next;
- return 0;
- }
- } while (ether_addr_greater(addr, next.mac));
-
- memset(entry, 0, sizeof(*entry));
- entry->fid = fid;
- ether_addr_copy(entry->mac, addr);
-
- return 0;
-}
-
static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
const unsigned char *addr, u16 vid,
u8 state)
@@ -2107,21 +1964,32 @@ static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
if (err)
return err;
- err = mv88e6xxx_atu_get(chip, vlan.fid, addr, &entry);
+ entry.state = GLOBAL_ATU_DATA_STATE_UNUSED;
+ ether_addr_copy(entry.mac, addr);
+ eth_addr_dec(entry.mac);
+
+ err = mv88e6xxx_g1_atu_getnext(chip, vlan.fid, &entry);
if (err)
return err;
+ /* Initialize a fresh ATU entry if it isn't found */
+ if (entry.state == GLOBAL_ATU_DATA_STATE_UNUSED ||
+ !ether_addr_equal(entry.mac, addr)) {
+ memset(&entry, 0, sizeof(entry));
+ ether_addr_copy(entry.mac, addr);
+ }
+
/* Purge the ATU entry only if no port is using it anymore */
if (state == GLOBAL_ATU_DATA_STATE_UNUSED) {
- entry.portv_trunkid &= ~BIT(port);
- if (!entry.portv_trunkid)
+ entry.portvec &= ~BIT(port);
+ if (!entry.portvec)
entry.state = GLOBAL_ATU_DATA_STATE_UNUSED;
} else {
- entry.portv_trunkid |= BIT(port);
+ entry.portvec |= BIT(port);
entry.state = state;
}
- return _mv88e6xxx_atu_load(chip, &entry);
+ return mv88e6xxx_g1_atu_loadpurge(chip, vlan.fid, &entry);
}
static int mv88e6xxx_port_fdb_prepare(struct dsa_switch *ds, int port,
@@ -2161,75 +2029,26 @@ static int mv88e6xxx_port_fdb_del(struct dsa_switch *ds, int port,
return err;
}
-static int _mv88e6xxx_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid,
- struct mv88e6xxx_atu_entry *entry)
-{
- struct mv88e6xxx_atu_entry next = { 0 };
- u16 val;
- int err;
-
- next.fid = fid;
-
- err = _mv88e6xxx_atu_wait(chip);
- if (err)
- return err;
-
- err = _mv88e6xxx_atu_cmd(chip, fid, GLOBAL_ATU_OP_GET_NEXT_DB);
- if (err)
- return err;
-
- err = _mv88e6xxx_atu_mac_read(chip, next.mac);
- if (err)
- return err;
-
- err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_DATA, &val);
- if (err)
- return err;
-
- next.state = val & GLOBAL_ATU_DATA_STATE_MASK;
- if (next.state != GLOBAL_ATU_DATA_STATE_UNUSED) {
- unsigned int mask, shift;
-
- if (val & GLOBAL_ATU_DATA_TRUNK) {
- next.trunk = true;
- mask = GLOBAL_ATU_DATA_TRUNK_ID_MASK;
- shift = GLOBAL_ATU_DATA_TRUNK_ID_SHIFT;
- } else {
- next.trunk = false;
- mask = GLOBAL_ATU_DATA_PORT_VECTOR_MASK;
- shift = GLOBAL_ATU_DATA_PORT_VECTOR_SHIFT;
- }
-
- next.portv_trunkid = (val & mask) >> shift;
- }
-
- *entry = next;
- return 0;
-}
-
static int mv88e6xxx_port_db_dump_fid(struct mv88e6xxx_chip *chip,
u16 fid, u16 vid, int port,
struct switchdev_obj *obj,
int (*cb)(struct switchdev_obj *obj))
{
- struct mv88e6xxx_atu_entry addr = {
- .mac = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff },
- };
+ struct mv88e6xxx_atu_entry addr;
int err;
- err = _mv88e6xxx_atu_mac_write(chip, addr.mac);
- if (err)
- return err;
+ addr.state = GLOBAL_ATU_DATA_STATE_UNUSED;
+ eth_broadcast_addr(addr.mac);
do {
- err = _mv88e6xxx_atu_getnext(chip, fid, &addr);
+ err = mv88e6xxx_g1_atu_getnext(chip, fid, &addr);
if (err)
return err;
if (addr.state == GLOBAL_ATU_DATA_STATE_UNUSED)
break;
- if (addr.trunk || (addr.portv_trunkid & BIT(port)) == 0)
+ if (addr.trunk || (addr.portvec & BIT(port)) == 0)
continue;
if (obj->id == SWITCHDEV_OBJ_ID_PORT_FDB) {
@@ -2321,23 +2140,52 @@ static int mv88e6xxx_port_fdb_dump(struct dsa_switch *ds, int port,
return err;
}
+static int mv88e6xxx_bridge_map(struct mv88e6xxx_chip *chip,
+ struct net_device *br)
+{
+ struct dsa_switch *ds;
+ int port;
+ int dev;
+ int err;
+
+ /* Remap the Port VLAN of each local bridge group member */
+ for (port = 0; port < mv88e6xxx_num_ports(chip); ++port) {
+ if (chip->ds->ports[port].bridge_dev == br) {
+ err = mv88e6xxx_port_vlan_map(chip, port);
+ if (err)
+ return err;
+ }
+ }
+
+ if (!mv88e6xxx_has_pvt(chip))
+ return 0;
+
+ /* Remap the Port VLAN of each cross-chip bridge group member */
+ for (dev = 0; dev < DSA_MAX_SWITCHES; ++dev) {
+ ds = chip->ds->dst->ds[dev];
+ if (!ds)
+ break;
+
+ for (port = 0; port < ds->num_ports; ++port) {
+ if (ds->ports[port].bridge_dev == br) {
+ err = mv88e6xxx_pvt_map(chip, dev, port);
+ if (err)
+ return err;
+ }
+ }
+ }
+
+ return 0;
+}
+
static int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port,
struct net_device *br)
{
struct mv88e6xxx_chip *chip = ds->priv;
- int i, err = 0;
+ int err;
mutex_lock(&chip->reg_lock);
-
- /* Remap each port's VLANTable */
- for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) {
- if (ds->ports[i].bridge_dev == br) {
- err = _mv88e6xxx_port_based_vlan_map(chip, i);
- if (err)
- break;
- }
- }
-
+ err = mv88e6xxx_bridge_map(chip, br);
mutex_unlock(&chip->reg_lock);
return err;
@@ -2347,17 +2195,41 @@ static void mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port,
struct net_device *br)
{
struct mv88e6xxx_chip *chip = ds->priv;
- int i;
mutex_lock(&chip->reg_lock);
+ if (mv88e6xxx_bridge_map(chip, br) ||
+ mv88e6xxx_port_vlan_map(chip, port))
+ dev_err(ds->dev, "failed to remap in-chip Port VLAN\n");
+ mutex_unlock(&chip->reg_lock);
+}
- /* Remap each port's VLANTable */
- for (i = 0; i < mv88e6xxx_num_ports(chip); ++i)
- if (i == port || ds->ports[i].bridge_dev == br)
- if (_mv88e6xxx_port_based_vlan_map(chip, i))
- netdev_warn(ds->ports[i].netdev,
- "failed to remap\n");
+static int mv88e6xxx_crosschip_bridge_join(struct dsa_switch *ds, int dev,
+ int port, struct net_device *br)
+{
+ struct mv88e6xxx_chip *chip = ds->priv;
+ int err;
+ if (!mv88e6xxx_has_pvt(chip))
+ return 0;
+
+ mutex_lock(&chip->reg_lock);
+ err = mv88e6xxx_pvt_map(chip, dev, port);
+ mutex_unlock(&chip->reg_lock);
+
+ return err;
+}
+
+static void mv88e6xxx_crosschip_bridge_leave(struct dsa_switch *ds, int dev,
+ int port, struct net_device *br)
+{
+ struct mv88e6xxx_chip *chip = ds->priv;
+
+ if (!mv88e6xxx_has_pvt(chip))
+ return;
+
+ mutex_lock(&chip->reg_lock);
+ if (mv88e6xxx_pvt_map(chip, dev, port))
+ dev_err(ds->dev, "failed to remap cross-chip Port VLAN\n");
mutex_unlock(&chip->reg_lock);
}
@@ -2433,70 +2305,85 @@ static int mv88e6xxx_serdes_power_on(struct mv88e6xxx_chip *chip)
return err;
}
-static int mv88e6xxx_setup_port_dsa(struct mv88e6xxx_chip *chip, int port,
- int upstream_port)
+static int mv88e6xxx_set_port_mode(struct mv88e6xxx_chip *chip, int port,
+ enum mv88e6xxx_frame_mode frame, u16 egress,
+ u16 etype)
{
int err;
- err = chip->info->ops->port_set_frame_mode(
- chip, port, MV88E6XXX_FRAME_MODE_DSA);
+ if (!chip->info->ops->port_set_frame_mode)
+ return -EOPNOTSUPP;
+
+ err = mv88e6xxx_port_set_egress_mode(chip, port, egress);
if (err)
return err;
- return chip->info->ops->port_set_egress_unknowns(
- chip, port, port == upstream_port);
+ err = chip->info->ops->port_set_frame_mode(chip, port, frame);
+ if (err)
+ return err;
+
+ if (chip->info->ops->port_set_ether_type)
+ return chip->info->ops->port_set_ether_type(chip, port, etype);
+
+ return 0;
}
-static int mv88e6xxx_setup_port_cpu(struct mv88e6xxx_chip *chip, int port)
+static int mv88e6xxx_set_port_mode_normal(struct mv88e6xxx_chip *chip, int port)
{
- int err;
-
- switch (chip->info->tag_protocol) {
- case DSA_TAG_PROTO_EDSA:
- err = chip->info->ops->port_set_frame_mode(
- chip, port, MV88E6XXX_FRAME_MODE_ETHERTYPE);
- if (err)
- return err;
-
- err = mv88e6xxx_port_set_egress_mode(
- chip, port, PORT_CONTROL_EGRESS_ADD_TAG);
- if (err)
- return err;
-
- if (chip->info->ops->port_set_ether_type)
- err = chip->info->ops->port_set_ether_type(
- chip, port, ETH_P_EDSA);
- break;
-
- case DSA_TAG_PROTO_DSA:
- err = chip->info->ops->port_set_frame_mode(
- chip, port, MV88E6XXX_FRAME_MODE_DSA);
- if (err)
- return err;
-
- err = mv88e6xxx_port_set_egress_mode(
- chip, port, PORT_CONTROL_EGRESS_UNMODIFIED);
- break;
- default:
- err = -EINVAL;
- }
-
- if (err)
- return err;
-
- return chip->info->ops->port_set_egress_unknowns(chip, port, true);
+ return mv88e6xxx_set_port_mode(chip, port, MV88E6XXX_FRAME_MODE_NORMAL,
+ PORT_CONTROL_EGRESS_UNMODIFIED,
+ PORT_ETH_TYPE_DEFAULT);
}
-static int mv88e6xxx_setup_port_normal(struct mv88e6xxx_chip *chip, int port)
+static int mv88e6xxx_set_port_mode_dsa(struct mv88e6xxx_chip *chip, int port)
{
- int err;
+ return mv88e6xxx_set_port_mode(chip, port, MV88E6XXX_FRAME_MODE_DSA,
+ PORT_CONTROL_EGRESS_UNMODIFIED,
+ PORT_ETH_TYPE_DEFAULT);
+}
- err = chip->info->ops->port_set_frame_mode(
- chip, port, MV88E6XXX_FRAME_MODE_NORMAL);
- if (err)
- return err;
+static int mv88e6xxx_set_port_mode_edsa(struct mv88e6xxx_chip *chip, int port)
+{
+ return mv88e6xxx_set_port_mode(chip, port,
+ MV88E6XXX_FRAME_MODE_ETHERTYPE,
+ PORT_CONTROL_EGRESS_ADD_TAG, ETH_P_EDSA);
+}
- return chip->info->ops->port_set_egress_unknowns(chip, port, false);
+static int mv88e6xxx_setup_port_mode(struct mv88e6xxx_chip *chip, int port)
+{
+ if (dsa_is_dsa_port(chip->ds, port))
+ return mv88e6xxx_set_port_mode_dsa(chip, port);
+
+ if (dsa_is_normal_port(chip->ds, port))
+ return mv88e6xxx_set_port_mode_normal(chip, port);
+
+ /* Setup CPU port mode depending on its supported tag format */
+ if (chip->info->tag_protocol == DSA_TAG_PROTO_DSA)
+ return mv88e6xxx_set_port_mode_dsa(chip, port);
+
+ if (chip->info->tag_protocol == DSA_TAG_PROTO_EDSA)
+ return mv88e6xxx_set_port_mode_edsa(chip, port);
+
+ return -EINVAL;
+}
+
+static int mv88e6xxx_setup_message_port(struct mv88e6xxx_chip *chip, int port)
+{
+ bool message = dsa_is_dsa_port(chip->ds, port);
+
+ return mv88e6xxx_port_set_message_port(chip, port, message);
+}
+
+static int mv88e6xxx_setup_egress_floods(struct mv88e6xxx_chip *chip, int port)
+{
+ bool flood = port == dsa_upstream_port(chip->ds);
+
+ /* Upstream ports flood frames with unknown unicast or multicast DA */
+ if (chip->info->ops->port_set_egress_floods)
+ return chip->info->ops->port_set_egress_floods(chip, port,
+ flood, flood);
+
+ return 0;
}
static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
@@ -2541,14 +2428,11 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
if (err)
return err;
- if (dsa_is_cpu_port(ds, port)) {
- err = mv88e6xxx_setup_port_cpu(chip, port);
- } else if (dsa_is_dsa_port(ds, port)) {
- err = mv88e6xxx_setup_port_dsa(chip, port,
- dsa_upstream_port(ds));
- } else {
- err = mv88e6xxx_setup_port_normal(chip, port);
- }
+ err = mv88e6xxx_setup_port_mode(chip, port);
+ if (err)
+ return err;
+
+ err = mv88e6xxx_setup_egress_floods(chip, port);
if (err)
return err;
@@ -2623,20 +2507,14 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
return err;
}
- if (mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip) ||
- mv88e6xxx_6165_family(chip) || mv88e6xxx_6097_family(chip) ||
- mv88e6xxx_6320_family(chip) || mv88e6xxx_6341_family(chip)) {
- /* Port ATU control: disable limiting the number of
- * address database entries that this port is allowed
- * to use.
- */
- err = mv88e6xxx_port_write(chip, port, PORT_ATU_CONTROL,
- 0x0000);
- /* Priority Override: disable DA, SA and VTU priority
- * override.
- */
- err = mv88e6xxx_port_write(chip, port, PORT_PRI_OVERRIDE,
- 0x0000);
+ if (chip->info->ops->port_disable_learn_limit) {
+ err = chip->info->ops->port_disable_learn_limit(chip, port);
+ if (err)
+ return err;
+ }
+
+ if (chip->info->ops->port_disable_pri_override) {
+ err = chip->info->ops->port_disable_pri_override(chip, port);
if (err)
return err;
}
@@ -2653,10 +2531,7 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
return err;
}
- /* Port Control 1: disable trunking, disable sending
- * learning messages to this port.
- */
- err = mv88e6xxx_port_write(chip, port, PORT_CONTROL_1, 0x0000);
+ err = mv88e6xxx_setup_message_port(chip, port);
if (err)
return err;
@@ -2668,7 +2543,7 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
if (err)
return err;
- err = _mv88e6xxx_port_based_vlan_map(chip, port);
+ err = mv88e6xxx_port_vlan_map(chip, port);
if (err)
return err;
@@ -2697,33 +2572,6 @@ static int mv88e6xxx_g1_set_switch_mac(struct mv88e6xxx_chip *chip, u8 *addr)
return 0;
}
-static int mv88e6xxx_g1_set_age_time(struct mv88e6xxx_chip *chip,
- unsigned int msecs)
-{
- const unsigned int coeff = chip->info->age_time_coeff;
- const unsigned int min = 0x01 * coeff;
- const unsigned int max = 0xff * coeff;
- u8 age_time;
- u16 val;
- int err;
-
- if (msecs < min || msecs > max)
- return -ERANGE;
-
- /* Round to nearest multiple of coeff */
- age_time = (msecs + coeff / 2) / coeff;
-
- err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val);
- if (err)
- return err;
-
- /* AgeTime is 11:4 bits */
- val &= ~0xff0;
- val |= age_time << 4;
-
- return mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, val);
-}
-
static int mv88e6xxx_set_ageing_time(struct dsa_switch *ds,
unsigned int ageing_time)
{
@@ -2731,7 +2579,7 @@ static int mv88e6xxx_set_ageing_time(struct dsa_switch *ds,
int err;
mutex_lock(&chip->reg_lock);
- err = mv88e6xxx_g1_set_age_time(chip, ageing_time);
+ err = mv88e6xxx_g1_atu_set_age_time(chip, ageing_time);
mutex_unlock(&chip->reg_lock);
return err;
@@ -2774,24 +2622,6 @@ static int mv88e6xxx_g1_setup(struct mv88e6xxx_chip *chip)
if (err < 0)
return err;
- /* Set the default address aging time to 5 minutes, and
- * enable address learn messages to be sent to all message
- * ports.
- */
- err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL,
- GLOBAL_ATU_CONTROL_LEARN2ALL);
- if (err)
- return err;
-
- err = mv88e6xxx_g1_set_age_time(chip, 300000);
- if (err)
- return err;
-
- /* Clear all ATU entries */
- err = _mv88e6xxx_atu_flush(chip, 0, true);
- if (err)
- return err;
-
/* Configure the IP ToS mapping registers. */
err = mv88e6xxx_g1_write(chip, GLOBAL_IP_PRI_0, 0x0000);
if (err)
@@ -2872,6 +2702,14 @@ static int mv88e6xxx_setup(struct dsa_switch *ds)
goto unlock;
}
+ err = mv88e6xxx_pvt_setup(chip);
+ if (err)
+ goto unlock;
+
+ err = mv88e6xxx_atu_setup(chip);
+ if (err)
+ goto unlock;
+
/* Some generations have the configuration of sending reserved
* management frames to the CPU in global2, others in
* global1. Hence it does not fit the two setup functions
@@ -3101,10 +2939,12 @@ static const struct mv88e6xxx_ops mv88e6085_ops = {
.port_set_speed = mv88e6185_port_set_speed,
.port_tag_remap = mv88e6095_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6352_port_set_egress_floods,
.port_set_ether_type = mv88e6351_port_set_ether_type,
.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
.port_pause_config = mv88e6097_port_pause_config,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
.stats_get_sset_count = mv88e6095_stats_get_sset_count,
.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3127,7 +2967,7 @@ static const struct mv88e6xxx_ops mv88e6095_ops = {
.port_set_duplex = mv88e6xxx_port_set_duplex,
.port_set_speed = mv88e6185_port_set_speed,
.port_set_frame_mode = mv88e6085_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6095_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6185_port_set_egress_floods,
.port_set_upstream_port = mv88e6095_port_set_upstream_port,
.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3149,11 +2989,13 @@ static const struct mv88e6xxx_ops mv88e6097_ops = {
.port_set_speed = mv88e6185_port_set_speed,
.port_tag_remap = mv88e6095_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6352_port_set_egress_floods,
.port_set_ether_type = mv88e6351_port_set_ether_type,
.port_jumbo_config = mv88e6165_port_jumbo_config,
.port_egress_rate_limiting = mv88e6095_port_egress_rate_limiting,
.port_pause_config = mv88e6097_port_pause_config,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
.stats_get_sset_count = mv88e6095_stats_get_sset_count,
.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3174,7 +3016,9 @@ static const struct mv88e6xxx_ops mv88e6123_ops = {
.port_set_duplex = mv88e6xxx_port_set_duplex,
.port_set_speed = mv88e6185_port_set_speed,
.port_set_frame_mode = mv88e6085_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6085_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6352_port_set_egress_floods,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
.stats_get_sset_count = mv88e6095_stats_get_sset_count,
.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3196,7 +3040,7 @@ static const struct mv88e6xxx_ops mv88e6131_ops = {
.port_set_speed = mv88e6185_port_set_speed,
.port_tag_remap = mv88e6095_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6095_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6185_port_set_egress_floods,
.port_set_ether_type = mv88e6351_port_set_ether_type,
.port_set_upstream_port = mv88e6095_port_set_upstream_port,
.port_jumbo_config = mv88e6165_port_jumbo_config,
@@ -3215,6 +3059,37 @@ static const struct mv88e6xxx_ops mv88e6131_ops = {
.reset = mv88e6185_g1_reset,
};
+static const struct mv88e6xxx_ops mv88e6141_ops = {
+ /* MV88E6XXX_FAMILY_6341 */
+ .get_eeprom = mv88e6xxx_g2_get_eeprom8,
+ .set_eeprom = mv88e6xxx_g2_set_eeprom8,
+ .set_switch_mac = mv88e6xxx_g2_set_switch_mac,
+ .phy_read = mv88e6xxx_g2_smi_phy_read,
+ .phy_write = mv88e6xxx_g2_smi_phy_write,
+ .port_set_link = mv88e6xxx_port_set_link,
+ .port_set_duplex = mv88e6xxx_port_set_duplex,
+ .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
+ .port_set_speed = mv88e6390_port_set_speed,
+ .port_tag_remap = mv88e6095_port_tag_remap,
+ .port_set_frame_mode = mv88e6351_port_set_frame_mode,
+ .port_set_egress_floods = mv88e6352_port_set_egress_floods,
+ .port_set_ether_type = mv88e6351_port_set_ether_type,
+ .port_jumbo_config = mv88e6165_port_jumbo_config,
+ .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
+ .port_pause_config = mv88e6097_port_pause_config,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+ .stats_snapshot = mv88e6390_g1_stats_snapshot,
+ .stats_get_sset_count = mv88e6320_stats_get_sset_count,
+ .stats_get_strings = mv88e6320_stats_get_strings,
+ .stats_get_stats = mv88e6390_stats_get_stats,
+ .g1_set_cpu_port = mv88e6390_g1_set_cpu_port,
+ .g1_set_egress_port = mv88e6390_g1_set_egress_port,
+ .watchdog_ops = &mv88e6390_watchdog_ops,
+ .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
+ .reset = mv88e6352_g1_reset,
+};
+
static const struct mv88e6xxx_ops mv88e6161_ops = {
/* MV88E6XXX_FAMILY_6165 */
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
@@ -3225,11 +3100,13 @@ static const struct mv88e6xxx_ops mv88e6161_ops = {
.port_set_speed = mv88e6185_port_set_speed,
.port_tag_remap = mv88e6095_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6352_port_set_egress_floods,
.port_set_ether_type = mv88e6351_port_set_ether_type,
.port_jumbo_config = mv88e6165_port_jumbo_config,
.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
.port_pause_config = mv88e6097_port_pause_config,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
.stats_get_sset_count = mv88e6095_stats_get_sset_count,
.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3249,6 +3126,8 @@ static const struct mv88e6xxx_ops mv88e6165_ops = {
.port_set_link = mv88e6xxx_port_set_link,
.port_set_duplex = mv88e6xxx_port_set_duplex,
.port_set_speed = mv88e6185_port_set_speed,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
.stats_get_sset_count = mv88e6095_stats_get_sset_count,
.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3271,11 +3150,13 @@ static const struct mv88e6xxx_ops mv88e6171_ops = {
.port_set_speed = mv88e6185_port_set_speed,
.port_tag_remap = mv88e6095_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6352_port_set_egress_floods,
.port_set_ether_type = mv88e6351_port_set_ether_type,
.port_jumbo_config = mv88e6165_port_jumbo_config,
.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
.port_pause_config = mv88e6097_port_pause_config,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
.stats_snapshot = mv88e6320_g1_stats_snapshot,
.stats_get_sset_count = mv88e6095_stats_get_sset_count,
.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3300,11 +3181,13 @@ static const struct mv88e6xxx_ops mv88e6172_ops = {
.port_set_speed = mv88e6352_port_set_speed,
.port_tag_remap = mv88e6095_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6352_port_set_egress_floods,
.port_set_ether_type = mv88e6351_port_set_ether_type,
.port_jumbo_config = mv88e6165_port_jumbo_config,
.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
.port_pause_config = mv88e6097_port_pause_config,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
.stats_snapshot = mv88e6320_g1_stats_snapshot,
.stats_get_sset_count = mv88e6095_stats_get_sset_count,
.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3327,11 +3210,13 @@ static const struct mv88e6xxx_ops mv88e6175_ops = {
.port_set_speed = mv88e6185_port_set_speed,
.port_tag_remap = mv88e6095_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6352_port_set_egress_floods,
.port_set_ether_type = mv88e6351_port_set_ether_type,
.port_jumbo_config = mv88e6165_port_jumbo_config,
.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
.port_pause_config = mv88e6097_port_pause_config,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
.stats_snapshot = mv88e6320_g1_stats_snapshot,
.stats_get_sset_count = mv88e6095_stats_get_sset_count,
.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3356,11 +3241,13 @@ static const struct mv88e6xxx_ops mv88e6176_ops = {
.port_set_speed = mv88e6352_port_set_speed,
.port_tag_remap = mv88e6095_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6352_port_set_egress_floods,
.port_set_ether_type = mv88e6351_port_set_ether_type,
.port_jumbo_config = mv88e6165_port_jumbo_config,
.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
.port_pause_config = mv88e6097_port_pause_config,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
.stats_snapshot = mv88e6320_g1_stats_snapshot,
.stats_get_sset_count = mv88e6095_stats_get_sset_count,
.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3381,7 +3268,7 @@ static const struct mv88e6xxx_ops mv88e6185_ops = {
.port_set_duplex = mv88e6xxx_port_set_duplex,
.port_set_speed = mv88e6185_port_set_speed,
.port_set_frame_mode = mv88e6085_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6095_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6185_port_set_egress_floods,
.port_egress_rate_limiting = mv88e6095_port_egress_rate_limiting,
.port_set_upstream_port = mv88e6095_port_set_upstream_port,
.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
@@ -3410,9 +3297,11 @@ static const struct mv88e6xxx_ops mv88e6190_ops = {
.port_set_speed = mv88e6390_port_set_speed,
.port_tag_remap = mv88e6390_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6352_port_set_egress_floods,
.port_set_ether_type = mv88e6351_port_set_ether_type,
.port_pause_config = mv88e6390_port_pause_config,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
.stats_snapshot = mv88e6390_g1_stats_snapshot,
.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3438,9 +3327,11 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = {
.port_set_speed = mv88e6390x_port_set_speed,
.port_tag_remap = mv88e6390_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6352_port_set_egress_floods,
.port_set_ether_type = mv88e6351_port_set_ether_type,
.port_pause_config = mv88e6390_port_pause_config,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
.stats_snapshot = mv88e6390_g1_stats_snapshot,
.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3466,9 +3357,11 @@ static const struct mv88e6xxx_ops mv88e6191_ops = {
.port_set_speed = mv88e6390_port_set_speed,
.port_tag_remap = mv88e6390_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6352_port_set_egress_floods,
.port_set_ether_type = mv88e6351_port_set_ether_type,
.port_pause_config = mv88e6390_port_pause_config,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
.stats_snapshot = mv88e6390_g1_stats_snapshot,
.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3494,11 +3387,13 @@ static const struct mv88e6xxx_ops mv88e6240_ops = {
.port_set_speed = mv88e6352_port_set_speed,
.port_tag_remap = mv88e6095_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6352_port_set_egress_floods,
.port_set_ether_type = mv88e6351_port_set_ether_type,
.port_jumbo_config = mv88e6165_port_jumbo_config,
.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
.port_pause_config = mv88e6097_port_pause_config,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
.stats_snapshot = mv88e6320_g1_stats_snapshot,
.stats_get_sset_count = mv88e6095_stats_get_sset_count,
.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3523,10 +3418,12 @@ static const struct mv88e6xxx_ops mv88e6290_ops = {
.port_set_speed = mv88e6390_port_set_speed,
.port_tag_remap = mv88e6390_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6352_port_set_egress_floods,
.port_set_ether_type = mv88e6351_port_set_ether_type,
.port_pause_config = mv88e6390_port_pause_config,
.port_set_cmode = mv88e6390x_port_set_cmode,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
.stats_snapshot = mv88e6390_g1_stats_snapshot,
.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3551,11 +3448,13 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
.port_set_speed = mv88e6185_port_set_speed,
.port_tag_remap = mv88e6095_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6352_port_set_egress_floods,
.port_set_ether_type = mv88e6351_port_set_ether_type,
.port_jumbo_config = mv88e6165_port_jumbo_config,
.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
.port_pause_config = mv88e6097_port_pause_config,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
.stats_snapshot = mv88e6320_g1_stats_snapshot,
.stats_get_sset_count = mv88e6320_stats_get_sset_count,
.stats_get_strings = mv88e6320_stats_get_strings,
@@ -3578,11 +3477,13 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
.port_set_speed = mv88e6185_port_set_speed,
.port_tag_remap = mv88e6095_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6352_port_set_egress_floods,
.port_set_ether_type = mv88e6351_port_set_ether_type,
.port_jumbo_config = mv88e6165_port_jumbo_config,
.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
.port_pause_config = mv88e6097_port_pause_config,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
.stats_snapshot = mv88e6320_g1_stats_snapshot,
.stats_get_sset_count = mv88e6320_stats_get_sset_count,
.stats_get_strings = mv88e6320_stats_get_strings,
@@ -3592,6 +3493,37 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
.reset = mv88e6352_g1_reset,
};
+static const struct mv88e6xxx_ops mv88e6341_ops = {
+ /* MV88E6XXX_FAMILY_6341 */
+ .get_eeprom = mv88e6xxx_g2_get_eeprom8,
+ .set_eeprom = mv88e6xxx_g2_set_eeprom8,
+ .set_switch_mac = mv88e6xxx_g2_set_switch_mac,
+ .phy_read = mv88e6xxx_g2_smi_phy_read,
+ .phy_write = mv88e6xxx_g2_smi_phy_write,
+ .port_set_link = mv88e6xxx_port_set_link,
+ .port_set_duplex = mv88e6xxx_port_set_duplex,
+ .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
+ .port_set_speed = mv88e6390_port_set_speed,
+ .port_tag_remap = mv88e6095_port_tag_remap,
+ .port_set_frame_mode = mv88e6351_port_set_frame_mode,
+ .port_set_egress_floods = mv88e6352_port_set_egress_floods,
+ .port_set_ether_type = mv88e6351_port_set_ether_type,
+ .port_jumbo_config = mv88e6165_port_jumbo_config,
+ .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
+ .port_pause_config = mv88e6097_port_pause_config,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+ .stats_snapshot = mv88e6390_g1_stats_snapshot,
+ .stats_get_sset_count = mv88e6320_stats_get_sset_count,
+ .stats_get_strings = mv88e6320_stats_get_strings,
+ .stats_get_stats = mv88e6390_stats_get_stats,
+ .g1_set_cpu_port = mv88e6390_g1_set_cpu_port,
+ .g1_set_egress_port = mv88e6390_g1_set_egress_port,
+ .watchdog_ops = &mv88e6390_watchdog_ops,
+ .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
+ .reset = mv88e6352_g1_reset,
+};
+
static const struct mv88e6xxx_ops mv88e6350_ops = {
/* MV88E6XXX_FAMILY_6351 */
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
@@ -3603,11 +3535,13 @@ static const struct mv88e6xxx_ops mv88e6350_ops = {
.port_set_speed = mv88e6185_port_set_speed,
.port_tag_remap = mv88e6095_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6352_port_set_egress_floods,
.port_set_ether_type = mv88e6351_port_set_ether_type,
.port_jumbo_config = mv88e6165_port_jumbo_config,
.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
.port_pause_config = mv88e6097_port_pause_config,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
.stats_snapshot = mv88e6320_g1_stats_snapshot,
.stats_get_sset_count = mv88e6095_stats_get_sset_count,
.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3630,11 +3564,13 @@ static const struct mv88e6xxx_ops mv88e6351_ops = {
.port_set_speed = mv88e6185_port_set_speed,
.port_tag_remap = mv88e6095_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6352_port_set_egress_floods,
.port_set_ether_type = mv88e6351_port_set_ether_type,
.port_jumbo_config = mv88e6165_port_jumbo_config,
.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
.port_pause_config = mv88e6097_port_pause_config,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
.stats_snapshot = mv88e6320_g1_stats_snapshot,
.stats_get_sset_count = mv88e6095_stats_get_sset_count,
.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3659,11 +3595,13 @@ static const struct mv88e6xxx_ops mv88e6352_ops = {
.port_set_speed = mv88e6352_port_set_speed,
.port_tag_remap = mv88e6095_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6352_port_set_egress_floods,
.port_set_ether_type = mv88e6351_port_set_ether_type,
.port_jumbo_config = mv88e6165_port_jumbo_config,
.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
.port_pause_config = mv88e6097_port_pause_config,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
.stats_snapshot = mv88e6320_g1_stats_snapshot,
.stats_get_sset_count = mv88e6095_stats_get_sset_count,
.stats_get_strings = mv88e6095_stats_get_strings,
@@ -3675,64 +3613,6 @@ static const struct mv88e6xxx_ops mv88e6352_ops = {
.reset = mv88e6352_g1_reset,
};
-static const struct mv88e6xxx_ops mv88e6141_ops = {
- /* MV88E6XXX_FAMILY_6341 */
- .get_eeprom = mv88e6xxx_g2_get_eeprom8,
- .set_eeprom = mv88e6xxx_g2_set_eeprom8,
- .set_switch_mac = mv88e6xxx_g2_set_switch_mac,
- .phy_read = mv88e6xxx_g2_smi_phy_read,
- .phy_write = mv88e6xxx_g2_smi_phy_write,
- .port_set_link = mv88e6xxx_port_set_link,
- .port_set_duplex = mv88e6xxx_port_set_duplex,
- .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
- .port_set_speed = mv88e6390_port_set_speed,
- .port_tag_remap = mv88e6095_port_tag_remap,
- .port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
- .port_set_ether_type = mv88e6351_port_set_ether_type,
- .port_jumbo_config = mv88e6165_port_jumbo_config,
- .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
- .port_pause_config = mv88e6097_port_pause_config,
- .stats_snapshot = mv88e6390_g1_stats_snapshot,
- .stats_get_sset_count = mv88e6320_stats_get_sset_count,
- .stats_get_strings = mv88e6320_stats_get_strings,
- .stats_get_stats = mv88e6390_stats_get_stats,
- .g1_set_cpu_port = mv88e6390_g1_set_cpu_port,
- .g1_set_egress_port = mv88e6390_g1_set_egress_port,
- .watchdog_ops = &mv88e6390_watchdog_ops,
- .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
- .reset = mv88e6352_g1_reset,
-};
-
-static const struct mv88e6xxx_ops mv88e6341_ops = {
- /* MV88E6XXX_FAMILY_6341 */
- .get_eeprom = mv88e6xxx_g2_get_eeprom8,
- .set_eeprom = mv88e6xxx_g2_set_eeprom8,
- .set_switch_mac = mv88e6xxx_g2_set_switch_mac,
- .phy_read = mv88e6xxx_g2_smi_phy_read,
- .phy_write = mv88e6xxx_g2_smi_phy_write,
- .port_set_link = mv88e6xxx_port_set_link,
- .port_set_duplex = mv88e6xxx_port_set_duplex,
- .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
- .port_set_speed = mv88e6390_port_set_speed,
- .port_tag_remap = mv88e6095_port_tag_remap,
- .port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
- .port_set_ether_type = mv88e6351_port_set_ether_type,
- .port_jumbo_config = mv88e6165_port_jumbo_config,
- .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
- .port_pause_config = mv88e6097_port_pause_config,
- .stats_snapshot = mv88e6390_g1_stats_snapshot,
- .stats_get_sset_count = mv88e6320_stats_get_sset_count,
- .stats_get_strings = mv88e6320_stats_get_strings,
- .stats_get_stats = mv88e6390_stats_get_stats,
- .g1_set_cpu_port = mv88e6390_g1_set_cpu_port,
- .g1_set_egress_port = mv88e6390_g1_set_egress_port,
- .watchdog_ops = &mv88e6390_watchdog_ops,
- .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
- .reset = mv88e6352_g1_reset,
-};
-
static const struct mv88e6xxx_ops mv88e6390_ops = {
/* MV88E6XXX_FAMILY_6390 */
.get_eeprom = mv88e6xxx_g2_get_eeprom8,
@@ -3746,12 +3626,14 @@ static const struct mv88e6xxx_ops mv88e6390_ops = {
.port_set_speed = mv88e6390_port_set_speed,
.port_tag_remap = mv88e6390_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6352_port_set_egress_floods,
.port_set_ether_type = mv88e6351_port_set_ether_type,
.port_jumbo_config = mv88e6165_port_jumbo_config,
.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
.port_pause_config = mv88e6390_port_pause_config,
.port_set_cmode = mv88e6390x_port_set_cmode,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
.stats_snapshot = mv88e6390_g1_stats_snapshot,
.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3777,11 +3659,13 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
.port_set_speed = mv88e6390x_port_set_speed,
.port_tag_remap = mv88e6390_port_tag_remap,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
+ .port_set_egress_floods = mv88e6352_port_set_egress_floods,
.port_set_ether_type = mv88e6351_port_set_ether_type,
.port_jumbo_config = mv88e6165_port_jumbo_config,
.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
.port_pause_config = mv88e6390_port_pause_config,
+ .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
+ .port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
.stats_snapshot = mv88e6390_g1_stats_snapshot,
.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3794,50 +3678,6 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
.reset = mv88e6352_g1_reset,
};
-static const struct mv88e6xxx_ops mv88e6391_ops = {
- /* MV88E6XXX_FAMILY_6390 */
- .get_eeprom = mv88e6xxx_g2_get_eeprom8,
- .set_eeprom = mv88e6xxx_g2_set_eeprom8,
- .set_switch_mac = mv88e6xxx_g2_set_switch_mac,
- .phy_read = mv88e6xxx_g2_smi_phy_read,
- .phy_write = mv88e6xxx_g2_smi_phy_write,
- .port_set_link = mv88e6xxx_port_set_link,
- .port_set_duplex = mv88e6xxx_port_set_duplex,
- .port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
- .port_set_speed = mv88e6390_port_set_speed,
- .port_tag_remap = mv88e6390_port_tag_remap,
- .port_set_frame_mode = mv88e6351_port_set_frame_mode,
- .port_set_egress_unknowns = mv88e6351_port_set_egress_unknowns,
- .port_set_ether_type = mv88e6351_port_set_ether_type,
- .port_pause_config = mv88e6390_port_pause_config,
- .stats_snapshot = mv88e6390_g1_stats_snapshot,
- .stats_set_histogram = mv88e6390_g1_stats_set_histogram,
- .stats_get_sset_count = mv88e6320_stats_get_sset_count,
- .stats_get_strings = mv88e6320_stats_get_strings,
- .stats_get_stats = mv88e6390_stats_get_stats,
- .g1_set_cpu_port = mv88e6390_g1_set_cpu_port,
- .g1_set_egress_port = mv88e6390_g1_set_egress_port,
- .watchdog_ops = &mv88e6390_watchdog_ops,
- .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
- .reset = mv88e6352_g1_reset,
-};
-
-static int mv88e6xxx_verify_madatory_ops(struct mv88e6xxx_chip *chip,
- const struct mv88e6xxx_ops *ops)
-{
- if (!ops->port_set_frame_mode) {
- dev_err(chip->dev, "Missing port_set_frame_mode");
- return -EINVAL;
- }
-
- if (!ops->port_set_egress_unknowns) {
- dev_err(chip->dev, "Missing port_set_egress_mode");
- return -EINVAL;
- }
-
- return 0;
-}
-
static const struct mv88e6xxx_info mv88e6xxx_table[] = {
[MV88E6085] = {
.prod_num = PORT_SWITCH_ID_PROD_NUM_6085,
@@ -3849,6 +3689,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 15000,
.g1_irqs = 8,
+ .atu_move_port_mask = 0xf,
+ .pvt = true,
.tag_protocol = DSA_TAG_PROTO_DSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6097,
.ops = &mv88e6085_ops,
@@ -3864,6 +3706,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 15000,
.g1_irqs = 8,
+ .atu_move_port_mask = 0xf,
.tag_protocol = DSA_TAG_PROTO_DSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6095,
.ops = &mv88e6095_ops,
@@ -3879,6 +3722,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 15000,
.g1_irqs = 8,
+ .atu_move_port_mask = 0xf,
+ .pvt = true,
.tag_protocol = DSA_TAG_PROTO_EDSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6097,
.ops = &mv88e6097_ops,
@@ -3894,6 +3739,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 15000,
.g1_irqs = 9,
+ .atu_move_port_mask = 0xf,
+ .pvt = true,
.tag_protocol = DSA_TAG_PROTO_DSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6165,
.ops = &mv88e6123_ops,
@@ -3909,11 +3756,28 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 15000,
.g1_irqs = 9,
+ .atu_move_port_mask = 0xf,
.tag_protocol = DSA_TAG_PROTO_DSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6185,
.ops = &mv88e6131_ops,
},
+ [MV88E6141] = {
+ .prod_num = PORT_SWITCH_ID_PROD_NUM_6141,
+ .family = MV88E6XXX_FAMILY_6341,
+ .name = "Marvell 88E6341",
+ .num_databases = 4096,
+ .num_ports = 6,
+ .port_base_addr = 0x10,
+ .global1_addr = 0x1b,
+ .age_time_coeff = 3750,
+ .atu_move_port_mask = 0x1f,
+ .pvt = true,
+ .tag_protocol = DSA_TAG_PROTO_EDSA,
+ .flags = MV88E6XXX_FLAGS_FAMILY_6341,
+ .ops = &mv88e6141_ops,
+ },
+
[MV88E6161] = {
.prod_num = PORT_SWITCH_ID_PROD_NUM_6161,
.family = MV88E6XXX_FAMILY_6165,
@@ -3924,6 +3788,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 15000,
.g1_irqs = 9,
+ .atu_move_port_mask = 0xf,
+ .pvt = true,
.tag_protocol = DSA_TAG_PROTO_DSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6165,
.ops = &mv88e6161_ops,
@@ -3939,6 +3805,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 15000,
.g1_irqs = 9,
+ .atu_move_port_mask = 0xf,
+ .pvt = true,
.tag_protocol = DSA_TAG_PROTO_DSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6165,
.ops = &mv88e6165_ops,
@@ -3954,6 +3822,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 15000,
.g1_irqs = 9,
+ .atu_move_port_mask = 0xf,
+ .pvt = true,
.tag_protocol = DSA_TAG_PROTO_EDSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6351,
.ops = &mv88e6171_ops,
@@ -3969,6 +3839,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 15000,
.g1_irqs = 9,
+ .atu_move_port_mask = 0xf,
+ .pvt = true,
.tag_protocol = DSA_TAG_PROTO_EDSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6352,
.ops = &mv88e6172_ops,
@@ -3984,6 +3856,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 15000,
.g1_irqs = 9,
+ .atu_move_port_mask = 0xf,
+ .pvt = true,
.tag_protocol = DSA_TAG_PROTO_EDSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6351,
.ops = &mv88e6175_ops,
@@ -3999,6 +3873,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 15000,
.g1_irqs = 9,
+ .atu_move_port_mask = 0xf,
+ .pvt = true,
.tag_protocol = DSA_TAG_PROTO_EDSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6352,
.ops = &mv88e6176_ops,
@@ -4014,6 +3890,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 15000,
.g1_irqs = 8,
+ .atu_move_port_mask = 0xf,
.tag_protocol = DSA_TAG_PROTO_EDSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6185,
.ops = &mv88e6185_ops,
@@ -4030,6 +3907,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.tag_protocol = DSA_TAG_PROTO_DSA,
.age_time_coeff = 3750,
.g1_irqs = 9,
+ .pvt = true,
+ .atu_move_port_mask = 0x1f,
.flags = MV88E6XXX_FLAGS_FAMILY_6390,
.ops = &mv88e6190_ops,
},
@@ -4044,6 +3923,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 3750,
.g1_irqs = 9,
+ .atu_move_port_mask = 0x1f,
+ .pvt = true,
.tag_protocol = DSA_TAG_PROTO_DSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6390,
.ops = &mv88e6190x_ops,
@@ -4059,9 +3940,11 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 3750,
.g1_irqs = 9,
+ .atu_move_port_mask = 0x1f,
+ .pvt = true,
.tag_protocol = DSA_TAG_PROTO_DSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6390,
- .ops = &mv88e6391_ops,
+ .ops = &mv88e6191_ops,
},
[MV88E6240] = {
@@ -4074,6 +3957,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 15000,
.g1_irqs = 9,
+ .atu_move_port_mask = 0xf,
+ .pvt = true,
.tag_protocol = DSA_TAG_PROTO_EDSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6352,
.ops = &mv88e6240_ops,
@@ -4089,6 +3974,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 3750,
.g1_irqs = 9,
+ .atu_move_port_mask = 0x1f,
+ .pvt = true,
.tag_protocol = DSA_TAG_PROTO_DSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6390,
.ops = &mv88e6290_ops,
@@ -4104,6 +3991,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 15000,
.g1_irqs = 8,
+ .atu_move_port_mask = 0xf,
+ .pvt = true,
.tag_protocol = DSA_TAG_PROTO_EDSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6320,
.ops = &mv88e6320_ops,
@@ -4119,25 +4008,12 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 15000,
.g1_irqs = 8,
+ .atu_move_port_mask = 0xf,
.tag_protocol = DSA_TAG_PROTO_EDSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6320,
.ops = &mv88e6321_ops,
},
- [MV88E6141] = {
- .prod_num = PORT_SWITCH_ID_PROD_NUM_6141,
- .family = MV88E6XXX_FAMILY_6341,
- .name = "Marvell 88E6341",
- .num_databases = 4096,
- .num_ports = 6,
- .port_base_addr = 0x10,
- .global1_addr = 0x1b,
- .age_time_coeff = 3750,
- .tag_protocol = DSA_TAG_PROTO_EDSA,
- .flags = MV88E6XXX_FLAGS_FAMILY_6341,
- .ops = &mv88e6141_ops,
- },
-
[MV88E6341] = {
.prod_num = PORT_SWITCH_ID_PROD_NUM_6341,
.family = MV88E6XXX_FAMILY_6341,
@@ -4147,6 +4023,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.port_base_addr = 0x10,
.global1_addr = 0x1b,
.age_time_coeff = 3750,
+ .atu_move_port_mask = 0x1f,
+ .pvt = true,
.tag_protocol = DSA_TAG_PROTO_EDSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6341,
.ops = &mv88e6341_ops,
@@ -4162,6 +4040,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 15000,
.g1_irqs = 9,
+ .atu_move_port_mask = 0xf,
+ .pvt = true,
.tag_protocol = DSA_TAG_PROTO_EDSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6351,
.ops = &mv88e6350_ops,
@@ -4177,6 +4057,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 15000,
.g1_irqs = 9,
+ .atu_move_port_mask = 0xf,
+ .pvt = true,
.tag_protocol = DSA_TAG_PROTO_EDSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6351,
.ops = &mv88e6351_ops,
@@ -4192,6 +4074,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 15000,
.g1_irqs = 9,
+ .atu_move_port_mask = 0xf,
+ .pvt = true,
.tag_protocol = DSA_TAG_PROTO_EDSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6352,
.ops = &mv88e6352_ops,
@@ -4206,6 +4090,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 3750,
.g1_irqs = 9,
+ .atu_move_port_mask = 0x1f,
+ .pvt = true,
.tag_protocol = DSA_TAG_PROTO_DSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6390,
.ops = &mv88e6390_ops,
@@ -4220,6 +4106,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.global1_addr = 0x1b,
.age_time_coeff = 3750,
.g1_irqs = 9,
+ .atu_move_port_mask = 0x1f,
+ .pvt = true,
.tag_protocol = DSA_TAG_PROTO_DSA,
.flags = MV88E6XXX_FLAGS_FAMILY_6390,
.ops = &mv88e6390x_ops,
@@ -4455,6 +4343,8 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = {
.port_mdb_add = mv88e6xxx_port_mdb_add,
.port_mdb_del = mv88e6xxx_port_mdb_del,
.port_mdb_dump = mv88e6xxx_port_mdb_dump,
+ .crosschip_bridge_join = mv88e6xxx_crosschip_bridge_join,
+ .crosschip_bridge_leave = mv88e6xxx_crosschip_bridge_leave,
};
static struct dsa_switch_driver mv88e6xxx_switch_drv = {
@@ -4466,12 +4356,14 @@ static int mv88e6xxx_register_switch(struct mv88e6xxx_chip *chip)
struct device *dev = chip->dev;
struct dsa_switch *ds;
- ds = dsa_switch_alloc(dev, DSA_MAX_PORTS);
+ ds = dsa_switch_alloc(dev, mv88e6xxx_num_ports(chip));
if (!ds)
return -ENOMEM;
ds->priv = chip;
ds->ops = &mv88e6xxx_switch_ops;
+ ds->ageing_time_min = chip->info->age_time_coeff;
+ ds->ageing_time_max = chip->info->age_time_coeff * U8_MAX;
dev_set_drvdata(dev, ds);
@@ -4502,10 +4394,6 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
chip->info = compat_info;
- err = mv88e6xxx_verify_madatory_ops(chip, chip->info->ops);
- if (err)
- return err;
-
err = mv88e6xxx_smi_init(chip, mdiodev->bus, mdiodev->addr);
if (err)
return err;
diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c
index 75af86a..3982583 100644
--- a/drivers/net/dsa/mv88e6xxx/global1.c
+++ b/drivers/net/dsa/mv88e6xxx/global1.c
@@ -3,7 +3,8 @@
*
* Copyright (c) 2008 Marvell Semiconductor
*
- * Copyright (c) 2016 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ * Copyright (c) 2016-2017 Savoir-faire Linux Inc.
+ * Vivien Didelot <vivien.didelot@savoirfairelinux.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h
index 1aec738..e30cbe4 100644
--- a/drivers/net/dsa/mv88e6xxx/global1.h
+++ b/drivers/net/dsa/mv88e6xxx/global1.h
@@ -3,7 +3,8 @@
*
* Copyright (c) 2008 Marvell Semiconductor
*
- * Copyright (c) 2016 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ * Copyright (c) 2016-2017 Savoir-faire Linux Inc.
+ * Vivien Didelot <vivien.didelot@savoirfairelinux.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -38,4 +39,15 @@ int mv88e6095_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port);
int mv88e6390_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port);
int mv88e6390_g1_mgmt_rsvd2cpu(struct mv88e6xxx_chip *chip);
+int mv88e6xxx_g1_atu_set_learn2all(struct mv88e6xxx_chip *chip, bool learn2all);
+int mv88e6xxx_g1_atu_set_age_time(struct mv88e6xxx_chip *chip,
+ unsigned int msecs);
+int mv88e6xxx_g1_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid,
+ struct mv88e6xxx_atu_entry *entry);
+int mv88e6xxx_g1_atu_loadpurge(struct mv88e6xxx_chip *chip, u16 fid,
+ struct mv88e6xxx_atu_entry *entry);
+int mv88e6xxx_g1_atu_flush(struct mv88e6xxx_chip *chip, u16 fid, bool all);
+int mv88e6xxx_g1_atu_remove(struct mv88e6xxx_chip *chip, u16 fid, int port,
+ bool all);
+
#endif /* _MV88E6XXX_GLOBAL1_H */
diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c
new file mode 100644
index 0000000..fa7e7db
--- /dev/null
+++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c
@@ -0,0 +1,305 @@
+/*
+ * Marvell 88E6xxx Address Translation Unit (ATU) support
+ *
+ * Copyright (c) 2008 Marvell Semiconductor
+ * Copyright (c) 2017 Savoir-faire Linux, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include "mv88e6xxx.h"
+#include "global1.h"
+
+/* Offset 0x01: ATU FID Register */
+
+static int mv88e6xxx_g1_atu_fid_write(struct mv88e6xxx_chip *chip, u16 fid)
+{
+ return mv88e6xxx_g1_write(chip, GLOBAL_ATU_FID, fid & 0xfff);
+}
+
+/* Offset 0x0A: ATU Control Register */
+
+int mv88e6xxx_g1_atu_set_learn2all(struct mv88e6xxx_chip *chip, bool learn2all)
+{
+ u16 val;
+ int err;
+
+ err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val);
+ if (err)
+ return err;
+
+ if (learn2all)
+ val |= GLOBAL_ATU_CONTROL_LEARN2ALL;
+ else
+ val &= ~GLOBAL_ATU_CONTROL_LEARN2ALL;
+
+ return mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, val);
+}
+
+int mv88e6xxx_g1_atu_set_age_time(struct mv88e6xxx_chip *chip,
+ unsigned int msecs)
+{
+ const unsigned int coeff = chip->info->age_time_coeff;
+ const unsigned int min = 0x01 * coeff;
+ const unsigned int max = 0xff * coeff;
+ u8 age_time;
+ u16 val;
+ int err;
+
+ if (msecs < min || msecs > max)
+ return -ERANGE;
+
+ /* Round to nearest multiple of coeff */
+ age_time = (msecs + coeff / 2) / coeff;
+
+ err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val);
+ if (err)
+ return err;
+
+ /* AgeTime is 11:4 bits */
+ val &= ~0xff0;
+ val |= age_time << 4;
+
+ err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, val);
+ if (err)
+ return err;
+
+ dev_dbg(chip->dev, "AgeTime set to 0x%02x (%d ms)\n", age_time,
+ age_time * coeff);
+
+ return 0;
+}
+
+/* Offset 0x0B: ATU Operation Register */
+
+static int mv88e6xxx_g1_atu_op_wait(struct mv88e6xxx_chip *chip)
+{
+ return mv88e6xxx_g1_wait(chip, GLOBAL_ATU_OP, GLOBAL_ATU_OP_BUSY);
+}
+
+static int mv88e6xxx_g1_atu_op(struct mv88e6xxx_chip *chip, u16 fid, u16 op)
+{
+ u16 val;
+ int err;
+
+ /* FID bits are dispatched all around gradually as more are supported */
+ if (mv88e6xxx_num_databases(chip) > 256) {
+ err = mv88e6xxx_g1_atu_fid_write(chip, fid);
+ if (err)
+ return err;
+ } else {
+ if (mv88e6xxx_num_databases(chip) > 16) {
+ /* ATU DBNum[7:4] are located in ATU Control 15:12 */
+ err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_CONTROL, &val);
+ if (err)
+ return err;
+
+ val = (val & 0x0fff) | ((fid << 8) & 0xf000);
+ err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_CONTROL, val);
+ if (err)
+ return err;
+ }
+
+ /* ATU DBNum[3:0] are located in ATU Operation 3:0 */
+ op |= fid & 0xf;
+ }
+
+ err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_OP, op);
+ if (err)
+ return err;
+
+ return mv88e6xxx_g1_atu_op_wait(chip);
+}
+
+/* Offset 0x0C: ATU Data Register */
+
+static int mv88e6xxx_g1_atu_data_read(struct mv88e6xxx_chip *chip,
+ struct mv88e6xxx_atu_entry *entry)
+{
+ u16 val;
+ int err;
+
+ err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_DATA, &val);
+ if (err)
+ return err;
+
+ entry->state = val & 0xf;
+ if (entry->state != GLOBAL_ATU_DATA_STATE_UNUSED) {
+ entry->trunk = !!(val & GLOBAL_ATU_DATA_TRUNK);
+ entry->portvec = (val >> 4) & mv88e6xxx_port_mask(chip);
+ }
+
+ return 0;
+}
+
+static int mv88e6xxx_g1_atu_data_write(struct mv88e6xxx_chip *chip,
+ struct mv88e6xxx_atu_entry *entry)
+{
+ u16 data = entry->state & 0xf;
+
+ if (entry->state != GLOBAL_ATU_DATA_STATE_UNUSED) {
+ if (entry->trunk)
+ data |= GLOBAL_ATU_DATA_TRUNK;
+
+ data |= (entry->portvec & mv88e6xxx_port_mask(chip)) << 4;
+ }
+
+ return mv88e6xxx_g1_write(chip, GLOBAL_ATU_DATA, data);
+}
+
+/* Offset 0x0D: ATU MAC Address Register Bytes 0 & 1
+ * Offset 0x0E: ATU MAC Address Register Bytes 2 & 3
+ * Offset 0x0F: ATU MAC Address Register Bytes 4 & 5
+ */
+
+static int mv88e6xxx_g1_atu_mac_read(struct mv88e6xxx_chip *chip,
+ struct mv88e6xxx_atu_entry *entry)
+{
+ u16 val;
+ int i, err;
+
+ for (i = 0; i < 3; i++) {
+ err = mv88e6xxx_g1_read(chip, GLOBAL_ATU_MAC_01 + i, &val);
+ if (err)
+ return err;
+
+ entry->mac[i * 2] = val >> 8;
+ entry->mac[i * 2 + 1] = val & 0xff;
+ }
+
+ return 0;
+}
+
+static int mv88e6xxx_g1_atu_mac_write(struct mv88e6xxx_chip *chip,
+ struct mv88e6xxx_atu_entry *entry)
+{
+ u16 val;
+ int i, err;
+
+ for (i = 0; i < 3; i++) {
+ val = (entry->mac[i * 2] << 8) | entry->mac[i * 2 + 1];
+ err = mv88e6xxx_g1_write(chip, GLOBAL_ATU_MAC_01 + i, val);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+/* Address Translation Unit operations */
+
+int mv88e6xxx_g1_atu_getnext(struct mv88e6xxx_chip *chip, u16 fid,
+ struct mv88e6xxx_atu_entry *entry)
+{
+ int err;
+
+ err = mv88e6xxx_g1_atu_op_wait(chip);
+ if (err)
+ return err;
+
+ /* Write the MAC address to iterate from only once */
+ if (entry->state == GLOBAL_ATU_DATA_STATE_UNUSED) {
+ err = mv88e6xxx_g1_atu_mac_write(chip, entry);
+ if (err)
+ return err;
+ }
+
+ err = mv88e6xxx_g1_atu_op(chip, fid, GLOBAL_ATU_OP_GET_NEXT_DB);
+ if (err)
+ return err;
+
+ err = mv88e6xxx_g1_atu_data_read(chip, entry);
+ if (err)
+ return err;
+
+ return mv88e6xxx_g1_atu_mac_read(chip, entry);
+}
+
+int mv88e6xxx_g1_atu_loadpurge(struct mv88e6xxx_chip *chip, u16 fid,
+ struct mv88e6xxx_atu_entry *entry)
+{
+ int err;
+
+ err = mv88e6xxx_g1_atu_op_wait(chip);
+ if (err)
+ return err;
+
+ err = mv88e6xxx_g1_atu_mac_write(chip, entry);
+ if (err)
+ return err;
+
+ err = mv88e6xxx_g1_atu_data_write(chip, entry);
+ if (err)
+ return err;
+
+ return mv88e6xxx_g1_atu_op(chip, fid, GLOBAL_ATU_OP_LOAD_DB);
+}
+
+static int mv88e6xxx_g1_atu_flushmove(struct mv88e6xxx_chip *chip, u16 fid,
+ struct mv88e6xxx_atu_entry *entry,
+ bool all)
+{
+ u16 op;
+ int err;
+
+ err = mv88e6xxx_g1_atu_op_wait(chip);
+ if (err)
+ return err;
+
+ err = mv88e6xxx_g1_atu_data_write(chip, entry);
+ if (err)
+ return err;
+
+ /* Flush/Move all or non-static entries from all or a given database */
+ if (all && fid)
+ op = GLOBAL_ATU_OP_FLUSH_MOVE_ALL_DB;
+ else if (fid)
+ op = GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC_DB;
+ else if (all)
+ op = GLOBAL_ATU_OP_FLUSH_MOVE_ALL;
+ else
+ op = GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC;
+
+ return mv88e6xxx_g1_atu_op(chip, fid, op);
+}
+
+int mv88e6xxx_g1_atu_flush(struct mv88e6xxx_chip *chip, u16 fid, bool all)
+{
+ struct mv88e6xxx_atu_entry entry = {
+ .state = 0, /* Null EntryState means Flush */
+ };
+
+ return mv88e6xxx_g1_atu_flushmove(chip, fid, &entry, all);
+}
+
+static int mv88e6xxx_g1_atu_move(struct mv88e6xxx_chip *chip, u16 fid,
+ int from_port, int to_port, bool all)
+{
+ struct mv88e6xxx_atu_entry entry = { 0 };
+ unsigned long mask;
+ int shift;
+
+ if (!chip->info->atu_move_port_mask)
+ return -EOPNOTSUPP;
+
+ mask = chip->info->atu_move_port_mask;
+ shift = bitmap_weight(&mask, 16);
+
+ entry.state = 0xf, /* Full EntryState means Move */
+ entry.portvec = from_port & mask;
+ entry.portvec |= (to_port & mask) << shift;
+
+ return mv88e6xxx_g1_atu_flushmove(chip, fid, &entry, all);
+}
+
+int mv88e6xxx_g1_atu_remove(struct mv88e6xxx_chip *chip, u16 fid, int port,
+ bool all)
+{
+ int from_port = port;
+ int to_port = chip->info->atu_move_port_mask;
+
+ return mv88e6xxx_g1_atu_move(chip, fid, from_port, to_port, all);
+}
diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c
index 8f15bc7..b3fea55 100644
--- a/drivers/net/dsa/mv88e6xxx/global2.c
+++ b/drivers/net/dsa/mv88e6xxx/global2.c
@@ -4,7 +4,8 @@
*
* Copyright (c) 2008 Marvell Semiconductor
*
- * Copyright (c) 2016 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ * Copyright (c) 2016-2017 Savoir-faire Linux Inc.
+ * Vivien Didelot <vivien.didelot@savoirfairelinux.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -12,6 +13,7 @@
* (at your option) any later version.
*/
+#include <linux/interrupt.h>
#include <linux/irqdomain.h>
#include "mv88e6xxx.h"
#include "global2.h"
@@ -170,6 +172,50 @@ static int mv88e6xxx_g2_clear_irl(struct mv88e6xxx_chip *chip)
return err;
}
+/* Offset 0x0B: Cross-chip Port VLAN (Addr) Register
+ * Offset 0x0C: Cross-chip Port VLAN Data Register
+ */
+
+static int mv88e6xxx_g2_pvt_op_wait(struct mv88e6xxx_chip *chip)
+{
+ return mv88e6xxx_g2_wait(chip, GLOBAL2_PVT_ADDR, GLOBAL2_PVT_ADDR_BUSY);
+}
+
+static int mv88e6xxx_g2_pvt_op(struct mv88e6xxx_chip *chip, int src_dev,
+ int src_port, u16 op)
+{
+ int err;
+
+ /* 9-bit Cross-chip PVT pointer: with GLOBAL2_MISC_5_BIT_PORT cleared,
+ * source device is 5-bit, source port is 4-bit.
+ */
+ op |= (src_dev & 0x1f) << 4;
+ op |= (src_port & 0xf);
+
+ err = mv88e6xxx_g2_write(chip, GLOBAL2_PVT_ADDR, op);
+ if (err)
+ return err;
+
+ return mv88e6xxx_g2_pvt_op_wait(chip);
+}
+
+int mv88e6xxx_g2_pvt_write(struct mv88e6xxx_chip *chip, int src_dev,
+ int src_port, u16 data)
+{
+ int err;
+
+ err = mv88e6xxx_g2_pvt_op_wait(chip);
+ if (err)
+ return err;
+
+ err = mv88e6xxx_g2_write(chip, GLOBAL2_PVT_DATA, data);
+ if (err)
+ return err;
+
+ return mv88e6xxx_g2_pvt_op(chip, src_dev, src_port,
+ GLOBAL2_PVT_ADDR_OP_WRITE_PVLAN);
+}
+
/* Offset 0x0D: Switch MAC/WoL/WoF register */
static int mv88e6xxx_g2_switch_mac_write(struct mv88e6xxx_chip *chip,
@@ -522,8 +568,9 @@ static int mv88e6xxx_g2_smi_phy_write_addr(struct mv88e6xxx_chip *chip,
return mv88e6xxx_g2_smi_phy_cmd(chip, cmd);
}
-int mv88e6xxx_g2_smi_phy_read_c45(struct mv88e6xxx_chip *chip, int addr,
- int reg_c45, u16 *val, bool external)
+static int mv88e6xxx_g2_smi_phy_read_c45(struct mv88e6xxx_chip *chip,
+ int addr, int reg_c45, u16 *val,
+ bool external)
{
int device = (reg_c45 >> 16) & 0x1f;
int reg = reg_c45 & 0xffff;
@@ -553,8 +600,9 @@ int mv88e6xxx_g2_smi_phy_read_c45(struct mv88e6xxx_chip *chip, int addr,
return 0;
}
-int mv88e6xxx_g2_smi_phy_read_c22(struct mv88e6xxx_chip *chip, int addr,
- int reg, u16 *val, bool external)
+static int mv88e6xxx_g2_smi_phy_read_c22(struct mv88e6xxx_chip *chip,
+ int addr, int reg, u16 *val,
+ bool external)
{
u16 cmd = GLOBAL2_SMI_PHY_CMD_OP_22_READ_DATA | (addr << 5) | reg;
int err;
@@ -586,8 +634,9 @@ int mv88e6xxx_g2_smi_phy_read(struct mv88e6xxx_chip *chip,
return mv88e6xxx_g2_smi_phy_read_c22(chip, addr, reg, val, external);
}
-int mv88e6xxx_g2_smi_phy_write_c45(struct mv88e6xxx_chip *chip, int addr,
- int reg_c45, u16 val, bool external)
+static int mv88e6xxx_g2_smi_phy_write_c45(struct mv88e6xxx_chip *chip,
+ int addr, int reg_c45, u16 val,
+ bool external)
{
int device = (reg_c45 >> 16) & 0x1f;
int reg = reg_c45 & 0xffff;
@@ -615,8 +664,9 @@ int mv88e6xxx_g2_smi_phy_write_c45(struct mv88e6xxx_chip *chip, int addr,
return 0;
}
-int mv88e6xxx_g2_smi_phy_write_c22(struct mv88e6xxx_chip *chip, int addr,
- int reg, u16 val, bool external)
+static int mv88e6xxx_g2_smi_phy_write_c22(struct mv88e6xxx_chip *chip,
+ int addr, int reg, u16 val,
+ bool external)
{
u16 cmd = GLOBAL2_SMI_PHY_CMD_OP_22_WRITE_DATA | (addr << 5) | reg;
int err;
@@ -782,6 +832,31 @@ static int mv88e6xxx_g2_watchdog_setup(struct mv88e6xxx_chip *chip)
return err;
}
+/* Offset 0x1D: Misc Register */
+
+static int mv88e6xxx_g2_misc_5_bit_port(struct mv88e6xxx_chip *chip,
+ bool port_5_bit)
+{
+ u16 val;
+ int err;
+
+ err = mv88e6xxx_g2_read(chip, GLOBAL2_MISC, &val);
+ if (err)
+ return err;
+
+ if (port_5_bit)
+ val |= GLOBAL2_MISC_5_BIT_PORT;
+ else
+ val &= ~GLOBAL2_MISC_5_BIT_PORT;
+
+ return mv88e6xxx_g2_write(chip, GLOBAL2_MISC, val);
+}
+
+int mv88e6xxx_g2_misc_4_bit_port(struct mv88e6xxx_chip *chip)
+{
+ return mv88e6xxx_g2_misc_5_bit_port(chip, false);
+}
+
static void mv88e6xxx_g2_irq_mask(struct irq_data *d)
{
struct mv88e6xxx_chip *chip = irq_data_get_irq_chip_data(d);
@@ -964,14 +1039,6 @@ int mv88e6xxx_g2_setup(struct mv88e6xxx_chip *chip)
return err;
}
- if (mv88e6xxx_has(chip, MV88E6XXX_FLAGS_PVT)) {
- /* Initialize Cross-chip Port VLAN Table to reset defaults */
- err = mv88e6xxx_g2_write(chip, GLOBAL2_PVT_ADDR,
- GLOBAL2_PVT_ADDR_OP_INIT_ONES);
- if (err)
- return err;
- }
-
if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_G2_POT)) {
/* Clear the priority override table. */
err = mv88e6xxx_g2_clear_pot(chip);
diff --git a/drivers/net/dsa/mv88e6xxx/global2.h b/drivers/net/dsa/mv88e6xxx/global2.h
index a8b2f94..96046bb 100644
--- a/drivers/net/dsa/mv88e6xxx/global2.h
+++ b/drivers/net/dsa/mv88e6xxx/global2.h
@@ -3,7 +3,8 @@
*
* Copyright (c) 2008 Marvell Semiconductor
*
- * Copyright (c) 2016 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ * Copyright (c) 2016-2017 Savoir-faire Linux Inc.
+ * Vivien Didelot <vivien.didelot@savoirfairelinux.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -41,6 +42,10 @@ int mv88e6xxx_g2_get_eeprom16(struct mv88e6xxx_chip *chip,
int mv88e6xxx_g2_set_eeprom16(struct mv88e6xxx_chip *chip,
struct ethtool_eeprom *eeprom, u8 *data);
+int mv88e6xxx_g2_pvt_write(struct mv88e6xxx_chip *chip, int src_dev,
+ int src_port, u16 data);
+int mv88e6xxx_g2_misc_4_bit_port(struct mv88e6xxx_chip *chip);
+
int mv88e6xxx_g2_setup(struct mv88e6xxx_chip *chip);
int mv88e6xxx_g2_irq_setup(struct mv88e6xxx_chip *chip);
void mv88e6xxx_g2_irq_free(struct mv88e6xxx_chip *chip);
@@ -109,6 +114,17 @@ static inline int mv88e6xxx_g2_set_eeprom16(struct mv88e6xxx_chip *chip,
return -EOPNOTSUPP;
}
+int mv88e6xxx_g2_pvt_write(struct mv88e6xxx_chip *chip, int src_dev,
+ int src_port, u16 data)
+{
+ return -EOPNOTSUPP;
+}
+
+int mv88e6xxx_g2_misc_4_bit_port(struct mv88e6xxx_chip *chip)
+{
+ return -EOPNOTSUPP;
+}
+
static inline int mv88e6xxx_g2_setup(struct mv88e6xxx_chip *chip)
{
return -EOPNOTSUPP;
diff --git a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h
index 6033f2f..c8f5498 100644
--- a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h
+++ b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h
@@ -16,6 +16,7 @@
#include <linux/irq.h>
#include <linux/gpio/consumer.h>
#include <linux/phy.h>
+#include <net/dsa.h>
#ifndef UINT64_MAX
#define UINT64_MAX (u64)(~((u64)0))
@@ -132,18 +133,19 @@
#define PORT_CONTROL_TAG_IF_BOTH BIT(6)
#define PORT_CONTROL_USE_IP BIT(5)
#define PORT_CONTROL_USE_TAG BIT(4)
-#define PORT_CONTROL_FORWARD_UNKNOWN_MC BIT(3)
#define PORT_CONTROL_FORWARD_UNKNOWN BIT(2)
-#define PORT_CONTROL_NOT_EGRESS_UNKNOWN_DA (0x0 << 2)
-#define PORT_CONTROL_NOT_EGRESS_UNKNOWN_MULTICAST_DA (0x1 << 2)
-#define PORT_CONTROL_NOT_EGRESS_UNKNOWN_UNITCAST_DA (0x2 << 2)
-#define PORT_CONTROL_EGRESS_ALL_UNKNOWN_DA (0x3 << 2)
+#define PORT_CONTROL_EGRESS_FLOODS_MASK (0x3 << 2)
+#define PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_DA (0x0 << 2)
+#define PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_MC_DA (0x1 << 2)
+#define PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_UC_DA (0x2 << 2)
+#define PORT_CONTROL_EGRESS_FLOODS_ALL_UNKNOWN_DA (0x3 << 2)
#define PORT_CONTROL_STATE_MASK 0x03
#define PORT_CONTROL_STATE_DISABLED 0x00
#define PORT_CONTROL_STATE_BLOCKING 0x01
#define PORT_CONTROL_STATE_LEARNING 0x02
#define PORT_CONTROL_STATE_FORWARDING 0x03
#define PORT_CONTROL_1 0x05
+#define PORT_CONTROL_1_MESSAGE_PORT BIT(15)
#define PORT_CONTROL_1_FID_11_4_MASK (0xff << 0)
#define PORT_BASE_VLAN 0x06
#define PORT_BASE_VLAN_FID_3_0_MASK (0xf << 12)
@@ -166,7 +168,6 @@
#define PORT_CONTROL_2_DISCARD_UNTAGGED BIT(8)
#define PORT_CONTROL_2_MAP_DA BIT(7)
#define PORT_CONTROL_2_DEFAULT_FORWARD BIT(6)
-#define PORT_CONTROL_2_FORWARD_UNKNOWN BIT(6)
#define PORT_CONTROL_2_EGRESS_MONITOR BIT(5)
#define PORT_CONTROL_2_INGRESS_MONITOR BIT(4)
#define PORT_CONTROL_2_UPSTREAM_MASK 0x0f
@@ -181,6 +182,7 @@
#define PORT_ATU_CONTROL 0x0c
#define PORT_PRI_OVERRIDE 0x0d
#define PORT_ETH_TYPE 0x0f
+#define PORT_ETH_TYPE_DEFAULT 0x9100
#define PORT_IN_DISCARD_LO 0x10
#define PORT_IN_DISCARD_HI 0x11
#define PORT_IN_FILTERED 0x12
@@ -437,9 +439,14 @@
#define GLOBAL2_WDOG_FORCE_IRQ BIT(0)
#define GLOBAL2_QOS_WEIGHT 0x1c
#define GLOBAL2_MISC 0x1d
+#define GLOBAL2_MISC_5_BIT_PORT BIT(14)
#define MV88E6XXX_N_FID 4096
+/* PVT limits for 4-bit port and 5-bit switch */
+#define MV88E6XXX_MAX_PVT_SWITCHES 32
+#define MV88E6XXX_MAX_PVT_PORTS 16
+
enum mv88e6xxx_frame_mode {
MV88E6XXX_FRAME_MODE_NORMAL,
MV88E6XXX_FRAME_MODE_DSA,
@@ -525,8 +532,6 @@ enum mv88e6xxx_cap {
MV88E6XXX_CAP_G2_MGMT_EN_0X, /* (0x03) MGMT Enable Register 0x */
MV88E6XXX_CAP_G2_IRL_CMD, /* (0x09) Ingress Rate Command */
MV88E6XXX_CAP_G2_IRL_DATA, /* (0x0a) Ingress Rate Data */
- MV88E6XXX_CAP_G2_PVT_ADDR, /* (0x0b) Cross Chip Port VLAN Addr */
- MV88E6XXX_CAP_G2_PVT_DATA, /* (0x0c) Cross Chip Port VLAN Data */
MV88E6XXX_CAP_G2_POT, /* (0x0f) Priority Override Table */
/* Per VLAN Spanning Tree Unit (STU).
@@ -551,7 +556,6 @@ enum mv88e6xxx_cap {
#define MV88E6XXX_FLAG_SERDES BIT_ULL(MV88E6XXX_CAP_SERDES)
-#define MV88E6XXX_FLAG_G1_ATU_FID BIT_ULL(MV88E6XXX_CAP_G1_ATU_FID)
#define MV88E6XXX_FLAG_G1_VTU_FID BIT_ULL(MV88E6XXX_CAP_G1_VTU_FID)
#define MV88E6XXX_FLAG_GLOBAL2 BIT_ULL(MV88E6XXX_CAP_GLOBAL2)
@@ -560,8 +564,6 @@ enum mv88e6xxx_cap {
#define MV88E6XXX_FLAG_G2_MGMT_EN_0X BIT_ULL(MV88E6XXX_CAP_G2_MGMT_EN_0X)
#define MV88E6XXX_FLAG_G2_IRL_CMD BIT_ULL(MV88E6XXX_CAP_G2_IRL_CMD)
#define MV88E6XXX_FLAG_G2_IRL_DATA BIT_ULL(MV88E6XXX_CAP_G2_IRL_DATA)
-#define MV88E6XXX_FLAG_G2_PVT_ADDR BIT_ULL(MV88E6XXX_CAP_G2_PVT_ADDR)
-#define MV88E6XXX_FLAG_G2_PVT_DATA BIT_ULL(MV88E6XXX_CAP_G2_PVT_DATA)
#define MV88E6XXX_FLAG_G2_POT BIT_ULL(MV88E6XXX_CAP_G2_POT)
#define MV88E6XXX_FLAG_STU BIT_ULL(MV88E6XXX_CAP_STU)
@@ -577,11 +579,6 @@ enum mv88e6xxx_cap {
(MV88E6XXX_FLAG_SMI_CMD | \
MV88E6XXX_FLAG_SMI_DATA)
-/* Cross-chip Port VLAN Table */
-#define MV88E6XXX_FLAGS_PVT \
- (MV88E6XXX_FLAG_G2_PVT_ADDR | \
- MV88E6XXX_FLAG_G2_PVT_DATA)
-
/* Fiber/SERDES Registers at SMI address F, page 1 */
#define MV88E6XXX_FLAGS_SERDES \
(MV88E6XXX_FLAG_PHY_PAGE | \
@@ -594,8 +591,7 @@ enum mv88e6xxx_cap {
MV88E6XXX_FLAGS_MULTI_CHIP)
#define MV88E6XXX_FLAGS_FAMILY_6097 \
- (MV88E6XXX_FLAG_G1_ATU_FID | \
- MV88E6XXX_FLAG_G1_VTU_FID | \
+ (MV88E6XXX_FLAG_G1_VTU_FID | \
MV88E6XXX_FLAG_GLOBAL2 | \
MV88E6XXX_FLAG_G2_INT | \
MV88E6XXX_FLAG_G2_MGMT_EN_2X | \
@@ -604,12 +600,10 @@ enum mv88e6xxx_cap {
MV88E6XXX_FLAG_STU | \
MV88E6XXX_FLAG_VTU | \
MV88E6XXX_FLAGS_IRL | \
- MV88E6XXX_FLAGS_MULTI_CHIP | \
- MV88E6XXX_FLAGS_PVT)
+ MV88E6XXX_FLAGS_MULTI_CHIP)
#define MV88E6XXX_FLAGS_FAMILY_6165 \
- (MV88E6XXX_FLAG_G1_ATU_FID | \
- MV88E6XXX_FLAG_G1_VTU_FID | \
+ (MV88E6XXX_FLAG_G1_VTU_FID | \
MV88E6XXX_FLAG_GLOBAL2 | \
MV88E6XXX_FLAG_G2_INT | \
MV88E6XXX_FLAG_G2_MGMT_EN_2X | \
@@ -618,8 +612,7 @@ enum mv88e6xxx_cap {
MV88E6XXX_FLAG_STU | \
MV88E6XXX_FLAG_VTU | \
MV88E6XXX_FLAGS_IRL | \
- MV88E6XXX_FLAGS_MULTI_CHIP | \
- MV88E6XXX_FLAGS_PVT)
+ MV88E6XXX_FLAGS_MULTI_CHIP)
#define MV88E6XXX_FLAGS_FAMILY_6185 \
(MV88E6XXX_FLAG_GLOBAL2 | \
@@ -636,12 +629,10 @@ enum mv88e6xxx_cap {
MV88E6XXX_FLAG_G2_POT | \
MV88E6XXX_FLAG_VTU | \
MV88E6XXX_FLAGS_IRL | \
- MV88E6XXX_FLAGS_MULTI_CHIP | \
- MV88E6XXX_FLAGS_PVT)
+ MV88E6XXX_FLAGS_MULTI_CHIP)
#define MV88E6XXX_FLAGS_FAMILY_6341 \
(MV88E6XXX_FLAG_EEE | \
- MV88E6XXX_FLAG_G1_ATU_FID | \
MV88E6XXX_FLAG_G1_VTU_FID | \
MV88E6XXX_FLAG_GLOBAL2 | \
MV88E6XXX_FLAG_G2_INT | \
@@ -650,12 +641,10 @@ enum mv88e6xxx_cap {
MV88E6XXX_FLAG_VTU | \
MV88E6XXX_FLAGS_IRL | \
MV88E6XXX_FLAGS_MULTI_CHIP | \
- MV88E6XXX_FLAGS_PVT | \
MV88E6XXX_FLAGS_SERDES)
#define MV88E6XXX_FLAGS_FAMILY_6351 \
- (MV88E6XXX_FLAG_G1_ATU_FID | \
- MV88E6XXX_FLAG_G1_VTU_FID | \
+ (MV88E6XXX_FLAG_G1_VTU_FID | \
MV88E6XXX_FLAG_GLOBAL2 | \
MV88E6XXX_FLAG_G2_INT | \
MV88E6XXX_FLAG_G2_MGMT_EN_2X | \
@@ -664,12 +653,10 @@ enum mv88e6xxx_cap {
MV88E6XXX_FLAG_STU | \
MV88E6XXX_FLAG_VTU | \
MV88E6XXX_FLAGS_IRL | \
- MV88E6XXX_FLAGS_MULTI_CHIP | \
- MV88E6XXX_FLAGS_PVT)
+ MV88E6XXX_FLAGS_MULTI_CHIP)
#define MV88E6XXX_FLAGS_FAMILY_6352 \
(MV88E6XXX_FLAG_EEE | \
- MV88E6XXX_FLAG_G1_ATU_FID | \
MV88E6XXX_FLAG_G1_VTU_FID | \
MV88E6XXX_FLAG_GLOBAL2 | \
MV88E6XXX_FLAG_G2_INT | \
@@ -680,7 +667,6 @@ enum mv88e6xxx_cap {
MV88E6XXX_FLAG_VTU | \
MV88E6XXX_FLAGS_IRL | \
MV88E6XXX_FLAGS_MULTI_CHIP | \
- MV88E6XXX_FLAGS_PVT | \
MV88E6XXX_FLAGS_SERDES)
#define MV88E6XXX_FLAGS_FAMILY_6390 \
@@ -690,8 +676,7 @@ enum mv88e6xxx_cap {
MV88E6XXX_FLAG_STU | \
MV88E6XXX_FLAG_VTU | \
MV88E6XXX_FLAGS_IRL | \
- MV88E6XXX_FLAGS_MULTI_CHIP | \
- MV88E6XXX_FLAGS_PVT)
+ MV88E6XXX_FLAGS_MULTI_CHIP)
struct mv88e6xxx_ops;
@@ -705,16 +690,21 @@ struct mv88e6xxx_info {
unsigned int global1_addr;
unsigned int age_time_coeff;
unsigned int g1_irqs;
+ bool pvt;
enum dsa_tag_protocol tag_protocol;
unsigned long long flags;
+
+ /* Mask for FromPort and ToPort value of PortVec used in ATU Move
+ * operation. 0 means that the ATU Move operation is not supported.
+ */
+ u8 atu_move_port_mask;
const struct mv88e6xxx_ops *ops;
};
struct mv88e6xxx_atu_entry {
- u16 fid;
u8 state;
bool trunk;
- u16 portv_trunkid;
+ u16 portvec;
u8 mac[ETH_ALEN];
};
@@ -864,14 +854,16 @@ struct mv88e6xxx_ops {
int (*port_set_frame_mode)(struct mv88e6xxx_chip *chip, int port,
enum mv88e6xxx_frame_mode mode);
- int (*port_set_egress_unknowns)(struct mv88e6xxx_chip *chip, int port,
- bool on);
+ int (*port_set_egress_floods)(struct mv88e6xxx_chip *chip, int port,
+ bool unicast, bool multicast);
int (*port_set_ether_type)(struct mv88e6xxx_chip *chip, int port,
u16 etype);
int (*port_jumbo_config)(struct mv88e6xxx_chip *chip, int port);
int (*port_egress_rate_limiting)(struct mv88e6xxx_chip *chip, int port);
int (*port_pause_config)(struct mv88e6xxx_chip *chip, int port);
+ int (*port_disable_learn_limit)(struct mv88e6xxx_chip *chip, int port);
+ int (*port_disable_pri_override)(struct mv88e6xxx_chip *chip, int port);
/* CMODE control what PHY mode the MAC will use, eg. SGMII, RGMII, etc.
* Some chips allow this to be configured on specific ports.
@@ -934,6 +926,11 @@ static inline bool mv88e6xxx_has(struct mv88e6xxx_chip *chip,
return (chip->info->flags & flags) == flags;
}
+static inline bool mv88e6xxx_has_pvt(struct mv88e6xxx_chip *chip)
+{
+ return chip->info->pvt;
+}
+
static inline unsigned int mv88e6xxx_num_databases(struct mv88e6xxx_chip *chip)
{
return chip->info->num_databases;
@@ -944,6 +941,11 @@ static inline unsigned int mv88e6xxx_num_ports(struct mv88e6xxx_chip *chip)
return chip->info->num_ports;
}
+static inline u16 mv88e6xxx_port_mask(struct mv88e6xxx_chip *chip)
+{
+ return GENMASK(mv88e6xxx_num_ports(chip) - 1, 0);
+}
+
int mv88e6xxx_read(struct mv88e6xxx_chip *chip, int addr, int reg, u16 *val);
int mv88e6xxx_write(struct mv88e6xxx_chip *chip, int addr, int reg, u16 val);
int mv88e6xxx_update(struct mv88e6xxx_chip *chip, int addr, int reg,
diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index 8875784..548a956 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -3,7 +3,8 @@
*
* Copyright (c) 2008 Marvell Semiconductor
*
- * Copyright (c) 2016 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ * Copyright (c) 2016-2017 Savoir-faire Linux Inc.
+ * Vivien Didelot <vivien.didelot@savoirfairelinux.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -497,8 +498,8 @@ int mv88e6351_port_set_frame_mode(struct mv88e6xxx_chip *chip, int port,
return mv88e6xxx_port_write(chip, port, PORT_CONTROL, reg);
}
-int mv88e6085_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
- bool on)
+static int mv88e6185_port_set_forward_unknown(struct mv88e6xxx_chip *chip,
+ int port, bool unicast)
{
int err;
u16 reg;
@@ -507,7 +508,7 @@ int mv88e6085_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
if (err)
return err;
- if (on)
+ if (unicast)
reg |= PORT_CONTROL_FORWARD_UNKNOWN;
else
reg &= ~PORT_CONTROL_FORWARD_UNKNOWN;
@@ -515,8 +516,8 @@ int mv88e6085_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
return mv88e6xxx_port_write(chip, port, PORT_CONTROL, reg);
}
-int mv88e6351_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
- bool on)
+int mv88e6352_port_set_egress_floods(struct mv88e6xxx_chip *chip, int port,
+ bool unicast, bool multicast)
{
int err;
u16 reg;
@@ -525,21 +526,45 @@ int mv88e6351_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
if (err)
return err;
- if (on)
- reg |= PORT_CONTROL_EGRESS_ALL_UNKNOWN_DA;
+ reg &= ~PORT_CONTROL_EGRESS_FLOODS_MASK;
+
+ if (unicast && multicast)
+ reg |= PORT_CONTROL_EGRESS_FLOODS_ALL_UNKNOWN_DA;
+ else if (unicast)
+ reg |= PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_MC_DA;
+ else if (multicast)
+ reg |= PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_UC_DA;
else
- reg &= ~PORT_CONTROL_EGRESS_ALL_UNKNOWN_DA;
+ reg |= PORT_CONTROL_EGRESS_FLOODS_NO_UNKNOWN_DA;
return mv88e6xxx_port_write(chip, port, PORT_CONTROL, reg);
}
/* Offset 0x05: Port Control 1 */
+int mv88e6xxx_port_set_message_port(struct mv88e6xxx_chip *chip, int port,
+ bool message_port)
+{
+ u16 val;
+ int err;
+
+ err = mv88e6xxx_port_read(chip, port, PORT_CONTROL_1, &val);
+ if (err)
+ return err;
+
+ if (message_port)
+ val |= PORT_CONTROL_1_MESSAGE_PORT;
+ else
+ val &= ~PORT_CONTROL_1_MESSAGE_PORT;
+
+ return mv88e6xxx_port_write(chip, port, PORT_CONTROL_1, val);
+}
+
/* Offset 0x06: Port Based VLAN Map */
int mv88e6xxx_port_set_vlan_map(struct mv88e6xxx_chip *chip, int port, u16 map)
{
- const u16 mask = GENMASK(mv88e6xxx_num_ports(chip) - 1, 0);
+ const u16 mask = mv88e6xxx_port_mask(chip);
u16 reg;
int err;
@@ -672,8 +697,8 @@ static const char * const mv88e6xxx_port_8021q_mode_names[] = {
[PORT_CONTROL_2_8021Q_SECURE] = "Secure",
};
-int mv88e6095_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
- bool on)
+static int mv88e6185_port_set_default_forward(struct mv88e6xxx_chip *chip,
+ int port, bool multicast)
{
int err;
u16 reg;
@@ -682,14 +707,26 @@ int mv88e6095_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
if (err)
return err;
- if (on)
- reg |= PORT_CONTROL_2_FORWARD_UNKNOWN;
+ if (multicast)
+ reg |= PORT_CONTROL_2_DEFAULT_FORWARD;
else
- reg &= ~PORT_CONTROL_2_FORWARD_UNKNOWN;
+ reg &= ~PORT_CONTROL_2_DEFAULT_FORWARD;
return mv88e6xxx_port_write(chip, port, PORT_CONTROL_2, reg);
}
+int mv88e6185_port_set_egress_floods(struct mv88e6xxx_chip *chip, int port,
+ bool unicast, bool multicast)
+{
+ int err;
+
+ err = mv88e6185_port_set_forward_unknown(chip, port, unicast);
+ if (err)
+ return err;
+
+ return mv88e6185_port_set_default_forward(chip, port, multicast);
+}
+
int mv88e6095_port_set_upstream_port(struct mv88e6xxx_chip *chip, int port,
int upstream_port)
{
@@ -769,6 +806,20 @@ int mv88e6097_port_egress_rate_limiting(struct mv88e6xxx_chip *chip, int port)
return mv88e6xxx_port_write(chip, port, PORT_RATE_CONTROL, 0x0001);
}
+/* Offset 0x0C: Port ATU Control */
+
+int mv88e6xxx_port_disable_learn_limit(struct mv88e6xxx_chip *chip, int port)
+{
+ return mv88e6xxx_port_write(chip, port, PORT_ATU_CONTROL, 0);
+}
+
+/* Offset 0x0D: (Priority) Override Register */
+
+int mv88e6xxx_port_disable_pri_override(struct mv88e6xxx_chip *chip, int port)
+{
+ return mv88e6xxx_port_write(chip, port, PORT_PRI_OVERRIDE, 0);
+}
+
/* Offset 0x0f: Port Ether type */
int mv88e6351_port_set_ether_type(struct mv88e6xxx_chip *chip, int port,
diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h
index c83cbb3..86f4088 100644
--- a/drivers/net/dsa/mv88e6xxx/port.h
+++ b/drivers/net/dsa/mv88e6xxx/port.h
@@ -3,7 +3,8 @@
*
* Copyright (c) 2008 Marvell Semiconductor
*
- * Copyright (c) 2016 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ * Copyright (c) 2016-2017 Savoir-faire Linux Inc.
+ * Vivien Didelot <vivien.didelot@savoirfairelinux.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -56,14 +57,14 @@ int mv88e6085_port_set_frame_mode(struct mv88e6xxx_chip *chip, int port,
enum mv88e6xxx_frame_mode mode);
int mv88e6351_port_set_frame_mode(struct mv88e6xxx_chip *chip, int port,
enum mv88e6xxx_frame_mode mode);
-int mv88e6085_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
- bool on);
-int mv88e6095_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
- bool on);
-int mv88e6351_port_set_egress_unknowns(struct mv88e6xxx_chip *chip, int port,
- bool on);
+int mv88e6185_port_set_egress_floods(struct mv88e6xxx_chip *chip, int port,
+ bool unicast, bool multicast);
+int mv88e6352_port_set_egress_floods(struct mv88e6xxx_chip *chip, int port,
+ bool unicast, bool multicast);
int mv88e6351_port_set_ether_type(struct mv88e6xxx_chip *chip, int port,
u16 etype);
+int mv88e6xxx_port_set_message_port(struct mv88e6xxx_chip *chip, int port,
+ bool message_port);
int mv88e6165_port_jumbo_config(struct mv88e6xxx_chip *chip, int port);
int mv88e6095_port_egress_rate_limiting(struct mv88e6xxx_chip *chip, int port);
int mv88e6097_port_egress_rate_limiting(struct mv88e6xxx_chip *chip, int port);
@@ -75,4 +76,8 @@ int mv88e6xxx_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode);
int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port);
int mv88e6095_port_set_upstream_port(struct mv88e6xxx_chip *chip, int port,
int upstream_port);
+
+int mv88e6xxx_port_disable_learn_limit(struct mv88e6xxx_chip *chip, int port);
+int mv88e6xxx_port_disable_pri_override(struct mv88e6xxx_chip *chip, int port);
+
#endif /* _MV88E6XXX_PORT_H */
diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index 2c80611..149244a 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -35,6 +35,7 @@
#include <linux/init.h>
#include <linux/moduleparam.h>
#include <linux/rtnetlink.h>
+#include <linux/net_tstamp.h>
#include <net/rtnetlink.h>
#include <linux/u64_stats_sync.h>
@@ -125,6 +126,7 @@ static netdev_tx_t dummy_xmit(struct sk_buff *skb, struct net_device *dev)
dstats->tx_bytes += skb->len;
u64_stats_update_end(&dstats->syncp);
+ skb_tx_timestamp(skb);
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
@@ -304,8 +306,21 @@ static void dummy_get_drvinfo(struct net_device *dev,
strlcpy(info->version, DRV_VERSION, sizeof(info->version));
}
+static int dummy_get_ts_info(struct net_device *dev,
+ struct ethtool_ts_info *ts_info)
+{
+ ts_info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+ SOF_TIMESTAMPING_RX_SOFTWARE |
+ SOF_TIMESTAMPING_SOFTWARE;
+
+ ts_info->phc_index = -1;
+
+ return 0;
+};
+
static const struct ethtool_ops dummy_ethtool_ops = {
.get_drvinfo = dummy_get_drvinfo,
+ .get_ts_info = dummy_get_ts_info,
};
static void dummy_free_netdev(struct net_device *dev)
diff --git a/drivers/net/ethernet/3com/typhoon.c b/drivers/net/ethernet/3com/typhoon.c
index 084a6d5..be823c18 100644
--- a/drivers/net/ethernet/3com/typhoon.c
+++ b/drivers/net/ethernet/3com/typhoon.c
@@ -283,7 +283,6 @@ struct typhoon {
spinlock_t command_lock ____cacheline_aligned;
struct basic_ring cmdRing;
struct basic_ring respRing;
- struct net_device_stats stats;
struct net_device_stats stats_saved;
struct typhoon_shared * shared;
dma_addr_t shared_dma;
@@ -898,7 +897,7 @@ typhoon_set_rx_mode(struct net_device *dev)
static int
typhoon_do_get_stats(struct typhoon *tp)
{
- struct net_device_stats *stats = &tp->stats;
+ struct net_device_stats *stats = &tp->dev->stats;
struct net_device_stats *saved = &tp->stats_saved;
struct cmd_desc xp_cmd;
struct resp_desc xp_resp[7];
@@ -951,7 +950,7 @@ static struct net_device_stats *
typhoon_get_stats(struct net_device *dev)
{
struct typhoon *tp = netdev_priv(dev);
- struct net_device_stats *stats = &tp->stats;
+ struct net_device_stats *stats = &tp->dev->stats;
struct net_device_stats *saved = &tp->stats_saved;
smp_rmb();
@@ -1991,7 +1990,7 @@ typhoon_stop_runtime(struct typhoon *tp, int wait_type)
tp->card_state = Sleeping;
smp_wmb();
typhoon_do_get_stats(tp);
- memcpy(&tp->stats_saved, &tp->stats, sizeof(struct net_device_stats));
+ memcpy(&tp->stats_saved, &tp->dev->stats, sizeof(struct net_device_stats));
INIT_COMMAND_NO_RESPONSE(&xp_cmd, TYPHOON_CMD_HALT);
typhoon_issue_command(tp, 1, &xp_cmd, 0, NULL);
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index 8c08f9d..edae15ac 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -180,5 +180,6 @@
source "drivers/net/ethernet/wiznet/Kconfig"
source "drivers/net/ethernet/xilinx/Kconfig"
source "drivers/net/ethernet/xircom/Kconfig"
+source "drivers/net/ethernet/synopsys/Kconfig"
endif # ETHERNET
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 26dce5b..bf7f450 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -91,3 +91,4 @@
obj-$(CONFIG_NET_VENDOR_WIZNET) += wiznet/
obj-$(CONFIG_NET_VENDOR_XILINX) += xilinx/
obj-$(CONFIG_NET_VENDOR_XIRCOM) += xircom/
+obj-$(CONFIG_NET_VENDOR_SYNOPSYS) += synopsys/
diff --git a/drivers/net/ethernet/adi/bfin_mac.h b/drivers/net/ethernet/adi/bfin_mac.h
index 8c3b561..4ad5b9b 100644
--- a/drivers/net/ethernet/adi/bfin_mac.h
+++ b/drivers/net/ethernet/adi/bfin_mac.h
@@ -68,13 +68,6 @@ struct net_dma_desc_tx {
};
struct bfin_mac_local {
- /*
- * these are things that the kernel wants me to keep, so users
- * can find out semi-useless statistics of how well the card is
- * performing
- */
- struct net_device_stats stats;
-
spinlock_t lock;
int wol; /* Wake On Lan */
diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c
index 9f7422a..d8e133c 100644
--- a/drivers/net/ethernet/aeroflex/greth.c
+++ b/drivers/net/ethernet/aeroflex/greth.c
@@ -34,6 +34,7 @@
#include <linux/crc32.h>
#include <linux/mii.h>
#include <linux/of_device.h>
+#include <linux/of_net.h>
#include <linux/of_platform.h>
#include <linux/slab.h>
#include <asm/cacheflush.h>
@@ -1454,11 +1455,10 @@ static int greth_of_probe(struct platform_device *ofdev)
break;
}
if (i == 6) {
- const unsigned char *addr;
- int len;
- addr = of_get_property(ofdev->dev.of_node, "local-mac-address",
- &len);
- if (addr != NULL && len == 6) {
+ const u8 *addr;
+
+ addr = of_get_mac_address(ofdev->dev.of_node);
+ if (addr) {
for (i = 0; i < 6; i++)
macaddr[i] = (unsigned int) addr[i];
} else {
diff --git a/drivers/net/ethernet/amd/nmclan_cs.c b/drivers/net/ethernet/amd/nmclan_cs.c
index b556c92..9c152d8 100644
--- a/drivers/net/ethernet/amd/nmclan_cs.c
+++ b/drivers/net/ethernet/amd/nmclan_cs.c
@@ -359,7 +359,6 @@ typedef struct _mace_statistics {
typedef struct _mace_private {
struct pcmcia_device *p_dev;
- struct net_device_stats linux_stats; /* Linux statistics counters */
mace_statistics mace_stats; /* MACE chip statistics counters */
/* restore_multicast_list() state variables */
@@ -879,7 +878,7 @@ static netdev_tx_t mace_start_xmit(struct sk_buff *skb,
service a transmit interrupt while we are in here.
*/
- lp->linux_stats.tx_bytes += skb->len;
+ dev->stats.tx_bytes += skb->len;
lp->tx_free_frames--;
/* WARNING: Write the _exact_ number of bytes written in the header! */
@@ -967,7 +966,7 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id)
fifofc = inb(ioaddr + AM2150_MACE_BASE + MACE_FIFOFC);
if ((fifofc & MACE_FIFOFC_XMTFC)==0) {
- lp->linux_stats.tx_errors++;
+ dev->stats.tx_errors++;
outb(0xFF, ioaddr + AM2150_XMT_SKIP);
}
@@ -1016,7 +1015,7 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id)
} /* if (xmtfs & MACE_XMTFS_XMTSV) */
- lp->linux_stats.tx_packets++;
+ dev->stats.tx_packets++;
lp->tx_free_frames++;
netif_wake_queue(dev);
} /* if (status & MACE_IR_XMTINT) */
@@ -1077,7 +1076,7 @@ static int mace_rx(struct net_device *dev, unsigned char RxCnt)
" 0x%X.\n", dev->name, rx_framecnt, rx_status);
if (rx_status & MACE_RCVFS_RCVSTS) { /* Error, update stats. */
- lp->linux_stats.rx_errors++;
+ dev->stats.rx_errors++;
if (rx_status & MACE_RCVFS_OFLO) {
lp->mace_stats.oflo++;
}
@@ -1114,14 +1113,14 @@ static int mace_rx(struct net_device *dev, unsigned char RxCnt)
netif_rx(skb); /* Send the packet to the upper (protocol) layers. */
- lp->linux_stats.rx_packets++;
- lp->linux_stats.rx_bytes += pkt_len;
+ dev->stats.rx_packets++;
+ dev->stats.rx_bytes += pkt_len;
outb(0xFF, ioaddr + AM2150_RCV_NEXT); /* skip to next frame */
continue;
} else {
pr_debug("%s: couldn't allocate a sk_buff of size"
" %d.\n", dev->name, pkt_len);
- lp->linux_stats.rx_dropped++;
+ dev->stats.rx_dropped++;
}
}
outb(0xFF, ioaddr + AM2150_RCV_NEXT); /* skip to next frame */
@@ -1231,13 +1230,13 @@ static void update_stats(unsigned int ioaddr, struct net_device *dev)
lp->mace_stats.rntpc += mace_read(lp, ioaddr, MACE_RNTPC);
lp->mace_stats.mpc += mace_read(lp, ioaddr, MACE_MPC);
/* At this point, mace_stats is fully updated for this call.
- We may now update the linux_stats. */
+ We may now update the netdev stats. */
- /* The MACE has no equivalent for linux_stats field which are commented
+ /* The MACE has no equivalent for netdev stats field which are commented
out. */
- /* lp->linux_stats.multicast; */
- lp->linux_stats.collisions =
+ /* dev->stats.multicast; */
+ dev->stats.collisions =
lp->mace_stats.rcvcco * 256 + lp->mace_stats.rcvcc;
/* Collision: The MACE may retry sending a packet 15 times
before giving up. The retry count is in XMTRC.
@@ -1245,22 +1244,22 @@ static void update_stats(unsigned int ioaddr, struct net_device *dev)
If so, why doesn't the RCVCC record these collisions? */
/* detailed rx_errors: */
- lp->linux_stats.rx_length_errors =
+ dev->stats.rx_length_errors =
lp->mace_stats.rntpco * 256 + lp->mace_stats.rntpc;
- /* lp->linux_stats.rx_over_errors */
- lp->linux_stats.rx_crc_errors = lp->mace_stats.fcs;
- lp->linux_stats.rx_frame_errors = lp->mace_stats.fram;
- lp->linux_stats.rx_fifo_errors = lp->mace_stats.oflo;
- lp->linux_stats.rx_missed_errors =
+ /* dev->stats.rx_over_errors */
+ dev->stats.rx_crc_errors = lp->mace_stats.fcs;
+ dev->stats.rx_frame_errors = lp->mace_stats.fram;
+ dev->stats.rx_fifo_errors = lp->mace_stats.oflo;
+ dev->stats.rx_missed_errors =
lp->mace_stats.mpco * 256 + lp->mace_stats.mpc;
/* detailed tx_errors */
- lp->linux_stats.tx_aborted_errors = lp->mace_stats.rtry;
- lp->linux_stats.tx_carrier_errors = lp->mace_stats.lcar;
+ dev->stats.tx_aborted_errors = lp->mace_stats.rtry;
+ dev->stats.tx_carrier_errors = lp->mace_stats.lcar;
/* LCAR usually results from bad cabling. */
- lp->linux_stats.tx_fifo_errors = lp->mace_stats.uflo;
- lp->linux_stats.tx_heartbeat_errors = lp->mace_stats.cerr;
- /* lp->linux_stats.tx_window_errors; */
+ dev->stats.tx_fifo_errors = lp->mace_stats.uflo;
+ dev->stats.tx_heartbeat_errors = lp->mace_stats.cerr;
+ /* dev->stats.tx_window_errors; */
} /* update_stats */
/* ----------------------------------------------------------------------------
@@ -1274,10 +1273,10 @@ static struct net_device_stats *mace_get_stats(struct net_device *dev)
update_stats(dev->base_addr, dev);
pr_debug("%s: updating the statistics.\n", dev->name);
- pr_linux_stats(&lp->linux_stats);
+ pr_linux_stats(&dev->stats);
pr_mace_stats(&lp->mace_stats);
- return &lp->linux_stats;
+ return &dev->stats;
} /* net_device_stats */
/* ----------------------------------------------------------------------------
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index 8a280e7..127adbe 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -984,29 +984,29 @@
#define XP_ECC_CNT1_DESC_DED_WIDTH 8
#define XP_ECC_CNT1_DESC_SEC_INDEX 0
#define XP_ECC_CNT1_DESC_SEC_WIDTH 8
-#define XP_ECC_IER_DESC_DED_INDEX 0
+#define XP_ECC_IER_DESC_DED_INDEX 5
#define XP_ECC_IER_DESC_DED_WIDTH 1
-#define XP_ECC_IER_DESC_SEC_INDEX 1
+#define XP_ECC_IER_DESC_SEC_INDEX 4
#define XP_ECC_IER_DESC_SEC_WIDTH 1
-#define XP_ECC_IER_RX_DED_INDEX 2
+#define XP_ECC_IER_RX_DED_INDEX 3
#define XP_ECC_IER_RX_DED_WIDTH 1
-#define XP_ECC_IER_RX_SEC_INDEX 3
+#define XP_ECC_IER_RX_SEC_INDEX 2
#define XP_ECC_IER_RX_SEC_WIDTH 1
-#define XP_ECC_IER_TX_DED_INDEX 4
+#define XP_ECC_IER_TX_DED_INDEX 1
#define XP_ECC_IER_TX_DED_WIDTH 1
-#define XP_ECC_IER_TX_SEC_INDEX 5
+#define XP_ECC_IER_TX_SEC_INDEX 0
#define XP_ECC_IER_TX_SEC_WIDTH 1
-#define XP_ECC_ISR_DESC_DED_INDEX 0
+#define XP_ECC_ISR_DESC_DED_INDEX 5
#define XP_ECC_ISR_DESC_DED_WIDTH 1
-#define XP_ECC_ISR_DESC_SEC_INDEX 1
+#define XP_ECC_ISR_DESC_SEC_INDEX 4
#define XP_ECC_ISR_DESC_SEC_WIDTH 1
-#define XP_ECC_ISR_RX_DED_INDEX 2
+#define XP_ECC_ISR_RX_DED_INDEX 3
#define XP_ECC_ISR_RX_DED_WIDTH 1
-#define XP_ECC_ISR_RX_SEC_INDEX 3
+#define XP_ECC_ISR_RX_SEC_INDEX 2
#define XP_ECC_ISR_RX_SEC_WIDTH 1
-#define XP_ECC_ISR_TX_DED_INDEX 4
+#define XP_ECC_ISR_TX_DED_INDEX 1
#define XP_ECC_ISR_TX_DED_WIDTH 1
-#define XP_ECC_ISR_TX_SEC_INDEX 5
+#define XP_ECC_ISR_TX_SEC_INDEX 0
#define XP_ECC_ISR_TX_SEC_WIDTH 1
#define XP_I2C_MUTEX_BUSY_INDEX 31
#define XP_I2C_MUTEX_BUSY_WIDTH 1
@@ -1148,8 +1148,8 @@
#define RX_PACKET_ATTRIBUTES_CSUM_DONE_WIDTH 1
#define RX_PACKET_ATTRIBUTES_VLAN_CTAG_INDEX 1
#define RX_PACKET_ATTRIBUTES_VLAN_CTAG_WIDTH 1
-#define RX_PACKET_ATTRIBUTES_INCOMPLETE_INDEX 2
-#define RX_PACKET_ATTRIBUTES_INCOMPLETE_WIDTH 1
+#define RX_PACKET_ATTRIBUTES_LAST_INDEX 2
+#define RX_PACKET_ATTRIBUTES_LAST_WIDTH 1
#define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_INDEX 3
#define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_WIDTH 1
#define RX_PACKET_ATTRIBUTES_CONTEXT_INDEX 4
@@ -1158,6 +1158,8 @@
#define RX_PACKET_ATTRIBUTES_RX_TSTAMP_WIDTH 1
#define RX_PACKET_ATTRIBUTES_RSS_HASH_INDEX 6
#define RX_PACKET_ATTRIBUTES_RSS_HASH_WIDTH 1
+#define RX_PACKET_ATTRIBUTES_FIRST_INDEX 7
+#define RX_PACKET_ATTRIBUTES_FIRST_WIDTH 1
#define RX_NORMAL_DESC0_OVT_INDEX 0
#define RX_NORMAL_DESC0_OVT_WIDTH 16
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index 937f37a..24a687c 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -1896,10 +1896,15 @@ static int xgbe_dev_read(struct xgbe_channel *channel)
/* Get the header length */
if (XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, FD)) {
+ XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+ FIRST, 1);
rdata->rx.hdr_len = XGMAC_GET_BITS_LE(rdesc->desc2,
RX_NORMAL_DESC2, HL);
if (rdata->rx.hdr_len)
pdata->ext_stats.rx_split_header_packets++;
+ } else {
+ XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+ FIRST, 0);
}
/* Get the RSS hash */
@@ -1922,19 +1927,16 @@ static int xgbe_dev_read(struct xgbe_channel *channel)
}
}
- /* Get the packet length */
- rdata->rx.len = XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, PL);
-
- if (!XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, LD)) {
- /* Not all the data has been transferred for this packet */
- XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
- INCOMPLETE, 1);
+ /* Not all the data has been transferred for this packet */
+ if (!XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, LD))
return 0;
- }
/* This is the last of the data for this packet */
XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
- INCOMPLETE, 0);
+ LAST, 1);
+
+ /* Get the packet length */
+ rdata->rx.len = XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, PL);
/* Set checksum done indicator as appropriate */
if (netdev->features & NETIF_F_RXCSUM)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 248f60d..c772420 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -118,6 +118,7 @@
#include <linux/spinlock.h>
#include <linux/tcp.h>
#include <linux/if_vlan.h>
+#include <linux/interrupt.h>
#include <net/busy_poll.h>
#include <linux/clk.h>
#include <linux/if_ether.h>
@@ -1854,7 +1855,8 @@ static int xgbe_setup_tc(struct net_device *netdev, u32 handle, __be16 proto,
if (tc_to_netdev->type != TC_SETUP_MQPRIO)
return -EINVAL;
- tc = tc_to_netdev->tc;
+ tc_to_netdev->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+ tc = tc_to_netdev->mqprio->num_tc;
if (tc > pdata->hw_feat.tc_cnt)
return -EINVAL;
@@ -1971,13 +1973,12 @@ static struct sk_buff *xgbe_create_skb(struct xgbe_prv_data *pdata,
{
struct sk_buff *skb;
u8 *packet;
- unsigned int copy_len;
skb = napi_alloc_skb(napi, rdata->rx.hdr.dma_len);
if (!skb)
return NULL;
- /* Start with the header buffer which may contain just the header
+ /* Pull in the header buffer which may contain just the header
* or the header plus data
*/
dma_sync_single_range_for_cpu(pdata->dev, rdata->rx.hdr.dma_base,
@@ -1986,30 +1987,49 @@ static struct sk_buff *xgbe_create_skb(struct xgbe_prv_data *pdata,
packet = page_address(rdata->rx.hdr.pa.pages) +
rdata->rx.hdr.pa.pages_offset;
- copy_len = (rdata->rx.hdr_len) ? rdata->rx.hdr_len : len;
- copy_len = min(rdata->rx.hdr.dma_len, copy_len);
- skb_copy_to_linear_data(skb, packet, copy_len);
- skb_put(skb, copy_len);
-
- len -= copy_len;
- if (len) {
- /* Add the remaining data as a frag */
- dma_sync_single_range_for_cpu(pdata->dev,
- rdata->rx.buf.dma_base,
- rdata->rx.buf.dma_off,
- rdata->rx.buf.dma_len,
- DMA_FROM_DEVICE);
-
- skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
- rdata->rx.buf.pa.pages,
- rdata->rx.buf.pa.pages_offset,
- len, rdata->rx.buf.dma_len);
- rdata->rx.buf.pa.pages = NULL;
- }
+ skb_copy_to_linear_data(skb, packet, len);
+ skb_put(skb, len);
return skb;
}
+static unsigned int xgbe_rx_buf1_len(struct xgbe_ring_data *rdata,
+ struct xgbe_packet_data *packet)
+{
+ /* Always zero if not the first descriptor */
+ if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, FIRST))
+ return 0;
+
+ /* First descriptor with split header, return header length */
+ if (rdata->rx.hdr_len)
+ return rdata->rx.hdr_len;
+
+ /* First descriptor but not the last descriptor and no split header,
+ * so the full buffer was used
+ */
+ if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, LAST))
+ return rdata->rx.hdr.dma_len;
+
+ /* First descriptor and last descriptor and no split header, so
+ * calculate how much of the buffer was used
+ */
+ return min_t(unsigned int, rdata->rx.hdr.dma_len, rdata->rx.len);
+}
+
+static unsigned int xgbe_rx_buf2_len(struct xgbe_ring_data *rdata,
+ struct xgbe_packet_data *packet,
+ unsigned int len)
+{
+ /* Always the full buffer if not the last descriptor */
+ if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, LAST))
+ return rdata->rx.buf.dma_len;
+
+ /* Last descriptor so calculate how much of the buffer was used
+ * for the last bit of data
+ */
+ return rdata->rx.len - len;
+}
+
static int xgbe_tx_poll(struct xgbe_channel *channel)
{
struct xgbe_prv_data *pdata = channel->pdata;
@@ -2092,8 +2112,8 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
struct napi_struct *napi;
struct sk_buff *skb;
struct skb_shared_hwtstamps *hwtstamps;
- unsigned int incomplete, error, context_next, context;
- unsigned int len, rdesc_len, max_len;
+ unsigned int last, error, context_next, context;
+ unsigned int len, buf1_len, buf2_len, max_len;
unsigned int received = 0;
int packet_count = 0;
@@ -2103,7 +2123,7 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
if (!ring)
return 0;
- incomplete = 0;
+ last = 0;
context_next = 0;
napi = (pdata->per_channel_irq) ? &channel->napi : &pdata->napi;
@@ -2137,9 +2157,8 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
received++;
ring->cur++;
- incomplete = XGMAC_GET_BITS(packet->attributes,
- RX_PACKET_ATTRIBUTES,
- INCOMPLETE);
+ last = XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+ LAST);
context_next = XGMAC_GET_BITS(packet->attributes,
RX_PACKET_ATTRIBUTES,
CONTEXT_NEXT);
@@ -2148,7 +2167,7 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
CONTEXT);
/* Earlier error, just drain the remaining data */
- if ((incomplete || context_next) && error)
+ if ((!last || context_next) && error)
goto read_again;
if (error || packet->errors) {
@@ -2160,16 +2179,22 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
}
if (!context) {
- /* Length is cumulative, get this descriptor's length */
- rdesc_len = rdata->rx.len - len;
- len += rdesc_len;
+ /* Get the data length in the descriptor buffers */
+ buf1_len = xgbe_rx_buf1_len(rdata, packet);
+ len += buf1_len;
+ buf2_len = xgbe_rx_buf2_len(rdata, packet, len);
+ len += buf2_len;
- if (rdesc_len && !skb) {
+ if (!skb) {
skb = xgbe_create_skb(pdata, napi, rdata,
- rdesc_len);
- if (!skb)
+ buf1_len);
+ if (!skb) {
error = 1;
- } else if (rdesc_len) {
+ goto skip_data;
+ }
+ }
+
+ if (buf2_len) {
dma_sync_single_range_for_cpu(pdata->dev,
rdata->rx.buf.dma_base,
rdata->rx.buf.dma_off,
@@ -2179,13 +2204,14 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
rdata->rx.buf.pa.pages,
rdata->rx.buf.pa.pages_offset,
- rdesc_len,
+ buf2_len,
rdata->rx.buf.dma_len);
rdata->rx.buf.pa.pages = NULL;
}
}
- if (incomplete || context_next)
+skip_data:
+ if (!last || context_next)
goto read_again;
if (!skb)
@@ -2243,7 +2269,7 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
}
/* Check if we need to save state before leaving */
- if (received && (incomplete || context_next)) {
+ if (received && (!last || context_next)) {
rdata = XGBE_GET_DESC_DATA(ring, ring->cur);
rdata->state_saved = 1;
rdata->state.skb = skb;
@@ -2272,10 +2298,7 @@ static int xgbe_one_poll(struct napi_struct *napi, int budget)
processed = xgbe_rx_poll(channel, budget);
/* If we processed everything, we are done */
- if (processed < budget) {
- /* Turn off polling */
- napi_complete_done(napi, processed);
-
+ if ((processed < budget) && napi_complete_done(napi, processed)) {
/* Enable Tx and Rx interrupts */
if (pdata->channel_irq_mode)
xgbe_enable_rx_tx_int(pdata, channel);
@@ -2317,10 +2340,7 @@ static int xgbe_all_poll(struct napi_struct *napi, int budget)
} while ((processed < budget) && (processed != last_processed));
/* If we processed everything, we are done */
- if (processed < budget) {
- /* Turn off polling */
- napi_complete_done(napi, processed);
-
+ if ((processed < budget) && napi_complete_done(napi, processed)) {
/* Enable Tx and Rx interrupts */
xgbe_enable_rx_tx_ints(pdata);
}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c b/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
index 0c7088a..417bdb5 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
@@ -115,6 +115,7 @@
*/
#include <linux/module.h>
+#include <linux/interrupt.h>
#include <linux/kmod.h>
#include <linux/delay.h>
#include <linux/completion.h>
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 4c5b90e..b672d92 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -114,6 +114,7 @@
* THE POSSIBILITY OF SUCH DAMAGE.
*/
+#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/kmod.h>
#include <linux/mdio.h>
diff --git a/drivers/net/ethernet/apm/Kconfig b/drivers/net/ethernet/apm/Kconfig
index ec63d70..59efe5b 100644
--- a/drivers/net/ethernet/apm/Kconfig
+++ b/drivers/net/ethernet/apm/Kconfig
@@ -1 +1,2 @@
source "drivers/net/ethernet/apm/xgene/Kconfig"
+source "drivers/net/ethernet/apm/xgene-v2/Kconfig"
diff --git a/drivers/net/ethernet/apm/Makefile b/drivers/net/ethernet/apm/Makefile
index 65ce32a..946b2a4 100644
--- a/drivers/net/ethernet/apm/Makefile
+++ b/drivers/net/ethernet/apm/Makefile
@@ -3,3 +3,4 @@
#
obj-$(CONFIG_NET_XGENE) += xgene/
+obj-$(CONFIG_NET_XGENE_V2) += xgene-v2/
diff --git a/drivers/net/ethernet/apm/xgene-v2/Kconfig b/drivers/net/ethernet/apm/xgene-v2/Kconfig
new file mode 100644
index 0000000..1205861
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/Kconfig
@@ -0,0 +1,11 @@
+config NET_XGENE_V2
+ tristate "APM X-Gene SoC Ethernet-v2 Driver"
+ depends on HAS_DMA
+ depends on ARCH_XGENE || COMPILE_TEST
+ help
+ This is the Ethernet driver for the on-chip ethernet interface
+ which uses a linked list of DMA descriptor architecture (v2) for
+ APM X-Gene SoCs.
+
+ To compile this driver as a module, choose M here. This module will
+ be called xgene-enet-v2.
diff --git a/drivers/net/ethernet/apm/xgene-v2/Makefile b/drivers/net/ethernet/apm/xgene-v2/Makefile
new file mode 100644
index 0000000..f16a2b3
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/Makefile
@@ -0,0 +1,6 @@
+#
+# Makefile for APM X-Gene Ethernet v2 driver
+#
+
+xgene-enet-v2-objs := main.o mac.o enet.o ring.o mdio.o ethtool.o
+obj-$(CONFIG_NET_XGENE_V2) += xgene-enet-v2.o
diff --git a/drivers/net/ethernet/apm/xgene-v2/enet.c b/drivers/net/ethernet/apm/xgene-v2/enet.c
new file mode 100644
index 0000000..5998da0
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/enet.c
@@ -0,0 +1,83 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ * Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "main.h"
+
+void xge_wr_csr(struct xge_pdata *pdata, u32 offset, u32 val)
+{
+ void __iomem *addr = pdata->resources.base_addr + offset;
+
+ iowrite32(val, addr);
+}
+
+u32 xge_rd_csr(struct xge_pdata *pdata, u32 offset)
+{
+ void __iomem *addr = pdata->resources.base_addr + offset;
+
+ return ioread32(addr);
+}
+
+int xge_port_reset(struct net_device *ndev)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+ struct device *dev = &pdata->pdev->dev;
+ u32 data, wait = 10;
+
+ xge_wr_csr(pdata, ENET_CLKEN, 0x3);
+ xge_wr_csr(pdata, ENET_SRST, 0xf);
+ xge_wr_csr(pdata, ENET_SRST, 0);
+ xge_wr_csr(pdata, CFG_MEM_RAM_SHUTDOWN, 1);
+ xge_wr_csr(pdata, CFG_MEM_RAM_SHUTDOWN, 0);
+
+ do {
+ usleep_range(100, 110);
+ data = xge_rd_csr(pdata, BLOCK_MEM_RDY);
+ } while (data != MEM_RDY && wait--);
+
+ if (data != MEM_RDY) {
+ dev_err(dev, "ECC init failed: %x\n", data);
+ return -ETIMEDOUT;
+ }
+
+ xge_wr_csr(pdata, ENET_SHIM, DEVM_ARAUX_COH | DEVM_AWAUX_COH);
+
+ return 0;
+}
+
+static void xge_traffic_resume(struct net_device *ndev)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+
+ xge_wr_csr(pdata, CFG_FORCE_LINK_STATUS_EN, 1);
+ xge_wr_csr(pdata, FORCE_LINK_STATUS, 1);
+
+ xge_wr_csr(pdata, CFG_LINK_AGGR_RESUME, 1);
+ xge_wr_csr(pdata, RX_DV_GATE_REG, 1);
+}
+
+void xge_port_init(struct net_device *ndev)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+
+ pdata->phy_speed = SPEED_1000;
+ xge_mac_init(pdata);
+ xge_traffic_resume(ndev);
+}
diff --git a/drivers/net/ethernet/apm/xgene-v2/enet.h b/drivers/net/ethernet/apm/xgene-v2/enet.h
new file mode 100644
index 0000000..3fd36dc6
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/enet.h
@@ -0,0 +1,45 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ * Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __XGENE_ENET_V2_ENET_H__
+#define __XGENE_ENET_V2_ENET_H__
+
+#define ENET_CLKEN 0xc008
+#define ENET_SRST 0xc000
+#define ENET_SHIM 0xc010
+#define CFG_MEM_RAM_SHUTDOWN 0xd070
+#define BLOCK_MEM_RDY 0xd074
+
+#define MEM_RDY 0xffffffff
+#define DEVM_ARAUX_COH BIT(19)
+#define DEVM_AWAUX_COH BIT(3)
+
+#define CFG_FORCE_LINK_STATUS_EN 0x229c
+#define FORCE_LINK_STATUS 0x22a0
+#define CFG_LINK_AGGR_RESUME 0x27c8
+#define RX_DV_GATE_REG 0x2dfc
+
+void xge_wr_csr(struct xge_pdata *pdata, u32 offset, u32 val);
+u32 xge_rd_csr(struct xge_pdata *pdata, u32 offset);
+int xge_port_reset(struct net_device *ndev);
+void xge_port_init(struct net_device *ndev);
+
+#endif /* __XGENE_ENET_V2_ENET__H__ */
diff --git a/drivers/net/ethernet/apm/xgene-v2/ethtool.c b/drivers/net/ethernet/apm/xgene-v2/ethtool.c
new file mode 100644
index 0000000..0c426f5
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/ethtool.c
@@ -0,0 +1,121 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ * Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "main.h"
+
+struct xge_gstrings_stats {
+ char name[ETH_GSTRING_LEN];
+ int offset;
+};
+
+#define XGE_STAT(m) { #m, offsetof(struct xge_pdata, stats.m) }
+
+static const struct xge_gstrings_stats gstrings_stats[] = {
+ XGE_STAT(rx_packets),
+ XGE_STAT(tx_packets),
+ XGE_STAT(rx_bytes),
+ XGE_STAT(tx_bytes),
+ XGE_STAT(rx_errors)
+};
+
+#define XGE_STATS_LEN ARRAY_SIZE(gstrings_stats)
+
+static void xge_get_drvinfo(struct net_device *ndev,
+ struct ethtool_drvinfo *info)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+ struct platform_device *pdev = pdata->pdev;
+
+ strcpy(info->driver, "xgene-enet-v2");
+ strcpy(info->version, XGENE_ENET_V2_VERSION);
+ snprintf(info->fw_version, ETHTOOL_FWVERS_LEN, "N/A");
+ sprintf(info->bus_info, "%s", pdev->name);
+}
+
+static void xge_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
+{
+ u8 *p = data;
+ int i;
+
+ if (stringset != ETH_SS_STATS)
+ return;
+
+ for (i = 0; i < XGE_STATS_LEN; i++) {
+ memcpy(p, gstrings_stats[i].name, ETH_GSTRING_LEN);
+ p += ETH_GSTRING_LEN;
+ }
+}
+
+static int xge_get_sset_count(struct net_device *ndev, int sset)
+{
+ if (sset != ETH_SS_STATS)
+ return -EINVAL;
+
+ return XGE_STATS_LEN;
+}
+
+static void xge_get_ethtool_stats(struct net_device *ndev,
+ struct ethtool_stats *dummy,
+ u64 *data)
+{
+ void *pdata = netdev_priv(ndev);
+ int i;
+
+ for (i = 0; i < XGE_STATS_LEN; i++)
+ *data++ = *(u64 *)(pdata + gstrings_stats[i].offset);
+}
+
+static int xge_get_link_ksettings(struct net_device *ndev,
+ struct ethtool_link_ksettings *cmd)
+{
+ struct phy_device *phydev = ndev->phydev;
+
+ if (!phydev)
+ return -ENODEV;
+
+ return phy_ethtool_ksettings_get(phydev, cmd);
+}
+
+static int xge_set_link_ksettings(struct net_device *ndev,
+ const struct ethtool_link_ksettings *cmd)
+{
+ struct phy_device *phydev = ndev->phydev;
+
+ if (!phydev)
+ return -ENODEV;
+
+ return phy_ethtool_ksettings_set(phydev, cmd);
+}
+
+static const struct ethtool_ops xge_ethtool_ops = {
+ .get_drvinfo = xge_get_drvinfo,
+ .get_link = ethtool_op_get_link,
+ .get_strings = xge_get_strings,
+ .get_sset_count = xge_get_sset_count,
+ .get_ethtool_stats = xge_get_ethtool_stats,
+ .get_link_ksettings = xge_get_link_ksettings,
+ .set_link_ksettings = xge_set_link_ksettings,
+};
+
+void xge_set_ethtool_ops(struct net_device *ndev)
+{
+ ndev->ethtool_ops = &xge_ethtool_ops;
+}
diff --git a/drivers/net/ethernet/apm/xgene-v2/mac.c b/drivers/net/ethernet/apm/xgene-v2/mac.c
new file mode 100644
index 0000000..ee431e3
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/mac.c
@@ -0,0 +1,116 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ * Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "main.h"
+
+void xge_mac_reset(struct xge_pdata *pdata)
+{
+ xge_wr_csr(pdata, MAC_CONFIG_1, SOFT_RESET);
+ xge_wr_csr(pdata, MAC_CONFIG_1, 0);
+}
+
+void xge_mac_set_speed(struct xge_pdata *pdata)
+{
+ u32 icm0, icm2, ecm0, mc2;
+ u32 intf_ctrl, rgmii;
+
+ icm0 = xge_rd_csr(pdata, ICM_CONFIG0_REG_0);
+ icm2 = xge_rd_csr(pdata, ICM_CONFIG2_REG_0);
+ ecm0 = xge_rd_csr(pdata, ECM_CONFIG0_REG_0);
+ rgmii = xge_rd_csr(pdata, RGMII_REG_0);
+ mc2 = xge_rd_csr(pdata, MAC_CONFIG_2);
+ intf_ctrl = xge_rd_csr(pdata, INTERFACE_CONTROL);
+ icm2 |= CFG_WAITASYNCRD_EN;
+
+ switch (pdata->phy_speed) {
+ case SPEED_10:
+ SET_REG_BITS(&mc2, INTF_MODE, 1);
+ SET_REG_BITS(&intf_ctrl, HD_MODE, 0);
+ SET_REG_BITS(&icm0, CFG_MACMODE, 0);
+ SET_REG_BITS(&icm2, CFG_WAITASYNCRD, 500);
+ SET_REG_BIT(&rgmii, CFG_SPEED_125, 0);
+ break;
+ case SPEED_100:
+ SET_REG_BITS(&mc2, INTF_MODE, 1);
+ SET_REG_BITS(&intf_ctrl, HD_MODE, 1);
+ SET_REG_BITS(&icm0, CFG_MACMODE, 1);
+ SET_REG_BITS(&icm2, CFG_WAITASYNCRD, 80);
+ SET_REG_BIT(&rgmii, CFG_SPEED_125, 0);
+ break;
+ default:
+ SET_REG_BITS(&mc2, INTF_MODE, 2);
+ SET_REG_BITS(&intf_ctrl, HD_MODE, 2);
+ SET_REG_BITS(&icm0, CFG_MACMODE, 2);
+ SET_REG_BITS(&icm2, CFG_WAITASYNCRD, 16);
+ SET_REG_BIT(&rgmii, CFG_SPEED_125, 1);
+ break;
+ }
+
+ mc2 |= FULL_DUPLEX | CRC_EN | PAD_CRC;
+ SET_REG_BITS(&ecm0, CFG_WFIFOFULLTHR, 0x32);
+
+ xge_wr_csr(pdata, MAC_CONFIG_2, mc2);
+ xge_wr_csr(pdata, INTERFACE_CONTROL, intf_ctrl);
+ xge_wr_csr(pdata, RGMII_REG_0, rgmii);
+ xge_wr_csr(pdata, ICM_CONFIG0_REG_0, icm0);
+ xge_wr_csr(pdata, ICM_CONFIG2_REG_0, icm2);
+ xge_wr_csr(pdata, ECM_CONFIG0_REG_0, ecm0);
+}
+
+void xge_mac_set_station_addr(struct xge_pdata *pdata)
+{
+ u8 *dev_addr = pdata->ndev->dev_addr;
+ u32 addr0, addr1;
+
+ addr0 = (dev_addr[3] << 24) | (dev_addr[2] << 16) |
+ (dev_addr[1] << 8) | dev_addr[0];
+ addr1 = (dev_addr[5] << 24) | (dev_addr[4] << 16);
+
+ xge_wr_csr(pdata, STATION_ADDR0, addr0);
+ xge_wr_csr(pdata, STATION_ADDR1, addr1);
+}
+
+void xge_mac_init(struct xge_pdata *pdata)
+{
+ xge_mac_reset(pdata);
+ xge_mac_set_speed(pdata);
+ xge_mac_set_station_addr(pdata);
+}
+
+void xge_mac_enable(struct xge_pdata *pdata)
+{
+ u32 data;
+
+ data = xge_rd_csr(pdata, MAC_CONFIG_1);
+ data |= TX_EN | RX_EN;
+ xge_wr_csr(pdata, MAC_CONFIG_1, data);
+
+ data = xge_rd_csr(pdata, MAC_CONFIG_1);
+}
+
+void xge_mac_disable(struct xge_pdata *pdata)
+{
+ u32 data;
+
+ data = xge_rd_csr(pdata, MAC_CONFIG_1);
+ data &= ~(TX_EN | RX_EN);
+ xge_wr_csr(pdata, MAC_CONFIG_1, data);
+}
diff --git a/drivers/net/ethernet/apm/xgene-v2/mac.h b/drivers/net/ethernet/apm/xgene-v2/mac.h
new file mode 100644
index 0000000..18a9c9d
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/mac.h
@@ -0,0 +1,110 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ * Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __XGENE_ENET_V2_MAC_H__
+#define __XGENE_ENET_V2_MAC_H__
+
+/* Register offsets */
+#define MAC_CONFIG_1 0xa000
+#define MAC_CONFIG_2 0xa004
+#define MII_MGMT_CONFIG 0xa020
+#define MII_MGMT_COMMAND 0xa024
+#define MII_MGMT_ADDRESS 0xa028
+#define MII_MGMT_CONTROL 0xa02c
+#define MII_MGMT_STATUS 0xa030
+#define MII_MGMT_INDICATORS 0xa034
+#define INTERFACE_CONTROL 0xa038
+#define STATION_ADDR0 0xa040
+#define STATION_ADDR1 0xa044
+#define RBYT 0xa09c
+#define RPKT 0xa0a0
+#define RFCS 0xa0a4
+
+#define RGMII_REG_0 0x27e0
+#define ICM_CONFIG0_REG_0 0x2c00
+#define ICM_CONFIG2_REG_0 0x2c08
+#define ECM_CONFIG0_REG_0 0x2d00
+
+/* Register fields */
+#define SOFT_RESET BIT(31)
+#define TX_EN BIT(0)
+#define RX_EN BIT(2)
+#define PAD_CRC BIT(2)
+#define CRC_EN BIT(1)
+#define FULL_DUPLEX BIT(0)
+
+#define INTF_MODE_POS 8
+#define INTF_MODE_LEN 2
+#define HD_MODE_POS 25
+#define HD_MODE_LEN 2
+#define CFG_MACMODE_POS 18
+#define CFG_MACMODE_LEN 2
+#define CFG_WAITASYNCRD_POS 0
+#define CFG_WAITASYNCRD_LEN 16
+#define CFG_SPEED_125_POS 24
+#define CFG_WFIFOFULLTHR_POS 0
+#define CFG_WFIFOFULLTHR_LEN 7
+#define MGMT_CLOCK_SEL_POS 0
+#define MGMT_CLOCK_SEL_LEN 3
+#define PHY_ADDR_POS 8
+#define PHY_ADDR_LEN 5
+#define REG_ADDR_POS 0
+#define REG_ADDR_LEN 5
+#define MII_MGMT_BUSY BIT(0)
+#define MII_READ_CYCLE BIT(0)
+#define CFG_WAITASYNCRD_EN BIT(16)
+
+static inline void xgene_set_reg_bits(u32 *var, int pos, int len, u32 val)
+{
+ u32 mask = GENMASK(pos + len, pos);
+
+ *var &= ~mask;
+ *var |= ((val << pos) & mask);
+}
+
+static inline u32 xgene_get_reg_bits(u32 var, int pos, int len)
+{
+ u32 mask = GENMASK(pos + len, pos);
+
+ return (var & mask) >> pos;
+}
+
+#define SET_REG_BITS(var, field, val) \
+ xgene_set_reg_bits(var, field ## _POS, field ## _LEN, val)
+
+#define SET_REG_BIT(var, field, val) \
+ xgene_set_reg_bits(var, field ## _POS, 1, val)
+
+#define GET_REG_BITS(var, field) \
+ xgene_get_reg_bits(var, field ## _POS, field ## _LEN)
+
+#define GET_REG_BIT(var, field) ((var) & (field))
+
+struct xge_pdata;
+
+void xge_mac_reset(struct xge_pdata *pdata);
+void xge_mac_set_speed(struct xge_pdata *pdata);
+void xge_mac_enable(struct xge_pdata *pdata);
+void xge_mac_disable(struct xge_pdata *pdata);
+void xge_mac_init(struct xge_pdata *pdata);
+void xge_mac_set_station_addr(struct xge_pdata *pdata);
+
+#endif /* __XGENE_ENET_V2_MAC_H__ */
diff --git a/drivers/net/ethernet/apm/xgene-v2/main.c b/drivers/net/ethernet/apm/xgene-v2/main.c
new file mode 100644
index 0000000..0f2ad50
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/main.c
@@ -0,0 +1,759 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ * Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "main.h"
+
+static const struct acpi_device_id xge_acpi_match[];
+
+static int xge_get_resources(struct xge_pdata *pdata)
+{
+ struct platform_device *pdev;
+ struct net_device *ndev;
+ int phy_mode, ret = 0;
+ struct resource *res;
+ struct device *dev;
+
+ pdev = pdata->pdev;
+ dev = &pdev->dev;
+ ndev = pdata->ndev;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res) {
+ dev_err(dev, "Resource enet_csr not defined\n");
+ return -ENODEV;
+ }
+
+ pdata->resources.base_addr = devm_ioremap(dev, res->start,
+ resource_size(res));
+ if (!pdata->resources.base_addr) {
+ dev_err(dev, "Unable to retrieve ENET Port CSR region\n");
+ return -ENOMEM;
+ }
+
+ if (!device_get_mac_address(dev, ndev->dev_addr, ETH_ALEN))
+ eth_hw_addr_random(ndev);
+
+ memcpy(ndev->perm_addr, ndev->dev_addr, ndev->addr_len);
+
+ phy_mode = device_get_phy_mode(dev);
+ if (phy_mode < 0) {
+ dev_err(dev, "Unable to get phy-connection-type\n");
+ return phy_mode;
+ }
+ pdata->resources.phy_mode = phy_mode;
+
+ if (pdata->resources.phy_mode != PHY_INTERFACE_MODE_RGMII) {
+ dev_err(dev, "Incorrect phy-connection-type specified\n");
+ return -ENODEV;
+ }
+
+ ret = platform_get_irq(pdev, 0);
+ if (ret < 0) {
+ dev_err(dev, "Unable to get irq\n");
+ return ret;
+ }
+ pdata->resources.irq = ret;
+
+ return 0;
+}
+
+static int xge_refill_buffers(struct net_device *ndev, u32 nbuf)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+ struct xge_desc_ring *ring = pdata->rx_ring;
+ const u8 slots = XGENE_ENET_NUM_DESC - 1;
+ struct device *dev = &pdata->pdev->dev;
+ struct xge_raw_desc *raw_desc;
+ u64 addr_lo, addr_hi;
+ u8 tail = ring->tail;
+ struct sk_buff *skb;
+ dma_addr_t dma_addr;
+ u16 len;
+ int i;
+
+ for (i = 0; i < nbuf; i++) {
+ raw_desc = &ring->raw_desc[tail];
+
+ len = XGENE_ENET_STD_MTU;
+ skb = netdev_alloc_skb(ndev, len);
+ if (unlikely(!skb))
+ return -ENOMEM;
+
+ dma_addr = dma_map_single(dev, skb->data, len, DMA_FROM_DEVICE);
+ if (dma_mapping_error(dev, dma_addr)) {
+ netdev_err(ndev, "DMA mapping error\n");
+ dev_kfree_skb_any(skb);
+ return -EINVAL;
+ }
+
+ ring->pkt_info[tail].skb = skb;
+ ring->pkt_info[tail].dma_addr = dma_addr;
+
+ addr_hi = GET_BITS(NEXT_DESC_ADDRH, le64_to_cpu(raw_desc->m1));
+ addr_lo = GET_BITS(NEXT_DESC_ADDRL, le64_to_cpu(raw_desc->m1));
+ raw_desc->m1 = cpu_to_le64(SET_BITS(NEXT_DESC_ADDRL, addr_lo) |
+ SET_BITS(NEXT_DESC_ADDRH, addr_hi) |
+ SET_BITS(PKT_ADDRH,
+ upper_32_bits(dma_addr)));
+
+ dma_wmb();
+ raw_desc->m0 = cpu_to_le64(SET_BITS(PKT_ADDRL, dma_addr) |
+ SET_BITS(E, 1));
+ tail = (tail + 1) & slots;
+ }
+
+ ring->tail = tail;
+
+ return 0;
+}
+
+static int xge_init_hw(struct net_device *ndev)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+ int ret;
+
+ ret = xge_port_reset(ndev);
+ if (ret)
+ return ret;
+
+ xge_port_init(ndev);
+ pdata->nbufs = NUM_BUFS;
+
+ return 0;
+}
+
+static irqreturn_t xge_irq(const int irq, void *data)
+{
+ struct xge_pdata *pdata = data;
+
+ if (napi_schedule_prep(&pdata->napi)) {
+ xge_intr_disable(pdata);
+ __napi_schedule(&pdata->napi);
+ }
+
+ return IRQ_HANDLED;
+}
+
+static int xge_request_irq(struct net_device *ndev)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+ int ret;
+
+ snprintf(pdata->irq_name, IRQ_ID_SIZE, "%s", ndev->name);
+
+ ret = request_irq(pdata->resources.irq, xge_irq, 0, pdata->irq_name,
+ pdata);
+ if (ret)
+ netdev_err(ndev, "Failed to request irq %s\n", pdata->irq_name);
+
+ return ret;
+}
+
+static void xge_free_irq(struct net_device *ndev)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+
+ free_irq(pdata->resources.irq, pdata);
+}
+
+static bool is_tx_slot_available(struct xge_raw_desc *raw_desc)
+{
+ if (GET_BITS(E, le64_to_cpu(raw_desc->m0)) &&
+ (GET_BITS(PKT_SIZE, le64_to_cpu(raw_desc->m0)) == SLOT_EMPTY))
+ return true;
+
+ return false;
+}
+
+static netdev_tx_t xge_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+ struct device *dev = &pdata->pdev->dev;
+ struct xge_desc_ring *tx_ring;
+ struct xge_raw_desc *raw_desc;
+ static dma_addr_t dma_addr;
+ u64 addr_lo, addr_hi;
+ void *pkt_buf;
+ u8 tail;
+ u16 len;
+
+ tx_ring = pdata->tx_ring;
+ tail = tx_ring->tail;
+ len = skb_headlen(skb);
+ raw_desc = &tx_ring->raw_desc[tail];
+
+ if (!is_tx_slot_available(raw_desc)) {
+ netif_stop_queue(ndev);
+ return NETDEV_TX_BUSY;
+ }
+
+ /* Packet buffers should be 64B aligned */
+ pkt_buf = dma_zalloc_coherent(dev, XGENE_ENET_STD_MTU, &dma_addr,
+ GFP_ATOMIC);
+ if (unlikely(!pkt_buf)) {
+ dev_kfree_skb_any(skb);
+ return NETDEV_TX_OK;
+ }
+ memcpy(pkt_buf, skb->data, len);
+
+ addr_hi = GET_BITS(NEXT_DESC_ADDRH, le64_to_cpu(raw_desc->m1));
+ addr_lo = GET_BITS(NEXT_DESC_ADDRL, le64_to_cpu(raw_desc->m1));
+ raw_desc->m1 = cpu_to_le64(SET_BITS(NEXT_DESC_ADDRL, addr_lo) |
+ SET_BITS(NEXT_DESC_ADDRH, addr_hi) |
+ SET_BITS(PKT_ADDRH,
+ upper_32_bits(dma_addr)));
+
+ tx_ring->pkt_info[tail].skb = skb;
+ tx_ring->pkt_info[tail].dma_addr = dma_addr;
+ tx_ring->pkt_info[tail].pkt_buf = pkt_buf;
+
+ dma_wmb();
+
+ raw_desc->m0 = cpu_to_le64(SET_BITS(PKT_ADDRL, dma_addr) |
+ SET_BITS(PKT_SIZE, len) |
+ SET_BITS(E, 0));
+ skb_tx_timestamp(skb);
+ xge_wr_csr(pdata, DMATXCTRL, 1);
+
+ tx_ring->tail = (tail + 1) & (XGENE_ENET_NUM_DESC - 1);
+
+ return NETDEV_TX_OK;
+}
+
+static bool is_tx_hw_done(struct xge_raw_desc *raw_desc)
+{
+ if (GET_BITS(E, le64_to_cpu(raw_desc->m0)) &&
+ !GET_BITS(PKT_SIZE, le64_to_cpu(raw_desc->m0)))
+ return true;
+
+ return false;
+}
+
+static void xge_txc_poll(struct net_device *ndev)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+ struct device *dev = &pdata->pdev->dev;
+ struct xge_desc_ring *tx_ring;
+ struct xge_raw_desc *raw_desc;
+ dma_addr_t dma_addr;
+ struct sk_buff *skb;
+ void *pkt_buf;
+ u32 data;
+ u8 head;
+
+ tx_ring = pdata->tx_ring;
+ head = tx_ring->head;
+
+ data = xge_rd_csr(pdata, DMATXSTATUS);
+ if (!GET_BITS(TXPKTCOUNT, data))
+ return;
+
+ while (1) {
+ raw_desc = &tx_ring->raw_desc[head];
+
+ if (!is_tx_hw_done(raw_desc))
+ break;
+
+ dma_rmb();
+
+ skb = tx_ring->pkt_info[head].skb;
+ dma_addr = tx_ring->pkt_info[head].dma_addr;
+ pkt_buf = tx_ring->pkt_info[head].pkt_buf;
+ pdata->stats.tx_packets++;
+ pdata->stats.tx_bytes += skb->len;
+ dma_free_coherent(dev, XGENE_ENET_STD_MTU, pkt_buf, dma_addr);
+ dev_kfree_skb_any(skb);
+
+ /* clear pktstart address and pktsize */
+ raw_desc->m0 = cpu_to_le64(SET_BITS(E, 1) |
+ SET_BITS(PKT_SIZE, SLOT_EMPTY));
+ xge_wr_csr(pdata, DMATXSTATUS, 1);
+
+ head = (head + 1) & (XGENE_ENET_NUM_DESC - 1);
+ }
+
+ if (netif_queue_stopped(ndev))
+ netif_wake_queue(ndev);
+
+ tx_ring->head = head;
+}
+
+static int xge_rx_poll(struct net_device *ndev, unsigned int budget)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+ struct device *dev = &pdata->pdev->dev;
+ struct xge_desc_ring *rx_ring;
+ struct xge_raw_desc *raw_desc;
+ struct sk_buff *skb;
+ dma_addr_t dma_addr;
+ int processed = 0;
+ u8 head, rx_error;
+ int i, ret;
+ u32 data;
+ u16 len;
+
+ rx_ring = pdata->rx_ring;
+ head = rx_ring->head;
+
+ data = xge_rd_csr(pdata, DMARXSTATUS);
+ if (!GET_BITS(RXPKTCOUNT, data))
+ return 0;
+
+ for (i = 0; i < budget; i++) {
+ raw_desc = &rx_ring->raw_desc[head];
+
+ if (GET_BITS(E, le64_to_cpu(raw_desc->m0)))
+ break;
+
+ dma_rmb();
+
+ skb = rx_ring->pkt_info[head].skb;
+ rx_ring->pkt_info[head].skb = NULL;
+ dma_addr = rx_ring->pkt_info[head].dma_addr;
+ len = GET_BITS(PKT_SIZE, le64_to_cpu(raw_desc->m0));
+ dma_unmap_single(dev, dma_addr, XGENE_ENET_STD_MTU,
+ DMA_FROM_DEVICE);
+
+ rx_error = GET_BITS(D, le64_to_cpu(raw_desc->m2));
+ if (unlikely(rx_error)) {
+ pdata->stats.rx_errors++;
+ dev_kfree_skb_any(skb);
+ goto out;
+ }
+
+ skb_put(skb, len);
+ skb->protocol = eth_type_trans(skb, ndev);
+
+ pdata->stats.rx_packets++;
+ pdata->stats.rx_bytes += len;
+ napi_gro_receive(&pdata->napi, skb);
+out:
+ ret = xge_refill_buffers(ndev, 1);
+ xge_wr_csr(pdata, DMARXSTATUS, 1);
+ xge_wr_csr(pdata, DMARXCTRL, 1);
+
+ if (ret)
+ break;
+
+ head = (head + 1) & (XGENE_ENET_NUM_DESC - 1);
+ processed++;
+ }
+
+ rx_ring->head = head;
+
+ return processed;
+}
+
+static void xge_delete_desc_ring(struct net_device *ndev,
+ struct xge_desc_ring *ring)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+ struct device *dev = &pdata->pdev->dev;
+ u16 size;
+
+ if (!ring)
+ return;
+
+ size = XGENE_ENET_DESC_SIZE * XGENE_ENET_NUM_DESC;
+ if (ring->desc_addr)
+ dma_free_coherent(dev, size, ring->desc_addr, ring->dma_addr);
+
+ kfree(ring->pkt_info);
+ kfree(ring);
+}
+
+static void xge_free_buffers(struct net_device *ndev)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+ struct xge_desc_ring *ring = pdata->rx_ring;
+ struct device *dev = &pdata->pdev->dev;
+ struct sk_buff *skb;
+ dma_addr_t dma_addr;
+ int i;
+
+ for (i = 0; i < XGENE_ENET_NUM_DESC; i++) {
+ skb = ring->pkt_info[i].skb;
+ dma_addr = ring->pkt_info[i].dma_addr;
+
+ if (!skb)
+ continue;
+
+ dma_unmap_single(dev, dma_addr, XGENE_ENET_STD_MTU,
+ DMA_FROM_DEVICE);
+ dev_kfree_skb_any(skb);
+ }
+}
+
+static void xge_delete_desc_rings(struct net_device *ndev)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+
+ xge_txc_poll(ndev);
+ xge_delete_desc_ring(ndev, pdata->tx_ring);
+
+ xge_rx_poll(ndev, 64);
+ xge_free_buffers(ndev);
+ xge_delete_desc_ring(ndev, pdata->rx_ring);
+}
+
+static struct xge_desc_ring *xge_create_desc_ring(struct net_device *ndev)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+ struct device *dev = &pdata->pdev->dev;
+ struct xge_desc_ring *ring;
+ u16 size;
+
+ ring = kzalloc(sizeof(*ring), GFP_KERNEL);
+ if (!ring)
+ return NULL;
+
+ ring->ndev = ndev;
+
+ size = XGENE_ENET_DESC_SIZE * XGENE_ENET_NUM_DESC;
+ ring->desc_addr = dma_zalloc_coherent(dev, size, &ring->dma_addr,
+ GFP_KERNEL);
+ if (!ring->desc_addr)
+ goto err;
+
+ ring->pkt_info = kcalloc(XGENE_ENET_NUM_DESC, sizeof(*ring->pkt_info),
+ GFP_KERNEL);
+ if (!ring->pkt_info)
+ goto err;
+
+ xge_setup_desc(ring);
+
+ return ring;
+
+err:
+ xge_delete_desc_ring(ndev, ring);
+
+ return NULL;
+}
+
+static int xge_create_desc_rings(struct net_device *ndev)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+ struct xge_desc_ring *ring;
+ int ret;
+
+ /* create tx ring */
+ ring = xge_create_desc_ring(ndev);
+ if (!ring)
+ goto err;
+
+ pdata->tx_ring = ring;
+ xge_update_tx_desc_addr(pdata);
+
+ /* create rx ring */
+ ring = xge_create_desc_ring(ndev);
+ if (!ring)
+ goto err;
+
+ pdata->rx_ring = ring;
+ xge_update_rx_desc_addr(pdata);
+
+ ret = xge_refill_buffers(ndev, XGENE_ENET_NUM_DESC);
+ if (ret)
+ goto err;
+
+ return 0;
+err:
+ xge_delete_desc_rings(ndev);
+
+ return -ENOMEM;
+}
+
+static int xge_open(struct net_device *ndev)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+ int ret;
+
+ ret = xge_create_desc_rings(ndev);
+ if (ret)
+ return ret;
+
+ napi_enable(&pdata->napi);
+ ret = xge_request_irq(ndev);
+ if (ret)
+ return ret;
+
+ xge_intr_enable(pdata);
+ xge_wr_csr(pdata, DMARXCTRL, 1);
+
+ phy_start(ndev->phydev);
+ xge_mac_enable(pdata);
+ netif_start_queue(ndev);
+
+ return 0;
+}
+
+static int xge_close(struct net_device *ndev)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+
+ netif_stop_queue(ndev);
+ xge_mac_disable(pdata);
+ phy_stop(ndev->phydev);
+
+ xge_intr_disable(pdata);
+ xge_free_irq(ndev);
+ napi_disable(&pdata->napi);
+ xge_delete_desc_rings(ndev);
+
+ return 0;
+}
+
+static int xge_napi(struct napi_struct *napi, const int budget)
+{
+ struct net_device *ndev = napi->dev;
+ struct xge_pdata *pdata;
+ int processed;
+
+ pdata = netdev_priv(ndev);
+
+ xge_txc_poll(ndev);
+ processed = xge_rx_poll(ndev, budget);
+
+ if (processed < budget) {
+ napi_complete_done(napi, processed);
+ xge_intr_enable(pdata);
+ }
+
+ return processed;
+}
+
+static int xge_set_mac_addr(struct net_device *ndev, void *addr)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+ int ret;
+
+ ret = eth_mac_addr(ndev, addr);
+ if (ret)
+ return ret;
+
+ xge_mac_set_station_addr(pdata);
+
+ return 0;
+}
+
+static bool is_tx_pending(struct xge_raw_desc *raw_desc)
+{
+ if (!GET_BITS(E, le64_to_cpu(raw_desc->m0)))
+ return true;
+
+ return false;
+}
+
+static void xge_free_pending_skb(struct net_device *ndev)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+ struct device *dev = &pdata->pdev->dev;
+ struct xge_desc_ring *tx_ring;
+ struct xge_raw_desc *raw_desc;
+ dma_addr_t dma_addr;
+ struct sk_buff *skb;
+ void *pkt_buf;
+ int i;
+
+ tx_ring = pdata->tx_ring;
+
+ for (i = 0; i < XGENE_ENET_NUM_DESC; i++) {
+ raw_desc = &tx_ring->raw_desc[i];
+
+ if (!is_tx_pending(raw_desc))
+ continue;
+
+ skb = tx_ring->pkt_info[i].skb;
+ dma_addr = tx_ring->pkt_info[i].dma_addr;
+ pkt_buf = tx_ring->pkt_info[i].pkt_buf;
+ dma_free_coherent(dev, XGENE_ENET_STD_MTU, pkt_buf, dma_addr);
+ dev_kfree_skb_any(skb);
+ }
+}
+
+static void xge_timeout(struct net_device *ndev)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+
+ rtnl_lock();
+
+ if (!netif_running(ndev))
+ goto out;
+
+ netif_stop_queue(ndev);
+ xge_intr_disable(pdata);
+ napi_disable(&pdata->napi);
+
+ xge_wr_csr(pdata, DMATXCTRL, 0);
+ xge_txc_poll(ndev);
+ xge_free_pending_skb(ndev);
+ xge_wr_csr(pdata, DMATXSTATUS, ~0U);
+
+ xge_setup_desc(pdata->tx_ring);
+ xge_update_tx_desc_addr(pdata);
+ xge_mac_init(pdata);
+
+ napi_enable(&pdata->napi);
+ xge_intr_enable(pdata);
+ xge_mac_enable(pdata);
+ netif_start_queue(ndev);
+
+out:
+ rtnl_unlock();
+}
+
+static void xge_get_stats64(struct net_device *ndev,
+ struct rtnl_link_stats64 *storage)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+ struct xge_stats *stats = &pdata->stats;
+
+ storage->tx_packets += stats->tx_packets;
+ storage->tx_bytes += stats->tx_bytes;
+
+ storage->rx_packets += stats->rx_packets;
+ storage->rx_bytes += stats->rx_bytes;
+ storage->rx_errors += stats->rx_errors;
+}
+
+static const struct net_device_ops xgene_ndev_ops = {
+ .ndo_open = xge_open,
+ .ndo_stop = xge_close,
+ .ndo_start_xmit = xge_start_xmit,
+ .ndo_set_mac_address = xge_set_mac_addr,
+ .ndo_tx_timeout = xge_timeout,
+ .ndo_get_stats64 = xge_get_stats64,
+};
+
+static int xge_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct net_device *ndev;
+ struct xge_pdata *pdata;
+ int ret;
+
+ ndev = alloc_etherdev(sizeof(*pdata));
+ if (!ndev)
+ return -ENOMEM;
+
+ pdata = netdev_priv(ndev);
+
+ pdata->pdev = pdev;
+ pdata->ndev = ndev;
+ SET_NETDEV_DEV(ndev, dev);
+ platform_set_drvdata(pdev, pdata);
+ ndev->netdev_ops = &xgene_ndev_ops;
+
+ ndev->features |= NETIF_F_GSO |
+ NETIF_F_GRO;
+
+ ret = xge_get_resources(pdata);
+ if (ret)
+ goto err;
+
+ ndev->hw_features = ndev->features;
+ xge_set_ethtool_ops(ndev);
+
+ ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(64));
+ if (ret) {
+ netdev_err(ndev, "No usable DMA configuration\n");
+ goto err;
+ }
+
+ ret = xge_init_hw(ndev);
+ if (ret)
+ goto err;
+
+ ret = xge_mdio_config(ndev);
+ if (ret)
+ goto err;
+
+ netif_napi_add(ndev, &pdata->napi, xge_napi, NAPI_POLL_WEIGHT);
+
+ ret = register_netdev(ndev);
+ if (ret) {
+ netdev_err(ndev, "Failed to register netdev\n");
+ goto err;
+ }
+
+ return 0;
+
+err:
+ free_netdev(ndev);
+
+ return ret;
+}
+
+static int xge_remove(struct platform_device *pdev)
+{
+ struct xge_pdata *pdata;
+ struct net_device *ndev;
+
+ pdata = platform_get_drvdata(pdev);
+ ndev = pdata->ndev;
+
+ rtnl_lock();
+ if (netif_running(ndev))
+ dev_close(ndev);
+ rtnl_unlock();
+
+ xge_mdio_remove(ndev);
+ unregister_netdev(ndev);
+ free_netdev(ndev);
+
+ return 0;
+}
+
+static void xge_shutdown(struct platform_device *pdev)
+{
+ struct xge_pdata *pdata;
+
+ pdata = platform_get_drvdata(pdev);
+ if (!pdata)
+ return;
+
+ if (!pdata->ndev)
+ return;
+
+ xge_remove(pdev);
+}
+
+static const struct acpi_device_id xge_acpi_match[] = {
+ { "APMC0D80" },
+ { }
+};
+MODULE_DEVICE_TABLE(acpi, xge_acpi_match);
+
+static struct platform_driver xge_driver = {
+ .driver = {
+ .name = "xgene-enet-v2",
+ .acpi_match_table = ACPI_PTR(xge_acpi_match),
+ },
+ .probe = xge_probe,
+ .remove = xge_remove,
+ .shutdown = xge_shutdown,
+};
+module_platform_driver(xge_driver);
+
+MODULE_DESCRIPTION("APM X-Gene SoC Ethernet v2 driver");
+MODULE_AUTHOR("Iyappan Subramanian <isubramanian@apm.com>");
+MODULE_VERSION(XGENE_ENET_V2_VERSION);
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/apm/xgene-v2/main.h b/drivers/net/ethernet/apm/xgene-v2/main.h
new file mode 100644
index 0000000..db1178e
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/main.h
@@ -0,0 +1,80 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ * Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __XGENE_ENET_V2_MAIN_H__
+#define __XGENE_ENET_V2_MAIN_H__
+
+#include <linux/acpi.h>
+#include <linux/clk.h>
+#include <linux/efi.h>
+#include <linux/if_vlan.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/of_net.h>
+#include <linux/of_mdio.h>
+#include <linux/prefetch.h>
+#include <linux/phy.h>
+#include <net/ip.h>
+#include "mac.h"
+#include "enet.h"
+#include "ring.h"
+
+#define XGENE_ENET_V2_VERSION "v1.0"
+#define XGENE_ENET_STD_MTU 1536
+#define XGENE_ENET_MIN_FRAME 60
+#define IRQ_ID_SIZE 16
+
+struct xge_resource {
+ void __iomem *base_addr;
+ int phy_mode;
+ u32 irq;
+};
+
+struct xge_stats {
+ u64 tx_packets;
+ u64 tx_bytes;
+ u64 rx_packets;
+ u64 rx_bytes;
+ u64 rx_errors;
+};
+
+/* ethernet private data */
+struct xge_pdata {
+ struct xge_resource resources;
+ struct xge_desc_ring *tx_ring;
+ struct xge_desc_ring *rx_ring;
+ struct platform_device *pdev;
+ char irq_name[IRQ_ID_SIZE];
+ struct mii_bus *mdio_bus;
+ struct net_device *ndev;
+ struct napi_struct napi;
+ struct xge_stats stats;
+ int phy_speed;
+ u8 nbufs;
+};
+
+int xge_mdio_config(struct net_device *ndev);
+void xge_mdio_remove(struct net_device *ndev);
+void xge_set_ethtool_ops(struct net_device *ndev);
+
+#endif /* __XGENE_ENET_V2_MAIN_H__ */
diff --git a/drivers/net/ethernet/apm/xgene-v2/mdio.c b/drivers/net/ethernet/apm/xgene-v2/mdio.c
new file mode 100644
index 0000000..a583c6a
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/mdio.c
@@ -0,0 +1,167 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ * Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "main.h"
+
+static int xge_mdio_write(struct mii_bus *bus, int phy_id, int reg, u16 data)
+{
+ struct xge_pdata *pdata = bus->priv;
+ u32 done, val = 0;
+ u8 wait = 10;
+
+ SET_REG_BITS(&val, PHY_ADDR, phy_id);
+ SET_REG_BITS(&val, REG_ADDR, reg);
+ xge_wr_csr(pdata, MII_MGMT_ADDRESS, val);
+
+ xge_wr_csr(pdata, MII_MGMT_CONTROL, data);
+ do {
+ usleep_range(5, 10);
+ done = xge_rd_csr(pdata, MII_MGMT_INDICATORS);
+ } while ((done & MII_MGMT_BUSY) && wait--);
+
+ if (done & MII_MGMT_BUSY) {
+ dev_err(&bus->dev, "MII_MGMT write failed\n");
+ return -ETIMEDOUT;
+ }
+
+ return 0;
+}
+
+static int xge_mdio_read(struct mii_bus *bus, int phy_id, int reg)
+{
+ struct xge_pdata *pdata = bus->priv;
+ u32 data, done, val = 0;
+ u8 wait = 10;
+
+ SET_REG_BITS(&val, PHY_ADDR, phy_id);
+ SET_REG_BITS(&val, REG_ADDR, reg);
+ xge_wr_csr(pdata, MII_MGMT_ADDRESS, val);
+
+ xge_wr_csr(pdata, MII_MGMT_COMMAND, MII_READ_CYCLE);
+ do {
+ usleep_range(5, 10);
+ done = xge_rd_csr(pdata, MII_MGMT_INDICATORS);
+ } while ((done & MII_MGMT_BUSY) && wait--);
+
+ if (done & MII_MGMT_BUSY) {
+ dev_err(&bus->dev, "MII_MGMT read failed\n");
+ return -ETIMEDOUT;
+ }
+
+ data = xge_rd_csr(pdata, MII_MGMT_STATUS);
+ xge_wr_csr(pdata, MII_MGMT_COMMAND, 0);
+
+ return data;
+}
+
+static void xge_adjust_link(struct net_device *ndev)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+ struct phy_device *phydev = ndev->phydev;
+
+ if (phydev->link) {
+ if (pdata->phy_speed != phydev->speed) {
+ pdata->phy_speed = phydev->speed;
+ xge_mac_set_speed(pdata);
+ xge_mac_enable(pdata);
+ phy_print_status(phydev);
+ }
+ } else {
+ if (pdata->phy_speed != SPEED_UNKNOWN) {
+ pdata->phy_speed = SPEED_UNKNOWN;
+ xge_mac_disable(pdata);
+ phy_print_status(phydev);
+ }
+ }
+}
+
+void xge_mdio_remove(struct net_device *ndev)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+ struct mii_bus *mdio_bus = pdata->mdio_bus;
+
+ if (ndev->phydev)
+ phy_disconnect(ndev->phydev);
+
+ if (mdio_bus->state == MDIOBUS_REGISTERED)
+ mdiobus_unregister(mdio_bus);
+
+ mdiobus_free(mdio_bus);
+}
+
+int xge_mdio_config(struct net_device *ndev)
+{
+ struct xge_pdata *pdata = netdev_priv(ndev);
+ struct device *dev = &pdata->pdev->dev;
+ struct mii_bus *mdio_bus;
+ struct phy_device *phydev;
+ int ret;
+
+ mdio_bus = mdiobus_alloc();
+ if (!mdio_bus)
+ return -ENOMEM;
+
+ mdio_bus->name = "APM X-Gene Ethernet (v2) MDIO Bus";
+ mdio_bus->read = xge_mdio_read;
+ mdio_bus->write = xge_mdio_write;
+ mdio_bus->priv = pdata;
+ mdio_bus->parent = dev;
+ snprintf(mdio_bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(dev));
+ pdata->mdio_bus = mdio_bus;
+
+ mdio_bus->phy_mask = 0x1;
+ ret = mdiobus_register(mdio_bus);
+ if (ret)
+ goto err;
+
+ phydev = phy_find_first(mdio_bus);
+ if (!phydev) {
+ dev_err(dev, "no PHY found\n");
+ goto err;
+ }
+ phydev = phy_connect(ndev, phydev_name(phydev),
+ &xge_adjust_link,
+ pdata->resources.phy_mode);
+
+ if (IS_ERR(phydev)) {
+ netdev_err(ndev, "Could not attach to PHY\n");
+ ret = PTR_ERR(phydev);
+ goto err;
+ }
+
+ phydev->supported &= ~(SUPPORTED_10baseT_Half |
+ SUPPORTED_10baseT_Full |
+ SUPPORTED_100baseT_Half |
+ SUPPORTED_100baseT_Full |
+ SUPPORTED_1000baseT_Half |
+ SUPPORTED_AUI |
+ SUPPORTED_MII |
+ SUPPORTED_FIBRE |
+ SUPPORTED_BNC);
+ phydev->advertising = phydev->supported;
+ pdata->phy_speed = SPEED_UNKNOWN;
+
+ return 0;
+err:
+ xge_mdio_remove(ndev);
+
+ return ret;
+}
diff --git a/drivers/net/ethernet/apm/xgene-v2/ring.c b/drivers/net/ethernet/apm/xgene-v2/ring.c
new file mode 100644
index 0000000..3881082
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/ring.c
@@ -0,0 +1,81 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ * Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "main.h"
+
+/* create circular linked list of descriptors */
+void xge_setup_desc(struct xge_desc_ring *ring)
+{
+ struct xge_raw_desc *raw_desc;
+ dma_addr_t dma_h, next_dma;
+ u16 offset;
+ int i;
+
+ for (i = 0; i < XGENE_ENET_NUM_DESC; i++) {
+ raw_desc = &ring->raw_desc[i];
+
+ offset = (i + 1) & (XGENE_ENET_NUM_DESC - 1);
+ next_dma = ring->dma_addr + (offset * XGENE_ENET_DESC_SIZE);
+
+ raw_desc->m0 = cpu_to_le64(SET_BITS(E, 1) |
+ SET_BITS(PKT_SIZE, SLOT_EMPTY));
+ dma_h = upper_32_bits(next_dma);
+ raw_desc->m1 = cpu_to_le64(SET_BITS(NEXT_DESC_ADDRL, next_dma) |
+ SET_BITS(NEXT_DESC_ADDRH, dma_h));
+ }
+}
+
+void xge_update_tx_desc_addr(struct xge_pdata *pdata)
+{
+ struct xge_desc_ring *ring = pdata->tx_ring;
+ dma_addr_t dma_addr = ring->dma_addr;
+
+ xge_wr_csr(pdata, DMATXDESCL, dma_addr);
+ xge_wr_csr(pdata, DMATXDESCH, upper_32_bits(dma_addr));
+
+ ring->head = 0;
+ ring->tail = 0;
+}
+
+void xge_update_rx_desc_addr(struct xge_pdata *pdata)
+{
+ struct xge_desc_ring *ring = pdata->rx_ring;
+ dma_addr_t dma_addr = ring->dma_addr;
+
+ xge_wr_csr(pdata, DMARXDESCL, dma_addr);
+ xge_wr_csr(pdata, DMARXDESCH, upper_32_bits(dma_addr));
+
+ ring->head = 0;
+ ring->tail = 0;
+}
+
+void xge_intr_enable(struct xge_pdata *pdata)
+{
+ u32 data;
+
+ data = RX_PKT_RCVD | TX_PKT_SENT;
+ xge_wr_csr(pdata, DMAINTRMASK, data);
+}
+
+void xge_intr_disable(struct xge_pdata *pdata)
+{
+ xge_wr_csr(pdata, DMAINTRMASK, 0);
+}
diff --git a/drivers/net/ethernet/apm/xgene-v2/ring.h b/drivers/net/ethernet/apm/xgene-v2/ring.h
new file mode 100644
index 0000000..abc8c9a
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene-v2/ring.h
@@ -0,0 +1,119 @@
+/*
+ * Applied Micro X-Gene SoC Ethernet v2 Driver
+ *
+ * Copyright (c) 2017, Applied Micro Circuits Corporation
+ * Author(s): Iyappan Subramanian <isubramanian@apm.com>
+ * Keyur Chudgar <kchudgar@apm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __XGENE_ENET_V2_RING_H__
+#define __XGENE_ENET_V2_RING_H__
+
+#define XGENE_ENET_DESC_SIZE 64
+#define XGENE_ENET_NUM_DESC 256
+#define NUM_BUFS 8
+#define SLOT_EMPTY 0xfff
+
+#define DMATXCTRL 0xa180
+#define DMATXDESCL 0xa184
+#define DMATXDESCH 0xa1a0
+#define DMATXSTATUS 0xa188
+#define DMARXCTRL 0xa18c
+#define DMARXDESCL 0xa190
+#define DMARXDESCH 0xa1a4
+#define DMARXSTATUS 0xa194
+#define DMAINTRMASK 0xa198
+#define DMAINTERRUPT 0xa19c
+
+#define D_POS 62
+#define D_LEN 2
+#define E_POS 63
+#define E_LEN 1
+#define PKT_ADDRL_POS 0
+#define PKT_ADDRL_LEN 32
+#define PKT_ADDRH_POS 32
+#define PKT_ADDRH_LEN 10
+#define PKT_SIZE_POS 32
+#define PKT_SIZE_LEN 12
+#define NEXT_DESC_ADDRL_POS 0
+#define NEXT_DESC_ADDRL_LEN 32
+#define NEXT_DESC_ADDRH_POS 48
+#define NEXT_DESC_ADDRH_LEN 10
+
+#define TXPKTCOUNT_POS 16
+#define TXPKTCOUNT_LEN 8
+#define RXPKTCOUNT_POS 16
+#define RXPKTCOUNT_LEN 8
+
+#define TX_PKT_SENT BIT(0)
+#define TX_BUS_ERROR BIT(3)
+#define RX_PKT_RCVD BIT(4)
+#define RX_BUS_ERROR BIT(7)
+#define RXSTATUS_RXPKTRCVD BIT(0)
+
+struct xge_raw_desc {
+ __le64 m0;
+ __le64 m1;
+ __le64 m2;
+ __le64 m3;
+ __le64 m4;
+ __le64 m5;
+ __le64 m6;
+ __le64 m7;
+};
+
+struct pkt_info {
+ struct sk_buff *skb;
+ dma_addr_t dma_addr;
+ void *pkt_buf;
+};
+
+/* software context of a descriptor ring */
+struct xge_desc_ring {
+ struct net_device *ndev;
+ dma_addr_t dma_addr;
+ u8 head;
+ u8 tail;
+ union {
+ void *desc_addr;
+ struct xge_raw_desc *raw_desc;
+ };
+ struct pkt_info (*pkt_info);
+};
+
+static inline u64 xge_set_desc_bits(int pos, int len, u64 val)
+{
+ return (val & ((1ULL << len) - 1)) << pos;
+}
+
+static inline u64 xge_get_desc_bits(int pos, int len, u64 src)
+{
+ return (src >> pos) & ((1ULL << len) - 1);
+}
+
+#define SET_BITS(field, val) \
+ xge_set_desc_bits(field ## _POS, field ## _LEN, val)
+
+#define GET_BITS(field, src) \
+ xge_get_desc_bits(field ## _POS, field ## _LEN, src)
+
+void xge_setup_desc(struct xge_desc_ring *ring);
+void xge_update_tx_desc_addr(struct xge_pdata *pdata);
+void xge_update_rx_desc_addr(struct xge_pdata *pdata);
+void xge_intr_enable(struct xge_pdata *pdata);
+void xge_intr_disable(struct xge_pdata *pdata);
+
+#endif /* __XGENE_ENET_V2_RING_H__ */
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
index 06e6816..2a835e0 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
@@ -494,7 +494,7 @@ static void xgene_gmac_set_speed(struct xgene_enet_pdata *pdata)
break;
}
- mc2 |= FULL_DUPLEX2 | PAD_CRC;
+ mc2 |= FULL_DUPLEX2 | PAD_CRC | LENGTH_CHK;
xgene_enet_wr_mcx_mac(pdata, MAC_CONFIG_2_ADDR, mc2);
xgene_enet_wr_mcx_mac(pdata, INTERFACE_CONTROL_ADDR, intf_ctl);
xgene_enet_wr_csr(pdata, RGMII_REG_0_ADDR, rgmii);
@@ -623,6 +623,7 @@ static void xgene_enet_cle_bypass(struct xgene_enet_pdata *pdata,
xgene_enet_rd_csr(pdata, CLE_BYPASS_REG0_0_ADDR, &cb);
cb |= CFG_CLE_BYPASS_EN0;
CFG_CLE_IP_PROTOCOL0_SET(&cb, 3);
+ CFG_CLE_IP_HDR_LEN_SET(&cb, 0);
xgene_enet_wr_csr(pdata, CLE_BYPASS_REG0_0_ADDR, cb);
xgene_enet_rd_csr(pdata, CLE_BYPASS_REG1_0_ADDR, &cb);
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h
index 5f83037..d250bfe 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h
@@ -163,6 +163,7 @@ enum xgene_enet_rm {
#define CFG_RXCLK_MUXSEL0_SET(dst, val) xgene_set_bits(dst, val, 26, 3)
#define CFG_CLE_IP_PROTOCOL0_SET(dst, val) xgene_set_bits(dst, val, 16, 2)
+#define CFG_CLE_IP_HDR_LEN_SET(dst, val) xgene_set_bits(dst, val, 8, 5)
#define CFG_CLE_DSTQID0_SET(dst, val) xgene_set_bits(dst, val, 0, 12)
#define CFG_CLE_FPSEL0_SET(dst, val) xgene_set_bits(dst, val, 16, 4)
#define CFG_CLE_NXTFPSEL0_SET(dst, val) xgene_set_bits(dst, val, 20, 4)
@@ -215,6 +216,7 @@ enum xgene_enet_rm {
#define ENET_GHD_MODE BIT(26)
#define FULL_DUPLEX2 BIT(0)
#define PAD_CRC BIT(2)
+#define LENGTH_CHK BIT(4)
#define SCAN_AUTO_INCR BIT(5)
#define TBYT_ADDR 0x38
#define TPKT_ADDR 0x39
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
index b3568c4..5f37ed3 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
@@ -601,14 +601,24 @@ static netdev_tx_t xgene_enet_start_xmit(struct sk_buff *skb,
return NETDEV_TX_OK;
}
-static void xgene_enet_skip_csum(struct sk_buff *skb)
+static void xgene_enet_rx_csum(struct sk_buff *skb)
{
+ struct net_device *ndev = skb->dev;
struct iphdr *iph = ip_hdr(skb);
- if (!ip_is_fragment(iph) ||
- (iph->protocol != IPPROTO_TCP && iph->protocol != IPPROTO_UDP)) {
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- }
+ if (!(ndev->features & NETIF_F_RXCSUM))
+ return;
+
+ if (skb->protocol != htons(ETH_P_IP))
+ return;
+
+ if (ip_is_fragment(iph))
+ return;
+
+ if (iph->protocol != IPPROTO_TCP && iph->protocol != IPPROTO_UDP)
+ return;
+
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
}
static void xgene_enet_free_pagepool(struct xgene_enet_desc_ring *buf_pool,
@@ -648,12 +658,24 @@ static void xgene_enet_free_pagepool(struct xgene_enet_desc_ring *buf_pool,
buf_pool->head = head;
}
+/* Errata 10GE_8 and ENET_11 - allow packet with length <=64B */
+static bool xgene_enet_errata_10GE_8(struct sk_buff *skb, u32 len, u8 status)
+{
+ if (status == INGRESS_PKT_LEN && len == ETHER_MIN_PACKET) {
+ if (ntohs(eth_hdr(skb)->h_proto) < 46)
+ return true;
+ }
+
+ return false;
+}
+
static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring,
struct xgene_enet_raw_desc *raw_desc,
struct xgene_enet_raw_desc *exp_desc)
{
struct xgene_enet_desc_ring *buf_pool, *page_pool;
u32 datalen, frag_size, skb_index;
+ struct xgene_enet_pdata *pdata;
struct net_device *ndev;
dma_addr_t dma_addr;
struct sk_buff *skb;
@@ -666,6 +688,7 @@ static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring,
bool nv;
ndev = rx_ring->ndev;
+ pdata = netdev_priv(ndev);
dev = ndev_to_dev(rx_ring->ndev);
buf_pool = rx_ring->buf_pool;
page_pool = rx_ring->page_pool;
@@ -676,30 +699,29 @@ static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring,
skb = buf_pool->rx_skb[skb_index];
buf_pool->rx_skb[skb_index] = NULL;
- /* checking for error */
- status = (GET_VAL(ELERR, le64_to_cpu(raw_desc->m0)) << LERR_LEN) ||
- GET_VAL(LERR, le64_to_cpu(raw_desc->m0));
- if (unlikely(status > 2)) {
- dev_kfree_skb_any(skb);
- xgene_enet_free_pagepool(page_pool, raw_desc, exp_desc);
- xgene_enet_parse_error(rx_ring, netdev_priv(rx_ring->ndev),
- status);
- ret = -EIO;
- goto out;
- }
-
- /* strip off CRC as HW isn't doing this */
datalen = xgene_enet_get_data_len(le64_to_cpu(raw_desc->m1));
-
- nv = GET_VAL(NV, le64_to_cpu(raw_desc->m0));
- if (!nv)
- datalen -= 4;
-
skb_put(skb, datalen);
prefetch(skb->data - NET_IP_ALIGN);
+ skb->protocol = eth_type_trans(skb, ndev);
- if (!nv)
+ /* checking for error */
+ status = (GET_VAL(ELERR, le64_to_cpu(raw_desc->m0)) << LERR_LEN) |
+ GET_VAL(LERR, le64_to_cpu(raw_desc->m0));
+ if (unlikely(status)) {
+ if (!xgene_enet_errata_10GE_8(skb, datalen, status)) {
+ dev_kfree_skb_any(skb);
+ xgene_enet_free_pagepool(page_pool, raw_desc, exp_desc);
+ xgene_enet_parse_error(rx_ring, pdata, status);
+ goto out;
+ }
+ }
+
+ nv = GET_VAL(NV, le64_to_cpu(raw_desc->m0));
+ if (!nv) {
+ /* strip off CRC as HW isn't doing this */
+ datalen -= 4;
goto skip_jumbo;
+ }
slots = page_pool->slots - 1;
head = page_pool->head;
@@ -728,11 +750,7 @@ static int xgene_enet_rx_frame(struct xgene_enet_desc_ring *rx_ring,
skip_jumbo:
skb_checksum_none_assert(skb);
- skb->protocol = eth_type_trans(skb, ndev);
- if (likely((ndev->features & NETIF_F_IP_CSUM) &&
- skb->protocol == htons(ETH_P_IP))) {
- xgene_enet_skip_csum(skb);
- }
+ xgene_enet_rx_csum(skb);
rx_ring->rx_packets++;
rx_ring->rx_bytes += datalen;
@@ -2039,7 +2057,7 @@ static int xgene_enet_probe(struct platform_device *pdev)
xgene_enet_setup_ops(pdata);
if (pdata->phy_mode == PHY_INTERFACE_MODE_XGMII) {
- ndev->features |= NETIF_F_TSO;
+ ndev->features |= NETIF_F_TSO | NETIF_F_RXCSUM;
spin_lock_init(&pdata->mss_lock);
}
ndev->hw_features = ndev->features;
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h
index 5257174..0d4be24 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h
@@ -41,6 +41,7 @@
#include "../../../phy/mdio-xgene.h"
#define XGENE_DRV_VERSION "v1.0"
+#define ETHER_MIN_PACKET 64
#define XGENE_ENET_STD_MTU 1536
#define XGENE_ENET_MAX_MTU 9600
#define SKB_BUFFER_SIZE (XGENE_ENET_STD_MTU - NET_IP_ALIGN)
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
index ece19e6..423240c 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
@@ -341,8 +341,15 @@ static void xgene_xgmac_init(struct xgene_enet_pdata *pdata)
xgene_enet_rd_csr(pdata, XG_RSIF_CONFIG_REG_ADDR, &data);
data |= CFG_RSIF_FPBUFF_TIMEOUT_EN;
+ /* Errata 10GE_1 - FIFO threshold default value incorrect */
+ RSIF_CLE_BUFF_THRESH_SET(&data, XG_RSIF_CLE_BUFF_THRESH);
xgene_enet_wr_csr(pdata, XG_RSIF_CONFIG_REG_ADDR, data);
+ /* Errata 10GE_1 - FIFO threshold default value incorrect */
+ xgene_enet_rd_csr(pdata, XG_RSIF_CONFIG1_REG_ADDR, &data);
+ RSIF_PLC_CLE_BUFF_THRESH_SET(&data, XG_RSIF_PLC_CLE_BUFF_THRESH);
+ xgene_enet_wr_csr(pdata, XG_RSIF_CONFIG1_REG_ADDR, data);
+
xgene_enet_rd_csr(pdata, XG_ENET_SPARE_CFG_REG_ADDR, &data);
data |= BIT(12);
xgene_enet_wr_csr(pdata, XG_ENET_SPARE_CFG_REG_ADDR, data);
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h
index 03b847a..e644a42 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h
@@ -65,6 +65,11 @@
#define XG_DEF_PAUSE_THRES 0x390
#define XG_DEF_PAUSE_OFF_THRES 0x2c0
#define XG_RSIF_CONFIG_REG_ADDR 0x00a0
+#define XG_RSIF_CLE_BUFF_THRESH 0x3
+#define RSIF_CLE_BUFF_THRESH_SET(dst, val) xgene_set_bits(dst, val, 0, 3)
+#define XG_RSIF_CONFIG1_REG_ADDR 0x00b8
+#define XG_RSIF_PLC_CLE_BUFF_THRESH 0x1
+#define RSIF_PLC_CLE_BUFF_THRESH_SET(dst, val) xgene_set_bits(dst, val, 0, 2)
#define XCLE_BYPASS_REG0_ADDR 0x0160
#define XCLE_BYPASS_REG1_ADDR 0x0164
#define XG_CFG_BYPASS_ADDR 0x0204
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index dad6362..5d6c40d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -98,11 +98,7 @@ static int aq_ndev_change_mtu(struct net_device *ndev, int new_mtu)
if (err < 0)
goto err_exit;
-
- if (netif_running(ndev)) {
- aq_ndev_close(ndev);
- aq_ndev_open(ndev);
- }
+ ndev->mtu = new_mtu;
err_exit:
return err;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index ee78444..cdb0299 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -487,6 +487,9 @@ static unsigned int aq_nic_map_skb(struct aq_nic_s *self,
dx_buff->mss = skb_shinfo(skb)->gso_size;
dx_buff->is_txc = 1U;
+ dx_buff->is_ipv6 =
+ (ip_hdr(skb)->version == 6) ? 1U : 0U;
+
dx = aq_ring_next_dx(ring, dx);
dx_buff = &ring->buff_ring[dx];
++ret;
@@ -510,10 +513,22 @@ static unsigned int aq_nic_map_skb(struct aq_nic_s *self,
if (skb->ip_summed == CHECKSUM_PARTIAL) {
dx_buff->is_ip_cso = (htons(ETH_P_IP) == skb->protocol) ?
1U : 0U;
- dx_buff->is_tcp_cso =
- (ip_hdr(skb)->protocol == IPPROTO_TCP) ? 1U : 0U;
- dx_buff->is_udp_cso =
- (ip_hdr(skb)->protocol == IPPROTO_UDP) ? 1U : 0U;
+
+ if (ip_hdr(skb)->version == 4) {
+ dx_buff->is_tcp_cso =
+ (ip_hdr(skb)->protocol == IPPROTO_TCP) ?
+ 1U : 0U;
+ dx_buff->is_udp_cso =
+ (ip_hdr(skb)->protocol == IPPROTO_UDP) ?
+ 1U : 0U;
+ } else if (ip_hdr(skb)->version == 6) {
+ dx_buff->is_tcp_cso =
+ (ipv6_hdr(skb)->nexthdr == NEXTHDR_TCP) ?
+ 1U : 0U;
+ dx_buff->is_udp_cso =
+ (ipv6_hdr(skb)->nexthdr == NEXTHDR_UDP) ?
+ 1U : 0U;
+ }
}
for (; nr_frags--; ++frag_count) {
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
index 581de71..4c6c882 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
@@ -213,9 +213,9 @@ void aq_pci_func_free_irqs(struct aq_pci_func_s *self)
if (!((1U << i) & self->msix_entry_mask))
continue;
- free_irq(pci_irq_vector(pdev, i), self->aq_vec[i]);
if (pdev->msix_enabled)
irq_set_affinity_hint(pci_irq_vector(pdev, i), NULL);
+ free_irq(pci_irq_vector(pdev, i), self->aq_vec[i]);
self->msix_entry_mask &= ~(1U << i);
}
}
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 0358e607..3a8a4aa 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -101,6 +101,7 @@ int aq_ring_init(struct aq_ring_s *self)
self->hw_head = 0;
self->sw_head = 0;
self->sw_tail = 0;
+ spin_lock_init(&self->header.lock);
return 0;
}
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
index 2572546..eecd6d1 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
@@ -58,7 +58,8 @@ struct __packed aq_ring_buff_s {
u8 len_l2;
u8 len_l3;
u8 len_l4;
- u8 rsvd2;
+ u8 is_ipv6:1;
+ u8 rsvd2:7;
u32 len_pkt;
};
};
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
index a2b746a..4ee15ff 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
@@ -433,6 +433,9 @@ static int hw_atl_a0_hw_ring_tx_xmit(struct aq_hw_s *self,
buff->len_l3 +
buff->len_l2);
is_gso = true;
+
+ if (buff->is_ipv6)
+ txd->ctl |= HW_ATL_A0_TXD_CTL_CMD_IPV6;
} else {
buff_pa_len = buff->len;
@@ -458,6 +461,7 @@ static int hw_atl_a0_hw_ring_tx_xmit(struct aq_hw_s *self,
if (unlikely(buff->is_eop)) {
txd->ctl |= HW_ATL_A0_TXD_CTL_EOP;
txd->ctl |= HW_ATL_A0_TXD_CTL_CMD_WB;
+ is_gso = false;
}
}
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h
index 1093ea1..0592a03 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h
@@ -137,6 +137,7 @@ static struct aq_hw_caps_s hw_atl_a0_hw_caps_ = {
.tx_rings = HW_ATL_A0_TX_RINGS,
.rx_rings = HW_ATL_A0_RX_RINGS,
.hw_features = NETIF_F_HW_CSUM |
+ NETIF_F_RXCSUM |
NETIF_F_RXHASH |
NETIF_F_SG |
NETIF_F_TSO,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index cab2931..4215070 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -471,6 +471,9 @@ static int hw_atl_b0_hw_ring_tx_xmit(struct aq_hw_s *self,
buff->len_l3 +
buff->len_l2);
is_gso = true;
+
+ if (buff->is_ipv6)
+ txd->ctl |= HW_ATL_B0_TXD_CTL_CMD_IPV6;
} else {
buff_pa_len = buff->len;
@@ -496,6 +499,7 @@ static int hw_atl_b0_hw_ring_tx_xmit(struct aq_hw_s *self,
if (unlikely(buff->is_eop)) {
txd->ctl |= HW_ATL_B0_TXD_CTL_EOP;
txd->ctl |= HW_ATL_B0_TXD_CTL_CMD_WB;
+ is_gso = false;
}
}
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
index 8bdee3d..f3957e93 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
@@ -188,6 +188,7 @@ static struct aq_hw_caps_s hw_atl_b0_hw_caps_ = {
.tx_rings = HW_ATL_B0_TX_RINGS,
.rx_rings = HW_ATL_B0_RX_RINGS,
.hw_features = NETIF_F_HW_CSUM |
+ NETIF_F_RXCSUM |
NETIF_F_RXHASH |
NETIF_F_SG |
NETIF_F_TSO |
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index 940fb24..9641380 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -109,7 +109,6 @@
tristate "Broadcom Tigon3 support"
depends on PCI
select PHYLIB
- select HWMON
imply PTP_1588_CLOCK
---help---
This driver supports Broadcom Tigon3 based gigabit Ethernet cards.
@@ -117,6 +116,13 @@
To compile this driver as a module, choose M here: the module
will be called tg3. This is recommended.
+config TIGON3_HWMON
+ bool "Broadcom Tigon3 HWMON support"
+ default y
+ depends on TIGON3 && HWMON && !(TIGON3=y && HWMON=m)
+ ---help---
+ Say Y if you want to expose the thermal sensor on Tigon3 devices.
+
config BNX2X
tristate "Broadcom NetXtremeII 10Gb support"
depends on PCI
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index a68d4889..099b374 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -22,6 +22,7 @@
#include <linux/of_mdio.h>
#include <linux/phy.h>
#include <linux/phy_fixed.h>
+#include <net/dsa.h>
#include <net/ip.h>
#include <net/ipv6.h>
@@ -284,6 +285,7 @@ static const struct bcm_sysport_stats bcm_sysport_gstrings_stats[] = {
STAT_MIB_SOFT("alloc_rx_buff_failed", mib.alloc_rx_buff_failed),
STAT_MIB_SOFT("rx_dma_failed", mib.rx_dma_failed),
STAT_MIB_SOFT("tx_dma_failed", mib.tx_dma_failed),
+ /* Per TX-queue statistics are dynamically appended */
};
#define BCM_SYSPORT_STATS_LEN ARRAY_SIZE(bcm_sysport_gstrings_stats)
@@ -338,7 +340,8 @@ static int bcm_sysport_get_sset_count(struct net_device *dev, int string_set)
continue;
j++;
}
- return j;
+ /* Include per-queue statistics */
+ return j + dev->num_tx_queues * NUM_SYSPORT_TXQ_STAT;
default:
return -EOPNOTSUPP;
}
@@ -349,6 +352,7 @@ static void bcm_sysport_get_strings(struct net_device *dev,
{
struct bcm_sysport_priv *priv = netdev_priv(dev);
const struct bcm_sysport_stats *s;
+ char buf[128];
int i, j;
switch (stringset) {
@@ -363,6 +367,18 @@ static void bcm_sysport_get_strings(struct net_device *dev,
ETH_GSTRING_LEN);
j++;
}
+
+ for (i = 0; i < dev->num_tx_queues; i++) {
+ snprintf(buf, sizeof(buf), "txq%d_packets", i);
+ memcpy(data + j * ETH_GSTRING_LEN, buf,
+ ETH_GSTRING_LEN);
+ j++;
+
+ snprintf(buf, sizeof(buf), "txq%d_bytes", i);
+ memcpy(data + j * ETH_GSTRING_LEN, buf,
+ ETH_GSTRING_LEN);
+ j++;
+ }
break;
default:
break;
@@ -418,6 +434,7 @@ static void bcm_sysport_get_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 *data)
{
struct bcm_sysport_priv *priv = netdev_priv(dev);
+ struct bcm_sysport_tx_ring *ring;
int i, j;
if (netif_running(dev))
@@ -436,6 +453,22 @@ static void bcm_sysport_get_stats(struct net_device *dev,
data[j] = *(unsigned long *)p;
j++;
}
+
+ /* For SYSTEMPORT Lite since we have holes in our statistics, j would
+ * be equal to BCM_SYSPORT_STATS_LEN at the end of the loop, but it
+ * needs to point to how many total statistics we have minus the
+ * number of per TX queue statistics
+ */
+ j = bcm_sysport_get_sset_count(dev, ETH_SS_STATS) -
+ dev->num_tx_queues * NUM_SYSPORT_TXQ_STAT;
+
+ for (i = 0; i < dev->num_tx_queues; i++) {
+ ring = &priv->tx_rings[i];
+ data[j] = ring->packets;
+ j++;
+ data[j] = ring->bytes;
+ j++;
+ }
}
static void bcm_sysport_get_wol(struct net_device *dev,
@@ -637,6 +670,9 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
u16 len, status;
struct bcm_rsb *rsb;
+ /* Clear status before servicing to reduce spurious interrupts */
+ intrl2_0_writel(priv, INTRL2_0_RDMA_MBDONE, INTRL2_CPU_CLEAR);
+
/* Determine how much we should process since last call, SYSTEMPORT Lite
* groups the producer and consumer indexes into the same 32-bit
* which we access using RDMA_CONS_INDEX
@@ -647,11 +683,7 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
p_index = rdma_readl(priv, RDMA_CONS_INDEX);
p_index &= RDMA_PROD_INDEX_MASK;
- if (p_index < priv->rx_c_index)
- to_process = (RDMA_CONS_INDEX_MASK + 1) -
- priv->rx_c_index + p_index;
- else
- to_process = p_index - priv->rx_c_index;
+ to_process = (p_index - priv->rx_c_index) & RDMA_CONS_INDEX_MASK;
netif_dbg(priv, rx_status, ndev,
"p_index=%d rx_c_index=%d to_process=%d\n",
@@ -746,26 +778,26 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
return processed;
}
-static void bcm_sysport_tx_reclaim_one(struct bcm_sysport_priv *priv,
+static void bcm_sysport_tx_reclaim_one(struct bcm_sysport_tx_ring *ring,
struct bcm_sysport_cb *cb,
unsigned int *bytes_compl,
unsigned int *pkts_compl)
{
+ struct bcm_sysport_priv *priv = ring->priv;
struct device *kdev = &priv->pdev->dev;
- struct net_device *ndev = priv->netdev;
if (cb->skb) {
- ndev->stats.tx_bytes += cb->skb->len;
+ ring->bytes += cb->skb->len;
*bytes_compl += cb->skb->len;
dma_unmap_single(kdev, dma_unmap_addr(cb, dma_addr),
dma_unmap_len(cb, dma_len),
DMA_TO_DEVICE);
- ndev->stats.tx_packets++;
+ ring->packets++;
(*pkts_compl)++;
bcm_sysport_free_cb(cb);
/* SKB fragment */
} else if (dma_unmap_addr(cb, dma_addr)) {
- ndev->stats.tx_bytes += dma_unmap_len(cb, dma_len);
+ ring->bytes += dma_unmap_len(cb, dma_len);
dma_unmap_page(kdev, dma_unmap_addr(cb, dma_addr),
dma_unmap_len(cb, dma_len), DMA_TO_DEVICE);
dma_unmap_addr_set(cb, dma_addr, 0);
@@ -782,6 +814,13 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
struct bcm_sysport_cb *cb;
u32 hw_ind;
+ /* Clear status before servicing to reduce spurious interrupts */
+ if (!ring->priv->is_lite)
+ intrl2_1_writel(ring->priv, BIT(ring->index), INTRL2_CPU_CLEAR);
+ else
+ intrl2_0_writel(ring->priv, BIT(ring->index +
+ INTRL2_0_TDMA_MBDONE_SHIFT), INTRL2_CPU_CLEAR);
+
/* Compute how many descriptors have been processed since last call */
hw_ind = tdma_readl(priv, TDMA_DESC_RING_PROD_CONS_INDEX(ring->index));
c_index = (hw_ind >> RING_CONS_INDEX_SHIFT) & RING_CONS_INDEX_MASK;
@@ -803,7 +842,7 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
while (last_tx_cn-- > 0) {
cb = ring->cbs + last_c_index;
- bcm_sysport_tx_reclaim_one(priv, cb, &bytes_compl, &pkts_compl);
+ bcm_sysport_tx_reclaim_one(ring, cb, &bytes_compl, &pkts_compl);
ring->desc_count++;
last_c_index++;
@@ -1632,6 +1671,24 @@ static int bcm_sysport_change_mac(struct net_device *dev, void *p)
return 0;
}
+static struct net_device_stats *bcm_sysport_get_nstats(struct net_device *dev)
+{
+ struct bcm_sysport_priv *priv = netdev_priv(dev);
+ unsigned long tx_bytes = 0, tx_packets = 0;
+ struct bcm_sysport_tx_ring *ring;
+ unsigned int q;
+
+ for (q = 0; q < dev->num_tx_queues; q++) {
+ ring = &priv->tx_rings[q];
+ tx_bytes += ring->bytes;
+ tx_packets += ring->packets;
+ }
+
+ dev->stats.tx_bytes = tx_bytes;
+ dev->stats.tx_packets = tx_packets;
+ return &dev->stats;
+}
+
static void bcm_sysport_netif_start(struct net_device *dev)
{
struct bcm_sysport_priv *priv = netdev_priv(dev);
@@ -1893,6 +1950,7 @@ static const struct net_device_ops bcm_sysport_netdev_ops = {
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = bcm_sysport_poll_controller,
#endif
+ .ndo_get_stats = bcm_sysport_get_nstats,
};
#define REV_FMT "v%2x.%02x"
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index 863ddd7..77a51c1 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -647,6 +647,9 @@ enum bcm_sysport_stat_type {
.reg_offset = ofs, \
}
+/* TX bytes and packets */
+#define NUM_SYSPORT_TXQ_STAT 2
+
struct bcm_sysport_stats {
char stat_string[ETH_GSTRING_LEN];
int stat_sizeof;
@@ -690,6 +693,8 @@ struct bcm_sysport_tx_ring {
struct bcm_sysport_cb *cbs; /* Transmit control blocks */
struct dma_desc *desc_cpu; /* CPU view of the descriptor */
struct bcm_sysport_priv *priv; /* private context backpointer */
+ unsigned long packets; /* packets statistics */
+ unsigned long bytes; /* bytes statistics */
};
/* Driver private structure */
diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c
index cf15b7e..6322594 100644
--- a/drivers/net/ethernet/broadcom/bgmac-bcma.c
+++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c
@@ -11,6 +11,7 @@
#include <linux/bcma/bcma.h>
#include <linux/brcmphy.h>
#include <linux/etherdevice.h>
+#include <linux/of_net.h>
#include "bgmac.h"
static inline bool bgmac_is_bcm4707_family(struct bcma_device *core)
@@ -114,7 +115,7 @@ static int bgmac_probe(struct bcma_device *core)
struct ssb_sprom *sprom = &core->bus->sprom;
struct mii_bus *mii_bus;
struct bgmac *bgmac;
- u8 *mac;
+ const u8 *mac = NULL;
int err;
bgmac = bgmac_alloc(&core->dev);
@@ -127,21 +128,27 @@ static int bgmac_probe(struct bcma_device *core)
bcma_set_drvdata(core, bgmac);
- switch (core->core_unit) {
- case 0:
- mac = sprom->et0mac;
- break;
- case 1:
- mac = sprom->et1mac;
- break;
- case 2:
- mac = sprom->et2mac;
- break;
- default:
- dev_err(bgmac->dev, "Unsupported core_unit %d\n",
- core->core_unit);
- err = -ENOTSUPP;
- goto err;
+ if (bgmac->dev->of_node)
+ mac = of_get_mac_address(bgmac->dev->of_node);
+
+ /* If no MAC address assigned via device tree, check SPROM */
+ if (!mac) {
+ switch (core->core_unit) {
+ case 0:
+ mac = sprom->et0mac;
+ break;
+ case 1:
+ mac = sprom->et1mac;
+ break;
+ case 2:
+ mac = sprom->et2mac;
+ break;
+ default:
+ dev_err(bgmac->dev, "Unsupported core_unit %d\n",
+ core->core_unit);
+ err = -ENOTSUPP;
+ goto err;
+ }
}
ether_addr_copy(bgmac->net_dev->dev_addr, mac);
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index e1a24ee..ba4d2e1 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -11,6 +11,7 @@
#include <linux/bcma/bcma.h>
#include <linux/etherdevice.h>
+#include <linux/interrupt.h>
#include <linux/bcm47xx_nvram.h>
#include <linux/phy.h>
#include <linux/phy_fixed.h>
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 0a23034..352beff 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -2277,7 +2277,7 @@ void bnx2x_igu_clear_sb_gen(struct bnx2x *bp, u8 func, u8 idu_sb_id,
GENERAL_ATTEN_OFFSET(LATCHED_ATTN_RBCP) | \
GENERAL_ATTEN_OFFSET(LATCHED_ATTN_RSVD_GRC))
-#define HW_INTERRUT_ASSERT_SET_0 \
+#define HW_INTERRUPT_ASSERT_SET_0 \
(AEU_INPUTS_ATTN_BITS_TSDM_HW_INTERRUPT | \
AEU_INPUTS_ATTN_BITS_TCM_HW_INTERRUPT | \
AEU_INPUTS_ATTN_BITS_TSEMI_HW_INTERRUPT | \
@@ -2290,7 +2290,7 @@ void bnx2x_igu_clear_sb_gen(struct bnx2x *bp, u8 func, u8 idu_sb_id,
AEU_INPUTS_ATTN_BITS_TSEMI_PARITY_ERROR |\
AEU_INPUTS_ATTN_BITS_TCM_PARITY_ERROR |\
AEU_INPUTS_ATTN_BITS_PBCLIENT_PARITY_ERROR)
-#define HW_INTERRUT_ASSERT_SET_1 \
+#define HW_INTERRUPT_ASSERT_SET_1 \
(AEU_INPUTS_ATTN_BITS_QM_HW_INTERRUPT | \
AEU_INPUTS_ATTN_BITS_TIMERS_HW_INTERRUPT | \
AEU_INPUTS_ATTN_BITS_XSDM_HW_INTERRUPT | \
@@ -2318,7 +2318,7 @@ void bnx2x_igu_clear_sb_gen(struct bnx2x *bp, u8 func, u8 idu_sb_id,
AEU_INPUTS_ATTN_BITS_UPB_PARITY_ERROR | \
AEU_INPUTS_ATTN_BITS_CSDM_PARITY_ERROR |\
AEU_INPUTS_ATTN_BITS_CCM_PARITY_ERROR)
-#define HW_INTERRUT_ASSERT_SET_2 \
+#define HW_INTERRUPT_ASSERT_SET_2 \
(AEU_INPUTS_ATTN_BITS_CSEMI_HW_INTERRUPT | \
AEU_INPUTS_ATTN_BITS_CDU_HW_INTERRUPT | \
AEU_INPUTS_ATTN_BITS_DMAE_HW_INTERRUPT | \
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 9e8c061..ad3e063 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -4277,7 +4277,10 @@ int __bnx2x_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
{
if (tc->type != TC_SETUP_MQPRIO)
return -EINVAL;
- return bnx2x_setup_tc(dev, tc->tc);
+
+ tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+ return bnx2x_setup_tc(dev, tc->mqprio->num_tc);
}
/* called with rtnl_lock */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index d8d06fd..a851f95 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -4166,14 +4166,14 @@ static void bnx2x_attn_int_deasserted0(struct bnx2x *bp, u32 attn)
bnx2x_release_phy_lock(bp);
}
- if (attn & HW_INTERRUT_ASSERT_SET_0) {
+ if (attn & HW_INTERRUPT_ASSERT_SET_0) {
val = REG_RD(bp, reg_offset);
- val &= ~(attn & HW_INTERRUT_ASSERT_SET_0);
+ val &= ~(attn & HW_INTERRUPT_ASSERT_SET_0);
REG_WR(bp, reg_offset, val);
BNX2X_ERR("FATAL HW block attention set0 0x%x\n",
- (u32)(attn & HW_INTERRUT_ASSERT_SET_0));
+ (u32)(attn & HW_INTERRUPT_ASSERT_SET_0));
bnx2x_panic();
}
}
@@ -4191,7 +4191,7 @@ static void bnx2x_attn_int_deasserted1(struct bnx2x *bp, u32 attn)
BNX2X_ERR("FATAL error from DORQ\n");
}
- if (attn & HW_INTERRUT_ASSERT_SET_1) {
+ if (attn & HW_INTERRUPT_ASSERT_SET_1) {
int port = BP_PORT(bp);
int reg_offset;
@@ -4200,11 +4200,11 @@ static void bnx2x_attn_int_deasserted1(struct bnx2x *bp, u32 attn)
MISC_REG_AEU_ENABLE1_FUNC_0_OUT_1);
val = REG_RD(bp, reg_offset);
- val &= ~(attn & HW_INTERRUT_ASSERT_SET_1);
+ val &= ~(attn & HW_INTERRUPT_ASSERT_SET_1);
REG_WR(bp, reg_offset, val);
BNX2X_ERR("FATAL HW block attention set1 0x%x\n",
- (u32)(attn & HW_INTERRUT_ASSERT_SET_1));
+ (u32)(attn & HW_INTERRUPT_ASSERT_SET_1));
bnx2x_panic();
}
}
@@ -4235,7 +4235,7 @@ static void bnx2x_attn_int_deasserted2(struct bnx2x *bp, u32 attn)
}
}
- if (attn & HW_INTERRUT_ASSERT_SET_2) {
+ if (attn & HW_INTERRUPT_ASSERT_SET_2) {
int port = BP_PORT(bp);
int reg_offset;
@@ -4244,11 +4244,11 @@ static void bnx2x_attn_int_deasserted2(struct bnx2x *bp, u32 attn)
MISC_REG_AEU_ENABLE1_FUNC_0_OUT_2);
val = REG_RD(bp, reg_offset);
- val &= ~(attn & HW_INTERRUT_ASSERT_SET_2);
+ val &= ~(attn & HW_INTERRUPT_ASSERT_SET_2);
REG_WR(bp, reg_offset, val);
BNX2X_ERR("FATAL HW block attention set2 0x%x\n",
- (u32)(attn & HW_INTERRUT_ASSERT_SET_2));
+ (u32)(attn & HW_INTERRUPT_ASSERT_SET_2));
bnx2x_panic();
}
}
@@ -13292,17 +13292,15 @@ static int bnx2x_init_dev(struct bnx2x *bp, struct pci_dev *pdev,
dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6 | NETIF_F_HIGHDMA;
- /* VF with OLD Hypervisor or old PF do not support filtering */
if (IS_PF(bp)) {
if (chip_is_e1x)
bp->accept_any_vlan = true;
else
dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
-#ifdef CONFIG_BNX2X_SRIOV
- } else if (bp->acquire_resp.pfdev_info.pf_cap & PFVF_CAP_VLAN_FILTER) {
- dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
-#endif
}
+ /* For VF we'll know whether to enable VLAN filtering after
+ * getting a response to CHANNEL_TLV_ACQUIRE from PF.
+ */
dev->features |= dev->hw_features | NETIF_F_HW_VLAN_CTAG_RX;
dev->features |= NETIF_F_HIGHDMA;
@@ -13738,7 +13736,7 @@ static int bnx2x_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
if (!netif_running(bp->dev)) {
DP(BNX2X_MSG_PTP,
"PTP adjfreq called while the interface is down\n");
- return -EFAULT;
+ return -ENETDOWN;
}
if (ppb < 0) {
@@ -13797,6 +13795,12 @@ static int bnx2x_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
{
struct bnx2x *bp = container_of(ptp, struct bnx2x, ptp_clock_info);
+ if (!netif_running(bp->dev)) {
+ DP(BNX2X_MSG_PTP,
+ "PTP adjtime called while the interface is down\n");
+ return -ENETDOWN;
+ }
+
DP(BNX2X_MSG_PTP, "PTP adjtime called, delta = %llx\n", delta);
timecounter_adjtime(&bp->timecounter, delta);
@@ -13809,6 +13813,12 @@ static int bnx2x_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
struct bnx2x *bp = container_of(ptp, struct bnx2x, ptp_clock_info);
u64 ns;
+ if (!netif_running(bp->dev)) {
+ DP(BNX2X_MSG_PTP,
+ "PTP gettime called while the interface is down\n");
+ return -ENETDOWN;
+ }
+
ns = timecounter_read(&bp->timecounter);
DP(BNX2X_MSG_PTP, "PTP gettime called, ns = %llu\n", ns);
@@ -13824,6 +13834,12 @@ static int bnx2x_ptp_settime(struct ptp_clock_info *ptp,
struct bnx2x *bp = container_of(ptp, struct bnx2x, ptp_clock_info);
u64 ns;
+ if (!netif_running(bp->dev)) {
+ DP(BNX2X_MSG_PTP,
+ "PTP settime called while the interface is down\n");
+ return -ENETDOWN;
+ }
+
ns = timespec64_to_ns(ts);
DP(BNX2X_MSG_PTP, "PTP settime called, ns = %llu\n", ns);
@@ -13991,6 +14007,14 @@ static int bnx2x_init_one(struct pci_dev *pdev,
rc = bnx2x_vfpf_acquire(bp, tx_count, rx_count);
if (rc)
goto init_one_freemem;
+
+#ifdef CONFIG_BNX2X_SRIOV
+ /* VF with OLD Hypervisor or old PF do not support filtering */
+ if (bp->acquire_resp.pfdev_info.pf_cap & PFVF_CAP_VLAN_FILTER) {
+ dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+ dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+ }
+#endif
}
/* Enable SRIOV if capability found in configuration space */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index 6fad22a..bdfd53b 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -434,7 +434,9 @@ static int bnx2x_vf_mac_vlan_config(struct bnx2x *bp,
/* Add/Remove the filter */
rc = bnx2x_config_vlan_mac(bp, &ramrod);
- if (rc && rc != -EEXIST) {
+ if (rc == -EEXIST)
+ return 0;
+ if (rc) {
BNX2X_ERR("Failed to %s %s\n",
filter->add ? "add" : "delete",
(filter->type == BNX2X_VF_FILTER_VLAN_MAC) ?
@@ -444,6 +446,8 @@ static int bnx2x_vf_mac_vlan_config(struct bnx2x *bp,
return rc;
}
+ filter->applied = true;
+
return 0;
}
@@ -469,8 +473,10 @@ int bnx2x_vf_mac_vlan_config_list(struct bnx2x *bp, struct bnx2x_virtf *vf,
/* Rollback if needed */
if (i != filters->count) {
BNX2X_ERR("Managed only %d/%d filters - rolling back\n",
- i, filters->count + 1);
+ i, filters->count);
while (--i >= 0) {
+ if (!filters->filters[i].applied)
+ continue;
filters->filters[i].add = !filters->filters[i].add;
bnx2x_vf_mac_vlan_config(bp, vf, qid,
&filters->filters[i],
@@ -1899,7 +1905,8 @@ void bnx2x_iov_adjust_stats_req(struct bnx2x *bp)
continue;
}
- DP(BNX2X_MSG_IOV, "add addresses for vf %d\n", vf->abs_vfid);
+ DP_AND((BNX2X_MSG_IOV | BNX2X_MSG_STATS),
+ "add addresses for vf %d\n", vf->abs_vfid);
for_each_vfq(vf, j) {
struct bnx2x_vf_queue *rxq = vfq_get(vf, j);
@@ -1920,11 +1927,12 @@ void bnx2x_iov_adjust_stats_req(struct bnx2x *bp)
cpu_to_le32(U64_HI(q_stats_addr));
cur_query_entry->address.lo =
cpu_to_le32(U64_LO(q_stats_addr));
- DP(BNX2X_MSG_IOV,
- "added address %x %x for vf %d queue %d client %d\n",
- cur_query_entry->address.hi,
- cur_query_entry->address.lo, cur_query_entry->funcID,
- j, cur_query_entry->index);
+ DP_AND((BNX2X_MSG_IOV | BNX2X_MSG_STATS),
+ "added address %x %x for vf %d queue %d client %d\n",
+ cur_query_entry->address.hi,
+ cur_query_entry->address.lo,
+ cur_query_entry->funcID,
+ j, cur_query_entry->index);
cur_query_entry++;
cur_data_offset += sizeof(struct per_queue_stats);
stats_count++;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
index 7a6d406..888d0b6 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
@@ -114,6 +114,7 @@ struct bnx2x_vf_mac_vlan_filter {
(BNX2X_VF_FILTER_MAC | BNX2X_VF_FILTER_VLAN) /*shortcut*/
bool add;
+ bool applied;
u8 *mac;
u16 vid;
};
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index bfae300..76a4668 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -868,7 +868,7 @@ int bnx2x_vfpf_set_mcast(struct net_device *dev)
struct bnx2x *bp = netdev_priv(dev);
struct vfpf_set_q_filters_tlv *req = &bp->vf2pf_mbox->req.set_q_filters;
struct pfvf_general_resp_tlv *resp = &bp->vf2pf_mbox->resp.general_resp;
- int rc, i = 0;
+ int rc = 0, i = 0;
struct netdev_hw_addr *ha;
if (bp->state != BNX2X_STATE_OPEN) {
@@ -883,6 +883,15 @@ int bnx2x_vfpf_set_mcast(struct net_device *dev)
/* Get Rx mode requested */
DP(NETIF_MSG_IFUP, "dev->flags = %x\n", dev->flags);
+ /* We support PFVF_MAX_MULTICAST_PER_VF mcast addresses tops */
+ if (netdev_mc_count(dev) > PFVF_MAX_MULTICAST_PER_VF) {
+ DP(NETIF_MSG_IFUP,
+ "VF supports not more than %d multicast MAC addresses\n",
+ PFVF_MAX_MULTICAST_PER_VF);
+ rc = -EINVAL;
+ goto out;
+ }
+
netdev_for_each_mc_addr(ha, dev) {
DP(NETIF_MSG_IFUP, "Adding mcast MAC: %pM\n",
bnx2x_mc_addr(ha));
@@ -890,16 +899,6 @@ int bnx2x_vfpf_set_mcast(struct net_device *dev)
i++;
}
- /* We support four PFVF_MAX_MULTICAST_PER_VF mcast
- * addresses tops
- */
- if (i >= PFVF_MAX_MULTICAST_PER_VF) {
- DP(NETIF_MSG_IFUP,
- "VF supports not more than %d multicast MAC addresses\n",
- PFVF_MAX_MULTICAST_PER_VF);
- return -EINVAL;
- }
-
req->n_multicast = i;
req->flags |= VFPF_SET_Q_FILTERS_MULTICAST_CHANGED;
req->vf_qid = 0;
@@ -924,7 +923,7 @@ int bnx2x_vfpf_set_mcast(struct net_device *dev)
out:
bnx2x_vfpf_finalize(bp, &req->first_tlv);
- return 0;
+ return rc;
}
/* request pf to add a vlan for the vf */
@@ -1778,6 +1777,23 @@ static int bnx2x_vf_mbx_qfilters(struct bnx2x *bp, struct bnx2x_virtf *vf)
goto op_err;
}
+ /* build vlan list */
+ fl = NULL;
+
+ rc = bnx2x_vf_mbx_macvlan_list(bp, vf, msg, &fl,
+ VFPF_VLAN_FILTER);
+ if (rc)
+ goto op_err;
+
+ if (fl) {
+ /* set vlan list */
+ rc = bnx2x_vf_mac_vlan_config_list(bp, vf, fl,
+ msg->vf_qid,
+ false);
+ if (rc)
+ goto op_err;
+ }
+
}
if (msg->flags & VFPF_SET_Q_FILTERS_RX_MASK_CHANGED) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 235733e..129b810 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1983,20 +1983,25 @@ static void bnxt_free_rx_skbs(struct bnxt *bp)
for (j = 0; j < max_idx; j++) {
struct bnxt_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[j];
+ dma_addr_t mapping = rx_buf->mapping;
void *data = rx_buf->data;
if (!data)
continue;
- dma_unmap_single(&pdev->dev, rx_buf->mapping,
- bp->rx_buf_use_size, bp->rx_dir);
-
rx_buf->data = NULL;
- if (BNXT_RX_PAGE_MODE(bp))
+ if (BNXT_RX_PAGE_MODE(bp)) {
+ mapping -= bp->rx_dma_offset;
+ dma_unmap_page(&pdev->dev, mapping,
+ PAGE_SIZE, bp->rx_dir);
__free_page(data);
- else
+ } else {
+ dma_unmap_single(&pdev->dev, mapping,
+ bp->rx_buf_use_size,
+ bp->rx_dir);
kfree(data);
+ }
}
for (j = 0; j < max_agg_idx; j++) {
@@ -2455,6 +2460,18 @@ static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr)
return 0;
}
+static void bnxt_init_cp_rings(struct bnxt *bp)
+{
+ int i;
+
+ for (i = 0; i < bp->cp_nr_rings; i++) {
+ struct bnxt_cp_ring_info *cpr = &bp->bnapi[i]->cp_ring;
+ struct bnxt_ring_struct *ring = &cpr->cp_ring_struct;
+
+ ring->fw_ring_id = INVALID_HW_RING_ID;
+ }
+}
+
static int bnxt_init_rx_rings(struct bnxt *bp)
{
int i, rc = 0;
@@ -4465,6 +4482,10 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
vf->vlan = le16_to_cpu(resp->vlan) & VLAN_VID_MASK;
}
#endif
+ if (BNXT_PF(bp) && (le16_to_cpu(resp->flags) &
+ FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED))
+ bp->flags |= BNXT_FLAG_FW_LLDP_AGENT;
+
switch (resp->port_partition_type) {
case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_0:
case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_5:
@@ -4528,6 +4549,9 @@ static int bnxt_hwrm_func_qcaps(struct bnxt *bp)
pf->max_tx_wm_flows = le32_to_cpu(resp->max_tx_wm_flows);
pf->max_rx_em_flows = le32_to_cpu(resp->max_rx_em_flows);
pf->max_rx_wm_flows = le32_to_cpu(resp->max_rx_wm_flows);
+ if (resp->flags &
+ cpu_to_le32(FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED))
+ bp->flags |= BNXT_FLAG_WOL_CAP;
} else {
#ifdef CONFIG_BNXT_SRIOV
struct bnxt_vf_info *vf = &bp->vf;
@@ -4728,7 +4752,7 @@ static int bnxt_set_tpa(struct bnxt *bp, bool set_tpa)
rc = bnxt_hwrm_vnic_set_tpa(bp, i, tpa_flags);
if (rc) {
netdev_err(bp->dev, "hwrm vnic set tpa failure rc for vnic %d: %x\n",
- rc, i);
+ i, rc);
return rc;
}
}
@@ -5002,6 +5026,7 @@ static int bnxt_shutdown_nic(struct bnxt *bp, bool irq_re_init)
static int bnxt_init_nic(struct bnxt *bp, bool irq_re_init)
{
+ bnxt_init_cp_rings(bp);
bnxt_init_rx_rings(bp);
bnxt_init_tx_rings(bp);
bnxt_init_ring_grps(bp, irq_re_init);
@@ -5176,9 +5201,10 @@ static unsigned int bnxt_get_max_func_irqs(struct bnxt *bp)
{
#if defined(CONFIG_BNXT_SRIOV)
if (BNXT_VF(bp))
- return bp->vf.max_irqs;
+ return min_t(unsigned int, bp->vf.max_irqs,
+ bp->vf.max_cp_rings);
#endif
- return bp->pf.max_irqs;
+ return min_t(unsigned int, bp->pf.max_irqs, bp->pf.max_cp_rings);
}
void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max_irqs)
@@ -5507,8 +5533,9 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp)
bp->lpi_tmr_hi = le32_to_cpu(resp->valid_tx_lpi_timer_high) &
PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_HIGH_MASK;
}
- link_info->support_auto_speeds =
- le16_to_cpu(resp->supported_speeds_auto_mode);
+ if (resp->supported_speeds_auto_mode)
+ link_info->support_auto_speeds =
+ le16_to_cpu(resp->supported_speeds_auto_mode);
hwrm_phy_qcaps_exit:
mutex_unlock(&bp->hwrm_cmd_lock);
@@ -5834,6 +5861,76 @@ static int bnxt_hwrm_port_led_qcaps(struct bnxt *bp)
return 0;
}
+int bnxt_hwrm_alloc_wol_fltr(struct bnxt *bp)
+{
+ struct hwrm_wol_filter_alloc_input req = {0};
+ struct hwrm_wol_filter_alloc_output *resp = bp->hwrm_cmd_resp_addr;
+ int rc;
+
+ bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_WOL_FILTER_ALLOC, -1, -1);
+ req.port_id = cpu_to_le16(bp->pf.port_id);
+ req.wol_type = WOL_FILTER_ALLOC_REQ_WOL_TYPE_MAGICPKT;
+ req.enables = cpu_to_le32(WOL_FILTER_ALLOC_REQ_ENABLES_MAC_ADDRESS);
+ memcpy(req.mac_address, bp->dev->dev_addr, ETH_ALEN);
+ mutex_lock(&bp->hwrm_cmd_lock);
+ rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+ if (!rc)
+ bp->wol_filter_id = resp->wol_filter_id;
+ mutex_unlock(&bp->hwrm_cmd_lock);
+ return rc;
+}
+
+int bnxt_hwrm_free_wol_fltr(struct bnxt *bp)
+{
+ struct hwrm_wol_filter_free_input req = {0};
+ int rc;
+
+ bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_WOL_FILTER_FREE, -1, -1);
+ req.port_id = cpu_to_le16(bp->pf.port_id);
+ req.enables = cpu_to_le32(WOL_FILTER_FREE_REQ_ENABLES_WOL_FILTER_ID);
+ req.wol_filter_id = bp->wol_filter_id;
+ rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+ return rc;
+}
+
+static u16 bnxt_hwrm_get_wol_fltrs(struct bnxt *bp, u16 handle)
+{
+ struct hwrm_wol_filter_qcfg_input req = {0};
+ struct hwrm_wol_filter_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
+ u16 next_handle = 0;
+ int rc;
+
+ bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_WOL_FILTER_QCFG, -1, -1);
+ req.port_id = cpu_to_le16(bp->pf.port_id);
+ req.handle = cpu_to_le16(handle);
+ mutex_lock(&bp->hwrm_cmd_lock);
+ rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+ if (!rc) {
+ next_handle = le16_to_cpu(resp->next_handle);
+ if (next_handle != 0) {
+ if (resp->wol_type ==
+ WOL_FILTER_ALLOC_REQ_WOL_TYPE_MAGICPKT) {
+ bp->wol = 1;
+ bp->wol_filter_id = resp->wol_filter_id;
+ }
+ }
+ }
+ mutex_unlock(&bp->hwrm_cmd_lock);
+ return next_handle;
+}
+
+static void bnxt_get_wol_settings(struct bnxt *bp)
+{
+ u16 handle = 0;
+
+ if (!BNXT_PF(bp) || !(bp->flags & BNXT_FLAG_WOL_CAP))
+ return;
+
+ do {
+ handle = bnxt_hwrm_get_wol_fltrs(bp, handle);
+ } while (handle && handle != 0xffff);
+}
+
static bool bnxt_eee_config_ok(struct bnxt *bp)
{
struct ethtool_eee *eee = &bp->eee;
@@ -6019,6 +6116,43 @@ int bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
return rc;
}
+/* rtnl_lock held, open the NIC half way by allocating all resources, but
+ * NAPI, IRQ, and TX are not enabled. This is mainly used for offline
+ * self tests.
+ */
+int bnxt_half_open_nic(struct bnxt *bp)
+{
+ int rc = 0;
+
+ rc = bnxt_alloc_mem(bp, false);
+ if (rc) {
+ netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc);
+ goto half_open_err;
+ }
+ rc = bnxt_init_nic(bp, false);
+ if (rc) {
+ netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc);
+ goto half_open_err;
+ }
+ return 0;
+
+half_open_err:
+ bnxt_free_skbs(bp);
+ bnxt_free_mem(bp, false);
+ dev_close(bp->dev);
+ return rc;
+}
+
+/* rtnl_lock held, this call can only be made after a previous successful
+ * call to bnxt_half_open_nic().
+ */
+void bnxt_half_close_nic(struct bnxt *bp)
+{
+ bnxt_hwrm_resource_free(bp, false, false);
+ bnxt_free_skbs(bp);
+ bnxt_free_mem(bp, false);
+}
+
static int bnxt_open(struct net_device *dev)
{
struct bnxt *bp = netdev_priv(dev);
@@ -6495,8 +6629,14 @@ static void bnxt_reset_task(struct bnxt *bp, bool silent)
if (!silent)
bnxt_dbg_dump_states(bp);
if (netif_running(bp->dev)) {
+ int rc;
+
+ if (!silent)
+ bnxt_ulp_stop(bp);
bnxt_close_nic(bp, false, false);
- bnxt_open_nic(bp, false, false);
+ rc = bnxt_open_nic(bp, false, false);
+ if (!silent && !rc)
+ bnxt_ulp_start(bp);
}
}
@@ -6894,7 +7034,9 @@ static int bnxt_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
if (ntc->type != TC_SETUP_MQPRIO)
return -EINVAL;
- return bnxt_setup_mq_tc(dev, ntc->tc);
+ ntc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+ return bnxt_setup_mq_tc(dev, ntc->mqprio->num_tc);
}
#ifdef CONFIG_RFS_ACCEL
@@ -7195,6 +7337,7 @@ static void bnxt_remove_one(struct pci_dev *pdev)
bnxt_clear_int_mode(bp);
bnxt_hwrm_func_drv_unrgtr(bp);
bnxt_free_hwrm_resources(bp);
+ bnxt_ethtool_free(bp);
bnxt_dcb_free(bp);
kfree(bp->edev);
bp->edev = NULL;
@@ -7444,6 +7587,10 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
if (rc)
goto init_err_pci_clean;
+ rc = bnxt_hwrm_func_reset(bp);
+ if (rc)
+ goto init_err_pci_clean;
+
bnxt_hwrm_fw_set_time(bp);
dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG |
@@ -7513,6 +7660,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
bnxt_hwrm_func_qcfg(bp);
bnxt_hwrm_port_led_qcaps(bp);
+ bnxt_ethtool_init(bp);
bnxt_set_rx_skb_mode(bp, false);
bnxt_set_tpa_flags(bp);
@@ -7554,14 +7702,16 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
if (rc)
goto init_err_pci_clean;
- rc = bnxt_hwrm_func_reset(bp);
- if (rc)
- goto init_err_pci_clean;
-
rc = bnxt_init_int_mode(bp);
if (rc)
goto init_err_pci_clean;
+ bnxt_get_wol_settings(bp);
+ if (bp->flags & BNXT_FLAG_WOL_CAP)
+ device_set_wakeup_enable(&pdev->dev, bp->wol);
+ else
+ device_set_wakeup_capable(&pdev->dev, false);
+
rc = register_netdev(dev);
if (rc)
goto init_err_clr_int;
@@ -7585,6 +7735,88 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
return rc;
}
+static void bnxt_shutdown(struct pci_dev *pdev)
+{
+ struct net_device *dev = pci_get_drvdata(pdev);
+ struct bnxt *bp;
+
+ if (!dev)
+ return;
+
+ rtnl_lock();
+ bp = netdev_priv(dev);
+ if (!bp)
+ goto shutdown_exit;
+
+ if (netif_running(dev))
+ dev_close(dev);
+
+ if (system_state == SYSTEM_POWER_OFF) {
+ bnxt_clear_int_mode(bp);
+ pci_wake_from_d3(pdev, bp->wol);
+ pci_set_power_state(pdev, PCI_D3hot);
+ }
+
+shutdown_exit:
+ rtnl_unlock();
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int bnxt_suspend(struct device *device)
+{
+ struct pci_dev *pdev = to_pci_dev(device);
+ struct net_device *dev = pci_get_drvdata(pdev);
+ struct bnxt *bp = netdev_priv(dev);
+ int rc = 0;
+
+ rtnl_lock();
+ if (netif_running(dev)) {
+ netif_device_detach(dev);
+ rc = bnxt_close(dev);
+ }
+ bnxt_hwrm_func_drv_unrgtr(bp);
+ rtnl_unlock();
+ return rc;
+}
+
+static int bnxt_resume(struct device *device)
+{
+ struct pci_dev *pdev = to_pci_dev(device);
+ struct net_device *dev = pci_get_drvdata(pdev);
+ struct bnxt *bp = netdev_priv(dev);
+ int rc = 0;
+
+ rtnl_lock();
+ if (bnxt_hwrm_ver_get(bp) || bnxt_hwrm_func_drv_rgtr(bp)) {
+ rc = -ENODEV;
+ goto resume_exit;
+ }
+ rc = bnxt_hwrm_func_reset(bp);
+ if (rc) {
+ rc = -EBUSY;
+ goto resume_exit;
+ }
+ bnxt_get_wol_settings(bp);
+ if (netif_running(dev)) {
+ rc = bnxt_open(dev);
+ if (!rc)
+ netif_device_attach(dev);
+ }
+
+resume_exit:
+ rtnl_unlock();
+ return rc;
+}
+
+static SIMPLE_DEV_PM_OPS(bnxt_pm_ops, bnxt_suspend, bnxt_resume);
+#define BNXT_PM_OPS (&bnxt_pm_ops)
+
+#else
+
+#define BNXT_PM_OPS NULL
+
+#endif /* CONFIG_PM_SLEEP */
+
/**
* bnxt_io_error_detected - called when PCI error is detected
* @pdev: Pointer to PCI device
@@ -7701,6 +7933,8 @@ static struct pci_driver bnxt_pci_driver = {
.id_table = bnxt_pci_tbl,
.probe = bnxt_init_one,
.remove = bnxt_remove_one,
+ .shutdown = bnxt_shutdown,
+ .driver.pm = BNXT_PM_OPS,
.err_handler = &bnxt_err_handler,
#if defined(CONFIG_BNXT_SRIOV)
.sriov_configure = bnxt_sriov_configure,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index faf26a2..c9a1688a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -18,6 +18,8 @@
#define DRV_VER_MIN 7
#define DRV_VER_UPD 0
+#include <linux/interrupt.h>
+
struct tx_bd {
__le32 tx_bd_len_flags_type;
#define TX_BD_TYPE (0x3f << 0)
@@ -424,8 +426,6 @@ struct rx_tpa_end_cmp_ext {
#define BNXT_MIN_PKT_SIZE 52
-#define BNXT_NUM_TESTS(bp) 0
-
#define BNXT_DEFAULT_RX_RING_SIZE 511
#define BNXT_DEFAULT_TX_RING_SIZE 511
@@ -909,6 +909,14 @@ struct bnxt_led_info {
__le16 led_color_caps;
};
+#define BNXT_MAX_TEST 8
+
+struct bnxt_test_info {
+ u8 offline_mask;
+ u16 timeout;
+ char string[BNXT_MAX_TEST][ETH_GSTRING_LEN];
+};
+
#define BNXT_GRCPF_REG_WINDOW_BASE_OUT 0x400
#define BNXT_CAG_REG_LEGACY_INT_STATUS 0x4014
#define BNXT_CAG_REG_BASE 0x300000
@@ -987,12 +995,14 @@ struct bnxt {
#define BNXT_FLAG_UDP_RSS_CAP 0x800
#define BNXT_FLAG_EEE_CAP 0x1000
#define BNXT_FLAG_NEW_RSS_CAP 0x2000
+ #define BNXT_FLAG_WOL_CAP 0x4000
#define BNXT_FLAG_ROCEV1_CAP 0x8000
#define BNXT_FLAG_ROCEV2_CAP 0x10000
#define BNXT_FLAG_ROCE_CAP (BNXT_FLAG_ROCEV1_CAP | \
BNXT_FLAG_ROCEV2_CAP)
#define BNXT_FLAG_NO_AGG_RINGS 0x20000
#define BNXT_FLAG_RX_PAGE_MODE 0x40000
+ #define BNXT_FLAG_FW_LLDP_AGENT 0x80000
#define BNXT_FLAG_CHIP_NITRO_A0 0x1000000
#define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA | \
@@ -1177,6 +1187,12 @@ struct bnxt {
u32 lpi_tmr_lo;
u32 lpi_tmr_hi;
+ u8 num_tests;
+ struct bnxt_test_info *test_info;
+
+ u8 wol_filter_id;
+ u8 wol;
+
u8 num_leds;
struct bnxt_led_info leds[BNXT_MAX_LED];
@@ -1235,8 +1251,12 @@ void bnxt_tx_disable(struct bnxt *bp);
void bnxt_tx_enable(struct bnxt *bp);
int bnxt_hwrm_set_pause(struct bnxt *);
int bnxt_hwrm_set_link_setting(struct bnxt *, bool, bool);
+int bnxt_hwrm_alloc_wol_fltr(struct bnxt *bp);
+int bnxt_hwrm_free_wol_fltr(struct bnxt *bp);
int bnxt_hwrm_fw_set_time(struct bnxt *);
int bnxt_open_nic(struct bnxt *, bool, bool);
+int bnxt_half_open_nic(struct bnxt *bp);
+void bnxt_half_close_nic(struct bnxt *bp);
int bnxt_close_nic(struct bnxt *, bool, bool);
int bnxt_reserve_rings(struct bnxt *bp, int tx, int rx, int tcs, int tx_xdp);
int bnxt_setup_mq_tc(struct net_device *dev, u8 tc);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index fdf2d8c..03532061 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -474,7 +474,7 @@ void bnxt_dcb_init(struct bnxt *bp)
return;
bp->dcbx_cap = DCB_CAP_DCBX_VER_IEEE;
- if (BNXT_PF(bp))
+ if (BNXT_PF(bp) && !(bp->flags & BNXT_FLAG_FW_LLDP_AGENT))
bp->dcbx_cap |= DCB_CAP_DCBX_HOST;
else
bp->dcbx_cap |= DCB_CAP_DCBX_LLD_MANAGED;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 6903a87..848ecf2 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1,6 +1,7 @@
/* Broadcom NetXtreme-C/E network driver.
*
* Copyright (c) 2014-2016 Broadcom Corporation
+ * Copyright (c) 2016-2017 Broadcom Limited
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -17,6 +18,7 @@
#include <linux/firmware.h>
#include "bnxt_hsi.h"
#include "bnxt.h"
+#include "bnxt_xdp.h"
#include "bnxt_ethtool.h"
#include "bnxt_nvm_defs.h" /* NVRAM content constant and structure defs */
#include "bnxt_fw_hdr.h" /* Firmware hdr constant and structure defs */
@@ -209,6 +211,10 @@ static int bnxt_get_sset_count(struct net_device *dev, int sset)
return num_stats;
}
+ case ETH_SS_TEST:
+ if (!bp->num_tests)
+ return -EOPNOTSUPP;
+ return bp->num_tests;
default:
return -EOPNOTSUPP;
}
@@ -306,6 +312,11 @@ static void bnxt_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
}
}
break;
+ case ETH_SS_TEST:
+ if (bp->num_tests)
+ memcpy(buf, bp->test_info->string,
+ bp->num_tests * ETH_GSTRING_LEN);
+ break;
default:
netdev_err(bp->dev, "bnxt_get_strings invalid request %x\n",
stringset);
@@ -824,7 +835,7 @@ static void bnxt_get_drvinfo(struct net_device *dev,
sizeof(info->fw_version));
strlcpy(info->bus_info, pci_name(bp->pdev), sizeof(info->bus_info));
info->n_stats = BNXT_NUM_STATS * bp->cp_nr_rings;
- info->testinfo_len = BNXT_NUM_TESTS(bp);
+ info->testinfo_len = bp->num_tests;
/* TODO CHIMP_FW: eeprom dump details */
info->eedump_len = 0;
/* TODO CHIMP FW: reg dump details */
@@ -832,6 +843,45 @@ static void bnxt_get_drvinfo(struct net_device *dev,
kfree(pkglog);
}
+static void bnxt_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
+{
+ struct bnxt *bp = netdev_priv(dev);
+
+ wol->supported = 0;
+ wol->wolopts = 0;
+ memset(&wol->sopass, 0, sizeof(wol->sopass));
+ if (bp->flags & BNXT_FLAG_WOL_CAP) {
+ wol->supported = WAKE_MAGIC;
+ if (bp->wol)
+ wol->wolopts = WAKE_MAGIC;
+ }
+}
+
+static int bnxt_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
+{
+ struct bnxt *bp = netdev_priv(dev);
+
+ if (wol->wolopts & ~WAKE_MAGIC)
+ return -EINVAL;
+
+ if (wol->wolopts & WAKE_MAGIC) {
+ if (!(bp->flags & BNXT_FLAG_WOL_CAP))
+ return -EINVAL;
+ if (!bp->wol) {
+ if (bnxt_hwrm_alloc_wol_fltr(bp))
+ return -EBUSY;
+ bp->wol = 1;
+ }
+ } else {
+ if (bp->wol) {
+ if (bnxt_hwrm_free_wol_fltr(bp))
+ return -EBUSY;
+ bp->wol = 0;
+ }
+ }
+ return 0;
+}
+
u32 _bnxt_fw_to_ethtool_adv_spds(u16 fw_speeds, u8 fw_pause)
{
u32 speed_mask = 0;
@@ -2128,12 +2178,372 @@ static int bnxt_set_phys_id(struct net_device *dev,
return rc;
}
+static int bnxt_hwrm_selftest_irq(struct bnxt *bp, u16 cmpl_ring)
+{
+ struct hwrm_selftest_irq_input req = {0};
+
+ bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_SELFTEST_IRQ, cmpl_ring, -1);
+ return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+}
+
+static int bnxt_test_irq(struct bnxt *bp)
+{
+ int i;
+
+ for (i = 0; i < bp->cp_nr_rings; i++) {
+ u16 cmpl_ring = bp->grp_info[i].cp_fw_ring_id;
+ int rc;
+
+ rc = bnxt_hwrm_selftest_irq(bp, cmpl_ring);
+ if (rc)
+ return rc;
+ }
+ return 0;
+}
+
+static int bnxt_hwrm_mac_loopback(struct bnxt *bp, bool enable)
+{
+ struct hwrm_port_mac_cfg_input req = {0};
+
+ bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_MAC_CFG, -1, -1);
+
+ req.enables = cpu_to_le32(PORT_MAC_CFG_REQ_ENABLES_LPBK);
+ if (enable)
+ req.lpbk = PORT_MAC_CFG_REQ_LPBK_LOCAL;
+ else
+ req.lpbk = PORT_MAC_CFG_REQ_LPBK_NONE;
+ return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+}
+
+static int bnxt_disable_an_for_lpbk(struct bnxt *bp,
+ struct hwrm_port_phy_cfg_input *req)
+{
+ struct bnxt_link_info *link_info = &bp->link_info;
+ u16 fw_advertising = link_info->advertising;
+ u16 fw_speed;
+ int rc;
+
+ if (!link_info->autoneg)
+ return 0;
+
+ fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_1GB;
+ if (netif_carrier_ok(bp->dev))
+ fw_speed = bp->link_info.link_speed;
+ else if (fw_advertising & BNXT_LINK_SPEED_MSK_10GB)
+ fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_10GB;
+ else if (fw_advertising & BNXT_LINK_SPEED_MSK_25GB)
+ fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_25GB;
+ else if (fw_advertising & BNXT_LINK_SPEED_MSK_40GB)
+ fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_40GB;
+ else if (fw_advertising & BNXT_LINK_SPEED_MSK_50GB)
+ fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_50GB;
+
+ req->force_link_speed = cpu_to_le16(fw_speed);
+ req->flags |= cpu_to_le32(PORT_PHY_CFG_REQ_FLAGS_FORCE |
+ PORT_PHY_CFG_REQ_FLAGS_RESET_PHY);
+ rc = hwrm_send_message(bp, req, sizeof(*req), HWRM_CMD_TIMEOUT);
+ req->flags = 0;
+ req->force_link_speed = cpu_to_le16(0);
+ return rc;
+}
+
+static int bnxt_hwrm_phy_loopback(struct bnxt *bp, bool enable)
+{
+ struct hwrm_port_phy_cfg_input req = {0};
+
+ bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_CFG, -1, -1);
+
+ if (enable) {
+ bnxt_disable_an_for_lpbk(bp, &req);
+ req.lpbk = PORT_PHY_CFG_REQ_LPBK_LOCAL;
+ } else {
+ req.lpbk = PORT_PHY_CFG_REQ_LPBK_NONE;
+ }
+ req.enables = cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_LPBK);
+ return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+}
+
+static int bnxt_rx_loopback(struct bnxt *bp, struct bnxt_napi *bnapi,
+ u32 raw_cons, int pkt_size)
+{
+ struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
+ struct bnxt_rx_ring_info *rxr = bnapi->rx_ring;
+ struct bnxt_sw_rx_bd *rx_buf;
+ struct rx_cmp *rxcmp;
+ u16 cp_cons, cons;
+ u8 *data;
+ u32 len;
+ int i;
+
+ cp_cons = RING_CMP(raw_cons);
+ rxcmp = (struct rx_cmp *)
+ &cpr->cp_desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)];
+ cons = rxcmp->rx_cmp_opaque;
+ rx_buf = &rxr->rx_buf_ring[cons];
+ data = rx_buf->data_ptr;
+ len = le32_to_cpu(rxcmp->rx_cmp_len_flags_type) >> RX_CMP_LEN_SHIFT;
+ if (len != pkt_size)
+ return -EIO;
+ i = ETH_ALEN;
+ if (!ether_addr_equal(data + i, bnapi->bp->dev->dev_addr))
+ return -EIO;
+ i += ETH_ALEN;
+ for ( ; i < pkt_size; i++) {
+ if (data[i] != (u8)(i & 0xff))
+ return -EIO;
+ }
+ return 0;
+}
+
+static int bnxt_poll_loopback(struct bnxt *bp, int pkt_size)
+{
+ struct bnxt_napi *bnapi = bp->bnapi[0];
+ struct bnxt_cp_ring_info *cpr;
+ struct tx_cmp *txcmp;
+ int rc = -EIO;
+ u32 raw_cons;
+ u32 cons;
+ int i;
+
+ cpr = &bnapi->cp_ring;
+ raw_cons = cpr->cp_raw_cons;
+ for (i = 0; i < 200; i++) {
+ cons = RING_CMP(raw_cons);
+ txcmp = &cpr->cp_desc_ring[CP_RING(cons)][CP_IDX(cons)];
+
+ if (!TX_CMP_VALID(txcmp, raw_cons)) {
+ udelay(5);
+ continue;
+ }
+
+ /* The valid test of the entry must be done first before
+ * reading any further.
+ */
+ dma_rmb();
+ if (TX_CMP_TYPE(txcmp) == CMP_TYPE_RX_L2_CMP) {
+ rc = bnxt_rx_loopback(bp, bnapi, raw_cons, pkt_size);
+ raw_cons = NEXT_RAW_CMP(raw_cons);
+ raw_cons = NEXT_RAW_CMP(raw_cons);
+ break;
+ }
+ raw_cons = NEXT_RAW_CMP(raw_cons);
+ }
+ cpr->cp_raw_cons = raw_cons;
+ return rc;
+}
+
+static int bnxt_run_loopback(struct bnxt *bp)
+{
+ struct bnxt_tx_ring_info *txr = &bp->tx_ring[0];
+ int pkt_size, i = 0;
+ struct sk_buff *skb;
+ dma_addr_t map;
+ u8 *data;
+ int rc;
+
+ pkt_size = min(bp->dev->mtu + ETH_HLEN, bp->rx_copy_thresh);
+ skb = netdev_alloc_skb(bp->dev, pkt_size);
+ if (!skb)
+ return -ENOMEM;
+ data = skb_put(skb, pkt_size);
+ eth_broadcast_addr(data);
+ i += ETH_ALEN;
+ ether_addr_copy(&data[i], bp->dev->dev_addr);
+ i += ETH_ALEN;
+ for ( ; i < pkt_size; i++)
+ data[i] = (u8)(i & 0xff);
+
+ map = dma_map_single(&bp->pdev->dev, skb->data, pkt_size,
+ PCI_DMA_TODEVICE);
+ if (dma_mapping_error(&bp->pdev->dev, map)) {
+ dev_kfree_skb(skb);
+ return -EIO;
+ }
+ bnxt_xmit_xdp(bp, txr, map, pkt_size, 0);
+
+ /* Sync BD data before updating doorbell */
+ wmb();
+
+ writel(DB_KEY_TX | txr->tx_prod, txr->tx_doorbell);
+ writel(DB_KEY_TX | txr->tx_prod, txr->tx_doorbell);
+ rc = bnxt_poll_loopback(bp, pkt_size);
+
+ dma_unmap_single(&bp->pdev->dev, map, pkt_size, PCI_DMA_TODEVICE);
+ dev_kfree_skb(skb);
+ return rc;
+}
+
+static int bnxt_run_fw_tests(struct bnxt *bp, u8 test_mask, u8 *test_results)
+{
+ struct hwrm_selftest_exec_output *resp = bp->hwrm_cmd_resp_addr;
+ struct hwrm_selftest_exec_input req = {0};
+ int rc;
+
+ bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_SELFTEST_EXEC, -1, -1);
+ mutex_lock(&bp->hwrm_cmd_lock);
+ resp->test_success = 0;
+ req.flags = test_mask;
+ rc = _hwrm_send_message(bp, &req, sizeof(req), bp->test_info->timeout);
+ *test_results = resp->test_success;
+ mutex_unlock(&bp->hwrm_cmd_lock);
+ return rc;
+}
+
+#define BNXT_DRV_TESTS 3
+#define BNXT_MACLPBK_TEST_IDX (bp->num_tests - BNXT_DRV_TESTS)
+#define BNXT_PHYLPBK_TEST_IDX (BNXT_MACLPBK_TEST_IDX + 1)
+#define BNXT_IRQ_TEST_IDX (BNXT_MACLPBK_TEST_IDX + 2)
+
+static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
+ u64 *buf)
+{
+ struct bnxt *bp = netdev_priv(dev);
+ bool offline = false;
+ u8 test_results = 0;
+ u8 test_mask = 0;
+ int rc, i;
+
+ if (!bp->num_tests || !BNXT_SINGLE_PF(bp))
+ return;
+ memset(buf, 0, sizeof(u64) * bp->num_tests);
+ if (!netif_running(dev)) {
+ etest->flags |= ETH_TEST_FL_FAILED;
+ return;
+ }
+
+ if (etest->flags & ETH_TEST_FL_OFFLINE) {
+ if (bp->pf.active_vfs) {
+ etest->flags |= ETH_TEST_FL_FAILED;
+ netdev_warn(dev, "Offline tests cannot be run with active VFs\n");
+ return;
+ }
+ offline = true;
+ }
+
+ for (i = 0; i < bp->num_tests - BNXT_DRV_TESTS; i++) {
+ u8 bit_val = 1 << i;
+
+ if (!(bp->test_info->offline_mask & bit_val))
+ test_mask |= bit_val;
+ else if (offline)
+ test_mask |= bit_val;
+ }
+ if (!offline) {
+ bnxt_run_fw_tests(bp, test_mask, &test_results);
+ } else {
+ rc = bnxt_close_nic(bp, false, false);
+ if (rc)
+ return;
+ bnxt_run_fw_tests(bp, test_mask, &test_results);
+
+ buf[BNXT_MACLPBK_TEST_IDX] = 1;
+ bnxt_hwrm_mac_loopback(bp, true);
+ msleep(250);
+ rc = bnxt_half_open_nic(bp);
+ if (rc) {
+ bnxt_hwrm_mac_loopback(bp, false);
+ etest->flags |= ETH_TEST_FL_FAILED;
+ return;
+ }
+ if (bnxt_run_loopback(bp))
+ etest->flags |= ETH_TEST_FL_FAILED;
+ else
+ buf[BNXT_MACLPBK_TEST_IDX] = 0;
+
+ bnxt_hwrm_mac_loopback(bp, false);
+ bnxt_hwrm_phy_loopback(bp, true);
+ msleep(1000);
+ if (bnxt_run_loopback(bp)) {
+ buf[BNXT_PHYLPBK_TEST_IDX] = 1;
+ etest->flags |= ETH_TEST_FL_FAILED;
+ }
+ bnxt_hwrm_phy_loopback(bp, false);
+ bnxt_half_close_nic(bp);
+ bnxt_open_nic(bp, false, true);
+ }
+ if (bnxt_test_irq(bp)) {
+ buf[BNXT_IRQ_TEST_IDX] = 1;
+ etest->flags |= ETH_TEST_FL_FAILED;
+ }
+ for (i = 0; i < bp->num_tests - BNXT_DRV_TESTS; i++) {
+ u8 bit_val = 1 << i;
+
+ if ((test_mask & bit_val) && !(test_results & bit_val)) {
+ buf[i] = 1;
+ etest->flags |= ETH_TEST_FL_FAILED;
+ }
+ }
+}
+
+void bnxt_ethtool_init(struct bnxt *bp)
+{
+ struct hwrm_selftest_qlist_output *resp = bp->hwrm_cmd_resp_addr;
+ struct hwrm_selftest_qlist_input req = {0};
+ struct bnxt_test_info *test_info;
+ int i, rc;
+
+ if (bp->hwrm_spec_code < 0x10704 || !BNXT_SINGLE_PF(bp))
+ return;
+
+ bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_SELFTEST_QLIST, -1, -1);
+ mutex_lock(&bp->hwrm_cmd_lock);
+ rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+ if (rc)
+ goto ethtool_init_exit;
+
+ test_info = kzalloc(sizeof(*bp->test_info), GFP_KERNEL);
+ if (!test_info)
+ goto ethtool_init_exit;
+
+ bp->test_info = test_info;
+ bp->num_tests = resp->num_tests + BNXT_DRV_TESTS;
+ if (bp->num_tests > BNXT_MAX_TEST)
+ bp->num_tests = BNXT_MAX_TEST;
+
+ test_info->offline_mask = resp->offline_tests;
+ test_info->timeout = le16_to_cpu(resp->test_timeout);
+ if (!test_info->timeout)
+ test_info->timeout = HWRM_CMD_TIMEOUT;
+ for (i = 0; i < bp->num_tests; i++) {
+ char *str = test_info->string[i];
+ char *fw_str = resp->test0_name + i * 32;
+
+ if (i == BNXT_MACLPBK_TEST_IDX) {
+ strcpy(str, "Mac loopback test (offline)");
+ } else if (i == BNXT_PHYLPBK_TEST_IDX) {
+ strcpy(str, "Phy loopback test (offline)");
+ } else if (i == BNXT_IRQ_TEST_IDX) {
+ strcpy(str, "Interrupt_test (offline)");
+ } else {
+ strlcpy(str, fw_str, ETH_GSTRING_LEN);
+ strncat(str, " test", ETH_GSTRING_LEN - strlen(str));
+ if (test_info->offline_mask & (1 << i))
+ strncat(str, " (offline)",
+ ETH_GSTRING_LEN - strlen(str));
+ else
+ strncat(str, " (online)",
+ ETH_GSTRING_LEN - strlen(str));
+ }
+ }
+
+ethtool_init_exit:
+ mutex_unlock(&bp->hwrm_cmd_lock);
+}
+
+void bnxt_ethtool_free(struct bnxt *bp)
+{
+ kfree(bp->test_info);
+ bp->test_info = NULL;
+}
+
const struct ethtool_ops bnxt_ethtool_ops = {
.get_link_ksettings = bnxt_get_link_ksettings,
.set_link_ksettings = bnxt_set_link_ksettings,
.get_pauseparam = bnxt_get_pauseparam,
.set_pauseparam = bnxt_set_pauseparam,
.get_drvinfo = bnxt_get_drvinfo,
+ .get_wol = bnxt_get_wol,
+ .set_wol = bnxt_set_wol,
.get_coalesce = bnxt_get_coalesce,
.set_coalesce = bnxt_set_coalesce,
.get_msglevel = bnxt_get_msglevel,
@@ -2161,4 +2571,5 @@ const struct ethtool_ops bnxt_ethtool_ops = {
.get_module_eeprom = bnxt_get_module_eeprom,
.nway_reset = bnxt_nway_reset,
.set_phys_id = bnxt_set_phys_id,
+ .self_test = bnxt_self_test,
};
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
index ed1e555..f1bc90b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
@@ -1,6 +1,7 @@
/* Broadcom NetXtreme-C/E network driver.
*
* Copyright (c) 2014-2016 Broadcom Corporation
+ * Copyright (c) 2016-2017 Broadcom Limited
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -38,5 +39,7 @@ extern const struct ethtool_ops bnxt_ethtool_ops;
u32 _bnxt_fw_to_ethtool_adv_spds(u16, u8);
u32 bnxt_fw_to_ethtool_speed(u16);
u16 bnxt_get_fw_auto_link_speeds(u32);
+void bnxt_ethtool_init(struct bnxt *bp);
+void bnxt_ethtool_free(struct bnxt *bp);
#endif
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index 6e275c2..7dc71bb 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -11,19 +11,21 @@
#ifndef BNXT_HSI_H
#define BNXT_HSI_H
-/* HSI and HWRM Specification 1.7.0 */
+/* HSI and HWRM Specification 1.7.6 */
#define HWRM_VERSION_MAJOR 1
#define HWRM_VERSION_MINOR 7
-#define HWRM_VERSION_UPDATE 0
+#define HWRM_VERSION_UPDATE 6
-#define HWRM_VERSION_STR "1.7.0"
+#define HWRM_VERSION_RSVD 2 /* non-zero means beta version */
+
+#define HWRM_VERSION_STR "1.7.6.2"
/*
* Following is the signature for HWRM message field that indicates not
* applicable (All F's). Need to cast it the size of the field if needed.
*/
#define HWRM_NA_SIGNATURE ((__le32)(-1))
#define HWRM_MAX_REQ_LEN (128) /* hwrm_func_buf_rgtr */
-#define HWRM_MAX_RESP_LEN (176) /* hwrm_func_qstats */
+#define HWRM_MAX_RESP_LEN (248) /* hwrm_selftest_qlist */
#define HW_HASH_INDEX_SIZE 0x80 /* 7 bit indirection table index. */
#define HW_HASH_KEY_SIZE 40
#define HWRM_RESP_VALID_KEY 1 /* valid key for HWRM response */
@@ -571,9 +573,10 @@ struct hwrm_ver_get_output {
__le16 max_req_win_len;
__le16 max_resp_len;
__le16 def_req_timeout;
+ u8 init_pending;
+ #define VER_GET_RESP_INIT_PENDING_DEV_NOT_RDY 0x1UL
u8 unused_0;
u8 unused_1;
- u8 unused_2;
u8 valid;
};
@@ -809,6 +812,8 @@ struct hwrm_func_qcfg_output {
#define FUNC_QCFG_RESP_FLAGS_OOB_WOL_BMP_ENABLED 0x2UL
#define FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED 0x4UL
#define FUNC_QCFG_RESP_FLAGS_STD_TX_RING_MODE_ENABLED 0x8UL
+ #define FUNC_QCFG_RESP_FLAGS_FW_LLDP_AGENT_ENABLED 0x10UL
+ #define FUNC_QCFG_RESP_FLAGS_MULTI_HOST 0x20UL
u8 mac_address[6];
__le16 pci_id;
__le16 alloc_rsscos_ctx;
@@ -827,10 +832,12 @@ struct hwrm_func_qcfg_output {
#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_5 0x3UL
#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR2_0 0x4UL
#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_UNKNOWN 0xffUL
- u8 unused_0;
+ u8 port_pf_cnt;
+ #define FUNC_QCFG_RESP_PORT_PF_CNT_UNAVAIL 0x0UL
__le16 dflt_vnic_id;
- u8 unused_1;
- u8 unused_2;
+ u8 host_cnt;
+ #define FUNC_QCFG_RESP_HOST_CNT_UNAVAIL 0x0UL
+ u8 unused_0;
__le32 min_bw;
#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_MASK 0xfffffffUL
#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_SFT 0
@@ -867,12 +874,12 @@ struct hwrm_func_qcfg_output {
#define FUNC_QCFG_RESP_EVB_MODE_NO_EVB 0x0UL
#define FUNC_QCFG_RESP_EVB_MODE_VEB 0x1UL
#define FUNC_QCFG_RESP_EVB_MODE_VEPA 0x2UL
- u8 unused_3;
+ u8 unused_1;
__le16 alloc_vfs;
__le32 alloc_mcast_filters;
__le32 alloc_hw_ring_grps;
__le16 alloc_sp_tx_rings;
- u8 unused_4;
+ u8 unused_2;
u8 valid;
};
@@ -888,16 +895,13 @@ struct hwrm_func_cfg_input {
u8 unused_0;
u8 unused_1;
__le32 flags;
- #define FUNC_CFG_REQ_FLAGS_PROM_MODE 0x1UL
- #define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK 0x2UL
- #define FUNC_CFG_REQ_FLAGS_SRC_IP_ADDR_CHECK 0x4UL
- #define FUNC_CFG_REQ_FLAGS_VLAN_PRI_MATCH 0x8UL
- #define FUNC_CFG_REQ_FLAGS_DFLT_PRI_NOMATCH 0x10UL
- #define FUNC_CFG_REQ_FLAGS_DISABLE_PAUSE 0x20UL
- #define FUNC_CFG_REQ_FLAGS_DISABLE_STP 0x40UL
- #define FUNC_CFG_REQ_FLAGS_DISABLE_LLDP 0x80UL
- #define FUNC_CFG_REQ_FLAGS_DISABLE_PTPV2 0x100UL
- #define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE 0x200UL
+ #define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE 0x1UL
+ #define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE 0x2UL
+ #define FUNC_CFG_REQ_FLAGS_RSVD_MASK 0x1fcUL
+ #define FUNC_CFG_REQ_FLAGS_RSVD_SFT 2
+ #define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE_ENABLE 0x200UL
+ #define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE_DISABLE 0x400UL
+ #define FUNC_CFG_REQ_FLAGS_VIRT_MAC_PERSIST 0x800UL
__le32 enables;
#define FUNC_CFG_REQ_ENABLES_MTU 0x1UL
#define FUNC_CFG_REQ_ENABLES_MRU 0x2UL
@@ -1013,7 +1017,7 @@ struct hwrm_func_qstats_output {
__le64 tx_ucast_pkts;
__le64 tx_mcast_pkts;
__le64 tx_bcast_pkts;
- __le64 tx_err_pkts;
+ __le64 tx_discard_pkts;
__le64 tx_drop_pkts;
__le64 tx_ucast_bytes;
__le64 tx_mcast_bytes;
@@ -1021,7 +1025,7 @@ struct hwrm_func_qstats_output {
__le64 rx_ucast_pkts;
__le64 rx_mcast_pkts;
__le64 rx_bcast_pkts;
- __le64 rx_err_pkts;
+ __le64 rx_discard_pkts;
__le64 rx_drop_pkts;
__le64 rx_ucast_bytes;
__le64 rx_mcast_bytes;
@@ -4743,6 +4747,165 @@ struct hwrm_temp_monitor_query_output {
u8 valid;
};
+/* hwrm_wol_filter_alloc */
+/* Input (64 bytes) */
+struct hwrm_wol_filter_alloc_input {
+ __le16 req_type;
+ __le16 cmpl_ring;
+ __le16 seq_id;
+ __le16 target_id;
+ __le64 resp_addr;
+ __le32 flags;
+ __le32 enables;
+ #define WOL_FILTER_ALLOC_REQ_ENABLES_MAC_ADDRESS 0x1UL
+ #define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_OFFSET 0x2UL
+ #define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_BUF_SIZE 0x4UL
+ #define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_BUF_ADDR 0x8UL
+ #define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_MASK_ADDR 0x10UL
+ #define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_MASK_SIZE 0x20UL
+ __le16 port_id;
+ u8 wol_type;
+ #define WOL_FILTER_ALLOC_REQ_WOL_TYPE_MAGICPKT 0x0UL
+ #define WOL_FILTER_ALLOC_REQ_WOL_TYPE_BMP 0x1UL
+ #define WOL_FILTER_ALLOC_REQ_WOL_TYPE_INVALID 0xffUL
+ u8 unused_0;
+ __le32 unused_1;
+ u8 mac_address[6];
+ __le16 pattern_offset;
+ __le16 pattern_buf_size;
+ __le16 pattern_mask_size;
+ __le32 unused_2;
+ __le64 pattern_buf_addr;
+ __le64 pattern_mask_addr;
+};
+
+/* Output (16 bytes) */
+struct hwrm_wol_filter_alloc_output {
+ __le16 error_code;
+ __le16 req_type;
+ __le16 seq_id;
+ __le16 resp_len;
+ u8 wol_filter_id;
+ u8 unused_0;
+ __le16 unused_1;
+ u8 unused_2;
+ u8 unused_3;
+ u8 unused_4;
+ u8 valid;
+};
+
+/* hwrm_wol_filter_free */
+/* Input (32 bytes) */
+struct hwrm_wol_filter_free_input {
+ __le16 req_type;
+ __le16 cmpl_ring;
+ __le16 seq_id;
+ __le16 target_id;
+ __le64 resp_addr;
+ __le32 flags;
+ #define WOL_FILTER_FREE_REQ_FLAGS_FREE_ALL_WOL_FILTERS 0x1UL
+ __le32 enables;
+ #define WOL_FILTER_FREE_REQ_ENABLES_WOL_FILTER_ID 0x1UL
+ __le16 port_id;
+ u8 wol_filter_id;
+ u8 unused_0[5];
+};
+
+/* Output (16 bytes) */
+struct hwrm_wol_filter_free_output {
+ __le16 error_code;
+ __le16 req_type;
+ __le16 seq_id;
+ __le16 resp_len;
+ __le32 unused_0;
+ u8 unused_1;
+ u8 unused_2;
+ u8 unused_3;
+ u8 valid;
+};
+
+/* hwrm_wol_filter_qcfg */
+/* Input (56 bytes) */
+struct hwrm_wol_filter_qcfg_input {
+ __le16 req_type;
+ __le16 cmpl_ring;
+ __le16 seq_id;
+ __le16 target_id;
+ __le64 resp_addr;
+ __le16 port_id;
+ __le16 handle;
+ __le32 unused_0;
+ __le64 pattern_buf_addr;
+ __le16 pattern_buf_size;
+ u8 unused_1;
+ u8 unused_2;
+ u8 unused_3[3];
+ u8 unused_4;
+ __le64 pattern_mask_addr;
+ __le16 pattern_mask_size;
+ __le16 unused_5[3];
+};
+
+/* Output (32 bytes) */
+struct hwrm_wol_filter_qcfg_output {
+ __le16 error_code;
+ __le16 req_type;
+ __le16 seq_id;
+ __le16 resp_len;
+ __le16 next_handle;
+ u8 wol_filter_id;
+ u8 wol_type;
+ #define WOL_FILTER_QCFG_RESP_WOL_TYPE_MAGICPKT 0x0UL
+ #define WOL_FILTER_QCFG_RESP_WOL_TYPE_BMP 0x1UL
+ #define WOL_FILTER_QCFG_RESP_WOL_TYPE_INVALID 0xffUL
+ __le32 unused_0;
+ u8 mac_address[6];
+ __le16 pattern_offset;
+ __le16 pattern_size;
+ __le16 pattern_mask_size;
+ u8 unused_1;
+ u8 unused_2;
+ u8 unused_3;
+ u8 valid;
+};
+
+/* hwrm_wol_reason_qcfg */
+/* Input (40 bytes) */
+struct hwrm_wol_reason_qcfg_input {
+ __le16 req_type;
+ __le16 cmpl_ring;
+ __le16 seq_id;
+ __le16 target_id;
+ __le64 resp_addr;
+ __le16 port_id;
+ u8 unused_0;
+ u8 unused_1;
+ u8 unused_2[3];
+ u8 unused_3;
+ __le64 wol_pkt_buf_addr;
+ __le16 wol_pkt_buf_size;
+ __le16 unused_4[3];
+};
+
+/* Output (16 bytes) */
+struct hwrm_wol_reason_qcfg_output {
+ __le16 error_code;
+ __le16 req_type;
+ __le16 seq_id;
+ __le16 resp_len;
+ u8 wol_filter_id;
+ u8 wol_reason;
+ #define WOL_REASON_QCFG_RESP_WOL_REASON_MAGICPKT 0x0UL
+ #define WOL_REASON_QCFG_RESP_WOL_REASON_BMP 0x1UL
+ #define WOL_REASON_QCFG_RESP_WOL_REASON_INVALID 0xffUL
+ u8 wol_pkt_len;
+ u8 unused_0;
+ u8 unused_1;
+ u8 unused_2;
+ u8 unused_3;
+ u8 valid;
+};
+
/* hwrm_nvm_read */
/* Input (40 bytes) */
struct hwrm_nvm_read_input {
@@ -4773,32 +4936,6 @@ struct hwrm_nvm_read_output {
u8 valid;
};
-/* hwrm_nvm_raw_dump */
-/* Input (32 bytes) */
-struct hwrm_nvm_raw_dump_input {
- __le16 req_type;
- __le16 cmpl_ring;
- __le16 seq_id;
- __le16 target_id;
- __le64 resp_addr;
- __le64 host_dest_addr;
- __le32 offset;
- __le32 len;
-};
-
-/* Output (16 bytes) */
-struct hwrm_nvm_raw_dump_output {
- __le16 error_code;
- __le16 req_type;
- __le16 seq_id;
- __le16 resp_len;
- __le32 unused_0;
- u8 unused_1;
- u8 unused_2;
- u8 unused_3;
- u8 valid;
-};
-
/* hwrm_nvm_get_dir_entries */
/* Input (24 bytes) */
struct hwrm_nvm_get_dir_entries_input {
@@ -4881,6 +5018,15 @@ struct hwrm_nvm_write_output {
u8 valid;
};
+/* Command specific Error Codes (8 bytes) */
+struct hwrm_nvm_write_cmd_err {
+ u8 code;
+ #define NVM_WRITE_CMD_ERR_CODE_UNKNOWN 0x0UL
+ #define NVM_WRITE_CMD_ERR_CODE_FRAG_ERR 0x1UL
+ #define NVM_WRITE_CMD_ERR_CODE_NO_SPACE 0x2UL
+ u8 unused_0[7];
+};
+
/* hwrm_nvm_modify */
/* Input (40 bytes) */
struct hwrm_nvm_modify_input {
@@ -5112,6 +5258,100 @@ struct hwrm_nvm_install_update_cmd_err {
u8 unused_0[7];
};
+/* hwrm_selftest_qlist */
+/* Input (16 bytes) */
+struct hwrm_selftest_qlist_input {
+ __le16 req_type;
+ __le16 cmpl_ring;
+ __le16 seq_id;
+ __le16 target_id;
+ __le64 resp_addr;
+};
+
+/* Output (248 bytes) */
+struct hwrm_selftest_qlist_output {
+ __le16 error_code;
+ __le16 req_type;
+ __le16 seq_id;
+ __le16 resp_len;
+ u8 num_tests;
+ u8 available_tests;
+ #define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_NVM_TEST 0x1UL
+ #define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_LINK_TEST 0x2UL
+ #define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_REGISTER_TEST 0x4UL
+ #define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_MEMORY_TEST 0x8UL
+ u8 offline_tests;
+ #define SELFTEST_QLIST_RESP_OFFLINE_TESTS_NVM_TEST 0x1UL
+ #define SELFTEST_QLIST_RESP_OFFLINE_TESTS_LINK_TEST 0x2UL
+ #define SELFTEST_QLIST_RESP_OFFLINE_TESTS_REGISTER_TEST 0x4UL
+ #define SELFTEST_QLIST_RESP_OFFLINE_TESTS_MEMORY_TEST 0x8UL
+ u8 unused_0;
+ __le16 test_timeout;
+ u8 unused_1;
+ u8 unused_2;
+ char test0_name[32];
+ char test1_name[32];
+ char test2_name[32];
+ char test3_name[32];
+ char test4_name[32];
+ char test5_name[32];
+ char test6_name[32];
+ char test7_name[32];
+};
+
+/* hwrm_selftest_exec */
+/* Input (24 bytes) */
+struct hwrm_selftest_exec_input {
+ __le16 req_type;
+ __le16 cmpl_ring;
+ __le16 seq_id;
+ __le16 target_id;
+ __le64 resp_addr;
+ u8 flags;
+ #define SELFTEST_EXEC_REQ_FLAGS_NVM_TEST 0x1UL
+ #define SELFTEST_EXEC_REQ_FLAGS_LINK_TEST 0x2UL
+ #define SELFTEST_EXEC_REQ_FLAGS_REGISTER_TEST 0x4UL
+ #define SELFTEST_EXEC_REQ_FLAGS_MEMORY_TEST 0x8UL
+ u8 unused_0[7];
+};
+
+/* Output (16 bytes) */
+struct hwrm_selftest_exec_output {
+ __le16 error_code;
+ __le16 req_type;
+ __le16 seq_id;
+ __le16 resp_len;
+ u8 requested_tests;
+ #define SELFTEST_EXEC_RESP_REQUESTED_TESTS_NVM_TEST 0x1UL
+ #define SELFTEST_EXEC_RESP_REQUESTED_TESTS_LINK_TEST 0x2UL
+ #define SELFTEST_EXEC_RESP_REQUESTED_TESTS_REGISTER_TEST 0x4UL
+ #define SELFTEST_EXEC_RESP_REQUESTED_TESTS_MEMORY_TEST 0x8UL
+ u8 test_success;
+ #define SELFTEST_EXEC_RESP_TEST_SUCCESS_NVM_TEST 0x1UL
+ #define SELFTEST_EXEC_RESP_TEST_SUCCESS_LINK_TEST 0x2UL
+ #define SELFTEST_EXEC_RESP_TEST_SUCCESS_REGISTER_TEST 0x4UL
+ #define SELFTEST_EXEC_RESP_TEST_SUCCESS_MEMORY_TEST 0x8UL
+ __le16 unused_0[3];
+};
+
+/* hwrm_selftest_irq */
+/* Input (16 bytes) */
+struct hwrm_selftest_irq_input {
+ __le16 req_type;
+ __le16 cmpl_ring;
+ __le16 seq_id;
+ __le16 target_id;
+ __le64 resp_addr;
+};
+
+/* Output (8 bytes) */
+struct hwrm_selftest_irq_output {
+ __le16 error_code;
+ __le16 req_type;
+ __le16 seq_id;
+ __le16 resp_len;
+};
+
/* Hardware Resource Manager Specification */
/* Input (16 bytes) */
struct input {
@@ -5130,6 +5370,16 @@ struct output {
__le16 resp_len;
};
+/* Short Command Structure (16 bytes) */
+struct hwrm_short_input {
+ __le16 req_type;
+ __le16 signature;
+ #define SHORT_REQ_SIGNATURE_SHORT_CMD 0x4321UL
+ __le16 unused_0;
+ __le16 size;
+ __le64 req_addr;
+};
+
/* Command numbering (8 bytes) */
struct cmd_nums {
__le16 req_type;
@@ -5252,11 +5502,15 @@ struct cmd_nums {
#define HWRM_CFA_FLOW_FLUSH (0x105UL)
#define HWRM_CFA_FLOW_STATS (0x106UL)
#define HWRM_CFA_FLOW_INFO (0x107UL)
+ #define HWRM_SELFTEST_QLIST (0x200UL)
+ #define HWRM_SELFTEST_EXEC (0x201UL)
+ #define HWRM_SELFTEST_IRQ (0x202UL)
#define HWRM_DBG_READ_DIRECT (0xff10UL)
#define HWRM_DBG_READ_INDIRECT (0xff11UL)
#define HWRM_DBG_WRITE_DIRECT (0xff12UL)
#define HWRM_DBG_WRITE_INDIRECT (0xff13UL)
#define HWRM_DBG_DUMP (0xff14UL)
+ #define HWRM_NVM_FACTORY_DEFAULTS (0xffeeUL)
#define HWRM_NVM_VALIDATE_OPTION (0xffefUL)
#define HWRM_NVM_FLUSH (0xfff0UL)
#define HWRM_NVM_GET_VARIABLE (0xfff1UL)
@@ -5464,6 +5718,7 @@ struct hwrm_struct_hdr {
#define STRUCT_HDR_STRUCT_ID_DCBX_FEATURE_STATE 0x422UL
#define STRUCT_HDR_STRUCT_ID_LLDP_GENERIC 0x424UL
#define STRUCT_HDR_STRUCT_ID_LLDP_DEVICE 0x426UL
+ #define STRUCT_HDR_STRUCT_ID_AFM_OPAQUE 0x1UL
#define STRUCT_HDR_STRUCT_ID_PORT_DESCRIPTION 0xaUL
__le16 len;
u8 version;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 0b8cd74..f893531 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -1,6 +1,7 @@
/* Broadcom NetXtreme-C/E network driver.
*
* Copyright (c) 2014-2016 Broadcom Corporation
+ * Copyright (c) 2016-2017 Broadcom Limited
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -84,6 +85,9 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting)
u32 func_flags;
int rc;
+ if (bp->hwrm_spec_code < 0x10701)
+ return -ENOTSUPP;
+
rc = bnxt_vf_ndo_prep(bp, vf_id);
if (rc)
return rc;
@@ -96,9 +100,9 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting)
func_flags = vf->func_flags;
if (setting)
- func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK;
+ func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE;
else
- func_flags &= ~FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK;
+ func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE;
/*TODO: if the driver supports VLAN filter on guest VLAN,
* the spoof check should also include vlan anti-spoofing
*/
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h
index 1ab72e4..dbc8d97 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h
@@ -1,6 +1,7 @@
/* Broadcom NetXtreme-C/E network driver.
*
* Copyright (c) 2014-2016 Broadcom Corporation
+ * Copyright (c) 2016-2017 Broadcom Limited
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 899c30f..9dae327 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -19,11 +19,10 @@
#include "bnxt.h"
#include "bnxt_xdp.h"
-static void bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
- dma_addr_t mapping, u32 len, u16 rx_prod)
+void bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
+ dma_addr_t mapping, u32 len, u16 rx_prod)
{
struct bnxt_sw_tx_bd *tx_buf;
- struct tx_bd_ext *txbd1;
struct tx_bd *txbd;
u32 flags;
u16 prod;
@@ -33,23 +32,13 @@ static void bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
tx_buf->rx_prod = rx_prod;
txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
- flags = (len << TX_BD_LEN_SHIFT) | TX_BD_TYPE_LONG_TX_BD |
- (2 << TX_BD_FLAGS_BD_CNT_SHIFT) | TX_BD_FLAGS_COAL_NOW |
+ flags = (len << TX_BD_LEN_SHIFT) | (1 << TX_BD_FLAGS_BD_CNT_SHIFT) |
TX_BD_FLAGS_PACKET_END | bnxt_lhint_arr[len >> 9];
txbd->tx_bd_len_flags_type = cpu_to_le32(flags);
txbd->tx_bd_opaque = prod;
txbd->tx_bd_haddr = cpu_to_le64(mapping);
prod = NEXT_TX(prod);
- txbd1 = (struct tx_bd_ext *)
- &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
-
- txbd1->tx_bd_hsize_lflags = cpu_to_le32(0);
- txbd1->tx_bd_mss = cpu_to_le32(0);
- txbd1->tx_bd_cfa_action = cpu_to_le32(0);
- txbd1->tx_bd_cfa_meta = cpu_to_le32(0);
-
- prod = NEXT_TX(prod);
txr->tx_prod = prod;
}
@@ -66,7 +55,6 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
for (i = 0; i < nr_pkts; i++) {
last_tx_cons = tx_cons;
tx_cons = NEXT_TX(tx_cons);
- tx_cons = NEXT_TX(tx_cons);
}
txr->tx_cons = tx_cons;
if (bnxt_tx_avail(bp, txr) == bp->tx_ring_size) {
@@ -133,7 +121,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
return false;
case XDP_TX:
- if (tx_avail < 2) {
+ if (tx_avail < 1) {
trace_xdp_exception(bp->dev, xdp_prog, act);
bnxt_reuse_rx_data(rxr, cons, page);
return true;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
index b529f2c..12a5ad6 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
@@ -10,6 +10,8 @@
#ifndef BNXT_XDP_H
#define BNXT_XDP_H
+void bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
+ dma_addr_t mapping, u32 len, u16 rx_prod);
void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts);
bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
struct page *page, u8 **data_ptr, unsigned int *len,
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index f928968..a205a9f 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1,7 +1,7 @@
/*
* Broadcom GENET (Gigabit Ethernet) controller driver
*
- * Copyright (c) 2014 Broadcom Corporation
+ * Copyright (c) 2014-2017 Broadcom
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -450,6 +450,22 @@ static inline void bcmgenet_rdma_ring_writel(struct bcmgenet_priv *priv,
genet_dma_ring_regs[r]);
}
+static int bcmgenet_begin(struct net_device *dev)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+
+ /* Turn on the clock */
+ return clk_prepare_enable(priv->clk);
+}
+
+static void bcmgenet_complete(struct net_device *dev)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+
+ /* Turn off the clock */
+ clk_disable_unprepare(priv->clk);
+}
+
static int bcmgenet_get_link_ksettings(struct net_device *dev,
struct ethtool_link_ksettings *cmd)
{
@@ -605,7 +621,7 @@ static int bcmgenet_set_coalesce(struct net_device *dev,
/* GENET TDMA hardware does not support a configurable timeout, but will
* always generate an interrupt either after MBDONE packets have been
- * transmitted, or when the ring is emtpy.
+ * transmitted, or when the ring is empty.
*/
if (ec->tx_coalesce_usecs || ec->tx_coalesce_usecs_high ||
ec->tx_coalesce_usecs_irq || ec->tx_coalesce_usecs_low)
@@ -691,6 +707,19 @@ struct bcmgenet_stats {
.reg_offset = offset, \
}
+#define STAT_GENET_Q(num) \
+ STAT_GENET_SOFT_MIB("txq" __stringify(num) "_packets", \
+ tx_rings[num].packets), \
+ STAT_GENET_SOFT_MIB("txq" __stringify(num) "_bytes", \
+ tx_rings[num].bytes), \
+ STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_bytes", \
+ rx_rings[num].bytes), \
+ STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_packets", \
+ rx_rings[num].packets), \
+ STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_errors", \
+ rx_rings[num].errors), \
+ STAT_GENET_SOFT_MIB("rxq" __stringify(num) "_dropped", \
+ rx_rings[num].dropped)
/* There is a 0xC gap between the end of RX and beginning of TX stats and then
* between the end of TX stats and the beginning of the RX RUNT
@@ -778,12 +807,19 @@ static const struct bcmgenet_stats bcmgenet_gstrings_stats[] = {
STAT_GENET_RUNT("rx_runt_bytes", mib.rx_runt_bytes),
/* Misc UniMAC counters */
STAT_GENET_MISC("rbuf_ovflow_cnt", mib.rbuf_ovflow_cnt,
- UMAC_RBUF_OVFL_CNT),
- STAT_GENET_MISC("rbuf_err_cnt", mib.rbuf_err_cnt, UMAC_RBUF_ERR_CNT),
+ UMAC_RBUF_OVFL_CNT_V1),
+ STAT_GENET_MISC("rbuf_err_cnt", mib.rbuf_err_cnt,
+ UMAC_RBUF_ERR_CNT_V1),
STAT_GENET_MISC("mdf_err_cnt", mib.mdf_err_cnt, UMAC_MDF_ERR_CNT),
STAT_GENET_SOFT_MIB("alloc_rx_buff_failed", mib.alloc_rx_buff_failed),
STAT_GENET_SOFT_MIB("rx_dma_failed", mib.rx_dma_failed),
STAT_GENET_SOFT_MIB("tx_dma_failed", mib.tx_dma_failed),
+ /* Per TX queues */
+ STAT_GENET_Q(0),
+ STAT_GENET_Q(1),
+ STAT_GENET_Q(2),
+ STAT_GENET_Q(3),
+ STAT_GENET_Q(16),
};
#define BCMGENET_STATS_LEN ARRAY_SIZE(bcmgenet_gstrings_stats)
@@ -821,6 +857,45 @@ static void bcmgenet_get_strings(struct net_device *dev, u32 stringset,
}
}
+static u32 bcmgenet_update_stat_misc(struct bcmgenet_priv *priv, u16 offset)
+{
+ u16 new_offset;
+ u32 val;
+
+ switch (offset) {
+ case UMAC_RBUF_OVFL_CNT_V1:
+ if (GENET_IS_V2(priv))
+ new_offset = RBUF_OVFL_CNT_V2;
+ else
+ new_offset = RBUF_OVFL_CNT_V3PLUS;
+
+ val = bcmgenet_rbuf_readl(priv, new_offset);
+ /* clear if overflowed */
+ if (val == ~0)
+ bcmgenet_rbuf_writel(priv, 0, new_offset);
+ break;
+ case UMAC_RBUF_ERR_CNT_V1:
+ if (GENET_IS_V2(priv))
+ new_offset = RBUF_ERR_CNT_V2;
+ else
+ new_offset = RBUF_ERR_CNT_V3PLUS;
+
+ val = bcmgenet_rbuf_readl(priv, new_offset);
+ /* clear if overflowed */
+ if (val == ~0)
+ bcmgenet_rbuf_writel(priv, 0, new_offset);
+ break;
+ default:
+ val = bcmgenet_umac_readl(priv, offset);
+ /* clear if overflowed */
+ if (val == ~0)
+ bcmgenet_umac_writel(priv, 0, offset);
+ break;
+ }
+
+ return val;
+}
+
static void bcmgenet_update_mib_counters(struct bcmgenet_priv *priv)
{
int i, j = 0;
@@ -836,19 +911,28 @@ static void bcmgenet_update_mib_counters(struct bcmgenet_priv *priv)
case BCMGENET_STAT_NETDEV:
case BCMGENET_STAT_SOFT:
continue;
- case BCMGENET_STAT_MIB_RX:
- case BCMGENET_STAT_MIB_TX:
case BCMGENET_STAT_RUNT:
- if (s->type != BCMGENET_STAT_MIB_RX)
- offset = BCMGENET_STAT_OFFSET;
+ offset += BCMGENET_STAT_OFFSET;
+ /* fall through */
+ case BCMGENET_STAT_MIB_TX:
+ offset += BCMGENET_STAT_OFFSET;
+ /* fall through */
+ case BCMGENET_STAT_MIB_RX:
val = bcmgenet_umac_readl(priv,
UMAC_MIB_START + j + offset);
+ offset = 0; /* Reset Offset */
break;
case BCMGENET_STAT_MISC:
- val = bcmgenet_umac_readl(priv, s->reg_offset);
- /* clear if overflowed */
- if (val == ~0)
- bcmgenet_umac_writel(priv, 0, s->reg_offset);
+ if (GENET_IS_V1(priv)) {
+ val = bcmgenet_umac_readl(priv, s->reg_offset);
+ /* clear if overflowed */
+ if (val == ~0)
+ bcmgenet_umac_writel(priv, 0,
+ s->reg_offset);
+ } else {
+ val = bcmgenet_update_stat_misc(priv,
+ s->reg_offset);
+ }
break;
}
@@ -973,6 +1057,8 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e)
/* standard ethtool support functions. */
static const struct ethtool_ops bcmgenet_ethtool_ops = {
+ .begin = bcmgenet_begin,
+ .complete = bcmgenet_complete,
.get_strings = bcmgenet_get_strings,
.get_sset_count = bcmgenet_get_sset_count,
.get_ethtool_stats = bcmgenet_get_ethtool_stats,
@@ -1011,8 +1097,17 @@ static int bcmgenet_power_down(struct bcmgenet_priv *priv,
/* Power down LED */
if (priv->hw_params->flags & GENET_HAS_EXT) {
reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
- reg |= (EXT_PWR_DOWN_PHY |
- EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS);
+ if (GENET_IS_V5(priv))
+ reg |= EXT_PWR_DOWN_PHY_EN |
+ EXT_PWR_DOWN_PHY_RD |
+ EXT_PWR_DOWN_PHY_SD |
+ EXT_PWR_DOWN_PHY_RX |
+ EXT_PWR_DOWN_PHY_TX |
+ EXT_IDDQ_GLBL_PWR;
+ else
+ reg |= EXT_PWR_DOWN_PHY;
+
+ reg |= (EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS);
bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
bcmgenet_phy_power_set(priv->dev, false);
@@ -1037,12 +1132,34 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv,
switch (mode) {
case GENET_POWER_PASSIVE:
- reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_PHY |
- EXT_PWR_DOWN_BIAS);
- /* fallthrough */
+ reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS);
+ if (GENET_IS_V5(priv)) {
+ reg &= ~(EXT_PWR_DOWN_PHY_EN |
+ EXT_PWR_DOWN_PHY_RD |
+ EXT_PWR_DOWN_PHY_SD |
+ EXT_PWR_DOWN_PHY_RX |
+ EXT_PWR_DOWN_PHY_TX |
+ EXT_IDDQ_GLBL_PWR);
+ reg |= EXT_PHY_RESET;
+ bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
+ mdelay(1);
+
+ reg &= ~EXT_PHY_RESET;
+ } else {
+ reg &= ~EXT_PWR_DOWN_PHY;
+ reg |= EXT_PWR_DN_EN_LD;
+ }
+ bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
+ bcmgenet_phy_power_set(priv->dev, true);
+ bcmgenet_mii_reset(priv->dev);
+ break;
+
case GENET_POWER_CABLE_SENSE:
/* enable APD */
- reg |= EXT_PWR_DN_EN_LD;
+ if (!GENET_IS_V5(priv)) {
+ reg |= EXT_PWR_DN_EN_LD;
+ bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
+ }
break;
case GENET_POWER_WOL_MAGIC:
bcmgenet_wol_power_up_cfg(priv, mode);
@@ -1050,39 +1167,20 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv,
default:
break;
}
-
- bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
- if (mode == GENET_POWER_PASSIVE) {
- bcmgenet_phy_power_set(priv->dev, true);
- bcmgenet_mii_reset(priv->dev);
- }
}
/* ioctl handle special commands that are not present in ethtool. */
static int bcmgenet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
{
struct bcmgenet_priv *priv = netdev_priv(dev);
- int val = 0;
if (!netif_running(dev))
return -EINVAL;
- switch (cmd) {
- case SIOCGMIIPHY:
- case SIOCGMIIREG:
- case SIOCSMIIREG:
- if (!priv->phydev)
- val = -ENODEV;
- else
- val = phy_mii_ioctl(priv->phydev, rq, cmd);
- break;
+ if (!priv->phydev)
+ return -ENODEV;
- default:
- val = -EINVAL;
- break;
- }
-
- return val;
+ return phy_mii_ioctl(priv->phydev, rq, cmd);
}
static struct enet_cb *bcmgenet_get_txcb(struct bcmgenet_priv *priv,
@@ -1167,21 +1265,24 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
struct bcmgenet_priv *priv = netdev_priv(dev);
struct device *kdev = &priv->pdev->dev;
struct enet_cb *tx_cb_ptr;
- struct netdev_queue *txq;
unsigned int pkts_compl = 0;
unsigned int bytes_compl = 0;
unsigned int c_index;
unsigned int txbds_ready;
unsigned int txbds_processed = 0;
- /* Compute how many buffers are transmitted since last xmit call */
- c_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_CONS_INDEX);
- c_index &= DMA_C_INDEX_MASK;
-
- if (likely(c_index >= ring->c_index))
- txbds_ready = c_index - ring->c_index;
+ /* Clear status before servicing to reduce spurious interrupts */
+ if (ring->index == DESC_INDEX)
+ bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_TXDMA_DONE,
+ INTRL2_CPU_CLEAR);
else
- txbds_ready = (DMA_C_INDEX_MASK + 1) - ring->c_index + c_index;
+ bcmgenet_intrl2_1_writel(priv, (1 << ring->index),
+ INTRL2_CPU_CLEAR);
+
+ /* Compute how many buffers are transmitted since last xmit call */
+ c_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_CONS_INDEX)
+ & DMA_C_INDEX_MASK;
+ txbds_ready = (c_index - ring->c_index) & DMA_C_INDEX_MASK;
netif_dbg(priv, tx_done, dev,
"%s ring=%d old_c_index=%u c_index=%u txbds_ready=%u\n",
@@ -1214,20 +1315,15 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
}
ring->free_bds += txbds_processed;
- ring->c_index = (ring->c_index + txbds_processed) & DMA_C_INDEX_MASK;
+ ring->c_index = c_index;
- dev->stats.tx_packets += pkts_compl;
- dev->stats.tx_bytes += bytes_compl;
+ ring->packets += pkts_compl;
+ ring->bytes += bytes_compl;
- txq = netdev_get_tx_queue(dev, ring->queue);
- netdev_tx_completed_queue(txq, pkts_compl, bytes_compl);
+ netdev_tx_completed_queue(netdev_get_tx_queue(dev, ring->queue),
+ pkts_compl, bytes_compl);
- if (ring->free_bds > (MAX_SKB_FRAGS + 1)) {
- if (netif_tx_queue_stopped(txq))
- netif_tx_wake_queue(txq);
- }
-
- return pkts_compl;
+ return txbds_processed;
}
static unsigned int bcmgenet_tx_reclaim(struct net_device *dev,
@@ -1248,8 +1344,16 @@ static int bcmgenet_tx_poll(struct napi_struct *napi, int budget)
struct bcmgenet_tx_ring *ring =
container_of(napi, struct bcmgenet_tx_ring, napi);
unsigned int work_done = 0;
+ struct netdev_queue *txq;
+ unsigned long flags;
- work_done = bcmgenet_tx_reclaim(ring->priv->dev, ring);
+ spin_lock_irqsave(&ring->lock, flags);
+ work_done = __bcmgenet_tx_reclaim(ring->priv->dev, ring);
+ if (ring->free_bds > (MAX_SKB_FRAGS + 1)) {
+ txq = netdev_get_tx_queue(ring->priv->dev, ring->queue);
+ netif_tx_wake_queue(txq);
+ }
+ spin_unlock_irqrestore(&ring->lock, flags);
if (work_done == 0) {
napi_complete(napi);
@@ -1588,18 +1692,28 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
unsigned long dma_flag;
int len;
unsigned int rxpktprocessed = 0, rxpkttoprocess;
- unsigned int p_index;
+ unsigned int p_index, mask;
unsigned int discards;
unsigned int chksum_ok = 0;
+ /* Clear status before servicing to reduce spurious interrupts */
+ if (ring->index == DESC_INDEX) {
+ bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_RXDMA_DONE,
+ INTRL2_CPU_CLEAR);
+ } else {
+ mask = 1 << (UMAC_IRQ1_RX_INTR_SHIFT + ring->index);
+ bcmgenet_intrl2_1_writel(priv,
+ mask,
+ INTRL2_CPU_CLEAR);
+ }
+
p_index = bcmgenet_rdma_ring_readl(priv, ring->index, RDMA_PROD_INDEX);
discards = (p_index >> DMA_P_INDEX_DISCARD_CNT_SHIFT) &
DMA_P_INDEX_DISCARD_CNT_MASK;
if (discards > ring->old_discards) {
discards = discards - ring->old_discards;
- dev->stats.rx_missed_errors += discards;
- dev->stats.rx_errors += discards;
+ ring->errors += discards;
ring->old_discards += discards;
/* Clear HW register when we reach 75% of maximum 0xFFFF */
@@ -1611,12 +1725,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
}
p_index &= DMA_P_INDEX_MASK;
-
- if (likely(p_index >= ring->c_index))
- rxpkttoprocess = p_index - ring->c_index;
- else
- rxpkttoprocess = (DMA_C_INDEX_MASK + 1) - ring->c_index +
- p_index;
+ rxpkttoprocess = (p_index - ring->c_index) & DMA_C_INDEX_MASK;
netif_dbg(priv, rx_status, dev,
"RDMA: rxpkttoprocess=%d\n", rxpkttoprocess);
@@ -1627,7 +1736,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
skb = bcmgenet_rx_refill(priv, cb);
if (unlikely(!skb)) {
- dev->stats.rx_dropped++;
+ ring->dropped++;
goto next;
}
@@ -1655,7 +1764,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
if (unlikely(!(dma_flag & DMA_EOP) || !(dma_flag & DMA_SOP))) {
netif_err(priv, rx_status, dev,
"dropping fragmented packet!\n");
- dev->stats.rx_errors++;
+ ring->errors++;
dev_kfree_skb_any(skb);
goto next;
}
@@ -1704,8 +1813,8 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
/*Finish setting up the received SKB and send it to the kernel*/
skb->protocol = eth_type_trans(skb, priv->dev);
- dev->stats.rx_packets++;
- dev->stats.rx_bytes += len;
+ ring->packets++;
+ ring->bytes += len;
if (dma_flag & DMA_RX_MULT)
dev->stats.multicast++;
@@ -1843,10 +1952,8 @@ static void bcmgenet_intr_disable(struct bcmgenet_priv *priv)
/* Mask all interrupts.*/
bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_MASK_SET);
bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_CLEAR);
- bcmgenet_intrl2_0_writel(priv, 0, INTRL2_CPU_MASK_CLEAR);
bcmgenet_intrl2_1_writel(priv, 0xFFFFFFFF, INTRL2_CPU_MASK_SET);
bcmgenet_intrl2_1_writel(priv, 0xFFFFFFFF, INTRL2_CPU_CLEAR);
- bcmgenet_intrl2_1_writel(priv, 0, INTRL2_CPU_MASK_CLEAR);
}
static void bcmgenet_link_intr_enable(struct bcmgenet_priv *priv)
@@ -1873,8 +1980,6 @@ static int init_umac(struct bcmgenet_priv *priv)
int ret;
u32 reg;
u32 int0_enable = 0;
- u32 int1_enable = 0;
- int i;
dev_dbg(&priv->pdev->dev, "bcmgenet: init_umac\n");
@@ -1901,12 +2006,6 @@ static int init_umac(struct bcmgenet_priv *priv)
bcmgenet_intr_disable(priv);
- /* Enable Rx default queue 16 interrupts */
- int0_enable |= UMAC_IRQ_RXDMA_DONE;
-
- /* Enable Tx default queue 16 interrupts */
- int0_enable |= UMAC_IRQ_TXDMA_DONE;
-
/* Configure backpressure vectors for MoCA */
if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) {
reg = bcmgenet_bp_mc_get(priv);
@@ -1924,18 +2023,8 @@ static int init_umac(struct bcmgenet_priv *priv)
if (priv->hw_params->flags & GENET_HAS_MDIO_INTR)
int0_enable |= (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR);
- /* Enable Rx priority queue interrupts */
- for (i = 0; i < priv->hw_params->rx_queues; ++i)
- int1_enable |= (1 << (UMAC_IRQ1_RX_INTR_SHIFT + i));
-
- /* Enable Tx priority queue interrupts */
- for (i = 0; i < priv->hw_params->tx_queues; ++i)
- int1_enable |= (1 << i);
-
bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
- bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR);
- /* Enable rx/tx engine.*/
dev_dbg(kdev, "done init umac\n");
return 0;
@@ -2067,22 +2156,33 @@ static void bcmgenet_init_tx_napi(struct bcmgenet_priv *priv)
static void bcmgenet_enable_tx_napi(struct bcmgenet_priv *priv)
{
unsigned int i;
+ u32 int0_enable = UMAC_IRQ_TXDMA_DONE;
+ u32 int1_enable = 0;
struct bcmgenet_tx_ring *ring;
for (i = 0; i < priv->hw_params->tx_queues; ++i) {
ring = &priv->tx_rings[i];
napi_enable(&ring->napi);
+ int1_enable |= (1 << i);
}
ring = &priv->tx_rings[DESC_INDEX];
napi_enable(&ring->napi);
+
+ bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
+ bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR);
}
static void bcmgenet_disable_tx_napi(struct bcmgenet_priv *priv)
{
unsigned int i;
+ u32 int0_disable = UMAC_IRQ_TXDMA_DONE;
+ u32 int1_disable = 0xffff;
struct bcmgenet_tx_ring *ring;
+ bcmgenet_intrl2_0_writel(priv, int0_disable, INTRL2_CPU_MASK_SET);
+ bcmgenet_intrl2_1_writel(priv, int1_disable, INTRL2_CPU_MASK_SET);
+
for (i = 0; i < priv->hw_params->tx_queues; ++i) {
ring = &priv->tx_rings[i];
napi_disable(&ring->napi);
@@ -2195,22 +2295,33 @@ static void bcmgenet_init_rx_napi(struct bcmgenet_priv *priv)
static void bcmgenet_enable_rx_napi(struct bcmgenet_priv *priv)
{
unsigned int i;
+ u32 int0_enable = UMAC_IRQ_RXDMA_DONE;
+ u32 int1_enable = 0;
struct bcmgenet_rx_ring *ring;
for (i = 0; i < priv->hw_params->rx_queues; ++i) {
ring = &priv->rx_rings[i];
napi_enable(&ring->napi);
+ int1_enable |= (1 << (UMAC_IRQ1_RX_INTR_SHIFT + i));
}
ring = &priv->rx_rings[DESC_INDEX];
napi_enable(&ring->napi);
+
+ bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
+ bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR);
}
static void bcmgenet_disable_rx_napi(struct bcmgenet_priv *priv)
{
unsigned int i;
+ u32 int0_disable = UMAC_IRQ_RXDMA_DONE;
+ u32 int1_disable = 0xffff << UMAC_IRQ1_RX_INTR_SHIFT;
struct bcmgenet_rx_ring *ring;
+ bcmgenet_intrl2_0_writel(priv, int0_disable, INTRL2_CPU_MASK_SET);
+ bcmgenet_intrl2_1_writel(priv, int1_disable, INTRL2_CPU_MASK_SET);
+
for (i = 0; i < priv->hw_params->rx_queues; ++i) {
ring = &priv->rx_rings[i];
napi_disable(&ring->napi);
@@ -2457,24 +2568,28 @@ static int bcmgenet_init_dma(struct bcmgenet_priv *priv)
/* Interrupt bottom half */
static void bcmgenet_irq_task(struct work_struct *work)
{
+ unsigned long flags;
+ unsigned int status;
struct bcmgenet_priv *priv = container_of(
work, struct bcmgenet_priv, bcmgenet_irq_work);
netif_dbg(priv, intr, priv->dev, "%s\n", __func__);
- if (priv->irq0_stat & UMAC_IRQ_MPD_R) {
- priv->irq0_stat &= ~UMAC_IRQ_MPD_R;
+ spin_lock_irqsave(&priv->lock, flags);
+ status = priv->irq0_stat;
+ priv->irq0_stat = 0;
+ spin_unlock_irqrestore(&priv->lock, flags);
+
+ if (status & UMAC_IRQ_MPD_R) {
netif_dbg(priv, wol, priv->dev,
"magic packet detected, waking up\n");
bcmgenet_power_up(priv, GENET_POWER_WOL_MAGIC);
}
/* Link UP/DOWN event */
- if (priv->irq0_stat & UMAC_IRQ_LINK_EVENT) {
+ if (status & UMAC_IRQ_LINK_EVENT)
phy_mac_interrupt(priv->phydev,
- !!(priv->irq0_stat & UMAC_IRQ_LINK_UP));
- priv->irq0_stat &= ~UMAC_IRQ_LINK_EVENT;
- }
+ !!(status & UMAC_IRQ_LINK_UP));
}
/* bcmgenet_isr1: handle Rx and Tx priority queues */
@@ -2483,22 +2598,21 @@ static irqreturn_t bcmgenet_isr1(int irq, void *dev_id)
struct bcmgenet_priv *priv = dev_id;
struct bcmgenet_rx_ring *rx_ring;
struct bcmgenet_tx_ring *tx_ring;
- unsigned int index;
+ unsigned int index, status;
- /* Save irq status for bottom-half processing. */
- priv->irq1_stat =
- bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_STAT) &
+ /* Read irq status */
+ status = bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_STAT) &
~bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_MASK_STATUS);
/* clear interrupts */
- bcmgenet_intrl2_1_writel(priv, priv->irq1_stat, INTRL2_CPU_CLEAR);
+ bcmgenet_intrl2_1_writel(priv, status, INTRL2_CPU_CLEAR);
netif_dbg(priv, intr, priv->dev,
- "%s: IRQ=0x%x\n", __func__, priv->irq1_stat);
+ "%s: IRQ=0x%x\n", __func__, status);
/* Check Rx priority queue interrupts */
for (index = 0; index < priv->hw_params->rx_queues; index++) {
- if (!(priv->irq1_stat & BIT(UMAC_IRQ1_RX_INTR_SHIFT + index)))
+ if (!(status & BIT(UMAC_IRQ1_RX_INTR_SHIFT + index)))
continue;
rx_ring = &priv->rx_rings[index];
@@ -2511,7 +2625,7 @@ static irqreturn_t bcmgenet_isr1(int irq, void *dev_id)
/* Check Tx priority queue interrupts */
for (index = 0; index < priv->hw_params->tx_queues; index++) {
- if (!(priv->irq1_stat & BIT(index)))
+ if (!(status & BIT(index)))
continue;
tx_ring = &priv->tx_rings[index];
@@ -2531,19 +2645,20 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
struct bcmgenet_priv *priv = dev_id;
struct bcmgenet_rx_ring *rx_ring;
struct bcmgenet_tx_ring *tx_ring;
+ unsigned int status;
+ unsigned long flags;
- /* Save irq status for bottom-half processing. */
- priv->irq0_stat =
- bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_STAT) &
+ /* Read irq status */
+ status = bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_STAT) &
~bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_MASK_STATUS);
/* clear interrupts */
- bcmgenet_intrl2_0_writel(priv, priv->irq0_stat, INTRL2_CPU_CLEAR);
+ bcmgenet_intrl2_0_writel(priv, status, INTRL2_CPU_CLEAR);
netif_dbg(priv, intr, priv->dev,
- "IRQ=0x%x\n", priv->irq0_stat);
+ "IRQ=0x%x\n", status);
- if (priv->irq0_stat & UMAC_IRQ_RXDMA_DONE) {
+ if (status & UMAC_IRQ_RXDMA_DONE) {
rx_ring = &priv->rx_rings[DESC_INDEX];
if (likely(napi_schedule_prep(&rx_ring->napi))) {
@@ -2552,7 +2667,7 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
}
}
- if (priv->irq0_stat & UMAC_IRQ_TXDMA_DONE) {
+ if (status & UMAC_IRQ_TXDMA_DONE) {
tx_ring = &priv->tx_rings[DESC_INDEX];
if (likely(napi_schedule_prep(&tx_ring->napi))) {
@@ -2565,18 +2680,28 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
UMAC_IRQ_PHY_DET_F |
UMAC_IRQ_LINK_EVENT |
UMAC_IRQ_HFB_SM |
- UMAC_IRQ_HFB_MM |
- UMAC_IRQ_MPD_R)) {
+ UMAC_IRQ_HFB_MM)) {
/* all other interested interrupts handled in bottom half */
schedule_work(&priv->bcmgenet_irq_work);
}
if ((priv->hw_params->flags & GENET_HAS_MDIO_INTR) &&
- priv->irq0_stat & (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR)) {
- priv->irq0_stat &= ~(UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR);
+ status & (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR)) {
wake_up(&priv->wq);
}
+ /* all other interested interrupts handled in bottom half */
+ status &= (UMAC_IRQ_LINK_EVENT |
+ UMAC_IRQ_MPD_R);
+ if (status) {
+ /* Save irq status for bottom-half processing. */
+ spin_lock_irqsave(&priv->lock, flags);
+ priv->irq0_stat |= status;
+ spin_unlock_irqrestore(&priv->lock, flags);
+
+ schedule_work(&priv->bcmgenet_irq_work);
+ }
+
return IRQ_HANDLED;
}
@@ -2801,6 +2926,8 @@ static int bcmgenet_open(struct net_device *dev)
err_fini_dma:
bcmgenet_fini_dma(priv);
err_clk_disable:
+ if (priv->internal_phy)
+ bcmgenet_power_down(priv, GENET_POWER_PASSIVE);
clk_disable_unprepare(priv->clk);
return ret;
}
@@ -2845,7 +2972,7 @@ static int bcmgenet_close(struct net_device *dev)
if (ret)
return ret;
- /* Disable MAC transmit. TX DMA disabled have to done before this */
+ /* Disable MAC transmit. TX DMA disabled must be done before this */
umac_enable_set(priv, CMD_TX_EN, false);
/* tx reclaim */
@@ -3025,6 +3152,48 @@ static int bcmgenet_set_mac_addr(struct net_device *dev, void *p)
return 0;
}
+static struct net_device_stats *bcmgenet_get_stats(struct net_device *dev)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ unsigned long tx_bytes = 0, tx_packets = 0;
+ unsigned long rx_bytes = 0, rx_packets = 0;
+ unsigned long rx_errors = 0, rx_dropped = 0;
+ struct bcmgenet_tx_ring *tx_ring;
+ struct bcmgenet_rx_ring *rx_ring;
+ unsigned int q;
+
+ for (q = 0; q < priv->hw_params->tx_queues; q++) {
+ tx_ring = &priv->tx_rings[q];
+ tx_bytes += tx_ring->bytes;
+ tx_packets += tx_ring->packets;
+ }
+ tx_ring = &priv->tx_rings[DESC_INDEX];
+ tx_bytes += tx_ring->bytes;
+ tx_packets += tx_ring->packets;
+
+ for (q = 0; q < priv->hw_params->rx_queues; q++) {
+ rx_ring = &priv->rx_rings[q];
+
+ rx_bytes += rx_ring->bytes;
+ rx_packets += rx_ring->packets;
+ rx_errors += rx_ring->errors;
+ rx_dropped += rx_ring->dropped;
+ }
+ rx_ring = &priv->rx_rings[DESC_INDEX];
+ rx_bytes += rx_ring->bytes;
+ rx_packets += rx_ring->packets;
+ rx_errors += rx_ring->errors;
+ rx_dropped += rx_ring->dropped;
+
+ dev->stats.tx_bytes = tx_bytes;
+ dev->stats.tx_packets = tx_packets;
+ dev->stats.rx_bytes = rx_bytes;
+ dev->stats.rx_packets = rx_packets;
+ dev->stats.rx_errors = rx_errors;
+ dev->stats.rx_missed_errors = rx_errors;
+ return &dev->stats;
+}
+
static const struct net_device_ops bcmgenet_netdev_ops = {
.ndo_open = bcmgenet_open,
.ndo_stop = bcmgenet_close,
@@ -3037,6 +3206,7 @@ static const struct net_device_ops bcmgenet_netdev_ops = {
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = bcmgenet_poll_controller,
#endif
+ .ndo_get_stats = bcmgenet_get_stats,
};
/* Array of GENET hardware parameters/characteristics */
@@ -3110,6 +3280,25 @@ static struct bcmgenet_hw_params bcmgenet_hw_params[] = {
.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
},
+ [GENET_V5] = {
+ .tx_queues = 4,
+ .tx_bds_per_q = 32,
+ .rx_queues = 0,
+ .rx_bds_per_q = 0,
+ .bp_in_en_shift = 17,
+ .bp_in_mask = 0x1ffff,
+ .hfb_filter_cnt = 48,
+ .hfb_filter_size = 128,
+ .qtag_mask = 0x3F,
+ .tbuf_offset = 0x0600,
+ .hfb_offset = 0x8000,
+ .hfb_reg_offset = 0xfc00,
+ .rdma_offset = 0x2000,
+ .tdma_offset = 0x4000,
+ .words_per_bd = 3,
+ .flags = GENET_HAS_40BITS | GENET_HAS_EXT |
+ GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
+ },
};
/* Infer hardware parameters from the detected GENET version */
@@ -3120,26 +3309,22 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv)
u8 major;
u16 gphy_rev;
- if (GENET_IS_V4(priv)) {
+ if (GENET_IS_V5(priv) || GENET_IS_V4(priv)) {
bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus;
genet_dma_ring_regs = genet_dma_ring_regs_v4;
priv->dma_rx_chk_bit = DMA_RX_CHK_V3PLUS;
- priv->version = GENET_V4;
} else if (GENET_IS_V3(priv)) {
bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus;
genet_dma_ring_regs = genet_dma_ring_regs_v123;
priv->dma_rx_chk_bit = DMA_RX_CHK_V3PLUS;
- priv->version = GENET_V3;
} else if (GENET_IS_V2(priv)) {
bcmgenet_dma_regs = bcmgenet_dma_regs_v2;
genet_dma_ring_regs = genet_dma_ring_regs_v123;
priv->dma_rx_chk_bit = DMA_RX_CHK_V12;
- priv->version = GENET_V2;
} else if (GENET_IS_V1(priv)) {
bcmgenet_dma_regs = bcmgenet_dma_regs_v1;
genet_dma_ring_regs = genet_dma_ring_regs_v123;
priv->dma_rx_chk_bit = DMA_RX_CHK_V12;
- priv->version = GENET_V1;
}
/* enum genet_version starts at 1 */
@@ -3149,7 +3334,9 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv)
/* Read GENET HW version */
reg = bcmgenet_sys_readl(priv, SYS_REV_CTRL);
major = (reg >> 24 & 0x0f);
- if (major == 5)
+ if (major == 6)
+ major = 5;
+ else if (major == 5)
major = 4;
else if (major == 0)
major = 1;
@@ -3177,18 +3364,24 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv)
*/
gphy_rev = reg & 0xffff;
- /* This is the good old scheme, just GPHY major, no minor nor patch */
- if ((gphy_rev & 0xf0) != 0)
- priv->gphy_rev = gphy_rev << 8;
-
- /* This is the new scheme, GPHY major rolls over with 0x10 = rev G0 */
- else if ((gphy_rev & 0xff00) != 0)
- priv->gphy_rev = gphy_rev;
-
+ if (GENET_IS_V5(priv)) {
+ /* The EPHY revision should come from the MDIO registers of
+ * the PHY not from GENET.
+ */
+ if (gphy_rev != 0) {
+ pr_warn("GENET is reporting EPHY revision: 0x%04x\n",
+ gphy_rev);
+ }
/* This is reserved so should require special treatment */
- else if (gphy_rev == 0 || gphy_rev == 0x01ff) {
+ } else if (gphy_rev == 0 || gphy_rev == 0x01ff) {
pr_warn("Invalid GPHY revision detected: 0x%04x\n", gphy_rev);
return;
+ /* This is the good old scheme, just GPHY major, no minor nor patch */
+ } else if ((gphy_rev & 0xf0) != 0) {
+ priv->gphy_rev = gphy_rev << 8;
+ /* This is the new scheme, GPHY major rolls over with 0x10 = rev G0 */
+ } else if ((gphy_rev & 0xff00) != 0) {
+ priv->gphy_rev = gphy_rev;
}
#ifdef CONFIG_PHYS_ADDR_T_64BIT
@@ -3219,6 +3412,7 @@ static const struct of_device_id bcmgenet_match[] = {
{ .compatible = "brcm,genet-v2", .data = (void *)GENET_V2 },
{ .compatible = "brcm,genet-v3", .data = (void *)GENET_V3 },
{ .compatible = "brcm,genet-v4", .data = (void *)GENET_V4 },
+ { .compatible = "brcm,genet-v5", .data = (void *)GENET_V5 },
{ },
};
MODULE_DEVICE_TABLE(of, bcmgenet_match);
@@ -3233,6 +3427,7 @@ static int bcmgenet_probe(struct platform_device *pdev)
const void *macaddr;
struct resource *r;
int err = -EIO;
+ const char *phy_mode_str;
/* Up to GENET_MAX_MQ_CNT + 1 TX queues and RX queues */
dev = alloc_etherdev_mqs(sizeof(*priv), GENET_MAX_MQ_CNT + 1,
@@ -3276,6 +3471,8 @@ static int bcmgenet_probe(struct platform_device *pdev)
goto err;
}
+ spin_lock_init(&priv->lock);
+
SET_NETDEV_DEV(dev, &pdev->dev);
dev_set_drvdata(&pdev->dev, dev);
ether_addr_copy(dev->dev_addr, macaddr);
@@ -3338,6 +3535,13 @@ static int bcmgenet_probe(struct platform_device *pdev)
priv->clk_eee = NULL;
}
+ /* If this is an internal GPHY, power it on now, before UniMAC is
+ * brought out of reset as absolutely no UniMAC activity is allowed
+ */
+ if (dn && !of_property_read_string(dn, "phy-mode", &phy_mode_str) &&
+ !strcasecmp(phy_mode_str, "internal"))
+ bcmgenet_power_up(priv, GENET_POWER_PASSIVE);
+
err = reset_umac(priv);
if (err)
goto err_clk_disable;
@@ -3395,7 +3599,8 @@ static int bcmgenet_suspend(struct device *d)
bcmgenet_netif_stop(dev);
- phy_suspend(priv->phydev);
+ if (!device_may_wakeup(d))
+ phy_suspend(priv->phydev);
netif_device_detach(dev);
@@ -3406,7 +3611,7 @@ static int bcmgenet_suspend(struct device *d)
if (ret)
return ret;
- /* Disable MAC transmit. TX DMA disabled have to done before this */
+ /* Disable MAC transmit. TX DMA disabled must be done before this */
umac_enable_set(priv, CMD_TX_EN, false);
/* tx reclaim */
@@ -3492,7 +3697,8 @@ static int bcmgenet_resume(struct device *d)
netif_device_attach(dev);
- phy_resume(priv->phydev);
+ if (!device_may_wakeup(d))
+ phy_resume(priv->phydev);
if (priv->eee.eee_enabled)
bcmgenet_eee_enable_set(dev, true);
@@ -3502,6 +3708,8 @@ static int bcmgenet_resume(struct device *d)
return 0;
out_clk_disable:
+ if (priv->internal_phy)
+ bcmgenet_power_down(priv, GENET_POWER_PASSIVE);
clk_disable_unprepare(priv->clk);
return ret;
}
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 1e2dc34..efd0702 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2014 Broadcom Corporation
+ * Copyright (c) 2014-2017 Broadcom
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -214,7 +214,9 @@ struct bcmgenet_mib_counters {
#define MDIO_REG_SHIFT 16
#define MDIO_REG_MASK 0x1F
-#define UMAC_RBUF_OVFL_CNT 0x61C
+#define UMAC_RBUF_OVFL_CNT_V1 0x61C
+#define RBUF_OVFL_CNT_V2 0x80
+#define RBUF_OVFL_CNT_V3PLUS 0x94
#define UMAC_MPD_CTRL 0x620
#define MPD_EN (1 << 0)
@@ -224,7 +226,9 @@ struct bcmgenet_mib_counters {
#define UMAC_MPD_PW_MS 0x624
#define UMAC_MPD_PW_LS 0x628
-#define UMAC_RBUF_ERR_CNT 0x634
+#define UMAC_RBUF_ERR_CNT_V1 0x634
+#define RBUF_ERR_CNT_V2 0x84
+#define RBUF_ERR_CNT_V3PLUS 0x98
#define UMAC_MDF_ERR_CNT 0x638
#define UMAC_MDF_CTRL 0x650
#define UMAC_MDF_ADDR 0x654
@@ -351,8 +355,14 @@ struct bcmgenet_mib_counters {
#define EXT_PWR_DN_EN_LD (1 << 3)
#define EXT_ENERGY_DET (1 << 4)
#define EXT_IDDQ_FROM_PHY (1 << 5)
+#define EXT_IDDQ_GLBL_PWR (1 << 7)
#define EXT_PHY_RESET (1 << 8)
#define EXT_ENERGY_DET_MASK (1 << 12)
+#define EXT_PWR_DOWN_PHY_TX (1 << 16)
+#define EXT_PWR_DOWN_PHY_RX (1 << 17)
+#define EXT_PWR_DOWN_PHY_SD (1 << 18)
+#define EXT_PWR_DOWN_PHY_RD (1 << 19)
+#define EXT_PWR_DOWN_PHY_EN (1 << 20)
#define EXT_RGMII_OOB_CTRL 0x0C
#define RGMII_LINK (1 << 4)
@@ -495,13 +505,15 @@ enum bcmgenet_version {
GENET_V1 = 1,
GENET_V2,
GENET_V3,
- GENET_V4
+ GENET_V4,
+ GENET_V5
};
#define GENET_IS_V1(p) ((p)->version == GENET_V1)
#define GENET_IS_V2(p) ((p)->version == GENET_V2)
#define GENET_IS_V3(p) ((p)->version == GENET_V3)
#define GENET_IS_V4(p) ((p)->version == GENET_V4)
+#define GENET_IS_V5(p) ((p)->version == GENET_V5)
/* Hardware flags */
#define GENET_HAS_40BITS (1 << 0)
@@ -540,6 +552,8 @@ struct bcmgenet_skb_cb {
struct bcmgenet_tx_ring {
spinlock_t lock; /* ring lock */
struct napi_struct napi; /* NAPI per tx queue */
+ unsigned long packets;
+ unsigned long bytes;
unsigned int index; /* ring index */
unsigned int queue; /* queue index */
struct enet_cb *cbs; /* tx ring buffer control block*/
@@ -558,6 +572,10 @@ struct bcmgenet_tx_ring {
struct bcmgenet_rx_ring {
struct napi_struct napi; /* Rx NAPI struct */
+ unsigned long bytes;
+ unsigned long packets;
+ unsigned long errors;
+ unsigned long dropped;
unsigned int index; /* Rx ring index */
struct enet_cb *cbs; /* Rx ring buffer control block */
unsigned int size; /* Rx ring size */
@@ -619,11 +637,13 @@ struct bcmgenet_priv {
struct work_struct bcmgenet_irq_work;
int irq0;
int irq1;
- unsigned int irq0_stat;
- unsigned int irq1_stat;
int wol_irq;
bool wol_irq_disabled;
+ /* shared status */
+ spinlock_t lock;
+ unsigned int irq0_stat;
+
/* HW descriptors/checksum variables */
bool desc_64b_en;
bool desc_rxchk_en;
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index b971229..2fbd027 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -1,7 +1,7 @@
/*
* Broadcom GENET (Gigabit Ethernet) Wake-on-LAN support
*
- * Copyright (c) 2014 Broadcom Corporation
+ * Copyright (c) 2014-2017 Broadcom
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -127,7 +127,6 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
enum bcmgenet_power_mode mode)
{
struct net_device *dev = priv->dev;
- u32 cpu_mask_clear;
int retries = 0;
u32 reg;
@@ -173,18 +172,12 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
}
- /* Enable the MPD interrupt */
- cpu_mask_clear = UMAC_IRQ_MPD_R;
-
- bcmgenet_intrl2_0_writel(priv, cpu_mask_clear, INTRL2_CPU_MASK_CLEAR);
-
return 0;
}
void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
enum bcmgenet_power_mode mode)
{
- u32 cpu_mask_set;
u32 reg;
if (mode != GENET_POWER_WOL_MAGIC) {
@@ -201,10 +194,4 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
reg &= ~CMD_CRC_FWD;
bcmgenet_umac_writel(priv, reg, UMAC_CMD);
priv->crc_fwd_en = 0;
-
- /* Stop monitoring magic packet IRQ */
- cpu_mask_set = UMAC_IRQ_MPD_R;
-
- /* Stop monitoring magic packet IRQ */
- bcmgenet_intrl2_0_writel(priv, cpu_mask_set, INTRL2_CPU_MASK_SET);
}
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index e876076..285676f 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -1,7 +1,7 @@
/*
* Broadcom GENET MDIO routines
*
- * Copyright (c) 2014 Broadcom Corporation
+ * Copyright (c) 2014-2017 Broadcom
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -195,53 +195,43 @@ void bcmgenet_phy_power_set(struct net_device *dev, bool enable)
u32 reg = 0;
/* EXT_GPHY_CTRL is only valid for GENETv4 and onward */
- if (!GENET_IS_V4(priv))
- return;
+ if (GENET_IS_V4(priv)) {
+ reg = bcmgenet_ext_readl(priv, EXT_GPHY_CTRL);
+ if (enable) {
+ reg &= ~EXT_CK25_DIS;
+ bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
+ mdelay(1);
- reg = bcmgenet_ext_readl(priv, EXT_GPHY_CTRL);
- if (enable) {
- reg &= ~EXT_CK25_DIS;
+ reg &= ~(EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN);
+ reg |= EXT_GPHY_RESET;
+ bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
+ mdelay(1);
+
+ reg &= ~EXT_GPHY_RESET;
+ } else {
+ reg |= EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN |
+ EXT_GPHY_RESET;
+ bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
+ mdelay(1);
+ reg |= EXT_CK25_DIS;
+ }
bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
- mdelay(1);
-
- reg &= ~(EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN);
- reg |= EXT_GPHY_RESET;
- bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
- mdelay(1);
-
- reg &= ~EXT_GPHY_RESET;
+ udelay(60);
} else {
- reg |= EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN | EXT_GPHY_RESET;
- bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
mdelay(1);
- reg |= EXT_CK25_DIS;
}
- bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
- udelay(60);
-}
-
-static void bcmgenet_internal_phy_setup(struct net_device *dev)
-{
- struct bcmgenet_priv *priv = netdev_priv(dev);
- u32 reg;
-
- /* Power up PHY */
- bcmgenet_phy_power_set(dev, true);
- /* enable APD */
- reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
- reg |= EXT_PWR_DN_EN_LD;
- bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
- bcmgenet_mii_reset(dev);
}
static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv)
{
u32 reg;
- /* Speed settings are set in bcmgenet_mii_setup() */
- reg = bcmgenet_sys_readl(priv, SYS_PORT_CTRL);
- reg |= LED_ACT_SOURCE_MAC;
- bcmgenet_sys_writel(priv, reg, SYS_PORT_CTRL);
+ if (!GENET_IS_V5(priv)) {
+ /* Speed settings are set in bcmgenet_mii_setup() */
+ reg = bcmgenet_sys_readl(priv, SYS_PORT_CTRL);
+ reg |= LED_ACT_SOURCE_MAC;
+ bcmgenet_sys_writel(priv, reg, SYS_PORT_CTRL);
+ }
if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET)
fixed_phy_set_link_update(priv->phydev,
@@ -281,7 +271,6 @@ int bcmgenet_mii_config(struct net_device *dev)
if (priv->internal_phy) {
phy_name = "internal PHY";
- bcmgenet_internal_phy_setup(dev);
} else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) {
phy_name = "MoCA";
bcmgenet_moca_phy_setup(priv);
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 30d1eb9..f395b95 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -825,6 +825,7 @@ static int tg3_ape_event_lock(struct tg3 *tp, u32 timeout_us)
return timeout_us ? 0 : -EBUSY;
}
+#ifdef CONFIG_TIGON3_HWMON
static int tg3_ape_wait_for_event(struct tg3 *tp, u32 timeout_us)
{
u32 i, apedata;
@@ -904,6 +905,7 @@ static int tg3_ape_scratchpad_read(struct tg3 *tp, u32 *data, u32 base_off,
return 0;
}
+#endif
static int tg3_ape_send_event(struct tg3 *tp, u32 event)
{
@@ -10744,6 +10746,7 @@ static int tg3_init_hw(struct tg3 *tp, bool reset_phy)
return tg3_reset_hw(tp, reset_phy);
}
+#ifdef CONFIG_TIGON3_HWMON
static void tg3_sd_scan_scratchpad(struct tg3 *tp, struct tg3_ocir *ocir)
{
int i;
@@ -10826,6 +10829,10 @@ static void tg3_hwmon_open(struct tg3 *tp)
dev_err(&pdev->dev, "Cannot register hwmon device, aborting\n");
}
}
+#else
+static inline void tg3_hwmon_close(struct tg3 *tp) { }
+static inline void tg3_hwmon_open(struct tg3 *tp) { }
+#endif /* CONFIG_TIGON3_HWMON */
#define TG3_STAT_ADD32(PSTAT, REG) \
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
index 9e59663..0f68118 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
@@ -1930,13 +1930,13 @@ static void
bfa_ioc_send_enable(struct bfa_ioc *ioc)
{
struct bfi_ioc_ctrl_req enable_req;
- struct timeval tv;
bfi_h2i_set(enable_req.mh, BFI_MC_IOC, BFI_IOC_H2I_ENABLE_REQ,
bfa_ioc_portid(ioc));
enable_req.clscode = htons(ioc->clscode);
- do_gettimeofday(&tv);
- enable_req.tv_sec = ntohl(tv.tv_sec);
+ enable_req.rsvd = htons(0);
+ /* overflow in 2106 */
+ enable_req.tv_sec = ntohl(ktime_get_real_seconds());
bfa_ioc_mbox_send(ioc, &enable_req, sizeof(struct bfi_ioc_ctrl_req));
}
@@ -1947,6 +1947,10 @@ bfa_ioc_send_disable(struct bfa_ioc *ioc)
bfi_h2i_set(disable_req.mh, BFI_MC_IOC, BFI_IOC_H2I_DISABLE_REQ,
bfa_ioc_portid(ioc));
+ disable_req.clscode = htons(ioc->clscode);
+ disable_req.rsvd = htons(0);
+ /* overflow in 2106 */
+ disable_req.tv_sec = ntohl(ktime_get_real_seconds());
bfa_ioc_mbox_send(ioc, &disable_req, sizeof(struct bfi_ioc_ctrl_req));
}
diff --git a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c
index 05c1c1d..cebfe3b 100644
--- a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c
+++ b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c
@@ -325,7 +325,7 @@ bnad_debugfs_write_regrd(struct file *file, const char __user *buf,
return PTR_ERR(kern_buf);
rc = sscanf(kern_buf, "%x:%x", &addr, &len);
- if (rc < 2) {
+ if (rc < 2 || len > UINT_MAX >> 2) {
netdev_warn(bnad->netdev, "failed to read user buffer\n");
kfree(kern_buf);
return -EINVAL;
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index 30606b1..5cbd1e7 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -684,8 +684,8 @@ static void macb_tx_error_task(struct work_struct *work)
netdev_vdbg(bp->dev, "txerr skb %u (data %p) TX complete\n",
macb_tx_ring_wrap(bp, tail),
skb->data);
- bp->stats.tx_packets++;
- bp->stats.tx_bytes += skb->len;
+ bp->dev->stats.tx_packets++;
+ bp->dev->stats.tx_bytes += skb->len;
}
} else {
/* "Buffers exhausted mid-frame" errors may only happen
@@ -778,8 +778,8 @@ static void macb_tx_interrupt(struct macb_queue *queue)
netdev_vdbg(bp->dev, "skb %u (data %p) TX complete\n",
macb_tx_ring_wrap(bp, tail),
skb->data);
- bp->stats.tx_packets++;
- bp->stats.tx_bytes += skb->len;
+ bp->dev->stats.tx_packets++;
+ bp->dev->stats.tx_bytes += skb->len;
}
/* Now we can safely release resources */
@@ -911,14 +911,14 @@ static int gem_rx(struct macb *bp, int budget)
if (!(ctrl & MACB_BIT(RX_SOF) && ctrl & MACB_BIT(RX_EOF))) {
netdev_err(bp->dev,
"not whole frame pointed by descriptor\n");
- bp->stats.rx_dropped++;
+ bp->dev->stats.rx_dropped++;
break;
}
skb = bp->rx_skbuff[entry];
if (unlikely(!skb)) {
netdev_err(bp->dev,
"inconsistent Rx descriptor chain\n");
- bp->stats.rx_dropped++;
+ bp->dev->stats.rx_dropped++;
break;
}
/* now everything is ready for receiving packet */
@@ -938,8 +938,8 @@ static int gem_rx(struct macb *bp, int budget)
GEM_BFEXT(RX_CSUM, ctrl) & GEM_RX_CSUM_CHECKED_MASK)
skb->ip_summed = CHECKSUM_UNNECESSARY;
- bp->stats.rx_packets++;
- bp->stats.rx_bytes += skb->len;
+ bp->dev->stats.rx_packets++;
+ bp->dev->stats.rx_bytes += skb->len;
#if defined(DEBUG) && defined(VERBOSE_DEBUG)
netdev_vdbg(bp->dev, "received skb of length %u, csum: %08x\n",
@@ -984,7 +984,7 @@ static int macb_rx_frame(struct macb *bp, unsigned int first_frag,
*/
skb = netdev_alloc_skb(bp->dev, len + NET_IP_ALIGN);
if (!skb) {
- bp->stats.rx_dropped++;
+ bp->dev->stats.rx_dropped++;
for (frag = first_frag; ; frag++) {
desc = macb_rx_desc(bp, frag);
desc->addr &= ~MACB_BIT(RX_USED);
@@ -1030,8 +1030,8 @@ static int macb_rx_frame(struct macb *bp, unsigned int first_frag,
__skb_pull(skb, NET_IP_ALIGN);
skb->protocol = eth_type_trans(skb, bp->dev);
- bp->stats.rx_packets++;
- bp->stats.rx_bytes += skb->len;
+ bp->dev->stats.rx_packets++;
+ bp->dev->stats.rx_bytes += skb->len;
netdev_vdbg(bp->dev, "received skb of length %u, csum: %08x\n",
skb->len, skb->csum);
netif_receive_skb(skb);
@@ -2210,7 +2210,7 @@ static void gem_update_stats(struct macb *bp)
static struct net_device_stats *gem_get_stats(struct macb *bp)
{
struct gem_stats *hwstat = &bp->hw_stats.gem;
- struct net_device_stats *nstat = &bp->stats;
+ struct net_device_stats *nstat = &bp->dev->stats;
gem_update_stats(bp);
@@ -2281,7 +2281,7 @@ static void gem_get_ethtool_strings(struct net_device *dev, u32 sset, u8 *p)
static struct net_device_stats *macb_get_stats(struct net_device *dev)
{
struct macb *bp = netdev_priv(dev);
- struct net_device_stats *nstat = &bp->stats;
+ struct net_device_stats *nstat = &bp->dev->stats;
struct macb_stats *hwstat = &bp->hw_stats.macb;
if (macb_is_gem(bp))
@@ -2993,15 +2993,15 @@ static void at91ether_rx(struct net_device *dev)
memcpy(skb_put(skb, pktlen), p_recv, pktlen);
skb->protocol = eth_type_trans(skb, dev);
- lp->stats.rx_packets++;
- lp->stats.rx_bytes += pktlen;
+ dev->stats.rx_packets++;
+ dev->stats.rx_bytes += pktlen;
netif_rx(skb);
} else {
- lp->stats.rx_dropped++;
+ dev->stats.rx_dropped++;
}
if (desc->ctrl & MACB_BIT(RX_MHASH_MATCH))
- lp->stats.multicast++;
+ dev->stats.multicast++;
/* reset ownership bit */
desc->addr &= ~MACB_BIT(RX_USED);
@@ -3036,15 +3036,15 @@ static irqreturn_t at91ether_interrupt(int irq, void *dev_id)
if (intstatus & MACB_BIT(TCOMP)) {
/* The TCOM bit is set even if the transmission failed */
if (intstatus & (MACB_BIT(ISR_TUND) | MACB_BIT(ISR_RLE)))
- lp->stats.tx_errors++;
+ dev->stats.tx_errors++;
if (lp->skb) {
dev_kfree_skb_irq(lp->skb);
lp->skb = NULL;
dma_unmap_single(NULL, lp->skb_physaddr,
lp->skb_length, DMA_TO_DEVICE);
- lp->stats.tx_packets++;
- lp->stats.tx_bytes += lp->skb_length;
+ dev->stats.tx_packets++;
+ dev->stats.tx_bytes += lp->skb_length;
}
netif_wake_queue(dev);
}
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 234a49e..ec037b0 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -919,7 +919,6 @@ struct macb {
struct clk *rx_clk;
struct net_device *dev;
struct napi_struct napi;
- struct net_device_stats stats;
union {
struct macb_stats macb;
struct gem_stats gem;
diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h
index 2fedd91..dee6046 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h
@@ -43,6 +43,8 @@ struct octeon_cn23xx_pf {
struct octeon_config *conf;
};
+#define CN23XX_SLI_DEF_BP 0x40
+
int setup_cn23xx_octeon_pf_device(struct octeon_device *oct);
int validate_cn23xx_pf_config_info(struct octeon_device *oct,
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c
index f629c2f..796c2cb 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_core.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c
@@ -26,6 +26,9 @@
#include "octeon_main.h"
#include "octeon_network.h"
+/* OOM task polling interval */
+#define LIO_OOM_POLL_INTERVAL_MS 250
+
int liquidio_set_feature(struct net_device *netdev, int cmd, u16 param1)
{
struct lio *lio = GET_LIO(netdev);
@@ -124,6 +127,17 @@ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr)
struct octeon_device *oct = lio->oct_dev;
u8 *mac;
+ if (nctrl->completion && nctrl->response_code) {
+ /* Signal whoever is interested that the response code from the
+ * firmware has arrived.
+ */
+ WRITE_ONCE(*nctrl->response_code, nctrl->status);
+ complete(nctrl->completion);
+ }
+
+ if (nctrl->status)
+ return;
+
switch (nctrl->ncmd.s.cmd) {
case OCTNET_CMD_CHANGE_DEVFLAGS:
case OCTNET_CMD_SET_MULTI_LIST:
@@ -131,11 +145,20 @@ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr)
case OCTNET_CMD_CHANGE_MACADDR:
mac = ((u8 *)&nctrl->udd[0]) + 2;
- netif_info(lio, probe, lio->netdev,
- "MACAddr changed to %2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x\n",
- mac[0], mac[1],
- mac[2], mac[3],
- mac[4], mac[5]);
+ if (nctrl->ncmd.s.param1) {
+ /* vfidx is 0 based, but vf_num (param1) is 1 based */
+ int vfidx = nctrl->ncmd.s.param1 - 1;
+ bool mac_is_admin_assigned = nctrl->ncmd.s.param2;
+
+ if (mac_is_admin_assigned)
+ netif_info(lio, probe, lio->netdev,
+ "MAC Address %pM is configured for VF %d\n",
+ mac, vfidx);
+ } else {
+ netif_info(lio, probe, lio->netdev,
+ " MACAddr changed to %pM\n",
+ mac);
+ }
break;
case OCTNET_CMD_CHANGE_MTU:
@@ -284,3 +307,56 @@ void octeon_pf_changed_vf_macaddr(struct octeon_device *oct, u8 *mac)
* the PF did that already
*/
}
+
+static void octnet_poll_check_rxq_oom_status(struct work_struct *work)
+{
+ struct cavium_wk *wk = (struct cavium_wk *)work;
+ struct lio *lio = (struct lio *)wk->ctxptr;
+ struct octeon_device *oct = lio->oct_dev;
+ struct octeon_droq *droq;
+ int q, q_no = 0;
+
+ if (ifstate_check(lio, LIO_IFSTATE_RUNNING)) {
+ for (q = 0; q < lio->linfo.num_rxpciq; q++) {
+ q_no = lio->linfo.rxpciq[q].s.q_no;
+ droq = oct->droq[q_no];
+ if (!droq)
+ continue;
+ octeon_droq_check_oom(droq);
+ }
+ }
+ queue_delayed_work(lio->rxq_status_wq.wq,
+ &lio->rxq_status_wq.wk.work,
+ msecs_to_jiffies(LIO_OOM_POLL_INTERVAL_MS));
+}
+
+int setup_rx_oom_poll_fn(struct net_device *netdev)
+{
+ struct lio *lio = GET_LIO(netdev);
+ struct octeon_device *oct = lio->oct_dev;
+
+ lio->rxq_status_wq.wq = alloc_workqueue("rxq-oom-status",
+ WQ_MEM_RECLAIM, 0);
+ if (!lio->rxq_status_wq.wq) {
+ dev_err(&oct->pci_dev->dev, "unable to create cavium rxq oom status wq\n");
+ return -ENOMEM;
+ }
+ INIT_DELAYED_WORK(&lio->rxq_status_wq.wk.work,
+ octnet_poll_check_rxq_oom_status);
+ lio->rxq_status_wq.wk.ctxptr = lio;
+ queue_delayed_work(lio->rxq_status_wq.wq,
+ &lio->rxq_status_wq.wk.work,
+ msecs_to_jiffies(LIO_OOM_POLL_INTERVAL_MS));
+ return 0;
+}
+
+void cleanup_rx_oom_poll_fn(struct net_device *netdev)
+{
+ struct lio *lio = GET_LIO(netdev);
+
+ if (lio->rxq_status_wq.wq) {
+ cancel_delayed_work_sync(&lio->rxq_status_wq.wk.work);
+ flush_workqueue(lio->rxq_status_wq.wq);
+ destroy_workqueue(lio->rxq_status_wq.wq);
+ }
+}
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
index 50384ce..dab10c7 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
@@ -33,6 +33,19 @@
static int octnet_get_link_stats(struct net_device *netdev);
+struct oct_intrmod_context {
+ int octeon_id;
+ wait_queue_head_t wc;
+ int cond;
+ int status;
+};
+
+struct oct_intrmod_resp {
+ u64 rh;
+ struct oct_intrmod_cfg intrmod;
+ u64 status;
+};
+
struct oct_mdio_cmd_context {
int octeon_id;
wait_queue_head_t wc;
@@ -213,17 +226,23 @@ static int lio_get_link_ksettings(struct net_device *netdev,
struct lio *lio = GET_LIO(netdev);
struct octeon_device *oct = lio->oct_dev;
struct oct_link_info *linfo;
- u32 supported, advertising;
+ u32 supported = 0, advertising = 0;
linfo = &lio->linfo;
if (linfo->link.s.if_mode == INTERFACE_MODE_XAUI ||
linfo->link.s.if_mode == INTERFACE_MODE_RXAUI ||
+ linfo->link.s.if_mode == INTERFACE_MODE_XLAUI ||
linfo->link.s.if_mode == INTERFACE_MODE_XFI) {
ecmd->base.port = PORT_FIBRE;
- supported = (SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE |
- SUPPORTED_Pause);
- advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_Pause);
+
+ if (linfo->link.s.speed == SPEED_10000) {
+ supported = SUPPORTED_10000baseT_Full;
+ advertising = ADVERTISED_10000baseT_Full;
+ }
+
+ supported |= SUPPORTED_FIBRE | SUPPORTED_Pause;
+ advertising |= ADVERTISED_Pause;
ethtool_convert_legacy_u32_to_link_mode(
ecmd->link_modes.supported, supported);
ethtool_convert_legacy_u32_to_link_mode(
@@ -1292,95 +1311,103 @@ static int lio_vf_get_sset_count(struct net_device *netdev, int sset)
}
}
-static int lio_get_intr_coalesce(struct net_device *netdev,
- struct ethtool_coalesce *intr_coal)
-{
- struct lio *lio = GET_LIO(netdev);
- struct octeon_device *oct = lio->oct_dev;
- struct octeon_instr_queue *iq;
- struct oct_intrmod_cfg *intrmod_cfg;
-
- intrmod_cfg = &oct->intrmod;
-
- switch (oct->chip_id) {
- case OCTEON_CN23XX_PF_VID:
- case OCTEON_CN23XX_VF_VID:
- if (!intrmod_cfg->rx_enable) {
- intr_coal->rx_coalesce_usecs = intrmod_cfg->rx_usecs;
- intr_coal->rx_max_coalesced_frames =
- intrmod_cfg->rx_frames;
- }
- if (!intrmod_cfg->tx_enable)
- intr_coal->tx_max_coalesced_frames =
- intrmod_cfg->tx_frames;
- break;
- case OCTEON_CN68XX:
- case OCTEON_CN66XX: {
- struct octeon_cn6xxx *cn6xxx =
- (struct octeon_cn6xxx *)oct->chip;
-
- if (!intrmod_cfg->rx_enable) {
- intr_coal->rx_coalesce_usecs =
- CFG_GET_OQ_INTR_TIME(cn6xxx->conf);
- intr_coal->rx_max_coalesced_frames =
- CFG_GET_OQ_INTR_PKT(cn6xxx->conf);
- }
- iq = oct->instr_queue[lio->linfo.txpciq[0].s.q_no];
- intr_coal->tx_max_coalesced_frames = iq->fill_threshold;
- break;
- }
- default:
- netif_info(lio, drv, lio->netdev, "Unknown Chip !!\n");
- return -EINVAL;
- }
- if (intrmod_cfg->rx_enable) {
- intr_coal->use_adaptive_rx_coalesce =
- intrmod_cfg->rx_enable;
- intr_coal->rate_sample_interval =
- intrmod_cfg->check_intrvl;
- intr_coal->pkt_rate_high =
- intrmod_cfg->maxpkt_ratethr;
- intr_coal->pkt_rate_low =
- intrmod_cfg->minpkt_ratethr;
- intr_coal->rx_max_coalesced_frames_high =
- intrmod_cfg->rx_maxcnt_trigger;
- intr_coal->rx_coalesce_usecs_high =
- intrmod_cfg->rx_maxtmr_trigger;
- intr_coal->rx_coalesce_usecs_low =
- intrmod_cfg->rx_mintmr_trigger;
- intr_coal->rx_max_coalesced_frames_low =
- intrmod_cfg->rx_mincnt_trigger;
- }
- if ((OCTEON_CN23XX_PF(oct) || OCTEON_CN23XX_VF(oct)) &&
- (intrmod_cfg->tx_enable)) {
- intr_coal->use_adaptive_tx_coalesce = intrmod_cfg->tx_enable;
- intr_coal->tx_max_coalesced_frames_high =
- intrmod_cfg->tx_maxcnt_trigger;
- intr_coal->tx_max_coalesced_frames_low =
- intrmod_cfg->tx_mincnt_trigger;
- }
- return 0;
-}
-
/* Callback function for intrmod */
static void octnet_intrmod_callback(struct octeon_device *oct_dev,
u32 status,
void *ptr)
{
- struct oct_intrmod_cmd *cmd = ptr;
- struct octeon_soft_command *sc = cmd->sc;
+ struct octeon_soft_command *sc = (struct octeon_soft_command *)ptr;
+ struct oct_intrmod_context *ctx;
- oct_dev = cmd->oct_dev;
+ ctx = (struct oct_intrmod_context *)sc->ctxptr;
- if (status)
- dev_err(&oct_dev->pci_dev->dev, "intrmod config failed. Status: %llx\n",
- CVM_CAST64(status));
- else
- dev_info(&oct_dev->pci_dev->dev,
- "Rx-Adaptive Interrupt moderation enabled:%llx\n",
- oct_dev->intrmod.rx_enable);
+ ctx->status = status;
+
+ oct_dev = lio_get_device(ctx->octeon_id);
+
+ WRITE_ONCE(ctx->cond, 1);
+
+ /* This barrier is required to be sure that the response has been
+ * written fully before waking up the handler
+ */
+ wmb();
+
+ wake_up_interruptible(&ctx->wc);
+}
+
+/* get interrupt moderation parameters */
+static int octnet_get_intrmod_cfg(struct lio *lio,
+ struct oct_intrmod_cfg *intr_cfg)
+{
+ struct octeon_soft_command *sc;
+ struct oct_intrmod_context *ctx;
+ struct oct_intrmod_resp *resp;
+ int retval;
+ struct octeon_device *oct_dev = lio->oct_dev;
+
+ /* Alloc soft command */
+ sc = (struct octeon_soft_command *)
+ octeon_alloc_soft_command(oct_dev,
+ 0,
+ sizeof(struct oct_intrmod_resp),
+ sizeof(struct oct_intrmod_context));
+
+ if (!sc)
+ return -ENOMEM;
+
+ resp = (struct oct_intrmod_resp *)sc->virtrptr;
+ memset(resp, 0, sizeof(struct oct_intrmod_resp));
+
+ ctx = (struct oct_intrmod_context *)sc->ctxptr;
+ memset(ctx, 0, sizeof(struct oct_intrmod_context));
+ WRITE_ONCE(ctx->cond, 0);
+ ctx->octeon_id = lio_get_device_id(oct_dev);
+ init_waitqueue_head(&ctx->wc);
+
+ sc->iq_no = lio->linfo.txpciq[0].s.q_no;
+
+ octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC,
+ OPCODE_NIC_INTRMOD_PARAMS, 0, 0, 0);
+
+ sc->callback = octnet_intrmod_callback;
+ sc->callback_arg = sc;
+ sc->wait_time = 1000;
+
+ retval = octeon_send_soft_command(oct_dev, sc);
+ if (retval == IQ_SEND_FAILED) {
+ octeon_free_soft_command(oct_dev, sc);
+ return -EINVAL;
+ }
+
+ /* Sleep on a wait queue till the cond flag indicates that the
+ * response arrived or timed-out.
+ */
+ if (sleep_cond(&ctx->wc, &ctx->cond) == -EINTR) {
+ dev_err(&oct_dev->pci_dev->dev, "Wait interrupted\n");
+ goto intrmod_info_wait_intr;
+ }
+
+ retval = ctx->status || resp->status;
+ if (retval) {
+ dev_err(&oct_dev->pci_dev->dev,
+ "Get interrupt moderation parameters failed\n");
+ goto intrmod_info_wait_fail;
+ }
+
+ octeon_swap_8B_data((u64 *)&resp->intrmod,
+ (sizeof(struct oct_intrmod_cfg)) / 8);
+ memcpy(intr_cfg, &resp->intrmod, sizeof(struct oct_intrmod_cfg));
+ octeon_free_soft_command(oct_dev, sc);
+
+ return 0;
+
+intrmod_info_wait_fail:
octeon_free_soft_command(oct_dev, sc);
+
+intrmod_info_wait_intr:
+
+ return -ENODEV;
}
/* Configure interrupt moderation parameters */
@@ -1388,7 +1415,7 @@ static int octnet_set_intrmod_cfg(struct lio *lio,
struct oct_intrmod_cfg *intr_cfg)
{
struct octeon_soft_command *sc;
- struct oct_intrmod_cmd *cmd;
+ struct oct_intrmod_context *ctx;
struct oct_intrmod_cfg *cfg;
int retval;
struct octeon_device *oct_dev = lio->oct_dev;
@@ -1398,19 +1425,21 @@ static int octnet_set_intrmod_cfg(struct lio *lio,
octeon_alloc_soft_command(oct_dev,
sizeof(struct oct_intrmod_cfg),
0,
- sizeof(struct oct_intrmod_cmd));
+ sizeof(struct oct_intrmod_context));
if (!sc)
return -ENOMEM;
- cmd = (struct oct_intrmod_cmd *)sc->ctxptr;
+ ctx = (struct oct_intrmod_context *)sc->ctxptr;
+
+ WRITE_ONCE(ctx->cond, 0);
+ ctx->octeon_id = lio_get_device_id(oct_dev);
+ init_waitqueue_head(&ctx->wc);
+
cfg = (struct oct_intrmod_cfg *)sc->virtdptr;
memcpy(cfg, intr_cfg, sizeof(struct oct_intrmod_cfg));
octeon_swap_8B_data((u64 *)cfg, (sizeof(struct oct_intrmod_cfg)) / 8);
- cmd->sc = sc;
- cmd->cfg = cfg;
- cmd->oct_dev = oct_dev;
sc->iq_no = lio->linfo.txpciq[0].s.q_no;
@@ -1418,7 +1447,7 @@ static int octnet_set_intrmod_cfg(struct lio *lio,
OPCODE_NIC_INTRMOD_CFG, 0, 0, 0);
sc->callback = octnet_intrmod_callback;
- sc->callback_arg = cmd;
+ sc->callback_arg = sc;
sc->wait_time = 1000;
retval = octeon_send_soft_command(oct_dev, sc);
@@ -1427,7 +1456,29 @@ static int octnet_set_intrmod_cfg(struct lio *lio,
return -EINVAL;
}
- return 0;
+ /* Sleep on a wait queue till the cond flag indicates that the
+ * response arrived or timed-out.
+ */
+ if (sleep_cond(&ctx->wc, &ctx->cond) != -EINTR) {
+ retval = ctx->status;
+ if (retval)
+ dev_err(&oct_dev->pci_dev->dev,
+ "intrmod config failed. Status: %llx\n",
+ CVM_CAST64(retval));
+ else
+ dev_info(&oct_dev->pci_dev->dev,
+ "Rx-Adaptive Interrupt moderation %s\n",
+ (intr_cfg->rx_enable) ?
+ "enabled" : "disabled");
+
+ octeon_free_soft_command(oct_dev, sc);
+
+ return ((retval) ? -ENODEV : 0);
+ }
+
+ dev_err(&oct_dev->pci_dev->dev, "iq/oq config failed\n");
+
+ return -EINTR;
}
static void
@@ -1584,80 +1635,106 @@ static int octnet_get_link_stats(struct net_device *netdev)
return 0;
}
+static int lio_get_intr_coalesce(struct net_device *netdev,
+ struct ethtool_coalesce *intr_coal)
+{
+ struct lio *lio = GET_LIO(netdev);
+ struct octeon_device *oct = lio->oct_dev;
+ struct octeon_instr_queue *iq;
+ struct oct_intrmod_cfg intrmod_cfg;
+
+ if (octnet_get_intrmod_cfg(lio, &intrmod_cfg))
+ return -ENODEV;
+
+ switch (oct->chip_id) {
+ case OCTEON_CN23XX_PF_VID:
+ case OCTEON_CN23XX_VF_VID: {
+ if (!intrmod_cfg.rx_enable) {
+ intr_coal->rx_coalesce_usecs = oct->rx_coalesce_usecs;
+ intr_coal->rx_max_coalesced_frames =
+ oct->rx_max_coalesced_frames;
+ }
+ if (!intrmod_cfg.tx_enable)
+ intr_coal->tx_max_coalesced_frames =
+ oct->tx_max_coalesced_frames;
+ break;
+ }
+ case OCTEON_CN68XX:
+ case OCTEON_CN66XX: {
+ struct octeon_cn6xxx *cn6xxx =
+ (struct octeon_cn6xxx *)oct->chip;
+
+ if (!intrmod_cfg.rx_enable) {
+ intr_coal->rx_coalesce_usecs =
+ CFG_GET_OQ_INTR_TIME(cn6xxx->conf);
+ intr_coal->rx_max_coalesced_frames =
+ CFG_GET_OQ_INTR_PKT(cn6xxx->conf);
+ }
+ iq = oct->instr_queue[lio->linfo.txpciq[0].s.q_no];
+ intr_coal->tx_max_coalesced_frames = iq->fill_threshold;
+ break;
+ }
+ default:
+ netif_info(lio, drv, lio->netdev, "Unknown Chip !!\n");
+ return -EINVAL;
+ }
+ if (intrmod_cfg.rx_enable) {
+ intr_coal->use_adaptive_rx_coalesce =
+ intrmod_cfg.rx_enable;
+ intr_coal->rate_sample_interval =
+ intrmod_cfg.check_intrvl;
+ intr_coal->pkt_rate_high =
+ intrmod_cfg.maxpkt_ratethr;
+ intr_coal->pkt_rate_low =
+ intrmod_cfg.minpkt_ratethr;
+ intr_coal->rx_max_coalesced_frames_high =
+ intrmod_cfg.rx_maxcnt_trigger;
+ intr_coal->rx_coalesce_usecs_high =
+ intrmod_cfg.rx_maxtmr_trigger;
+ intr_coal->rx_coalesce_usecs_low =
+ intrmod_cfg.rx_mintmr_trigger;
+ intr_coal->rx_max_coalesced_frames_low =
+ intrmod_cfg.rx_mincnt_trigger;
+ }
+ if ((OCTEON_CN23XX_PF(oct) || OCTEON_CN23XX_VF(oct)) &&
+ (intrmod_cfg.tx_enable)) {
+ intr_coal->use_adaptive_tx_coalesce =
+ intrmod_cfg.tx_enable;
+ intr_coal->tx_max_coalesced_frames_high =
+ intrmod_cfg.tx_maxcnt_trigger;
+ intr_coal->tx_max_coalesced_frames_low =
+ intrmod_cfg.tx_mincnt_trigger;
+ }
+ return 0;
+}
+
/* Enable/Disable auto interrupt Moderation */
-static int oct_cfg_adaptive_intr(struct lio *lio, struct ethtool_coalesce
- *intr_coal)
+static int oct_cfg_adaptive_intr(struct lio *lio,
+ struct oct_intrmod_cfg *intrmod_cfg,
+ struct ethtool_coalesce *intr_coal)
{
int ret = 0;
- struct octeon_device *oct = lio->oct_dev;
- struct oct_intrmod_cfg *intrmod_cfg;
- intrmod_cfg = &oct->intrmod;
-
- if (oct->intrmod.rx_enable || oct->intrmod.tx_enable) {
- if (intr_coal->rate_sample_interval)
- intrmod_cfg->check_intrvl =
- intr_coal->rate_sample_interval;
- else
- intrmod_cfg->check_intrvl =
- LIO_INTRMOD_CHECK_INTERVAL;
-
- if (intr_coal->pkt_rate_high)
- intrmod_cfg->maxpkt_ratethr =
- intr_coal->pkt_rate_high;
- else
- intrmod_cfg->maxpkt_ratethr =
- LIO_INTRMOD_MAXPKT_RATETHR;
-
- if (intr_coal->pkt_rate_low)
- intrmod_cfg->minpkt_ratethr =
- intr_coal->pkt_rate_low;
- else
- intrmod_cfg->minpkt_ratethr =
- LIO_INTRMOD_MINPKT_RATETHR;
+ if (intrmod_cfg->rx_enable || intrmod_cfg->tx_enable) {
+ intrmod_cfg->check_intrvl = intr_coal->rate_sample_interval;
+ intrmod_cfg->maxpkt_ratethr = intr_coal->pkt_rate_high;
+ intrmod_cfg->minpkt_ratethr = intr_coal->pkt_rate_low;
}
- if (oct->intrmod.rx_enable) {
- if (intr_coal->rx_max_coalesced_frames_high)
- intrmod_cfg->rx_maxcnt_trigger =
- intr_coal->rx_max_coalesced_frames_high;
- else
- intrmod_cfg->rx_maxcnt_trigger =
- LIO_INTRMOD_RXMAXCNT_TRIGGER;
-
- if (intr_coal->rx_coalesce_usecs_high)
- intrmod_cfg->rx_maxtmr_trigger =
- intr_coal->rx_coalesce_usecs_high;
- else
- intrmod_cfg->rx_maxtmr_trigger =
- LIO_INTRMOD_RXMAXTMR_TRIGGER;
-
- if (intr_coal->rx_coalesce_usecs_low)
- intrmod_cfg->rx_mintmr_trigger =
- intr_coal->rx_coalesce_usecs_low;
- else
- intrmod_cfg->rx_mintmr_trigger =
- LIO_INTRMOD_RXMINTMR_TRIGGER;
-
- if (intr_coal->rx_max_coalesced_frames_low)
- intrmod_cfg->rx_mincnt_trigger =
- intr_coal->rx_max_coalesced_frames_low;
- else
- intrmod_cfg->rx_mincnt_trigger =
- LIO_INTRMOD_RXMINCNT_TRIGGER;
+ if (intrmod_cfg->rx_enable) {
+ intrmod_cfg->rx_maxcnt_trigger =
+ intr_coal->rx_max_coalesced_frames_high;
+ intrmod_cfg->rx_maxtmr_trigger =
+ intr_coal->rx_coalesce_usecs_high;
+ intrmod_cfg->rx_mintmr_trigger =
+ intr_coal->rx_coalesce_usecs_low;
+ intrmod_cfg->rx_mincnt_trigger =
+ intr_coal->rx_max_coalesced_frames_low;
}
- if (oct->intrmod.tx_enable) {
- if (intr_coal->tx_max_coalesced_frames_high)
- intrmod_cfg->tx_maxcnt_trigger =
- intr_coal->tx_max_coalesced_frames_high;
- else
- intrmod_cfg->tx_maxcnt_trigger =
- LIO_INTRMOD_TXMAXCNT_TRIGGER;
- if (intr_coal->tx_max_coalesced_frames_low)
- intrmod_cfg->tx_mincnt_trigger =
- intr_coal->tx_max_coalesced_frames_low;
- else
- intrmod_cfg->tx_mincnt_trigger =
- LIO_INTRMOD_TXMINCNT_TRIGGER;
+ if (intrmod_cfg->tx_enable) {
+ intrmod_cfg->tx_maxcnt_trigger =
+ intr_coal->tx_max_coalesced_frames_high;
+ intrmod_cfg->tx_mincnt_trigger =
+ intr_coal->tx_max_coalesced_frames_low;
}
ret = octnet_set_intrmod_cfg(lio, intrmod_cfg);
@@ -1666,7 +1743,9 @@ static int oct_cfg_adaptive_intr(struct lio *lio, struct ethtool_coalesce
}
static int
-oct_cfg_rx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal)
+oct_cfg_rx_intrcnt(struct lio *lio,
+ struct oct_intrmod_cfg *intrmod,
+ struct ethtool_coalesce *intr_coal)
{
struct octeon_device *oct = lio->oct_dev;
u32 rx_max_coalesced_frames;
@@ -1692,7 +1771,7 @@ oct_cfg_rx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal)
int q_no;
if (!intr_coal->rx_max_coalesced_frames)
- rx_max_coalesced_frames = oct->intrmod.rx_frames;
+ rx_max_coalesced_frames = intrmod->rx_frames;
else
rx_max_coalesced_frames =
intr_coal->rx_max_coalesced_frames;
@@ -1703,17 +1782,18 @@ oct_cfg_rx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal)
(octeon_read_csr64(
oct, CN23XX_SLI_OQ_PKT_INT_LEVELS(q_no)) &
(0x3fffff00000000UL)) |
- rx_max_coalesced_frames);
+ (rx_max_coalesced_frames - 1));
/*consider setting resend bit*/
}
- oct->intrmod.rx_frames = rx_max_coalesced_frames;
+ intrmod->rx_frames = rx_max_coalesced_frames;
+ oct->rx_max_coalesced_frames = rx_max_coalesced_frames;
break;
}
case OCTEON_CN23XX_VF_VID: {
int q_no;
if (!intr_coal->rx_max_coalesced_frames)
- rx_max_coalesced_frames = oct->intrmod.rx_frames;
+ rx_max_coalesced_frames = intrmod->rx_frames;
else
rx_max_coalesced_frames =
intr_coal->rx_max_coalesced_frames;
@@ -1724,9 +1804,10 @@ oct_cfg_rx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal)
oct, CN23XX_VF_SLI_OQ_PKT_INT_LEVELS(q_no)) &
(0x3fffff00000000UL)) |
rx_max_coalesced_frames);
- /* consider writing to resend bit here */
+ /*consider writing to resend bit here*/
}
- oct->intrmod.rx_frames = rx_max_coalesced_frames;
+ intrmod->rx_frames = rx_max_coalesced_frames;
+ oct->rx_max_coalesced_frames = rx_max_coalesced_frames;
break;
}
default:
@@ -1736,6 +1817,7 @@ oct_cfg_rx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal)
}
static int oct_cfg_rx_intrtime(struct lio *lio,
+ struct oct_intrmod_cfg *intrmod,
struct ethtool_coalesce *intr_coal)
{
struct octeon_device *oct = lio->oct_dev;
@@ -1766,7 +1848,7 @@ static int oct_cfg_rx_intrtime(struct lio *lio,
int q_no;
if (!intr_coal->rx_coalesce_usecs)
- rx_coalesce_usecs = oct->intrmod.rx_usecs;
+ rx_coalesce_usecs = intrmod->rx_usecs;
else
rx_coalesce_usecs = intr_coal->rx_coalesce_usecs;
time_threshold =
@@ -1775,11 +1857,12 @@ static int oct_cfg_rx_intrtime(struct lio *lio,
q_no += oct->sriov_info.pf_srn;
octeon_write_csr64(oct,
CN23XX_SLI_OQ_PKT_INT_LEVELS(q_no),
- (oct->intrmod.rx_frames |
- (time_threshold << 32)));
+ (intrmod->rx_frames |
+ ((u64)time_threshold << 32)));
/*consider writing to resend bit here*/
}
- oct->intrmod.rx_usecs = rx_coalesce_usecs;
+ intrmod->rx_usecs = rx_coalesce_usecs;
+ oct->rx_coalesce_usecs = rx_coalesce_usecs;
break;
}
case OCTEON_CN23XX_VF_VID: {
@@ -1787,7 +1870,7 @@ static int oct_cfg_rx_intrtime(struct lio *lio,
int q_no;
if (!intr_coal->rx_coalesce_usecs)
- rx_coalesce_usecs = oct->intrmod.rx_usecs;
+ rx_coalesce_usecs = intrmod->rx_usecs;
else
rx_coalesce_usecs = intr_coal->rx_coalesce_usecs;
@@ -1796,11 +1879,12 @@ static int oct_cfg_rx_intrtime(struct lio *lio,
for (q_no = 0; q_no < oct->num_oqs; q_no++) {
octeon_write_csr64(
oct, CN23XX_VF_SLI_OQ_PKT_INT_LEVELS(q_no),
- (oct->intrmod.rx_frames |
- (time_threshold << 32)));
- /* consider setting resend bit */
+ (intrmod->rx_frames |
+ ((u64)time_threshold << 32)));
+ /*consider setting resend bit*/
}
- oct->intrmod.rx_usecs = rx_coalesce_usecs;
+ intrmod->rx_usecs = rx_coalesce_usecs;
+ oct->rx_coalesce_usecs = rx_coalesce_usecs;
break;
}
default:
@@ -1811,8 +1895,9 @@ static int oct_cfg_rx_intrtime(struct lio *lio,
}
static int
-oct_cfg_tx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal
- __attribute__((unused)))
+oct_cfg_tx_intrcnt(struct lio *lio,
+ struct oct_intrmod_cfg *intrmod,
+ struct ethtool_coalesce *intr_coal)
{
struct octeon_device *oct = lio->oct_dev;
u32 iq_intr_pkt;
@@ -1839,12 +1924,13 @@ oct_cfg_tx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal
val = readq(inst_cnt_reg);
/*clear wmark and count.dont want to write count back*/
val = (val & 0xFFFF000000000000ULL) |
- ((u64)iq_intr_pkt
+ ((u64)(iq_intr_pkt - 1)
<< CN23XX_PKT_IN_DONE_WMARK_BIT_POS);
writeq(val, inst_cnt_reg);
/*consider setting resend bit*/
}
- oct->intrmod.tx_frames = iq_intr_pkt;
+ intrmod->tx_frames = iq_intr_pkt;
+ oct->tx_max_coalesced_frames = iq_intr_pkt;
break;
}
default:
@@ -1859,6 +1945,7 @@ static int lio_set_intr_coalesce(struct net_device *netdev,
struct lio *lio = GET_LIO(netdev);
int ret;
struct octeon_device *oct = lio->oct_dev;
+ struct oct_intrmod_cfg intrmod = {0};
u32 j, q_no;
int db_max, db_min;
@@ -1877,8 +1964,8 @@ static int lio_set_intr_coalesce(struct net_device *netdev,
} else {
dev_err(&oct->pci_dev->dev,
"LIQUIDIO: Invalid tx-frames:%d. Range is min:%d max:%d\n",
- intr_coal->tx_max_coalesced_frames, db_min,
- db_max);
+ intr_coal->tx_max_coalesced_frames,
+ db_min, db_max);
return -EINVAL;
}
break;
@@ -1889,24 +1976,36 @@ static int lio_set_intr_coalesce(struct net_device *netdev,
return -EINVAL;
}
- oct->intrmod.rx_enable = intr_coal->use_adaptive_rx_coalesce ? 1 : 0;
- oct->intrmod.tx_enable = intr_coal->use_adaptive_tx_coalesce ? 1 : 0;
+ intrmod.rx_enable = intr_coal->use_adaptive_rx_coalesce ? 1 : 0;
+ intrmod.tx_enable = intr_coal->use_adaptive_tx_coalesce ? 1 : 0;
+ intrmod.rx_frames = CFG_GET_OQ_INTR_PKT(octeon_get_conf(oct));
+ intrmod.rx_usecs = CFG_GET_OQ_INTR_TIME(octeon_get_conf(oct));
+ intrmod.tx_frames = CFG_GET_IQ_INTR_PKT(octeon_get_conf(oct));
- ret = oct_cfg_adaptive_intr(lio, intr_coal);
+ ret = oct_cfg_adaptive_intr(lio, &intrmod, intr_coal);
if (!intr_coal->use_adaptive_rx_coalesce) {
- ret = oct_cfg_rx_intrtime(lio, intr_coal);
+ ret = oct_cfg_rx_intrtime(lio, &intrmod, intr_coal);
if (ret)
goto ret_intrmod;
- ret = oct_cfg_rx_intrcnt(lio, intr_coal);
+ ret = oct_cfg_rx_intrcnt(lio, &intrmod, intr_coal);
if (ret)
goto ret_intrmod;
+ } else {
+ oct->rx_coalesce_usecs =
+ CFG_GET_OQ_INTR_TIME(octeon_get_conf(oct));
+ oct->rx_max_coalesced_frames =
+ CFG_GET_OQ_INTR_PKT(octeon_get_conf(oct));
}
+
if (!intr_coal->use_adaptive_tx_coalesce) {
- ret = oct_cfg_tx_intrcnt(lio, intr_coal);
+ ret = oct_cfg_tx_intrcnt(lio, &intrmod, intr_coal);
if (ret)
goto ret_intrmod;
+ } else {
+ oct->tx_max_coalesced_frames =
+ CFG_GET_IQ_INTR_PKT(octeon_get_conf(oct));
}
return 0;
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index be9c0e3..927617c 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -16,6 +16,7 @@
* NONINFRINGEMENT. See the GNU General Public License for more details.
***********************************************************************/
#include <linux/module.h>
+#include <linux/interrupt.h>
#include <linux/pci.h>
#include <linux/firmware.h>
#include <net/vxlan.h>
@@ -60,12 +61,6 @@ MODULE_PARM_DESC(fw_type, "Type of firmware to be loaded. Default \"nic\"");
static int ptp_enable = 1;
-/* Bit mask values for lio->ifstate */
-#define LIO_IFSTATE_DROQ_OPS 0x01
-#define LIO_IFSTATE_REGISTERED 0x02
-#define LIO_IFSTATE_RUNNING 0x04
-#define LIO_IFSTATE_RX_TIMESTAMP_ENABLED 0x08
-
/* Polling interval for determining when NIC application is alive */
#define LIQUIDIO_STARTER_POLL_INTERVAL_MS 100
@@ -152,7 +147,7 @@ struct octnic_gather {
*/
struct octeon_sg_entry *sg;
- u64 sg_dma_ptr;
+ dma_addr_t sg_dma_ptr;
};
struct handshake {
@@ -178,6 +173,8 @@ static int liquidio_stop(struct net_device *netdev);
static void liquidio_remove(struct pci_dev *pdev);
static int liquidio_probe(struct pci_dev *pdev,
const struct pci_device_id *ent);
+static int liquidio_set_vf_link_state(struct net_device *netdev, int vfidx,
+ int linkstate);
static struct handshake handshake[MAX_OCTEON_DEVICES];
static struct completion first_stage;
@@ -531,36 +528,6 @@ static void liquidio_deinit_pci(void)
}
/**
- * \brief check interface state
- * @param lio per-network private data
- * @param state_flag flag state to check
- */
-static inline int ifstate_check(struct lio *lio, int state_flag)
-{
- return atomic_read(&lio->ifstate) & state_flag;
-}
-
-/**
- * \brief set interface state
- * @param lio per-network private data
- * @param state_flag flag state to set
- */
-static inline void ifstate_set(struct lio *lio, int state_flag)
-{
- atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) | state_flag));
-}
-
-/**
- * \brief clear interface state
- * @param lio per-network private data
- * @param state_flag flag state to clear
- */
-static inline void ifstate_reset(struct lio *lio, int state_flag)
-{
- atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) & ~(state_flag)));
-}
-
-/**
* \brief Stop Tx queues
* @param netdev network device
*/
@@ -734,6 +701,9 @@ static void delete_glists(struct lio *lio)
struct octnic_gather *g;
int i;
+ kfree(lio->glist_lock);
+ lio->glist_lock = NULL;
+
if (!lio->glist)
return;
@@ -741,23 +711,27 @@ static void delete_glists(struct lio *lio)
do {
g = (struct octnic_gather *)
list_delete_head(&lio->glist[i]);
- if (g) {
- if (g->sg) {
- dma_unmap_single(&lio->oct_dev->
- pci_dev->dev,
- g->sg_dma_ptr,
- g->sg_size,
- DMA_TO_DEVICE);
- kfree((void *)((unsigned long)g->sg -
- g->adjust));
- }
+ if (g)
kfree(g);
- }
} while (g);
+
+ if (lio->glists_virt_base && lio->glists_virt_base[i] &&
+ lio->glists_dma_base && lio->glists_dma_base[i]) {
+ lio_dma_free(lio->oct_dev,
+ lio->glist_entry_size * lio->tx_qsize,
+ lio->glists_virt_base[i],
+ lio->glists_dma_base[i]);
+ }
}
- kfree((void *)lio->glist);
- kfree((void *)lio->glist_lock);
+ kfree(lio->glists_virt_base);
+ lio->glists_virt_base = NULL;
+
+ kfree(lio->glists_dma_base);
+ lio->glists_dma_base = NULL;
+
+ kfree(lio->glist);
+ lio->glist = NULL;
}
/**
@@ -772,22 +746,49 @@ static int setup_glists(struct octeon_device *oct, struct lio *lio, int num_iqs)
lio->glist_lock = kcalloc(num_iqs, sizeof(*lio->glist_lock),
GFP_KERNEL);
if (!lio->glist_lock)
- return 1;
+ return -ENOMEM;
lio->glist = kcalloc(num_iqs, sizeof(*lio->glist),
GFP_KERNEL);
if (!lio->glist) {
- kfree((void *)lio->glist_lock);
- return 1;
+ kfree(lio->glist_lock);
+ lio->glist_lock = NULL;
+ return -ENOMEM;
+ }
+
+ lio->glist_entry_size =
+ ROUNDUP8((ROUNDUP4(OCTNIC_MAX_SG) >> 2) * OCT_SG_ENTRY_SIZE);
+
+ /* allocate memory to store virtual and dma base address of
+ * per glist consistent memory
+ */
+ lio->glists_virt_base = kcalloc(num_iqs, sizeof(*lio->glists_virt_base),
+ GFP_KERNEL);
+ lio->glists_dma_base = kcalloc(num_iqs, sizeof(*lio->glists_dma_base),
+ GFP_KERNEL);
+
+ if (!lio->glists_virt_base || !lio->glists_dma_base) {
+ delete_glists(lio);
+ return -ENOMEM;
}
for (i = 0; i < num_iqs; i++) {
- int numa_node = cpu_to_node(i % num_online_cpus());
+ int numa_node = dev_to_node(&oct->pci_dev->dev);
spin_lock_init(&lio->glist_lock[i]);
INIT_LIST_HEAD(&lio->glist[i]);
+ lio->glists_virt_base[i] =
+ lio_dma_alloc(oct,
+ lio->glist_entry_size * lio->tx_qsize,
+ &lio->glists_dma_base[i]);
+
+ if (!lio->glists_virt_base[i]) {
+ delete_glists(lio);
+ return -ENOMEM;
+ }
+
for (j = 0; j < lio->tx_qsize; j++) {
g = kzalloc_node(sizeof(*g), GFP_KERNEL,
numa_node);
@@ -796,43 +797,18 @@ static int setup_glists(struct octeon_device *oct, struct lio *lio, int num_iqs)
if (!g)
break;
- g->sg_size = ((ROUNDUP4(OCTNIC_MAX_SG) >> 2) *
- OCT_SG_ENTRY_SIZE);
+ g->sg = lio->glists_virt_base[i] +
+ (j * lio->glist_entry_size);
- g->sg = kmalloc_node(g->sg_size + 8,
- GFP_KERNEL, numa_node);
- if (!g->sg)
- g->sg = kmalloc(g->sg_size + 8, GFP_KERNEL);
- if (!g->sg) {
- kfree(g);
- break;
- }
-
- /* The gather component should be aligned on 64-bit
- * boundary
- */
- if (((unsigned long)g->sg) & 7) {
- g->adjust = 8 - (((unsigned long)g->sg) & 7);
- g->sg = (struct octeon_sg_entry *)
- ((unsigned long)g->sg + g->adjust);
- }
- g->sg_dma_ptr = dma_map_single(&oct->pci_dev->dev,
- g->sg, g->sg_size,
- DMA_TO_DEVICE);
- if (dma_mapping_error(&oct->pci_dev->dev,
- g->sg_dma_ptr)) {
- kfree((void *)((unsigned long)g->sg -
- g->adjust));
- kfree(g);
- break;
- }
+ g->sg_dma_ptr = lio->glists_dma_base[i] +
+ (j * lio->glist_entry_size);
list_add_tail(&g->list, &lio->glist[i]);
}
if (j != lio->tx_qsize) {
delete_glists(lio);
- return 1;
+ return -ENOMEM;
}
}
@@ -959,14 +935,13 @@ static void update_txq_status(struct octeon_device *oct, int iq_num)
INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, iq_num,
tx_restart, 1);
netif_wake_subqueue(netdev, iq->q_index);
- } else {
- if (!octnet_iq_is_full(oct, lio->txq)) {
- INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev,
- lio->txq,
- tx_restart, 1);
- wake_q(netdev, lio->txq);
- }
}
+ } else if (netif_queue_stopped(netdev) &&
+ lio->linfo.link.s.link_up &&
+ (!octnet_iq_is_full(oct, lio->txq))) {
+ INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev,
+ lio->txq, tx_restart, 1);
+ netif_wake_queue(netdev);
}
}
@@ -1076,16 +1051,35 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
int i;
int num_ioq_vectors;
int num_alloc_ioq_vectors;
+ char *queue_irq_names = NULL;
+ char *aux_irq_name = NULL;
if (OCTEON_CN23XX_PF(oct) && oct->msix_on) {
oct->num_msix_irqs = oct->sriov_info.num_pf_rings;
/* one non ioq interrupt for handling sli_mac_pf_int_sum */
oct->num_msix_irqs += 1;
+ /* allocate storage for the names assigned to each irq */
+ oct->irq_name_storage =
+ kcalloc((MAX_IOQ_INTERRUPTS_PER_PF + 1), INTRNAMSIZ,
+ GFP_KERNEL);
+ if (!oct->irq_name_storage) {
+ dev_err(&oct->pci_dev->dev, "Irq name storage alloc failed...\n");
+ return -ENOMEM;
+ }
+
+ queue_irq_names = oct->irq_name_storage;
+ aux_irq_name = &queue_irq_names
+ [IRQ_NAME_OFF(MAX_IOQ_INTERRUPTS_PER_PF)];
+
oct->msix_entries = kcalloc(
oct->num_msix_irqs, sizeof(struct msix_entry), GFP_KERNEL);
- if (!oct->msix_entries)
- return 1;
+ if (!oct->msix_entries) {
+ dev_err(&oct->pci_dev->dev, "Memory Alloc failed...\n");
+ kfree(oct->irq_name_storage);
+ oct->irq_name_storage = NULL;
+ return -ENOMEM;
+ }
msix_entries = (struct msix_entry *)oct->msix_entries;
/*Assumption is that pf msix vectors start from pf srn to pf to
@@ -1103,7 +1097,9 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
dev_err(&oct->pci_dev->dev, "unable to Allocate MSI-X interrupts\n");
kfree(oct->msix_entries);
oct->msix_entries = NULL;
- return 1;
+ kfree(oct->irq_name_storage);
+ oct->irq_name_storage = NULL;
+ return num_alloc_ioq_vectors;
}
dev_dbg(&oct->pci_dev->dev, "OCTEON: Enough MSI-X interrupts are allocated...\n");
@@ -1111,9 +1107,12 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
/** For PF, there is one non-ioq interrupt handler */
num_ioq_vectors -= 1;
+
+ snprintf(aux_irq_name, INTRNAMSIZ,
+ "LiquidIO%u-pf%u-aux", oct->octeon_id, oct->pf_num);
irqret = request_irq(msix_entries[num_ioq_vectors].vector,
- liquidio_legacy_intr_handler, 0, "octeon",
- oct);
+ liquidio_legacy_intr_handler, 0,
+ aux_irq_name, oct);
if (irqret) {
dev_err(&oct->pci_dev->dev,
"OCTEON: Request_irq failed for MSIX interrupt Error: %d\n",
@@ -1121,13 +1120,20 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
pci_disable_msix(oct->pci_dev);
kfree(oct->msix_entries);
oct->msix_entries = NULL;
- return 1;
+ kfree(oct->irq_name_storage);
+ oct->irq_name_storage = NULL;
+ return irqret;
}
for (i = 0; i < num_ioq_vectors; i++) {
+ snprintf(&queue_irq_names[IRQ_NAME_OFF(i)], INTRNAMSIZ,
+ "LiquidIO%u-pf%u-rxtx-%u",
+ oct->octeon_id, oct->pf_num, i);
+
irqret = request_irq(msix_entries[i].vector,
liquidio_msix_intr_handler, 0,
- "octeon", &oct->ioq_vector[i]);
+ &queue_irq_names[IRQ_NAME_OFF(i)],
+ &oct->ioq_vector[i]);
if (irqret) {
dev_err(&oct->pci_dev->dev,
"OCTEON: Request_irq failed for MSIX interrupt Error: %d\n",
@@ -1147,7 +1153,9 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
pci_disable_msix(oct->pci_dev);
kfree(oct->msix_entries);
oct->msix_entries = NULL;
- return 1;
+ kfree(oct->irq_name_storage);
+ oct->irq_name_storage = NULL;
+ return irqret;
}
oct->ioq_vector[i].vector = msix_entries[i].vector;
/* assign the cpu mask for this msix interrupt vector */
@@ -1165,111 +1173,150 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
else
oct->flags |= LIO_FLAG_MSI_ENABLED;
+ /* allocate storage for the names assigned to the irq */
+ oct->irq_name_storage = kcalloc(1, INTRNAMSIZ, GFP_KERNEL);
+ if (!oct->irq_name_storage)
+ return -ENOMEM;
+
+ queue_irq_names = oct->irq_name_storage;
+
+ snprintf(&queue_irq_names[IRQ_NAME_OFF(0)], INTRNAMSIZ,
+ "LiquidIO%u-pf%u-rxtx-%u",
+ oct->octeon_id, oct->pf_num, 0);
+
irqret = request_irq(oct->pci_dev->irq,
- liquidio_legacy_intr_handler, IRQF_SHARED,
- "octeon", oct);
+ liquidio_legacy_intr_handler,
+ IRQF_SHARED,
+ &queue_irq_names[IRQ_NAME_OFF(0)], oct);
if (irqret) {
if (oct->flags & LIO_FLAG_MSI_ENABLED)
pci_disable_msi(oct->pci_dev);
dev_err(&oct->pci_dev->dev, "Request IRQ failed with code: %d\n",
irqret);
- return 1;
+ kfree(oct->irq_name_storage);
+ oct->irq_name_storage = NULL;
+ return irqret;
}
}
return 0;
}
+static struct octeon_device *get_other_octeon_device(struct octeon_device *oct)
+{
+ struct octeon_device *other_oct;
+
+ other_oct = lio_get_device(oct->octeon_id + 1);
+
+ if (other_oct && other_oct->pci_dev) {
+ int oct_busnum, other_oct_busnum;
+
+ oct_busnum = oct->pci_dev->bus->number;
+ other_oct_busnum = other_oct->pci_dev->bus->number;
+
+ if (oct_busnum == other_oct_busnum) {
+ int oct_slot, other_oct_slot;
+
+ oct_slot = PCI_SLOT(oct->pci_dev->devfn);
+ other_oct_slot = PCI_SLOT(other_oct->pci_dev->devfn);
+
+ if (oct_slot == other_oct_slot)
+ return other_oct;
+ }
+ }
+
+ return NULL;
+}
+
+static void disable_all_vf_links(struct octeon_device *oct)
+{
+ struct net_device *netdev;
+ int max_vfs, vf, i;
+
+ if (!oct)
+ return;
+
+ max_vfs = oct->sriov_info.max_vfs;
+
+ for (i = 0; i < oct->ifcount; i++) {
+ netdev = oct->props[i].netdev;
+ if (!netdev)
+ continue;
+
+ for (vf = 0; vf < max_vfs; vf++)
+ liquidio_set_vf_link_state(netdev, vf,
+ IFLA_VF_LINK_STATE_DISABLE);
+ }
+}
+
static int liquidio_watchdog(void *param)
{
- u64 wdog;
- u16 mask_of_stuck_cores = 0;
- u16 mask_of_crashed_cores = 0;
- int core_num;
- u8 core_is_stuck[LIO_MAX_CORES];
- u8 core_crashed[LIO_MAX_CORES];
+ bool err_msg_was_printed[LIO_MAX_CORES];
+ u16 mask_of_crashed_or_stuck_cores = 0;
+ bool all_vf_links_are_disabled = false;
struct octeon_device *oct = param;
+ struct octeon_device *other_oct;
+#ifdef CONFIG_MODULE_UNLOAD
+ long refcount, vfs_referencing_pf;
+ u64 vfs_mask1, vfs_mask2;
+#endif
+ int core;
- memset(core_is_stuck, 0, sizeof(core_is_stuck));
- memset(core_crashed, 0, sizeof(core_crashed));
+ memset(err_msg_was_printed, 0, sizeof(err_msg_was_printed));
while (!kthread_should_stop()) {
- mask_of_crashed_cores =
+ /* sleep for a couple of seconds so that we don't hog the CPU */
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout(msecs_to_jiffies(2000));
+
+ mask_of_crashed_or_stuck_cores =
(u16)octeon_read_csr64(oct, CN23XX_SLI_SCRATCH2);
- for (core_num = 0; core_num < LIO_MAX_CORES; core_num++) {
- if (!core_is_stuck[core_num]) {
- wdog = lio_pci_readq(oct, CIU3_WDOG(core_num));
+ if (!mask_of_crashed_or_stuck_cores)
+ continue;
- /* look at watchdog state field */
- wdog &= CIU3_WDOG_MASK;
- if (wdog) {
- /* this watchdog timer has expired */
- core_is_stuck[core_num] =
- LIO_MONITOR_WDOG_EXPIRE;
- mask_of_stuck_cores |= (1 << core_num);
- }
- }
+ WRITE_ONCE(oct->cores_crashed, true);
+ other_oct = get_other_octeon_device(oct);
+ if (other_oct)
+ WRITE_ONCE(other_oct->cores_crashed, true);
- if (!core_crashed[core_num])
- core_crashed[core_num] =
- (mask_of_crashed_cores >> core_num) & 1;
- }
+ for (core = 0; core < LIO_MAX_CORES; core++) {
+ bool core_crashed_or_got_stuck;
- if (mask_of_stuck_cores) {
- for (core_num = 0; core_num < LIO_MAX_CORES;
- core_num++) {
- if (core_is_stuck[core_num] == 1) {
- dev_err(&oct->pci_dev->dev,
- "ERROR: Octeon core %d is stuck!\n",
- core_num);
- /* 2 means we have printk'd an error
- * so no need to repeat the same printk
- */
- core_is_stuck[core_num] =
- LIO_MONITOR_CORE_STUCK_MSGD;
- }
+ core_crashed_or_got_stuck =
+ (mask_of_crashed_or_stuck_cores
+ >> core) & 1;
+
+ if (core_crashed_or_got_stuck &&
+ !err_msg_was_printed[core]) {
+ dev_err(&oct->pci_dev->dev,
+ "ERROR: Octeon core %d crashed or got stuck! See oct-fwdump for details.\n",
+ core);
+ err_msg_was_printed[core] = true;
}
}
- if (mask_of_crashed_cores) {
- for (core_num = 0; core_num < LIO_MAX_CORES;
- core_num++) {
- if (core_crashed[core_num] == 1) {
- dev_err(&oct->pci_dev->dev,
- "ERROR: Octeon core %d crashed! See oct-fwdump for details.\n",
- core_num);
- /* 2 means we have printk'd an error
- * so no need to repeat the same printk
- */
- core_crashed[core_num] =
- LIO_MONITOR_CORE_STUCK_MSGD;
- }
- }
- }
+ if (all_vf_links_are_disabled)
+ continue;
+
+ disable_all_vf_links(oct);
+ disable_all_vf_links(other_oct);
+ all_vf_links_are_disabled = true;
+
#ifdef CONFIG_MODULE_UNLOAD
- if (mask_of_stuck_cores || mask_of_crashed_cores) {
- /* make module refcount=0 so that rmmod will work */
- long refcount;
+ vfs_mask1 = READ_ONCE(oct->sriov_info.vf_drv_loaded_mask);
+ vfs_mask2 = READ_ONCE(other_oct->sriov_info.vf_drv_loaded_mask);
- refcount = module_refcount(THIS_MODULE);
+ vfs_referencing_pf = hweight64(vfs_mask1);
+ vfs_referencing_pf += hweight64(vfs_mask2);
- while (refcount > 0) {
+ refcount = module_refcount(THIS_MODULE);
+ if (refcount >= vfs_referencing_pf) {
+ while (vfs_referencing_pf) {
module_put(THIS_MODULE);
- refcount = module_refcount(THIS_MODULE);
- }
-
- /* compensate for and withstand an unlikely (but still
- * possible) race condition
- */
- while (refcount < 0) {
- try_module_get(THIS_MODULE);
- refcount = module_refcount(THIS_MODULE);
+ vfs_referencing_pf--;
}
}
#endif
- /* sleep for two seconds */
- set_current_state(TASK_INTERRUPTIBLE);
- schedule_timeout(2 * HZ);
}
return 0;
@@ -1361,6 +1408,12 @@ liquidio_probe(struct pci_dev *pdev,
return 0;
}
+static bool fw_type_is_none(void)
+{
+ return strncmp(fw_type, LIO_FW_NAME_TYPE_NONE,
+ sizeof(LIO_FW_NAME_TYPE_NONE)) == 0;
+}
+
/**
*\brief Destroy resources associated with octeon device
* @param pdev PCI device structure
@@ -1441,6 +1494,9 @@ static void octeon_destroy_resources(struct octeon_device *oct)
pci_disable_msi(oct->pci_dev);
}
+ kfree(oct->irq_name_storage);
+ oct->irq_name_storage = NULL;
+
/* fallthrough */
case OCT_DEV_MSIX_ALLOC_VECTOR_DONE:
if (OCTEON_CN23XX_PF(oct))
@@ -1500,9 +1556,12 @@ static void octeon_destroy_resources(struct octeon_device *oct)
/* fallthrough */
case OCT_DEV_PCI_MAP_DONE:
- /* Soft reset the octeon device before exiting */
- if ((!OCTEON_CN23XX_PF(oct)) || !oct->octeon_id)
- oct->fn_list.soft_reset(oct);
+ if (!fw_type_is_none()) {
+ /* Soft reset the octeon device before exiting */
+ if (!OCTEON_CN23XX_PF(oct) ||
+ (OCTEON_CN23XX_PF(oct) && !oct->octeon_id))
+ oct->fn_list.soft_reset(oct);
+ }
octeon_unmap_pci_barx(oct, 0);
octeon_unmap_pci_barx(oct, 1);
@@ -1635,6 +1694,15 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx)
if (atomic_read(&lio->ifstate) & LIO_IFSTATE_RUNNING)
liquidio_stop(netdev);
+ if (fw_type_is_none()) {
+ struct octnic_ctrl_pkt nctrl;
+
+ memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+ nctrl.ncmd.s.cmd = OCTNET_CMD_RESET_PF;
+ nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
+ octnet_send_nic_ctrl_pkt(oct, &nctrl);
+ }
+
if (oct->props[lio->ifidx].napi_enabled == 1) {
list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list)
napi_disable(napi);
@@ -1650,6 +1718,8 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx)
cleanup_link_status_change_wq(netdev);
+ cleanup_rx_oom_poll_fn(netdev);
+
delete_glists(lio);
free_netdev(netdev);
@@ -1885,9 +1955,6 @@ static void free_netsgbuf(void *buf)
i++;
}
- dma_sync_single_for_cpu(&lio->oct_dev->pci_dev->dev,
- g->sg_dma_ptr, g->sg_size, DMA_TO_DEVICE);
-
iq = skb_iq(lio, skb);
spin_lock(&lio->glist_lock[iq]);
list_add_tail(&g->list, &lio->glist[iq]);
@@ -1933,9 +2000,6 @@ static void free_netsgbuf_with_resp(void *buf)
i++;
}
- dma_sync_single_for_cpu(&lio->oct_dev->pci_dev->dev,
- g->sg_dma_ptr, g->sg_size, DMA_TO_DEVICE);
-
iq = skb_iq(lio, skb);
spin_lock(&lio->glist_lock[iq]);
@@ -2124,8 +2188,7 @@ static int load_firmware(struct octeon_device *oct)
char fw_name[LIO_MAX_FW_FILENAME_LEN];
char *tmp_fw_type;
- if (strncmp(fw_type, LIO_FW_NAME_TYPE_NONE,
- sizeof(LIO_FW_NAME_TYPE_NONE)) == 0) {
+ if (fw_type_is_none()) {
dev_info(&oct->pci_dev->dev, "Skipping firmware load\n");
return ret;
}
@@ -2209,8 +2272,8 @@ static void if_cfg_callback(struct octeon_device *oct,
oct = lio_get_device(ctx->octeon_id);
if (resp->status)
- dev_err(&oct->pci_dev->dev, "nic if cfg instruction failed. Status: %llx\n",
- CVM_CAST64(resp->status));
+ dev_err(&oct->pci_dev->dev, "nic if cfg instruction failed. Status: 0x%llx (0x%08x)\n",
+ CVM_CAST64(resp->status), status);
WRITE_ONCE(ctx->cond, 1);
snprintf(oct->fw_info.liquidio_firmware_version, 32, "%s",
@@ -2435,8 +2498,11 @@ static int liquidio_napi_poll(struct napi_struct *napi, int budget)
/* Flush the instruction queue */
iq = oct->instr_queue[iq_no];
if (iq) {
- /* Process iq buffers with in the budget limits */
- tx_done = octeon_flush_iq(oct, iq, budget);
+ if (atomic_read(&iq->instr_pending))
+ /* Process iq buffers with in the budget limits */
+ tx_done = octeon_flush_iq(oct, iq, budget);
+ else
+ tx_done = 1;
/* Update iq read-index rather than waiting for next interrupt.
* Return back if tx_done is false.
*/
@@ -2553,6 +2619,15 @@ static inline int setup_io_queues(struct octeon_device *octeon_dev,
__func__);
return 1;
}
+
+ if (octeon_dev->ioq_vector) {
+ struct octeon_ioq_vector *ioq_vector;
+
+ ioq_vector = &octeon_dev->ioq_vector[q];
+ netif_set_xps_queue(netdev,
+ &ioq_vector->affinity_mask,
+ ioq_vector->iq_index);
+ }
}
return 0;
@@ -3273,8 +3348,6 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
i++;
}
- dma_sync_single_for_device(&oct->pci_dev->dev, g->sg_dma_ptr,
- g->sg_size, DMA_TO_DEVICE);
dptr = g->sg_dma_ptr;
if (OCTEON_CN23XX_PF(oct))
@@ -3426,6 +3499,8 @@ static int liquidio_set_rxcsum_command(struct net_device *netdev, int command,
struct octnic_ctrl_pkt nctrl;
int ret = 0;
+ memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+
nctrl.ncmd.u64 = 0;
nctrl.ncmd.s.cmd = command;
nctrl.ncmd.s.param1 = rx_cmd;
@@ -3459,6 +3534,8 @@ static int liquidio_vxlan_port_command(struct net_device *netdev, int command,
struct octnic_ctrl_pkt nctrl;
int ret = 0;
+ memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+
nctrl.ncmd.u64 = 0;
nctrl.ncmd.s.cmd = command;
nctrl.ncmd.s.more = vxlan_cmd_bit;
@@ -3596,7 +3673,8 @@ static int __liquidio_set_vf_mac(struct net_device *netdev, int vfidx,
nctrl.ncmd.s.param2 = (is_admin_assigned ? 1 : 0);
nctrl.ncmd.s.more = 1;
nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
- nctrl.cb_fn = 0;
+ nctrl.netpndev = (u64)netdev;
+ nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
nctrl.wait_time = LIO_CMD_WAIT_TM;
nctrl.udd[0] = 0;
@@ -4122,6 +4200,9 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
if (setup_link_status_change_wq(netdev))
goto setup_nic_dev_fail;
+ if (setup_rx_oom_poll_fn(netdev))
+ goto setup_nic_dev_fail;
+
/* Register the network device with the OS */
if (register_netdev(netdev)) {
dev_err(&octeon_dev->pci_dev->dev, "Device registration failed\n");
@@ -4271,7 +4352,6 @@ static int liquidio_enable_sriov(struct pci_dev *dev, int num_vfs)
*/
static int liquidio_init_nic_module(struct octeon_device *oct)
{
- struct oct_intrmod_cfg *intrmod_cfg;
int i, retval = 0;
int num_nic_ports = CFG_GET_NUM_NIC_PORTS(octeon_get_conf(oct));
@@ -4296,22 +4376,6 @@ static int liquidio_init_nic_module(struct octeon_device *oct)
liquidio_ptp_init(oct);
- /* Initialize interrupt moderation params */
- intrmod_cfg = &((struct octeon_device *)oct)->intrmod;
- intrmod_cfg->rx_enable = 1;
- intrmod_cfg->check_intrvl = LIO_INTRMOD_CHECK_INTERVAL;
- intrmod_cfg->maxpkt_ratethr = LIO_INTRMOD_MAXPKT_RATETHR;
- intrmod_cfg->minpkt_ratethr = LIO_INTRMOD_MINPKT_RATETHR;
- intrmod_cfg->rx_maxcnt_trigger = LIO_INTRMOD_RXMAXCNT_TRIGGER;
- intrmod_cfg->rx_maxtmr_trigger = LIO_INTRMOD_RXMAXTMR_TRIGGER;
- intrmod_cfg->rx_mintmr_trigger = LIO_INTRMOD_RXMINTMR_TRIGGER;
- intrmod_cfg->rx_mincnt_trigger = LIO_INTRMOD_RXMINCNT_TRIGGER;
- intrmod_cfg->tx_enable = 1;
- intrmod_cfg->tx_maxcnt_trigger = LIO_INTRMOD_TXMAXCNT_TRIGGER;
- intrmod_cfg->tx_mincnt_trigger = LIO_INTRMOD_TXMINCNT_TRIGGER;
- intrmod_cfg->rx_frames = CFG_GET_OQ_INTR_PKT(octeon_get_conf(oct));
- intrmod_cfg->rx_usecs = CFG_GET_OQ_INTR_TIME(octeon_get_conf(oct));
- intrmod_cfg->tx_frames = CFG_GET_IQ_INTR_PKT(octeon_get_conf(oct));
dev_dbg(&oct->pci_dev->dev, "Network interfaces ready\n");
return retval;
@@ -4373,6 +4437,7 @@ octeon_recv_vf_drv_notice(struct octeon_recv_info *recv_info, void *buf)
struct octeon_device *oct = (struct octeon_device *)buf;
struct octeon_recv_pkt *recv_pkt = recv_info->recv_pkt;
int i, notice, vf_idx;
+ bool cores_crashed;
u64 *data, vf_num;
notice = recv_pkt->rh.r.ossp;
@@ -4383,19 +4448,23 @@ octeon_recv_vf_drv_notice(struct octeon_recv_info *recv_info, void *buf)
octeon_swap_8B_data(&vf_num, 1);
vf_idx = (int)vf_num - 1;
+ cores_crashed = READ_ONCE(oct->cores_crashed);
+
if (notice == VF_DRV_LOADED) {
if (!(oct->sriov_info.vf_drv_loaded_mask & BIT_ULL(vf_idx))) {
oct->sriov_info.vf_drv_loaded_mask |= BIT_ULL(vf_idx);
dev_info(&oct->pci_dev->dev,
"driver for VF%d was loaded\n", vf_idx);
- try_module_get(THIS_MODULE);
+ if (!cores_crashed)
+ try_module_get(THIS_MODULE);
}
} else if (notice == VF_DRV_REMOVED) {
if (oct->sriov_info.vf_drv_loaded_mask & BIT_ULL(vf_idx)) {
oct->sriov_info.vf_drv_loaded_mask &= ~BIT_ULL(vf_idx);
dev_info(&oct->pci_dev->dev,
"driver for VF%d was removed\n", vf_idx);
- module_put(THIS_MODULE);
+ if (!cores_crashed)
+ module_put(THIS_MODULE);
}
} else if (notice == VF_DRV_MACADDR_CHANGED) {
u8 *b = (u8 *)&data[1];
@@ -4447,14 +4516,16 @@ static int octeon_device_init(struct octeon_device *octeon_dev)
if (OCTEON_CN23XX_PF(octeon_dev)) {
if (!cn23xx_fw_loaded(octeon_dev)) {
fw_loaded = 0;
- /* Do a soft reset of the Octeon device. */
- if (octeon_dev->fn_list.soft_reset(octeon_dev))
- return 1;
- /* things might have changed */
- if (!cn23xx_fw_loaded(octeon_dev))
- fw_loaded = 0;
- else
- fw_loaded = 1;
+ if (!fw_type_is_none()) {
+ /* Do a soft reset of the Octeon device. */
+ if (octeon_dev->fn_list.soft_reset(octeon_dev))
+ return 1;
+ /* things might have changed */
+ if (!cn23xx_fw_loaded(octeon_dev))
+ fw_loaded = 0;
+ else
+ fw_loaded = 1;
+ }
} else {
fw_loaded = 1;
}
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
index 9d5e035..34c7782 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
@@ -16,6 +16,7 @@
* NONINFRINGEMENT. See the GNU General Public License for more details.
***********************************************************************/
#include <linux/module.h>
+#include <linux/interrupt.h>
#include <linux/pci.h>
#include <net/vxlan.h>
#include "liquidio_common.h"
@@ -39,12 +40,6 @@ MODULE_PARM_DESC(debug, "NETIF_MSG debug bits");
#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK)
-/* Bit mask values for lio->ifstate */
-#define LIO_IFSTATE_DROQ_OPS 0x01
-#define LIO_IFSTATE_REGISTERED 0x02
-#define LIO_IFSTATE_RUNNING 0x04
-#define LIO_IFSTATE_RX_TIMESTAMP_ENABLED 0x08
-
struct liquidio_if_cfg_context {
int octeon_id;
@@ -108,6 +103,8 @@ struct octnic_gather {
* received from the IP layer.
*/
struct octeon_sg_entry *sg;
+
+ dma_addr_t sg_dma_ptr;
};
struct octeon_device_priv {
@@ -334,36 +331,6 @@ static struct pci_driver liquidio_vf_pci_driver = {
};
/**
- * \brief check interface state
- * @param lio per-network private data
- * @param state_flag flag state to check
- */
-static int ifstate_check(struct lio *lio, int state_flag)
-{
- return atomic_read(&lio->ifstate) & state_flag;
-}
-
-/**
- * \brief set interface state
- * @param lio per-network private data
- * @param state_flag flag state to set
- */
-static void ifstate_set(struct lio *lio, int state_flag)
-{
- atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) | state_flag));
-}
-
-/**
- * \brief clear interface state
- * @param lio per-network private data
- * @param state_flag flag state to clear
- */
-static void ifstate_reset(struct lio *lio, int state_flag)
-{
- atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) & ~(state_flag)));
-}
-
-/**
* \brief Stop Tx queues
* @param netdev network device
*/
@@ -490,6 +457,9 @@ static void delete_glists(struct lio *lio)
struct octnic_gather *g;
int i;
+ kfree(lio->glist_lock);
+ lio->glist_lock = NULL;
+
if (!lio->glist)
return;
@@ -497,17 +467,27 @@ static void delete_glists(struct lio *lio)
do {
g = (struct octnic_gather *)
list_delete_head(&lio->glist[i]);
- if (g) {
- if (g->sg)
- kfree((void *)((unsigned long)g->sg -
- g->adjust));
+ if (g)
kfree(g);
- }
} while (g);
+
+ if (lio->glists_virt_base && lio->glists_virt_base[i] &&
+ lio->glists_dma_base && lio->glists_dma_base[i]) {
+ lio_dma_free(lio->oct_dev,
+ lio->glist_entry_size * lio->tx_qsize,
+ lio->glists_virt_base[i],
+ lio->glists_dma_base[i]);
+ }
}
+ kfree(lio->glists_virt_base);
+ lio->glists_virt_base = NULL;
+
+ kfree(lio->glists_dma_base);
+ lio->glists_dma_base = NULL;
+
kfree(lio->glist);
- kfree(lio->glist_lock);
+ lio->glist = NULL;
}
/**
@@ -522,13 +502,30 @@ static int setup_glists(struct lio *lio, int num_iqs)
lio->glist_lock =
kzalloc(sizeof(*lio->glist_lock) * num_iqs, GFP_KERNEL);
if (!lio->glist_lock)
- return 1;
+ return -ENOMEM;
lio->glist =
kzalloc(sizeof(*lio->glist) * num_iqs, GFP_KERNEL);
if (!lio->glist) {
kfree(lio->glist_lock);
- return 1;
+ lio->glist_lock = NULL;
+ return -ENOMEM;
+ }
+
+ lio->glist_entry_size =
+ ROUNDUP8((ROUNDUP4(OCTNIC_MAX_SG) >> 2) * OCT_SG_ENTRY_SIZE);
+
+ /* allocate memory to store virtual and dma base address of
+ * per glist consistent memory
+ */
+ lio->glists_virt_base = kcalloc(num_iqs, sizeof(*lio->glists_virt_base),
+ GFP_KERNEL);
+ lio->glists_dma_base = kcalloc(num_iqs, sizeof(*lio->glists_dma_base),
+ GFP_KERNEL);
+
+ if (!lio->glists_virt_base || !lio->glists_dma_base) {
+ delete_glists(lio);
+ return -ENOMEM;
}
for (i = 0; i < num_iqs; i++) {
@@ -536,34 +533,33 @@ static int setup_glists(struct lio *lio, int num_iqs)
INIT_LIST_HEAD(&lio->glist[i]);
+ lio->glists_virt_base[i] =
+ lio_dma_alloc(lio->oct_dev,
+ lio->glist_entry_size * lio->tx_qsize,
+ &lio->glists_dma_base[i]);
+
+ if (!lio->glists_virt_base[i]) {
+ delete_glists(lio);
+ return -ENOMEM;
+ }
+
for (j = 0; j < lio->tx_qsize; j++) {
g = kzalloc(sizeof(*g), GFP_KERNEL);
if (!g)
break;
- g->sg_size = ((ROUNDUP4(OCTNIC_MAX_SG) >> 2) *
- OCT_SG_ENTRY_SIZE);
+ g->sg = lio->glists_virt_base[i] +
+ (j * lio->glist_entry_size);
- g->sg = kmalloc(g->sg_size + 8, GFP_KERNEL);
- if (!g->sg) {
- kfree(g);
- break;
- }
+ g->sg_dma_ptr = lio->glists_dma_base[i] +
+ (j * lio->glist_entry_size);
- /* The gather component should be aligned on 64-bit
- * boundary
- */
- if (((unsigned long)g->sg) & 7) {
- g->adjust = 8 - (((unsigned long)g->sg) & 7);
- g->sg = (struct octeon_sg_entry *)
- ((unsigned long)g->sg + g->adjust);
- }
list_add_tail(&g->list, &lio->glist[i]);
}
if (j != lio->tx_qsize) {
delete_glists(lio);
- return 1;
+ return -ENOMEM;
}
}
@@ -692,13 +688,12 @@ static void update_txq_status(struct octeon_device *oct, int iq_num)
netif_wake_subqueue(netdev, iq->q_index);
INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, iq_num,
tx_restart, 1);
- } else {
- if (!octnet_iq_is_full(oct, lio->txq)) {
- INCR_INSTRQUEUE_PKT_COUNT(
- lio->oct_dev, lio->txq, tx_restart, 1);
- wake_q(netdev, lio->txq);
- }
}
+ } else if (netif_queue_stopped(netdev) && lio->linfo.link.s.link_up &&
+ (!octnet_iq_is_full(oct, lio->txq))) {
+ INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev,
+ lio->txq, tx_restart, 1);
+ netif_wake_queue(netdev);
}
}
@@ -750,6 +745,7 @@ liquidio_msix_intr_handler(int irq __attribute__((unused)), void *dev)
static int octeon_setup_interrupt(struct octeon_device *oct)
{
struct msix_entry *msix_entries;
+ char *queue_irq_names = NULL;
int num_alloc_ioq_vectors;
int num_ioq_vectors;
int irqret;
@@ -758,10 +754,25 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
if (oct->msix_on) {
oct->num_msix_irqs = oct->sriov_info.rings_per_vf;
+ /* allocate storage for the names assigned to each irq */
+ oct->irq_name_storage =
+ kcalloc(MAX_IOQ_INTERRUPTS_PER_VF, INTRNAMSIZ,
+ GFP_KERNEL);
+ if (!oct->irq_name_storage) {
+ dev_err(&oct->pci_dev->dev, "Irq name storage alloc failed...\n");
+ return -ENOMEM;
+ }
+
+ queue_irq_names = oct->irq_name_storage;
+
oct->msix_entries = kcalloc(
oct->num_msix_irqs, sizeof(struct msix_entry), GFP_KERNEL);
- if (!oct->msix_entries)
- return 1;
+ if (!oct->msix_entries) {
+ dev_err(&oct->pci_dev->dev, "Memory Alloc failed...\n");
+ kfree(oct->irq_name_storage);
+ oct->irq_name_storage = NULL;
+ return -ENOMEM;
+ }
msix_entries = (struct msix_entry *)oct->msix_entries;
@@ -775,16 +786,23 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
dev_err(&oct->pci_dev->dev, "unable to Allocate MSI-X interrupts\n");
kfree(oct->msix_entries);
oct->msix_entries = NULL;
- return 1;
+ kfree(oct->irq_name_storage);
+ oct->irq_name_storage = NULL;
+ return num_alloc_ioq_vectors;
}
dev_dbg(&oct->pci_dev->dev, "OCTEON: Enough MSI-X interrupts are allocated...\n");
num_ioq_vectors = oct->num_msix_irqs;
for (i = 0; i < num_ioq_vectors; i++) {
+ snprintf(&queue_irq_names[IRQ_NAME_OFF(i)], INTRNAMSIZ,
+ "LiquidIO%u-vf%u-rxtx-%u",
+ oct->octeon_id, oct->vf_num, i);
+
irqret = request_irq(msix_entries[i].vector,
liquidio_msix_intr_handler, 0,
- "octeon", &oct->ioq_vector[i]);
+ &queue_irq_names[IRQ_NAME_OFF(i)],
+ &oct->ioq_vector[i]);
if (irqret) {
dev_err(&oct->pci_dev->dev,
"OCTEON: Request_irq failed for MSIX interrupt Error: %d\n",
@@ -800,7 +818,9 @@ static int octeon_setup_interrupt(struct octeon_device *oct)
pci_disable_msix(oct->pci_dev);
kfree(oct->msix_entries);
oct->msix_entries = NULL;
- return 1;
+ kfree(oct->irq_name_storage);
+ oct->irq_name_storage = NULL;
+ return irqret;
}
oct->ioq_vector[i].vector = msix_entries[i].vector;
/* assign the cpu mask for this msix interrupt vector */
@@ -945,6 +965,8 @@ static void octeon_destroy_resources(struct octeon_device *oct)
pci_disable_msix(oct->pci_dev);
kfree(oct->msix_entries);
oct->msix_entries = NULL;
+ kfree(oct->irq_name_storage);
+ oct->irq_name_storage = NULL;
}
/* Soft reset the octeon device before exiting */
if (oct->pci_dev->reset_fn)
@@ -1133,6 +1155,8 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx)
if (atomic_read(&lio->ifstate) & LIO_IFSTATE_REGISTERED)
unregister_netdev(netdev);
+ cleanup_rx_oom_poll_fn(netdev);
+
cleanup_link_status_change_wq(netdev);
delete_glists(lio);
@@ -1324,10 +1348,6 @@ static void free_netsgbuf(void *buf)
i++;
}
- dma_unmap_single(&lio->oct_dev->pci_dev->dev,
- finfo->dptr, g->sg_size,
- DMA_TO_DEVICE);
-
iq = skb_iq(lio, skb);
spin_lock(&lio->glist_lock[iq]);
@@ -1374,10 +1394,6 @@ static void free_netsgbuf_with_resp(void *buf)
i++;
}
- dma_unmap_single(&lio->oct_dev->pci_dev->dev,
- finfo->dptr, g->sg_size,
- DMA_TO_DEVICE);
-
iq = skb_iq(lio, skb);
spin_lock(&lio->glist_lock[iq]);
@@ -1620,8 +1636,12 @@ static int liquidio_napi_poll(struct napi_struct *napi, int budget)
/* Flush the instruction queue */
iq = oct->instr_queue[iq_no];
if (iq) {
- /* Process iq buffers with in the budget limits */
- tx_done = octeon_flush_iq(oct, iq, budget);
+ if (atomic_read(&iq->instr_pending))
+ /* Process iq buffers with in the budget limits */
+ tx_done = octeon_flush_iq(oct, iq, budget);
+ else
+ tx_done = 1;
+
/* Update iq read-index rather than waiting for next interrupt.
* Return back if tx_done is false.
*/
@@ -2382,23 +2402,7 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
i++;
}
- dptr = dma_map_single(&oct->pci_dev->dev,
- g->sg, g->sg_size,
- DMA_TO_DEVICE);
- if (dma_mapping_error(&oct->pci_dev->dev, dptr)) {
- dev_err(&oct->pci_dev->dev, "%s DMA mapping error 4\n",
- __func__);
- dma_unmap_single(&oct->pci_dev->dev, g->sg[0].ptr[0],
- skb->len - skb->data_len,
- DMA_TO_DEVICE);
- for (j = 1; j <= frags; j++) {
- frag = &skb_shinfo(skb)->frags[j - 1];
- dma_unmap_page(&oct->pci_dev->dev,
- g->sg[j >> 2].ptr[j & 3],
- frag->size, DMA_TO_DEVICE);
- }
- return NETDEV_TX_BUSY;
- }
+ dptr = g->sg_dma_ptr;
ndata.cmd.cmd3.dptr = dptr;
finfo->dptr = dptr;
@@ -2480,6 +2484,8 @@ liquidio_vlan_rx_add_vid(struct net_device *netdev,
struct lio *lio = GET_LIO(netdev);
struct octeon_device *oct = lio->oct_dev;
struct octnic_ctrl_pkt nctrl;
+ struct completion compl;
+ u16 response_code;
int ret = 0;
memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
@@ -2491,14 +2497,25 @@ liquidio_vlan_rx_add_vid(struct net_device *netdev,
nctrl.wait_time = 100;
nctrl.netpndev = (u64)netdev;
nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
+ init_completion(&compl);
+ nctrl.completion = &compl;
+ nctrl.response_code = &response_code;
ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
if (ret < 0) {
dev_err(&oct->pci_dev->dev, "Add VLAN filter failed in core (ret: 0x%x)\n",
ret);
+ return -EIO;
}
- return ret;
+ if (!wait_for_completion_timeout(&compl,
+ msecs_to_jiffies(nctrl.wait_time)))
+ return -EPERM;
+
+ if (READ_ONCE(response_code))
+ return -EPERM;
+
+ return 0;
}
static int
@@ -2543,6 +2560,8 @@ static int liquidio_set_rxcsum_command(struct net_device *netdev, int command,
struct octnic_ctrl_pkt nctrl;
int ret = 0;
+ memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+
nctrl.ncmd.u64 = 0;
nctrl.ncmd.s.cmd = command;
nctrl.ncmd.s.param1 = rx_cmd;
@@ -2575,6 +2594,8 @@ static int liquidio_vxlan_port_command(struct net_device *netdev, int command,
struct octnic_ctrl_pkt nctrl;
int ret = 0;
+ memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+
nctrl.ncmd.u64 = 0;
nctrl.ncmd.s.cmd = command;
nctrl.ncmd.s.more = vxlan_cmd_bit;
@@ -2997,6 +3018,9 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
if (setup_link_status_change_wq(netdev))
goto setup_nic_dev_fail;
+ if (setup_rx_oom_poll_fn(netdev))
+ goto setup_nic_dev_fail;
+
/* Register the network device with the OS */
if (register_netdev(netdev)) {
dev_err(&octeon_dev->pci_dev->dev, "Device registration failed\n");
@@ -3051,7 +3075,6 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
*/
static int liquidio_init_nic_module(struct octeon_device *oct)
{
- struct oct_intrmod_cfg *intrmod_cfg;
int num_nic_ports = 1;
int i, retval = 0;
@@ -3073,22 +3096,6 @@ static int liquidio_init_nic_module(struct octeon_device *oct)
goto octnet_init_failure;
}
- /* Initialize interrupt moderation params */
- intrmod_cfg = &((struct octeon_device *)oct)->intrmod;
- intrmod_cfg->rx_enable = 1;
- intrmod_cfg->check_intrvl = LIO_INTRMOD_CHECK_INTERVAL;
- intrmod_cfg->maxpkt_ratethr = LIO_INTRMOD_MAXPKT_RATETHR;
- intrmod_cfg->minpkt_ratethr = LIO_INTRMOD_MINPKT_RATETHR;
- intrmod_cfg->rx_maxcnt_trigger = LIO_INTRMOD_RXMAXCNT_TRIGGER;
- intrmod_cfg->rx_maxtmr_trigger = LIO_INTRMOD_RXMAXTMR_TRIGGER;
- intrmod_cfg->rx_mintmr_trigger = LIO_INTRMOD_RXMINTMR_TRIGGER;
- intrmod_cfg->rx_mincnt_trigger = LIO_INTRMOD_RXMINCNT_TRIGGER;
- intrmod_cfg->tx_enable = 1;
- intrmod_cfg->tx_maxcnt_trigger = LIO_INTRMOD_TXMAXCNT_TRIGGER;
- intrmod_cfg->tx_mincnt_trigger = LIO_INTRMOD_TXMINCNT_TRIGGER;
- intrmod_cfg->rx_frames = CFG_GET_OQ_INTR_PKT(octeon_get_conf(oct));
- intrmod_cfg->rx_usecs = CFG_GET_OQ_INTR_TIME(octeon_get_conf(oct));
- intrmod_cfg->tx_frames = CFG_GET_IQ_INTR_PKT(octeon_get_conf(oct));
dev_dbg(&oct->pci_dev->dev, "Network interfaces ready\n");
return retval;
diff --git a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
index 294c6f3..8ea2323 100644
--- a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
+++ b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
@@ -27,7 +27,7 @@
#define LIQUIDIO_PACKAGE ""
#define LIQUIDIO_BASE_MAJOR_VERSION 1
-#define LIQUIDIO_BASE_MINOR_VERSION 4
+#define LIQUIDIO_BASE_MINOR_VERSION 5
#define LIQUIDIO_BASE_MICRO_VERSION 1
#define LIQUIDIO_BASE_VERSION __stringify(LIQUIDIO_BASE_MAJOR_VERSION) "." \
__stringify(LIQUIDIO_BASE_MINOR_VERSION)
@@ -83,6 +83,7 @@ enum octeon_tag_type {
#define OPCODE_NIC_INTRMOD_CFG 0x08
#define OPCODE_NIC_IF_CFG 0x09
#define OPCODE_NIC_VF_DRV_NOTICE 0x0A
+#define OPCODE_NIC_INTRMOD_PARAMS 0x0B
#define VF_DRV_LOADED 1
#define VF_DRV_REMOVED -1
#define VF_DRV_MACADDR_CHANGED 2
@@ -100,6 +101,11 @@ enum octeon_tag_type {
#define BYTES_PER_DHLEN_UNIT 8
#define MAX_REG_CNT 2000000U
+#define INTRNAMSIZ 32
+#define IRQ_NAME_OFF(i) ((i) * INTRNAMSIZ)
+#define MAX_IOQ_INTERRUPTS_PER_PF (64 * 2)
+#define MAX_IOQ_INTERRUPTS_PER_VF (8 * 2)
+
static inline u32 incr_index(u32 index, u32 count, u32 max)
{
@@ -181,6 +187,7 @@ static inline void add_sg_size(struct octeon_sg_entry *sg_entry,
#define OCTNET_CMD_Q 0
/* NIC Command types */
+#define OCTNET_CMD_RESET_PF 0x0
#define OCTNET_CMD_CHANGE_MTU 0x1
#define OCTNET_CMD_CHANGE_MACADDR 0x2
#define OCTNET_CMD_CHANGE_DEVFLAGS 0x3
@@ -845,29 +852,6 @@ struct oct_mdio_cmd {
#define OCT_LINK_STATS_SIZE (sizeof(struct oct_link_stats))
-/* intrmod: max. packet rate threshold */
-#define LIO_INTRMOD_MAXPKT_RATETHR 196608
-/* intrmod: min. packet rate threshold */
-#define LIO_INTRMOD_MINPKT_RATETHR 9216
-/* intrmod: max. packets to trigger interrupt */
-#define LIO_INTRMOD_RXMAXCNT_TRIGGER 384
-/* intrmod: min. packets to trigger interrupt */
-#define LIO_INTRMOD_RXMINCNT_TRIGGER 0
-/* intrmod: max. time to trigger interrupt */
-#define LIO_INTRMOD_RXMAXTMR_TRIGGER 128
-/* 66xx:intrmod: min. time to trigger interrupt
- * (value of 1 is optimum for TCP_RR)
- */
-#define LIO_INTRMOD_RXMINTMR_TRIGGER 1
-
-/* intrmod: max. packets to trigger interrupt */
-#define LIO_INTRMOD_TXMAXCNT_TRIGGER 64
-/* intrmod: min. packets to trigger interrupt */
-#define LIO_INTRMOD_TXMINCNT_TRIGGER 0
-
-/* intrmod: poll interval in seconds */
-#define LIO_INTRMOD_CHECK_INTERVAL 1
-
struct oct_intrmod_cfg {
u64 rx_enable;
u64 tx_enable;
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_config.h b/drivers/net/ethernet/cavium/liquidio/octeon_config.h
index b3dc2e9..d29ebc5 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_config.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_config.h
@@ -71,17 +71,17 @@
#define CN23XX_MAX_RINGS_PER_VF 8
#define CN23XX_MAX_INPUT_QUEUES CN23XX_MAX_RINGS_PER_PF
-#define CN23XX_MAX_IQ_DESCRIPTORS 2048
+#define CN23XX_MAX_IQ_DESCRIPTORS 512
#define CN23XX_DB_MIN 1
#define CN23XX_DB_MAX 8
#define CN23XX_DB_TIMEOUT 1
#define CN23XX_MAX_OUTPUT_QUEUES CN23XX_MAX_RINGS_PER_PF
-#define CN23XX_MAX_OQ_DESCRIPTORS 2048
+#define CN23XX_MAX_OQ_DESCRIPTORS 512
#define CN23XX_OQ_BUF_SIZE 1536
#define CN23XX_OQ_PKTSPER_INTR 128
/*#define CAVIUM_ONLY_CN23XX_RX_PERF*/
-#define CN23XX_OQ_REFIL_THRESHOLD 128
+#define CN23XX_OQ_REFIL_THRESHOLD 16
#define CN23XX_OQ_INTR_PKT 64
#define CN23XX_OQ_INTR_TIME 100
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
index 9675ffb..e21b477 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
@@ -793,7 +793,7 @@ int octeon_setup_instr_queues(struct octeon_device *oct)
u32 num_descs = 0;
u32 iq_no = 0;
union oct_txpciq txpciq;
- int numa_node = cpu_to_node(iq_no % num_online_cpus());
+ int numa_node = dev_to_node(&oct->pci_dev->dev);
if (OCTEON_CN6XXX(oct))
num_descs =
@@ -837,7 +837,7 @@ int octeon_setup_output_queues(struct octeon_device *oct)
u32 num_descs = 0;
u32 desc_size = 0;
u32 oq_no = 0;
- int numa_node = cpu_to_node(oq_no % num_online_cpus());
+ int numa_node = dev_to_node(&oct->pci_dev->dev);
if (OCTEON_CN6XXX(oct)) {
num_descs =
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
index c301a38..92f67de 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
@@ -453,9 +453,6 @@ struct octeon_device {
/** List of dispatch functions */
struct octeon_dispatch_list dispatch;
- /* Interrupt Moderation */
- struct oct_intrmod_cfg intrmod;
-
u32 int_status;
u64 droq_intr;
@@ -517,6 +514,9 @@ struct octeon_device {
void *msix_entries;
+ /* when requesting IRQs, the names are stored here */
+ void *irq_name_storage;
+
struct octeon_sriov_info sriov_info;
struct octeon_pf_vf_hs_word pfvf_hsword;
@@ -538,6 +538,12 @@ struct octeon_device {
u32 priv_flags;
void *watchdog_task;
+
+ u32 rx_coalesce_usecs;
+ u32 rx_max_coalesced_frames;
+ u32 tx_max_coalesced_frames;
+
+ bool cores_crashed;
};
#define OCT_DRV_ONLINE 1
@@ -551,12 +557,6 @@ struct octeon_device {
#define CHIP_CONF(oct, TYPE) \
(((struct octeon_ ## TYPE *)((oct)->chip))->conf)
-struct oct_intrmod_cmd {
- struct octeon_device *oct_dev;
- struct octeon_soft_command *sc;
- struct oct_intrmod_cfg *cfg;
-};
-
/*------------------ Function Prototypes ----------------------*/
/** Initialize device list memory */
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
index 0be87d1..286be55 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
@@ -155,11 +155,6 @@ octeon_droq_destroy_ring_buffers(struct octeon_device *oct,
recv_buffer_destroy(droq->recv_buf_list[i].buffer,
pg_info);
- if (droq->desc_ring && droq->desc_ring[i].info_ptr)
- lio_unmap_ring_info(oct->pci_dev,
- (u64)droq->
- desc_ring[i].info_ptr,
- OCT_DROQ_INFO_SIZE);
droq->recv_buf_list[i].buffer = NULL;
}
@@ -211,10 +206,7 @@ int octeon_delete_droq(struct octeon_device *oct, u32 q_no)
vfree(droq->recv_buf_list);
if (droq->info_base_addr)
- cnnic_free_aligned_dma(oct->pci_dev, droq->info_list,
- droq->info_alloc_size,
- droq->info_base_addr,
- droq->info_list_dma);
+ lio_free_info_buffer(oct, droq);
if (droq->desc_ring)
lio_dma_free(oct, (droq->max_count * OCT_DROQ_DESC_SIZE),
@@ -234,8 +226,7 @@ int octeon_init_droq(struct octeon_device *oct,
struct octeon_droq *droq;
u32 desc_ring_size = 0, c_num_descs = 0, c_buf_size = 0;
u32 c_pkts_per_intr = 0, c_refill_threshold = 0;
- int orig_node = dev_to_node(&oct->pci_dev->dev);
- int numa_node = cpu_to_node(q_no % num_online_cpus());
+ int numa_node = dev_to_node(&oct->pci_dev->dev);
dev_dbg(&oct->pci_dev->dev, "%s[%d]\n", __func__, q_no);
@@ -275,13 +266,8 @@ int octeon_init_droq(struct octeon_device *oct,
droq->buffer_size = c_buf_size;
desc_ring_size = droq->max_count * OCT_DROQ_DESC_SIZE;
- set_dev_node(&oct->pci_dev->dev, numa_node);
droq->desc_ring = lio_dma_alloc(oct, desc_ring_size,
(dma_addr_t *)&droq->desc_ring_dma);
- set_dev_node(&oct->pci_dev->dev, orig_node);
- if (!droq->desc_ring)
- droq->desc_ring = lio_dma_alloc(oct, desc_ring_size,
- (dma_addr_t *)&droq->desc_ring_dma);
if (!droq->desc_ring) {
dev_err(&oct->pci_dev->dev,
@@ -294,12 +280,7 @@ int octeon_init_droq(struct octeon_device *oct,
dev_dbg(&oct->pci_dev->dev, "droq[%d]: num_desc: %d\n", q_no,
droq->max_count);
- droq->info_list =
- cnnic_numa_alloc_aligned_dma((droq->max_count *
- OCT_DROQ_INFO_SIZE),
- &droq->info_alloc_size,
- &droq->info_base_addr,
- numa_node);
+ droq->info_list = lio_alloc_info_buffer(oct, droq);
if (!droq->info_list) {
dev_err(&oct->pci_dev->dev, "Cannot allocate memory for info list.\n");
lio_dma_free(oct, (droq->max_count * OCT_DROQ_DESC_SIZE),
@@ -532,6 +513,32 @@ octeon_droq_refill(struct octeon_device *octeon_dev, struct octeon_droq *droq)
return desc_refilled;
}
+/** check if we can allocate packets to get out of oom.
+ * @param droq - Droq being checked.
+ * @return does not return anything
+ */
+void octeon_droq_check_oom(struct octeon_droq *droq)
+{
+ int desc_refilled;
+ struct octeon_device *oct = droq->oct_dev;
+
+ if (readl(droq->pkts_credit_reg) <= CN23XX_SLI_DEF_BP) {
+ spin_lock_bh(&droq->lock);
+ desc_refilled = octeon_droq_refill(oct, droq);
+ if (desc_refilled) {
+ /* Flush the droq descriptor data to memory to be sure
+ * that when we update the credits the data in memory
+ * is accurate.
+ */
+ wmb();
+ writel(desc_refilled, droq->pkts_credit_reg);
+ /* make sure mmio write completes */
+ mmiowb();
+ }
+ spin_unlock_bh(&droq->lock);
+ }
+}
+
static inline u32
octeon_droq_get_bufcount(u32 buf_size, u32 total_len)
{
@@ -983,7 +990,7 @@ int octeon_create_droq(struct octeon_device *oct,
u32 desc_size, void *app_ctx)
{
struct octeon_droq *droq;
- int numa_node = cpu_to_node(q_no % num_online_cpus());
+ int numa_node = dev_to_node(&oct->pci_dev->dev);
if (oct->droq[q_no]) {
dev_dbg(&oct->pci_dev->dev, "Droq already in use. Cannot create droq %d again\n",
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
index e620740..9781577 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
@@ -325,10 +325,10 @@ struct octeon_droq {
size_t desc_ring_dma;
/** Info ptr list are allocated at this virtual address. */
- size_t info_base_addr;
+ void *info_base_addr;
/** DMA mapped address of the info list */
- size_t info_list_dma;
+ dma_addr_t info_list_dma;
/** Allocated size of info list. */
u32 info_alloc_size;
@@ -426,4 +426,6 @@ int octeon_droq_process_packets(struct octeon_device *oct,
int octeon_process_droq_poll_cmd(struct octeon_device *oct, u32 q_no,
int cmd, u32 arg);
+void octeon_droq_check_oom(struct octeon_droq *droq);
+
#endif /*__OCTEON_DROQ_H__ */
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
index 4608a5a..5063a12 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
@@ -152,7 +152,7 @@ struct octeon_instr_queue {
struct oct_iq_stats stats;
/** DMA mapped base address of the input descriptor ring. */
- u64 base_addr_dma;
+ dma_addr_t base_addr_dma;
/** Application context */
void *app_ctx;
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_main.h b/drivers/net/ethernet/cavium/liquidio/octeon_main.h
index aa36e9a..bed9ef1 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_main.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_main.h
@@ -140,48 +140,6 @@ static inline int octeon_map_pci_barx(struct octeon_device *oct,
return 1;
}
-static inline void *
-cnnic_numa_alloc_aligned_dma(u32 size,
- u32 *alloc_size,
- size_t *orig_ptr,
- int numa_node)
-{
- int retries = 0;
- void *ptr = NULL;
-
-#define OCTEON_MAX_ALLOC_RETRIES 1
- do {
- struct page *page = NULL;
-
- page = alloc_pages_node(numa_node,
- GFP_KERNEL,
- get_order(size));
- if (!page)
- page = alloc_pages(GFP_KERNEL,
- get_order(size));
- ptr = (void *)page_address(page);
- if ((unsigned long)ptr & 0x07) {
- __free_pages(page, get_order(size));
- ptr = NULL;
- /* Increment the size required if the first
- * attempt failed.
- */
- if (!retries)
- size += 7;
- }
- retries++;
- } while ((retries <= OCTEON_MAX_ALLOC_RETRIES) && !ptr);
-
- *alloc_size = size;
- *orig_ptr = (unsigned long)ptr;
- if ((unsigned long)ptr & 0x07)
- ptr = (void *)(((unsigned long)ptr + 7) & ~(7UL));
- return ptr;
-}
-
-#define cnnic_free_aligned_dma(pci_dev, ptr, size, orig_ptr, dma_addr) \
- free_pages(orig_ptr, get_order(size))
-
static inline int
sleep_cond(wait_queue_head_t *wait_queue, int *condition)
{
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_network.h b/drivers/net/ethernet/cavium/liquidio/octeon_network.h
index 6bb8941..bf48393 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_network.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_network.h
@@ -28,6 +28,12 @@
#define LIO_MAX_MTU_SIZE (OCTNET_MAX_FRM_SIZE - OCTNET_FRM_HEADER_SIZE)
#define LIO_MIN_MTU_SIZE ETH_MIN_MTU
+/* Bit mask values for lio->ifstate */
+#define LIO_IFSTATE_DROQ_OPS 0x01
+#define LIO_IFSTATE_REGISTERED 0x02
+#define LIO_IFSTATE_RUNNING 0x04
+#define LIO_IFSTATE_RX_TIMESTAMP_ENABLED 0x08
+
struct oct_nic_stats_resp {
u64 rh;
struct oct_link_stats stats;
@@ -62,6 +68,9 @@ struct lio {
/** Array of gather component linked lists */
struct list_head *glist;
+ void **glists_virt_base;
+ dma_addr_t *glists_dma_base;
+ u32 glist_entry_size;
/** Pointer to the NIC properties for the Octeon device this network
* interface is associated with.
@@ -120,6 +129,9 @@ struct lio {
/* work queue for txq status */
struct cavium_wq txq_status_wq;
+ /* work queue for rxq oom status */
+ struct cavium_wq rxq_status_wq;
+
/* work queue for link status */
struct cavium_wq link_status_wq;
@@ -129,10 +141,6 @@ struct lio {
#define LIO_SIZE (sizeof(struct lio))
#define GET_LIO(netdev) ((struct lio *)netdev_priv(netdev))
-#define CIU3_WDOG(c) (0x1010000020000ULL + ((c) << 3))
-#define CIU3_WDOG_MASK 12ULL
-#define LIO_MONITOR_WDOG_EXPIRE 1
-#define LIO_MONITOR_CORE_STUCK_MSGD 2
#define LIO_MAX_CORES 12
/**
@@ -143,6 +151,10 @@ struct lio {
*/
int liquidio_set_feature(struct net_device *netdev, int cmd, u16 param1);
+int setup_rx_oom_poll_fn(struct net_device *netdev);
+
+void cleanup_rx_oom_poll_fn(struct net_device *netdev);
+
/**
* \brief Link control command completion callback
* @param nctrl_ptr pointer to control packet structure
@@ -344,6 +356,29 @@ static inline void tx_buffer_free(void *buffer)
#define lio_dma_free(oct, size, virt_addr, dma_addr) \
dma_free_coherent(&(oct)->pci_dev->dev, size, virt_addr, dma_addr)
+static inline void *
+lio_alloc_info_buffer(struct octeon_device *oct,
+ struct octeon_droq *droq)
+{
+ void *virt_ptr;
+
+ virt_ptr = lio_dma_alloc(oct, (droq->max_count * OCT_DROQ_INFO_SIZE),
+ &droq->info_list_dma);
+ if (virt_ptr) {
+ droq->info_alloc_size = droq->max_count * OCT_DROQ_INFO_SIZE;
+ droq->info_base_addr = virt_ptr;
+ }
+
+ return virt_ptr;
+}
+
+static inline void lio_free_info_buffer(struct octeon_device *oct,
+ struct octeon_droq *droq)
+{
+ lio_dma_free(oct, droq->info_alloc_size, droq->info_base_addr,
+ droq->info_list_dma);
+}
+
static inline
void *get_rbd(struct sk_buff *skb)
{
@@ -359,22 +394,7 @@ void *get_rbd(struct sk_buff *skb)
static inline u64
lio_map_ring_info(struct octeon_droq *droq, u32 i)
{
- dma_addr_t dma_addr;
- struct octeon_device *oct = droq->oct_dev;
-
- dma_addr = dma_map_single(&oct->pci_dev->dev, &droq->info_list[i],
- OCT_DROQ_INFO_SIZE, DMA_FROM_DEVICE);
-
- WARN_ON(dma_mapping_error(&oct->pci_dev->dev, dma_addr));
-
- return (u64)dma_addr;
-}
-
-static inline void
-lio_unmap_ring_info(struct pci_dev *pci_dev,
- u64 info_ptr, u32 size)
-{
- dma_unmap_single(&pci_dev->dev, info_ptr, size, DMA_FROM_DEVICE);
+ return droq->info_list_dma + (i * sizeof(struct octeon_droq_info));
}
static inline u64
@@ -427,4 +447,34 @@ static inline void octeon_fast_packet_next(struct octeon_droq *droq,
get_rbd(droq->recv_buf_list[idx].buffer), copy_len);
}
+/**
+ * \brief check interface state
+ * @param lio per-network private data
+ * @param state_flag flag state to check
+ */
+static inline int ifstate_check(struct lio *lio, int state_flag)
+{
+ return atomic_read(&lio->ifstate) & state_flag;
+}
+
+/**
+ * \brief set interface state
+ * @param lio per-network private data
+ * @param state_flag flag state to set
+ */
+static inline void ifstate_set(struct lio *lio, int state_flag)
+{
+ atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) | state_flag));
+}
+
+/**
+ * \brief clear interface state
+ * @param lio per-network private data
+ * @param state_flag flag state to clear
+ */
+static inline void ifstate_reset(struct lio *lio, int state_flag)
+{
+ atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) & ~(state_flag)));
+}
+
#endif
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
index 0243be8..b457cf2 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
@@ -100,14 +100,16 @@ static void octnet_link_ctrl_callback(struct octeon_device *oct,
nctrl = (struct octnic_ctrl_pkt *)sc->ctxptr;
- /* Call the callback function if status is OK.
- * Status is OK only if a response was expected and core returned
- * success.
+ /* Call the callback function if status is zero (meaning OK) or status
+ * contains a firmware status code bigger than zero (meaning the
+ * firmware is reporting an error).
* If no response was expected, status is OK if the command was posted
* successfully.
*/
- if (!status && nctrl->cb_fn)
+ if ((!status || status > FIRMWARE_STATUS_CODE(0)) && nctrl->cb_fn) {
+ nctrl->status = status;
nctrl->cb_fn(nctrl);
+ }
octeon_free_soft_command(oct, sc);
}
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
index 0c7a5c9..6480ef8 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
@@ -62,6 +62,10 @@ struct octnic_ctrl_pkt {
/** Callback function called when the command has been fetched */
octnic_ctrl_pkt_cb_fn_t cb_fn;
+
+ u32 status;
+ u16 *response_code;
+ struct completion *completion;
};
#define MAX_UDD_SIZE(nctrl) (sizeof((nctrl)->udd))
diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c
index 707bc15..261f448 100644
--- a/drivers/net/ethernet/cavium/liquidio/request_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c
@@ -62,8 +62,7 @@ int octeon_init_instr_queue(struct octeon_device *oct,
u32 iq_no = (u32)txpciq.s.q_no;
u32 q_size;
struct cavium_wq *db_wq;
- int orig_node = dev_to_node(&oct->pci_dev->dev);
- int numa_node = cpu_to_node(iq_no % num_online_cpus());
+ int numa_node = dev_to_node(&oct->pci_dev->dev);
if (OCTEON_CN6XXX(oct))
conf = &(CFG_GET_IQ_CFG(CHIP_CONF(oct, cn6xxx)));
@@ -91,13 +90,7 @@ int octeon_init_instr_queue(struct octeon_device *oct,
iq->oct_dev = oct;
- set_dev_node(&oct->pci_dev->dev, numa_node);
- iq->base_addr = lio_dma_alloc(oct, q_size,
- (dma_addr_t *)&iq->base_addr_dma);
- set_dev_node(&oct->pci_dev->dev, orig_node);
- if (!iq->base_addr)
- iq->base_addr = lio_dma_alloc(oct, q_size,
- (dma_addr_t *)&iq->base_addr_dma);
+ iq->base_addr = lio_dma_alloc(oct, q_size, &iq->base_addr_dma);
if (!iq->base_addr) {
dev_err(&oct->pci_dev->dev, "Cannot allocate memory for instr queue %d\n",
iq_no);
@@ -211,7 +204,7 @@ int octeon_setup_iq(struct octeon_device *oct,
void *app_ctx)
{
u32 iq_no = (u32)txpciq.s.q_no;
- int numa_node = cpu_to_node(iq_no % num_online_cpus());
+ int numa_node = dev_to_node(&oct->pci_dev->dev);
if (oct->instr_queue[iq_no]) {
dev_dbg(&oct->pci_dev->dev, "IQ is in use. Cannot create the IQ: %d again\n",
diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.c b/drivers/net/ethernet/cavium/liquidio/response_manager.c
index 2fbaae9..3d691c6 100644
--- a/drivers/net/ethernet/cavium/liquidio/response_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/response_manager.c
@@ -69,50 +69,53 @@ int lio_process_ordered_list(struct octeon_device *octeon_dev,
int resp_to_process = MAX_ORD_REQS_TO_PROCESS;
u32 status;
u64 status64;
- struct octeon_instr_rdp *rdp;
- u64 rptr;
ordered_sc_list = &octeon_dev->response_list[OCTEON_ORDERED_SC_LIST];
do {
spin_lock_bh(&ordered_sc_list->lock);
- if (ordered_sc_list->head.next == &ordered_sc_list->head) {
+ if (list_empty(&ordered_sc_list->head)) {
spin_unlock_bh(&ordered_sc_list->lock);
return 1;
}
- sc = (struct octeon_soft_command *)ordered_sc_list->
- head.next;
- if (OCTEON_CN23XX_PF(octeon_dev) ||
- OCTEON_CN23XX_VF(octeon_dev)) {
- rdp = (struct octeon_instr_rdp *)&sc->cmd.cmd3.rdp;
- rptr = sc->cmd.cmd3.rptr;
- } else {
- rdp = (struct octeon_instr_rdp *)&sc->cmd.cmd2.rdp;
- rptr = sc->cmd.cmd2.rptr;
- }
+ sc = list_first_entry(&ordered_sc_list->head,
+ struct octeon_soft_command, node);
status = OCTEON_REQUEST_PENDING;
/* check if octeon has finished DMA'ing a response
* to where rptr is pointing to
*/
- dma_sync_single_for_cpu(&octeon_dev->pci_dev->dev,
- rptr, rdp->rlen,
- DMA_FROM_DEVICE);
status64 = *sc->status_word;
if (status64 != COMPLETION_WORD_INIT) {
+ /* This logic ensures that all 64b have been written.
+ * 1. check byte 0 for non-FF
+ * 2. if non-FF, then swap result from BE to host order
+ * 3. check byte 7 (swapped to 0) for non-FF
+ * 4. if non-FF, use the low 32-bit status code
+ * 5. if either byte 0 or byte 7 is FF, don't use status
+ */
if ((status64 & 0xff) != 0xff) {
octeon_swap_8B_data(&status64, 1);
if (((status64 & 0xff) != 0xff)) {
- status = (u32)(status64 &
- 0xffffffffULL);
+ /* retrieve 16-bit firmware status */
+ status = (u32)(status64 & 0xffffULL);
+ if (status) {
+ status =
+ FIRMWARE_STATUS_CODE(status);
+ } else {
+ /* i.e. no error */
+ status = OCTEON_REQUEST_DONE;
+ }
}
}
} else if (force_quit || (sc->timeout &&
time_after(jiffies, (unsigned long)sc->timeout))) {
+ dev_err(&octeon_dev->pci_dev->dev, "%s: cmd failed, timeout (%ld, %ld)\n",
+ __func__, (long)jiffies, (long)sc->timeout);
status = OCTEON_REQUEST_TIMEOUT;
}
diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.h b/drivers/net/ethernet/cavium/liquidio/response_manager.h
index cbb2d84..9169c28 100644
--- a/drivers/net/ethernet/cavium/liquidio/response_manager.h
+++ b/drivers/net/ethernet/cavium/liquidio/response_manager.h
@@ -78,6 +78,8 @@ enum {
/*------------ Error codes used by host driver -----------------*/
#define DRIVER_MAJOR_ERROR_CODE 0x0000
+/*------ Error codes used by firmware (bits 15..0 set by firmware */
+#define FIRMWARE_MAJOR_ERROR_CODE 0x0001
/** A value of 0x00000000 indicates no error i.e. success */
#define DRIVER_ERROR_NONE 0x00000000
@@ -116,6 +118,9 @@ enum {
};
+#define FIRMWARE_STATUS_CODE(status) \
+ ((FIRMWARE_MAJOR_ERROR_CODE << 16) | (status))
+
/** Initialize the response lists. The number of response lists to create is
* given by count.
* @param octeon_dev - the octeon device structure.
diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
index e739c71..2269ff5 100644
--- a/drivers/net/ethernet/cavium/thunder/nic.h
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -269,6 +269,7 @@ struct nicvf {
#define MAX_QUEUES_PER_QSET 8
struct queue_set *qs;
struct nicvf_cq_poll *napi[8];
+ void *iommu_domain;
u8 vf_id;
u8 sqs_id;
bool sqs_mode;
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 6feaa24..330d8a0 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -16,6 +16,7 @@
#include <linux/log2.h>
#include <linux/prefetch.h>
#include <linux/irq.h>
+#include <linux/iommu.h>
#include "nic_reg.h"
#include "nic.h"
@@ -525,7 +526,12 @@ static void nicvf_snd_pkt_handler(struct net_device *netdev,
/* Get actual TSO descriptors and free them */
tso_sqe =
(struct sq_hdr_subdesc *)GET_SQ_DESC(sq, hdr->rsvd2);
+ nicvf_unmap_sndq_buffers(nic, sq, hdr->rsvd2,
+ tso_sqe->subdesc_cnt);
nicvf_put_sq_desc(sq, tso_sqe->subdesc_cnt + 1);
+ } else {
+ nicvf_unmap_sndq_buffers(nic, sq, cqe_tx->sqe_ptr,
+ hdr->subdesc_cnt);
}
nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1);
prefetch(skb);
@@ -576,6 +582,7 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev,
{
struct sk_buff *skb;
struct nicvf *nic = netdev_priv(netdev);
+ struct nicvf *snic = nic;
int err = 0;
int rq_idx;
@@ -592,7 +599,7 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev,
if (err && !cqe_rx->rb_cnt)
return;
- skb = nicvf_get_rcv_skb(nic, cqe_rx);
+ skb = nicvf_get_rcv_skb(snic, cqe_rx);
if (!skb) {
netdev_dbg(nic->netdev, "Packet not received\n");
return;
@@ -1643,6 +1650,9 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
if (!pass1_silicon(nic->pdev))
nic->hw_tso = true;
+ /* Get iommu domain for iova to physical addr conversion */
+ nic->iommu_domain = iommu_get_domain_for_dev(dev);
+
pci_read_config_word(nic->pdev, PCI_SUBSYSTEM_ID, &sdevid);
if (sdevid == 0xA134)
nic->t88 = true;
@@ -1655,8 +1665,9 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
if (err)
goto err_unregister_interrupts;
- netdev->hw_features = (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_SG |
- NETIF_F_TSO | NETIF_F_GRO |
+ netdev->hw_features = (NETIF_F_RXCSUM | NETIF_F_SG |
+ NETIF_F_TSO | NETIF_F_GRO | NETIF_F_TSO6 |
+ NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
NETIF_F_HW_VLAN_CTAG_RX);
netdev->hw_features |= NETIF_F_RXHASH;
@@ -1664,7 +1675,8 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
netdev->features |= netdev->hw_features;
netdev->hw_features |= NETIF_F_LOOPBACK;
- netdev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO;
+ netdev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM |
+ NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO6;
netdev->netdev_ops = &nicvf_netdev_ops;
netdev->watchdog_timeo = NICVF_TX_TIMEOUT;
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index ac0390b..7b0fd8d 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -10,6 +10,7 @@
#include <linux/netdevice.h>
#include <linux/ip.h>
#include <linux/etherdevice.h>
+#include <linux/iommu.h>
#include <net/ip.h>
#include <net/tso.h>
@@ -18,6 +19,16 @@
#include "q_struct.h"
#include "nicvf_queues.h"
+#define NICVF_PAGE_ORDER ((PAGE_SIZE <= 4096) ? PAGE_ALLOC_COSTLY_ORDER : 0)
+
+static inline u64 nicvf_iova_to_phys(struct nicvf *nic, dma_addr_t dma_addr)
+{
+ /* Translation is installed only when IOMMU is present */
+ if (nic->iommu_domain)
+ return iommu_iova_to_phys(nic->iommu_domain, dma_addr);
+ return dma_addr;
+}
+
static void nicvf_get_page(struct nicvf *nic)
{
if (!nic->rb_pageref || !nic->rb_page)
@@ -87,7 +98,7 @@ static void nicvf_free_q_desc_mem(struct nicvf *nic, struct q_desc_mem *dmem)
static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, gfp_t gfp,
u32 buf_len, u64 **rbuf)
{
- int order = (PAGE_SIZE <= 4096) ? PAGE_ALLOC_COSTLY_ORDER : 0;
+ int order = NICVF_PAGE_ORDER;
/* Check if request can be accomodated in previous allocated page */
if (nic->rb_page &&
@@ -97,22 +108,27 @@ static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, gfp_t gfp,
}
nicvf_get_page(nic);
- nic->rb_page = NULL;
/* Allocate a new page */
+ nic->rb_page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN,
+ order);
if (!nic->rb_page) {
- nic->rb_page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN,
- order);
- if (!nic->rb_page) {
- this_cpu_inc(nic->pnicvf->drv_stats->
- rcv_buffer_alloc_failures);
- return -ENOMEM;
- }
- nic->rb_page_offset = 0;
+ this_cpu_inc(nic->pnicvf->drv_stats->rcv_buffer_alloc_failures);
+ return -ENOMEM;
}
-
+ nic->rb_page_offset = 0;
ret:
- *rbuf = (u64 *)((u64)page_address(nic->rb_page) + nic->rb_page_offset);
+ /* HW will ensure data coherency, CPU sync not required */
+ *rbuf = (u64 *)((u64)dma_map_page_attrs(&nic->pdev->dev, nic->rb_page,
+ nic->rb_page_offset, buf_len,
+ DMA_FROM_DEVICE,
+ DMA_ATTR_SKIP_CPU_SYNC));
+ if (dma_mapping_error(&nic->pdev->dev, (dma_addr_t)*rbuf)) {
+ if (!nic->rb_page_offset)
+ __free_pages(nic->rb_page, order);
+ nic->rb_page = NULL;
+ return -ENOMEM;
+ }
nic->rb_page_offset += buf_len;
return 0;
@@ -158,16 +174,21 @@ static int nicvf_init_rbdr(struct nicvf *nic, struct rbdr *rbdr,
rbdr->dma_size = buf_size;
rbdr->enable = true;
rbdr->thresh = RBDR_THRESH;
+ rbdr->head = 0;
+ rbdr->tail = 0;
nic->rb_page = NULL;
for (idx = 0; idx < ring_len; idx++) {
err = nicvf_alloc_rcv_buffer(nic, GFP_KERNEL, RCV_FRAG_LEN,
&rbuf);
- if (err)
+ if (err) {
+ /* To free already allocated and mapped ones */
+ rbdr->tail = idx - 1;
return err;
+ }
desc = GET_RBDR_DESC(rbdr, idx);
- desc->buf_addr = virt_to_phys(rbuf) >> NICVF_RCV_BUF_ALIGN;
+ desc->buf_addr = (u64)rbuf >> NICVF_RCV_BUF_ALIGN;
}
nicvf_get_page(nic);
@@ -179,7 +200,7 @@ static int nicvf_init_rbdr(struct nicvf *nic, struct rbdr *rbdr,
static void nicvf_free_rbdr(struct nicvf *nic, struct rbdr *rbdr)
{
int head, tail;
- u64 buf_addr;
+ u64 buf_addr, phys_addr;
struct rbdr_entry_t *desc;
if (!rbdr)
@@ -192,18 +213,26 @@ static void nicvf_free_rbdr(struct nicvf *nic, struct rbdr *rbdr)
head = rbdr->head;
tail = rbdr->tail;
- /* Free SKBs */
+ /* Release page references */
while (head != tail) {
desc = GET_RBDR_DESC(rbdr, head);
- buf_addr = desc->buf_addr << NICVF_RCV_BUF_ALIGN;
- put_page(virt_to_page(phys_to_virt(buf_addr)));
+ buf_addr = ((u64)desc->buf_addr) << NICVF_RCV_BUF_ALIGN;
+ phys_addr = nicvf_iova_to_phys(nic, buf_addr);
+ dma_unmap_page_attrs(&nic->pdev->dev, buf_addr, RCV_FRAG_LEN,
+ DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+ if (phys_addr)
+ put_page(virt_to_page(phys_to_virt(phys_addr)));
head++;
head &= (rbdr->dmem.q_len - 1);
}
- /* Free SKB of tail desc */
+ /* Release buffer of tail desc */
desc = GET_RBDR_DESC(rbdr, tail);
- buf_addr = desc->buf_addr << NICVF_RCV_BUF_ALIGN;
- put_page(virt_to_page(phys_to_virt(buf_addr)));
+ buf_addr = ((u64)desc->buf_addr) << NICVF_RCV_BUF_ALIGN;
+ phys_addr = nicvf_iova_to_phys(nic, buf_addr);
+ dma_unmap_page_attrs(&nic->pdev->dev, buf_addr, RCV_FRAG_LEN,
+ DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+ if (phys_addr)
+ put_page(virt_to_page(phys_to_virt(phys_addr)));
/* Free RBDR ring */
nicvf_free_q_desc_mem(nic, &rbdr->dmem);
@@ -250,7 +279,7 @@ static void nicvf_refill_rbdr(struct nicvf *nic, gfp_t gfp)
break;
desc = GET_RBDR_DESC(rbdr, tail);
- desc->buf_addr = virt_to_phys(rbuf) >> NICVF_RCV_BUF_ALIGN;
+ desc->buf_addr = (u64)rbuf >> NICVF_RCV_BUF_ALIGN;
refill_rb_cnt--;
new_rb++;
}
@@ -361,9 +390,29 @@ static int nicvf_init_snd_queue(struct nicvf *nic,
return 0;
}
+void nicvf_unmap_sndq_buffers(struct nicvf *nic, struct snd_queue *sq,
+ int hdr_sqe, u8 subdesc_cnt)
+{
+ u8 idx;
+ struct sq_gather_subdesc *gather;
+
+ /* Unmap DMA mapped skb data buffers */
+ for (idx = 0; idx < subdesc_cnt; idx++) {
+ hdr_sqe++;
+ hdr_sqe &= (sq->dmem.q_len - 1);
+ gather = (struct sq_gather_subdesc *)GET_SQ_DESC(sq, hdr_sqe);
+ /* HW will ensure data coherency, CPU sync not required */
+ dma_unmap_page_attrs(&nic->pdev->dev, gather->addr,
+ gather->size, DMA_TO_DEVICE,
+ DMA_ATTR_SKIP_CPU_SYNC);
+ }
+}
+
static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq)
{
struct sk_buff *skb;
+ struct sq_hdr_subdesc *hdr;
+ struct sq_hdr_subdesc *tso_sqe;
if (!sq)
return;
@@ -379,8 +428,22 @@ static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq)
smp_rmb();
while (sq->head != sq->tail) {
skb = (struct sk_buff *)sq->skbuff[sq->head];
- if (skb)
- dev_kfree_skb_any(skb);
+ if (!skb)
+ goto next;
+ hdr = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, sq->head);
+ /* Check for dummy descriptor used for HW TSO offload on 88xx */
+ if (hdr->dont_send) {
+ /* Get actual TSO descriptors and unmap them */
+ tso_sqe =
+ (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, hdr->rsvd2);
+ nicvf_unmap_sndq_buffers(nic, sq, hdr->rsvd2,
+ tso_sqe->subdesc_cnt);
+ } else {
+ nicvf_unmap_sndq_buffers(nic, sq, sq->head,
+ hdr->subdesc_cnt);
+ }
+ dev_kfree_skb_any(skb);
+next:
sq->head++;
sq->head &= (sq->dmem.q_len - 1);
}
@@ -559,9 +622,11 @@ static void nicvf_rcv_queue_config(struct nicvf *nic, struct queue_set *qs,
nicvf_send_msg_to_pf(nic, &mbx);
if (!nic->sqs_mode && (qidx == 0)) {
- /* Enable checking L3/L4 length and TCP/UDP checksums */
+ /* Enable checking L3/L4 length and TCP/UDP checksums
+ * Also allow IPv6 pkts with zero UDP checksum.
+ */
nicvf_queue_reg_write(nic, NIC_QSET_RQ_GEN_CFG, 0,
- (BIT(24) | BIT(23) | BIT(21)));
+ (BIT(24) | BIT(23) | BIT(21) | BIT(20)));
nicvf_config_vlan_stripping(nic, nic->netdev->features);
}
@@ -882,6 +947,14 @@ static inline int nicvf_get_sq_desc(struct snd_queue *sq, int desc_cnt)
return qentry;
}
+/* Rollback to previous tail pointer when descriptors not used */
+static inline void nicvf_rollback_sq_desc(struct snd_queue *sq,
+ int qentry, int desc_cnt)
+{
+ sq->tail = qentry;
+ atomic_add(desc_cnt, &sq->free_cnt);
+}
+
/* Free descriptor back to SQ for future use */
void nicvf_put_sq_desc(struct snd_queue *sq, int desc_cnt)
{
@@ -1021,7 +1094,13 @@ nicvf_sq_add_hdr_subdesc(struct nicvf *nic, struct snd_queue *sq, int qentry,
{
int proto;
struct sq_hdr_subdesc *hdr;
+ union {
+ struct iphdr *v4;
+ struct ipv6hdr *v6;
+ unsigned char *hdr;
+ } ip;
+ ip.hdr = skb_network_header(skb);
hdr = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, qentry);
memset(hdr, 0, SND_QUEUE_DESC_SIZE);
hdr->subdesc_type = SQ_DESC_TYPE_HEADER;
@@ -1046,7 +1125,9 @@ nicvf_sq_add_hdr_subdesc(struct nicvf *nic, struct snd_queue *sq, int qentry,
hdr->l3_offset = skb_network_offset(skb);
hdr->l4_offset = skb_transport_offset(skb);
- proto = ip_hdr(skb)->protocol;
+ proto = (ip.v4->version == 4) ? ip.v4->protocol :
+ ip.v6->nexthdr;
+
switch (proto) {
case IPPROTO_TCP:
hdr->csum_l4 = SEND_L4_CSUM_TCP;
@@ -1207,8 +1288,9 @@ int nicvf_sq_append_skb(struct nicvf *nic, struct snd_queue *sq,
struct sk_buff *skb, u8 sq_num)
{
int i, size;
- int subdesc_cnt, tso_sqe = 0;
+ int subdesc_cnt, hdr_sqe = 0;
int qentry;
+ u64 dma_addr;
subdesc_cnt = nicvf_sq_subdesc_required(nic, skb);
if (subdesc_cnt > atomic_read(&sq->free_cnt))
@@ -1223,12 +1305,21 @@ int nicvf_sq_append_skb(struct nicvf *nic, struct snd_queue *sq,
/* Add SQ header subdesc */
nicvf_sq_add_hdr_subdesc(nic, sq, qentry, subdesc_cnt - 1,
skb, skb->len);
- tso_sqe = qentry;
+ hdr_sqe = qentry;
/* Add SQ gather subdescs */
qentry = nicvf_get_nxt_sqentry(sq, qentry);
size = skb_is_nonlinear(skb) ? skb_headlen(skb) : skb->len;
- nicvf_sq_add_gather_subdesc(sq, qentry, size, virt_to_phys(skb->data));
+ /* HW will ensure data coherency, CPU sync not required */
+ dma_addr = dma_map_page_attrs(&nic->pdev->dev, virt_to_page(skb->data),
+ offset_in_page(skb->data), size,
+ DMA_TO_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+ if (dma_mapping_error(&nic->pdev->dev, dma_addr)) {
+ nicvf_rollback_sq_desc(sq, qentry, subdesc_cnt);
+ return 0;
+ }
+
+ nicvf_sq_add_gather_subdesc(sq, qentry, size, dma_addr);
/* Check for scattered buffer */
if (!skb_is_nonlinear(skb))
@@ -1241,15 +1332,26 @@ int nicvf_sq_append_skb(struct nicvf *nic, struct snd_queue *sq,
qentry = nicvf_get_nxt_sqentry(sq, qentry);
size = skb_frag_size(frag);
- nicvf_sq_add_gather_subdesc(sq, qentry, size,
- virt_to_phys(
- skb_frag_address(frag)));
+ dma_addr = dma_map_page_attrs(&nic->pdev->dev,
+ skb_frag_page(frag),
+ frag->page_offset, size,
+ DMA_TO_DEVICE,
+ DMA_ATTR_SKIP_CPU_SYNC);
+ if (dma_mapping_error(&nic->pdev->dev, dma_addr)) {
+ /* Free entire chain of mapped buffers
+ * here 'i' = frags mapped + above mapped skb->data
+ */
+ nicvf_unmap_sndq_buffers(nic, sq, hdr_sqe, i);
+ nicvf_rollback_sq_desc(sq, qentry, subdesc_cnt);
+ return 0;
+ }
+ nicvf_sq_add_gather_subdesc(sq, qentry, size, dma_addr);
}
doorbell:
if (nic->t88 && skb_shinfo(skb)->gso_size) {
qentry = nicvf_get_nxt_sqentry(sq, qentry);
- nicvf_sq_add_cqe_subdesc(sq, qentry, tso_sqe, skb);
+ nicvf_sq_add_cqe_subdesc(sq, qentry, hdr_sqe, skb);
}
nicvf_sq_doorbell(nic, skb, sq_num, subdesc_cnt);
@@ -1282,6 +1384,7 @@ struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
int offset;
u16 *rb_lens = NULL;
u64 *rb_ptrs = NULL;
+ u64 phys_addr;
rb_lens = (void *)cqe_rx + (3 * sizeof(u64));
/* Except 88xx pass1 on all other chips CQE_RX2_S is added to
@@ -1296,15 +1399,23 @@ struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
else
rb_ptrs = (void *)cqe_rx + (7 * sizeof(u64));
- netdev_dbg(nic->netdev, "%s rb_cnt %d rb0_ptr %llx rb0_sz %d\n",
- __func__, cqe_rx->rb_cnt, cqe_rx->rb0_ptr, cqe_rx->rb0_sz);
-
for (frag = 0; frag < cqe_rx->rb_cnt; frag++) {
payload_len = rb_lens[frag_num(frag)];
+ phys_addr = nicvf_iova_to_phys(nic, *rb_ptrs);
+ if (!phys_addr) {
+ if (skb)
+ dev_kfree_skb_any(skb);
+ return NULL;
+ }
+
if (!frag) {
/* First fragment */
+ dma_unmap_page_attrs(&nic->pdev->dev,
+ *rb_ptrs - cqe_rx->align_pad,
+ RCV_FRAG_LEN, DMA_FROM_DEVICE,
+ DMA_ATTR_SKIP_CPU_SYNC);
skb = nicvf_rb_ptr_to_skb(nic,
- *rb_ptrs - cqe_rx->align_pad,
+ phys_addr - cqe_rx->align_pad,
payload_len);
if (!skb)
return NULL;
@@ -1312,8 +1423,11 @@ struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
skb_put(skb, payload_len);
} else {
/* Add fragments */
- page = virt_to_page(phys_to_virt(*rb_ptrs));
- offset = phys_to_virt(*rb_ptrs) - page_address(page);
+ dma_unmap_page_attrs(&nic->pdev->dev, *rb_ptrs,
+ RCV_FRAG_LEN, DMA_FROM_DEVICE,
+ DMA_ATTR_SKIP_CPU_SYNC);
+ page = virt_to_page(phys_to_virt(phys_addr));
+ offset = phys_to_virt(phys_addr) - page_address(page);
skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
offset, payload_len, RCV_FRAG_LEN);
}
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
index 5cb84da..10cb4b8 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
@@ -87,7 +87,7 @@
#define RCV_BUF_COUNT (1ULL << (RBDR_SIZE + 13))
#define MAX_RCV_BUF_COUNT (1ULL << (RBDR_SIZE6 + 13))
#define RBDR_THRESH (RCV_BUF_COUNT / 2)
-#define DMA_BUFFER_LEN 2048 /* In multiples of 128bytes */
+#define DMA_BUFFER_LEN 1536 /* In multiples of 128bytes */
#define RCV_FRAG_LEN (SKB_DATA_ALIGN(DMA_BUFFER_LEN + NET_SKB_PAD) + \
SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
@@ -301,6 +301,8 @@ struct queue_set {
#define CQ_ERR_MASK (CQ_WR_FULL | CQ_WR_DISABLE | CQ_WR_FAULT)
+void nicvf_unmap_sndq_buffers(struct nicvf *nic, struct snd_queue *sq,
+ int hdr_sqe, u8 subdesc_cnt);
void nicvf_config_vlan_stripping(struct nicvf *nic,
netdev_features_t features);
int nicvf_set_qset_resources(struct nicvf *nic);
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 4c8e8cf..64a1095 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -123,14 +123,44 @@ static int bgx_poll_reg(struct bgx *bgx, u8 lmac, u64 reg, u64 mask, bool zero)
return 1;
}
+static int max_bgx_per_node;
+static void set_max_bgx_per_node(struct pci_dev *pdev)
+{
+ u16 sdevid;
+
+ if (max_bgx_per_node)
+ return;
+
+ pci_read_config_word(pdev, PCI_SUBSYSTEM_ID, &sdevid);
+ switch (sdevid) {
+ case PCI_SUBSYS_DEVID_81XX_BGX:
+ max_bgx_per_node = MAX_BGX_PER_CN81XX;
+ break;
+ case PCI_SUBSYS_DEVID_83XX_BGX:
+ max_bgx_per_node = MAX_BGX_PER_CN83XX;
+ break;
+ case PCI_SUBSYS_DEVID_88XX_BGX:
+ default:
+ max_bgx_per_node = MAX_BGX_PER_CN88XX;
+ break;
+ }
+}
+
+static struct bgx *get_bgx(int node, int bgx_idx)
+{
+ int idx = (node * max_bgx_per_node) + bgx_idx;
+
+ return bgx_vnic[idx];
+}
+
/* Return number of BGX present in HW */
unsigned bgx_get_map(int node)
{
int i;
unsigned map = 0;
- for (i = 0; i < MAX_BGX_PER_NODE; i++) {
- if (bgx_vnic[(node * MAX_BGX_PER_NODE) + i])
+ for (i = 0; i < max_bgx_per_node; i++) {
+ if (bgx_vnic[(node * max_bgx_per_node) + i])
map |= (1 << i);
}
@@ -143,7 +173,7 @@ int bgx_get_lmac_count(int node, int bgx_idx)
{
struct bgx *bgx;
- bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+ bgx = get_bgx(node, bgx_idx);
if (bgx)
return bgx->lmac_count;
@@ -158,7 +188,7 @@ void bgx_get_lmac_link_state(int node, int bgx_idx, int lmacid, void *status)
struct bgx *bgx;
struct lmac *lmac;
- bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+ bgx = get_bgx(node, bgx_idx);
if (!bgx)
return;
@@ -172,7 +202,7 @@ EXPORT_SYMBOL(bgx_get_lmac_link_state);
const u8 *bgx_get_lmac_mac(int node, int bgx_idx, int lmacid)
{
- struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+ struct bgx *bgx = get_bgx(node, bgx_idx);
if (bgx)
return bgx->lmac[lmacid].mac;
@@ -183,7 +213,7 @@ EXPORT_SYMBOL(bgx_get_lmac_mac);
void bgx_set_lmac_mac(int node, int bgx_idx, int lmacid, const u8 *mac)
{
- struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+ struct bgx *bgx = get_bgx(node, bgx_idx);
if (!bgx)
return;
@@ -194,7 +224,7 @@ EXPORT_SYMBOL(bgx_set_lmac_mac);
void bgx_lmac_rx_tx_enable(int node, int bgx_idx, int lmacid, bool enable)
{
- struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+ struct bgx *bgx = get_bgx(node, bgx_idx);
struct lmac *lmac;
u64 cfg;
@@ -217,7 +247,7 @@ EXPORT_SYMBOL(bgx_lmac_rx_tx_enable);
void bgx_lmac_get_pfc(int node, int bgx_idx, int lmacid, void *pause)
{
struct pfc *pfc = (struct pfc *)pause;
- struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx];
+ struct bgx *bgx = get_bgx(node, bgx_idx);
struct lmac *lmac;
u64 cfg;
@@ -237,7 +267,7 @@ EXPORT_SYMBOL(bgx_lmac_get_pfc);
void bgx_lmac_set_pfc(int node, int bgx_idx, int lmacid, void *pause)
{
struct pfc *pfc = (struct pfc *)pause;
- struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx];
+ struct bgx *bgx = get_bgx(node, bgx_idx);
struct lmac *lmac;
u64 cfg;
@@ -369,7 +399,7 @@ u64 bgx_get_rx_stats(int node, int bgx_idx, int lmac, int idx)
{
struct bgx *bgx;
- bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+ bgx = get_bgx(node, bgx_idx);
if (!bgx)
return 0;
@@ -383,7 +413,7 @@ u64 bgx_get_tx_stats(int node, int bgx_idx, int lmac, int idx)
{
struct bgx *bgx;
- bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+ bgx = get_bgx(node, bgx_idx);
if (!bgx)
return 0;
@@ -411,7 +441,7 @@ void bgx_lmac_internal_loopback(int node, int bgx_idx,
struct lmac *lmac;
u64 cfg;
- bgx = bgx_vnic[(node * MAX_BGX_PER_NODE) + bgx_idx];
+ bgx = get_bgx(node, bgx_idx);
if (!bgx)
return;
@@ -1011,12 +1041,6 @@ static void bgx_print_qlm_mode(struct bgx *bgx, u8 lmacid)
dev_info(dev, "%s: 40G_KR4\n", (char *)str);
break;
case BGX_MODE_QSGMII:
- if ((lmacid == 0) &&
- (bgx_get_lane2sds_cfg(bgx, lmac) != lmacid))
- return;
- if ((lmacid == 2) &&
- (bgx_get_lane2sds_cfg(bgx, lmac) == lmacid))
- return;
dev_info(dev, "%s: QSGMII\n", (char *)str);
break;
case BGX_MODE_RGMII:
@@ -1334,11 +1358,13 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
goto err_release_regions;
}
+ set_max_bgx_per_node(pdev);
+
pci_read_config_word(pdev, PCI_DEVICE_ID, &sdevid);
if (sdevid != PCI_DEVICE_ID_THUNDER_RGX) {
bgx->bgx_id = (pci_resource_start(pdev,
PCI_CFG_REG_BAR_NUM) >> 24) & BGX_ID_MASK;
- bgx->bgx_id += nic_get_node_id(pdev) * MAX_BGX_PER_NODE;
+ bgx->bgx_id += nic_get_node_id(pdev) * max_bgx_per_node;
bgx->max_lmac = MAX_LMAC_PER_BGX;
bgx_vnic[bgx->bgx_id] = bgx;
} else {
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
index a60f189..c5080f2c 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -22,7 +22,6 @@
#define MAX_BGX_PER_CN88XX 2
#define MAX_BGX_PER_CN81XX 3 /* 2 BGXs + 1 RGX */
#define MAX_BGX_PER_CN83XX 4
-#define MAX_BGX_PER_NODE 4
#define MAX_LMAC_PER_BGX 4
#define MAX_BGX_CHANS_PER_LMAC 16
#define MAX_DMAC_PER_LMAC 8
diff --git a/drivers/net/ethernet/chelsio/cxgb/common.h b/drivers/net/ethernet/chelsio/cxgb/common.h
index 6916c62..94b9482f 100644
--- a/drivers/net/ethernet/chelsio/cxgb/common.h
+++ b/drivers/net/ethernet/chelsio/cxgb/common.h
@@ -223,7 +223,6 @@ struct port_info {
struct cmac *mac;
struct cphy *phy;
struct link_config link_config;
- struct net_device_stats netstats;
};
struct sge;
diff --git a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
index d8aff7a..8623be1 100644
--- a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
+++ b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
@@ -296,7 +296,7 @@ static struct net_device_stats *t1_get_stats(struct net_device *dev)
{
struct adapter *adapter = dev->ml_priv;
struct port_info *p = &adapter->port[dev->if_port];
- struct net_device_stats *ns = &p->netstats;
+ struct net_device_stats *ns = &dev->stats;
const struct cmac_statistics *pstats;
/* Do a full update of the MAC stats */
diff --git a/drivers/net/ethernet/chelsio/cxgb3/adapter.h b/drivers/net/ethernet/chelsio/cxgb3/adapter.h
index 8b395b5..087ff0f 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/adapter.h
+++ b/drivers/net/ethernet/chelsio/cxgb3/adapter.h
@@ -72,7 +72,6 @@ struct port_info {
struct cphy phy;
struct cmac mac;
struct link_config link_config;
- struct net_device_stats netstats;
int activity;
__be32 iscsi_ipv4addr;
struct iscsi_config iscsic;
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
index d764916..2ff6bd1 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
@@ -1489,7 +1489,7 @@ static struct net_device_stats *cxgb_get_stats(struct net_device *dev)
{
struct port_info *pi = netdev_priv(dev);
struct adapter *adapter = pi->adapter;
- struct net_device_stats *ns = &pi->netstats;
+ struct net_device_stats *ns = &dev->stats;
const struct mac_stats *pstats;
spin_lock(&adapter->stats_lock);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 87000cd..0de8eb7 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -6369,7 +6369,6 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size,
unsigned int stat_len = cache_line_size > 64 ? 128 : 64;
unsigned int fl_align = cache_line_size < 32 ? 32 : cache_line_size;
unsigned int fl_align_log = fls(fl_align) - 1;
- unsigned int ingpad;
t4_write_reg(adap, SGE_HOST_PAGE_SIZE_A,
HOSTPAGESIZEPF0_V(sge_hps) |
@@ -6389,6 +6388,10 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size,
INGPADBOUNDARY_SHIFT_X) |
EGRSTATUSPAGESIZE_V(stat_len != 64));
} else {
+ unsigned int pack_align;
+ unsigned int ingpad, ingpack;
+ unsigned int pcie_cap;
+
/* T5 introduced the separation of the Free List Padding and
* Packing Boundaries. Thus, we can select a smaller Padding
* Boundary to avoid uselessly chewing up PCIe Link and Memory
@@ -6401,27 +6404,62 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size,
* Size (the minimum unit of transfer to/from Memory). If we
* have a Padding Boundary which is smaller than the Memory
* Line Size, that'll involve a Read-Modify-Write cycle on the
- * Memory Controller which is never good. For T5 the smallest
- * Padding Boundary which we can select is 32 bytes which is
- * larger than any known Memory Controller Line Size so we'll
- * use that.
- *
- * T5 has a different interpretation of the "0" value for the
- * Packing Boundary. This corresponds to 16 bytes instead of
- * the expected 32 bytes. We never have a Packing Boundary
- * less than 32 bytes so we can't use that special value but
- * on the other hand, if we wanted 32 bytes, the best we can
- * really do is 64 bytes.
- */
- if (fl_align <= 32) {
- fl_align = 64;
- fl_align_log = 6;
+ * Memory Controller which is never good.
+ */
+
+ /* We want the Packing Boundary to be based on the Cache Line
+ * Size in order to help avoid False Sharing performance
+ * issues between CPUs, etc. We also want the Packing
+ * Boundary to incorporate the PCI-E Maximum Payload Size. We
+ * get best performance when the Packing Boundary is a
+ * multiple of the Maximum Payload Size.
+ */
+ pack_align = fl_align;
+ pcie_cap = pci_find_capability(adap->pdev, PCI_CAP_ID_EXP);
+ if (pcie_cap) {
+ unsigned int mps, mps_log;
+ u16 devctl;
+
+ /* The PCIe Device Control Maximum Payload Size field
+ * [bits 7:5] encodes sizes as powers of 2 starting at
+ * 128 bytes.
+ */
+ pci_read_config_word(adap->pdev,
+ pcie_cap + PCI_EXP_DEVCTL,
+ &devctl);
+ mps_log = ((devctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5) + 7;
+ mps = 1 << mps_log;
+ if (mps > pack_align)
+ pack_align = mps;
}
+ /* N.B. T5/T6 have a crazy special interpretation of the "0"
+ * value for the Packing Boundary. This corresponds to 16
+ * bytes instead of the expected 32 bytes. So if we want 32
+ * bytes, the best we can really do is 64 bytes ...
+ */
+ if (pack_align <= 16) {
+ ingpack = INGPACKBOUNDARY_16B_X;
+ fl_align = 16;
+ } else if (pack_align == 32) {
+ ingpack = INGPACKBOUNDARY_64B_X;
+ fl_align = 64;
+ } else {
+ unsigned int pack_align_log = fls(pack_align) - 1;
+
+ ingpack = pack_align_log - INGPACKBOUNDARY_SHIFT_X;
+ fl_align = pack_align;
+ }
+
+ /* Use the smallest Ingress Padding which isn't smaller than
+ * the Memory Controller Read/Write Size. We'll take that as
+ * being 8 bytes since we don't know of any system with a
+ * wider Memory Controller Bus Width.
+ */
if (is_t5(adap->params.chip))
- ingpad = INGPCIEBOUNDARY_32B_X;
+ ingpad = INGPADBOUNDARY_32B_X;
else
- ingpad = T6_INGPADBOUNDARY_32B_X;
+ ingpad = T6_INGPADBOUNDARY_8B_X;
t4_set_reg_field(adap, SGE_CONTROL_A,
INGPADBOUNDARY_V(INGPADBOUNDARY_M) |
@@ -6430,8 +6468,7 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size,
EGRSTATUSPAGESIZE_V(stat_len != 64));
t4_set_reg_field(adap, SGE_CONTROL2_A,
INGPACKBOUNDARY_V(INGPACKBOUNDARY_M),
- INGPACKBOUNDARY_V(fl_align_log -
- INGPACKBOUNDARY_SHIFT_X));
+ INGPACKBOUNDARY_V(ingpack));
}
/*
* Adjust various SGE Free List Host Buffer Sizes.
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_values.h b/drivers/net/ethernet/chelsio/cxgb4/t4_values.h
index 36cf307..f6558cb 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_values.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_values.h
@@ -54,11 +54,15 @@
#define INGPADBOUNDARY_SHIFT_X 5
#define T6_INGPADBOUNDARY_SHIFT_X 3
+#define T6_INGPADBOUNDARY_8B_X 0
#define T6_INGPADBOUNDARY_32B_X 2
+#define INGPADBOUNDARY_32B_X 0
+
/* CONTROL2 register */
#define INGPACKBOUNDARY_SHIFT_X 5
#define INGPACKBOUNDARY_16B_X 0
+#define INGPACKBOUNDARY_64B_X 1
/* GTS register */
#define SGE_TIMERREGS 6
diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c
index 127ce970..91b8f6f 100644
--- a/drivers/net/ethernet/dec/tulip/de2104x.c
+++ b/drivers/net/ethernet/dec/tulip/de2104x.c
@@ -312,8 +312,6 @@ struct de_private {
u32 msg_enable;
- struct net_device_stats net_stats;
-
struct pci_dev *pdev;
u16 setup_frame[DE_SETUP_FRAME_WORDS];
@@ -388,14 +386,14 @@ static void de_rx_err_acct (struct de_private *de, unsigned rx_tail,
netif_warn(de, rx_err, de->dev,
"Oversized Ethernet frame spanned multiple buffers, status %08x!\n",
status);
- de->net_stats.rx_length_errors++;
+ de->dev->stats.rx_length_errors++;
}
} else if (status & RxError) {
/* There was a fatal error. */
- de->net_stats.rx_errors++; /* end of a packet.*/
- if (status & 0x0890) de->net_stats.rx_length_errors++;
- if (status & RxErrCRC) de->net_stats.rx_crc_errors++;
- if (status & RxErrFIFO) de->net_stats.rx_fifo_errors++;
+ de->dev->stats.rx_errors++; /* end of a packet.*/
+ if (status & 0x0890) de->dev->stats.rx_length_errors++;
+ if (status & RxErrCRC) de->dev->stats.rx_crc_errors++;
+ if (status & RxErrFIFO) de->dev->stats.rx_fifo_errors++;
}
}
@@ -423,7 +421,7 @@ static void de_rx (struct de_private *de)
mapping = de->rx_skb[rx_tail].mapping;
if (unlikely(drop)) {
- de->net_stats.rx_dropped++;
+ de->dev->stats.rx_dropped++;
goto rx_next;
}
@@ -441,7 +439,7 @@ static void de_rx (struct de_private *de)
buflen = copying_skb ? (len + RX_OFFSET) : de->rx_buf_sz;
copy_skb = netdev_alloc_skb(de->dev, buflen);
if (unlikely(!copy_skb)) {
- de->net_stats.rx_dropped++;
+ de->dev->stats.rx_dropped++;
drop = 1;
rx_work = 100;
goto rx_next;
@@ -470,8 +468,8 @@ static void de_rx (struct de_private *de)
skb->protocol = eth_type_trans (skb, de->dev);
- de->net_stats.rx_packets++;
- de->net_stats.rx_bytes += skb->len;
+ de->dev->stats.rx_packets++;
+ de->dev->stats.rx_bytes += skb->len;
rc = netif_rx (skb);
if (rc == NET_RX_DROP)
drop = 1;
@@ -572,18 +570,18 @@ static void de_tx (struct de_private *de)
netif_dbg(de, tx_err, de->dev,
"tx err, status 0x%x\n",
status);
- de->net_stats.tx_errors++;
+ de->dev->stats.tx_errors++;
if (status & TxOWC)
- de->net_stats.tx_window_errors++;
+ de->dev->stats.tx_window_errors++;
if (status & TxMaxCol)
- de->net_stats.tx_aborted_errors++;
+ de->dev->stats.tx_aborted_errors++;
if (status & TxLinkFail)
- de->net_stats.tx_carrier_errors++;
+ de->dev->stats.tx_carrier_errors++;
if (status & TxFIFOUnder)
- de->net_stats.tx_fifo_errors++;
+ de->dev->stats.tx_fifo_errors++;
} else {
- de->net_stats.tx_packets++;
- de->net_stats.tx_bytes += skb->len;
+ de->dev->stats.tx_packets++;
+ de->dev->stats.tx_bytes += skb->len;
netif_dbg(de, tx_done, de->dev,
"tx done, slot %d\n", tx_tail);
}
@@ -814,9 +812,9 @@ static void de_set_rx_mode (struct net_device *dev)
static inline void de_rx_missed(struct de_private *de, u32 rx_missed)
{
if (unlikely(rx_missed & RxMissedOver))
- de->net_stats.rx_missed_errors += RxMissedMask;
+ de->dev->stats.rx_missed_errors += RxMissedMask;
else
- de->net_stats.rx_missed_errors += (rx_missed & RxMissedMask);
+ de->dev->stats.rx_missed_errors += (rx_missed & RxMissedMask);
}
static void __de_get_stats(struct de_private *de)
@@ -836,7 +834,7 @@ static struct net_device_stats *de_get_stats(struct net_device *dev)
__de_get_stats(de);
spin_unlock_irq(&de->lock);
- return &de->net_stats;
+ return &dev->stats;
}
static inline int de_is_running (struct de_private *de)
@@ -1348,7 +1346,7 @@ static void de_clean_rings (struct de_private *de)
struct sk_buff *skb = de->tx_skb[i].skb;
if ((skb) && (skb != DE_DUMMY_SKB)) {
if (skb != DE_SETUP_SKB) {
- de->net_stats.tx_dropped++;
+ de->dev->stats.tx_dropped++;
pci_unmap_single(de->pdev,
de->tx_skb[i].mapping,
skb->len, PCI_DMA_TODEVICE);
diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c
index 1e35013..778f974 100644
--- a/drivers/net/ethernet/dlink/dl2k.c
+++ b/drivers/net/ethernet/dlink/dl2k.c
@@ -878,10 +878,10 @@ tx_error (struct net_device *dev, int tx_status)
frame_id = (tx_status & 0xffff0000);
printk (KERN_ERR "%s: Transmit error, TxStatus %4.4x, FrameId %d.\n",
dev->name, tx_status, frame_id);
- np->stats.tx_errors++;
+ dev->stats.tx_errors++;
/* Ttransmit Underrun */
if (tx_status & 0x10) {
- np->stats.tx_fifo_errors++;
+ dev->stats.tx_fifo_errors++;
dw16(TxStartThresh, dr16(TxStartThresh) + 0x10);
/* Transmit Underrun need to set TxReset, DMARest, FIFOReset */
dw16(ASICCtrl + 2,
@@ -903,7 +903,7 @@ tx_error (struct net_device *dev, int tx_status)
}
/* Late Collision */
if (tx_status & 0x04) {
- np->stats.tx_fifo_errors++;
+ dev->stats.tx_fifo_errors++;
/* TxReset and clear FIFO */
dw16(ASICCtrl + 2, TxReset | FIFOReset);
/* Wait reset done */
@@ -916,13 +916,8 @@ tx_error (struct net_device *dev, int tx_status)
/* Let TxStartThresh stay default value */
}
/* Maximum Collisions */
-#ifdef ETHER_STATS
if (tx_status & 0x08)
- np->stats.collisions16++;
-#else
- if (tx_status & 0x08)
- np->stats.collisions++;
-#endif
+ dev->stats.collisions++;
/* Restart the Tx */
dw32(MACCtrl, dr16(MACCtrl) | TxEnable);
}
@@ -952,15 +947,15 @@ receive_packet (struct net_device *dev)
break;
/* Update rx error statistics, drop packet. */
if (frame_status & RFS_Errors) {
- np->stats.rx_errors++;
+ dev->stats.rx_errors++;
if (frame_status & (RxRuntFrame | RxLengthError))
- np->stats.rx_length_errors++;
+ dev->stats.rx_length_errors++;
if (frame_status & RxFCSError)
- np->stats.rx_crc_errors++;
+ dev->stats.rx_crc_errors++;
if (frame_status & RxAlignmentError && np->speed != 1000)
- np->stats.rx_frame_errors++;
+ dev->stats.rx_frame_errors++;
if (frame_status & RxFIFOOverrun)
- np->stats.rx_fifo_errors++;
+ dev->stats.rx_fifo_errors++;
} else {
struct sk_buff *skb;
@@ -1096,23 +1091,23 @@ get_stats (struct net_device *dev)
/* All statistics registers need to be acknowledged,
else statistic overflow could cause problems */
- np->stats.rx_packets += dr32(FramesRcvOk);
- np->stats.tx_packets += dr32(FramesXmtOk);
- np->stats.rx_bytes += dr32(OctetRcvOk);
- np->stats.tx_bytes += dr32(OctetXmtOk);
+ dev->stats.rx_packets += dr32(FramesRcvOk);
+ dev->stats.tx_packets += dr32(FramesXmtOk);
+ dev->stats.rx_bytes += dr32(OctetRcvOk);
+ dev->stats.tx_bytes += dr32(OctetXmtOk);
- np->stats.multicast = dr32(McstFramesRcvdOk);
- np->stats.collisions += dr32(SingleColFrames)
+ dev->stats.multicast = dr32(McstFramesRcvdOk);
+ dev->stats.collisions += dr32(SingleColFrames)
+ dr32(MultiColFrames);
/* detailed tx errors */
stat_reg = dr16(FramesAbortXSColls);
- np->stats.tx_aborted_errors += stat_reg;
- np->stats.tx_errors += stat_reg;
+ dev->stats.tx_aborted_errors += stat_reg;
+ dev->stats.tx_errors += stat_reg;
stat_reg = dr16(CarrierSenseErrors);
- np->stats.tx_carrier_errors += stat_reg;
- np->stats.tx_errors += stat_reg;
+ dev->stats.tx_carrier_errors += stat_reg;
+ dev->stats.tx_errors += stat_reg;
/* Clear all other statistic register. */
dr32(McstOctetXmtOk);
@@ -1142,7 +1137,7 @@ get_stats (struct net_device *dev)
dr16(TCPCheckSumErrors);
dr16(UDPCheckSumErrors);
dr16(IPCheckSumErrors);
- return &np->stats;
+ return &dev->stats;
}
static int
diff --git a/drivers/net/ethernet/dlink/dl2k.h b/drivers/net/ethernet/dlink/dl2k.h
index 5d8ae53..10e98ba 100644
--- a/drivers/net/ethernet/dlink/dl2k.h
+++ b/drivers/net/ethernet/dlink/dl2k.h
@@ -377,7 +377,6 @@ struct netdev_private {
void __iomem *eeprom_addr;
spinlock_t tx_lock;
spinlock_t rx_lock;
- struct net_device_stats stats;
unsigned int rx_buf_sz; /* Based on MTU+slack. */
unsigned int speed; /* Operating speed */
unsigned int vlan; /* VLAN Id */
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 30e8550..02dd524 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -4939,8 +4939,9 @@ static int
__be_cmd_set_logical_link_config(struct be_adapter *adapter,
int link_state, int version, u8 domain)
{
- struct be_mcc_wrb *wrb;
struct be_cmd_req_set_ll_link *req;
+ struct be_mcc_wrb *wrb;
+ u32 link_config = 0;
int status;
mutex_lock(&adapter->mcc_lock);
@@ -4962,10 +4963,12 @@ __be_cmd_set_logical_link_config(struct be_adapter *adapter,
if (link_state == IFLA_VF_LINK_STATE_ENABLE ||
link_state == IFLA_VF_LINK_STATE_AUTO)
- req->link_config |= PLINK_ENABLE;
+ link_config |= PLINK_ENABLE;
if (link_state == IFLA_VF_LINK_STATE_AUTO)
- req->link_config |= PLINK_TRACK;
+ link_config |= PLINK_TRACK;
+
+ req->link_config = cpu_to_le32(link_config);
status = be_mcc_notify_wait(adapter);
err:
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index 23d8274..e863ba7 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -1148,14 +1148,14 @@ static int ethoc_probe(struct platform_device *pdev)
/* Allow the platform setup code to pass in a MAC address. */
if (pdata) {
- memcpy(netdev->dev_addr, pdata->hwaddr, IFHWADDRLEN);
+ ether_addr_copy(netdev->dev_addr, pdata->hwaddr);
priv->phy_id = pdata->phy_id;
} else {
const void *mac;
mac = of_get_mac_address(pdev->dev.of_node);
if (mac)
- memcpy(netdev->dev_addr, mac, IFHWADDRLEN);
+ ether_addr_copy(netdev->dev_addr, mac);
priv->phy_id = -1;
}
diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c
index 992ebe9..659f1ad 100644
--- a/drivers/net/ethernet/ezchip/nps_enet.c
+++ b/drivers/net/ethernet/ezchip/nps_enet.c
@@ -16,6 +16,7 @@
#include <linux/module.h>
#include <linux/etherdevice.h>
+#include <linux/interrupt.h>
#include <linux/of_address.h>
#include <linux/of_irq.h>
#include <linux/of_net.h>
@@ -189,11 +190,9 @@ static int nps_enet_poll(struct napi_struct *napi, int budget)
nps_enet_tx_handler(ndev);
work_done = nps_enet_rx_handler(ndev);
- if (work_done < budget) {
+ if ((work_done < budget) && napi_complete_done(napi, work_done)) {
u32 buf_int_enable_value = 0;
- napi_complete_done(napi, work_done);
-
/* set tx_done and rx_rdy bits */
buf_int_enable_value |= NPS_ENET_ENABLE << RX_RDY_SHIFT;
buf_int_enable_value |= NPS_ENET_ENABLE << TX_DONE_SHIFT;
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index 928b0df..8447987 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -28,8 +28,10 @@
#include <linux/io.h>
#include <linux/module.h>
#include <linux/netdevice.h>
+#include <linux/of.h>
#include <linux/phy.h>
#include <linux/platform_device.h>
+#include <linux/property.h>
#include <net/ip.h>
#include <net/ncsi.h>
@@ -41,55 +43,55 @@
#define RX_QUEUE_ENTRIES 256 /* must be power of 2 */
#define TX_QUEUE_ENTRIES 512 /* must be power of 2 */
-#define MAX_PKT_SIZE 1518
-#define RX_BUF_SIZE PAGE_SIZE /* must be smaller than 0x3fff */
+#define MAX_PKT_SIZE 1536
+#define RX_BUF_SIZE MAX_PKT_SIZE /* must be smaller than 0x3fff */
-/******************************************************************************
- * private data
- *****************************************************************************/
struct ftgmac100_descs {
struct ftgmac100_rxdes rxdes[RX_QUEUE_ENTRIES];
struct ftgmac100_txdes txdes[TX_QUEUE_ENTRIES];
};
struct ftgmac100 {
+ /* Registers */
struct resource *res;
void __iomem *base;
- int irq;
struct ftgmac100_descs *descs;
dma_addr_t descs_dma_addr;
- struct page *rx_pages[RX_QUEUE_ENTRIES];
-
+ /* Rx ring */
+ struct sk_buff *rx_skbs[RX_QUEUE_ENTRIES];
unsigned int rx_pointer;
+ u32 rxdes0_edorr_mask;
+
+ /* Tx ring */
unsigned int tx_clean_pointer;
unsigned int tx_pointer;
unsigned int tx_pending;
-
+ u32 txdes0_edotr_mask;
spinlock_t tx_lock;
+ /* Scratch page to use when rx skb alloc fails */
+ void *rx_scratch;
+ dma_addr_t rx_scratch_dma;
+
+ /* Component structures */
struct net_device *netdev;
struct device *dev;
struct ncsi_dev *ndev;
struct napi_struct napi;
-
+ struct work_struct reset_task;
struct mii_bus *mii_bus;
- int old_speed;
- int int_mask_all;
- bool use_ncsi;
- bool enabled;
- u32 rxdes0_edorr_mask;
- u32 txdes0_edotr_mask;
+ /* Link management */
+ int cur_speed;
+ int cur_duplex;
+ bool use_ncsi;
+
+ /* Misc */
+ bool need_mac_restart;
};
-static int ftgmac100_alloc_rx_page(struct ftgmac100 *priv,
- struct ftgmac100_rxdes *rxdes, gfp_t gfp);
-
-/******************************************************************************
- * internal functions (hardware register access)
- *****************************************************************************/
static void ftgmac100_set_rx_ring_base(struct ftgmac100 *priv, dma_addr_t addr)
{
iowrite32(addr, priv->base + FTGMAC100_OFFSET_RXR_BADR);
@@ -113,27 +115,64 @@ static void ftgmac100_txdma_normal_prio_start_polling(struct ftgmac100 *priv)
iowrite32(1, priv->base + FTGMAC100_OFFSET_NPTXPD);
}
-static int ftgmac100_reset_hw(struct ftgmac100 *priv)
+static int ftgmac100_reset_mac(struct ftgmac100 *priv, u32 maccr)
{
struct net_device *netdev = priv->netdev;
int i;
/* NOTE: reset clears all registers */
- iowrite32(FTGMAC100_MACCR_SW_RST, priv->base + FTGMAC100_OFFSET_MACCR);
- for (i = 0; i < 5; i++) {
+ iowrite32(maccr, priv->base + FTGMAC100_OFFSET_MACCR);
+ iowrite32(maccr | FTGMAC100_MACCR_SW_RST,
+ priv->base + FTGMAC100_OFFSET_MACCR);
+ for (i = 0; i < 50; i++) {
unsigned int maccr;
maccr = ioread32(priv->base + FTGMAC100_OFFSET_MACCR);
if (!(maccr & FTGMAC100_MACCR_SW_RST))
return 0;
- udelay(1000);
+ udelay(1);
}
- netdev_err(netdev, "software reset failed\n");
+ netdev_err(netdev, "Hardware reset failed\n");
return -EIO;
}
+static int ftgmac100_reset_and_config_mac(struct ftgmac100 *priv)
+{
+ u32 maccr = 0;
+
+ switch (priv->cur_speed) {
+ case SPEED_10:
+ case 0: /* no link */
+ break;
+
+ case SPEED_100:
+ maccr |= FTGMAC100_MACCR_FAST_MODE;
+ break;
+
+ case SPEED_1000:
+ maccr |= FTGMAC100_MACCR_GIGA_MODE;
+ break;
+ default:
+ netdev_err(priv->netdev, "Unknown speed %d !\n",
+ priv->cur_speed);
+ break;
+ }
+
+ /* (Re)initialize the queue pointers */
+ priv->rx_pointer = 0;
+ priv->tx_clean_pointer = 0;
+ priv->tx_pointer = 0;
+ priv->tx_pending = 0;
+
+ /* The doc says reset twice with 10us interval */
+ if (ftgmac100_reset_mac(priv, maccr))
+ return -EIO;
+ usleep_range(10, 1000);
+ return ftgmac100_reset_mac(priv, maccr);
+}
+
static void ftgmac100_set_mac(struct ftgmac100 *priv, const unsigned char *mac)
{
unsigned int maddr = mac[0] << 8 | mac[1];
@@ -209,33 +248,28 @@ static void ftgmac100_init_hw(struct ftgmac100 *priv)
ftgmac100_set_mac(priv, priv->netdev->dev_addr);
}
-#define MACCR_ENABLE_ALL (FTGMAC100_MACCR_TXDMA_EN | \
- FTGMAC100_MACCR_RXDMA_EN | \
- FTGMAC100_MACCR_TXMAC_EN | \
- FTGMAC100_MACCR_RXMAC_EN | \
- FTGMAC100_MACCR_FULLDUP | \
- FTGMAC100_MACCR_CRC_APD | \
- FTGMAC100_MACCR_RX_RUNT | \
- FTGMAC100_MACCR_RX_BROADPKT)
-
-static void ftgmac100_start_hw(struct ftgmac100 *priv, int speed)
+static void ftgmac100_start_hw(struct ftgmac100 *priv)
{
- int maccr = MACCR_ENABLE_ALL;
+ u32 maccr = ioread32(priv->base + FTGMAC100_OFFSET_MACCR);
- switch (speed) {
- default:
- case 10:
- break;
+ /* Keep the original GMAC and FAST bits */
+ maccr &= (FTGMAC100_MACCR_FAST_MODE | FTGMAC100_MACCR_GIGA_MODE);
- case 100:
- maccr |= FTGMAC100_MACCR_FAST_MODE;
- break;
+ /* Add all the main enable bits */
+ maccr |= FTGMAC100_MACCR_TXDMA_EN |
+ FTGMAC100_MACCR_RXDMA_EN |
+ FTGMAC100_MACCR_TXMAC_EN |
+ FTGMAC100_MACCR_RXMAC_EN |
+ FTGMAC100_MACCR_CRC_APD |
+ FTGMAC100_MACCR_PHY_LINK_LEVEL |
+ FTGMAC100_MACCR_RX_RUNT |
+ FTGMAC100_MACCR_RX_BROADPKT;
- case 1000:
- maccr |= FTGMAC100_MACCR_GIGA_MODE;
- break;
- }
+ /* Add other bits as needed */
+ if (priv->cur_duplex == DUPLEX_FULL)
+ maccr |= FTGMAC100_MACCR_FULLDUP;
+ /* Hit the HW */
iowrite32(maccr, priv->base + FTGMAC100_OFFSET_MACCR);
}
@@ -244,237 +278,70 @@ static void ftgmac100_stop_hw(struct ftgmac100 *priv)
iowrite32(0, priv->base + FTGMAC100_OFFSET_MACCR);
}
-/******************************************************************************
- * internal functions (receive descriptor)
- *****************************************************************************/
-static bool ftgmac100_rxdes_first_segment(struct ftgmac100_rxdes *rxdes)
+static int ftgmac100_alloc_rx_buf(struct ftgmac100 *priv, unsigned int entry,
+ struct ftgmac100_rxdes *rxdes, gfp_t gfp)
{
- return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_FRS);
+ struct net_device *netdev = priv->netdev;
+ struct sk_buff *skb;
+ dma_addr_t map;
+ int err;
+
+ skb = netdev_alloc_skb_ip_align(netdev, RX_BUF_SIZE);
+ if (unlikely(!skb)) {
+ if (net_ratelimit())
+ netdev_warn(netdev, "failed to allocate rx skb\n");
+ err = -ENOMEM;
+ map = priv->rx_scratch_dma;
+ } else {
+ map = dma_map_single(priv->dev, skb->data, RX_BUF_SIZE,
+ DMA_FROM_DEVICE);
+ if (unlikely(dma_mapping_error(priv->dev, map))) {
+ if (net_ratelimit())
+ netdev_err(netdev, "failed to map rx page\n");
+ dev_kfree_skb_any(skb);
+ map = priv->rx_scratch_dma;
+ skb = NULL;
+ err = -ENOMEM;
+ }
+ }
+
+ /* Store skb */
+ priv->rx_skbs[entry] = skb;
+
+ /* Store DMA address into RX desc */
+ rxdes->rxdes3 = cpu_to_le32(map);
+
+ /* Ensure the above is ordered vs clearing the OWN bit */
+ dma_wmb();
+
+ /* Clean status (which resets own bit) */
+ if (entry == (RX_QUEUE_ENTRIES - 1))
+ rxdes->rxdes0 = cpu_to_le32(priv->rxdes0_edorr_mask);
+ else
+ rxdes->rxdes0 = 0;
+
+ return 0;
}
-static bool ftgmac100_rxdes_last_segment(struct ftgmac100_rxdes *rxdes)
-{
- return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_LRS);
-}
-
-static bool ftgmac100_rxdes_packet_ready(struct ftgmac100_rxdes *rxdes)
-{
- return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_RXPKT_RDY);
-}
-
-static void ftgmac100_rxdes_set_dma_own(const struct ftgmac100 *priv,
- struct ftgmac100_rxdes *rxdes)
-{
- /* clear status bits */
- rxdes->rxdes0 &= cpu_to_le32(priv->rxdes0_edorr_mask);
-}
-
-static bool ftgmac100_rxdes_rx_error(struct ftgmac100_rxdes *rxdes)
-{
- return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_RX_ERR);
-}
-
-static bool ftgmac100_rxdes_crc_error(struct ftgmac100_rxdes *rxdes)
-{
- return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_CRC_ERR);
-}
-
-static bool ftgmac100_rxdes_frame_too_long(struct ftgmac100_rxdes *rxdes)
-{
- return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_FTL);
-}
-
-static bool ftgmac100_rxdes_runt(struct ftgmac100_rxdes *rxdes)
-{
- return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_RUNT);
-}
-
-static bool ftgmac100_rxdes_odd_nibble(struct ftgmac100_rxdes *rxdes)
-{
- return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_RX_ODD_NB);
-}
-
-static unsigned int ftgmac100_rxdes_data_length(struct ftgmac100_rxdes *rxdes)
-{
- return le32_to_cpu(rxdes->rxdes0) & FTGMAC100_RXDES0_VDBC;
-}
-
-static bool ftgmac100_rxdes_multicast(struct ftgmac100_rxdes *rxdes)
-{
- return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_MULTICAST);
-}
-
-static void ftgmac100_rxdes_set_end_of_ring(const struct ftgmac100 *priv,
- struct ftgmac100_rxdes *rxdes)
-{
- rxdes->rxdes0 |= cpu_to_le32(priv->rxdes0_edorr_mask);
-}
-
-static void ftgmac100_rxdes_set_dma_addr(struct ftgmac100_rxdes *rxdes,
- dma_addr_t addr)
-{
- rxdes->rxdes3 = cpu_to_le32(addr);
-}
-
-static dma_addr_t ftgmac100_rxdes_get_dma_addr(struct ftgmac100_rxdes *rxdes)
-{
- return le32_to_cpu(rxdes->rxdes3);
-}
-
-static bool ftgmac100_rxdes_is_tcp(struct ftgmac100_rxdes *rxdes)
-{
- return (rxdes->rxdes1 & cpu_to_le32(FTGMAC100_RXDES1_PROT_MASK)) ==
- cpu_to_le32(FTGMAC100_RXDES1_PROT_TCPIP);
-}
-
-static bool ftgmac100_rxdes_is_udp(struct ftgmac100_rxdes *rxdes)
-{
- return (rxdes->rxdes1 & cpu_to_le32(FTGMAC100_RXDES1_PROT_MASK)) ==
- cpu_to_le32(FTGMAC100_RXDES1_PROT_UDPIP);
-}
-
-static bool ftgmac100_rxdes_tcpcs_err(struct ftgmac100_rxdes *rxdes)
-{
- return rxdes->rxdes1 & cpu_to_le32(FTGMAC100_RXDES1_TCP_CHKSUM_ERR);
-}
-
-static bool ftgmac100_rxdes_udpcs_err(struct ftgmac100_rxdes *rxdes)
-{
- return rxdes->rxdes1 & cpu_to_le32(FTGMAC100_RXDES1_UDP_CHKSUM_ERR);
-}
-
-static bool ftgmac100_rxdes_ipcs_err(struct ftgmac100_rxdes *rxdes)
-{
- return rxdes->rxdes1 & cpu_to_le32(FTGMAC100_RXDES1_IP_CHKSUM_ERR);
-}
-
-static inline struct page **ftgmac100_rxdes_page_slot(struct ftgmac100 *priv,
- struct ftgmac100_rxdes *rxdes)
-{
- return &priv->rx_pages[rxdes - priv->descs->rxdes];
-}
-
-/*
- * rxdes2 is not used by hardware. We use it to keep track of page.
- * Since hardware does not touch it, we can skip cpu_to_le32()/le32_to_cpu().
- */
-static void ftgmac100_rxdes_set_page(struct ftgmac100 *priv,
- struct ftgmac100_rxdes *rxdes,
- struct page *page)
-{
- *ftgmac100_rxdes_page_slot(priv, rxdes) = page;
-}
-
-static struct page *ftgmac100_rxdes_get_page(struct ftgmac100 *priv,
- struct ftgmac100_rxdes *rxdes)
-{
- return *ftgmac100_rxdes_page_slot(priv, rxdes);
-}
-
-/******************************************************************************
- * internal functions (receive)
- *****************************************************************************/
static int ftgmac100_next_rx_pointer(int pointer)
{
return (pointer + 1) & (RX_QUEUE_ENTRIES - 1);
}
-static void ftgmac100_rx_pointer_advance(struct ftgmac100 *priv)
-{
- priv->rx_pointer = ftgmac100_next_rx_pointer(priv->rx_pointer);
-}
-
-static struct ftgmac100_rxdes *ftgmac100_current_rxdes(struct ftgmac100 *priv)
-{
- return &priv->descs->rxdes[priv->rx_pointer];
-}
-
-static struct ftgmac100_rxdes *
-ftgmac100_rx_locate_first_segment(struct ftgmac100 *priv)
-{
- struct ftgmac100_rxdes *rxdes = ftgmac100_current_rxdes(priv);
-
- while (ftgmac100_rxdes_packet_ready(rxdes)) {
- if (ftgmac100_rxdes_first_segment(rxdes))
- return rxdes;
-
- ftgmac100_rxdes_set_dma_own(priv, rxdes);
- ftgmac100_rx_pointer_advance(priv);
- rxdes = ftgmac100_current_rxdes(priv);
- }
-
- return NULL;
-}
-
-static bool ftgmac100_rx_packet_error(struct ftgmac100 *priv,
- struct ftgmac100_rxdes *rxdes)
+static void ftgmac100_rx_packet_error(struct ftgmac100 *priv, u32 status)
{
struct net_device *netdev = priv->netdev;
- bool error = false;
- if (unlikely(ftgmac100_rxdes_rx_error(rxdes))) {
- if (net_ratelimit())
- netdev_info(netdev, "rx err\n");
-
+ if (status & FTGMAC100_RXDES0_RX_ERR)
netdev->stats.rx_errors++;
- error = true;
- }
- if (unlikely(ftgmac100_rxdes_crc_error(rxdes))) {
- if (net_ratelimit())
- netdev_info(netdev, "rx crc err\n");
-
+ if (status & FTGMAC100_RXDES0_CRC_ERR)
netdev->stats.rx_crc_errors++;
- error = true;
- } else if (unlikely(ftgmac100_rxdes_ipcs_err(rxdes))) {
- if (net_ratelimit())
- netdev_info(netdev, "rx IP checksum err\n");
- error = true;
- }
-
- if (unlikely(ftgmac100_rxdes_frame_too_long(rxdes))) {
- if (net_ratelimit())
- netdev_info(netdev, "rx frame too long\n");
-
+ if (status & (FTGMAC100_RXDES0_FTL |
+ FTGMAC100_RXDES0_RUNT |
+ FTGMAC100_RXDES0_RX_ODD_NB))
netdev->stats.rx_length_errors++;
- error = true;
- } else if (unlikely(ftgmac100_rxdes_runt(rxdes))) {
- if (net_ratelimit())
- netdev_info(netdev, "rx runt\n");
-
- netdev->stats.rx_length_errors++;
- error = true;
- } else if (unlikely(ftgmac100_rxdes_odd_nibble(rxdes))) {
- if (net_ratelimit())
- netdev_info(netdev, "rx odd nibble\n");
-
- netdev->stats.rx_length_errors++;
- error = true;
- }
-
- return error;
-}
-
-static void ftgmac100_rx_drop_packet(struct ftgmac100 *priv)
-{
- struct net_device *netdev = priv->netdev;
- struct ftgmac100_rxdes *rxdes = ftgmac100_current_rxdes(priv);
- bool done = false;
-
- if (net_ratelimit())
- netdev_dbg(netdev, "drop packet %p\n", rxdes);
-
- do {
- if (ftgmac100_rxdes_last_segment(rxdes))
- done = true;
-
- ftgmac100_rxdes_set_dma_own(priv, rxdes);
- ftgmac100_rx_pointer_advance(priv);
- rxdes = ftgmac100_current_rxdes(priv);
- } while (!done && ftgmac100_rxdes_packet_ready(rxdes));
-
- netdev->stats.rx_dropped++;
}
static bool ftgmac100_rx_packet(struct ftgmac100 *priv, int *processed)
@@ -482,85 +349,124 @@ static bool ftgmac100_rx_packet(struct ftgmac100 *priv, int *processed)
struct net_device *netdev = priv->netdev;
struct ftgmac100_rxdes *rxdes;
struct sk_buff *skb;
- bool done = false;
+ unsigned int pointer, size;
+ u32 status, csum_vlan;
+ dma_addr_t map;
- rxdes = ftgmac100_rx_locate_first_segment(priv);
- if (!rxdes)
+ /* Grab next RX descriptor */
+ pointer = priv->rx_pointer;
+ rxdes = &priv->descs->rxdes[pointer];
+
+ /* Grab descriptor status */
+ status = le32_to_cpu(rxdes->rxdes0);
+
+ /* Do we have a packet ? */
+ if (!(status & FTGMAC100_RXDES0_RXPKT_RDY))
return false;
- if (unlikely(ftgmac100_rx_packet_error(priv, rxdes))) {
- ftgmac100_rx_drop_packet(priv);
- return true;
+ /* Order subsequent reads with the test for the ready bit */
+ dma_rmb();
+
+ /* We don't cope with fragmented RX packets */
+ if (unlikely(!(status & FTGMAC100_RXDES0_FRS) ||
+ !(status & FTGMAC100_RXDES0_LRS)))
+ goto drop;
+
+ /* Grab received size and csum vlan field in the descriptor */
+ size = status & FTGMAC100_RXDES0_VDBC;
+ csum_vlan = le32_to_cpu(rxdes->rxdes1);
+
+ /* Any error (other than csum offload) flagged ? */
+ if (unlikely(status & RXDES0_ANY_ERROR)) {
+ /* Correct for incorrect flagging of runt packets
+ * with vlan tags... Just accept a runt packet that
+ * has been flagged as vlan and whose size is at
+ * least 60 bytes.
+ */
+ if ((status & FTGMAC100_RXDES0_RUNT) &&
+ (csum_vlan & FTGMAC100_RXDES1_VLANTAG_AVAIL) &&
+ (size >= 60))
+ status &= ~FTGMAC100_RXDES0_RUNT;
+
+ /* Any error still in there ? */
+ if (status & RXDES0_ANY_ERROR) {
+ ftgmac100_rx_packet_error(priv, status);
+ goto drop;
+ }
}
- /* start processing */
- skb = netdev_alloc_skb_ip_align(netdev, 128);
- if (unlikely(!skb)) {
- if (net_ratelimit())
- netdev_err(netdev, "rx skb alloc failed\n");
-
- ftgmac100_rx_drop_packet(priv);
- return true;
+ /* If the packet had no skb (failed to allocate earlier)
+ * then try to allocate one and skip
+ */
+ skb = priv->rx_skbs[pointer];
+ if (!unlikely(skb)) {
+ ftgmac100_alloc_rx_buf(priv, pointer, rxdes, GFP_ATOMIC);
+ goto drop;
}
- if (unlikely(ftgmac100_rxdes_multicast(rxdes)))
+ if (unlikely(status & FTGMAC100_RXDES0_MULTICAST))
netdev->stats.multicast++;
- /*
- * It seems that HW does checksum incorrectly with fragmented packets,
- * so we are conservative here - if HW checksum error, let software do
- * the checksum again.
+ /* If the HW found checksum errors, bounce it to software.
+ *
+ * If we didn't, we need to see if the packet was recognized
+ * by HW as one of the supported checksummed protocols before
+ * we accept the HW test results.
*/
- if ((ftgmac100_rxdes_is_tcp(rxdes) && !ftgmac100_rxdes_tcpcs_err(rxdes)) ||
- (ftgmac100_rxdes_is_udp(rxdes) && !ftgmac100_rxdes_udpcs_err(rxdes)))
- skb->ip_summed = CHECKSUM_UNNECESSARY;
-
- do {
- dma_addr_t map = ftgmac100_rxdes_get_dma_addr(rxdes);
- struct page *page = ftgmac100_rxdes_get_page(priv, rxdes);
- unsigned int size;
-
- dma_unmap_page(priv->dev, map, RX_BUF_SIZE, DMA_FROM_DEVICE);
-
- size = ftgmac100_rxdes_data_length(rxdes);
- skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags, page, 0, size);
-
- skb->len += size;
- skb->data_len += size;
- skb->truesize += PAGE_SIZE;
-
- if (ftgmac100_rxdes_last_segment(rxdes))
- done = true;
-
- ftgmac100_alloc_rx_page(priv, rxdes, GFP_ATOMIC);
-
- ftgmac100_rx_pointer_advance(priv);
- rxdes = ftgmac100_current_rxdes(priv);
- } while (!done);
-
- /* Small frames are copied into linear part of skb to free one page */
- if (skb->len <= 128) {
- skb->truesize -= PAGE_SIZE;
- __pskb_pull_tail(skb, skb->len);
- } else {
- /* We pull the minimum amount into linear part */
- __pskb_pull_tail(skb, ETH_HLEN);
+ if (netdev->features & NETIF_F_RXCSUM) {
+ u32 err_bits = FTGMAC100_RXDES1_TCP_CHKSUM_ERR |
+ FTGMAC100_RXDES1_UDP_CHKSUM_ERR |
+ FTGMAC100_RXDES1_IP_CHKSUM_ERR;
+ if ((csum_vlan & err_bits) ||
+ !(csum_vlan & FTGMAC100_RXDES1_PROT_MASK))
+ skb->ip_summed = CHECKSUM_NONE;
+ else
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
}
+
+ /* Transfer received size to skb */
+ skb_put(skb, size);
+
+ /* Tear down DMA mapping, do necessary cache management */
+ map = le32_to_cpu(rxdes->rxdes3);
+
+#if defined(CONFIG_ARM) && !defined(CONFIG_ARM_DMA_USE_IOMMU)
+ /* When we don't have an iommu, we can save cycles by not
+ * invalidating the cache for the part of the packet that
+ * wasn't received.
+ */
+ dma_unmap_single(priv->dev, map, size, DMA_FROM_DEVICE);
+#else
+ dma_unmap_single(priv->dev, map, RX_BUF_SIZE, DMA_FROM_DEVICE);
+#endif
+
+
+ /* Resplenish rx ring */
+ ftgmac100_alloc_rx_buf(priv, pointer, rxdes, GFP_ATOMIC);
+ priv->rx_pointer = ftgmac100_next_rx_pointer(pointer);
+
skb->protocol = eth_type_trans(skb, netdev);
netdev->stats.rx_packets++;
- netdev->stats.rx_bytes += skb->len;
+ netdev->stats.rx_bytes += size;
/* push packet to protocol stack */
- napi_gro_receive(&priv->napi, skb);
+ if (skb->ip_summed == CHECKSUM_NONE)
+ netif_receive_skb(skb);
+ else
+ napi_gro_receive(&priv->napi, skb);
(*processed)++;
return true;
+
+ drop:
+ /* Clean rxdes0 (which resets own bit) */
+ rxdes->rxdes0 = cpu_to_le32(status & priv->rxdes0_edorr_mask);
+ priv->rx_pointer = ftgmac100_next_rx_pointer(pointer);
+ netdev->stats.rx_dropped++;
+ return true;
}
-/******************************************************************************
- * internal functions (transmit descriptor)
- *****************************************************************************/
static void ftgmac100_txdes_reset(const struct ftgmac100 *priv,
struct ftgmac100_txdes *txdes)
{
@@ -654,9 +560,6 @@ static struct sk_buff *ftgmac100_txdes_get_skb(struct ftgmac100_txdes *txdes)
return (struct sk_buff *)txdes->txdes2;
}
-/******************************************************************************
- * internal functions (transmit)
- *****************************************************************************/
static int ftgmac100_next_tx_pointer(int pointer)
{
return (pointer + 1) & (TX_QUEUE_ENTRIES - 1);
@@ -772,53 +675,25 @@ static int ftgmac100_xmit(struct ftgmac100 *priv, struct sk_buff *skb,
return NETDEV_TX_OK;
}
-/******************************************************************************
- * internal functions (buffer)
- *****************************************************************************/
-static int ftgmac100_alloc_rx_page(struct ftgmac100 *priv,
- struct ftgmac100_rxdes *rxdes, gfp_t gfp)
-{
- struct net_device *netdev = priv->netdev;
- struct page *page;
- dma_addr_t map;
-
- page = alloc_page(gfp);
- if (!page) {
- if (net_ratelimit())
- netdev_err(netdev, "failed to allocate rx page\n");
- return -ENOMEM;
- }
-
- map = dma_map_page(priv->dev, page, 0, RX_BUF_SIZE, DMA_FROM_DEVICE);
- if (unlikely(dma_mapping_error(priv->dev, map))) {
- if (net_ratelimit())
- netdev_err(netdev, "failed to map rx page\n");
- __free_page(page);
- return -ENOMEM;
- }
-
- ftgmac100_rxdes_set_page(priv, rxdes, page);
- ftgmac100_rxdes_set_dma_addr(rxdes, map);
- ftgmac100_rxdes_set_dma_own(priv, rxdes);
- return 0;
-}
-
static void ftgmac100_free_buffers(struct ftgmac100 *priv)
{
int i;
+ /* Free all RX buffers */
for (i = 0; i < RX_QUEUE_ENTRIES; i++) {
struct ftgmac100_rxdes *rxdes = &priv->descs->rxdes[i];
- struct page *page = ftgmac100_rxdes_get_page(priv, rxdes);
- dma_addr_t map = ftgmac100_rxdes_get_dma_addr(rxdes);
+ struct sk_buff *skb = priv->rx_skbs[i];
+ dma_addr_t map = le32_to_cpu(rxdes->rxdes3);
- if (!page)
+ if (!skb)
continue;
- dma_unmap_page(priv->dev, map, RX_BUF_SIZE, DMA_FROM_DEVICE);
- __free_page(page);
+ priv->rx_skbs[i] = NULL;
+ dma_unmap_single(priv->dev, map, RX_BUF_SIZE, DMA_FROM_DEVICE);
+ dev_kfree_skb_any(skb);
}
+ /* Free all TX buffers */
for (i = 0; i < TX_QUEUE_ENTRIES; i++) {
struct ftgmac100_txdes *txdes = &priv->descs->txdes[i];
struct sk_buff *skb = ftgmac100_txdes_get_skb(txdes);
@@ -830,70 +705,108 @@ static void ftgmac100_free_buffers(struct ftgmac100 *priv)
dma_unmap_single(priv->dev, map, skb_headlen(skb), DMA_TO_DEVICE);
kfree_skb(skb);
}
-
- dma_free_coherent(priv->dev, sizeof(struct ftgmac100_descs),
- priv->descs, priv->descs_dma_addr);
}
-static int ftgmac100_alloc_buffers(struct ftgmac100 *priv)
+static void ftgmac100_free_rings(struct ftgmac100 *priv)
{
- int i;
+ /* Free descriptors */
+ if (priv->descs)
+ dma_free_coherent(priv->dev, sizeof(struct ftgmac100_descs),
+ priv->descs, priv->descs_dma_addr);
+ /* Free scratch packet buffer */
+ if (priv->rx_scratch)
+ dma_free_coherent(priv->dev, RX_BUF_SIZE,
+ priv->rx_scratch, priv->rx_scratch_dma);
+}
+
+static int ftgmac100_alloc_rings(struct ftgmac100 *priv)
+{
+ /* Allocate descriptors */
priv->descs = dma_zalloc_coherent(priv->dev,
sizeof(struct ftgmac100_descs),
&priv->descs_dma_addr, GFP_KERNEL);
if (!priv->descs)
return -ENOMEM;
- /* initialize RX ring */
- ftgmac100_rxdes_set_end_of_ring(priv,
- &priv->descs->rxdes[RX_QUEUE_ENTRIES - 1]);
+ /* Allocate scratch packet buffer */
+ priv->rx_scratch = dma_alloc_coherent(priv->dev,
+ RX_BUF_SIZE,
+ &priv->rx_scratch_dma,
+ GFP_KERNEL);
+ if (!priv->rx_scratch)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void ftgmac100_init_rings(struct ftgmac100 *priv)
+{
+ struct ftgmac100_rxdes *rxdes;
+ int i;
+
+ /* Initialize RX ring */
+ for (i = 0; i < RX_QUEUE_ENTRIES; i++) {
+ rxdes = &priv->descs->rxdes[i];
+ rxdes->rxdes0 = 0;
+ rxdes->rxdes3 = cpu_to_le32(priv->rx_scratch_dma);
+ }
+ /* Mark the end of the ring */
+ rxdes->rxdes0 |= cpu_to_le32(priv->rxdes0_edorr_mask);
+
+ /* Initialize TX ring */
+ for (i = 0; i < TX_QUEUE_ENTRIES; i++)
+ priv->descs->txdes[i].txdes0 = 0;
+ ftgmac100_txdes_set_end_of_ring(priv, &priv->descs->txdes[i -1]);
+}
+
+static int ftgmac100_alloc_rx_buffers(struct ftgmac100 *priv)
+{
+ int i;
for (i = 0; i < RX_QUEUE_ENTRIES; i++) {
struct ftgmac100_rxdes *rxdes = &priv->descs->rxdes[i];
- if (ftgmac100_alloc_rx_page(priv, rxdes, GFP_KERNEL))
- goto err;
+ if (ftgmac100_alloc_rx_buf(priv, i, rxdes, GFP_KERNEL))
+ return -ENOMEM;
}
-
- /* initialize TX ring */
- ftgmac100_txdes_set_end_of_ring(priv,
- &priv->descs->txdes[TX_QUEUE_ENTRIES - 1]);
return 0;
-
-err:
- ftgmac100_free_buffers(priv);
- return -ENOMEM;
}
-/******************************************************************************
- * internal functions (mdio)
- *****************************************************************************/
static void ftgmac100_adjust_link(struct net_device *netdev)
{
struct ftgmac100 *priv = netdev_priv(netdev);
struct phy_device *phydev = netdev->phydev;
- int ier;
+ int new_speed;
- if (phydev->speed == priv->old_speed)
+ /* We store "no link" as speed 0 */
+ if (!phydev->link)
+ new_speed = 0;
+ else
+ new_speed = phydev->speed;
+
+ if (phydev->speed == priv->cur_speed &&
+ phydev->duplex == priv->cur_duplex)
return;
- priv->old_speed = phydev->speed;
+ /* Print status if we have a link or we had one and just lost it,
+ * don't print otherwise.
+ */
+ if (new_speed || priv->cur_speed)
+ phy_print_status(phydev);
- ier = ioread32(priv->base + FTGMAC100_OFFSET_IER);
+ priv->cur_speed = new_speed;
+ priv->cur_duplex = phydev->duplex;
- /* disable all interrupts */
+ /* Link is down, do nothing else */
+ if (!new_speed)
+ return;
+
+ /* Disable all interrupts */
iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);
- netif_stop_queue(netdev);
- ftgmac100_stop_hw(priv);
-
- netif_start_queue(netdev);
- ftgmac100_init_hw(priv);
- ftgmac100_start_hw(priv, phydev->speed);
-
- /* re-enable interrupts */
- iowrite32(ier, priv->base + FTGMAC100_OFFSET_IER);
+ /* Reset the adapter asynchronously */
+ schedule_work(&priv->reset_task);
}
static int ftgmac100_mii_probe(struct ftgmac100 *priv)
@@ -918,9 +831,6 @@ static int ftgmac100_mii_probe(struct ftgmac100 *priv)
return 0;
}
-/******************************************************************************
- * struct mii_bus functions
- *****************************************************************************/
static int ftgmac100_mdiobus_read(struct mii_bus *bus, int phy_addr, int regnum)
{
struct net_device *netdev = bus->priv;
@@ -992,9 +902,6 @@ static int ftgmac100_mdiobus_write(struct mii_bus *bus, int phy_addr,
return -EIO;
}
-/******************************************************************************
- * struct ethtool_ops functions
- *****************************************************************************/
static void ftgmac100_get_drvinfo(struct net_device *netdev,
struct ethtool_drvinfo *info)
{
@@ -1010,168 +917,267 @@ static const struct ethtool_ops ftgmac100_ethtool_ops = {
.set_link_ksettings = phy_ethtool_set_link_ksettings,
};
-/******************************************************************************
- * interrupt handler
- *****************************************************************************/
static irqreturn_t ftgmac100_interrupt(int irq, void *dev_id)
{
struct net_device *netdev = dev_id;
struct ftgmac100 *priv = netdev_priv(netdev);
+ unsigned int status, new_mask = FTGMAC100_INT_BAD;
- /* When running in NCSI mode, the interface should be ready for
- * receiving or transmitting NCSI packets before it's opened.
- */
- if (likely(priv->use_ncsi || netif_running(netdev))) {
- /* Disable interrupts for polling */
- iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);
- napi_schedule(&priv->napi);
+ /* Fetch and clear interrupt bits, process abnormal ones */
+ status = ioread32(priv->base + FTGMAC100_OFFSET_ISR);
+ iowrite32(status, priv->base + FTGMAC100_OFFSET_ISR);
+ if (unlikely(status & FTGMAC100_INT_BAD)) {
+
+ /* RX buffer unavailable */
+ if (status & FTGMAC100_INT_NO_RXBUF)
+ netdev->stats.rx_over_errors++;
+
+ /* received packet lost due to RX FIFO full */
+ if (status & FTGMAC100_INT_RPKT_LOST)
+ netdev->stats.rx_fifo_errors++;
+
+ /* sent packet lost due to excessive TX collision */
+ if (status & FTGMAC100_INT_XPKT_LOST)
+ netdev->stats.tx_fifo_errors++;
+
+ /* AHB error -> Reset the chip */
+ if (status & FTGMAC100_INT_AHB_ERR) {
+ if (net_ratelimit())
+ netdev_warn(netdev,
+ "AHB bus error ! Resetting chip.\n");
+ iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);
+ schedule_work(&priv->reset_task);
+ return IRQ_HANDLED;
+ }
+
+ /* We may need to restart the MAC after such errors, delay
+ * this until after we have freed some Rx buffers though
+ */
+ priv->need_mac_restart = true;
+
+ /* Disable those errors until we restart */
+ new_mask &= ~status;
}
+ /* Only enable "bad" interrupts while NAPI is on */
+ iowrite32(new_mask, priv->base + FTGMAC100_OFFSET_IER);
+
+ /* Schedule NAPI bh */
+ napi_schedule_irqoff(&priv->napi);
+
return IRQ_HANDLED;
}
-/******************************************************************************
- * struct napi_struct functions
- *****************************************************************************/
+static bool ftgmac100_check_rx(struct ftgmac100 *priv)
+{
+ struct ftgmac100_rxdes *rxdes = &priv->descs->rxdes[priv->rx_pointer];
+
+ /* Do we have a packet ? */
+ return !!(rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_RXPKT_RDY));
+}
+
static int ftgmac100_poll(struct napi_struct *napi, int budget)
{
struct ftgmac100 *priv = container_of(napi, struct ftgmac100, napi);
- struct net_device *netdev = priv->netdev;
- unsigned int status;
- bool completed = true;
+ bool more, completed = true;
int rx = 0;
- status = ioread32(priv->base + FTGMAC100_OFFSET_ISR);
- iowrite32(status, priv->base + FTGMAC100_OFFSET_ISR);
+ ftgmac100_tx_complete(priv);
- if (status & (FTGMAC100_INT_RPKT_BUF | FTGMAC100_INT_NO_RXBUF)) {
- /*
- * FTGMAC100_INT_RPKT_BUF:
- * RX DMA has received packets into RX buffer successfully
- *
- * FTGMAC100_INT_NO_RXBUF:
- * RX buffer unavailable
- */
- bool retry;
+ do {
+ more = ftgmac100_rx_packet(priv, &rx);
+ } while (more && rx < budget);
- do {
- retry = ftgmac100_rx_packet(priv, &rx);
- } while (retry && rx < budget);
+ if (more && rx == budget)
+ completed = false;
- if (retry && rx == budget)
- completed = false;
+
+ /* The interrupt is telling us to kick the MAC back to life
+ * after an RX overflow
+ */
+ if (unlikely(priv->need_mac_restart)) {
+ ftgmac100_start_hw(priv);
+
+ /* Re-enable "bad" interrupts */
+ iowrite32(FTGMAC100_INT_BAD,
+ priv->base + FTGMAC100_OFFSET_IER);
}
- if (status & (FTGMAC100_INT_XPKT_ETH | FTGMAC100_INT_XPKT_LOST)) {
- /*
- * FTGMAC100_INT_XPKT_ETH:
- * packet transmitted to ethernet successfully
- *
- * FTGMAC100_INT_XPKT_LOST:
- * packet transmitted to ethernet lost due to late
- * collision or excessive collision
- */
- ftgmac100_tx_complete(priv);
- }
-
- if (status & priv->int_mask_all & (FTGMAC100_INT_NO_RXBUF |
- FTGMAC100_INT_RPKT_LOST | FTGMAC100_INT_AHB_ERR)) {
- if (net_ratelimit())
- netdev_info(netdev, "[ISR] = 0x%x: %s%s%s\n", status,
- status & FTGMAC100_INT_NO_RXBUF ? "NO_RXBUF " : "",
- status & FTGMAC100_INT_RPKT_LOST ? "RPKT_LOST " : "",
- status & FTGMAC100_INT_AHB_ERR ? "AHB_ERR " : "");
-
- if (status & FTGMAC100_INT_NO_RXBUF) {
- /* RX buffer unavailable */
- netdev->stats.rx_over_errors++;
- }
-
- if (status & FTGMAC100_INT_RPKT_LOST) {
- /* received packet lost due to RX FIFO full */
- netdev->stats.rx_fifo_errors++;
- }
- }
+ /* Keep NAPI going if we have still packets to reclaim */
+ if (priv->tx_pending)
+ return budget;
if (completed) {
+ /* We are about to re-enable all interrupts. However
+ * the HW has been latching RX/TX packet interrupts while
+ * they were masked. So we clear them first, then we need
+ * to re-check if there's something to process
+ */
+ iowrite32(FTGMAC100_INT_RXTX,
+ priv->base + FTGMAC100_OFFSET_ISR);
+ if (ftgmac100_check_rx(priv) || priv->tx_pending)
+ return budget;
+
+ /* deschedule NAPI */
napi_complete(napi);
/* enable all interrupts */
- iowrite32(priv->int_mask_all,
+ iowrite32(FTGMAC100_INT_ALL,
priv->base + FTGMAC100_OFFSET_IER);
}
return rx;
}
-/******************************************************************************
- * struct net_device_ops functions
- *****************************************************************************/
+static int ftgmac100_init_all(struct ftgmac100 *priv, bool ignore_alloc_err)
+{
+ int err = 0;
+
+ /* Re-init descriptors (adjust queue sizes) */
+ ftgmac100_init_rings(priv);
+
+ /* Realloc rx descriptors */
+ err = ftgmac100_alloc_rx_buffers(priv);
+ if (err && !ignore_alloc_err)
+ return err;
+
+ /* Reinit and restart HW */
+ ftgmac100_init_hw(priv);
+ ftgmac100_start_hw(priv);
+
+ /* Re-enable the device */
+ napi_enable(&priv->napi);
+ netif_start_queue(priv->netdev);
+
+ /* Enable all interrupts */
+ iowrite32(FTGMAC100_INT_ALL, priv->base + FTGMAC100_OFFSET_IER);
+
+ return err;
+}
+
+static void ftgmac100_reset_task(struct work_struct *work)
+{
+ struct ftgmac100 *priv = container_of(work, struct ftgmac100,
+ reset_task);
+ struct net_device *netdev = priv->netdev;
+ int err;
+
+ netdev_dbg(netdev, "Resetting NIC...\n");
+
+ /* Lock the world */
+ rtnl_lock();
+ if (netdev->phydev)
+ mutex_lock(&netdev->phydev->lock);
+ if (priv->mii_bus)
+ mutex_lock(&priv->mii_bus->mdio_lock);
+
+
+ /* Check if the interface is still up */
+ if (!netif_running(netdev))
+ goto bail;
+
+ /* Stop the network stack */
+ netif_trans_update(netdev);
+ napi_disable(&priv->napi);
+ netif_tx_disable(netdev);
+
+ /* Stop and reset the MAC */
+ ftgmac100_stop_hw(priv);
+ err = ftgmac100_reset_and_config_mac(priv);
+ if (err) {
+ /* Not much we can do ... it might come back... */
+ netdev_err(netdev, "attempting to continue...\n");
+ }
+
+ /* Free all rx and tx buffers */
+ ftgmac100_free_buffers(priv);
+
+ /* Setup everything again and restart chip */
+ ftgmac100_init_all(priv, true);
+
+ netdev_dbg(netdev, "Reset done !\n");
+ bail:
+ if (priv->mii_bus)
+ mutex_unlock(&priv->mii_bus->mdio_lock);
+ if (netdev->phydev)
+ mutex_unlock(&netdev->phydev->lock);
+ rtnl_unlock();
+}
+
static int ftgmac100_open(struct net_device *netdev)
{
struct ftgmac100 *priv = netdev_priv(netdev);
- unsigned int status;
int err;
- err = ftgmac100_alloc_buffers(priv);
+ /* Allocate ring buffers */
+ err = ftgmac100_alloc_rings(priv);
if (err) {
- netdev_err(netdev, "failed to allocate buffers\n");
- goto err_alloc;
+ netdev_err(netdev, "Failed to allocate descriptors\n");
+ return err;
}
- err = request_irq(priv->irq, ftgmac100_interrupt, 0, netdev->name, netdev);
- if (err) {
- netdev_err(netdev, "failed to request irq %d\n", priv->irq);
- goto err_irq;
+ /* When using NC-SI we force the speed to 100Mbit/s full duplex,
+ *
+ * Otherwise we leave it set to 0 (no link), the link
+ * message from the PHY layer will handle setting it up to
+ * something else if needed.
+ */
+ if (priv->use_ncsi) {
+ priv->cur_duplex = DUPLEX_FULL;
+ priv->cur_speed = SPEED_100;
+ } else {
+ priv->cur_duplex = 0;
+ priv->cur_speed = 0;
}
- priv->rx_pointer = 0;
- priv->tx_clean_pointer = 0;
- priv->tx_pointer = 0;
- priv->tx_pending = 0;
-
- err = ftgmac100_reset_hw(priv);
+ /* Reset the hardware */
+ err = ftgmac100_reset_and_config_mac(priv);
if (err)
goto err_hw;
- ftgmac100_init_hw(priv);
- ftgmac100_start_hw(priv, priv->use_ncsi ? 100 : 10);
+ /* Initialize NAPI */
+ netif_napi_add(netdev, &priv->napi, ftgmac100_poll, 64);
- /* Clear stale interrupts */
- status = ioread32(priv->base + FTGMAC100_OFFSET_ISR);
- iowrite32(status, priv->base + FTGMAC100_OFFSET_ISR);
+ /* Grab our interrupt */
+ err = request_irq(netdev->irq, ftgmac100_interrupt, 0, netdev->name, netdev);
+ if (err) {
+ netdev_err(netdev, "failed to request irq %d\n", netdev->irq);
+ goto err_irq;
+ }
- if (netdev->phydev)
+ /* Start things up */
+ err = ftgmac100_init_all(priv, false);
+ if (err) {
+ netdev_err(netdev, "Failed to allocate packet buffers\n");
+ goto err_alloc;
+ }
+
+ if (netdev->phydev) {
+ /* If we have a PHY, start polling */
phy_start(netdev->phydev);
- else if (priv->use_ncsi)
+ } else if (priv->use_ncsi) {
+ /* If using NC-SI, set our carrier on and start the stack */
netif_carrier_on(netdev);
- napi_enable(&priv->napi);
- netif_start_queue(netdev);
-
- /* enable all interrupts */
- iowrite32(priv->int_mask_all, priv->base + FTGMAC100_OFFSET_IER);
-
- /* Start the NCSI device */
- if (priv->use_ncsi) {
+ /* Start the NCSI device */
err = ncsi_start_dev(priv->ndev);
if (err)
goto err_ncsi;
}
- priv->enabled = true;
-
return 0;
-err_ncsi:
+ err_ncsi:
napi_disable(&priv->napi);
netif_stop_queue(netdev);
- iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);
-err_hw:
- free_irq(priv->irq, netdev);
-err_irq:
+ err_alloc:
ftgmac100_free_buffers(priv);
-err_alloc:
+ free_irq(netdev->irq, netdev);
+ err_irq:
+ netif_napi_del(&priv->napi);
+ err_hw:
+ iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);
+ ftgmac100_free_rings(priv);
return err;
}
@@ -1179,23 +1185,29 @@ static int ftgmac100_stop(struct net_device *netdev)
{
struct ftgmac100 *priv = netdev_priv(netdev);
- if (!priv->enabled)
- return 0;
+ /* Note about the reset task: We are called with the rtnl lock
+ * held, so we are synchronized against the core of the reset
+ * task. We must not try to synchronously cancel it otherwise
+ * we can deadlock. But since it will test for netif_running()
+ * which has already been cleared by the net core, we don't
+ * anything special to do.
+ */
/* disable all interrupts */
- priv->enabled = false;
iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);
netif_stop_queue(netdev);
napi_disable(&priv->napi);
+ netif_napi_del(&priv->napi);
if (netdev->phydev)
phy_stop(netdev->phydev);
else if (priv->use_ncsi)
ncsi_stop_dev(priv->ndev);
ftgmac100_stop_hw(priv);
- free_irq(priv->irq, netdev);
+ free_irq(netdev->irq, netdev);
ftgmac100_free_buffers(priv);
+ ftgmac100_free_rings(priv);
return 0;
}
@@ -1319,9 +1331,6 @@ static void ftgmac100_ncsi_handler(struct ncsi_dev *nd)
nd->link_up ? "up" : "down");
}
-/******************************************************************************
- * struct platform_driver functions
- *****************************************************************************/
static int ftgmac100_probe(struct platform_device *pdev)
{
struct resource *res;
@@ -1359,12 +1368,10 @@ static int ftgmac100_probe(struct platform_device *pdev)
priv = netdev_priv(netdev);
priv->netdev = netdev;
priv->dev = &pdev->dev;
+ INIT_WORK(&priv->reset_task, ftgmac100_reset_task);
spin_lock_init(&priv->tx_lock);
- /* initialize NAPI */
- netif_napi_add(netdev, &priv->napi, ftgmac100_poll, 64);
-
/* map io memory */
priv->res = request_mem_region(res->start, resource_size(res),
dev_name(&pdev->dev));
@@ -1381,18 +1388,11 @@ static int ftgmac100_probe(struct platform_device *pdev)
goto err_ioremap;
}
- priv->irq = irq;
+ netdev->irq = irq;
/* MAC address from chip or random one */
ftgmac100_setup_mac(priv);
- priv->int_mask_all = (FTGMAC100_INT_RPKT_LOST |
- FTGMAC100_INT_XPKT_ETH |
- FTGMAC100_INT_XPKT_LOST |
- FTGMAC100_INT_AHB_ERR |
- FTGMAC100_INT_RPKT_BUF |
- FTGMAC100_INT_NO_RXBUF);
-
if (of_machine_is_compatible("aspeed,ast2400") ||
of_machine_is_compatible("aspeed,ast2500")) {
priv->rxdes0_edorr_mask = BIT(30);
@@ -1425,7 +1425,7 @@ static int ftgmac100_probe(struct platform_device *pdev)
* when NCSI is enabled on the interface. It doesn't work
* in that case.
*/
- netdev->features = NETIF_F_IP_CSUM | NETIF_F_GRO;
+ netdev->features = NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_GRO;
if (priv->use_ncsi &&
of_get_property(pdev->dev.of_node, "no-hw-checksum", NULL))
netdev->features &= ~NETIF_F_IP_CSUM;
@@ -1438,7 +1438,7 @@ static int ftgmac100_probe(struct platform_device *pdev)
goto err_register_netdev;
}
- netdev_info(netdev, "irq %d, mapped at %p\n", priv->irq, priv->base);
+ netdev_info(netdev, "irq %d, mapped at %p\n", netdev->irq, priv->base);
return 0;
@@ -1465,6 +1465,12 @@ static int ftgmac100_remove(struct platform_device *pdev)
priv = netdev_priv(netdev);
unregister_netdev(netdev);
+
+ /* There's a small chance the reset task will have been re-queued,
+ * during stop, make sure it's gone before we free the structure.
+ */
+ cancel_work_sync(&priv->reset_task);
+
ftgmac100_destroy_mdio(netdev);
iounmap(priv->base);
diff --git a/drivers/net/ethernet/faraday/ftgmac100.h b/drivers/net/ethernet/faraday/ftgmac100.h
index a7ce0ac..9124785 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.h
+++ b/drivers/net/ethernet/faraday/ftgmac100.h
@@ -86,6 +86,20 @@
#define FTGMAC100_INT_PHYSTS_CHG (1 << 9)
#define FTGMAC100_INT_NO_HPTXBUF (1 << 10)
+/* Interrupts we care about in NAPI mode */
+#define FTGMAC100_INT_BAD (FTGMAC100_INT_RPKT_LOST | \
+ FTGMAC100_INT_XPKT_LOST | \
+ FTGMAC100_INT_AHB_ERR | \
+ FTGMAC100_INT_NO_RXBUF)
+
+/* Normal RX/TX interrupts, enabled when NAPI off */
+#define FTGMAC100_INT_RXTX (FTGMAC100_INT_XPKT_ETH | \
+ FTGMAC100_INT_RPKT_BUF)
+
+/* All the interrupts we care about */
+#define FTGMAC100_INT_ALL (FTGMAC100_INT_RPKT_BUF | \
+ FTGMAC100_INT_BAD)
+
/*
* Interrupt timer control register
*/
@@ -213,10 +227,10 @@ struct ftgmac100_txdes {
* Receive descriptor, aligned to 16 bytes
*/
struct ftgmac100_rxdes {
- unsigned int rxdes0;
- unsigned int rxdes1;
- unsigned int rxdes2; /* not used by HW */
- unsigned int rxdes3; /* RXBUF_BADR */
+ __le32 rxdes0; /* Control & status bits */
+ __le32 rxdes1; /* Checksum and vlan status */
+ __le32 rxdes2; /* length/type on AST2500 */
+ __le32 rxdes3; /* DMA buffer address */
} __attribute__ ((aligned(16)));
#define FTGMAC100_RXDES0_VDBC 0x3fff
@@ -234,6 +248,14 @@ struct ftgmac100_rxdes {
#define FTGMAC100_RXDES0_FRS (1 << 29)
#define FTGMAC100_RXDES0_RXPKT_RDY (1 << 31)
+/* Errors we care about for dropping packets */
+#define RXDES0_ANY_ERROR ( \
+ FTGMAC100_RXDES0_RX_ERR | \
+ FTGMAC100_RXDES0_CRC_ERR | \
+ FTGMAC100_RXDES0_FTL | \
+ FTGMAC100_RXDES0_RUNT | \
+ FTGMAC100_RXDES0_RX_ODD_NB)
+
#define FTGMAC100_RXDES1_VLANTAG_CI 0xffff
#define FTGMAC100_RXDES1_PROT_MASK (0x3 << 20)
#define FTGMAC100_RXDES1_PROT_NONIP (0x0 << 20)
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index e2ca107..9a520e4 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -137,6 +137,13 @@ MODULE_PARM_DESC(tx_timeout, "The Tx timeout in ms");
/* L4 Type field: TCP */
#define FM_L4_PARSE_RESULT_TCP 0x20
+/* FD status field indicating whether the FM Parser has attempted to validate
+ * the L4 csum of the frame.
+ * Note that having this bit set doesn't necessarily imply that the checksum
+ * is valid. One would have to check the parse results to find that out.
+ */
+#define FM_FD_STAT_L4CV 0x00000004
+
#define DPAA_SGT_MAX_ENTRIES 16 /* maximum number of entries in SG Table */
#define DPAA_BUFF_RELEASE_MAX 8 /* maximum number of buffers released at once */
@@ -235,6 +242,7 @@ static int dpaa_netdev_init(struct net_device *net_dev,
* For conformity, we'll still declare GSO explicitly.
*/
net_dev->features |= NETIF_F_GSO;
+ net_dev->features |= NETIF_F_RXCSUM;
net_dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
/* we do not want shared skbs on TX */
@@ -334,6 +342,45 @@ static void dpaa_get_stats64(struct net_device *net_dev,
}
}
+static int dpaa_setup_tc(struct net_device *net_dev, u32 handle, __be16 proto,
+ struct tc_to_netdev *tc)
+{
+ struct dpaa_priv *priv = netdev_priv(net_dev);
+ u8 num_tc;
+ int i;
+
+ if (tc->type != TC_SETUP_MQPRIO)
+ return -EINVAL;
+
+ tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+ num_tc = tc->mqprio->num_tc;
+
+ if (num_tc == priv->num_tc)
+ return 0;
+
+ if (!num_tc) {
+ netdev_reset_tc(net_dev);
+ goto out;
+ }
+
+ if (num_tc > DPAA_TC_NUM) {
+ netdev_err(net_dev, "Too many traffic classes: max %d supported.\n",
+ DPAA_TC_NUM);
+ return -EINVAL;
+ }
+
+ netdev_set_num_tc(net_dev, num_tc);
+
+ for (i = 0; i < num_tc; i++)
+ netdev_set_tc_queue(net_dev, i, DPAA_TC_TXQ_NUM,
+ i * DPAA_TC_TXQ_NUM);
+
+out:
+ priv->num_tc = num_tc ? : 1;
+ netif_set_real_num_tx_queues(net_dev, priv->num_tc * DPAA_TC_TXQ_NUM);
+ return 0;
+}
+
static struct mac_device *dpaa_mac_dev_get(struct platform_device *pdev)
{
struct platform_device *of_dev;
@@ -557,16 +604,18 @@ static void dpaa_bps_free(struct dpaa_priv *priv)
/* Use multiple WQs for FQ assignment:
* - Tx Confirmation queues go to WQ1.
- * - Rx Error and Tx Error queues go to WQ2 (giving them a better chance
- * to be scheduled, in case there are many more FQs in WQ3).
- * - Rx Default and Tx queues go to WQ3 (no differentiation between
- * Rx and Tx traffic).
+ * - Rx Error and Tx Error queues go to WQ5 (giving them a better chance
+ * to be scheduled, in case there are many more FQs in WQ6).
+ * - Rx Default goes to WQ6.
+ * - Tx queues go to different WQs depending on their priority. Equal
+ * chunks of NR_CPUS queues go to WQ6 (lowest priority), WQ2, WQ1 and
+ * WQ0 (highest priority).
* This ensures that Tx-confirmed buffers are timely released. In particular,
* it avoids congestion on the Tx Confirm FQs, which can pile up PFDRs if they
* are greatly outnumbered by other FQs in the system, while
* dequeue scheduling is round-robin.
*/
-static inline void dpaa_assign_wq(struct dpaa_fq *fq)
+static inline void dpaa_assign_wq(struct dpaa_fq *fq, int idx)
{
switch (fq->fq_type) {
case FQ_TYPE_TX_CONFIRM:
@@ -575,11 +624,33 @@ static inline void dpaa_assign_wq(struct dpaa_fq *fq)
break;
case FQ_TYPE_RX_ERROR:
case FQ_TYPE_TX_ERROR:
- fq->wq = 2;
+ fq->wq = 5;
break;
case FQ_TYPE_RX_DEFAULT:
+ fq->wq = 6;
+ break;
case FQ_TYPE_TX:
- fq->wq = 3;
+ switch (idx / DPAA_TC_TXQ_NUM) {
+ case 0:
+ /* Low priority (best effort) */
+ fq->wq = 6;
+ break;
+ case 1:
+ /* Medium priority */
+ fq->wq = 2;
+ break;
+ case 2:
+ /* High priority */
+ fq->wq = 1;
+ break;
+ case 3:
+ /* Very high priority */
+ fq->wq = 0;
+ break;
+ default:
+ WARN(1, "Too many TX FQs: more than %d!\n",
+ DPAA_ETH_TXQ_NUM);
+ }
break;
default:
WARN(1, "Invalid FQ type %d for FQID %d!\n",
@@ -607,7 +678,7 @@ static struct dpaa_fq *dpaa_fq_alloc(struct device *dev,
}
for (i = 0; i < count; i++)
- dpaa_assign_wq(dpaa_fq + i);
+ dpaa_assign_wq(dpaa_fq + i, i);
return dpaa_fq;
}
@@ -903,7 +974,7 @@ static int dpaa_fq_init(struct dpaa_fq *dpaa_fq, bool td_enable)
* Tx Confirmation FQs.
*/
if (dpaa_fq->fq_type == FQ_TYPE_TX_CONFIRM)
- initfq.fqd.fq_ctrl |= cpu_to_be16(QM_FQCTRL_HOLDACTIVE);
+ initfq.fqd.fq_ctrl |= cpu_to_be16(QM_FQCTRL_AVOIDBLOCK);
/* FQ placement */
initfq.we_mask |= cpu_to_be16(QM_INITFQ_WE_DESTWQ);
@@ -985,7 +1056,8 @@ static int dpaa_fq_init(struct dpaa_fq *dpaa_fq, bool td_enable)
/* Initialization common to all ingress queues */
if (dpaa_fq->flags & QMAN_FQ_FLAG_NO_ENQUEUE) {
initfq.we_mask |= cpu_to_be16(QM_INITFQ_WE_CONTEXTA);
- initfq.fqd.fq_ctrl |= cpu_to_be16(QM_FQCTRL_HOLDACTIVE);
+ initfq.fqd.fq_ctrl |= cpu_to_be16(QM_FQCTRL_HOLDACTIVE |
+ QM_FQCTRL_CTXASTASHING);
initfq.fqd.context_a.stashing.exclusive =
QM_STASHING_EXCL_DATA | QM_STASHING_EXCL_CTX |
QM_STASHING_EXCL_ANNOTATION;
@@ -1055,9 +1127,9 @@ static int dpaa_fq_free(struct device *dev, struct list_head *list)
return err;
}
-static void dpaa_eth_init_tx_port(struct fman_port *port, struct dpaa_fq *errq,
- struct dpaa_fq *defq,
- struct dpaa_buffer_layout *buf_layout)
+static int dpaa_eth_init_tx_port(struct fman_port *port, struct dpaa_fq *errq,
+ struct dpaa_fq *defq,
+ struct dpaa_buffer_layout *buf_layout)
{
struct fman_buffer_prefix_content buf_prefix_content;
struct fman_port_params params;
@@ -1076,23 +1148,29 @@ static void dpaa_eth_init_tx_port(struct fman_port *port, struct dpaa_fq *errq,
params.specific_params.non_rx_params.dflt_fqid = defq->fqid;
err = fman_port_config(port, ¶ms);
- if (err)
+ if (err) {
pr_err("%s: fman_port_config failed\n", __func__);
+ return err;
+ }
err = fman_port_cfg_buf_prefix_content(port, &buf_prefix_content);
- if (err)
+ if (err) {
pr_err("%s: fman_port_cfg_buf_prefix_content failed\n",
__func__);
+ return err;
+ }
err = fman_port_init(port);
if (err)
pr_err("%s: fm_port_init failed\n", __func__);
+
+ return err;
}
-static void dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp **bps,
- size_t count, struct dpaa_fq *errq,
- struct dpaa_fq *defq,
- struct dpaa_buffer_layout *buf_layout)
+static int dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp **bps,
+ size_t count, struct dpaa_fq *errq,
+ struct dpaa_fq *defq,
+ struct dpaa_buffer_layout *buf_layout)
{
struct fman_buffer_prefix_content buf_prefix_content;
struct fman_port_rx_params *rx_p;
@@ -1120,32 +1198,44 @@ static void dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp **bps,
}
err = fman_port_config(port, ¶ms);
- if (err)
+ if (err) {
pr_err("%s: fman_port_config failed\n", __func__);
+ return err;
+ }
err = fman_port_cfg_buf_prefix_content(port, &buf_prefix_content);
- if (err)
+ if (err) {
pr_err("%s: fman_port_cfg_buf_prefix_content failed\n",
__func__);
+ return err;
+ }
err = fman_port_init(port);
if (err)
pr_err("%s: fm_port_init failed\n", __func__);
+
+ return err;
}
-static void dpaa_eth_init_ports(struct mac_device *mac_dev,
- struct dpaa_bp **bps, size_t count,
- struct fm_port_fqs *port_fqs,
- struct dpaa_buffer_layout *buf_layout,
- struct device *dev)
+static int dpaa_eth_init_ports(struct mac_device *mac_dev,
+ struct dpaa_bp **bps, size_t count,
+ struct fm_port_fqs *port_fqs,
+ struct dpaa_buffer_layout *buf_layout,
+ struct device *dev)
{
struct fman_port *rxport = mac_dev->port[RX];
struct fman_port *txport = mac_dev->port[TX];
+ int err;
- dpaa_eth_init_tx_port(txport, port_fqs->tx_errq,
- port_fqs->tx_defq, &buf_layout[TX]);
- dpaa_eth_init_rx_port(rxport, bps, count, port_fqs->rx_errq,
- port_fqs->rx_defq, &buf_layout[RX]);
+ err = dpaa_eth_init_tx_port(txport, port_fqs->tx_errq,
+ port_fqs->tx_defq, &buf_layout[TX]);
+ if (err)
+ return err;
+
+ err = dpaa_eth_init_rx_port(rxport, bps, count, port_fqs->rx_errq,
+ port_fqs->rx_defq, &buf_layout[RX]);
+
+ return err;
}
static int dpaa_bman_release(const struct dpaa_bp *dpaa_bp,
@@ -1526,6 +1616,23 @@ static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv,
return skb;
}
+static u8 rx_csum_offload(const struct dpaa_priv *priv, const struct qm_fd *fd)
+{
+ /* The parser has run and performed L4 checksum validation.
+ * We know there were no parser errors (and implicitly no
+ * L4 csum error), otherwise we wouldn't be here.
+ */
+ if ((priv->net_dev->features & NETIF_F_RXCSUM) &&
+ (be32_to_cpu(fd->status) & FM_FD_STAT_L4CV))
+ return CHECKSUM_UNNECESSARY;
+
+ /* We're here because either the parser didn't run or the L4 checksum
+ * was not verified. This may include the case of a UDP frame with
+ * checksum zero or an L4 proto other than TCP/UDP
+ */
+ return CHECKSUM_NONE;
+}
+
/* Build a linear skb around the received buffer.
* We are guaranteed there is enough room at the end of the data buffer to
* accommodate the shared info area of the skb.
@@ -1556,7 +1663,7 @@ static struct sk_buff *contig_fd_to_skb(const struct dpaa_priv *priv,
skb_reserve(skb, fd_off);
skb_put(skb, qm_fd_get_length(fd));
- skb->ip_summed = CHECKSUM_NONE;
+ skb->ip_summed = rx_csum_offload(priv, fd);
return skb;
@@ -1616,7 +1723,7 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv,
if (WARN_ON(unlikely(!skb)))
goto free_buffers;
- skb->ip_summed = CHECKSUM_NONE;
+ skb->ip_summed = rx_csum_offload(priv, fd);
/* Make sure forwarded skbs will have enough space
* on Tx, if extra headers are added.
@@ -2093,7 +2200,7 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal,
dma_addr_t addr = qm_fd_addr(fd);
enum qm_fd_format fd_format;
struct net_device *net_dev;
- u32 fd_status = fd->status;
+ u32 fd_status;
struct dpaa_bp *dpaa_bp;
struct dpaa_priv *priv;
unsigned int skb_len;
@@ -2350,6 +2457,7 @@ static const struct net_device_ops dpaa_ops = {
.ndo_validate_addr = eth_validate_addr,
.ndo_set_rx_mode = dpaa_set_rx_mode,
.ndo_do_ioctl = dpaa_ioctl,
+ .ndo_setup_tc = dpaa_setup_tc,
};
static int dpaa_napi_add(struct net_device *net_dev)
@@ -2624,8 +2732,10 @@ static int dpaa_eth_probe(struct platform_device *pdev)
priv->rx_headroom = dpaa_get_headroom(&priv->buf_layout[RX]);
/* All real interfaces need their ports initialized */
- dpaa_eth_init_ports(mac_dev, dpaa_bps, DPAA_BPS_NUM, &port_fqs,
- &priv->buf_layout[0], dev);
+ err = dpaa_eth_init_ports(mac_dev, dpaa_bps, DPAA_BPS_NUM, &port_fqs,
+ &priv->buf_layout[0], dev);
+ if (err)
+ goto init_ports_failed;
priv->percpu_priv = devm_alloc_percpu(dev, *priv->percpu_priv);
if (!priv->percpu_priv) {
@@ -2638,6 +2748,9 @@ static int dpaa_eth_probe(struct platform_device *pdev)
memset(percpu_priv, 0, sizeof(*percpu_priv));
}
+ priv->num_tc = 1;
+ netif_set_real_num_tx_queues(net_dev, priv->num_tc * DPAA_TC_TXQ_NUM);
+
/* Initialize NAPI */
err = dpaa_napi_add(net_dev);
if (err < 0)
@@ -2658,6 +2771,7 @@ static int dpaa_eth_probe(struct platform_device *pdev)
napi_add_failed:
dpaa_napi_del(net_dev);
alloc_percpu_failed:
+init_ports_failed:
dpaa_fq_free(dev, &priv->dpaa_fq_list);
fq_alloc_failed:
qman_delete_cgr_safe(&priv->ingress_cgr);
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
index 1f9aebf..9941a78 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
@@ -39,7 +39,12 @@
#include "mac.h"
#include "dpaa_eth_trace.h"
-#define DPAA_ETH_TXQ_NUM NR_CPUS
+/* Number of prioritised traffic classes */
+#define DPAA_TC_NUM 4
+/* Number of Tx queues per traffic class */
+#define DPAA_TC_TXQ_NUM NR_CPUS
+/* Total number of Tx queues */
+#define DPAA_ETH_TXQ_NUM (DPAA_TC_NUM * DPAA_TC_TXQ_NUM)
#define DPAA_BPS_NUM 3 /* number of bpools per interface */
@@ -152,6 +157,7 @@ struct dpaa_priv {
u16 channel;
struct list_head dpaa_fq_list;
+ u8 num_tc;
u32 msg_enable; /* net_device message level */
struct {
diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c
index f60845f..4aefe24 100644
--- a/drivers/net/ethernet/freescale/fman/fman.c
+++ b/drivers/net/ethernet/freescale/fman/fman.c
@@ -59,6 +59,7 @@
#define DMA_OFFSET 0x000C2000
#define FPM_OFFSET 0x000C3000
#define IMEM_OFFSET 0x000C4000
+#define HWP_OFFSET 0x000C7000
#define CGP_OFFSET 0x000DB000
/* Exceptions bit map */
@@ -218,6 +219,9 @@
#define QMI_GS_HALT_NOT_BUSY 0x00000002
+/* HWP defines */
+#define HWP_RPIMAC_PEN 0x00000001
+
/* IRAM defines */
#define IRAM_IADD_AIE 0x80000000
#define IRAM_READY 0x80000000
@@ -475,6 +479,12 @@ struct fman_dma_regs {
u32 res00e0[0x400 - 56];
};
+struct fman_hwp_regs {
+ u32 res0000[0x844 / 4]; /* 0x000..0x843 */
+ u32 fmprrpimac; /* FM Parser Internal memory access control */
+ u32 res[(0x1000 - 0x848) / 4]; /* 0x848..0xFFF */
+};
+
/* Structure that holds current FMan state.
* Used for saving run time information.
*/
@@ -606,6 +616,7 @@ struct fman {
struct fman_bmi_regs __iomem *bmi_regs;
struct fman_qmi_regs __iomem *qmi_regs;
struct fman_dma_regs __iomem *dma_regs;
+ struct fman_hwp_regs __iomem *hwp_regs;
fman_exceptions_cb *exception_cb;
fman_bus_error_cb *bus_error_cb;
/* Spinlock for FMan use */
@@ -999,6 +1010,12 @@ static void qmi_init(struct fman_qmi_regs __iomem *qmi_rg,
iowrite32be(tmp_reg, &qmi_rg->fmqm_ien);
}
+static void hwp_init(struct fman_hwp_regs __iomem *hwp_rg)
+{
+ /* enable HW Parser */
+ iowrite32be(HWP_RPIMAC_PEN, &hwp_rg->fmprrpimac);
+}
+
static int enable(struct fman *fman, struct fman_cfg *cfg)
{
u32 cfg_reg = 0;
@@ -1195,7 +1212,7 @@ static int fill_soc_specific_params(struct fman_state_struct *state)
state->max_num_of_open_dmas = 32;
state->fm_port_num_of_cg = 256;
state->num_of_rx_ports = 6;
- state->total_fifo_size = 122 * 1024;
+ state->total_fifo_size = 136 * 1024;
break;
case 2:
@@ -1793,6 +1810,7 @@ static int fman_config(struct fman *fman)
fman->bmi_regs = base_addr + BMI_OFFSET;
fman->qmi_regs = base_addr + QMI_OFFSET;
fman->dma_regs = base_addr + DMA_OFFSET;
+ fman->hwp_regs = base_addr + HWP_OFFSET;
fman->base_addr = base_addr;
spin_lock_init(&fman->spinlock);
@@ -2062,6 +2080,9 @@ static int fman_init(struct fman *fman)
/* Init QMI Registers */
qmi_init(fman->qmi_regs, fman->cfg);
+ /* Init HW Parser */
+ hwp_init(fman->hwp_regs);
+
err = enable(fman, cfg);
if (err != 0)
return err;
diff --git a/drivers/net/ethernet/freescale/fman/fman.h b/drivers/net/ethernet/freescale/fman/fman.h
index 57aae8d..f53e147 100644
--- a/drivers/net/ethernet/freescale/fman/fman.h
+++ b/drivers/net/ethernet/freescale/fman/fman.h
@@ -134,14 +134,14 @@ enum fman_exceptions {
struct fman_prs_result {
u8 lpid; /* Logical port id */
u8 shimr; /* Shim header result */
- u16 l2r; /* Layer 2 result */
- u16 l3r; /* Layer 3 result */
+ __be16 l2r; /* Layer 2 result */
+ __be16 l3r; /* Layer 3 result */
u8 l4r; /* Layer 4 result */
u8 cplan; /* Classification plan id */
- u16 nxthdr; /* Next Header */
- u16 cksum; /* Running-sum */
+ __be16 nxthdr; /* Next Header */
+ __be16 cksum; /* Running-sum */
/* Flags&fragment-offset field of the last IP-header */
- u16 flags_frag_off;
+ __be16 flags_frag_off;
/* Routing type field of a IPV6 routing extension header */
u8 route_type;
/* Routing Extension Header Present; last bit is IP valid */
diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c
index 84ea130..98bba10 100644
--- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c
+++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c
@@ -381,6 +381,9 @@ static int init(struct dtsec_regs __iomem *regs, struct dtsec_cfg *cfg,
/* check RGMII support */
if (iface == PHY_INTERFACE_MODE_RGMII ||
+ iface == PHY_INTERFACE_MODE_RGMII_ID ||
+ iface == PHY_INTERFACE_MODE_RGMII_RXID ||
+ iface == PHY_INTERFACE_MODE_RGMII_TXID ||
iface == PHY_INTERFACE_MODE_RMII)
if (tmp & DTSEC_ID2_INT_REDUCED_OFF)
return -EINVAL;
@@ -390,7 +393,10 @@ static int init(struct dtsec_regs __iomem *regs, struct dtsec_cfg *cfg,
if (tmp & DTSEC_ID2_INT_REDUCED_OFF)
return -EINVAL;
- is_rgmii = iface == PHY_INTERFACE_MODE_RGMII;
+ is_rgmii = iface == PHY_INTERFACE_MODE_RGMII ||
+ iface == PHY_INTERFACE_MODE_RGMII_ID ||
+ iface == PHY_INTERFACE_MODE_RGMII_RXID ||
+ iface == PHY_INTERFACE_MODE_RGMII_TXID;
is_sgmii = iface == PHY_INTERFACE_MODE_SGMII;
is_qsgmii = iface == PHY_INTERFACE_MODE_QSGMII;
diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c
index cd6a53e..c029688 100644
--- a/drivers/net/ethernet/freescale/fman/fman_memac.c
+++ b/drivers/net/ethernet/freescale/fman/fman_memac.c
@@ -443,7 +443,10 @@ static int init(struct memac_regs __iomem *regs, struct memac_cfg *cfg,
break;
default:
tmp |= IF_MODE_GMII;
- if (phy_if == PHY_INTERFACE_MODE_RGMII)
+ if (phy_if == PHY_INTERFACE_MODE_RGMII ||
+ phy_if == PHY_INTERFACE_MODE_RGMII_ID ||
+ phy_if == PHY_INTERFACE_MODE_RGMII_RXID ||
+ phy_if == PHY_INTERFACE_MODE_RGMII_TXID)
tmp |= IF_MODE_RGMII | IF_MODE_RGMII_AUTO;
}
iowrite32be(tmp, ®s->if_mode);
diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.h b/drivers/net/ethernet/freescale/fman/fman_memac.h
index 173d8e0..c4a6646 100644
--- a/drivers/net/ethernet/freescale/fman/fman_memac.h
+++ b/drivers/net/ethernet/freescale/fman/fman_memac.h
@@ -36,6 +36,7 @@
#include "fman_mac.h"
#include <linux/netdevice.h>
+#include <linux/phy_fixed.h>
struct fman_mac *memac_config(struct fman_mac_params *params);
int memac_set_promiscuous(struct fman_mac *memac, bool new_val);
diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c
index 9f3bb50..57bf44f 100644
--- a/drivers/net/ethernet/freescale/fman/fman_port.c
+++ b/drivers/net/ethernet/freescale/fman/fman_port.c
@@ -62,6 +62,7 @@
#define BMI_PORT_REGS_OFFSET 0
#define QMI_PORT_REGS_OFFSET 0x400
+#define HWP_PORT_REGS_OFFSET 0x800
/* Default values */
#define DFLT_PORT_BUFFER_PREFIX_CONTEXT_DATA_ALIGN \
@@ -182,7 +183,7 @@
#define NIA_ENG_BMI 0x00500000
#define NIA_ENG_QMI_ENQ 0x00540000
#define NIA_ENG_QMI_DEQ 0x00580000
-
+#define NIA_ENG_HWP 0x00440000
#define NIA_BMI_AC_ENQ_FRAME 0x00000002
#define NIA_BMI_AC_TX_RELEASE 0x000002C0
#define NIA_BMI_AC_RELEASE 0x000000C0
@@ -317,6 +318,19 @@ struct fman_port_qmi_regs {
u32 fmqm_pndcc; /* PortID n Dequeue Confirm Counter */
};
+#define HWP_HXS_COUNT 16
+#define HWP_HXS_PHE_REPORT 0x00000800
+#define HWP_HXS_PCAC_PSTAT 0x00000100
+#define HWP_HXS_PCAC_PSTOP 0x00000001
+struct fman_port_hwp_regs {
+ struct {
+ u32 ssa; /* Soft Sequence Attachment */
+ u32 lcv; /* Line-up Enable Confirmation Mask */
+ } pmda[HWP_HXS_COUNT]; /* Parse Memory Direct Access Registers */
+ u32 reserved080[(0x3f8 - 0x080) / 4]; /* (0x080-0x3f7) */
+ u32 fmpr_pcac; /* Configuration Access Control */
+};
+
/* QMI dequeue prefetch modes */
enum fman_port_deq_prefetch {
FMAN_PORT_DEQ_NO_PREFETCH, /* No prefetch mode */
@@ -436,6 +450,7 @@ struct fman_port {
union fman_port_bmi_regs __iomem *bmi_regs;
struct fman_port_qmi_regs __iomem *qmi_regs;
+ struct fman_port_hwp_regs __iomem *hwp_regs;
struct fman_sp_buffer_offsets buffer_offsets;
@@ -521,9 +536,12 @@ static int init_bmi_rx(struct fman_port *port)
/* NIA */
tmp = (u32)cfg->rx_fd_bits << BMI_NEXT_ENG_FD_BITS_SHIFT;
- tmp |= NIA_ENG_BMI | NIA_BMI_AC_ENQ_FRAME;
+ tmp |= NIA_ENG_HWP;
iowrite32be(tmp, ®s->fmbm_rfne);
+ /* Parser Next Engine NIA */
+ iowrite32be(NIA_ENG_BMI | NIA_BMI_AC_ENQ_FRAME, ®s->fmbm_rfpne);
+
/* Enqueue NIA */
iowrite32be(NIA_ENG_QMI_ENQ | NIA_ORDER_RESTOR, ®s->fmbm_rfene);
@@ -665,6 +683,50 @@ static int init_qmi(struct fman_port *port)
return 0;
}
+static void stop_port_hwp(struct fman_port *port)
+{
+ struct fman_port_hwp_regs __iomem *regs = port->hwp_regs;
+ int cnt = 100;
+
+ iowrite32be(HWP_HXS_PCAC_PSTOP, ®s->fmpr_pcac);
+
+ while (cnt-- > 0 &&
+ (ioread32be(®s->fmpr_pcac) & HWP_HXS_PCAC_PSTAT))
+ udelay(10);
+ if (!cnt)
+ pr_err("Timeout stopping HW Parser\n");
+}
+
+static void start_port_hwp(struct fman_port *port)
+{
+ struct fman_port_hwp_regs __iomem *regs = port->hwp_regs;
+ int cnt = 100;
+
+ iowrite32be(0, ®s->fmpr_pcac);
+
+ while (cnt-- > 0 &&
+ !(ioread32be(®s->fmpr_pcac) & HWP_HXS_PCAC_PSTAT))
+ udelay(10);
+ if (!cnt)
+ pr_err("Timeout starting HW Parser\n");
+}
+
+static void init_hwp(struct fman_port *port)
+{
+ struct fman_port_hwp_regs __iomem *regs = port->hwp_regs;
+ int i;
+
+ stop_port_hwp(port);
+
+ for (i = 0; i < HWP_HXS_COUNT; i++) {
+ /* enable HXS error reporting into FD[STATUS] PHE */
+ iowrite32be(0x00000000, ®s->pmda[i].ssa);
+ iowrite32be(0xffffffff, ®s->pmda[i].lcv);
+ }
+
+ start_port_hwp(port);
+}
+
static int init(struct fman_port *port)
{
int err;
@@ -673,6 +735,8 @@ static int init(struct fman_port *port)
switch (port->port_type) {
case FMAN_PORT_TYPE_RX:
err = init_bmi_rx(port);
+ if (!err)
+ init_hwp(port);
break;
case FMAN_PORT_TYPE_TX:
err = init_bmi_tx(port);
@@ -686,7 +750,8 @@ static int init(struct fman_port *port)
/* Init QMI registers */
err = init_qmi(port);
- return err;
+ if (err)
+ return err;
return 0;
}
@@ -1247,7 +1312,7 @@ int fman_port_config(struct fman_port *port, struct fman_port_params *params)
/* Allocate the FM driver's parameters structure */
port->cfg = kzalloc(sizeof(*port->cfg), GFP_KERNEL);
if (!port->cfg)
- goto err_params;
+ return -EINVAL;
/* Initialize FM port parameters which will be kept by the driver */
port->port_type = port->dts_params.type;
@@ -1276,6 +1341,7 @@ int fman_port_config(struct fman_port *port, struct fman_port_params *params)
/* set memory map pointers */
port->bmi_regs = base_addr + BMI_PORT_REGS_OFFSET;
port->qmi_regs = base_addr + QMI_PORT_REGS_OFFSET;
+ port->hwp_regs = base_addr + HWP_PORT_REGS_OFFSET;
port->max_frame_length = DFLT_PORT_MAX_FRAME_LENGTH;
/* resource distribution. */
@@ -1327,8 +1393,6 @@ int fman_port_config(struct fman_port *port, struct fman_port_params *params)
err_port_cfg:
kfree(port->cfg);
-err_params:
- kfree(port);
return -EINVAL;
}
EXPORT_SYMBOL(fman_port_config);
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
index db9c0bc..1fc27c9 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
@@ -38,12 +38,6 @@
#include <asm/irq.h>
#include <linux/uaccess.h>
-#ifdef CONFIG_8xx
-#include <asm/8xx_immap.h>
-#include <asm/pgtable.h>
-#include <asm/cpm1.h>
-#endif
-
#include "fs_enet.h"
#include "fec.h"
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
index 96d44cf..64300ac 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
@@ -37,12 +37,6 @@
#include <asm/irq.h>
#include <linux/uaccess.h>
-#ifdef CONFIG_8xx
-#include <asm/8xx_immap.h>
-#include <asm/pgtable.h>
-#include <asm/cpm1.h>
-#endif
-
#include "fs_enet.h"
/*************************************************/
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c
index b6ed818..9d9b6e6 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.c
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.c
@@ -9,9 +9,9 @@
#include <linux/dma-mapping.h>
#include <linux/interrupt.h>
+#include <linux/of.h>
#include <linux/skbuff.h>
#include <linux/slab.h>
-
#include "hnae.h"
#define cls_to_ae_dev(dev) container_of(dev, struct hnae_ae_dev, cls_dev)
@@ -57,11 +57,15 @@ static int hnae_alloc_buffer(struct hnae_ring *ring, struct hnae_desc_cb *cb)
static void hnae_free_buffer(struct hnae_ring *ring, struct hnae_desc_cb *cb)
{
+ if (unlikely(!cb->priv))
+ return;
+
if (cb->type == DESC_TYPE_SKB)
dev_kfree_skb_any((struct sk_buff *)cb->priv);
else if (unlikely(is_rx_ring(ring)))
put_page((struct page *)cb->priv);
- memset(cb, 0, sizeof(*cb));
+
+ cb->priv = NULL;
}
static int hnae_map_buffer(struct hnae_ring *ring, struct hnae_desc_cb *cb)
@@ -197,6 +201,7 @@ hnae_init_ring(struct hnae_queue *q, struct hnae_ring *ring, int flags)
ring->q = q;
ring->flags = flags;
+ spin_lock_init(&ring->lock);
assert(!ring->desc && !ring->desc_cb && !ring->desc_dma_addr);
/* not matter for tx or rx ring, the ntc and ntc start from 0 */
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h
index 8016854..04211ac 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.h
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.h
@@ -67,6 +67,8 @@ do { \
#define AE_IS_VER1(ver) ((ver) == AE_VERSION_1)
#define AE_NAME_SIZE 16
+#define BD_SIZE_2048_MAX_MTU 6000
+
/* some said the RX and TX RCB format should not be the same in the future. But
* it is the same now...
*/
@@ -101,7 +103,6 @@ enum hnae_led_state {
#define HNS_RX_FLAG_L4ID_TCP 0x1
#define HNS_RX_FLAG_L4ID_SCTP 0x3
-
#define HNS_TXD_ASID_S 0
#define HNS_TXD_ASID_M (0xff << HNS_TXD_ASID_S)
#define HNS_TXD_BUFNUM_S 8
@@ -273,6 +274,9 @@ struct hnae_ring {
/* statistic */
struct ring_stats stats;
+ /* ring lock for poll one */
+ spinlock_t lock;
+
dma_addr_t desc_dma_addr;
u32 buf_size; /* size for hnae_desc->addr, preset by AE */
u16 desc_num; /* total number of desc */
@@ -483,11 +487,11 @@ struct hnae_ae_ops {
u32 auto_neg, u32 rx_en, u32 tx_en);
void (*get_coalesce_usecs)(struct hnae_handle *handle,
u32 *tx_usecs, u32 *rx_usecs);
- void (*get_rx_max_coalesced_frames)(struct hnae_handle *handle,
- u32 *tx_frames, u32 *rx_frames);
+ void (*get_max_coalesced_frames)(struct hnae_handle *handle,
+ u32 *tx_frames, u32 *rx_frames);
int (*set_coalesce_usecs)(struct hnae_handle *handle, u32 timeout);
int (*set_coalesce_frames)(struct hnae_handle *handle,
- u32 coalesce_frames);
+ u32 tx_frames, u32 rx_frames);
void (*get_coalesce_range)(struct hnae_handle *handle,
u32 *tx_frames_low, u32 *rx_frames_low,
u32 *tx_frames_high, u32 *rx_frames_high,
@@ -646,6 +650,41 @@ static inline void hnae_reuse_buffer(struct hnae_ring *ring, int i)
ring->desc[i].rx.ipoff_bnum_pid_flag = 0;
}
+/* when reinit buffer size, we should reinit buffer description */
+static inline void hnae_reinit_all_ring_desc(struct hnae_handle *h)
+{
+ int i, j;
+ struct hnae_ring *ring;
+
+ for (i = 0; i < h->q_num; i++) {
+ ring = &h->qs[i]->rx_ring;
+ for (j = 0; j < ring->desc_num; j++)
+ ring->desc[j].addr = cpu_to_le64(ring->desc_cb[j].dma);
+ }
+
+ wmb(); /* commit all data before submit */
+}
+
+/* when reinit buffer size, we should reinit page offset */
+static inline void hnae_reinit_all_ring_page_off(struct hnae_handle *h)
+{
+ int i, j;
+ struct hnae_ring *ring;
+
+ for (i = 0; i < h->q_num; i++) {
+ ring = &h->qs[i]->rx_ring;
+ for (j = 0; j < ring->desc_num; j++) {
+ ring->desc_cb[j].page_offset = 0;
+ if (ring->desc[j].addr !=
+ cpu_to_le64(ring->desc_cb[j].dma))
+ ring->desc[j].addr =
+ cpu_to_le64(ring->desc_cb[j].dma);
+ }
+ }
+
+ wmb(); /* commit all data before submit */
+}
+
#define hnae_set_field(origin, mask, shift, val) \
do { \
(origin) &= (~(mask)); \
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
index 0a9cdf0..ff864a1 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
@@ -267,8 +267,32 @@ static int hns_ae_clr_multicast(struct hnae_handle *handle)
static int hns_ae_set_mtu(struct hnae_handle *handle, int new_mtu)
{
struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle);
+ struct hnae_queue *q;
+ u32 rx_buf_size;
+ int i, ret;
- return hns_mac_set_mtu(mac_cb, new_mtu);
+ /* when buf_size is 2048, max mtu is 6K for rx ring max bd num is 3. */
+ if (!AE_IS_VER1(mac_cb->dsaf_dev->dsaf_ver)) {
+ if (new_mtu <= BD_SIZE_2048_MAX_MTU)
+ rx_buf_size = 2048;
+ else
+ rx_buf_size = 4096;
+ } else {
+ rx_buf_size = mac_cb->dsaf_dev->buf_size;
+ }
+
+ ret = hns_mac_set_mtu(mac_cb, new_mtu, rx_buf_size);
+
+ if (!ret) {
+ /* reinit ring buf_size */
+ for (i = 0; i < handle->q_num; i++) {
+ q = handle->qs[i];
+ q->rx_ring.buf_size = rx_buf_size;
+ hns_rcb_set_rx_ring_bs(q, rx_buf_size);
+ }
+ }
+
+ return ret;
}
static void hns_ae_set_tso_stats(struct hnae_handle *handle, int enable)
@@ -463,15 +487,21 @@ static void hns_ae_get_coalesce_usecs(struct hnae_handle *handle,
ring_pair->port_id_in_comm);
}
-static void hns_ae_get_rx_max_coalesced_frames(struct hnae_handle *handle,
- u32 *tx_frames, u32 *rx_frames)
+static void hns_ae_get_max_coalesced_frames(struct hnae_handle *handle,
+ u32 *tx_frames, u32 *rx_frames)
{
struct ring_pair_cb *ring_pair =
container_of(handle->qs[0], struct ring_pair_cb, q);
+ struct dsaf_device *dsaf_dev = hns_ae_get_dsaf_dev(handle->dev);
- *tx_frames = hns_rcb_get_coalesced_frames(ring_pair->rcb_common,
- ring_pair->port_id_in_comm);
- *rx_frames = hns_rcb_get_coalesced_frames(ring_pair->rcb_common,
+ if (AE_IS_VER1(dsaf_dev->dsaf_ver) ||
+ handle->port_type == HNAE_PORT_DEBUG)
+ *tx_frames = hns_rcb_get_rx_coalesced_frames(
+ ring_pair->rcb_common, ring_pair->port_id_in_comm);
+ else
+ *tx_frames = hns_rcb_get_tx_coalesced_frames(
+ ring_pair->rcb_common, ring_pair->port_id_in_comm);
+ *rx_frames = hns_rcb_get_rx_coalesced_frames(ring_pair->rcb_common,
ring_pair->port_id_in_comm);
}
@@ -485,15 +515,34 @@ static int hns_ae_set_coalesce_usecs(struct hnae_handle *handle,
ring_pair->rcb_common, ring_pair->port_id_in_comm, timeout);
}
-static int hns_ae_set_coalesce_frames(struct hnae_handle *handle,
- u32 coalesce_frames)
+static int hns_ae_set_coalesce_frames(struct hnae_handle *handle,
+ u32 tx_frames, u32 rx_frames)
{
+ int ret;
struct ring_pair_cb *ring_pair =
container_of(handle->qs[0], struct ring_pair_cb, q);
+ struct dsaf_device *dsaf_dev = hns_ae_get_dsaf_dev(handle->dev);
- return hns_rcb_set_coalesced_frames(
- ring_pair->rcb_common,
- ring_pair->port_id_in_comm, coalesce_frames);
+ if (AE_IS_VER1(dsaf_dev->dsaf_ver) ||
+ handle->port_type == HNAE_PORT_DEBUG) {
+ if (tx_frames != rx_frames)
+ return -EINVAL;
+ return hns_rcb_set_rx_coalesced_frames(
+ ring_pair->rcb_common,
+ ring_pair->port_id_in_comm, rx_frames);
+ } else {
+ if (tx_frames != 1)
+ return -EINVAL;
+ ret = hns_rcb_set_tx_coalesced_frames(
+ ring_pair->rcb_common,
+ ring_pair->port_id_in_comm, tx_frames);
+ if (ret)
+ return ret;
+
+ return hns_rcb_set_rx_coalesced_frames(
+ ring_pair->rcb_common,
+ ring_pair->port_id_in_comm, rx_frames);
+ }
}
static void hns_ae_get_coalesce_range(struct hnae_handle *handle,
@@ -504,20 +553,27 @@ static void hns_ae_get_coalesce_range(struct hnae_handle *handle,
{
struct dsaf_device *dsaf_dev;
+ assert(handle);
+
dsaf_dev = hns_ae_get_dsaf_dev(handle->dev);
- *tx_frames_low = HNS_RCB_MIN_COALESCED_FRAMES;
- *rx_frames_low = HNS_RCB_MIN_COALESCED_FRAMES;
- *tx_frames_high =
- (dsaf_dev->desc_num - 1 > HNS_RCB_MAX_COALESCED_FRAMES) ?
- HNS_RCB_MAX_COALESCED_FRAMES : dsaf_dev->desc_num - 1;
- *rx_frames_high =
- (dsaf_dev->desc_num - 1 > HNS_RCB_MAX_COALESCED_FRAMES) ?
- HNS_RCB_MAX_COALESCED_FRAMES : dsaf_dev->desc_num - 1;
- *tx_usecs_low = 0;
- *rx_usecs_low = 0;
- *tx_usecs_high = HNS_RCB_MAX_COALESCED_USECS;
- *rx_usecs_high = HNS_RCB_MAX_COALESCED_USECS;
+ *tx_frames_low = HNS_RCB_TX_FRAMES_LOW;
+ *rx_frames_low = HNS_RCB_RX_FRAMES_LOW;
+
+ if (AE_IS_VER1(dsaf_dev->dsaf_ver) ||
+ handle->port_type == HNAE_PORT_DEBUG)
+ *tx_frames_high =
+ (dsaf_dev->desc_num - 1 > HNS_RCB_TX_FRAMES_HIGH) ?
+ HNS_RCB_TX_FRAMES_HIGH : dsaf_dev->desc_num - 1;
+ else
+ *tx_frames_high = 1;
+
+ *rx_frames_high = (dsaf_dev->desc_num - 1 > HNS_RCB_RX_FRAMES_HIGH) ?
+ HNS_RCB_RX_FRAMES_HIGH : dsaf_dev->desc_num - 1;
+ *tx_usecs_low = HNS_RCB_TX_USECS_LOW;
+ *rx_usecs_low = HNS_RCB_RX_USECS_LOW;
+ *tx_usecs_high = HNS_RCB_TX_USECS_HIGH;
+ *rx_usecs_high = HNS_RCB_RX_USECS_HIGH;
}
void hns_ae_update_stats(struct hnae_handle *handle,
@@ -802,8 +858,9 @@ static int hns_ae_get_rss(struct hnae_handle *handle, u32 *indir, u8 *key,
memcpy(key, ppe_cb->rss_key, HNS_PPEV2_RSS_KEY_SIZE);
/* update the current hash->queue mappings from the shadow RSS table */
- memcpy(indir, ppe_cb->rss_indir_table,
- HNS_PPEV2_RSS_IND_TBL_SIZE * sizeof(*indir));
+ if (indir)
+ memcpy(indir, ppe_cb->rss_indir_table,
+ HNS_PPEV2_RSS_IND_TBL_SIZE * sizeof(*indir));
return 0;
}
@@ -814,15 +871,19 @@ static int hns_ae_set_rss(struct hnae_handle *handle, const u32 *indir,
struct hns_ppe_cb *ppe_cb = hns_get_ppe_cb(handle);
/* set the RSS Hash Key if specififed by the user */
- if (key)
- hns_ppe_set_rss_key(ppe_cb, (u32 *)key);
+ if (key) {
+ memcpy(ppe_cb->rss_key, key, HNS_PPEV2_RSS_KEY_SIZE);
+ hns_ppe_set_rss_key(ppe_cb, ppe_cb->rss_key);
+ }
- /* update the shadow RSS table with user specified qids */
- memcpy(ppe_cb->rss_indir_table, indir,
- HNS_PPEV2_RSS_IND_TBL_SIZE * sizeof(*indir));
+ if (indir) {
+ /* update the shadow RSS table with user specified qids */
+ memcpy(ppe_cb->rss_indir_table, indir,
+ HNS_PPEV2_RSS_IND_TBL_SIZE * sizeof(*indir));
- /* now update the hardware */
- hns_ppe_set_indir_table(ppe_cb, ppe_cb->rss_indir_table);
+ /* now update the hardware */
+ hns_ppe_set_indir_table(ppe_cb, ppe_cb->rss_indir_table);
+ }
return 0;
}
@@ -846,7 +907,7 @@ static struct hnae_ae_ops hns_dsaf_ops = {
.get_autoneg = hns_ae_get_autoneg,
.set_pauseparam = hns_ae_set_pauseparam,
.get_coalesce_usecs = hns_ae_get_coalesce_usecs,
- .get_rx_max_coalesced_frames = hns_ae_get_rx_max_coalesced_frames,
+ .get_max_coalesced_frames = hns_ae_get_max_coalesced_frames,
.set_coalesce_usecs = hns_ae_set_coalesce_usecs,
.set_coalesce_frames = hns_ae_set_coalesce_frames,
.get_coalesce_range = hns_ae_get_coalesce_range,
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
index 3382441..74bd260 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
@@ -86,12 +86,11 @@ static void hns_gmac_disable(void *mac_drv, enum mac_commom_mode mode)
dsaf_set_dev_bit(drv, GMAC_PORT_EN_REG, GMAC_PORT_RX_EN_B, 0);
}
-/**
-*hns_gmac_get_en - get port enable
-*@mac_drv:mac device
-*@rx:rx enable
-*@tx:tx enable
-*/
+/* hns_gmac_get_en - get port enable
+ * @mac_drv:mac device
+ * @rx:rx enable
+ * @tx:tx enable
+ */
static void hns_gmac_get_en(void *mac_drv, u32 *rx, u32 *tx)
{
struct mac_driver *drv = (struct mac_driver *)mac_drv;
@@ -148,6 +147,17 @@ static void hns_gmac_config_max_frame_length(void *mac_drv, u16 newval)
GMAC_MAX_FRM_SIZE_S, newval);
}
+static void hns_gmac_config_pad_and_crc(void *mac_drv, u8 newval)
+{
+ u32 tx_ctrl;
+ struct mac_driver *drv = (struct mac_driver *)mac_drv;
+
+ tx_ctrl = dsaf_read_dev(drv, GMAC_TRANSMIT_CONTROL_REG);
+ dsaf_set_bit(tx_ctrl, GMAC_TX_PAD_EN_B, !!newval);
+ dsaf_set_bit(tx_ctrl, GMAC_TX_CRC_ADD_B, !!newval);
+ dsaf_write_dev(drv, GMAC_TRANSMIT_CONTROL_REG, tx_ctrl);
+}
+
static void hns_gmac_config_an_mode(void *mac_drv, u8 newval)
{
struct mac_driver *drv = (struct mac_driver *)mac_drv;
@@ -250,7 +260,6 @@ static void hns_gmac_get_pausefrm_cfg(void *mac_drv, u32 *rx_pause_en,
static int hns_gmac_adjust_link(void *mac_drv, enum mac_speed speed,
u32 full_duplex)
{
- u32 tx_ctrl;
struct mac_driver *drv = (struct mac_driver *)mac_drv;
dsaf_set_dev_bit(drv, GMAC_DUPLEX_TYPE_REG,
@@ -279,14 +288,6 @@ static int hns_gmac_adjust_link(void *mac_drv, enum mac_speed speed,
return -EINVAL;
}
- tx_ctrl = dsaf_read_dev(drv, GMAC_TRANSMIT_CONTROL_REG);
- dsaf_set_bit(tx_ctrl, GMAC_TX_PAD_EN_B, 1);
- dsaf_set_bit(tx_ctrl, GMAC_TX_CRC_ADD_B, 1);
- dsaf_write_dev(drv, GMAC_TRANSMIT_CONTROL_REG, tx_ctrl);
-
- dsaf_set_dev_bit(drv, GMAC_MODE_CHANGE_EN_REG,
- GMAC_MODE_CHANGE_EB_B, 1);
-
return 0;
}
@@ -325,6 +326,17 @@ static void hns_gmac_init(void *mac_drv)
hns_gmac_tx_loop_pkt_dis(mac_drv);
if (drv->mac_cb->mac_type == HNAE_PORT_DEBUG)
hns_gmac_set_uc_match(mac_drv, 0);
+
+ hns_gmac_config_pad_and_crc(mac_drv, 1);
+
+ dsaf_set_dev_bit(drv, GMAC_MODE_CHANGE_EN_REG,
+ GMAC_MODE_CHANGE_EB_B, 1);
+
+ /* reduce gmac tx water line to avoid gmac hang-up
+ * in speed 100M and duplex half.
+ */
+ dsaf_set_dev_field(drv, GMAC_TX_WATER_LINE_REG, GMAC_TX_WATER_LINE_MASK,
+ GMAC_TX_WATER_LINE_SHIFT, 8);
}
void hns_gmac_update_stats(void *mac_drv)
@@ -453,24 +465,6 @@ static int hns_gmac_config_loopback(void *mac_drv, enum hnae_loop loop_mode,
return 0;
}
-static void hns_gmac_config_pad_and_crc(void *mac_drv, u8 newval)
-{
- u32 tx_ctrl;
- struct mac_driver *drv = (struct mac_driver *)mac_drv;
-
- tx_ctrl = dsaf_read_dev(drv, GMAC_TRANSMIT_CONTROL_REG);
- dsaf_set_bit(tx_ctrl, GMAC_TX_PAD_EN_B, !!newval);
- dsaf_set_bit(tx_ctrl, GMAC_TX_CRC_ADD_B, !!newval);
- dsaf_write_dev(drv, GMAC_TRANSMIT_CONTROL_REG, tx_ctrl);
-}
-
-static void hns_gmac_get_id(void *mac_drv, u8 *mac_id)
-{
- struct mac_driver *drv = (struct mac_driver *)mac_drv;
-
- *mac_id = drv->mac_id;
-}
-
static void hns_gmac_get_info(void *mac_drv, struct mac_info *mac_info)
{
enum hns_gmac_duplex_mdoe duplex;
@@ -712,7 +706,6 @@ void *hns_gmac_config(struct hns_mac_cb *mac_cb, struct mac_params *mac_param)
mac_drv->config_pad_and_crc = hns_gmac_config_pad_and_crc;
mac_drv->config_half_duplex = hns_gmac_set_duplex_type;
mac_drv->set_rx_ignore_pause_frames = hns_gmac_set_rx_auto_pause_frames;
- mac_drv->mac_get_id = hns_gmac_get_id;
mac_drv->get_info = hns_gmac_get_info;
mac_drv->autoneg_stat = hns_gmac_autoneg_stat;
mac_drv->get_pause_enable = hns_gmac_get_pausefrm_cfg;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
index 3239d27..0c1f56e 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
@@ -82,9 +82,12 @@ void hns_mac_get_link_status(struct hns_mac_cb *mac_cb, u32 *link_status)
else
*link_status = 0;
- ret = mac_cb->dsaf_dev->misc_op->get_sfp_prsnt(mac_cb, &sfp_prsnt);
- if (!ret)
- *link_status = *link_status && sfp_prsnt;
+ if (mac_cb->media_type == HNAE_MEDIA_TYPE_FIBER) {
+ ret = mac_cb->dsaf_dev->misc_op->get_sfp_prsnt(mac_cb,
+ &sfp_prsnt);
+ if (!ret)
+ *link_status = *link_status && sfp_prsnt;
+ }
mac_cb->link = *link_status;
}
@@ -332,44 +335,6 @@ int hns_mac_set_multi(struct hns_mac_cb *mac_cb,
return 0;
}
-/**
- *hns_mac_del_mac - delete mac address into dsaf table,can't delete the same
- * address twice
- *@net_dev: net device
- *@vfn : vf lan
- *@mac : mac address
- *return status
- */
-int hns_mac_del_mac(struct hns_mac_cb *mac_cb, u32 vfn, char *mac)
-{
- struct mac_entry_idx *old_mac;
- struct dsaf_device *dsaf_dev;
- u32 ret;
-
- dsaf_dev = mac_cb->dsaf_dev;
-
- if (vfn < DSAF_MAX_VM_NUM) {
- old_mac = &mac_cb->addr_entry_idx[vfn];
- } else {
- dev_err(mac_cb->dev,
- "vf queue is too large, %s mac%d queue = %#x!\n",
- mac_cb->dsaf_dev->ae_dev.name, mac_cb->mac_id, vfn);
- return -EINVAL;
- }
-
- if (dsaf_dev) {
- ret = hns_dsaf_del_mac_entry(dsaf_dev, old_mac->vlan_id,
- mac_cb->mac_id, old_mac->addr);
- if (ret)
- return ret;
-
- if (memcmp(old_mac->addr, mac, sizeof(old_mac->addr)) == 0)
- old_mac->valid = 0;
- }
-
- return 0;
-}
-
int hns_mac_clr_multicast(struct hns_mac_cb *mac_cb, int vfn)
{
struct dsaf_device *dsaf_dev = mac_cb->dsaf_dev;
@@ -491,10 +456,9 @@ void hns_mac_reset(struct hns_mac_cb *mac_cb)
}
}
-int hns_mac_set_mtu(struct hns_mac_cb *mac_cb, u32 new_mtu)
+int hns_mac_set_mtu(struct hns_mac_cb *mac_cb, u32 new_mtu, u32 buf_size)
{
struct mac_driver *drv = hns_mac_get_drv(mac_cb);
- u32 buf_size = mac_cb->dsaf_dev->buf_size;
u32 new_frm = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
u32 max_frm = AE_IS_VER1(mac_cb->dsaf_dev->dsaf_ver) ?
MAC_MAX_MTU : MAC_MAX_MTU_V2;
@@ -855,7 +819,7 @@ static int hns_mac_get_info(struct hns_mac_cb *mac_cb)
of_node_put(np);
np = of_parse_phandle(to_of_node(mac_cb->fw_port),
- "serdes-syscon", 0);
+ "serdes-syscon", 0);
syscon = syscon_node_to_regmap(np);
of_node_put(np);
if (IS_ERR_OR_NULL(syscon)) {
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
index 2bb3d1e..24dfba5 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
@@ -373,8 +373,6 @@ struct mac_driver {
void (*set_rx_ignore_pause_frames)(void *mac_drv, u32 enable);
/* config rx mode for promiscuous*/
void (*set_promiscuous)(void *mac_drv, u8 enable);
- /* get mac id */
- void (*mac_get_id)(void *mac_drv, u8 *mac_id);
void (*mac_pausefrm_cfg)(void *mac_drv, u32 rx_en, u32 tx_en);
void (*autoneg_stat)(void *mac_drv, u32 *enable);
@@ -436,7 +434,6 @@ int hns_mac_set_multi(struct hns_mac_cb *mac_cb,
int hns_mac_vm_config_bc_en(struct hns_mac_cb *mac_cb, u32 vm, bool enable);
void hns_mac_start(struct hns_mac_cb *mac_cb);
void hns_mac_stop(struct hns_mac_cb *mac_cb);
-int hns_mac_del_mac(struct hns_mac_cb *mac_cb, u32 vfn, char *mac);
void hns_mac_uninit(struct dsaf_device *dsaf_dev);
void hns_mac_adjust_link(struct hns_mac_cb *mac_cb, int speed, int duplex);
void hns_mac_reset(struct hns_mac_cb *mac_cb);
@@ -444,7 +441,7 @@ void hns_mac_get_autoneg(struct hns_mac_cb *mac_cb, u32 *auto_neg);
void hns_mac_get_pauseparam(struct hns_mac_cb *mac_cb, u32 *rx_en, u32 *tx_en);
int hns_mac_set_autoneg(struct hns_mac_cb *mac_cb, u8 enable);
int hns_mac_set_pauseparam(struct hns_mac_cb *mac_cb, u32 rx_en, u32 tx_en);
-int hns_mac_set_mtu(struct hns_mac_cb *mac_cb, u32 new_mtu);
+int hns_mac_set_mtu(struct hns_mac_cb *mac_cb, u32 new_mtu, u32 buf_size);
int hns_mac_get_port_info(struct hns_mac_cb *mac_cb,
u8 *auto_neg, u16 *speed, u8 *duplex);
int hns_mac_config_mac_loopback(struct hns_mac_cb *mac_cb,
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
index 90dbda7..e0bc79e 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
@@ -510,10 +510,10 @@ static void hns_dsafv2_sbm_bp_wl_cfg(struct dsaf_device *dsaf_dev)
o_sbm_bp_cfg = dsaf_read_dev(dsaf_dev, reg);
dsaf_set_field(o_sbm_bp_cfg,
DSAFV2_SBM_CFG3_SET_BUF_NUM_NO_PFC_M,
- DSAFV2_SBM_CFG3_SET_BUF_NUM_NO_PFC_S, 48);
+ DSAFV2_SBM_CFG3_SET_BUF_NUM_NO_PFC_S, 55);
dsaf_set_field(o_sbm_bp_cfg,
DSAFV2_SBM_CFG3_RESET_BUF_NUM_NO_PFC_M,
- DSAFV2_SBM_CFG3_RESET_BUF_NUM_NO_PFC_S, 80);
+ DSAFV2_SBM_CFG3_RESET_BUF_NUM_NO_PFC_S, 110);
dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg);
/* for no enable pfc mode */
@@ -521,10 +521,10 @@ static void hns_dsafv2_sbm_bp_wl_cfg(struct dsaf_device *dsaf_dev)
o_sbm_bp_cfg = dsaf_read_dev(dsaf_dev, reg);
dsaf_set_field(o_sbm_bp_cfg,
DSAFV2_SBM_CFG4_SET_BUF_NUM_NO_PFC_M,
- DSAFV2_SBM_CFG4_SET_BUF_NUM_NO_PFC_S, 192);
+ DSAFV2_SBM_CFG4_SET_BUF_NUM_NO_PFC_S, 128);
dsaf_set_field(o_sbm_bp_cfg,
DSAFV2_SBM_CFG4_RESET_BUF_NUM_NO_PFC_M,
- DSAFV2_SBM_CFG4_RESET_BUF_NUM_NO_PFC_S, 240);
+ DSAFV2_SBM_CFG4_RESET_BUF_NUM_NO_PFC_S, 192);
dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg);
}
@@ -1519,6 +1519,7 @@ static void hns_dsaf_set_mac_key(
mac_key->high.bits.mac_3 = addr[3];
mac_key->low.bits.mac_4 = addr[4];
mac_key->low.bits.mac_5 = addr[5];
+ mac_key->low.bits.port_vlan = 0;
dsaf_set_field(mac_key->low.bits.port_vlan, DSAF_TBL_TCAM_KEY_VLAN_M,
DSAF_TBL_TCAM_KEY_VLAN_S, vlan_id);
dsaf_set_field(mac_key->low.bits.port_vlan, DSAF_TBL_TCAM_KEY_PORT_M,
@@ -1647,87 +1648,6 @@ int hns_dsaf_rm_mac_addr(
mac_entry->addr);
}
-/**
- * hns_dsaf_set_mac_mc_entry - set mac mc-entry
- * @dsaf_dev: dsa fabric device struct pointer
- * @mac_entry: mc-mac entry
- */
-int hns_dsaf_set_mac_mc_entry(
- struct dsaf_device *dsaf_dev,
- struct dsaf_drv_mac_multi_dest_entry *mac_entry)
-{
- u16 entry_index = DSAF_INVALID_ENTRY_IDX;
- struct dsaf_drv_tbl_tcam_key mac_key;
- struct dsaf_tbl_tcam_mcast_cfg mac_data;
- struct dsaf_drv_priv *priv =
- (struct dsaf_drv_priv *)hns_dsaf_dev_priv(dsaf_dev);
- struct dsaf_drv_soft_mac_tbl *soft_mac_entry = priv->soft_mac_tbl;
- struct dsaf_drv_tbl_tcam_key tmp_mac_key;
- struct dsaf_tbl_tcam_data tcam_data;
-
- /* mac addr check */
- if (MAC_IS_ALL_ZEROS(mac_entry->addr)) {
- dev_err(dsaf_dev->dev, "set uc %s Mac %pM err!\n",
- dsaf_dev->ae_dev.name, mac_entry->addr);
- return -EINVAL;
- }
-
- /*config key */
- hns_dsaf_set_mac_key(dsaf_dev, &mac_key,
- mac_entry->in_vlan_id,
- mac_entry->in_port_num, mac_entry->addr);
-
- /* entry ie exist? */
- entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key);
- if (entry_index == DSAF_INVALID_ENTRY_IDX) {
- /*if hasnot, find enpty entry*/
- entry_index = hns_dsaf_find_empty_mac_entry(dsaf_dev);
- if (entry_index == DSAF_INVALID_ENTRY_IDX) {
- /*if hasnot empty, error*/
- dev_err(dsaf_dev->dev,
- "set_uc_entry failed, %s Mac key(%#x:%#x)\n",
- dsaf_dev->ae_dev.name,
- mac_key.high.val, mac_key.low.val);
- return -EINVAL;
- }
-
- /* config hardware entry */
- memset(mac_data.tbl_mcast_port_msk,
- 0, sizeof(mac_data.tbl_mcast_port_msk));
- } else {
- /* config hardware entry */
- hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data,
- &mac_data);
-
- tmp_mac_key.high.val =
- le32_to_cpu(tcam_data.tbl_tcam_data_high);
- tmp_mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
- }
- mac_data.tbl_mcast_old_en = 0;
- mac_data.tbl_mcast_item_vld = 1;
- dsaf_set_field(mac_data.tbl_mcast_port_msk[0],
- 0x3F, 0, mac_entry->port_mask[0]);
-
- dev_dbg(dsaf_dev->dev,
- "set_uc_entry, %s key(%#x:%#x) entry_index%d\n",
- dsaf_dev->ae_dev.name, mac_key.high.val,
- mac_key.low.val, entry_index);
-
- tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val);
- tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val);
-
- hns_dsaf_tcam_mc_cfg(dsaf_dev, entry_index, &tcam_data, NULL,
- &mac_data);
-
- /* config software entry */
- soft_mac_entry += entry_index;
- soft_mac_entry->index = entry_index;
- soft_mac_entry->tcam_key.high.val = mac_key.high.val;
- soft_mac_entry->tcam_key.low.val = mac_key.low.val;
-
- return 0;
-}
-
static void hns_dsaf_mc_mask_bit_clear(char *dst, const char *src)
{
u16 *a = (u16 *)dst;
@@ -2089,166 +2009,6 @@ int hns_dsaf_clr_mac_mc_port(struct dsaf_device *dsaf_dev, u8 mac_id,
return ret;
}
-/**
- * hns_dsaf_get_mac_uc_entry - get mac uc entry
- * @dsaf_dev: dsa fabric device struct pointer
- * @mac_entry: mac entry
- */
-int hns_dsaf_get_mac_uc_entry(struct dsaf_device *dsaf_dev,
- struct dsaf_drv_mac_single_dest_entry *mac_entry)
-{
- u16 entry_index = DSAF_INVALID_ENTRY_IDX;
- struct dsaf_drv_tbl_tcam_key mac_key;
-
- struct dsaf_tbl_tcam_ucast_cfg mac_data;
- struct dsaf_tbl_tcam_data tcam_data;
-
- /* check macaddr */
- if (MAC_IS_ALL_ZEROS(mac_entry->addr) ||
- MAC_IS_BROADCAST(mac_entry->addr)) {
- dev_err(dsaf_dev->dev, "get_entry failed,addr %pM\n",
- mac_entry->addr);
- return -EINVAL;
- }
-
- /*config key */
- hns_dsaf_set_mac_key(dsaf_dev, &mac_key, mac_entry->in_vlan_id,
- mac_entry->in_port_num, mac_entry->addr);
-
- /*check exist? */
- entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key);
- if (entry_index == DSAF_INVALID_ENTRY_IDX) {
- /*find none, error */
- dev_err(dsaf_dev->dev,
- "get_uc_entry failed, %s Mac key(%#x:%#x)\n",
- dsaf_dev->ae_dev.name,
- mac_key.high.val, mac_key.low.val);
- return -EINVAL;
- }
- dev_dbg(dsaf_dev->dev,
- "get_uc_entry, %s Mac key(%#x:%#x) entry_index%d\n",
- dsaf_dev->ae_dev.name, mac_key.high.val,
- mac_key.low.val, entry_index);
-
- /* read entry */
- hns_dsaf_tcam_uc_get(dsaf_dev, entry_index, &tcam_data, &mac_data);
-
- mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high);
- mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
-
- mac_entry->port_num = mac_data.tbl_ucast_out_port;
-
- return 0;
-}
-
-/**
- * hns_dsaf_get_mac_mc_entry - get mac mc entry
- * @dsaf_dev: dsa fabric device struct pointer
- * @mac_entry: mac entry
- */
-int hns_dsaf_get_mac_mc_entry(struct dsaf_device *dsaf_dev,
- struct dsaf_drv_mac_multi_dest_entry *mac_entry)
-{
- u16 entry_index = DSAF_INVALID_ENTRY_IDX;
- struct dsaf_drv_tbl_tcam_key mac_key;
-
- struct dsaf_tbl_tcam_mcast_cfg mac_data;
- struct dsaf_tbl_tcam_data tcam_data;
-
- /*check mac addr */
- if (MAC_IS_ALL_ZEROS(mac_entry->addr) ||
- MAC_IS_BROADCAST(mac_entry->addr)) {
- dev_err(dsaf_dev->dev, "get_entry failed,addr %pM\n",
- mac_entry->addr);
- return -EINVAL;
- }
-
- /*config key */
- hns_dsaf_set_mac_key(dsaf_dev, &mac_key, mac_entry->in_vlan_id,
- mac_entry->in_port_num, mac_entry->addr);
-
- /*check exist? */
- entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key);
- if (entry_index == DSAF_INVALID_ENTRY_IDX) {
- /* find none, error */
- dev_err(dsaf_dev->dev,
- "get_mac_uc_entry failed, %s Mac key(%#x:%#x)\n",
- dsaf_dev->ae_dev.name, mac_key.high.val,
- mac_key.low.val);
- return -EINVAL;
- }
- dev_dbg(dsaf_dev->dev,
- "get_mac_uc_entry, %s Mac key(%#x:%#x) entry_index%d\n",
- dsaf_dev->ae_dev.name, mac_key.high.val,
- mac_key.low.val, entry_index);
-
- /*read entry */
- hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data, &mac_data);
-
- mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high);
- mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
-
- mac_entry->port_mask[0] = mac_data.tbl_mcast_port_msk[0] & 0x3F;
- return 0;
-}
-
-/**
- * hns_dsaf_get_mac_entry_by_index - get mac entry by tab index
- * @dsaf_dev: dsa fabric device struct pointer
- * @entry_index: tab entry index
- * @mac_entry: mac entry
- */
-int hns_dsaf_get_mac_entry_by_index(
- struct dsaf_device *dsaf_dev,
- u16 entry_index, struct dsaf_drv_mac_multi_dest_entry *mac_entry)
-{
- struct dsaf_drv_tbl_tcam_key mac_key;
-
- struct dsaf_tbl_tcam_mcast_cfg mac_data;
- struct dsaf_tbl_tcam_ucast_cfg mac_uc_data;
- struct dsaf_tbl_tcam_data tcam_data;
- char mac_addr[ETH_ALEN] = {0};
-
- if (entry_index >= dsaf_dev->tcam_max_num) {
- /* find none, del error */
- dev_err(dsaf_dev->dev, "get_uc_entry failed, %s\n",
- dsaf_dev->ae_dev.name);
- return -EINVAL;
- }
-
- /* mc entry, do read opt */
- hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data, &mac_data);
-
- mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high);
- mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
-
- mac_entry->port_mask[0] = mac_data.tbl_mcast_port_msk[0] & 0x3F;
-
- /***get mac addr*/
- mac_addr[0] = mac_key.high.bits.mac_0;
- mac_addr[1] = mac_key.high.bits.mac_1;
- mac_addr[2] = mac_key.high.bits.mac_2;
- mac_addr[3] = mac_key.high.bits.mac_3;
- mac_addr[4] = mac_key.low.bits.mac_4;
- mac_addr[5] = mac_key.low.bits.mac_5;
- /**is mc or uc*/
- if (MAC_IS_MULTICAST((u8 *)mac_addr) ||
- MAC_IS_L3_MULTICAST((u8 *)mac_addr)) {
- /**mc donot do*/
- } else {
- /*is not mc, just uc... */
- hns_dsaf_tcam_uc_get(dsaf_dev, entry_index, &tcam_data,
- &mac_uc_data);
-
- mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high);
- mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
-
- mac_entry->port_mask[0] = (1 << mac_uc_data.tbl_ucast_out_port);
- }
-
- return 0;
-}
-
static struct dsaf_device *hns_dsaf_alloc_dev(struct device *dev,
size_t sizeof_priv)
{
@@ -2924,10 +2684,11 @@ void hns_dsaf_set_promisc_tcam(struct dsaf_device *dsaf_dev,
/* find the tcam entry index for promisc */
entry_index = dsaf_promisc_tcam_entry(port);
+ memset(&tbl_tcam_data, 0, sizeof(tbl_tcam_data));
+ memset(&tbl_tcam_mask, 0, sizeof(tbl_tcam_mask));
+
/* config key mask */
if (enable) {
- memset(&tbl_tcam_data, 0, sizeof(tbl_tcam_data));
- memset(&tbl_tcam_mask, 0, sizeof(tbl_tcam_mask));
dsaf_set_field(tbl_tcam_data.low.bits.port_vlan,
DSAF_TBL_TCAM_KEY_PORT_M,
DSAF_TBL_TCAM_KEY_PORT_S, port);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
index cef6bf4..4507e82 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
@@ -68,7 +68,7 @@ enum dsaf_roce_qos_sl {
};
#define DSAF_STATS_READ(p, offset) (*((u64 *)((u8 *)(p) + (offset))))
-#define HNS_DSAF_IS_DEBUG(dev) (dev->dsaf_mode == DSAF_MODE_DISABLE_SP)
+#define HNS_DSAF_IS_DEBUG(dev) ((dev)->dsaf_mode == DSAF_MODE_DISABLE_SP)
enum hal_dsaf_mode {
HRD_DSAF_NO_DSAF_MODE = 0x0,
@@ -429,23 +429,12 @@ static inline struct hnae_vf_cb *hns_ae_get_vf_cb(
int hns_dsaf_set_mac_uc_entry(struct dsaf_device *dsaf_dev,
struct dsaf_drv_mac_single_dest_entry *mac_entry);
-int hns_dsaf_set_mac_mc_entry(struct dsaf_device *dsaf_dev,
- struct dsaf_drv_mac_multi_dest_entry *mac_entry);
int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev,
struct dsaf_drv_mac_single_dest_entry *mac_entry);
int hns_dsaf_del_mac_entry(struct dsaf_device *dsaf_dev, u16 vlan_id,
u8 in_port_num, u8 *addr);
int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev,
struct dsaf_drv_mac_single_dest_entry *mac_entry);
-int hns_dsaf_get_mac_uc_entry(struct dsaf_device *dsaf_dev,
- struct dsaf_drv_mac_single_dest_entry *mac_entry);
-int hns_dsaf_get_mac_mc_entry(struct dsaf_device *dsaf_dev,
- struct dsaf_drv_mac_multi_dest_entry *mac_entry);
-int hns_dsaf_get_mac_entry_by_index(
- struct dsaf_device *dsaf_dev,
- u16 entry_index,
- struct dsaf_drv_mac_multi_dest_entry *mac_entry);
-
void hns_dsaf_fix_mac_mode(struct hns_mac_cb *mac_cb);
int hns_dsaf_ae_init(struct dsaf_device *dsaf_dev);
@@ -475,5 +464,4 @@ int hns_dsaf_rm_mac_addr(
int hns_dsaf_clr_mac_mc_port(struct dsaf_device *dsaf_dev,
u8 mac_id, u8 port_num);
-
#endif /* __HNS_DSAF_MAIN_H__ */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
index a2c22d0..e13aa06 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
@@ -461,6 +461,32 @@ int hns_mac_get_sfp_prsnt(struct hns_mac_cb *mac_cb, int *sfp_prsnt)
return 0;
}
+int hns_mac_get_sfp_prsnt_acpi(struct hns_mac_cb *mac_cb, int *sfp_prsnt)
+{
+ union acpi_object *obj;
+ union acpi_object obj_args, argv4;
+
+ obj_args.integer.type = ACPI_TYPE_INTEGER;
+ obj_args.integer.value = mac_cb->mac_id;
+
+ argv4.type = ACPI_TYPE_PACKAGE,
+ argv4.package.count = 1,
+ argv4.package.elements = &obj_args,
+
+ obj = acpi_evaluate_dsm(ACPI_HANDLE(mac_cb->dev),
+ hns_dsaf_acpi_dsm_uuid, 0,
+ HNS_OP_GET_SFP_STAT_FUNC, &argv4);
+
+ if (!obj || obj->type != ACPI_TYPE_INTEGER)
+ return -ENODEV;
+
+ *sfp_prsnt = obj->integer.value;
+
+ ACPI_FREE(obj);
+
+ return 0;
+}
+
/**
* hns_mac_config_sds_loopback - set loop back for serdes
* @mac_cb: mac control block
@@ -592,7 +618,7 @@ struct dsaf_misc_op *hns_misc_op_get(struct dsaf_device *dsaf_dev)
misc_op->hns_dsaf_roce_srst = hns_dsaf_roce_srst_acpi;
misc_op->get_phy_if = hns_mac_get_phy_if_acpi;
- misc_op->get_sfp_prsnt = hns_mac_get_sfp_prsnt;
+ misc_op->get_sfp_prsnt = hns_mac_get_sfp_prsnt_acpi;
misc_op->cfg_serdes_loopback = hns_mac_config_sds_loopback_acpi;
} else {
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
index 6ea8722..eba406b 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
@@ -496,17 +496,17 @@ void hns_ppe_get_stats(struct hns_ppe_cb *ppe_cb, u64 *data)
*/
int hns_ppe_init(struct dsaf_device *dsaf_dev)
{
- int i, k;
int ret;
+ int i;
for (i = 0; i < HNS_PPE_COM_NUM; i++) {
ret = hns_ppe_common_get_cfg(dsaf_dev, i);
if (ret)
- goto get_ppe_cfg_fail;
+ goto get_cfg_fail;
ret = hns_rcb_common_get_cfg(dsaf_dev, i);
if (ret)
- goto get_rcb_cfg_fail;
+ goto get_cfg_fail;
hns_ppe_get_cfg(dsaf_dev->ppe_common[i]);
@@ -518,13 +518,12 @@ int hns_ppe_init(struct dsaf_device *dsaf_dev)
return 0;
-get_rcb_cfg_fail:
- hns_ppe_common_free_cfg(dsaf_dev, i);
-get_ppe_cfg_fail:
- for (k = i - 1; k >= 0; k--) {
- hns_rcb_common_free_cfg(dsaf_dev, k);
- hns_ppe_common_free_cfg(dsaf_dev, k);
+get_cfg_fail:
+ for (i = 0; i < HNS_PPE_COM_NUM; i++) {
+ hns_rcb_common_free_cfg(dsaf_dev, i);
+ hns_ppe_common_free_cfg(dsaf_dev, i);
}
+
return ret;
}
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
index f0ed80d6..c20a0f4 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
@@ -32,6 +32,9 @@
#define RCB_RESET_WAIT_TIMES 30
#define RCB_RESET_TRY_TIMES 10
+/* Because default mtu is 1500, rcb buffer size is set to 2048 enough */
+#define RCB_DEFAULT_BUFFER_SIZE 2048
+
/**
*hns_rcb_wait_fbd_clean - clean fbd
*@qs: ring struct pointer array
@@ -192,6 +195,30 @@ void hns_rcb_common_init_commit_hw(struct rcb_common_cb *rcb_common)
wmb(); /* Sync point after breakpoint */
}
+/* hns_rcb_set_tx_ring_bs - init rcb ring buf size regester
+ *@q: hnae_queue
+ *@buf_size: buffer size set to hw
+ */
+void hns_rcb_set_tx_ring_bs(struct hnae_queue *q, u32 buf_size)
+{
+ u32 bd_size_type = hns_rcb_buf_size2type(buf_size);
+
+ dsaf_write_dev(q, RCB_RING_TX_RING_BD_LEN_REG,
+ bd_size_type);
+}
+
+/* hns_rcb_set_rx_ring_bs - init rcb ring buf size regester
+ *@q: hnae_queue
+ *@buf_size: buffer size set to hw
+ */
+void hns_rcb_set_rx_ring_bs(struct hnae_queue *q, u32 buf_size)
+{
+ u32 bd_size_type = hns_rcb_buf_size2type(buf_size);
+
+ dsaf_write_dev(q, RCB_RING_RX_RING_BD_LEN_REG,
+ bd_size_type);
+}
+
/**
*hns_rcb_ring_init - init rcb ring
*@ring_pair: ring pair control block
@@ -200,8 +227,6 @@ void hns_rcb_common_init_commit_hw(struct rcb_common_cb *rcb_common)
static void hns_rcb_ring_init(struct ring_pair_cb *ring_pair, int ring_type)
{
struct hnae_queue *q = &ring_pair->q;
- struct rcb_common_cb *rcb_common = ring_pair->rcb_common;
- u32 bd_size_type = rcb_common->dsaf_dev->buf_size_type;
struct hnae_ring *ring =
(ring_type == RX_RING) ? &q->rx_ring : &q->tx_ring;
dma_addr_t dma = ring->desc_dma_addr;
@@ -212,8 +237,8 @@ static void hns_rcb_ring_init(struct ring_pair_cb *ring_pair, int ring_type)
dsaf_write_dev(q, RCB_RING_RX_RING_BASEADDR_H_REG,
(u32)((dma >> 31) >> 1));
- dsaf_write_dev(q, RCB_RING_RX_RING_BD_LEN_REG,
- bd_size_type);
+ hns_rcb_set_rx_ring_bs(q, ring->buf_size);
+
dsaf_write_dev(q, RCB_RING_RX_RING_BD_NUM_REG,
ring_pair->port_id_in_comm);
dsaf_write_dev(q, RCB_RING_RX_RING_PKTLINE_REG,
@@ -224,12 +249,12 @@ static void hns_rcb_ring_init(struct ring_pair_cb *ring_pair, int ring_type)
dsaf_write_dev(q, RCB_RING_TX_RING_BASEADDR_H_REG,
(u32)((dma >> 31) >> 1));
- dsaf_write_dev(q, RCB_RING_TX_RING_BD_LEN_REG,
- bd_size_type);
+ hns_rcb_set_tx_ring_bs(q, ring->buf_size);
+
dsaf_write_dev(q, RCB_RING_TX_RING_BD_NUM_REG,
ring_pair->port_id_in_comm);
dsaf_write_dev(q, RCB_RING_TX_RING_PKTLINE_REG,
- ring_pair->port_id_in_comm);
+ ring_pair->port_id_in_comm + HNS_RCB_TX_PKTLINE_OFFSET);
}
}
@@ -259,13 +284,27 @@ static void hns_rcb_set_port_desc_cnt(struct rcb_common_cb *rcb_common,
static void hns_rcb_set_port_timeout(
struct rcb_common_cb *rcb_common, u32 port_idx, u32 timeout)
{
- if (AE_IS_VER1(rcb_common->dsaf_dev->dsaf_ver))
+ if (AE_IS_VER1(rcb_common->dsaf_dev->dsaf_ver)) {
dsaf_write_dev(rcb_common, RCB_CFG_OVERTIME_REG,
timeout * HNS_RCB_CLK_FREQ_MHZ);
- else
+ } else if (!HNS_DSAF_IS_DEBUG(rcb_common->dsaf_dev)) {
+ if (timeout > HNS_RCB_DEF_GAP_TIME_USECS)
+ dsaf_write_dev(rcb_common,
+ RCB_PORT_INT_GAPTIME_REG + port_idx * 4,
+ HNS_RCB_DEF_GAP_TIME_USECS);
+ else
+ dsaf_write_dev(rcb_common,
+ RCB_PORT_INT_GAPTIME_REG + port_idx * 4,
+ timeout);
+
dsaf_write_dev(rcb_common,
RCB_PORT_CFG_OVERTIME_REG + port_idx * 4,
timeout);
+ } else {
+ dsaf_write_dev(rcb_common,
+ RCB_PORT_CFG_OVERTIME_REG + port_idx * 4,
+ timeout);
+ }
}
static int hns_rcb_common_get_port_num(struct rcb_common_cb *rcb_common)
@@ -327,8 +366,12 @@ int hns_rcb_common_init_hw(struct rcb_common_cb *rcb_common)
for (i = 0; i < port_num; i++) {
hns_rcb_set_port_desc_cnt(rcb_common, i, rcb_common->desc_num);
- (void)hns_rcb_set_coalesced_frames(
- rcb_common, i, HNS_RCB_DEF_COALESCED_FRAMES);
+ hns_rcb_set_rx_coalesced_frames(
+ rcb_common, i, HNS_RCB_DEF_RX_COALESCED_FRAMES);
+ if (!AE_IS_VER1(rcb_common->dsaf_dev->dsaf_ver) &&
+ !HNS_DSAF_IS_DEBUG(rcb_common->dsaf_dev))
+ hns_rcb_set_tx_coalesced_frames(
+ rcb_common, i, HNS_RCB_DEF_TX_COALESCED_FRAMES);
hns_rcb_set_port_timeout(
rcb_common, i, HNS_RCB_DEF_COALESCED_USECS);
}
@@ -380,7 +423,6 @@ static void hns_rcb_ring_get_cfg(struct hnae_queue *q, int ring_type)
struct hnae_ring *ring;
struct rcb_common_cb *rcb_common;
struct ring_pair_cb *ring_pair_cb;
- u32 buf_size;
u16 desc_num, mdnum_ppkt;
bool irq_idx, is_ver1;
@@ -401,7 +443,6 @@ static void hns_rcb_ring_get_cfg(struct hnae_queue *q, int ring_type)
}
rcb_common = ring_pair_cb->rcb_common;
- buf_size = rcb_common->dsaf_dev->buf_size;
desc_num = rcb_common->dsaf_dev->desc_num;
ring->desc = NULL;
@@ -410,7 +451,7 @@ static void hns_rcb_ring_get_cfg(struct hnae_queue *q, int ring_type)
ring->irq = ring_pair_cb->virq[irq_idx];
ring->desc_dma_addr = 0;
- ring->buf_size = buf_size;
+ ring->buf_size = RCB_DEFAULT_BUFFER_SIZE;
ring->desc_num = desc_num;
ring->max_desc_num_per_pkt = mdnum_ppkt;
ring->max_raw_data_sz_per_desc = HNS_RCB_MAX_PKT_SIZE;
@@ -430,7 +471,6 @@ static void hns_rcb_ring_pair_get_cfg(struct ring_pair_cb *ring_pair_cb)
static int hns_rcb_get_port_in_comm(
struct rcb_common_cb *rcb_common, int ring_idx)
{
-
return ring_idx / (rcb_common->max_q_per_vf * rcb_common->max_vfn);
}
@@ -484,19 +524,35 @@ void hns_rcb_get_cfg(struct rcb_common_cb *rcb_common)
}
/**
- *hns_rcb_get_coalesced_frames - get rcb port coalesced frames
+ *hns_rcb_get_rx_coalesced_frames - get rcb port rx coalesced frames
*@rcb_common: rcb_common device
*@port_idx:port id in comm
*
*Returns: coalesced_frames
*/
-u32 hns_rcb_get_coalesced_frames(
+u32 hns_rcb_get_rx_coalesced_frames(
struct rcb_common_cb *rcb_common, u32 port_idx)
{
return dsaf_read_dev(rcb_common, RCB_CFG_PKTLINE_REG + port_idx * 4);
}
/**
+ *hns_rcb_get_tx_coalesced_frames - get rcb port tx coalesced frames
+ *@rcb_common: rcb_common device
+ *@port_idx:port id in comm
+ *
+ *Returns: coalesced_frames
+ */
+u32 hns_rcb_get_tx_coalesced_frames(
+ struct rcb_common_cb *rcb_common, u32 port_idx)
+{
+ u64 reg;
+
+ reg = RCB_CFG_PKTLINE_REG + (port_idx + HNS_RCB_TX_PKTLINE_OFFSET) * 4;
+ return dsaf_read_dev(rcb_common, reg);
+}
+
+/**
*hns_rcb_get_coalesce_usecs - get rcb port coalesced time_out
*@rcb_common: rcb_common device
*@port_idx:port id in comm
@@ -538,33 +594,17 @@ int hns_rcb_set_coalesce_usecs(
return -EINVAL;
}
}
- if (timeout > HNS_RCB_MAX_COALESCED_USECS) {
+ if (timeout > HNS_RCB_MAX_COALESCED_USECS || timeout == 0) {
dev_err(rcb_common->dsaf_dev->dev,
- "error: coalesce_usecs setting supports 0~1023us\n");
+ "error: coalesce_usecs setting supports 1~1023us\n");
return -EINVAL;
}
-
- if (!AE_IS_VER1(rcb_common->dsaf_dev->dsaf_ver)) {
- if (timeout == 0)
- /* set timeout to 0, Disable gap time */
- dsaf_set_reg_field(rcb_common->io_base,
- RCB_INT_GAP_TIME_REG + port_idx * 4,
- PPE_INT_GAPTIME_M, PPE_INT_GAPTIME_B,
- 0);
- else
- /* set timeout non 0, restore gap time to 1 */
- dsaf_set_reg_field(rcb_common->io_base,
- RCB_INT_GAP_TIME_REG + port_idx * 4,
- PPE_INT_GAPTIME_M, PPE_INT_GAPTIME_B,
- 1);
- }
-
hns_rcb_set_port_timeout(rcb_common, port_idx, timeout);
return 0;
}
/**
- *hns_rcb_set_coalesced_frames - set rcb coalesced frames
+ *hns_rcb_set_tx_coalesced_frames - set rcb coalesced frames
*@rcb_common: rcb_common device
*@port_idx:port id in comm
*@coalesced_frames:tx/rx BD num for coalesced frames
@@ -572,10 +612,41 @@ int hns_rcb_set_coalesce_usecs(
* Returns:
* Zero for success, or an error code in case of failure
*/
-int hns_rcb_set_coalesced_frames(
+int hns_rcb_set_tx_coalesced_frames(
struct rcb_common_cb *rcb_common, u32 port_idx, u32 coalesced_frames)
{
- u32 old_waterline = hns_rcb_get_coalesced_frames(rcb_common, port_idx);
+ u32 old_waterline =
+ hns_rcb_get_tx_coalesced_frames(rcb_common, port_idx);
+ u64 reg;
+
+ if (coalesced_frames == old_waterline)
+ return 0;
+
+ if (coalesced_frames != 1) {
+ dev_err(rcb_common->dsaf_dev->dev,
+ "error: not support tx coalesce_frames setting!\n");
+ return -EINVAL;
+ }
+
+ reg = RCB_CFG_PKTLINE_REG + (port_idx + HNS_RCB_TX_PKTLINE_OFFSET) * 4;
+ dsaf_write_dev(rcb_common, reg, coalesced_frames);
+ return 0;
+}
+
+/**
+ *hns_rcb_set_rx_coalesced_frames - set rcb rx coalesced frames
+ *@rcb_common: rcb_common device
+ *@port_idx:port id in comm
+ *@coalesced_frames:tx/rx BD num for coalesced frames
+ *
+ * Returns:
+ * Zero for success, or an error code in case of failure
+ */
+int hns_rcb_set_rx_coalesced_frames(
+ struct rcb_common_cb *rcb_common, u32 port_idx, u32 coalesced_frames)
+{
+ u32 old_waterline =
+ hns_rcb_get_rx_coalesced_frames(rcb_common, port_idx);
if (coalesced_frames == old_waterline)
return 0;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h
index 99b4e1b..a664ee8 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h
@@ -35,12 +35,23 @@ struct rcb_common_cb;
#define HNS_RCB_REG_OFFSET 0x10000
+#define HNS_RCB_TX_FRAMES_LOW 1
+#define HNS_RCB_RX_FRAMES_LOW 1
+#define HNS_RCB_TX_FRAMES_HIGH 1023
+#define HNS_RCB_RX_FRAMES_HIGH 1023
+#define HNS_RCB_TX_USECS_LOW 1
+#define HNS_RCB_RX_USECS_LOW 1
+#define HNS_RCB_TX_USECS_HIGH 1023
+#define HNS_RCB_RX_USECS_HIGH 1023
#define HNS_RCB_MAX_COALESCED_FRAMES 1023
#define HNS_RCB_MIN_COALESCED_FRAMES 1
-#define HNS_RCB_DEF_COALESCED_FRAMES 50
+#define HNS_RCB_DEF_RX_COALESCED_FRAMES 50
+#define HNS_RCB_DEF_TX_COALESCED_FRAMES 1
#define HNS_RCB_CLK_FREQ_MHZ 350
#define HNS_RCB_MAX_COALESCED_USECS 0x3ff
-#define HNS_RCB_DEF_COALESCED_USECS 50
+#define HNS_RCB_DEF_COALESCED_USECS 30
+#define HNS_RCB_DEF_GAP_TIME_USECS 20
+#define HNS_RCB_TX_PKTLINE_OFFSET 8
#define HNS_RCB_COMMON_ENDIAN 1
@@ -125,13 +136,17 @@ void hns_rcbv2_int_clr_hw(struct hnae_queue *q, u32 flag);
void hns_rcb_init_hw(struct ring_pair_cb *ring);
void hns_rcb_reset_ring_hw(struct hnae_queue *q);
void hns_rcb_wait_fbd_clean(struct hnae_queue **qs, int q_num, u32 flag);
-u32 hns_rcb_get_coalesced_frames(
+u32 hns_rcb_get_rx_coalesced_frames(
+ struct rcb_common_cb *rcb_common, u32 port_idx);
+u32 hns_rcb_get_tx_coalesced_frames(
struct rcb_common_cb *rcb_common, u32 port_idx);
u32 hns_rcb_get_coalesce_usecs(
struct rcb_common_cb *rcb_common, u32 port_idx);
int hns_rcb_set_coalesce_usecs(
struct rcb_common_cb *rcb_common, u32 port_idx, u32 timeout);
-int hns_rcb_set_coalesced_frames(
+int hns_rcb_set_rx_coalesced_frames(
+ struct rcb_common_cb *rcb_common, u32 port_idx, u32 coalesced_frames);
+int hns_rcb_set_tx_coalesced_frames(
struct rcb_common_cb *rcb_common, u32 port_idx, u32 coalesced_frames);
void hns_rcb_update_stats(struct hnae_queue *queue);
@@ -146,4 +161,7 @@ int hns_rcb_get_ring_regs_count(void);
void hns_rcb_get_ring_regs(struct hnae_queue *queue, void *data);
void hns_rcb_get_strings(int stringset, u8 *data, int index);
+void hns_rcb_set_rx_ring_bs(struct hnae_queue *q, u32 buf_size);
+void hns_rcb_set_tx_ring_bs(struct hnae_queue *q, u32 buf_size);
+
#endif /* _HNS_DSAF_RCB_H */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
index 8fa18fc..46a52d9 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
@@ -421,7 +421,7 @@
#define RCB_CFG_OVERTIME_REG 0x9300
#define RCB_CFG_PKTLINE_INT_NUM_REG 0x9304
#define RCB_CFG_OVERTIME_INT_NUM_REG 0x9308
-#define RCB_INT_GAP_TIME_REG 0x9400
+#define RCB_PORT_INT_GAPTIME_REG 0x9400
#define RCB_PORT_CFG_OVERTIME_REG 0x9430
#define RCB_RING_RX_RING_BASEADDR_L_REG 0x00000
@@ -466,6 +466,7 @@
#define GMAC_DUPLEX_TYPE_REG 0x0008UL
#define GMAC_FD_FC_TYPE_REG 0x000CUL
+#define GMAC_TX_WATER_LINE_REG 0x0010UL
#define GMAC_FC_TX_TIMER_REG 0x001CUL
#define GMAC_FD_FC_ADDR_LOW_REG 0x0020UL
#define GMAC_FD_FC_ADDR_HIGH_REG 0x0024UL
@@ -912,6 +913,9 @@
#define GMAC_DUPLEX_TYPE_B 0
+#define GMAC_TX_WATER_LINE_MASK ((1UL << 8) - 1)
+#define GMAC_TX_WATER_LINE_SHIFT 0
+
#define GMAC_FC_TX_TIMER_S 0
#define GMAC_FC_TX_TIMER_M 0xffff
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
index aae830a..37a2fc3 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
@@ -300,18 +300,6 @@ static void hns_xgmac_set_tx_auto_pause_frames(void *mac_drv, u16 enable)
}
/**
- *hns_xgmac_get_id - get xgmac port id
- *@mac_drv: mac driver
- *@newval:xgmac max frame length
- */
-static void hns_xgmac_get_id(void *mac_drv, u8 *mac_id)
-{
- struct mac_driver *drv = (struct mac_driver *)mac_drv;
-
- *mac_id = drv->mac_id;
-}
-
-/**
*hns_xgmac_config_max_frame_length - set xgmac max frame length
*@mac_drv: mac driver
*@newval:xgmac max frame length
@@ -833,7 +821,6 @@ void *hns_xgmac_config(struct hns_mac_cb *mac_cb, struct mac_params *mac_param)
mac_drv->config_half_duplex = NULL;
mac_drv->set_rx_ignore_pause_frames =
hns_xgmac_set_rx_ignore_pause_frames;
- mac_drv->mac_get_id = hns_xgmac_get_id;
mac_drv->mac_free = hns_xgmac_free;
mac_drv->adjust_link = NULL;
mac_drv->set_tx_auto_pause_frames = hns_xgmac_set_tx_auto_pause_frames;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index fca37e2..c6700b9 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -512,7 +512,8 @@ static void hns_nic_reuse_page(struct sk_buff *skb, int i,
int last_offset;
bool twobufs;
- twobufs = ((PAGE_SIZE < 8192) && hnae_buf_size(ring) == HNS_BUFFER_SIZE_2048);
+ twobufs = ((PAGE_SIZE < 8192) &&
+ hnae_buf_size(ring) == HNS_BUFFER_SIZE_2048);
desc = &ring->desc[ring->next_to_clean];
size = le16_to_cpu(desc->rx.size);
@@ -859,7 +860,7 @@ static int hns_nic_rx_poll_one(struct hns_nic_ring_data *ring_data,
return recv_pkts;
}
-static void hns_nic_rx_fini_pro(struct hns_nic_ring_data *ring_data)
+static bool hns_nic_rx_fini_pro(struct hns_nic_ring_data *ring_data)
{
struct hnae_ring *ring = ring_data->ring;
int num = 0;
@@ -873,22 +874,23 @@ static void hns_nic_rx_fini_pro(struct hns_nic_ring_data *ring_data)
ring_data->ring->q->handle->dev->ops->toggle_ring_irq(
ring_data->ring, 1);
- napi_schedule(&ring_data->napi);
+ return false;
+ } else {
+ return true;
}
}
-static void hns_nic_rx_fini_pro_v2(struct hns_nic_ring_data *ring_data)
+static bool hns_nic_rx_fini_pro_v2(struct hns_nic_ring_data *ring_data)
{
struct hnae_ring *ring = ring_data->ring;
- int num = 0;
+ int num;
num = readl_relaxed(ring->io_base + RCB_REG_FBDNUM);
- if (num == 0)
- ring_data->ring->q->handle->dev->ops->toggle_ring_irq(
- ring, 0);
+ if (!num)
+ return true;
else
- napi_schedule(&ring_data->napi);
+ return false;
}
static inline void hns_nic_reclaim_one_desc(struct hnae_ring *ring,
@@ -921,12 +923,13 @@ static int is_valid_clean_head(struct hnae_ring *ring, int h)
/* netif_tx_lock will turn down the performance, set only when necessary */
#ifdef CONFIG_NET_POLL_CONTROLLER
-#define NETIF_TX_LOCK(ndev) netif_tx_lock(ndev)
-#define NETIF_TX_UNLOCK(ndev) netif_tx_unlock(ndev)
+#define NETIF_TX_LOCK(ring) spin_lock(&(ring)->lock)
+#define NETIF_TX_UNLOCK(ring) spin_unlock(&(ring)->lock)
#else
-#define NETIF_TX_LOCK(ndev)
-#define NETIF_TX_UNLOCK(ndev)
+#define NETIF_TX_LOCK(ring)
+#define NETIF_TX_UNLOCK(ring)
#endif
+
/* reclaim all desc in one budget
* return error or number of desc left
*/
@@ -940,13 +943,13 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
int head;
int bytes, pkts;
- NETIF_TX_LOCK(ndev);
+ NETIF_TX_LOCK(ring);
head = readl_relaxed(ring->io_base + RCB_REG_HEAD);
rmb(); /* make sure head is ready before touch any data */
if (is_ring_empty(ring) || head == ring->next_to_clean) {
- NETIF_TX_UNLOCK(ndev);
+ NETIF_TX_UNLOCK(ring);
return 0; /* no data to poll */
}
@@ -954,7 +957,7 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
netdev_err(ndev, "wrong head (%d, %d-%d)\n", head,
ring->next_to_use, ring->next_to_clean);
ring->stats.io_err_cnt++;
- NETIF_TX_UNLOCK(ndev);
+ NETIF_TX_UNLOCK(ring);
return -EIO;
}
@@ -966,7 +969,7 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
prefetch(&ring->desc_cb[ring->next_to_clean]);
}
- NETIF_TX_UNLOCK(ndev);
+ NETIF_TX_UNLOCK(ring);
dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index);
netdev_tx_completed_queue(dev_queue, pkts, bytes);
@@ -989,7 +992,7 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
return 0;
}
-static void hns_nic_tx_fini_pro(struct hns_nic_ring_data *ring_data)
+static bool hns_nic_tx_fini_pro(struct hns_nic_ring_data *ring_data)
{
struct hnae_ring *ring = ring_data->ring;
int head;
@@ -1002,20 +1005,21 @@ static void hns_nic_tx_fini_pro(struct hns_nic_ring_data *ring_data)
ring_data->ring->q->handle->dev->ops->toggle_ring_irq(
ring_data->ring, 1);
- napi_schedule(&ring_data->napi);
+ return false;
+ } else {
+ return true;
}
}
-static void hns_nic_tx_fini_pro_v2(struct hns_nic_ring_data *ring_data)
+static bool hns_nic_tx_fini_pro_v2(struct hns_nic_ring_data *ring_data)
{
struct hnae_ring *ring = ring_data->ring;
int head = readl_relaxed(ring->io_base + RCB_REG_HEAD);
if (head == ring->next_to_clean)
- ring_data->ring->q->handle->dev->ops->toggle_ring_irq(
- ring, 0);
+ return true;
else
- napi_schedule(&ring_data->napi);
+ return false;
}
static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data)
@@ -1026,7 +1030,7 @@ static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data)
int head;
int bytes, pkts;
- NETIF_TX_LOCK(ndev);
+ NETIF_TX_LOCK(ring);
head = ring->next_to_use; /* ntu :soft setted ring position*/
bytes = 0;
@@ -1034,7 +1038,7 @@ static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data)
while (head != ring->next_to_clean)
hns_nic_reclaim_one_desc(ring, &bytes, &pkts);
- NETIF_TX_UNLOCK(ndev);
+ NETIF_TX_UNLOCK(ring);
dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index);
netdev_tx_reset_queue(dev_queue);
@@ -1042,15 +1046,23 @@ static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data)
static int hns_nic_common_poll(struct napi_struct *napi, int budget)
{
+ int clean_complete = 0;
struct hns_nic_ring_data *ring_data =
container_of(napi, struct hns_nic_ring_data, napi);
- int clean_complete = ring_data->poll_one(
- ring_data, budget, ring_data->ex_process);
+ struct hnae_ring *ring = ring_data->ring;
- if (clean_complete >= 0 && clean_complete < budget) {
- napi_complete(napi);
- ring_data->fini_process(ring_data);
- return 0;
+try_again:
+ clean_complete += ring_data->poll_one(
+ ring_data, budget - clean_complete,
+ ring_data->ex_process);
+
+ if (clean_complete < budget) {
+ if (ring_data->fini_process(ring_data)) {
+ napi_complete(napi);
+ ring->q->handle->dev->ops->toggle_ring_irq(ring, 0);
+ } else {
+ goto try_again;
+ }
}
return clean_complete;
@@ -1196,54 +1208,31 @@ static void hns_nic_ring_close(struct net_device *netdev, int idx)
napi_disable(&priv->ring_data[idx].napi);
}
-static void hns_set_irq_affinity(struct hns_nic_priv *priv)
+static int hns_nic_init_affinity_mask(int q_num, int ring_idx,
+ struct hnae_ring *ring, cpumask_t *mask)
{
- struct hnae_handle *h = priv->ae_handle;
- struct hns_nic_ring_data *rd;
- int i;
int cpu;
- cpumask_var_t mask;
- if (!alloc_cpumask_var(&mask, GFP_KERNEL))
- return;
-
- /*diffrent irq banlance for 16core and 32core*/
- if (h->q_num == num_possible_cpus()) {
- for (i = 0; i < h->q_num * 2; i++) {
- rd = &priv->ring_data[i];
- if (cpu_online(rd->queue_index)) {
- cpumask_clear(mask);
- cpu = rd->queue_index;
- cpumask_set_cpu(cpu, mask);
- (void)irq_set_affinity_hint(rd->ring->irq,
- mask);
- }
- }
+ /* Diffrent irq banlance between 16core and 32core.
+ * The cpu mask set by ring index according to the ring flag
+ * which indicate the ring is tx or rx.
+ */
+ if (q_num == num_possible_cpus()) {
+ if (is_tx_ring(ring))
+ cpu = ring_idx;
+ else
+ cpu = ring_idx - q_num;
} else {
- for (i = 0; i < h->q_num; i++) {
- rd = &priv->ring_data[i];
- if (cpu_online(rd->queue_index * 2)) {
- cpumask_clear(mask);
- cpu = rd->queue_index * 2;
- cpumask_set_cpu(cpu, mask);
- (void)irq_set_affinity_hint(rd->ring->irq,
- mask);
- }
- }
-
- for (i = h->q_num; i < h->q_num * 2; i++) {
- rd = &priv->ring_data[i];
- if (cpu_online(rd->queue_index * 2 + 1)) {
- cpumask_clear(mask);
- cpu = rd->queue_index * 2 + 1;
- cpumask_set_cpu(cpu, mask);
- (void)irq_set_affinity_hint(rd->ring->irq,
- mask);
- }
- }
+ if (is_tx_ring(ring))
+ cpu = ring_idx * 2;
+ else
+ cpu = (ring_idx - q_num) * 2 + 1;
}
- free_cpumask_var(mask);
+ cpumask_clear(mask);
+ cpumask_set_cpu(cpu, mask);
+
+ return cpu;
}
static int hns_nic_init_irq(struct hns_nic_priv *priv)
@@ -1252,6 +1241,7 @@ static int hns_nic_init_irq(struct hns_nic_priv *priv)
struct hns_nic_ring_data *rd;
int i;
int ret;
+ int cpu;
for (i = 0; i < h->q_num * 2; i++) {
rd = &priv->ring_data[i];
@@ -1261,7 +1251,7 @@ static int hns_nic_init_irq(struct hns_nic_priv *priv)
snprintf(rd->ring->ring_name, RCB_RING_NAME_LEN,
"%s-%s%d", priv->netdev->name,
- (i < h->q_num ? "tx" : "rx"), rd->queue_index);
+ (is_tx_ring(rd->ring) ? "tx" : "rx"), rd->queue_index);
rd->ring->ring_name[RCB_RING_NAME_LEN - 1] = '\0';
@@ -1273,12 +1263,17 @@ static int hns_nic_init_irq(struct hns_nic_priv *priv)
return ret;
}
disable_irq(rd->ring->irq);
+
+ cpu = hns_nic_init_affinity_mask(h->q_num, i,
+ rd->ring, &rd->mask);
+
+ if (cpu_online(cpu))
+ irq_set_affinity_hint(rd->ring->irq,
+ &rd->mask);
+
rd->ring->irq_init_flag = RCB_IRQ_INITED;
}
- /*set cpu affinity*/
- hns_set_irq_affinity(priv);
-
return 0;
}
@@ -1487,32 +1482,259 @@ static netdev_tx_t hns_nic_net_xmit(struct sk_buff *skb,
return (netdev_tx_t)ret;
}
+static void hns_nic_drop_rx_fetch(struct hns_nic_ring_data *ring_data,
+ struct sk_buff *skb)
+{
+ dev_kfree_skb_any(skb);
+}
+
+#define HNS_LB_TX_RING 0
+static struct sk_buff *hns_assemble_skb(struct net_device *ndev)
+{
+ struct sk_buff *skb;
+ struct ethhdr *ethhdr;
+ int frame_len;
+
+ /* allocate test skb */
+ skb = alloc_skb(64, GFP_KERNEL);
+ if (!skb)
+ return NULL;
+
+ skb_put(skb, 64);
+ skb->dev = ndev;
+ memset(skb->data, 0xFF, skb->len);
+
+ /* must be tcp/ip package */
+ ethhdr = (struct ethhdr *)skb->data;
+ ethhdr->h_proto = htons(ETH_P_IP);
+
+ frame_len = skb->len & (~1ul);
+ memset(&skb->data[frame_len / 2], 0xAA,
+ frame_len / 2 - 1);
+
+ skb->queue_mapping = HNS_LB_TX_RING;
+
+ return skb;
+}
+
+static int hns_enable_serdes_lb(struct net_device *ndev)
+{
+ struct hns_nic_priv *priv = netdev_priv(ndev);
+ struct hnae_handle *h = priv->ae_handle;
+ struct hnae_ae_ops *ops = h->dev->ops;
+ int speed, duplex;
+ int ret;
+
+ ret = ops->set_loopback(h, MAC_INTERNALLOOP_SERDES, 1);
+ if (ret)
+ return ret;
+
+ ret = ops->start ? ops->start(h) : 0;
+ if (ret)
+ return ret;
+
+ /* link adjust duplex*/
+ if (h->phy_if != PHY_INTERFACE_MODE_XGMII)
+ speed = 1000;
+ else
+ speed = 10000;
+ duplex = 1;
+
+ ops->adjust_link(h, speed, duplex);
+
+ /* wait h/w ready */
+ mdelay(300);
+
+ return 0;
+}
+
+static void hns_disable_serdes_lb(struct net_device *ndev)
+{
+ struct hns_nic_priv *priv = netdev_priv(ndev);
+ struct hnae_handle *h = priv->ae_handle;
+ struct hnae_ae_ops *ops = h->dev->ops;
+
+ ops->stop(h);
+ ops->set_loopback(h, MAC_INTERNALLOOP_SERDES, 0);
+}
+
+/**
+ *hns_nic_clear_all_rx_fetch - clear the chip fetched descriptions. The
+ *function as follows:
+ * 1. if one rx ring has found the page_offset is not equal 0 between head
+ * and tail, it means that the chip fetched the wrong descs for the ring
+ * which buffer size is 4096.
+ * 2. we set the chip serdes loopback and set rss indirection to the ring.
+ * 3. construct 64-bytes ip broadcast packages, wait the associated rx ring
+ * recieving all packages and it will fetch new descriptions.
+ * 4. recover to the original state.
+ *
+ *@ndev: net device
+ */
+static int hns_nic_clear_all_rx_fetch(struct net_device *ndev)
+{
+ struct hns_nic_priv *priv = netdev_priv(ndev);
+ struct hnae_handle *h = priv->ae_handle;
+ struct hnae_ae_ops *ops = h->dev->ops;
+ struct hns_nic_ring_data *rd;
+ struct hnae_ring *ring;
+ struct sk_buff *skb;
+ u32 *org_indir;
+ u32 *cur_indir;
+ int indir_size;
+ int head, tail;
+ int fetch_num;
+ int i, j;
+ bool found;
+ int retry_times;
+ int ret = 0;
+
+ /* alloc indir memory */
+ indir_size = ops->get_rss_indir_size(h) * sizeof(*org_indir);
+ org_indir = kzalloc(indir_size, GFP_KERNEL);
+ if (!org_indir)
+ return -ENOMEM;
+
+ /* store the orginal indirection */
+ ops->get_rss(h, org_indir, NULL, NULL);
+
+ cur_indir = kzalloc(indir_size, GFP_KERNEL);
+ if (!cur_indir) {
+ ret = -ENOMEM;
+ goto cur_indir_alloc_err;
+ }
+
+ /* set loopback */
+ if (hns_enable_serdes_lb(ndev)) {
+ ret = -EINVAL;
+ goto enable_serdes_lb_err;
+ }
+
+ /* foreach every rx ring to clear fetch desc */
+ for (i = 0; i < h->q_num; i++) {
+ ring = &h->qs[i]->rx_ring;
+ head = readl_relaxed(ring->io_base + RCB_REG_HEAD);
+ tail = readl_relaxed(ring->io_base + RCB_REG_TAIL);
+ found = false;
+ fetch_num = ring_dist(ring, head, tail);
+
+ while (head != tail) {
+ if (ring->desc_cb[head].page_offset != 0) {
+ found = true;
+ break;
+ }
+
+ head++;
+ if (head == ring->desc_num)
+ head = 0;
+ }
+
+ if (found) {
+ for (j = 0; j < indir_size / sizeof(*org_indir); j++)
+ cur_indir[j] = i;
+ ops->set_rss(h, cur_indir, NULL, 0);
+
+ for (j = 0; j < fetch_num; j++) {
+ /* alloc one skb and init */
+ skb = hns_assemble_skb(ndev);
+ if (!skb)
+ goto out;
+ rd = &tx_ring_data(priv, skb->queue_mapping);
+ hns_nic_net_xmit_hw(ndev, skb, rd);
+
+ retry_times = 0;
+ while (retry_times++ < 10) {
+ mdelay(10);
+ /* clean rx */
+ rd = &rx_ring_data(priv, i);
+ if (rd->poll_one(rd, fetch_num,
+ hns_nic_drop_rx_fetch))
+ break;
+ }
+
+ retry_times = 0;
+ while (retry_times++ < 10) {
+ mdelay(10);
+ /* clean tx ring 0 send package */
+ rd = &tx_ring_data(priv,
+ HNS_LB_TX_RING);
+ if (rd->poll_one(rd, fetch_num, NULL))
+ break;
+ }
+ }
+ }
+ }
+
+out:
+ /* restore everything */
+ ops->set_rss(h, org_indir, NULL, 0);
+ hns_disable_serdes_lb(ndev);
+enable_serdes_lb_err:
+ kfree(cur_indir);
+cur_indir_alloc_err:
+ kfree(org_indir);
+
+ return ret;
+}
+
static int hns_nic_change_mtu(struct net_device *ndev, int new_mtu)
{
struct hns_nic_priv *priv = netdev_priv(ndev);
struct hnae_handle *h = priv->ae_handle;
+ bool if_running = netif_running(ndev);
int ret;
+ /* MTU < 68 is an error and causes problems on some kernels */
+ if (new_mtu < 68)
+ return -EINVAL;
+
+ /* MTU no change */
+ if (new_mtu == ndev->mtu)
+ return 0;
+
if (!h->dev->ops->set_mtu)
return -ENOTSUPP;
- if (netif_running(ndev)) {
+ if (if_running) {
(void)hns_nic_net_stop(ndev);
msleep(100);
-
- ret = h->dev->ops->set_mtu(h, new_mtu);
- if (ret)
- netdev_err(ndev, "set mtu fail, return value %d\n",
- ret);
-
- if (hns_nic_net_open(ndev))
- netdev_err(ndev, "hns net open fail\n");
- } else {
- ret = h->dev->ops->set_mtu(h, new_mtu);
}
- if (!ret)
- ndev->mtu = new_mtu;
+ if (priv->enet_ver != AE_VERSION_1 &&
+ ndev->mtu <= BD_SIZE_2048_MAX_MTU &&
+ new_mtu > BD_SIZE_2048_MAX_MTU) {
+ /* update desc */
+ hnae_reinit_all_ring_desc(h);
+
+ /* clear the package which the chip has fetched */
+ ret = hns_nic_clear_all_rx_fetch(ndev);
+
+ /* the page offset must be consist with desc */
+ hnae_reinit_all_ring_page_off(h);
+
+ if (ret) {
+ netdev_err(ndev, "clear the fetched desc fail\n");
+ goto out;
+ }
+ }
+
+ ret = h->dev->ops->set_mtu(h, new_mtu);
+ if (ret) {
+ netdev_err(ndev, "set mtu fail, return value %d\n",
+ ret);
+ goto out;
+ }
+
+ /* finally, set new mtu to netdevice */
+ ndev->mtu = new_mtu;
+
+out:
+ if (if_running) {
+ if (hns_nic_net_open(ndev)) {
+ netdev_err(ndev, "hns net open fail\n");
+ ret = -EINVAL;
+ }
+ }
return ret;
}
@@ -1791,7 +2013,7 @@ static void hns_nic_reset_subtask(struct hns_nic_priv *priv)
static void hns_nic_service_event_complete(struct hns_nic_priv *priv)
{
WARN_ON(!test_bit(NIC_STATE_SERVICE_SCHED, &priv->state));
-
+ /* make sure to commit the things */
smp_mb__before_atomic();
clear_bit(NIC_STATE_SERVICE_SCHED, &priv->state);
}
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.h b/drivers/net/ethernet/hisilicon/hns/hns_enet.h
index 5b412de..1b83232 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.h
@@ -37,10 +37,11 @@ enum hns_nic_state {
struct hns_nic_ring_data {
struct hnae_ring *ring;
struct napi_struct napi;
+ cpumask_t mask; /* affinity mask */
int queue_index;
int (*poll_one)(struct hns_nic_ring_data *, int, void *);
void (*ex_process)(struct hns_nic_ring_data *, struct sk_buff *);
- void (*fini_process)(struct hns_nic_ring_data *);
+ bool (*fini_process)(struct hns_nic_ring_data *);
};
/* compatible the difference between two versions */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index 3ac2183..b8fab14 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -146,7 +146,7 @@ static int hns_nic_get_link_ksettings(struct net_device *net_dev,
/* When there is no phy, autoneg is off. */
cmd->base.autoneg = false;
- cmd->base.cmd = speed;
+ cmd->base.speed = speed;
cmd->base.duplex = duplex;
if (net_dev->phydev)
@@ -764,14 +764,14 @@ static int hns_get_coalesce(struct net_device *net_dev,
ec->use_adaptive_tx_coalesce = 1;
if ((!ops->get_coalesce_usecs) ||
- (!ops->get_rx_max_coalesced_frames))
+ (!ops->get_max_coalesced_frames))
return -ESRCH;
ops->get_coalesce_usecs(priv->ae_handle,
&ec->tx_coalesce_usecs,
&ec->rx_coalesce_usecs);
- ops->get_rx_max_coalesced_frames(
+ ops->get_max_coalesced_frames(
priv->ae_handle,
&ec->tx_max_coalesced_frames,
&ec->rx_max_coalesced_frames);
@@ -801,30 +801,28 @@ static int hns_set_coalesce(struct net_device *net_dev,
{
struct hns_nic_priv *priv = netdev_priv(net_dev);
struct hnae_ae_ops *ops;
- int ret;
+ int rc1, rc2;
ops = priv->ae_handle->dev->ops;
if (ec->tx_coalesce_usecs != ec->rx_coalesce_usecs)
return -EINVAL;
- if (ec->rx_max_coalesced_frames != ec->tx_max_coalesced_frames)
- return -EINVAL;
-
if ((!ops->set_coalesce_usecs) ||
(!ops->set_coalesce_frames))
return -ESRCH;
- ret = ops->set_coalesce_usecs(priv->ae_handle,
+ rc1 = ops->set_coalesce_usecs(priv->ae_handle,
ec->rx_coalesce_usecs);
- if (ret)
- return ret;
- ret = ops->set_coalesce_frames(
- priv->ae_handle,
- ec->rx_max_coalesced_frames);
+ rc2 = ops->set_coalesce_frames(priv->ae_handle,
+ ec->tx_max_coalesced_frames,
+ ec->rx_max_coalesced_frames);
- return ret;
+ if (rc1 || rc2)
+ return -EINVAL;
+
+ return 0;
}
/**
@@ -1253,12 +1251,10 @@ hns_set_rss(struct net_device *netdev, const u32 *indir, const u8 *key,
ops = priv->ae_handle->dev->ops;
- /* currently hfunc can only be Toeplitz hash */
- if (key ||
- (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+ if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) {
+ netdev_err(netdev, "Invalid hfunc!\n");
return -EOPNOTSUPP;
- if (!indir)
- return 0;
+ }
return ops->set_rss(priv->ae_handle, indir, key, hfunc);
}
diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c
index 501eb20..e5221d9 100644
--- a/drivers/net/ethernet/hisilicon/hns_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns_mdio.c
@@ -23,17 +23,9 @@
#include <linux/phy.h>
#include <linux/platform_device.h>
#include <linux/regmap.h>
-#include <linux/spinlock_types.h>
#define MDIO_DRV_NAME "Hi-HNS_MDIO"
#define MDIO_BUS_NAME "Hisilicon MII Bus"
-#define MDIO_DRV_VERSION "1.3.0"
-#define MDIO_COPYRIGHT "Copyright(c) 2015 Huawei Corporation."
-#define MDIO_DRV_STRING MDIO_BUS_NAME
-#define MDIO_DEFAULT_DEVICE_DESCR MDIO_BUS_NAME
-
-#define MDIO_CTL_DEV_ADDR(x) (x & 0x1f)
-#define MDIO_CTL_PORT_ADDR(x) ((x & 0x1f) << 5)
#define MDIO_TIMEOUT 1000000
@@ -64,9 +56,7 @@ struct hns_mdio_device {
#define MDIO_CMD_DEVAD_S 0
#define MDIO_CMD_PRTAD_M 0x1f
#define MDIO_CMD_PRTAD_S 5
-#define MDIO_CMD_OP_M 0x3
#define MDIO_CMD_OP_S 10
-#define MDIO_CMD_ST_M 0x3
#define MDIO_CMD_ST_S 12
#define MDIO_CMD_START_B 14
@@ -185,18 +175,20 @@ static int mdio_sc_cfg_reg_write(struct hns_mdio_device *mdio_dev,
static int hns_mdio_wait_ready(struct mii_bus *bus)
{
struct hns_mdio_device *mdio_dev = bus->priv;
+ u32 cmd_reg_value;
int i;
- u32 cmd_reg_value = 1;
/* waitting for MDIO_COMMAND_REG 's mdio_start==0 */
/* after that can do read or write*/
- for (i = 0; cmd_reg_value; i++) {
+ for (i = 0; i < MDIO_TIMEOUT; i++) {
cmd_reg_value = MDIO_GET_REG_BIT(mdio_dev,
MDIO_COMMAND_REG,
MDIO_CMD_START_B);
- if (i == MDIO_TIMEOUT)
- return -ETIMEDOUT;
+ if (!cmd_reg_value)
+ break;
}
+ if ((i == MDIO_TIMEOUT) && cmd_reg_value)
+ return -ETIMEDOUT;
return 0;
}
diff --git a/drivers/net/ethernet/ibm/emac/Makefile b/drivers/net/ethernet/ibm/emac/Makefile
index eba2183..98768ba 100644
--- a/drivers/net/ethernet/ibm/emac/Makefile
+++ b/drivers/net/ethernet/ibm/emac/Makefile
@@ -8,4 +8,3 @@
ibm_emac-$(CONFIG_IBM_EMAC_ZMII) += zmii.o
ibm_emac-$(CONFIG_IBM_EMAC_RGMII) += rgmii.o
ibm_emac-$(CONFIG_IBM_EMAC_TAH) += tah.o
-ibm_emac-$(CONFIG_IBM_EMAC_DEBUG) += debug.o
diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index 275c2e2..508923f 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -1929,7 +1929,7 @@ static struct net_device_stats *emac_stats(struct net_device *ndev)
struct emac_instance *dev = netdev_priv(ndev);
struct emac_stats *st = &dev->stats;
struct emac_error_stats *est = &dev->estats;
- struct net_device_stats *nst = &dev->nstats;
+ struct net_device_stats *nst = &ndev->stats;
unsigned long flags;
DBG2(dev, "stats" NL);
@@ -2589,8 +2589,6 @@ static int emac_dt_mdio_probe(struct emac_instance *dev)
static int emac_dt_phy_connect(struct emac_instance *dev,
struct device_node *phy_handle)
{
- int res;
-
dev->phy.def = devm_kzalloc(&dev->ofdev->dev, sizeof(*dev->phy.def),
GFP_KERNEL);
if (!dev->phy.def)
@@ -2617,7 +2615,7 @@ static int emac_dt_phy_probe(struct emac_instance *dev)
{
struct device_node *np = dev->ofdev->dev.of_node;
struct device_node *phy_handle;
- int res = 0;
+ int res = 1;
phy_handle = of_parse_phandle(np, "phy-handle", 0);
@@ -2714,13 +2712,24 @@ static int emac_init_phy(struct emac_instance *dev)
if (emac_has_feature(dev, EMAC_FTR_HAS_RGMII)) {
int res = emac_dt_phy_probe(dev);
- mutex_unlock(&emac_phy_map_lock);
- if (!res)
+ switch (res) {
+ case 1:
+ /* No phy-handle property configured.
+ * Continue with the existing phy probe
+ * and setup code.
+ */
+ break;
+
+ case 0:
+ mutex_unlock(&emac_phy_map_lock);
goto init_phy;
- dev_err(&dev->ofdev->dev, "failed to attach dt phy (%d).\n",
- res);
- return res;
+ default:
+ mutex_unlock(&emac_phy_map_lock);
+ dev_err(&dev->ofdev->dev, "failed to attach dt phy (%d).\n",
+ res);
+ return res;
+ }
}
if (dev->phy_address != 0xffffffff)
@@ -3164,8 +3173,6 @@ static int emac_probe(struct platform_device *ofdev)
printk("%s: found %s PHY (0x%02x)\n", ndev->name,
dev->phy.def->name, dev->phy.address);
- emac_dbg_register(dev);
-
/* Life is good */
return 0;
@@ -3234,7 +3241,6 @@ static int emac_remove(struct platform_device *ofdev)
mal_unregister_commac(dev->mal, &dev->commac);
emac_put_deps(dev);
- emac_dbg_unregister(dev);
iounmap(dev->emacp);
if (dev->wol_irq)
@@ -3317,9 +3323,6 @@ static int __init emac_init(void)
printk(KERN_INFO DRV_DESC ", version " DRV_VERSION "\n");
- /* Init debug stuff */
- emac_init_debug();
-
/* Build EMAC boot list */
emac_make_bootlist();
@@ -3364,7 +3367,6 @@ static void __exit emac_exit(void)
rgmii_exit();
zmii_exit();
mal_exit();
- emac_fini_debug();
/* Destroy EMAC boot list */
for (i = 0; i < EMAC_BOOT_LIST_SIZE; i++)
diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h
index 0710a66..f10e156 100644
--- a/drivers/net/ethernet/ibm/emac/core.h
+++ b/drivers/net/ethernet/ibm/emac/core.h
@@ -265,7 +265,6 @@ struct emac_instance {
/* Stats
*/
struct emac_error_stats estats;
- struct net_device_stats nstats;
struct emac_stats stats;
/* Misc
diff --git a/drivers/net/ethernet/ibm/emac/debug.c b/drivers/net/ethernet/ibm/emac/debug.c
deleted file mode 100644
index a559f32..0000000
--- a/drivers/net/ethernet/ibm/emac/debug.c
+++ /dev/null
@@ -1,270 +0,0 @@
-/*
- * drivers/net/ethernet/ibm/emac/debug.c
- *
- * Driver for PowerPC 4xx on-chip ethernet controller, debug print routines.
- *
- * Copyright 2007 Benjamin Herrenschmidt, IBM Corp.
- * <benh@kernel.crashing.org>
- *
- * Based on the arch/ppc version of the driver:
- *
- * Copyright (c) 2004, 2005 Zultys Technologies
- * Eugene Surovegin <eugene.surovegin@zultys.com> or <ebs@ebshome.net>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
- *
- */
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/netdevice.h>
-#include <linux/sysrq.h>
-#include <asm/io.h>
-
-#include "core.h"
-
-static DEFINE_SPINLOCK(emac_dbg_lock);
-
-static void emac_desc_dump(struct emac_instance *p)
-{
- int i;
- printk("** EMAC %s TX BDs **\n"
- " tx_cnt = %d tx_slot = %d ack_slot = %d\n",
- p->ofdev->dev.of_node->full_name,
- p->tx_cnt, p->tx_slot, p->ack_slot);
- for (i = 0; i < NUM_TX_BUFF / 2; ++i)
- printk
- ("bd[%2d] 0x%08x %c 0x%04x %4u - bd[%2d] 0x%08x %c 0x%04x %4u\n",
- i, p->tx_desc[i].data_ptr, p->tx_skb[i] ? 'V' : ' ',
- p->tx_desc[i].ctrl, p->tx_desc[i].data_len,
- NUM_TX_BUFF / 2 + i,
- p->tx_desc[NUM_TX_BUFF / 2 + i].data_ptr,
- p->tx_skb[NUM_TX_BUFF / 2 + i] ? 'V' : ' ',
- p->tx_desc[NUM_TX_BUFF / 2 + i].ctrl,
- p->tx_desc[NUM_TX_BUFF / 2 + i].data_len);
-
- printk("** EMAC %s RX BDs **\n"
- " rx_slot = %d flags = 0x%lx rx_skb_size = %d rx_sync_size = %d\n"
- " rx_sg_skb = 0x%p\n",
- p->ofdev->dev.of_node->full_name,
- p->rx_slot, p->commac.flags, p->rx_skb_size,
- p->rx_sync_size, p->rx_sg_skb);
- for (i = 0; i < NUM_RX_BUFF / 2; ++i)
- printk
- ("bd[%2d] 0x%08x %c 0x%04x %4u - bd[%2d] 0x%08x %c 0x%04x %4u\n",
- i, p->rx_desc[i].data_ptr, p->rx_skb[i] ? 'V' : ' ',
- p->rx_desc[i].ctrl, p->rx_desc[i].data_len,
- NUM_RX_BUFF / 2 + i,
- p->rx_desc[NUM_RX_BUFF / 2 + i].data_ptr,
- p->rx_skb[NUM_RX_BUFF / 2 + i] ? 'V' : ' ',
- p->rx_desc[NUM_RX_BUFF / 2 + i].ctrl,
- p->rx_desc[NUM_RX_BUFF / 2 + i].data_len);
-}
-
-static void emac_mac_dump(struct emac_instance *dev)
-{
- struct emac_regs __iomem *p = dev->emacp;
- const int xaht_regs = EMAC_XAHT_REGS(dev);
- u32 *gaht_base = emac_gaht_base(dev);
- u32 *iaht_base = emac_iaht_base(dev);
- int emac4sync = emac_has_feature(dev, EMAC_FTR_EMAC4SYNC);
- int n;
-
- printk("** EMAC %s registers **\n"
- "MR0 = 0x%08x MR1 = 0x%08x TMR0 = 0x%08x TMR1 = 0x%08x\n"
- "RMR = 0x%08x ISR = 0x%08x ISER = 0x%08x\n"
- "IAR = %04x%08x VTPID = 0x%04x VTCI = 0x%04x\n",
- dev->ofdev->dev.of_node->full_name,
- in_be32(&p->mr0), in_be32(&p->mr1),
- in_be32(&p->tmr0), in_be32(&p->tmr1),
- in_be32(&p->rmr), in_be32(&p->isr), in_be32(&p->iser),
- in_be32(&p->iahr), in_be32(&p->ialr), in_be32(&p->vtpid),
- in_be32(&p->vtci)
- );
-
- if (emac4sync)
- printk("MAR = %04x%08x MMAR = %04x%08x\n",
- in_be32(&p->u0.emac4sync.mahr),
- in_be32(&p->u0.emac4sync.malr),
- in_be32(&p->u0.emac4sync.mmahr),
- in_be32(&p->u0.emac4sync.mmalr)
- );
-
- for (n = 0; n < xaht_regs; n++)
- printk("IAHT%02d = 0x%08x\n", n + 1, in_be32(iaht_base + n));
-
- for (n = 0; n < xaht_regs; n++)
- printk("GAHT%02d = 0x%08x\n", n + 1, in_be32(gaht_base + n));
-
- printk("LSA = %04x%08x IPGVR = 0x%04x\n"
- "STACR = 0x%08x TRTR = 0x%08x RWMR = 0x%08x\n"
- "OCTX = 0x%08x OCRX = 0x%08x\n",
- in_be32(&p->lsah), in_be32(&p->lsal), in_be32(&p->ipgvr),
- in_be32(&p->stacr), in_be32(&p->trtr), in_be32(&p->rwmr),
- in_be32(&p->octx), in_be32(&p->ocrx)
- );
-
- if (!emac4sync) {
- printk("IPCR = 0x%08x\n",
- in_be32(&p->u1.emac4.ipcr)
- );
- } else {
- printk("REVID = 0x%08x TPC = 0x%08x\n",
- in_be32(&p->u1.emac4sync.revid),
- in_be32(&p->u1.emac4sync.tpc)
- );
- }
-
- emac_desc_dump(dev);
-}
-
-static void emac_mal_dump(struct mal_instance *mal)
-{
- int i;
-
- printk("** MAL %s Registers **\n"
- "CFG = 0x%08x ESR = 0x%08x IER = 0x%08x\n"
- "TX|CASR = 0x%08x CARR = 0x%08x EOBISR = 0x%08x DEIR = 0x%08x\n"
- "RX|CASR = 0x%08x CARR = 0x%08x EOBISR = 0x%08x DEIR = 0x%08x\n",
- mal->ofdev->dev.of_node->full_name,
- get_mal_dcrn(mal, MAL_CFG), get_mal_dcrn(mal, MAL_ESR),
- get_mal_dcrn(mal, MAL_IER),
- get_mal_dcrn(mal, MAL_TXCASR), get_mal_dcrn(mal, MAL_TXCARR),
- get_mal_dcrn(mal, MAL_TXEOBISR), get_mal_dcrn(mal, MAL_TXDEIR),
- get_mal_dcrn(mal, MAL_RXCASR), get_mal_dcrn(mal, MAL_RXCARR),
- get_mal_dcrn(mal, MAL_RXEOBISR), get_mal_dcrn(mal, MAL_RXDEIR)
- );
-
- printk("TX|");
- for (i = 0; i < mal->num_tx_chans; ++i) {
- if (i && !(i % 4))
- printk("\n ");
- printk("CTP%d = 0x%08x ", i, get_mal_dcrn(mal, MAL_TXCTPR(i)));
- }
- printk("\nRX|");
- for (i = 0; i < mal->num_rx_chans; ++i) {
- if (i && !(i % 4))
- printk("\n ");
- printk("CTP%d = 0x%08x ", i, get_mal_dcrn(mal, MAL_RXCTPR(i)));
- }
- printk("\n ");
- for (i = 0; i < mal->num_rx_chans; ++i) {
- u32 r = get_mal_dcrn(mal, MAL_RCBS(i));
- if (i && !(i % 3))
- printk("\n ");
- printk("RCBS%d = 0x%08x (%d) ", i, r, r * 16);
- }
- printk("\n");
-}
-
-static struct emac_instance *__emacs[4];
-static struct mal_instance *__mals[1];
-
-void emac_dbg_register(struct emac_instance *dev)
-{
- unsigned long flags;
- int i;
-
- spin_lock_irqsave(&emac_dbg_lock, flags);
- for (i = 0; i < ARRAY_SIZE(__emacs); i++)
- if (__emacs[i] == NULL) {
- __emacs[i] = dev;
- break;
- }
- spin_unlock_irqrestore(&emac_dbg_lock, flags);
-}
-
-void emac_dbg_unregister(struct emac_instance *dev)
-{
- unsigned long flags;
- int i;
-
- spin_lock_irqsave(&emac_dbg_lock, flags);
- for (i = 0; i < ARRAY_SIZE(__emacs); i++)
- if (__emacs[i] == dev) {
- __emacs[i] = NULL;
- break;
- }
- spin_unlock_irqrestore(&emac_dbg_lock, flags);
-}
-
-void mal_dbg_register(struct mal_instance *mal)
-{
- unsigned long flags;
- int i;
-
- spin_lock_irqsave(&emac_dbg_lock, flags);
- for (i = 0; i < ARRAY_SIZE(__mals); i++)
- if (__mals[i] == NULL) {
- __mals[i] = mal;
- break;
- }
- spin_unlock_irqrestore(&emac_dbg_lock, flags);
-}
-
-void mal_dbg_unregister(struct mal_instance *mal)
-{
- unsigned long flags;
- int i;
-
- spin_lock_irqsave(&emac_dbg_lock, flags);
- for (i = 0; i < ARRAY_SIZE(__mals); i++)
- if (__mals[i] == mal) {
- __mals[i] = NULL;
- break;
- }
- spin_unlock_irqrestore(&emac_dbg_lock, flags);
-}
-
-void emac_dbg_dump_all(void)
-{
- unsigned int i;
- unsigned long flags;
-
- spin_lock_irqsave(&emac_dbg_lock, flags);
-
- for (i = 0; i < ARRAY_SIZE(__mals); ++i)
- if (__mals[i])
- emac_mal_dump(__mals[i]);
-
- for (i = 0; i < ARRAY_SIZE(__emacs); ++i)
- if (__emacs[i])
- emac_mac_dump(__emacs[i]);
-
- spin_unlock_irqrestore(&emac_dbg_lock, flags);
-}
-
-#if defined(CONFIG_MAGIC_SYSRQ)
-static void emac_sysrq_handler(int key)
-{
- emac_dbg_dump_all();
-}
-
-static struct sysrq_key_op emac_sysrq_op = {
- .handler = emac_sysrq_handler,
- .help_msg = "emac(c)",
- .action_msg = "Show EMAC(s) status",
-};
-
-int __init emac_init_debug(void)
-{
- return register_sysrq_key('c', &emac_sysrq_op);
-}
-
-void __exit emac_fini_debug(void)
-{
- unregister_sysrq_key('c', &emac_sysrq_op);
-}
-
-#else
-int __init emac_init_debug(void)
-{
- return 0;
-}
-void __exit emac_fini_debug(void)
-{
-}
-#endif /* CONFIG_MAGIC_SYSRQ */
diff --git a/drivers/net/ethernet/ibm/emac/debug.h b/drivers/net/ethernet/ibm/emac/debug.h
index 9c45efe..5bdfc17 100644
--- a/drivers/net/ethernet/ibm/emac/debug.h
+++ b/drivers/net/ethernet/ibm/emac/debug.h
@@ -25,32 +25,9 @@
#include "core.h"
#if defined(CONFIG_IBM_EMAC_DEBUG)
-
-struct emac_instance;
-struct mal_instance;
-
-void emac_dbg_register(struct emac_instance *dev);
-void emac_dbg_unregister(struct emac_instance *dev);
-void mal_dbg_register(struct mal_instance *mal);
-void mal_dbg_unregister(struct mal_instance *mal);
-int emac_init_debug(void) __init;
-void emac_fini_debug(void) __exit;
-void emac_dbg_dump_all(void);
-
# define DBG_LEVEL 1
-
#else
-
-# define emac_dbg_register(x) do { } while(0)
-# define emac_dbg_unregister(x) do { } while(0)
-# define mal_dbg_register(x) do { } while(0)
-# define mal_dbg_unregister(x) do { } while(0)
-# define emac_init_debug() do { } while(0)
-# define emac_fini_debug() do { } while(0)
-# define emac_dbg_dump_all() do { } while(0)
-
# define DBG_LEVEL 0
-
#endif
#define EMAC_DBG(d, name, fmt, arg...) \
diff --git a/drivers/net/ethernet/ibm/emac/mal.c b/drivers/net/ethernet/ibm/emac/mal.c
index cd3227b..91b1a55 100644
--- a/drivers/net/ethernet/ibm/emac/mal.c
+++ b/drivers/net/ethernet/ibm/emac/mal.c
@@ -695,8 +695,6 @@ static int mal_probe(struct platform_device *ofdev)
wmb();
platform_set_drvdata(ofdev, mal);
- mal_dbg_register(mal);
-
return 0;
fail6:
@@ -740,8 +738,6 @@ static int mal_remove(struct platform_device *ofdev)
mal_reset(mal);
- mal_dbg_unregister(mal);
-
dma_free_coherent(&ofdev->dev,
sizeof(struct mal_descriptor) *
(NUM_TX_BUFF * mal->num_tx_chans +
diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h
index 7acda04..ed8780c 100644
--- a/drivers/net/ethernet/ibm/ibmveth.h
+++ b/drivers/net/ethernet/ibm/ibmveth.h
@@ -146,7 +146,6 @@ struct ibmveth_adapter {
struct vio_dev *vdev;
struct net_device *netdev;
struct napi_struct napi;
- struct net_device_stats stats;
unsigned int mcastFilterSize;
void * buffer_list_addr;
void * filter_list_addr;
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 9198e6b..7ba43cf 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -65,7 +65,6 @@
#include <linux/irq.h>
#include <linux/kthread.h>
#include <linux/seq_file.h>
-#include <linux/debugfs.h>
#include <linux/interrupt.h>
#include <net/net_namespace.h>
#include <asm/hvcall.h>
@@ -89,7 +88,6 @@ MODULE_VERSION(IBMVNIC_DRIVER_VERSION);
static int ibmvnic_version = IBMVNIC_INITIAL_VERSION;
static int ibmvnic_remove(struct vio_dev *);
static void release_sub_crqs(struct ibmvnic_adapter *);
-static void release_sub_crqs_no_irqs(struct ibmvnic_adapter *);
static int ibmvnic_reset_crq(struct ibmvnic_adapter *);
static int ibmvnic_send_crq_init(struct ibmvnic_adapter *);
static int ibmvnic_reenable_crq_queue(struct ibmvnic_adapter *);
@@ -110,6 +108,11 @@ static int ibmvnic_poll(struct napi_struct *napi, int data);
static void send_map_query(struct ibmvnic_adapter *adapter);
static void send_request_map(struct ibmvnic_adapter *, dma_addr_t, __be32, u8);
static void send_request_unmap(struct ibmvnic_adapter *, u8);
+static void send_login(struct ibmvnic_adapter *adapter);
+static void send_cap_queries(struct ibmvnic_adapter *adapter);
+static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter);
+static int ibmvnic_init(struct ibmvnic_adapter *);
+static void release_crq_queue(struct ibmvnic_adapter *);
struct ibmvnic_stat {
char name[ETH_GSTRING_LEN];
@@ -159,21 +162,6 @@ static long h_reg_sub_crq(unsigned long unit_address, unsigned long token,
return rc;
}
-/* net_device_ops functions */
-
-static void init_rx_pool(struct ibmvnic_adapter *adapter,
- struct ibmvnic_rx_pool *rx_pool, int num, int index,
- int buff_size, int active)
-{
- netdev_dbg(adapter->netdev,
- "Initializing rx_pool %d, %d buffs, %d bytes each\n",
- index, num, buff_size);
- rx_pool->size = num;
- rx_pool->index = index;
- rx_pool->buff_size = buff_size;
- rx_pool->active = active;
-}
-
static int alloc_long_term_buff(struct ibmvnic_adapter *adapter,
struct ibmvnic_long_term_buff *ltb, int size)
{
@@ -202,47 +190,14 @@ static void free_long_term_buff(struct ibmvnic_adapter *adapter,
{
struct device *dev = &adapter->vdev->dev;
+ if (!ltb->buff)
+ return;
+
dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr);
if (!adapter->failover)
send_request_unmap(adapter, ltb->map_id);
}
-static int alloc_rx_pool(struct ibmvnic_adapter *adapter,
- struct ibmvnic_rx_pool *pool)
-{
- struct device *dev = &adapter->vdev->dev;
- int i;
-
- pool->free_map = kcalloc(pool->size, sizeof(int), GFP_KERNEL);
- if (!pool->free_map)
- return -ENOMEM;
-
- pool->rx_buff = kcalloc(pool->size, sizeof(struct ibmvnic_rx_buff),
- GFP_KERNEL);
-
- if (!pool->rx_buff) {
- dev_err(dev, "Couldn't alloc rx buffers\n");
- kfree(pool->free_map);
- return -ENOMEM;
- }
-
- if (alloc_long_term_buff(adapter, &pool->long_term_buff,
- pool->size * pool->buff_size)) {
- kfree(pool->free_map);
- kfree(pool->rx_buff);
- return -ENOMEM;
- }
-
- for (i = 0; i < pool->size; ++i)
- pool->free_map[i] = i;
-
- atomic_set(&pool->available, 0);
- pool->next_alloc = 0;
- pool->next_free = 0;
-
- return 0;
-}
-
static void replenish_rx_pool(struct ibmvnic_adapter *adapter,
struct ibmvnic_rx_pool *pool)
{
@@ -347,114 +302,349 @@ static void replenish_pools(struct ibmvnic_adapter *adapter)
}
}
-static void free_rx_pool(struct ibmvnic_adapter *adapter,
- struct ibmvnic_rx_pool *pool)
+static void release_stats_token(struct ibmvnic_adapter *adapter)
{
- int i;
+ struct device *dev = &adapter->vdev->dev;
- kfree(pool->free_map);
- pool->free_map = NULL;
-
- if (!pool->rx_buff)
+ if (!adapter->stats_token)
return;
- for (i = 0; i < pool->size; i++) {
- if (pool->rx_buff[i].skb) {
- dev_kfree_skb_any(pool->rx_buff[i].skb);
- pool->rx_buff[i].skb = NULL;
- }
+ dma_unmap_single(dev, adapter->stats_token,
+ sizeof(struct ibmvnic_statistics),
+ DMA_FROM_DEVICE);
+ adapter->stats_token = 0;
+}
+
+static int init_stats_token(struct ibmvnic_adapter *adapter)
+{
+ struct device *dev = &adapter->vdev->dev;
+ dma_addr_t stok;
+
+ stok = dma_map_single(dev, &adapter->stats,
+ sizeof(struct ibmvnic_statistics),
+ DMA_FROM_DEVICE);
+ if (dma_mapping_error(dev, stok)) {
+ dev_err(dev, "Couldn't map stats buffer\n");
+ return -1;
}
- kfree(pool->rx_buff);
- pool->rx_buff = NULL;
+
+ adapter->stats_token = stok;
+ return 0;
+}
+
+static void release_rx_pools(struct ibmvnic_adapter *adapter)
+{
+ struct ibmvnic_rx_pool *rx_pool;
+ int rx_scrqs;
+ int i, j;
+
+ if (!adapter->rx_pool)
+ return;
+
+ rx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
+ for (i = 0; i < rx_scrqs; i++) {
+ rx_pool = &adapter->rx_pool[i];
+
+ kfree(rx_pool->free_map);
+ free_long_term_buff(adapter, &rx_pool->long_term_buff);
+
+ if (!rx_pool->rx_buff)
+ continue;
+
+ for (j = 0; j < rx_pool->size; j++) {
+ if (rx_pool->rx_buff[j].skb) {
+ dev_kfree_skb_any(rx_pool->rx_buff[i].skb);
+ rx_pool->rx_buff[i].skb = NULL;
+ }
+ }
+
+ kfree(rx_pool->rx_buff);
+ }
+
+ kfree(adapter->rx_pool);
+ adapter->rx_pool = NULL;
+}
+
+static int init_rx_pools(struct net_device *netdev)
+{
+ struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+ struct device *dev = &adapter->vdev->dev;
+ struct ibmvnic_rx_pool *rx_pool;
+ int rxadd_subcrqs;
+ u64 *size_array;
+ int i, j;
+
+ rxadd_subcrqs =
+ be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
+ size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) +
+ be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size));
+
+ adapter->rx_pool = kcalloc(rxadd_subcrqs,
+ sizeof(struct ibmvnic_rx_pool),
+ GFP_KERNEL);
+ if (!adapter->rx_pool) {
+ dev_err(dev, "Failed to allocate rx pools\n");
+ return -1;
+ }
+
+ for (i = 0; i < rxadd_subcrqs; i++) {
+ rx_pool = &adapter->rx_pool[i];
+
+ netdev_dbg(adapter->netdev,
+ "Initializing rx_pool %d, %lld buffs, %lld bytes each\n",
+ i, adapter->req_rx_add_entries_per_subcrq,
+ be64_to_cpu(size_array[i]));
+
+ rx_pool->size = adapter->req_rx_add_entries_per_subcrq;
+ rx_pool->index = i;
+ rx_pool->buff_size = be64_to_cpu(size_array[i]);
+ rx_pool->active = 1;
+
+ rx_pool->free_map = kcalloc(rx_pool->size, sizeof(int),
+ GFP_KERNEL);
+ if (!rx_pool->free_map) {
+ release_rx_pools(adapter);
+ return -1;
+ }
+
+ rx_pool->rx_buff = kcalloc(rx_pool->size,
+ sizeof(struct ibmvnic_rx_buff),
+ GFP_KERNEL);
+ if (!rx_pool->rx_buff) {
+ dev_err(dev, "Couldn't alloc rx buffers\n");
+ release_rx_pools(adapter);
+ return -1;
+ }
+
+ if (alloc_long_term_buff(adapter, &rx_pool->long_term_buff,
+ rx_pool->size * rx_pool->buff_size)) {
+ release_rx_pools(adapter);
+ return -1;
+ }
+
+ for (j = 0; j < rx_pool->size; ++j)
+ rx_pool->free_map[j] = j;
+
+ atomic_set(&rx_pool->available, 0);
+ rx_pool->next_alloc = 0;
+ rx_pool->next_free = 0;
+ }
+
+ return 0;
+}
+
+static void release_tx_pools(struct ibmvnic_adapter *adapter)
+{
+ struct ibmvnic_tx_pool *tx_pool;
+ int i, tx_scrqs;
+
+ if (!adapter->tx_pool)
+ return;
+
+ tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
+ for (i = 0; i < tx_scrqs; i++) {
+ tx_pool = &adapter->tx_pool[i];
+ kfree(tx_pool->tx_buff);
+ free_long_term_buff(adapter, &tx_pool->long_term_buff);
+ kfree(tx_pool->free_map);
+ }
+
+ kfree(adapter->tx_pool);
+ adapter->tx_pool = NULL;
+}
+
+static int init_tx_pools(struct net_device *netdev)
+{
+ struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+ struct device *dev = &adapter->vdev->dev;
+ struct ibmvnic_tx_pool *tx_pool;
+ int tx_subcrqs;
+ int i, j;
+
+ tx_subcrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
+ adapter->tx_pool = kcalloc(tx_subcrqs,
+ sizeof(struct ibmvnic_tx_pool), GFP_KERNEL);
+ if (!adapter->tx_pool)
+ return -1;
+
+ for (i = 0; i < tx_subcrqs; i++) {
+ tx_pool = &adapter->tx_pool[i];
+ tx_pool->tx_buff = kcalloc(adapter->req_tx_entries_per_subcrq,
+ sizeof(struct ibmvnic_tx_buff),
+ GFP_KERNEL);
+ if (!tx_pool->tx_buff) {
+ dev_err(dev, "tx pool buffer allocation failed\n");
+ release_tx_pools(adapter);
+ return -1;
+ }
+
+ if (alloc_long_term_buff(adapter, &tx_pool->long_term_buff,
+ adapter->req_tx_entries_per_subcrq *
+ adapter->req_mtu)) {
+ release_tx_pools(adapter);
+ return -1;
+ }
+
+ tx_pool->free_map = kcalloc(adapter->req_tx_entries_per_subcrq,
+ sizeof(int), GFP_KERNEL);
+ if (!tx_pool->free_map) {
+ release_tx_pools(adapter);
+ return -1;
+ }
+
+ for (j = 0; j < adapter->req_tx_entries_per_subcrq; j++)
+ tx_pool->free_map[j] = j;
+
+ tx_pool->consumer_index = 0;
+ tx_pool->producer_index = 0;
+ }
+
+ return 0;
+}
+
+static void release_bounce_buffer(struct ibmvnic_adapter *adapter)
+{
+ struct device *dev = &adapter->vdev->dev;
+
+ if (!adapter->bounce_buffer)
+ return;
+
+ if (!dma_mapping_error(dev, adapter->bounce_buffer_dma)) {
+ dma_unmap_single(dev, adapter->bounce_buffer_dma,
+ adapter->bounce_buffer_size,
+ DMA_BIDIRECTIONAL);
+ adapter->bounce_buffer_dma = DMA_ERROR_CODE;
+ }
+
+ kfree(adapter->bounce_buffer);
+ adapter->bounce_buffer = NULL;
+}
+
+static int init_bounce_buffer(struct net_device *netdev)
+{
+ struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+ struct device *dev = &adapter->vdev->dev;
+ char *buf;
+ int buf_sz;
+ dma_addr_t map_addr;
+
+ buf_sz = (netdev->mtu + ETH_HLEN - 1) / PAGE_SIZE + 1;
+ buf = kmalloc(adapter->bounce_buffer_size, GFP_KERNEL);
+ if (!buf)
+ return -1;
+
+ map_addr = dma_map_single(dev, buf, buf_sz, DMA_TO_DEVICE);
+ if (dma_mapping_error(dev, map_addr)) {
+ dev_err(dev, "Couldn't map bounce buffer\n");
+ kfree(buf);
+ return -1;
+ }
+
+ adapter->bounce_buffer = buf;
+ adapter->bounce_buffer_size = buf_sz;
+ adapter->bounce_buffer_dma = map_addr;
+ return 0;
+}
+
+static int ibmvnic_login(struct net_device *netdev)
+{
+ struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+ unsigned long timeout = msecs_to_jiffies(30000);
+ struct device *dev = &adapter->vdev->dev;
+
+ do {
+ if (adapter->renegotiate) {
+ adapter->renegotiate = false;
+ release_sub_crqs(adapter);
+
+ reinit_completion(&adapter->init_done);
+ send_cap_queries(adapter);
+ if (!wait_for_completion_timeout(&adapter->init_done,
+ timeout)) {
+ dev_err(dev, "Capabilities query timeout\n");
+ return -1;
+ }
+ }
+
+ reinit_completion(&adapter->init_done);
+ send_login(adapter);
+ if (!wait_for_completion_timeout(&adapter->init_done,
+ timeout)) {
+ dev_err(dev, "Login timeout\n");
+ return -1;
+ }
+ } while (adapter->renegotiate);
+
+ return 0;
+}
+
+static void release_resources(struct ibmvnic_adapter *adapter)
+{
+ release_bounce_buffer(adapter);
+ release_tx_pools(adapter);
+ release_rx_pools(adapter);
+
+ release_sub_crqs(adapter);
+ release_crq_queue(adapter);
+
+ release_stats_token(adapter);
}
static int ibmvnic_open(struct net_device *netdev)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
struct device *dev = &adapter->vdev->dev;
- struct ibmvnic_tx_pool *tx_pool;
union ibmvnic_crq crq;
- int rxadd_subcrqs;
- u64 *size_array;
- int tx_subcrqs;
- int i, j;
+ int rc = 0;
+ int i;
- rxadd_subcrqs =
- be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
- tx_subcrqs =
- be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
- size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) +
- be32_to_cpu(adapter->login_rsp_buf->
- off_rxadd_buff_size));
+ if (adapter->is_closed) {
+ rc = ibmvnic_init(adapter);
+ if (rc)
+ return rc;
+ }
+
+ rc = ibmvnic_login(netdev);
+ if (rc)
+ return rc;
+
+ rc = netif_set_real_num_tx_queues(netdev, adapter->req_tx_queues);
+ if (rc) {
+ dev_err(dev, "failed to set the number of tx queues\n");
+ return -1;
+ }
+
+ rc = init_sub_crq_irqs(adapter);
+ if (rc) {
+ dev_err(dev, "failed to initialize sub crq irqs\n");
+ return -1;
+ }
+
adapter->map_id = 1;
adapter->napi = kcalloc(adapter->req_rx_queues,
sizeof(struct napi_struct), GFP_KERNEL);
if (!adapter->napi)
- goto alloc_napi_failed;
+ goto ibmvnic_open_fail;
for (i = 0; i < adapter->req_rx_queues; i++) {
netif_napi_add(netdev, &adapter->napi[i], ibmvnic_poll,
NAPI_POLL_WEIGHT);
napi_enable(&adapter->napi[i]);
}
- adapter->rx_pool =
- kcalloc(rxadd_subcrqs, sizeof(struct ibmvnic_rx_pool), GFP_KERNEL);
- if (!adapter->rx_pool)
- goto rx_pool_arr_alloc_failed;
send_map_query(adapter);
- for (i = 0; i < rxadd_subcrqs; i++) {
- init_rx_pool(adapter, &adapter->rx_pool[i],
- IBMVNIC_BUFFS_PER_POOL, i,
- be64_to_cpu(size_array[i]), 1);
- if (alloc_rx_pool(adapter, &adapter->rx_pool[i])) {
- dev_err(dev, "Couldn't alloc rx pool\n");
- goto rx_pool_alloc_failed;
- }
- }
- adapter->tx_pool =
- kcalloc(tx_subcrqs, sizeof(struct ibmvnic_tx_pool), GFP_KERNEL);
- if (!adapter->tx_pool)
- goto tx_pool_arr_alloc_failed;
- for (i = 0; i < tx_subcrqs; i++) {
- tx_pool = &adapter->tx_pool[i];
- tx_pool->tx_buff =
- kcalloc(adapter->max_tx_entries_per_subcrq,
- sizeof(struct ibmvnic_tx_buff), GFP_KERNEL);
- if (!tx_pool->tx_buff)
- goto tx_pool_alloc_failed;
+ rc = init_rx_pools(netdev);
+ if (rc)
+ goto ibmvnic_open_fail;
- if (alloc_long_term_buff(adapter, &tx_pool->long_term_buff,
- adapter->max_tx_entries_per_subcrq *
- adapter->req_mtu))
- goto tx_ltb_alloc_failed;
+ rc = init_tx_pools(netdev);
+ if (rc)
+ goto ibmvnic_open_fail;
- tx_pool->free_map =
- kcalloc(adapter->max_tx_entries_per_subcrq,
- sizeof(int), GFP_KERNEL);
- if (!tx_pool->free_map)
- goto tx_fm_alloc_failed;
+ rc = init_bounce_buffer(netdev);
+ if (rc)
+ goto ibmvnic_open_fail;
- for (j = 0; j < adapter->max_tx_entries_per_subcrq; j++)
- tx_pool->free_map[j] = j;
-
- tx_pool->consumer_index = 0;
- tx_pool->producer_index = 0;
- }
- adapter->bounce_buffer_size =
- (netdev->mtu + ETH_HLEN - 1) / PAGE_SIZE + 1;
- adapter->bounce_buffer = kmalloc(adapter->bounce_buffer_size,
- GFP_KERNEL);
- if (!adapter->bounce_buffer)
- goto bounce_alloc_failed;
-
- adapter->bounce_buffer_dma = dma_map_single(dev, adapter->bounce_buffer,
- adapter->bounce_buffer_size,
- DMA_TO_DEVICE);
- if (dma_mapping_error(dev, adapter->bounce_buffer_dma)) {
- dev_err(dev, "Couldn't map tx bounce buffer\n");
- goto bounce_map_failed;
- }
replenish_pools(adapter);
/* We're ready to receive frames, enable the sub-crq interrupts and
@@ -473,48 +663,20 @@ static int ibmvnic_open(struct net_device *netdev)
ibmvnic_send_crq(adapter, &crq);
netif_tx_start_all_queues(netdev);
+ adapter->is_closed = false;
return 0;
-bounce_map_failed:
- kfree(adapter->bounce_buffer);
-bounce_alloc_failed:
- i = tx_subcrqs - 1;
- kfree(adapter->tx_pool[i].free_map);
-tx_fm_alloc_failed:
- free_long_term_buff(adapter, &adapter->tx_pool[i].long_term_buff);
-tx_ltb_alloc_failed:
- kfree(adapter->tx_pool[i].tx_buff);
-tx_pool_alloc_failed:
- for (j = 0; j < i; j++) {
- kfree(adapter->tx_pool[j].tx_buff);
- free_long_term_buff(adapter,
- &adapter->tx_pool[j].long_term_buff);
- kfree(adapter->tx_pool[j].free_map);
- }
- kfree(adapter->tx_pool);
- adapter->tx_pool = NULL;
-tx_pool_arr_alloc_failed:
- i = rxadd_subcrqs;
-rx_pool_alloc_failed:
- for (j = 0; j < i; j++) {
- free_rx_pool(adapter, &adapter->rx_pool[j]);
- free_long_term_buff(adapter,
- &adapter->rx_pool[j].long_term_buff);
- }
- kfree(adapter->rx_pool);
- adapter->rx_pool = NULL;
-rx_pool_arr_alloc_failed:
+ibmvnic_open_fail:
for (i = 0; i < adapter->req_rx_queues; i++)
napi_disable(&adapter->napi[i]);
-alloc_napi_failed:
+ release_resources(adapter);
return -ENOMEM;
}
static int ibmvnic_close(struct net_device *netdev)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
- struct device *dev = &adapter->vdev->dev;
union ibmvnic_crq crq;
int i;
@@ -526,45 +688,16 @@ static int ibmvnic_close(struct net_device *netdev)
if (!adapter->failover)
netif_tx_stop_all_queues(netdev);
- if (adapter->bounce_buffer) {
- if (!dma_mapping_error(dev, adapter->bounce_buffer_dma)) {
- dma_unmap_single(&adapter->vdev->dev,
- adapter->bounce_buffer_dma,
- adapter->bounce_buffer_size,
- DMA_BIDIRECTIONAL);
- adapter->bounce_buffer_dma = DMA_ERROR_CODE;
- }
- kfree(adapter->bounce_buffer);
- adapter->bounce_buffer = NULL;
- }
-
memset(&crq, 0, sizeof(crq));
crq.logical_link_state.first = IBMVNIC_CRQ_CMD;
crq.logical_link_state.cmd = LOGICAL_LINK_STATE;
crq.logical_link_state.link_state = IBMVNIC_LOGICAL_LNK_DN;
ibmvnic_send_crq(adapter, &crq);
- for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
- i++) {
- kfree(adapter->tx_pool[i].tx_buff);
- free_long_term_buff(adapter,
- &adapter->tx_pool[i].long_term_buff);
- kfree(adapter->tx_pool[i].free_map);
- }
- kfree(adapter->tx_pool);
- adapter->tx_pool = NULL;
+ release_resources(adapter);
- for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
- i++) {
- free_rx_pool(adapter, &adapter->rx_pool[i]);
- free_long_term_buff(adapter,
- &adapter->rx_pool[i].long_term_buff);
- }
- kfree(adapter->rx_pool);
- adapter->rx_pool = NULL;
-
+ adapter->is_closed = true;
adapter->closing = false;
-
return 0;
}
@@ -705,6 +838,7 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
u8 *hdrs = (u8 *)&adapter->tx_rx_desc_req;
struct device *dev = &adapter->vdev->dev;
struct ibmvnic_tx_buff *tx_buff = NULL;
+ struct ibmvnic_sub_crq_queue *tx_scrq;
struct ibmvnic_tx_pool *tx_pool;
unsigned int tx_send_failed = 0;
unsigned int tx_map_failed = 0;
@@ -724,6 +858,7 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
int ret = 0;
tx_pool = &adapter->tx_pool[queue_num];
+ tx_scrq = adapter->tx_scrq[queue_num];
txq = netdev_get_tx_queue(netdev, skb_get_queue_mapping(skb));
handle_array = (u64 *)((u8 *)(adapter->login_rsp_buf) +
be32_to_cpu(adapter->login_rsp_buf->
@@ -744,7 +879,7 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
tx_pool->consumer_index =
(tx_pool->consumer_index + 1) %
- adapter->max_tx_entries_per_subcrq;
+ adapter->req_tx_entries_per_subcrq;
tx_buff = &tx_pool->tx_buff[index];
tx_buff->skb = skb;
@@ -817,7 +952,7 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
if (tx_pool->consumer_index == 0)
tx_pool->consumer_index =
- adapter->max_tx_entries_per_subcrq - 1;
+ adapter->req_tx_entries_per_subcrq - 1;
else
tx_pool->consumer_index--;
@@ -826,6 +961,14 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
ret = NETDEV_TX_BUSY;
goto out;
}
+
+ atomic_inc(&tx_scrq->used);
+
+ if (atomic_read(&tx_scrq->used) >= adapter->req_tx_entries_per_subcrq) {
+ netdev_info(netdev, "Stopping queue %d\n", queue_num);
+ netif_stop_subqueue(netdev, queue_num);
+ }
+
tx_packets++;
tx_bytes += skb->len;
txq->trans_start = jiffies;
@@ -1213,6 +1356,7 @@ static struct ibmvnic_sub_crq_queue *init_sub_crq_queue(struct ibmvnic_adapter
scrq->adapter = adapter;
scrq->size = 4 * PAGE_SIZE / sizeof(*scrq->msgs);
scrq->cur = 0;
+ atomic_set(&scrq->used, 0);
scrq->rx_skb_top = NULL;
spin_lock_init(&scrq->lock);
@@ -1238,47 +1382,40 @@ static void release_sub_crqs(struct ibmvnic_adapter *adapter)
int i;
if (adapter->tx_scrq) {
- for (i = 0; i < adapter->req_tx_queues; i++)
- if (adapter->tx_scrq[i]) {
+ for (i = 0; i < adapter->req_tx_queues; i++) {
+ if (!adapter->tx_scrq[i])
+ continue;
+
+ if (adapter->tx_scrq[i]->irq) {
free_irq(adapter->tx_scrq[i]->irq,
adapter->tx_scrq[i]);
irq_dispose_mapping(adapter->tx_scrq[i]->irq);
- release_sub_crq_queue(adapter,
- adapter->tx_scrq[i]);
+ adapter->tx_scrq[i]->irq = 0;
}
+
+ release_sub_crq_queue(adapter, adapter->tx_scrq[i]);
+ }
+
+ kfree(adapter->tx_scrq);
adapter->tx_scrq = NULL;
}
if (adapter->rx_scrq) {
- for (i = 0; i < adapter->req_rx_queues; i++)
- if (adapter->rx_scrq[i]) {
+ for (i = 0; i < adapter->req_rx_queues; i++) {
+ if (!adapter->rx_scrq[i])
+ continue;
+
+ if (adapter->rx_scrq[i]->irq) {
free_irq(adapter->rx_scrq[i]->irq,
adapter->rx_scrq[i]);
irq_dispose_mapping(adapter->rx_scrq[i]->irq);
- release_sub_crq_queue(adapter,
- adapter->rx_scrq[i]);
+ adapter->rx_scrq[i]->irq = 0;
}
- adapter->rx_scrq = NULL;
- }
-}
-static void release_sub_crqs_no_irqs(struct ibmvnic_adapter *adapter)
-{
- int i;
+ release_sub_crq_queue(adapter, adapter->rx_scrq[i]);
+ }
- if (adapter->tx_scrq) {
- for (i = 0; i < adapter->req_tx_queues; i++)
- if (adapter->tx_scrq[i])
- release_sub_crq_queue(adapter,
- adapter->tx_scrq[i]);
- adapter->tx_scrq = NULL;
- }
-
- if (adapter->rx_scrq) {
- for (i = 0; i < adapter->req_rx_queues; i++)
- if (adapter->rx_scrq[i])
- release_sub_crq_queue(adapter,
- adapter->rx_scrq[i]);
+ kfree(adapter->rx_scrq);
adapter->rx_scrq = NULL;
}
}
@@ -1355,14 +1492,28 @@ static int ibmvnic_complete_tx(struct ibmvnic_adapter *adapter,
DMA_TO_DEVICE);
}
- if (txbuff->last_frag)
+ if (txbuff->last_frag) {
+ atomic_dec(&scrq->used);
+
+ if (atomic_read(&scrq->used) <=
+ (adapter->req_tx_entries_per_subcrq / 2) &&
+ netif_subqueue_stopped(adapter->netdev,
+ txbuff->skb)) {
+ netif_wake_subqueue(adapter->netdev,
+ scrq->pool_index);
+ netdev_dbg(adapter->netdev,
+ "Started queue %d\n",
+ scrq->pool_index);
+ }
+
dev_kfree_skb_any(txbuff->skb);
+ }
adapter->tx_pool[pool].free_map[adapter->tx_pool[pool].
producer_index] = index;
adapter->tx_pool[pool].producer_index =
(adapter->tx_pool[pool].producer_index + 1) %
- adapter->max_tx_entries_per_subcrq;
+ adapter->req_tx_entries_per_subcrq;
}
/* remove tx_comp scrq*/
next->tx_comp.first = 0;
@@ -1460,7 +1611,7 @@ static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter)
free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]);
irq_dispose_mapping(adapter->rx_scrq[j]->irq);
}
- release_sub_crqs_no_irqs(adapter);
+ release_sub_crqs(adapter);
return rc;
}
@@ -2215,57 +2366,6 @@ static void handle_error_info_rsp(union ibmvnic_crq *crq,
kfree(error_buff);
}
-static void handle_dump_size_rsp(union ibmvnic_crq *crq,
- struct ibmvnic_adapter *adapter)
-{
- int len = be32_to_cpu(crq->request_dump_size_rsp.len);
- struct ibmvnic_inflight_cmd *inflight_cmd;
- struct device *dev = &adapter->vdev->dev;
- union ibmvnic_crq newcrq;
- unsigned long flags;
-
- /* allocate and map buffer */
- adapter->dump_data = kmalloc(len, GFP_KERNEL);
- if (!adapter->dump_data) {
- complete(&adapter->fw_done);
- return;
- }
-
- adapter->dump_data_token = dma_map_single(dev, adapter->dump_data, len,
- DMA_FROM_DEVICE);
-
- if (dma_mapping_error(dev, adapter->dump_data_token)) {
- if (!firmware_has_feature(FW_FEATURE_CMO))
- dev_err(dev, "Couldn't map dump data\n");
- kfree(adapter->dump_data);
- complete(&adapter->fw_done);
- return;
- }
-
- inflight_cmd = kmalloc(sizeof(*inflight_cmd), GFP_ATOMIC);
- if (!inflight_cmd) {
- dma_unmap_single(dev, adapter->dump_data_token, len,
- DMA_FROM_DEVICE);
- kfree(adapter->dump_data);
- complete(&adapter->fw_done);
- return;
- }
-
- memset(&newcrq, 0, sizeof(newcrq));
- newcrq.request_dump.first = IBMVNIC_CRQ_CMD;
- newcrq.request_dump.cmd = REQUEST_DUMP;
- newcrq.request_dump.ioba = cpu_to_be32(adapter->dump_data_token);
- newcrq.request_dump.len = cpu_to_be32(adapter->dump_data_size);
-
- memcpy(&inflight_cmd->crq, &newcrq, sizeof(newcrq));
-
- spin_lock_irqsave(&adapter->inflight_lock, flags);
- list_add_tail(&inflight_cmd->list, &adapter->inflight);
- spin_unlock_irqrestore(&adapter->inflight_lock, flags);
-
- ibmvnic_send_crq(adapter, &newcrq);
-}
-
static void handle_error_indication(union ibmvnic_crq *crq,
struct ibmvnic_adapter *adapter)
{
@@ -2401,7 +2501,7 @@ static void handle_request_cap_rsp(union ibmvnic_crq *crq,
*req_value,
(long int)be64_to_cpu(crq->request_capability_rsp.
number), name);
- release_sub_crqs_no_irqs(adapter);
+ release_sub_crqs(adapter);
*req_value = be64_to_cpu(crq->request_capability_rsp.number);
init_sub_crqs(adapter, 1);
return;
@@ -2446,7 +2546,6 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq,
struct device *dev = &adapter->vdev->dev;
struct ibmvnic_login_rsp_buffer *login_rsp = adapter->login_rsp_buf;
struct ibmvnic_login_buffer *login = adapter->login_buf;
- union ibmvnic_crq crq;
int i;
dma_unmap_single(dev, adapter->login_buf_token, adapter->login_buf_sz,
@@ -2481,11 +2580,6 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq,
}
complete(&adapter->init_done);
- memset(&crq, 0, sizeof(crq));
- crq.request_ras_comp_num.first = IBMVNIC_CRQ_CMD;
- crq.request_ras_comp_num.cmd = REQUEST_RAS_COMP_NUM;
- ibmvnic_send_crq(adapter, &crq);
-
return 0;
}
@@ -2721,476 +2815,6 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq,
}
}
-static void handle_control_ras_rsp(union ibmvnic_crq *crq,
- struct ibmvnic_adapter *adapter)
-{
- u8 correlator = crq->control_ras_rsp.correlator;
- struct device *dev = &adapter->vdev->dev;
- bool found = false;
- int i;
-
- if (crq->control_ras_rsp.rc.code) {
- dev_warn(dev, "Control ras failed rc=%d\n",
- crq->control_ras_rsp.rc.code);
- return;
- }
-
- for (i = 0; i < adapter->ras_comp_num; i++) {
- if (adapter->ras_comps[i].correlator == correlator) {
- found = true;
- break;
- }
- }
-
- if (!found) {
- dev_warn(dev, "Correlator not found on control_ras_rsp\n");
- return;
- }
-
- switch (crq->control_ras_rsp.op) {
- case IBMVNIC_TRACE_LEVEL:
- adapter->ras_comps[i].trace_level = crq->control_ras.level;
- break;
- case IBMVNIC_ERROR_LEVEL:
- adapter->ras_comps[i].error_check_level =
- crq->control_ras.level;
- break;
- case IBMVNIC_TRACE_PAUSE:
- adapter->ras_comp_int[i].paused = 1;
- break;
- case IBMVNIC_TRACE_RESUME:
- adapter->ras_comp_int[i].paused = 0;
- break;
- case IBMVNIC_TRACE_ON:
- adapter->ras_comps[i].trace_on = 1;
- break;
- case IBMVNIC_TRACE_OFF:
- adapter->ras_comps[i].trace_on = 0;
- break;
- case IBMVNIC_CHG_TRACE_BUFF_SZ:
- /* trace_buff_sz is 3 bytes, stuff it into an int */
- ((u8 *)(&adapter->ras_comps[i].trace_buff_size))[0] = 0;
- ((u8 *)(&adapter->ras_comps[i].trace_buff_size))[1] =
- crq->control_ras_rsp.trace_buff_sz[0];
- ((u8 *)(&adapter->ras_comps[i].trace_buff_size))[2] =
- crq->control_ras_rsp.trace_buff_sz[1];
- ((u8 *)(&adapter->ras_comps[i].trace_buff_size))[3] =
- crq->control_ras_rsp.trace_buff_sz[2];
- break;
- default:
- dev_err(dev, "invalid op %d on control_ras_rsp",
- crq->control_ras_rsp.op);
- }
-}
-
-static ssize_t trace_read(struct file *file, char __user *user_buf, size_t len,
- loff_t *ppos)
-{
- struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
- struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
- struct device *dev = &adapter->vdev->dev;
- struct ibmvnic_fw_trace_entry *trace;
- int num = ras_comp_int->num;
- union ibmvnic_crq crq;
- dma_addr_t trace_tok;
-
- if (*ppos >= be32_to_cpu(adapter->ras_comps[num].trace_buff_size))
- return 0;
-
- trace =
- dma_alloc_coherent(dev,
- be32_to_cpu(adapter->ras_comps[num].
- trace_buff_size), &trace_tok,
- GFP_KERNEL);
- if (!trace) {
- dev_err(dev, "Couldn't alloc trace buffer\n");
- return 0;
- }
-
- memset(&crq, 0, sizeof(crq));
- crq.collect_fw_trace.first = IBMVNIC_CRQ_CMD;
- crq.collect_fw_trace.cmd = COLLECT_FW_TRACE;
- crq.collect_fw_trace.correlator = adapter->ras_comps[num].correlator;
- crq.collect_fw_trace.ioba = cpu_to_be32(trace_tok);
- crq.collect_fw_trace.len = adapter->ras_comps[num].trace_buff_size;
-
- init_completion(&adapter->fw_done);
- ibmvnic_send_crq(adapter, &crq);
- wait_for_completion(&adapter->fw_done);
-
- if (*ppos + len > be32_to_cpu(adapter->ras_comps[num].trace_buff_size))
- len =
- be32_to_cpu(adapter->ras_comps[num].trace_buff_size) -
- *ppos;
-
- copy_to_user(user_buf, &((u8 *)trace)[*ppos], len);
-
- dma_free_coherent(dev,
- be32_to_cpu(adapter->ras_comps[num].trace_buff_size),
- trace, trace_tok);
- *ppos += len;
- return len;
-}
-
-static const struct file_operations trace_ops = {
- .owner = THIS_MODULE,
- .open = simple_open,
- .read = trace_read,
-};
-
-static ssize_t paused_read(struct file *file, char __user *user_buf, size_t len,
- loff_t *ppos)
-{
- struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
- struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
- int num = ras_comp_int->num;
- char buff[5]; /* 1 or 0 plus \n and \0 */
- int size;
-
- size = sprintf(buff, "%d\n", adapter->ras_comp_int[num].paused);
-
- if (*ppos >= size)
- return 0;
-
- copy_to_user(user_buf, buff, size);
- *ppos += size;
- return size;
-}
-
-static ssize_t paused_write(struct file *file, const char __user *user_buf,
- size_t len, loff_t *ppos)
-{
- struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
- struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
- int num = ras_comp_int->num;
- union ibmvnic_crq crq;
- unsigned long val;
- char buff[9]; /* decimal max int plus \n and \0 */
-
- copy_from_user(buff, user_buf, sizeof(buff));
- val = kstrtoul(buff, 10, NULL);
-
- adapter->ras_comp_int[num].paused = val ? 1 : 0;
-
- memset(&crq, 0, sizeof(crq));
- crq.control_ras.first = IBMVNIC_CRQ_CMD;
- crq.control_ras.cmd = CONTROL_RAS;
- crq.control_ras.correlator = adapter->ras_comps[num].correlator;
- crq.control_ras.op = val ? IBMVNIC_TRACE_PAUSE : IBMVNIC_TRACE_RESUME;
- ibmvnic_send_crq(adapter, &crq);
-
- return len;
-}
-
-static const struct file_operations paused_ops = {
- .owner = THIS_MODULE,
- .open = simple_open,
- .read = paused_read,
- .write = paused_write,
-};
-
-static ssize_t tracing_read(struct file *file, char __user *user_buf,
- size_t len, loff_t *ppos)
-{
- struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
- struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
- int num = ras_comp_int->num;
- char buff[5]; /* 1 or 0 plus \n and \0 */
- int size;
-
- size = sprintf(buff, "%d\n", adapter->ras_comps[num].trace_on);
-
- if (*ppos >= size)
- return 0;
-
- copy_to_user(user_buf, buff, size);
- *ppos += size;
- return size;
-}
-
-static ssize_t tracing_write(struct file *file, const char __user *user_buf,
- size_t len, loff_t *ppos)
-{
- struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
- struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
- int num = ras_comp_int->num;
- union ibmvnic_crq crq;
- unsigned long val;
- char buff[9]; /* decimal max int plus \n and \0 */
-
- copy_from_user(buff, user_buf, sizeof(buff));
- val = kstrtoul(buff, 10, NULL);
-
- memset(&crq, 0, sizeof(crq));
- crq.control_ras.first = IBMVNIC_CRQ_CMD;
- crq.control_ras.cmd = CONTROL_RAS;
- crq.control_ras.correlator = adapter->ras_comps[num].correlator;
- crq.control_ras.op = val ? IBMVNIC_TRACE_ON : IBMVNIC_TRACE_OFF;
-
- return len;
-}
-
-static const struct file_operations tracing_ops = {
- .owner = THIS_MODULE,
- .open = simple_open,
- .read = tracing_read,
- .write = tracing_write,
-};
-
-static ssize_t error_level_read(struct file *file, char __user *user_buf,
- size_t len, loff_t *ppos)
-{
- struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
- struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
- int num = ras_comp_int->num;
- char buff[5]; /* decimal max char plus \n and \0 */
- int size;
-
- size = sprintf(buff, "%d\n", adapter->ras_comps[num].error_check_level);
-
- if (*ppos >= size)
- return 0;
-
- copy_to_user(user_buf, buff, size);
- *ppos += size;
- return size;
-}
-
-static ssize_t error_level_write(struct file *file, const char __user *user_buf,
- size_t len, loff_t *ppos)
-{
- struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
- struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
- int num = ras_comp_int->num;
- union ibmvnic_crq crq;
- unsigned long val;
- char buff[9]; /* decimal max int plus \n and \0 */
-
- copy_from_user(buff, user_buf, sizeof(buff));
- val = kstrtoul(buff, 10, NULL);
-
- if (val > 9)
- val = 9;
-
- memset(&crq, 0, sizeof(crq));
- crq.control_ras.first = IBMVNIC_CRQ_CMD;
- crq.control_ras.cmd = CONTROL_RAS;
- crq.control_ras.correlator = adapter->ras_comps[num].correlator;
- crq.control_ras.op = IBMVNIC_ERROR_LEVEL;
- crq.control_ras.level = val;
- ibmvnic_send_crq(adapter, &crq);
-
- return len;
-}
-
-static const struct file_operations error_level_ops = {
- .owner = THIS_MODULE,
- .open = simple_open,
- .read = error_level_read,
- .write = error_level_write,
-};
-
-static ssize_t trace_level_read(struct file *file, char __user *user_buf,
- size_t len, loff_t *ppos)
-{
- struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
- struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
- int num = ras_comp_int->num;
- char buff[5]; /* decimal max char plus \n and \0 */
- int size;
-
- size = sprintf(buff, "%d\n", adapter->ras_comps[num].trace_level);
- if (*ppos >= size)
- return 0;
-
- copy_to_user(user_buf, buff, size);
- *ppos += size;
- return size;
-}
-
-static ssize_t trace_level_write(struct file *file, const char __user *user_buf,
- size_t len, loff_t *ppos)
-{
- struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
- struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
- union ibmvnic_crq crq;
- unsigned long val;
- char buff[9]; /* decimal max int plus \n and \0 */
-
- copy_from_user(buff, user_buf, sizeof(buff));
- val = kstrtoul(buff, 10, NULL);
- if (val > 9)
- val = 9;
-
- memset(&crq, 0, sizeof(crq));
- crq.control_ras.first = IBMVNIC_CRQ_CMD;
- crq.control_ras.cmd = CONTROL_RAS;
- crq.control_ras.correlator =
- adapter->ras_comps[ras_comp_int->num].correlator;
- crq.control_ras.op = IBMVNIC_TRACE_LEVEL;
- crq.control_ras.level = val;
- ibmvnic_send_crq(adapter, &crq);
-
- return len;
-}
-
-static const struct file_operations trace_level_ops = {
- .owner = THIS_MODULE,
- .open = simple_open,
- .read = trace_level_read,
- .write = trace_level_write,
-};
-
-static ssize_t trace_buff_size_read(struct file *file, char __user *user_buf,
- size_t len, loff_t *ppos)
-{
- struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
- struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
- int num = ras_comp_int->num;
- char buff[9]; /* decimal max int plus \n and \0 */
- int size;
-
- size = sprintf(buff, "%d\n", adapter->ras_comps[num].trace_buff_size);
- if (*ppos >= size)
- return 0;
-
- copy_to_user(user_buf, buff, size);
- *ppos += size;
- return size;
-}
-
-static ssize_t trace_buff_size_write(struct file *file,
- const char __user *user_buf, size_t len,
- loff_t *ppos)
-{
- struct ibmvnic_fw_comp_internal *ras_comp_int = file->private_data;
- struct ibmvnic_adapter *adapter = ras_comp_int->adapter;
- union ibmvnic_crq crq;
- unsigned long val;
- char buff[9]; /* decimal max int plus \n and \0 */
-
- copy_from_user(buff, user_buf, sizeof(buff));
- val = kstrtoul(buff, 10, NULL);
-
- memset(&crq, 0, sizeof(crq));
- crq.control_ras.first = IBMVNIC_CRQ_CMD;
- crq.control_ras.cmd = CONTROL_RAS;
- crq.control_ras.correlator =
- adapter->ras_comps[ras_comp_int->num].correlator;
- crq.control_ras.op = IBMVNIC_CHG_TRACE_BUFF_SZ;
- /* trace_buff_sz is 3 bytes, stuff an int into it */
- crq.control_ras.trace_buff_sz[0] = ((u8 *)(&val))[5];
- crq.control_ras.trace_buff_sz[1] = ((u8 *)(&val))[6];
- crq.control_ras.trace_buff_sz[2] = ((u8 *)(&val))[7];
- ibmvnic_send_crq(adapter, &crq);
-
- return len;
-}
-
-static const struct file_operations trace_size_ops = {
- .owner = THIS_MODULE,
- .open = simple_open,
- .read = trace_buff_size_read,
- .write = trace_buff_size_write,
-};
-
-static void handle_request_ras_comps_rsp(union ibmvnic_crq *crq,
- struct ibmvnic_adapter *adapter)
-{
- struct device *dev = &adapter->vdev->dev;
- struct dentry *dir_ent;
- struct dentry *ent;
- int i;
-
- debugfs_remove_recursive(adapter->ras_comps_ent);
-
- adapter->ras_comps_ent = debugfs_create_dir("ras_comps",
- adapter->debugfs_dir);
- if (!adapter->ras_comps_ent || IS_ERR(adapter->ras_comps_ent)) {
- dev_info(dev, "debugfs create ras_comps dir failed\n");
- return;
- }
-
- for (i = 0; i < adapter->ras_comp_num; i++) {
- dir_ent = debugfs_create_dir(adapter->ras_comps[i].name,
- adapter->ras_comps_ent);
- if (!dir_ent || IS_ERR(dir_ent)) {
- dev_info(dev, "debugfs create %s dir failed\n",
- adapter->ras_comps[i].name);
- continue;
- }
-
- adapter->ras_comp_int[i].adapter = adapter;
- adapter->ras_comp_int[i].num = i;
- adapter->ras_comp_int[i].desc_blob.data =
- &adapter->ras_comps[i].description;
- adapter->ras_comp_int[i].desc_blob.size =
- sizeof(adapter->ras_comps[i].description);
-
- /* Don't need to remember the dentry's because the debugfs dir
- * gets removed recursively
- */
- ent = debugfs_create_blob("description", S_IRUGO, dir_ent,
- &adapter->ras_comp_int[i].desc_blob);
- ent = debugfs_create_file("trace_buf_size", S_IRUGO | S_IWUSR,
- dir_ent, &adapter->ras_comp_int[i],
- &trace_size_ops);
- ent = debugfs_create_file("trace_level",
- S_IRUGO |
- (adapter->ras_comps[i].trace_level !=
- 0xFF ? S_IWUSR : 0),
- dir_ent, &adapter->ras_comp_int[i],
- &trace_level_ops);
- ent = debugfs_create_file("error_level",
- S_IRUGO |
- (adapter->
- ras_comps[i].error_check_level !=
- 0xFF ? S_IWUSR : 0),
- dir_ent, &adapter->ras_comp_int[i],
- &trace_level_ops);
- ent = debugfs_create_file("tracing", S_IRUGO | S_IWUSR,
- dir_ent, &adapter->ras_comp_int[i],
- &tracing_ops);
- ent = debugfs_create_file("paused", S_IRUGO | S_IWUSR,
- dir_ent, &adapter->ras_comp_int[i],
- &paused_ops);
- ent = debugfs_create_file("trace", S_IRUGO, dir_ent,
- &adapter->ras_comp_int[i],
- &trace_ops);
- }
-}
-
-static void handle_request_ras_comp_num_rsp(union ibmvnic_crq *crq,
- struct ibmvnic_adapter *adapter)
-{
- int len = adapter->ras_comp_num * sizeof(struct ibmvnic_fw_component);
- struct device *dev = &adapter->vdev->dev;
- union ibmvnic_crq newcrq;
-
- adapter->ras_comps = dma_alloc_coherent(dev, len,
- &adapter->ras_comps_tok,
- GFP_KERNEL);
- if (!adapter->ras_comps) {
- if (!firmware_has_feature(FW_FEATURE_CMO))
- dev_err(dev, "Couldn't alloc fw comps buffer\n");
- return;
- }
-
- adapter->ras_comp_int = kmalloc(adapter->ras_comp_num *
- sizeof(struct ibmvnic_fw_comp_internal),
- GFP_KERNEL);
- if (!adapter->ras_comp_int)
- dma_free_coherent(dev, len, adapter->ras_comps,
- adapter->ras_comps_tok);
-
- memset(&newcrq, 0, sizeof(newcrq));
- newcrq.request_ras_comps.first = IBMVNIC_CRQ_CMD;
- newcrq.request_ras_comps.cmd = REQUEST_RAS_COMPS;
- newcrq.request_ras_comps.ioba = cpu_to_be32(adapter->ras_comps_tok);
- newcrq.request_ras_comps.len = cpu_to_be32(len);
- ibmvnic_send_crq(adapter, &newcrq);
-}
-
static void ibmvnic_free_inflight(struct ibmvnic_adapter *adapter)
{
struct ibmvnic_inflight_cmd *inflight_cmd, *tmp1;
@@ -3212,9 +2836,6 @@ static void ibmvnic_free_inflight(struct ibmvnic_adapter *adapter)
kfree(adapter->login_rsp_buf);
kfree(adapter->login_buf);
break;
- case REQUEST_DUMP:
- complete(&adapter->fw_done);
- break;
case REQUEST_ERROR_INFO:
spin_lock_irqsave(&adapter->error_list_lock, flags2);
list_for_each_entry_safe(error_buff, tmp2,
@@ -3374,14 +2995,6 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
netdev_dbg(netdev, "Got Statistics Response\n");
complete(&adapter->stats_done);
break;
- case REQUEST_DUMP_SIZE_RSP:
- netdev_dbg(netdev, "Got Request Dump Size Response\n");
- handle_dump_size_rsp(crq, adapter);
- break;
- case REQUEST_DUMP_RSP:
- netdev_dbg(netdev, "Got Request Dump Response\n");
- complete(&adapter->fw_done);
- break;
case QUERY_IP_OFFLOAD_RSP:
netdev_dbg(netdev, "Got Query IP offload Response\n");
handle_query_ip_offload_rsp(adapter);
@@ -3394,26 +3007,7 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
dma_unmap_single(dev, adapter->ip_offload_ctrl_tok,
sizeof(adapter->ip_offload_ctrl),
DMA_TO_DEVICE);
- /* We're done with the queries, perform the login */
- send_login(adapter);
- break;
- case REQUEST_RAS_COMP_NUM_RSP:
- netdev_dbg(netdev, "Got Request RAS Comp Num Response\n");
- if (crq->request_ras_comp_num_rsp.rc.code == 10) {
- netdev_dbg(netdev, "Request RAS Comp Num not supported\n");
- break;
- }
- adapter->ras_comp_num =
- be32_to_cpu(crq->request_ras_comp_num_rsp.num_components);
- handle_request_ras_comp_num_rsp(crq, adapter);
- break;
- case REQUEST_RAS_COMPS_RSP:
- netdev_dbg(netdev, "Got Request RAS Comps Response\n");
- handle_request_ras_comps_rsp(crq, adapter);
- break;
- case CONTROL_RAS_RSP:
- netdev_dbg(netdev, "Got Control RAS Response\n");
- handle_control_ras_rsp(crq, adapter);
+ complete(&adapter->init_done);
break;
case COLLECT_FW_TRACE_RSP:
netdev_dbg(netdev, "Got Collect firmware trace Response\n");
@@ -3520,12 +3114,15 @@ static int ibmvnic_reset_crq(struct ibmvnic_adapter *adapter)
return rc;
}
-static void ibmvnic_release_crq_queue(struct ibmvnic_adapter *adapter)
+static void release_crq_queue(struct ibmvnic_adapter *adapter)
{
struct ibmvnic_crq_queue *crq = &adapter->crq;
struct vio_dev *vdev = adapter->vdev;
long rc;
+ if (!crq->msgs)
+ return;
+
netdev_dbg(adapter->netdev, "Releasing CRQ\n");
free_irq(vdev->irq, adapter);
tasklet_kill(&adapter->tasklet);
@@ -3536,15 +3133,19 @@ static void ibmvnic_release_crq_queue(struct ibmvnic_adapter *adapter)
dma_unmap_single(&vdev->dev, crq->msg_token, PAGE_SIZE,
DMA_BIDIRECTIONAL);
free_page((unsigned long)crq->msgs);
+ crq->msgs = NULL;
}
-static int ibmvnic_init_crq_queue(struct ibmvnic_adapter *adapter)
+static int init_crq_queue(struct ibmvnic_adapter *adapter)
{
struct ibmvnic_crq_queue *crq = &adapter->crq;
struct device *dev = &adapter->vdev->dev;
struct vio_dev *vdev = adapter->vdev;
int rc, retrc = -ENOMEM;
+ if (crq->msgs)
+ return 0;
+
crq->msgs = (union ibmvnic_crq *)get_zeroed_page(GFP_KERNEL);
/* Should we allocate more than one page? */
@@ -3606,48 +3207,10 @@ static int ibmvnic_init_crq_queue(struct ibmvnic_adapter *adapter)
dma_unmap_single(dev, crq->msg_token, PAGE_SIZE, DMA_BIDIRECTIONAL);
map_failed:
free_page((unsigned long)crq->msgs);
+ crq->msgs = NULL;
return retrc;
}
-/* debugfs for dump */
-static int ibmvnic_dump_show(struct seq_file *seq, void *v)
-{
- struct net_device *netdev = seq->private;
- struct ibmvnic_adapter *adapter = netdev_priv(netdev);
- struct device *dev = &adapter->vdev->dev;
- union ibmvnic_crq crq;
-
- memset(&crq, 0, sizeof(crq));
- crq.request_dump_size.first = IBMVNIC_CRQ_CMD;
- crq.request_dump_size.cmd = REQUEST_DUMP_SIZE;
-
- init_completion(&adapter->fw_done);
- ibmvnic_send_crq(adapter, &crq);
- wait_for_completion(&adapter->fw_done);
-
- seq_write(seq, adapter->dump_data, adapter->dump_data_size);
-
- dma_unmap_single(dev, adapter->dump_data_token, adapter->dump_data_size,
- DMA_BIDIRECTIONAL);
-
- kfree(adapter->dump_data);
-
- return 0;
-}
-
-static int ibmvnic_dump_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ibmvnic_dump_show, inode->i_private);
-}
-
-static const struct file_operations ibmvnic_dump_ops = {
- .owner = THIS_MODULE,
- .open = ibmvnic_dump_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static void handle_crq_init_rsp(struct work_struct *work)
{
struct ibmvnic_adapter *adapter = container_of(work,
@@ -3675,26 +3238,6 @@ static void handle_crq_init_rsp(struct work_struct *work)
goto task_failed;
}
- do {
- if (adapter->renegotiate) {
- adapter->renegotiate = false;
- release_sub_crqs_no_irqs(adapter);
-
- reinit_completion(&adapter->init_done);
- send_cap_queries(adapter);
- if (!wait_for_completion_timeout(&adapter->init_done,
- timeout)) {
- dev_err(dev, "Passive init timeout\n");
- goto task_failed;
- }
- }
- } while (adapter->renegotiate);
- rc = init_sub_crq_irqs(adapter);
-
- if (rc)
- goto task_failed;
-
- netdev->real_num_tx_queues = adapter->req_tx_queues;
netdev->mtu = adapter->req_mtu - ETH_HLEN;
if (adapter->failover) {
@@ -3726,14 +3269,40 @@ static void handle_crq_init_rsp(struct work_struct *work)
dev_err(dev, "Passive initialization was not successful\n");
}
+static int ibmvnic_init(struct ibmvnic_adapter *adapter)
+{
+ struct device *dev = &adapter->vdev->dev;
+ unsigned long timeout = msecs_to_jiffies(30000);
+ int rc;
+
+ rc = init_crq_queue(adapter);
+ if (rc) {
+ dev_err(dev, "Couldn't initialize crq. rc=%d\n", rc);
+ return rc;
+ }
+
+ rc = init_stats_token(adapter);
+ if (rc) {
+ release_crq_queue(adapter);
+ return rc;
+ }
+
+ init_completion(&adapter->init_done);
+ ibmvnic_send_crq_init(adapter);
+ if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
+ dev_err(dev, "Initialization sequence timed out\n");
+ release_crq_queue(adapter);
+ return -1;
+ }
+
+ return 0;
+}
+
static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
{
- unsigned long timeout = msecs_to_jiffies(30000);
struct ibmvnic_adapter *adapter;
struct net_device *netdev;
unsigned char *mac_addr_p;
- struct dentry *ent;
- char buf[17]; /* debugfs name buf */
int rc;
dev_dbg(&dev->dev, "entering ibmvnic_probe for UA 0x%x\n",
@@ -3771,118 +3340,36 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
spin_lock_init(&adapter->stats_lock);
- rc = ibmvnic_init_crq_queue(adapter);
- if (rc) {
- dev_err(&dev->dev, "Couldn't initialize crq. rc=%d\n", rc);
- goto free_netdev;
- }
-
INIT_LIST_HEAD(&adapter->errors);
INIT_LIST_HEAD(&adapter->inflight);
spin_lock_init(&adapter->error_list_lock);
spin_lock_init(&adapter->inflight_lock);
- adapter->stats_token = dma_map_single(&dev->dev, &adapter->stats,
- sizeof(struct ibmvnic_statistics),
- DMA_FROM_DEVICE);
- if (dma_mapping_error(&dev->dev, adapter->stats_token)) {
- if (!firmware_has_feature(FW_FEATURE_CMO))
- dev_err(&dev->dev, "Couldn't map stats buffer\n");
- rc = -ENOMEM;
- goto free_crq;
- }
-
- snprintf(buf, sizeof(buf), "ibmvnic_%x", dev->unit_address);
- ent = debugfs_create_dir(buf, NULL);
- if (!ent || IS_ERR(ent)) {
- dev_info(&dev->dev, "debugfs create directory failed\n");
- adapter->debugfs_dir = NULL;
- } else {
- adapter->debugfs_dir = ent;
- ent = debugfs_create_file("dump", S_IRUGO, adapter->debugfs_dir,
- netdev, &ibmvnic_dump_ops);
- if (!ent || IS_ERR(ent)) {
- dev_info(&dev->dev,
- "debugfs create dump file failed\n");
- adapter->debugfs_dump = NULL;
- } else {
- adapter->debugfs_dump = ent;
- }
- }
-
- init_completion(&adapter->init_done);
- ibmvnic_send_crq_init(adapter);
- if (!wait_for_completion_timeout(&adapter->init_done, timeout))
- return 0;
-
- do {
- if (adapter->renegotiate) {
- adapter->renegotiate = false;
- release_sub_crqs_no_irqs(adapter);
-
- reinit_completion(&adapter->init_done);
- send_cap_queries(adapter);
- if (!wait_for_completion_timeout(&adapter->init_done,
- timeout))
- return 0;
- }
- } while (adapter->renegotiate);
-
- rc = init_sub_crq_irqs(adapter);
+ rc = ibmvnic_init(adapter);
if (rc) {
- dev_err(&dev->dev, "failed to initialize sub crq irqs\n");
- goto free_debugfs;
+ free_netdev(netdev);
+ return rc;
}
- netdev->real_num_tx_queues = adapter->req_tx_queues;
netdev->mtu = adapter->req_mtu - ETH_HLEN;
+ adapter->is_closed = false;
rc = register_netdev(netdev);
if (rc) {
dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc);
- goto free_sub_crqs;
+ free_netdev(netdev);
+ return rc;
}
dev_info(&dev->dev, "ibmvnic registered\n");
return 0;
-
-free_sub_crqs:
- release_sub_crqs(adapter);
-free_debugfs:
- if (adapter->debugfs_dir && !IS_ERR(adapter->debugfs_dir))
- debugfs_remove_recursive(adapter->debugfs_dir);
-free_crq:
- ibmvnic_release_crq_queue(adapter);
-free_netdev:
- free_netdev(netdev);
- return rc;
}
static int ibmvnic_remove(struct vio_dev *dev)
{
struct net_device *netdev = dev_get_drvdata(&dev->dev);
- struct ibmvnic_adapter *adapter = netdev_priv(netdev);
unregister_netdev(netdev);
-
- release_sub_crqs(adapter);
-
- ibmvnic_release_crq_queue(adapter);
-
- if (adapter->debugfs_dir && !IS_ERR(adapter->debugfs_dir))
- debugfs_remove_recursive(adapter->debugfs_dir);
-
- dma_unmap_single(&dev->dev, adapter->stats_token,
- sizeof(struct ibmvnic_statistics), DMA_FROM_DEVICE);
-
- if (adapter->ras_comps)
- dma_free_coherent(&dev->dev,
- adapter->ras_comp_num *
- sizeof(struct ibmvnic_fw_component),
- adapter->ras_comps, adapter->ras_comps_tok);
-
- kfree(adapter->ras_comp_int);
-
free_netdev(netdev);
dev_set_drvdata(&dev->dev, NULL);
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index 422824f..b0d0b89 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -772,20 +772,10 @@ enum ibmvnic_commands {
ERROR_INDICATION = 0x08,
REQUEST_ERROR_INFO = 0x09,
REQUEST_ERROR_RSP = 0x89,
- REQUEST_DUMP_SIZE = 0x0A,
- REQUEST_DUMP_SIZE_RSP = 0x8A,
- REQUEST_DUMP = 0x0B,
- REQUEST_DUMP_RSP = 0x8B,
LOGICAL_LINK_STATE = 0x0C,
LOGICAL_LINK_STATE_RSP = 0x8C,
REQUEST_STATISTICS = 0x0D,
REQUEST_STATISTICS_RSP = 0x8D,
- REQUEST_RAS_COMP_NUM = 0x0E,
- REQUEST_RAS_COMP_NUM_RSP = 0x8E,
- REQUEST_RAS_COMPS = 0x0F,
- REQUEST_RAS_COMPS_RSP = 0x8F,
- CONTROL_RAS = 0x10,
- CONTROL_RAS_RSP = 0x90,
COLLECT_FW_TRACE = 0x11,
COLLECT_FW_TRACE_RSP = 0x91,
LINK_STATE_INDICATION = 0x12,
@@ -806,8 +796,6 @@ enum ibmvnic_commands {
ACL_CHANGE_INDICATION = 0x1A,
ACL_QUERY = 0x1B,
ACL_QUERY_RSP = 0x9B,
- REQUEST_DEBUG_STATS = 0x1C,
- REQUEST_DEBUG_STATS_RSP = 0x9C,
QUERY_MAP = 0x1D,
QUERY_MAP_RSP = 0x9D,
REQUEST_MAP = 0x1E,
@@ -863,6 +851,7 @@ struct ibmvnic_sub_crq_queue {
spinlock_t lock;
struct sk_buff *rx_skb_top;
struct ibmvnic_adapter *adapter;
+ atomic_t used;
};
struct ibmvnic_long_term_buff {
@@ -924,13 +913,6 @@ struct ibmvnic_error_buff {
__be32 error_id;
};
-struct ibmvnic_fw_comp_internal {
- struct ibmvnic_adapter *adapter;
- int num;
- struct debugfs_blob_wrapper desc_blob;
- int paused;
-};
-
struct ibmvnic_inflight_cmd {
union ibmvnic_crq crq;
struct list_head list;
@@ -952,7 +934,6 @@ struct ibmvnic_adapter {
dma_addr_t bounce_buffer_dma;
/* Statistics */
- struct net_device_stats net_stats;
struct ibmvnic_statistics stats;
dma_addr_t stats_token;
struct completion stats_done;
@@ -995,18 +976,7 @@ struct ibmvnic_adapter {
struct list_head errors;
spinlock_t error_list_lock;
- /* debugfs */
- struct dentry *debugfs_dir;
- struct dentry *debugfs_dump;
struct completion fw_done;
- char *dump_data;
- dma_addr_t dump_data_token;
- int dump_data_size;
- int ras_comp_num;
- struct ibmvnic_fw_component *ras_comps;
- struct ibmvnic_fw_comp_internal *ras_comp_int;
- dma_addr_t ras_comps_tok;
- struct dentry *ras_comps_ent;
/* in-flight commands that allocate and/or map memory*/
struct list_head inflight;
@@ -1051,4 +1021,5 @@ struct ibmvnic_adapter {
struct work_struct ibmvnic_xport;
struct tasklet_struct tasklet;
bool failover;
+ bool is_closed;
};
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index 1349b45..1542a21 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -235,17 +235,6 @@
If unsure, say N.
-config I40E_FCOE
- bool "Fibre Channel over Ethernet (FCoE)"
- default n
- depends on I40E && DCB && FCOE
- ---help---
- Say Y here if you want to use Fibre Channel over Ethernet (FCoE)
- in the driver. This will create new netdev for exclusive FCoE
- use with XL710 FCoE offloads enabled.
-
- If unsure, say N.
-
config I40EVF
tristate "Intel(R) XL710 X710 Virtual Function Ethernet support"
depends on PCI_MSI
diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
index 975eeb8..ec8aa45 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
@@ -103,104 +103,104 @@ static const char e1000_gstrings_test[][ETH_GSTRING_LEN] = {
#define E1000_TEST_LEN ARRAY_SIZE(e1000_gstrings_test)
-static int e1000_get_settings(struct net_device *netdev,
- struct ethtool_cmd *ecmd)
+static int e1000_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *cmd)
{
struct e1000_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
+ u32 supported, advertising;
if (hw->media_type == e1000_media_type_copper) {
- ecmd->supported = (SUPPORTED_10baseT_Half |
- SUPPORTED_10baseT_Full |
- SUPPORTED_100baseT_Half |
- SUPPORTED_100baseT_Full |
- SUPPORTED_1000baseT_Full|
- SUPPORTED_Autoneg |
- SUPPORTED_TP);
- ecmd->advertising = ADVERTISED_TP;
+ supported = (SUPPORTED_10baseT_Half |
+ SUPPORTED_10baseT_Full |
+ SUPPORTED_100baseT_Half |
+ SUPPORTED_100baseT_Full |
+ SUPPORTED_1000baseT_Full|
+ SUPPORTED_Autoneg |
+ SUPPORTED_TP);
+ advertising = ADVERTISED_TP;
if (hw->autoneg == 1) {
- ecmd->advertising |= ADVERTISED_Autoneg;
+ advertising |= ADVERTISED_Autoneg;
/* the e1000 autoneg seems to match ethtool nicely */
- ecmd->advertising |= hw->autoneg_advertised;
+ advertising |= hw->autoneg_advertised;
}
- ecmd->port = PORT_TP;
- ecmd->phy_address = hw->phy_addr;
-
- if (hw->mac_type == e1000_82543)
- ecmd->transceiver = XCVR_EXTERNAL;
- else
- ecmd->transceiver = XCVR_INTERNAL;
-
+ cmd->base.port = PORT_TP;
+ cmd->base.phy_address = hw->phy_addr;
} else {
- ecmd->supported = (SUPPORTED_1000baseT_Full |
- SUPPORTED_FIBRE |
- SUPPORTED_Autoneg);
+ supported = (SUPPORTED_1000baseT_Full |
+ SUPPORTED_FIBRE |
+ SUPPORTED_Autoneg);
- ecmd->advertising = (ADVERTISED_1000baseT_Full |
- ADVERTISED_FIBRE |
- ADVERTISED_Autoneg);
+ advertising = (ADVERTISED_1000baseT_Full |
+ ADVERTISED_FIBRE |
+ ADVERTISED_Autoneg);
- ecmd->port = PORT_FIBRE;
-
- if (hw->mac_type >= e1000_82545)
- ecmd->transceiver = XCVR_INTERNAL;
- else
- ecmd->transceiver = XCVR_EXTERNAL;
+ cmd->base.port = PORT_FIBRE;
}
if (er32(STATUS) & E1000_STATUS_LU) {
e1000_get_speed_and_duplex(hw, &adapter->link_speed,
&adapter->link_duplex);
- ethtool_cmd_speed_set(ecmd, adapter->link_speed);
+ cmd->base.speed = adapter->link_speed;
/* unfortunately FULL_DUPLEX != DUPLEX_FULL
* and HALF_DUPLEX != DUPLEX_HALF
*/
if (adapter->link_duplex == FULL_DUPLEX)
- ecmd->duplex = DUPLEX_FULL;
+ cmd->base.duplex = DUPLEX_FULL;
else
- ecmd->duplex = DUPLEX_HALF;
+ cmd->base.duplex = DUPLEX_HALF;
} else {
- ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
- ecmd->duplex = DUPLEX_UNKNOWN;
+ cmd->base.speed = SPEED_UNKNOWN;
+ cmd->base.duplex = DUPLEX_UNKNOWN;
}
- ecmd->autoneg = ((hw->media_type == e1000_media_type_fiber) ||
+ cmd->base.autoneg = ((hw->media_type == e1000_media_type_fiber) ||
hw->autoneg) ? AUTONEG_ENABLE : AUTONEG_DISABLE;
/* MDI-X => 1; MDI => 0 */
if ((hw->media_type == e1000_media_type_copper) &&
netif_carrier_ok(netdev))
- ecmd->eth_tp_mdix = (!!adapter->phy_info.mdix_mode ?
+ cmd->base.eth_tp_mdix = (!!adapter->phy_info.mdix_mode ?
ETH_TP_MDI_X : ETH_TP_MDI);
else
- ecmd->eth_tp_mdix = ETH_TP_MDI_INVALID;
+ cmd->base.eth_tp_mdix = ETH_TP_MDI_INVALID;
if (hw->mdix == AUTO_ALL_MODES)
- ecmd->eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
+ cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
else
- ecmd->eth_tp_mdix_ctrl = hw->mdix;
+ cmd->base.eth_tp_mdix_ctrl = hw->mdix;
+
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ supported);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+ advertising);
+
return 0;
}
-static int e1000_set_settings(struct net_device *netdev,
- struct ethtool_cmd *ecmd)
+static int e1000_set_link_ksettings(struct net_device *netdev,
+ const struct ethtool_link_ksettings *cmd)
{
struct e1000_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
+ u32 advertising;
+
+ ethtool_convert_link_mode_to_legacy_u32(&advertising,
+ cmd->link_modes.advertising);
/* MDI setting is only allowed when autoneg enabled because
* some hardware doesn't allow MDI setting when speed or
* duplex is forced.
*/
- if (ecmd->eth_tp_mdix_ctrl) {
+ if (cmd->base.eth_tp_mdix_ctrl) {
if (hw->media_type != e1000_media_type_copper)
return -EOPNOTSUPP;
- if ((ecmd->eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
- (ecmd->autoneg != AUTONEG_ENABLE)) {
+ if ((cmd->base.eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
+ (cmd->base.autoneg != AUTONEG_ENABLE)) {
e_err(drv, "forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
return -EINVAL;
}
@@ -209,32 +209,31 @@ static int e1000_set_settings(struct net_device *netdev,
while (test_and_set_bit(__E1000_RESETTING, &adapter->flags))
msleep(1);
- if (ecmd->autoneg == AUTONEG_ENABLE) {
+ if (cmd->base.autoneg == AUTONEG_ENABLE) {
hw->autoneg = 1;
if (hw->media_type == e1000_media_type_fiber)
hw->autoneg_advertised = ADVERTISED_1000baseT_Full |
- ADVERTISED_FIBRE |
- ADVERTISED_Autoneg;
+ ADVERTISED_FIBRE |
+ ADVERTISED_Autoneg;
else
- hw->autoneg_advertised = ecmd->advertising |
+ hw->autoneg_advertised = advertising |
ADVERTISED_TP |
ADVERTISED_Autoneg;
- ecmd->advertising = hw->autoneg_advertised;
} else {
- u32 speed = ethtool_cmd_speed(ecmd);
+ u32 speed = cmd->base.speed;
/* calling this overrides forced MDI setting */
- if (e1000_set_spd_dplx(adapter, speed, ecmd->duplex)) {
+ if (e1000_set_spd_dplx(adapter, speed, cmd->base.duplex)) {
clear_bit(__E1000_RESETTING, &adapter->flags);
return -EINVAL;
}
}
/* MDI-X => 2; MDI => 1; Auto => 3 */
- if (ecmd->eth_tp_mdix_ctrl) {
- if (ecmd->eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
+ if (cmd->base.eth_tp_mdix_ctrl) {
+ if (cmd->base.eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
hw->mdix = AUTO_ALL_MODES;
else
- hw->mdix = ecmd->eth_tp_mdix_ctrl;
+ hw->mdix = cmd->base.eth_tp_mdix_ctrl;
}
/* reset the link */
@@ -1875,8 +1874,6 @@ static void e1000_get_strings(struct net_device *netdev, u32 stringset,
}
static const struct ethtool_ops e1000_ethtool_ops = {
- .get_settings = e1000_get_settings,
- .set_settings = e1000_set_settings,
.get_drvinfo = e1000_get_drvinfo,
.get_regs_len = e1000_get_regs_len,
.get_regs = e1000_get_regs,
@@ -1901,6 +1898,8 @@ static const struct ethtool_ops e1000_ethtool_ops = {
.get_coalesce = e1000_get_coalesce,
.set_coalesce = e1000_set_coalesce,
.get_ts_info = ethtool_op_get_ts_info,
+ .get_link_ksettings = e1000_get_link_ksettings,
+ .set_link_ksettings = e1000_set_link_ksettings,
};
void e1000_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c
index 7aff68a..e70b1eb 100644
--- a/drivers/net/ethernet/intel/e1000e/ethtool.c
+++ b/drivers/net/ethernet/intel/e1000e/ethtool.c
@@ -117,55 +117,52 @@ static const char e1000_gstrings_test[][ETH_GSTRING_LEN] = {
#define E1000_TEST_LEN ARRAY_SIZE(e1000_gstrings_test)
-static int e1000_get_settings(struct net_device *netdev,
- struct ethtool_cmd *ecmd)
+static int e1000_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *cmd)
{
struct e1000_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
- u32 speed;
+ u32 speed, supported, advertising;
if (hw->phy.media_type == e1000_media_type_copper) {
- ecmd->supported = (SUPPORTED_10baseT_Half |
- SUPPORTED_10baseT_Full |
- SUPPORTED_100baseT_Half |
- SUPPORTED_100baseT_Full |
- SUPPORTED_1000baseT_Full |
- SUPPORTED_Autoneg |
- SUPPORTED_TP);
+ supported = (SUPPORTED_10baseT_Half |
+ SUPPORTED_10baseT_Full |
+ SUPPORTED_100baseT_Half |
+ SUPPORTED_100baseT_Full |
+ SUPPORTED_1000baseT_Full |
+ SUPPORTED_Autoneg |
+ SUPPORTED_TP);
if (hw->phy.type == e1000_phy_ife)
- ecmd->supported &= ~SUPPORTED_1000baseT_Full;
- ecmd->advertising = ADVERTISED_TP;
+ supported &= ~SUPPORTED_1000baseT_Full;
+ advertising = ADVERTISED_TP;
if (hw->mac.autoneg == 1) {
- ecmd->advertising |= ADVERTISED_Autoneg;
+ advertising |= ADVERTISED_Autoneg;
/* the e1000 autoneg seems to match ethtool nicely */
- ecmd->advertising |= hw->phy.autoneg_advertised;
+ advertising |= hw->phy.autoneg_advertised;
}
- ecmd->port = PORT_TP;
- ecmd->phy_address = hw->phy.addr;
- ecmd->transceiver = XCVR_INTERNAL;
-
+ cmd->base.port = PORT_TP;
+ cmd->base.phy_address = hw->phy.addr;
} else {
- ecmd->supported = (SUPPORTED_1000baseT_Full |
- SUPPORTED_FIBRE |
- SUPPORTED_Autoneg);
+ supported = (SUPPORTED_1000baseT_Full |
+ SUPPORTED_FIBRE |
+ SUPPORTED_Autoneg);
- ecmd->advertising = (ADVERTISED_1000baseT_Full |
- ADVERTISED_FIBRE |
- ADVERTISED_Autoneg);
+ advertising = (ADVERTISED_1000baseT_Full |
+ ADVERTISED_FIBRE |
+ ADVERTISED_Autoneg);
- ecmd->port = PORT_FIBRE;
- ecmd->transceiver = XCVR_EXTERNAL;
+ cmd->base.port = PORT_FIBRE;
}
speed = SPEED_UNKNOWN;
- ecmd->duplex = DUPLEX_UNKNOWN;
+ cmd->base.duplex = DUPLEX_UNKNOWN;
if (netif_running(netdev)) {
if (netif_carrier_ok(netdev)) {
speed = adapter->link_speed;
- ecmd->duplex = adapter->link_duplex - 1;
+ cmd->base.duplex = adapter->link_duplex - 1;
}
} else if (!pm_runtime_suspended(netdev->dev.parent)) {
u32 status = er32(STATUS);
@@ -179,30 +176,36 @@ static int e1000_get_settings(struct net_device *netdev,
speed = SPEED_10;
if (status & E1000_STATUS_FD)
- ecmd->duplex = DUPLEX_FULL;
+ cmd->base.duplex = DUPLEX_FULL;
else
- ecmd->duplex = DUPLEX_HALF;
+ cmd->base.duplex = DUPLEX_HALF;
}
}
- ethtool_cmd_speed_set(ecmd, speed);
- ecmd->autoneg = ((hw->phy.media_type == e1000_media_type_fiber) ||
+ cmd->base.speed = speed;
+ cmd->base.autoneg = ((hw->phy.media_type == e1000_media_type_fiber) ||
hw->mac.autoneg) ? AUTONEG_ENABLE : AUTONEG_DISABLE;
/* MDI-X => 2; MDI =>1; Invalid =>0 */
if ((hw->phy.media_type == e1000_media_type_copper) &&
netif_carrier_ok(netdev))
- ecmd->eth_tp_mdix = hw->phy.is_mdix ? ETH_TP_MDI_X : ETH_TP_MDI;
+ cmd->base.eth_tp_mdix = hw->phy.is_mdix ?
+ ETH_TP_MDI_X : ETH_TP_MDI;
else
- ecmd->eth_tp_mdix = ETH_TP_MDI_INVALID;
+ cmd->base.eth_tp_mdix = ETH_TP_MDI_INVALID;
if (hw->phy.mdix == AUTO_ALL_MODES)
- ecmd->eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
+ cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
else
- ecmd->eth_tp_mdix_ctrl = hw->phy.mdix;
+ cmd->base.eth_tp_mdix_ctrl = hw->phy.mdix;
if (hw->phy.media_type != e1000_media_type_copper)
- ecmd->eth_tp_mdix_ctrl = ETH_TP_MDI_INVALID;
+ cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_INVALID;
+
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ supported);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+ advertising);
return 0;
}
@@ -262,12 +265,16 @@ static int e1000_set_spd_dplx(struct e1000_adapter *adapter, u32 spd, u8 dplx)
return -EINVAL;
}
-static int e1000_set_settings(struct net_device *netdev,
- struct ethtool_cmd *ecmd)
+static int e1000_set_link_ksettings(struct net_device *netdev,
+ const struct ethtool_link_ksettings *cmd)
{
struct e1000_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
int ret_val = 0;
+ u32 advertising;
+
+ ethtool_convert_link_mode_to_legacy_u32(&advertising,
+ cmd->link_modes.advertising);
pm_runtime_get_sync(netdev->dev.parent);
@@ -285,14 +292,14 @@ static int e1000_set_settings(struct net_device *netdev,
* some hardware doesn't allow MDI setting when speed or
* duplex is forced.
*/
- if (ecmd->eth_tp_mdix_ctrl) {
+ if (cmd->base.eth_tp_mdix_ctrl) {
if (hw->phy.media_type != e1000_media_type_copper) {
ret_val = -EOPNOTSUPP;
goto out;
}
- if ((ecmd->eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
- (ecmd->autoneg != AUTONEG_ENABLE)) {
+ if ((cmd->base.eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
+ (cmd->base.autoneg != AUTONEG_ENABLE)) {
e_err("forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
ret_val = -EINVAL;
goto out;
@@ -302,35 +309,35 @@ static int e1000_set_settings(struct net_device *netdev,
while (test_and_set_bit(__E1000_RESETTING, &adapter->state))
usleep_range(1000, 2000);
- if (ecmd->autoneg == AUTONEG_ENABLE) {
+ if (cmd->base.autoneg == AUTONEG_ENABLE) {
hw->mac.autoneg = 1;
if (hw->phy.media_type == e1000_media_type_fiber)
hw->phy.autoneg_advertised = ADVERTISED_1000baseT_Full |
ADVERTISED_FIBRE | ADVERTISED_Autoneg;
else
- hw->phy.autoneg_advertised = ecmd->advertising |
+ hw->phy.autoneg_advertised = advertising |
ADVERTISED_TP | ADVERTISED_Autoneg;
- ecmd->advertising = hw->phy.autoneg_advertised;
+ advertising = hw->phy.autoneg_advertised;
if (adapter->fc_autoneg)
hw->fc.requested_mode = e1000_fc_default;
} else {
- u32 speed = ethtool_cmd_speed(ecmd);
+ u32 speed = cmd->base.speed;
/* calling this overrides forced MDI setting */
- if (e1000_set_spd_dplx(adapter, speed, ecmd->duplex)) {
+ if (e1000_set_spd_dplx(adapter, speed, cmd->base.duplex)) {
ret_val = -EINVAL;
goto out;
}
}
/* MDI-X => 2; MDI => 1; Auto => 3 */
- if (ecmd->eth_tp_mdix_ctrl) {
+ if (cmd->base.eth_tp_mdix_ctrl) {
/* fix up the value for auto (3 => 0) as zero is mapped
* internally to auto
*/
- if (ecmd->eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
+ if (cmd->base.eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
hw->phy.mdix = AUTO_ALL_MODES;
else
- hw->phy.mdix = ecmd->eth_tp_mdix_ctrl;
+ hw->phy.mdix = cmd->base.eth_tp_mdix_ctrl;
}
/* reset the link */
@@ -2313,8 +2320,6 @@ static int e1000e_get_ts_info(struct net_device *netdev,
}
static const struct ethtool_ops e1000_ethtool_ops = {
- .get_settings = e1000_get_settings,
- .set_settings = e1000_set_settings,
.get_drvinfo = e1000_get_drvinfo,
.get_regs_len = e1000_get_regs_len,
.get_regs = e1000_get_regs,
@@ -2342,6 +2347,8 @@ static const struct ethtool_ops e1000_ethtool_ops = {
.get_ts_info = e1000e_get_ts_info,
.get_eee = e1000e_get_eee,
.set_eee = e1000e_set_eee,
+ .get_link_ksettings = e1000_get_link_ksettings,
+ .set_link_ksettings = e1000_set_link_ksettings,
};
void e1000e_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 2175cce..e9af89a 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -6274,8 +6274,8 @@ static int e1000e_pm_freeze(struct device *dev)
/* Quiesce the device without resetting the hardware */
e1000e_down(adapter, false);
e1000_free_irq(adapter);
- e1000e_reset_interrupt_capability(adapter);
}
+ e1000e_reset_interrupt_capability(adapter);
/* Allow time for pending master requests to run */
e1000e_disable_pcie_master(&adapter->hw);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h
index 52b9794..689c413 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k.h
@@ -1,5 +1,5 @@
/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
@@ -65,14 +65,16 @@ enum fm10k_ring_state_t {
__FM10K_TX_DETECT_HANG,
__FM10K_HANG_CHECK_ARMED,
__FM10K_TX_XPS_INIT_DONE,
+ /* This must be last and is used to calculate BITMAP size */
+ __FM10K_TX_STATE_SIZE__,
};
#define check_for_tx_hang(ring) \
- test_bit(__FM10K_TX_DETECT_HANG, &(ring)->state)
+ test_bit(__FM10K_TX_DETECT_HANG, (ring)->state)
#define set_check_for_tx_hang(ring) \
- set_bit(__FM10K_TX_DETECT_HANG, &(ring)->state)
+ set_bit(__FM10K_TX_DETECT_HANG, (ring)->state)
#define clear_check_for_tx_hang(ring) \
- clear_bit(__FM10K_TX_DETECT_HANG, &(ring)->state)
+ clear_bit(__FM10K_TX_DETECT_HANG, (ring)->state)
struct fm10k_tx_buffer {
struct fm10k_tx_desc *next_to_watch;
@@ -126,7 +128,7 @@ struct fm10k_ring {
struct fm10k_rx_buffer *rx_buffer;
};
u32 __iomem *tail;
- unsigned long state;
+ DECLARE_BITMAP(state, __FM10K_TX_STATE_SIZE__);
dma_addr_t dma; /* phys. address of descriptor ring */
unsigned int size; /* length in bytes */
@@ -249,18 +251,46 @@ struct fm10k_udp_port {
/* one work queue for entire driver */
extern struct workqueue_struct *fm10k_workqueue;
+/* The following enumeration contains flags which indicate or enable modified
+ * driver behaviors. To avoid race conditions, the flags are stored in
+ * a BITMAP in the fm10k_intfc structure. The BITMAP should be accessed using
+ * atomic *_bit() operations.
+ */
+enum fm10k_flags_t {
+ FM10K_FLAG_RESET_REQUESTED,
+ FM10K_FLAG_RSS_FIELD_IPV4_UDP,
+ FM10K_FLAG_RSS_FIELD_IPV6_UDP,
+ FM10K_FLAG_SWPRI_CONFIG,
+ /* __FM10K_FLAGS_SIZE__ is used to calculate the size of
+ * interface->flags and must be the last value in this
+ * enumeration.
+ */
+ __FM10K_FLAGS_SIZE__
+};
+
+enum fm10k_state_t {
+ __FM10K_RESETTING,
+ __FM10K_DOWN,
+ __FM10K_SERVICE_SCHED,
+ __FM10K_SERVICE_REQUEST,
+ __FM10K_SERVICE_DISABLE,
+ __FM10K_MBX_LOCK,
+ __FM10K_LINK_DOWN,
+ __FM10K_UPDATING_STATS,
+ /* This value must be last and determines the BITMAP size */
+ __FM10K_STATE_SIZE__,
+};
+
struct fm10k_intfc {
unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
struct net_device *netdev;
struct fm10k_l2_accel *l2_accel; /* pointer to L2 acceleration list */
struct pci_dev *pdev;
- unsigned long state;
+ DECLARE_BITMAP(state, __FM10K_STATE_SIZE__);
- u32 flags;
-#define FM10K_FLAG_RESET_REQUESTED (u32)(BIT(0))
-#define FM10K_FLAG_RSS_FIELD_IPV4_UDP (u32)(BIT(1))
-#define FM10K_FLAG_RSS_FIELD_IPV6_UDP (u32)(BIT(2))
-#define FM10K_FLAG_SWPRI_CONFIG (u32)(BIT(3))
+ /* Access flag values using atomic *_bit() operations */
+ DECLARE_BITMAP(flags, __FM10K_FLAGS_SIZE__);
+
int xcast_mode;
/* Tx fast path data */
@@ -352,22 +382,12 @@ struct fm10k_intfc {
u16 vid;
};
-enum fm10k_state_t {
- __FM10K_RESETTING,
- __FM10K_DOWN,
- __FM10K_SERVICE_SCHED,
- __FM10K_SERVICE_DISABLE,
- __FM10K_MBX_LOCK,
- __FM10K_LINK_DOWN,
- __FM10K_UPDATING_STATS,
-};
-
static inline void fm10k_mbx_lock(struct fm10k_intfc *interface)
{
/* busy loop if we cannot obtain the lock as some calls
* such as ndo_set_rx_mode may be made in atomic context
*/
- while (test_and_set_bit(__FM10K_MBX_LOCK, &interface->state))
+ while (test_and_set_bit(__FM10K_MBX_LOCK, interface->state))
udelay(20);
}
@@ -375,12 +395,12 @@ static inline void fm10k_mbx_unlock(struct fm10k_intfc *interface)
{
/* flush memory to make sure state is correct */
smp_mb__before_atomic();
- clear_bit(__FM10K_MBX_LOCK, &interface->state);
+ clear_bit(__FM10K_MBX_LOCK, interface->state);
}
static inline int fm10k_mbx_trylock(struct fm10k_intfc *interface)
{
- return !test_and_set_bit(__FM10K_MBX_LOCK, &interface->state);
+ return !test_and_set_bit(__FM10K_MBX_LOCK, interface->state);
}
/* fm10k_test_staterr - test bits in Rx descriptor status and error fields */
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
index 0c84fef..c7234f3 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
@@ -1,5 +1,5 @@
/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
@@ -562,7 +562,7 @@ static int fm10k_set_ringparam(struct net_device *netdev,
return 0;
}
- while (test_and_set_bit(__FM10K_RESETTING, &interface->state))
+ while (test_and_set_bit(__FM10K_RESETTING, interface->state))
usleep_range(1000, 2000);
if (!netif_running(interface->netdev)) {
@@ -648,7 +648,7 @@ static int fm10k_set_ringparam(struct net_device *netdev,
fm10k_up(interface);
vfree(temp_ring);
clear_reset:
- clear_bit(__FM10K_RESETTING, &interface->state);
+ clear_bit(__FM10K_RESETTING, interface->state);
return err;
}
@@ -716,7 +716,8 @@ static int fm10k_get_rss_hash_opts(struct fm10k_intfc *interface,
cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
/* fall through */
case UDP_V4_FLOW:
- if (interface->flags & FM10K_FLAG_RSS_FIELD_IPV4_UDP)
+ if (test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP,
+ interface->flags))
cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
/* fall through */
case SCTP_V4_FLOW:
@@ -732,7 +733,8 @@ static int fm10k_get_rss_hash_opts(struct fm10k_intfc *interface,
cmd->data |= RXH_IP_SRC | RXH_IP_DST;
break;
case UDP_V6_FLOW:
- if (interface->flags & FM10K_FLAG_RSS_FIELD_IPV6_UDP)
+ if (test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP,
+ interface->flags))
cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
cmd->data |= RXH_IP_SRC | RXH_IP_DST;
break;
@@ -764,12 +766,13 @@ static int fm10k_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
return ret;
}
-#define UDP_RSS_FLAGS (FM10K_FLAG_RSS_FIELD_IPV4_UDP | \
- FM10K_FLAG_RSS_FIELD_IPV6_UDP)
static int fm10k_set_rss_hash_opt(struct fm10k_intfc *interface,
struct ethtool_rxnfc *nfc)
{
- u32 flags = interface->flags;
+ int rss_ipv4_udp = test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP,
+ interface->flags);
+ int rss_ipv6_udp = test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP,
+ interface->flags);
/* RSS does not support anything other than hashing
* to queues on src and dst IPs and ports
@@ -793,10 +796,12 @@ static int fm10k_set_rss_hash_opt(struct fm10k_intfc *interface,
return -EINVAL;
switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
case 0:
- flags &= ~FM10K_FLAG_RSS_FIELD_IPV4_UDP;
+ clear_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP,
+ interface->flags);
break;
case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
- flags |= FM10K_FLAG_RSS_FIELD_IPV4_UDP;
+ set_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP,
+ interface->flags);
break;
default:
return -EINVAL;
@@ -808,10 +813,12 @@ static int fm10k_set_rss_hash_opt(struct fm10k_intfc *interface,
return -EINVAL;
switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
case 0:
- flags &= ~FM10K_FLAG_RSS_FIELD_IPV6_UDP;
+ clear_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP,
+ interface->flags);
break;
case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
- flags |= FM10K_FLAG_RSS_FIELD_IPV6_UDP;
+ set_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP,
+ interface->flags);
break;
default:
return -EINVAL;
@@ -835,28 +842,41 @@ static int fm10k_set_rss_hash_opt(struct fm10k_intfc *interface,
return -EINVAL;
}
- /* if we changed something we need to update flags */
- if (flags != interface->flags) {
+ /* If something changed we need to update the MRQC register. Note that
+ * test_bit() is guaranteed to return strictly 0 or 1, so testing for
+ * equality is safe.
+ */
+ if ((rss_ipv4_udp != test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP,
+ interface->flags)) ||
+ (rss_ipv6_udp != test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP,
+ interface->flags))) {
struct fm10k_hw *hw = &interface->hw;
+ bool warn = false;
u32 mrqc;
- if ((flags & UDP_RSS_FLAGS) &&
- !(interface->flags & UDP_RSS_FLAGS))
- netif_warn(interface, drv, interface->netdev,
- "enabling UDP RSS: fragmented packets may arrive out of order to the stack above\n");
-
- interface->flags = flags;
-
/* Perform hash on these packet types */
mrqc = FM10K_MRQC_IPV4 |
FM10K_MRQC_TCP_IPV4 |
FM10K_MRQC_IPV6 |
FM10K_MRQC_TCP_IPV6;
- if (flags & FM10K_FLAG_RSS_FIELD_IPV4_UDP)
+ if (test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP,
+ interface->flags)) {
mrqc |= FM10K_MRQC_UDP_IPV4;
- if (flags & FM10K_FLAG_RSS_FIELD_IPV6_UDP)
+ warn = true;
+ }
+ if (test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP,
+ interface->flags)) {
mrqc |= FM10K_MRQC_UDP_IPV6;
+ warn = true;
+ }
+
+ /* If we enable UDP RSS display a warning that this may cause
+ * fragmented UDP packets to arrive out of order.
+ */
+ if (warn)
+ netif_warn(interface, drv, interface->netdev,
+ "enabling UDP RSS: fragmented packets may arrive out of order to the stack above\n");
fm10k_write_reg(hw, FM10K_MRQC(0), mrqc);
}
@@ -939,7 +959,7 @@ static void fm10k_self_test(struct net_device *dev,
memset(data, 0, sizeof(*data) * FM10K_TEST_LEN);
- if (FM10K_REMOVED(hw)) {
+ if (FM10K_REMOVED(hw->hw_addr)) {
netif_err(interface, drv, dev,
"Interface removed - test blocked\n");
eth_test->flags |= ETH_TEST_FL_FAILED;
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 5bb233a..9dffaba 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -1,5 +1,5 @@
/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
@@ -34,7 +34,7 @@ const char fm10k_driver_version[] = DRV_VERSION;
char fm10k_driver_name[] = "fm10k";
static const char fm10k_driver_string[] = DRV_SUMMARY;
static const char fm10k_copyright[] =
- "Copyright (c) 2013 - 2016 Intel Corporation.";
+ "Copyright(c) 2013 - 2017 Intel Corporation.";
MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
MODULE_DESCRIPTION(DRV_SUMMARY);
@@ -1175,13 +1175,13 @@ bool fm10k_check_tx_hang(struct fm10k_ring *tx_ring)
/* update completed stats and continue */
tx_ring->tx_stats.tx_done_old = tx_done;
/* reset the countdown */
- clear_bit(__FM10K_HANG_CHECK_ARMED, &tx_ring->state);
+ clear_bit(__FM10K_HANG_CHECK_ARMED, tx_ring->state);
return false;
}
/* make sure it is true for two checks in a row */
- return test_and_set_bit(__FM10K_HANG_CHECK_ARMED, &tx_ring->state);
+ return test_and_set_bit(__FM10K_HANG_CHECK_ARMED, tx_ring->state);
}
/**
@@ -1191,9 +1191,9 @@ bool fm10k_check_tx_hang(struct fm10k_ring *tx_ring)
void fm10k_tx_timeout_reset(struct fm10k_intfc *interface)
{
/* Do the reset outside of interrupt context */
- if (!test_bit(__FM10K_DOWN, &interface->state)) {
+ if (!test_bit(__FM10K_DOWN, interface->state)) {
interface->tx_timeout_count++;
- interface->flags |= FM10K_FLAG_RESET_REQUESTED;
+ set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
fm10k_service_event_schedule(interface);
}
}
@@ -1214,7 +1214,7 @@ static bool fm10k_clean_tx_irq(struct fm10k_q_vector *q_vector,
unsigned int budget = q_vector->tx.work_limit;
unsigned int i = tx_ring->next_to_clean;
- if (test_bit(__FM10K_DOWN, &interface->state))
+ if (test_bit(__FM10K_DOWN, interface->state))
return true;
tx_buffer = &tx_ring->tx_buffer[i];
@@ -1344,7 +1344,7 @@ static bool fm10k_clean_tx_irq(struct fm10k_q_vector *q_vector,
smp_mb();
if (__netif_subqueue_stopped(tx_ring->netdev,
tx_ring->queue_index) &&
- !test_bit(__FM10K_DOWN, &interface->state)) {
+ !test_bit(__FM10K_DOWN, interface->state)) {
netif_wake_subqueue(tx_ring->netdev,
tx_ring->queue_index);
++tx_ring->tx_stats.restart_queue;
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
index 01db688..24f2f6f 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
@@ -1,5 +1,5 @@
/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
@@ -737,6 +737,23 @@ static void fm10k_tx_timeout(struct net_device *netdev)
}
}
+/**
+ * fm10k_host_mbx_ready - Check PF interface's mailbox readiness
+ * @interface: board private structure
+ *
+ * This function checks if the PF interface's mailbox is ready before queueing
+ * mailbox messages for transmission. This will prevent filling the TX mailbox
+ * queue when the receiver is not ready. VF interfaces are exempt from this
+ * check since it will block all PF-VF mailbox messages from being sent from
+ * the VF to the PF at initialization.
+ **/
+static bool fm10k_host_mbx_ready(struct fm10k_intfc *interface)
+{
+ struct fm10k_hw *hw = &interface->hw;
+
+ return (hw->mac.type == fm10k_mac_vf || interface->host_ready);
+}
+
static int fm10k_uc_vlan_unsync(struct net_device *netdev,
const unsigned char *uc_addr)
{
@@ -745,12 +762,15 @@ static int fm10k_uc_vlan_unsync(struct net_device *netdev,
u16 glort = interface->glort;
u16 vid = interface->vid;
bool set = !!(vid / VLAN_N_VID);
- int err;
+ int err = -EHOSTDOWN;
/* drop any leading bits on the VLAN ID */
vid &= VLAN_N_VID - 1;
- err = hw->mac.ops.update_uc_addr(hw, glort, uc_addr, vid, set, 0);
+ if (fm10k_host_mbx_ready(interface))
+ err = hw->mac.ops.update_uc_addr(hw, glort, uc_addr,
+ vid, set, 0);
+
if (err)
return err;
@@ -766,12 +786,14 @@ static int fm10k_mc_vlan_unsync(struct net_device *netdev,
u16 glort = interface->glort;
u16 vid = interface->vid;
bool set = !!(vid / VLAN_N_VID);
- int err;
+ int err = -EHOSTDOWN;
/* drop any leading bits on the VLAN ID */
vid &= VLAN_N_VID - 1;
- err = hw->mac.ops.update_mc_addr(hw, glort, mc_addr, vid, set);
+ if (fm10k_host_mbx_ready(interface))
+ err = hw->mac.ops.update_mc_addr(hw, glort, mc_addr, vid, set);
+
if (err)
return err;
@@ -822,7 +844,7 @@ static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set)
/* Do not throw an error if the interface is down. We will sync once
* we come up
*/
- if (test_bit(__FM10K_DOWN, &interface->state))
+ if (test_bit(__FM10K_DOWN, interface->state))
return 0;
fm10k_mbx_lock(interface);
@@ -834,9 +856,13 @@ static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set)
goto err_out;
}
- /* update our base MAC address */
- err = hw->mac.ops.update_uc_addr(hw, interface->glort, hw->mac.addr,
- vid, set, 0);
+ /* update our base MAC address if host's mailbox is ready */
+ if (fm10k_host_mbx_ready(interface))
+ err = hw->mac.ops.update_uc_addr(hw, interface->glort,
+ hw->mac.addr, vid, set, 0);
+ else
+ err = -EHOSTDOWN;
+
if (err)
goto err_out;
@@ -907,12 +933,15 @@ static int __fm10k_uc_sync(struct net_device *dev,
if (!is_valid_ether_addr(addr))
return -EADDRNOTAVAIL;
- /* update table with current entries */
+ /* update table with current entries if host's mailbox is ready */
+ if (!fm10k_host_mbx_ready(interface))
+ return -EHOSTDOWN;
+
for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1;
vid < VLAN_N_VID;
vid = fm10k_find_next_vlan(interface, vid)) {
err = hw->mac.ops.update_uc_addr(hw, glort, addr,
- vid, sync, 0);
+ vid, sync, 0);
if (err)
return err;
}
@@ -970,7 +999,10 @@ static int __fm10k_mc_sync(struct net_device *dev,
struct fm10k_hw *hw = &interface->hw;
u16 vid, glort = interface->glort;
- /* update table with current entries */
+ /* update table with current entries if host's mailbox is ready */
+ if (!fm10k_host_mbx_ready(interface))
+ return 0;
+
for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1;
vid < VLAN_N_VID;
vid = fm10k_find_next_vlan(interface, vid)) {
@@ -1018,8 +1050,10 @@ static void fm10k_set_rx_mode(struct net_device *dev)
if (interface->xcast_mode == FM10K_XCAST_MODE_PROMISC)
fm10k_clear_unused_vlans(interface);
- /* update xcast mode */
- hw->mac.ops.update_xcast_mode(hw, interface->glort, xcast_mode);
+ /* update xcast mode if host's mailbox is ready */
+ if (fm10k_host_mbx_ready(interface))
+ hw->mac.ops.update_xcast_mode(hw, interface->glort,
+ xcast_mode);
/* record updated xcast mode state */
interface->xcast_mode = xcast_mode;
@@ -1054,8 +1088,10 @@ void fm10k_restore_rx_state(struct fm10k_intfc *interface)
fm10k_mbx_lock(interface);
- /* Enable logical port */
- hw->mac.ops.update_lport_state(hw, glort, interface->glort_count, true);
+ /* Enable logical port if host's mailbox is ready */
+ if (fm10k_host_mbx_ready(interface))
+ hw->mac.ops.update_lport_state(hw, glort,
+ interface->glort_count, true);
/* update VLAN table */
hw->mac.ops.update_vlan(hw, FM10K_VLAN_ALL, 0,
@@ -1069,12 +1105,18 @@ void fm10k_restore_rx_state(struct fm10k_intfc *interface)
vid < VLAN_N_VID;
vid = fm10k_find_next_vlan(interface, vid)) {
hw->mac.ops.update_vlan(hw, vid, 0, true);
- hw->mac.ops.update_uc_addr(hw, glort, hw->mac.addr,
- vid, true, 0);
+
+ /* Update unicast entries if host's mailbox is ready */
+ if (fm10k_host_mbx_ready(interface))
+ hw->mac.ops.update_uc_addr(hw, glort, hw->mac.addr,
+ vid, true, 0);
}
- /* update xcast mode before synchronizing addresses */
- hw->mac.ops.update_xcast_mode(hw, glort, xcast_mode);
+ /* update xcast mode before synchronizing addresses if host's mailbox
+ * is ready
+ */
+ if (fm10k_host_mbx_ready(interface))
+ hw->mac.ops.update_xcast_mode(hw, glort, xcast_mode);
/* synchronize all of the addresses */
__dev_uc_sync(netdev, fm10k_uc_sync, fm10k_uc_unsync);
@@ -1096,9 +1138,12 @@ void fm10k_reset_rx_state(struct fm10k_intfc *interface)
fm10k_mbx_lock(interface);
- /* clear the logical port state on lower device */
- hw->mac.ops.update_lport_state(hw, interface->glort,
- interface->glort_count, false);
+ /* clear the logical port state on lower device if host's mailbox is
+ * ready
+ */
+ if (fm10k_host_mbx_ready(interface))
+ hw->mac.ops.update_lport_state(hw, interface->glort,
+ interface->glort_count, false);
fm10k_mbx_unlock(interface);
@@ -1115,8 +1160,8 @@ void fm10k_reset_rx_state(struct fm10k_intfc *interface)
* @netdev: network interface device structure
* @stats: storage space for 64bit statistics
*
- * Returns 64bit statistics, for use in the ndo_get_stats64 callback. This
- * function replaces fm10k_get_stats for kernels which support it.
+ * Obtain 64bit statistics in a way that is safe for both 32bit and 64bit
+ * architectures.
*/
static void fm10k_get_stats64(struct net_device *netdev,
struct rtnl_link_stats64 *stats)
@@ -1207,7 +1252,7 @@ int fm10k_setup_tc(struct net_device *dev, u8 tc)
goto err_open;
/* flag to indicate SWPRI has yet to be updated */
- interface->flags |= FM10K_FLAG_SWPRI_CONFIG;
+ set_bit(FM10K_FLAG_SWPRI_CONFIG, interface->flags);
return 0;
err_open:
@@ -1226,7 +1271,9 @@ static int __fm10k_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
if (tc->type != TC_SETUP_MQPRIO)
return -EINVAL;
- return fm10k_setup_tc(dev, tc->tc);
+ tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+ return fm10k_setup_tc(dev, tc->mqprio->num_tc);
}
static void fm10k_assign_l2_accel(struct fm10k_intfc *interface,
@@ -1317,8 +1364,13 @@ static void *fm10k_dfwd_add_station(struct net_device *dev,
fm10k_mbx_lock(interface);
glort = l2_accel->dglort + 1 + i;
- hw->mac.ops.update_xcast_mode(hw, glort, FM10K_XCAST_MODE_MULTI);
- hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr, 0, true, 0);
+
+ if (fm10k_host_mbx_ready(interface)) {
+ hw->mac.ops.update_xcast_mode(hw, glort,
+ FM10K_XCAST_MODE_MULTI);
+ hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr,
+ 0, true, 0);
+ }
fm10k_mbx_unlock(interface);
@@ -1352,8 +1404,13 @@ static void fm10k_dfwd_del_station(struct net_device *dev, void *priv)
fm10k_mbx_lock(interface);
glort = l2_accel->dglort + 1 + i;
- hw->mac.ops.update_xcast_mode(hw, glort, FM10K_XCAST_MODE_NONE);
- hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr, 0, false, 0);
+
+ if (fm10k_host_mbx_ready(interface)) {
+ hw->mac.ops.update_xcast_mode(hw, glort,
+ FM10K_XCAST_MODE_NONE);
+ hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr,
+ 0, false, 0);
+ }
fm10k_mbx_unlock(interface);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
index e372a58..3e26d27 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
@@ -1,5 +1,5 @@
/* Intel(R) Ethernet Switch Host Interface Driver
- * Copyright(c) 2013 - 2016 Intel Corporation.
+ * Copyright(c) 2013 - 2017 Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
@@ -19,6 +19,7 @@
*/
#include <linux/module.h>
+#include <linux/interrupt.h>
#include <linux/aer.h>
#include "fm10k.h"
@@ -92,18 +93,29 @@ static int fm10k_hw_ready(struct fm10k_intfc *interface)
void fm10k_service_event_schedule(struct fm10k_intfc *interface)
{
- if (!test_bit(__FM10K_SERVICE_DISABLE, &interface->state) &&
- !test_and_set_bit(__FM10K_SERVICE_SCHED, &interface->state))
+ if (!test_bit(__FM10K_SERVICE_DISABLE, interface->state) &&
+ !test_and_set_bit(__FM10K_SERVICE_SCHED, interface->state)) {
+ clear_bit(__FM10K_SERVICE_REQUEST, interface->state);
queue_work(fm10k_workqueue, &interface->service_task);
+ } else {
+ set_bit(__FM10K_SERVICE_REQUEST, interface->state);
+ }
}
static void fm10k_service_event_complete(struct fm10k_intfc *interface)
{
- WARN_ON(!test_bit(__FM10K_SERVICE_SCHED, &interface->state));
+ WARN_ON(!test_bit(__FM10K_SERVICE_SCHED, interface->state));
/* flush memory to make sure state is correct before next watchog */
smp_mb__before_atomic();
- clear_bit(__FM10K_SERVICE_SCHED, &interface->state);
+ clear_bit(__FM10K_SERVICE_SCHED, interface->state);
+
+ /* If a service event was requested since we started, immediately
+ * re-schedule now. This ensures we don't drop a request until the
+ * next timer event.
+ */
+ if (test_bit(__FM10K_SERVICE_REQUEST, interface->state))
+ fm10k_service_event_schedule(interface);
}
/**
@@ -136,7 +148,7 @@ static void fm10k_detach_subtask(struct fm10k_intfc *interface)
if (~value) {
interface->hw.hw_addr = interface->uc_addr;
netif_device_attach(netdev);
- interface->flags |= FM10K_FLAG_RESET_REQUESTED;
+ set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
netdev_warn(netdev, "PCIe link restored, device now attached\n");
return;
}
@@ -158,7 +170,7 @@ static void fm10k_prepare_for_reset(struct fm10k_intfc *interface)
/* put off any impending NetWatchDogTimeout */
netif_trans_update(netdev);
- while (test_and_set_bit(__FM10K_RESETTING, &interface->state))
+ while (test_and_set_bit(__FM10K_RESETTING, interface->state))
usleep_range(1000, 2000);
rtnl_lock();
@@ -241,7 +253,7 @@ static int fm10k_handle_reset(struct fm10k_intfc *interface)
rtnl_unlock();
- clear_bit(__FM10K_RESETTING, &interface->state);
+ clear_bit(__FM10K_RESETTING, interface->state);
return err;
err_open:
@@ -253,7 +265,7 @@ static int fm10k_handle_reset(struct fm10k_intfc *interface)
rtnl_unlock();
- clear_bit(__FM10K_RESETTING, &interface->state);
+ clear_bit(__FM10K_RESETTING, interface->state);
return err;
}
@@ -272,11 +284,10 @@ static void fm10k_reinit(struct fm10k_intfc *interface)
static void fm10k_reset_subtask(struct fm10k_intfc *interface)
{
- if (!(interface->flags & FM10K_FLAG_RESET_REQUESTED))
+ if (!test_and_clear_bit(FM10K_FLAG_RESET_REQUESTED,
+ interface->flags))
return;
- interface->flags &= ~FM10K_FLAG_RESET_REQUESTED;
-
netdev_err(interface->netdev, "Reset interface\n");
fm10k_reinit(interface);
@@ -295,7 +306,7 @@ static void fm10k_configure_swpri_map(struct fm10k_intfc *interface)
int i;
/* clear flag indicating update is needed */
- interface->flags &= ~FM10K_FLAG_SWPRI_CONFIG;
+ clear_bit(FM10K_FLAG_SWPRI_CONFIG, interface->flags);
/* these registers are only available on the PF */
if (hw->mac.type != fm10k_mac_pf)
@@ -316,14 +327,14 @@ static void fm10k_watchdog_update_host_state(struct fm10k_intfc *interface)
struct fm10k_hw *hw = &interface->hw;
s32 err;
- if (test_bit(__FM10K_LINK_DOWN, &interface->state)) {
+ if (test_bit(__FM10K_LINK_DOWN, interface->state)) {
interface->host_ready = false;
if (time_is_after_jiffies(interface->link_down_event))
return;
- clear_bit(__FM10K_LINK_DOWN, &interface->state);
+ clear_bit(__FM10K_LINK_DOWN, interface->state);
}
- if (interface->flags & FM10K_FLAG_SWPRI_CONFIG) {
+ if (test_bit(FM10K_FLAG_SWPRI_CONFIG, interface->flags)) {
if (rtnl_trylock()) {
fm10k_configure_swpri_map(interface);
rtnl_unlock();
@@ -335,7 +346,7 @@ static void fm10k_watchdog_update_host_state(struct fm10k_intfc *interface)
err = hw->mac.ops.get_host_state(hw, &interface->host_ready);
if (err && time_is_before_jiffies(interface->last_reset))
- interface->flags |= FM10K_FLAG_RESET_REQUESTED;
+ set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
/* free the lock */
fm10k_mbx_unlock(interface);
@@ -411,7 +422,7 @@ void fm10k_update_stats(struct fm10k_intfc *interface)
int i;
/* ensure only one thread updates stats at a time */
- if (test_and_set_bit(__FM10K_UPDATING_STATS, &interface->state))
+ if (test_and_set_bit(__FM10K_UPDATING_STATS, interface->state))
return;
/* do not allow stats update via service task for next second */
@@ -492,7 +503,7 @@ void fm10k_update_stats(struct fm10k_intfc *interface)
net_stats->rx_errors = rx_errors;
net_stats->rx_dropped = interface->stats.nodesc_drop.count;
- clear_bit(__FM10K_UPDATING_STATS, &interface->state);
+ clear_bit(__FM10K_UPDATING_STATS, interface->state);
}
/**
@@ -522,7 +533,7 @@ static void fm10k_watchdog_flush_tx(struct fm10k_intfc *interface)
* controller to flush Tx.
*/
if (some_tx_pending)
- interface->flags |= FM10K_FLAG_RESET_REQUESTED;
+ set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
}
/**
@@ -532,8 +543,8 @@ static void fm10k_watchdog_flush_tx(struct fm10k_intfc *interface)
static void fm10k_watchdog_subtask(struct fm10k_intfc *interface)
{
/* if interface is down do nothing */
- if (test_bit(__FM10K_DOWN, &interface->state) ||
- test_bit(__FM10K_RESETTING, &interface->state))
+ if (test_bit(__FM10K_DOWN, interface->state) ||
+ test_bit(__FM10K_RESETTING, interface->state))
return;
if (interface->host_ready)
@@ -563,8 +574,8 @@ static void fm10k_check_hang_subtask(struct fm10k_intfc *interface)
int i;
/* If we're down or resetting, just bail */
- if (test_bit(__FM10K_DOWN, &interface->state) ||
- test_bit(__FM10K_RESETTING, &interface->state))
+ if (test_bit(__FM10K_DOWN, interface->state) ||
+ test_bit(__FM10K_RESETTING, interface->state))
return;
/* rate limit tx hang checks to only once every 2 seconds */
@@ -663,7 +674,7 @@ static void fm10k_configure_tx_ring(struct fm10k_intfc *interface,
FM10K_PFVTCTL_FTAG_DESC_ENABLE);
/* Initialize XPS */
- if (!test_and_set_bit(__FM10K_TX_XPS_INIT_DONE, &ring->state) &&
+ if (!test_and_set_bit(__FM10K_TX_XPS_INIT_DONE, ring->state) &&
ring->q_vector)
netif_set_xps_queue(ring->netdev,
&ring->q_vector->affinity_mask,
@@ -743,6 +754,7 @@ static void fm10k_configure_rx_ring(struct fm10k_intfc *interface,
/* disable queue to avoid issues while updating state */
rxqctl = fm10k_read_reg(hw, FM10K_RXQCTL(reg_idx));
rxqctl &= ~FM10K_RXQCTL_ENABLE;
+ fm10k_write_reg(hw, FM10K_RXQCTL(reg_idx), rxqctl);
fm10k_write_flush(hw);
/* possible poll here to verify ring resources have been cleaned */
@@ -863,9 +875,9 @@ static void fm10k_configure_dglort(struct fm10k_intfc *interface)
FM10K_MRQC_IPV6 |
FM10K_MRQC_TCP_IPV6;
- if (interface->flags & FM10K_FLAG_RSS_FIELD_IPV4_UDP)
+ if (test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP, interface->flags))
mrqc |= FM10K_MRQC_UDP_IPV4;
- if (interface->flags & FM10K_FLAG_RSS_FIELD_IPV6_UDP)
+ if (test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP, interface->flags))
mrqc |= FM10K_MRQC_UDP_IPV6;
fm10k_write_reg(hw, FM10K_MRQC(0), mrqc);
@@ -980,7 +992,7 @@ void fm10k_netpoll(struct net_device *netdev)
int i;
/* if interface is down do nothing */
- if (test_bit(__FM10K_DOWN, &interface->state))
+ if (test_bit(__FM10K_DOWN, interface->state))
return;
for (i = 0; i < interface->num_q_vectors; i++)
@@ -1167,13 +1179,13 @@ static irqreturn_t fm10k_msix_mbx_pf(int __always_unused irq, void *data)
}
if (err == FM10K_ERR_RESET_REQUESTED)
- interface->flags |= FM10K_FLAG_RESET_REQUESTED;
+ set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
/* if switch toggled state we should reset GLORTs */
if (eicr & FM10K_EICR_SWITCHNOTREADY) {
/* force link down for at least 4 seconds */
interface->link_down_event = jiffies + (4 * HZ);
- set_bit(__FM10K_LINK_DOWN, &interface->state);
+ set_bit(__FM10K_LINK_DOWN, interface->state);
/* reset dglort_map back to no config */
hw->mac.dglort_map = FM10K_DGLORTMAP_NONE;
@@ -1246,12 +1258,12 @@ static s32 fm10k_mbx_mac_addr(struct fm10k_hw *hw, u32 **results,
/* MAC was changed so we need reset */
if (is_valid_ether_addr(hw->mac.perm_addr) &&
!ether_addr_equal(hw->mac.perm_addr, hw->mac.addr))
- interface->flags |= FM10K_FLAG_RESET_REQUESTED;
+ set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
/* VLAN override was changed, or default VLAN changed */
if ((vlan_override != hw->mac.vlan_override) ||
(default_vid != hw->mac.default_vid))
- interface->flags |= FM10K_FLAG_RESET_REQUESTED;
+ set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
return 0;
}
@@ -1325,7 +1337,7 @@ static s32 fm10k_lport_map(struct fm10k_hw *hw, u32 **results,
if (!err && hw->swapi.status) {
/* force link down for a reasonable delay */
interface->link_down_event = jiffies + (2 * HZ);
- set_bit(__FM10K_LINK_DOWN, &interface->state);
+ set_bit(__FM10K_LINK_DOWN, interface->state);
/* reset dglort_map back to no config */
hw->mac.dglort_map = FM10K_DGLORTMAP_NONE;
@@ -1356,7 +1368,7 @@ static s32 fm10k_lport_map(struct fm10k_hw *hw, u32 **results,
/* we need to reset if port count was just updated */
if (dglort_map != hw->mac.dglort_map)
- interface->flags |= FM10K_FLAG_RESET_REQUESTED;
+ set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
return 0;
}
@@ -1395,7 +1407,7 @@ static s32 fm10k_update_pvid(struct fm10k_hw *hw, u32 **results,
/* we need to reset if default VLAN was just updated */
if (pvid != hw->mac.default_vid)
- interface->flags |= FM10K_FLAG_RESET_REQUESTED;
+ set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags);
hw->mac.default_vid = pvid;
@@ -1623,10 +1635,10 @@ void fm10k_up(struct fm10k_intfc *interface)
hw->mac.ops.update_int_moderator(hw);
/* enable statistics capture again */
- clear_bit(__FM10K_UPDATING_STATS, &interface->state);
+ clear_bit(__FM10K_UPDATING_STATS, interface->state);
/* clear down bit to indicate we are ready to go */
- clear_bit(__FM10K_DOWN, &interface->state);
+ clear_bit(__FM10K_DOWN, interface->state);
/* enable polling cleanups */
fm10k_napi_enable_all(interface);
@@ -1660,7 +1672,7 @@ void fm10k_down(struct fm10k_intfc *interface)
int err, i = 0, count = 0;
/* signal that we are down to the interrupt handler and service task */
- if (test_and_set_bit(__FM10K_DOWN, &interface->state))
+ if (test_and_set_bit(__FM10K_DOWN, interface->state))
return;
/* call carrier off first to avoid false dev_watchdog timeouts */
@@ -1680,7 +1692,7 @@ void fm10k_down(struct fm10k_intfc *interface)
fm10k_update_stats(interface);
/* prevent updating statistics while we're down */
- while (test_and_set_bit(__FM10K_UPDATING_STATS, &interface->state))
+ while (test_and_set_bit(__FM10K_UPDATING_STATS, interface->state))
usleep_range(1000, 2000);
/* skip waiting for TX DMA if we lost PCIe link */
@@ -1849,8 +1861,8 @@ static int fm10k_sw_init(struct fm10k_intfc *interface,
memcpy(interface->rssrk, rss_key, sizeof(rss_key));
/* Start off interface as being down */
- set_bit(__FM10K_DOWN, &interface->state);
- set_bit(__FM10K_UPDATING_STATS, &interface->state);
+ set_bit(__FM10K_DOWN, interface->state);
+ set_bit(__FM10K_UPDATING_STATS, interface->state);
return 0;
}
@@ -2027,7 +2039,7 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
* must ensure it is disabled since we haven't yet requested the timer
* or work item.
*/
- set_bit(__FM10K_SERVICE_DISABLE, &interface->state);
+ set_bit(__FM10K_SERVICE_DISABLE, interface->state);
err = fm10k_mbx_request_irq(interface);
if (err)
@@ -2068,7 +2080,7 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
fm10k_iov_configure(pdev, 0);
/* clear the service task disable bit to allow service task to start */
- clear_bit(__FM10K_SERVICE_DISABLE, &interface->state);
+ clear_bit(__FM10K_SERVICE_DISABLE, interface->state);
return 0;
@@ -2106,7 +2118,7 @@ static void fm10k_remove(struct pci_dev *pdev)
del_timer_sync(&interface->service_timer);
- set_bit(__FM10K_SERVICE_DISABLE, &interface->state);
+ set_bit(__FM10K_SERVICE_DISABLE, interface->state);
cancel_work_sync(&interface->service_task);
/* free netdev, this may bounce the interrupts due to setup_tc */
@@ -2145,7 +2157,7 @@ static void fm10k_prepare_suspend(struct fm10k_intfc *interface)
* stopped. We stop the watchdog task until after we resume software
* activity.
*/
- set_bit(__FM10K_SERVICE_DISABLE, &interface->state);
+ set_bit(__FM10K_SERVICE_DISABLE, interface->state);
cancel_work_sync(&interface->service_task);
fm10k_prepare_for_reset(interface);
@@ -2171,10 +2183,10 @@ static int fm10k_handle_resume(struct fm10k_intfc *interface)
/* force link to stay down for a second to prevent link flutter */
interface->link_down_event = jiffies + (HZ);
- set_bit(__FM10K_LINK_DOWN, &interface->state);
+ set_bit(__FM10K_LINK_DOWN, interface->state);
/* clear the service task disable bit to allow service task to start */
- clear_bit(__FM10K_SERVICE_DISABLE, &interface->state);
+ clear_bit(__FM10K_SERVICE_DISABLE, interface->state);
fm10k_service_event_schedule(interface);
return err;
diff --git a/drivers/net/ethernet/intel/i40e/Makefile b/drivers/net/ethernet/intel/i40e/Makefile
index 3b3c63e..4f454d3 100644
--- a/drivers/net/ethernet/intel/i40e/Makefile
+++ b/drivers/net/ethernet/intel/i40e/Makefile
@@ -45,4 +45,3 @@
i40e_virtchnl_pf.o
i40e-$(CONFIG_I40E_DCB) += i40e_dcb.o i40e_dcb_nl.o
-i40e-$(CONFIG_I40E_FCOE) += i40e_fcoe.o
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 82d8040..e987503 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -56,9 +56,6 @@
#include <linux/ptp_clock_kernel.h>
#include "i40e_type.h"
#include "i40e_prototype.h"
-#ifdef I40E_FCOE
-#include "i40e_fcoe.h"
-#endif
#include "i40e_client.h"
#include "i40e_virtchnl.h"
#include "i40e_virtchnl_pf.h"
@@ -85,10 +82,6 @@
(((pf)->flags & I40E_FLAG_128_QP_RSS_CAPABLE) ? 128 : 64)
#define I40E_FDIR_RING 0
#define I40E_FDIR_RING_COUNT 32
-#ifdef I40E_FCOE
-#define I40E_DEFAULT_FCOE 8 /* default number of QPs for FCoE */
-#define I40E_MINIMUM_FCOE 1 /* minimum number of QPs for FCoE */
-#endif /* I40E_FCOE */
#define I40E_MAX_AQ_BUF_SIZE 4096
#define I40E_AQ_LEN 256
#define I40E_AQ_WORK_LIMIT 66 /* max number of VFs + a little */
@@ -98,14 +91,6 @@
#define I40E_QUEUE_WAIT_RETRY_LIMIT 10
#define I40E_INT_NAME_STR_LEN (IFNAMSIZ + 16)
-/* Ethtool Private Flags */
-#define I40E_PRIV_FLAGS_MFP_FLAG BIT(0)
-#define I40E_PRIV_FLAGS_LINKPOLL_FLAG BIT(1)
-#define I40E_PRIV_FLAGS_FD_ATR BIT(2)
-#define I40E_PRIV_FLAGS_VEB_STATS BIT(3)
-#define I40E_PRIV_FLAGS_HW_ATR_EVICT BIT(4)
-#define I40E_PRIV_FLAGS_TRUE_PROMISC_SUPPORT BIT(5)
-
#define I40E_NVM_VERSION_LO_SHIFT 0
#define I40E_NVM_VERSION_LO_MASK (0xff << I40E_NVM_VERSION_LO_SHIFT)
#define I40E_NVM_VERSION_HI_SHIFT 12
@@ -202,17 +187,32 @@ enum i40e_fd_stat_idx {
#define I40E_FD_ATR_TUNNEL_STAT_IDX(pf_id) \
(I40E_FD_STAT_PF_IDX(pf_id) + I40E_FD_STAT_ATR_TUNNEL)
+/* The following structure contains the data parsed from the user-defined
+ * field of the ethtool_rx_flow_spec structure.
+ */
+struct i40e_rx_flow_userdef {
+ bool flex_filter;
+ u16 flex_word;
+ u16 flex_offset;
+};
+
struct i40e_fdir_filter {
struct hlist_node fdir_node;
/* filter ipnut set */
u8 flow_type;
u8 ip4_proto;
/* TX packet view of src and dst */
- __be32 dst_ip[4];
- __be32 src_ip[4];
+ __be32 dst_ip;
+ __be32 src_ip;
__be16 src_port;
__be16 dst_port;
__be32 sctp_v_tag;
+
+ /* Flexible data to match within the packet payload */
+ __be16 flex_word;
+ u16 flex_offset;
+ bool flex_filter;
+
/* filter control */
u16 q_index;
u8 flex_off;
@@ -244,10 +244,80 @@ struct i40e_tc_configuration {
};
struct i40e_udp_port_config {
- __be16 index;
+ /* AdminQ command interface expects port number in Host byte order */
+ u16 index;
u8 type;
};
+/* macros related to FLX_PIT */
+#define I40E_FLEX_SET_FSIZE(fsize) (((fsize) << \
+ I40E_PRTQF_FLX_PIT_FSIZE_SHIFT) & \
+ I40E_PRTQF_FLX_PIT_FSIZE_MASK)
+#define I40E_FLEX_SET_DST_WORD(dst) (((dst) << \
+ I40E_PRTQF_FLX_PIT_DEST_OFF_SHIFT) & \
+ I40E_PRTQF_FLX_PIT_DEST_OFF_MASK)
+#define I40E_FLEX_SET_SRC_WORD(src) (((src) << \
+ I40E_PRTQF_FLX_PIT_SOURCE_OFF_SHIFT) & \
+ I40E_PRTQF_FLX_PIT_SOURCE_OFF_MASK)
+#define I40E_FLEX_PREP_VAL(dst, fsize, src) (I40E_FLEX_SET_DST_WORD(dst) | \
+ I40E_FLEX_SET_FSIZE(fsize) | \
+ I40E_FLEX_SET_SRC_WORD(src))
+
+#define I40E_FLEX_PIT_GET_SRC(flex) (((flex) & \
+ I40E_PRTQF_FLX_PIT_SOURCE_OFF_MASK) >> \
+ I40E_PRTQF_FLX_PIT_SOURCE_OFF_SHIFT)
+#define I40E_FLEX_PIT_GET_DST(flex) (((flex) & \
+ I40E_PRTQF_FLX_PIT_DEST_OFF_MASK) >> \
+ I40E_PRTQF_FLX_PIT_DEST_OFF_SHIFT)
+#define I40E_FLEX_PIT_GET_FSIZE(flex) (((flex) & \
+ I40E_PRTQF_FLX_PIT_FSIZE_MASK) >> \
+ I40E_PRTQF_FLX_PIT_FSIZE_SHIFT)
+
+#define I40E_MAX_FLEX_SRC_OFFSET 0x1F
+
+/* macros related to GLQF_ORT */
+#define I40E_ORT_SET_IDX(idx) (((idx) << \
+ I40E_GLQF_ORT_PIT_INDX_SHIFT) & \
+ I40E_GLQF_ORT_PIT_INDX_MASK)
+
+#define I40E_ORT_SET_COUNT(count) (((count) << \
+ I40E_GLQF_ORT_FIELD_CNT_SHIFT) & \
+ I40E_GLQF_ORT_FIELD_CNT_MASK)
+
+#define I40E_ORT_SET_PAYLOAD(payload) (((payload) << \
+ I40E_GLQF_ORT_FLX_PAYLOAD_SHIFT) & \
+ I40E_GLQF_ORT_FLX_PAYLOAD_MASK)
+
+#define I40E_ORT_PREP_VAL(idx, count, payload) (I40E_ORT_SET_IDX(idx) | \
+ I40E_ORT_SET_COUNT(count) | \
+ I40E_ORT_SET_PAYLOAD(payload))
+
+#define I40E_L3_GLQF_ORT_IDX 34
+#define I40E_L4_GLQF_ORT_IDX 35
+
+/* Flex PIT register index */
+#define I40E_FLEX_PIT_IDX_START_L2 0
+#define I40E_FLEX_PIT_IDX_START_L3 3
+#define I40E_FLEX_PIT_IDX_START_L4 6
+
+#define I40E_FLEX_PIT_TABLE_SIZE 3
+
+#define I40E_FLEX_DEST_UNUSED 63
+
+#define I40E_FLEX_INDEX_ENTRIES 8
+
+/* Flex MASK to disable all flexible entries */
+#define I40E_FLEX_INPUT_MASK (I40E_FLEX_50_MASK | I40E_FLEX_51_MASK | \
+ I40E_FLEX_52_MASK | I40E_FLEX_53_MASK | \
+ I40E_FLEX_54_MASK | I40E_FLEX_55_MASK | \
+ I40E_FLEX_56_MASK | I40E_FLEX_57_MASK)
+
+struct i40e_flex_pit {
+ struct list_head list;
+ u16 src_offset;
+ u8 pit_index;
+};
+
/* struct that defines the Ethernet device */
struct i40e_pf {
struct pci_dev *pdev;
@@ -262,10 +332,6 @@ struct i40e_pf {
u16 num_vmdq_msix; /* num queue vectors per vmdq pool */
u16 num_req_vfs; /* num VFs requested for this VF */
u16 num_vf_qps; /* num queue pairs per VF */
-#ifdef I40E_FCOE
- u16 num_fcoe_qps; /* num fcoe queues this PF has set up */
- u16 num_fcoe_msix; /* num queue vectors per fcoe pool */
-#endif /* I40E_FCOE */
u16 num_lan_qps; /* num lan queues this PF has set up */
u16 num_lan_msix; /* num queue vectors for the base PF vsi */
u16 num_fdsb_msix; /* num queue vectors for sideband Fdir */
@@ -285,7 +351,23 @@ struct i40e_pf {
u32 fd_flush_cnt;
u32 fd_add_err;
u32 fd_atr_cnt;
- u32 fd_tcp_rule;
+
+ /* Book-keeping of side-band filter count per flow-type.
+ * This is used to detect and handle input set changes for
+ * respective flow-type.
+ */
+ u16 fd_tcp4_filter_cnt;
+ u16 fd_udp4_filter_cnt;
+ u16 fd_sctp4_filter_cnt;
+ u16 fd_ip4_filter_cnt;
+
+ /* Flexible filter table values that need to be programmed into
+ * hardware, which expects L3 and L4 to be programmed separately. We
+ * need to ensure that the values are in ascended order and don't have
+ * duplicates, so we track each L3 and L4 values in separate lists.
+ */
+ struct list_head l3_flex_pit_list;
+ struct list_head l4_flex_pit_list;
struct i40e_udp_port_config udp_ports[I40E_MAX_PF_UDP_OFFLOAD_PORTS];
u16 pending_udp_bitmap;
@@ -307,17 +389,9 @@ struct i40e_pf {
#define I40E_FLAG_MSIX_ENABLED BIT_ULL(3)
#define I40E_FLAG_RSS_ENABLED BIT_ULL(6)
#define I40E_FLAG_VMDQ_ENABLED BIT_ULL(7)
-#define I40E_FLAG_FDIR_REQUIRES_REINIT BIT_ULL(8)
-#define I40E_FLAG_NEED_LINK_UPDATE BIT_ULL(9)
#define I40E_FLAG_IWARP_ENABLED BIT_ULL(10)
-#ifdef I40E_FCOE
-#define I40E_FLAG_FCOE_ENABLED BIT_ULL(11)
-#endif /* I40E_FCOE */
-#define I40E_FLAG_CLEAN_ADMINQ BIT_ULL(14)
#define I40E_FLAG_FILTER_SYNC BIT_ULL(15)
#define I40E_FLAG_SERVICE_CLIENT_REQUESTED BIT_ULL(16)
-#define I40E_FLAG_PROCESS_MDD_EVENT BIT_ULL(17)
-#define I40E_FLAG_PROCESS_VFLR_EVENT BIT_ULL(18)
#define I40E_FLAG_SRIOV_ENABLED BIT_ULL(19)
#define I40E_FLAG_DCB_ENABLED BIT_ULL(20)
#define I40E_FLAG_FD_SB_ENABLED BIT_ULL(21)
@@ -348,16 +422,20 @@ struct i40e_pf {
#define I40E_FLAG_TRUE_PROMISC_SUPPORT BIT_ULL(51)
#define I40E_FLAG_HAVE_CRT_RETIMER BIT_ULL(52)
#define I40E_FLAG_PTP_L4_CAPABLE BIT_ULL(53)
-#define I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE BIT_ULL(54)
+#define I40E_FLAG_CLIENT_RESET BIT_ULL(54)
#define I40E_FLAG_TEMP_LINK_POLLING BIT_ULL(55)
+#define I40E_FLAG_CLIENT_L2_CHANGE BIT_ULL(56)
+#define I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE BIT_ULL(57)
+#define I40E_FLAG_LEGACY_RX BIT_ULL(58)
- /* tracks features that get auto disabled by errors */
- u64 auto_disable_flags;
+ /* Tracks features that are disabled due to hw limitations.
+ * If a bit is set here, it means that the corresponding
+ * bit in the 'flags' field is cleared i.e that feature
+ * is disabled
+ */
+ u64 hw_disabled_flags;
-#ifdef I40E_FCOE
- struct i40e_fcoe fcoe;
-
-#endif /* I40E_FCOE */
+ struct i40e_client_instance *cinst;
bool stat_offsets_loaded;
struct i40e_hw_port_stats stats;
struct i40e_hw_port_stats stats_offsets;
@@ -412,8 +490,6 @@ struct i40e_pf {
*/
u16 dcbx_cap;
- u32 fcoe_hmc_filt_num;
- u32 fcoe_hmc_cntx_num;
struct i40e_filter_control_settings filter_settings;
struct ptp_clock *ptp_clock;
@@ -533,16 +609,10 @@ struct i40e_vsi {
struct rtnl_link_stats64 net_stats_offsets;
struct i40e_eth_stats eth_stats;
struct i40e_eth_stats eth_stats_offsets;
-#ifdef I40E_FCOE
- struct i40e_fcoe_stats fcoe_stats;
- struct i40e_fcoe_stats fcoe_stats_offsets;
- bool fcoe_stat_offsets_loaded;
-#endif
u32 tx_restart;
u32 tx_busy;
u64 tx_linearize;
u64 tx_force_wb;
- u64 tx_lost_interrupt;
u32 rx_buf_failed;
u32 rx_page_failed;
@@ -628,9 +698,6 @@ struct i40e_q_vector {
u8 num_ringpairs; /* total number of ring pairs in vector */
-#define I40E_Q_VECTOR_HUNG_DETECT 0 /* Bit Index for hung detection logic */
- unsigned long hung_detected; /* Set/Reset for hung_detection logic */
-
cpumask_t affinity_mask;
struct irq_affinity_notify affinity_notify;
@@ -719,13 +786,50 @@ static inline int i40e_get_fd_cnt_all(struct i40e_pf *pf)
return pf->hw.fdir_shared_filter_count + pf->fdir_pf_filter_count;
}
+/**
+ * i40e_read_fd_input_set - reads value of flow director input set register
+ * @pf: pointer to the PF struct
+ * @addr: register addr
+ *
+ * This function reads value of flow director input set register
+ * specified by 'addr' (which is specific to flow-type)
+ **/
+static inline u64 i40e_read_fd_input_set(struct i40e_pf *pf, u16 addr)
+{
+ u64 val;
+
+ val = i40e_read_rx_ctl(&pf->hw, I40E_PRTQF_FD_INSET(addr, 1));
+ val <<= 32;
+ val += i40e_read_rx_ctl(&pf->hw, I40E_PRTQF_FD_INSET(addr, 0));
+
+ return val;
+}
+
+/**
+ * i40e_write_fd_input_set - writes value into flow director input set register
+ * @pf: pointer to the PF struct
+ * @addr: register addr
+ * @val: value to be written
+ *
+ * This function writes specified value to the register specified by 'addr'.
+ * This register is input set register based on flow-type.
+ **/
+static inline void i40e_write_fd_input_set(struct i40e_pf *pf,
+ u16 addr, u64 val)
+{
+ i40e_write_rx_ctl(&pf->hw, I40E_PRTQF_FD_INSET(addr, 1),
+ (u32)(val >> 32));
+ i40e_write_rx_ctl(&pf->hw, I40E_PRTQF_FD_INSET(addr, 0),
+ (u32)(val & 0xFFFFFFFFULL));
+}
+
/* needed by i40e_ethtool.c */
int i40e_up(struct i40e_vsi *vsi);
void i40e_down(struct i40e_vsi *vsi);
extern const char i40e_driver_name[];
extern const char i40e_driver_version_str[];
void i40e_do_reset_safe(struct i40e_pf *pf, u32 reset_flags);
-void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags);
+void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired);
int i40e_config_rss(struct i40e_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size);
int i40e_get_rss(struct i40e_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size);
void i40e_fill_rss_lut(struct i40e_pf *pf, u8 *lut,
@@ -773,11 +877,6 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi);
struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
u16 uplink, u32 param1);
int i40e_vsi_release(struct i40e_vsi *vsi);
-#ifdef I40E_FCOE
-void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
- struct i40e_vsi_context *ctxt,
- u8 enabled_tc, bool is_add);
-#endif
void i40e_service_event_schedule(struct i40e_pf *pf);
void i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id,
u8 *msg, u16 len);
@@ -813,8 +912,7 @@ void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi);
void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset);
void i40e_notify_client_of_vf_enable(struct i40e_pf *pf, u32 num_vfs);
void i40e_notify_client_of_vf_reset(struct i40e_pf *pf, u32 vf_id);
-int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id,
- enum i40e_client_type type);
+int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id);
/**
* i40e_irq_dynamic_enable - Enable default interrupt generation settings
* @vsi: pointer to a vsi
@@ -838,20 +936,7 @@ static inline void i40e_irq_dynamic_enable(struct i40e_vsi *vsi, int vector)
void i40e_irq_dynamic_disable_icr0(struct i40e_pf *pf);
void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf, bool clearpba);
-#ifdef I40E_FCOE
-void i40e_get_netdev_stats_struct(struct net_device *netdev,
- struct rtnl_link_stats64 *storage);
-int i40e_set_mac(struct net_device *netdev, void *p);
-void i40e_set_rx_mode(struct net_device *netdev);
-#endif
int i40e_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd);
-#ifdef I40E_FCOE
-void i40e_tx_timeout(struct net_device *netdev);
-int i40e_vlan_rx_add_vid(struct net_device *netdev,
- __always_unused __be16 proto, u16 vid);
-int i40e_vlan_rx_kill_vid(struct net_device *netdev,
- __always_unused __be16 proto, u16 vid);
-#endif
int i40e_open(struct net_device *netdev);
int i40e_close(struct net_device *netdev);
int i40e_vsi_open(struct i40e_vsi *vsi);
@@ -865,25 +950,6 @@ struct i40e_mac_filter *i40e_add_mac_filter(struct i40e_vsi *vsi,
int i40e_del_mac_filter(struct i40e_vsi *vsi, const u8 *macaddr);
bool i40e_is_vsi_in_vlan(struct i40e_vsi *vsi);
struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, const u8 *macaddr);
-#ifdef I40E_FCOE
-int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto,
- struct tc_to_netdev *tc);
-void i40e_netpoll(struct net_device *netdev);
-int i40e_fcoe_enable(struct net_device *netdev);
-int i40e_fcoe_disable(struct net_device *netdev);
-int i40e_fcoe_vsi_init(struct i40e_vsi *vsi, struct i40e_vsi_context *ctxt);
-u8 i40e_get_fcoe_tc_map(struct i40e_pf *pf);
-void i40e_fcoe_config_netdev(struct net_device *netdev, struct i40e_vsi *vsi);
-void i40e_fcoe_vsi_setup(struct i40e_pf *pf);
-void i40e_init_pf_fcoe(struct i40e_pf *pf);
-int i40e_fcoe_setup_ddp_resources(struct i40e_vsi *vsi);
-void i40e_fcoe_free_ddp_resources(struct i40e_vsi *vsi);
-int i40e_fcoe_handle_offload(struct i40e_ring *rx_ring,
- union i40e_rx_desc *rx_desc,
- struct sk_buff *skb);
-void i40e_fcoe_handle_status(struct i40e_ring *rx_ring,
- union i40e_rx_desc *rx_desc, u8 prog_id);
-#endif /* I40E_FCOE */
void i40e_vlan_stripping_enable(struct i40e_vsi *vsi);
#ifdef CONFIG_I40E_DCB
void i40e_dcbnl_flush_apps(struct i40e_pf *pf,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 451f48b..251074c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -132,6 +132,10 @@ enum i40e_admin_queue_opc {
i40e_aqc_opc_list_func_capabilities = 0x000A,
i40e_aqc_opc_list_dev_capabilities = 0x000B,
+ /* Proxy commands */
+ i40e_aqc_opc_set_proxy_config = 0x0104,
+ i40e_aqc_opc_set_ns_proxy_table_entry = 0x0105,
+
/* LAA */
i40e_aqc_opc_mac_address_read = 0x0107,
i40e_aqc_opc_mac_address_write = 0x0108,
@@ -139,6 +143,10 @@ enum i40e_admin_queue_opc {
/* PXE */
i40e_aqc_opc_clear_pxe_mode = 0x0110,
+ /* WoL commands */
+ i40e_aqc_opc_set_wol_filter = 0x0120,
+ i40e_aqc_opc_get_wake_reason = 0x0121,
+
/* internal switch commands */
i40e_aqc_opc_get_switch_config = 0x0200,
i40e_aqc_opc_add_statistics = 0x0201,
@@ -177,6 +185,7 @@ enum i40e_admin_queue_opc {
i40e_aqc_opc_remove_control_packet_filter = 0x025B,
i40e_aqc_opc_add_cloud_filters = 0x025C,
i40e_aqc_opc_remove_cloud_filters = 0x025D,
+ i40e_aqc_opc_clear_wol_switch_filters = 0x025E,
i40e_aqc_opc_add_mirror_rule = 0x0260,
i40e_aqc_opc_delete_mirror_rule = 0x0261,
@@ -563,6 +572,56 @@ struct i40e_aqc_clear_pxe {
I40E_CHECK_CMD_LENGTH(i40e_aqc_clear_pxe);
+/* Set WoL Filter (0x0120) */
+
+struct i40e_aqc_set_wol_filter {
+ __le16 filter_index;
+#define I40E_AQC_MAX_NUM_WOL_FILTERS 8
+#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT 15
+#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_MASK (0x1 << \
+ I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT)
+
+#define I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT 0
+#define I40E_AQC_SET_WOL_FILTER_INDEX_MASK (0x7 << \
+ I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT)
+ __le16 cmd_flags;
+#define I40E_AQC_SET_WOL_FILTER 0x8000
+#define I40E_AQC_SET_WOL_FILTER_NO_TCO_WOL 0x4000
+#define I40E_AQC_SET_WOL_FILTER_ACTION_CLEAR 0
+#define I40E_AQC_SET_WOL_FILTER_ACTION_SET 1
+ __le16 valid_flags;
+#define I40E_AQC_SET_WOL_FILTER_ACTION_VALID 0x8000
+#define I40E_AQC_SET_WOL_FILTER_NO_TCO_ACTION_VALID 0x4000
+ u8 reserved[2];
+ __le32 address_high;
+ __le32 address_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_set_wol_filter);
+
+struct i40e_aqc_set_wol_filter_data {
+ u8 filter[128];
+ u8 mask[16];
+};
+
+I40E_CHECK_STRUCT_LEN(0x90, i40e_aqc_set_wol_filter_data);
+
+/* Get Wake Reason (0x0121) */
+
+struct i40e_aqc_get_wake_reason_completion {
+ u8 reserved_1[2];
+ __le16 wake_reason;
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT 0
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_MASK (0xFF << \
+ I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT)
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT 8
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_MASK (0xFF << \
+ I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT)
+ u8 reserved_2[12];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_get_wake_reason_completion);
+
/* Switch configuration commands (0x02xx) */
/* Used by many indirect commands that only pass an seid and a buffer in the
@@ -645,6 +704,8 @@ struct i40e_aqc_set_port_parameters {
#define I40E_AQ_SET_P_PARAMS_PAD_SHORT_PACKETS 2 /* must set! */
#define I40E_AQ_SET_P_PARAMS_DOUBLE_VLAN_ENA 4
__le16 bad_frame_vsi;
+#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_SHIFT 0x0
+#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_MASK 0x3FF
__le16 default_seid; /* reserved for command */
u8 reserved[10];
};
@@ -696,6 +757,7 @@ I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_resource_alloc_element_resp);
/* Set Switch Configuration (direct 0x0205) */
struct i40e_aqc_set_switch_config {
__le16 flags;
+/* flags used for both fields below */
#define I40E_AQ_SET_SWITCH_CFG_PROMISC 0x0001
#define I40E_AQ_SET_SWITCH_CFG_L2_FILTER 0x0002
__le16 valid_flags;
@@ -1844,11 +1906,12 @@ struct i40e_aqc_get_link_status {
#define I40E_AQ_CONFIG_FEC_RS_ENA 0x02
#define I40E_AQ_CONFIG_CRC_ENA 0x04
#define I40E_AQ_CONFIG_PACING_MASK 0x78
- u8 external_power_ability;
+ u8 power_desc;
#define I40E_AQ_LINK_POWER_CLASS_1 0x00
#define I40E_AQ_LINK_POWER_CLASS_2 0x01
#define I40E_AQ_LINK_POWER_CLASS_3 0x02
#define I40E_AQ_LINK_POWER_CLASS_4 0x03
+#define I40E_AQ_PWR_CLASS_MASK 0x03
u8 reserved[4];
};
diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c
index d570219..eb2896f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_client.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_client.c
@@ -32,16 +32,10 @@
#include "i40e_client.h"
static const char i40e_client_interface_version_str[] = I40E_CLIENT_VERSION_STR;
-
+static struct i40e_client *registered_client;
static LIST_HEAD(i40e_devices);
static DEFINE_MUTEX(i40e_device_mutex);
-static LIST_HEAD(i40e_clients);
-static DEFINE_MUTEX(i40e_client_mutex);
-
-static LIST_HEAD(i40e_client_instances);
-static DEFINE_MUTEX(i40e_client_instance_mutex);
-
static int i40e_client_virtchnl_send(struct i40e_info *ldev,
struct i40e_client *client,
u32 vf_id, u8 *msg, u16 len);
@@ -67,28 +61,6 @@ static struct i40e_ops i40e_lan_ops = {
};
/**
- * i40e_client_type_to_vsi_type - convert client type to vsi type
- * @client_type: the i40e_client type
- *
- * returns the related vsi type value
- **/
-static
-enum i40e_vsi_type i40e_client_type_to_vsi_type(enum i40e_client_type type)
-{
- switch (type) {
- case I40E_CLIENT_IWARP:
- return I40E_VSI_IWARP;
-
- case I40E_CLIENT_VMDQ2:
- return I40E_VSI_VMDQ2;
-
- default:
- pr_err("i40e: Client type unknown\n");
- return I40E_VSI_TYPE_UNKNOWN;
- }
-}
-
-/**
* i40e_client_get_params - Get the params that can change at runtime
* @vsi: the VSI with the message
* @param: clinet param struct
@@ -134,31 +106,22 @@ int i40e_client_get_params(struct i40e_vsi *vsi, struct i40e_params *params)
void
i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id, u8 *msg, u16 len)
{
- struct i40e_client_instance *cdev;
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_client_instance *cdev = pf->cinst;
- if (!vsi)
+ if (!cdev || !cdev->client)
return;
- mutex_lock(&i40e_client_instance_mutex);
- list_for_each_entry(cdev, &i40e_client_instances, list) {
- if (cdev->lan_info.pf == vsi->back) {
- if (!cdev->client ||
- !cdev->client->ops ||
- !cdev->client->ops->virtchnl_receive) {
- dev_dbg(&vsi->back->pdev->dev,
- "Cannot locate client instance virtual channel receive routine\n");
- continue;
- }
- if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,
- &cdev->state)) {
- dev_dbg(&vsi->back->pdev->dev, "Client is not open, abort virtchnl_receive\n");
- continue;
- }
- cdev->client->ops->virtchnl_receive(&cdev->lan_info,
- cdev->client,
- vf_id, msg, len);
- }
+ if (!cdev->client->ops || !cdev->client->ops->virtchnl_receive) {
+ dev_dbg(&pf->pdev->dev,
+ "Cannot locate client instance virtual channel receive routine\n");
+ return;
}
- mutex_unlock(&i40e_client_instance_mutex);
+ if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) {
+ dev_dbg(&pf->pdev->dev, "Client is not open, abort virtchnl_receive\n");
+ return;
+ }
+ cdev->client->ops->virtchnl_receive(&cdev->lan_info, cdev->client,
+ vf_id, msg, len);
}
/**
@@ -169,39 +132,30 @@ i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id, u8 *msg, u16 len)
**/
void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi)
{
- struct i40e_client_instance *cdev;
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_client_instance *cdev = pf->cinst;
struct i40e_params params;
- if (!vsi)
+ if (!cdev || !cdev->client)
return;
- mutex_lock(&i40e_client_instance_mutex);
- list_for_each_entry(cdev, &i40e_client_instances, list) {
- if (cdev->lan_info.pf == vsi->back) {
- if (!cdev->client ||
- !cdev->client->ops ||
- !cdev->client->ops->l2_param_change) {
- dev_dbg(&vsi->back->pdev->dev,
- "Cannot locate client instance l2_param_change routine\n");
- continue;
- }
+ if (!cdev->client->ops || !cdev->client->ops->l2_param_change) {
+ dev_dbg(&vsi->back->pdev->dev,
+ "Cannot locate client instance l2_param_change routine\n");
+ return;
+ }
+ if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) {
+ dev_dbg(&vsi->back->pdev->dev, "Client is not open, abort l2 param change\n");
+ return;
+ }
memset(¶ms, 0, sizeof(params));
i40e_client_get_params(vsi, ¶ms);
- if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,
- &cdev->state)) {
- dev_dbg(&vsi->back->pdev->dev, "Client is not open, abort l2 param change\n");
- continue;
- }
- cdev->lan_info.params = params;
- cdev->client->ops->l2_param_change(&cdev->lan_info,
- cdev->client,
- ¶ms);
- }
- }
- mutex_unlock(&i40e_client_instance_mutex);
+ memcpy(&cdev->lan_info.params, ¶ms, sizeof(struct i40e_params));
+ cdev->client->ops->l2_param_change(&cdev->lan_info, cdev->client,
+ ¶ms);
}
/**
- * i40e_client_release_qvlist
+ * i40e_client_release_qvlist - release MSI-X vector mapping for client
* @ldev: pointer to L2 context.
*
**/
@@ -237,26 +191,19 @@ static void i40e_client_release_qvlist(struct i40e_info *ldev)
**/
void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset)
{
- struct i40e_client_instance *cdev;
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_client_instance *cdev = pf->cinst;
- if (!vsi)
+ if (!cdev || !cdev->client)
return;
- mutex_lock(&i40e_client_instance_mutex);
- list_for_each_entry(cdev, &i40e_client_instances, list) {
- if (cdev->lan_info.netdev == vsi->netdev) {
- if (!cdev->client ||
- !cdev->client->ops || !cdev->client->ops->close) {
- dev_dbg(&vsi->back->pdev->dev,
- "Cannot locate client instance close routine\n");
- continue;
- }
- cdev->client->ops->close(&cdev->lan_info, cdev->client,
- reset);
- clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state);
- i40e_client_release_qvlist(&cdev->lan_info);
- }
+ if (!cdev->client->ops || !cdev->client->ops->close) {
+ dev_dbg(&vsi->back->pdev->dev,
+ "Cannot locate client instance close routine\n");
+ return;
}
- mutex_unlock(&i40e_client_instance_mutex);
+ cdev->client->ops->close(&cdev->lan_info, cdev->client, reset);
+ clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state);
+ i40e_client_release_qvlist(&cdev->lan_info);
}
/**
@@ -268,30 +215,20 @@ void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset)
**/
void i40e_notify_client_of_vf_reset(struct i40e_pf *pf, u32 vf_id)
{
- struct i40e_client_instance *cdev;
+ struct i40e_client_instance *cdev = pf->cinst;
- if (!pf)
+ if (!cdev || !cdev->client)
return;
- mutex_lock(&i40e_client_instance_mutex);
- list_for_each_entry(cdev, &i40e_client_instances, list) {
- if (cdev->lan_info.pf == pf) {
- if (!cdev->client ||
- !cdev->client->ops ||
- !cdev->client->ops->vf_reset) {
- dev_dbg(&pf->pdev->dev,
- "Cannot locate client instance VF reset routine\n");
- continue;
- }
- if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,
- &cdev->state)) {
- dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-reset\n");
- continue;
- }
- cdev->client->ops->vf_reset(&cdev->lan_info,
- cdev->client, vf_id);
- }
+ if (!cdev->client->ops || !cdev->client->ops->vf_reset) {
+ dev_dbg(&pf->pdev->dev,
+ "Cannot locate client instance VF reset routine\n");
+ return;
}
- mutex_unlock(&i40e_client_instance_mutex);
+ if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) {
+ dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-reset\n");
+ return;
+ }
+ cdev->client->ops->vf_reset(&cdev->lan_info, cdev->client, vf_id);
}
/**
@@ -303,30 +240,21 @@ void i40e_notify_client_of_vf_reset(struct i40e_pf *pf, u32 vf_id)
**/
void i40e_notify_client_of_vf_enable(struct i40e_pf *pf, u32 num_vfs)
{
- struct i40e_client_instance *cdev;
+ struct i40e_client_instance *cdev = pf->cinst;
- if (!pf)
+ if (!cdev || !cdev->client)
return;
- mutex_lock(&i40e_client_instance_mutex);
- list_for_each_entry(cdev, &i40e_client_instances, list) {
- if (cdev->lan_info.pf == pf) {
- if (!cdev->client ||
- !cdev->client->ops ||
- !cdev->client->ops->vf_enable) {
- dev_dbg(&pf->pdev->dev,
- "Cannot locate client instance VF enable routine\n");
- continue;
- }
- if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,
- &cdev->state)) {
- dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-enable\n");
- continue;
- }
- cdev->client->ops->vf_enable(&cdev->lan_info,
- cdev->client, num_vfs);
- }
+ if (!cdev->client->ops || !cdev->client->ops->vf_enable) {
+ dev_dbg(&pf->pdev->dev,
+ "Cannot locate client instance VF enable routine\n");
+ return;
}
- mutex_unlock(&i40e_client_instance_mutex);
+ if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,
+ &cdev->state)) {
+ dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-enable\n");
+ return;
+ }
+ cdev->client->ops->vf_enable(&cdev->lan_info, cdev->client, num_vfs);
}
/**
@@ -337,37 +265,25 @@ void i40e_notify_client_of_vf_enable(struct i40e_pf *pf, u32 num_vfs)
* If there is a client of the specified type attached to this PF, call
* its vf_capable routine
**/
-int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id,
- enum i40e_client_type type)
+int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id)
{
- struct i40e_client_instance *cdev;
+ struct i40e_client_instance *cdev = pf->cinst;
int capable = false;
- if (!pf)
- return false;
- mutex_lock(&i40e_client_instance_mutex);
- list_for_each_entry(cdev, &i40e_client_instances, list) {
- if (cdev->lan_info.pf == pf) {
- if (!cdev->client ||
- !cdev->client->ops ||
- !cdev->client->ops->vf_capable ||
- !(cdev->client->type == type)) {
- dev_dbg(&pf->pdev->dev,
- "Cannot locate client instance VF capability routine\n");
- continue;
- }
- if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,
- &cdev->state)) {
- dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-capable\n");
- continue;
- }
- capable = cdev->client->ops->vf_capable(&cdev->lan_info,
- cdev->client,
- vf_id);
- break;
- }
+ if (!cdev || !cdev->client)
+ goto out;
+ if (!cdev->client->ops || !cdev->client->ops->vf_capable) {
+ dev_info(&pf->pdev->dev,
+ "Cannot locate client instance VF capability routine\n");
+ goto out;
}
- mutex_unlock(&i40e_client_instance_mutex);
+ if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state))
+ goto out;
+
+ capable = cdev->client->ops->vf_capable(&cdev->lan_info,
+ cdev->client,
+ vf_id);
+out:
return capable;
}
@@ -377,27 +293,19 @@ int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id,
* @client: pointer to a client struct in the client list.
* @existing: if there was already an existing instance
*
- * Returns cdev ptr on success or if already exists, NULL on failure
**/
-static
-struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf,
- struct i40e_client *client,
- bool *existing)
+static void i40e_client_add_instance(struct i40e_pf *pf)
{
- struct i40e_client_instance *cdev;
+ struct i40e_client_instance *cdev = NULL;
struct netdev_hw_addr *mac = NULL;
struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
- mutex_lock(&i40e_client_instance_mutex);
- list_for_each_entry(cdev, &i40e_client_instances, list) {
- if ((cdev->lan_info.pf == pf) && (cdev->client == client)) {
- *existing = true;
- goto out;
- }
- }
+ if (!registered_client || pf->cinst)
+ return;
+
cdev = kzalloc(sizeof(*cdev), GFP_KERNEL);
if (!cdev)
- goto out;
+ return;
cdev->lan_info.pf = (void *)pf;
cdev->lan_info.netdev = vsi->netdev;
@@ -417,7 +325,7 @@ struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf,
if (i40e_client_get_params(vsi, &cdev->lan_info.params)) {
kfree(cdev);
cdev = NULL;
- goto out;
+ return;
}
cdev->lan_info.msix_count = pf->num_iwarp_msix;
@@ -430,41 +338,20 @@ struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf,
else
dev_err(&pf->pdev->dev, "MAC address list is empty!\n");
- cdev->client = client;
- INIT_LIST_HEAD(&cdev->list);
- list_add(&cdev->list, &i40e_client_instances);
-out:
- mutex_unlock(&i40e_client_instance_mutex);
- return cdev;
+ cdev->client = registered_client;
+ pf->cinst = cdev;
}
/**
* i40e_client_del_instance - removes a client instance from the list
* @pf: pointer to the board struct
*
- * Returns 0 on success or non-0 on error
**/
static
-int i40e_client_del_instance(struct i40e_pf *pf, struct i40e_client *client)
+void i40e_client_del_instance(struct i40e_pf *pf)
{
- struct i40e_client_instance *cdev, *tmp;
- int ret = -ENODEV;
-
- mutex_lock(&i40e_client_instance_mutex);
- list_for_each_entry_safe(cdev, tmp, &i40e_client_instances, list) {
- if ((cdev->lan_info.pf != pf) || (cdev->client != client))
- continue;
-
- dev_info(&pf->pdev->dev, "Deleted instance of Client %s, of dev %d bus=0x%02x func=0x%02x)\n",
- client->name, pf->hw.pf_id,
- pf->hw.bus.device, pf->hw.bus.func);
- list_del(&cdev->list);
- kfree(cdev);
- ret = 0;
- break;
- }
- mutex_unlock(&i40e_client_instance_mutex);
- return ret;
+ kfree(pf->cinst);
+ pf->cinst = NULL;
}
/**
@@ -473,67 +360,50 @@ int i40e_client_del_instance(struct i40e_pf *pf, struct i40e_client *client)
**/
void i40e_client_subtask(struct i40e_pf *pf)
{
+ struct i40e_client *client = registered_client;
struct i40e_client_instance *cdev;
- struct i40e_client *client;
- bool existing = false;
+ struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
int ret = 0;
if (!(pf->flags & I40E_FLAG_SERVICE_CLIENT_REQUESTED))
return;
pf->flags &= ~I40E_FLAG_SERVICE_CLIENT_REQUESTED;
+ cdev = pf->cinst;
/* If we're down or resetting, just bail */
if (test_bit(__I40E_DOWN, &pf->state) ||
test_bit(__I40E_CONFIG_BUSY, &pf->state))
return;
- /* Check client state and instantiate client if client registered */
- mutex_lock(&i40e_client_mutex);
- list_for_each_entry(client, &i40e_clients, list) {
- /* first check client is registered */
- if (!test_bit(__I40E_CLIENT_REGISTERED, &client->state))
- continue;
+ if (!client || !cdev)
+ return;
- /* Do we also need the LAN VSI to be up, to create instance */
- if (!(client->flags & I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE)) {
- /* check if L2 VSI is up, if not we are not ready */
- if (test_bit(__I40E_DOWN, &pf->vsi[pf->lan_vsi]->state))
- continue;
- } else {
- dev_warn(&pf->pdev->dev, "This client %s is being instantiated at probe\n",
- client->name);
- }
-
- /* Add the client instance to the instance list */
- cdev = i40e_client_add_instance(pf, client, &existing);
- if (!cdev)
- continue;
-
- if (!existing) {
- dev_info(&pf->pdev->dev, "Added instance of Client %s to PF%d bus=0x%02x dev=0x%02x func=0x%02x\n",
- client->name, pf->hw.pf_id,
- pf->hw.bus.bus_id, pf->hw.bus.device,
- pf->hw.bus.func);
- }
-
- mutex_lock(&i40e_client_instance_mutex);
- if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED,
- &cdev->state)) {
- /* Send an Open request to the client */
- if (client->ops && client->ops->open)
- ret = client->ops->open(&cdev->lan_info,
- client);
- if (!ret) {
- set_bit(__I40E_CLIENT_INSTANCE_OPENED,
- &cdev->state);
- } else {
- /* remove client instance */
- i40e_client_del_instance(pf, client);
+ /* Here we handle client opens. If the client is down, but
+ * the netdev is up, then open the client.
+ */
+ if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) {
+ if (!test_bit(__I40E_DOWN, &vsi->state) &&
+ client->ops && client->ops->open) {
+ set_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state);
+ ret = client->ops->open(&cdev->lan_info, client);
+ if (ret) {
+ /* Remove failed client instance */
+ clear_bit(__I40E_CLIENT_INSTANCE_OPENED,
+ &cdev->state);
+ i40e_client_del_instance(pf);
}
}
- mutex_unlock(&i40e_client_instance_mutex);
+ } else {
+ /* Likewise for client close. If the client is up, but the netdev
+ * is down, then close the client.
+ */
+ if (test_bit(__I40E_DOWN, &vsi->state) &&
+ client->ops && client->ops->close) {
+ clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state);
+ client->ops->close(&cdev->lan_info, client, false);
+ i40e_client_release_qvlist(&cdev->lan_info);
+ }
}
- mutex_unlock(&i40e_client_mutex);
}
/**
@@ -566,6 +436,12 @@ int i40e_lan_add_device(struct i40e_pf *pf)
pf->hw.pf_id, pf->hw.bus.bus_id,
pf->hw.bus.device, pf->hw.bus.func);
+ /* If a client has already been registered, we need to add an instance
+ * of it to our new LAN device.
+ */
+ if (registered_client)
+ i40e_client_add_instance(pf);
+
/* Since in some cases register may have happened before a device gets
* added, we can schedule a subtask to go initiate the clients if
* they can be launched at probe time.
@@ -589,6 +465,9 @@ int i40e_lan_del_device(struct i40e_pf *pf)
struct i40e_device *ldev, *tmp;
int ret = -ENODEV;
+ /* First, remove any client instance. */
+ i40e_client_del_instance(pf);
+
mutex_lock(&i40e_device_mutex);
list_for_each_entry_safe(ldev, tmp, &i40e_devices, list) {
if (ldev->pf == pf) {
@@ -601,7 +480,6 @@ int i40e_lan_del_device(struct i40e_pf *pf)
break;
}
}
-
mutex_unlock(&i40e_device_mutex);
return ret;
}
@@ -610,22 +488,24 @@ int i40e_lan_del_device(struct i40e_pf *pf)
* i40e_client_release - release client specific resources
* @client: pointer to the registered client
*
- * Return 0 on success or < 0 on error
**/
-static int i40e_client_release(struct i40e_client *client)
+static void i40e_client_release(struct i40e_client *client)
{
- struct i40e_client_instance *cdev, *tmp;
+ struct i40e_client_instance *cdev;
+ struct i40e_device *ldev;
struct i40e_pf *pf;
- int ret = 0;
- LIST_HEAD(cdevs_tmp);
-
- mutex_lock(&i40e_client_instance_mutex);
- list_for_each_entry_safe(cdev, tmp, &i40e_client_instances, list) {
- if (strncmp(cdev->client->name, client->name,
- I40E_CLIENT_STR_LENGTH))
+ mutex_lock(&i40e_device_mutex);
+ list_for_each_entry(ldev, &i40e_devices, list) {
+ pf = ldev->pf;
+ cdev = pf->cinst;
+ if (!cdev)
continue;
- pf = (struct i40e_pf *)cdev->lan_info.pf;
+
+ while (test_and_set_bit(__I40E_SERVICE_SCHED,
+ &pf->state))
+ usleep_range(500, 1000);
+
if (test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) {
if (client->ops && client->ops->close)
client->ops->close(&cdev->lan_info, client,
@@ -637,18 +517,13 @@ static int i40e_client_release(struct i40e_client *client)
"Client %s instance for PF id %d closed\n",
client->name, pf->hw.pf_id);
}
- /* delete the client instance from the list */
- list_move(&cdev->list, &cdevs_tmp);
+ /* delete the client instance */
+ i40e_client_del_instance(pf);
dev_info(&pf->pdev->dev, "Deleted client instance of Client %s\n",
client->name);
+ clear_bit(__I40E_SERVICE_SCHED, &pf->state);
}
- mutex_unlock(&i40e_client_instance_mutex);
-
- /* free the client device and release its vsi */
- list_for_each_entry_safe(cdev, tmp, &cdevs_tmp, list) {
- kfree(cdev);
- }
- return ret;
+ mutex_unlock(&i40e_device_mutex);
}
/**
@@ -664,6 +539,7 @@ static void i40e_client_prepare(struct i40e_client *client)
mutex_lock(&i40e_device_mutex);
list_for_each_entry(ldev, &i40e_devices, list) {
pf = ldev->pf;
+ i40e_client_add_instance(pf);
/* Start the client subtask */
pf->flags |= I40E_FLAG_SERVICE_CLIENT_REQUESTED;
i40e_service_event_schedule(pf);
@@ -792,8 +668,8 @@ static void i40e_client_request_reset(struct i40e_info *ldev,
break;
default:
dev_warn(&pf->pdev->dev,
- "Client %s instance for PF id %d request an unsupported reset: %d.\n",
- client->name, pf->hw.pf_id, reset_level);
+ "Client for PF id %d requested an unsupported reset: %d.\n",
+ pf->hw.pf_id, reset_level);
break;
}
@@ -852,8 +728,8 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev,
} else {
update = false;
dev_warn(&pf->pdev->dev,
- "Client %s instance for PF id %d request an unsupported Config: %x.\n",
- client->name, pf->hw.pf_id, flag);
+ "Client for PF id %d request an unsupported Config: %x.\n",
+ pf->hw.pf_id, flag);
}
if (update) {
@@ -878,7 +754,6 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev,
int i40e_register_client(struct i40e_client *client)
{
int ret = 0;
- enum i40e_vsi_type vsi_type;
if (!client) {
ret = -EIO;
@@ -891,11 +766,9 @@ int i40e_register_client(struct i40e_client *client)
goto out;
}
- mutex_lock(&i40e_client_mutex);
- if (i40e_client_is_registered(client)) {
+ if (registered_client) {
pr_info("i40e: Client %s has already been registered!\n",
client->name);
- mutex_unlock(&i40e_client_mutex);
ret = -EEXIST;
goto out;
}
@@ -908,22 +781,11 @@ int i40e_register_client(struct i40e_client *client)
client->version.major, client->version.minor,
client->version.build,
i40e_client_interface_version_str);
- mutex_unlock(&i40e_client_mutex);
ret = -EIO;
goto out;
}
- vsi_type = i40e_client_type_to_vsi_type(client->type);
- if (vsi_type == I40E_VSI_TYPE_UNKNOWN) {
- pr_info("i40e: Failed to register client %s due to unknown client type %d\n",
- client->name, client->type);
- mutex_unlock(&i40e_client_mutex);
- ret = -EIO;
- goto out;
- }
- list_add(&client->list, &i40e_clients);
- set_bit(__I40E_CLIENT_REGISTERED, &client->state);
- mutex_unlock(&i40e_client_mutex);
+ registered_client = client;
i40e_client_prepare(client);
@@ -943,29 +805,21 @@ int i40e_unregister_client(struct i40e_client *client)
{
int ret = 0;
- /* When a unregister request comes through we would have to send
- * a close for each of the client instances that were opened.
- * client_release function is called to handle this.
- */
- mutex_lock(&i40e_client_mutex);
- if (!client || i40e_client_release(client)) {
- ret = -EIO;
- goto out;
- }
-
- /* TODO: check if device is in reset, or if that matters? */
- if (!i40e_client_is_registered(client)) {
+ if (registered_client != client) {
pr_info("i40e: Client %s has not been registered\n",
client->name);
ret = -ENODEV;
goto out;
}
- clear_bit(__I40E_CLIENT_REGISTERED, &client->state);
- list_del(&client->list);
- pr_info("i40e: Unregistered client %s with return code %d\n",
- client->name, ret);
+ registered_client = NULL;
+ /* When a unregister request comes through we would have to send
+ * a close for each of the client instances that were opened.
+ * client_release function is called to handle this.
+ */
+ i40e_client_release(client);
+
+ pr_info("i40e: Unregistered client %s\n", client->name);
out:
- mutex_unlock(&i40e_client_mutex);
return ret;
}
EXPORT_SYMBOL(i40e_unregister_client);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.h b/drivers/net/ethernet/intel/i40e/i40e_client.h
index 528bd79..15b21a5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_client.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_client.h
@@ -57,11 +57,6 @@ enum i40e_client_instance_state {
__I40E_CLIENT_INSTANCE_OPENED,
};
-enum i40e_client_type {
- I40E_CLIENT_IWARP,
- I40E_CLIENT_VMDQ2
-};
-
struct i40e_ops;
struct i40e_client;
@@ -214,7 +209,8 @@ struct i40e_client {
u32 flags;
#define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE BIT(0)
#define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS BIT(2)
- enum i40e_client_type type;
+ u8 type;
+#define I40E_CLIENT_IWARP 0
const struct i40e_client_ops *ops; /* client ops provided by the client */
};
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index ece57d6..f9db95a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1088,33 +1088,6 @@ void i40e_pre_tx_queue_cfg(struct i40e_hw *hw, u32 queue, bool enable)
wr32(hw, I40E_GLLAN_TXPRE_QDIS(reg_block), reg_val);
}
-#ifdef I40E_FCOE
-
-/**
- * i40e_get_san_mac_addr - get SAN MAC address
- * @hw: pointer to the HW structure
- * @mac_addr: pointer to SAN MAC address
- *
- * Reads the adapter's SAN MAC address from NVM
- **/
-i40e_status i40e_get_san_mac_addr(struct i40e_hw *hw, u8 *mac_addr)
-{
- struct i40e_aqc_mac_address_read_data addrs;
- i40e_status status;
- u16 flags = 0;
-
- status = i40e_aq_mac_address_read(hw, &flags, &addrs, NULL);
- if (status)
- return status;
-
- if (flags & I40E_AQC_SAN_ADDR_VALID)
- ether_addr_copy(mac_addr, addrs.pf_san_mac);
- else
- status = I40E_ERR_INVALID_MAC_ADDR;
-
- return status;
-}
-#endif
/**
* i40e_read_pba_string - Reads part number string from EEPROM
@@ -4990,7 +4963,9 @@ u32 i40e_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr)
int retry = 5;
u32 val = 0;
- use_register = (hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver < 5);
+ use_register = (((hw->aq.api_maj_ver == 1) &&
+ (hw->aq.api_min_ver < 5)) ||
+ (hw->mac.type == I40E_MAC_X722));
if (!use_register) {
do_retry:
status = i40e_aq_rx_ctl_read_register(hw, reg_addr, &val, NULL);
@@ -5049,7 +5024,9 @@ void i40e_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val)
bool use_register;
int retry = 5;
- use_register = (hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver < 5);
+ use_register = (((hw->aq.api_maj_ver == 1) &&
+ (hw->aq.api_min_ver < 5)) ||
+ (hw->mac.type == I40E_MAC_X722));
if (!use_register) {
do_retry:
status = i40e_aq_rx_ctl_write_register(hw, reg_addr,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index 267ad25..c5f68cc 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -484,25 +484,6 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
vsi->bw_ets_limit_credits[i],
vsi->bw_ets_max_quanta[i]);
}
-#ifdef I40E_FCOE
- if (vsi->type == I40E_VSI_FCOE) {
- dev_info(&pf->pdev->dev,
- " fcoe_stats: rx_packets = %llu, rx_dwords = %llu, rx_dropped = %llu\n",
- vsi->fcoe_stats.rx_fcoe_packets,
- vsi->fcoe_stats.rx_fcoe_dwords,
- vsi->fcoe_stats.rx_fcoe_dropped);
- dev_info(&pf->pdev->dev,
- " fcoe_stats: tx_packets = %llu, tx_dwords = %llu\n",
- vsi->fcoe_stats.tx_fcoe_packets,
- vsi->fcoe_stats.tx_fcoe_dwords);
- dev_info(&pf->pdev->dev,
- " fcoe_stats: bad_crc = %llu, last_error = %llu\n",
- vsi->fcoe_stats.fcoe_bad_fccrc,
- vsi->fcoe_stats.fcoe_last_error);
- dev_info(&pf->pdev->dev, " fcoe_stats: ddp_count = %llu\n",
- vsi->fcoe_stats.fcoe_ddp_count);
- }
-#endif
}
/**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index a22e262..10325b5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -89,7 +89,6 @@ static const struct i40e_stats i40e_gstrings_misc_stats[] = {
I40E_VSI_STAT("rx_unknown_protocol", eth_stats.rx_unknown_protocol),
I40E_VSI_STAT("tx_linearize", tx_linearize),
I40E_VSI_STAT("tx_force_wb", tx_force_wb),
- I40E_VSI_STAT("tx_lost_interrupt", tx_lost_interrupt),
I40E_VSI_STAT("rx_alloc_fail", rx_buf_failed),
I40E_VSI_STAT("rx_pg_alloc_fail", rx_page_failed),
};
@@ -162,19 +161,6 @@ static const struct i40e_stats i40e_gstrings_stats[] = {
I40E_PF_STAT("rx_lpi_count", stats.rx_lpi_count),
};
-#ifdef I40E_FCOE
-static const struct i40e_stats i40e_gstrings_fcoe_stats[] = {
- I40E_VSI_STAT("fcoe_bad_fccrc", fcoe_stats.fcoe_bad_fccrc),
- I40E_VSI_STAT("rx_fcoe_dropped", fcoe_stats.rx_fcoe_dropped),
- I40E_VSI_STAT("rx_fcoe_packets", fcoe_stats.rx_fcoe_packets),
- I40E_VSI_STAT("rx_fcoe_dwords", fcoe_stats.rx_fcoe_dwords),
- I40E_VSI_STAT("fcoe_ddp_count", fcoe_stats.fcoe_ddp_count),
- I40E_VSI_STAT("fcoe_last_error", fcoe_stats.fcoe_last_error),
- I40E_VSI_STAT("tx_fcoe_packets", fcoe_stats.tx_fcoe_packets),
- I40E_VSI_STAT("tx_fcoe_dwords", fcoe_stats.tx_fcoe_dwords),
-};
-
-#endif /* I40E_FCOE */
#define I40E_QUEUE_STATS_LEN(n) \
(((struct i40e_netdev_priv *)netdev_priv((n)))->vsi->num_queue_pairs \
* 2 /* Tx and Rx together */ \
@@ -182,17 +168,9 @@ static const struct i40e_stats i40e_gstrings_fcoe_stats[] = {
#define I40E_GLOBAL_STATS_LEN ARRAY_SIZE(i40e_gstrings_stats)
#define I40E_NETDEV_STATS_LEN ARRAY_SIZE(i40e_gstrings_net_stats)
#define I40E_MISC_STATS_LEN ARRAY_SIZE(i40e_gstrings_misc_stats)
-#ifdef I40E_FCOE
-#define I40E_FCOE_STATS_LEN ARRAY_SIZE(i40e_gstrings_fcoe_stats)
-#define I40E_VSI_STATS_LEN(n) (I40E_NETDEV_STATS_LEN + \
- I40E_FCOE_STATS_LEN + \
- I40E_MISC_STATS_LEN + \
- I40E_QUEUE_STATS_LEN((n)))
-#else
#define I40E_VSI_STATS_LEN(n) (I40E_NETDEV_STATS_LEN + \
I40E_MISC_STATS_LEN + \
I40E_QUEUE_STATS_LEN((n)))
-#endif /* I40E_FCOE */
#define I40E_PFC_STATS_LEN ( \
(FIELD_SIZEOF(struct i40e_pf, stats.priority_xoff_rx) + \
FIELD_SIZEOF(struct i40e_pf, stats.priority_xon_rx) + \
@@ -228,22 +206,37 @@ static const char i40e_gstrings_test[][ETH_GSTRING_LEN] = {
#define I40E_TEST_LEN (sizeof(i40e_gstrings_test) / ETH_GSTRING_LEN)
-static const char i40e_priv_flags_strings[][ETH_GSTRING_LEN] = {
- "MFP",
- "LinkPolling",
- "flow-director-atr",
- "veb-stats",
- "hw-atr-eviction",
+struct i40e_priv_flags {
+ char flag_string[ETH_GSTRING_LEN];
+ u64 flag;
+ bool read_only;
};
-#define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_priv_flags_strings)
+#define I40E_PRIV_FLAG(_name, _flag, _read_only) { \
+ .flag_string = _name, \
+ .flag = _flag, \
+ .read_only = _read_only, \
+}
+
+static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = {
+ /* NOTE: MFP setting cannot be changed */
+ I40E_PRIV_FLAG("MFP", I40E_FLAG_MFP_ENABLED, 1),
+ I40E_PRIV_FLAG("LinkPolling", I40E_FLAG_LINK_POLLING_ENABLED, 0),
+ I40E_PRIV_FLAG("flow-director-atr", I40E_FLAG_FD_ATR_ENABLED, 0),
+ I40E_PRIV_FLAG("veb-stats", I40E_FLAG_VEB_STATS_ENABLED, 0),
+ I40E_PRIV_FLAG("hw-atr-eviction", I40E_FLAG_HW_ATR_EVICT_CAPABLE, 0),
+ I40E_PRIV_FLAG("legacy-rx", I40E_FLAG_LEGACY_RX, 0),
+};
+
+#define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gstrings_priv_flags)
/* Private flags with a global effect, restricted to PF 0 */
-static const char i40e_gl_priv_flags_strings[][ETH_GSTRING_LEN] = {
- "vf-true-promisc-support",
+static const struct i40e_priv_flags i40e_gl_gstrings_priv_flags[] = {
+ I40E_PRIV_FLAG("vf-true-promisc-support",
+ I40E_FLAG_TRUE_PROMISC_SUPPORT, 0),
};
-#define I40E_GL_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gl_priv_flags_strings)
+#define I40E_GL_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gl_gstrings_priv_flags)
/**
* i40e_partition_setting_complaint - generic complaint for MFP restriction
@@ -387,7 +380,7 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported,
*
**/
static void i40e_get_settings_link_up(struct i40e_hw *hw,
- struct ethtool_cmd *ecmd,
+ struct ethtool_link_ksettings *cmd,
struct net_device *netdev,
struct i40e_pf *pf)
{
@@ -395,90 +388,96 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
u32 link_speed = hw_link_info->link_speed;
u32 e_advertising = 0x0;
u32 e_supported = 0x0;
+ u32 supported, advertising;
+
+ ethtool_convert_link_mode_to_legacy_u32(&supported,
+ cmd->link_modes.supported);
+ ethtool_convert_link_mode_to_legacy_u32(&advertising,
+ cmd->link_modes.advertising);
/* Initialize supported and advertised settings based on phy settings */
switch (hw_link_info->phy_type) {
case I40E_PHY_TYPE_40GBASE_CR4:
case I40E_PHY_TYPE_40GBASE_CR4_CU:
- ecmd->supported = SUPPORTED_Autoneg |
- SUPPORTED_40000baseCR4_Full;
- ecmd->advertising = ADVERTISED_Autoneg |
- ADVERTISED_40000baseCR4_Full;
+ supported = SUPPORTED_Autoneg |
+ SUPPORTED_40000baseCR4_Full;
+ advertising = ADVERTISED_Autoneg |
+ ADVERTISED_40000baseCR4_Full;
break;
case I40E_PHY_TYPE_XLAUI:
case I40E_PHY_TYPE_XLPPI:
case I40E_PHY_TYPE_40GBASE_AOC:
- ecmd->supported = SUPPORTED_40000baseCR4_Full;
+ supported = SUPPORTED_40000baseCR4_Full;
break;
case I40E_PHY_TYPE_40GBASE_SR4:
- ecmd->supported = SUPPORTED_40000baseSR4_Full;
+ supported = SUPPORTED_40000baseSR4_Full;
break;
case I40E_PHY_TYPE_40GBASE_LR4:
- ecmd->supported = SUPPORTED_40000baseLR4_Full;
+ supported = SUPPORTED_40000baseLR4_Full;
break;
case I40E_PHY_TYPE_10GBASE_SR:
case I40E_PHY_TYPE_10GBASE_LR:
case I40E_PHY_TYPE_1000BASE_SX:
case I40E_PHY_TYPE_1000BASE_LX:
- ecmd->supported = SUPPORTED_10000baseT_Full;
+ supported = SUPPORTED_10000baseT_Full;
if (hw_link_info->module_type[2] &
I40E_MODULE_TYPE_1000BASE_SX ||
hw_link_info->module_type[2] &
I40E_MODULE_TYPE_1000BASE_LX) {
- ecmd->supported |= SUPPORTED_1000baseT_Full;
+ supported |= SUPPORTED_1000baseT_Full;
if (hw_link_info->requested_speeds &
I40E_LINK_SPEED_1GB)
- ecmd->advertising |= ADVERTISED_1000baseT_Full;
+ advertising |= ADVERTISED_1000baseT_Full;
}
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
- ecmd->advertising |= ADVERTISED_10000baseT_Full;
+ advertising |= ADVERTISED_10000baseT_Full;
break;
case I40E_PHY_TYPE_10GBASE_T:
case I40E_PHY_TYPE_1000BASE_T:
case I40E_PHY_TYPE_100BASE_TX:
- ecmd->supported = SUPPORTED_Autoneg |
- SUPPORTED_10000baseT_Full |
- SUPPORTED_1000baseT_Full |
- SUPPORTED_100baseT_Full;
- ecmd->advertising = ADVERTISED_Autoneg;
+ supported = SUPPORTED_Autoneg |
+ SUPPORTED_10000baseT_Full |
+ SUPPORTED_1000baseT_Full |
+ SUPPORTED_100baseT_Full;
+ advertising = ADVERTISED_Autoneg;
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
- ecmd->advertising |= ADVERTISED_10000baseT_Full;
+ advertising |= ADVERTISED_10000baseT_Full;
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
- ecmd->advertising |= ADVERTISED_1000baseT_Full;
+ advertising |= ADVERTISED_1000baseT_Full;
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB)
- ecmd->advertising |= ADVERTISED_100baseT_Full;
+ advertising |= ADVERTISED_100baseT_Full;
break;
case I40E_PHY_TYPE_1000BASE_T_OPTICAL:
- ecmd->supported = SUPPORTED_Autoneg |
- SUPPORTED_1000baseT_Full;
- ecmd->advertising = ADVERTISED_Autoneg |
- ADVERTISED_1000baseT_Full;
+ supported = SUPPORTED_Autoneg |
+ SUPPORTED_1000baseT_Full;
+ advertising = ADVERTISED_Autoneg |
+ ADVERTISED_1000baseT_Full;
break;
case I40E_PHY_TYPE_10GBASE_CR1_CU:
case I40E_PHY_TYPE_10GBASE_CR1:
- ecmd->supported = SUPPORTED_Autoneg |
- SUPPORTED_10000baseT_Full;
- ecmd->advertising = ADVERTISED_Autoneg |
- ADVERTISED_10000baseT_Full;
+ supported = SUPPORTED_Autoneg |
+ SUPPORTED_10000baseT_Full;
+ advertising = ADVERTISED_Autoneg |
+ ADVERTISED_10000baseT_Full;
break;
case I40E_PHY_TYPE_XAUI:
case I40E_PHY_TYPE_XFI:
case I40E_PHY_TYPE_SFI:
case I40E_PHY_TYPE_10GBASE_SFPP_CU:
case I40E_PHY_TYPE_10GBASE_AOC:
- ecmd->supported = SUPPORTED_10000baseT_Full;
- ecmd->advertising = SUPPORTED_10000baseT_Full;
+ supported = SUPPORTED_10000baseT_Full;
+ advertising = SUPPORTED_10000baseT_Full;
break;
case I40E_PHY_TYPE_SGMII:
- ecmd->supported = SUPPORTED_Autoneg |
- SUPPORTED_1000baseT_Full;
+ supported = SUPPORTED_Autoneg |
+ SUPPORTED_1000baseT_Full;
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
- ecmd->advertising |= ADVERTISED_1000baseT_Full;
+ advertising |= ADVERTISED_1000baseT_Full;
if (pf->flags & I40E_FLAG_100M_SGMII_CAPABLE) {
- ecmd->supported |= SUPPORTED_100baseT_Full;
+ supported |= SUPPORTED_100baseT_Full;
if (hw_link_info->requested_speeds &
I40E_LINK_SPEED_100MB)
- ecmd->advertising |= ADVERTISED_100baseT_Full;
+ advertising |= ADVERTISED_100baseT_Full;
}
break;
case I40E_PHY_TYPE_40GBASE_KR4:
@@ -486,25 +485,25 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
case I40E_PHY_TYPE_10GBASE_KR:
case I40E_PHY_TYPE_10GBASE_KX4:
case I40E_PHY_TYPE_1000BASE_KX:
- ecmd->supported |= SUPPORTED_40000baseKR4_Full |
- SUPPORTED_20000baseKR2_Full |
- SUPPORTED_10000baseKR_Full |
- SUPPORTED_10000baseKX4_Full |
- SUPPORTED_1000baseKX_Full |
- SUPPORTED_Autoneg;
- ecmd->advertising |= ADVERTISED_40000baseKR4_Full |
- ADVERTISED_20000baseKR2_Full |
- ADVERTISED_10000baseKR_Full |
- ADVERTISED_10000baseKX4_Full |
- ADVERTISED_1000baseKX_Full |
- ADVERTISED_Autoneg;
+ supported |= SUPPORTED_40000baseKR4_Full |
+ SUPPORTED_20000baseKR2_Full |
+ SUPPORTED_10000baseKR_Full |
+ SUPPORTED_10000baseKX4_Full |
+ SUPPORTED_1000baseKX_Full |
+ SUPPORTED_Autoneg;
+ advertising |= ADVERTISED_40000baseKR4_Full |
+ ADVERTISED_20000baseKR2_Full |
+ ADVERTISED_10000baseKR_Full |
+ ADVERTISED_10000baseKX4_Full |
+ ADVERTISED_1000baseKX_Full |
+ ADVERTISED_Autoneg;
break;
case I40E_PHY_TYPE_25GBASE_KR:
case I40E_PHY_TYPE_25GBASE_CR:
case I40E_PHY_TYPE_25GBASE_SR:
case I40E_PHY_TYPE_25GBASE_LR:
- ecmd->supported = SUPPORTED_Autoneg;
- ecmd->advertising = ADVERTISED_Autoneg;
+ supported = SUPPORTED_Autoneg;
+ advertising = ADVERTISED_Autoneg;
/* TODO: add speeds when ethtool is ready to support*/
break;
default:
@@ -520,38 +519,43 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
i40e_phy_type_to_ethtool(pf, &e_supported,
&e_advertising);
- ecmd->supported = ecmd->supported & e_supported;
- ecmd->advertising = ecmd->advertising & e_advertising;
+ supported = supported & e_supported;
+ advertising = advertising & e_advertising;
/* Set speed and duplex */
switch (link_speed) {
case I40E_LINK_SPEED_40GB:
- ethtool_cmd_speed_set(ecmd, SPEED_40000);
+ cmd->base.speed = SPEED_40000;
break;
case I40E_LINK_SPEED_25GB:
#ifdef SPEED_25000
- ethtool_cmd_speed_set(ecmd, SPEED_25000);
+ cmd->base.speed = SPEED_25000;
#else
netdev_info(netdev,
"Speed is 25G, display not supported by this version of ethtool.\n");
#endif
break;
case I40E_LINK_SPEED_20GB:
- ethtool_cmd_speed_set(ecmd, SPEED_20000);
+ cmd->base.speed = SPEED_20000;
break;
case I40E_LINK_SPEED_10GB:
- ethtool_cmd_speed_set(ecmd, SPEED_10000);
+ cmd->base.speed = SPEED_10000;
break;
case I40E_LINK_SPEED_1GB:
- ethtool_cmd_speed_set(ecmd, SPEED_1000);
+ cmd->base.speed = SPEED_1000;
break;
case I40E_LINK_SPEED_100MB:
- ethtool_cmd_speed_set(ecmd, SPEED_100);
+ cmd->base.speed = SPEED_100;
break;
default:
break;
}
- ecmd->duplex = DUPLEX_FULL;
+ cmd->base.duplex = DUPLEX_FULL;
+
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ supported);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+ advertising);
}
/**
@@ -562,18 +566,24 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
* Reports link settings that can be determined when link is down
**/
static void i40e_get_settings_link_down(struct i40e_hw *hw,
- struct ethtool_cmd *ecmd,
+ struct ethtool_link_ksettings *cmd,
struct i40e_pf *pf)
{
+ u32 supported, advertising;
+
/* link is down and the driver needs to fall back on
* supported phy types to figure out what info to display
*/
- i40e_phy_type_to_ethtool(pf, &ecmd->supported,
- &ecmd->advertising);
+ i40e_phy_type_to_ethtool(pf, &supported, &advertising);
+
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ supported);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+ advertising);
/* With no link speed and duplex are unknown */
- ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
- ecmd->duplex = DUPLEX_UNKNOWN;
+ cmd->base.speed = SPEED_UNKNOWN;
+ cmd->base.duplex = DUPLEX_UNKNOWN;
}
/**
@@ -583,74 +593,85 @@ static void i40e_get_settings_link_down(struct i40e_hw *hw,
*
* Reports speed/duplex settings based on media_type
**/
-static int i40e_get_settings(struct net_device *netdev,
- struct ethtool_cmd *ecmd)
+static int i40e_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *cmd)
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_pf *pf = np->vsi->back;
struct i40e_hw *hw = &pf->hw;
struct i40e_link_status *hw_link_info = &hw->phy.link_info;
bool link_up = hw_link_info->link_info & I40E_AQ_LINK_UP;
+ u32 advertising;
if (link_up)
- i40e_get_settings_link_up(hw, ecmd, netdev, pf);
+ i40e_get_settings_link_up(hw, cmd, netdev, pf);
else
- i40e_get_settings_link_down(hw, ecmd, pf);
+ i40e_get_settings_link_down(hw, cmd, pf);
/* Now set the settings that don't rely on link being up/down */
/* Set autoneg settings */
- ecmd->autoneg = ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ?
+ cmd->base.autoneg = ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ?
AUTONEG_ENABLE : AUTONEG_DISABLE);
switch (hw->phy.media_type) {
case I40E_MEDIA_TYPE_BACKPLANE:
- ecmd->supported |= SUPPORTED_Autoneg |
- SUPPORTED_Backplane;
- ecmd->advertising |= ADVERTISED_Autoneg |
- ADVERTISED_Backplane;
- ecmd->port = PORT_NONE;
+ ethtool_link_ksettings_add_link_mode(cmd, supported,
+ Autoneg);
+ ethtool_link_ksettings_add_link_mode(cmd, supported,
+ Backplane);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising,
+ Autoneg);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising,
+ Backplane);
+ cmd->base.port = PORT_NONE;
break;
case I40E_MEDIA_TYPE_BASET:
- ecmd->supported |= SUPPORTED_TP;
- ecmd->advertising |= ADVERTISED_TP;
- ecmd->port = PORT_TP;
+ ethtool_link_ksettings_add_link_mode(cmd, supported, TP);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising, TP);
+ cmd->base.port = PORT_TP;
break;
case I40E_MEDIA_TYPE_DA:
case I40E_MEDIA_TYPE_CX4:
- ecmd->supported |= SUPPORTED_FIBRE;
- ecmd->advertising |= ADVERTISED_FIBRE;
- ecmd->port = PORT_DA;
+ ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE);
+ cmd->base.port = PORT_DA;
break;
case I40E_MEDIA_TYPE_FIBER:
- ecmd->supported |= SUPPORTED_FIBRE;
- ecmd->port = PORT_FIBRE;
+ ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
+ cmd->base.port = PORT_FIBRE;
break;
case I40E_MEDIA_TYPE_UNKNOWN:
default:
- ecmd->port = PORT_OTHER;
+ cmd->base.port = PORT_OTHER;
break;
}
- /* Set transceiver */
- ecmd->transceiver = XCVR_EXTERNAL;
-
/* Set flow control settings */
- ecmd->supported |= SUPPORTED_Pause;
+ ethtool_link_ksettings_add_link_mode(cmd, supported, Pause);
switch (hw->fc.requested_mode) {
case I40E_FC_FULL:
- ecmd->advertising |= ADVERTISED_Pause;
+ ethtool_link_ksettings_add_link_mode(cmd, advertising,
+ Pause);
break;
case I40E_FC_TX_PAUSE:
- ecmd->advertising |= ADVERTISED_Asym_Pause;
+ ethtool_link_ksettings_add_link_mode(cmd, advertising,
+ Asym_Pause);
break;
case I40E_FC_RX_PAUSE:
- ecmd->advertising |= (ADVERTISED_Pause |
- ADVERTISED_Asym_Pause);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising,
+ Pause);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising,
+ Asym_Pause);
break;
default:
- ecmd->advertising &= ~(ADVERTISED_Pause |
- ADVERTISED_Asym_Pause);
+ ethtool_convert_link_mode_to_legacy_u32(
+ &advertising, cmd->link_modes.advertising);
+
+ advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause);
+
+ ethtool_convert_legacy_u32_to_link_mode(
+ cmd->link_modes.advertising, advertising);
break;
}
@@ -664,8 +685,8 @@ static int i40e_get_settings(struct net_device *netdev,
*
* Set speed/duplex per media_types advertised/forced
**/
-static int i40e_set_settings(struct net_device *netdev,
- struct ethtool_cmd *ecmd)
+static int i40e_set_link_ksettings(struct net_device *netdev,
+ const struct ethtool_link_ksettings *cmd)
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_aq_get_phy_abilities_resp abilities;
@@ -673,12 +694,14 @@ static int i40e_set_settings(struct net_device *netdev,
struct i40e_pf *pf = np->vsi->back;
struct i40e_vsi *vsi = np->vsi;
struct i40e_hw *hw = &pf->hw;
- struct ethtool_cmd safe_ecmd;
+ struct ethtool_link_ksettings safe_cmd;
+ struct ethtool_link_ksettings copy_cmd;
i40e_status status = 0;
bool change = false;
int err = 0;
- u8 autoneg;
+ u32 autoneg;
u32 advertise;
+ u32 tmp;
/* Changing port settings is not supported if this isn't the
* port's controlling PF
@@ -706,23 +729,31 @@ static int i40e_set_settings(struct net_device *netdev,
return -EOPNOTSUPP;
}
- /* get our own copy of the bits to check against */
- memset(&safe_ecmd, 0, sizeof(struct ethtool_cmd));
- i40e_get_settings(netdev, &safe_ecmd);
+ /* copy the cmd to copy_cmd to avoid modifying the origin */
+ memcpy(©_cmd, cmd, sizeof(struct ethtool_link_ksettings));
- /* save autoneg and speed out of ecmd */
- autoneg = ecmd->autoneg;
- advertise = ecmd->advertising;
+ /* get our own copy of the bits to check against */
+ memset(&safe_cmd, 0, sizeof(struct ethtool_link_ksettings));
+ i40e_get_link_ksettings(netdev, &safe_cmd);
+
+ /* save autoneg and speed out of cmd */
+ autoneg = cmd->base.autoneg;
+ ethtool_convert_link_mode_to_legacy_u32(&advertise,
+ cmd->link_modes.advertising);
/* set autoneg and speed back to what they currently are */
- ecmd->autoneg = safe_ecmd.autoneg;
- ecmd->advertising = safe_ecmd.advertising;
+ copy_cmd.base.autoneg = safe_cmd.base.autoneg;
+ ethtool_convert_link_mode_to_legacy_u32(
+ &tmp, safe_cmd.link_modes.advertising);
+ ethtool_convert_legacy_u32_to_link_mode(
+ copy_cmd.link_modes.advertising, tmp);
- ecmd->cmd = safe_ecmd.cmd;
- /* If ecmd and safe_ecmd are not the same now, then they are
+ copy_cmd.base.cmd = safe_cmd.base.cmd;
+
+ /* If copy_cmd and safe_cmd are not the same now, then they are
* trying to set something that we do not support
*/
- if (memcmp(ecmd, &safe_ecmd, sizeof(struct ethtool_cmd)))
+ if (memcmp(©_cmd, &safe_cmd, sizeof(struct ethtool_link_ksettings)))
return -EOPNOTSUPP;
while (test_bit(__I40E_CONFIG_BUSY, &vsi->state))
@@ -745,7 +776,8 @@ static int i40e_set_settings(struct net_device *netdev,
/* If autoneg was not already enabled */
if (!(hw->phy.link_info.an_info & I40E_AQ_AN_COMPLETED)) {
/* If autoneg is not supported, return error */
- if (!(safe_ecmd.supported & SUPPORTED_Autoneg)) {
+ if (!ethtool_link_ksettings_test_link_mode(
+ &safe_cmd, supported, Autoneg)) {
netdev_info(netdev, "Autoneg not supported on this phy\n");
return -EINVAL;
}
@@ -760,7 +792,8 @@ static int i40e_set_settings(struct net_device *netdev,
/* If autoneg is supported 10GBASE_T is the only PHY
* that can disable it, so otherwise return error
*/
- if (safe_ecmd.supported & SUPPORTED_Autoneg &&
+ if (ethtool_link_ksettings_test_link_mode(
+ &safe_cmd, supported, Autoneg) &&
hw->phy.link_info.phy_type !=
I40E_PHY_TYPE_10GBASE_T) {
netdev_info(netdev, "Autoneg cannot be disabled on this phy\n");
@@ -773,7 +806,9 @@ static int i40e_set_settings(struct net_device *netdev,
}
}
- if (advertise & ~safe_ecmd.supported)
+ ethtool_convert_link_mode_to_legacy_u32(&tmp,
+ safe_cmd.link_modes.supported);
+ if (advertise & ~tmp)
return -EINVAL;
if (advertise & ADVERTISED_100baseT_Full)
@@ -1165,6 +1200,11 @@ static int i40e_get_eeprom_len(struct net_device *netdev)
struct i40e_hw *hw = &np->vsi->back->hw;
u32 val;
+#define X722_EEPROM_SCOPE_LIMIT 0x5B9FFF
+ if (hw->mac.type == I40E_MAC_X722) {
+ val = X722_EEPROM_SCOPE_LIMIT + 1;
+ return val;
+ }
val = (rd32(hw, I40E_GLPCI_LBARCTRL)
& I40E_GLPCI_LBARCTRL_FL_SIZE_MASK)
>> I40E_GLPCI_LBARCTRL_FL_SIZE_SHIFT;
@@ -1483,13 +1523,6 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
data[i++] = (i40e_gstrings_misc_stats[j].sizeof_stat ==
sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
}
-#ifdef I40E_FCOE
- for (j = 0; j < I40E_FCOE_STATS_LEN; j++) {
- p = (char *)vsi + i40e_gstrings_fcoe_stats[j].stat_offset;
- data[i++] = (i40e_gstrings_fcoe_stats[j].sizeof_stat ==
- sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
- }
-#endif
rcu_read_lock();
for (j = 0; j < vsi->num_queue_pairs; j++) {
tx_ring = ACCESS_ONCE(vsi->tx_rings[j]);
@@ -1577,13 +1610,6 @@ static void i40e_get_strings(struct net_device *netdev, u32 stringset,
i40e_gstrings_misc_stats[i].stat_string);
p += ETH_GSTRING_LEN;
}
-#ifdef I40E_FCOE
- for (i = 0; i < I40E_FCOE_STATS_LEN; i++) {
- snprintf(p, ETH_GSTRING_LEN, "%s",
- i40e_gstrings_fcoe_stats[i].stat_string);
- p += ETH_GSTRING_LEN;
- }
-#endif
for (i = 0; i < vsi->num_queue_pairs; i++) {
snprintf(p, ETH_GSTRING_LEN, "tx-%d.tx_packets", i);
p += ETH_GSTRING_LEN;
@@ -1648,12 +1674,18 @@ static void i40e_get_strings(struct net_device *netdev, u32 stringset,
/* BUG_ON(p - data != I40E_STATS_LEN * ETH_GSTRING_LEN); */
break;
case ETH_SS_PRIV_FLAGS:
- memcpy(data, i40e_priv_flags_strings,
- I40E_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN);
- data += I40E_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN;
- if (pf->hw.pf_id == 0)
- memcpy(data, i40e_gl_priv_flags_strings,
- I40E_GL_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN);
+ for (i = 0; i < I40E_PRIV_FLAGS_STR_LEN; i++) {
+ snprintf(p, ETH_GSTRING_LEN, "%s",
+ i40e_gstrings_priv_flags[i].flag_string);
+ p += ETH_GSTRING_LEN;
+ }
+ if (pf->hw.pf_id != 0)
+ break;
+ for (i = 0; i < I40E_GL_PRIV_FLAGS_STR_LEN; i++) {
+ snprintf(p, ETH_GSTRING_LEN, "%s",
+ i40e_gl_gstrings_priv_flags[i].flag_string);
+ p += ETH_GSTRING_LEN;
+ }
break;
default:
break;
@@ -1819,7 +1851,7 @@ static void i40e_diag_test(struct net_device *netdev,
* link then the following link test would have
* to be moved to before the reset
*/
- i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED));
+ i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED), true);
if (i40e_link_test(netdev, &data[I40E_ETH_TEST_LINK]))
eth_test->flags |= ETH_TEST_FL_FAILED;
@@ -1835,7 +1867,7 @@ static void i40e_diag_test(struct net_device *netdev,
eth_test->flags |= ETH_TEST_FL_FAILED;
clear_bit(__I40E_TESTING, &pf->state);
- i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED));
+ i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED), true);
if (if_running)
i40e_open(netdev);
@@ -2285,6 +2317,102 @@ static int i40e_get_rss_hash_opts(struct i40e_pf *pf, struct ethtool_rxnfc *cmd)
}
/**
+ * i40e_check_mask - Check whether a mask field is set
+ * @mask: the full mask value
+ * @field; mask of the field to check
+ *
+ * If the given mask is fully set, return positive value. If the mask for the
+ * field is fully unset, return zero. Otherwise return a negative error code.
+ **/
+static int i40e_check_mask(u64 mask, u64 field)
+{
+ u64 value = mask & field;
+
+ if (value == field)
+ return 1;
+ else if (!value)
+ return 0;
+ else
+ return -1;
+}
+
+/**
+ * i40e_parse_rx_flow_user_data - Deconstruct user-defined data
+ * @fsp: pointer to rx flow specification
+ * @data: pointer to userdef data structure for storage
+ *
+ * Read the user-defined data and deconstruct the value into a structure. No
+ * other code should read the user-defined data, so as to ensure that every
+ * place consistently reads the value correctly.
+ *
+ * The user-defined field is a 64bit Big Endian format value, which we
+ * deconstruct by reading bits or bit fields from it. Single bit flags shall
+ * be defined starting from the highest bits, while small bit field values
+ * shall be defined starting from the lowest bits.
+ *
+ * Returns 0 if the data is valid, and non-zero if the userdef data is invalid
+ * and the filter should be rejected. The data structure will always be
+ * modified even if FLOW_EXT is not set.
+ *
+ **/
+static int i40e_parse_rx_flow_user_data(struct ethtool_rx_flow_spec *fsp,
+ struct i40e_rx_flow_userdef *data)
+{
+ u64 value, mask;
+ int valid;
+
+ /* Zero memory first so it's always consistent. */
+ memset(data, 0, sizeof(*data));
+
+ if (!(fsp->flow_type & FLOW_EXT))
+ return 0;
+
+ value = be64_to_cpu(*((__be64 *)fsp->h_ext.data));
+ mask = be64_to_cpu(*((__be64 *)fsp->m_ext.data));
+
+#define I40E_USERDEF_FLEX_WORD GENMASK_ULL(15, 0)
+#define I40E_USERDEF_FLEX_OFFSET GENMASK_ULL(31, 16)
+#define I40E_USERDEF_FLEX_FILTER GENMASK_ULL(31, 0)
+
+ valid = i40e_check_mask(mask, I40E_USERDEF_FLEX_FILTER);
+ if (valid < 0) {
+ return -EINVAL;
+ } else if (valid) {
+ data->flex_word = value & I40E_USERDEF_FLEX_WORD;
+ data->flex_offset =
+ (value & I40E_USERDEF_FLEX_OFFSET) >> 16;
+ data->flex_filter = true;
+ }
+
+ return 0;
+}
+
+/**
+ * i40e_fill_rx_flow_user_data - Fill in user-defined data field
+ * @fsp: pointer to rx_flow specification
+ *
+ * Reads the userdef data structure and properly fills in the user defined
+ * fields of the rx_flow_spec.
+ **/
+static void i40e_fill_rx_flow_user_data(struct ethtool_rx_flow_spec *fsp,
+ struct i40e_rx_flow_userdef *data)
+{
+ u64 value = 0, mask = 0;
+
+ if (data->flex_filter) {
+ value |= data->flex_word;
+ value |= (u64)data->flex_offset << 16;
+ mask |= I40E_USERDEF_FLEX_FILTER;
+ }
+
+ if (value || mask)
+ fsp->flow_type |= FLOW_EXT;
+
+ *((__be64 *)fsp->h_ext.data) = cpu_to_be64(value);
+ *((__be64 *)fsp->m_ext.data) = cpu_to_be64(mask);
+}
+
+/**
* i40e_get_ethtool_fdir_all - Populates the rule count of a command
* @pf: Pointer to the physical function struct
* @cmd: The command to get or set Rx flow classification rules
@@ -2335,8 +2463,11 @@ static int i40e_get_ethtool_fdir_entry(struct i40e_pf *pf,
{
struct ethtool_rx_flow_spec *fsp =
(struct ethtool_rx_flow_spec *)&cmd->fs;
+ struct i40e_rx_flow_userdef userdef = {0};
struct i40e_fdir_filter *rule = NULL;
struct hlist_node *node2;
+ u64 input_set;
+ u16 index;
hlist_for_each_entry_safe(rule, node2,
&pf->fdir_filter_list, fdir_node) {
@@ -2359,8 +2490,48 @@ static int i40e_get_ethtool_fdir_entry(struct i40e_pf *pf,
*/
fsp->h_u.tcp_ip4_spec.psrc = rule->dst_port;
fsp->h_u.tcp_ip4_spec.pdst = rule->src_port;
- fsp->h_u.tcp_ip4_spec.ip4src = rule->dst_ip[0];
- fsp->h_u.tcp_ip4_spec.ip4dst = rule->src_ip[0];
+ fsp->h_u.tcp_ip4_spec.ip4src = rule->dst_ip;
+ fsp->h_u.tcp_ip4_spec.ip4dst = rule->src_ip;
+
+ switch (rule->flow_type) {
+ case SCTP_V4_FLOW:
+ index = I40E_FILTER_PCTYPE_NONF_IPV4_SCTP;
+ break;
+ case TCP_V4_FLOW:
+ index = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
+ break;
+ case UDP_V4_FLOW:
+ index = I40E_FILTER_PCTYPE_NONF_IPV4_UDP;
+ break;
+ case IP_USER_FLOW:
+ index = I40E_FILTER_PCTYPE_NONF_IPV4_OTHER;
+ break;
+ default:
+ /* If we have stored a filter with a flow type not listed here
+ * it is almost certainly a driver bug. WARN(), and then
+ * assign the input_set as if all fields are enabled to avoid
+ * reading unassigned memory.
+ */
+ WARN(1, "Missing input set index for flow_type %d\n",
+ rule->flow_type);
+ input_set = 0xFFFFFFFFFFFFFFFFULL;
+ goto no_input_set;
+ }
+
+ input_set = i40e_read_fd_input_set(pf, index);
+
+no_input_set:
+ if (input_set & I40E_L3_SRC_MASK)
+ fsp->m_u.tcp_ip4_spec.ip4src = htonl(0xFFFF);
+
+ if (input_set & I40E_L3_DST_MASK)
+ fsp->m_u.tcp_ip4_spec.ip4dst = htonl(0xFFFF);
+
+ if (input_set & I40E_L4_SRC_MASK)
+ fsp->m_u.tcp_ip4_spec.psrc = htons(0xFFFFFFFF);
+
+ if (input_set & I40E_L4_DST_MASK)
+ fsp->m_u.tcp_ip4_spec.pdst = htons(0xFFFFFFFF);
if (rule->dest_ctl == I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET)
fsp->ring_cookie = RX_CLS_FLOW_DISC;
@@ -2372,11 +2543,24 @@ static int i40e_get_ethtool_fdir_entry(struct i40e_pf *pf,
vsi = i40e_find_vsi_from_id(pf, rule->dest_vsi);
if (vsi && vsi->type == I40E_VSI_SRIOV) {
- fsp->h_ext.data[1] = htonl(vsi->vf_id);
- fsp->m_ext.data[1] = htonl(0x1);
+ /* VFs are zero-indexed by the driver, but ethtool
+ * expects them to be one-indexed, so add one here
+ */
+ u64 ring_vf = vsi->vf_id + 1;
+
+ ring_vf <<= ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF;
+ fsp->ring_cookie |= ring_vf;
}
}
+ if (rule->flex_filter) {
+ userdef.flex_filter = true;
+ userdef.flex_word = be16_to_cpu(rule->flex_word);
+ userdef.flex_offset = rule->flex_offset;
+ }
+
+ i40e_fill_rx_flow_user_data(fsp, &userdef);
+
return 0;
}
@@ -2574,24 +2758,6 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
}
/**
- * i40e_match_fdir_input_set - Match a new filter against an existing one
- * @rule: The filter already added
- * @input: The new filter to comapre against
- *
- * Returns true if the two input set match
- **/
-static bool i40e_match_fdir_input_set(struct i40e_fdir_filter *rule,
- struct i40e_fdir_filter *input)
-{
- if ((rule->dst_ip[0] != input->dst_ip[0]) ||
- (rule->src_ip[0] != input->src_ip[0]) ||
- (rule->dst_port != input->dst_port) ||
- (rule->src_port != input->src_port))
- return false;
- return true;
-}
-
-/**
* i40e_update_ethtool_fdir_entry - Updates the fdir filter entry
* @vsi: Pointer to the targeted VSI
* @input: The filter to update or NULL to indicate deletion
@@ -2626,22 +2792,22 @@ static int i40e_update_ethtool_fdir_entry(struct i40e_vsi *vsi,
/* if there is an old rule occupying our place remove it */
if (rule && (rule->fd_id == sw_idx)) {
- if (input && !i40e_match_fdir_input_set(rule, input))
- err = i40e_add_del_fdir(vsi, rule, false);
- else if (!input)
- err = i40e_add_del_fdir(vsi, rule, false);
+ /* Remove this rule, since we're either deleting it, or
+ * replacing it.
+ */
+ err = i40e_add_del_fdir(vsi, rule, false);
hlist_del(&rule->fdir_node);
kfree(rule);
pf->fdir_pf_active_filters--;
}
- /* If no input this was a delete, err should be 0 if a rule was
- * successfully found and removed from the list else -EINVAL
+ /* If we weren't given an input, this is a delete, so just return the
+ * error code indicating if there was an entry at the requested slot
*/
if (!input)
return err;
- /* initialize node and set software index */
+ /* Otherwise, install the new rule as requested */
INIT_HLIST_NODE(&input->fdir_node);
/* add filter to the list */
@@ -2658,6 +2824,69 @@ static int i40e_update_ethtool_fdir_entry(struct i40e_vsi *vsi,
}
/**
+ * i40e_prune_flex_pit_list - Cleanup unused entries in FLX_PIT table
+ * @pf: pointer to PF structure
+ *
+ * This function searches the list of filters and determines which FLX_PIT
+ * entries are still required. It will prune any entries which are no longer
+ * in use after the deletion.
+ **/
+static void i40e_prune_flex_pit_list(struct i40e_pf *pf)
+{
+ struct i40e_flex_pit *entry, *tmp;
+ struct i40e_fdir_filter *rule;
+
+ /* First, we'll check the l3 table */
+ list_for_each_entry_safe(entry, tmp, &pf->l3_flex_pit_list, list) {
+ bool found = false;
+
+ hlist_for_each_entry(rule, &pf->fdir_filter_list, fdir_node) {
+ if (rule->flow_type != IP_USER_FLOW)
+ continue;
+ if (rule->flex_filter &&
+ rule->flex_offset == entry->src_offset) {
+ found = true;
+ break;
+ }
+ }
+
+ /* If we didn't find the filter, then we can prune this entry
+ * from the list.
+ */
+ if (!found) {
+ list_del(&entry->list);
+ kfree(entry);
+ }
+ }
+
+ /* Followed by the L4 table */
+ list_for_each_entry_safe(entry, tmp, &pf->l4_flex_pit_list, list) {
+ bool found = false;
+
+ hlist_for_each_entry(rule, &pf->fdir_filter_list, fdir_node) {
+ /* Skip this filter if it's L3, since we already
+ * checked those in the above loop
+ */
+ if (rule->flow_type == IP_USER_FLOW)
+ continue;
+ if (rule->flex_filter &&
+ rule->flex_offset == entry->src_offset) {
+ found = true;
+ break;
+ }
+ }
+
+ /* If we didn't find the filter, then we can prune this entry
+ * from the list.
+ */
+ if (!found) {
+ list_del(&entry->list);
+ kfree(entry);
+ }
+ }
+}
+
+/**
* i40e_del_fdir_entry - Deletes a Flow Director filter entry
* @vsi: Pointer to the targeted VSI
* @cmd: The command to get or set Rx flow classification rules
@@ -2684,11 +2913,691 @@ static int i40e_del_fdir_entry(struct i40e_vsi *vsi,
ret = i40e_update_ethtool_fdir_entry(vsi, NULL, fsp->location, cmd);
+ i40e_prune_flex_pit_list(pf);
+
i40e_fdir_check_and_reenable(pf);
return ret;
}
/**
+ * i40e_unused_pit_index - Find an unused PIT index for given list
+ * @pf: the PF data structure
+ *
+ * Find the first unused flexible PIT index entry. We search both the L3 and
+ * L4 flexible PIT lists so that the returned index is unique and unused by
+ * either currently programmed L3 or L4 filters. We use a bit field as storage
+ * to track which indexes are already used.
+ **/
+static u8 i40e_unused_pit_index(struct i40e_pf *pf)
+{
+ unsigned long available_index = 0xFF;
+ struct i40e_flex_pit *entry;
+
+ /* We need to make sure that the new index isn't in use by either L3
+ * or L4 filters so that IP_USER_FLOW filters can program both L3 and
+ * L4 to use the same index.
+ */
+
+ list_for_each_entry(entry, &pf->l4_flex_pit_list, list)
+ clear_bit(entry->pit_index, &available_index);
+
+ list_for_each_entry(entry, &pf->l3_flex_pit_list, list)
+ clear_bit(entry->pit_index, &available_index);
+
+ return find_first_bit(&available_index, 8);
+}
+
+/**
+ * i40e_find_flex_offset - Find an existing flex src_offset
+ * @flex_pit_list: L3 or L4 flex PIT list
+ * @src_offset: new src_offset to find
+ *
+ * Searches the flex_pit_list for an existing offset. If no offset is
+ * currently programmed, then this will return an ERR_PTR if there is no space
+ * to add a new offset, otherwise it returns NULL.
+ **/
+static
+struct i40e_flex_pit *i40e_find_flex_offset(struct list_head *flex_pit_list,
+ u16 src_offset)
+{
+ struct i40e_flex_pit *entry;
+ int size = 0;
+
+ /* Search for the src_offset first. If we find a matching entry
+ * already programmed, we can simply re-use it.
+ */
+ list_for_each_entry(entry, flex_pit_list, list) {
+ size++;
+ if (entry->src_offset == src_offset)
+ return entry;
+ }
+
+ /* If we haven't found an entry yet, then the provided src offset has
+ * not yet been programmed. We will program the src offset later on,
+ * but we need to indicate whether there is enough space to do so
+ * here. We'll make use of ERR_PTR for this purpose.
+ */
+ if (size >= I40E_FLEX_PIT_TABLE_SIZE)
+ return ERR_PTR(-ENOSPC);
+
+ return NULL;
+}
+
+/**
+ * i40e_add_flex_offset - Add src_offset to flex PIT table list
+ * @flex_pit_list: L3 or L4 flex PIT list
+ * @src_offset: new src_offset to add
+ * @pit_index: the PIT index to program
+ *
+ * This function programs the new src_offset to the list. It is expected that
+ * i40e_find_flex_offset has already been tried and returned NULL, indicating
+ * that this offset is not programmed, and that the list has enough space to
+ * store another offset.
+ *
+ * Returns 0 on success, and negative value on error.
+ **/
+static int i40e_add_flex_offset(struct list_head *flex_pit_list,
+ u16 src_offset,
+ u8 pit_index)
+{
+ struct i40e_flex_pit *new_pit, *entry;
+
+ new_pit = kzalloc(sizeof(*entry), GFP_KERNEL);
+ if (!new_pit)
+ return -ENOMEM;
+
+ new_pit->src_offset = src_offset;
+ new_pit->pit_index = pit_index;
+
+ /* We need to insert this item such that the list is sorted by
+ * src_offset in ascending order.
+ */
+ list_for_each_entry(entry, flex_pit_list, list) {
+ if (new_pit->src_offset < entry->src_offset) {
+ list_add_tail(&new_pit->list, &entry->list);
+ return 0;
+ }
+
+ /* If we found an entry with our offset already programmed we
+ * can simply return here, after freeing the memory. However,
+ * if the pit_index does not match we need to report an error.
+ */
+ if (new_pit->src_offset == entry->src_offset) {
+ int err = 0;
+
+ /* If the PIT index is not the same we can't re-use
+ * the entry, so we must report an error.
+ */
+ if (new_pit->pit_index != entry->pit_index)
+ err = -EINVAL;
+
+ kfree(new_pit);
+ return err;
+ }
+ }
+
+ /* If we reached here, then we haven't yet added the item. This means
+ * that we should add the item at the end of the list.
+ */
+ list_add_tail(&new_pit->list, flex_pit_list);
+ return 0;
+}
+
+/**
+ * __i40e_reprogram_flex_pit - Re-program specific FLX_PIT table
+ * @pf: Pointer to the PF structure
+ * @flex_pit_list: list of flexible src offsets in use
+ * #flex_pit_start: index to first entry for this section of the table
+ *
+ * In order to handle flexible data, the hardware uses a table of values
+ * called the FLX_PIT table. This table is used to indicate which sections of
+ * the input correspond to what PIT index values. Unfortunately, hardware is
+ * very restrictive about programming this table. Entries must be ordered by
+ * src_offset in ascending order, without duplicates. Additionally, unused
+ * entries must be set to the unused index value, and must have valid size and
+ * length according to the src_offset ordering.
+ *
+ * This function will reprogram the FLX_PIT register from a book-keeping
+ * structure that we guarantee is already ordered correctly, and has no more
+ * than 3 entries.
+ *
+ * To make things easier, we only support flexible values of one word length,
+ * rather than allowing variable length flexible values.
+ **/
+static void __i40e_reprogram_flex_pit(struct i40e_pf *pf,
+ struct list_head *flex_pit_list,
+ int flex_pit_start)
+{
+ struct i40e_flex_pit *entry = NULL;
+ u16 last_offset = 0;
+ int i = 0, j = 0;
+
+ /* First, loop over the list of flex PIT entries, and reprogram the
+ * registers.
+ */
+ list_for_each_entry(entry, flex_pit_list, list) {
+ /* We have to be careful when programming values for the
+ * largest SRC_OFFSET value. It is possible that adding
+ * additional empty values at the end would overflow the space
+ * for the SRC_OFFSET in the FLX_PIT register. To avoid this,
+ * we check here and add the empty values prior to adding the
+ * largest value.
+ *
+ * To determine this, we will use a loop from i+1 to 3, which
+ * will determine whether the unused entries would have valid
+ * SRC_OFFSET. Note that there cannot be extra entries past
+ * this value, because the only valid values would have been
+ * larger than I40E_MAX_FLEX_SRC_OFFSET, and thus would not
+ * have been added to the list in the first place.
+ */
+ for (j = i + 1; j < 3; j++) {
+ u16 offset = entry->src_offset + j;
+ int index = flex_pit_start + i;
+ u32 value = I40E_FLEX_PREP_VAL(I40E_FLEX_DEST_UNUSED,
+ 1,
+ offset - 3);
+
+ if (offset > I40E_MAX_FLEX_SRC_OFFSET) {
+ i40e_write_rx_ctl(&pf->hw,
+ I40E_PRTQF_FLX_PIT(index),
+ value);
+ i++;
+ }
+ }
+
+ /* Now, we can program the actual value into the table */
+ i40e_write_rx_ctl(&pf->hw,
+ I40E_PRTQF_FLX_PIT(flex_pit_start + i),
+ I40E_FLEX_PREP_VAL(entry->pit_index + 50,
+ 1,
+ entry->src_offset));
+ i++;
+ }
+
+ /* In order to program the last entries in the table, we need to
+ * determine the valid offset. If the list is empty, we'll just start
+ * with 0. Otherwise, we'll start with the last item offset and add 1.
+ * This ensures that all entries have valid sizes. If we don't do this
+ * correctly, the hardware will disable flexible field parsing.
+ */
+ if (!list_empty(flex_pit_list))
+ last_offset = list_prev_entry(entry, list)->src_offset + 1;
+
+ for (; i < 3; i++, last_offset++) {
+ i40e_write_rx_ctl(&pf->hw,
+ I40E_PRTQF_FLX_PIT(flex_pit_start + i),
+ I40E_FLEX_PREP_VAL(I40E_FLEX_DEST_UNUSED,
+ 1,
+ last_offset));
+ }
+}
+
+/**
+ * i40e_reprogram_flex_pit - Reprogram all FLX_PIT tables after input set change
+ * @pf: pointer to the PF structure
+ *
+ * This function reprograms both the L3 and L4 FLX_PIT tables. See the
+ * internal helper function for implementation details.
+ **/
+static void i40e_reprogram_flex_pit(struct i40e_pf *pf)
+{
+ __i40e_reprogram_flex_pit(pf, &pf->l3_flex_pit_list,
+ I40E_FLEX_PIT_IDX_START_L3);
+
+ __i40e_reprogram_flex_pit(pf, &pf->l4_flex_pit_list,
+ I40E_FLEX_PIT_IDX_START_L4);
+
+ /* We also need to program the L3 and L4 GLQF ORT register */
+ i40e_write_rx_ctl(&pf->hw,
+ I40E_GLQF_ORT(I40E_L3_GLQF_ORT_IDX),
+ I40E_ORT_PREP_VAL(I40E_FLEX_PIT_IDX_START_L3,
+ 3, 1));
+
+ i40e_write_rx_ctl(&pf->hw,
+ I40E_GLQF_ORT(I40E_L4_GLQF_ORT_IDX),
+ I40E_ORT_PREP_VAL(I40E_FLEX_PIT_IDX_START_L4,
+ 3, 1));
+}
+
+/**
+ * i40e_flow_str - Converts a flow_type into a human readable string
+ * @flow_type: the flow type from a flow specification
+ *
+ * Currently only flow types we support are included here, and the string
+ * value attempts to match what ethtool would use to configure this flow type.
+ **/
+static const char *i40e_flow_str(struct ethtool_rx_flow_spec *fsp)
+{
+ switch (fsp->flow_type & ~FLOW_EXT) {
+ case TCP_V4_FLOW:
+ return "tcp4";
+ case UDP_V4_FLOW:
+ return "udp4";
+ case SCTP_V4_FLOW:
+ return "sctp4";
+ case IP_USER_FLOW:
+ return "ip4";
+ default:
+ return "unknown";
+ }
+}
+
+/**
+ * i40e_pit_index_to_mask - Return the FLEX mask for a given PIT index
+ * @pit_index: PIT index to convert
+ *
+ * Returns the mask for a given PIT index. Will return 0 if the pit_index is
+ * of range.
+ **/
+static u64 i40e_pit_index_to_mask(int pit_index)
+{
+ switch (pit_index) {
+ case 0:
+ return I40E_FLEX_50_MASK;
+ case 1:
+ return I40E_FLEX_51_MASK;
+ case 2:
+ return I40E_FLEX_52_MASK;
+ case 3:
+ return I40E_FLEX_53_MASK;
+ case 4:
+ return I40E_FLEX_54_MASK;
+ case 5:
+ return I40E_FLEX_55_MASK;
+ case 6:
+ return I40E_FLEX_56_MASK;
+ case 7:
+ return I40E_FLEX_57_MASK;
+ default:
+ return 0;
+ }
+}
+
+/**
+ * i40e_print_input_set - Show changes between two input sets
+ * @vsi: the vsi being configured
+ * @old: the old input set
+ * @new: the new input set
+ *
+ * Print the difference between old and new input sets by showing which series
+ * of words are toggled on or off. Only displays the bits we actually support
+ * changing.
+ **/
+static void i40e_print_input_set(struct i40e_vsi *vsi, u64 old, u64 new)
+{
+ struct i40e_pf *pf = vsi->back;
+ bool old_value, new_value;
+ int i;
+
+ old_value = !!(old & I40E_L3_SRC_MASK);
+ new_value = !!(new & I40E_L3_SRC_MASK);
+ if (old_value != new_value)
+ netif_info(pf, drv, vsi->netdev, "L3 source address: %s -> %s\n",
+ old_value ? "ON" : "OFF",
+ new_value ? "ON" : "OFF");
+
+ old_value = !!(old & I40E_L3_DST_MASK);
+ new_value = !!(new & I40E_L3_DST_MASK);
+ if (old_value != new_value)
+ netif_info(pf, drv, vsi->netdev, "L3 destination address: %s -> %s\n",
+ old_value ? "ON" : "OFF",
+ new_value ? "ON" : "OFF");
+
+ old_value = !!(old & I40E_L4_SRC_MASK);
+ new_value = !!(new & I40E_L4_SRC_MASK);
+ if (old_value != new_value)
+ netif_info(pf, drv, vsi->netdev, "L4 source port: %s -> %s\n",
+ old_value ? "ON" : "OFF",
+ new_value ? "ON" : "OFF");
+
+ old_value = !!(old & I40E_L4_DST_MASK);
+ new_value = !!(new & I40E_L4_DST_MASK);
+ if (old_value != new_value)
+ netif_info(pf, drv, vsi->netdev, "L4 destination port: %s -> %s\n",
+ old_value ? "ON" : "OFF",
+ new_value ? "ON" : "OFF");
+
+ old_value = !!(old & I40E_VERIFY_TAG_MASK);
+ new_value = !!(new & I40E_VERIFY_TAG_MASK);
+ if (old_value != new_value)
+ netif_info(pf, drv, vsi->netdev, "SCTP verification tag: %s -> %s\n",
+ old_value ? "ON" : "OFF",
+ new_value ? "ON" : "OFF");
+
+ /* Show change of flexible filter entries */
+ for (i = 0; i < I40E_FLEX_INDEX_ENTRIES; i++) {
+ u64 flex_mask = i40e_pit_index_to_mask(i);
+
+ old_value = !!(old & flex_mask);
+ new_value = !!(new & flex_mask);
+ if (old_value != new_value)
+ netif_info(pf, drv, vsi->netdev, "FLEX index %d: %s -> %s\n",
+ i,
+ old_value ? "ON" : "OFF",
+ new_value ? "ON" : "OFF");
+ }
+
+ netif_info(pf, drv, vsi->netdev, " Current input set: %0llx\n",
+ old);
+ netif_info(pf, drv, vsi->netdev, "Requested input set: %0llx\n",
+ new);
+}
+
+/**
+ * i40e_check_fdir_input_set - Check that a given rx_flow_spec mask is valid
+ * @vsi: pointer to the targeted VSI
+ * @fsp: pointer to Rx flow specification
+ * @userdef: userdefined data from flow specification
+ *
+ * Ensures that a given ethtool_rx_flow_spec has a valid mask. Some support
+ * for partial matches exists with a few limitations. First, hardware only
+ * supports masking by word boundary (2 bytes) and not per individual bit.
+ * Second, hardware is limited to using one mask for a flow type and cannot
+ * use a separate mask for each filter.
+ *
+ * To support these limitations, if we already have a configured filter for
+ * the specified type, this function enforces that new filters of the type
+ * match the configured input set. Otherwise, if we do not have a filter of
+ * the specified type, we allow the input set to be updated to match the
+ * desired filter.
+ *
+ * To help ensure that administrators understand why filters weren't displayed
+ * as supported, we print a diagnostic message displaying how the input set
+ * would change and warning to delete the preexisting filters if required.
+ *
+ * Returns 0 on successful input set match, and a negative return code on
+ * failure.
+ **/
+static int i40e_check_fdir_input_set(struct i40e_vsi *vsi,
+ struct ethtool_rx_flow_spec *fsp,
+ struct i40e_rx_flow_userdef *userdef)
+{
+ struct i40e_pf *pf = vsi->back;
+ struct ethtool_tcpip4_spec *tcp_ip4_spec;
+ struct ethtool_usrip4_spec *usr_ip4_spec;
+ u64 current_mask, new_mask;
+ bool new_flex_offset = false;
+ bool flex_l3 = false;
+ u16 *fdir_filter_count;
+ u16 index, src_offset = 0;
+ u8 pit_index = 0;
+ int err;
+
+ switch (fsp->flow_type & ~FLOW_EXT) {
+ case SCTP_V4_FLOW:
+ index = I40E_FILTER_PCTYPE_NONF_IPV4_SCTP;
+ fdir_filter_count = &pf->fd_sctp4_filter_cnt;
+ break;
+ case TCP_V4_FLOW:
+ index = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
+ fdir_filter_count = &pf->fd_tcp4_filter_cnt;
+ break;
+ case UDP_V4_FLOW:
+ index = I40E_FILTER_PCTYPE_NONF_IPV4_UDP;
+ fdir_filter_count = &pf->fd_udp4_filter_cnt;
+ break;
+ case IP_USER_FLOW:
+ index = I40E_FILTER_PCTYPE_NONF_IPV4_OTHER;
+ fdir_filter_count = &pf->fd_ip4_filter_cnt;
+ flex_l3 = true;
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ /* Read the current input set from register memory. */
+ current_mask = i40e_read_fd_input_set(pf, index);
+ new_mask = current_mask;
+
+ /* Determine, if any, the required changes to the input set in order
+ * to support the provided mask.
+ *
+ * Hardware only supports masking at word (2 byte) granularity and does
+ * not support full bitwise masking. This implementation simplifies
+ * even further and only supports fully enabled or fully disabled
+ * masks for each field, even though we could split the ip4src and
+ * ip4dst fields.
+ */
+ switch (fsp->flow_type & ~FLOW_EXT) {
+ case SCTP_V4_FLOW:
+ new_mask &= ~I40E_VERIFY_TAG_MASK;
+ /* Fall through */
+ case TCP_V4_FLOW:
+ case UDP_V4_FLOW:
+ tcp_ip4_spec = &fsp->m_u.tcp_ip4_spec;
+
+ /* IPv4 source address */
+ if (tcp_ip4_spec->ip4src == htonl(0xFFFFFFFF))
+ new_mask |= I40E_L3_SRC_MASK;
+ else if (!tcp_ip4_spec->ip4src)
+ new_mask &= ~I40E_L3_SRC_MASK;
+ else
+ return -EOPNOTSUPP;
+
+ /* IPv4 destination address */
+ if (tcp_ip4_spec->ip4dst == htonl(0xFFFFFFFF))
+ new_mask |= I40E_L3_DST_MASK;
+ else if (!tcp_ip4_spec->ip4dst)
+ new_mask &= ~I40E_L3_DST_MASK;
+ else
+ return -EOPNOTSUPP;
+
+ /* L4 source port */
+ if (tcp_ip4_spec->psrc == htons(0xFFFF))
+ new_mask |= I40E_L4_SRC_MASK;
+ else if (!tcp_ip4_spec->psrc)
+ new_mask &= ~I40E_L4_SRC_MASK;
+ else
+ return -EOPNOTSUPP;
+
+ /* L4 destination port */
+ if (tcp_ip4_spec->pdst == htons(0xFFFF))
+ new_mask |= I40E_L4_DST_MASK;
+ else if (!tcp_ip4_spec->pdst)
+ new_mask &= ~I40E_L4_DST_MASK;
+ else
+ return -EOPNOTSUPP;
+
+ /* Filtering on Type of Service is not supported. */
+ if (tcp_ip4_spec->tos)
+ return -EOPNOTSUPP;
+
+ break;
+ case IP_USER_FLOW:
+ usr_ip4_spec = &fsp->m_u.usr_ip4_spec;
+
+ /* IPv4 source address */
+ if (usr_ip4_spec->ip4src == htonl(0xFFFFFFFF))
+ new_mask |= I40E_L3_SRC_MASK;
+ else if (!usr_ip4_spec->ip4src)
+ new_mask &= ~I40E_L3_SRC_MASK;
+ else
+ return -EOPNOTSUPP;
+
+ /* IPv4 destination address */
+ if (usr_ip4_spec->ip4dst == htonl(0xFFFFFFFF))
+ new_mask |= I40E_L3_DST_MASK;
+ else if (!usr_ip4_spec->ip4dst)
+ new_mask &= ~I40E_L3_DST_MASK;
+ else
+ return -EOPNOTSUPP;
+
+ /* First 4 bytes of L4 header */
+ if (usr_ip4_spec->l4_4_bytes == htonl(0xFFFFFFFF))
+ new_mask |= I40E_L4_SRC_MASK | I40E_L4_DST_MASK;
+ else if (!usr_ip4_spec->l4_4_bytes)
+ new_mask &= ~(I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
+ else
+ return -EOPNOTSUPP;
+
+ /* Filtering on Type of Service is not supported. */
+ if (usr_ip4_spec->tos)
+ return -EOPNOTSUPP;
+
+ /* Filtering on IP version is not supported */
+ if (usr_ip4_spec->ip_ver)
+ return -EINVAL;
+
+ /* Filtering on L4 protocol is not supported */
+ if (usr_ip4_spec->proto)
+ return -EINVAL;
+
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ /* First, clear all flexible filter entries */
+ new_mask &= ~I40E_FLEX_INPUT_MASK;
+
+ /* If we have a flexible filter, try to add this offset to the correct
+ * flexible filter PIT list. Once finished, we can update the mask.
+ * If the src_offset changed, we will get a new mask value which will
+ * trigger an input set change.
+ */
+ if (userdef->flex_filter) {
+ struct i40e_flex_pit *l3_flex_pit = NULL, *flex_pit = NULL;
+
+ /* Flexible offset must be even, since the flexible payload
+ * must be aligned on 2-byte boundary.
+ */
+ if (userdef->flex_offset & 0x1) {
+ dev_warn(&pf->pdev->dev,
+ "Flexible data offset must be 2-byte aligned\n");
+ return -EINVAL;
+ }
+
+ src_offset = userdef->flex_offset >> 1;
+
+ /* FLX_PIT source offset value is only so large */
+ if (src_offset > I40E_MAX_FLEX_SRC_OFFSET) {
+ dev_warn(&pf->pdev->dev,
+ "Flexible data must reside within first 64 bytes of the packet payload\n");
+ return -EINVAL;
+ }
+
+ /* See if this offset has already been programmed. If we get
+ * an ERR_PTR, then the filter is not safe to add. Otherwise,
+ * if we get a NULL pointer, this means we will need to add
+ * the offset.
+ */
+ flex_pit = i40e_find_flex_offset(&pf->l4_flex_pit_list,
+ src_offset);
+ if (IS_ERR(flex_pit))
+ return PTR_ERR(flex_pit);
+
+ /* IP_USER_FLOW filters match both L4 (ICMP) and L3 (unknown)
+ * packet types, and thus we need to program both L3 and L4
+ * flexible values. These must have identical flexible index,
+ * as otherwise we can't correctly program the input set. So
+ * we'll find both an L3 and L4 index and make sure they are
+ * the same.
+ */
+ if (flex_l3) {
+ l3_flex_pit =
+ i40e_find_flex_offset(&pf->l3_flex_pit_list,
+ src_offset);
+ if (IS_ERR(l3_flex_pit))
+ return PTR_ERR(l3_flex_pit);
+
+ if (flex_pit) {
+ /* If we already had a matching L4 entry, we
+ * need to make sure that the L3 entry we
+ * obtained uses the same index.
+ */
+ if (l3_flex_pit) {
+ if (l3_flex_pit->pit_index !=
+ flex_pit->pit_index) {
+ return -EINVAL;
+ }
+ } else {
+ new_flex_offset = true;
+ }
+ } else {
+ flex_pit = l3_flex_pit;
+ }
+ }
+
+ /* If we didn't find an existing flex offset, we need to
+ * program a new one. However, we don't immediately program it
+ * here because we will wait to program until after we check
+ * that it is safe to change the input set.
+ */
+ if (!flex_pit) {
+ new_flex_offset = true;
+ pit_index = i40e_unused_pit_index(pf);
+ } else {
+ pit_index = flex_pit->pit_index;
+ }
+
+ /* Update the mask with the new offset */
+ new_mask |= i40e_pit_index_to_mask(pit_index);
+ }
+
+ /* If the mask and flexible filter offsets for this filter match the
+ * currently programmed values we don't need any input set change, so
+ * this filter is safe to install.
+ */
+ if (new_mask == current_mask && !new_flex_offset)
+ return 0;
+
+ netif_info(pf, drv, vsi->netdev, "Input set change requested for %s flows:\n",
+ i40e_flow_str(fsp));
+ i40e_print_input_set(vsi, current_mask, new_mask);
+ if (new_flex_offset) {
+ netif_info(pf, drv, vsi->netdev, "FLEX index %d: Offset -> %d",
+ pit_index, src_offset);
+ }
+
+ /* Hardware input sets are global across multiple ports, so even the
+ * main port cannot change them when in MFP mode as this would impact
+ * any filters on the other ports.
+ */
+ if (pf->flags & I40E_FLAG_MFP_ENABLED) {
+ netif_err(pf, drv, vsi->netdev, "Cannot change Flow Director input sets while MFP is enabled\n");
+ return -EOPNOTSUPP;
+ }
+
+ /* This filter requires us to update the input set. However, hardware
+ * only supports one input set per flow type, and does not support
+ * separate masks for each filter. This means that we can only support
+ * a single mask for all filters of a specific type.
+ *
+ * If we have preexisting filters, they obviously depend on the
+ * current programmed input set. Display a diagnostic message in this
+ * case explaining why the filter could not be accepted.
+ */
+ if (*fdir_filter_count) {
+ netif_err(pf, drv, vsi->netdev, "Cannot change input set for %s flows until %d preexisting filters are removed\n",
+ i40e_flow_str(fsp),
+ *fdir_filter_count);
+ return -EOPNOTSUPP;
+ }
+
+ i40e_write_fd_input_set(pf, index, new_mask);
+
+ /* Add the new offset and update table, if necessary */
+ if (new_flex_offset) {
+ err = i40e_add_flex_offset(&pf->l4_flex_pit_list, src_offset,
+ pit_index);
+ if (err)
+ return err;
+
+ if (flex_l3) {
+ err = i40e_add_flex_offset(&pf->l3_flex_pit_list,
+ src_offset,
+ pit_index);
+ if (err)
+ return err;
+ }
+
+ i40e_reprogram_flex_pit(pf);
+ }
+
+ return 0;
+}
+
+/**
* i40e_add_fdir_ethtool - Add/Remove Flow Director filters
* @vsi: pointer to the targeted VSI
* @cmd: command to get or set RX flow classification rules
@@ -2699,11 +3608,13 @@ static int i40e_del_fdir_entry(struct i40e_vsi *vsi,
static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
struct ethtool_rxnfc *cmd)
{
+ struct i40e_rx_flow_userdef userdef;
struct ethtool_rx_flow_spec *fsp;
struct i40e_fdir_filter *input;
+ u16 dest_vsi = 0, q_index = 0;
struct i40e_pf *pf;
int ret = -EINVAL;
- u16 vf_id;
+ u8 dest_ctl;
if (!vsi)
return -EINVAL;
@@ -2712,7 +3623,7 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED))
return -EOPNOTSUPP;
- if (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)
+ if (pf->hw_disabled_flags & I40E_FLAG_FD_SB_ENABLED)
return -ENOSPC;
if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state) ||
@@ -2724,14 +3635,49 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
fsp = (struct ethtool_rx_flow_spec *)&cmd->fs;
+ /* Parse the user-defined field */
+ if (i40e_parse_rx_flow_user_data(fsp, &userdef))
+ return -EINVAL;
+
+ /* Extended MAC field is not supported */
+ if (fsp->flow_type & FLOW_MAC_EXT)
+ return -EINVAL;
+
+ ret = i40e_check_fdir_input_set(vsi, fsp, &userdef);
+ if (ret)
+ return ret;
+
if (fsp->location >= (pf->hw.func_caps.fd_filters_best_effort +
pf->hw.func_caps.fd_filters_guaranteed)) {
return -EINVAL;
}
- if ((fsp->ring_cookie != RX_CLS_FLOW_DISC) &&
- (fsp->ring_cookie >= vsi->num_queue_pairs))
- return -EINVAL;
+ /* ring_cookie is either the drop index, or is a mask of the queue
+ * index and VF id we wish to target.
+ */
+ if (fsp->ring_cookie == RX_CLS_FLOW_DISC) {
+ dest_ctl = I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET;
+ } else {
+ u32 ring = ethtool_get_flow_spec_ring(fsp->ring_cookie);
+ u8 vf = ethtool_get_flow_spec_ring_vf(fsp->ring_cookie);
+
+ if (!vf) {
+ if (ring >= vsi->num_queue_pairs)
+ return -EINVAL;
+ dest_vsi = vsi->id;
+ } else {
+ /* VFs are zero-indexed, so we subtract one here */
+ vf--;
+
+ if (vf >= pf->num_alloc_vfs)
+ return -EINVAL;
+ if (ring >= pf->vf[vf].num_queue_pairs)
+ return -EINVAL;
+ dest_vsi = pf->vf[vf].lan_vsi_id;
+ }
+ dest_ctl = I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_QINDEX;
+ q_index = ring;
+ }
input = kzalloc(sizeof(*input), GFP_KERNEL);
@@ -2739,20 +3685,14 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
return -ENOMEM;
input->fd_id = fsp->location;
-
- if (fsp->ring_cookie == RX_CLS_FLOW_DISC)
- input->dest_ctl = I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET;
- else
- input->dest_ctl =
- I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_QINDEX;
-
- input->q_index = fsp->ring_cookie;
- input->flex_off = 0;
- input->pctype = 0;
- input->dest_vsi = vsi->id;
+ input->q_index = q_index;
+ input->dest_vsi = dest_vsi;
+ input->dest_ctl = dest_ctl;
input->fd_status = I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID;
input->cnt_index = I40E_FD_SB_STAT_IDX(pf->hw.pf_id);
- input->flow_type = fsp->flow_type;
+ input->dst_ip = fsp->h_u.tcp_ip4_spec.ip4src;
+ input->src_ip = fsp->h_u.tcp_ip4_spec.ip4dst;
+ input->flow_type = fsp->flow_type & ~FLOW_EXT;
input->ip4_proto = fsp->h_u.usr_ip4_spec.proto;
/* Reverse the src and dest notion, since the HW expects them to be from
@@ -2760,33 +3700,29 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
*/
input->dst_port = fsp->h_u.tcp_ip4_spec.psrc;
input->src_port = fsp->h_u.tcp_ip4_spec.pdst;
- input->dst_ip[0] = fsp->h_u.tcp_ip4_spec.ip4src;
- input->src_ip[0] = fsp->h_u.tcp_ip4_spec.ip4dst;
+ input->dst_ip = fsp->h_u.tcp_ip4_spec.ip4src;
+ input->src_ip = fsp->h_u.tcp_ip4_spec.ip4dst;
- if (ntohl(fsp->m_ext.data[1])) {
- vf_id = ntohl(fsp->h_ext.data[1]);
- if (vf_id >= pf->num_alloc_vfs) {
- netif_info(pf, drv, vsi->netdev,
- "Invalid VF id %d\n", vf_id);
- goto free_input;
- }
- /* Find vsi id from vf id and override dest vsi */
- input->dest_vsi = pf->vf[vf_id].lan_vsi_id;
- if (input->q_index >= pf->vf[vf_id].num_queue_pairs) {
- netif_info(pf, drv, vsi->netdev,
- "Invalid queue id %d for VF %d\n",
- input->q_index, vf_id);
- goto free_input;
- }
+ if (userdef.flex_filter) {
+ input->flex_filter = true;
+ input->flex_word = cpu_to_be16(userdef.flex_word);
+ input->flex_offset = userdef.flex_offset;
}
ret = i40e_add_del_fdir(vsi, input, true);
-free_input:
if (ret)
- kfree(input);
- else
- i40e_update_ethtool_fdir_entry(vsi, input, fsp->location, NULL);
+ goto free_input;
+ /* Add the input filter to the fdir_input_list, possibly replacing
+ * a previous filter. Do not free the input structure after adding it
+ * to the list as this would cause a use-after-free bug.
+ */
+ i40e_update_ethtool_fdir_entry(vsi, input, fsp->location, NULL);
+
+ return 0;
+
+free_input:
+ kfree(input);
return ret;
}
@@ -3036,7 +3972,7 @@ static int i40e_set_rxfh(struct net_device *netdev, const u32 *indir,
* @dev: network interface device structure
*
* The get string set count and the string set should be matched for each
- * flag returned. Add new strings for each flag to the i40e_priv_flags_strings
+ * flag returned. Add new strings for each flag to the i40e_gstrings_priv_flags
* array.
*
* Returns a u32 bitmap of flags.
@@ -3046,19 +3982,27 @@ static u32 i40e_get_priv_flags(struct net_device *dev)
struct i40e_netdev_priv *np = netdev_priv(dev);
struct i40e_vsi *vsi = np->vsi;
struct i40e_pf *pf = vsi->back;
- u32 ret_flags = 0;
+ u32 i, j, ret_flags = 0;
- ret_flags |= pf->flags & I40E_FLAG_LINK_POLLING_ENABLED ?
- I40E_PRIV_FLAGS_LINKPOLL_FLAG : 0;
- ret_flags |= pf->flags & I40E_FLAG_FD_ATR_ENABLED ?
- I40E_PRIV_FLAGS_FD_ATR : 0;
- ret_flags |= pf->flags & I40E_FLAG_VEB_STATS_ENABLED ?
- I40E_PRIV_FLAGS_VEB_STATS : 0;
- ret_flags |= pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE ?
- 0 : I40E_PRIV_FLAGS_HW_ATR_EVICT;
- if (pf->hw.pf_id == 0) {
- ret_flags |= pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT ?
- I40E_PRIV_FLAGS_TRUE_PROMISC_SUPPORT : 0;
+ for (i = 0; i < I40E_PRIV_FLAGS_STR_LEN; i++) {
+ const struct i40e_priv_flags *priv_flags;
+
+ priv_flags = &i40e_gstrings_priv_flags[i];
+
+ if (priv_flags->flag & pf->flags)
+ ret_flags |= BIT(i);
+ }
+
+ if (pf->hw.pf_id != 0)
+ return ret_flags;
+
+ for (j = 0; j < I40E_GL_PRIV_FLAGS_STR_LEN; j++) {
+ const struct i40e_priv_flags *priv_flags;
+
+ priv_flags = &i40e_gl_gstrings_priv_flags[j];
+
+ if (priv_flags->flag & pf->flags)
+ ret_flags |= BIT(i + j);
}
return ret_flags;
@@ -3074,54 +4018,66 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags)
struct i40e_netdev_priv *np = netdev_priv(dev);
struct i40e_vsi *vsi = np->vsi;
struct i40e_pf *pf = vsi->back;
- u16 sw_flags = 0, valid_flags = 0;
- bool reset_required = false;
- bool promisc_change = false;
- int ret;
+ u64 changed_flags;
+ u32 i, j;
- /* NOTE: MFP is not settable */
+ changed_flags = pf->flags;
- if (flags & I40E_PRIV_FLAGS_LINKPOLL_FLAG)
- pf->flags |= I40E_FLAG_LINK_POLLING_ENABLED;
- else
- pf->flags &= ~I40E_FLAG_LINK_POLLING_ENABLED;
+ for (i = 0; i < I40E_PRIV_FLAGS_STR_LEN; i++) {
+ const struct i40e_priv_flags *priv_flags;
- /* allow the user to control the state of the Flow
- * Director ATR (Application Targeted Routing) feature
- * of the driver
+ priv_flags = &i40e_gstrings_priv_flags[i];
+
+ if (priv_flags->read_only)
+ continue;
+
+ if (flags & BIT(i))
+ pf->flags |= priv_flags->flag;
+ else
+ pf->flags &= ~(priv_flags->flag);
+ }
+
+ if (pf->hw.pf_id != 0)
+ goto flags_complete;
+
+ for (j = 0; j < I40E_GL_PRIV_FLAGS_STR_LEN; j++) {
+ const struct i40e_priv_flags *priv_flags;
+
+ priv_flags = &i40e_gl_gstrings_priv_flags[j];
+
+ if (priv_flags->read_only)
+ continue;
+
+ if (flags & BIT(i + j))
+ pf->flags |= priv_flags->flag;
+ else
+ pf->flags &= ~(priv_flags->flag);
+ }
+
+flags_complete:
+ /* check for flags that changed */
+ changed_flags ^= pf->flags;
+
+ /* Process any additional changes needed as a result of flag changes.
+ * The changed_flags value reflects the list of bits that were
+ * changed in the code above.
*/
- if (flags & I40E_PRIV_FLAGS_FD_ATR) {
- pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
- } else {
- pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED;
- pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED;
- /* flush current ATR settings */
+ /* Flush current ATR settings if ATR was disabled */
+ if ((changed_flags & I40E_FLAG_FD_ATR_ENABLED) &&
+ !(pf->flags & I40E_FLAG_FD_ATR_ENABLED)) {
+ pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED;
set_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state);
}
- if ((flags & I40E_PRIV_FLAGS_VEB_STATS) &&
- !(pf->flags & I40E_FLAG_VEB_STATS_ENABLED)) {
- pf->flags |= I40E_FLAG_VEB_STATS_ENABLED;
- reset_required = true;
- } else if (!(flags & I40E_PRIV_FLAGS_VEB_STATS) &&
- (pf->flags & I40E_FLAG_VEB_STATS_ENABLED)) {
- pf->flags &= ~I40E_FLAG_VEB_STATS_ENABLED;
- reset_required = true;
- }
+ /* Only allow ATR evict on hardware that is capable of handling it */
+ if (pf->hw_disabled_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE)
+ pf->flags &= ~I40E_FLAG_HW_ATR_EVICT_CAPABLE;
- if (pf->hw.pf_id == 0) {
- if ((flags & I40E_PRIV_FLAGS_TRUE_PROMISC_SUPPORT) &&
- !(pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT)) {
- pf->flags |= I40E_FLAG_TRUE_PROMISC_SUPPORT;
- promisc_change = true;
- } else if (!(flags & I40E_PRIV_FLAGS_TRUE_PROMISC_SUPPORT) &&
- (pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT)) {
- pf->flags &= ~I40E_FLAG_TRUE_PROMISC_SUPPORT;
- promisc_change = true;
- }
- }
- if (promisc_change) {
+ if (changed_flags & I40E_FLAG_TRUE_PROMISC_SUPPORT) {
+ u16 sw_flags = 0, valid_flags = 0;
+ int ret;
+
if (!(pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT))
sw_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC;
valid_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC;
@@ -3137,22 +4093,17 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags)
}
}
- if ((flags & I40E_PRIV_FLAGS_HW_ATR_EVICT) &&
- (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))
- pf->auto_disable_flags &= ~I40E_FLAG_HW_ATR_EVICT_CAPABLE;
- else
- pf->auto_disable_flags |= I40E_FLAG_HW_ATR_EVICT_CAPABLE;
-
- /* if needed, issue reset to cause things to take effect */
- if (reset_required)
- i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED));
+ /* Issue reset to cause things to take effect, as additional bits
+ * are added we will need to create a mask of bits requiring reset
+ */
+ if ((changed_flags & I40E_FLAG_VEB_STATS_ENABLED) ||
+ ((changed_flags & I40E_FLAG_LEGACY_RX) && netif_running(dev)))
+ i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED), true);
return 0;
}
static const struct ethtool_ops i40e_ethtool_ops = {
- .get_settings = i40e_get_settings,
- .set_settings = i40e_set_settings,
.get_drvinfo = i40e_get_drvinfo,
.get_regs_len = i40e_get_regs_len,
.get_regs = i40e_get_regs,
@@ -3189,6 +4140,8 @@ static const struct ethtool_ops i40e_ethtool_ops = {
.set_priv_flags = i40e_set_priv_flags,
.get_per_queue_coalesce = i40e_get_per_queue_coalesce,
.set_per_queue_coalesce = i40e_set_per_queue_coalesce,
+ .get_link_ksettings = i40e_get_link_ksettings,
+ .set_link_ksettings = i40e_set_link_ksettings,
};
void i40e_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index e8a8351..b6ec9be 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -39,9 +39,9 @@ static const char i40e_driver_string[] =
#define DRV_KERN "-k"
-#define DRV_VERSION_MAJOR 1
-#define DRV_VERSION_MINOR 6
-#define DRV_VERSION_BUILD 27
+#define DRV_VERSION_MAJOR 2
+#define DRV_VERSION_MINOR 1
+#define DRV_VERSION_BUILD 7
#define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
__stringify(DRV_VERSION_MINOR) "." \
__stringify(DRV_VERSION_BUILD) DRV_KERN
@@ -50,13 +50,16 @@ static const char i40e_copyright[] = "Copyright (c) 2013 - 2014 Intel Corporatio
/* a bit of forward declarations */
static void i40e_vsi_reinit_locked(struct i40e_vsi *vsi);
-static void i40e_handle_reset_warning(struct i40e_pf *pf);
+static void i40e_handle_reset_warning(struct i40e_pf *pf, bool lock_acquired);
static int i40e_add_vsi(struct i40e_vsi *vsi);
static int i40e_add_veb(struct i40e_veb *veb, struct i40e_vsi *vsi);
static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit);
static int i40e_setup_misc_vector(struct i40e_pf *pf);
static void i40e_determine_queue_usage(struct i40e_pf *pf);
static int i40e_setup_pf_filter_control(struct i40e_pf *pf);
+static void i40e_prep_for_reset(struct i40e_pf *pf, bool lock_acquired);
+static int i40e_reset(struct i40e_pf *pf);
+static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired);
static void i40e_fdir_sb_setup(struct i40e_pf *pf);
static int i40e_veb_get_bw_info(struct i40e_veb *veb);
@@ -299,11 +302,7 @@ void i40e_service_event_schedule(struct i40e_pf *pf)
* device is munged, not just the one netdev port, so go for the full
* reset.
**/
-#ifdef I40E_FCOE
-void i40e_tx_timeout(struct net_device *netdev)
-#else
static void i40e_tx_timeout(struct net_device *netdev)
-#endif
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
@@ -408,10 +407,7 @@ struct rtnl_link_stats64 *i40e_get_vsi_stats_struct(struct i40e_vsi *vsi)
* Returns the address of the device statistics structure.
* The statistics are actually updated from the service task.
**/
-#ifndef I40E_FCOE
-static
-#endif
-void i40e_get_netdev_stats_struct(struct net_device *netdev,
+static void i40e_get_netdev_stats_struct(struct net_device *netdev,
struct rtnl_link_stats64 *stats)
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
@@ -723,55 +719,6 @@ static void i40e_update_veb_stats(struct i40e_veb *veb)
veb->stat_offsets_loaded = true;
}
-#ifdef I40E_FCOE
-/**
- * i40e_update_fcoe_stats - Update FCoE-specific ethernet statistics counters.
- * @vsi: the VSI that is capable of doing FCoE
- **/
-static void i40e_update_fcoe_stats(struct i40e_vsi *vsi)
-{
- struct i40e_pf *pf = vsi->back;
- struct i40e_hw *hw = &pf->hw;
- struct i40e_fcoe_stats *ofs;
- struct i40e_fcoe_stats *fs; /* device's eth stats */
- int idx;
-
- if (vsi->type != I40E_VSI_FCOE)
- return;
-
- idx = hw->pf_id + I40E_FCOE_PF_STAT_OFFSET;
- fs = &vsi->fcoe_stats;
- ofs = &vsi->fcoe_stats_offsets;
-
- i40e_stat_update32(hw, I40E_GL_FCOEPRC(idx),
- vsi->fcoe_stat_offsets_loaded,
- &ofs->rx_fcoe_packets, &fs->rx_fcoe_packets);
- i40e_stat_update48(hw, I40E_GL_FCOEDWRCH(idx), I40E_GL_FCOEDWRCL(idx),
- vsi->fcoe_stat_offsets_loaded,
- &ofs->rx_fcoe_dwords, &fs->rx_fcoe_dwords);
- i40e_stat_update32(hw, I40E_GL_FCOERPDC(idx),
- vsi->fcoe_stat_offsets_loaded,
- &ofs->rx_fcoe_dropped, &fs->rx_fcoe_dropped);
- i40e_stat_update32(hw, I40E_GL_FCOEPTC(idx),
- vsi->fcoe_stat_offsets_loaded,
- &ofs->tx_fcoe_packets, &fs->tx_fcoe_packets);
- i40e_stat_update48(hw, I40E_GL_FCOEDWTCH(idx), I40E_GL_FCOEDWTCL(idx),
- vsi->fcoe_stat_offsets_loaded,
- &ofs->tx_fcoe_dwords, &fs->tx_fcoe_dwords);
- i40e_stat_update32(hw, I40E_GL_FCOECRC(idx),
- vsi->fcoe_stat_offsets_loaded,
- &ofs->fcoe_bad_fccrc, &fs->fcoe_bad_fccrc);
- i40e_stat_update32(hw, I40E_GL_FCOELAST(idx),
- vsi->fcoe_stat_offsets_loaded,
- &ofs->fcoe_last_error, &fs->fcoe_last_error);
- i40e_stat_update32(hw, I40E_GL_FCOEDDPC(idx),
- vsi->fcoe_stat_offsets_loaded,
- &ofs->fcoe_ddp_count, &fs->fcoe_ddp_count);
-
- vsi->fcoe_stat_offsets_loaded = true;
-}
-
-#endif
/**
* i40e_update_vsi_stats - Update the vsi statistics counters.
* @vsi: the VSI to be updated
@@ -790,7 +737,6 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
struct i40e_eth_stats *oes;
struct i40e_eth_stats *es; /* device's eth stats */
u32 tx_restart, tx_busy;
- u64 tx_lost_interrupt;
struct i40e_ring *p;
u32 rx_page, rx_buf;
u64 bytes, packets;
@@ -816,7 +762,6 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
rx_b = rx_p = 0;
tx_b = tx_p = 0;
tx_restart = tx_busy = tx_linearize = tx_force_wb = 0;
- tx_lost_interrupt = 0;
rx_page = 0;
rx_buf = 0;
rcu_read_lock();
@@ -835,7 +780,6 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
tx_busy += p->tx_stats.tx_busy;
tx_linearize += p->tx_stats.tx_linearize;
tx_force_wb += p->tx_stats.tx_force_wb;
- tx_lost_interrupt += p->tx_stats.tx_lost_interrupt;
/* Rx queue is part of the same block as Tx queue */
p = &p[1];
@@ -854,7 +798,6 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
vsi->tx_busy = tx_busy;
vsi->tx_linearize = tx_linearize;
vsi->tx_force_wb = tx_force_wb;
- vsi->tx_lost_interrupt = tx_lost_interrupt;
vsi->rx_page_failed = rx_page;
vsi->rx_buf_failed = rx_buf;
@@ -1101,13 +1044,13 @@ static void i40e_update_pf_stats(struct i40e_pf *pf)
&osd->rx_lpi_count, &nsd->rx_lpi_count);
if (pf->flags & I40E_FLAG_FD_SB_ENABLED &&
- !(pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED))
+ !(pf->hw_disabled_flags & I40E_FLAG_FD_SB_ENABLED))
nsd->fd_sb_status = true;
else
nsd->fd_sb_status = false;
if (pf->flags & I40E_FLAG_FD_ATR_ENABLED &&
- !(pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED))
+ !(pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED))
nsd->fd_atr_status = true;
else
nsd->fd_atr_status = false;
@@ -1129,9 +1072,6 @@ void i40e_update_stats(struct i40e_vsi *vsi)
i40e_update_pf_stats(pf);
i40e_update_vsi_stats(vsi);
-#ifdef I40E_FCOE
- i40e_update_fcoe_stats(vsi);
-#endif
}
/**
@@ -1562,11 +1502,7 @@ int i40e_del_mac_filter(struct i40e_vsi *vsi, const u8 *macaddr)
*
* Returns 0 on success, negative on failure
**/
-#ifdef I40E_FCOE
-int i40e_set_mac(struct net_device *netdev, void *p)
-#else
static int i40e_set_mac(struct net_device *netdev, void *p)
-#endif
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
@@ -1626,17 +1562,10 @@ static int i40e_set_mac(struct net_device *netdev, void *p)
*
* Setup VSI queue mapping for enabled traffic classes.
**/
-#ifdef I40E_FCOE
-void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
- struct i40e_vsi_context *ctxt,
- u8 enabled_tc,
- bool is_add)
-#else
static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
struct i40e_vsi_context *ctxt,
u8 enabled_tc,
bool is_add)
-#endif
{
struct i40e_pf *pf = vsi->back;
u16 sections = 0;
@@ -1686,11 +1615,6 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
qcount = min_t(int, pf->alloc_rss_size,
num_tc_qps);
break;
-#ifdef I40E_FCOE
- case I40E_VSI_FCOE:
- qcount = num_tc_qps;
- break;
-#endif
case I40E_VSI_FDIR:
case I40E_VSI_SRIOV:
case I40E_VSI_VMDQ2:
@@ -1800,11 +1724,7 @@ static int i40e_addr_unsync(struct net_device *netdev, const u8 *addr)
* i40e_set_rx_mode - NDO callback to set the netdev filters
* @netdev: network interface device structure
**/
-#ifdef I40E_FCOE
-void i40e_set_rx_mode(struct net_device *netdev)
-#else
static void i40e_set_rx_mode(struct net_device *netdev)
-#endif
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
@@ -1883,19 +1803,12 @@ static void i40e_undo_add_filter_entries(struct i40e_vsi *vsi,
static
struct i40e_new_mac_filter *i40e_next_filter(struct i40e_new_mac_filter *next)
{
- while (next) {
- next = hlist_entry(next->hlist.next,
- typeof(struct i40e_new_mac_filter),
- hlist);
-
- /* keep going if we found a broadcast filter */
- if (next && is_broadcast_ether_addr(next->f->macaddr))
- continue;
-
- break;
+ hlist_for_each_entry_continue(next, hlist) {
+ if (!is_broadcast_ether_addr(next->f->macaddr))
+ return next;
}
- return next;
+ return NULL;
}
/**
@@ -2487,13 +2400,15 @@ static int i40e_change_mtu(struct net_device *netdev, int new_mtu)
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
netdev_info(netdev, "changing MTU from %d to %d\n",
netdev->mtu, new_mtu);
netdev->mtu = new_mtu;
if (netif_running(netdev))
i40e_vsi_reinit_locked(vsi);
- i40e_notify_client_of_l2_param_changes(vsi);
+ pf->flags |= (I40E_FLAG_SERVICE_CLIENT_REQUESTED |
+ I40E_FLAG_CLIENT_L2_CHANGE);
return 0;
}
@@ -2707,13 +2622,8 @@ void i40e_vsi_kill_vlan(struct i40e_vsi *vsi, u16 vid)
*
* net_device_ops implementation for adding vlan ids
**/
-#ifdef I40E_FCOE
-int i40e_vlan_rx_add_vid(struct net_device *netdev,
- __always_unused __be16 proto, u16 vid)
-#else
static int i40e_vlan_rx_add_vid(struct net_device *netdev,
__always_unused __be16 proto, u16 vid)
-#endif
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
@@ -2744,13 +2654,8 @@ static int i40e_vlan_rx_add_vid(struct net_device *netdev,
*
* net_device_ops implementation for removing vlan ids
**/
-#ifdef I40E_FCOE
-int i40e_vlan_rx_kill_vid(struct net_device *netdev,
- __always_unused __be16 proto, u16 vid)
-#else
static int i40e_vlan_rx_kill_vid(struct net_device *netdev,
__always_unused __be16 proto, u16 vid)
-#endif
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
@@ -2920,9 +2825,6 @@ static int i40e_vsi_setup_rx_resources(struct i40e_vsi *vsi)
for (i = 0; i < vsi->num_queue_pairs && !err; i++)
err = i40e_setup_rx_descriptors(vsi->rx_rings[i]);
-#ifdef I40E_FCOE
- i40e_fcoe_setup_ddp_resources(vsi);
-#endif
return err;
}
@@ -2942,9 +2844,6 @@ static void i40e_vsi_free_rx_resources(struct i40e_vsi *vsi)
for (i = 0; i < vsi->num_queue_pairs; i++)
if (vsi->rx_rings[i] && vsi->rx_rings[i]->desc)
i40e_free_rx_resources(vsi->rx_rings[i]);
-#ifdef I40E_FCOE
- i40e_fcoe_free_ddp_resources(vsi);
-#endif
}
/**
@@ -3015,9 +2914,6 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring)
tx_ctx.qlen = ring->count;
tx_ctx.fd_ena = !!(vsi->back->flags & (I40E_FLAG_FD_SB_ENABLED |
I40E_FLAG_FD_ATR_ENABLED));
-#ifdef I40E_FCOE
- tx_ctx.fc_ena = (vsi->type == I40E_VSI_FCOE);
-#endif
tx_ctx.timesync_ena = !!(vsi->back->flags & I40E_FLAG_PTP);
/* FDIR VSI tx ring can still use RS bit and writebacks */
if (vsi->type != I40E_VSI_FDIR)
@@ -3098,7 +2994,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
ring->rx_buf_len = vsi->rx_buf_len;
- rx_ctx.dbuff = ring->rx_buf_len >> I40E_RXQ_CTX_DBUFF_SHIFT;
+ rx_ctx.dbuff = DIV_ROUND_UP(ring->rx_buf_len,
+ BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT));
rx_ctx.base = (ring->dma / 128);
rx_ctx.qlen = ring->count;
@@ -3120,9 +3017,6 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
rx_ctx.l2tsel = 1;
/* this controls whether VLAN is stripped from inner headers */
rx_ctx.showiv = 0;
-#ifdef I40E_FCOE
- rx_ctx.fc_ena = (vsi->type == I40E_VSI_FCOE);
-#endif
/* set the prefena field to 1 because the manual says to */
rx_ctx.prefena = 1;
@@ -3144,6 +3038,12 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
return -ENOMEM;
}
+ /* configure Rx buffer alignment */
+ if (!vsi->netdev || (vsi->back->flags & I40E_FLAG_LEGACY_RX))
+ clear_ring_build_skb_enabled(ring);
+ else
+ set_ring_build_skb_enabled(ring);
+
/* cache tail for quicker writes, and clear the reg before use */
ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q);
writel(0, ring->tail);
@@ -3181,27 +3081,21 @@ static int i40e_vsi_configure_rx(struct i40e_vsi *vsi)
int err = 0;
u16 i;
- if (vsi->netdev && (vsi->netdev->mtu > ETH_DATA_LEN))
- vsi->max_frame = vsi->netdev->mtu + ETH_HLEN
- + ETH_FCS_LEN + VLAN_HLEN;
- else
- vsi->max_frame = I40E_RXBUFFER_2048;
-
- vsi->rx_buf_len = I40E_RXBUFFER_2048;
-
-#ifdef I40E_FCOE
- /* setup rx buffer for FCoE */
- if ((vsi->type == I40E_VSI_FCOE) &&
- (vsi->back->flags & I40E_FLAG_FCOE_ENABLED)) {
- vsi->rx_buf_len = I40E_RXBUFFER_3072;
- vsi->max_frame = I40E_RXBUFFER_3072;
+ if (!vsi->netdev || (vsi->back->flags & I40E_FLAG_LEGACY_RX)) {
+ vsi->max_frame = I40E_MAX_RXBUFFER;
+ vsi->rx_buf_len = I40E_RXBUFFER_2048;
+#if (PAGE_SIZE < 8192)
+ } else if (!I40E_2K_TOO_SMALL_WITH_PADDING &&
+ (vsi->netdev->mtu <= ETH_DATA_LEN)) {
+ vsi->max_frame = I40E_RXBUFFER_1536 - NET_IP_ALIGN;
+ vsi->rx_buf_len = I40E_RXBUFFER_1536 - NET_IP_ALIGN;
+#endif
+ } else {
+ vsi->max_frame = I40E_MAX_RXBUFFER;
+ vsi->rx_buf_len = (PAGE_SIZE < 8192) ? I40E_RXBUFFER_3072 :
+ I40E_RXBUFFER_2048;
}
-#endif /* I40E_FCOE */
- /* round up for the chip's needs */
- vsi->rx_buf_len = ALIGN(vsi->rx_buf_len,
- BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT));
-
/* set up individual rings */
for (i = 0; i < vsi->num_queue_pairs && !err; i++)
err = i40e_configure_rx_ring(vsi->rx_rings[i]);
@@ -3281,6 +3175,12 @@ static void i40e_fdir_filter_restore(struct i40e_vsi *vsi)
if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED))
return;
+ /* Reset FDir counters as we're replaying all existing filters */
+ pf->fd_tcp4_filter_cnt = 0;
+ pf->fd_udp4_filter_cnt = 0;
+ pf->fd_sctp4_filter_cnt = 0;
+ pf->fd_ip4_filter_cnt = 0;
+
hlist_for_each_entry_safe(filter, node,
&pf->fdir_filter_list, fdir_node) {
i40e_add_del_fdir(vsi, filter, true);
@@ -3993,11 +3893,7 @@ static int i40e_vsi_request_irq(struct i40e_vsi *vsi, char *basename)
* This is used by netconsole to send skbs without having to re-enable
* interrupts. It's not called while the normal interrupt routine is executing.
**/
-#ifdef I40E_FCOE
-void i40e_netpoll(struct net_device *netdev)
-#else
static void i40e_netpoll(struct net_device *netdev)
-#endif
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
@@ -4100,8 +3996,6 @@ static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable)
}
}
- if (hw->revision_id == 0)
- mdelay(50);
return ret;
}
@@ -4180,6 +4074,12 @@ static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable)
}
}
+ /* Due to HW errata, on Rx disable only, the register can indicate done
+ * before it really is. Needs 50ms to be sure
+ */
+ if (!enable)
+ mdelay(50);
+
return ret;
}
@@ -4438,8 +4338,12 @@ static void i40e_napi_enable_all(struct i40e_vsi *vsi)
if (!vsi->netdev)
return;
- for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
- napi_enable(&vsi->q_vectors[q_idx]->napi);
+ for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) {
+ struct i40e_q_vector *q_vector = vsi->q_vectors[q_idx];
+
+ if (q_vector->rx.ring || q_vector->tx.ring)
+ napi_enable(&q_vector->napi);
+ }
}
/**
@@ -4453,8 +4357,12 @@ static void i40e_napi_disable_all(struct i40e_vsi *vsi)
if (!vsi->netdev)
return;
- for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
- napi_disable(&vsi->q_vectors[q_idx]->napi);
+ for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) {
+ struct i40e_q_vector *q_vector = vsi->q_vectors[q_idx];
+
+ if (q_vector->rx.ring || q_vector->tx.ring)
+ napi_disable(&q_vector->napi);
+ }
}
/**
@@ -4463,17 +4371,16 @@ static void i40e_napi_disable_all(struct i40e_vsi *vsi)
**/
static void i40e_vsi_close(struct i40e_vsi *vsi)
{
- bool reset = false;
-
+ struct i40e_pf *pf = vsi->back;
if (!test_and_set_bit(__I40E_DOWN, &vsi->state))
i40e_down(vsi);
i40e_vsi_free_irq(vsi);
i40e_vsi_free_tx_resources(vsi);
i40e_vsi_free_rx_resources(vsi);
vsi->current_netdev_flags = 0;
- if (test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state))
- reset = true;
- i40e_notify_client_of_netdev_close(vsi, reset);
+ pf->flags |= I40E_FLAG_SERVICE_CLIENT_REQUESTED;
+ if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state))
+ pf->flags |= I40E_FLAG_CLIENT_RESET;
}
/**
@@ -4485,14 +4392,6 @@ static void i40e_quiesce_vsi(struct i40e_vsi *vsi)
if (test_bit(__I40E_DOWN, &vsi->state))
return;
- /* No need to disable FCoE VSI when Tx suspended */
- if ((test_bit(__I40E_PORT_TX_SUSPENDED, &vsi->back->state)) &&
- vsi->type == I40E_VSI_FCOE) {
- dev_dbg(&vsi->back->pdev->dev,
- "VSI seid %d skipping FCoE VSI disable\n", vsi->seid);
- return;
- }
-
set_bit(__I40E_NEEDS_RESTART, &vsi->state);
if (vsi->netdev && netif_running(vsi->netdev))
vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
@@ -4549,7 +4448,7 @@ static void i40e_pf_unquiesce_all_vsi(struct i40e_pf *pf)
* i40e_vsi_wait_queues_disabled - Wait for VSI's queues to be disabled
* @vsi: the VSI being configured
*
- * This function waits for the given VSI's queues to be disabled.
+ * Wait until all queues on a given VSI have been disabled.
**/
static int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi)
{
@@ -4558,7 +4457,7 @@ static int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi)
pf_q = vsi->base_queue;
for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
- /* Check and wait for the disable status of the queue */
+ /* Check and wait for the Tx queue */
ret = i40e_pf_txq_wait(pf, pf_q, false);
if (ret) {
dev_info(&pf->pdev->dev,
@@ -4566,11 +4465,7 @@ static int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi)
vsi->seid, pf_q);
return ret;
}
- }
-
- pf_q = vsi->base_queue;
- for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
- /* Check and wait for the disable status of the queue */
+ /* Check and wait for the Tx queue */
ret = i40e_pf_rxq_wait(pf, pf_q, false);
if (ret) {
dev_info(&pf->pdev->dev,
@@ -4595,8 +4490,7 @@ static int i40e_pf_wait_queues_disabled(struct i40e_pf *pf)
int v, ret = 0;
for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
- /* No need to wait for FCoE VSI queues */
- if (pf->vsi[v] && pf->vsi[v]->type != I40E_VSI_FCOE) {
+ if (pf->vsi[v]) {
ret = i40e_vsi_wait_queues_disabled(pf->vsi[v]);
if (ret)
break;
@@ -4614,16 +4508,15 @@ static int i40e_pf_wait_queues_disabled(struct i40e_pf *pf)
* @vsi: Pointer to VSI struct
*
* This function checks specified queue for given VSI. Detects hung condition.
- * Sets hung bit since it is two step process. Before next run of service task
- * if napi_poll runs, it reset 'hung' bit for respective q_vector. If not,
- * hung condition remain unchanged and during subsequent run, this function
- * issues SW interrupt to recover from hung condition.
+ * We proactively detect hung TX queues by checking if interrupts are disabled
+ * but there are pending descriptors. If it appears hung, attempt to recover
+ * by triggering a SW interrupt.
**/
static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi)
{
struct i40e_ring *tx_ring = NULL;
struct i40e_pf *pf;
- u32 head, val, tx_pending_hw;
+ u32 val, tx_pending;
int i;
pf = vsi->back;
@@ -4649,47 +4542,15 @@ static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi)
else
val = rd32(&pf->hw, I40E_PFINT_DYN_CTL0);
- head = i40e_get_head(tx_ring);
+ tx_pending = i40e_get_tx_pending(tx_ring);
- tx_pending_hw = i40e_get_tx_pending(tx_ring, false);
-
- /* HW is done executing descriptors, updated HEAD write back,
- * but SW hasn't processed those descriptors. If interrupt is
- * not generated from this point ON, it could result into
- * dev_watchdog detecting timeout on those netdev_queue,
- * hence proactively trigger SW interrupt.
+ /* Interrupts are disabled and TX pending is non-zero,
+ * trigger the SW interrupt (don't wait). Worst case
+ * there will be one extra interrupt which may result
+ * into not cleaning any queues because queues are cleaned.
*/
- if (tx_pending_hw && (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))) {
- /* NAPI Poll didn't run and clear since it was set */
- if (test_and_clear_bit(I40E_Q_VECTOR_HUNG_DETECT,
- &tx_ring->q_vector->hung_detected)) {
- netdev_info(vsi->netdev, "VSI_seid %d, Hung TX queue %d, tx_pending_hw: %d, NTC:0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x\n",
- vsi->seid, q_idx, tx_pending_hw,
- tx_ring->next_to_clean, head,
- tx_ring->next_to_use,
- readl(tx_ring->tail));
- netdev_info(vsi->netdev, "VSI_seid %d, Issuing force_wb for TX queue %d, Interrupt Reg: 0x%x\n",
- vsi->seid, q_idx, val);
- i40e_force_wb(vsi, tx_ring->q_vector);
- } else {
- /* First Chance - detected possible hung */
- set_bit(I40E_Q_VECTOR_HUNG_DETECT,
- &tx_ring->q_vector->hung_detected);
- }
- }
-
- /* This is the case where we have interrupts missing,
- * so the tx_pending in HW will most likely be 0, but we
- * will have tx_pending in SW since the WB happened but the
- * interrupt got lost.
- */
- if ((!tx_pending_hw) && i40e_get_tx_pending(tx_ring, true) &&
- (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))) {
- local_bh_disable();
- if (napi_reschedule(&tx_ring->q_vector->napi))
- tx_ring->tx_stats.tx_lost_interrupt++;
- local_bh_enable();
- }
+ if (tx_pending && (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK)))
+ i40e_force_wb(vsi, tx_ring->q_vector);
}
/**
@@ -5220,20 +5081,12 @@ static void i40e_dcb_reconfigure(struct i40e_pf *pf)
continue;
/* - Enable all TCs for the LAN VSI
-#ifdef I40E_FCOE
- * - For FCoE VSI only enable the TC configured
- * as per the APP TLV
-#endif
* - For all others keep them at TC0 for now
*/
if (v == pf->lan_vsi)
tc_map = i40e_pf_get_tc_map(pf);
else
tc_map = I40E_DEFAULT_TRAFFIC_CLASS;
-#ifdef I40E_FCOE
- if (pf->vsi[v]->type == I40E_VSI_FCOE)
- tc_map = i40e_get_fcoe_tc_map(pf);
-#endif /* #ifdef I40E_FCOE */
ret = i40e_vsi_config_tc(pf->vsi[v], tc_map);
if (ret) {
@@ -5300,10 +5153,6 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf)
(hw->dcbx_status == I40E_DCBX_STATUS_DISABLED)) {
dev_info(&pf->pdev->dev,
"DCBX offload is not supported or is disabled for this PF.\n");
-
- if (pf->flags & I40E_FLAG_MFP_ENABLED)
- goto out;
-
} else {
/* When status is not DISABLED then DCBX in FW */
pf->dcbx_cap = DCB_CAP_DCBX_LLD_MANAGED |
@@ -5464,13 +5313,8 @@ static int i40e_up_complete(struct i40e_vsi *vsi)
/* replay FDIR SB filters */
if (vsi->type == I40E_VSI_FDIR) {
/* reset fd counters */
- pf->fd_add_err = pf->fd_atr_cnt = 0;
- if (pf->fd_tcp_rule > 0) {
- pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED;
- if (I40E_DEBUG_FD & pf->hw.debug_mask)
- dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 exist\n");
- pf->fd_tcp_rule = 0;
- }
+ pf->fd_add_err = 0;
+ pf->fd_atr_cnt = 0;
i40e_fdir_filter_restore(vsi);
}
@@ -5542,8 +5386,6 @@ void i40e_down(struct i40e_vsi *vsi)
i40e_clean_rx_ring(vsi->rx_rings[i]);
}
- i40e_notify_client_of_netdev_close(vsi, false);
-
}
/**
@@ -5604,17 +5446,15 @@ static int i40e_setup_tc(struct net_device *netdev, u8 tc)
return ret;
}
-#ifdef I40E_FCOE
-int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto,
- struct tc_to_netdev *tc)
-#else
static int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto,
struct tc_to_netdev *tc)
-#endif
{
- if (handle != TC_H_ROOT || tc->type != TC_SETUP_MQPRIO)
+ if (tc->type != TC_SETUP_MQPRIO)
return -EINVAL;
- return i40e_setup_tc(netdev, tc->tc);
+
+ tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+ return i40e_setup_tc(netdev, tc->mqprio->num_tc);
}
/**
@@ -5667,6 +5507,8 @@ int i40e_open(struct net_device *netdev)
* Finish initialization of the VSI.
*
* Returns 0 on success, negative value on failure
+ *
+ * Note: expects to be called while under rtnl_lock()
**/
int i40e_vsi_open(struct i40e_vsi *vsi)
{
@@ -5730,7 +5572,7 @@ int i40e_vsi_open(struct i40e_vsi *vsi)
err_setup_tx:
i40e_vsi_free_tx_resources(vsi);
if (vsi == pf->vsi[pf->lan_vsi])
- i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED));
+ i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), true);
return err;
}
@@ -5745,6 +5587,7 @@ int i40e_vsi_open(struct i40e_vsi *vsi)
static void i40e_fdir_filter_exit(struct i40e_pf *pf)
{
struct i40e_fdir_filter *filter;
+ struct i40e_flex_pit *pit_entry, *tmp;
struct hlist_node *node2;
hlist_for_each_entry_safe(filter, node2,
@@ -5752,7 +5595,43 @@ static void i40e_fdir_filter_exit(struct i40e_pf *pf)
hlist_del(&filter->fdir_node);
kfree(filter);
}
+
+ list_for_each_entry_safe(pit_entry, tmp, &pf->l3_flex_pit_list, list) {
+ list_del(&pit_entry->list);
+ kfree(pit_entry);
+ }
+ INIT_LIST_HEAD(&pf->l3_flex_pit_list);
+
+ list_for_each_entry_safe(pit_entry, tmp, &pf->l4_flex_pit_list, list) {
+ list_del(&pit_entry->list);
+ kfree(pit_entry);
+ }
+ INIT_LIST_HEAD(&pf->l4_flex_pit_list);
+
pf->fdir_pf_active_filters = 0;
+ pf->fd_tcp4_filter_cnt = 0;
+ pf->fd_udp4_filter_cnt = 0;
+ pf->fd_sctp4_filter_cnt = 0;
+ pf->fd_ip4_filter_cnt = 0;
+
+ /* Reprogram the default input set for TCP/IPv4 */
+ i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_TCP,
+ I40E_L3_SRC_MASK | I40E_L3_DST_MASK |
+ I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
+
+ /* Reprogram the default input set for UDP/IPv4 */
+ i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_UDP,
+ I40E_L3_SRC_MASK | I40E_L3_DST_MASK |
+ I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
+
+ /* Reprogram the default input set for SCTP/IPv4 */
+ i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_SCTP,
+ I40E_L3_SRC_MASK | I40E_L3_DST_MASK |
+ I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
+
+ /* Reprogram the default input set for Other/IPv4 */
+ i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_OTHER,
+ I40E_L3_SRC_MASK | I40E_L3_DST_MASK);
}
/**
@@ -5779,12 +5658,14 @@ int i40e_close(struct net_device *netdev)
* i40e_do_reset - Start a PF or Core Reset sequence
* @pf: board private structure
* @reset_flags: which reset is requested
+ * @lock_acquired: indicates whether or not the lock has been acquired
+ * before this function was called.
*
* The essential difference in resets is that the PF Reset
* doesn't clear the packet buffers, doesn't reset the PE
* firmware, and doesn't bother the other PFs on the chip.
**/
-void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags)
+void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired)
{
u32 val;
@@ -5830,7 +5711,7 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags)
* for the Core Reset.
*/
dev_dbg(&pf->pdev->dev, "PFR requested\n");
- i40e_handle_reset_warning(pf);
+ i40e_handle_reset_warning(pf, lock_acquired);
} else if (reset_flags & BIT_ULL(__I40E_REINIT_REQUESTED)) {
int v;
@@ -6021,8 +5902,8 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
i40e_service_event_schedule(pf);
} else {
i40e_pf_unquiesce_all_vsi(pf);
- /* Notify the client for the DCB changes */
- i40e_notify_client_of_l2_param_changes(pf->vsi[pf->lan_vsi]);
+ pf->flags |= (I40E_FLAG_SERVICE_CLIENT_REQUESTED |
+ I40E_FLAG_CLIENT_L2_CHANGE);
}
exit:
@@ -6039,7 +5920,7 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
void i40e_do_reset_safe(struct i40e_pf *pf, u32 reset_flags)
{
rtnl_lock();
- i40e_do_reset(pf, reset_flags);
+ i40e_do_reset(pf, reset_flags, true);
rtnl_unlock();
}
@@ -6144,8 +6025,8 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf)
(pf->fd_add_err == 0) ||
(i40e_get_current_atr_cnt(pf) < pf->fd_atr_cnt)) {
if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) &&
- (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) {
- pf->auto_disable_flags &= ~I40E_FLAG_FD_SB_ENABLED;
+ (pf->hw_disabled_flags & I40E_FLAG_FD_SB_ENABLED)) {
+ pf->hw_disabled_flags &= ~I40E_FLAG_FD_SB_ENABLED;
if (I40E_DEBUG_FD & pf->hw.debug_mask)
dev_info(&pf->pdev->dev, "FD Sideband/ntuple is being enabled since we have space in the table now\n");
}
@@ -6156,9 +6037,9 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf)
*/
if (fcnt_prog < (fcnt_avail - I40E_FDIR_BUFFER_HEAD_ROOM * 2)) {
if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
- (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED) &&
- (pf->fd_tcp_rule == 0)) {
- pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
+ (pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED) &&
+ (pf->fd_tcp4_filter_cnt == 0)) {
+ pf->hw_disabled_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
if (I40E_DEBUG_FD & pf->hw.debug_mask)
dev_info(&pf->pdev->dev, "ATR is being enabled since we have space in the table and there are no conflicting ntuple rules\n");
}
@@ -6210,7 +6091,7 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf)
}
pf->fd_flush_timestamp = jiffies;
- pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED;
+ pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED;
/* flush all filters */
wr32(&pf->hw, I40E_PFQF_CTL_1,
I40E_PFQF_CTL_1_CLEARFDTABLE_MASK);
@@ -6229,8 +6110,8 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf)
} else {
/* replay sideband filters */
i40e_fdir_filter_restore(pf->vsi[pf->lan_vsi]);
- if (!disable_atr)
- pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
+ if (!disable_atr && !pf->fd_tcp4_filter_cnt)
+ pf->hw_disabled_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
clear_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state);
if (I40E_DEBUG_FD & pf->hw.debug_mask)
dev_info(&pf->pdev->dev, "FD Filter table flushed and FD-SB replayed.\n");
@@ -6283,9 +6164,6 @@ static void i40e_vsi_link_event(struct i40e_vsi *vsi, bool link_up)
switch (vsi->type) {
case I40E_VSI_MAIN:
-#ifdef I40E_FCOE
- case I40E_VSI_FCOE:
-#endif
if (!vsi->netdev || !vsi->netdev_registered)
break;
@@ -6444,7 +6322,6 @@ static void i40e_reset_subtask(struct i40e_pf *pf)
{
u32 reset_flags = 0;
- rtnl_lock();
if (test_bit(__I40E_REINIT_REQUESTED, &pf->state)) {
reset_flags |= BIT(__I40E_REINIT_REQUESTED);
clear_bit(__I40E_REINIT_REQUESTED, &pf->state);
@@ -6470,18 +6347,19 @@ static void i40e_reset_subtask(struct i40e_pf *pf)
* precedence before starting a new reset sequence.
*/
if (test_bit(__I40E_RESET_INTR_RECEIVED, &pf->state)) {
- i40e_handle_reset_warning(pf);
- goto unlock;
+ i40e_prep_for_reset(pf, false);
+ i40e_reset(pf);
+ i40e_rebuild(pf, false, false);
}
/* If we're already down or resetting, just bail */
if (reset_flags &&
!test_bit(__I40E_DOWN, &pf->state) &&
- !test_bit(__I40E_CONFIG_BUSY, &pf->state))
- i40e_do_reset(pf, reset_flags);
-
-unlock:
- rtnl_unlock();
+ !test_bit(__I40E_CONFIG_BUSY, &pf->state)) {
+ rtnl_lock();
+ i40e_do_reset(pf, reset_flags, true);
+ rtnl_unlock();
+ }
}
/**
@@ -6627,9 +6505,11 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf)
opcode);
break;
}
- } while (pending && (i++ < pf->adminq_work_limit));
+ } while (i++ < pf->adminq_work_limit);
- clear_bit(__I40E_ADMINQ_EVENT_PENDING, &pf->state);
+ if (i < pf->adminq_work_limit)
+ clear_bit(__I40E_ADMINQ_EVENT_PENDING, &pf->state);
+
/* re-enable Admin queue interrupt cause */
val = rd32(hw, I40E_PFINT_ICR0_ENA);
val |= I40E_PFINT_ICR0_ENA_ADMINQ_MASK;
@@ -6967,10 +6847,12 @@ static void i40e_fdir_teardown(struct i40e_pf *pf)
/**
* i40e_prep_for_reset - prep for the core to reset
* @pf: board private structure
+ * @lock_acquired: indicates whether or not the lock has been acquired
+ * before this function was called.
*
* Close up the VFs and other things in prep for PF Reset.
**/
-static void i40e_prep_for_reset(struct i40e_pf *pf)
+static void i40e_prep_for_reset(struct i40e_pf *pf, bool lock_acquired)
{
struct i40e_hw *hw = &pf->hw;
i40e_status ret = 0;
@@ -6985,7 +6867,12 @@ static void i40e_prep_for_reset(struct i40e_pf *pf)
dev_dbg(&pf->pdev->dev, "Tearing down internal switch for reset\n");
/* quiesce the VSIs and their queues that are not already DOWN */
+ /* pf_quiesce_all_vsi modifies netdev structures -rtnl_lock needed */
+ if (!lock_acquired)
+ rtnl_lock();
i40e_pf_quiesce_all_vsi(pf);
+ if (!lock_acquired)
+ rtnl_unlock();
for (v = 0; v < pf->num_alloc_vsi; v++) {
if (pf->vsi[v])
@@ -7020,29 +6907,39 @@ static void i40e_send_version(struct i40e_pf *pf)
}
/**
- * i40e_reset_and_rebuild - reset and rebuild using a saved config
+ * i40e_reset - wait for core reset to finish reset, reset pf if corer not seen
+ * @pf: board private structure
+ **/
+static int i40e_reset(struct i40e_pf *pf)
+{
+ struct i40e_hw *hw = &pf->hw;
+ i40e_status ret;
+
+ ret = i40e_pf_reset(hw);
+ if (ret) {
+ dev_info(&pf->pdev->dev, "PF reset failed, %d\n", ret);
+ set_bit(__I40E_RESET_FAILED, &pf->state);
+ clear_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state);
+ } else {
+ pf->pfr_count++;
+ }
+ return ret;
+}
+
+/**
+ * i40e_rebuild - rebuild using a saved config
* @pf: board private structure
* @reinit: if the Main VSI needs to re-initialized.
+ * @lock_acquired: indicates whether or not the lock has been acquired
+ * before this function was called.
**/
-static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
+static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
{
struct i40e_hw *hw = &pf->hw;
u8 set_fc_aq_fail = 0;
i40e_status ret;
u32 val;
- u32 v;
-
- /* Now we wait for GRST to settle out.
- * We don't have to delete the VEBs or VSIs from the hw switch
- * because the reset will make them disappear.
- */
- ret = i40e_pf_reset(hw);
- if (ret) {
- dev_info(&pf->pdev->dev, "PF reset failed, %d\n", ret);
- set_bit(__I40E_RESET_FAILED, &pf->state);
- goto clear_recovery;
- }
- pf->pfr_count++;
+ int v;
if (test_bit(__I40E_DOWN, &pf->state))
goto clear_recovery;
@@ -7067,8 +6964,7 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
goto end_core_reset;
ret = i40e_init_lan_hmc(hw, hw->func_caps.num_tx_qp,
- hw->func_caps.num_rx_qp,
- pf->fcoe_hmc_cntx_num, pf->fcoe_hmc_filt_num);
+ hw->func_caps.num_rx_qp, 0, 0);
if (ret) {
dev_info(&pf->pdev->dev, "init_lan_hmc failed: %d\n", ret);
goto end_core_reset;
@@ -7087,14 +6983,12 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
/* Continue without DCB enabled */
}
#endif /* CONFIG_I40E_DCB */
-#ifdef I40E_FCOE
- i40e_init_pf_fcoe(pf);
-
-#endif
/* do basic switch setup */
+ if (!lock_acquired)
+ rtnl_lock();
ret = i40e_setup_pf_switch(pf, reinit);
if (ret)
- goto end_core_reset;
+ goto end_unlock;
/* The driver only wants link up/down and module qualification
* reports from firmware. Note the negative logic.
@@ -7165,7 +7059,7 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
if (ret) {
dev_info(&pf->pdev->dev,
"rebuild of Main VSI failed: %d\n", ret);
- goto end_core_reset;
+ goto end_unlock;
}
}
@@ -7216,6 +7110,9 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
/* tell the firmware that we're starting */
i40e_send_version(pf);
+end_unlock:
+if (!lock_acquired)
+ rtnl_unlock();
end_core_reset:
clear_bit(__I40E_RESET_FAILED, &pf->state);
clear_recovery:
@@ -7223,16 +7120,38 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
}
/**
+ * i40e_reset_and_rebuild - reset and rebuild using a saved config
+ * @pf: board private structure
+ * @reinit: if the Main VSI needs to re-initialized.
+ * @lock_acquired: indicates whether or not the lock has been acquired
+ * before this function was called.
+ **/
+static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit,
+ bool lock_acquired)
+{
+ int ret;
+ /* Now we wait for GRST to settle out.
+ * We don't have to delete the VEBs or VSIs from the hw switch
+ * because the reset will make them disappear.
+ */
+ ret = i40e_reset(pf);
+ if (!ret)
+ i40e_rebuild(pf, reinit, lock_acquired);
+}
+
+/**
* i40e_handle_reset_warning - prep for the PF to reset, reset and rebuild
* @pf: board private structure
*
* Close up the VFs and other things in prep for a Core Reset,
* then get ready to rebuild the world.
+ * @lock_acquired: indicates whether or not the lock has been acquired
+ * before this function was called.
**/
-static void i40e_handle_reset_warning(struct i40e_pf *pf)
+static void i40e_handle_reset_warning(struct i40e_pf *pf, bool lock_acquired)
{
- i40e_prep_for_reset(pf);
- i40e_reset_and_rebuild(pf, false);
+ i40e_prep_for_reset(pf, lock_acquired);
+ i40e_reset_and_rebuild(pf, false, lock_acquired);
}
/**
@@ -7351,7 +7270,7 @@ static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf)
{
struct i40e_hw *hw = &pf->hw;
i40e_status ret;
- __be16 port;
+ u16 port;
int i;
if (!(pf->flags & I40E_FLAG_UDP_FILTER_SYNC))
@@ -7375,7 +7294,7 @@ static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf)
"%s %s port %d, index %d failed, err %s aq_err %s\n",
pf->udp_ports[i].type ? "vxlan" : "geneve",
port ? "add" : "delete",
- ntohs(port), i,
+ port, i,
i40e_stat_str(&pf->hw, ret),
i40e_aq_str(&pf->hw,
pf->hw.aq.asq_last_status));
@@ -7411,7 +7330,18 @@ static void i40e_service_task(struct work_struct *work)
i40e_vc_process_vflr_event(pf);
i40e_watchdog_subtask(pf);
i40e_fdir_reinit_subtask(pf);
- i40e_client_subtask(pf);
+ if (pf->flags & I40E_FLAG_CLIENT_RESET) {
+ /* Client subtask will reopen next time through. */
+ i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], true);
+ pf->flags &= ~I40E_FLAG_CLIENT_RESET;
+ } else {
+ i40e_client_subtask(pf);
+ if (pf->flags & I40E_FLAG_CLIENT_L2_CHANGE) {
+ i40e_notify_client_of_l2_param_changes(
+ pf->vsi[pf->lan_vsi]);
+ pf->flags &= ~I40E_FLAG_CLIENT_L2_CHANGE;
+ }
+ }
i40e_sync_filters_subtask(pf);
i40e_sync_udp_filters_subtask(pf);
i40e_clean_adminq_subtask(pf);
@@ -7484,15 +7414,6 @@ static int i40e_set_num_rings_in_vsi(struct i40e_vsi *vsi)
I40E_REQ_DESCRIPTOR_MULTIPLE);
break;
-#ifdef I40E_FCOE
- case I40E_VSI_FCOE:
- vsi->alloc_queue_pairs = pf->num_fcoe_qps;
- vsi->num_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
- I40E_REQ_DESCRIPTOR_MULTIPLE);
- vsi->num_q_vectors = pf->num_fcoe_msix;
- break;
-
-#endif /* I40E_FCOE */
default:
WARN_ON(1);
return -ENODATA;
@@ -7809,6 +7730,7 @@ static int i40e_reserve_msix_vectors(struct i40e_pf *pf, int vectors)
static int i40e_init_msix(struct i40e_pf *pf)
{
struct i40e_hw *hw = &pf->hw;
+ int cpus, extra_vectors;
int vectors_left;
int v_budget, i;
int v_actual;
@@ -7827,9 +7749,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
* - assumes symmetric Tx/Rx pairing
* - The number of VMDq pairs
* - The CPU count within the NUMA node if iWARP is enabled
-#ifdef I40E_FCOE
- * - The number of FCOE qps.
-#endif
* Once we count this up, try the request.
*
* If we can't get what we want, we'll simplify to nearly nothing
@@ -7844,10 +7763,16 @@ static int i40e_init_msix(struct i40e_pf *pf)
vectors_left--;
}
- /* reserve vectors for the main PF traffic queues */
- pf->num_lan_msix = min_t(int, num_online_cpus(), vectors_left);
+ /* reserve some vectors for the main PF traffic queues. Initially we
+ * only reserve at most 50% of the available vectors, in the case that
+ * the number of online CPUs is large. This ensures that we can enable
+ * extra features as well. Once we've enabled the other features, we
+ * will use any remaining vectors to reach as close as we can to the
+ * number of online CPUs.
+ */
+ cpus = num_online_cpus();
+ pf->num_lan_msix = min_t(int, cpus, vectors_left / 2);
vectors_left -= pf->num_lan_msix;
- v_budget += pf->num_lan_msix;
/* reserve one vector for sideband flow director */
if (pf->flags & I40E_FLAG_FD_SB_ENABLED) {
@@ -7860,20 +7785,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
}
}
-#ifdef I40E_FCOE
- /* can we reserve enough for FCoE? */
- if (pf->flags & I40E_FLAG_FCOE_ENABLED) {
- if (!vectors_left)
- pf->num_fcoe_msix = 0;
- else if (vectors_left >= pf->num_fcoe_qps)
- pf->num_fcoe_msix = pf->num_fcoe_qps;
- else
- pf->num_fcoe_msix = 1;
- v_budget += pf->num_fcoe_msix;
- vectors_left -= pf->num_fcoe_msix;
- }
-
-#endif
/* can we reserve enough for iWARP? */
if (pf->flags & I40E_FLAG_IWARP_ENABLED) {
iwarp_requested = pf->num_iwarp_msix;
@@ -7910,6 +7821,23 @@ static int i40e_init_msix(struct i40e_pf *pf)
}
}
+ /* On systems with a large number of SMP cores, we previously limited
+ * the number of vectors for num_lan_msix to be at most 50% of the
+ * available vectors, to allow for other features. Now, we add back
+ * the remaining vectors. However, we ensure that the total
+ * num_lan_msix will not exceed num_online_cpus(). To do this, we
+ * calculate the number of vectors we can add without going over the
+ * cap of CPUs. For systems with a small number of CPUs this will be
+ * zero.
+ */
+ extra_vectors = min_t(int, cpus - pf->num_lan_msix, vectors_left);
+ pf->num_lan_msix += extra_vectors;
+ vectors_left -= extra_vectors;
+
+ WARN(vectors_left < 0,
+ "Calculation of remaining vectors underflowed. This is an accounting bug when determining total MSI-X vectors.\n");
+
+ v_budget += pf->num_lan_msix;
pf->msix_entries = kcalloc(v_budget, sizeof(struct msix_entry),
GFP_KERNEL);
if (!pf->msix_entries)
@@ -7950,10 +7878,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
pf->num_vmdq_msix = 1; /* force VMDqs to only one vector */
pf->num_vmdq_vsis = 1;
pf->num_vmdq_qps = 1;
-#ifdef I40E_FCOE
- pf->num_fcoe_qps = 0;
- pf->num_fcoe_msix = 0;
-#endif
/* partition out the remaining vectors */
switch (vec) {
@@ -7967,13 +7891,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
} else {
pf->num_lan_msix = 2;
}
-#ifdef I40E_FCOE
- /* give one vector to FCoE */
- if (pf->flags & I40E_FLAG_FCOE_ENABLED) {
- pf->num_lan_msix = 1;
- pf->num_fcoe_msix = 1;
- }
-#endif
break;
default:
if (pf->flags & I40E_FLAG_IWARP_ENABLED) {
@@ -7993,13 +7910,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
(vec - (pf->num_iwarp_msix + pf->num_vmdq_vsis)),
pf->num_lan_msix);
pf->num_lan_qps = pf->num_lan_msix;
-#ifdef I40E_FCOE
- /* give one vector to FCoE */
- if (pf->flags & I40E_FLAG_FCOE_ENABLED) {
- pf->num_fcoe_msix = 1;
- vec--;
- }
-#endif
break;
}
}
@@ -8020,13 +7930,6 @@ static int i40e_init_msix(struct i40e_pf *pf)
dev_info(&pf->pdev->dev, "IWARP disabled, not enough MSI-X vectors\n");
pf->flags &= ~I40E_FLAG_IWARP_ENABLED;
}
-#ifdef I40E_FCOE
-
- if ((pf->flags & I40E_FLAG_FCOE_ENABLED) && (pf->num_fcoe_msix == 0)) {
- dev_info(&pf->pdev->dev, "FCOE disabled, not enough MSI-X vectors\n");
- pf->flags &= ~I40E_FLAG_FCOE_ENABLED;
- }
-#endif
i40e_debug(&pf->hw, I40E_DEBUG_INIT,
"MSI-X vector distribution: PF %d, VMDq %d, FDSB %d, iWARP %d\n",
pf->num_lan_msix,
@@ -8125,9 +8028,6 @@ static int i40e_init_interrupt_scheme(struct i40e_pf *pf)
if (vectors < 0) {
pf->flags &= ~(I40E_FLAG_MSIX_ENABLED |
I40E_FLAG_IWARP_ENABLED |
-#ifdef I40E_FCOE
- I40E_FLAG_FCOE_ENABLED |
-#endif
I40E_FLAG_RSS_ENABLED |
I40E_FLAG_DCB_CAPABLE |
I40E_FLAG_DCB_ENABLED |
@@ -8360,13 +8260,10 @@ static int i40e_config_rss_reg(struct i40e_vsi *vsi, const u8 *seed,
if (vsi->type == I40E_VSI_MAIN) {
for (i = 0; i <= I40E_PFQF_HKEY_MAX_INDEX; i++)
- i40e_write_rx_ctl(hw, I40E_PFQF_HKEY(i),
- seed_dw[i]);
+ wr32(hw, I40E_PFQF_HKEY(i), seed_dw[i]);
} else if (vsi->type == I40E_VSI_SRIOV) {
for (i = 0; i <= I40E_VFQF_HKEY1_MAX_INDEX; i++)
- i40e_write_rx_ctl(hw,
- I40E_VFQF_HKEY1(i, vf_id),
- seed_dw[i]);
+ wr32(hw, I40E_VFQF_HKEY1(i, vf_id), seed_dw[i]);
} else {
dev_err(&pf->pdev->dev, "Cannot set RSS seed - invalid VSI type\n");
}
@@ -8384,9 +8281,7 @@ static int i40e_config_rss_reg(struct i40e_vsi *vsi, const u8 *seed,
if (lut_size != I40E_VF_HLUT_ARRAY_SIZE)
return -EINVAL;
for (i = 0; i <= I40E_VFQF_HLUT_MAX_INDEX; i++)
- i40e_write_rx_ctl(hw,
- I40E_VFQF_HLUT1(i, vf_id),
- lut_dw[i]);
+ wr32(hw, I40E_VFQF_HLUT1(i, vf_id), lut_dw[i]);
} else {
dev_err(&pf->pdev->dev, "Cannot set RSS LUT - invalid VSI type\n");
}
@@ -8514,9 +8409,12 @@ static int i40e_pf_config_rss(struct i40e_pf *pf)
i40e_write_rx_ctl(hw, I40E_PFQF_CTL_0, reg_val);
/* Determine the RSS size of the VSI */
- if (!vsi->rss_size)
- vsi->rss_size = min_t(int, pf->alloc_rss_size,
- vsi->num_queue_pairs);
+ if (!vsi->rss_size) {
+ u16 qcount;
+
+ qcount = vsi->num_queue_pairs / vsi->tc_config.numtc;
+ vsi->rss_size = min_t(int, pf->alloc_rss_size, qcount);
+ }
if (!vsi->rss_size)
return -EINVAL;
@@ -8550,6 +8448,7 @@ static int i40e_pf_config_rss(struct i40e_pf *pf)
*
* returns 0 if rss is not enabled, if enabled returns the final rss queue
* count which may be different from the requested queue count.
+ * Note: expects to be called while under rtnl_lock()
**/
int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count)
{
@@ -8562,12 +8461,14 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count)
new_rss_size = min_t(int, queue_count, pf->rss_size_max);
if (queue_count != vsi->num_queue_pairs) {
+ u16 qcount;
+
vsi->req_queue_pairs = queue_count;
- i40e_prep_for_reset(pf);
+ i40e_prep_for_reset(pf, true);
pf->alloc_rss_size = new_rss_size;
- i40e_reset_and_rebuild(pf, true);
+ i40e_reset_and_rebuild(pf, true, true);
/* Discard the user configured hash keys and lut, if less
* queues are enabled.
@@ -8579,8 +8480,8 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count)
}
/* Reset vsi->rss_size, as number of enabled queues changed */
- vsi->rss_size = min_t(int, pf->alloc_rss_size,
- vsi->num_queue_pairs);
+ qcount = vsi->num_queue_pairs / vsi->tc_config.numtc;
+ vsi->rss_size = min_t(int, pf->alloc_rss_size, qcount);
i40e_pf_config_rss(pf);
}
@@ -8813,10 +8714,6 @@ static int i40e_sw_init(struct i40e_pf *pf)
pf->num_iwarp_msix = (int)num_online_cpus() + 1;
}
-#ifdef I40E_FCOE
- i40e_init_pf_fcoe(pf);
-
-#endif /* I40E_FCOE */
#ifdef CONFIG_PCI_IOV
if (pf->hw.func_caps.num_vfs && pf->hw.partition_id == 1) {
pf->num_vf_qps = I40E_DEFAULT_QUEUES_PER_VF;
@@ -8843,9 +8740,9 @@ static int i40e_sw_init(struct i40e_pf *pf)
(pf->hw.aq.api_min_ver > 4))) {
/* Supported in FW API version higher than 1.4 */
pf->flags |= I40E_FLAG_GENEVE_OFFLOAD_CAPABLE;
- pf->auto_disable_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE;
+ pf->hw_disabled_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE;
} else {
- pf->auto_disable_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE;
+ pf->hw_disabled_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE;
}
pf->eeprom_version = 0xDEAD;
@@ -8906,14 +8803,14 @@ bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features)
i40e_fdir_filter_exit(pf);
}
pf->flags &= ~I40E_FLAG_FD_SB_ENABLED;
- pf->auto_disable_flags &= ~I40E_FLAG_FD_SB_ENABLED;
+ pf->hw_disabled_flags &= ~I40E_FLAG_FD_SB_ENABLED;
/* reset fd counters */
- pf->fd_add_err = pf->fd_atr_cnt = pf->fd_tcp_rule = 0;
- pf->fdir_pf_active_filters = 0;
+ pf->fd_add_err = 0;
+ pf->fd_atr_cnt = 0;
/* if ATR was auto disabled it can be re-enabled. */
if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
- (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED)) {
- pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
+ (pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED)) {
+ pf->hw_disabled_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
if (I40E_DEBUG_FD & pf->hw.debug_mask)
dev_info(&pf->pdev->dev, "ATR re-enabled.\n");
}
@@ -8947,6 +8844,7 @@ static void i40e_clear_rss_lut(struct i40e_vsi *vsi)
* i40e_set_features - set the netdev feature flags
* @netdev: ptr to the netdev being adjusted
* @features: the feature set that the stack is suggesting
+ * Note: expects to be called while under rtnl_lock()
**/
static int i40e_set_features(struct net_device *netdev,
netdev_features_t features)
@@ -8970,7 +8868,7 @@ static int i40e_set_features(struct net_device *netdev,
need_reset = i40e_set_ntuple(pf, features);
if (need_reset)
- i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED));
+ i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), true);
return 0;
}
@@ -8982,7 +8880,7 @@ static int i40e_set_features(struct net_device *netdev,
*
* Returns the index number or I40E_MAX_PF_UDP_OFFLOAD_PORTS if port not found
**/
-static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, __be16 port)
+static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, u16 port)
{
u8 i;
@@ -9005,7 +8903,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev,
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
struct i40e_pf *pf = vsi->back;
- __be16 port = ti->port;
+ u16 port = ntohs(ti->port);
u8 next_idx;
u8 idx;
@@ -9013,8 +8911,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev,
/* Check if port already exists */
if (idx < I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
- netdev_info(netdev, "port %d already offloaded\n",
- ntohs(port));
+ netdev_info(netdev, "port %d already offloaded\n", port);
return;
}
@@ -9023,7 +8920,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev,
if (next_idx == I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
netdev_info(netdev, "maximum number of offloaded UDP ports reached, not adding port %d\n",
- ntohs(port));
+ port);
return;
}
@@ -9057,7 +8954,7 @@ static void i40e_udp_tunnel_del(struct net_device *netdev,
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
struct i40e_pf *pf = vsi->back;
- __be16 port = ti->port;
+ u16 port = ntohs(ti->port);
u8 idx;
idx = i40e_get_udp_port_idx(pf, port);
@@ -9089,7 +8986,7 @@ static void i40e_udp_tunnel_del(struct net_device *netdev,
return;
not_found:
netdev_warn(netdev, "UDP port %d was not found, not deleting\n",
- ntohs(port));
+ port);
}
static int i40e_get_phys_port_id(struct net_device *netdev,
@@ -9166,6 +9063,8 @@ static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
* is to change the mode then that requires a PF reset to
* allow rebuild of the components with required hardware
* bridge mode enabled.
+ *
+ * Note: expects to be called while under rtnl_lock()
**/
static int i40e_ndo_bridge_setlink(struct net_device *dev,
struct nlmsghdr *nlh,
@@ -9221,7 +9120,8 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev,
pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
else
pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED;
- i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED));
+ i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED),
+ true);
break;
}
}
@@ -9344,10 +9244,6 @@ static const struct net_device_ops i40e_netdev_ops = {
.ndo_poll_controller = i40e_netpoll,
#endif
.ndo_setup_tc = __i40e_setup_tc,
-#ifdef I40E_FCOE
- .ndo_fcoe_enable = i40e_fcoe_enable,
- .ndo_fcoe_disable = i40e_fcoe_disable,
-#endif
.ndo_set_features = i40e_set_features,
.ndo_set_vf_mac = i40e_ndo_set_vf_mac,
.ndo_set_vf_vlan = i40e_ndo_set_vf_port_vlan,
@@ -9380,6 +9276,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
u8 broadcast[ETH_ALEN];
u8 mac_addr[ETH_ALEN];
int etherdev_size;
+ netdev_features_t hw_enc_features;
+ netdev_features_t hw_features;
etherdev_size = sizeof(struct i40e_netdev_priv);
netdev = alloc_etherdev_mq(etherdev_size, vsi->alloc_queue_pairs);
@@ -9390,52 +9288,57 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
np = netdev_priv(netdev);
np->vsi = vsi;
- netdev->hw_enc_features |= NETIF_F_SG |
- NETIF_F_IP_CSUM |
- NETIF_F_IPV6_CSUM |
- NETIF_F_HIGHDMA |
- NETIF_F_SOFT_FEATURES |
- NETIF_F_TSO |
- NETIF_F_TSO_ECN |
- NETIF_F_TSO6 |
- NETIF_F_GSO_GRE |
- NETIF_F_GSO_GRE_CSUM |
- NETIF_F_GSO_IPXIP4 |
- NETIF_F_GSO_IPXIP6 |
- NETIF_F_GSO_UDP_TUNNEL |
- NETIF_F_GSO_UDP_TUNNEL_CSUM |
- NETIF_F_GSO_PARTIAL |
- NETIF_F_SCTP_CRC |
- NETIF_F_RXHASH |
- NETIF_F_RXCSUM |
- 0;
+ hw_enc_features = NETIF_F_SG |
+ NETIF_F_IP_CSUM |
+ NETIF_F_IPV6_CSUM |
+ NETIF_F_HIGHDMA |
+ NETIF_F_SOFT_FEATURES |
+ NETIF_F_TSO |
+ NETIF_F_TSO_ECN |
+ NETIF_F_TSO6 |
+ NETIF_F_GSO_GRE |
+ NETIF_F_GSO_GRE_CSUM |
+ NETIF_F_GSO_PARTIAL |
+ NETIF_F_GSO_UDP_TUNNEL |
+ NETIF_F_GSO_UDP_TUNNEL_CSUM |
+ NETIF_F_SCTP_CRC |
+ NETIF_F_RXHASH |
+ NETIF_F_RXCSUM |
+ 0;
if (!(pf->flags & I40E_FLAG_OUTER_UDP_CSUM_CAPABLE))
netdev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
+ netdev->hw_enc_features |= hw_enc_features;
+
/* record features VLANs can make use of */
- netdev->vlan_features |= netdev->hw_enc_features |
- NETIF_F_TSO_MANGLEID;
+ netdev->vlan_features |= hw_enc_features | NETIF_F_TSO_MANGLEID;
if (!(pf->flags & I40E_FLAG_MFP_ENABLED))
netdev->hw_features |= NETIF_F_NTUPLE;
+ hw_features = hw_enc_features |
+ NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_CTAG_RX;
- netdev->hw_features |= netdev->hw_enc_features |
- NETIF_F_HW_VLAN_CTAG_TX |
- NETIF_F_HW_VLAN_CTAG_RX;
+ netdev->hw_features |= hw_features;
- netdev->features |= netdev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER;
+ netdev->features |= hw_features | NETIF_F_HW_VLAN_CTAG_FILTER;
netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID;
if (vsi->type == I40E_VSI_MAIN) {
SET_NETDEV_DEV(netdev, &pf->pdev->dev);
ether_addr_copy(mac_addr, hw->mac.perm_addr);
- /* The following steps are necessary to prevent reception
- * of tagged packets - some older NVM configurations load a
- * default a MAC-VLAN filter that accepts any tagged packet
- * which must be replaced by a normal filter.
+ /* The following steps are necessary for two reasons. First,
+ * some older NVM configurations load a default MAC-VLAN
+ * filter that will accept any tagged packet, and we want to
+ * replace this with a normal filter. Additionally, it is
+ * possible our MAC address was provided by the platform using
+ * Open Firmware or similar.
+ *
+ * Thus, we need to remove the default filter and install one
+ * specific to the MAC address.
*/
i40e_rm_default_mac_filter(vsi, mac_addr);
spin_lock_bh(&vsi->mac_filter_hash_lock);
@@ -9481,9 +9384,6 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
netdev->netdev_ops = &i40e_netdev_ops;
netdev->watchdog_timeo = 5 * HZ;
i40e_set_ethtool_ops(netdev);
-#ifdef I40E_FCOE
- i40e_fcoe_config_netdev(netdev, vsi);
-#endif
/* MTU range: 68 - 9706 */
netdev->min_mtu = ETH_MIN_MTU;
@@ -9707,16 +9607,6 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
i40e_vsi_setup_queue_map(vsi, &ctxt, enabled_tc, true);
break;
-#ifdef I40E_FCOE
- case I40E_VSI_FCOE:
- ret = i40e_fcoe_vsi_init(vsi, &ctxt);
- if (ret) {
- dev_info(&pf->pdev->dev, "failed to initialize FCoE VSI\n");
- return ret;
- }
- break;
-
-#endif /* I40E_FCOE */
case I40E_VSI_IWARP:
/* send down message to iWARP */
break;
@@ -10133,7 +10023,6 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
}
}
case I40E_VSI_VMDQ2:
- case I40E_VSI_FCOE:
ret = i40e_config_netdev(vsi);
if (ret)
goto err_netdev;
@@ -10793,9 +10682,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
int queues_left;
pf->num_lan_qps = 0;
-#ifdef I40E_FCOE
- pf->num_fcoe_qps = 0;
-#endif
/* Find the max queues to be put into basic use. We'll always be
* using TC0, whether or not DCB is running, and TC0 will get the
@@ -10812,9 +10698,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
/* make sure all the fancies are disabled */
pf->flags &= ~(I40E_FLAG_RSS_ENABLED |
I40E_FLAG_IWARP_ENABLED |
-#ifdef I40E_FCOE
- I40E_FLAG_FCOE_ENABLED |
-#endif
I40E_FLAG_FD_SB_ENABLED |
I40E_FLAG_FD_ATR_ENABLED |
I40E_FLAG_DCB_CAPABLE |
@@ -10831,9 +10714,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
pf->flags &= ~(I40E_FLAG_RSS_ENABLED |
I40E_FLAG_IWARP_ENABLED |
-#ifdef I40E_FCOE
- I40E_FLAG_FCOE_ENABLED |
-#endif
I40E_FLAG_FD_SB_ENABLED |
I40E_FLAG_FD_ATR_ENABLED |
I40E_FLAG_DCB_ENABLED |
@@ -10854,22 +10734,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
queues_left -= pf->num_lan_qps;
}
-#ifdef I40E_FCOE
- if (pf->flags & I40E_FLAG_FCOE_ENABLED) {
- if (I40E_DEFAULT_FCOE <= queues_left) {
- pf->num_fcoe_qps = I40E_DEFAULT_FCOE;
- } else if (I40E_MINIMUM_FCOE <= queues_left) {
- pf->num_fcoe_qps = I40E_MINIMUM_FCOE;
- } else {
- pf->num_fcoe_qps = 0;
- pf->flags &= ~I40E_FLAG_FCOE_ENABLED;
- dev_info(&pf->pdev->dev, "not enough queues for FCoE. FCoE feature will be disabled\n");
- }
-
- queues_left -= pf->num_fcoe_qps;
- }
-
-#endif
if (pf->flags & I40E_FLAG_FD_SB_ENABLED) {
if (queues_left > 1) {
queues_left -= 1; /* save 1 queue for FD */
@@ -10901,9 +10765,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
pf->num_lan_qps, pf->alloc_rss_size, pf->num_req_vfs,
pf->num_vf_qps, pf->num_vmdq_vsis, pf->num_vmdq_qps,
queues_left);
-#ifdef I40E_FCOE
- dev_dbg(&pf->pdev->dev, "fcoe queues = %d\n", pf->num_fcoe_qps);
-#endif
}
/**
@@ -10970,10 +10831,6 @@ static void i40e_print_features(struct i40e_pf *pf)
i += snprintf(&buf[i], REMAIN(i), " Geneve");
if (pf->flags & I40E_FLAG_PTP)
i += snprintf(&buf[i], REMAIN(i), " PTP");
-#ifdef I40E_FCOE
- if (pf->flags & I40E_FLAG_FCOE_ENABLED)
- i += snprintf(&buf[i], REMAIN(i), " FCOE");
-#endif
if (pf->flags & I40E_FLAG_VEB_MODE_ENABLED)
i += snprintf(&buf[i], REMAIN(i), " VEB");
else
@@ -10986,20 +10843,18 @@ static void i40e_print_features(struct i40e_pf *pf)
/**
* i40e_get_platform_mac_addr - get platform-specific MAC address
- *
* @pdev: PCI device information struct
* @pf: board private structure
*
- * Look up the MAC address in Open Firmware on systems that support it,
- * and use IDPROM on SPARC if no OF address is found. On return, the
- * I40E_FLAG_PF_MAC will be wset in pf->flags if a platform-specific value
- * has been selected.
+ * Look up the MAC address for the device. First we'll try
+ * eth_platform_get_mac_address, which will check Open Firmware, or arch
+ * specific fallback. Otherwise, we'll default to the stored value in
+ * firmware.
**/
static void i40e_get_platform_mac_addr(struct pci_dev *pdev, struct i40e_pf *pf)
{
- pf->flags &= ~I40E_FLAG_PF_MAC;
- if (!eth_platform_get_mac_address(&pdev->dev, pf->hw.mac.addr))
- pf->flags |= I40E_FLAG_PF_MAC;
+ if (eth_platform_get_mac_address(&pdev->dev, pf->hw.mac.addr))
+ i40e_get_mac_addr(&pf->hw, pf->hw.mac.addr);
}
/**
@@ -11090,6 +10945,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
hw->bus.bus_id = pdev->bus->number;
pf->instance = pfs_found;
+ INIT_LIST_HEAD(&pf->l3_flex_pit_list);
+ INIT_LIST_HEAD(&pf->l4_flex_pit_list);
+
/* set up the locks for the AQ, do this only once in probe
* and destroy them only once in remove
*/
@@ -11188,8 +11046,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
}
err = i40e_init_lan_hmc(hw, hw->func_caps.num_tx_qp,
- hw->func_caps.num_rx_qp,
- pf->fcoe_hmc_cntx_num, pf->fcoe_hmc_filt_num);
+ hw->func_caps.num_rx_qp, 0, 0);
if (err) {
dev_info(&pdev->dev, "init_lan_hmc failed: %d\n", err);
goto err_init_lan_hmc;
@@ -11211,9 +11068,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
i40e_aq_stop_lldp(hw, true, NULL);
}
- i40e_get_mac_addr(hw, hw->mac.addr);
/* allow a platform config to override the HW addr */
i40e_get_platform_mac_addr(pdev, pf);
+
if (!is_valid_ether_addr(hw->mac.addr)) {
dev_info(&pdev->dev, "invalid MAC address %pM\n", hw->mac.addr);
err = -EIO;
@@ -11224,18 +11081,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
i40e_get_port_mac_addr(hw, hw->mac.port_addr);
if (is_valid_ether_addr(hw->mac.port_addr))
pf->flags |= I40E_FLAG_PORT_ID_VALID;
-#ifdef I40E_FCOE
- err = i40e_get_san_mac_addr(hw, hw->mac.san_addr);
- if (err)
- dev_info(&pdev->dev,
- "(non-fatal) SAN MAC retrieval failed: %d\n", err);
- if (!is_valid_ether_addr(hw->mac.san_addr)) {
- dev_warn(&pdev->dev, "invalid SAN MAC address %pM, falling back to LAN MAC\n",
- hw->mac.san_addr);
- ether_addr_copy(hw->mac.san_addr, hw->mac.addr);
- }
- dev_info(&pf->pdev->dev, "SAN MAC: %pM\n", hw->mac.san_addr);
-#endif /* I40E_FCOE */
pci_set_drvdata(pdev, pf);
pci_save_state(pdev);
@@ -11254,7 +11099,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
INIT_WORK(&pf->service_task, i40e_service_task);
clear_bit(__I40E_SERVICE_SCHED, &pf->state);
- pf->flags |= I40E_FLAG_NEED_LINK_UPDATE;
/* NVM bit on means WoL disabled for the port */
i40e_read_nvm_word(hw, I40E_SR_NVM_WAKE_ON_LAN, &wol_nvm_bits);
@@ -11426,16 +11270,13 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
round_jiffies(jiffies + pf->service_timer_period));
/* add this PF to client device list and launch a client service task */
- err = i40e_lan_add_device(pf);
- if (err)
- dev_info(&pdev->dev, "Failed to add PF to client API service list: %d\n",
- err);
+ if (pf->flags & I40E_FLAG_IWARP_ENABLED) {
+ err = i40e_lan_add_device(pf);
+ if (err)
+ dev_info(&pdev->dev, "Failed to add PF to client API service list: %d\n",
+ err);
+ }
-#ifdef I40E_FCOE
- /* create FCoE interface */
- i40e_fcoe_vsi_setup(pf);
-
-#endif
#define PCI_SPEED_SIZE 8
#define PCI_WIDTH_SIZE 8
/* Devices on the IOSF bus do not have this information
@@ -11581,6 +11422,11 @@ static void i40e_remove(struct pci_dev *pdev)
if (pf->service_task.func)
cancel_work_sync(&pf->service_task);
+ /* Client close must be called explicitly here because the timer
+ * has been stopped.
+ */
+ i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false);
+
if (pf->flags & I40E_FLAG_SRIOV_ENABLED) {
i40e_free_vfs(pf);
pf->flags &= ~I40E_FLAG_SRIOV_ENABLED;
@@ -11607,10 +11453,11 @@ static void i40e_remove(struct pci_dev *pdev)
i40e_vsi_release(pf->vsi[pf->lan_vsi]);
/* remove attached clients */
- ret_code = i40e_lan_del_device(pf);
- if (ret_code) {
- dev_warn(&pdev->dev, "Failed to delete client device: %d\n",
- ret_code);
+ if (pf->flags & I40E_FLAG_IWARP_ENABLED) {
+ ret_code = i40e_lan_del_device(pf);
+ if (ret_code)
+ dev_warn(&pdev->dev, "Failed to delete client device: %d\n",
+ ret_code);
}
/* shutdown and destroy the HMC */
@@ -11679,7 +11526,7 @@ static pci_ers_result_t i40e_pci_error_detected(struct pci_dev *pdev,
/* shutdown all operations */
if (!test_bit(__I40E_SUSPENDED, &pf->state)) {
rtnl_lock();
- i40e_prep_for_reset(pf);
+ i40e_prep_for_reset(pf, true);
rtnl_unlock();
}
@@ -11748,7 +11595,7 @@ static void i40e_pci_error_resume(struct pci_dev *pdev)
return;
rtnl_lock();
- i40e_handle_reset_warning(pf);
+ i40e_handle_reset_warning(pf, true);
rtnl_unlock();
}
@@ -11811,7 +11658,7 @@ static void i40e_shutdown(struct pci_dev *pdev)
set_bit(__I40E_SUSPENDED, &pf->state);
set_bit(__I40E_DOWN, &pf->state);
rtnl_lock();
- i40e_prep_for_reset(pf);
+ i40e_prep_for_reset(pf, true);
rtnl_unlock();
wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0));
@@ -11821,11 +11668,16 @@ static void i40e_shutdown(struct pci_dev *pdev)
cancel_work_sync(&pf->service_task);
i40e_fdir_teardown(pf);
+ /* Client close must be called explicitly here because the timer
+ * has been stopped.
+ */
+ i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false);
+
if (pf->wol_en && (pf->flags & I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE))
i40e_enable_mc_magic_wake(pf);
rtnl_lock();
- i40e_prep_for_reset(pf);
+ i40e_prep_for_reset(pf, true);
rtnl_unlock();
wr32(hw, I40E_PFPM_APM,
@@ -11859,7 +11711,7 @@ static int i40e_suspend(struct pci_dev *pdev, pm_message_t state)
i40e_enable_mc_magic_wake(pf);
rtnl_lock();
- i40e_prep_for_reset(pf);
+ i40e_prep_for_reset(pf, true);
rtnl_unlock();
wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0));
@@ -11907,7 +11759,7 @@ static int i40e_resume(struct pci_dev *pdev)
if (test_and_clear_bit(__I40E_SUSPENDED, &pf->state)) {
clear_bit(__I40E_DOWN, &pf->state);
rtnl_lock();
- i40e_reset_and_rebuild(pf, false);
+ i40e_reset_and_rebuild(pf, false, true);
rtnl_unlock();
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
index 38ee18f..800bd55 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
@@ -292,14 +292,14 @@ i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset,
{
enum i40e_status_code ret_code = 0;
- if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) {
- ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
- if (!ret_code) {
+ ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
+ if (!ret_code) {
+ if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) {
ret_code = i40e_read_nvm_word_aq(hw, offset, data);
- i40e_release_nvm(hw);
+ } else {
+ ret_code = i40e_read_nvm_word_srctl(hw, offset, data);
}
- } else {
- ret_code = i40e_read_nvm_word_srctl(hw, offset, data);
+ i40e_release_nvm(hw);
}
return ret_code;
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_osdep.h b/drivers/net/ethernet/intel/i40e/i40e_osdep.h
index fea81ed..80e66da 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_osdep.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_osdep.h
@@ -78,7 +78,4 @@ do { \
} while (0)
typedef enum i40e_status_code i40e_status;
-#ifdef CONFIG_I40E_FCOE
-#define I40E_FCOE
-#endif
#endif /* _I40E_OSDEP_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index 2551fc8..dfc5e59 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -304,9 +304,6 @@ i40e_status i40e_read_pba_string(struct i40e_hw *hw, u8 *pba_num,
u32 pba_num_size);
i40e_status i40e_validate_mac_addr(u8 *mac_addr);
void i40e_pre_tx_queue_cfg(struct i40e_hw *hw, u32 queue, bool enable);
-#ifdef I40E_FCOE
-i40e_status i40e_get_san_mac_addr(struct i40e_hw *hw, u8 *mac_addr);
-#endif
/* prototype for functions used for NVM access */
i40e_status i40e_init_nvm(struct i40e_hw *hw);
i40e_status i40e_acquire_nvm(struct i40e_hw *hw,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 97d4605..20691d2 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -71,6 +71,9 @@ static void i40e_fdir(struct i40e_ring *tx_ring,
flex_ptype |= I40E_TXD_FLTR_QW0_PCTYPE_MASK &
(fdata->pctype << I40E_TXD_FLTR_QW0_PCTYPE_SHIFT);
+ flex_ptype |= I40E_TXD_FLTR_QW0_PCTYPE_MASK &
+ (fdata->flex_offset << I40E_TXD_FLTR_QW0_FLEXOFF_SHIFT);
+
/* Use LAN VSI Id if not programmed by user */
flex_ptype |= I40E_TXD_FLTR_QW0_DEST_VSI_MASK &
((u32)(fdata->dest_vsi ? : pf->vsi[pf->lan_vsi]->id) <<
@@ -203,7 +206,6 @@ static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi,
struct i40e_pf *pf = vsi->back;
struct udphdr *udp;
struct iphdr *ip;
- bool err = false;
u8 *raw_packet;
int ret;
static char packet[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0,
@@ -219,18 +221,28 @@ static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi,
udp = (struct udphdr *)(raw_packet + IP_HEADER_OFFSET
+ sizeof(struct iphdr));
- ip->daddr = fd_data->dst_ip[0];
+ ip->daddr = fd_data->dst_ip;
udp->dest = fd_data->dst_port;
- ip->saddr = fd_data->src_ip[0];
+ ip->saddr = fd_data->src_ip;
udp->source = fd_data->src_port;
+ if (fd_data->flex_filter) {
+ u8 *payload = raw_packet + I40E_UDPIP_DUMMY_PACKET_LEN;
+ __be16 pattern = fd_data->flex_word;
+ u16 off = fd_data->flex_offset;
+
+ *((__force __be16 *)(payload + off)) = pattern;
+ }
+
fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_UDP;
ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add);
if (ret) {
dev_info(&pf->pdev->dev,
"PCTYPE:%d, Filter command send failed for fd_id:%d (ret = %d)\n",
fd_data->pctype, fd_data->fd_id, ret);
- err = true;
+ /* Free the packet buffer since it wasn't added to the ring */
+ kfree(raw_packet);
+ return -EOPNOTSUPP;
} else if (I40E_DEBUG_FD & pf->hw.debug_mask) {
if (add)
dev_info(&pf->pdev->dev,
@@ -241,10 +253,13 @@ static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi,
"Filter deleted for PCTYPE %d loc = %d\n",
fd_data->pctype, fd_data->fd_id);
}
- if (err)
- kfree(raw_packet);
- return err ? -EOPNOTSUPP : 0;
+ if (add)
+ pf->fd_udp4_filter_cnt++;
+ else
+ pf->fd_udp4_filter_cnt--;
+
+ return 0;
}
#define I40E_TCPIP_DUMMY_PACKET_LEN 54
@@ -263,7 +278,6 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi,
struct i40e_pf *pf = vsi->back;
struct tcphdr *tcp;
struct iphdr *ip;
- bool err = false;
u8 *raw_packet;
int ret;
/* Dummy packet */
@@ -281,36 +295,28 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi,
tcp = (struct tcphdr *)(raw_packet + IP_HEADER_OFFSET
+ sizeof(struct iphdr));
- ip->daddr = fd_data->dst_ip[0];
+ ip->daddr = fd_data->dst_ip;
tcp->dest = fd_data->dst_port;
- ip->saddr = fd_data->src_ip[0];
+ ip->saddr = fd_data->src_ip;
tcp->source = fd_data->src_port;
- if (add) {
- pf->fd_tcp_rule++;
- if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
- I40E_DEBUG_FD & pf->hw.debug_mask)
- dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 flow being applied\n");
- pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED;
- } else {
- pf->fd_tcp_rule = (pf->fd_tcp_rule > 0) ?
- (pf->fd_tcp_rule - 1) : 0;
- if (pf->fd_tcp_rule == 0) {
- if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
- I40E_DEBUG_FD & pf->hw.debug_mask)
- dev_info(&pf->pdev->dev, "ATR re-enabled due to no sideband TCP/IPv4 rules\n");
- pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
- }
+ if (fd_data->flex_filter) {
+ u8 *payload = raw_packet + I40E_TCPIP_DUMMY_PACKET_LEN;
+ __be16 pattern = fd_data->flex_word;
+ u16 off = fd_data->flex_offset;
+
+ *((__force __be16 *)(payload + off)) = pattern;
}
fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add);
-
if (ret) {
dev_info(&pf->pdev->dev,
"PCTYPE:%d, Filter command send failed for fd_id:%d (ret = %d)\n",
fd_data->pctype, fd_data->fd_id, ret);
- err = true;
+ /* Free the packet buffer since it wasn't added to the ring */
+ kfree(raw_packet);
+ return -EOPNOTSUPP;
} else if (I40E_DEBUG_FD & pf->hw.debug_mask) {
if (add)
dev_info(&pf->pdev->dev, "Filter OK for PCTYPE %d loc = %d)\n",
@@ -321,10 +327,97 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi,
fd_data->pctype, fd_data->fd_id);
}
- if (err)
- kfree(raw_packet);
+ if (add) {
+ pf->fd_tcp4_filter_cnt++;
+ if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
+ I40E_DEBUG_FD & pf->hw.debug_mask)
+ dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 flow being applied\n");
+ pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED;
+ } else {
+ pf->fd_tcp4_filter_cnt--;
+ if (pf->fd_tcp4_filter_cnt == 0) {
+ if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
+ I40E_DEBUG_FD & pf->hw.debug_mask)
+ dev_info(&pf->pdev->dev, "ATR re-enabled due to no sideband TCP/IPv4 rules\n");
+ pf->hw_disabled_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
+ }
+ }
- return err ? -EOPNOTSUPP : 0;
+ return 0;
+}
+
+#define I40E_SCTPIP_DUMMY_PACKET_LEN 46
+/**
+ * i40e_add_del_fdir_sctpv4 - Add/Remove SCTPv4 Flow Director filters for
+ * a specific flow spec
+ * @vsi: pointer to the targeted VSI
+ * @fd_data: the flow director data required for the FDir descriptor
+ * @add: true adds a filter, false removes it
+ *
+ * Returns 0 if the filters were successfully added or removed
+ **/
+static int i40e_add_del_fdir_sctpv4(struct i40e_vsi *vsi,
+ struct i40e_fdir_filter *fd_data,
+ bool add)
+{
+ struct i40e_pf *pf = vsi->back;
+ struct sctphdr *sctp;
+ struct iphdr *ip;
+ u8 *raw_packet;
+ int ret;
+ /* Dummy packet */
+ static char packet[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0,
+ 0x45, 0, 0, 0x20, 0, 0, 0x40, 0, 0x40, 0x84, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
+
+ raw_packet = kzalloc(I40E_FDIR_MAX_RAW_PACKET_SIZE, GFP_KERNEL);
+ if (!raw_packet)
+ return -ENOMEM;
+ memcpy(raw_packet, packet, I40E_SCTPIP_DUMMY_PACKET_LEN);
+
+ ip = (struct iphdr *)(raw_packet + IP_HEADER_OFFSET);
+ sctp = (struct sctphdr *)(raw_packet + IP_HEADER_OFFSET
+ + sizeof(struct iphdr));
+
+ ip->daddr = fd_data->dst_ip;
+ sctp->dest = fd_data->dst_port;
+ ip->saddr = fd_data->src_ip;
+ sctp->source = fd_data->src_port;
+
+ if (fd_data->flex_filter) {
+ u8 *payload = raw_packet + I40E_SCTPIP_DUMMY_PACKET_LEN;
+ __be16 pattern = fd_data->flex_word;
+ u16 off = fd_data->flex_offset;
+
+ *((__force __be16 *)(payload + off)) = pattern;
+ }
+
+ fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_SCTP;
+ ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "PCTYPE:%d, Filter command send failed for fd_id:%d (ret = %d)\n",
+ fd_data->pctype, fd_data->fd_id, ret);
+ /* Free the packet buffer since it wasn't added to the ring */
+ kfree(raw_packet);
+ return -EOPNOTSUPP;
+ } else if (I40E_DEBUG_FD & pf->hw.debug_mask) {
+ if (add)
+ dev_info(&pf->pdev->dev,
+ "Filter OK for PCTYPE %d loc = %d\n",
+ fd_data->pctype, fd_data->fd_id);
+ else
+ dev_info(&pf->pdev->dev,
+ "Filter deleted for PCTYPE %d loc = %d\n",
+ fd_data->pctype, fd_data->fd_id);
+ }
+
+ if (add)
+ pf->fd_sctp4_filter_cnt++;
+ else
+ pf->fd_sctp4_filter_cnt--;
+
+ return 0;
}
#define I40E_IP_DUMMY_PACKET_LEN 34
@@ -343,7 +436,6 @@ static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi,
{
struct i40e_pf *pf = vsi->back;
struct iphdr *ip;
- bool err = false;
u8 *raw_packet;
int ret;
int i;
@@ -359,18 +451,29 @@ static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi,
memcpy(raw_packet, packet, I40E_IP_DUMMY_PACKET_LEN);
ip = (struct iphdr *)(raw_packet + IP_HEADER_OFFSET);
- ip->saddr = fd_data->src_ip[0];
- ip->daddr = fd_data->dst_ip[0];
+ ip->saddr = fd_data->src_ip;
+ ip->daddr = fd_data->dst_ip;
ip->protocol = 0;
+ if (fd_data->flex_filter) {
+ u8 *payload = raw_packet + I40E_IP_DUMMY_PACKET_LEN;
+ __be16 pattern = fd_data->flex_word;
+ u16 off = fd_data->flex_offset;
+
+ *((__force __be16 *)(payload + off)) = pattern;
+ }
+
fd_data->pctype = i;
ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add);
-
if (ret) {
dev_info(&pf->pdev->dev,
"PCTYPE:%d, Filter command send failed for fd_id:%d (ret = %d)\n",
fd_data->pctype, fd_data->fd_id, ret);
- err = true;
+ /* The packet buffer wasn't added to the ring so we
+ * need to free it now.
+ */
+ kfree(raw_packet);
+ return -EOPNOTSUPP;
} else if (I40E_DEBUG_FD & pf->hw.debug_mask) {
if (add)
dev_info(&pf->pdev->dev,
@@ -383,10 +486,12 @@ static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi,
}
}
- if (err)
- kfree(raw_packet);
+ if (add)
+ pf->fd_ip4_filter_cnt++;
+ else
+ pf->fd_ip4_filter_cnt--;
- return err ? -EOPNOTSUPP : 0;
+ return 0;
}
/**
@@ -409,6 +514,9 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi,
case UDP_V4_FLOW:
ret = i40e_add_del_fdir_udpv4(vsi, input, add);
break;
+ case SCTP_V4_FLOW:
+ ret = i40e_add_del_fdir_sctpv4(vsi, input, add);
+ break;
case IP_USER_FLOW:
switch (input->ip4_proto) {
case IPPROTO_TCP:
@@ -417,19 +525,23 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi,
case IPPROTO_UDP:
ret = i40e_add_del_fdir_udpv4(vsi, input, add);
break;
+ case IPPROTO_SCTP:
+ ret = i40e_add_del_fdir_sctpv4(vsi, input, add);
+ break;
case IPPROTO_IP:
ret = i40e_add_del_fdir_ipv4(vsi, input, add);
break;
default:
/* We cannot support masking based on protocol */
- goto unsupported_flow;
+ dev_info(&pf->pdev->dev, "Unsupported IPv4 protocol 0x%02x\n",
+ input->ip4_proto);
+ return -EINVAL;
}
break;
default:
-unsupported_flow:
- dev_info(&pf->pdev->dev, "Could not specify spec type %d\n",
+ dev_info(&pf->pdev->dev, "Unsupported flow type 0x%02x\n",
input->flow_type);
- ret = -EINVAL;
+ return -EINVAL;
}
/* The buffer allocated here will be normally be freed by
@@ -484,8 +596,8 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring,
pf->fd_atr_cnt = i40e_get_current_atr_cnt(pf);
if ((rx_desc->wb.qword0.hi_dword.fd_id == 0) &&
- (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) {
- pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED;
+ (pf->hw_disabled_flags & I40E_FLAG_FD_SB_ENABLED)) {
+ pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED;
set_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state);
}
@@ -498,11 +610,11 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring,
*/
if (fcnt_prog >= (fcnt_avail - I40E_FDIR_BUFFER_FULL_MARGIN)) {
if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) &&
- !(pf->auto_disable_flags &
+ !(pf->hw_disabled_flags &
I40E_FLAG_FD_SB_ENABLED)) {
if (I40E_DEBUG_FD & pf->hw.debug_mask)
dev_warn(&pdev->dev, "FD filter space full, new ntuple rules will not be added\n");
- pf->auto_disable_flags |=
+ pf->hw_disabled_flags |=
I40E_FLAG_FD_SB_ENABLED;
}
}
@@ -599,19 +711,15 @@ void i40e_free_tx_resources(struct i40e_ring *tx_ring)
/**
* i40e_get_tx_pending - how many tx descriptors not processed
* @tx_ring: the ring of descriptors
- * @in_sw: is tx_pending being checked in SW or HW
*
* Since there is no access to the ring head register
* in XL710, we need to use our local copies
**/
-u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw)
+u32 i40e_get_tx_pending(struct i40e_ring *ring)
{
u32 head, tail;
- if (!in_sw)
- head = i40e_get_head(ring);
- else
- head = ring->next_to_clean;
+ head = i40e_get_head(ring);
tail = readl(ring->tail);
if (head != tail)
@@ -734,7 +842,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
* them to be written back in case we stay in NAPI.
* In this mode on X722 we do not enable Interrupt.
*/
- unsigned int j = i40e_get_tx_pending(tx_ring, false);
+ unsigned int j = i40e_get_tx_pending(tx_ring);
if (budget &&
((j / WB_STRIDE) == 0) && (j > 0) &&
@@ -951,11 +1059,6 @@ static void i40e_clean_programming_status(struct i40e_ring *rx_ring,
if (id == I40E_RX_PROG_STATUS_DESC_FD_FILTER_STATUS)
i40e_fd_handle_status(rx_ring, rx_desc, id);
-#ifdef I40E_FCOE
- else if ((id == I40E_RX_PROG_STATUS_DESC_FCOE_CTXT_PROG_STATUS) ||
- (id == I40E_RX_PROG_STATUS_DESC_FCOE_CTXT_INVL_STATUS))
- i40e_fcoe_handle_status(rx_ring, rx_desc, id);
-#endif
}
/**
@@ -1010,7 +1113,6 @@ int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring)
**/
void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
{
- struct device *dev = rx_ring->dev;
unsigned long bi_size;
u16 i;
@@ -1030,8 +1132,22 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
if (!rx_bi->page)
continue;
- dma_unmap_page(dev, rx_bi->dma, PAGE_SIZE, DMA_FROM_DEVICE);
- __free_pages(rx_bi->page, 0);
+ /* Invalidate cache lines that may have been written to by
+ * device so that we avoid corrupting memory.
+ */
+ dma_sync_single_range_for_cpu(rx_ring->dev,
+ rx_bi->dma,
+ rx_bi->page_offset,
+ rx_ring->rx_buf_len,
+ DMA_FROM_DEVICE);
+
+ /* free resources associated with mapping */
+ dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma,
+ i40e_rx_pg_size(rx_ring),
+ DMA_FROM_DEVICE,
+ I40E_RX_DMA_ATTR);
+
+ __page_frag_cache_drain(rx_bi->page, rx_bi->pagecnt_bias);
rx_bi->page = NULL;
rx_bi->page_offset = 0;
@@ -1132,6 +1248,17 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val)
}
/**
+ * i40e_rx_offset - Return expected offset into page to access data
+ * @rx_ring: Ring we are requesting offset of
+ *
+ * Returns the offset value for ring into the data buffer.
+ */
+static inline unsigned int i40e_rx_offset(struct i40e_ring *rx_ring)
+{
+ return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0;
+}
+
+/**
* i40e_alloc_mapped_page - recycle or make a new page
* @rx_ring: ring to use
* @bi: rx_buffer struct to modify
@@ -1152,27 +1279,33 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring,
}
/* alloc new page for storage */
- page = dev_alloc_page();
+ page = dev_alloc_pages(i40e_rx_pg_order(rx_ring));
if (unlikely(!page)) {
rx_ring->rx_stats.alloc_page_failed++;
return false;
}
/* map page for use */
- dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+ dma = dma_map_page_attrs(rx_ring->dev, page, 0,
+ i40e_rx_pg_size(rx_ring),
+ DMA_FROM_DEVICE,
+ I40E_RX_DMA_ATTR);
/* if mapping failed free memory back to system since
* there isn't much point in holding memory we can't use
*/
if (dma_mapping_error(rx_ring->dev, dma)) {
- __free_pages(page, 0);
+ __free_pages(page, i40e_rx_pg_order(rx_ring));
rx_ring->rx_stats.alloc_page_failed++;
return false;
}
bi->dma = dma;
bi->page = page;
- bi->page_offset = 0;
+ bi->page_offset = i40e_rx_offset(rx_ring);
+
+ /* initialize pagecnt_bias to 1 representing we fully own page */
+ bi->pagecnt_bias = 1;
return true;
}
@@ -1219,6 +1352,12 @@ bool i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count)
if (!i40e_alloc_mapped_page(rx_ring, bi))
goto no_buffers;
+ /* sync the buffer for use by the device */
+ dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
+ bi->page_offset,
+ rx_ring->rx_buf_len,
+ DMA_FROM_DEVICE);
+
/* Refresh the desc even if buffer_addrs didn't change
* because each write-back erases this info.
*/
@@ -1259,8 +1398,6 @@ bool i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count)
* @vsi: the VSI we care about
* @skb: skb currently being received and modified
* @rx_desc: the receive descriptor
- *
- * skb->protocol must be set before this function is called
**/
static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
struct sk_buff *skb,
@@ -1422,12 +1559,12 @@ void i40e_process_skb_fields(struct i40e_ring *rx_ring,
i40e_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
- /* modifies the skb - consumes the enet header */
- skb->protocol = eth_type_trans(skb, rx_ring->netdev);
-
i40e_rx_checksum(rx_ring->vsi, skb, rx_desc);
skb_record_rx_queue(skb, rx_ring->queue_index);
+
+ /* modifies the skb - consumes the enet header */
+ skb->protocol = eth_type_trans(skb, rx_ring->netdev);
}
/**
@@ -1472,7 +1609,10 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring,
rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
/* transfer page from old buffer to new buffer */
- *new_buff = *old_buff;
+ new_buff->dma = old_buff->dma;
+ new_buff->page = old_buff->page;
+ new_buff->page_offset = old_buff->page_offset;
+ new_buff->pagecnt_bias = old_buff->pagecnt_bias;
}
/**
@@ -1493,8 +1633,6 @@ static inline bool i40e_page_is_reusable(struct page *page)
* the adapter for another receive
*
* @rx_buffer: buffer containing the page
- * @page: page address from rx_buffer
- * @truesize: actual size of the buffer in this page
*
* If page is reusable, rx_buffer->page_offset is adjusted to point to
* an unused region in the page.
@@ -1517,13 +1655,10 @@ static inline bool i40e_page_is_reusable(struct page *page)
*
* In either case, if the page is reusable its refcount is increased.
**/
-static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer,
- struct page *page,
- const unsigned int truesize)
+static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer)
{
-#if (PAGE_SIZE >= 8192)
- unsigned int last_offset = PAGE_SIZE - I40E_RXBUFFER_2048;
-#endif
+ unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
+ struct page *page = rx_buffer->page;
/* Is any reuse possible? */
if (unlikely(!i40e_page_is_reusable(page)))
@@ -1531,21 +1666,23 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer,
#if (PAGE_SIZE < 8192)
/* if we are only owner of page we can reuse it */
- if (unlikely(page_count(page) != 1))
+ if (unlikely((page_count(page) - pagecnt_bias) > 1))
return false;
-
- /* flip page offset to other buffer */
- rx_buffer->page_offset ^= truesize;
#else
- /* move offset up to the next cache line */
- rx_buffer->page_offset += truesize;
-
- if (rx_buffer->page_offset > last_offset)
+#define I40E_LAST_OFFSET \
+ (SKB_WITH_OVERHEAD(PAGE_SIZE) - I40E_RXBUFFER_2048)
+ if (rx_buffer->page_offset > I40E_LAST_OFFSET)
return false;
#endif
- /* Inc ref count on page before passing it up to the stack */
- get_page(page);
+ /* If we have drained the page fragment pool we need to update
+ * the pagecnt_bias and page count so that we fully restock the
+ * number of references the driver holds.
+ */
+ if (unlikely(!pagecnt_bias)) {
+ page_ref_add(page, USHRT_MAX);
+ rx_buffer->pagecnt_bias = USHRT_MAX;
+ }
return true;
}
@@ -1554,122 +1691,51 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer,
* i40e_add_rx_frag - Add contents of Rx buffer to sk_buff
* @rx_ring: rx descriptor ring to transact packets on
* @rx_buffer: buffer containing page to add
- * @size: packet length from rx_desc
* @skb: sk_buff to place the data into
+ * @size: packet length from rx_desc
*
* This function will add the data contained in rx_buffer->page to the skb.
- * This is done either through a direct copy if the data in the buffer is
- * less than the skb header size, otherwise it will just attach the page as
- * a frag to the skb.
+ * It will just attach the page as a frag to the skb.
*
- * The function will then update the page offset if necessary and return
- * true if the buffer can be reused by the adapter.
+ * The function will then update the page offset.
**/
-static bool i40e_add_rx_frag(struct i40e_ring *rx_ring,
+static void i40e_add_rx_frag(struct i40e_ring *rx_ring,
struct i40e_rx_buffer *rx_buffer,
- unsigned int size,
- struct sk_buff *skb)
+ struct sk_buff *skb,
+ unsigned int size)
{
- struct page *page = rx_buffer->page;
- unsigned char *va = page_address(page) + rx_buffer->page_offset;
#if (PAGE_SIZE < 8192)
- unsigned int truesize = I40E_RXBUFFER_2048;
+ unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
#else
- unsigned int truesize = ALIGN(size, L1_CACHE_BYTES);
+ unsigned int truesize = SKB_DATA_ALIGN(size + i40e_rx_offset(rx_ring));
#endif
- unsigned int pull_len;
- if (unlikely(skb_is_nonlinear(skb)))
- goto add_tail_frag;
+ skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
+ rx_buffer->page_offset, size, truesize);
- /* will the data fit in the skb we allocated? if so, just
- * copy it as it is pretty small anyway
- */
- if (size <= I40E_RX_HDR_SIZE) {
- memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
-
- /* page is reusable, we can reuse buffer as-is */
- if (likely(i40e_page_is_reusable(page)))
- return true;
-
- /* this page cannot be reused so discard it */
- __free_pages(page, 0);
- return false;
- }
-
- /* we need the header to contain the greater of either
- * ETH_HLEN or 60 bytes if the skb->len is less than
- * 60 for skb_pad.
- */
- pull_len = eth_get_headlen(va, I40E_RX_HDR_SIZE);
-
- /* align pull length to size of long to optimize
- * memcpy performance
- */
- memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long)));
-
- /* update all of the pointers */
- va += pull_len;
- size -= pull_len;
-
-add_tail_frag:
- skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
- (unsigned long)va & ~PAGE_MASK, size, truesize);
-
- return i40e_can_reuse_rx_page(rx_buffer, page, truesize);
+ /* page is being used so we must update the page offset */
+#if (PAGE_SIZE < 8192)
+ rx_buffer->page_offset ^= truesize;
+#else
+ rx_buffer->page_offset += truesize;
+#endif
}
/**
- * i40e_fetch_rx_buffer - Allocate skb and populate it
+ * i40e_get_rx_buffer - Fetch Rx buffer and synchronize data for use
* @rx_ring: rx descriptor ring to transact packets on
- * @rx_desc: descriptor containing info written by hardware
+ * @size: size of buffer to add to skb
*
- * This function allocates an skb on the fly, and populates it with the page
- * data from the current receive descriptor, taking care to set up the skb
- * correctly, as well as handling calling the page recycle function if
- * necessary.
+ * This function will pull an Rx buffer from the ring and synchronize it
+ * for use by the CPU.
*/
-static inline
-struct sk_buff *i40e_fetch_rx_buffer(struct i40e_ring *rx_ring,
- union i40e_rx_desc *rx_desc,
- struct sk_buff *skb)
+static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring,
+ const unsigned int size)
{
- u64 local_status_error_len =
- le64_to_cpu(rx_desc->wb.qword1.status_error_len);
- unsigned int size =
- (local_status_error_len & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
- I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
struct i40e_rx_buffer *rx_buffer;
- struct page *page;
rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
- page = rx_buffer->page;
- prefetchw(page);
-
- if (likely(!skb)) {
- void *page_addr = page_address(page) + rx_buffer->page_offset;
-
- /* prefetch first cache line of first page */
- prefetch(page_addr);
-#if L1_CACHE_BYTES < 128
- prefetch(page_addr + L1_CACHE_BYTES);
-#endif
-
- /* allocate a skb to store the frags */
- skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
- I40E_RX_HDR_SIZE,
- GFP_ATOMIC | __GFP_NOWARN);
- if (unlikely(!skb)) {
- rx_ring->rx_stats.alloc_buff_failed++;
- return NULL;
- }
-
- /* we will be copying header into skb->data in
- * pskb_may_pull so it is in our interest to prefetch
- * it now to avoid a possible cache miss
- */
- prefetchw(skb->data);
- }
+ prefetchw(rx_buffer->page);
/* we are reusing so sync this buffer for CPU use */
dma_sync_single_range_for_cpu(rx_ring->dev,
@@ -1678,21 +1744,148 @@ struct sk_buff *i40e_fetch_rx_buffer(struct i40e_ring *rx_ring,
size,
DMA_FROM_DEVICE);
- /* pull page into skb */
- if (i40e_add_rx_frag(rx_ring, rx_buffer, size, skb)) {
+ /* We have pulled a buffer for use, so decrement pagecnt_bias */
+ rx_buffer->pagecnt_bias--;
+
+ return rx_buffer;
+}
+
+/**
+ * i40e_construct_skb - Allocate skb and populate it
+ * @rx_ring: rx descriptor ring to transact packets on
+ * @rx_buffer: rx buffer to pull data from
+ * @size: size of buffer to add to skb
+ *
+ * This function allocates an skb. It then populates it with the page
+ * data from the current receive descriptor, taking care to set up the
+ * skb correctly.
+ */
+static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
+ struct i40e_rx_buffer *rx_buffer,
+ unsigned int size)
+{
+ void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+ unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
+#else
+ unsigned int truesize = SKB_DATA_ALIGN(size);
+#endif
+ unsigned int headlen;
+ struct sk_buff *skb;
+
+ /* prefetch first cache line of first page */
+ prefetch(va);
+#if L1_CACHE_BYTES < 128
+ prefetch(va + L1_CACHE_BYTES);
+#endif
+
+ /* allocate a skb to store the frags */
+ skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
+ I40E_RX_HDR_SIZE,
+ GFP_ATOMIC | __GFP_NOWARN);
+ if (unlikely(!skb))
+ return NULL;
+
+ /* Determine available headroom for copy */
+ headlen = size;
+ if (headlen > I40E_RX_HDR_SIZE)
+ headlen = eth_get_headlen(va, I40E_RX_HDR_SIZE);
+
+ /* align pull length to size of long to optimize memcpy performance */
+ memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
+
+ /* update all of the pointers */
+ size -= headlen;
+ if (size) {
+ skb_add_rx_frag(skb, 0, rx_buffer->page,
+ rx_buffer->page_offset + headlen,
+ size, truesize);
+
+ /* buffer is used by skb, update page_offset */
+#if (PAGE_SIZE < 8192)
+ rx_buffer->page_offset ^= truesize;
+#else
+ rx_buffer->page_offset += truesize;
+#endif
+ } else {
+ /* buffer is unused, reset bias back to rx_buffer */
+ rx_buffer->pagecnt_bias++;
+ }
+
+ return skb;
+}
+
+/**
+ * i40e_build_skb - Build skb around an existing buffer
+ * @rx_ring: Rx descriptor ring to transact packets on
+ * @rx_buffer: Rx buffer to pull data from
+ * @size: size of buffer to add to skb
+ *
+ * This function builds an skb around an existing Rx buffer, taking care
+ * to set up the skb correctly and avoid any memcpy overhead.
+ */
+static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring,
+ struct i40e_rx_buffer *rx_buffer,
+ unsigned int size)
+{
+ void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+ unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
+#else
+ unsigned int truesize = SKB_DATA_ALIGN(size);
+#endif
+ struct sk_buff *skb;
+
+ /* prefetch first cache line of first page */
+ prefetch(va);
+#if L1_CACHE_BYTES < 128
+ prefetch(va + L1_CACHE_BYTES);
+#endif
+ /* build an skb around the page buffer */
+ skb = build_skb(va - I40E_SKB_PAD, truesize);
+ if (unlikely(!skb))
+ return NULL;
+
+ /* update pointers within the skb to store the data */
+ skb_reserve(skb, I40E_SKB_PAD);
+ __skb_put(skb, size);
+
+ /* buffer is used by skb, update page_offset */
+#if (PAGE_SIZE < 8192)
+ rx_buffer->page_offset ^= truesize;
+#else
+ rx_buffer->page_offset += truesize;
+#endif
+
+ return skb;
+}
+
+/**
+ * i40e_put_rx_buffer - Clean up used buffer and either recycle or free
+ * @rx_ring: rx descriptor ring to transact packets on
+ * @rx_buffer: rx buffer to pull data from
+ *
+ * This function will clean up the contents of the rx_buffer. It will
+ * either recycle the bufer or unmap it and free the associated resources.
+ */
+static void i40e_put_rx_buffer(struct i40e_ring *rx_ring,
+ struct i40e_rx_buffer *rx_buffer)
+{
+ if (i40e_can_reuse_rx_page(rx_buffer)) {
/* hand second half of page back to the ring */
i40e_reuse_rx_page(rx_ring, rx_buffer);
rx_ring->rx_stats.page_reuse_count++;
} else {
/* we are not reusing the buffer so unmap it */
- dma_unmap_page(rx_ring->dev, rx_buffer->dma, PAGE_SIZE,
- DMA_FROM_DEVICE);
+ dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
+ i40e_rx_pg_size(rx_ring),
+ DMA_FROM_DEVICE, I40E_RX_DMA_ATTR);
+ __page_frag_cache_drain(rx_buffer->page,
+ rx_buffer->pagecnt_bias);
}
/* clear contents of buffer_info */
rx_buffer->page = NULL;
-
- return skb;
}
/**
@@ -1753,7 +1946,9 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
bool failure = false;
while (likely(total_rx_packets < budget)) {
+ struct i40e_rx_buffer *rx_buffer;
union i40e_rx_desc *rx_desc;
+ unsigned int size;
u16 vlan_tag;
u8 rx_ptype;
u64 qword;
@@ -1770,22 +1965,38 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
/* status_error_len will always be zero for unused descriptors
* because it's cleared in cleanup, and overlaps with hdr_addr
* which is always zero because packet split isn't used, if the
- * hardware wrote DD then it will be non-zero
+ * hardware wrote DD then the length will be non-zero
*/
- if (!i40e_test_staterr(rx_desc,
- BIT(I40E_RX_DESC_STATUS_DD_SHIFT)))
+ qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
+ size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
+ I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
+ if (!size)
break;
/* This memory barrier is needed to keep us from reading
- * any other fields out of the rx_desc until we know the
- * DD bit is set.
+ * any other fields out of the rx_desc until we have
+ * verified the descriptor has been written back.
*/
dma_rmb();
- skb = i40e_fetch_rx_buffer(rx_ring, rx_desc, skb);
- if (!skb)
- break;
+ rx_buffer = i40e_get_rx_buffer(rx_ring, size);
+ /* retrieve a buffer from the ring */
+ if (skb)
+ i40e_add_rx_frag(rx_ring, rx_buffer, skb, size);
+ else if (ring_uses_build_skb(rx_ring))
+ skb = i40e_build_skb(rx_ring, rx_buffer, size);
+ else
+ skb = i40e_construct_skb(rx_ring, rx_buffer, size);
+
+ /* exit if we failed to retrieve a buffer */
+ if (!skb) {
+ rx_ring->rx_stats.alloc_buff_failed++;
+ rx_buffer->pagecnt_bias++;
+ break;
+ }
+
+ i40e_put_rx_buffer(rx_ring, rx_buffer);
cleaned_count++;
if (i40e_is_non_eop(rx_ring, rx_desc, skb))
@@ -1798,6 +2009,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
*/
if (unlikely(i40e_test_staterr(rx_desc, BIT(I40E_RXD_QW1_ERROR_SHIFT)))) {
dev_kfree_skb_any(skb);
+ skb = NULL;
continue;
}
@@ -1816,15 +2028,6 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
/* populate checksum, VLAN, and protocol */
i40e_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
-#ifdef I40E_FCOE
- if (unlikely(
- i40e_rx_is_fcoe(rx_ptype) &&
- !i40e_fcoe_handle_offload(rx_ring, rx_desc, skb))) {
- dev_kfree_skb_any(skb);
- continue;
- }
-#endif
-
vlan_tag = (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) ?
le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0;
@@ -1978,8 +2181,6 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
return 0;
}
- /* Clear hung_detected bit */
- clear_bit(I40E_Q_VECTOR_HUNG_DETECT, &q_vector->hung_detected);
/* Since the actual Tx work is minimal, we can give the Tx a larger
* budget and be more aggressive about cleaning up the Tx descriptors.
*/
@@ -2079,7 +2280,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
if (!(pf->flags & I40E_FLAG_FD_ATR_ENABLED))
return;
- if ((pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED))
+ if ((pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED))
return;
/* if sampling is disabled do nothing */
@@ -2113,10 +2314,9 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
th = (struct tcphdr *)(hdr.network + hlen);
/* Due to lack of space, no more new filters can be programmed */
- if (th->syn && (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED))
+ if (th->syn && (pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED))
return;
- if ((pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) &&
- (!(pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))) {
+ if (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) {
/* HW ATR eviction will take care of removing filters on FIN
* and RST packets.
*/
@@ -2178,8 +2378,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) &
I40E_TXD_FLTR_QW1_CNTINDEX_MASK;
- if ((pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) &&
- (!(pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE)))
+ if (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE)
dtype_cmd |= I40E_TXD_FLTR_QW1_ATR_MASK;
fdir_desc->qindex_flex_ptype_vsi = cpu_to_le32(flex_ptype);
@@ -2200,15 +2399,9 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
* Returns error code indicate the frame should be dropped upon error and the
* otherwise returns 0 to indicate the flags has been set properly.
**/
-#ifdef I40E_FCOE
-inline int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
- struct i40e_ring *tx_ring,
- u32 *flags)
-#else
static inline int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
struct i40e_ring *tx_ring,
u32 *flags)
-#endif
{
__be16 protocol = skb->protocol;
u32 tx_flags = 0;
@@ -2716,15 +2909,9 @@ bool __i40e_chk_linearize(struct sk_buff *skb)
* @td_cmd: the command field in the descriptor
* @td_offset: offset for checksum or crc
**/
-#ifdef I40E_FCOE
-inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
- struct i40e_tx_buffer *first, u32 tx_flags,
- const u8 hdr_len, u32 td_cmd, u32 td_offset)
-#else
static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
struct i40e_tx_buffer *first, u32 tx_flags,
const u8 hdr_len, u32 td_cmd, u32 td_offset)
-#endif
{
unsigned int data_len = skb->data_len;
unsigned int size = skb_headlen(skb);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index f809790..f5de511 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -117,10 +117,9 @@ enum i40e_dyn_idx_t {
/* Supported Rx Buffer Sizes (a multiple of 128) */
#define I40E_RXBUFFER_256 256
+#define I40E_RXBUFFER_1536 1536 /* 128B aligned standard Ethernet frame */
#define I40E_RXBUFFER_2048 2048
-#define I40E_RXBUFFER_3072 3072 /* For FCoE MTU of 2158 */
-#define I40E_RXBUFFER_4096 4096
-#define I40E_RXBUFFER_8192 8192
+#define I40E_RXBUFFER_3072 3072 /* Used for large frames w/ padding */
#define I40E_MAX_RXBUFFER 9728 /* largest size for single descriptor */
/* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we
@@ -133,6 +132,61 @@ enum i40e_dyn_idx_t {
#define I40E_RX_HDR_SIZE I40E_RXBUFFER_256
#define i40e_rx_desc i40e_32byte_rx_desc
+#define I40E_RX_DMA_ATTR \
+ (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
+
+/* Attempt to maximize the headroom available for incoming frames. We
+ * use a 2K buffer for receives and need 1536/1534 to store the data for
+ * the frame. This leaves us with 512 bytes of room. From that we need
+ * to deduct the space needed for the shared info and the padding needed
+ * to IP align the frame.
+ *
+ * Note: For cache line sizes 256 or larger this value is going to end
+ * up negative. In these cases we should fall back to the legacy
+ * receive path.
+ */
+#if (PAGE_SIZE < 8192)
+#define I40E_2K_TOO_SMALL_WITH_PADDING \
+((NET_SKB_PAD + I40E_RXBUFFER_1536) > SKB_WITH_OVERHEAD(I40E_RXBUFFER_2048))
+
+static inline int i40e_compute_pad(int rx_buf_len)
+{
+ int page_size, pad_size;
+
+ page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2);
+ pad_size = SKB_WITH_OVERHEAD(page_size) - rx_buf_len;
+
+ return pad_size;
+}
+
+static inline int i40e_skb_pad(void)
+{
+ int rx_buf_len;
+
+ /* If a 2K buffer cannot handle a standard Ethernet frame then
+ * optimize padding for a 3K buffer instead of a 1.5K buffer.
+ *
+ * For a 3K buffer we need to add enough padding to allow for
+ * tailroom due to NET_IP_ALIGN possibly shifting us out of
+ * cache-line alignment.
+ */
+ if (I40E_2K_TOO_SMALL_WITH_PADDING)
+ rx_buf_len = I40E_RXBUFFER_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN);
+ else
+ rx_buf_len = I40E_RXBUFFER_1536;
+
+ /* if needed make room for NET_IP_ALIGN */
+ rx_buf_len -= NET_IP_ALIGN;
+
+ return i40e_compute_pad(rx_buf_len);
+}
+
+#define I40E_SKB_PAD i40e_skb_pad()
+#else
+#define I40E_2K_TOO_SMALL_WITH_PADDING false
+#define I40E_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN)
+#endif
+
/**
* i40e_test_staterr - tests bits in Rx descriptor status and error fields
* @rx_desc: pointer to receive descriptor (in le64 format)
@@ -255,7 +309,12 @@ struct i40e_tx_buffer {
struct i40e_rx_buffer {
dma_addr_t dma;
struct page *page;
- unsigned int page_offset;
+#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
+ __u32 page_offset;
+#else
+ __u16 page_offset;
+#endif
+ __u16 pagecnt_bias;
};
struct i40e_queue_stats {
@@ -269,7 +328,6 @@ struct i40e_tx_queue_stats {
u64 tx_done_old;
u64 tx_linearize;
u64 tx_force_wb;
- u64 tx_lost_interrupt;
};
struct i40e_rx_queue_stats {
@@ -335,7 +393,8 @@ struct i40e_ring {
u8 packet_stride;
u16 flags;
-#define I40E_TXR_FLAGS_WB_ON_ITR BIT(0)
+#define I40E_TXR_FLAGS_WB_ON_ITR BIT(0)
+#define I40E_RXR_FLAGS_BUILD_SKB_ENABLED BIT(1)
/* stats structs */
struct i40e_queue_stats stats;
@@ -363,6 +422,21 @@ struct i40e_ring {
*/
} ____cacheline_internodealigned_in_smp;
+static inline bool ring_uses_build_skb(struct i40e_ring *ring)
+{
+ return !!(ring->flags & I40E_RXR_FLAGS_BUILD_SKB_ENABLED);
+}
+
+static inline void set_ring_build_skb_enabled(struct i40e_ring *ring)
+{
+ ring->flags |= I40E_RXR_FLAGS_BUILD_SKB_ENABLED;
+}
+
+static inline void clear_ring_build_skb_enabled(struct i40e_ring *ring)
+{
+ ring->flags &= ~I40E_RXR_FLAGS_BUILD_SKB_ENABLED;
+}
+
enum i40e_latency_range {
I40E_LOWEST_LATENCY = 0,
I40E_LOW_LATENCY = 1,
@@ -384,6 +458,17 @@ struct i40e_ring_container {
#define i40e_for_each_ring(pos, head) \
for (pos = (head).ring; pos != NULL; pos = pos->next)
+static inline unsigned int i40e_rx_pg_order(struct i40e_ring *ring)
+{
+#if (PAGE_SIZE < 8192)
+ if (ring->rx_buf_len > (PAGE_SIZE / 2))
+ return 1;
+#endif
+ return 0;
+}
+
+#define i40e_rx_pg_size(_ring) (PAGE_SIZE << i40e_rx_pg_order(_ring))
+
bool i40e_alloc_rx_buffers(struct i40e_ring *rxr, u16 cleaned_count);
netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev);
void i40e_clean_tx_ring(struct i40e_ring *tx_ring);
@@ -393,15 +478,8 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring);
void i40e_free_tx_resources(struct i40e_ring *tx_ring);
void i40e_free_rx_resources(struct i40e_ring *rx_ring);
int i40e_napi_poll(struct napi_struct *napi, int budget);
-#ifdef I40E_FCOE
-void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
- struct i40e_tx_buffer *first, u32 tx_flags,
- const u8 hdr_len, u32 td_cmd, u32 td_offset);
-int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
- struct i40e_ring *tx_ring, u32 *flags);
-#endif
void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector);
-u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw);
+u32 i40e_get_tx_pending(struct i40e_ring *ring);
int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size);
bool __i40e_chk_linearize(struct sk_buff *skb);
@@ -483,16 +561,6 @@ static inline bool i40e_chk_linearize(struct sk_buff *skb, int count)
}
/**
- * i40e_rx_is_fcoe - returns true if the Rx packet type is FCoE
- * @ptype: the packet type field from Rx descriptor write-back
- **/
-static inline bool i40e_rx_is_fcoe(u16 ptype)
-{
- return (ptype >= I40E_RX_PTYPE_L2_FCOE_PAY3) &&
- (ptype <= I40E_RX_PTYPE_L2_FCOE_VFT_FCOTHER);
-}
-
-/**
* txring_txq - Find the netdev Tx ring based on the i40e Tx ring
* @ring: Tx ring to find the netdev equivalent of
**/
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 939f9fd..9200f2d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -1213,25 +1213,6 @@ struct i40e_veb_tc_stats {
u64 tc_tx_bytes[I40E_MAX_TRAFFIC_CLASS];
};
-#ifdef I40E_FCOE
-/* Statistics collected per function for FCoE */
-struct i40e_fcoe_stats {
- u64 rx_fcoe_packets; /* fcoeprc */
- u64 rx_fcoe_dwords; /* focedwrc */
- u64 rx_fcoe_dropped; /* fcoerpdc */
- u64 tx_fcoe_packets; /* fcoeptc */
- u64 tx_fcoe_dwords; /* focedwtc */
- u64 fcoe_bad_fccrc; /* fcoecrc */
- u64 fcoe_last_error; /* fcoelast */
- u64 fcoe_ddp_count; /* fcoeddpc */
-};
-
-/* offset to per function FCoE statistics block */
-#define I40E_FCOE_VF_STAT_OFFSET 0
-#define I40E_FCOE_PF_STAT_OFFSET 128
-#define I40E_FCOE_STAT_MAX (I40E_FCOE_PF_STAT_OFFSET + I40E_MAX_PF)
-
-#endif
/* Statistics collected by the MAC */
struct i40e_hw_port_stats {
/* eth stats collected by the port */
@@ -1319,125 +1300,6 @@ struct i40e_hw_port_stats {
#define I40E_SRRD_SRCTL_ATTEMPTS 100000
-#ifdef I40E_FCOE
-/* FCoE Tx context descriptor - Use the i40e_tx_context_desc struct */
-
-enum i40E_fcoe_tx_ctx_desc_cmd_bits {
- I40E_FCOE_TX_CTX_DESC_OPCODE_SINGLE_SEND = 0x00, /* 4 BITS */
- I40E_FCOE_TX_CTX_DESC_OPCODE_TSO_FC_CLASS2 = 0x01, /* 4 BITS */
- I40E_FCOE_TX_CTX_DESC_OPCODE_TSO_FC_CLASS3 = 0x05, /* 4 BITS */
- I40E_FCOE_TX_CTX_DESC_OPCODE_ETSO_FC_CLASS2 = 0x02, /* 4 BITS */
- I40E_FCOE_TX_CTX_DESC_OPCODE_ETSO_FC_CLASS3 = 0x06, /* 4 BITS */
- I40E_FCOE_TX_CTX_DESC_OPCODE_DWO_FC_CLASS2 = 0x03, /* 4 BITS */
- I40E_FCOE_TX_CTX_DESC_OPCODE_DWO_FC_CLASS3 = 0x07, /* 4 BITS */
- I40E_FCOE_TX_CTX_DESC_OPCODE_DDP_CTX_INVL = 0x08, /* 4 BITS */
- I40E_FCOE_TX_CTX_DESC_OPCODE_DWO_CTX_INVL = 0x09, /* 4 BITS */
- I40E_FCOE_TX_CTX_DESC_RELOFF = 0x10,
- I40E_FCOE_TX_CTX_DESC_CLRSEQ = 0x20,
- I40E_FCOE_TX_CTX_DESC_DIFENA = 0x40,
- I40E_FCOE_TX_CTX_DESC_IL2TAG2 = 0x80
-};
-
-/* FCoE DDP Context descriptor */
-struct i40e_fcoe_ddp_context_desc {
- __le64 rsvd;
- __le64 type_cmd_foff_lsize;
-};
-
-#define I40E_FCOE_DDP_CTX_QW1_DTYPE_SHIFT 0
-#define I40E_FCOE_DDP_CTX_QW1_DTYPE_MASK (0xFULL << \
- I40E_FCOE_DDP_CTX_QW1_DTYPE_SHIFT)
-
-#define I40E_FCOE_DDP_CTX_QW1_CMD_SHIFT 4
-#define I40E_FCOE_DDP_CTX_QW1_CMD_MASK (0xFULL << \
- I40E_FCOE_DDP_CTX_QW1_CMD_SHIFT)
-
-enum i40e_fcoe_ddp_ctx_desc_cmd_bits {
- I40E_FCOE_DDP_CTX_DESC_BSIZE_512B = 0x00, /* 2 BITS */
- I40E_FCOE_DDP_CTX_DESC_BSIZE_4K = 0x01, /* 2 BITS */
- I40E_FCOE_DDP_CTX_DESC_BSIZE_8K = 0x02, /* 2 BITS */
- I40E_FCOE_DDP_CTX_DESC_BSIZE_16K = 0x03, /* 2 BITS */
- I40E_FCOE_DDP_CTX_DESC_DIFENA = 0x04, /* 1 BIT */
- I40E_FCOE_DDP_CTX_DESC_LASTSEQH = 0x08, /* 1 BIT */
-};
-
-#define I40E_FCOE_DDP_CTX_QW1_FOFF_SHIFT 16
-#define I40E_FCOE_DDP_CTX_QW1_FOFF_MASK (0x3FFFULL << \
- I40E_FCOE_DDP_CTX_QW1_FOFF_SHIFT)
-
-#define I40E_FCOE_DDP_CTX_QW1_LSIZE_SHIFT 32
-#define I40E_FCOE_DDP_CTX_QW1_LSIZE_MASK (0x3FFFULL << \
- I40E_FCOE_DDP_CTX_QW1_LSIZE_SHIFT)
-
-/* FCoE DDP/DWO Queue Context descriptor */
-struct i40e_fcoe_queue_context_desc {
- __le64 dmaindx_fbase; /* 0:11 DMAINDX, 12:63 FBASE */
- __le64 flen_tph; /* 0:12 FLEN, 13:15 TPH */
-};
-
-#define I40E_FCOE_QUEUE_CTX_QW0_DMAINDX_SHIFT 0
-#define I40E_FCOE_QUEUE_CTX_QW0_DMAINDX_MASK (0xFFFULL << \
- I40E_FCOE_QUEUE_CTX_QW0_DMAINDX_SHIFT)
-
-#define I40E_FCOE_QUEUE_CTX_QW0_FBASE_SHIFT 12
-#define I40E_FCOE_QUEUE_CTX_QW0_FBASE_MASK (0xFFFFFFFFFFFFFULL << \
- I40E_FCOE_QUEUE_CTX_QW0_FBASE_SHIFT)
-
-#define I40E_FCOE_QUEUE_CTX_QW1_FLEN_SHIFT 0
-#define I40E_FCOE_QUEUE_CTX_QW1_FLEN_MASK (0x1FFFULL << \
- I40E_FCOE_QUEUE_CTX_QW1_FLEN_SHIFT)
-
-#define I40E_FCOE_QUEUE_CTX_QW1_TPH_SHIFT 13
-#define I40E_FCOE_QUEUE_CTX_QW1_TPH_MASK (0x7ULL << \
- I40E_FCOE_QUEUE_CTX_QW1_FLEN_SHIFT)
-
-enum i40e_fcoe_queue_ctx_desc_tph_bits {
- I40E_FCOE_QUEUE_CTX_DESC_TPHRDESC = 0x1,
- I40E_FCOE_QUEUE_CTX_DESC_TPHDATA = 0x2
-};
-
-#define I40E_FCOE_QUEUE_CTX_QW1_RECIPE_SHIFT 30
-#define I40E_FCOE_QUEUE_CTX_QW1_RECIPE_MASK (0x3ULL << \
- I40E_FCOE_QUEUE_CTX_QW1_RECIPE_SHIFT)
-
-/* FCoE DDP/DWO Filter Context descriptor */
-struct i40e_fcoe_filter_context_desc {
- __le32 param;
- __le16 seqn;
-
- /* 48:51(0:3) RSVD, 52:63(4:15) DMAINDX */
- __le16 rsvd_dmaindx;
-
- /* 0:7 FLAGS, 8:52 RSVD, 53:63 LANQ */
- __le64 flags_rsvd_lanq;
-};
-
-#define I40E_FCOE_FILTER_CTX_QW0_DMAINDX_SHIFT 4
-#define I40E_FCOE_FILTER_CTX_QW0_DMAINDX_MASK (0xFFF << \
- I40E_FCOE_FILTER_CTX_QW0_DMAINDX_SHIFT)
-
-enum i40e_fcoe_filter_ctx_desc_flags_bits {
- I40E_FCOE_FILTER_CTX_DESC_CTYP_DDP = 0x00,
- I40E_FCOE_FILTER_CTX_DESC_CTYP_DWO = 0x01,
- I40E_FCOE_FILTER_CTX_DESC_ENODE_INIT = 0x00,
- I40E_FCOE_FILTER_CTX_DESC_ENODE_RSP = 0x02,
- I40E_FCOE_FILTER_CTX_DESC_FC_CLASS2 = 0x00,
- I40E_FCOE_FILTER_CTX_DESC_FC_CLASS3 = 0x04
-};
-
-#define I40E_FCOE_FILTER_CTX_QW1_FLAGS_SHIFT 0
-#define I40E_FCOE_FILTER_CTX_QW1_FLAGS_MASK (0xFFULL << \
- I40E_FCOE_FILTER_CTX_QW1_FLAGS_SHIFT)
-
-#define I40E_FCOE_FILTER_CTX_QW1_PCTYPE_SHIFT 8
-#define I40E_FCOE_FILTER_CTX_QW1_PCTYPE_MASK (0x3FULL << \
- I40E_FCOE_FILTER_CTX_QW1_PCTYPE_SHIFT)
-
-#define I40E_FCOE_FILTER_CTX_QW1_LANQINDX_SHIFT 53
-#define I40E_FCOE_FILTER_CTX_QW1_LANQINDX_MASK (0x7FFULL << \
- I40E_FCOE_FILTER_CTX_QW1_LANQINDX_SHIFT)
-
-#endif /* I40E_FCOE */
enum i40e_switch_element_types {
I40E_SWITCH_ELEMENT_TYPE_MAC = 1,
I40E_SWITCH_ELEMENT_TYPE_PF = 2,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h
index 974ba2b..8552192 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h
@@ -163,7 +163,8 @@ struct i40e_virtchnl_vsi_resource {
#define I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING 0x00020000
#define I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 0x00040000
#define I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF 0X00080000
-#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM 0X00100000
+#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP 0X00100000
+#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM 0X00200000
#define I40E_VF_BASE_MODE_OFFLOADS (I40E_VIRTCHNL_VF_OFFLOAD_L2 | \
I40E_VIRTCHNL_VF_OFFLOAD_VLAN | \
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 78460c5..65c95ff 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -702,10 +702,8 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type)
dev_info(&pf->pdev->dev,
"Could not allocate VF broadcast filter\n");
spin_unlock_bh(&vsi->mac_filter_hash_lock);
- i40e_write_rx_ctl(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id),
- (u32)hena);
- i40e_write_rx_ctl(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id),
- (u32)(hena >> 32));
+ wr32(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id), (u32)hena);
+ wr32(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id), (u32)(hena >> 32));
}
/* program mac filter */
@@ -811,6 +809,11 @@ static void i40e_free_vf_res(struct i40e_vf *vf)
u32 reg_idx, reg;
int i, msix_vf;
+ /* Start by disabling VF's configuration API to prevent the OS from
+ * accessing the VF's VSI after it's freed / invalidated.
+ */
+ clear_bit(I40E_VF_STAT_INIT, &vf->vf_states);
+
/* free vsi & disconnect it from the parent uplink */
if (vf->lan_vsi_idx) {
i40e_vsi_release(pf->vsi[vf->lan_vsi_idx]);
@@ -850,7 +853,6 @@ static void i40e_free_vf_res(struct i40e_vf *vf)
/* reset some of the state variables keeping track of the resources */
vf->num_queue_pairs = 0;
vf->vf_states = 0;
- clear_bit(I40E_VF_STAT_INIT, &vf->vf_states);
}
/**
@@ -941,6 +943,14 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
/* warn the VF */
clear_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states);
+ /* Disable VF's configuration API during reset. The flag is re-enabled
+ * in i40e_alloc_vf_res(), when it's safe again to access VF's VSI.
+ * It's normally disabled in i40e_free_vf_res(), but it's safer
+ * to do it earlier to give some time to finish to any VF config
+ * functions that may still be running at this point.
+ */
+ clear_bit(I40E_VF_STAT_INIT, &vf->vf_states);
+
/* In the case of a VFLR, the HW has already reset the VF and we
* just need to clean up, so don't hit the VFRTRIG register.
*/
@@ -984,11 +994,6 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
if (!rsd)
dev_err(&pf->pdev->dev, "VF reset check timeout on VF %d\n",
vf->vf_id);
- wr32(hw, I40E_VFGEN_RSTAT1(vf->vf_id), I40E_VFR_COMPLETED);
- /* clear the reset bit in the VPGEN_VFRTRIG reg */
- reg = rd32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id));
- reg &= ~I40E_VPGEN_VFRTRIG_VFSWR_MASK;
- wr32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id), reg);
/* On initial reset, we won't have any queues */
if (vf->lan_vsi_idx == 0)
@@ -996,8 +1001,24 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
i40e_vsi_stop_rings(pf->vsi[vf->lan_vsi_idx]);
complete_reset:
- /* reallocate VF resources to reset the VSI state */
+ /* free VF resources to begin resetting the VSI state */
i40e_free_vf_res(vf);
+
+ /* Enable hardware by clearing the reset bit in the VPGEN_VFRTRIG reg.
+ * By doing this we allow HW to access VF memory at any point. If we
+ * did it any sooner, HW could access memory while it was being freed
+ * in i40e_free_vf_res(), causing an IOMMU fault.
+ *
+ * On the other hand, this needs to be done ASAP, because the VF driver
+ * is waiting for this to happen and may report a timeout. It's
+ * harmless, but it gets logged into Guest OS kernel log, so best avoid
+ * it.
+ */
+ reg = rd32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id));
+ reg &= ~I40E_VPGEN_VFRTRIG_VFSWR_MASK;
+ wr32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id), reg);
+
+ /* reallocate VF resources to finish resetting the VSI state */
if (!i40e_alloc_vf_res(vf)) {
int abs_vf_id = vf->vf_id + hw->func_caps.vf_base_id;
i40e_enable_vf_mappings(vf);
@@ -1008,7 +1029,11 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
i40e_notify_client_of_vf_reset(pf, abs_vf_id);
vf->num_vlan = 0;
}
- /* tell the VF the reset is done */
+
+ /* Tell the VF driver the reset is done. This needs to be done only
+ * after VF has been fully initialized, because the VF driver may
+ * request resources immediately after setting this flag.
+ */
wr32(hw, I40E_VFGEN_RSTAT1(vf->vf_id), I40E_VFR_VFACTIVE);
i40e_flush(hw);
@@ -1359,7 +1384,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
if (!vsi->info.pvid)
vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_VLAN;
- if (i40e_vf_client_capable(pf, vf->vf_id, I40E_CLIENT_IWARP) &&
+ if (i40e_vf_client_capable(pf, vf->vf_id) &&
(vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_IWARP)) {
vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_IWARP;
set_bit(I40E_VF_STAT_IWARPENA, &vf->vf_states);
@@ -1383,6 +1408,13 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2;
}
+ if (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_ENCAP)
+ vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_ENCAP;
+
+ if ((pf->flags & I40E_FLAG_OUTER_UDP_CSUM_CAPABLE) &&
+ (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM))
+ vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM;
+
if (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING) {
if (pf->flags & I40E_FLAG_MFP_ENABLED) {
dev_err(&pf->pdev->dev,
@@ -1853,7 +1885,7 @@ static int i40e_vc_get_stats_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
}
/* If the VF is not trusted restrict the number of MAC/VLAN it can program */
-#define I40E_VC_MAX_MAC_ADDR_PER_VF 8
+#define I40E_VC_MAX_MAC_ADDR_PER_VF 12
#define I40E_VC_MAX_VLAN_PER_VF 8
/**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index 4012d06..37af437 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -87,7 +87,6 @@ struct i40e_vf {
u16 stag;
struct i40e_virtchnl_ether_addr default_lan_addr;
- struct i40e_virtchnl_ether_addr default_fcoe_addr;
u16 port_vlan_id;
bool pf_set_mac; /* The VMM admin set the VF MAC address */
bool trusted;
diff --git a/drivers/net/ethernet/intel/i40evf/Makefile b/drivers/net/ethernet/intel/i40evf/Makefile
index 3a42383..827c7a6 100644
--- a/drivers/net/ethernet/intel/i40evf/Makefile
+++ b/drivers/net/ethernet/intel/i40evf/Makefile
@@ -32,5 +32,5 @@
obj-$(CONFIG_I40EVF) += i40evf.o
i40evf-objs := i40evf_main.o i40evf_ethtool.o i40evf_virtchnl.o \
- i40e_txrx.o i40e_common.o i40e_adminq.o
+ i40e_txrx.o i40e_common.o i40e_adminq.o i40evf_client.o
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
index eeb9864..c28cb8f 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
@@ -132,6 +132,10 @@ enum i40e_admin_queue_opc {
i40e_aqc_opc_list_func_capabilities = 0x000A,
i40e_aqc_opc_list_dev_capabilities = 0x000B,
+ /* Proxy commands */
+ i40e_aqc_opc_set_proxy_config = 0x0104,
+ i40e_aqc_opc_set_ns_proxy_table_entry = 0x0105,
+
/* LAA */
i40e_aqc_opc_mac_address_read = 0x0107,
i40e_aqc_opc_mac_address_write = 0x0108,
@@ -139,6 +143,10 @@ enum i40e_admin_queue_opc {
/* PXE */
i40e_aqc_opc_clear_pxe_mode = 0x0110,
+ /* WoL commands */
+ i40e_aqc_opc_set_wol_filter = 0x0120,
+ i40e_aqc_opc_get_wake_reason = 0x0121,
+
/* internal switch commands */
i40e_aqc_opc_get_switch_config = 0x0200,
i40e_aqc_opc_add_statistics = 0x0201,
@@ -177,6 +185,7 @@ enum i40e_admin_queue_opc {
i40e_aqc_opc_remove_control_packet_filter = 0x025B,
i40e_aqc_opc_add_cloud_filters = 0x025C,
i40e_aqc_opc_remove_cloud_filters = 0x025D,
+ i40e_aqc_opc_clear_wol_switch_filters = 0x025E,
i40e_aqc_opc_add_mirror_rule = 0x0260,
i40e_aqc_opc_delete_mirror_rule = 0x0261,
@@ -558,6 +567,56 @@ struct i40e_aqc_clear_pxe {
I40E_CHECK_CMD_LENGTH(i40e_aqc_clear_pxe);
+/* Set WoL Filter (0x0120) */
+
+struct i40e_aqc_set_wol_filter {
+ __le16 filter_index;
+#define I40E_AQC_MAX_NUM_WOL_FILTERS 8
+#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT 15
+#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_MASK (0x1 << \
+ I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT)
+
+#define I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT 0
+#define I40E_AQC_SET_WOL_FILTER_INDEX_MASK (0x7 << \
+ I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT)
+ __le16 cmd_flags;
+#define I40E_AQC_SET_WOL_FILTER 0x8000
+#define I40E_AQC_SET_WOL_FILTER_NO_TCO_WOL 0x4000
+#define I40E_AQC_SET_WOL_FILTER_ACTION_CLEAR 0
+#define I40E_AQC_SET_WOL_FILTER_ACTION_SET 1
+ __le16 valid_flags;
+#define I40E_AQC_SET_WOL_FILTER_ACTION_VALID 0x8000
+#define I40E_AQC_SET_WOL_FILTER_NO_TCO_ACTION_VALID 0x4000
+ u8 reserved[2];
+ __le32 address_high;
+ __le32 address_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_set_wol_filter);
+
+struct i40e_aqc_set_wol_filter_data {
+ u8 filter[128];
+ u8 mask[16];
+};
+
+I40E_CHECK_STRUCT_LEN(0x90, i40e_aqc_set_wol_filter_data);
+
+/* Get Wake Reason (0x0121) */
+
+struct i40e_aqc_get_wake_reason_completion {
+ u8 reserved_1[2];
+ __le16 wake_reason;
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT 0
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_MASK (0xFF << \
+ I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT)
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT 8
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_MASK (0xFF << \
+ I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT)
+ u8 reserved_2[12];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_get_wake_reason_completion);
+
/* Switch configuration commands (0x02xx) */
/* Used by many indirect commands that only pass an seid and a buffer in the
@@ -640,6 +699,8 @@ struct i40e_aqc_set_port_parameters {
#define I40E_AQ_SET_P_PARAMS_PAD_SHORT_PACKETS 2 /* must set! */
#define I40E_AQ_SET_P_PARAMS_DOUBLE_VLAN_ENA 4
__le16 bad_frame_vsi;
+#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_SHIFT 0x0
+#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_MASK 0x3FF
__le16 default_seid; /* reserved for command */
u8 reserved[10];
};
@@ -691,6 +752,7 @@ I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_resource_alloc_element_resp);
/* Set Switch Configuration (direct 0x0205) */
struct i40e_aqc_set_switch_config {
__le16 flags;
+/* flags used for both fields below */
#define I40E_AQ_SET_SWITCH_CFG_PROMISC 0x0001
#define I40E_AQ_SET_SWITCH_CFG_L2_FILTER 0x0002
__le16 valid_flags;
@@ -1839,11 +1901,12 @@ struct i40e_aqc_get_link_status {
#define I40E_AQ_CONFIG_FEC_RS_ENA 0x02
#define I40E_AQ_CONFIG_CRC_ENA 0x04
#define I40E_AQ_CONFIG_PACING_MASK 0x78
- u8 external_power_ability;
+ u8 power_desc;
#define I40E_AQ_LINK_POWER_CLASS_1 0x00
#define I40E_AQ_LINK_POWER_CLASS_2 0x01
#define I40E_AQ_LINK_POWER_CLASS_3 0x02
#define I40E_AQ_LINK_POWER_CLASS_4 0x03
+#define I40E_AQ_PWR_CLASS_MASK 0x03
u8 reserved[4];
};
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c
index 89dfdbc..626fbf1 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c
@@ -958,7 +958,9 @@ u32 i40evf_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr)
int retry = 5;
u32 val = 0;
- use_register = (hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver < 5);
+ use_register = (((hw->aq.api_maj_ver == 1) &&
+ (hw->aq.api_min_ver < 5)) ||
+ (hw->mac.type == I40E_MAC_X722));
if (!use_register) {
do_retry:
status = i40evf_aq_rx_ctl_read_register(hw, reg_addr,
@@ -1019,7 +1021,9 @@ void i40evf_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val)
bool use_register;
int retry = 5;
- use_register = (hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver < 5);
+ use_register = (((hw->aq.api_maj_ver == 1) &&
+ (hw->aq.api_min_ver < 5)) ||
+ (hw->mac.type == I40E_MAC_X722));
if (!use_register) {
do_retry:
status = i40evf_aq_rx_ctl_write_register(hw, reg_addr,
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index c91fcf4..460171e 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -137,10 +137,7 @@ u32 i40evf_get_tx_pending(struct i40e_ring *ring, bool in_sw)
{
u32 head, tail;
- if (!in_sw)
- head = i40e_get_head(ring);
- else
- head = ring->next_to_clean;
+ head = ring->next_to_clean;
tail = readl(ring->tail);
if (head != tail)
@@ -165,7 +162,6 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
{
u16 i = tx_ring->next_to_clean;
struct i40e_tx_buffer *tx_buf;
- struct i40e_tx_desc *tx_head;
struct i40e_tx_desc *tx_desc;
unsigned int total_bytes = 0, total_packets = 0;
unsigned int budget = vsi->work_limit;
@@ -174,8 +170,6 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
tx_desc = I40E_TX_DESC(tx_ring, i);
i -= tx_ring->count;
- tx_head = I40E_TX_DESC(tx_ring, i40e_get_head(tx_ring));
-
do {
struct i40e_tx_desc *eop_desc = tx_buf->next_to_watch;
@@ -186,8 +180,9 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
/* prevent any other reads prior to eop_desc */
read_barrier_depends();
- /* we have caught up to head, no work left to do */
- if (tx_head == tx_desc)
+ /* if the descriptor isn't done, no work yet to do */
+ if (!(eop_desc->cmd_type_offset_bsz &
+ cpu_to_le64(I40E_TX_DESC_DTYPE_DESC_DONE)))
break;
/* clear next_to_watch to prevent false hangs */
@@ -464,10 +459,6 @@ int i40evf_setup_tx_descriptors(struct i40e_ring *tx_ring)
/* round up to nearest 4K */
tx_ring->size = tx_ring->count * sizeof(struct i40e_tx_desc);
- /* add u32 for head writeback, align after this takes care of
- * guaranteeing this is at least one cache line in size
- */
- tx_ring->size += sizeof(u32);
tx_ring->size = ALIGN(tx_ring->size, 4096);
tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size,
&tx_ring->dma, GFP_KERNEL);
@@ -493,7 +484,6 @@ int i40evf_setup_tx_descriptors(struct i40e_ring *tx_ring)
**/
void i40evf_clean_rx_ring(struct i40e_ring *rx_ring)
{
- struct device *dev = rx_ring->dev;
unsigned long bi_size;
u16 i;
@@ -513,8 +503,22 @@ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring)
if (!rx_bi->page)
continue;
- dma_unmap_page(dev, rx_bi->dma, PAGE_SIZE, DMA_FROM_DEVICE);
- __free_pages(rx_bi->page, 0);
+ /* Invalidate cache lines that may have been written to by
+ * device so that we avoid corrupting memory.
+ */
+ dma_sync_single_range_for_cpu(rx_ring->dev,
+ rx_bi->dma,
+ rx_bi->page_offset,
+ rx_ring->rx_buf_len,
+ DMA_FROM_DEVICE);
+
+ /* free resources associated with mapping */
+ dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma,
+ i40e_rx_pg_size(rx_ring),
+ DMA_FROM_DEVICE,
+ I40E_RX_DMA_ATTR);
+
+ __page_frag_cache_drain(rx_bi->page, rx_bi->pagecnt_bias);
rx_bi->page = NULL;
rx_bi->page_offset = 0;
@@ -615,6 +619,17 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val)
}
/**
+ * i40e_rx_offset - Return expected offset into page to access data
+ * @rx_ring: Ring we are requesting offset of
+ *
+ * Returns the offset value for ring into the data buffer.
+ */
+static inline unsigned int i40e_rx_offset(struct i40e_ring *rx_ring)
+{
+ return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0;
+}
+
+/**
* i40e_alloc_mapped_page - recycle or make a new page
* @rx_ring: ring to use
* @bi: rx_buffer struct to modify
@@ -635,27 +650,33 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring,
}
/* alloc new page for storage */
- page = dev_alloc_page();
+ page = dev_alloc_pages(i40e_rx_pg_order(rx_ring));
if (unlikely(!page)) {
rx_ring->rx_stats.alloc_page_failed++;
return false;
}
/* map page for use */
- dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+ dma = dma_map_page_attrs(rx_ring->dev, page, 0,
+ i40e_rx_pg_size(rx_ring),
+ DMA_FROM_DEVICE,
+ I40E_RX_DMA_ATTR);
/* if mapping failed free memory back to system since
* there isn't much point in holding memory we can't use
*/
if (dma_mapping_error(rx_ring->dev, dma)) {
- __free_pages(page, 0);
+ __free_pages(page, i40e_rx_pg_order(rx_ring));
rx_ring->rx_stats.alloc_page_failed++;
return false;
}
bi->dma = dma;
bi->page = page;
- bi->page_offset = 0;
+ bi->page_offset = i40e_rx_offset(rx_ring);
+
+ /* initialize pagecnt_bias to 1 representing we fully own page */
+ bi->pagecnt_bias = 1;
return true;
}
@@ -702,6 +723,12 @@ bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count)
if (!i40e_alloc_mapped_page(rx_ring, bi))
goto no_buffers;
+ /* sync the buffer for use by the device */
+ dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
+ bi->page_offset,
+ rx_ring->rx_buf_len,
+ DMA_FROM_DEVICE);
+
/* Refresh the desc even if buffer_addrs didn't change
* because each write-back erases this info.
*/
@@ -742,8 +769,6 @@ bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count)
* @vsi: the VSI we care about
* @skb: skb currently being received and modified
* @rx_desc: the receive descriptor
- *
- * skb->protocol must be set before this function is called
**/
static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
struct sk_buff *skb,
@@ -895,12 +920,12 @@ void i40evf_process_skb_fields(struct i40e_ring *rx_ring,
{
i40e_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
- /* modifies the skb - consumes the enet header */
- skb->protocol = eth_type_trans(skb, rx_ring->netdev);
-
i40e_rx_checksum(rx_ring->vsi, skb, rx_desc);
skb_record_rx_queue(skb, rx_ring->queue_index);
+
+ /* modifies the skb - consumes the enet header */
+ skb->protocol = eth_type_trans(skb, rx_ring->netdev);
}
/**
@@ -945,7 +970,10 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring,
rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
/* transfer page from old buffer to new buffer */
- *new_buff = *old_buff;
+ new_buff->dma = old_buff->dma;
+ new_buff->page = old_buff->page;
+ new_buff->page_offset = old_buff->page_offset;
+ new_buff->pagecnt_bias = old_buff->pagecnt_bias;
}
/**
@@ -966,8 +994,6 @@ static inline bool i40e_page_is_reusable(struct page *page)
* the adapter for another receive
*
* @rx_buffer: buffer containing the page
- * @page: page address from rx_buffer
- * @truesize: actual size of the buffer in this page
*
* If page is reusable, rx_buffer->page_offset is adjusted to point to
* an unused region in the page.
@@ -990,13 +1016,10 @@ static inline bool i40e_page_is_reusable(struct page *page)
*
* In either case, if the page is reusable its refcount is increased.
**/
-static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer,
- struct page *page,
- const unsigned int truesize)
+static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer)
{
-#if (PAGE_SIZE >= 8192)
- unsigned int last_offset = PAGE_SIZE - I40E_RXBUFFER_2048;
-#endif
+ unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
+ struct page *page = rx_buffer->page;
/* Is any reuse possible? */
if (unlikely(!i40e_page_is_reusable(page)))
@@ -1004,21 +1027,23 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer,
#if (PAGE_SIZE < 8192)
/* if we are only owner of page we can reuse it */
- if (unlikely(page_count(page) != 1))
+ if (unlikely((page_count(page) - pagecnt_bias) > 1))
return false;
-
- /* flip page offset to other buffer */
- rx_buffer->page_offset ^= truesize;
#else
- /* move offset up to the next cache line */
- rx_buffer->page_offset += truesize;
-
- if (rx_buffer->page_offset > last_offset)
+#define I40E_LAST_OFFSET \
+ (SKB_WITH_OVERHEAD(PAGE_SIZE) - I40E_RXBUFFER_2048)
+ if (rx_buffer->page_offset > I40E_LAST_OFFSET)
return false;
#endif
- /* Inc ref count on page before passing it up to the stack */
- get_page(page);
+ /* If we have drained the page fragment pool we need to update
+ * the pagecnt_bias and page count so that we fully restock the
+ * number of references the driver holds.
+ */
+ if (unlikely(!pagecnt_bias)) {
+ page_ref_add(page, USHRT_MAX);
+ rx_buffer->pagecnt_bias = USHRT_MAX;
+ }
return true;
}
@@ -1027,122 +1052,51 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer,
* i40e_add_rx_frag - Add contents of Rx buffer to sk_buff
* @rx_ring: rx descriptor ring to transact packets on
* @rx_buffer: buffer containing page to add
- * @size: packet length from rx_desc
* @skb: sk_buff to place the data into
+ * @size: packet length from rx_desc
*
* This function will add the data contained in rx_buffer->page to the skb.
- * This is done either through a direct copy if the data in the buffer is
- * less than the skb header size, otherwise it will just attach the page as
- * a frag to the skb.
+ * It will just attach the page as a frag to the skb.
*
- * The function will then update the page offset if necessary and return
- * true if the buffer can be reused by the adapter.
+ * The function will then update the page offset.
**/
-static bool i40e_add_rx_frag(struct i40e_ring *rx_ring,
+static void i40e_add_rx_frag(struct i40e_ring *rx_ring,
struct i40e_rx_buffer *rx_buffer,
- unsigned int size,
- struct sk_buff *skb)
+ struct sk_buff *skb,
+ unsigned int size)
{
- struct page *page = rx_buffer->page;
- unsigned char *va = page_address(page) + rx_buffer->page_offset;
#if (PAGE_SIZE < 8192)
- unsigned int truesize = I40E_RXBUFFER_2048;
+ unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
#else
- unsigned int truesize = ALIGN(size, L1_CACHE_BYTES);
+ unsigned int truesize = SKB_DATA_ALIGN(size + i40e_rx_offset(rx_ring));
#endif
- unsigned int pull_len;
- if (unlikely(skb_is_nonlinear(skb)))
- goto add_tail_frag;
+ skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
+ rx_buffer->page_offset, size, truesize);
- /* will the data fit in the skb we allocated? if so, just
- * copy it as it is pretty small anyway
- */
- if (size <= I40E_RX_HDR_SIZE) {
- memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
-
- /* page is reusable, we can reuse buffer as-is */
- if (likely(i40e_page_is_reusable(page)))
- return true;
-
- /* this page cannot be reused so discard it */
- __free_pages(page, 0);
- return false;
- }
-
- /* we need the header to contain the greater of either
- * ETH_HLEN or 60 bytes if the skb->len is less than
- * 60 for skb_pad.
- */
- pull_len = eth_get_headlen(va, I40E_RX_HDR_SIZE);
-
- /* align pull length to size of long to optimize
- * memcpy performance
- */
- memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long)));
-
- /* update all of the pointers */
- va += pull_len;
- size -= pull_len;
-
-add_tail_frag:
- skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
- (unsigned long)va & ~PAGE_MASK, size, truesize);
-
- return i40e_can_reuse_rx_page(rx_buffer, page, truesize);
+ /* page is being used so we must update the page offset */
+#if (PAGE_SIZE < 8192)
+ rx_buffer->page_offset ^= truesize;
+#else
+ rx_buffer->page_offset += truesize;
+#endif
}
/**
- * i40evf_fetch_rx_buffer - Allocate skb and populate it
+ * i40e_get_rx_buffer - Fetch Rx buffer and synchronize data for use
* @rx_ring: rx descriptor ring to transact packets on
- * @rx_desc: descriptor containing info written by hardware
+ * @size: size of buffer to add to skb
*
- * This function allocates an skb on the fly, and populates it with the page
- * data from the current receive descriptor, taking care to set up the skb
- * correctly, as well as handling calling the page recycle function if
- * necessary.
+ * This function will pull an Rx buffer from the ring and synchronize it
+ * for use by the CPU.
*/
-static inline
-struct sk_buff *i40evf_fetch_rx_buffer(struct i40e_ring *rx_ring,
- union i40e_rx_desc *rx_desc,
- struct sk_buff *skb)
+static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring,
+ const unsigned int size)
{
- u64 local_status_error_len =
- le64_to_cpu(rx_desc->wb.qword1.status_error_len);
- unsigned int size =
- (local_status_error_len & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
- I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
struct i40e_rx_buffer *rx_buffer;
- struct page *page;
rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
- page = rx_buffer->page;
- prefetchw(page);
-
- if (likely(!skb)) {
- void *page_addr = page_address(page) + rx_buffer->page_offset;
-
- /* prefetch first cache line of first page */
- prefetch(page_addr);
-#if L1_CACHE_BYTES < 128
- prefetch(page_addr + L1_CACHE_BYTES);
-#endif
-
- /* allocate a skb to store the frags */
- skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
- I40E_RX_HDR_SIZE,
- GFP_ATOMIC | __GFP_NOWARN);
- if (unlikely(!skb)) {
- rx_ring->rx_stats.alloc_buff_failed++;
- return NULL;
- }
-
- /* we will be copying header into skb->data in
- * pskb_may_pull so it is in our interest to prefetch
- * it now to avoid a possible cache miss
- */
- prefetchw(skb->data);
- }
+ prefetchw(rx_buffer->page);
/* we are reusing so sync this buffer for CPU use */
dma_sync_single_range_for_cpu(rx_ring->dev,
@@ -1151,21 +1105,148 @@ struct sk_buff *i40evf_fetch_rx_buffer(struct i40e_ring *rx_ring,
size,
DMA_FROM_DEVICE);
- /* pull page into skb */
- if (i40e_add_rx_frag(rx_ring, rx_buffer, size, skb)) {
+ /* We have pulled a buffer for use, so decrement pagecnt_bias */
+ rx_buffer->pagecnt_bias--;
+
+ return rx_buffer;
+}
+
+/**
+ * i40e_construct_skb - Allocate skb and populate it
+ * @rx_ring: rx descriptor ring to transact packets on
+ * @rx_buffer: rx buffer to pull data from
+ * @size: size of buffer to add to skb
+ *
+ * This function allocates an skb. It then populates it with the page
+ * data from the current receive descriptor, taking care to set up the
+ * skb correctly.
+ */
+static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
+ struct i40e_rx_buffer *rx_buffer,
+ unsigned int size)
+{
+ void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+ unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
+#else
+ unsigned int truesize = SKB_DATA_ALIGN(size);
+#endif
+ unsigned int headlen;
+ struct sk_buff *skb;
+
+ /* prefetch first cache line of first page */
+ prefetch(va);
+#if L1_CACHE_BYTES < 128
+ prefetch(va + L1_CACHE_BYTES);
+#endif
+
+ /* allocate a skb to store the frags */
+ skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
+ I40E_RX_HDR_SIZE,
+ GFP_ATOMIC | __GFP_NOWARN);
+ if (unlikely(!skb))
+ return NULL;
+
+ /* Determine available headroom for copy */
+ headlen = size;
+ if (headlen > I40E_RX_HDR_SIZE)
+ headlen = eth_get_headlen(va, I40E_RX_HDR_SIZE);
+
+ /* align pull length to size of long to optimize memcpy performance */
+ memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
+
+ /* update all of the pointers */
+ size -= headlen;
+ if (size) {
+ skb_add_rx_frag(skb, 0, rx_buffer->page,
+ rx_buffer->page_offset + headlen,
+ size, truesize);
+
+ /* buffer is used by skb, update page_offset */
+#if (PAGE_SIZE < 8192)
+ rx_buffer->page_offset ^= truesize;
+#else
+ rx_buffer->page_offset += truesize;
+#endif
+ } else {
+ /* buffer is unused, reset bias back to rx_buffer */
+ rx_buffer->pagecnt_bias++;
+ }
+
+ return skb;
+}
+
+/**
+ * i40e_build_skb - Build skb around an existing buffer
+ * @rx_ring: Rx descriptor ring to transact packets on
+ * @rx_buffer: Rx buffer to pull data from
+ * @size: size of buffer to add to skb
+ *
+ * This function builds an skb around an existing Rx buffer, taking care
+ * to set up the skb correctly and avoid any memcpy overhead.
+ */
+static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring,
+ struct i40e_rx_buffer *rx_buffer,
+ unsigned int size)
+{
+ void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+ unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
+#else
+ unsigned int truesize = SKB_DATA_ALIGN(size);
+#endif
+ struct sk_buff *skb;
+
+ /* prefetch first cache line of first page */
+ prefetch(va);
+#if L1_CACHE_BYTES < 128
+ prefetch(va + L1_CACHE_BYTES);
+#endif
+ /* build an skb around the page buffer */
+ skb = build_skb(va - I40E_SKB_PAD, truesize);
+ if (unlikely(!skb))
+ return NULL;
+
+ /* update pointers within the skb to store the data */
+ skb_reserve(skb, I40E_SKB_PAD);
+ __skb_put(skb, size);
+
+ /* buffer is used by skb, update page_offset */
+#if (PAGE_SIZE < 8192)
+ rx_buffer->page_offset ^= truesize;
+#else
+ rx_buffer->page_offset += truesize;
+#endif
+
+ return skb;
+}
+
+/**
+ * i40e_put_rx_buffer - Clean up used buffer and either recycle or free
+ * @rx_ring: rx descriptor ring to transact packets on
+ * @rx_buffer: rx buffer to pull data from
+ *
+ * This function will clean up the contents of the rx_buffer. It will
+ * either recycle the bufer or unmap it and free the associated resources.
+ */
+static void i40e_put_rx_buffer(struct i40e_ring *rx_ring,
+ struct i40e_rx_buffer *rx_buffer)
+{
+ if (i40e_can_reuse_rx_page(rx_buffer)) {
/* hand second half of page back to the ring */
i40e_reuse_rx_page(rx_ring, rx_buffer);
rx_ring->rx_stats.page_reuse_count++;
} else {
/* we are not reusing the buffer so unmap it */
- dma_unmap_page(rx_ring->dev, rx_buffer->dma, PAGE_SIZE,
- DMA_FROM_DEVICE);
+ dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
+ i40e_rx_pg_size(rx_ring),
+ DMA_FROM_DEVICE, I40E_RX_DMA_ATTR);
+ __page_frag_cache_drain(rx_buffer->page,
+ rx_buffer->pagecnt_bias);
}
/* clear contents of buffer_info */
rx_buffer->page = NULL;
-
- return skb;
}
/**
@@ -1221,7 +1302,9 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
bool failure = false;
while (likely(total_rx_packets < budget)) {
+ struct i40e_rx_buffer *rx_buffer;
union i40e_rx_desc *rx_desc;
+ unsigned int size;
u16 vlan_tag;
u8 rx_ptype;
u64 qword;
@@ -1238,22 +1321,38 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
/* status_error_len will always be zero for unused descriptors
* because it's cleared in cleanup, and overlaps with hdr_addr
* which is always zero because packet split isn't used, if the
- * hardware wrote DD then it will be non-zero
+ * hardware wrote DD then the length will be non-zero
*/
- if (!i40e_test_staterr(rx_desc,
- BIT(I40E_RX_DESC_STATUS_DD_SHIFT)))
+ qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
+ size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
+ I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
+ if (!size)
break;
/* This memory barrier is needed to keep us from reading
- * any other fields out of the rx_desc until we know the
- * DD bit is set.
+ * any other fields out of the rx_desc until we have
+ * verified the descriptor has been written back.
*/
dma_rmb();
- skb = i40evf_fetch_rx_buffer(rx_ring, rx_desc, skb);
- if (!skb)
- break;
+ rx_buffer = i40e_get_rx_buffer(rx_ring, size);
+ /* retrieve a buffer from the ring */
+ if (skb)
+ i40e_add_rx_frag(rx_ring, rx_buffer, skb, size);
+ else if (ring_uses_build_skb(rx_ring))
+ skb = i40e_build_skb(rx_ring, rx_buffer, size);
+ else
+ skb = i40e_construct_skb(rx_ring, rx_buffer, size);
+
+ /* exit if we failed to retrieve a buffer */
+ if (!skb) {
+ rx_ring->rx_stats.alloc_buff_failed++;
+ rx_buffer->pagecnt_bias++;
+ break;
+ }
+
+ i40e_put_rx_buffer(rx_ring, rx_buffer);
cleaned_count++;
if (i40e_is_non_eop(rx_ring, rx_desc, skb))
@@ -1266,6 +1365,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
*/
if (unlikely(i40e_test_staterr(rx_desc, BIT(I40E_RXD_QW1_ERROR_SHIFT)))) {
dev_kfree_skb_any(skb);
+ skb = NULL;
continue;
}
@@ -1980,7 +2080,6 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
u16 i = tx_ring->next_to_use;
u32 td_tag = 0;
dma_addr_t dma;
- u16 desc_count = 1;
if (tx_flags & I40E_TX_FLAGS_HW_VLAN) {
td_cmd |= I40E_TX_DESC_CMD_IL2TAG1;
@@ -2016,7 +2115,6 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
tx_desc++;
i++;
- desc_count++;
if (i == tx_ring->count) {
tx_desc = I40E_TX_DESC(tx_ring, 0);
@@ -2038,7 +2136,6 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
tx_desc++;
i++;
- desc_count++;
if (i == tx_ring->count) {
tx_desc = I40E_TX_DESC(tx_ring, 0);
@@ -2064,46 +2161,8 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
i40e_maybe_stop_tx(tx_ring, DESC_NEEDED);
- /* write last descriptor with EOP bit */
- td_cmd |= I40E_TX_DESC_CMD_EOP;
-
- /* We can OR these values together as they both are checked against
- * 4 below and at this point desc_count will be used as a boolean value
- * after this if/else block.
- */
- desc_count |= ++tx_ring->packet_stride;
-
- /* Algorithm to optimize tail and RS bit setting:
- * if queue is stopped
- * mark RS bit
- * reset packet counter
- * else if xmit_more is supported and is true
- * advance packet counter to 4
- * reset desc_count to 0
- *
- * if desc_count >= 4
- * mark RS bit
- * reset packet counter
- * if desc_count > 0
- * update tail
- *
- * Note: If there are less than 4 descriptors
- * pending and interrupts were disabled the service task will
- * trigger a force WB.
- */
- if (netif_xmit_stopped(txring_txq(tx_ring))) {
- goto do_rs;
- } else if (skb->xmit_more) {
- /* set stride to arm on next packet and reset desc_count */
- tx_ring->packet_stride = WB_STRIDE;
- desc_count = 0;
- } else if (desc_count >= WB_STRIDE) {
-do_rs:
- /* write last descriptor with RS bit set */
- td_cmd |= I40E_TX_DESC_CMD_RS;
- tx_ring->packet_stride = 0;
- }
-
+ /* write last descriptor with RS and EOP bits */
+ td_cmd |= I40E_TXD_CMD;
tx_desc->cmd_type_offset_bsz =
build_ctob(td_cmd, td_offset, size, td_tag);
@@ -2119,7 +2178,7 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
first->next_to_watch = tx_desc;
/* notify HW of packet */
- if (desc_count) {
+ if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
writel(i, tx_ring->tail);
/* we need this if more than one processor can write to our tail
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index 8274ba6..901282c 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -104,10 +104,9 @@ enum i40e_dyn_idx_t {
/* Supported Rx Buffer Sizes (a multiple of 128) */
#define I40E_RXBUFFER_256 256
+#define I40E_RXBUFFER_1536 1536 /* 128B aligned standard Ethernet frame */
#define I40E_RXBUFFER_2048 2048
-#define I40E_RXBUFFER_3072 3072 /* For FCoE MTU of 2158 */
-#define I40E_RXBUFFER_4096 4096
-#define I40E_RXBUFFER_8192 8192
+#define I40E_RXBUFFER_3072 3072 /* Used for large frames w/ padding */
#define I40E_MAX_RXBUFFER 9728 /* largest size for single descriptor */
/* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we
@@ -120,6 +119,61 @@ enum i40e_dyn_idx_t {
#define I40E_RX_HDR_SIZE I40E_RXBUFFER_256
#define i40e_rx_desc i40e_32byte_rx_desc
+#define I40E_RX_DMA_ATTR \
+ (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
+
+/* Attempt to maximize the headroom available for incoming frames. We
+ * use a 2K buffer for receives and need 1536/1534 to store the data for
+ * the frame. This leaves us with 512 bytes of room. From that we need
+ * to deduct the space needed for the shared info and the padding needed
+ * to IP align the frame.
+ *
+ * Note: For cache line sizes 256 or larger this value is going to end
+ * up negative. In these cases we should fall back to the legacy
+ * receive path.
+ */
+#if (PAGE_SIZE < 8192)
+#define I40E_2K_TOO_SMALL_WITH_PADDING \
+((NET_SKB_PAD + I40E_RXBUFFER_1536) > SKB_WITH_OVERHEAD(I40E_RXBUFFER_2048))
+
+static inline int i40e_compute_pad(int rx_buf_len)
+{
+ int page_size, pad_size;
+
+ page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2);
+ pad_size = SKB_WITH_OVERHEAD(page_size) - rx_buf_len;
+
+ return pad_size;
+}
+
+static inline int i40e_skb_pad(void)
+{
+ int rx_buf_len;
+
+ /* If a 2K buffer cannot handle a standard Ethernet frame then
+ * optimize padding for a 3K buffer instead of a 1.5K buffer.
+ *
+ * For a 3K buffer we need to add enough padding to allow for
+ * tailroom due to NET_IP_ALIGN possibly shifting us out of
+ * cache-line alignment.
+ */
+ if (I40E_2K_TOO_SMALL_WITH_PADDING)
+ rx_buf_len = I40E_RXBUFFER_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN);
+ else
+ rx_buf_len = I40E_RXBUFFER_1536;
+
+ /* if needed make room for NET_IP_ALIGN */
+ rx_buf_len -= NET_IP_ALIGN;
+
+ return i40e_compute_pad(rx_buf_len);
+}
+
+#define I40E_SKB_PAD i40e_skb_pad()
+#else
+#define I40E_2K_TOO_SMALL_WITH_PADDING false
+#define I40E_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN)
+#endif
+
/**
* i40e_test_staterr - tests bits in Rx descriptor status and error fields
* @rx_desc: pointer to receive descriptor (in le64 format)
@@ -241,7 +295,12 @@ struct i40e_tx_buffer {
struct i40e_rx_buffer {
dma_addr_t dma;
struct page *page;
- unsigned int page_offset;
+#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
+ __u32 page_offset;
+#else
+ __u16 page_offset;
+#endif
+ __u16 pagecnt_bias;
};
struct i40e_queue_stats {
@@ -321,7 +380,8 @@ struct i40e_ring {
u8 packet_stride;
u16 flags;
-#define I40E_TXR_FLAGS_WB_ON_ITR BIT(0)
+#define I40E_TXR_FLAGS_WB_ON_ITR BIT(0)
+#define I40E_RXR_FLAGS_BUILD_SKB_ENABLED BIT(1)
/* stats structs */
struct i40e_queue_stats stats;
@@ -349,6 +409,21 @@ struct i40e_ring {
*/
} ____cacheline_internodealigned_in_smp;
+static inline bool ring_uses_build_skb(struct i40e_ring *ring)
+{
+ return !!(ring->flags & I40E_RXR_FLAGS_BUILD_SKB_ENABLED);
+}
+
+static inline void set_ring_build_skb_enabled(struct i40e_ring *ring)
+{
+ ring->flags |= I40E_RXR_FLAGS_BUILD_SKB_ENABLED;
+}
+
+static inline void clear_ring_build_skb_enabled(struct i40e_ring *ring)
+{
+ ring->flags &= ~I40E_RXR_FLAGS_BUILD_SKB_ENABLED;
+}
+
enum i40e_latency_range {
I40E_LOWEST_LATENCY = 0,
I40E_LOW_LATENCY = 1,
@@ -370,6 +445,17 @@ struct i40e_ring_container {
#define i40e_for_each_ring(pos, head) \
for (pos = (head).ring; pos != NULL; pos = pos->next)
+static inline unsigned int i40e_rx_pg_order(struct i40e_ring *ring)
+{
+#if (PAGE_SIZE < 8192)
+ if (ring->rx_buf_len > (PAGE_SIZE / 2))
+ return 1;
+#endif
+ return 0;
+}
+
+#define i40e_rx_pg_size(_ring) (PAGE_SIZE << i40e_rx_pg_order(_ring))
+
bool i40evf_alloc_rx_buffers(struct i40e_ring *rxr, u16 cleaned_count);
netdev_tx_t i40evf_xmit_frame(struct sk_buff *skb, struct net_device *netdev);
void i40evf_clean_tx_ring(struct i40e_ring *tx_ring);
@@ -385,20 +471,6 @@ int __i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size);
bool __i40evf_chk_linearize(struct sk_buff *skb);
/**
- * i40e_get_head - Retrieve head from head writeback
- * @tx_ring: Tx ring to fetch head of
- *
- * Returns value of Tx ring head based on value stored
- * in head write-back location
- **/
-static inline u32 i40e_get_head(struct i40e_ring *tx_ring)
-{
- void *head = (struct i40e_tx_desc *)tx_ring->desc + tx_ring->count;
-
- return le32_to_cpu(*(volatile __le32 *)head);
-}
-
-/**
* i40e_xmit_descriptor_count - calculate number of Tx descriptors needed
* @skb: send buffer
* @tx_ring: ring to send buffer on
@@ -460,19 +532,7 @@ static inline bool i40e_chk_linearize(struct sk_buff *skb, int count)
/* we can support up to 8 data buffers for a single send */
return count != I40E_MAX_BUFFER_TXD;
}
-
/**
- * i40e_rx_is_fcoe - returns true if the Rx packet type is FCoE
- * @ptype: the packet type field from Rx descriptor write-back
- **/
-static inline bool i40e_rx_is_fcoe(u16 ptype)
-{
- return (ptype >= I40E_RX_PTYPE_L2_FCOE_PAY3) &&
- (ptype <= I40E_RX_PTYPE_L2_FCOE_VFT_FCOTHER);
-}
-
-/**
- * txring_txq - Find the netdev Tx ring based on the i40e Tx ring
* @ring: Tx ring to find the netdev equivalent of
**/
static inline struct netdev_queue *txring_txq(const struct i40e_ring *ring)
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h
index d38a2b2..c5ad038 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h
@@ -81,7 +81,9 @@ enum i40e_virtchnl_ops {
I40E_VIRTCHNL_OP_GET_STATS = 15,
I40E_VIRTCHNL_OP_FCOE = 16,
I40E_VIRTCHNL_OP_EVENT = 17, /* must ALWAYS be 17 */
+ I40E_VIRTCHNL_OP_IWARP = 20,
I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP = 21,
+ I40E_VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP = 22,
I40E_VIRTCHNL_OP_CONFIG_RSS_KEY = 23,
I40E_VIRTCHNL_OP_CONFIG_RSS_LUT = 24,
I40E_VIRTCHNL_OP_GET_RSS_HENA_CAPS = 25,
@@ -161,7 +163,8 @@ struct i40e_virtchnl_vsi_resource {
#define I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING 0x00020000
#define I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 0x00040000
#define I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF 0X00080000
-#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM 0X00100000
+#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP 0X00100000
+#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM 0X00200000
#define I40E_VF_BASE_MODE_OFFLOADS (I40E_VIRTCHNL_VF_OFFLOAD_L2 | \
I40E_VIRTCHNL_VF_OFFLOAD_VLAN | \
@@ -393,6 +396,37 @@ struct i40e_virtchnl_pf_event {
int severity;
};
+/* I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP
+ * VF uses this message to request PF to map IWARP vectors to IWARP queues.
+ * The request for this originates from the VF IWARP driver through
+ * a client interface between VF LAN and VF IWARP driver.
+ * A vector could have an AEQ and CEQ attached to it although
+ * there is a single AEQ per VF IWARP instance in which case
+ * most vectors will have an INVALID_IDX for aeq and valid idx for ceq.
+ * There will never be a case where there will be multiple CEQs attached
+ * to a single vector.
+ * PF configures interrupt mapping and returns status.
+ */
+
+/* HW does not define a type value for AEQ; only for RX/TX and CEQ.
+ * In order for us to keep the interface simple, SW will define a
+ * unique type value for AEQ.
+ */
+#define I40E_QUEUE_TYPE_PE_AEQ 0x80
+#define I40E_QUEUE_INVALID_IDX 0xFFFF
+
+struct i40e_virtchnl_iwarp_qv_info {
+ u32 v_idx; /* msix_vector */
+ u16 ceq_idx;
+ u16 aeq_idx;
+ u8 itr_idx;
+};
+
+struct i40e_virtchnl_iwarp_qvlist_info {
+ u32 num_vectors;
+ struct i40e_virtchnl_iwarp_qv_info qv_info[1];
+};
+
/* VF reset states - these are written into the RSTAT register:
* I40E_VFGEN_RSTAT1 on the PF
* I40E_VFGEN_RSTAT on the VF
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h
index 00c42d8..35ded19 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf.h
+++ b/drivers/net/ethernet/intel/i40evf/i40evf.h
@@ -60,6 +60,7 @@ struct i40e_vsi {
int base_vector;
u16 work_limit;
u16 qs_handle;
+ void *priv; /* client driver data reference. */
};
/* How many Rx Buffers do we bundle into one write to the hardware ? */
@@ -71,10 +72,6 @@ struct i40e_vsi {
#define I40EVF_MAX_RXD 4096
#define I40EVF_MIN_RXD 64
#define I40EVF_REQ_DESCRIPTOR_MULTIPLE 32
-
-/* Supported Rx Buffer Sizes */
-#define I40EVF_RXBUFFER_2048 2048
-#define I40EVF_MAX_RXBUFFER 16384 /* largest size for single descriptor */
#define I40EVF_MAX_AQ_BUF_SIZE 4096
#define I40EVF_AQ_LEN 32
#define I40EVF_AQ_MAX_ERR 20 /* times to try before resetting AQ */
@@ -169,6 +166,7 @@ enum i40evf_state_t {
enum i40evf_critical_section_t {
__I40EVF_IN_CRITICAL_TASK, /* cannot be interrupted */
+ __I40EVF_IN_CLIENT_TASK,
};
/* make common code happy */
#define __I40E_DOWN __I40EVF_DOWN
@@ -178,6 +176,7 @@ struct i40evf_adapter {
struct timer_list watchdog_timer;
struct work_struct reset_task;
struct work_struct adminq_task;
+ struct delayed_work client_task;
struct delayed_work init_task;
struct i40e_q_vector *q_vectors;
struct list_head vlan_filter_list;
@@ -195,7 +194,10 @@ struct i40evf_adapter {
u64 hw_csum_rx_error;
u32 rx_desc_count;
int num_msix_vectors;
+ int num_iwarp_msix;
+ int iwarp_base_vector;
u32 client_pending;
+ struct i40e_client_instance *cinst;
struct msix_entry *msix_entries;
u32 flags;
@@ -203,7 +205,6 @@ struct i40evf_adapter {
#define I40EVF_FLAG_IN_NETPOLL BIT(4)
#define I40EVF_FLAG_IMIR_ENABLED BIT(5)
#define I40EVF_FLAG_MQ_CAPABLE BIT(6)
-#define I40EVF_FLAG_NEED_LINK_UPDATE BIT(7)
#define I40EVF_FLAG_PF_COMMS_FAILED BIT(8)
#define I40EVF_FLAG_RESET_PENDING BIT(9)
#define I40EVF_FLAG_RESET_NEEDED BIT(10)
@@ -211,8 +212,12 @@ struct i40evf_adapter {
#define I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE BIT(12)
#define I40EVF_FLAG_ADDR_SET_BY_PF BIT(13)
#define I40EVF_FLAG_SERVICE_CLIENT_REQUESTED BIT(14)
-#define I40EVF_FLAG_PROMISC_ON BIT(15)
-#define I40EVF_FLAG_ALLMULTI_ON BIT(16)
+#define I40EVF_FLAG_CLIENT_NEEDS_OPEN BIT(15)
+#define I40EVF_FLAG_CLIENT_NEEDS_CLOSE BIT(16)
+#define I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS BIT(17)
+#define I40EVF_FLAG_PROMISC_ON BIT(18)
+#define I40EVF_FLAG_ALLMULTI_ON BIT(19)
+#define I40EVF_FLAG_LEGACY_RX BIT(20)
/* duplicates for common code */
#define I40E_FLAG_FDIR_ATR_ENABLED 0
#define I40E_FLAG_DCB_ENABLED 0
@@ -220,6 +225,7 @@ struct i40evf_adapter {
#define I40E_FLAG_RX_CSUM_ENABLED I40EVF_FLAG_RX_CSUM_ENABLED
#define I40E_FLAG_WB_ON_ITR_CAPABLE I40EVF_FLAG_WB_ON_ITR_CAPABLE
#define I40E_FLAG_OUTER_UDP_CSUM_CAPABLE I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE
+#define I40E_FLAG_LEGACY_RX I40EVF_FLAG_LEGACY_RX
/* flags for admin queue service task */
u32 aq_required;
#define I40EVF_FLAG_AQ_ENABLE_QUEUES BIT(0)
@@ -258,10 +264,11 @@ struct i40evf_adapter {
bool link_up;
enum i40e_aq_link_speed link_speed;
enum i40e_virtchnl_ops current_op;
-#define CLIENT_ENABLED(_a) ((_a)->vf_res ? \
+#define CLIENT_ALLOWED(_a) ((_a)->vf_res ? \
(_a)->vf_res->vf_offload_flags & \
I40E_VIRTCHNL_VF_OFFLOAD_IWARP : \
0)
+#define CLIENT_ENABLED(_a) ((_a)->cinst)
/* RSS by the PF should be preferred over RSS via other methods. */
#define RSS_PF(_a) ((_a)->vf_res->vf_offload_flags & \
I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF)
@@ -292,6 +299,12 @@ struct i40evf_adapter {
/* Ethtool Private Flags */
+/* lan device */
+struct i40e_device {
+ struct list_head list;
+ struct i40evf_adapter *vf;
+};
+
/* needed by i40evf_ethtool.c */
extern char i40evf_driver_name[];
extern const char i40evf_driver_version[];
@@ -337,4 +350,11 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
enum i40e_virtchnl_ops v_opcode,
i40e_status v_retval, u8 *msg, u16 msglen);
int i40evf_config_rss(struct i40evf_adapter *adapter);
+int i40evf_lan_add_device(struct i40evf_adapter *adapter);
+int i40evf_lan_del_device(struct i40evf_adapter *adapter);
+void i40evf_client_subtask(struct i40evf_adapter *adapter);
+void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len);
+void i40evf_notify_client_l2_params(struct i40e_vsi *vsi);
+void i40evf_notify_client_open(struct i40e_vsi *vsi);
+void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset);
#endif /* _I40EVF_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_client.c b/drivers/net/ethernet/intel/i40evf/i40evf_client.c
new file mode 100644
index 0000000..ee73768
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_client.c
@@ -0,0 +1,564 @@
+#include <linux/list.h>
+#include <linux/errno.h>
+
+#include "i40evf.h"
+#include "i40e_prototype.h"
+#include "i40evf_client.h"
+
+static
+const char i40evf_client_interface_version_str[] = I40EVF_CLIENT_VERSION_STR;
+static struct i40e_client *vf_registered_client;
+static LIST_HEAD(i40evf_devices);
+static DEFINE_MUTEX(i40evf_device_mutex);
+
+static u32 i40evf_client_virtchnl_send(struct i40e_info *ldev,
+ struct i40e_client *client,
+ u8 *msg, u16 len);
+
+static int i40evf_client_setup_qvlist(struct i40e_info *ldev,
+ struct i40e_client *client,
+ struct i40e_qvlist_info *qvlist_info);
+
+static struct i40e_ops i40evf_lan_ops = {
+ .virtchnl_send = i40evf_client_virtchnl_send,
+ .setup_qvlist = i40evf_client_setup_qvlist,
+};
+
+/**
+ * i40evf_notify_client_message - call the client message receive callback
+ * @vsi: the VSI associated with this client
+ * @msg: message buffer
+ * @len: length of message
+ *
+ * If there is a client to this VSI, call the client
+ **/
+void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len)
+{
+ struct i40e_client_instance *cinst;
+
+ if (!vsi)
+ return;
+
+ cinst = vsi->back->cinst;
+ if (!cinst || !cinst->client || !cinst->client->ops ||
+ !cinst->client->ops->virtchnl_receive) {
+ dev_dbg(&vsi->back->pdev->dev,
+ "Cannot locate client instance virtchnl_receive function\n");
+ return;
+ }
+ cinst->client->ops->virtchnl_receive(&cinst->lan_info, cinst->client,
+ msg, len);
+}
+
+/**
+ * i40evf_notify_client_l2_params - call the client notify callback
+ * @vsi: the VSI with l2 param changes
+ *
+ * If there is a client to this VSI, call the client
+ **/
+void i40evf_notify_client_l2_params(struct i40e_vsi *vsi)
+{
+ struct i40e_client_instance *cinst;
+ struct i40e_params params;
+
+ if (!vsi)
+ return;
+
+ cinst = vsi->back->cinst;
+ memset(¶ms, 0, sizeof(params));
+ params.mtu = vsi->netdev->mtu;
+ params.link_up = vsi->back->link_up;
+ params.qos.prio_qos[0].qs_handle = vsi->qs_handle;
+
+ if (!cinst || !cinst->client || !cinst->client->ops ||
+ !cinst->client->ops->l2_param_change) {
+ dev_dbg(&vsi->back->pdev->dev,
+ "Cannot locate client instance l2_param_change function\n");
+ return;
+ }
+ cinst->client->ops->l2_param_change(&cinst->lan_info, cinst->client,
+ ¶ms);
+}
+
+/**
+ * i40evf_notify_client_open - call the client open callback
+ * @vsi: the VSI with netdev opened
+ *
+ * If there is a client to this netdev, call the client with open
+ **/
+void i40evf_notify_client_open(struct i40e_vsi *vsi)
+{
+ struct i40evf_adapter *adapter = vsi->back;
+ struct i40e_client_instance *cinst = adapter->cinst;
+ int ret;
+
+ if (!cinst || !cinst->client || !cinst->client->ops ||
+ !cinst->client->ops->open) {
+ dev_dbg(&vsi->back->pdev->dev,
+ "Cannot locate client instance open function\n");
+ return;
+ }
+ if (!(test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state))) {
+ ret = cinst->client->ops->open(&cinst->lan_info, cinst->client);
+ if (!ret)
+ set_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state);
+ }
+}
+
+/**
+ * i40evf_client_release_qvlist - send a message to the PF to release iwarp qv map
+ * @ldev: pointer to L2 context.
+ *
+ * Return 0 on success or < 0 on error
+ **/
+static int i40evf_client_release_qvlist(struct i40e_info *ldev)
+{
+ struct i40evf_adapter *adapter = ldev->vf;
+ i40e_status err;
+
+ if (adapter->aq_required)
+ return -EAGAIN;
+
+ err = i40e_aq_send_msg_to_pf(&adapter->hw,
+ I40E_VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP,
+ I40E_SUCCESS, NULL, 0, NULL);
+
+ if (err)
+ dev_err(&adapter->pdev->dev,
+ "Unable to send iWarp vector release message to PF, error %d, aq status %d\n",
+ err, adapter->hw.aq.asq_last_status);
+
+ return err;
+}
+
+/**
+ * i40evf_notify_client_close - call the client close callback
+ * @vsi: the VSI with netdev closed
+ * @reset: true when close called due to reset pending
+ *
+ * If there is a client to this netdev, call the client with close
+ **/
+void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset)
+{
+ struct i40evf_adapter *adapter = vsi->back;
+ struct i40e_client_instance *cinst = adapter->cinst;
+
+ if (!cinst || !cinst->client || !cinst->client->ops ||
+ !cinst->client->ops->close) {
+ dev_dbg(&vsi->back->pdev->dev,
+ "Cannot locate client instance close function\n");
+ return;
+ }
+ cinst->client->ops->close(&cinst->lan_info, cinst->client, reset);
+ i40evf_client_release_qvlist(&cinst->lan_info);
+ clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state);
+}
+
+/**
+ * i40evf_client_add_instance - add a client instance to the instance list
+ * @adapter: pointer to the board struct
+ * @client: pointer to a client struct in the client list.
+ *
+ * Returns cinst ptr on success, NULL on failure
+ **/
+static struct i40e_client_instance *
+i40evf_client_add_instance(struct i40evf_adapter *adapter)
+{
+ struct i40e_client_instance *cinst = NULL;
+ struct netdev_hw_addr *mac = NULL;
+ struct i40e_vsi *vsi = &adapter->vsi;
+ int i;
+
+ if (!vf_registered_client)
+ goto out;
+
+ if (adapter->cinst) {
+ cinst = adapter->cinst;
+ goto out;
+ }
+
+ cinst = kzalloc(sizeof(*cinst), GFP_KERNEL);
+ if (!cinst)
+ goto out;
+
+ cinst->lan_info.vf = (void *)adapter;
+ cinst->lan_info.netdev = vsi->netdev;
+ cinst->lan_info.pcidev = adapter->pdev;
+ cinst->lan_info.fid = 0;
+ cinst->lan_info.ftype = I40E_CLIENT_FTYPE_VF;
+ cinst->lan_info.hw_addr = adapter->hw.hw_addr;
+ cinst->lan_info.ops = &i40evf_lan_ops;
+ cinst->lan_info.version.major = I40EVF_CLIENT_VERSION_MAJOR;
+ cinst->lan_info.version.minor = I40EVF_CLIENT_VERSION_MINOR;
+ cinst->lan_info.version.build = I40EVF_CLIENT_VERSION_BUILD;
+ set_bit(__I40E_CLIENT_INSTANCE_NONE, &cinst->state);
+
+ cinst->lan_info.msix_count = adapter->num_iwarp_msix;
+ cinst->lan_info.msix_entries =
+ &adapter->msix_entries[adapter->iwarp_base_vector];
+
+ for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
+ cinst->lan_info.params.qos.prio_qos[i].tc = 0;
+ cinst->lan_info.params.qos.prio_qos[i].qs_handle =
+ vsi->qs_handle;
+ }
+
+ mac = list_first_entry(&cinst->lan_info.netdev->dev_addrs.list,
+ struct netdev_hw_addr, list);
+ if (mac)
+ ether_addr_copy(cinst->lan_info.lanmac, mac->addr);
+ else
+ dev_err(&adapter->pdev->dev, "MAC address list is empty!\n");
+
+ cinst->client = vf_registered_client;
+ adapter->cinst = cinst;
+out:
+ return cinst;
+}
+
+/**
+ * i40evf_client_del_instance - removes a client instance from the list
+ * @adapter: pointer to the board struct
+ * @client: pointer to the client struct
+ *
+ **/
+static
+void i40evf_client_del_instance(struct i40evf_adapter *adapter)
+{
+ kfree(adapter->cinst);
+ adapter->cinst = NULL;
+}
+
+/**
+ * i40evf_client_subtask - client maintenance work
+ * @adapter: board private structure
+ **/
+void i40evf_client_subtask(struct i40evf_adapter *adapter)
+{
+ struct i40e_client *client = vf_registered_client;
+ struct i40e_client_instance *cinst;
+ int ret = 0;
+
+ if (adapter->state < __I40EVF_DOWN)
+ return;
+
+ /* first check client is registered */
+ if (!client)
+ return;
+
+ /* Add the client instance to the instance list */
+ cinst = i40evf_client_add_instance(adapter);
+ if (!cinst)
+ return;
+
+ dev_info(&adapter->pdev->dev, "Added instance of Client %s\n",
+ client->name);
+
+ if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state)) {
+ /* Send an Open request to the client */
+
+ if (client->ops && client->ops->open)
+ ret = client->ops->open(&cinst->lan_info, client);
+ if (!ret)
+ set_bit(__I40E_CLIENT_INSTANCE_OPENED,
+ &cinst->state);
+ else
+ /* remove client instance */
+ i40evf_client_del_instance(adapter);
+ }
+}
+
+/**
+ * i40evf_lan_add_device - add a lan device struct to the list of lan devices
+ * @adapter: pointer to the board struct
+ *
+ * Returns 0 on success or none 0 on error
+ **/
+int i40evf_lan_add_device(struct i40evf_adapter *adapter)
+{
+ struct i40e_device *ldev;
+ int ret = 0;
+
+ mutex_lock(&i40evf_device_mutex);
+ list_for_each_entry(ldev, &i40evf_devices, list) {
+ if (ldev->vf == adapter) {
+ ret = -EEXIST;
+ goto out;
+ }
+ }
+ ldev = kzalloc(sizeof(*ldev), GFP_KERNEL);
+ if (!ldev) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ ldev->vf = adapter;
+ INIT_LIST_HEAD(&ldev->list);
+ list_add(&ldev->list, &i40evf_devices);
+ dev_info(&adapter->pdev->dev, "Added LAN device bus=0x%02x dev=0x%02x func=0x%02x\n",
+ adapter->hw.bus.bus_id, adapter->hw.bus.device,
+ adapter->hw.bus.func);
+
+ /* Since in some cases register may have happened before a device gets
+ * added, we can schedule a subtask to go initiate the clients.
+ */
+ adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
+
+out:
+ mutex_unlock(&i40evf_device_mutex);
+ return ret;
+}
+
+/**
+ * i40evf_lan_del_device - removes a lan device from the device list
+ * @adapter: pointer to the board struct
+ *
+ * Returns 0 on success or non-0 on error
+ **/
+int i40evf_lan_del_device(struct i40evf_adapter *adapter)
+{
+ struct i40e_device *ldev, *tmp;
+ int ret = -ENODEV;
+
+ mutex_lock(&i40evf_device_mutex);
+ list_for_each_entry_safe(ldev, tmp, &i40evf_devices, list) {
+ if (ldev->vf == adapter) {
+ dev_info(&adapter->pdev->dev,
+ "Deleted LAN device bus=0x%02x dev=0x%02x func=0x%02x\n",
+ adapter->hw.bus.bus_id, adapter->hw.bus.device,
+ adapter->hw.bus.func);
+ list_del(&ldev->list);
+ kfree(ldev);
+ ret = 0;
+ break;
+ }
+ }
+
+ mutex_unlock(&i40evf_device_mutex);
+ return ret;
+}
+
+/**
+ * i40evf_client_release - release client specific resources
+ * @client: pointer to the registered client
+ *
+ **/
+static void i40evf_client_release(struct i40e_client *client)
+{
+ struct i40e_client_instance *cinst;
+ struct i40e_device *ldev;
+ struct i40evf_adapter *adapter;
+
+ mutex_lock(&i40evf_device_mutex);
+ list_for_each_entry(ldev, &i40evf_devices, list) {
+ adapter = ldev->vf;
+ cinst = adapter->cinst;
+ if (!cinst)
+ continue;
+ if (test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state)) {
+ if (client->ops && client->ops->close)
+ client->ops->close(&cinst->lan_info, client,
+ false);
+ i40evf_client_release_qvlist(&cinst->lan_info);
+ clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state);
+
+ dev_warn(&adapter->pdev->dev,
+ "Client %s instance closed\n", client->name);
+ }
+ /* delete the client instance */
+ i40evf_client_del_instance(adapter);
+ dev_info(&adapter->pdev->dev, "Deleted client instance of Client %s\n",
+ client->name);
+ }
+ mutex_unlock(&i40evf_device_mutex);
+}
+
+/**
+ * i40evf_client_prepare - prepare client specific resources
+ * @client: pointer to the registered client
+ *
+ **/
+static void i40evf_client_prepare(struct i40e_client *client)
+{
+ struct i40e_device *ldev;
+ struct i40evf_adapter *adapter;
+
+ mutex_lock(&i40evf_device_mutex);
+ list_for_each_entry(ldev, &i40evf_devices, list) {
+ adapter = ldev->vf;
+ /* Signal the watchdog to service the client */
+ adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
+ }
+ mutex_unlock(&i40evf_device_mutex);
+}
+
+/**
+ * i40evf_client_virtchnl_send - send a message to the PF instance
+ * @ldev: pointer to L2 context.
+ * @client: Client pointer.
+ * @msg: pointer to message buffer
+ * @len: message length
+ *
+ * Return 0 on success or < 0 on error
+ **/
+static u32 i40evf_client_virtchnl_send(struct i40e_info *ldev,
+ struct i40e_client *client,
+ u8 *msg, u16 len)
+{
+ struct i40evf_adapter *adapter = ldev->vf;
+ i40e_status err;
+
+ if (adapter->aq_required)
+ return -EAGAIN;
+
+ err = i40e_aq_send_msg_to_pf(&adapter->hw, I40E_VIRTCHNL_OP_IWARP,
+ I40E_SUCCESS, msg, len, NULL);
+ if (err)
+ dev_err(&adapter->pdev->dev, "Unable to send iWarp message to PF, error %d, aq status %d\n",
+ err, adapter->hw.aq.asq_last_status);
+
+ return err;
+}
+
+/**
+ * i40evf_client_setup_qvlist - send a message to the PF to setup iwarp qv map
+ * @ldev: pointer to L2 context.
+ * @client: Client pointer.
+ * @qv_info: queue and vector list
+ *
+ * Return 0 on success or < 0 on error
+ **/
+static int i40evf_client_setup_qvlist(struct i40e_info *ldev,
+ struct i40e_client *client,
+ struct i40e_qvlist_info *qvlist_info)
+{
+ struct i40e_virtchnl_iwarp_qvlist_info *v_qvlist_info;
+ struct i40evf_adapter *adapter = ldev->vf;
+ struct i40e_qv_info *qv_info;
+ i40e_status err;
+ u32 v_idx, i;
+ u32 msg_size;
+
+ if (adapter->aq_required)
+ return -EAGAIN;
+
+ /* A quick check on whether the vectors belong to the client */
+ for (i = 0; i < qvlist_info->num_vectors; i++) {
+ qv_info = &qvlist_info->qv_info[i];
+ if (!qv_info)
+ continue;
+ v_idx = qv_info->v_idx;
+ if ((v_idx >=
+ (adapter->iwarp_base_vector + adapter->num_iwarp_msix)) ||
+ (v_idx < adapter->iwarp_base_vector))
+ return -EINVAL;
+ }
+
+ v_qvlist_info = (struct i40e_virtchnl_iwarp_qvlist_info *)qvlist_info;
+ msg_size = sizeof(struct i40e_virtchnl_iwarp_qvlist_info) +
+ (sizeof(struct i40e_virtchnl_iwarp_qv_info) *
+ (v_qvlist_info->num_vectors - 1));
+
+ adapter->client_pending |= BIT(I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP);
+ err = i40e_aq_send_msg_to_pf(&adapter->hw,
+ I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP,
+ I40E_SUCCESS, (u8 *)v_qvlist_info, msg_size, NULL);
+
+ if (err) {
+ dev_err(&adapter->pdev->dev,
+ "Unable to send iWarp vector config message to PF, error %d, aq status %d\n",
+ err, adapter->hw.aq.asq_last_status);
+ goto out;
+ }
+
+ err = -EBUSY;
+ for (i = 0; i < 5; i++) {
+ msleep(100);
+ if (!(adapter->client_pending &
+ BIT(I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP))) {
+ err = 0;
+ break;
+ }
+ }
+out:
+ return err;
+}
+
+/**
+ * i40evf_register_client - Register a i40e client driver with the L2 driver
+ * @client: pointer to the i40e_client struct
+ *
+ * Returns 0 on success or non-0 on error
+ **/
+int i40evf_register_client(struct i40e_client *client)
+{
+ int ret = 0;
+
+ if (!client) {
+ ret = -EIO;
+ goto out;
+ }
+
+ if (strlen(client->name) == 0) {
+ pr_info("i40evf: Failed to register client with no name\n");
+ ret = -EIO;
+ goto out;
+ }
+
+ if (vf_registered_client) {
+ pr_info("i40evf: Client %s has already been registered!\n",
+ client->name);
+ ret = -EEXIST;
+ goto out;
+ }
+
+ if ((client->version.major != I40EVF_CLIENT_VERSION_MAJOR) ||
+ (client->version.minor != I40EVF_CLIENT_VERSION_MINOR)) {
+ pr_info("i40evf: Failed to register client %s due to mismatched client interface version\n",
+ client->name);
+ pr_info("Client is using version: %02d.%02d.%02d while LAN driver supports %s\n",
+ client->version.major, client->version.minor,
+ client->version.build,
+ i40evf_client_interface_version_str);
+ ret = -EIO;
+ goto out;
+ }
+
+ vf_registered_client = client;
+
+ i40evf_client_prepare(client);
+
+ pr_info("i40evf: Registered client %s with return code %d\n",
+ client->name, ret);
+out:
+ return ret;
+}
+EXPORT_SYMBOL(i40evf_register_client);
+
+/**
+ * i40evf_unregister_client - Unregister a i40e client driver with the L2 driver
+ * @client: pointer to the i40e_client struct
+ *
+ * Returns 0 on success or non-0 on error
+ **/
+int i40evf_unregister_client(struct i40e_client *client)
+{
+ int ret = 0;
+
+ /* When a unregister request comes through we would have to send
+ * a close for each of the client instances that were opened.
+ * client_release function is called to handle this.
+ */
+ i40evf_client_release(client);
+
+ if (vf_registered_client != client) {
+ pr_info("i40evf: Client %s has not been registered\n",
+ client->name);
+ ret = -ENODEV;
+ goto out;
+ }
+ vf_registered_client = NULL;
+ pr_info("i40evf: Unregistered client %s\n", client->name);
+out:
+ return ret;
+}
+EXPORT_SYMBOL(i40evf_unregister_client);
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_client.h b/drivers/net/ethernet/intel/i40evf/i40evf_client.h
new file mode 100644
index 0000000..7d283c7
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_client.h
@@ -0,0 +1,166 @@
+#ifndef _I40E_CLIENT_H_
+#define _I40E_CLIENT_H_
+
+#define I40EVF_CLIENT_STR_LENGTH 10
+
+/* Client interface version should be updated anytime there is a change in the
+ * existing APIs or data structures.
+ */
+#define I40EVF_CLIENT_VERSION_MAJOR 0
+#define I40EVF_CLIENT_VERSION_MINOR 01
+#define I40EVF_CLIENT_VERSION_BUILD 00
+#define I40EVF_CLIENT_VERSION_STR \
+ __stringify(I40EVF_CLIENT_VERSION_MAJOR) "." \
+ __stringify(I40EVF_CLIENT_VERSION_MINOR) "." \
+ __stringify(I40EVF_CLIENT_VERSION_BUILD)
+
+struct i40e_client_version {
+ u8 major;
+ u8 minor;
+ u8 build;
+ u8 rsvd;
+};
+
+enum i40e_client_state {
+ __I40E_CLIENT_NULL,
+ __I40E_CLIENT_REGISTERED
+};
+
+enum i40e_client_instance_state {
+ __I40E_CLIENT_INSTANCE_NONE,
+ __I40E_CLIENT_INSTANCE_OPENED,
+};
+
+struct i40e_ops;
+struct i40e_client;
+
+/* HW does not define a type value for AEQ; only for RX/TX and CEQ.
+ * In order for us to keep the interface simple, SW will define a
+ * unique type value for AEQ.
+ */
+#define I40E_QUEUE_TYPE_PE_AEQ 0x80
+#define I40E_QUEUE_INVALID_IDX 0xFFFF
+
+struct i40e_qv_info {
+ u32 v_idx; /* msix_vector */
+ u16 ceq_idx;
+ u16 aeq_idx;
+ u8 itr_idx;
+};
+
+struct i40e_qvlist_info {
+ u32 num_vectors;
+ struct i40e_qv_info qv_info[1];
+};
+
+#define I40E_CLIENT_MSIX_ALL 0xFFFFFFFF
+
+/* set of LAN parameters useful for clients managed by LAN */
+
+/* Struct to hold per priority info */
+struct i40e_prio_qos_params {
+ u16 qs_handle; /* qs handle for prio */
+ u8 tc; /* TC mapped to prio */
+ u8 reserved;
+};
+
+#define I40E_CLIENT_MAX_USER_PRIORITY 8
+/* Struct to hold Client QoS */
+struct i40e_qos_params {
+ struct i40e_prio_qos_params prio_qos[I40E_CLIENT_MAX_USER_PRIORITY];
+};
+
+struct i40e_params {
+ struct i40e_qos_params qos;
+ u16 mtu;
+ u16 link_up; /* boolean */
+};
+
+/* Structure to hold LAN device info for a client device */
+struct i40e_info {
+ struct i40e_client_version version;
+ u8 lanmac[6];
+ struct net_device *netdev;
+ struct pci_dev *pcidev;
+ u8 __iomem *hw_addr;
+ u8 fid; /* function id, PF id or VF id */
+#define I40E_CLIENT_FTYPE_PF 0
+#define I40E_CLIENT_FTYPE_VF 1
+ u8 ftype; /* function type, PF or VF */
+ void *vf; /* cast to i40evf_adapter */
+
+ /* All L2 params that could change during the life span of the device
+ * and needs to be communicated to the client when they change
+ */
+ struct i40e_params params;
+ struct i40e_ops *ops;
+
+ u16 msix_count; /* number of msix vectors*/
+ /* Array down below will be dynamically allocated based on msix_count */
+ struct msix_entry *msix_entries;
+ u16 itr_index; /* Which ITR index the PE driver is suppose to use */
+};
+
+struct i40e_ops {
+ /* setup_q_vector_list enables queues with a particular vector */
+ int (*setup_qvlist)(struct i40e_info *ldev, struct i40e_client *client,
+ struct i40e_qvlist_info *qv_info);
+
+ u32 (*virtchnl_send)(struct i40e_info *ldev, struct i40e_client *client,
+ u8 *msg, u16 len);
+
+ /* If the PE Engine is unresponsive, RDMA driver can request a reset.*/
+ void (*request_reset)(struct i40e_info *ldev,
+ struct i40e_client *client);
+};
+
+struct i40e_client_ops {
+ /* Should be called from register_client() or whenever the driver is
+ * ready to create a specific client instance.
+ */
+ int (*open)(struct i40e_info *ldev, struct i40e_client *client);
+
+ /* Should be closed when netdev is unavailable or when unregister
+ * call comes in. If the close happens due to a reset, set the reset
+ * bit to true.
+ */
+ void (*close)(struct i40e_info *ldev, struct i40e_client *client,
+ bool reset);
+
+ /* called when some l2 managed parameters changes - mss */
+ void (*l2_param_change)(struct i40e_info *ldev,
+ struct i40e_client *client,
+ struct i40e_params *params);
+
+ /* called when a message is received from the PF */
+ int (*virtchnl_receive)(struct i40e_info *ldev,
+ struct i40e_client *client,
+ u8 *msg, u16 len);
+};
+
+/* Client device */
+struct i40e_client_instance {
+ struct list_head list;
+ struct i40e_info lan_info;
+ struct i40e_client *client;
+ unsigned long state;
+};
+
+struct i40e_client {
+ struct list_head list; /* list of registered clients */
+ char name[I40EVF_CLIENT_STR_LENGTH];
+ struct i40e_client_version version;
+ unsigned long state; /* client state */
+ atomic_t ref_cnt; /* Count of all the client devices of this kind */
+ u32 flags;
+#define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE BIT(0)
+#define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS BIT(2)
+ u8 type;
+#define I40E_CLIENT_IWARP 0
+ struct i40e_client_ops *ops; /* client ops provided by the client */
+};
+
+/* used by clients */
+int i40evf_register_client(struct i40e_client *client);
+int i40evf_unregister_client(struct i40e_client *client);
+#endif /* _I40E_CLIENT_H_ */
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
index 272d600..9bb2cc7 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
@@ -63,52 +63,74 @@ static const struct i40evf_stats i40evf_gstrings_stats[] = {
#define I40EVF_STATS_LEN(_dev) \
(I40EVF_GLOBAL_STATS_LEN + I40EVF_QUEUE_STATS_LEN(_dev))
+/* For now we have one and only one private flag and it is only defined
+ * when we have support for the SKIP_CPU_SYNC DMA attribute. Instead
+ * of leaving all this code sitting around empty we will strip it unless
+ * our one private flag is actually available.
+ */
+struct i40evf_priv_flags {
+ char flag_string[ETH_GSTRING_LEN];
+ u32 flag;
+ bool read_only;
+};
+
+#define I40EVF_PRIV_FLAG(_name, _flag, _read_only) { \
+ .flag_string = _name, \
+ .flag = _flag, \
+ .read_only = _read_only, \
+}
+
+static const struct i40evf_priv_flags i40evf_gstrings_priv_flags[] = {
+ I40EVF_PRIV_FLAG("legacy-rx", I40EVF_FLAG_LEGACY_RX, 0),
+};
+
+#define I40EVF_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40evf_gstrings_priv_flags)
+
/**
- * i40evf_get_settings - Get Link Speed and Duplex settings
+ * i40evf_get_link_ksettings - Get Link Speed and Duplex settings
* @netdev: network interface device structure
- * @ecmd: ethtool command
+ * @cmd: ethtool command
*
* Reports speed/duplex settings. Because this is a VF, we don't know what
* kind of link we really have, so we fake it.
**/
-static int i40evf_get_settings(struct net_device *netdev,
- struct ethtool_cmd *ecmd)
+static int i40evf_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *cmd)
{
struct i40evf_adapter *adapter = netdev_priv(netdev);
- ecmd->supported = 0;
- ecmd->autoneg = AUTONEG_DISABLE;
- ecmd->transceiver = XCVR_DUMMY1;
- ecmd->port = PORT_NONE;
+ ethtool_link_ksettings_zero_link_mode(cmd, supported);
+ cmd->base.autoneg = AUTONEG_DISABLE;
+ cmd->base.port = PORT_NONE;
/* Set speed and duplex */
switch (adapter->link_speed) {
case I40E_LINK_SPEED_40GB:
- ethtool_cmd_speed_set(ecmd, SPEED_40000);
+ cmd->base.speed = SPEED_40000;
break;
case I40E_LINK_SPEED_25GB:
#ifdef SPEED_25000
- ethtool_cmd_speed_set(ecmd, SPEED_25000);
+ cmd->base.speed = SPEED_25000;
#else
netdev_info(netdev,
"Speed is 25G, display not supported by this version of ethtool.\n");
#endif
break;
case I40E_LINK_SPEED_20GB:
- ethtool_cmd_speed_set(ecmd, SPEED_20000);
+ cmd->base.speed = SPEED_20000;
break;
case I40E_LINK_SPEED_10GB:
- ethtool_cmd_speed_set(ecmd, SPEED_10000);
+ cmd->base.speed = SPEED_10000;
break;
case I40E_LINK_SPEED_1GB:
- ethtool_cmd_speed_set(ecmd, SPEED_1000);
+ cmd->base.speed = SPEED_1000;
break;
case I40E_LINK_SPEED_100MB:
- ethtool_cmd_speed_set(ecmd, SPEED_100);
+ cmd->base.speed = SPEED_100;
break;
default:
break;
}
- ecmd->duplex = DUPLEX_FULL;
+ cmd->base.duplex = DUPLEX_FULL;
return 0;
}
@@ -125,6 +147,8 @@ static int i40evf_get_sset_count(struct net_device *netdev, int sset)
{
if (sset == ETH_SS_STATS)
return I40EVF_STATS_LEN(netdev);
+ else if (sset == ETH_SS_PRIV_FLAGS)
+ return I40EVF_PRIV_FLAGS_STR_LEN;
else
return -EINVAL;
}
@@ -190,10 +214,86 @@ static void i40evf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
snprintf(p, ETH_GSTRING_LEN, "rx-%u.bytes", i);
p += ETH_GSTRING_LEN;
}
+ } else if (sset == ETH_SS_PRIV_FLAGS) {
+ for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) {
+ snprintf(p, ETH_GSTRING_LEN, "%s",
+ i40evf_gstrings_priv_flags[i].flag_string);
+ p += ETH_GSTRING_LEN;
+ }
}
}
/**
+ * i40evf_get_priv_flags - report device private flags
+ * @dev: network interface device structure
+ *
+ * The get string set count and the string set should be matched for each
+ * flag returned. Add new strings for each flag to the i40e_gstrings_priv_flags
+ * array.
+ *
+ * Returns a u32 bitmap of flags.
+ **/
+static u32 i40evf_get_priv_flags(struct net_device *netdev)
+{
+ struct i40evf_adapter *adapter = netdev_priv(netdev);
+ u32 i, ret_flags = 0;
+
+ for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) {
+ const struct i40evf_priv_flags *priv_flags;
+
+ priv_flags = &i40evf_gstrings_priv_flags[i];
+
+ if (priv_flags->flag & adapter->flags)
+ ret_flags |= BIT(i);
+ }
+
+ return ret_flags;
+}
+
+/**
+ * i40evf_set_priv_flags - set private flags
+ * @dev: network interface device structure
+ * @flags: bit flags to be set
+ **/
+static int i40evf_set_priv_flags(struct net_device *netdev, u32 flags)
+{
+ struct i40evf_adapter *adapter = netdev_priv(netdev);
+ u64 changed_flags;
+ u32 i;
+
+ changed_flags = adapter->flags;
+
+ for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) {
+ const struct i40evf_priv_flags *priv_flags;
+
+ priv_flags = &i40evf_gstrings_priv_flags[i];
+
+ if (priv_flags->read_only)
+ continue;
+
+ if (flags & BIT(i))
+ adapter->flags |= priv_flags->flag;
+ else
+ adapter->flags &= ~(priv_flags->flag);
+ }
+
+ /* check for flags that changed */
+ changed_flags ^= adapter->flags;
+
+ /* Process any additional changes needed as a result of flag changes. */
+
+ /* issue a reset to force legacy-rx change to take effect */
+ if (changed_flags & I40EVF_FLAG_LEGACY_RX) {
+ if (netif_running(netdev)) {
+ adapter->flags |= I40EVF_FLAG_RESET_NEEDED;
+ schedule_work(&adapter->reset_task);
+ }
+ }
+
+ return 0;
+}
+
+/**
* i40evf_get_msglevel - Get debug message level
* @netdev: network interface device structure
*
@@ -239,6 +339,7 @@ static void i40evf_get_drvinfo(struct net_device *netdev,
strlcpy(drvinfo->version, i40evf_driver_version, 32);
strlcpy(drvinfo->fw_version, "N/A", 4);
strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
+ drvinfo->n_priv_flags = I40EVF_PRIV_FLAGS_STR_LEN;
}
/**
@@ -643,7 +744,6 @@ static int i40evf_set_rxfh(struct net_device *netdev, const u32 *indir,
}
static const struct ethtool_ops i40evf_ethtool_ops = {
- .get_settings = i40evf_get_settings,
.get_drvinfo = i40evf_get_drvinfo,
.get_link = ethtool_op_get_link,
.get_ringparam = i40evf_get_ringparam,
@@ -651,6 +751,8 @@ static const struct ethtool_ops i40evf_ethtool_ops = {
.get_strings = i40evf_get_strings,
.get_ethtool_stats = i40evf_get_ethtool_stats,
.get_sset_count = i40evf_get_sset_count,
+ .get_priv_flags = i40evf_get_priv_flags,
+ .set_priv_flags = i40evf_set_priv_flags,
.get_msglevel = i40evf_get_msglevel,
.set_msglevel = i40evf_set_msglevel,
.get_coalesce = i40evf_get_coalesce,
@@ -663,6 +765,7 @@ static const struct ethtool_ops i40evf_ethtool_ops = {
.set_rxfh = i40evf_set_rxfh,
.get_channels = i40evf_get_channels,
.get_rxfh_key_size = i40evf_get_rxfh_key_size,
+ .get_link_ksettings = i40evf_get_link_ksettings,
};
/**
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index f35dcaa..12a930e 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -26,6 +26,7 @@
#include "i40evf.h"
#include "i40e_prototype.h"
+#include "i40evf_client.h"
static int i40evf_setup_all_tx_resources(struct i40evf_adapter *adapter);
static int i40evf_setup_all_rx_resources(struct i40evf_adapter *adapter);
static int i40evf_close(struct net_device *netdev);
@@ -36,9 +37,9 @@ static const char i40evf_driver_string[] =
#define DRV_KERN "-k"
-#define DRV_VERSION_MAJOR 1
-#define DRV_VERSION_MINOR 6
-#define DRV_VERSION_BUILD 27
+#define DRV_VERSION_MAJOR 2
+#define DRV_VERSION_MINOR 1
+#define DRV_VERSION_BUILD 7
#define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
__stringify(DRV_VERSION_MINOR) "." \
__stringify(DRV_VERSION_BUILD) \
@@ -685,12 +686,38 @@ static void i40evf_configure_tx(struct i40evf_adapter *adapter)
**/
static void i40evf_configure_rx(struct i40evf_adapter *adapter)
{
+ unsigned int rx_buf_len = I40E_RXBUFFER_2048;
+ struct net_device *netdev = adapter->netdev;
struct i40e_hw *hw = &adapter->hw;
int i;
+ /* Legacy Rx will always default to a 2048 buffer size. */
+#if (PAGE_SIZE < 8192)
+ if (!(adapter->flags & I40EVF_FLAG_LEGACY_RX)) {
+ /* For jumbo frames on systems with 4K pages we have to use
+ * an order 1 page, so we might as well increase the size
+ * of our Rx buffer to make better use of the available space
+ */
+ rx_buf_len = I40E_RXBUFFER_3072;
+
+ /* We use a 1536 buffer size for configurations with
+ * standard Ethernet mtu. On x86 this gives us enough room
+ * for shared info and 192 bytes of padding.
+ */
+ if (!I40E_2K_TOO_SMALL_WITH_PADDING &&
+ (netdev->mtu <= ETH_DATA_LEN))
+ rx_buf_len = I40E_RXBUFFER_1536 - NET_IP_ALIGN;
+ }
+#endif
+
for (i = 0; i < adapter->num_active_queues; i++) {
adapter->rx_rings[i].tail = hw->hw_addr + I40E_QRX_TAIL1(i);
- adapter->rx_rings[i].rx_buf_len = I40EVF_RXBUFFER_2048;
+ adapter->rx_rings[i].rx_buf_len = rx_buf_len;
+
+ if (adapter->flags & I40EVF_FLAG_LEGACY_RX)
+ clear_ring_build_skb_enabled(&adapter->rx_rings[i]);
+ else
+ set_ring_build_skb_enabled(&adapter->rx_rings[i]);
}
}
@@ -1058,6 +1085,8 @@ static void i40evf_up_complete(struct i40evf_adapter *adapter)
i40evf_napi_enable_all(adapter);
adapter->aq_required |= I40EVF_FLAG_AQ_ENABLE_QUEUES;
+ if (CLIENT_ENABLED(adapter))
+ adapter->flags |= I40EVF_FLAG_CLIENT_NEEDS_OPEN;
mod_timer_pending(&adapter->watchdog_timer, jiffies + 1);
}
@@ -1685,6 +1714,7 @@ static void i40evf_watchdog_task(struct work_struct *work)
i40evf_set_promiscuous(adapter, 0);
goto watchdog_done;
}
+ schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5));
if (adapter->state == __I40EVF_RUNNING)
i40evf_request_stats(adapter);
@@ -1773,10 +1803,17 @@ static void i40evf_reset_task(struct work_struct *work)
u32 reg_val;
int i = 0, err;
- while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK,
+ while (test_and_set_bit(__I40EVF_IN_CLIENT_TASK,
&adapter->crit_section))
usleep_range(500, 1000);
-
+ if (CLIENT_ENABLED(adapter)) {
+ adapter->flags &= ~(I40EVF_FLAG_CLIENT_NEEDS_OPEN |
+ I40EVF_FLAG_CLIENT_NEEDS_CLOSE |
+ I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS |
+ I40EVF_FLAG_SERVICE_CLIENT_REQUESTED);
+ cancel_delayed_work_sync(&adapter->client_task);
+ i40evf_notify_client_close(&adapter->vsi, true);
+ }
i40evf_misc_irq_disable(adapter);
if (adapter->flags & I40EVF_FLAG_RESET_NEEDED) {
adapter->flags &= ~I40EVF_FLAG_RESET_NEEDED;
@@ -1819,6 +1856,7 @@ static void i40evf_reset_task(struct work_struct *work)
dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n",
reg_val);
i40evf_disable_vf(adapter);
+ clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section);
return; /* Do not attempt to reinit. It's dead, Jim. */
}
@@ -1861,9 +1899,8 @@ static void i40evf_reset_task(struct work_struct *work)
}
adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER;
adapter->aq_required |= I40EVF_FLAG_AQ_ADD_VLAN_FILTER;
- /* Open RDMA Client again */
- adapter->aq_required |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
+ clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section);
i40evf_misc_irq_enable(adapter);
mod_timer(&adapter->watchdog_timer, jiffies + 2);
@@ -1980,6 +2017,48 @@ static void i40evf_adminq_task(struct work_struct *work)
}
/**
+ * i40evf_client_task - worker thread to perform client work
+ * @work: pointer to work_struct containing our data
+ *
+ * This task handles client interactions. Because client calls can be
+ * reentrant, we can't handle them in the watchdog.
+ **/
+static void i40evf_client_task(struct work_struct *work)
+{
+ struct i40evf_adapter *adapter =
+ container_of(work, struct i40evf_adapter, client_task.work);
+
+ /* If we can't get the client bit, just give up. We'll be rescheduled
+ * later.
+ */
+
+ if (test_and_set_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section))
+ return;
+
+ if (adapter->flags & I40EVF_FLAG_SERVICE_CLIENT_REQUESTED) {
+ i40evf_client_subtask(adapter);
+ adapter->flags &= ~I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
+ goto out;
+ }
+ if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_CLOSE) {
+ i40evf_notify_client_close(&adapter->vsi, false);
+ adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_CLOSE;
+ goto out;
+ }
+ if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_OPEN) {
+ i40evf_notify_client_open(&adapter->vsi);
+ adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_OPEN;
+ goto out;
+ }
+ if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS) {
+ i40evf_notify_client_l2_params(&adapter->vsi);
+ adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS;
+ }
+out:
+ clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section);
+}
+
+/**
* i40evf_free_all_tx_resources - Free Tx Resources for All Queues
* @adapter: board private structure
*
@@ -2148,6 +2227,8 @@ static int i40evf_close(struct net_device *netdev)
set_bit(__I40E_DOWN, &adapter->vsi.state);
+ if (CLIENT_ENABLED(adapter))
+ adapter->flags |= I40EVF_FLAG_CLIENT_NEEDS_CLOSE;
i40evf_down(adapter);
adapter->state = __I40EVF_DOWN_PENDING;
@@ -2188,6 +2269,10 @@ static int i40evf_change_mtu(struct net_device *netdev, int new_mtu)
struct i40evf_adapter *adapter = netdev_priv(netdev);
netdev->mtu = new_mtu;
+ if (CLIENT_ENABLED(adapter)) {
+ i40evf_notify_client_l2_params(&adapter->vsi);
+ adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
+ }
adapter->flags |= I40EVF_FLAG_RESET_NEEDED;
schedule_work(&adapter->reset_task);
@@ -2328,6 +2413,8 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
struct net_device *netdev = adapter->netdev;
struct i40e_vsi *vsi = &adapter->vsi;
int i;
+ netdev_features_t hw_enc_features;
+ netdev_features_t hw_features;
/* got VF config message back from PF, now we can parse it */
for (i = 0; i < vfres->num_vsis; i++) {
@@ -2339,46 +2426,52 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
return -ENODEV;
}
- netdev->hw_enc_features |= NETIF_F_SG |
- NETIF_F_IP_CSUM |
- NETIF_F_IPV6_CSUM |
- NETIF_F_HIGHDMA |
- NETIF_F_SOFT_FEATURES |
- NETIF_F_TSO |
- NETIF_F_TSO_ECN |
- NETIF_F_TSO6 |
+ hw_enc_features = NETIF_F_SG |
+ NETIF_F_IP_CSUM |
+ NETIF_F_IPV6_CSUM |
+ NETIF_F_HIGHDMA |
+ NETIF_F_SOFT_FEATURES |
+ NETIF_F_TSO |
+ NETIF_F_TSO_ECN |
+ NETIF_F_TSO6 |
+ NETIF_F_SCTP_CRC |
+ NETIF_F_RXHASH |
+ NETIF_F_RXCSUM |
+ 0;
+
+ /* advertise to stack only if offloads for encapsulated packets is
+ * supported
+ */
+ if (vfres->vf_offload_flags & I40E_VIRTCHNL_VF_OFFLOAD_ENCAP) {
+ hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL |
NETIF_F_GSO_GRE |
NETIF_F_GSO_GRE_CSUM |
NETIF_F_GSO_IPXIP4 |
NETIF_F_GSO_IPXIP6 |
- NETIF_F_GSO_UDP_TUNNEL |
NETIF_F_GSO_UDP_TUNNEL_CSUM |
NETIF_F_GSO_PARTIAL |
- NETIF_F_SCTP_CRC |
- NETIF_F_RXHASH |
- NETIF_F_RXCSUM |
0;
- if (!(adapter->flags & I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE))
- netdev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+ if (!(vfres->vf_offload_flags &
+ I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM))
+ netdev->gso_partial_features |=
+ NETIF_F_GSO_UDP_TUNNEL_CSUM;
- netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
-
+ netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
+ netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID;
+ netdev->hw_enc_features |= hw_enc_features;
+ }
/* record features VLANs can make use of */
- netdev->vlan_features |= netdev->hw_enc_features |
- NETIF_F_TSO_MANGLEID;
+ netdev->vlan_features |= hw_enc_features | NETIF_F_TSO_MANGLEID;
/* Write features and hw_features separately to avoid polluting
- * with, or dropping, features that are set when we registgered.
+ * with, or dropping, features that are set when we registered.
*/
- netdev->hw_features |= netdev->hw_enc_features;
+ hw_features = hw_enc_features;
- netdev->features |= netdev->hw_enc_features | I40EVF_VLAN_FEATURES;
- netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID;
+ netdev->hw_features |= hw_features;
- /* disable VLAN features if not supported */
- if (!(vfres->vf_offload_flags & I40E_VIRTCHNL_VF_OFFLOAD_VLAN))
- netdev->features ^= I40EVF_VLAN_FEATURES;
+ netdev->features |= hw_features | I40EVF_VLAN_FEATURES;
adapter->vsi.id = adapter->vsi_res->vsi_id;
@@ -2519,9 +2612,6 @@ static void i40evf_init_task(struct work_struct *work)
goto err_alloc;
}
- if (hw->mac.type == I40E_MAC_X722_VF)
- adapter->flags |= I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE;
-
if (i40evf_process_config(adapter))
goto err_alloc;
adapter->current_op = I40E_VIRTCHNL_OP_UNKNOWN;
@@ -2581,6 +2671,12 @@ static void i40evf_init_task(struct work_struct *work)
adapter->netdev_registered = true;
netif_tx_stop_all_queues(netdev);
+ if (CLIENT_ALLOWED(adapter)) {
+ err = i40evf_lan_add_device(adapter);
+ if (err)
+ dev_info(&pdev->dev, "Failed to add VF to client API service list: %d\n",
+ err);
+ }
dev_info(&pdev->dev, "MAC address: %pM\n", adapter->hw.mac.addr);
if (netdev->features & NETIF_F_GRO)
@@ -2745,6 +2841,7 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
INIT_WORK(&adapter->reset_task, i40evf_reset_task);
INIT_WORK(&adapter->adminq_task, i40evf_adminq_task);
INIT_WORK(&adapter->watchdog_task, i40evf_watchdog_task);
+ INIT_DELAYED_WORK(&adapter->client_task, i40evf_client_task);
INIT_DELAYED_WORK(&adapter->init_task, i40evf_init_task);
schedule_delayed_work(&adapter->init_task,
msecs_to_jiffies(5 * (pdev->devfn & 0x07)));
@@ -2857,14 +2954,21 @@ static void i40evf_remove(struct pci_dev *pdev)
struct i40evf_adapter *adapter = netdev_priv(netdev);
struct i40evf_mac_filter *f, *ftmp;
struct i40e_hw *hw = &adapter->hw;
+ int err;
cancel_delayed_work_sync(&adapter->init_task);
cancel_work_sync(&adapter->reset_task);
-
+ cancel_delayed_work_sync(&adapter->client_task);
if (adapter->netdev_registered) {
unregister_netdev(netdev);
adapter->netdev_registered = false;
}
+ if (CLIENT_ALLOWED(adapter)) {
+ err = i40evf_lan_del_device(adapter);
+ if (err)
+ dev_warn(&pdev->dev, "Failed to delete client device: %d\n",
+ err);
+ }
/* Shut down all the garbage mashers on the detention level */
adapter->state = __I40EVF_REMOVE;
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
index bee58af..3bccfbb 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
@@ -26,6 +26,7 @@
#include "i40evf.h"
#include "i40e_prototype.h"
+#include "i40evf_client.h"
/* busy wait delay in msec */
#define I40EVF_BUSY_WAIT_DELAY 10
@@ -158,7 +159,9 @@ int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter)
I40E_VIRTCHNL_VF_OFFLOAD_RSS_REG |
I40E_VIRTCHNL_VF_OFFLOAD_VLAN |
I40E_VIRTCHNL_VF_OFFLOAD_WB_ON_ITR |
- I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2;
+ I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 |
+ I40E_VIRTCHNL_VF_OFFLOAD_ENCAP |
+ I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM;
adapter->current_op = I40E_VIRTCHNL_OP_GET_VF_RESOURCES;
adapter->aq_required &= ~I40EVF_FLAG_AQ_GET_CONFIG;
@@ -233,7 +236,7 @@ void i40evf_configure_queues(struct i40evf_adapter *adapter)
struct i40e_virtchnl_vsi_queue_config_info *vqci;
struct i40e_virtchnl_queue_pair_info *vqpi;
int pairs = adapter->num_active_queues;
- int i, len;
+ int i, len, max_frame = I40E_MAX_RXBUFFER;
if (adapter->current_op != I40E_VIRTCHNL_OP_UNKNOWN) {
/* bail because we already have a command pending */
@@ -248,6 +251,11 @@ void i40evf_configure_queues(struct i40evf_adapter *adapter)
if (!vqci)
return;
+ /* Limit maximum frame size when jumbo frames is not enabled */
+ if (!(adapter->flags & I40EVF_FLAG_LEGACY_RX) &&
+ (adapter->netdev->mtu <= ETH_DATA_LEN))
+ max_frame = I40E_RXBUFFER_1536 - NET_IP_ALIGN;
+
vqci->vsi_id = adapter->vsi_res->vsi_id;
vqci->num_queue_pairs = pairs;
vqpi = vqci->qpair;
@@ -259,17 +267,14 @@ void i40evf_configure_queues(struct i40evf_adapter *adapter)
vqpi->txq.queue_id = i;
vqpi->txq.ring_len = adapter->tx_rings[i].count;
vqpi->txq.dma_ring_addr = adapter->tx_rings[i].dma;
- vqpi->txq.headwb_enabled = 1;
- vqpi->txq.dma_headwb_addr = vqpi->txq.dma_ring_addr +
- (vqpi->txq.ring_len * sizeof(struct i40e_tx_desc));
-
vqpi->rxq.vsi_id = vqci->vsi_id;
vqpi->rxq.queue_id = i;
vqpi->rxq.ring_len = adapter->rx_rings[i].count;
vqpi->rxq.dma_ring_addr = adapter->rx_rings[i].dma;
- vqpi->rxq.max_pkt_size = adapter->netdev->mtu
- + ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN;
- vqpi->rxq.databuffer_size = adapter->rx_rings[i].rx_buf_len;
+ vqpi->rxq.max_pkt_size = max_frame;
+ vqpi->rxq.databuffer_size =
+ ALIGN(adapter->rx_rings[i].rx_buf_len,
+ BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT));
vqpi++;
}
@@ -999,6 +1004,16 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
if (v_opcode != adapter->current_op)
return;
break;
+ case I40E_VIRTCHNL_OP_IWARP:
+ /* Gobble zero-length replies from the PF. They indicate that
+ * a previous message was received OK, and the client doesn't
+ * care about that.
+ */
+ if (msglen && CLIENT_ENABLED(adapter))
+ i40evf_notify_client_message(&adapter->vsi,
+ msg, msglen);
+ break;
+
case I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP:
adapter->client_pending &=
~(BIT(I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP));
@@ -1014,7 +1029,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
}
break;
default:
- if (v_opcode != adapter->current_op)
+ if (adapter->current_op && (v_opcode != adapter->current_op))
dev_warn(&adapter->pdev->dev, "Expected response %d from PF, received %d\n",
adapter->current_op, v_opcode);
break;
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index acbc3ab..dc6e298 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -142,12 +142,24 @@ struct vf_data_storage {
/* Supported Rx Buffer Sizes */
#define IGB_RXBUFFER_256 256
#define IGB_RXBUFFER_2048 2048
+#define IGB_RXBUFFER_3072 3072
#define IGB_RX_HDR_LEN IGB_RXBUFFER_256
-#define IGB_RX_BUFSZ IGB_RXBUFFER_2048
+#define IGB_TS_HDR_LEN 16
+
+#define IGB_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN)
+#if (PAGE_SIZE < 8192)
+#define IGB_MAX_FRAME_BUILD_SKB \
+ (SKB_WITH_OVERHEAD(IGB_RXBUFFER_2048) - IGB_SKB_PAD - IGB_TS_HDR_LEN)
+#else
+#define IGB_MAX_FRAME_BUILD_SKB (IGB_RXBUFFER_2048 - IGB_TS_HDR_LEN)
+#endif
/* How many Rx Buffers do we bundle into one write to the hardware ? */
#define IGB_RX_BUFFER_WRITE 16 /* Must be power of 2 */
+#define IGB_RX_DMA_ATTR \
+ (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
+
#define AUTO_ALL_MODES 0
#define IGB_EEPROM_APME 0x0400
@@ -301,12 +313,51 @@ struct igb_q_vector {
};
enum e1000_ring_flags_t {
+ IGB_RING_FLAG_RX_3K_BUFFER,
+ IGB_RING_FLAG_RX_BUILD_SKB_ENABLED,
IGB_RING_FLAG_RX_SCTP_CSUM,
IGB_RING_FLAG_RX_LB_VLAN_BSWAP,
IGB_RING_FLAG_TX_CTX_IDX,
IGB_RING_FLAG_TX_DETECT_HANG
};
+#define ring_uses_large_buffer(ring) \
+ test_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags)
+#define set_ring_uses_large_buffer(ring) \
+ set_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags)
+#define clear_ring_uses_large_buffer(ring) \
+ clear_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags)
+
+#define ring_uses_build_skb(ring) \
+ test_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags)
+#define set_ring_build_skb_enabled(ring) \
+ set_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags)
+#define clear_ring_build_skb_enabled(ring) \
+ clear_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags)
+
+static inline unsigned int igb_rx_bufsz(struct igb_ring *ring)
+{
+#if (PAGE_SIZE < 8192)
+ if (ring_uses_large_buffer(ring))
+ return IGB_RXBUFFER_3072;
+
+ if (ring_uses_build_skb(ring))
+ return IGB_MAX_FRAME_BUILD_SKB + IGB_TS_HDR_LEN;
+#endif
+ return IGB_RXBUFFER_2048;
+}
+
+static inline unsigned int igb_rx_pg_order(struct igb_ring *ring)
+{
+#if (PAGE_SIZE < 8192)
+ if (ring_uses_large_buffer(ring))
+ return 1;
+#endif
+ return 0;
+}
+
+#define igb_rx_pg_size(_ring) (PAGE_SIZE << igb_rx_pg_order(_ring))
+
#define IGB_TXD_DCMD (E1000_ADVTXD_DCMD_EOP | E1000_ADVTXD_DCMD_RS)
#define IGB_RX_DESC(R, i) \
@@ -545,6 +596,7 @@ struct igb_adapter {
#define IGB_FLAG_HAS_MSIX BIT(13)
#define IGB_FLAG_EEE BIT(14)
#define IGB_FLAG_VLAN_PROMISC BIT(15)
+#define IGB_FLAG_RX_LEGACY BIT(16)
/* Media Auto Sense */
#define IGB_MAS_ENABLE_0 0X0001
@@ -558,7 +610,6 @@ struct igb_adapter {
#define IGB_DMCTLX_DCFLUSH_DIS 0x80000000 /* Disable DMA Coal Flush */
#define IGB_82576_TSYNC_SHIFT 19
-#define IGB_TS_HDR_LEN 16
enum e1000_state_t {
__IGB_TESTING,
__IGB_RESETTING,
@@ -591,7 +642,6 @@ void igb_configure_rx_ring(struct igb_adapter *, struct igb_ring *);
void igb_setup_tctl(struct igb_adapter *);
void igb_setup_rctl(struct igb_adapter *);
netdev_tx_t igb_xmit_frame_ring(struct sk_buff *, struct igb_ring *);
-void igb_unmap_and_free_tx_resource(struct igb_ring *, struct igb_tx_buffer *);
void igb_alloc_rx_buffers(struct igb_ring *, u16);
void igb_update_stats(struct igb_adapter *, struct rtnl_link_stats64 *);
bool igb_has_link(struct igb_adapter *adapter);
@@ -604,7 +654,7 @@ void igb_ptp_reset(struct igb_adapter *adapter);
void igb_ptp_suspend(struct igb_adapter *adapter);
void igb_ptp_rx_hang(struct igb_adapter *adapter);
void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb);
-void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, unsigned char *va,
+void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
struct sk_buff *skb);
int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr);
int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr);
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 737b664..0efb62d 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -144,7 +144,15 @@ static const char igb_gstrings_test[][ETH_GSTRING_LEN] = {
};
#define IGB_TEST_LEN (sizeof(igb_gstrings_test) / ETH_GSTRING_LEN)
-static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+static const char igb_priv_flags_strings[][ETH_GSTRING_LEN] = {
+#define IGB_PRIV_FLAGS_LEGACY_RX BIT(0)
+ "legacy-rx",
+};
+
+#define IGB_PRIV_FLAGS_STR_LEN ARRAY_SIZE(igb_priv_flags_strings)
+
+static int igb_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *cmd)
{
struct igb_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
@@ -152,76 +160,73 @@ static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
struct e1000_sfp_flags *eth_flags = &dev_spec->eth_flags;
u32 status;
u32 speed;
+ u32 supported, advertising;
status = rd32(E1000_STATUS);
if (hw->phy.media_type == e1000_media_type_copper) {
- ecmd->supported = (SUPPORTED_10baseT_Half |
- SUPPORTED_10baseT_Full |
- SUPPORTED_100baseT_Half |
- SUPPORTED_100baseT_Full |
- SUPPORTED_1000baseT_Full|
- SUPPORTED_Autoneg |
- SUPPORTED_TP |
- SUPPORTED_Pause);
- ecmd->advertising = ADVERTISED_TP;
+ supported = (SUPPORTED_10baseT_Half |
+ SUPPORTED_10baseT_Full |
+ SUPPORTED_100baseT_Half |
+ SUPPORTED_100baseT_Full |
+ SUPPORTED_1000baseT_Full|
+ SUPPORTED_Autoneg |
+ SUPPORTED_TP |
+ SUPPORTED_Pause);
+ advertising = ADVERTISED_TP;
if (hw->mac.autoneg == 1) {
- ecmd->advertising |= ADVERTISED_Autoneg;
+ advertising |= ADVERTISED_Autoneg;
/* the e1000 autoneg seems to match ethtool nicely */
- ecmd->advertising |= hw->phy.autoneg_advertised;
+ advertising |= hw->phy.autoneg_advertised;
}
- ecmd->port = PORT_TP;
- ecmd->phy_address = hw->phy.addr;
- ecmd->transceiver = XCVR_INTERNAL;
+ cmd->base.port = PORT_TP;
+ cmd->base.phy_address = hw->phy.addr;
} else {
- ecmd->supported = (SUPPORTED_FIBRE |
- SUPPORTED_1000baseKX_Full |
- SUPPORTED_Autoneg |
- SUPPORTED_Pause);
- ecmd->advertising = (ADVERTISED_FIBRE |
- ADVERTISED_1000baseKX_Full);
+ supported = (SUPPORTED_FIBRE |
+ SUPPORTED_1000baseKX_Full |
+ SUPPORTED_Autoneg |
+ SUPPORTED_Pause);
+ advertising = (ADVERTISED_FIBRE |
+ ADVERTISED_1000baseKX_Full);
if (hw->mac.type == e1000_i354) {
if ((hw->device_id ==
E1000_DEV_ID_I354_BACKPLANE_2_5GBPS) &&
!(status & E1000_STATUS_2P5_SKU_OVER)) {
- ecmd->supported |= SUPPORTED_2500baseX_Full;
- ecmd->supported &=
- ~SUPPORTED_1000baseKX_Full;
- ecmd->advertising |= ADVERTISED_2500baseX_Full;
- ecmd->advertising &=
- ~ADVERTISED_1000baseKX_Full;
+ supported |= SUPPORTED_2500baseX_Full;
+ supported &= ~SUPPORTED_1000baseKX_Full;
+ advertising |= ADVERTISED_2500baseX_Full;
+ advertising &= ~ADVERTISED_1000baseKX_Full;
}
}
if (eth_flags->e100_base_fx) {
- ecmd->supported |= SUPPORTED_100baseT_Full;
- ecmd->advertising |= ADVERTISED_100baseT_Full;
+ supported |= SUPPORTED_100baseT_Full;
+ advertising |= ADVERTISED_100baseT_Full;
}
if (hw->mac.autoneg == 1)
- ecmd->advertising |= ADVERTISED_Autoneg;
+ advertising |= ADVERTISED_Autoneg;
- ecmd->port = PORT_FIBRE;
- ecmd->transceiver = XCVR_EXTERNAL;
+ cmd->base.port = PORT_FIBRE;
}
if (hw->mac.autoneg != 1)
- ecmd->advertising &= ~(ADVERTISED_Pause |
- ADVERTISED_Asym_Pause);
+ advertising &= ~(ADVERTISED_Pause |
+ ADVERTISED_Asym_Pause);
switch (hw->fc.requested_mode) {
case e1000_fc_full:
- ecmd->advertising |= ADVERTISED_Pause;
+ advertising |= ADVERTISED_Pause;
break;
case e1000_fc_rx_pause:
- ecmd->advertising |= (ADVERTISED_Pause |
- ADVERTISED_Asym_Pause);
+ advertising |= (ADVERTISED_Pause |
+ ADVERTISED_Asym_Pause);
break;
case e1000_fc_tx_pause:
- ecmd->advertising |= ADVERTISED_Asym_Pause;
+ advertising |= ADVERTISED_Asym_Pause;
break;
default:
- ecmd->advertising &= ~(ADVERTISED_Pause |
- ADVERTISED_Asym_Pause);
+ advertising &= ~(ADVERTISED_Pause |
+ ADVERTISED_Asym_Pause);
}
if (status & E1000_STATUS_LU) {
if ((status & E1000_STATUS_2P5_SKU) &&
@@ -236,39 +241,46 @@ static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
}
if ((status & E1000_STATUS_FD) ||
hw->phy.media_type != e1000_media_type_copper)
- ecmd->duplex = DUPLEX_FULL;
+ cmd->base.duplex = DUPLEX_FULL;
else
- ecmd->duplex = DUPLEX_HALF;
+ cmd->base.duplex = DUPLEX_HALF;
} else {
speed = SPEED_UNKNOWN;
- ecmd->duplex = DUPLEX_UNKNOWN;
+ cmd->base.duplex = DUPLEX_UNKNOWN;
}
- ethtool_cmd_speed_set(ecmd, speed);
+ cmd->base.speed = speed;
if ((hw->phy.media_type == e1000_media_type_fiber) ||
hw->mac.autoneg)
- ecmd->autoneg = AUTONEG_ENABLE;
+ cmd->base.autoneg = AUTONEG_ENABLE;
else
- ecmd->autoneg = AUTONEG_DISABLE;
+ cmd->base.autoneg = AUTONEG_DISABLE;
/* MDI-X => 2; MDI =>1; Invalid =>0 */
if (hw->phy.media_type == e1000_media_type_copper)
- ecmd->eth_tp_mdix = hw->phy.is_mdix ? ETH_TP_MDI_X :
+ cmd->base.eth_tp_mdix = hw->phy.is_mdix ? ETH_TP_MDI_X :
ETH_TP_MDI;
else
- ecmd->eth_tp_mdix = ETH_TP_MDI_INVALID;
+ cmd->base.eth_tp_mdix = ETH_TP_MDI_INVALID;
if (hw->phy.mdix == AUTO_ALL_MODES)
- ecmd->eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
+ cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
else
- ecmd->eth_tp_mdix_ctrl = hw->phy.mdix;
+ cmd->base.eth_tp_mdix_ctrl = hw->phy.mdix;
+
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ supported);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+ advertising);
return 0;
}
-static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+static int igb_set_link_ksettings(struct net_device *netdev,
+ const struct ethtool_link_ksettings *cmd)
{
struct igb_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
+ u32 advertising;
/* When SoL/IDER sessions are active, autoneg/speed/duplex
* cannot be changed
@@ -283,12 +295,12 @@ static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
* some hardware doesn't allow MDI setting when speed or
* duplex is forced.
*/
- if (ecmd->eth_tp_mdix_ctrl) {
+ if (cmd->base.eth_tp_mdix_ctrl) {
if (hw->phy.media_type != e1000_media_type_copper)
return -EOPNOTSUPP;
- if ((ecmd->eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
- (ecmd->autoneg != AUTONEG_ENABLE)) {
+ if ((cmd->base.eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
+ (cmd->base.autoneg != AUTONEG_ENABLE)) {
dev_err(&adapter->pdev->dev, "forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
return -EINVAL;
}
@@ -297,10 +309,13 @@ static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
while (test_and_set_bit(__IGB_RESETTING, &adapter->state))
usleep_range(1000, 2000);
- if (ecmd->autoneg == AUTONEG_ENABLE) {
+ ethtool_convert_link_mode_to_legacy_u32(&advertising,
+ cmd->link_modes.advertising);
+
+ if (cmd->base.autoneg == AUTONEG_ENABLE) {
hw->mac.autoneg = 1;
if (hw->phy.media_type == e1000_media_type_fiber) {
- hw->phy.autoneg_advertised = ecmd->advertising |
+ hw->phy.autoneg_advertised = advertising |
ADVERTISED_FIBRE |
ADVERTISED_Autoneg;
switch (adapter->link_speed) {
@@ -320,31 +335,31 @@ static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
break;
}
} else {
- hw->phy.autoneg_advertised = ecmd->advertising |
+ hw->phy.autoneg_advertised = advertising |
ADVERTISED_TP |
ADVERTISED_Autoneg;
}
- ecmd->advertising = hw->phy.autoneg_advertised;
+ advertising = hw->phy.autoneg_advertised;
if (adapter->fc_autoneg)
hw->fc.requested_mode = e1000_fc_default;
} else {
- u32 speed = ethtool_cmd_speed(ecmd);
+ u32 speed = cmd->base.speed;
/* calling this overrides forced MDI setting */
- if (igb_set_spd_dplx(adapter, speed, ecmd->duplex)) {
+ if (igb_set_spd_dplx(adapter, speed, cmd->base.duplex)) {
clear_bit(__IGB_RESETTING, &adapter->state);
return -EINVAL;
}
}
/* MDI-X => 2; MDI => 1; Auto => 3 */
- if (ecmd->eth_tp_mdix_ctrl) {
+ if (cmd->base.eth_tp_mdix_ctrl) {
/* fix up the value for auto (3 => 0) as zero is mapped
* internally to auto
*/
- if (ecmd->eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
+ if (cmd->base.eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
hw->phy.mdix = AUTO_ALL_MODES;
else
- hw->phy.mdix = ecmd->eth_tp_mdix_ctrl;
+ hw->phy.mdix = cmd->base.eth_tp_mdix_ctrl;
}
/* reset the link */
@@ -852,6 +867,8 @@ static void igb_get_drvinfo(struct net_device *netdev,
sizeof(drvinfo->fw_version));
strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
sizeof(drvinfo->bus_info));
+
+ drvinfo->n_priv_flags = IGB_PRIV_FLAGS_STR_LEN;
}
static void igb_get_ringparam(struct net_device *netdev,
@@ -1811,14 +1828,14 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring,
tx_ntc = tx_ring->next_to_clean;
rx_desc = IGB_RX_DESC(rx_ring, rx_ntc);
- while (igb_test_staterr(rx_desc, E1000_RXD_STAT_DD)) {
+ while (rx_desc->wb.upper.length) {
/* check Rx buffer */
rx_buffer_info = &rx_ring->rx_buffer_info[rx_ntc];
/* sync Rx buffer for CPU read */
dma_sync_single_for_cpu(rx_ring->dev,
rx_buffer_info->dma,
- IGB_RX_BUFSZ,
+ size,
DMA_FROM_DEVICE);
/* verify contents of skb */
@@ -1828,12 +1845,21 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring,
/* sync Rx buffer for device write */
dma_sync_single_for_device(rx_ring->dev,
rx_buffer_info->dma,
- IGB_RX_BUFSZ,
+ size,
DMA_FROM_DEVICE);
/* unmap buffer on Tx side */
tx_buffer_info = &tx_ring->tx_buffer_info[tx_ntc];
- igb_unmap_and_free_tx_resource(tx_ring, tx_buffer_info);
+
+ /* Free all the Tx ring sk_buffs */
+ dev_kfree_skb_any(tx_buffer_info->skb);
+
+ /* unmap skb header data */
+ dma_unmap_single(tx_ring->dev,
+ dma_unmap_addr(tx_buffer_info, dma),
+ dma_unmap_len(tx_buffer_info, len),
+ DMA_TO_DEVICE);
+ dma_unmap_len_set(tx_buffer_info, len, 0);
/* increment Rx/Tx next to clean counters */
rx_ntc++;
@@ -2271,6 +2297,8 @@ static int igb_get_sset_count(struct net_device *netdev, int sset)
return IGB_STATS_LEN;
case ETH_SS_TEST:
return IGB_TEST_LEN;
+ case ETH_SS_PRIV_FLAGS:
+ return IGB_PRIV_FLAGS_STR_LEN;
default:
return -ENOTSUPP;
}
@@ -2376,6 +2404,10 @@ static void igb_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
}
/* BUG_ON(p - data != IGB_STATS_LEN * ETH_GSTRING_LEN); */
break;
+ case ETH_SS_PRIV_FLAGS:
+ memcpy(data, igb_priv_flags_strings,
+ IGB_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN);
+ break;
}
}
@@ -3388,9 +3420,38 @@ static int igb_set_channels(struct net_device *netdev,
return 0;
}
+static u32 igb_get_priv_flags(struct net_device *netdev)
+{
+ struct igb_adapter *adapter = netdev_priv(netdev);
+ u32 priv_flags = 0;
+
+ if (adapter->flags & IGB_FLAG_RX_LEGACY)
+ priv_flags |= IGB_PRIV_FLAGS_LEGACY_RX;
+
+ return priv_flags;
+}
+
+static int igb_set_priv_flags(struct net_device *netdev, u32 priv_flags)
+{
+ struct igb_adapter *adapter = netdev_priv(netdev);
+ unsigned int flags = adapter->flags;
+
+ flags &= ~IGB_FLAG_RX_LEGACY;
+ if (priv_flags & IGB_PRIV_FLAGS_LEGACY_RX)
+ flags |= IGB_FLAG_RX_LEGACY;
+
+ if (flags != adapter->flags) {
+ adapter->flags = flags;
+
+ /* reset interface to repopulate queues */
+ if (netif_running(netdev))
+ igb_reinit_locked(adapter);
+ }
+
+ return 0;
+}
+
static const struct ethtool_ops igb_ethtool_ops = {
- .get_settings = igb_get_settings,
- .set_settings = igb_set_settings,
.get_drvinfo = igb_get_drvinfo,
.get_regs_len = igb_get_regs_len,
.get_regs = igb_get_regs,
@@ -3426,8 +3487,12 @@ static const struct ethtool_ops igb_ethtool_ops = {
.set_rxfh = igb_set_rxfh,
.get_channels = igb_get_channels,
.set_channels = igb_set_channels,
+ .get_priv_flags = igb_get_priv_flags,
+ .set_priv_flags = igb_set_priv_flags,
.begin = igb_ethtool_begin,
.complete = igb_ethtool_complete,
+ .get_link_ksettings = igb_get_link_ksettings,
+ .set_link_ksettings = igb_set_link_ksettings,
};
void igb_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index be456ba..26a821f 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -554,7 +554,7 @@ static void igb_dump(struct igb_adapter *adapter)
16, 1,
page_address(buffer_info->page) +
buffer_info->page_offset,
- IGB_RX_BUFSZ, true);
+ igb_rx_bufsz(rx_ring), true);
}
}
}
@@ -3293,7 +3293,7 @@ int igb_setup_tx_resources(struct igb_ring *tx_ring)
size = sizeof(struct igb_tx_buffer) * tx_ring->count;
- tx_ring->tx_buffer_info = vzalloc(size);
+ tx_ring->tx_buffer_info = vmalloc(size);
if (!tx_ring->tx_buffer_info)
goto err;
@@ -3404,6 +3404,10 @@ void igb_configure_tx_ring(struct igb_adapter *adapter,
txdctl |= IGB_TX_HTHRESH << 8;
txdctl |= IGB_TX_WTHRESH << 16;
+ /* reinitialize tx_buffer_info */
+ memset(ring->tx_buffer_info, 0,
+ sizeof(struct igb_tx_buffer) * ring->count);
+
txdctl |= E1000_TXDCTL_QUEUE_ENABLE;
wr32(E1000_TXDCTL(reg_idx), txdctl);
}
@@ -3435,7 +3439,7 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring)
size = sizeof(struct igb_rx_buffer) * rx_ring->count;
- rx_ring->rx_buffer_info = vzalloc(size);
+ rx_ring->rx_buffer_info = vmalloc(size);
if (!rx_ring->rx_buffer_info)
goto err;
@@ -3720,6 +3724,7 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
struct igb_ring *ring)
{
struct e1000_hw *hw = &adapter->hw;
+ union e1000_adv_rx_desc *rx_desc;
u64 rdba = ring->dma;
int reg_idx = ring->reg_idx;
u32 srrctl = 0, rxdctl = 0;
@@ -3741,7 +3746,10 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
/* set descriptor configuration */
srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT;
- srrctl |= IGB_RX_BUFSZ >> E1000_SRRCTL_BSIZEPKT_SHIFT;
+ if (ring_uses_large_buffer(ring))
+ srrctl |= IGB_RXBUFFER_3072 >> E1000_SRRCTL_BSIZEPKT_SHIFT;
+ else
+ srrctl |= IGB_RXBUFFER_2048 >> E1000_SRRCTL_BSIZEPKT_SHIFT;
srrctl |= E1000_SRRCTL_DESCTYPE_ADV_ONEBUF;
if (hw->mac.type >= e1000_82580)
srrctl |= E1000_SRRCTL_TIMESTAMP;
@@ -3758,11 +3766,39 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
rxdctl |= IGB_RX_HTHRESH << 8;
rxdctl |= IGB_RX_WTHRESH << 16;
+ /* initialize rx_buffer_info */
+ memset(ring->rx_buffer_info, 0,
+ sizeof(struct igb_rx_buffer) * ring->count);
+
+ /* initialize Rx descriptor 0 */
+ rx_desc = IGB_RX_DESC(ring, 0);
+ rx_desc->wb.upper.length = 0;
+
/* enable receive descriptor fetching */
rxdctl |= E1000_RXDCTL_QUEUE_ENABLE;
wr32(E1000_RXDCTL(reg_idx), rxdctl);
}
+static void igb_set_rx_buffer_len(struct igb_adapter *adapter,
+ struct igb_ring *rx_ring)
+{
+ /* set build_skb and buffer size flags */
+ clear_ring_build_skb_enabled(rx_ring);
+ clear_ring_uses_large_buffer(rx_ring);
+
+ if (adapter->flags & IGB_FLAG_RX_LEGACY)
+ return;
+
+ set_ring_build_skb_enabled(rx_ring);
+
+#if (PAGE_SIZE < 8192)
+ if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB)
+ return;
+
+ set_ring_uses_large_buffer(rx_ring);
+#endif
+}
+
/**
* igb_configure_rx - Configure receive Unit after Reset
* @adapter: board private structure
@@ -3780,8 +3816,12 @@ static void igb_configure_rx(struct igb_adapter *adapter)
/* Setup the HW Rx Head and Tail Descriptor Pointers and
* the Base and Length of the Rx Descriptor Ring
*/
- for (i = 0; i < adapter->num_rx_queues; i++)
- igb_configure_rx_ring(adapter, adapter->rx_ring[i]);
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ struct igb_ring *rx_ring = adapter->rx_ring[i];
+
+ igb_set_rx_buffer_len(adapter, rx_ring);
+ igb_configure_rx_ring(adapter, rx_ring);
+ }
}
/**
@@ -3822,55 +3862,63 @@ static void igb_free_all_tx_resources(struct igb_adapter *adapter)
igb_free_tx_resources(adapter->tx_ring[i]);
}
-void igb_unmap_and_free_tx_resource(struct igb_ring *ring,
- struct igb_tx_buffer *tx_buffer)
-{
- if (tx_buffer->skb) {
- dev_kfree_skb_any(tx_buffer->skb);
- if (dma_unmap_len(tx_buffer, len))
- dma_unmap_single(ring->dev,
- dma_unmap_addr(tx_buffer, dma),
- dma_unmap_len(tx_buffer, len),
- DMA_TO_DEVICE);
- } else if (dma_unmap_len(tx_buffer, len)) {
- dma_unmap_page(ring->dev,
- dma_unmap_addr(tx_buffer, dma),
- dma_unmap_len(tx_buffer, len),
- DMA_TO_DEVICE);
- }
- tx_buffer->next_to_watch = NULL;
- tx_buffer->skb = NULL;
- dma_unmap_len_set(tx_buffer, len, 0);
- /* buffer_info must be completely set up in the transmit path */
-}
-
/**
* igb_clean_tx_ring - Free Tx Buffers
* @tx_ring: ring to be cleaned
**/
static void igb_clean_tx_ring(struct igb_ring *tx_ring)
{
- struct igb_tx_buffer *buffer_info;
- unsigned long size;
- u16 i;
+ u16 i = tx_ring->next_to_clean;
+ struct igb_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i];
- if (!tx_ring->tx_buffer_info)
- return;
- /* Free all the Tx ring sk_buffs */
+ while (i != tx_ring->next_to_use) {
+ union e1000_adv_tx_desc *eop_desc, *tx_desc;
- for (i = 0; i < tx_ring->count; i++) {
- buffer_info = &tx_ring->tx_buffer_info[i];
- igb_unmap_and_free_tx_resource(tx_ring, buffer_info);
+ /* Free all the Tx ring sk_buffs */
+ dev_kfree_skb_any(tx_buffer->skb);
+
+ /* unmap skb header data */
+ dma_unmap_single(tx_ring->dev,
+ dma_unmap_addr(tx_buffer, dma),
+ dma_unmap_len(tx_buffer, len),
+ DMA_TO_DEVICE);
+
+ /* check for eop_desc to determine the end of the packet */
+ eop_desc = tx_buffer->next_to_watch;
+ tx_desc = IGB_TX_DESC(tx_ring, i);
+
+ /* unmap remaining buffers */
+ while (tx_desc != eop_desc) {
+ tx_buffer++;
+ tx_desc++;
+ i++;
+ if (unlikely(i == tx_ring->count)) {
+ i = 0;
+ tx_buffer = tx_ring->tx_buffer_info;
+ tx_desc = IGB_TX_DESC(tx_ring, 0);
+ }
+
+ /* unmap any remaining paged data */
+ if (dma_unmap_len(tx_buffer, len))
+ dma_unmap_page(tx_ring->dev,
+ dma_unmap_addr(tx_buffer, dma),
+ dma_unmap_len(tx_buffer, len),
+ DMA_TO_DEVICE);
+ }
+
+ /* move us one more past the eop_desc for start of next pkt */
+ tx_buffer++;
+ i++;
+ if (unlikely(i == tx_ring->count)) {
+ i = 0;
+ tx_buffer = tx_ring->tx_buffer_info;
+ }
}
+ /* reset BQL for queue */
netdev_tx_reset_queue(txring_txq(tx_ring));
- size = sizeof(struct igb_tx_buffer) * tx_ring->count;
- memset(tx_ring->tx_buffer_info, 0, size);
-
- /* Zero out the descriptor ring */
- memset(tx_ring->desc, 0, tx_ring->size);
-
+ /* reset next_to_use and next_to_clean */
tx_ring->next_to_use = 0;
tx_ring->next_to_clean = 0;
}
@@ -3932,50 +3980,39 @@ static void igb_free_all_rx_resources(struct igb_adapter *adapter)
**/
static void igb_clean_rx_ring(struct igb_ring *rx_ring)
{
- unsigned long size;
- u16 i;
+ u16 i = rx_ring->next_to_clean;
if (rx_ring->skb)
dev_kfree_skb(rx_ring->skb);
rx_ring->skb = NULL;
- if (!rx_ring->rx_buffer_info)
- return;
-
/* Free all the Rx ring sk_buffs */
- for (i = 0; i < rx_ring->count; i++) {
+ while (i != rx_ring->next_to_alloc) {
struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i];
- if (!buffer_info->page)
- continue;
-
/* Invalidate cache lines that may have been written to by
* device so that we avoid corrupting memory.
*/
dma_sync_single_range_for_cpu(rx_ring->dev,
buffer_info->dma,
buffer_info->page_offset,
- IGB_RX_BUFSZ,
+ igb_rx_bufsz(rx_ring),
DMA_FROM_DEVICE);
/* free resources associated with mapping */
dma_unmap_page_attrs(rx_ring->dev,
buffer_info->dma,
- PAGE_SIZE,
+ igb_rx_pg_size(rx_ring),
DMA_FROM_DEVICE,
- DMA_ATTR_SKIP_CPU_SYNC);
+ IGB_RX_DMA_ATTR);
__page_frag_cache_drain(buffer_info->page,
buffer_info->pagecnt_bias);
- buffer_info->page = NULL;
+ i++;
+ if (i == rx_ring->count)
+ i = 0;
}
- size = sizeof(struct igb_rx_buffer) * rx_ring->count;
- memset(rx_ring->rx_buffer_info, 0, size);
-
- /* Zero out the descriptor ring */
- memset(rx_ring->desc, 0, rx_ring->size);
-
rx_ring->next_to_alloc = 0;
rx_ring->next_to_clean = 0;
rx_ring->next_to_use = 0;
@@ -4240,7 +4277,7 @@ static void igb_set_rx_mode(struct net_device *netdev)
struct igb_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
unsigned int vfn = adapter->vfs_allocated_count;
- u32 rctl = 0, vmolr = 0;
+ u32 rctl = 0, vmolr = 0, rlpml = MAX_JUMBO_FRAME_SIZE;
int count;
/* Check for Promiscuous and All Multicast modes */
@@ -4298,6 +4335,14 @@ static void igb_set_rx_mode(struct net_device *netdev)
E1000_RCTL_VFE);
wr32(E1000_RCTL, rctl);
+#if (PAGE_SIZE < 8192)
+ if (!adapter->vfs_allocated_count) {
+ if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB)
+ rlpml = IGB_MAX_FRAME_BUILD_SKB;
+ }
+#endif
+ wr32(E1000_RLPML, rlpml);
+
/* In order to support SR-IOV and eventually VMDq it is necessary to set
* the VMOLR to enable the appropriate modes. Without this workaround
* we will have issues with VLAN tag stripping not being done for frames
@@ -4312,12 +4357,17 @@ static void igb_set_rx_mode(struct net_device *netdev)
vmolr |= rd32(E1000_VMOLR(vfn)) &
~(E1000_VMOLR_ROPE | E1000_VMOLR_MPME | E1000_VMOLR_ROMPE);
- /* enable Rx jumbo frames, no need for restriction */
+ /* enable Rx jumbo frames, restrict as needed to support build_skb */
vmolr &= ~E1000_VMOLR_RLPML_MASK;
- vmolr |= MAX_JUMBO_FRAME_SIZE | E1000_VMOLR_LPE;
+#if (PAGE_SIZE < 8192)
+ if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB)
+ vmolr |= IGB_MAX_FRAME_BUILD_SKB;
+ else
+#endif
+ vmolr |= MAX_JUMBO_FRAME_SIZE;
+ vmolr |= E1000_VMOLR_LPE;
wr32(E1000_VMOLR(vfn), vmolr);
- wr32(E1000_RLPML, MAX_JUMBO_FRAME_SIZE);
igb_restore_vf_multicasts(adapter);
}
@@ -5256,18 +5306,32 @@ static void igb_tx_map(struct igb_ring *tx_ring,
dma_error:
dev_err(tx_ring->dev, "TX DMA map failed\n");
+ tx_buffer = &tx_ring->tx_buffer_info[i];
/* clear dma mappings for failed tx_buffer_info map */
- for (;;) {
+ while (tx_buffer != first) {
+ if (dma_unmap_len(tx_buffer, len))
+ dma_unmap_page(tx_ring->dev,
+ dma_unmap_addr(tx_buffer, dma),
+ dma_unmap_len(tx_buffer, len),
+ DMA_TO_DEVICE);
+ dma_unmap_len_set(tx_buffer, len, 0);
+
+ if (i--)
+ i += tx_ring->count;
tx_buffer = &tx_ring->tx_buffer_info[i];
- igb_unmap_and_free_tx_resource(tx_ring, tx_buffer);
- if (tx_buffer == first)
- break;
- if (i == 0)
- i = tx_ring->count;
- i--;
}
+ if (dma_unmap_len(tx_buffer, len))
+ dma_unmap_single(tx_ring->dev,
+ dma_unmap_addr(tx_buffer, dma),
+ dma_unmap_len(tx_buffer, len),
+ DMA_TO_DEVICE);
+ dma_unmap_len_set(tx_buffer, len, 0);
+
+ dev_kfree_skb_any(tx_buffer->skb);
+ tx_buffer->skb = NULL;
+
tx_ring->next_to_use = i;
}
@@ -5339,7 +5403,8 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
return NETDEV_TX_OK;
out_drop:
- igb_unmap_and_free_tx_resource(tx_ring, first);
+ dev_kfree_skb_any(first->skb);
+ first->skb = NULL;
return NETDEV_TX_OK;
}
@@ -6686,7 +6751,6 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget)
DMA_TO_DEVICE);
/* clear tx_buffer data */
- tx_buffer->skb = NULL;
dma_unmap_len_set(tx_buffer, len, 0);
/* clear last DMA location and unmap remaining buffers */
@@ -6822,8 +6886,14 @@ static void igb_reuse_rx_page(struct igb_ring *rx_ring,
nta++;
rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
- /* transfer page from old buffer to new buffer */
- *new_buff = *old_buff;
+ /* Transfer page from old buffer to new buffer.
+ * Move each member individually to avoid possible store
+ * forwarding stalls.
+ */
+ new_buff->dma = old_buff->dma;
+ new_buff->page = old_buff->page;
+ new_buff->page_offset = old_buff->page_offset;
+ new_buff->pagecnt_bias = old_buff->pagecnt_bias;
}
static inline bool igb_page_is_reserved(struct page *page)
@@ -6831,11 +6901,10 @@ static inline bool igb_page_is_reserved(struct page *page)
return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page);
}
-static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
- struct page *page,
- unsigned int truesize)
+static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer)
{
- unsigned int pagecnt_bias = rx_buffer->pagecnt_bias--;
+ unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
+ struct page *page = rx_buffer->page;
/* avoid re-using remote pages */
if (unlikely(igb_page_is_reserved(page)))
@@ -6843,16 +6912,13 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
#if (PAGE_SIZE < 8192)
/* if we are only owner of page we can reuse it */
- if (unlikely(page_ref_count(page) != pagecnt_bias))
+ if (unlikely((page_ref_count(page) - pagecnt_bias) > 1))
return false;
-
- /* flip page offset to other buffer */
- rx_buffer->page_offset ^= IGB_RX_BUFSZ;
#else
- /* move offset up to the next cache line */
- rx_buffer->page_offset += truesize;
+#define IGB_LAST_OFFSET \
+ (SKB_WITH_OVERHEAD(PAGE_SIZE) - IGB_RXBUFFER_2048)
- if (rx_buffer->page_offset > (PAGE_SIZE - IGB_RX_BUFSZ))
+ if (rx_buffer->page_offset > IGB_LAST_OFFSET)
return false;
#endif
@@ -6860,7 +6926,7 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
* the pagecnt_bias and page count so that we fully restock the
* number of references the driver holds.
*/
- if (unlikely(pagecnt_bias == 1)) {
+ if (unlikely(!pagecnt_bias)) {
page_ref_add(page, USHRT_MAX);
rx_buffer->pagecnt_bias = USHRT_MAX;
}
@@ -6872,34 +6938,56 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
* igb_add_rx_frag - Add contents of Rx buffer to sk_buff
* @rx_ring: rx descriptor ring to transact packets on
* @rx_buffer: buffer containing page to add
- * @rx_desc: descriptor containing length of buffer written by hardware
* @skb: sk_buff to place the data into
+ * @size: size of buffer to be added
*
* This function will add the data contained in rx_buffer->page to the skb.
- * This is done either through a direct copy if the data in the buffer is
- * less than the skb header size, otherwise it will just attach the page as
- * a frag to the skb.
- *
- * The function will then update the page offset if necessary and return
- * true if the buffer can be reused by the adapter.
**/
-static bool igb_add_rx_frag(struct igb_ring *rx_ring,
+static void igb_add_rx_frag(struct igb_ring *rx_ring,
struct igb_rx_buffer *rx_buffer,
- unsigned int size,
- union e1000_adv_rx_desc *rx_desc,
- struct sk_buff *skb)
+ struct sk_buff *skb,
+ unsigned int size)
{
- struct page *page = rx_buffer->page;
- unsigned char *va = page_address(page) + rx_buffer->page_offset;
#if (PAGE_SIZE < 8192)
- unsigned int truesize = IGB_RX_BUFSZ;
+ unsigned int truesize = igb_rx_pg_size(rx_ring) / 2;
+#else
+ unsigned int truesize = ring_uses_build_skb(rx_ring) ?
+ SKB_DATA_ALIGN(IGB_SKB_PAD + size) :
+ SKB_DATA_ALIGN(size);
+#endif
+ skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
+ rx_buffer->page_offset, size, truesize);
+#if (PAGE_SIZE < 8192)
+ rx_buffer->page_offset ^= truesize;
+#else
+ rx_buffer->page_offset += truesize;
+#endif
+}
+
+static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring,
+ struct igb_rx_buffer *rx_buffer,
+ union e1000_adv_rx_desc *rx_desc,
+ unsigned int size)
+{
+ void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+ unsigned int truesize = igb_rx_pg_size(rx_ring) / 2;
#else
unsigned int truesize = SKB_DATA_ALIGN(size);
#endif
- unsigned int pull_len;
+ unsigned int headlen;
+ struct sk_buff *skb;
- if (unlikely(skb_is_nonlinear(skb)))
- goto add_tail_frag;
+ /* prefetch first cache line of first page */
+ prefetch(va);
+#if L1_CACHE_BYTES < 128
+ prefetch(va + L1_CACHE_BYTES);
+#endif
+
+ /* allocate a skb to store the frags */
+ skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGB_RX_HDR_LEN);
+ if (unlikely(!skb))
+ return NULL;
if (unlikely(igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP))) {
igb_ptp_rx_pktstamp(rx_ring->q_vector, va, skb);
@@ -6907,95 +6995,73 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring,
size -= IGB_TS_HDR_LEN;
}
- if (likely(size <= IGB_RX_HDR_LEN)) {
- memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
-
- /* page is not reserved, we can reuse buffer as-is */
- if (likely(!igb_page_is_reserved(page)))
- return true;
-
- /* this page cannot be reused so discard it */
- return false;
- }
-
- /* we need the header to contain the greater of either ETH_HLEN or
- * 60 bytes if the skb->len is less than 60 for skb_pad.
- */
- pull_len = eth_get_headlen(va, IGB_RX_HDR_LEN);
+ /* Determine available headroom for copy */
+ headlen = size;
+ if (headlen > IGB_RX_HDR_LEN)
+ headlen = eth_get_headlen(va, IGB_RX_HDR_LEN);
/* align pull length to size of long to optimize memcpy performance */
- memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long)));
+ memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
/* update all of the pointers */
- va += pull_len;
- size -= pull_len;
+ size -= headlen;
+ if (size) {
+ skb_add_rx_frag(skb, 0, rx_buffer->page,
+ (va + headlen) - page_address(rx_buffer->page),
+ size, truesize);
+#if (PAGE_SIZE < 8192)
+ rx_buffer->page_offset ^= truesize;
+#else
+ rx_buffer->page_offset += truesize;
+#endif
+ } else {
+ rx_buffer->pagecnt_bias++;
+ }
-add_tail_frag:
- skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
- (unsigned long)va & ~PAGE_MASK, size, truesize);
-
- return igb_can_reuse_rx_page(rx_buffer, page, truesize);
+ return skb;
}
-static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring,
- union e1000_adv_rx_desc *rx_desc,
- struct sk_buff *skb)
+static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring,
+ struct igb_rx_buffer *rx_buffer,
+ union e1000_adv_rx_desc *rx_desc,
+ unsigned int size)
{
- unsigned int size = le16_to_cpu(rx_desc->wb.upper.length);
- struct igb_rx_buffer *rx_buffer;
- struct page *page;
+ void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+ unsigned int truesize = igb_rx_pg_size(rx_ring) / 2;
+#else
+ unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
+ SKB_DATA_ALIGN(IGB_SKB_PAD + size);
+#endif
+ struct sk_buff *skb;
- rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
- page = rx_buffer->page;
- prefetchw(page);
-
- /* we are reusing so sync this buffer for CPU use */
- dma_sync_single_range_for_cpu(rx_ring->dev,
- rx_buffer->dma,
- rx_buffer->page_offset,
- size,
- DMA_FROM_DEVICE);
-
- if (likely(!skb)) {
- void *page_addr = page_address(page) +
- rx_buffer->page_offset;
-
- /* prefetch first cache line of first page */
- prefetch(page_addr);
+ /* prefetch first cache line of first page */
+ prefetch(va);
#if L1_CACHE_BYTES < 128
- prefetch(page_addr + L1_CACHE_BYTES);
+ prefetch(va + L1_CACHE_BYTES);
#endif
- /* allocate a skb to store the frags */
- skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGB_RX_HDR_LEN);
- if (unlikely(!skb)) {
- rx_ring->rx_stats.alloc_failed++;
- return NULL;
- }
+ /* build an skb around the page buffer */
+ skb = build_skb(va - IGB_SKB_PAD, truesize);
+ if (unlikely(!skb))
+ return NULL;
- /* we will be copying header into skb->data in
- * pskb_may_pull so it is in our interest to prefetch
- * it now to avoid a possible cache miss
- */
- prefetchw(skb->data);
+ /* update pointers within the skb to store the data */
+ skb_reserve(skb, IGB_SKB_PAD);
+ __skb_put(skb, size);
+
+ /* pull timestamp out of packet data */
+ if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
+ igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb);
+ __skb_pull(skb, IGB_TS_HDR_LEN);
}
- /* pull page into skb */
- if (igb_add_rx_frag(rx_ring, rx_buffer, size, rx_desc, skb)) {
- /* hand second half of page back to the ring */
- igb_reuse_rx_page(rx_ring, rx_buffer);
- } else {
- /* We are not reusing the buffer so unmap it and free
- * any references we are holding to it
- */
- dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
- PAGE_SIZE, DMA_FROM_DEVICE,
- DMA_ATTR_SKIP_CPU_SYNC);
- __page_frag_cache_drain(page, rx_buffer->pagecnt_bias);
- }
-
- /* clear contents of rx_buffer */
- rx_buffer->page = NULL;
+ /* update buffer offset */
+#if (PAGE_SIZE < 8192)
+ rx_buffer->page_offset ^= truesize;
+#else
+ rx_buffer->page_offset += truesize;
+#endif
return skb;
}
@@ -7154,6 +7220,47 @@ static void igb_process_skb_fields(struct igb_ring *rx_ring,
skb->protocol = eth_type_trans(skb, rx_ring->netdev);
}
+static struct igb_rx_buffer *igb_get_rx_buffer(struct igb_ring *rx_ring,
+ const unsigned int size)
+{
+ struct igb_rx_buffer *rx_buffer;
+
+ rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
+ prefetchw(rx_buffer->page);
+
+ /* we are reusing so sync this buffer for CPU use */
+ dma_sync_single_range_for_cpu(rx_ring->dev,
+ rx_buffer->dma,
+ rx_buffer->page_offset,
+ size,
+ DMA_FROM_DEVICE);
+
+ rx_buffer->pagecnt_bias--;
+
+ return rx_buffer;
+}
+
+static void igb_put_rx_buffer(struct igb_ring *rx_ring,
+ struct igb_rx_buffer *rx_buffer)
+{
+ if (igb_can_reuse_rx_page(rx_buffer)) {
+ /* hand second half of page back to the ring */
+ igb_reuse_rx_page(rx_ring, rx_buffer);
+ } else {
+ /* We are not reusing the buffer so unmap it and free
+ * any references we are holding to it
+ */
+ dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
+ igb_rx_pg_size(rx_ring), DMA_FROM_DEVICE,
+ IGB_RX_DMA_ATTR);
+ __page_frag_cache_drain(rx_buffer->page,
+ rx_buffer->pagecnt_bias);
+ }
+
+ /* clear contents of rx_buffer */
+ rx_buffer->page = NULL;
+}
+
static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
{
struct igb_ring *rx_ring = q_vector->rx.ring;
@@ -7163,6 +7270,8 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
while (likely(total_packets < budget)) {
union e1000_adv_rx_desc *rx_desc;
+ struct igb_rx_buffer *rx_buffer;
+ unsigned int size;
/* return some buffers to hardware, one at a time is too slow */
if (cleaned_count >= IGB_RX_BUFFER_WRITE) {
@@ -7171,8 +7280,8 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
}
rx_desc = IGB_RX_DESC(rx_ring, rx_ring->next_to_clean);
-
- if (!rx_desc->wb.upper.status_error)
+ size = le16_to_cpu(rx_desc->wb.upper.length);
+ if (!size)
break;
/* This memory barrier is needed to keep us from reading
@@ -7181,13 +7290,25 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
*/
dma_rmb();
+ rx_buffer = igb_get_rx_buffer(rx_ring, size);
+
/* retrieve a buffer from the ring */
- skb = igb_fetch_rx_buffer(rx_ring, rx_desc, skb);
+ if (skb)
+ igb_add_rx_frag(rx_ring, rx_buffer, skb, size);
+ else if (ring_uses_build_skb(rx_ring))
+ skb = igb_build_skb(rx_ring, rx_buffer, rx_desc, size);
+ else
+ skb = igb_construct_skb(rx_ring, rx_buffer,
+ rx_desc, size);
/* exit if we failed to retrieve a buffer */
- if (!skb)
+ if (!skb) {
+ rx_ring->rx_stats.alloc_failed++;
+ rx_buffer->pagecnt_bias++;
break;
+ }
+ igb_put_rx_buffer(rx_ring, rx_buffer);
cleaned_count++;
/* fetch next buffer in frame if non-eop */
@@ -7231,6 +7352,11 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
return total_packets;
}
+static inline unsigned int igb_rx_offset(struct igb_ring *rx_ring)
+{
+ return ring_uses_build_skb(rx_ring) ? IGB_SKB_PAD : 0;
+}
+
static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
struct igb_rx_buffer *bi)
{
@@ -7242,21 +7368,23 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
return true;
/* alloc new page for storage */
- page = dev_alloc_page();
+ page = dev_alloc_pages(igb_rx_pg_order(rx_ring));
if (unlikely(!page)) {
rx_ring->rx_stats.alloc_failed++;
return false;
}
/* map page for use */
- dma = dma_map_page_attrs(rx_ring->dev, page, 0, PAGE_SIZE,
- DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+ dma = dma_map_page_attrs(rx_ring->dev, page, 0,
+ igb_rx_pg_size(rx_ring),
+ DMA_FROM_DEVICE,
+ IGB_RX_DMA_ATTR);
/* if mapping failed free memory back to system since
* there isn't much point in holding memory we can't use
*/
if (dma_mapping_error(rx_ring->dev, dma)) {
- __free_page(page);
+ __free_pages(page, igb_rx_pg_order(rx_ring));
rx_ring->rx_stats.alloc_failed++;
return false;
@@ -7264,7 +7392,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
bi->dma = dma;
bi->page = page;
- bi->page_offset = 0;
+ bi->page_offset = igb_rx_offset(rx_ring);
bi->pagecnt_bias = 1;
return true;
@@ -7279,6 +7407,7 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
union e1000_adv_rx_desc *rx_desc;
struct igb_rx_buffer *bi;
u16 i = rx_ring->next_to_use;
+ u16 bufsz;
/* nothing to do */
if (!cleaned_count)
@@ -7288,14 +7417,15 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
bi = &rx_ring->rx_buffer_info[i];
i -= rx_ring->count;
+ bufsz = igb_rx_bufsz(rx_ring);
+
do {
if (!igb_alloc_mapped_page(rx_ring, bi))
break;
/* sync the buffer for use by the device */
dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
- bi->page_offset,
- IGB_RX_BUFSZ,
+ bi->page_offset, bufsz,
DMA_FROM_DEVICE);
/* Refresh the desc even if buffer_addrs didn't change
@@ -7312,8 +7442,8 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
i -= rx_ring->count;
}
- /* clear the status bits for the next_to_use descriptor */
- rx_desc->wb.upper.status_error = 0;
+ /* clear the length for the next_to_use descriptor */
+ rx_desc->wb.upper.length = 0;
cleaned_count--;
} while (cleaned_count);
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index c447755..7a3fd4d 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -764,8 +764,7 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter)
* incoming frame. The value is stored in little endian format starting on
* byte 8.
**/
-void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector,
- unsigned char *va,
+void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
struct sk_buff *skb)
{
__le64 *regval = (__le64 *)va;
diff --git a/drivers/net/ethernet/intel/igbvf/ethtool.c b/drivers/net/ethernet/intel/igbvf/ethtool.c
index 8dea1b1..34faa11 100644
--- a/drivers/net/ethernet/intel/igbvf/ethtool.c
+++ b/drivers/net/ethernet/intel/igbvf/ethtool.c
@@ -71,45 +71,45 @@ static const char igbvf_gstrings_test[][ETH_GSTRING_LEN] = {
#define IGBVF_TEST_LEN ARRAY_SIZE(igbvf_gstrings_test)
-static int igbvf_get_settings(struct net_device *netdev,
- struct ethtool_cmd *ecmd)
+static int igbvf_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *cmd)
{
struct igbvf_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
u32 status;
- ecmd->supported = SUPPORTED_1000baseT_Full;
+ ethtool_link_ksettings_zero_link_mode(cmd, supported);
+ ethtool_link_ksettings_add_link_mode(cmd, supported, 1000baseT_Full);
+ ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising, 1000baseT_Full);
- ecmd->advertising = ADVERTISED_1000baseT_Full;
-
- ecmd->port = -1;
- ecmd->transceiver = XCVR_DUMMY1;
+ cmd->base.port = -1;
status = er32(STATUS);
if (status & E1000_STATUS_LU) {
if (status & E1000_STATUS_SPEED_1000)
- ethtool_cmd_speed_set(ecmd, SPEED_1000);
+ cmd->base.speed = SPEED_1000;
else if (status & E1000_STATUS_SPEED_100)
- ethtool_cmd_speed_set(ecmd, SPEED_100);
+ cmd->base.speed = SPEED_100;
else
- ethtool_cmd_speed_set(ecmd, SPEED_10);
+ cmd->base.speed = SPEED_10;
if (status & E1000_STATUS_FD)
- ecmd->duplex = DUPLEX_FULL;
+ cmd->base.duplex = DUPLEX_FULL;
else
- ecmd->duplex = DUPLEX_HALF;
+ cmd->base.duplex = DUPLEX_HALF;
} else {
- ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
- ecmd->duplex = DUPLEX_UNKNOWN;
+ cmd->base.speed = SPEED_UNKNOWN;
+ cmd->base.duplex = DUPLEX_UNKNOWN;
}
- ecmd->autoneg = AUTONEG_DISABLE;
+ cmd->base.autoneg = AUTONEG_DISABLE;
return 0;
}
-static int igbvf_set_settings(struct net_device *netdev,
- struct ethtool_cmd *ecmd)
+static int igbvf_set_link_ksettings(struct net_device *netdev,
+ const struct ethtool_link_ksettings *cmd)
{
return -EOPNOTSUPP;
}
@@ -443,8 +443,6 @@ static void igbvf_get_strings(struct net_device *netdev, u32 stringset,
}
static const struct ethtool_ops igbvf_ethtool_ops = {
- .get_settings = igbvf_get_settings,
- .set_settings = igbvf_set_settings,
.get_drvinfo = igbvf_get_drvinfo,
.get_regs_len = igbvf_get_regs_len,
.get_regs = igbvf_get_regs,
@@ -467,6 +465,8 @@ static const struct ethtool_ops igbvf_ethtool_ops = {
.get_ethtool_stats = igbvf_get_ethtool_stats,
.get_coalesce = igbvf_get_coalesce,
.set_coalesce = igbvf_set_coalesce,
+ .get_link_ksettings = igbvf_get_link_ksettings,
+ .set_link_ksettings = igbvf_set_link_ksettings,
};
void igbvf_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c
index e5d7255..d10a0d2 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c
@@ -94,24 +94,30 @@ static struct ixgb_stats ixgb_gstrings_stats[] = {
#define IXGB_STATS_LEN ARRAY_SIZE(ixgb_gstrings_stats)
static int
-ixgb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+ixgb_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *cmd)
{
struct ixgb_adapter *adapter = netdev_priv(netdev);
- ecmd->supported = (SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE);
- ecmd->advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_FIBRE);
- ecmd->port = PORT_FIBRE;
- ecmd->transceiver = XCVR_EXTERNAL;
+ ethtool_link_ksettings_zero_link_mode(cmd, supported);
+ ethtool_link_ksettings_add_link_mode(cmd, supported, 10000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
+
+ ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising, 10000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE);
+
+ cmd->base.port = PORT_FIBRE;
if (netif_carrier_ok(adapter->netdev)) {
- ethtool_cmd_speed_set(ecmd, SPEED_10000);
- ecmd->duplex = DUPLEX_FULL;
+ cmd->base.speed = SPEED_10000;
+ cmd->base.duplex = DUPLEX_FULL;
} else {
- ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
- ecmd->duplex = DUPLEX_UNKNOWN;
+ cmd->base.speed = SPEED_UNKNOWN;
+ cmd->base.duplex = DUPLEX_UNKNOWN;
}
- ecmd->autoneg = AUTONEG_DISABLE;
+ cmd->base.autoneg = AUTONEG_DISABLE;
return 0;
}
@@ -126,13 +132,14 @@ void ixgb_set_speed_duplex(struct net_device *netdev)
}
static int
-ixgb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+ixgb_set_link_ksettings(struct net_device *netdev,
+ const struct ethtool_link_ksettings *cmd)
{
struct ixgb_adapter *adapter = netdev_priv(netdev);
- u32 speed = ethtool_cmd_speed(ecmd);
+ u32 speed = cmd->base.speed;
- if (ecmd->autoneg == AUTONEG_ENABLE ||
- (speed + ecmd->duplex != SPEED_10000 + DUPLEX_FULL))
+ if (cmd->base.autoneg == AUTONEG_ENABLE ||
+ (speed + cmd->base.duplex != SPEED_10000 + DUPLEX_FULL))
return -EINVAL;
if (netif_running(adapter->netdev)) {
@@ -630,8 +637,6 @@ ixgb_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
}
static const struct ethtool_ops ixgb_ethtool_ops = {
- .get_settings = ixgb_get_settings,
- .set_settings = ixgb_set_settings,
.get_drvinfo = ixgb_get_drvinfo,
.get_regs_len = ixgb_get_regs_len,
.get_regs = ixgb_get_regs,
@@ -649,6 +654,8 @@ static const struct ethtool_ops ixgb_ethtool_ops = {
.set_phys_id = ixgb_set_phys_id,
.get_sset_count = ixgb_get_sset_count,
.get_ethtool_stats = ixgb_get_ethtool_stats,
+ .get_link_ksettings = ixgb_get_link_ksettings,
+ .set_link_ksettings = ixgb_set_link_ksettings,
};
void ixgb_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 90fa5bf..0da0752f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -186,60 +186,62 @@ static u32 ixgbe_get_supported_10gtypes(struct ixgbe_hw *hw)
}
}
-static int ixgbe_get_settings(struct net_device *netdev,
- struct ethtool_cmd *ecmd)
+static int ixgbe_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *cmd)
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
struct ixgbe_hw *hw = &adapter->hw;
ixgbe_link_speed supported_link;
bool autoneg = false;
+ u32 supported, advertising;
+
+ ethtool_convert_link_mode_to_legacy_u32(&supported,
+ cmd->link_modes.supported);
hw->mac.ops.get_link_capabilities(hw, &supported_link, &autoneg);
/* set the supported link speeds */
if (supported_link & IXGBE_LINK_SPEED_10GB_FULL)
- ecmd->supported |= ixgbe_get_supported_10gtypes(hw);
+ supported |= ixgbe_get_supported_10gtypes(hw);
if (supported_link & IXGBE_LINK_SPEED_1GB_FULL)
- ecmd->supported |= (ixgbe_isbackplane(hw->phy.media_type)) ?
+ supported |= (ixgbe_isbackplane(hw->phy.media_type)) ?
SUPPORTED_1000baseKX_Full :
SUPPORTED_1000baseT_Full;
if (supported_link & IXGBE_LINK_SPEED_100_FULL)
- ecmd->supported |= SUPPORTED_100baseT_Full;
+ supported |= SUPPORTED_100baseT_Full;
if (supported_link & IXGBE_LINK_SPEED_10_FULL)
- ecmd->supported |= SUPPORTED_10baseT_Full;
+ supported |= SUPPORTED_10baseT_Full;
/* default advertised speed if phy.autoneg_advertised isn't set */
- ecmd->advertising = ecmd->supported;
+ advertising = supported;
/* set the advertised speeds */
if (hw->phy.autoneg_advertised) {
- ecmd->advertising = 0;
+ advertising = 0;
if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10_FULL)
- ecmd->advertising |= ADVERTISED_10baseT_Full;
+ advertising |= ADVERTISED_10baseT_Full;
if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_100_FULL)
- ecmd->advertising |= ADVERTISED_100baseT_Full;
+ advertising |= ADVERTISED_100baseT_Full;
if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL)
- ecmd->advertising |= ecmd->supported & ADVRTSD_MSK_10G;
+ advertising |= supported & ADVRTSD_MSK_10G;
if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL) {
- if (ecmd->supported & SUPPORTED_1000baseKX_Full)
- ecmd->advertising |= ADVERTISED_1000baseKX_Full;
+ if (supported & SUPPORTED_1000baseKX_Full)
+ advertising |= ADVERTISED_1000baseKX_Full;
else
- ecmd->advertising |= ADVERTISED_1000baseT_Full;
+ advertising |= ADVERTISED_1000baseT_Full;
}
} else {
if (hw->phy.multispeed_fiber && !autoneg) {
if (supported_link & IXGBE_LINK_SPEED_10GB_FULL)
- ecmd->advertising = ADVERTISED_10000baseT_Full;
+ advertising = ADVERTISED_10000baseT_Full;
}
}
if (autoneg) {
- ecmd->supported |= SUPPORTED_Autoneg;
- ecmd->advertising |= ADVERTISED_Autoneg;
- ecmd->autoneg = AUTONEG_ENABLE;
+ supported |= SUPPORTED_Autoneg;
+ advertising |= ADVERTISED_Autoneg;
+ cmd->base.autoneg = AUTONEG_ENABLE;
} else
- ecmd->autoneg = AUTONEG_DISABLE;
-
- ecmd->transceiver = XCVR_EXTERNAL;
+ cmd->base.autoneg = AUTONEG_DISABLE;
/* Determine the remaining settings based on the PHY type. */
switch (adapter->hw.phy.type) {
@@ -248,14 +250,14 @@ static int ixgbe_get_settings(struct net_device *netdev,
case ixgbe_phy_x550em_ext_t:
case ixgbe_phy_fw:
case ixgbe_phy_cu_unknown:
- ecmd->supported |= SUPPORTED_TP;
- ecmd->advertising |= ADVERTISED_TP;
- ecmd->port = PORT_TP;
+ supported |= SUPPORTED_TP;
+ advertising |= ADVERTISED_TP;
+ cmd->base.port = PORT_TP;
break;
case ixgbe_phy_qt:
- ecmd->supported |= SUPPORTED_FIBRE;
- ecmd->advertising |= ADVERTISED_FIBRE;
- ecmd->port = PORT_FIBRE;
+ supported |= SUPPORTED_FIBRE;
+ advertising |= ADVERTISED_FIBRE;
+ cmd->base.port = PORT_FIBRE;
break;
case ixgbe_phy_nl:
case ixgbe_phy_sfp_passive_tyco:
@@ -273,9 +275,9 @@ static int ixgbe_get_settings(struct net_device *netdev,
case ixgbe_sfp_type_da_cu:
case ixgbe_sfp_type_da_cu_core0:
case ixgbe_sfp_type_da_cu_core1:
- ecmd->supported |= SUPPORTED_FIBRE;
- ecmd->advertising |= ADVERTISED_FIBRE;
- ecmd->port = PORT_DA;
+ supported |= SUPPORTED_FIBRE;
+ advertising |= ADVERTISED_FIBRE;
+ cmd->base.port = PORT_DA;
break;
case ixgbe_sfp_type_sr:
case ixgbe_sfp_type_lr:
@@ -285,102 +287,113 @@ static int ixgbe_get_settings(struct net_device *netdev,
case ixgbe_sfp_type_1g_sx_core1:
case ixgbe_sfp_type_1g_lx_core0:
case ixgbe_sfp_type_1g_lx_core1:
- ecmd->supported |= SUPPORTED_FIBRE;
- ecmd->advertising |= ADVERTISED_FIBRE;
- ecmd->port = PORT_FIBRE;
+ supported |= SUPPORTED_FIBRE;
+ advertising |= ADVERTISED_FIBRE;
+ cmd->base.port = PORT_FIBRE;
break;
case ixgbe_sfp_type_not_present:
- ecmd->supported |= SUPPORTED_FIBRE;
- ecmd->advertising |= ADVERTISED_FIBRE;
- ecmd->port = PORT_NONE;
+ supported |= SUPPORTED_FIBRE;
+ advertising |= ADVERTISED_FIBRE;
+ cmd->base.port = PORT_NONE;
break;
case ixgbe_sfp_type_1g_cu_core0:
case ixgbe_sfp_type_1g_cu_core1:
- ecmd->supported |= SUPPORTED_TP;
- ecmd->advertising |= ADVERTISED_TP;
- ecmd->port = PORT_TP;
+ supported |= SUPPORTED_TP;
+ advertising |= ADVERTISED_TP;
+ cmd->base.port = PORT_TP;
break;
case ixgbe_sfp_type_unknown:
default:
- ecmd->supported |= SUPPORTED_FIBRE;
- ecmd->advertising |= ADVERTISED_FIBRE;
- ecmd->port = PORT_OTHER;
+ supported |= SUPPORTED_FIBRE;
+ advertising |= ADVERTISED_FIBRE;
+ cmd->base.port = PORT_OTHER;
break;
}
break;
case ixgbe_phy_xaui:
- ecmd->supported |= SUPPORTED_FIBRE;
- ecmd->advertising |= ADVERTISED_FIBRE;
- ecmd->port = PORT_NONE;
+ supported |= SUPPORTED_FIBRE;
+ advertising |= ADVERTISED_FIBRE;
+ cmd->base.port = PORT_NONE;
break;
case ixgbe_phy_unknown:
case ixgbe_phy_generic:
case ixgbe_phy_sfp_unsupported:
default:
- ecmd->supported |= SUPPORTED_FIBRE;
- ecmd->advertising |= ADVERTISED_FIBRE;
- ecmd->port = PORT_OTHER;
+ supported |= SUPPORTED_FIBRE;
+ advertising |= ADVERTISED_FIBRE;
+ cmd->base.port = PORT_OTHER;
break;
}
/* Indicate pause support */
- ecmd->supported |= SUPPORTED_Pause;
+ supported |= SUPPORTED_Pause;
switch (hw->fc.requested_mode) {
case ixgbe_fc_full:
- ecmd->advertising |= ADVERTISED_Pause;
+ advertising |= ADVERTISED_Pause;
break;
case ixgbe_fc_rx_pause:
- ecmd->advertising |= ADVERTISED_Pause |
+ advertising |= ADVERTISED_Pause |
ADVERTISED_Asym_Pause;
break;
case ixgbe_fc_tx_pause:
- ecmd->advertising |= ADVERTISED_Asym_Pause;
+ advertising |= ADVERTISED_Asym_Pause;
break;
default:
- ecmd->advertising &= ~(ADVERTISED_Pause |
+ advertising &= ~(ADVERTISED_Pause |
ADVERTISED_Asym_Pause);
}
if (netif_carrier_ok(netdev)) {
switch (adapter->link_speed) {
case IXGBE_LINK_SPEED_10GB_FULL:
- ethtool_cmd_speed_set(ecmd, SPEED_10000);
+ cmd->base.speed = SPEED_10000;
break;
case IXGBE_LINK_SPEED_5GB_FULL:
- ethtool_cmd_speed_set(ecmd, SPEED_5000);
+ cmd->base.speed = SPEED_5000;
break;
case IXGBE_LINK_SPEED_2_5GB_FULL:
- ethtool_cmd_speed_set(ecmd, SPEED_2500);
+ cmd->base.speed = SPEED_2500;
break;
case IXGBE_LINK_SPEED_1GB_FULL:
- ethtool_cmd_speed_set(ecmd, SPEED_1000);
+ cmd->base.speed = SPEED_1000;
break;
case IXGBE_LINK_SPEED_100_FULL:
- ethtool_cmd_speed_set(ecmd, SPEED_100);
+ cmd->base.speed = SPEED_100;
break;
case IXGBE_LINK_SPEED_10_FULL:
- ethtool_cmd_speed_set(ecmd, SPEED_10);
+ cmd->base.speed = SPEED_10;
break;
default:
break;
}
- ecmd->duplex = DUPLEX_FULL;
+ cmd->base.duplex = DUPLEX_FULL;
} else {
- ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
- ecmd->duplex = DUPLEX_UNKNOWN;
+ cmd->base.speed = SPEED_UNKNOWN;
+ cmd->base.duplex = DUPLEX_UNKNOWN;
}
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ supported);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+ advertising);
+
return 0;
}
-static int ixgbe_set_settings(struct net_device *netdev,
- struct ethtool_cmd *ecmd)
+static int ixgbe_set_link_ksettings(struct net_device *netdev,
+ const struct ethtool_link_ksettings *cmd)
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
struct ixgbe_hw *hw = &adapter->hw;
u32 advertised, old;
s32 err = 0;
+ u32 supported, advertising;
+
+ ethtool_convert_link_mode_to_legacy_u32(&supported,
+ cmd->link_modes.supported);
+ ethtool_convert_link_mode_to_legacy_u32(&advertising,
+ cmd->link_modes.advertising);
if ((hw->phy.media_type == ixgbe_media_type_copper) ||
(hw->phy.multispeed_fiber)) {
@@ -388,12 +401,12 @@ static int ixgbe_set_settings(struct net_device *netdev,
* this function does not support duplex forcing, but can
* limit the advertising of the adapter to the specified speed
*/
- if (ecmd->advertising & ~ecmd->supported)
+ if (advertising & ~supported)
return -EINVAL;
/* only allow one speed at a time if no autoneg */
- if (!ecmd->autoneg && hw->phy.multispeed_fiber) {
- if (ecmd->advertising ==
+ if (!cmd->base.autoneg && hw->phy.multispeed_fiber) {
+ if (advertising ==
(ADVERTISED_10000baseT_Full |
ADVERTISED_1000baseT_Full))
return -EINVAL;
@@ -401,16 +414,16 @@ static int ixgbe_set_settings(struct net_device *netdev,
old = hw->phy.autoneg_advertised;
advertised = 0;
- if (ecmd->advertising & ADVERTISED_10000baseT_Full)
+ if (advertising & ADVERTISED_10000baseT_Full)
advertised |= IXGBE_LINK_SPEED_10GB_FULL;
- if (ecmd->advertising & ADVERTISED_1000baseT_Full)
+ if (advertising & ADVERTISED_1000baseT_Full)
advertised |= IXGBE_LINK_SPEED_1GB_FULL;
- if (ecmd->advertising & ADVERTISED_100baseT_Full)
+ if (advertising & ADVERTISED_100baseT_Full)
advertised |= IXGBE_LINK_SPEED_100_FULL;
- if (ecmd->advertising & ADVERTISED_10baseT_Full)
+ if (advertising & ADVERTISED_10baseT_Full)
advertised |= IXGBE_LINK_SPEED_10_FULL;
if (old == advertised)
@@ -428,10 +441,11 @@ static int ixgbe_set_settings(struct net_device *netdev,
clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state);
} else {
/* in this case we currently only support 10Gb/FULL */
- u32 speed = ethtool_cmd_speed(ecmd);
- if ((ecmd->autoneg == AUTONEG_ENABLE) ||
- (ecmd->advertising != ADVERTISED_10000baseT_Full) ||
- (speed + ecmd->duplex != SPEED_10000 + DUPLEX_FULL))
+ u32 speed = cmd->base.speed;
+
+ if ((cmd->base.autoneg == AUTONEG_ENABLE) ||
+ (advertising != ADVERTISED_10000baseT_Full) ||
+ (speed + cmd->base.duplex != SPEED_10000 + DUPLEX_FULL))
return -EINVAL;
}
@@ -3402,8 +3416,6 @@ static int ixgbe_set_priv_flags(struct net_device *netdev, u32 priv_flags)
}
static const struct ethtool_ops ixgbe_ethtool_ops = {
- .get_settings = ixgbe_get_settings,
- .set_settings = ixgbe_set_settings,
.get_drvinfo = ixgbe_get_drvinfo,
.get_regs_len = ixgbe_get_regs_len,
.get_regs = ixgbe_get_regs,
@@ -3442,6 +3454,8 @@ static const struct ethtool_ops ixgbe_ethtool_ops = {
.get_ts_info = ixgbe_get_ts_info,
.get_module_info = ixgbe_get_module_info,
.get_module_eeprom = ixgbe_get_module_eeprom,
+ .get_link_ksettings = ixgbe_get_link_ksettings,
+ .set_link_ksettings = ixgbe_set_link_ksettings,
};
void ixgbe_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index a7a430a..852a2e7 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2122,7 +2122,7 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
prefetch(va + L1_CACHE_BYTES);
#endif
- /* build an skb to around the page buffer */
+ /* build an skb around the page buffer */
skb = build_skb(va - IXGBE_SKB_PAD, truesize);
if (unlikely(!skb))
return NULL;
@@ -8948,7 +8948,9 @@ static int __ixgbe_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
if (tc->type != TC_SETUP_MQPRIO)
return -EINVAL;
- return ixgbe_setup_tc(dev, tc->tc);
+ tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+ return ixgbe_setup_tc(dev, tc->mqprio->num_tc);
}
#ifdef CONFIG_PCI_IOV
diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig
index d2555e8b..da6fb82 100644
--- a/drivers/net/ethernet/marvell/Kconfig
+++ b/drivers/net/ethernet/marvell/Kconfig
@@ -82,13 +82,13 @@
that all dependencies are met.
config MVPP2
- tristate "Marvell Armada 375 network interface support"
+ tristate "Marvell Armada 375/7K/8K network interface support"
depends on ARCH_MVEBU || COMPILE_TEST
depends on HAS_DMA
select MVMDIO
---help---
This driver supports the network interface units in the
- Marvell ARMADA 375 SoC.
+ Marvell ARMADA 375, 7K and 8K SoCs.
config PXA168_ETH
tristate "Marvell pxa168 ethernet support"
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 61dd446..34a3686 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -431,6 +431,7 @@ struct mvneta_port {
/* Flags for special SoC configurations */
bool neta_armada3700;
u16 rx_offset_correction;
+ const struct mbus_dram_target_info *dram_target_info;
};
/* The mvneta_tx_desc and mvneta_rx_desc structures describe the
@@ -4098,6 +4099,8 @@ static int mvneta_port_power_up(struct mvneta_port *pp, int phy_mode)
break;
case PHY_INTERFACE_MODE_RGMII:
case PHY_INTERFACE_MODE_RGMII_ID:
+ case PHY_INTERFACE_MODE_RGMII_RXID:
+ case PHY_INTERFACE_MODE_RGMII_TXID:
ctrl |= MVNETA_GMAC2_PORT_RGMII;
break;
default:
@@ -4118,7 +4121,6 @@ static int mvneta_port_power_up(struct mvneta_port *pp, int phy_mode)
/* Device initialization routine */
static int mvneta_probe(struct platform_device *pdev)
{
- const struct mbus_dram_target_info *dram_target_info;
struct resource *res;
struct device_node *dn = pdev->dev.of_node;
struct device_node *phy_node;
@@ -4267,13 +4269,13 @@ static int mvneta_probe(struct platform_device *pdev)
pp->tx_csum_limit = tx_csum_limit;
- dram_target_info = mv_mbus_dram_info();
+ pp->dram_target_info = mv_mbus_dram_info();
/* Armada3700 requires setting default configuration of Mbus
* windows, however without using filled mbus_dram_target_info
* structure.
*/
- if (dram_target_info || pp->neta_armada3700)
- mvneta_conf_mbus_windows(pp, dram_target_info);
+ if (pp->dram_target_info || pp->neta_armada3700)
+ mvneta_conf_mbus_windows(pp, pp->dram_target_info);
pp->tx_ring_size = MVNETA_MAX_TXD;
pp->rx_ring_size = MVNETA_MAX_RXD;
@@ -4405,6 +4407,61 @@ static int mvneta_remove(struct platform_device *pdev)
return 0;
}
+#ifdef CONFIG_PM_SLEEP
+static int mvneta_suspend(struct device *device)
+{
+ struct net_device *dev = dev_get_drvdata(device);
+ struct mvneta_port *pp = netdev_priv(dev);
+
+ if (netif_running(dev))
+ mvneta_stop(dev);
+ netif_device_detach(dev);
+ clk_disable_unprepare(pp->clk_bus);
+ clk_disable_unprepare(pp->clk);
+ return 0;
+}
+
+static int mvneta_resume(struct device *device)
+{
+ struct platform_device *pdev = to_platform_device(device);
+ struct net_device *dev = dev_get_drvdata(device);
+ struct mvneta_port *pp = netdev_priv(dev);
+ int err;
+
+ clk_prepare_enable(pp->clk);
+ if (!IS_ERR(pp->clk_bus))
+ clk_prepare_enable(pp->clk_bus);
+ if (pp->dram_target_info || pp->neta_armada3700)
+ mvneta_conf_mbus_windows(pp, pp->dram_target_info);
+ if (pp->bm_priv) {
+ err = mvneta_bm_port_init(pdev, pp);
+ if (err < 0) {
+ dev_info(&pdev->dev, "use SW buffer management\n");
+ pp->bm_priv = NULL;
+ }
+ }
+ mvneta_defaults_set(pp);
+ err = mvneta_port_power_up(pp, pp->phy_interface);
+ if (err < 0) {
+ dev_err(device, "can't power up port\n");
+ return err;
+ }
+
+ if (pp->use_inband_status)
+ mvneta_fixed_link_update(pp, dev->phydev);
+
+ netif_device_attach(dev);
+ if (netif_running(dev)) {
+ mvneta_open(dev);
+ mvneta_set_rx_mode(dev);
+ }
+
+ return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(mvneta_pm_ops, mvneta_suspend, mvneta_resume);
+
static const struct of_device_id mvneta_match[] = {
{ .compatible = "marvell,armada-370-neta" },
{ .compatible = "marvell,armada-xp-neta" },
@@ -4419,6 +4476,7 @@ static struct platform_driver mvneta_driver = {
.driver = {
.name = MVNETA_DRIVER_NAME,
.of_match_table = mvneta_match,
+ .pm = &mvneta_pm_ops,
},
};
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index d00421b..af5bfa1 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -25,6 +25,7 @@
#include <linux/of_mdio.h>
#include <linux/of_net.h>
#include <linux/of_address.h>
+#include <linux/of_device.h>
#include <linux/phy.h>
#include <linux/clk.h>
#include <linux/hrtimer.h>
@@ -49,9 +50,11 @@
#define MVPP2_SNOOP_PKT_SIZE_MASK 0x1ff
#define MVPP2_SNOOP_BUF_HDR_MASK BIT(9)
#define MVPP2_RXQ_POOL_SHORT_OFFS 20
-#define MVPP2_RXQ_POOL_SHORT_MASK 0x700000
+#define MVPP21_RXQ_POOL_SHORT_MASK 0x700000
+#define MVPP22_RXQ_POOL_SHORT_MASK 0xf00000
#define MVPP2_RXQ_POOL_LONG_OFFS 24
-#define MVPP2_RXQ_POOL_LONG_MASK 0x7000000
+#define MVPP21_RXQ_POOL_LONG_MASK 0x7000000
+#define MVPP22_RXQ_POOL_LONG_MASK 0xf000000
#define MVPP2_RXQ_PACKET_OFFSET_OFFS 28
#define MVPP2_RXQ_PACKET_OFFSET_MASK 0x70000000
#define MVPP2_RXQ_DISABLE_MASK BIT(31)
@@ -99,6 +102,7 @@
/* Descriptor Manager Top Registers */
#define MVPP2_RXQ_NUM_REG 0x2040
#define MVPP2_RXQ_DESC_ADDR_REG 0x2044
+#define MVPP22_DESC_ADDR_OFFS 8
#define MVPP2_RXQ_DESC_SIZE_REG 0x2048
#define MVPP2_RXQ_DESC_SIZE_MASK 0x3ff0
#define MVPP2_RXQ_STATUS_UPDATE_REG(rxq) (0x3000 + 4 * (rxq))
@@ -117,9 +121,6 @@
#define MVPP2_TXQ_DESC_SIZE_REG 0x2088
#define MVPP2_TXQ_DESC_SIZE_MASK 0x3ff0
#define MVPP2_AGGR_TXQ_UPDATE_REG 0x2090
-#define MVPP2_TXQ_THRESH_REG 0x2094
-#define MVPP2_TRANSMITTED_THRESH_OFFSET 16
-#define MVPP2_TRANSMITTED_THRESH_MASK 0x3fff0000
#define MVPP2_TXQ_INDEX_REG 0x2098
#define MVPP2_TXQ_PREF_BUF_REG 0x209c
#define MVPP2_PREF_BUF_PTR(desc) ((desc) & 0xfff)
@@ -140,6 +141,7 @@
#define MVPP2_TXQ_RSVD_CLR_REG 0x20b8
#define MVPP2_TXQ_RSVD_CLR_OFFSET 16
#define MVPP2_AGGR_TXQ_DESC_ADDR_REG(cpu) (0x2100 + 4 * (cpu))
+#define MVPP22_AGGR_TXQ_DESC_ADDR_OFFS 8
#define MVPP2_AGGR_TXQ_DESC_SIZE_REG(cpu) (0x2140 + 4 * (cpu))
#define MVPP2_AGGR_TXQ_DESC_SIZE_MASK 0x3ff0
#define MVPP2_AGGR_TXQ_STATUS_REG(cpu) (0x2180 + 4 * (cpu))
@@ -152,10 +154,52 @@
#define MVPP2_WIN_REMAP(w) (0x4040 + ((w) << 2))
#define MVPP2_BASE_ADDR_ENABLE 0x4060
+/* AXI Bridge Registers */
+#define MVPP22_AXI_BM_WR_ATTR_REG 0x4100
+#define MVPP22_AXI_BM_RD_ATTR_REG 0x4104
+#define MVPP22_AXI_AGGRQ_DESCR_RD_ATTR_REG 0x4110
+#define MVPP22_AXI_TXQ_DESCR_WR_ATTR_REG 0x4114
+#define MVPP22_AXI_TXQ_DESCR_RD_ATTR_REG 0x4118
+#define MVPP22_AXI_RXQ_DESCR_WR_ATTR_REG 0x411c
+#define MVPP22_AXI_RX_DATA_WR_ATTR_REG 0x4120
+#define MVPP22_AXI_TX_DATA_RD_ATTR_REG 0x4130
+#define MVPP22_AXI_RD_NORMAL_CODE_REG 0x4150
+#define MVPP22_AXI_RD_SNOOP_CODE_REG 0x4154
+#define MVPP22_AXI_WR_NORMAL_CODE_REG 0x4160
+#define MVPP22_AXI_WR_SNOOP_CODE_REG 0x4164
+
+/* Values for AXI Bridge registers */
+#define MVPP22_AXI_ATTR_CACHE_OFFS 0
+#define MVPP22_AXI_ATTR_DOMAIN_OFFS 12
+
+#define MVPP22_AXI_CODE_CACHE_OFFS 0
+#define MVPP22_AXI_CODE_DOMAIN_OFFS 4
+
+#define MVPP22_AXI_CODE_CACHE_NON_CACHE 0x3
+#define MVPP22_AXI_CODE_CACHE_WR_CACHE 0x7
+#define MVPP22_AXI_CODE_CACHE_RD_CACHE 0xb
+
+#define MVPP22_AXI_CODE_DOMAIN_OUTER_DOM 2
+#define MVPP22_AXI_CODE_DOMAIN_SYSTEM 3
+
/* Interrupt Cause and Mask registers */
#define MVPP2_ISR_RX_THRESHOLD_REG(rxq) (0x5200 + 4 * (rxq))
#define MVPP2_MAX_ISR_RX_THRESHOLD 0xfffff0
-#define MVPP2_ISR_RXQ_GROUP_REG(rxq) (0x5400 + 4 * (rxq))
+#define MVPP21_ISR_RXQ_GROUP_REG(rxq) (0x5400 + 4 * (rxq))
+
+#define MVPP22_ISR_RXQ_GROUP_INDEX_REG 0x5400
+#define MVPP22_ISR_RXQ_GROUP_INDEX_SUBGROUP_MASK 0xf
+#define MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_MASK 0x380
+#define MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_OFFSET 7
+
+#define MVPP22_ISR_RXQ_GROUP_INDEX_SUBGROUP_MASK 0xf
+#define MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_MASK 0x380
+
+#define MVPP22_ISR_RXQ_SUB_GROUP_CONFIG_REG 0x5404
+#define MVPP22_ISR_RXQ_SUB_GROUP_STARTQ_MASK 0x1f
+#define MVPP22_ISR_RXQ_SUB_GROUP_SIZE_MASK 0xf00
+#define MVPP22_ISR_RXQ_SUB_GROUP_SIZE_OFFSET 8
+
#define MVPP2_ISR_ENABLE_REG(port) (0x5420 + 4 * (port))
#define MVPP2_ISR_ENABLE_INTERRUPT(mask) ((mask) & 0xffff)
#define MVPP2_ISR_DISABLE_INTERRUPT(mask) (((mask) << 16) & 0xffff0000)
@@ -210,14 +254,19 @@
#define MVPP2_BM_PHY_ALLOC_REG(pool) (0x6400 + ((pool) * 4))
#define MVPP2_BM_PHY_ALLOC_GRNTD_MASK BIT(0)
#define MVPP2_BM_VIRT_ALLOC_REG 0x6440
+#define MVPP22_BM_ADDR_HIGH_ALLOC 0x6444
+#define MVPP22_BM_ADDR_HIGH_PHYS_MASK 0xff
+#define MVPP22_BM_ADDR_HIGH_VIRT_MASK 0xff00
+#define MVPP22_BM_ADDR_HIGH_VIRT_SHIFT 8
#define MVPP2_BM_PHY_RLS_REG(pool) (0x6480 + ((pool) * 4))
#define MVPP2_BM_PHY_RLS_MC_BUFF_MASK BIT(0)
#define MVPP2_BM_PHY_RLS_PRIO_EN_MASK BIT(1)
#define MVPP2_BM_PHY_RLS_GRNTD_MASK BIT(2)
#define MVPP2_BM_VIRT_RLS_REG 0x64c0
-#define MVPP2_BM_MC_RLS_REG 0x64c4
-#define MVPP2_BM_MC_ID_MASK 0xfff
-#define MVPP2_BM_FORCE_RELEASE_MASK BIT(12)
+#define MVPP22_BM_ADDR_HIGH_RLS_REG 0x64c4
+#define MVPP22_BM_ADDR_HIGH_PHYS_RLS_MASK 0xff
+#define MVPP22_BM_ADDR_HIGH_VIRT_RLS_MASK 0xff00
+#define MVPP22_BM_ADDR_HIGH_VIRT_RLS_SHIFT 8
/* TX Scheduler registers */
#define MVPP2_TXP_SCHED_PORT_INDEX_REG 0x8000
@@ -287,6 +336,24 @@
#define MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK 0x1fc0
#define MVPP2_GMAC_TX_FIFO_MIN_TH_MASK(v) (((v) << 6) & \
MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK)
+#define MVPP22_GMAC_CTRL_4_REG 0x90
+#define MVPP22_CTRL4_EXT_PIN_GMII_SEL BIT(0)
+#define MVPP22_CTRL4_DP_CLK_SEL BIT(5)
+#define MVPP22_CTRL4_SYNC_BYPASS BIT(6)
+#define MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE BIT(7)
+
+/* Per-port XGMAC registers. PPv2.2 only, only for GOP port 0,
+ * relative to port->base.
+ */
+#define MVPP22_XLG_CTRL3_REG 0x11c
+#define MVPP22_XLG_CTRL3_MACMODESELECT_MASK (7 << 13)
+#define MVPP22_XLG_CTRL3_MACMODESELECT_GMAC (0 << 13)
+
+/* SMI registers. PPv2.2 only, relative to priv->iface_base. */
+#define MVPP22_SMI_MISC_CFG_REG 0x1204
+#define MVPP22_SMI_POLLING_EN BIT(10)
+
+#define MVPP22_GMAC_BASE(port) (0x7000 + (port) * 0x1000 + 0xe00)
#define MVPP2_CAUSE_TXQ_SENT_DESC_ALL_MASK 0xff
@@ -335,15 +402,9 @@
/* Maximum number of TXQs used by single port */
#define MVPP2_MAX_TXQ 8
-/* Maximum number of RXQs used by single port */
-#define MVPP2_MAX_RXQ 8
-
/* Dfault number of RXQs in use */
#define MVPP2_DEFAULT_RXQ 4
-/* Total number of RXQs available to all ports */
-#define MVPP2_RXQ_TOTAL_NUM (MVPP2_MAX_PORTS * MVPP2_MAX_RXQ)
-
/* Max number of Rx descriptors */
#define MVPP2_MAX_RXD 128
@@ -615,6 +676,11 @@ enum mvpp2_prs_l3_cast {
*/
#define MVPP2_BM_SHORT_PKT_SIZE MVPP2_RX_MAX_PKT_SIZE(512)
+#define MVPP21_ADDR_SPACE_SZ 0
+#define MVPP22_ADDR_SPACE_SZ SZ_64K
+
+#define MVPP2_MAX_CPUS 4
+
enum mvpp2_bm_type {
MVPP2_BM_FREE,
MVPP2_BM_SWF_LONG,
@@ -626,12 +692,19 @@ enum mvpp2_bm_type {
/* Shared Packet Processor resources */
struct mvpp2 {
/* Shared registers' base addresses */
- void __iomem *base;
void __iomem *lms_base;
+ void __iomem *iface_base;
+
+ /* On PPv2.2, each CPU can access the base register through a
+ * separate address space, each 64 KB apart from each
+ * other.
+ */
+ void __iomem *cpu_base[MVPP2_MAX_CPUS];
/* Common clocks */
struct clk *pp_clk;
struct clk *gop_clk;
+ struct clk *mg_clk;
/* List of pointers to port structures */
struct mvpp2_port **port_list;
@@ -649,6 +722,12 @@ struct mvpp2 {
/* Tclk value */
u32 tclk;
+
+ /* HW version */
+ enum { MVPP21, MVPP22 } hw_version;
+
+ /* Maximum number of RXQs per port */
+ unsigned int max_port_rxqs;
};
struct mvpp2_pcpu_stats {
@@ -670,6 +749,11 @@ struct mvpp2_port_pcpu {
struct mvpp2_port {
u8 id;
+ /* Index of the port from the "group of ports" complex point
+ * of view
+ */
+ int gop_id;
+
int irq;
struct mvpp2 *priv;
@@ -741,22 +825,24 @@ struct mvpp2_port {
#define MVPP2_RXD_L3_IP6 BIT(30)
#define MVPP2_RXD_BUF_HDR BIT(31)
-struct mvpp2_tx_desc {
+/* HW TX descriptor for PPv2.1 */
+struct mvpp21_tx_desc {
u32 command; /* Options used by HW for packet transmitting.*/
u8 packet_offset; /* the offset from the buffer beginning */
u8 phys_txq; /* destination queue ID */
u16 data_size; /* data size of transmitted packet in bytes */
- u32 buf_phys_addr; /* physical addr of transmitted buffer */
+ u32 buf_dma_addr; /* physical addr of transmitted buffer */
u32 buf_cookie; /* cookie for access to TX buffer in tx path */
u32 reserved1[3]; /* hw_cmd (for future use, BM, PON, PNC) */
u32 reserved2; /* reserved (for future use) */
};
-struct mvpp2_rx_desc {
+/* HW RX descriptor for PPv2.1 */
+struct mvpp21_rx_desc {
u32 status; /* info about received packet */
u16 reserved1; /* parser_info (for future use, PnC) */
u16 data_size; /* size of received packet in bytes */
- u32 buf_phys_addr; /* physical address of the buffer */
+ u32 buf_dma_addr; /* physical address of the buffer */
u32 buf_cookie; /* cookie for access to RX buffer in rx path */
u16 reserved2; /* gem_port_id (for future use, PON) */
u16 reserved3; /* csum_l4 (for future use, PnC) */
@@ -767,12 +853,51 @@ struct mvpp2_rx_desc {
u32 reserved8;
};
+/* HW TX descriptor for PPv2.2 */
+struct mvpp22_tx_desc {
+ u32 command;
+ u8 packet_offset;
+ u8 phys_txq;
+ u16 data_size;
+ u64 reserved1;
+ u64 buf_dma_addr_ptp;
+ u64 buf_cookie_misc;
+};
+
+/* HW RX descriptor for PPv2.2 */
+struct mvpp22_rx_desc {
+ u32 status;
+ u16 reserved1;
+ u16 data_size;
+ u32 reserved2;
+ u32 reserved3;
+ u64 buf_dma_addr_key_hash;
+ u64 buf_cookie_misc;
+};
+
+/* Opaque type used by the driver to manipulate the HW TX and RX
+ * descriptors
+ */
+struct mvpp2_tx_desc {
+ union {
+ struct mvpp21_tx_desc pp21;
+ struct mvpp22_tx_desc pp22;
+ };
+};
+
+struct mvpp2_rx_desc {
+ union {
+ struct mvpp21_rx_desc pp21;
+ struct mvpp22_rx_desc pp22;
+ };
+};
+
struct mvpp2_txq_pcpu_buf {
/* Transmitted SKB */
struct sk_buff *skb;
/* Physical address of transmitted buffer */
- dma_addr_t phys;
+ dma_addr_t dma;
/* Size transmitted */
size_t size;
@@ -825,7 +950,7 @@ struct mvpp2_tx_queue {
struct mvpp2_tx_desc *descs;
/* DMA address of the Tx DMA descriptors array */
- dma_addr_t descs_phys;
+ dma_addr_t descs_dma;
/* Index of the last Tx DMA descriptor */
int last_desc;
@@ -848,7 +973,7 @@ struct mvpp2_rx_queue {
struct mvpp2_rx_desc *descs;
/* DMA address of the RX DMA descriptors array */
- dma_addr_t descs_phys;
+ dma_addr_t descs_dma;
/* Index of the last RX DMA descriptor */
int last_desc;
@@ -912,6 +1037,8 @@ struct mvpp2_bm_pool {
/* Buffer Pointers Pool External (BPPE) size */
int size;
+ /* BPPE size in bytes */
+ int size_bytes;
/* Number of buffers for this pool */
int buf_num;
/* Pool buffer size */
@@ -922,29 +1049,13 @@ struct mvpp2_bm_pool {
/* BPPE virtual base address */
u32 *virt_addr;
- /* BPPE physical base address */
- dma_addr_t phys_addr;
+ /* BPPE DMA base address */
+ dma_addr_t dma_addr;
/* Ports using BM pool */
u32 port_map;
};
-struct mvpp2_buff_hdr {
- u32 next_buff_phys_addr;
- u32 next_buff_virt_addr;
- u16 byte_count;
- u16 info;
- u8 reserved1; /* bm_qset (for future use, BM) */
-};
-
-/* Buffer header info bits */
-#define MVPP2_B_HDR_INFO_MC_ID_MASK 0xfff
-#define MVPP2_B_HDR_INFO_MC_ID(info) ((info) & MVPP2_B_HDR_INFO_MC_ID_MASK)
-#define MVPP2_B_HDR_INFO_LAST_OFFS 12
-#define MVPP2_B_HDR_INFO_LAST_MASK BIT(12)
-#define MVPP2_B_HDR_INFO_IS_LAST(info) \
- ((info & MVPP2_B_HDR_INFO_LAST_MASK) >> MVPP2_B_HDR_INFO_LAST_OFFS)
-
/* Static declaractions */
/* Number of RXQs used by single port */
@@ -959,12 +1070,177 @@ static int txq_number = MVPP2_MAX_TXQ;
static void mvpp2_write(struct mvpp2 *priv, u32 offset, u32 data)
{
- writel(data, priv->base + offset);
+ writel(data, priv->cpu_base[0] + offset);
}
static u32 mvpp2_read(struct mvpp2 *priv, u32 offset)
{
- return readl(priv->base + offset);
+ return readl(priv->cpu_base[0] + offset);
+}
+
+/* These accessors should be used to access:
+ *
+ * - per-CPU registers, where each CPU has its own copy of the
+ * register.
+ *
+ * MVPP2_BM_VIRT_ALLOC_REG
+ * MVPP2_BM_ADDR_HIGH_ALLOC
+ * MVPP22_BM_ADDR_HIGH_RLS_REG
+ * MVPP2_BM_VIRT_RLS_REG
+ * MVPP2_ISR_RX_TX_CAUSE_REG
+ * MVPP2_ISR_RX_TX_MASK_REG
+ * MVPP2_TXQ_NUM_REG
+ * MVPP2_AGGR_TXQ_UPDATE_REG
+ * MVPP2_TXQ_RSVD_REQ_REG
+ * MVPP2_TXQ_RSVD_RSLT_REG
+ * MVPP2_TXQ_SENT_REG
+ * MVPP2_RXQ_NUM_REG
+ *
+ * - global registers that must be accessed through a specific CPU
+ * window, because they are related to an access to a per-CPU
+ * register
+ *
+ * MVPP2_BM_PHY_ALLOC_REG (related to MVPP2_BM_VIRT_ALLOC_REG)
+ * MVPP2_BM_PHY_RLS_REG (related to MVPP2_BM_VIRT_RLS_REG)
+ * MVPP2_RXQ_THRESH_REG (related to MVPP2_RXQ_NUM_REG)
+ * MVPP2_RXQ_DESC_ADDR_REG (related to MVPP2_RXQ_NUM_REG)
+ * MVPP2_RXQ_DESC_SIZE_REG (related to MVPP2_RXQ_NUM_REG)
+ * MVPP2_RXQ_INDEX_REG (related to MVPP2_RXQ_NUM_REG)
+ * MVPP2_TXQ_PENDING_REG (related to MVPP2_TXQ_NUM_REG)
+ * MVPP2_TXQ_DESC_ADDR_REG (related to MVPP2_TXQ_NUM_REG)
+ * MVPP2_TXQ_DESC_SIZE_REG (related to MVPP2_TXQ_NUM_REG)
+ * MVPP2_TXQ_INDEX_REG (related to MVPP2_TXQ_NUM_REG)
+ * MVPP2_TXQ_PENDING_REG (related to MVPP2_TXQ_NUM_REG)
+ * MVPP2_TXQ_PREF_BUF_REG (related to MVPP2_TXQ_NUM_REG)
+ * MVPP2_TXQ_PREF_BUF_REG (related to MVPP2_TXQ_NUM_REG)
+ */
+static void mvpp2_percpu_write(struct mvpp2 *priv, int cpu,
+ u32 offset, u32 data)
+{
+ writel(data, priv->cpu_base[cpu] + offset);
+}
+
+static u32 mvpp2_percpu_read(struct mvpp2 *priv, int cpu,
+ u32 offset)
+{
+ return readl(priv->cpu_base[cpu] + offset);
+}
+
+static dma_addr_t mvpp2_txdesc_dma_addr_get(struct mvpp2_port *port,
+ struct mvpp2_tx_desc *tx_desc)
+{
+ if (port->priv->hw_version == MVPP21)
+ return tx_desc->pp21.buf_dma_addr;
+ else
+ return tx_desc->pp22.buf_dma_addr_ptp & GENMASK_ULL(40, 0);
+}
+
+static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port,
+ struct mvpp2_tx_desc *tx_desc,
+ dma_addr_t dma_addr)
+{
+ if (port->priv->hw_version == MVPP21) {
+ tx_desc->pp21.buf_dma_addr = dma_addr;
+ } else {
+ u64 val = (u64)dma_addr;
+
+ tx_desc->pp22.buf_dma_addr_ptp &= ~GENMASK_ULL(40, 0);
+ tx_desc->pp22.buf_dma_addr_ptp |= val;
+ }
+}
+
+static size_t mvpp2_txdesc_size_get(struct mvpp2_port *port,
+ struct mvpp2_tx_desc *tx_desc)
+{
+ if (port->priv->hw_version == MVPP21)
+ return tx_desc->pp21.data_size;
+ else
+ return tx_desc->pp22.data_size;
+}
+
+static void mvpp2_txdesc_size_set(struct mvpp2_port *port,
+ struct mvpp2_tx_desc *tx_desc,
+ size_t size)
+{
+ if (port->priv->hw_version == MVPP21)
+ tx_desc->pp21.data_size = size;
+ else
+ tx_desc->pp22.data_size = size;
+}
+
+static void mvpp2_txdesc_txq_set(struct mvpp2_port *port,
+ struct mvpp2_tx_desc *tx_desc,
+ unsigned int txq)
+{
+ if (port->priv->hw_version == MVPP21)
+ tx_desc->pp21.phys_txq = txq;
+ else
+ tx_desc->pp22.phys_txq = txq;
+}
+
+static void mvpp2_txdesc_cmd_set(struct mvpp2_port *port,
+ struct mvpp2_tx_desc *tx_desc,
+ unsigned int command)
+{
+ if (port->priv->hw_version == MVPP21)
+ tx_desc->pp21.command = command;
+ else
+ tx_desc->pp22.command = command;
+}
+
+static void mvpp2_txdesc_offset_set(struct mvpp2_port *port,
+ struct mvpp2_tx_desc *tx_desc,
+ unsigned int offset)
+{
+ if (port->priv->hw_version == MVPP21)
+ tx_desc->pp21.packet_offset = offset;
+ else
+ tx_desc->pp22.packet_offset = offset;
+}
+
+static unsigned int mvpp2_txdesc_offset_get(struct mvpp2_port *port,
+ struct mvpp2_tx_desc *tx_desc)
+{
+ if (port->priv->hw_version == MVPP21)
+ return tx_desc->pp21.packet_offset;
+ else
+ return tx_desc->pp22.packet_offset;
+}
+
+static dma_addr_t mvpp2_rxdesc_dma_addr_get(struct mvpp2_port *port,
+ struct mvpp2_rx_desc *rx_desc)
+{
+ if (port->priv->hw_version == MVPP21)
+ return rx_desc->pp21.buf_dma_addr;
+ else
+ return rx_desc->pp22.buf_dma_addr_key_hash & GENMASK_ULL(40, 0);
+}
+
+static unsigned long mvpp2_rxdesc_cookie_get(struct mvpp2_port *port,
+ struct mvpp2_rx_desc *rx_desc)
+{
+ if (port->priv->hw_version == MVPP21)
+ return rx_desc->pp21.buf_cookie;
+ else
+ return rx_desc->pp22.buf_cookie_misc & GENMASK_ULL(40, 0);
+}
+
+static size_t mvpp2_rxdesc_size_get(struct mvpp2_port *port,
+ struct mvpp2_rx_desc *rx_desc)
+{
+ if (port->priv->hw_version == MVPP21)
+ return rx_desc->pp21.data_size;
+ else
+ return rx_desc->pp22.data_size;
+}
+
+static u32 mvpp2_rxdesc_status_get(struct mvpp2_port *port,
+ struct mvpp2_rx_desc *rx_desc)
+{
+ if (port->priv->hw_version == MVPP21)
+ return rx_desc->pp21.status;
+ else
+ return rx_desc->pp22.status;
}
static void mvpp2_txq_inc_get(struct mvpp2_txq_pcpu *txq_pcpu)
@@ -974,15 +1250,17 @@ static void mvpp2_txq_inc_get(struct mvpp2_txq_pcpu *txq_pcpu)
txq_pcpu->txq_get_index = 0;
}
-static void mvpp2_txq_inc_put(struct mvpp2_txq_pcpu *txq_pcpu,
+static void mvpp2_txq_inc_put(struct mvpp2_port *port,
+ struct mvpp2_txq_pcpu *txq_pcpu,
struct sk_buff *skb,
struct mvpp2_tx_desc *tx_desc)
{
struct mvpp2_txq_pcpu_buf *tx_buf =
txq_pcpu->buffs + txq_pcpu->txq_put_index;
tx_buf->skb = skb;
- tx_buf->size = tx_desc->data_size;
- tx_buf->phys = tx_desc->buf_phys_addr + tx_desc->packet_offset;
+ tx_buf->size = mvpp2_txdesc_size_get(port, tx_desc);
+ tx_buf->dma = mvpp2_txdesc_dma_addr_get(port, tx_desc) +
+ mvpp2_txdesc_offset_get(port, tx_desc);
txq_pcpu->txq_put_index++;
if (txq_pcpu->txq_put_index == txq_pcpu->size)
txq_pcpu->txq_put_index = 0;
@@ -3378,27 +3656,39 @@ static int mvpp2_bm_pool_create(struct platform_device *pdev,
struct mvpp2 *priv,
struct mvpp2_bm_pool *bm_pool, int size)
{
- int size_bytes;
u32 val;
- size_bytes = sizeof(u32) * size;
- bm_pool->virt_addr = dma_alloc_coherent(&pdev->dev, size_bytes,
- &bm_pool->phys_addr,
+ /* Number of buffer pointers must be a multiple of 16, as per
+ * hardware constraints
+ */
+ if (!IS_ALIGNED(size, 16))
+ return -EINVAL;
+
+ /* PPv2.1 needs 8 bytes per buffer pointer, PPv2.2 needs 16
+ * bytes per buffer pointer
+ */
+ if (priv->hw_version == MVPP21)
+ bm_pool->size_bytes = 2 * sizeof(u32) * size;
+ else
+ bm_pool->size_bytes = 2 * sizeof(u64) * size;
+
+ bm_pool->virt_addr = dma_alloc_coherent(&pdev->dev, bm_pool->size_bytes,
+ &bm_pool->dma_addr,
GFP_KERNEL);
if (!bm_pool->virt_addr)
return -ENOMEM;
if (!IS_ALIGNED((unsigned long)bm_pool->virt_addr,
MVPP2_BM_POOL_PTR_ALIGN)) {
- dma_free_coherent(&pdev->dev, size_bytes, bm_pool->virt_addr,
- bm_pool->phys_addr);
+ dma_free_coherent(&pdev->dev, bm_pool->size_bytes,
+ bm_pool->virt_addr, bm_pool->dma_addr);
dev_err(&pdev->dev, "BM pool %d is not %d bytes aligned\n",
bm_pool->id, MVPP2_BM_POOL_PTR_ALIGN);
return -ENOMEM;
}
mvpp2_write(priv, MVPP2_BM_POOL_BASE_REG(bm_pool->id),
- bm_pool->phys_addr);
+ lower_32_bits(bm_pool->dma_addr));
mvpp2_write(priv, MVPP2_BM_POOL_SIZE_REG(bm_pool->id), size);
val = mvpp2_read(priv, MVPP2_BM_POOL_CTRL_REG(bm_pool->id));
@@ -3426,6 +3716,34 @@ static void mvpp2_bm_pool_bufsize_set(struct mvpp2 *priv,
mvpp2_write(priv, MVPP2_POOL_BUF_SIZE_REG(bm_pool->id), val);
}
+static void mvpp2_bm_bufs_get_addrs(struct device *dev, struct mvpp2 *priv,
+ struct mvpp2_bm_pool *bm_pool,
+ dma_addr_t *dma_addr,
+ phys_addr_t *phys_addr)
+{
+ int cpu = smp_processor_id();
+
+ *dma_addr = mvpp2_percpu_read(priv, cpu,
+ MVPP2_BM_PHY_ALLOC_REG(bm_pool->id));
+ *phys_addr = mvpp2_percpu_read(priv, cpu, MVPP2_BM_VIRT_ALLOC_REG);
+
+ if (priv->hw_version == MVPP22) {
+ u32 val;
+ u32 dma_addr_highbits, phys_addr_highbits;
+
+ val = mvpp2_percpu_read(priv, cpu, MVPP22_BM_ADDR_HIGH_ALLOC);
+ dma_addr_highbits = (val & MVPP22_BM_ADDR_HIGH_PHYS_MASK);
+ phys_addr_highbits = (val & MVPP22_BM_ADDR_HIGH_VIRT_MASK) >>
+ MVPP22_BM_ADDR_HIGH_VIRT_SHIFT;
+
+ if (sizeof(dma_addr_t) == 8)
+ *dma_addr |= (u64)dma_addr_highbits << 32;
+
+ if (sizeof(phys_addr_t) == 8)
+ *phys_addr |= (u64)phys_addr_highbits << 32;
+ }
+}
+
/* Free all buffers from the pool */
static void mvpp2_bm_bufs_free(struct device *dev, struct mvpp2 *priv,
struct mvpp2_bm_pool *bm_pool)
@@ -3433,21 +3751,21 @@ static void mvpp2_bm_bufs_free(struct device *dev, struct mvpp2 *priv,
int i;
for (i = 0; i < bm_pool->buf_num; i++) {
- dma_addr_t buf_phys_addr;
- unsigned long vaddr;
+ dma_addr_t buf_dma_addr;
+ phys_addr_t buf_phys_addr;
+ void *data;
- /* Get buffer virtual address (indirect access) */
- buf_phys_addr = mvpp2_read(priv,
- MVPP2_BM_PHY_ALLOC_REG(bm_pool->id));
- vaddr = mvpp2_read(priv, MVPP2_BM_VIRT_ALLOC_REG);
+ mvpp2_bm_bufs_get_addrs(dev, priv, bm_pool,
+ &buf_dma_addr, &buf_phys_addr);
- dma_unmap_single(dev, buf_phys_addr,
+ dma_unmap_single(dev, buf_dma_addr,
bm_pool->buf_size, DMA_FROM_DEVICE);
- if (!vaddr)
+ data = (void *)phys_to_virt(buf_phys_addr);
+ if (!data)
break;
- mvpp2_frag_free(bm_pool, (void *)vaddr);
+ mvpp2_frag_free(bm_pool, data);
}
/* Update BM driver with number of buffers removed from pool */
@@ -3471,9 +3789,9 @@ static int mvpp2_bm_pool_destroy(struct platform_device *pdev,
val |= MVPP2_BM_STOP_MASK;
mvpp2_write(priv, MVPP2_BM_POOL_CTRL_REG(bm_pool->id), val);
- dma_free_coherent(&pdev->dev, sizeof(u32) * bm_pool->size,
+ dma_free_coherent(&pdev->dev, bm_pool->size_bytes,
bm_pool->virt_addr,
- bm_pool->phys_addr);
+ bm_pool->dma_addr);
return 0;
}
@@ -3529,17 +3847,20 @@ static int mvpp2_bm_init(struct platform_device *pdev, struct mvpp2 *priv)
static void mvpp2_rxq_long_pool_set(struct mvpp2_port *port,
int lrxq, int long_pool)
{
- u32 val;
+ u32 val, mask;
int prxq;
/* Get queue physical ID */
prxq = port->rxqs[lrxq]->id;
- val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(prxq));
- val &= ~MVPP2_RXQ_POOL_LONG_MASK;
- val |= ((long_pool << MVPP2_RXQ_POOL_LONG_OFFS) &
- MVPP2_RXQ_POOL_LONG_MASK);
+ if (port->priv->hw_version == MVPP21)
+ mask = MVPP21_RXQ_POOL_LONG_MASK;
+ else
+ mask = MVPP22_RXQ_POOL_LONG_MASK;
+ val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(prxq));
+ val &= ~mask;
+ val |= (long_pool << MVPP2_RXQ_POOL_LONG_OFFS) & mask;
mvpp2_write(port->priv, MVPP2_RXQ_CONFIG_REG(prxq), val);
}
@@ -3547,40 +3868,45 @@ static void mvpp2_rxq_long_pool_set(struct mvpp2_port *port,
static void mvpp2_rxq_short_pool_set(struct mvpp2_port *port,
int lrxq, int short_pool)
{
- u32 val;
+ u32 val, mask;
int prxq;
/* Get queue physical ID */
prxq = port->rxqs[lrxq]->id;
- val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(prxq));
- val &= ~MVPP2_RXQ_POOL_SHORT_MASK;
- val |= ((short_pool << MVPP2_RXQ_POOL_SHORT_OFFS) &
- MVPP2_RXQ_POOL_SHORT_MASK);
+ if (port->priv->hw_version == MVPP21)
+ mask = MVPP21_RXQ_POOL_SHORT_MASK;
+ else
+ mask = MVPP22_RXQ_POOL_SHORT_MASK;
+ val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(prxq));
+ val &= ~mask;
+ val |= (short_pool << MVPP2_RXQ_POOL_SHORT_OFFS) & mask;
mvpp2_write(port->priv, MVPP2_RXQ_CONFIG_REG(prxq), val);
}
static void *mvpp2_buf_alloc(struct mvpp2_port *port,
struct mvpp2_bm_pool *bm_pool,
- dma_addr_t *buf_phys_addr,
+ dma_addr_t *buf_dma_addr,
+ phys_addr_t *buf_phys_addr,
gfp_t gfp_mask)
{
- dma_addr_t phys_addr;
+ dma_addr_t dma_addr;
void *data;
data = mvpp2_frag_alloc(bm_pool);
if (!data)
return NULL;
- phys_addr = dma_map_single(port->dev->dev.parent, data,
- MVPP2_RX_BUF_SIZE(bm_pool->pkt_size),
- DMA_FROM_DEVICE);
- if (unlikely(dma_mapping_error(port->dev->dev.parent, phys_addr))) {
+ dma_addr = dma_map_single(port->dev->dev.parent, data,
+ MVPP2_RX_BUF_SIZE(bm_pool->pkt_size),
+ DMA_FROM_DEVICE);
+ if (unlikely(dma_mapping_error(port->dev->dev.parent, dma_addr))) {
mvpp2_frag_free(bm_pool, data);
return NULL;
}
- *buf_phys_addr = phys_addr;
+ *buf_dma_addr = dma_addr;
+ *buf_phys_addr = virt_to_phys(data);
return data;
}
@@ -3604,37 +3930,46 @@ static inline int mvpp2_bm_cookie_pool_get(unsigned long cookie)
/* Release buffer to BM */
static inline void mvpp2_bm_pool_put(struct mvpp2_port *port, int pool,
- dma_addr_t buf_phys_addr,
- unsigned long buf_virt_addr)
+ dma_addr_t buf_dma_addr,
+ phys_addr_t buf_phys_addr)
{
- mvpp2_write(port->priv, MVPP2_BM_VIRT_RLS_REG, buf_virt_addr);
- mvpp2_write(port->priv, MVPP2_BM_PHY_RLS_REG(pool), buf_phys_addr);
-}
+ int cpu = smp_processor_id();
-/* Release multicast buffer */
-static void mvpp2_bm_pool_mc_put(struct mvpp2_port *port, int pool,
- dma_addr_t buf_phys_addr,
- unsigned long buf_virt_addr,
- int mc_id)
-{
- u32 val = 0;
+ if (port->priv->hw_version == MVPP22) {
+ u32 val = 0;
- val |= (mc_id & MVPP2_BM_MC_ID_MASK);
- mvpp2_write(port->priv, MVPP2_BM_MC_RLS_REG, val);
+ if (sizeof(dma_addr_t) == 8)
+ val |= upper_32_bits(buf_dma_addr) &
+ MVPP22_BM_ADDR_HIGH_PHYS_RLS_MASK;
- mvpp2_bm_pool_put(port, pool,
- buf_phys_addr | MVPP2_BM_PHY_RLS_MC_BUFF_MASK,
- buf_virt_addr);
+ if (sizeof(phys_addr_t) == 8)
+ val |= (upper_32_bits(buf_phys_addr)
+ << MVPP22_BM_ADDR_HIGH_VIRT_RLS_SHIFT) &
+ MVPP22_BM_ADDR_HIGH_VIRT_RLS_MASK;
+
+ mvpp2_percpu_write(port->priv, cpu,
+ MVPP22_BM_ADDR_HIGH_RLS_REG, val);
+ }
+
+ /* MVPP2_BM_VIRT_RLS_REG is not interpreted by HW, and simply
+ * returned in the "cookie" field of the RX
+ * descriptor. Instead of storing the virtual address, we
+ * store the physical address
+ */
+ mvpp2_percpu_write(port->priv, cpu,
+ MVPP2_BM_VIRT_RLS_REG, buf_phys_addr);
+ mvpp2_percpu_write(port->priv, cpu,
+ MVPP2_BM_PHY_RLS_REG(pool), buf_dma_addr);
}
/* Refill BM pool */
static void mvpp2_pool_refill(struct mvpp2_port *port, u32 bm,
- dma_addr_t phys_addr,
- unsigned long cookie)
+ dma_addr_t dma_addr,
+ phys_addr_t phys_addr)
{
int pool = mvpp2_bm_cookie_pool_get(bm);
- mvpp2_bm_pool_put(port, pool, phys_addr, cookie);
+ mvpp2_bm_pool_put(port, pool, dma_addr, phys_addr);
}
/* Allocate buffers for the pool */
@@ -3642,7 +3977,8 @@ static int mvpp2_bm_bufs_add(struct mvpp2_port *port,
struct mvpp2_bm_pool *bm_pool, int buf_num)
{
int i, buf_size, total_size;
- dma_addr_t phys_addr;
+ dma_addr_t dma_addr;
+ phys_addr_t phys_addr;
void *buf;
buf_size = MVPP2_RX_BUF_SIZE(bm_pool->pkt_size);
@@ -3657,12 +3993,13 @@ static int mvpp2_bm_bufs_add(struct mvpp2_port *port,
}
for (i = 0; i < buf_num; i++) {
- buf = mvpp2_buf_alloc(port, bm_pool, &phys_addr, GFP_KERNEL);
+ buf = mvpp2_buf_alloc(port, bm_pool, &dma_addr,
+ &phys_addr, GFP_KERNEL);
if (!buf)
break;
- mvpp2_bm_pool_put(port, bm_pool->id, phys_addr,
- (unsigned long)buf);
+ mvpp2_bm_pool_put(port, bm_pool->id, dma_addr,
+ phys_addr);
}
/* Update BM driver with number of buffers added to pool */
@@ -3830,7 +4167,8 @@ static void mvpp2_interrupts_mask(void *arg)
{
struct mvpp2_port *port = arg;
- mvpp2_write(port->priv, MVPP2_ISR_RX_TX_MASK_REG(port->id), 0);
+ mvpp2_percpu_write(port->priv, smp_processor_id(),
+ MVPP2_ISR_RX_TX_MASK_REG(port->id), 0);
}
/* Unmask the current CPU's Rx/Tx interrupts */
@@ -3838,17 +4176,46 @@ static void mvpp2_interrupts_unmask(void *arg)
{
struct mvpp2_port *port = arg;
- mvpp2_write(port->priv, MVPP2_ISR_RX_TX_MASK_REG(port->id),
- (MVPP2_CAUSE_MISC_SUM_MASK |
- MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK));
+ mvpp2_percpu_write(port->priv, smp_processor_id(),
+ MVPP2_ISR_RX_TX_MASK_REG(port->id),
+ (MVPP2_CAUSE_MISC_SUM_MASK |
+ MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK));
}
/* Port configuration routines */
+static void mvpp22_port_mii_set(struct mvpp2_port *port)
+{
+ u32 val;
+
+ return;
+
+ /* Only GOP port 0 has an XLG MAC */
+ if (port->gop_id == 0) {
+ val = readl(port->base + MVPP22_XLG_CTRL3_REG);
+ val &= ~MVPP22_XLG_CTRL3_MACMODESELECT_MASK;
+ val |= MVPP22_XLG_CTRL3_MACMODESELECT_GMAC;
+ writel(val, port->base + MVPP22_XLG_CTRL3_REG);
+ }
+
+ val = readl(port->base + MVPP22_GMAC_CTRL_4_REG);
+ if (port->phy_interface == PHY_INTERFACE_MODE_RGMII)
+ val |= MVPP22_CTRL4_EXT_PIN_GMII_SEL;
+ else
+ val &= ~MVPP22_CTRL4_EXT_PIN_GMII_SEL;
+ val &= ~MVPP22_CTRL4_DP_CLK_SEL;
+ val |= MVPP22_CTRL4_SYNC_BYPASS;
+ val |= MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE;
+ writel(val, port->base + MVPP22_GMAC_CTRL_4_REG);
+}
+
static void mvpp2_port_mii_set(struct mvpp2_port *port)
{
u32 val;
+ if (port->priv->hw_version == MVPP22)
+ mvpp22_port_mii_set(port);
+
val = readl(port->base + MVPP2_GMAC_CTRL_2_REG);
switch (port->phy_interface) {
@@ -3952,16 +4319,18 @@ static void mvpp2_defaults_set(struct mvpp2_port *port)
{
int tx_port_num, val, queue, ptxq, lrxq;
- /* Configure port to loopback if needed */
- if (port->flags & MVPP2_F_LOOPBACK)
- mvpp2_port_loopback_set(port);
+ if (port->priv->hw_version == MVPP21) {
+ /* Configure port to loopback if needed */
+ if (port->flags & MVPP2_F_LOOPBACK)
+ mvpp2_port_loopback_set(port);
- /* Update TX FIFO MIN Threshold */
- val = readl(port->base + MVPP2_GMAC_PORT_FIFO_CFG_1_REG);
- val &= ~MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK;
- /* Min. TX threshold must be less than minimal packet length */
- val |= MVPP2_GMAC_TX_FIFO_MIN_TH_MASK(64 - 4 - 2);
- writel(val, port->base + MVPP2_GMAC_PORT_FIFO_CFG_1_REG);
+ /* Update TX FIFO MIN Threshold */
+ val = readl(port->base + MVPP2_GMAC_PORT_FIFO_CFG_1_REG);
+ val &= ~MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK;
+ /* Min. TX threshold must be less than minimal packet length */
+ val |= MVPP2_GMAC_TX_FIFO_MIN_TH_MASK(64 - 4 - 2);
+ writel(val, port->base + MVPP2_GMAC_PORT_FIFO_CFG_1_REG);
+ }
/* Disable Legacy WRR, Disable EJP, Release from reset */
tx_port_num = mvpp2_egress_port(port);
@@ -4149,11 +4518,15 @@ static void mvpp2_rxq_offset_set(struct mvpp2_port *port,
}
/* Obtain BM cookie information from descriptor */
-static u32 mvpp2_bm_cookie_build(struct mvpp2_rx_desc *rx_desc)
+static u32 mvpp2_bm_cookie_build(struct mvpp2_port *port,
+ struct mvpp2_rx_desc *rx_desc)
{
- int pool = (rx_desc->status & MVPP2_RXD_BM_POOL_ID_MASK) >>
- MVPP2_RXD_BM_POOL_ID_OFFS;
int cpu = smp_processor_id();
+ int pool;
+
+ pool = (mvpp2_rxdesc_status_get(port, rx_desc) &
+ MVPP2_RXD_BM_POOL_ID_MASK) >>
+ MVPP2_RXD_BM_POOL_ID_OFFS;
return ((pool & 0xFF) << MVPP2_BM_COOKIE_POOL_OFFS) |
((cpu & 0xFF) << MVPP2_BM_COOKIE_CPU_OFFS);
@@ -4161,18 +4534,6 @@ static u32 mvpp2_bm_cookie_build(struct mvpp2_rx_desc *rx_desc)
/* Tx descriptors helper methods */
-/* Get number of Tx descriptors waiting to be transmitted by HW */
-static int mvpp2_txq_pend_desc_num_get(struct mvpp2_port *port,
- struct mvpp2_tx_queue *txq)
-{
- u32 val;
-
- mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id);
- val = mvpp2_read(port->priv, MVPP2_TXQ_PENDING_REG);
-
- return val & MVPP2_TXQ_PENDING_MASK;
-}
-
/* Get pointer to next Tx descriptor to be processed (send) by HW */
static struct mvpp2_tx_desc *
mvpp2_txq_next_desc_get(struct mvpp2_tx_queue *txq)
@@ -4187,7 +4548,8 @@ mvpp2_txq_next_desc_get(struct mvpp2_tx_queue *txq)
static void mvpp2_aggr_txq_pend_desc_add(struct mvpp2_port *port, int pending)
{
/* aggregated access - relevant TXQ number is written in TX desc */
- mvpp2_write(port->priv, MVPP2_AGGR_TXQ_UPDATE_REG, pending);
+ mvpp2_percpu_write(port->priv, smp_processor_id(),
+ MVPP2_AGGR_TXQ_UPDATE_REG, pending);
}
@@ -4216,11 +4578,12 @@ static int mvpp2_txq_alloc_reserved_desc(struct mvpp2 *priv,
struct mvpp2_tx_queue *txq, int num)
{
u32 val;
+ int cpu = smp_processor_id();
val = (txq->id << MVPP2_TXQ_RSVD_REQ_Q_OFFSET) | num;
- mvpp2_write(priv, MVPP2_TXQ_RSVD_REQ_REG, val);
+ mvpp2_percpu_write(priv, cpu, MVPP2_TXQ_RSVD_REQ_REG, val);
- val = mvpp2_read(priv, MVPP2_TXQ_RSVD_RSLT_REG);
+ val = mvpp2_percpu_read(priv, cpu, MVPP2_TXQ_RSVD_RSLT_REG);
return val & MVPP2_TXQ_RSVD_RSLT_MASK;
}
@@ -4321,7 +4684,8 @@ static inline int mvpp2_txq_sent_desc_proc(struct mvpp2_port *port,
u32 val;
/* Reading status reg resets transmitted descriptor counter */
- val = mvpp2_read(port->priv, MVPP2_TXQ_SENT_REG(txq->id));
+ val = mvpp2_percpu_read(port->priv, smp_processor_id(),
+ MVPP2_TXQ_SENT_REG(txq->id));
return (val & MVPP2_TRANSMITTED_COUNT_MASK) >>
MVPP2_TRANSMITTED_COUNT_OFFSET;
@@ -4335,7 +4699,8 @@ static void mvpp2_txq_sent_counter_clear(void *arg)
for (queue = 0; queue < txq_number; queue++) {
int id = port->txqs[queue]->id;
- mvpp2_read(port->priv, MVPP2_TXQ_SENT_REG(id));
+ mvpp2_percpu_read(port->priv, smp_processor_id(),
+ MVPP2_TXQ_SENT_REG(id));
}
}
@@ -4394,12 +4759,14 @@ static void mvpp2_txp_max_tx_size_set(struct mvpp2_port *port)
static void mvpp2_rx_pkts_coal_set(struct mvpp2_port *port,
struct mvpp2_rx_queue *rxq)
{
+ int cpu = smp_processor_id();
+
if (rxq->pkts_coal > MVPP2_OCCUPIED_THRESH_MASK)
rxq->pkts_coal = MVPP2_OCCUPIED_THRESH_MASK;
- mvpp2_write(port->priv, MVPP2_RXQ_NUM_REG, rxq->id);
- mvpp2_write(port->priv, MVPP2_RXQ_THRESH_REG,
- rxq->pkts_coal);
+ mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_NUM_REG, rxq->id);
+ mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_THRESH_REG,
+ rxq->pkts_coal);
}
static u32 mvpp2_usec_to_cycles(u32 usec, unsigned long clk_hz)
@@ -4449,7 +4816,7 @@ static void mvpp2_txq_bufs_free(struct mvpp2_port *port,
struct mvpp2_txq_pcpu_buf *tx_buf =
txq_pcpu->buffs + txq_pcpu->txq_get_index;
- dma_unmap_single(port->dev->dev.parent, tx_buf->phys,
+ dma_unmap_single(port->dev->dev.parent, tx_buf->dma,
tx_buf->size, DMA_TO_DEVICE);
if (tx_buf->skb)
dev_kfree_skb_any(tx_buf->skb);
@@ -4527,10 +4894,12 @@ static int mvpp2_aggr_txq_init(struct platform_device *pdev,
int desc_num, int cpu,
struct mvpp2 *priv)
{
+ u32 txq_dma;
+
/* Allocate memory for TX descriptors */
aggr_txq->descs = dma_alloc_coherent(&pdev->dev,
desc_num * MVPP2_DESC_ALIGNED_SIZE,
- &aggr_txq->descs_phys, GFP_KERNEL);
+ &aggr_txq->descs_dma, GFP_KERNEL);
if (!aggr_txq->descs)
return -ENOMEM;
@@ -4540,10 +4909,16 @@ static int mvpp2_aggr_txq_init(struct platform_device *pdev,
aggr_txq->next_desc_to_proc = mvpp2_read(priv,
MVPP2_AGGR_TXQ_INDEX_REG(cpu));
- /* Set Tx descriptors queue starting address */
- /* indirect access */
- mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_ADDR_REG(cpu),
- aggr_txq->descs_phys);
+ /* Set Tx descriptors queue starting address indirect
+ * access
+ */
+ if (priv->hw_version == MVPP21)
+ txq_dma = aggr_txq->descs_dma;
+ else
+ txq_dma = aggr_txq->descs_dma >>
+ MVPP22_AGGR_TXQ_DESC_ADDR_OFFS;
+
+ mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_ADDR_REG(cpu), txq_dma);
mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_SIZE_REG(cpu), desc_num);
return 0;
@@ -4554,12 +4929,15 @@ static int mvpp2_rxq_init(struct mvpp2_port *port,
struct mvpp2_rx_queue *rxq)
{
+ u32 rxq_dma;
+ int cpu;
+
rxq->size = port->rx_ring_size;
/* Allocate memory for RX descriptors */
rxq->descs = dma_alloc_coherent(port->dev->dev.parent,
rxq->size * MVPP2_DESC_ALIGNED_SIZE,
- &rxq->descs_phys, GFP_KERNEL);
+ &rxq->descs_dma, GFP_KERNEL);
if (!rxq->descs)
return -ENOMEM;
@@ -4569,10 +4947,15 @@ static int mvpp2_rxq_init(struct mvpp2_port *port,
mvpp2_write(port->priv, MVPP2_RXQ_STATUS_REG(rxq->id), 0);
/* Set Rx descriptors queue starting address - indirect access */
- mvpp2_write(port->priv, MVPP2_RXQ_NUM_REG, rxq->id);
- mvpp2_write(port->priv, MVPP2_RXQ_DESC_ADDR_REG, rxq->descs_phys);
- mvpp2_write(port->priv, MVPP2_RXQ_DESC_SIZE_REG, rxq->size);
- mvpp2_write(port->priv, MVPP2_RXQ_INDEX_REG, 0);
+ cpu = smp_processor_id();
+ mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_NUM_REG, rxq->id);
+ if (port->priv->hw_version == MVPP21)
+ rxq_dma = rxq->descs_dma;
+ else
+ rxq_dma = rxq->descs_dma >> MVPP22_DESC_ADDR_OFFS;
+ mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_ADDR_REG, rxq_dma);
+ mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_SIZE_REG, rxq->size);
+ mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_INDEX_REG, 0);
/* Set Offset */
mvpp2_rxq_offset_set(port, rxq->id, NET_SKB_PAD);
@@ -4599,10 +4982,11 @@ static void mvpp2_rxq_drop_pkts(struct mvpp2_port *port,
for (i = 0; i < rx_received; i++) {
struct mvpp2_rx_desc *rx_desc = mvpp2_rxq_next_desc_get(rxq);
- u32 bm = mvpp2_bm_cookie_build(rx_desc);
+ u32 bm = mvpp2_bm_cookie_build(port, rx_desc);
- mvpp2_pool_refill(port, bm, rx_desc->buf_phys_addr,
- rx_desc->buf_cookie);
+ mvpp2_pool_refill(port, bm,
+ mvpp2_rxdesc_dma_addr_get(port, rx_desc),
+ mvpp2_rxdesc_cookie_get(port, rx_desc));
}
mvpp2_rxq_status_update(port, rxq->id, rx_received, rx_received);
}
@@ -4611,26 +4995,29 @@ static void mvpp2_rxq_drop_pkts(struct mvpp2_port *port,
static void mvpp2_rxq_deinit(struct mvpp2_port *port,
struct mvpp2_rx_queue *rxq)
{
+ int cpu;
+
mvpp2_rxq_drop_pkts(port, rxq);
if (rxq->descs)
dma_free_coherent(port->dev->dev.parent,
rxq->size * MVPP2_DESC_ALIGNED_SIZE,
rxq->descs,
- rxq->descs_phys);
+ rxq->descs_dma);
rxq->descs = NULL;
rxq->last_desc = 0;
rxq->next_desc_to_proc = 0;
- rxq->descs_phys = 0;
+ rxq->descs_dma = 0;
/* Clear Rx descriptors queue starting address and size;
* free descriptor number
*/
mvpp2_write(port->priv, MVPP2_RXQ_STATUS_REG(rxq->id), 0);
- mvpp2_write(port->priv, MVPP2_RXQ_NUM_REG, rxq->id);
- mvpp2_write(port->priv, MVPP2_RXQ_DESC_ADDR_REG, 0);
- mvpp2_write(port->priv, MVPP2_RXQ_DESC_SIZE_REG, 0);
+ cpu = smp_processor_id();
+ mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_NUM_REG, rxq->id);
+ mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_ADDR_REG, 0);
+ mvpp2_percpu_write(port->priv, cpu, MVPP2_RXQ_DESC_SIZE_REG, 0);
}
/* Create and initialize a Tx queue */
@@ -4646,23 +5033,25 @@ static int mvpp2_txq_init(struct mvpp2_port *port,
/* Allocate memory for Tx descriptors */
txq->descs = dma_alloc_coherent(port->dev->dev.parent,
txq->size * MVPP2_DESC_ALIGNED_SIZE,
- &txq->descs_phys, GFP_KERNEL);
+ &txq->descs_dma, GFP_KERNEL);
if (!txq->descs)
return -ENOMEM;
txq->last_desc = txq->size - 1;
/* Set Tx descriptors queue starting address - indirect access */
- mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id);
- mvpp2_write(port->priv, MVPP2_TXQ_DESC_ADDR_REG, txq->descs_phys);
- mvpp2_write(port->priv, MVPP2_TXQ_DESC_SIZE_REG, txq->size &
- MVPP2_TXQ_DESC_SIZE_MASK);
- mvpp2_write(port->priv, MVPP2_TXQ_INDEX_REG, 0);
- mvpp2_write(port->priv, MVPP2_TXQ_RSVD_CLR_REG,
- txq->id << MVPP2_TXQ_RSVD_CLR_OFFSET);
- val = mvpp2_read(port->priv, MVPP2_TXQ_PENDING_REG);
+ cpu = smp_processor_id();
+ mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id);
+ mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_ADDR_REG,
+ txq->descs_dma);
+ mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_SIZE_REG,
+ txq->size & MVPP2_TXQ_DESC_SIZE_MASK);
+ mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_INDEX_REG, 0);
+ mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_RSVD_CLR_REG,
+ txq->id << MVPP2_TXQ_RSVD_CLR_OFFSET);
+ val = mvpp2_percpu_read(port->priv, cpu, MVPP2_TXQ_PENDING_REG);
val &= ~MVPP2_TXQ_PENDING_MASK;
- mvpp2_write(port->priv, MVPP2_TXQ_PENDING_REG, val);
+ mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PENDING_REG, val);
/* Calculate base address in prefetch buffer. We reserve 16 descriptors
* for each existing TXQ.
@@ -4673,9 +5062,9 @@ static int mvpp2_txq_init(struct mvpp2_port *port,
desc = (port->id * MVPP2_MAX_TXQ * desc_per_txq) +
(txq->log_id * desc_per_txq);
- mvpp2_write(port->priv, MVPP2_TXQ_PREF_BUF_REG,
- MVPP2_PREF_BUF_PTR(desc) | MVPP2_PREF_BUF_SIZE_16 |
- MVPP2_PREF_BUF_THRESH(desc_per_txq/2));
+ mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG,
+ MVPP2_PREF_BUF_PTR(desc) | MVPP2_PREF_BUF_SIZE_16 |
+ MVPP2_PREF_BUF_THRESH(desc_per_txq / 2));
/* WRR / EJP configuration - indirect access */
tx_port_num = mvpp2_egress_port(port);
@@ -4716,7 +5105,7 @@ static int mvpp2_txq_init(struct mvpp2_port *port,
dma_free_coherent(port->dev->dev.parent,
txq->size * MVPP2_DESC_ALIGNED_SIZE,
- txq->descs, txq->descs_phys);
+ txq->descs, txq->descs_dma);
return -ENOMEM;
}
@@ -4736,20 +5125,21 @@ static void mvpp2_txq_deinit(struct mvpp2_port *port,
if (txq->descs)
dma_free_coherent(port->dev->dev.parent,
txq->size * MVPP2_DESC_ALIGNED_SIZE,
- txq->descs, txq->descs_phys);
+ txq->descs, txq->descs_dma);
txq->descs = NULL;
txq->last_desc = 0;
txq->next_desc_to_proc = 0;
- txq->descs_phys = 0;
+ txq->descs_dma = 0;
/* Set minimum bandwidth for disabled TXQs */
mvpp2_write(port->priv, MVPP2_TXQ_SCHED_TOKEN_CNTR_REG(txq->id), 0);
/* Set Tx descriptors queue starting address and size */
- mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id);
- mvpp2_write(port->priv, MVPP2_TXQ_DESC_ADDR_REG, 0);
- mvpp2_write(port->priv, MVPP2_TXQ_DESC_SIZE_REG, 0);
+ cpu = smp_processor_id();
+ mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id);
+ mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_ADDR_REG, 0);
+ mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_DESC_SIZE_REG, 0);
}
/* Cleanup Tx ports */
@@ -4759,10 +5149,11 @@ static void mvpp2_txq_clean(struct mvpp2_port *port, struct mvpp2_tx_queue *txq)
int delay, pending, cpu;
u32 val;
- mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id);
- val = mvpp2_read(port->priv, MVPP2_TXQ_PREF_BUF_REG);
+ cpu = smp_processor_id();
+ mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id);
+ val = mvpp2_percpu_read(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG);
val |= MVPP2_TXQ_DRAIN_EN_MASK;
- mvpp2_write(port->priv, MVPP2_TXQ_PREF_BUF_REG, val);
+ mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG, val);
/* The napi queue has been stopped so wait for all packets
* to be transmitted.
@@ -4778,11 +5169,13 @@ static void mvpp2_txq_clean(struct mvpp2_port *port, struct mvpp2_tx_queue *txq)
mdelay(1);
delay++;
- pending = mvpp2_txq_pend_desc_num_get(port, txq);
+ pending = mvpp2_percpu_read(port->priv, cpu,
+ MVPP2_TXQ_PENDING_REG);
+ pending &= MVPP2_TXQ_PENDING_MASK;
} while (pending);
val &= ~MVPP2_TXQ_DRAIN_EN_MASK;
- mvpp2_write(port->priv, MVPP2_TXQ_PREF_BUF_REG, val);
+ mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_PREF_BUF_REG, val);
for_each_present_cpu(cpu) {
txq_pcpu = per_cpu_ptr(txq->pcpu, cpu);
@@ -4991,20 +5384,21 @@ static enum hrtimer_restart mvpp2_hr_timer_cb(struct hrtimer *timer)
static void mvpp2_rx_error(struct mvpp2_port *port,
struct mvpp2_rx_desc *rx_desc)
{
- u32 status = rx_desc->status;
+ u32 status = mvpp2_rxdesc_status_get(port, rx_desc);
+ size_t sz = mvpp2_rxdesc_size_get(port, rx_desc);
switch (status & MVPP2_RXD_ERR_CODE_MASK) {
case MVPP2_RXD_ERR_CRC:
- netdev_err(port->dev, "bad rx status %08x (crc error), size=%d\n",
- status, rx_desc->data_size);
+ netdev_err(port->dev, "bad rx status %08x (crc error), size=%zu\n",
+ status, sz);
break;
case MVPP2_RXD_ERR_OVERRUN:
- netdev_err(port->dev, "bad rx status %08x (overrun error), size=%d\n",
- status, rx_desc->data_size);
+ netdev_err(port->dev, "bad rx status %08x (overrun error), size=%zu\n",
+ status, sz);
break;
case MVPP2_RXD_ERR_RESOURCE:
- netdev_err(port->dev, "bad rx status %08x (resource error), size=%d\n",
- status, rx_desc->data_size);
+ netdev_err(port->dev, "bad rx status %08x (resource error), size=%zu\n",
+ status, sz);
break;
}
}
@@ -5031,15 +5425,17 @@ static void mvpp2_rx_csum(struct mvpp2_port *port, u32 status,
static int mvpp2_rx_refill(struct mvpp2_port *port,
struct mvpp2_bm_pool *bm_pool, u32 bm)
{
- dma_addr_t phys_addr;
+ dma_addr_t dma_addr;
+ phys_addr_t phys_addr;
void *buf;
/* No recycle or too many buffers are in use, so allocate a new skb */
- buf = mvpp2_buf_alloc(port, bm_pool, &phys_addr, GFP_ATOMIC);
+ buf = mvpp2_buf_alloc(port, bm_pool, &dma_addr, &phys_addr,
+ GFP_ATOMIC);
if (!buf)
return -ENOMEM;
- mvpp2_pool_refill(port, bm, phys_addr, (unsigned long)buf);
+ mvpp2_pool_refill(port, bm, dma_addr, phys_addr);
return 0;
}
@@ -5075,43 +5471,6 @@ static u32 mvpp2_skb_tx_csum(struct mvpp2_port *port, struct sk_buff *skb)
return MVPP2_TXD_L4_CSUM_NOT | MVPP2_TXD_IP_CSUM_DISABLE;
}
-static void mvpp2_buff_hdr_rx(struct mvpp2_port *port,
- struct mvpp2_rx_desc *rx_desc)
-{
- struct mvpp2_buff_hdr *buff_hdr;
- struct sk_buff *skb;
- u32 rx_status = rx_desc->status;
- dma_addr_t buff_phys_addr;
- unsigned long buff_virt_addr;
- dma_addr_t buff_phys_addr_next;
- unsigned long buff_virt_addr_next;
- int mc_id;
- int pool_id;
-
- pool_id = (rx_status & MVPP2_RXD_BM_POOL_ID_MASK) >>
- MVPP2_RXD_BM_POOL_ID_OFFS;
- buff_phys_addr = rx_desc->buf_phys_addr;
- buff_virt_addr = rx_desc->buf_cookie;
-
- do {
- skb = (struct sk_buff *)buff_virt_addr;
- buff_hdr = (struct mvpp2_buff_hdr *)skb->head;
-
- mc_id = MVPP2_B_HDR_INFO_MC_ID(buff_hdr->info);
-
- buff_phys_addr_next = buff_hdr->next_buff_phys_addr;
- buff_virt_addr_next = buff_hdr->next_buff_virt_addr;
-
- /* Release buffer */
- mvpp2_bm_pool_mc_put(port, pool_id, buff_phys_addr,
- buff_virt_addr, mc_id);
-
- buff_phys_addr = buff_phys_addr_next;
- buff_virt_addr = buff_virt_addr_next;
-
- } while (!MVPP2_B_HDR_INFO_IS_LAST(buff_hdr->info));
-}
-
/* Main rx processing */
static int mvpp2_rx(struct mvpp2_port *port, int rx_todo,
struct mvpp2_rx_queue *rxq)
@@ -5132,25 +5491,23 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo,
struct mvpp2_bm_pool *bm_pool;
struct sk_buff *skb;
unsigned int frag_size;
- dma_addr_t phys_addr;
+ dma_addr_t dma_addr;
+ phys_addr_t phys_addr;
u32 bm, rx_status;
int pool, rx_bytes, err;
void *data;
rx_done++;
- rx_status = rx_desc->status;
- rx_bytes = rx_desc->data_size - MVPP2_MH_SIZE;
- phys_addr = rx_desc->buf_phys_addr;
- data = (void *)(uintptr_t)rx_desc->buf_cookie;
+ rx_status = mvpp2_rxdesc_status_get(port, rx_desc);
+ rx_bytes = mvpp2_rxdesc_size_get(port, rx_desc);
+ rx_bytes -= MVPP2_MH_SIZE;
+ dma_addr = mvpp2_rxdesc_dma_addr_get(port, rx_desc);
+ phys_addr = mvpp2_rxdesc_cookie_get(port, rx_desc);
+ data = (void *)phys_to_virt(phys_addr);
- bm = mvpp2_bm_cookie_build(rx_desc);
+ bm = mvpp2_bm_cookie_build(port, rx_desc);
pool = mvpp2_bm_cookie_pool_get(bm);
bm_pool = &port->priv->bm_pools[pool];
- /* Check if buffer header is used */
- if (rx_status & MVPP2_RXD_BUF_HDR) {
- mvpp2_buff_hdr_rx(port, rx_desc);
- continue;
- }
/* In case of an error, release the requested buffer pointer
* to the Buffer Manager. This request process is controlled
@@ -5162,9 +5519,7 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo,
dev->stats.rx_errors++;
mvpp2_rx_error(port, rx_desc);
/* Return the buffer to the pool */
-
- mvpp2_pool_refill(port, bm, rx_desc->buf_phys_addr,
- rx_desc->buf_cookie);
+ mvpp2_pool_refill(port, bm, dma_addr, phys_addr);
continue;
}
@@ -5185,7 +5540,7 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo,
goto err_drop_frame;
}
- dma_unmap_single(dev->dev.parent, phys_addr,
+ dma_unmap_single(dev->dev.parent, dma_addr,
bm_pool->buf_size, DMA_FROM_DEVICE);
rcvd_pkts++;
@@ -5216,11 +5571,15 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo,
}
static inline void
-tx_desc_unmap_put(struct device *dev, struct mvpp2_tx_queue *txq,
+tx_desc_unmap_put(struct mvpp2_port *port, struct mvpp2_tx_queue *txq,
struct mvpp2_tx_desc *desc)
{
- dma_unmap_single(dev, desc->buf_phys_addr,
- desc->data_size, DMA_TO_DEVICE);
+ dma_addr_t buf_dma_addr =
+ mvpp2_txdesc_dma_addr_get(port, desc);
+ size_t buf_sz =
+ mvpp2_txdesc_size_get(port, desc);
+ dma_unmap_single(port->dev->dev.parent, buf_dma_addr,
+ buf_sz, DMA_TO_DEVICE);
mvpp2_txq_desc_put(txq);
}
@@ -5232,35 +5591,38 @@ static int mvpp2_tx_frag_process(struct mvpp2_port *port, struct sk_buff *skb,
struct mvpp2_txq_pcpu *txq_pcpu = this_cpu_ptr(txq->pcpu);
struct mvpp2_tx_desc *tx_desc;
int i;
- dma_addr_t buf_phys_addr;
+ dma_addr_t buf_dma_addr;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
void *addr = page_address(frag->page.p) + frag->page_offset;
tx_desc = mvpp2_txq_next_desc_get(aggr_txq);
- tx_desc->phys_txq = txq->id;
- tx_desc->data_size = frag->size;
+ mvpp2_txdesc_txq_set(port, tx_desc, txq->id);
+ mvpp2_txdesc_size_set(port, tx_desc, frag->size);
- buf_phys_addr = dma_map_single(port->dev->dev.parent, addr,
- tx_desc->data_size,
+ buf_dma_addr = dma_map_single(port->dev->dev.parent, addr,
+ frag->size,
DMA_TO_DEVICE);
- if (dma_mapping_error(port->dev->dev.parent, buf_phys_addr)) {
+ if (dma_mapping_error(port->dev->dev.parent, buf_dma_addr)) {
mvpp2_txq_desc_put(txq);
goto error;
}
- tx_desc->packet_offset = buf_phys_addr & MVPP2_TX_DESC_ALIGN;
- tx_desc->buf_phys_addr = buf_phys_addr & (~MVPP2_TX_DESC_ALIGN);
+ mvpp2_txdesc_offset_set(port, tx_desc,
+ buf_dma_addr & MVPP2_TX_DESC_ALIGN);
+ mvpp2_txdesc_dma_addr_set(port, tx_desc,
+ buf_dma_addr & ~MVPP2_TX_DESC_ALIGN);
if (i == (skb_shinfo(skb)->nr_frags - 1)) {
/* Last descriptor */
- tx_desc->command = MVPP2_TXD_L_DESC;
- mvpp2_txq_inc_put(txq_pcpu, skb, tx_desc);
+ mvpp2_txdesc_cmd_set(port, tx_desc,
+ MVPP2_TXD_L_DESC);
+ mvpp2_txq_inc_put(port, txq_pcpu, skb, tx_desc);
} else {
/* Descriptor in the middle: Not First, Not Last */
- tx_desc->command = 0;
- mvpp2_txq_inc_put(txq_pcpu, NULL, tx_desc);
+ mvpp2_txdesc_cmd_set(port, tx_desc, 0);
+ mvpp2_txq_inc_put(port, txq_pcpu, NULL, tx_desc);
}
}
@@ -5272,7 +5634,7 @@ static int mvpp2_tx_frag_process(struct mvpp2_port *port, struct sk_buff *skb,
*/
for (i = i - 1; i >= 0; i--) {
tx_desc = txq->descs + i;
- tx_desc_unmap_put(port->dev->dev.parent, txq, tx_desc);
+ tx_desc_unmap_put(port, txq, tx_desc);
}
return -ENOMEM;
@@ -5285,7 +5647,7 @@ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev)
struct mvpp2_tx_queue *txq, *aggr_txq;
struct mvpp2_txq_pcpu *txq_pcpu;
struct mvpp2_tx_desc *tx_desc;
- dma_addr_t buf_phys_addr;
+ dma_addr_t buf_dma_addr;
int frags = 0;
u16 txq_id;
u32 tx_cmd;
@@ -5307,35 +5669,38 @@ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev)
/* Get a descriptor for the first part of the packet */
tx_desc = mvpp2_txq_next_desc_get(aggr_txq);
- tx_desc->phys_txq = txq->id;
- tx_desc->data_size = skb_headlen(skb);
+ mvpp2_txdesc_txq_set(port, tx_desc, txq->id);
+ mvpp2_txdesc_size_set(port, tx_desc, skb_headlen(skb));
- buf_phys_addr = dma_map_single(dev->dev.parent, skb->data,
- tx_desc->data_size, DMA_TO_DEVICE);
- if (unlikely(dma_mapping_error(dev->dev.parent, buf_phys_addr))) {
+ buf_dma_addr = dma_map_single(dev->dev.parent, skb->data,
+ skb_headlen(skb), DMA_TO_DEVICE);
+ if (unlikely(dma_mapping_error(dev->dev.parent, buf_dma_addr))) {
mvpp2_txq_desc_put(txq);
frags = 0;
goto out;
}
- tx_desc->packet_offset = buf_phys_addr & MVPP2_TX_DESC_ALIGN;
- tx_desc->buf_phys_addr = buf_phys_addr & ~MVPP2_TX_DESC_ALIGN;
+
+ mvpp2_txdesc_offset_set(port, tx_desc,
+ buf_dma_addr & MVPP2_TX_DESC_ALIGN);
+ mvpp2_txdesc_dma_addr_set(port, tx_desc,
+ buf_dma_addr & ~MVPP2_TX_DESC_ALIGN);
tx_cmd = mvpp2_skb_tx_csum(port, skb);
if (frags == 1) {
/* First and Last descriptor */
tx_cmd |= MVPP2_TXD_F_DESC | MVPP2_TXD_L_DESC;
- tx_desc->command = tx_cmd;
- mvpp2_txq_inc_put(txq_pcpu, skb, tx_desc);
+ mvpp2_txdesc_cmd_set(port, tx_desc, tx_cmd);
+ mvpp2_txq_inc_put(port, txq_pcpu, skb, tx_desc);
} else {
/* First but not Last */
tx_cmd |= MVPP2_TXD_F_DESC | MVPP2_TXD_PADDING_DISABLE;
- tx_desc->command = tx_cmd;
- mvpp2_txq_inc_put(txq_pcpu, NULL, tx_desc);
+ mvpp2_txdesc_cmd_set(port, tx_desc, tx_cmd);
+ mvpp2_txq_inc_put(port, txq_pcpu, NULL, tx_desc);
/* Continue with other skb fragments */
if (mvpp2_tx_frag_process(port, skb, aggr_txq, txq)) {
- tx_desc_unmap_put(port->dev->dev.parent, txq, tx_desc);
+ tx_desc_unmap_put(port, txq, tx_desc);
frags = 0;
goto out;
}
@@ -5396,6 +5761,7 @@ static int mvpp2_poll(struct napi_struct *napi, int budget)
u32 cause_rx_tx, cause_rx, cause_misc;
int rx_done = 0;
struct mvpp2_port *port = netdev_priv(napi->dev);
+ int cpu = smp_processor_id();
/* Rx/Tx cause register
*
@@ -5407,8 +5773,8 @@ static int mvpp2_poll(struct napi_struct *napi, int budget)
*
* Each CPU has its own Rx/Tx cause register
*/
- cause_rx_tx = mvpp2_read(port->priv,
- MVPP2_ISR_RX_TX_CAUSE_REG(port->id));
+ cause_rx_tx = mvpp2_percpu_read(port->priv, cpu,
+ MVPP2_ISR_RX_TX_CAUSE_REG(port->id));
cause_rx_tx &= ~MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK;
cause_misc = cause_rx_tx & MVPP2_CAUSE_MISC_SUM_MASK;
@@ -5417,8 +5783,9 @@ static int mvpp2_poll(struct napi_struct *napi, int budget)
/* Clear the cause register */
mvpp2_write(port->priv, MVPP2_ISR_MISC_CAUSE_REG, 0);
- mvpp2_write(port->priv, MVPP2_ISR_RX_TX_CAUSE_REG(port->id),
- cause_rx_tx & ~MVPP2_CAUSE_MISC_SUM_MASK);
+ mvpp2_percpu_write(port->priv, cpu,
+ MVPP2_ISR_RX_TX_CAUSE_REG(port->id),
+ cause_rx_tx & ~MVPP2_CAUSE_MISC_SUM_MASK);
}
cause_rx = cause_rx_tx & MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK;
@@ -5530,7 +5897,7 @@ static int mvpp2_check_ringparam_valid(struct net_device *dev,
return 0;
}
-static void mvpp2_get_mac_address(struct mvpp2_port *port, unsigned char *addr)
+static void mvpp21_get_mac_address(struct mvpp2_port *port, unsigned char *addr)
{
u32 mac_addr_l, mac_addr_m, mac_addr_h;
@@ -5975,16 +6342,6 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = {
.set_link_ksettings = phy_ethtool_set_link_ksettings,
};
-/* Driver initialization */
-
-static void mvpp2_port_power_up(struct mvpp2_port *port)
-{
- mvpp2_port_mii_set(port);
- mvpp2_port_periodic_xon_disable(port);
- mvpp2_port_fc_adv_enable(port);
- mvpp2_port_reset(port);
-}
-
/* Initialize port HW */
static int mvpp2_port_init(struct mvpp2_port *port)
{
@@ -5993,7 +6350,8 @@ static int mvpp2_port_init(struct mvpp2_port *port)
struct mvpp2_txq_pcpu *txq_pcpu;
int queue, cpu, err;
- if (port->first_rxq + rxq_number > MVPP2_RXQ_TOTAL_NUM)
+ if (port->first_rxq + rxq_number >
+ MVPP2_MAX_PORTS * priv->max_port_rxqs)
return -EINVAL;
/* Disable port */
@@ -6061,7 +6419,18 @@ static int mvpp2_port_init(struct mvpp2_port *port)
}
/* Configure Rx queue group interrupt for this port */
- mvpp2_write(priv, MVPP2_ISR_RXQ_GROUP_REG(port->id), rxq_number);
+ if (priv->hw_version == MVPP21) {
+ mvpp2_write(priv, MVPP21_ISR_RXQ_GROUP_REG(port->id),
+ rxq_number);
+ } else {
+ u32 val;
+
+ val = (port->id << MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_OFFSET);
+ mvpp2_write(priv, MVPP22_ISR_RXQ_GROUP_INDEX_REG, val);
+
+ val = (rxq_number << MVPP22_ISR_RXQ_SUB_GROUP_SIZE_OFFSET);
+ mvpp2_write(priv, MVPP22_ISR_RXQ_SUB_GROUP_CONFIG_REG, val);
+ }
/* Create Rx descriptor rings */
for (queue = 0; queue < rxq_number; queue++) {
@@ -6103,8 +6472,7 @@ static int mvpp2_port_init(struct mvpp2_port *port)
/* Ports initialization */
static int mvpp2_port_probe(struct platform_device *pdev,
struct device_node *port_node,
- struct mvpp2 *priv,
- int *next_first_rxq)
+ struct mvpp2 *priv)
{
struct device_node *phy_node;
struct mvpp2_port *port;
@@ -6117,7 +6485,6 @@ static int mvpp2_port_probe(struct platform_device *pdev,
u32 id;
int features;
int phy_mode;
- int priv_common_regs_num = 2;
int err, i, cpu;
dev = alloc_etherdev_mqs(sizeof(struct mvpp2_port), txq_number,
@@ -6163,16 +6530,30 @@ static int mvpp2_port_probe(struct platform_device *pdev,
port->priv = priv;
port->id = id;
- port->first_rxq = *next_first_rxq;
+ if (priv->hw_version == MVPP21)
+ port->first_rxq = port->id * rxq_number;
+ else
+ port->first_rxq = port->id * priv->max_port_rxqs;
+
port->phy_node = phy_node;
port->phy_interface = phy_mode;
- res = platform_get_resource(pdev, IORESOURCE_MEM,
- priv_common_regs_num + id);
- port->base = devm_ioremap_resource(&pdev->dev, res);
- if (IS_ERR(port->base)) {
- err = PTR_ERR(port->base);
- goto err_free_irq;
+ if (priv->hw_version == MVPP21) {
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 2 + id);
+ port->base = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(port->base)) {
+ err = PTR_ERR(port->base);
+ goto err_free_irq;
+ }
+ } else {
+ if (of_property_read_u32(port_node, "gop-port-id",
+ &port->gop_id)) {
+ err = -EINVAL;
+ dev_err(&pdev->dev, "missing gop-port-id value\n");
+ goto err_free_irq;
+ }
+
+ port->base = priv->iface_base + MVPP22_GMAC_BASE(port->gop_id);
}
/* Alloc per-cpu stats */
@@ -6187,7 +6568,8 @@ static int mvpp2_port_probe(struct platform_device *pdev,
mac_from = "device tree";
ether_addr_copy(dev->dev_addr, dt_mac_addr);
} else {
- mvpp2_get_mac_address(port, hw_mac_addr);
+ if (priv->hw_version == MVPP21)
+ mvpp21_get_mac_address(port, hw_mac_addr);
if (is_valid_ether_addr(hw_mac_addr)) {
mac_from = "hardware";
ether_addr_copy(dev->dev_addr, hw_mac_addr);
@@ -6207,7 +6589,14 @@ static int mvpp2_port_probe(struct platform_device *pdev,
dev_err(&pdev->dev, "failed to init port %d\n", id);
goto err_free_stats;
}
- mvpp2_port_power_up(port);
+
+ mvpp2_port_mii_set(port);
+ mvpp2_port_periodic_xon_disable(port);
+
+ if (priv->hw_version == MVPP21)
+ mvpp2_port_fc_adv_enable(port);
+
+ mvpp2_port_reset(port);
port->pcpu = alloc_percpu(struct mvpp2_port_pcpu);
if (!port->pcpu) {
@@ -6245,8 +6634,6 @@ static int mvpp2_port_probe(struct platform_device *pdev,
}
netdev_info(dev, "Using %s mac address %pM\n", mac_from, dev->dev_addr);
- /* Increment the first Rx queue number to be used by the next port */
- *next_first_rxq += rxq_number;
priv->port_list[id] = port;
return 0;
@@ -6330,6 +6717,60 @@ static void mvpp2_rx_fifo_init(struct mvpp2 *priv)
mvpp2_write(priv, MVPP2_RX_FIFO_INIT_REG, 0x1);
}
+static void mvpp2_axi_init(struct mvpp2 *priv)
+{
+ u32 val, rdval, wrval;
+
+ mvpp2_write(priv, MVPP22_BM_ADDR_HIGH_RLS_REG, 0x0);
+
+ /* AXI Bridge Configuration */
+
+ rdval = MVPP22_AXI_CODE_CACHE_RD_CACHE
+ << MVPP22_AXI_ATTR_CACHE_OFFS;
+ rdval |= MVPP22_AXI_CODE_DOMAIN_OUTER_DOM
+ << MVPP22_AXI_ATTR_DOMAIN_OFFS;
+
+ wrval = MVPP22_AXI_CODE_CACHE_WR_CACHE
+ << MVPP22_AXI_ATTR_CACHE_OFFS;
+ wrval |= MVPP22_AXI_CODE_DOMAIN_OUTER_DOM
+ << MVPP22_AXI_ATTR_DOMAIN_OFFS;
+
+ /* BM */
+ mvpp2_write(priv, MVPP22_AXI_BM_WR_ATTR_REG, wrval);
+ mvpp2_write(priv, MVPP22_AXI_BM_RD_ATTR_REG, rdval);
+
+ /* Descriptors */
+ mvpp2_write(priv, MVPP22_AXI_AGGRQ_DESCR_RD_ATTR_REG, rdval);
+ mvpp2_write(priv, MVPP22_AXI_TXQ_DESCR_WR_ATTR_REG, wrval);
+ mvpp2_write(priv, MVPP22_AXI_TXQ_DESCR_RD_ATTR_REG, rdval);
+ mvpp2_write(priv, MVPP22_AXI_RXQ_DESCR_WR_ATTR_REG, wrval);
+
+ /* Buffer Data */
+ mvpp2_write(priv, MVPP22_AXI_TX_DATA_RD_ATTR_REG, rdval);
+ mvpp2_write(priv, MVPP22_AXI_RX_DATA_WR_ATTR_REG, wrval);
+
+ val = MVPP22_AXI_CODE_CACHE_NON_CACHE
+ << MVPP22_AXI_CODE_CACHE_OFFS;
+ val |= MVPP22_AXI_CODE_DOMAIN_SYSTEM
+ << MVPP22_AXI_CODE_DOMAIN_OFFS;
+ mvpp2_write(priv, MVPP22_AXI_RD_NORMAL_CODE_REG, val);
+ mvpp2_write(priv, MVPP22_AXI_WR_NORMAL_CODE_REG, val);
+
+ val = MVPP22_AXI_CODE_CACHE_RD_CACHE
+ << MVPP22_AXI_CODE_CACHE_OFFS;
+ val |= MVPP22_AXI_CODE_DOMAIN_OUTER_DOM
+ << MVPP22_AXI_CODE_DOMAIN_OFFS;
+
+ mvpp2_write(priv, MVPP22_AXI_RD_SNOOP_CODE_REG, val);
+
+ val = MVPP22_AXI_CODE_CACHE_WR_CACHE
+ << MVPP22_AXI_CODE_CACHE_OFFS;
+ val |= MVPP22_AXI_CODE_DOMAIN_OUTER_DOM
+ << MVPP22_AXI_CODE_DOMAIN_OFFS;
+
+ mvpp2_write(priv, MVPP22_AXI_WR_SNOOP_CODE_REG, val);
+}
+
/* Initialize network controller common part HW */
static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv)
{
@@ -6338,7 +6779,7 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv)
u32 val;
/* Checks for hardware constraints */
- if (rxq_number % 4 || (rxq_number > MVPP2_MAX_RXQ) ||
+ if (rxq_number % 4 || (rxq_number > priv->max_port_rxqs) ||
(txq_number > MVPP2_MAX_TXQ)) {
dev_err(&pdev->dev, "invalid queue size parameter\n");
return -EINVAL;
@@ -6349,10 +6790,19 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv)
if (dram_target_info)
mvpp2_conf_mbus_windows(dram_target_info, priv);
+ if (priv->hw_version == MVPP22)
+ mvpp2_axi_init(priv);
+
/* Disable HW PHY polling */
- val = readl(priv->lms_base + MVPP2_PHY_AN_CFG0_REG);
- val |= MVPP2_PHY_AN_STOP_SMI0_MASK;
- writel(val, priv->lms_base + MVPP2_PHY_AN_CFG0_REG);
+ if (priv->hw_version == MVPP21) {
+ val = readl(priv->lms_base + MVPP2_PHY_AN_CFG0_REG);
+ val |= MVPP2_PHY_AN_STOP_SMI0_MASK;
+ writel(val, priv->lms_base + MVPP2_PHY_AN_CFG0_REG);
+ } else {
+ val = readl(priv->iface_base + MVPP22_SMI_MISC_CFG_REG);
+ val &= ~MVPP22_SMI_POLLING_EN;
+ writel(val, priv->iface_base + MVPP22_SMI_MISC_CFG_REG);
+ }
/* Allocate and initialize aggregated TXQs */
priv->aggr_txqs = devm_kcalloc(&pdev->dev, num_present_cpus(),
@@ -6374,11 +6824,25 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv)
mvpp2_rx_fifo_init(priv);
/* Reset Rx queue group interrupt configuration */
- for (i = 0; i < MVPP2_MAX_PORTS; i++)
- mvpp2_write(priv, MVPP2_ISR_RXQ_GROUP_REG(i), rxq_number);
+ for (i = 0; i < MVPP2_MAX_PORTS; i++) {
+ if (priv->hw_version == MVPP21) {
+ mvpp2_write(priv, MVPP21_ISR_RXQ_GROUP_REG(i),
+ rxq_number);
+ continue;
+ } else {
+ u32 val;
- writel(MVPP2_EXT_GLOBAL_CTRL_DEFAULT,
- priv->lms_base + MVPP2_MNG_EXTENDED_GLOBAL_CTRL_REG);
+ val = (i << MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_OFFSET);
+ mvpp2_write(priv, MVPP22_ISR_RXQ_GROUP_INDEX_REG, val);
+
+ val = (rxq_number << MVPP22_ISR_RXQ_SUB_GROUP_SIZE_OFFSET);
+ mvpp2_write(priv, MVPP22_ISR_RXQ_SUB_GROUP_CONFIG_REG, val);
+ }
+ }
+
+ if (priv->hw_version == MVPP21)
+ writel(MVPP2_EXT_GLOBAL_CTRL_DEFAULT,
+ priv->lms_base + MVPP2_MNG_EXTENDED_GLOBAL_CTRL_REG);
/* Allow cache snoop when transmiting packets */
mvpp2_write(priv, MVPP2_TX_SNOOP_REG, 0x1);
@@ -6405,22 +6869,46 @@ static int mvpp2_probe(struct platform_device *pdev)
struct device_node *port_node;
struct mvpp2 *priv;
struct resource *res;
- int port_count, first_rxq;
+ void __iomem *base;
+ int port_count, cpu;
int err;
priv = devm_kzalloc(&pdev->dev, sizeof(struct mvpp2), GFP_KERNEL);
if (!priv)
return -ENOMEM;
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- priv->base = devm_ioremap_resource(&pdev->dev, res);
- if (IS_ERR(priv->base))
- return PTR_ERR(priv->base);
+ priv->hw_version =
+ (unsigned long)of_device_get_match_data(&pdev->dev);
- res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
- priv->lms_base = devm_ioremap_resource(&pdev->dev, res);
- if (IS_ERR(priv->lms_base))
- return PTR_ERR(priv->lms_base);
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ base = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(base))
+ return PTR_ERR(base);
+
+ if (priv->hw_version == MVPP21) {
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+ priv->lms_base = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(priv->lms_base))
+ return PTR_ERR(priv->lms_base);
+ } else {
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+ priv->iface_base = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(priv->iface_base))
+ return PTR_ERR(priv->iface_base);
+ }
+
+ for_each_present_cpu(cpu) {
+ u32 addr_space_sz;
+
+ addr_space_sz = (priv->hw_version == MVPP21 ?
+ MVPP21_ADDR_SPACE_SZ : MVPP22_ADDR_SPACE_SZ);
+ priv->cpu_base[cpu] = base + cpu * addr_space_sz;
+ }
+
+ if (priv->hw_version == MVPP21)
+ priv->max_port_rxqs = 8;
+ else
+ priv->max_port_rxqs = 32;
priv->pp_clk = devm_clk_get(&pdev->dev, "pp_clk");
if (IS_ERR(priv->pp_clk))
@@ -6438,21 +6926,47 @@ static int mvpp2_probe(struct platform_device *pdev)
if (err < 0)
goto err_pp_clk;
+ if (priv->hw_version == MVPP22) {
+ priv->mg_clk = devm_clk_get(&pdev->dev, "mg_clk");
+ if (IS_ERR(priv->mg_clk)) {
+ err = PTR_ERR(priv->mg_clk);
+ goto err_gop_clk;
+ }
+
+ err = clk_prepare_enable(priv->mg_clk);
+ if (err < 0)
+ goto err_gop_clk;
+ }
+
/* Get system's tclk rate */
priv->tclk = clk_get_rate(priv->pp_clk);
+ if (priv->hw_version == MVPP22) {
+ err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(40));
+ if (err)
+ goto err_mg_clk;
+ /* Sadly, the BM pools all share the same register to
+ * store the high 32 bits of their address. So they
+ * must all have the same high 32 bits, which forces
+ * us to restrict coherent memory to DMA_BIT_MASK(32).
+ */
+ err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
+ if (err)
+ goto err_mg_clk;
+ }
+
/* Initialize network controller */
err = mvpp2_init(pdev, priv);
if (err < 0) {
dev_err(&pdev->dev, "failed to initialize controller\n");
- goto err_gop_clk;
+ goto err_mg_clk;
}
port_count = of_get_available_child_count(dn);
if (port_count == 0) {
dev_err(&pdev->dev, "no ports enabled\n");
err = -ENODEV;
- goto err_gop_clk;
+ goto err_mg_clk;
}
priv->port_list = devm_kcalloc(&pdev->dev, port_count,
@@ -6460,20 +6974,22 @@ static int mvpp2_probe(struct platform_device *pdev)
GFP_KERNEL);
if (!priv->port_list) {
err = -ENOMEM;
- goto err_gop_clk;
+ goto err_mg_clk;
}
/* Initialize ports */
- first_rxq = 0;
for_each_available_child_of_node(dn, port_node) {
- err = mvpp2_port_probe(pdev, port_node, priv, &first_rxq);
+ err = mvpp2_port_probe(pdev, port_node, priv);
if (err < 0)
- goto err_gop_clk;
+ goto err_mg_clk;
}
platform_set_drvdata(pdev, priv);
return 0;
+err_mg_clk:
+ if (priv->hw_version == MVPP22)
+ clk_disable_unprepare(priv->mg_clk);
err_gop_clk:
clk_disable_unprepare(priv->gop_clk);
err_pp_clk:
@@ -6506,9 +7022,10 @@ static int mvpp2_remove(struct platform_device *pdev)
dma_free_coherent(&pdev->dev,
MVPP2_AGGR_TXQ_SIZE * MVPP2_DESC_ALIGNED_SIZE,
aggr_txq->descs,
- aggr_txq->descs_phys);
+ aggr_txq->descs_dma);
}
+ clk_disable_unprepare(priv->mg_clk);
clk_disable_unprepare(priv->pp_clk);
clk_disable_unprepare(priv->gop_clk);
@@ -6516,7 +7033,14 @@ static int mvpp2_remove(struct platform_device *pdev)
}
static const struct of_device_id mvpp2_match[] = {
- { .compatible = "marvell,armada-375-pp2" },
+ {
+ .compatible = "marvell,armada-375-pp2",
+ .data = (void *)MVPP21,
+ },
+ {
+ .compatible = "marvell,armada-7k-pp22",
+ .data = (void *)MVPP22,
+ },
{ }
};
MODULE_DEVICE_TABLE(of, mvpp2_match);
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 9e75768..d81d3b6 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -1846,6 +1846,12 @@ static int mtk_hw_init(struct mtk_eth *eth)
/* GE2, Force 1000M/FD, FC ON */
mtk_w32(eth, MAC_MCR_FIXED_LINK, MTK_MAC_MCR(1));
+ /* Indicates CDM to parse the MTK special tag from CPU
+ * which also is working out for untag packets.
+ */
+ val = mtk_r32(eth, MTK_CDMQ_IG_CTRL);
+ mtk_w32(eth, val | MTK_CDMQ_STAG_EN, MTK_CDMQ_IG_CTRL);
+
/* Enable RX VLan Offloading */
mtk_w32(eth, 1, MTK_CDMP_EG_CTRL);
@@ -1908,10 +1914,9 @@ static int __init mtk_init(struct net_device *dev)
/* If the mac address is invalid, use random mac address */
if (!is_valid_ether_addr(dev->dev_addr)) {
- random_ether_addr(dev->dev_addr);
+ eth_hw_addr_random(dev);
dev_err(eth->dev, "generated random MAC address %pM\n",
dev->dev_addr);
- dev->addr_assign_type = NET_ADDR_RANDOM;
}
return mtk_phy_connect(dev);
@@ -2317,6 +2322,8 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
eth->netdev[id]->ethtool_ops = &mtk_ethtool_ops;
eth->netdev[id]->irq = eth->irq[0];
+ eth->netdev[id]->dev.of_node = np;
+
return 0;
free_netdev:
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 99b1c8e..996024d 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -70,6 +70,10 @@
/* Frame Engine Interrupt Grouping Register */
#define MTK_FE_INT_GRP 0x20
+/* CDMP Ingress Control Register */
+#define MTK_CDMQ_IG_CTRL 0x1400
+#define MTK_CDMQ_STAG_EN BIT(0)
+
/* CDMP Exgress Control Register */
#define MTK_CDMP_EG_CTRL 0x404
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index e8c1051..0e0fa70 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2305,6 +2305,17 @@ static int sync_toggles(struct mlx4_dev *dev)
rd_toggle = swab32(readl(&priv->mfunc.comm->slave_read));
if (wr_toggle == 0xffffffff || rd_toggle == 0xffffffff) {
/* PCI might be offline */
+
+ /* If device removal has been requested,
+ * do not continue retrying.
+ */
+ if (dev->persist->interface_state &
+ MLX4_INTERFACE_STATE_NOWAIT) {
+ mlx4_warn(dev,
+ "communication channel is offline\n");
+ return -EIO;
+ }
+
msleep(100);
wr_toggle = swab32(readl(&priv->mfunc.comm->
slave_write));
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index c4d714f..ffbcb27 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -117,7 +117,7 @@ static const char main_strings[][ETH_GSTRING_LEN] = {
/* port statistics */
"tso_packets",
"xmit_more",
- "queue_stopped", "wake_queue", "tx_timeout", "rx_alloc_failed",
+ "queue_stopped", "wake_queue", "tx_timeout", "rx_alloc_pages",
"rx_csum_good", "rx_csum_none", "rx_csum_complete", "tx_chksum_offload",
/* pf statistics */
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 6142047..94fab20 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -92,7 +92,9 @@ static int __mlx4_en_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
if (tc->type != TC_SETUP_MQPRIO)
return -EINVAL;
- return mlx4_en_setup_tc(dev, tc->tc);
+ tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+ return mlx4_en_setup_tc(dev, tc->mqprio->num_tc);
}
#ifdef CONFIG_RFS_ACCEL
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index 9166d90..e0eb695 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -213,6 +213,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
priv->port_stats.rx_chksum_good = 0;
priv->port_stats.rx_chksum_none = 0;
priv->port_stats.rx_chksum_complete = 0;
+ priv->port_stats.rx_alloc_pages = 0;
priv->xdp_stats.rx_xdp_drop = 0;
priv->xdp_stats.rx_xdp_tx = 0;
priv->xdp_stats.rx_xdp_tx_full = 0;
@@ -223,6 +224,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
priv->port_stats.rx_chksum_good += READ_ONCE(ring->csum_ok);
priv->port_stats.rx_chksum_none += READ_ONCE(ring->csum_none);
priv->port_stats.rx_chksum_complete += READ_ONCE(ring->csum_complete);
+ priv->port_stats.rx_alloc_pages += READ_ONCE(ring->rx_alloc_pages);
priv->xdp_stats.rx_xdp_drop += READ_ONCE(ring->xdp_drop);
priv->xdp_stats.rx_xdp_tx += READ_ONCE(ring->xdp_tx);
priv->xdp_stats.rx_xdp_tx_full += READ_ONCE(ring->xdp_tx_full);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 8672928..aa074e5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -50,173 +50,62 @@
#include "mlx4_en.h"
-static int mlx4_alloc_pages(struct mlx4_en_priv *priv,
- struct mlx4_en_rx_alloc *page_alloc,
- const struct mlx4_en_frag_info *frag_info,
- gfp_t _gfp)
+static int mlx4_alloc_page(struct mlx4_en_priv *priv,
+ struct mlx4_en_rx_alloc *frag,
+ gfp_t gfp)
{
- int order;
struct page *page;
dma_addr_t dma;
- for (order = frag_info->order; ;) {
- gfp_t gfp = _gfp;
-
- if (order)
- gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NOMEMALLOC;
- page = alloc_pages(gfp, order);
- if (likely(page))
- break;
- if (--order < 0 ||
- ((PAGE_SIZE << order) < frag_info->frag_size))
- return -ENOMEM;
- }
- dma = dma_map_page(priv->ddev, page, 0, PAGE_SIZE << order,
- frag_info->dma_dir);
+ page = alloc_page(gfp);
+ if (unlikely(!page))
+ return -ENOMEM;
+ dma = dma_map_page(priv->ddev, page, 0, PAGE_SIZE, priv->dma_dir);
if (unlikely(dma_mapping_error(priv->ddev, dma))) {
- put_page(page);
+ __free_page(page);
return -ENOMEM;
}
- page_alloc->page_size = PAGE_SIZE << order;
- page_alloc->page = page;
- page_alloc->dma = dma;
- page_alloc->page_offset = 0;
- /* Not doing get_page() for each frag is a big win
- * on asymetric workloads. Note we can not use atomic_set().
- */
- page_ref_add(page, page_alloc->page_size / frag_info->frag_stride - 1);
+ frag->page = page;
+ frag->dma = dma;
+ frag->page_offset = priv->rx_headroom;
return 0;
}
static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv,
+ struct mlx4_en_rx_ring *ring,
struct mlx4_en_rx_desc *rx_desc,
struct mlx4_en_rx_alloc *frags,
- struct mlx4_en_rx_alloc *ring_alloc,
gfp_t gfp)
{
- struct mlx4_en_rx_alloc page_alloc[MLX4_EN_MAX_RX_FRAGS];
- const struct mlx4_en_frag_info *frag_info;
- struct page *page;
int i;
- for (i = 0; i < priv->num_frags; i++) {
- frag_info = &priv->frag_info[i];
- page_alloc[i] = ring_alloc[i];
- page_alloc[i].page_offset += frag_info->frag_stride;
-
- if (page_alloc[i].page_offset + frag_info->frag_stride <=
- ring_alloc[i].page_size)
- continue;
-
- if (unlikely(mlx4_alloc_pages(priv, &page_alloc[i],
- frag_info, gfp)))
- goto out;
- }
-
- for (i = 0; i < priv->num_frags; i++) {
- frags[i] = ring_alloc[i];
- frags[i].page_offset += priv->frag_info[i].rx_headroom;
- rx_desc->data[i].addr = cpu_to_be64(frags[i].dma +
- frags[i].page_offset);
- ring_alloc[i] = page_alloc[i];
- }
-
- return 0;
-
-out:
- while (i--) {
- if (page_alloc[i].page != ring_alloc[i].page) {
- dma_unmap_page(priv->ddev, page_alloc[i].dma,
- page_alloc[i].page_size,
- priv->frag_info[i].dma_dir);
- page = page_alloc[i].page;
- /* Revert changes done by mlx4_alloc_pages */
- page_ref_sub(page, page_alloc[i].page_size /
- priv->frag_info[i].frag_stride - 1);
- put_page(page);
+ for (i = 0; i < priv->num_frags; i++, frags++) {
+ if (!frags->page) {
+ if (mlx4_alloc_page(priv, frags, gfp))
+ return -ENOMEM;
+ ring->rx_alloc_pages++;
}
- }
- return -ENOMEM;
-}
-
-static void mlx4_en_free_frag(struct mlx4_en_priv *priv,
- struct mlx4_en_rx_alloc *frags,
- int i)
-{
- const struct mlx4_en_frag_info *frag_info = &priv->frag_info[i];
- u32 next_frag_end = frags[i].page_offset + 2 * frag_info->frag_stride;
-
-
- if (next_frag_end > frags[i].page_size)
- dma_unmap_page(priv->ddev, frags[i].dma, frags[i].page_size,
- frag_info->dma_dir);
-
- if (frags[i].page)
- put_page(frags[i].page);
-}
-
-static int mlx4_en_init_allocator(struct mlx4_en_priv *priv,
- struct mlx4_en_rx_ring *ring)
-{
- int i;
- struct mlx4_en_rx_alloc *page_alloc;
-
- for (i = 0; i < priv->num_frags; i++) {
- const struct mlx4_en_frag_info *frag_info = &priv->frag_info[i];
-
- if (mlx4_alloc_pages(priv, &ring->page_alloc[i],
- frag_info, GFP_KERNEL | __GFP_COLD))
- goto out;
-
- en_dbg(DRV, priv, " frag %d allocator: - size:%d frags:%d\n",
- i, ring->page_alloc[i].page_size,
- page_ref_count(ring->page_alloc[i].page));
+ rx_desc->data[i].addr = cpu_to_be64(frags->dma +
+ frags->page_offset);
}
return 0;
-
-out:
- while (i--) {
- struct page *page;
-
- page_alloc = &ring->page_alloc[i];
- dma_unmap_page(priv->ddev, page_alloc->dma,
- page_alloc->page_size,
- priv->frag_info[i].dma_dir);
- page = page_alloc->page;
- /* Revert changes done by mlx4_alloc_pages */
- page_ref_sub(page, page_alloc->page_size /
- priv->frag_info[i].frag_stride - 1);
- put_page(page);
- page_alloc->page = NULL;
- }
- return -ENOMEM;
}
-static void mlx4_en_destroy_allocator(struct mlx4_en_priv *priv,
- struct mlx4_en_rx_ring *ring)
+static void mlx4_en_free_frag(const struct mlx4_en_priv *priv,
+ struct mlx4_en_rx_alloc *frag)
{
- struct mlx4_en_rx_alloc *page_alloc;
- int i;
-
- for (i = 0; i < priv->num_frags; i++) {
- const struct mlx4_en_frag_info *frag_info = &priv->frag_info[i];
-
- page_alloc = &ring->page_alloc[i];
- en_dbg(DRV, priv, "Freeing allocator:%d count:%d\n",
- i, page_count(page_alloc->page));
-
- dma_unmap_page(priv->ddev, page_alloc->dma,
- page_alloc->page_size, frag_info->dma_dir);
- while (page_alloc->page_offset + frag_info->frag_stride <
- page_alloc->page_size) {
- put_page(page_alloc->page);
- page_alloc->page_offset += frag_info->frag_stride;
- }
- page_alloc->page = NULL;
+ if (frag->page) {
+ dma_unmap_page(priv->ddev, frag->dma,
+ PAGE_SIZE, priv->dma_dir);
+ __free_page(frag->page);
}
+ /* We need to clear all fields, otherwise a change of priv->log_rx_info
+ * could lead to see garbage later in frag->page.
+ */
+ memset(frag, 0, sizeof(*frag));
}
-static void mlx4_en_init_rx_desc(struct mlx4_en_priv *priv,
+static void mlx4_en_init_rx_desc(const struct mlx4_en_priv *priv,
struct mlx4_en_rx_ring *ring, int index)
{
struct mlx4_en_rx_desc *rx_desc = ring->buf + ring->stride * index;
@@ -248,18 +137,23 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv,
struct mlx4_en_rx_desc *rx_desc = ring->buf + (index * ring->stride);
struct mlx4_en_rx_alloc *frags = ring->rx_info +
(index << priv->log_rx_info);
-
if (ring->page_cache.index > 0) {
- frags[0] = ring->page_cache.buf[--ring->page_cache.index];
- rx_desc->data[0].addr = cpu_to_be64(frags[0].dma +
- frags[0].page_offset);
+ /* XDP uses a single page per frame */
+ if (!frags->page) {
+ ring->page_cache.index--;
+ frags->page = ring->page_cache.buf[ring->page_cache.index].page;
+ frags->dma = ring->page_cache.buf[ring->page_cache.index].dma;
+ }
+ frags->page_offset = XDP_PACKET_HEADROOM;
+ rx_desc->data[0].addr = cpu_to_be64(frags->dma +
+ XDP_PACKET_HEADROOM);
return 0;
}
- return mlx4_en_alloc_frags(priv, rx_desc, frags, ring->page_alloc, gfp);
+ return mlx4_en_alloc_frags(priv, ring, rx_desc, frags, gfp);
}
-static inline bool mlx4_en_is_ring_empty(struct mlx4_en_rx_ring *ring)
+static bool mlx4_en_is_ring_empty(const struct mlx4_en_rx_ring *ring)
{
return ring->prod == ring->cons;
}
@@ -269,7 +163,8 @@ static inline void mlx4_en_update_rx_prod_db(struct mlx4_en_rx_ring *ring)
*ring->wqres.db.db = cpu_to_be32(ring->prod & 0xffff);
}
-static void mlx4_en_free_rx_desc(struct mlx4_en_priv *priv,
+/* slow path */
+static void mlx4_en_free_rx_desc(const struct mlx4_en_priv *priv,
struct mlx4_en_rx_ring *ring,
int index)
{
@@ -279,7 +174,7 @@ static void mlx4_en_free_rx_desc(struct mlx4_en_priv *priv,
frags = ring->rx_info + (index << priv->log_rx_info);
for (nr = 0; nr < priv->num_frags; nr++) {
en_dbg(DRV, priv, "Freeing fragment:%d\n", nr);
- mlx4_en_free_frag(priv, frags, nr);
+ mlx4_en_free_frag(priv, frags + nr);
}
}
@@ -335,12 +230,12 @@ static void mlx4_en_free_rx_buf(struct mlx4_en_priv *priv,
ring->cons, ring->prod);
/* Unmap and free Rx buffers */
- while (!mlx4_en_is_ring_empty(ring)) {
- index = ring->cons & ring->size_mask;
+ for (index = 0; index < ring->size; index++) {
en_dbg(DRV, priv, "Processing descriptor:%d\n", index);
mlx4_en_free_rx_desc(priv, ring, index);
- ++ring->cons;
}
+ ring->cons = 0;
+ ring->prod = 0;
}
void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev)
@@ -392,9 +287,9 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
tmp = size * roundup_pow_of_two(MLX4_EN_MAX_RX_FRAGS *
sizeof(struct mlx4_en_rx_alloc));
- ring->rx_info = vmalloc_node(tmp, node);
+ ring->rx_info = vzalloc_node(tmp, node);
if (!ring->rx_info) {
- ring->rx_info = vmalloc(tmp);
+ ring->rx_info = vzalloc(tmp);
if (!ring->rx_info) {
err = -ENOMEM;
goto err_ring;
@@ -464,16 +359,6 @@ int mlx4_en_activate_rx_rings(struct mlx4_en_priv *priv)
/* Initialize all descriptors */
for (i = 0; i < ring->size; i++)
mlx4_en_init_rx_desc(priv, ring, i);
-
- /* Initialize page allocators */
- err = mlx4_en_init_allocator(priv, ring);
- if (err) {
- en_err(priv, "Failed initializing ring allocator\n");
- if (ring->stride <= TXBB_SIZE)
- ring->buf -= TXBB_SIZE;
- ring_ind--;
- goto err_allocator;
- }
}
err = mlx4_en_fill_rx_buffers(priv);
if (err)
@@ -493,11 +378,9 @@ int mlx4_en_activate_rx_rings(struct mlx4_en_priv *priv)
mlx4_en_free_rx_buf(priv, priv->rx_ring[ring_ind]);
ring_ind = priv->rx_ring_num - 1;
-err_allocator:
while (ring_ind >= 0) {
if (priv->rx_ring[ring_ind]->stride <= TXBB_SIZE)
priv->rx_ring[ring_ind]->buf -= TXBB_SIZE;
- mlx4_en_destroy_allocator(priv, priv->rx_ring[ring_ind]);
ring_ind--;
}
return err;
@@ -537,7 +420,9 @@ bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring,
if (cache->index >= MLX4_EN_CACHE_SIZE)
return false;
- cache->buf[cache->index++] = *frame;
+ cache->buf[cache->index].page = frame->page;
+ cache->buf[cache->index].dma = frame->dma;
+ cache->index++;
return true;
}
@@ -567,136 +452,91 @@ void mlx4_en_deactivate_rx_ring(struct mlx4_en_priv *priv,
int i;
for (i = 0; i < ring->page_cache.index; i++) {
- struct mlx4_en_rx_alloc *frame = &ring->page_cache.buf[i];
-
- dma_unmap_page(priv->ddev, frame->dma, frame->page_size,
- priv->frag_info[0].dma_dir);
- put_page(frame->page);
+ dma_unmap_page(priv->ddev, ring->page_cache.buf[i].dma,
+ PAGE_SIZE, priv->dma_dir);
+ put_page(ring->page_cache.buf[i].page);
}
ring->page_cache.index = 0;
mlx4_en_free_rx_buf(priv, ring);
if (ring->stride <= TXBB_SIZE)
ring->buf -= TXBB_SIZE;
- mlx4_en_destroy_allocator(priv, ring);
}
static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
- struct mlx4_en_rx_desc *rx_desc,
struct mlx4_en_rx_alloc *frags,
struct sk_buff *skb,
int length)
{
- struct skb_frag_struct *skb_frags_rx = skb_shinfo(skb)->frags;
- struct mlx4_en_frag_info *frag_info;
- int nr;
+ const struct mlx4_en_frag_info *frag_info = priv->frag_info;
+ unsigned int truesize = 0;
+ int nr, frag_size;
+ struct page *page;
dma_addr_t dma;
+ bool release;
/* Collect used fragments while replacing them in the HW descriptors */
- for (nr = 0; nr < priv->num_frags; nr++) {
- frag_info = &priv->frag_info[nr];
- if (length <= frag_info->frag_prefix_size)
- break;
- if (unlikely(!frags[nr].page))
+ for (nr = 0;; frags++) {
+ frag_size = min_t(int, length, frag_info->frag_size);
+
+ page = frags->page;
+ if (unlikely(!page))
goto fail;
- dma = be64_to_cpu(rx_desc->data[nr].addr);
- dma_sync_single_for_cpu(priv->ddev, dma, frag_info->frag_size,
- DMA_FROM_DEVICE);
+ dma = frags->dma;
+ dma_sync_single_range_for_cpu(priv->ddev, dma, frags->page_offset,
+ frag_size, priv->dma_dir);
- __skb_fill_page_desc(skb, nr, frags[nr].page,
- frags[nr].page_offset,
- frag_info->frag_size);
+ __skb_fill_page_desc(skb, nr, page, frags->page_offset,
+ frag_size);
- skb->truesize += frag_info->frag_stride;
- frags[nr].page = NULL;
+ truesize += frag_info->frag_stride;
+ if (frag_info->frag_stride == PAGE_SIZE / 2) {
+ frags->page_offset ^= PAGE_SIZE / 2;
+ release = page_count(page) != 1 ||
+ page_is_pfmemalloc(page) ||
+ page_to_nid(page) != numa_mem_id();
+ } else {
+ u32 sz_align = ALIGN(frag_size, SMP_CACHE_BYTES);
+
+ frags->page_offset += sz_align;
+ release = frags->page_offset + frag_info->frag_size > PAGE_SIZE;
+ }
+ if (release) {
+ dma_unmap_page(priv->ddev, dma, PAGE_SIZE, priv->dma_dir);
+ frags->page = NULL;
+ } else {
+ page_ref_inc(page);
+ }
+
+ nr++;
+ length -= frag_size;
+ if (!length)
+ break;
+ frag_info++;
}
- /* Adjust size of last fragment to match actual length */
- if (nr > 0)
- skb_frag_size_set(&skb_frags_rx[nr - 1],
- length - priv->frag_info[nr - 1].frag_prefix_size);
+ skb->truesize += truesize;
return nr;
fail:
while (nr > 0) {
nr--;
- __skb_frag_unref(&skb_frags_rx[nr]);
+ __skb_frag_unref(skb_shinfo(skb)->frags + nr);
}
return 0;
}
-
-static struct sk_buff *mlx4_en_rx_skb(struct mlx4_en_priv *priv,
- struct mlx4_en_rx_desc *rx_desc,
- struct mlx4_en_rx_alloc *frags,
- unsigned int length)
+static void validate_loopback(struct mlx4_en_priv *priv, void *va)
{
- struct sk_buff *skb;
- void *va;
- int used_frags;
- dma_addr_t dma;
-
- skb = netdev_alloc_skb(priv->dev, SMALL_PACKET_SIZE + NET_IP_ALIGN);
- if (unlikely(!skb)) {
- en_dbg(RX_ERR, priv, "Failed allocating skb\n");
- return NULL;
- }
- skb_reserve(skb, NET_IP_ALIGN);
- skb->len = length;
-
- /* Get pointer to first fragment so we could copy the headers into the
- * (linear part of the) skb */
- va = page_address(frags[0].page) + frags[0].page_offset;
-
- if (length <= SMALL_PACKET_SIZE) {
- /* We are copying all relevant data to the skb - temporarily
- * sync buffers for the copy */
- dma = be64_to_cpu(rx_desc->data[0].addr);
- dma_sync_single_for_cpu(priv->ddev, dma, length,
- DMA_FROM_DEVICE);
- skb_copy_to_linear_data(skb, va, length);
- skb->tail += length;
- } else {
- unsigned int pull_len;
-
- /* Move relevant fragments to skb */
- used_frags = mlx4_en_complete_rx_desc(priv, rx_desc, frags,
- skb, length);
- if (unlikely(!used_frags)) {
- kfree_skb(skb);
- return NULL;
- }
- skb_shinfo(skb)->nr_frags = used_frags;
-
- pull_len = eth_get_headlen(va, SMALL_PACKET_SIZE);
- /* Copy headers into the skb linear buffer */
- memcpy(skb->data, va, pull_len);
- skb->tail += pull_len;
-
- /* Skip headers in first fragment */
- skb_shinfo(skb)->frags[0].page_offset += pull_len;
-
- /* Adjust size of first fragment */
- skb_frag_size_sub(&skb_shinfo(skb)->frags[0], pull_len);
- skb->data_len = length - pull_len;
- }
- return skb;
-}
-
-static void validate_loopback(struct mlx4_en_priv *priv, struct sk_buff *skb)
-{
+ const unsigned char *data = va + ETH_HLEN;
int i;
- int offset = ETH_HLEN;
- for (i = 0; i < MLX4_LOOPBACK_TEST_PAYLOAD; i++, offset++) {
- if (*(skb->data + offset) != (unsigned char) (i & 0xff))
- goto out_loopback;
+ for (i = 0; i < MLX4_LOOPBACK_TEST_PAYLOAD; i++) {
+ if (data[i] != (unsigned char)i)
+ return;
}
/* Loopback found */
priv->loopback_ok = 1;
-
-out_loopback:
- dev_kfree_skb_any(skb);
}
static bool mlx4_en_refill_rx_buffers(struct mlx4_en_priv *priv,
@@ -801,7 +641,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
struct mlx4_cqe *cqe;
struct mlx4_en_rx_ring *ring = priv->rx_ring[cq->ring];
struct mlx4_en_rx_alloc *frags;
- struct mlx4_en_rx_desc *rx_desc;
struct bpf_prog *xdp_prog;
int doorbell_pending;
struct sk_buff *skb;
@@ -834,10 +673,10 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
/* Process all completed CQEs */
while (XNOR(cqe->owner_sr_opcode & MLX4_CQE_OWNER_MASK,
cq->mcq.cons_index & cq->size)) {
+ void *va;
frags = ring->rx_info + (index << priv->log_rx_info);
- rx_desc = ring->buf + (index << ring->log_stride);
-
+ va = page_address(frags[0].page) + frags[0].page_offset;
/*
* make sure we read the CQE after we read the ownership bit
*/
@@ -860,16 +699,14 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
* and not performing the selftest or flb disabled
*/
if (priv->flags & MLX4_EN_FLAG_RX_FILTER_NEEDED) {
- struct ethhdr *ethh;
+ const struct ethhdr *ethh = va;
dma_addr_t dma;
/* Get pointer to first fragment since we haven't
* skb yet and cast it to ethhdr struct
*/
- dma = be64_to_cpu(rx_desc->data[0].addr);
+ dma = frags[0].dma + frags[0].page_offset;
dma_sync_single_for_cpu(priv->ddev, dma, sizeof(*ethh),
DMA_FROM_DEVICE);
- ethh = (struct ethhdr *)(page_address(frags[0].page) +
- frags[0].page_offset);
if (is_multicast_ether_addr(ethh->h_dest)) {
struct mlx4_mac_entry *entry;
@@ -887,13 +724,16 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
}
}
+ if (unlikely(priv->validate_loopback)) {
+ validate_loopback(priv, va);
+ goto next;
+ }
+
/*
* Packet is OK - process it.
*/
length = be32_to_cpu(cqe->byte_cnt);
length -= ring->fcs_del;
- l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) &&
- (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL));
/* A bpf program gets first chance to drop the packet. It may
* read bytes but not past the end of the frag.
@@ -904,13 +744,13 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
void *orig_data;
u32 act;
- dma = be64_to_cpu(rx_desc->data[0].addr);
+ dma = frags[0].dma + frags[0].page_offset;
dma_sync_single_for_cpu(priv->ddev, dma,
priv->frag_info[0].frag_size,
DMA_FROM_DEVICE);
- xdp.data_hard_start = page_address(frags[0].page);
- xdp.data = xdp.data_hard_start + frags[0].page_offset;
+ xdp.data_hard_start = va - frags[0].page_offset;
+ xdp.data = va;
xdp.data_end = xdp.data + length;
orig_data = xdp.data;
@@ -920,6 +760,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
length = xdp.data_end - xdp.data;
frags[0].page_offset = xdp.data -
xdp.data_hard_start;
+ va = xdp.data;
}
switch (act) {
@@ -928,8 +769,10 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
case XDP_TX:
if (likely(!mlx4_en_xmit_frame(ring, frags, dev,
length, cq->ring,
- &doorbell_pending)))
- goto consumed;
+ &doorbell_pending))) {
+ frags[0].page = NULL;
+ goto next;
+ }
trace_xdp_exception(dev, xdp_prog, act);
goto xdp_drop_no_cnt; /* Drop on xmit failure */
default:
@@ -939,8 +782,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
case XDP_DROP:
ring->xdp_drop++;
xdp_drop_no_cnt:
- if (likely(mlx4_en_rx_recycle(ring, frags)))
- goto consumed;
goto next;
}
}
@@ -948,129 +789,51 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
ring->bytes += length;
ring->packets++;
+ skb = napi_get_frags(&cq->napi);
+ if (!skb)
+ goto next;
+
+ if (unlikely(ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL)) {
+ timestamp = mlx4_en_get_cqe_ts(cqe);
+ mlx4_en_fill_hwtstamps(mdev, skb_hwtstamps(skb),
+ timestamp);
+ }
+ skb_record_rx_queue(skb, cq->ring);
+
if (likely(dev->features & NETIF_F_RXCSUM)) {
if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP |
MLX4_CQE_STATUS_UDP)) {
if ((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) &&
cqe->checksum == cpu_to_be16(0xffff)) {
ip_summed = CHECKSUM_UNNECESSARY;
+ l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) &&
+ (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL));
+ if (l2_tunnel)
+ skb->csum_level = 1;
ring->csum_ok++;
} else {
- ip_summed = CHECKSUM_NONE;
- ring->csum_none++;
+ goto csum_none;
}
} else {
if (priv->flags & MLX4_EN_FLAG_RX_CSUM_NON_TCP_UDP &&
(cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV4 |
MLX4_CQE_STATUS_IPV6))) {
- ip_summed = CHECKSUM_COMPLETE;
- ring->csum_complete++;
+ if (check_csum(cqe, skb, va, dev->features)) {
+ goto csum_none;
+ } else {
+ ip_summed = CHECKSUM_COMPLETE;
+ ring->csum_complete++;
+ }
} else {
- ip_summed = CHECKSUM_NONE;
- ring->csum_none++;
+ goto csum_none;
}
}
} else {
+csum_none:
ip_summed = CHECKSUM_NONE;
ring->csum_none++;
}
-
- /* This packet is eligible for GRO if it is:
- * - DIX Ethernet (type interpretation)
- * - TCP/IP (v4)
- * - without IP options
- * - not an IP fragment
- */
- if (dev->features & NETIF_F_GRO) {
- struct sk_buff *gro_skb = napi_get_frags(&cq->napi);
- if (!gro_skb)
- goto next;
-
- nr = mlx4_en_complete_rx_desc(priv,
- rx_desc, frags, gro_skb,
- length);
- if (!nr)
- goto next;
-
- if (ip_summed == CHECKSUM_COMPLETE) {
- void *va = skb_frag_address(skb_shinfo(gro_skb)->frags);
- if (check_csum(cqe, gro_skb, va,
- dev->features)) {
- ip_summed = CHECKSUM_NONE;
- ring->csum_none++;
- ring->csum_complete--;
- }
- }
-
- skb_shinfo(gro_skb)->nr_frags = nr;
- gro_skb->len = length;
- gro_skb->data_len = length;
- gro_skb->ip_summed = ip_summed;
-
- if (l2_tunnel && ip_summed == CHECKSUM_UNNECESSARY)
- gro_skb->csum_level = 1;
-
- if ((cqe->vlan_my_qpn &
- cpu_to_be32(MLX4_CQE_CVLAN_PRESENT_MASK)) &&
- (dev->features & NETIF_F_HW_VLAN_CTAG_RX)) {
- u16 vid = be16_to_cpu(cqe->sl_vid);
-
- __vlan_hwaccel_put_tag(gro_skb, htons(ETH_P_8021Q), vid);
- } else if ((be32_to_cpu(cqe->vlan_my_qpn) &
- MLX4_CQE_SVLAN_PRESENT_MASK) &&
- (dev->features & NETIF_F_HW_VLAN_STAG_RX)) {
- __vlan_hwaccel_put_tag(gro_skb,
- htons(ETH_P_8021AD),
- be16_to_cpu(cqe->sl_vid));
- }
-
- if (dev->features & NETIF_F_RXHASH)
- skb_set_hash(gro_skb,
- be32_to_cpu(cqe->immed_rss_invalid),
- (ip_summed == CHECKSUM_UNNECESSARY) ?
- PKT_HASH_TYPE_L4 :
- PKT_HASH_TYPE_L3);
-
- skb_record_rx_queue(gro_skb, cq->ring);
-
- if (ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL) {
- timestamp = mlx4_en_get_cqe_ts(cqe);
- mlx4_en_fill_hwtstamps(mdev,
- skb_hwtstamps(gro_skb),
- timestamp);
- }
-
- napi_gro_frags(&cq->napi);
- goto next;
- }
-
- /* GRO not possible, complete processing here */
- skb = mlx4_en_rx_skb(priv, rx_desc, frags, length);
- if (unlikely(!skb)) {
- ring->dropped++;
- goto next;
- }
-
- if (unlikely(priv->validate_loopback)) {
- validate_loopback(priv, skb);
- goto next;
- }
-
- if (ip_summed == CHECKSUM_COMPLETE) {
- if (check_csum(cqe, skb, skb->data, dev->features)) {
- ip_summed = CHECKSUM_NONE;
- ring->csum_complete--;
- ring->csum_none++;
- }
- }
-
skb->ip_summed = ip_summed;
- skb->protocol = eth_type_trans(skb, dev);
- skb_record_rx_queue(skb, cq->ring);
-
- if (l2_tunnel && ip_summed == CHECKSUM_UNNECESSARY)
- skb->csum_level = 1;
-
if (dev->features & NETIF_F_RXHASH)
skb_set_hash(skb,
be32_to_cpu(cqe->immed_rss_invalid),
@@ -1078,36 +841,36 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
PKT_HASH_TYPE_L4 :
PKT_HASH_TYPE_L3);
- if ((be32_to_cpu(cqe->vlan_my_qpn) &
- MLX4_CQE_CVLAN_PRESENT_MASK) &&
+
+ if ((cqe->vlan_my_qpn &
+ cpu_to_be32(MLX4_CQE_CVLAN_PRESENT_MASK)) &&
(dev->features & NETIF_F_HW_VLAN_CTAG_RX))
- __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), be16_to_cpu(cqe->sl_vid));
- else if ((be32_to_cpu(cqe->vlan_my_qpn) &
- MLX4_CQE_SVLAN_PRESENT_MASK) &&
+ __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+ be16_to_cpu(cqe->sl_vid));
+ else if ((cqe->vlan_my_qpn &
+ cpu_to_be32(MLX4_CQE_SVLAN_PRESENT_MASK)) &&
(dev->features & NETIF_F_HW_VLAN_STAG_RX))
__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021AD),
be16_to_cpu(cqe->sl_vid));
- if (ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL) {
- timestamp = mlx4_en_get_cqe_ts(cqe);
- mlx4_en_fill_hwtstamps(mdev, skb_hwtstamps(skb),
- timestamp);
+ nr = mlx4_en_complete_rx_desc(priv, frags, skb, length);
+ if (likely(nr)) {
+ skb_shinfo(skb)->nr_frags = nr;
+ skb->len = length;
+ skb->data_len = length;
+ napi_gro_frags(&cq->napi);
+ } else {
+ skb->vlan_tci = 0;
+ skb_clear_hash(skb);
}
-
- napi_gro_receive(&cq->napi, skb);
next:
- for (nr = 0; nr < priv->num_frags; nr++)
- mlx4_en_free_frag(priv, frags, nr);
-
-consumed:
++cq->mcq.cons_index;
index = (cq->mcq.cons_index) & ring->size_mask;
cqe = mlx4_en_get_cqe(cq->buf, index, priv->cqe_size) + factor;
if (++polled == budget)
- goto out;
+ break;
}
-out:
rcu_read_unlock();
if (polled) {
@@ -1178,13 +941,6 @@ int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget)
return done;
}
-static const int frag_sizes[] = {
- FRAG_SZ0,
- FRAG_SZ1,
- FRAG_SZ2,
- FRAG_SZ3
-};
-
void mlx4_en_calc_rx_buf(struct net_device *dev)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
@@ -1195,33 +951,43 @@ void mlx4_en_calc_rx_buf(struct net_device *dev)
* This only works when num_frags == 1.
*/
if (priv->tx_ring_num[TX_XDP]) {
- priv->frag_info[0].order = 0;
priv->frag_info[0].frag_size = eff_mtu;
- priv->frag_info[0].frag_prefix_size = 0;
/* This will gain efficient xdp frame recycling at the
* expense of more costly truesize accounting
*/
priv->frag_info[0].frag_stride = PAGE_SIZE;
- priv->frag_info[0].dma_dir = PCI_DMA_BIDIRECTIONAL;
- priv->frag_info[0].rx_headroom = XDP_PACKET_HEADROOM;
+ priv->dma_dir = PCI_DMA_BIDIRECTIONAL;
+ priv->rx_headroom = XDP_PACKET_HEADROOM;
i = 1;
} else {
- int buf_size = 0;
+ int frag_size_max = 2048, buf_size = 0;
+
+ /* should not happen, right ? */
+ if (eff_mtu > PAGE_SIZE + (MLX4_EN_MAX_RX_FRAGS - 1) * 2048)
+ frag_size_max = PAGE_SIZE;
while (buf_size < eff_mtu) {
- priv->frag_info[i].order = MLX4_EN_ALLOC_PREFER_ORDER;
- priv->frag_info[i].frag_size =
- (eff_mtu > buf_size + frag_sizes[i]) ?
- frag_sizes[i] : eff_mtu - buf_size;
- priv->frag_info[i].frag_prefix_size = buf_size;
- priv->frag_info[i].frag_stride =
- ALIGN(priv->frag_info[i].frag_size,
- SMP_CACHE_BYTES);
- priv->frag_info[i].dma_dir = PCI_DMA_FROMDEVICE;
- priv->frag_info[i].rx_headroom = 0;
- buf_size += priv->frag_info[i].frag_size;
+ int frag_stride, frag_size = eff_mtu - buf_size;
+ int pad, nb;
+
+ if (i < MLX4_EN_MAX_RX_FRAGS - 1)
+ frag_size = min(frag_size, frag_size_max);
+
+ priv->frag_info[i].frag_size = frag_size;
+ frag_stride = ALIGN(frag_size, SMP_CACHE_BYTES);
+ /* We can only pack 2 1536-bytes frames in on 4K page
+ * Therefore, each frame would consume more bytes (truesize)
+ */
+ nb = PAGE_SIZE / frag_stride;
+ pad = (PAGE_SIZE - nb * frag_stride) / nb;
+ pad &= ~(SMP_CACHE_BYTES - 1);
+ priv->frag_info[i].frag_stride = frag_stride + pad;
+
+ buf_size += frag_size;
i++;
}
+ priv->dma_dir = PCI_DMA_FROMDEVICE;
+ priv->rx_headroom = 0;
}
priv->num_frags = i;
@@ -1232,10 +998,9 @@ void mlx4_en_calc_rx_buf(struct net_device *dev)
eff_mtu, priv->num_frags);
for (i = 0; i < priv->num_frags; i++) {
en_err(priv,
- " frag:%d - size:%d prefix:%d stride:%d\n",
+ " frag:%d - size:%d stride:%d\n",
i,
priv->frag_info[i].frag_size,
- priv->frag_info[i].frag_prefix_size,
priv->frag_info[i].frag_stride);
}
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
index 95290e1..17112fa 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
@@ -81,14 +81,11 @@ static int mlx4_en_test_loopback(struct mlx4_en_priv *priv)
{
u32 loopback_ok = 0;
int i;
- bool gro_enabled;
priv->loopback_ok = 0;
priv->validate_loopback = 1;
- gro_enabled = priv->dev->features & NETIF_F_GRO;
mlx4_en_update_loopback_state(priv->dev, priv->dev->features);
- priv->dev->features &= ~NETIF_F_GRO;
/* xmit */
if (mlx4_en_test_loopback_xmit(priv)) {
@@ -111,9 +108,6 @@ static int mlx4_en_test_loopback(struct mlx4_en_priv *priv)
priv->validate_loopback = 0;
- if (gro_enabled)
- priv->dev->features |= NETIF_F_GRO;
-
mlx4_en_update_loopback_state(priv->dev, priv->dev->features);
return !loopback_ok;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 3ed4219..3ba89bc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -354,13 +354,11 @@ u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
struct mlx4_en_rx_alloc frame = {
.page = tx_info->page,
.dma = tx_info->map0_dma,
- .page_offset = XDP_PACKET_HEADROOM,
- .page_size = PAGE_SIZE,
};
if (!mlx4_en_rx_recycle(ring->recycle_ring, &frame)) {
dma_unmap_page(priv->ddev, tx_info->map0_dma,
- PAGE_SIZE, priv->frag_info[0].dma_dir);
+ PAGE_SIZE, priv->dma_dir);
put_page(tx_info->page);
}
@@ -980,8 +978,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
ring->tso_packets++;
- i = ((skb->len - lso_header_size) / shinfo->gso_size) +
- !!((skb->len - lso_header_size) % shinfo->gso_size);
+ i = shinfo->gso_segs;
tx_info->nr_bytes = skb->len + (i - 1) * lso_header_size;
ring->packets += i;
} else {
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 21377c3..7032054 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -1940,6 +1940,14 @@ static int mlx4_comm_check_offline(struct mlx4_dev *dev)
(u32)(1 << COMM_CHAN_OFFLINE_OFFSET));
if (!offline_bit)
return 0;
+
+ /* If device removal has been requested,
+ * do not continue retrying.
+ */
+ if (dev->persist->interface_state &
+ MLX4_INTERFACE_STATE_NOWAIT)
+ break;
+
/* There are cases as part of AER/Reset flow that PF needs
* around 100 msec to load. We therefore sleep for 100 msec
* to allow other tasks to make use of that CPU during this
@@ -3955,6 +3963,9 @@ static void mlx4_remove_one(struct pci_dev *pdev)
struct devlink *devlink = priv_to_devlink(priv);
int active_vfs = 0;
+ if (mlx4_is_slave(dev))
+ persist->interface_state |= MLX4_INTERFACE_STATE_NOWAIT;
+
mutex_lock(&persist->interface_state_mutex);
persist->interface_state |= MLX4_INTERFACE_STATE_DELETION;
mutex_unlock(&persist->interface_state_mutex);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 3629ce1..39f401a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -102,17 +102,6 @@
/* Use the maximum between 16384 and a single page */
#define MLX4_EN_ALLOC_SIZE PAGE_ALIGN(16384)
-#define MLX4_EN_ALLOC_PREFER_ORDER min_t(int, get_order(32768), \
- PAGE_ALLOC_COSTLY_ORDER)
-
-/* Receive fragment sizes; we use at most 3 fragments (for 9600 byte MTU
- * and 4K allocations) */
-enum {
- FRAG_SZ0 = 1536 - NET_IP_ALIGN,
- FRAG_SZ1 = 4096,
- FRAG_SZ2 = 4096,
- FRAG_SZ3 = MLX4_EN_ALLOC_SIZE
-};
#define MLX4_EN_MAX_RX_FRAGS 4
/* Maximum ring sizes */
@@ -264,13 +253,16 @@ struct mlx4_en_rx_alloc {
struct page *page;
dma_addr_t dma;
u32 page_offset;
- u32 page_size;
};
#define MLX4_EN_CACHE_SIZE (2 * NAPI_POLL_WEIGHT)
+
struct mlx4_en_page_cache {
u32 index;
- struct mlx4_en_rx_alloc buf[MLX4_EN_CACHE_SIZE];
+ struct {
+ struct page *page;
+ dma_addr_t dma;
+ } buf[MLX4_EN_CACHE_SIZE];
};
struct mlx4_en_priv;
@@ -335,7 +327,6 @@ struct mlx4_en_rx_desc {
struct mlx4_en_rx_ring {
struct mlx4_hwq_resources wqres;
- struct mlx4_en_rx_alloc page_alloc[MLX4_EN_MAX_RX_FRAGS];
u32 size ; /* number of Rx descs*/
u32 actual_size;
u32 size_mask;
@@ -355,6 +346,7 @@ struct mlx4_en_rx_ring {
unsigned long csum_ok;
unsigned long csum_none;
unsigned long csum_complete;
+ unsigned long rx_alloc_pages;
unsigned long xdp_drop;
unsigned long xdp_tx;
unsigned long xdp_tx_full;
@@ -472,11 +464,7 @@ struct mlx4_en_mc_list {
struct mlx4_en_frag_info {
u16 frag_size;
- u16 frag_prefix_size;
u32 frag_stride;
- enum dma_data_direction dma_dir;
- u16 order;
- u16 rx_headroom;
};
#ifdef CONFIG_MLX4_EN_DCB
@@ -584,8 +572,10 @@ struct mlx4_en_priv {
u32 rx_ring_num;
u32 rx_skb_size;
struct mlx4_en_frag_info frag_info[MLX4_EN_MAX_RX_FRAGS];
- u16 num_frags;
- u16 log_rx_info;
+ u8 num_frags;
+ u8 log_rx_info;
+ u8 dma_dir;
+ u16 rx_headroom;
struct mlx4_en_tx_ring **tx_ring[MLX4_EN_NUM_TX_TYPES];
struct mlx4_en_rx_ring *rx_ring[MAX_RX_RINGS];
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h
index 48641cb..926f3c3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h
@@ -37,7 +37,7 @@ struct mlx4_en_port_stats {
unsigned long queue_stopped;
unsigned long wake_queue;
unsigned long tx_timeout;
- unsigned long rx_alloc_failed;
+ unsigned long rx_alloc_pages;
unsigned long rx_chksum_good;
unsigned long rx_chksum_none;
unsigned long rx_chksum_complete;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index ddb4ca4..1171700 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -14,6 +14,7 @@
config MLX5_CORE_EN
bool "Mellanox Technologies ConnectX-4 Ethernet support"
depends on NETDEVICES && ETHERNET && PCI && MLX5_CORE
+ depends on IPV6=y || IPV6=n || MLX5_CORE=m
imply PTP_1588_CLOCK
default n
---help---
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index caa837e..5bdaf3d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -279,6 +279,8 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
case MLX5_CMD_OP_DESTROY_XRC_SRQ:
case MLX5_CMD_OP_DESTROY_DCT:
case MLX5_CMD_OP_DEALLOC_Q_COUNTER:
+ case MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT:
+ case MLX5_CMD_OP_DESTROY_QOS_PARA_VPORT:
case MLX5_CMD_OP_DEALLOC_PD:
case MLX5_CMD_OP_DEALLOC_UAR:
case MLX5_CMD_OP_DETACH_FROM_MCG:
@@ -305,8 +307,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
case MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY:
case MLX5_CMD_OP_SET_FLOW_TABLE_ROOT:
case MLX5_CMD_OP_DEALLOC_ENCAP_HEADER:
- case MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT:
- case MLX5_CMD_OP_DESTROY_QOS_PARA_VPORT:
+ case MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT:
return MLX5_CMD_STAT_OK;
case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -361,6 +362,12 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
case MLX5_CMD_OP_QUERY_VPORT_COUNTER:
case MLX5_CMD_OP_ALLOC_Q_COUNTER:
case MLX5_CMD_OP_QUERY_Q_COUNTER:
+ case MLX5_CMD_OP_SET_RATE_LIMIT:
+ case MLX5_CMD_OP_QUERY_RATE_LIMIT:
+ case MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT:
+ case MLX5_CMD_OP_QUERY_SCHEDULING_ELEMENT:
+ case MLX5_CMD_OP_MODIFY_SCHEDULING_ELEMENT:
+ case MLX5_CMD_OP_CREATE_QOS_PARA_VPORT:
case MLX5_CMD_OP_ALLOC_PD:
case MLX5_CMD_OP_ALLOC_UAR:
case MLX5_CMD_OP_CONFIG_INT_MODERATION:
@@ -412,10 +419,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
case MLX5_CMD_OP_ALLOC_FLOW_COUNTER:
case MLX5_CMD_OP_QUERY_FLOW_COUNTER:
case MLX5_CMD_OP_ALLOC_ENCAP_HEADER:
- case MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT:
- case MLX5_CMD_OP_QUERY_SCHEDULING_ELEMENT:
- case MLX5_CMD_OP_MODIFY_SCHEDULING_ELEMENT:
- case MLX5_CMD_OP_CREATE_QOS_PARA_VPORT:
+ case MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT:
*status = MLX5_DRIVER_STATUS_ABORTED;
*synd = MLX5_DRIVER_SYND;
return -EIO;
@@ -497,6 +501,14 @@ const char *mlx5_command_str(int command)
MLX5_COMMAND_STR_CASE(ALLOC_Q_COUNTER);
MLX5_COMMAND_STR_CASE(DEALLOC_Q_COUNTER);
MLX5_COMMAND_STR_CASE(QUERY_Q_COUNTER);
+ MLX5_COMMAND_STR_CASE(SET_RATE_LIMIT);
+ MLX5_COMMAND_STR_CASE(QUERY_RATE_LIMIT);
+ MLX5_COMMAND_STR_CASE(CREATE_SCHEDULING_ELEMENT);
+ MLX5_COMMAND_STR_CASE(DESTROY_SCHEDULING_ELEMENT);
+ MLX5_COMMAND_STR_CASE(QUERY_SCHEDULING_ELEMENT);
+ MLX5_COMMAND_STR_CASE(MODIFY_SCHEDULING_ELEMENT);
+ MLX5_COMMAND_STR_CASE(CREATE_QOS_PARA_VPORT);
+ MLX5_COMMAND_STR_CASE(DESTROY_QOS_PARA_VPORT);
MLX5_COMMAND_STR_CASE(ALLOC_PD);
MLX5_COMMAND_STR_CASE(DEALLOC_PD);
MLX5_COMMAND_STR_CASE(ALLOC_UAR);
@@ -572,12 +584,8 @@ const char *mlx5_command_str(int command)
MLX5_COMMAND_STR_CASE(MODIFY_FLOW_TABLE);
MLX5_COMMAND_STR_CASE(ALLOC_ENCAP_HEADER);
MLX5_COMMAND_STR_CASE(DEALLOC_ENCAP_HEADER);
- MLX5_COMMAND_STR_CASE(CREATE_SCHEDULING_ELEMENT);
- MLX5_COMMAND_STR_CASE(DESTROY_SCHEDULING_ELEMENT);
- MLX5_COMMAND_STR_CASE(QUERY_SCHEDULING_ELEMENT);
- MLX5_COMMAND_STR_CASE(MODIFY_SCHEDULING_ELEMENT);
- MLX5_COMMAND_STR_CASE(CREATE_QOS_PARA_VPORT);
- MLX5_COMMAND_STR_CASE(DESTROY_QOS_PARA_VPORT);
+ MLX5_COMMAND_STR_CASE(ALLOC_MODIFY_HEADER_CONTEXT);
+ MLX5_COMMAND_STR_CASE(DEALLOC_MODIFY_HEADER_CONTEXT);
default: return "unknown command opcode";
}
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index f6a6ded..b7feecf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -111,18 +111,13 @@
#define MLX5E_MAX_NUM_SQS (MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC)
#define MLX5E_TX_CQ_POLL_BUDGET 128
#define MLX5E_UPDATE_STATS_INTERVAL 200 /* msecs */
-#define MLX5E_SQ_BF_BUDGET 16
#define MLX5E_ICOSQ_MAX_WQEBBS \
(DIV_ROUND_UP(sizeof(struct mlx5e_umr_wqe), MLX5_SEND_WQE_BB))
#define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
-#define MLX5E_XDP_IHS_DS_COUNT \
- DIV_ROUND_UP(MLX5E_XDP_MIN_INLINE - 2, MLX5_SEND_WQE_DS)
#define MLX5E_XDP_TX_DS_COUNT \
((sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) + 1 /* SG DS */)
-#define MLX5E_XDP_TX_WQEBBS \
- DIV_ROUND_UP(MLX5E_XDP_TX_DS_COUNT, MLX5_SEND_WQEBB_NUM_DS)
#define MLX5E_NUM_MAIN_GROUPS 9
@@ -187,15 +182,15 @@ enum mlx5e_priv_flag {
MLX5E_PFLAG_RX_CQE_COMPRESS = (1 << 1),
};
-#define MLX5E_SET_PFLAG(priv, pflag, enable) \
+#define MLX5E_SET_PFLAG(params, pflag, enable) \
do { \
if (enable) \
- (priv)->params.pflags |= (pflag); \
+ (params)->pflags |= (pflag); \
else \
- (priv)->params.pflags &= ~(pflag); \
+ (params)->pflags &= ~(pflag); \
} while (0)
-#define MLX5E_GET_PFLAG(priv, pflag) (!!((priv)->params.pflags & (pflag)))
+#define MLX5E_GET_PFLAG(params, pflag) (!!((params)->pflags & (pflag)))
#ifdef CONFIG_MLX5_CORE_EN_DCB
#define MLX5E_MAX_BW_ALLOC 100 /* Max percentage of BW allocation */
@@ -218,7 +213,6 @@ struct mlx5e_params {
bool rx_cqe_compress_def;
struct mlx5e_cq_moder rx_cq_moderation;
struct mlx5e_cq_moder tx_cq_moderation;
- u16 min_rx_wqes;
bool lro_en;
u32 lro_wqe_sz;
u16 tx_max_inline;
@@ -227,9 +221,11 @@ struct mlx5e_params {
u8 toeplitz_hash_key[40];
u32 indirection_rqt[MLX5E_INDIR_RQT_SIZE];
bool vlan_strip_disable;
+ bool scatter_fcs_en;
bool rx_am_enabled;
u32 lro_timeout;
u32 pflags;
+ struct bpf_prog *xdp_prog;
};
#ifdef CONFIG_MLX5_CORE_EN_DCB
@@ -285,7 +281,6 @@ struct mlx5e_cq {
struct napi_struct *napi;
struct mlx5_core_cq mcq;
struct mlx5e_channel *channel;
- struct mlx5e_priv *priv;
/* cqe decompression */
struct mlx5_cqe64 title;
@@ -295,22 +290,163 @@ struct mlx5e_cq {
u16 decmprs_wqe_counter;
/* control */
+ struct mlx5_core_dev *mdev;
struct mlx5_frag_wq_ctrl wq_ctrl;
} ____cacheline_aligned_in_smp;
-struct mlx5e_rq;
-typedef void (*mlx5e_fp_handle_rx_cqe)(struct mlx5e_rq *rq,
- struct mlx5_cqe64 *cqe);
-typedef int (*mlx5e_fp_alloc_wqe)(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe,
- u16 ix);
+struct mlx5e_tx_wqe_info {
+ u32 num_bytes;
+ u8 num_wqebbs;
+ u8 num_dma;
+};
-typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq *rq, u16 ix);
+enum mlx5e_dma_map_type {
+ MLX5E_DMA_MAP_SINGLE,
+ MLX5E_DMA_MAP_PAGE
+};
+
+struct mlx5e_sq_dma {
+ dma_addr_t addr;
+ u32 size;
+ enum mlx5e_dma_map_type type;
+};
+
+enum {
+ MLX5E_SQ_STATE_ENABLED,
+};
+
+struct mlx5e_sq_wqe_info {
+ u8 opcode;
+ u8 num_wqebbs;
+};
+
+struct mlx5e_txqsq {
+ /* data path */
+
+ /* dirtied @completion */
+ u16 cc;
+ u32 dma_fifo_cc;
+
+ /* dirtied @xmit */
+ u16 pc ____cacheline_aligned_in_smp;
+ u32 dma_fifo_pc;
+ struct mlx5e_sq_stats stats;
+
+ struct mlx5e_cq cq;
+
+ /* write@xmit, read@completion */
+ struct {
+ struct sk_buff **skb;
+ struct mlx5e_sq_dma *dma_fifo;
+ struct mlx5e_tx_wqe_info *wqe_info;
+ } db;
+
+ /* read only */
+ struct mlx5_wq_cyc wq;
+ u32 dma_fifo_mask;
+ void __iomem *uar_map;
+ struct netdev_queue *txq;
+ u32 sqn;
+ u16 max_inline;
+ u8 min_inline_mode;
+ u16 edge;
+ struct device *pdev;
+ struct mlx5e_tstamp *tstamp;
+ __be32 mkey_be;
+ unsigned long state;
+
+ /* control path */
+ struct mlx5_wq_ctrl wq_ctrl;
+ struct mlx5e_channel *channel;
+ int txq_ix;
+ u32 rate_limit;
+} ____cacheline_aligned_in_smp;
+
+struct mlx5e_xdpsq {
+ /* data path */
+
+ /* dirtied @rx completion */
+ u16 cc;
+ u16 pc;
+
+ struct mlx5e_cq cq;
+
+ /* write@xmit, read@completion */
+ struct {
+ struct mlx5e_dma_info *di;
+ bool doorbell;
+ } db;
+
+ /* read only */
+ struct mlx5_wq_cyc wq;
+ void __iomem *uar_map;
+ u32 sqn;
+ struct device *pdev;
+ __be32 mkey_be;
+ u8 min_inline_mode;
+ unsigned long state;
+
+ /* control path */
+ struct mlx5_wq_ctrl wq_ctrl;
+ struct mlx5e_channel *channel;
+} ____cacheline_aligned_in_smp;
+
+struct mlx5e_icosq {
+ /* data path */
+
+ /* dirtied @completion */
+ u16 cc;
+
+ /* dirtied @xmit */
+ u16 pc ____cacheline_aligned_in_smp;
+ u32 dma_fifo_pc;
+ u16 prev_cc;
+
+ struct mlx5e_cq cq;
+
+ /* write@xmit, read@completion */
+ struct {
+ struct mlx5e_sq_wqe_info *ico_wqe;
+ } db;
+
+ /* read only */
+ struct mlx5_wq_cyc wq;
+ void __iomem *uar_map;
+ u32 sqn;
+ u16 edge;
+ struct device *pdev;
+ __be32 mkey_be;
+ unsigned long state;
+
+ /* control path */
+ struct mlx5_wq_ctrl wq_ctrl;
+ struct mlx5e_channel *channel;
+} ____cacheline_aligned_in_smp;
+
+static inline bool
+mlx5e_wqc_has_room_for(struct mlx5_wq_cyc *wq, u16 cc, u16 pc, u16 n)
+{
+ return (((wq->sz_m1 & (cc - pc)) >= n) || (cc == pc));
+}
struct mlx5e_dma_info {
struct page *page;
dma_addr_t addr;
};
+struct mlx5e_umr_dma_info {
+ __be64 *mtt;
+ dma_addr_t mtt_addr;
+ struct mlx5e_dma_info dma_info[MLX5_MPWRQ_PAGES_PER_WQE];
+ struct mlx5e_umr_wqe wqe;
+};
+
+struct mlx5e_mpw_info {
+ struct mlx5e_umr_dma_info umr;
+ u16 consumed_strides;
+ u16 skbs_frags[MLX5_MPWRQ_PAGES_PER_WQE];
+};
+
struct mlx5e_rx_am_stats {
int ppms; /* packets per msec */
int epms; /* events per msec */
@@ -347,6 +483,11 @@ struct mlx5e_page_cache {
struct mlx5e_dma_info page_cache[MLX5E_CACHE_SIZE];
};
+struct mlx5e_rq;
+typedef void (*mlx5e_fp_handle_rx_cqe)(struct mlx5e_rq*, struct mlx5_cqe64*);
+typedef int (*mlx5e_fp_alloc_wqe)(struct mlx5e_rq*, struct mlx5e_rx_wqe*, u16);
+typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq*, u16);
+
struct mlx5e_rq {
/* data path */
struct mlx5_wq_ll wq;
@@ -381,7 +522,10 @@ struct mlx5e_rq {
u16 rx_headroom;
struct mlx5e_rx_am am; /* Adaptive Moderation */
+
+ /* XDP */
struct bpf_prog *xdp_prog;
+ struct mlx5e_xdpsq xdpsq;
/* control */
struct mlx5_wq_ctrl wq_ctrl;
@@ -390,118 +534,10 @@ struct mlx5e_rq {
u32 mpwqe_num_strides;
u32 rqn;
struct mlx5e_channel *channel;
- struct mlx5e_priv *priv;
+ struct mlx5_core_dev *mdev;
struct mlx5_core_mkey umr_mkey;
} ____cacheline_aligned_in_smp;
-struct mlx5e_umr_dma_info {
- __be64 *mtt;
- dma_addr_t mtt_addr;
- struct mlx5e_dma_info dma_info[MLX5_MPWRQ_PAGES_PER_WQE];
- struct mlx5e_umr_wqe wqe;
-};
-
-struct mlx5e_mpw_info {
- struct mlx5e_umr_dma_info umr;
- u16 consumed_strides;
- u16 skbs_frags[MLX5_MPWRQ_PAGES_PER_WQE];
-};
-
-struct mlx5e_tx_wqe_info {
- u32 num_bytes;
- u8 num_wqebbs;
- u8 num_dma;
-};
-
-enum mlx5e_dma_map_type {
- MLX5E_DMA_MAP_SINGLE,
- MLX5E_DMA_MAP_PAGE
-};
-
-struct mlx5e_sq_dma {
- dma_addr_t addr;
- u32 size;
- enum mlx5e_dma_map_type type;
-};
-
-enum {
- MLX5E_SQ_STATE_ENABLED,
- MLX5E_SQ_STATE_BF_ENABLE,
-};
-
-struct mlx5e_sq_wqe_info {
- u8 opcode;
- u8 num_wqebbs;
-};
-
-enum mlx5e_sq_type {
- MLX5E_SQ_TXQ,
- MLX5E_SQ_ICO,
- MLX5E_SQ_XDP
-};
-
-struct mlx5e_sq {
- /* data path */
-
- /* dirtied @completion */
- u16 cc;
- u32 dma_fifo_cc;
-
- /* dirtied @xmit */
- u16 pc ____cacheline_aligned_in_smp;
- u32 dma_fifo_pc;
- u16 bf_offset;
- u16 prev_cc;
- u8 bf_budget;
- struct mlx5e_sq_stats stats;
-
- struct mlx5e_cq cq;
-
- /* pointers to per tx element info: write@xmit, read@completion */
- union {
- struct {
- struct sk_buff **skb;
- struct mlx5e_sq_dma *dma_fifo;
- struct mlx5e_tx_wqe_info *wqe_info;
- } txq;
- struct mlx5e_sq_wqe_info *ico_wqe;
- struct {
- struct mlx5e_sq_wqe_info *wqe_info;
- struct mlx5e_dma_info *di;
- bool doorbell;
- } xdp;
- } db;
-
- /* read only */
- struct mlx5_wq_cyc wq;
- u32 dma_fifo_mask;
- void __iomem *uar_map;
- struct netdev_queue *txq;
- u32 sqn;
- u16 bf_buf_size;
- u16 max_inline;
- u8 min_inline_mode;
- u16 edge;
- struct device *pdev;
- struct mlx5e_tstamp *tstamp;
- __be32 mkey_be;
- unsigned long state;
-
- /* control path */
- struct mlx5_wq_ctrl wq_ctrl;
- struct mlx5_sq_bfreg bfreg;
- struct mlx5e_channel *channel;
- int tc;
- u32 rate_limit;
- u8 type;
-} ____cacheline_aligned_in_smp;
-
-static inline bool mlx5e_sq_has_room_for(struct mlx5e_sq *sq, u16 n)
-{
- return (((sq->wq.sz_m1 & (sq->cc - sq->pc)) >= n) ||
- (sq->cc == sq->pc));
-}
-
enum channel_flags {
MLX5E_CHANNEL_NAPI_SCHED = 1,
};
@@ -509,9 +545,8 @@ enum channel_flags {
struct mlx5e_channel {
/* data path */
struct mlx5e_rq rq;
- struct mlx5e_sq xdp_sq;
- struct mlx5e_sq sq[MLX5E_MAX_NUM_TC];
- struct mlx5e_sq icosq; /* internal control operations */
+ struct mlx5e_txqsq sq[MLX5E_MAX_NUM_TC];
+ struct mlx5e_icosq icosq; /* internal control operations */
bool xdp;
struct napi_struct napi;
struct device *pdev;
@@ -522,10 +557,18 @@ struct mlx5e_channel {
/* control */
struct mlx5e_priv *priv;
+ struct mlx5_core_dev *mdev;
+ struct mlx5e_tstamp *tstamp;
int ix;
int cpu;
};
+struct mlx5e_channels {
+ struct mlx5e_channel **c;
+ unsigned int num;
+ struct mlx5e_params params;
+};
+
enum mlx5e_traffic_types {
MLX5E_TT_IPV4_TCP,
MLX5E_TT_IPV6_TCP,
@@ -675,34 +718,17 @@ enum {
MLX5E_NIC_PRIO
};
-struct mlx5e_profile {
- void (*init)(struct mlx5_core_dev *mdev,
- struct net_device *netdev,
- const struct mlx5e_profile *profile, void *ppriv);
- void (*cleanup)(struct mlx5e_priv *priv);
- int (*init_rx)(struct mlx5e_priv *priv);
- void (*cleanup_rx)(struct mlx5e_priv *priv);
- int (*init_tx)(struct mlx5e_priv *priv);
- void (*cleanup_tx)(struct mlx5e_priv *priv);
- void (*enable)(struct mlx5e_priv *priv);
- void (*disable)(struct mlx5e_priv *priv);
- void (*update_stats)(struct mlx5e_priv *priv);
- int (*max_nch)(struct mlx5_core_dev *mdev);
- int max_tc;
-};
-
struct mlx5e_priv {
/* priv data path fields - start */
- struct mlx5e_sq **txq_to_sq_map;
- int channeltc_to_txq_map[MLX5E_MAX_NUM_CHANNELS][MLX5E_MAX_NUM_TC];
- struct bpf_prog *xdp_prog;
+ struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC];
+ int channel_tc2txq[MLX5E_MAX_NUM_CHANNELS][MLX5E_MAX_NUM_TC];
/* priv data path fields - end */
unsigned long state;
struct mutex state_lock; /* Protects Interface state */
struct mlx5e_rq drop_rq;
- struct mlx5e_channel **channel;
+ struct mlx5e_channels channels;
u32 tisn[MLX5E_MAX_NUM_TC];
struct mlx5e_rqt indir_rqt;
struct mlx5e_tir indir_tir[MLX5E_NUM_INDIR_TIRS];
@@ -712,7 +738,6 @@ struct mlx5e_priv {
struct mlx5e_flow_steering fs;
struct mlx5e_vxlan_db vxlan;
- struct mlx5e_params params;
struct workqueue_struct *wq;
struct work_struct update_carrier_work;
struct work_struct set_rx_mode_work;
@@ -732,9 +757,24 @@ struct mlx5e_priv {
void *ppriv;
};
+struct mlx5e_profile {
+ void (*init)(struct mlx5_core_dev *mdev,
+ struct net_device *netdev,
+ const struct mlx5e_profile *profile, void *ppriv);
+ void (*cleanup)(struct mlx5e_priv *priv);
+ int (*init_rx)(struct mlx5e_priv *priv);
+ void (*cleanup_rx)(struct mlx5e_priv *priv);
+ int (*init_tx)(struct mlx5e_priv *priv);
+ void (*cleanup_tx)(struct mlx5e_priv *priv);
+ void (*enable)(struct mlx5e_priv *priv);
+ void (*disable)(struct mlx5e_priv *priv);
+ void (*update_stats)(struct mlx5e_priv *priv);
+ int (*max_nch)(struct mlx5_core_dev *mdev);
+ int max_tc;
+};
+
void mlx5e_build_ptys2ethtool_map(void);
-void mlx5e_send_nop(struct mlx5e_sq *sq, bool notify_hw);
u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
void *accel_priv, select_queue_fallback_t fallback);
netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
@@ -744,7 +784,9 @@ void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event);
int mlx5e_napi_poll(struct napi_struct *napi, int budget);
bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget);
-void mlx5e_free_sq_descs(struct mlx5e_sq *sq);
+bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq);
+void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq);
+void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq);
void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info,
bool recycle);
@@ -792,7 +834,7 @@ void mlx5e_pps_event_handler(struct mlx5e_priv *priv,
struct ptp_clock_event *event);
int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr);
int mlx5e_hwstamp_get(struct net_device *dev, struct ifreq *ifr);
-void mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool val);
+int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool val);
int mlx5e_vlan_rx_add_vid(struct net_device *dev, __always_unused __be16 proto,
u16 vid);
@@ -801,14 +843,38 @@ int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto,
void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv);
void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv);
-int mlx5e_modify_rqs_vsd(struct mlx5e_priv *priv, bool vsd);
+struct mlx5e_redirect_rqt_param {
+ bool is_rss;
+ union {
+ u32 rqn; /* Direct RQN (Non-RSS) */
+ struct {
+ u8 hfunc;
+ struct mlx5e_channels *channels;
+ } rss; /* RSS data */
+ };
+};
-int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz, int ix);
-void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_priv *priv, void *tirc,
- enum mlx5e_traffic_types tt);
+int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz,
+ struct mlx5e_redirect_rqt_param rrp);
+void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_params *params,
+ enum mlx5e_traffic_types tt,
+ void *tirc);
int mlx5e_open_locked(struct net_device *netdev);
int mlx5e_close_locked(struct net_device *netdev);
+
+int mlx5e_open_channels(struct mlx5e_priv *priv,
+ struct mlx5e_channels *chs);
+void mlx5e_close_channels(struct mlx5e_channels *chs);
+
+/* Function pointer to be used to modify WH settings while
+ * switching channels
+ */
+typedef int (*mlx5e_fp_hw_modify)(struct mlx5e_priv *priv);
+void mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
+ struct mlx5e_channels *new_chs,
+ mlx5e_fp_hw_modify hw_modify);
+
void mlx5e_build_default_indir_rqt(struct mlx5_core_dev *mdev,
u32 *indirection_rqt, int len,
int num_channels);
@@ -816,30 +882,43 @@ int mlx5e_get_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params,
u8 cq_period_mode);
-void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type);
+void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev,
+ struct mlx5e_params *params, u8 rq_type);
-static inline void mlx5e_tx_notify_hw(struct mlx5e_sq *sq,
- struct mlx5_wqe_ctrl_seg *ctrl, int bf_sz)
+static inline
+struct mlx5e_tx_wqe *mlx5e_post_nop(struct mlx5_wq_cyc *wq, u32 sqn, u16 *pc)
{
- u16 ofst = sq->bf_offset;
+ u16 pi = *pc & wq->sz_m1;
+ struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi);
+ struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
+ memset(cseg, 0, sizeof(*cseg));
+
+ cseg->opmod_idx_opcode = cpu_to_be32((*pc << 8) | MLX5_OPCODE_NOP);
+ cseg->qpn_ds = cpu_to_be32((sqn << 8) | 0x01);
+
+ (*pc)++;
+
+ return wqe;
+}
+
+static inline
+void mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc,
+ void __iomem *uar_map,
+ struct mlx5_wqe_ctrl_seg *ctrl)
+{
+ ctrl->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE;
/* ensure wqe is visible to device before updating doorbell record */
dma_wmb();
- *sq->wq.db = cpu_to_be32(sq->pc);
+ *wq->db = cpu_to_be32(pc);
/* ensure doorbell record is visible to device before ringing the
* doorbell
*/
wmb();
- if (bf_sz)
- __iowrite64_copy(sq->uar_map + ofst, ctrl, bf_sz);
- else
- mlx5_write64((__be32 *)ctrl, sq->uar_map + ofst, NULL);
- /* flush the write-combining mapped buffer */
- wmb();
- sq->bf_offset ^= sq->bf_buf_size;
+ mlx5_write64((__be32 *)ctrl, uar_map, NULL);
}
static inline void mlx5e_cq_arm(struct mlx5e_cq *cq)
@@ -895,8 +974,7 @@ void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
struct mlx5e_tir *tir);
int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev);
void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev);
-int mlx5e_refresh_tirs_self_loopback(struct mlx5_core_dev *mdev,
- bool enable_uc_lb);
+int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb);
struct mlx5_eswitch_rep;
int mlx5e_vport_rep_load(struct mlx5_eswitch *esw,
@@ -928,10 +1006,6 @@ void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv);
int mlx5e_attach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev);
void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev);
u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout);
-void mlx5e_add_vxlan_port(struct net_device *netdev,
- struct udp_tunnel_info *ti);
-void mlx5e_del_vxlan_port(struct net_device *netdev,
- struct udp_tunnel_info *ti);
int mlx5e_get_offload_stats(int attr_id, const struct net_device *dev,
void *sp);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index 68419a0..c4e9cc7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -174,13 +174,9 @@ static int arfs_add_default_rule(struct mlx5e_priv *priv,
enum arfs_type type)
{
struct arfs_table *arfs_t = &priv->fs.arfs.arfs_tables[type];
- struct mlx5_flow_act flow_act = {
- .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- .flow_tag = MLX5_FS_DEFAULT_FLOW_TAG,
- .encap_id = 0,
- };
- struct mlx5_flow_destination dest;
struct mlx5e_tir *tir = priv->indir_tir;
+ struct mlx5_flow_destination dest;
+ MLX5_DECLARE_FLOW_ACT(flow_act);
struct mlx5_flow_spec *spec;
int err = 0;
@@ -469,15 +465,11 @@ static struct arfs_table *arfs_get_table(struct mlx5e_arfs_tables *arfs,
static struct mlx5_flow_handle *arfs_add_rule(struct mlx5e_priv *priv,
struct arfs_rule *arfs_rule)
{
- struct mlx5_flow_act flow_act = {
- .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- .flow_tag = MLX5_FS_DEFAULT_FLOW_TAG,
- .encap_id = 0,
- };
struct mlx5e_arfs_tables *arfs = &priv->fs.arfs;
struct arfs_tuple *tuple = &arfs_rule->tuple;
struct mlx5_flow_handle *rule = NULL;
struct mlx5_flow_destination dest;
+ MLX5_DECLARE_FLOW_ACT(flow_act);
struct arfs_table *arfs_table;
struct mlx5_flow_spec *spec;
struct mlx5_flow_table *ft;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
index 37e66ee..e706a87 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
@@ -90,6 +90,7 @@ int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr)
{
struct mlx5e_priv *priv = netdev_priv(dev);
struct hwtstamp_config config;
+ int err;
if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz))
return -EOPNOTSUPP;
@@ -111,7 +112,7 @@ int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr)
switch (config.rx_filter) {
case HWTSTAMP_FILTER_NONE:
/* Reset CQE compression to Admin default */
- mlx5e_modify_rx_cqe_compression_locked(priv, priv->params.rx_cqe_compress_def);
+ mlx5e_modify_rx_cqe_compression_locked(priv, priv->channels.params.rx_cqe_compress_def);
break;
case HWTSTAMP_FILTER_ALL:
case HWTSTAMP_FILTER_SOME:
@@ -129,7 +130,12 @@ int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr)
case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
/* Disable CQE compression */
netdev_warn(dev, "Disabling cqe compression");
- mlx5e_modify_rx_cqe_compression_locked(priv, false);
+ err = mlx5e_modify_rx_cqe_compression_locked(priv, false);
+ if (err) {
+ netdev_err(dev, "Failed disabling cqe compression err=%d\n", err);
+ mutex_unlock(&priv->state_lock);
+ return err;
+ }
config.rx_filter = HWTSTAMP_FILTER_ALL;
break;
default:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index bd898d8..f1f17f7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -107,10 +107,18 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
goto err_dealloc_transport_domain;
}
+ err = mlx5_alloc_bfreg(mdev, &res->bfreg, false, false);
+ if (err) {
+ mlx5_core_err(mdev, "alloc bfreg failed, %d\n", err);
+ goto err_destroy_mkey;
+ }
+
INIT_LIST_HEAD(&mdev->mlx5e_res.td.tirs_list);
return 0;
+err_destroy_mkey:
+ mlx5_core_destroy_mkey(mdev, &res->mkey);
err_dealloc_transport_domain:
mlx5_core_dealloc_transport_domain(mdev, res->td.tdn);
err_dealloc_pd:
@@ -122,23 +130,26 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev)
{
struct mlx5e_resources *res = &mdev->mlx5e_res;
+ mlx5_free_bfreg(mdev, &res->bfreg);
mlx5_core_destroy_mkey(mdev, &res->mkey);
mlx5_core_dealloc_transport_domain(mdev, res->td.tdn);
mlx5_core_dealloc_pd(mdev, res->pdn);
}
-int mlx5e_refresh_tirs_self_loopback(struct mlx5_core_dev *mdev,
- bool enable_uc_lb)
+int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
{
+ struct mlx5_core_dev *mdev = priv->mdev;
struct mlx5e_tir *tir;
- void *in;
+ int err = -ENOMEM;
+ u32 tirn = 0;
int inlen;
- int err = 0;
+ void *in;
+
inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
in = mlx5_vzalloc(inlen);
if (!in)
- return -ENOMEM;
+ goto out;
if (enable_uc_lb)
MLX5_SET(modify_tir_in, in, ctx.self_lb_block,
@@ -147,13 +158,16 @@ int mlx5e_refresh_tirs_self_loopback(struct mlx5_core_dev *mdev,
MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1);
list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) {
- err = mlx5_core_modify_tir(mdev, tir->tirn, in, inlen);
+ tirn = tir->tirn;
+ err = mlx5_core_modify_tir(mdev, tirn, in, inlen);
if (err)
goto out;
}
out:
kvfree(in);
+ if (err)
+ netdev_err(priv->netdev, "refresh tir(0x%x) failed, %d\n", tirn, err);
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 0523ed4..8fa23f6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -302,6 +302,9 @@ static u8 mlx5e_dcbnl_setdcbx(struct net_device *dev, u8 mode)
struct mlx5e_priv *priv = netdev_priv(dev);
struct mlx5e_dcbx *dcbx = &priv->dcbx;
+ if (mode & DCB_CAP_DCBX_LLD_MANAGED)
+ return 1;
+
if ((!mode) && MLX5_CAP_GEN(priv->mdev, dcbx)) {
if (dcbx->mode == MLX5E_DCBX_PARAM_VER_OPER_AUTO)
return 0;
@@ -315,13 +318,10 @@ static u8 mlx5e_dcbnl_setdcbx(struct net_device *dev, u8 mode)
return 1;
}
- if (mlx5e_dcbnl_switch_to_host_mode(netdev_priv(dev)))
+ if (!(mode & DCB_CAP_DCBX_HOST))
return 1;
- if ((mode & DCB_CAP_DCBX_LLD_MANAGED) ||
- !(mode & DCB_CAP_DCBX_VER_CEE) ||
- !(mode & DCB_CAP_DCBX_VER_IEEE) ||
- !(mode & DCB_CAP_DCBX_HOST))
+ if (mlx5e_dcbnl_switch_to_host_mode(netdev_priv(dev)))
return 1;
return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index a004a5a..ce7b09d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -42,8 +42,9 @@ static void mlx5e_get_drvinfo(struct net_device *dev,
strlcpy(drvinfo->version, DRIVER_VERSION " (" DRIVER_RELDATE ")",
sizeof(drvinfo->version));
snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
- "%d.%d.%d",
- fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev));
+ "%d.%d.%04d (%.16s)",
+ fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev),
+ mdev->board_id);
strlcpy(drvinfo->bus_info, pci_name(mdev->pdev),
sizeof(drvinfo->bus_info));
}
@@ -152,12 +153,9 @@ static bool mlx5e_query_global_pause_combined(struct mlx5e_priv *priv)
}
#define MLX5E_NUM_Q_CNTRS(priv) (NUM_Q_COUNTERS * (!!priv->q_counter))
-#define MLX5E_NUM_RQ_STATS(priv) \
- (NUM_RQ_STATS * priv->params.num_channels * \
- test_bit(MLX5E_STATE_OPENED, &priv->state))
+#define MLX5E_NUM_RQ_STATS(priv) (NUM_RQ_STATS * (priv)->channels.num)
#define MLX5E_NUM_SQ_STATS(priv) \
- (NUM_SQ_STATS * priv->params.num_channels * priv->params.num_tc * \
- test_bit(MLX5E_STATE_OPENED, &priv->state))
+ (NUM_SQ_STATS * (priv)->channels.num * (priv)->channels.params.num_tc)
#define MLX5E_NUM_PFC_COUNTERS(priv) \
((mlx5e_query_global_pause_combined(priv) + hweight8(mlx5e_query_pfc_combined(priv))) * \
NUM_PPORT_PER_PRIO_PFC_COUNTERS)
@@ -262,17 +260,17 @@ static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, uint8_t *data)
return;
/* per channel counters */
- for (i = 0; i < priv->params.num_channels; i++)
+ for (i = 0; i < priv->channels.num; i++)
for (j = 0; j < NUM_RQ_STATS; j++)
sprintf(data + (idx++) * ETH_GSTRING_LEN,
rq_stats_desc[j].format, i);
- for (tc = 0; tc < priv->params.num_tc; tc++)
- for (i = 0; i < priv->params.num_channels; i++)
+ for (tc = 0; tc < priv->channels.params.num_tc; tc++)
+ for (i = 0; i < priv->channels.num; i++)
for (j = 0; j < NUM_SQ_STATS; j++)
sprintf(data + (idx++) * ETH_GSTRING_LEN,
sq_stats_desc[j].format,
- priv->channeltc_to_txq_map[i][tc]);
+ priv->channel_tc2txq[i][tc]);
}
static void mlx5e_get_strings(struct net_device *dev,
@@ -303,6 +301,7 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 *data)
{
struct mlx5e_priv *priv = netdev_priv(dev);
+ struct mlx5e_channels *channels;
struct mlx5_priv *mlx5_priv;
int i, j, tc, prio, idx = 0;
unsigned long pfc_combined;
@@ -313,6 +312,7 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev,
mutex_lock(&priv->state_lock);
if (test_bit(MLX5E_STATE_OPENED, &priv->state))
mlx5e_update_stats(priv);
+ channels = &priv->channels;
mutex_unlock(&priv->state_lock);
for (i = 0; i < NUM_SW_COUNTERS; i++)
@@ -382,16 +382,16 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev,
return;
/* per channel counters */
- for (i = 0; i < priv->params.num_channels; i++)
+ for (i = 0; i < channels->num; i++)
for (j = 0; j < NUM_RQ_STATS; j++)
data[idx++] =
- MLX5E_READ_CTR64_CPU(&priv->channel[i]->rq.stats,
+ MLX5E_READ_CTR64_CPU(&channels->c[i]->rq.stats,
rq_stats_desc, j);
- for (tc = 0; tc < priv->params.num_tc; tc++)
- for (i = 0; i < priv->params.num_channels; i++)
+ for (tc = 0; tc < priv->channels.params.num_tc; tc++)
+ for (i = 0; i < channels->num; i++)
for (j = 0; j < NUM_SQ_STATS; j++)
- data[idx++] = MLX5E_READ_CTR64_CPU(&priv->channel[i]->sq[tc].stats,
+ data[idx++] = MLX5E_READ_CTR64_CPU(&channels->c[i]->sq[tc].stats,
sq_stats_desc, j);
}
@@ -406,8 +406,8 @@ static u32 mlx5e_rx_wqes_to_packets(struct mlx5e_priv *priv, int rq_wq_type,
if (rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
return num_wqe;
- stride_size = 1 << priv->params.mpwqe_log_stride_sz;
- num_strides = 1 << priv->params.mpwqe_log_num_strides;
+ stride_size = 1 << priv->channels.params.mpwqe_log_stride_sz;
+ num_strides = 1 << priv->channels.params.mpwqe_log_num_strides;
wqe_size = stride_size * num_strides;
packets_per_wqe = wqe_size /
@@ -427,8 +427,8 @@ static u32 mlx5e_packets_to_rx_wqes(struct mlx5e_priv *priv, int rq_wq_type,
if (rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
return num_packets;
- stride_size = 1 << priv->params.mpwqe_log_stride_sz;
- num_strides = 1 << priv->params.mpwqe_log_num_strides;
+ stride_size = 1 << priv->channels.params.mpwqe_log_stride_sz;
+ num_strides = 1 << priv->channels.params.mpwqe_log_num_strides;
wqe_size = stride_size * num_strides;
num_packets = (1 << order_base_2(num_packets));
@@ -443,26 +443,25 @@ static void mlx5e_get_ringparam(struct net_device *dev,
struct ethtool_ringparam *param)
{
struct mlx5e_priv *priv = netdev_priv(dev);
- int rq_wq_type = priv->params.rq_wq_type;
+ int rq_wq_type = priv->channels.params.rq_wq_type;
param->rx_max_pending = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
1 << mlx5_max_log_rq_size(rq_wq_type));
param->tx_max_pending = 1 << MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE;
param->rx_pending = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
- 1 << priv->params.log_rq_size);
- param->tx_pending = 1 << priv->params.log_sq_size;
+ 1 << priv->channels.params.log_rq_size);
+ param->tx_pending = 1 << priv->channels.params.log_sq_size;
}
static int mlx5e_set_ringparam(struct net_device *dev,
struct ethtool_ringparam *param)
{
struct mlx5e_priv *priv = netdev_priv(dev);
- bool was_opened;
- int rq_wq_type = priv->params.rq_wq_type;
+ int rq_wq_type = priv->channels.params.rq_wq_type;
+ struct mlx5e_channels new_channels = {};
u32 rx_pending_wqes;
u32 min_rq_size;
u32 max_rq_size;
- u16 min_rx_wqes;
u8 log_rq_size;
u8 log_sq_size;
u32 num_mtts;
@@ -500,7 +499,7 @@ static int mlx5e_set_ringparam(struct net_device *dev,
}
num_mtts = MLX5E_REQUIRED_MTTS(rx_pending_wqes);
- if (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ &&
+ if (priv->channels.params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ &&
!MLX5E_VALID_NUM_MTTS(num_mtts)) {
netdev_info(dev, "%s: rx_pending (%d) request can't be satisfied, try to reduce.\n",
__func__, param->rx_pending);
@@ -522,26 +521,29 @@ static int mlx5e_set_ringparam(struct net_device *dev,
log_rq_size = order_base_2(rx_pending_wqes);
log_sq_size = order_base_2(param->tx_pending);
- min_rx_wqes = mlx5_min_rx_wqes(rq_wq_type, rx_pending_wqes);
- if (log_rq_size == priv->params.log_rq_size &&
- log_sq_size == priv->params.log_sq_size &&
- min_rx_wqes == priv->params.min_rx_wqes)
+ if (log_rq_size == priv->channels.params.log_rq_size &&
+ log_sq_size == priv->channels.params.log_sq_size)
return 0;
mutex_lock(&priv->state_lock);
- was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
- if (was_opened)
- mlx5e_close_locked(dev);
+ new_channels.params = priv->channels.params;
+ new_channels.params.log_rq_size = log_rq_size;
+ new_channels.params.log_sq_size = log_sq_size;
- priv->params.log_rq_size = log_rq_size;
- priv->params.log_sq_size = log_sq_size;
- priv->params.min_rx_wqes = min_rx_wqes;
+ if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+ priv->channels.params = new_channels.params;
+ goto unlock;
+ }
- if (was_opened)
- err = mlx5e_open_locked(dev);
+ err = mlx5e_open_channels(priv, &new_channels);
+ if (err)
+ goto unlock;
+ mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+
+unlock:
mutex_unlock(&priv->state_lock);
return err;
@@ -553,7 +555,7 @@ static void mlx5e_get_channels(struct net_device *dev,
struct mlx5e_priv *priv = netdev_priv(dev);
ch->max_combined = priv->profile->max_nch(priv->mdev);
- ch->combined_count = priv->params.num_channels;
+ ch->combined_count = priv->channels.params.num_channels;
}
static int mlx5e_set_channels(struct net_device *dev,
@@ -561,8 +563,8 @@ static int mlx5e_set_channels(struct net_device *dev,
{
struct mlx5e_priv *priv = netdev_priv(dev);
unsigned int count = ch->combined_count;
+ struct mlx5e_channels new_channels = {};
bool arfs_enabled;
- bool was_opened;
int err = 0;
if (!count) {
@@ -571,27 +573,32 @@ static int mlx5e_set_channels(struct net_device *dev,
return -EINVAL;
}
- if (priv->params.num_channels == count)
+ if (priv->channels.params.num_channels == count)
return 0;
mutex_lock(&priv->state_lock);
- was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
- if (was_opened)
- mlx5e_close_locked(dev);
+ new_channels.params = priv->channels.params;
+ new_channels.params.num_channels = count;
+ mlx5e_build_default_indir_rqt(priv->mdev, new_channels.params.indirection_rqt,
+ MLX5E_INDIR_RQT_SIZE, count);
+
+ if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+ priv->channels.params = new_channels.params;
+ goto out;
+ }
+
+ /* Create fresh channels with new parameters */
+ err = mlx5e_open_channels(priv, &new_channels);
+ if (err)
+ goto out;
arfs_enabled = dev->features & NETIF_F_NTUPLE;
if (arfs_enabled)
mlx5e_arfs_disable(priv);
- priv->params.num_channels = count;
- mlx5e_build_default_indir_rqt(priv->mdev, priv->params.indirection_rqt,
- MLX5E_INDIR_RQT_SIZE, count);
-
- if (was_opened)
- err = mlx5e_open_locked(dev);
- if (err)
- goto out;
+ /* Switch to new channels, set new parameters and close old ones */
+ mlx5e_switch_priv_channels(priv, &new_channels, NULL);
if (arfs_enabled) {
err = mlx5e_arfs_enable(priv);
@@ -614,49 +621,24 @@ static int mlx5e_get_coalesce(struct net_device *netdev,
if (!MLX5_CAP_GEN(priv->mdev, cq_moderation))
return -EOPNOTSUPP;
- coal->rx_coalesce_usecs = priv->params.rx_cq_moderation.usec;
- coal->rx_max_coalesced_frames = priv->params.rx_cq_moderation.pkts;
- coal->tx_coalesce_usecs = priv->params.tx_cq_moderation.usec;
- coal->tx_max_coalesced_frames = priv->params.tx_cq_moderation.pkts;
- coal->use_adaptive_rx_coalesce = priv->params.rx_am_enabled;
+ coal->rx_coalesce_usecs = priv->channels.params.rx_cq_moderation.usec;
+ coal->rx_max_coalesced_frames = priv->channels.params.rx_cq_moderation.pkts;
+ coal->tx_coalesce_usecs = priv->channels.params.tx_cq_moderation.usec;
+ coal->tx_max_coalesced_frames = priv->channels.params.tx_cq_moderation.pkts;
+ coal->use_adaptive_rx_coalesce = priv->channels.params.rx_am_enabled;
return 0;
}
-static int mlx5e_set_coalesce(struct net_device *netdev,
- struct ethtool_coalesce *coal)
+static void
+mlx5e_set_priv_channels_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal)
{
- struct mlx5e_priv *priv = netdev_priv(netdev);
struct mlx5_core_dev *mdev = priv->mdev;
- struct mlx5e_channel *c;
- bool restart =
- !!coal->use_adaptive_rx_coalesce != priv->params.rx_am_enabled;
- bool was_opened;
- int err = 0;
int tc;
int i;
- if (!MLX5_CAP_GEN(mdev, cq_moderation))
- return -EOPNOTSUPP;
-
- mutex_lock(&priv->state_lock);
-
- was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
- if (was_opened && restart) {
- mlx5e_close_locked(netdev);
- priv->params.rx_am_enabled = !!coal->use_adaptive_rx_coalesce;
- }
-
- priv->params.tx_cq_moderation.usec = coal->tx_coalesce_usecs;
- priv->params.tx_cq_moderation.pkts = coal->tx_max_coalesced_frames;
- priv->params.rx_cq_moderation.usec = coal->rx_coalesce_usecs;
- priv->params.rx_cq_moderation.pkts = coal->rx_max_coalesced_frames;
-
- if (!was_opened || restart)
- goto out;
-
- for (i = 0; i < priv->params.num_channels; ++i) {
- c = priv->channel[i];
+ for (i = 0; i < priv->channels.num; ++i) {
+ struct mlx5e_channel *c = priv->channels.c[i];
for (tc = 0; tc < c->num_tc; tc++) {
mlx5_core_modify_cq_moderation(mdev,
@@ -669,11 +651,50 @@ static int mlx5e_set_coalesce(struct net_device *netdev,
coal->rx_coalesce_usecs,
coal->rx_max_coalesced_frames);
}
+}
+
+static int mlx5e_set_coalesce(struct net_device *netdev,
+ struct ethtool_coalesce *coal)
+{
+ struct mlx5e_priv *priv = netdev_priv(netdev);
+ struct mlx5_core_dev *mdev = priv->mdev;
+ struct mlx5e_channels new_channels = {};
+ int err = 0;
+ bool reset;
+
+ if (!MLX5_CAP_GEN(mdev, cq_moderation))
+ return -EOPNOTSUPP;
+
+ mutex_lock(&priv->state_lock);
+ new_channels.params = priv->channels.params;
+
+ new_channels.params.tx_cq_moderation.usec = coal->tx_coalesce_usecs;
+ new_channels.params.tx_cq_moderation.pkts = coal->tx_max_coalesced_frames;
+ new_channels.params.rx_cq_moderation.usec = coal->rx_coalesce_usecs;
+ new_channels.params.rx_cq_moderation.pkts = coal->rx_max_coalesced_frames;
+ new_channels.params.rx_am_enabled = !!coal->use_adaptive_rx_coalesce;
+
+ if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+ priv->channels.params = new_channels.params;
+ goto out;
+ }
+ /* we are opened */
+
+ reset = !!coal->use_adaptive_rx_coalesce != priv->channels.params.rx_am_enabled;
+ if (!reset) {
+ mlx5e_set_priv_channels_coalesce(priv, coal);
+ priv->channels.params = new_channels.params;
+ goto out;
+ }
+
+ /* open fresh channels with new coal parameters */
+ err = mlx5e_open_channels(priv, &new_channels);
+ if (err)
+ goto out;
+
+ mlx5e_switch_priv_channels(priv, &new_channels, NULL);
out:
- if (was_opened && restart)
- err = mlx5e_open_locked(netdev);
-
mutex_unlock(&priv->state_lock);
return err;
}
@@ -968,7 +989,7 @@ static u32 mlx5e_get_rxfh_key_size(struct net_device *netdev)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
- return sizeof(priv->params.toeplitz_hash_key);
+ return sizeof(priv->channels.params.toeplitz_hash_key);
}
static u32 mlx5e_get_rxfh_indir_size(struct net_device *netdev)
@@ -982,15 +1003,15 @@ static int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
struct mlx5e_priv *priv = netdev_priv(netdev);
if (indir)
- memcpy(indir, priv->params.indirection_rqt,
- sizeof(priv->params.indirection_rqt));
+ memcpy(indir, priv->channels.params.indirection_rqt,
+ sizeof(priv->channels.params.indirection_rqt));
if (key)
- memcpy(key, priv->params.toeplitz_hash_key,
- sizeof(priv->params.toeplitz_hash_key));
+ memcpy(key, priv->channels.params.toeplitz_hash_key,
+ sizeof(priv->channels.params.toeplitz_hash_key));
if (hfunc)
- *hfunc = priv->params.rss_hfunc;
+ *hfunc = priv->channels.params.rss_hfunc;
return 0;
}
@@ -1006,7 +1027,7 @@ static void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
memset(tirc, 0, ctxlen);
- mlx5e_build_indir_tir_ctx_hash(priv, tirc, tt);
+ mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc);
mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in, inlen);
}
}
@@ -1030,25 +1051,37 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
mutex_lock(&priv->state_lock);
- if (indir) {
- u32 rqtn = priv->indir_rqt.rqtn;
-
- memcpy(priv->params.indirection_rqt, indir,
- sizeof(priv->params.indirection_rqt));
- mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, 0);
- }
-
if (hfunc != ETH_RSS_HASH_NO_CHANGE &&
- hfunc != priv->params.rss_hfunc) {
- priv->params.rss_hfunc = hfunc;
+ hfunc != priv->channels.params.rss_hfunc) {
+ priv->channels.params.rss_hfunc = hfunc;
hash_changed = true;
}
+ if (indir) {
+ memcpy(priv->channels.params.indirection_rqt, indir,
+ sizeof(priv->channels.params.indirection_rqt));
+
+ if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+ u32 rqtn = priv->indir_rqt.rqtn;
+ struct mlx5e_redirect_rqt_param rrp = {
+ .is_rss = true,
+ {
+ .rss = {
+ .hfunc = priv->channels.params.rss_hfunc,
+ .channels = &priv->channels,
+ },
+ },
+ };
+
+ mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, rrp);
+ }
+ }
+
if (key) {
- memcpy(priv->params.toeplitz_hash_key, key,
- sizeof(priv->params.toeplitz_hash_key));
+ memcpy(priv->channels.params.toeplitz_hash_key, key,
+ sizeof(priv->channels.params.toeplitz_hash_key));
hash_changed = hash_changed ||
- priv->params.rss_hfunc == ETH_RSS_HASH_TOP;
+ priv->channels.params.rss_hfunc == ETH_RSS_HASH_TOP;
}
if (hash_changed)
@@ -1069,7 +1102,7 @@ static int mlx5e_get_rxnfc(struct net_device *netdev,
switch (info->cmd) {
case ETHTOOL_GRXRINGS:
- info->data = priv->params.num_channels;
+ info->data = priv->channels.params.num_channels;
break;
case ETHTOOL_GRXCLSRLCNT:
info->rule_cnt = priv->fs.ethtool.tot_num_rules;
@@ -1097,7 +1130,7 @@ static int mlx5e_get_tunable(struct net_device *dev,
switch (tuna->id) {
case ETHTOOL_TX_COPYBREAK:
- *(u32 *)data = priv->params.tx_max_inline;
+ *(u32 *)data = priv->channels.params.tx_max_inline;
break;
default:
err = -EINVAL;
@@ -1113,9 +1146,11 @@ static int mlx5e_set_tunable(struct net_device *dev,
{
struct mlx5e_priv *priv = netdev_priv(dev);
struct mlx5_core_dev *mdev = priv->mdev;
- bool was_opened;
- u32 val;
+ struct mlx5e_channels new_channels = {};
int err = 0;
+ u32 val;
+
+ mutex_lock(&priv->state_lock);
switch (tuna->id) {
case ETHTOOL_TX_COPYBREAK:
@@ -1125,24 +1160,26 @@ static int mlx5e_set_tunable(struct net_device *dev,
break;
}
- mutex_lock(&priv->state_lock);
+ new_channels.params = priv->channels.params;
+ new_channels.params.tx_max_inline = val;
- was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
- if (was_opened)
- mlx5e_close_locked(dev);
+ if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+ priv->channels.params = new_channels.params;
+ break;
+ }
- priv->params.tx_max_inline = val;
+ err = mlx5e_open_channels(priv, &new_channels);
+ if (err)
+ break;
+ mlx5e_switch_priv_channels(priv, &new_channels, NULL);
- if (was_opened)
- err = mlx5e_open_locked(dev);
-
- mutex_unlock(&priv->state_lock);
break;
default:
err = -EINVAL;
break;
}
+ mutex_unlock(&priv->state_lock);
return err;
}
@@ -1442,15 +1479,15 @@ static int set_pflag_rx_cqe_based_moder(struct net_device *netdev, bool enable)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
struct mlx5_core_dev *mdev = priv->mdev;
+ struct mlx5e_channels new_channels = {};
bool rx_mode_changed;
u8 rx_cq_period_mode;
int err = 0;
- bool reset;
rx_cq_period_mode = enable ?
MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
- rx_mode_changed = rx_cq_period_mode != priv->params.rx_cq_period_mode;
+ rx_mode_changed = rx_cq_period_mode != priv->channels.params.rx_cq_period_mode;
if (rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE &&
!MLX5_CAP_GEN(mdev, cq_period_start_from_cqe))
@@ -1459,16 +1496,51 @@ static int set_pflag_rx_cqe_based_moder(struct net_device *netdev, bool enable)
if (!rx_mode_changed)
return 0;
- reset = test_bit(MLX5E_STATE_OPENED, &priv->state);
- if (reset)
- mlx5e_close_locked(netdev);
+ new_channels.params = priv->channels.params;
+ mlx5e_set_rx_cq_mode_params(&new_channels.params, rx_cq_period_mode);
- mlx5e_set_rx_cq_mode_params(&priv->params, rx_cq_period_mode);
+ if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+ priv->channels.params = new_channels.params;
+ return 0;
+ }
- if (reset)
- err = mlx5e_open_locked(netdev);
+ err = mlx5e_open_channels(priv, &new_channels);
+ if (err)
+ return err;
- return err;
+ mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+ return 0;
+}
+
+int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val)
+{
+ bool curr_val = MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS);
+ struct mlx5e_channels new_channels = {};
+ int err = 0;
+
+ if (!MLX5_CAP_GEN(priv->mdev, cqe_compression))
+ return new_val ? -EOPNOTSUPP : 0;
+
+ if (curr_val == new_val)
+ return 0;
+
+ new_channels.params = priv->channels.params;
+ MLX5E_SET_PFLAG(&new_channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS, new_val);
+
+ mlx5e_set_rq_type_params(priv->mdev, &new_channels.params,
+ new_channels.params.rq_wq_type);
+
+ if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+ priv->channels.params = new_channels.params;
+ return 0;
+ }
+
+ err = mlx5e_open_channels(priv, &new_channels);
+ if (err)
+ return err;
+
+ mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+ return 0;
}
static int set_pflag_rx_cqe_compress(struct net_device *netdev,
@@ -1486,8 +1558,7 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev,
}
mlx5e_modify_rx_cqe_compression_locked(priv, enable);
- priv->params.rx_cqe_compress_def = enable;
- mlx5e_set_rq_type_params(priv, priv->params.rq_wq_type);
+ priv->channels.params.rx_cqe_compress_def = enable;
return 0;
}
@@ -1499,7 +1570,7 @@ static int mlx5e_handle_pflag(struct net_device *netdev,
{
struct mlx5e_priv *priv = netdev_priv(netdev);
bool enable = !!(wanted_flags & flag);
- u32 changes = wanted_flags ^ priv->params.pflags;
+ u32 changes = wanted_flags ^ priv->channels.params.pflags;
int err;
if (!(changes & flag))
@@ -1512,7 +1583,7 @@ static int mlx5e_handle_pflag(struct net_device *netdev,
return err;
}
- MLX5E_SET_PFLAG(priv, flag, enable);
+ MLX5E_SET_PFLAG(&priv->channels.params, flag, enable);
return 0;
}
@@ -1541,7 +1612,7 @@ static u32 mlx5e_get_priv_flags(struct net_device *netdev)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
- return priv->params.pflags;
+ return priv->channels.params.pflags;
}
static int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index f2762e4..5376d69 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -159,14 +159,10 @@ static int __mlx5e_add_vlan_rule(struct mlx5e_priv *priv,
enum mlx5e_vlan_rule_type rule_type,
u16 vid, struct mlx5_flow_spec *spec)
{
- struct mlx5_flow_act flow_act = {
- .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- .flow_tag = MLX5_FS_DEFAULT_FLOW_TAG,
- .encap_id = 0,
- };
struct mlx5_flow_table *ft = priv->fs.vlan.ft.t;
struct mlx5_flow_destination dest;
struct mlx5_flow_handle **rule_p;
+ MLX5_DECLARE_FLOW_ACT(flow_act);
int err = 0;
dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
@@ -659,11 +655,7 @@ mlx5e_generate_ttc_rule(struct mlx5e_priv *priv,
u16 etype,
u8 proto)
{
- struct mlx5_flow_act flow_act = {
- .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- .flow_tag = MLX5_FS_DEFAULT_FLOW_TAG,
- .encap_id = 0,
- };
+ MLX5_DECLARE_FLOW_ACT(flow_act);
struct mlx5_flow_handle *rule;
struct mlx5_flow_spec *spec;
int err = 0;
@@ -848,13 +840,9 @@ static void mlx5e_del_l2_flow_rule(struct mlx5e_priv *priv,
static int mlx5e_add_l2_flow_rule(struct mlx5e_priv *priv,
struct mlx5e_l2_rule *ai, int type)
{
- struct mlx5_flow_act flow_act = {
- .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- .flow_tag = MLX5_FS_DEFAULT_FLOW_TAG,
- .encap_id = 0,
- };
struct mlx5_flow_table *ft = priv->fs.l2.ft.t;
struct mlx5_flow_destination dest;
+ MLX5_DECLARE_FLOW_ACT(flow_act);
struct mlx5_flow_spec *spec;
int err = 0;
u8 *mc_dmac;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index d55fff0..e73c97f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -390,7 +390,7 @@ static int validate_flow(struct mlx5e_priv *priv,
if (fs->location >= MAX_NUM_OF_ETHTOOL_RULES)
return -EINVAL;
- if (fs->ring_cookie >= priv->params.num_channels &&
+ if (fs->ring_cookie >= priv->channels.params.num_channels &&
fs->ring_cookie != RX_CLS_FLOW_DISC)
return -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 8ef64c4..8b7b7e6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -44,15 +44,11 @@
struct mlx5e_rq_param {
u32 rqc[MLX5_ST_SZ_DW(rqc)];
struct mlx5_wq_param wq;
- bool am_enabled;
};
struct mlx5e_sq_param {
u32 sqc[MLX5_ST_SZ_DW(sqc)];
struct mlx5_wq_param wq;
- u16 max_inline;
- u8 min_inline_mode;
- enum mlx5e_sq_type type;
};
struct mlx5e_cq_param {
@@ -79,49 +75,47 @@ static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
MLX5_CAP_ETH(mdev, reg_umr_sq);
}
-void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type)
+void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev,
+ struct mlx5e_params *params, u8 rq_type)
{
- priv->params.rq_wq_type = rq_type;
- priv->params.lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
- switch (priv->params.rq_wq_type) {
+ params->rq_wq_type = rq_type;
+ params->lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
+ switch (params->rq_wq_type) {
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
- priv->params.log_rq_size = is_kdump_kernel() ?
+ params->log_rq_size = is_kdump_kernel() ?
MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW :
MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE_MPW;
- priv->params.mpwqe_log_stride_sz =
- MLX5E_GET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS) ?
- MLX5_MPWRQ_CQE_CMPRS_LOG_STRIDE_SZ(priv->mdev) :
- MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(priv->mdev);
- priv->params.mpwqe_log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ -
- priv->params.mpwqe_log_stride_sz;
+ params->mpwqe_log_stride_sz =
+ MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS) ?
+ MLX5_MPWRQ_CQE_CMPRS_LOG_STRIDE_SZ(mdev) :
+ MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev);
+ params->mpwqe_log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ -
+ params->mpwqe_log_stride_sz;
break;
default: /* MLX5_WQ_TYPE_LINKED_LIST */
- priv->params.log_rq_size = is_kdump_kernel() ?
+ params->log_rq_size = is_kdump_kernel() ?
MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE :
MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE;
/* Extra room needed for build_skb */
- priv->params.lro_wqe_sz -= MLX5_RX_HEADROOM +
+ params->lro_wqe_sz -= MLX5_RX_HEADROOM +
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
}
- priv->params.min_rx_wqes = mlx5_min_rx_wqes(priv->params.rq_wq_type,
- BIT(priv->params.log_rq_size));
- mlx5_core_info(priv->mdev,
- "MLX5E: StrdRq(%d) RqSz(%ld) StrdSz(%ld) RxCqeCmprss(%d)\n",
- priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ,
- BIT(priv->params.log_rq_size),
- BIT(priv->params.mpwqe_log_stride_sz),
- MLX5E_GET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS));
+ mlx5_core_info(mdev, "MLX5E: StrdRq(%d) RqSz(%ld) StrdSz(%ld) RxCqeCmprss(%d)\n",
+ params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ,
+ BIT(params->log_rq_size),
+ BIT(params->mpwqe_log_stride_sz),
+ MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS));
}
-static void mlx5e_set_rq_priv_params(struct mlx5e_priv *priv)
+static void mlx5e_set_rq_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
{
- u8 rq_type = mlx5e_check_fragmented_striding_rq_cap(priv->mdev) &&
- !priv->xdp_prog ?
+ u8 rq_type = mlx5e_check_fragmented_striding_rq_cap(mdev) &&
+ !params->xdp_prog ?
MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ :
MLX5_WQ_TYPE_LINKED_LIST;
- mlx5e_set_rq_type_params(priv, rq_type);
+ mlx5e_set_rq_type_params(mdev, params, rq_type);
}
static void mlx5e_update_carrier(struct mlx5e_priv *priv)
@@ -181,8 +175,10 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
int i, j;
memset(s, 0, sizeof(*s));
- for (i = 0; i < priv->params.num_channels; i++) {
- rq_stats = &priv->channel[i]->rq.stats;
+ for (i = 0; i < priv->channels.num; i++) {
+ struct mlx5e_channel *c = priv->channels.c[i];
+
+ rq_stats = &c->rq.stats;
s->rx_packets += rq_stats->packets;
s->rx_bytes += rq_stats->bytes;
@@ -204,8 +200,8 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
s->rx_cache_empty += rq_stats->cache_empty;
s->rx_cache_busy += rq_stats->cache_busy;
- for (j = 0; j < priv->params.num_tc; j++) {
- sq_stats = &priv->channel[i]->sq[j].stats;
+ for (j = 0; j < priv->channels.params.num_tc; j++) {
+ sq_stats = &c->sq[j].stats;
s->tx_packets += sq_stats->packets;
s->tx_bytes += sq_stats->bytes;
@@ -402,8 +398,10 @@ static inline int mlx5e_get_wqe_mtt_sz(void)
MLX5_UMR_MTT_ALIGNMENT);
}
-static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq, struct mlx5e_sq *sq,
- struct mlx5e_umr_wqe *wqe, u16 ix)
+static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
+ struct mlx5e_icosq *sq,
+ struct mlx5e_umr_wqe *wqe,
+ u16 ix)
{
struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
struct mlx5_wqe_umr_ctrl_seg *ucseg = &wqe->uctrl;
@@ -493,11 +491,10 @@ static void mlx5e_rq_free_mpwqe_info(struct mlx5e_rq *rq)
kfree(rq->mpwqe.info);
}
-static int mlx5e_create_umr_mkey(struct mlx5e_priv *priv,
+static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
u64 npages, u8 page_shift,
struct mlx5_core_mkey *umr_mkey)
{
- struct mlx5_core_dev *mdev = priv->mdev;
int inlen = MLX5_ST_SZ_BYTES(create_mkey_in);
void *mkc;
u32 *in;
@@ -531,21 +528,20 @@ static int mlx5e_create_umr_mkey(struct mlx5e_priv *priv,
return err;
}
-static int mlx5e_create_rq_umr_mkey(struct mlx5e_rq *rq)
+static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq *rq)
{
- struct mlx5e_priv *priv = rq->priv;
- u64 num_mtts = MLX5E_REQUIRED_MTTS(BIT(priv->params.log_rq_size));
+ u64 num_mtts = MLX5E_REQUIRED_MTTS(mlx5_wq_ll_get_size(&rq->wq));
- return mlx5e_create_umr_mkey(priv, num_mtts, PAGE_SHIFT, &rq->umr_mkey);
+ return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey);
}
-static int mlx5e_create_rq(struct mlx5e_channel *c,
- struct mlx5e_rq_param *param,
- struct mlx5e_rq *rq)
+static int mlx5e_alloc_rq(struct mlx5e_channel *c,
+ struct mlx5e_params *params,
+ struct mlx5e_rq_param *rqp,
+ struct mlx5e_rq *rq)
{
- struct mlx5e_priv *priv = c->priv;
- struct mlx5_core_dev *mdev = priv->mdev;
- void *rqc = param->rqc;
+ struct mlx5_core_dev *mdev = c->mdev;
+ void *rqc = rqp->rqc;
void *rqc_wq = MLX5_ADDR_OF(rqc, rqc, wq);
u32 byte_count;
u32 frag_sz;
@@ -554,9 +550,9 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
int err;
int i;
- param->wq.db_numa_node = cpu_to_node(c->cpu);
+ rqp->wq.db_numa_node = cpu_to_node(c->cpu);
- err = mlx5_wq_ll_create(mdev, ¶m->wq, rqc_wq, &rq->wq,
+ err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->wq,
&rq->wq_ctrl);
if (err)
return err;
@@ -565,15 +561,15 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
wq_sz = mlx5_wq_ll_get_size(&rq->wq);
- rq->wq_type = priv->params.rq_wq_type;
+ rq->wq_type = params->rq_wq_type;
rq->pdev = c->pdev;
rq->netdev = c->netdev;
- rq->tstamp = &priv->tstamp;
+ rq->tstamp = c->tstamp;
rq->channel = c;
rq->ix = c->ix;
- rq->priv = c->priv;
+ rq->mdev = mdev;
- rq->xdp_prog = priv->xdp_prog ? bpf_prog_inc(priv->xdp_prog) : NULL;
+ rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL;
if (IS_ERR(rq->xdp_prog)) {
err = PTR_ERR(rq->xdp_prog);
rq->xdp_prog = NULL;
@@ -588,9 +584,9 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
rq->rx_headroom = MLX5_RX_HEADROOM;
}
- switch (priv->params.rq_wq_type) {
+ switch (rq->wq_type) {
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
- if (mlx5e_is_vf_vport_rep(priv)) {
+ if (mlx5e_is_vf_vport_rep(c->priv)) {
err = -EINVAL;
goto err_rq_wq_destroy;
}
@@ -599,13 +595,13 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
rq->alloc_wqe = mlx5e_alloc_rx_mpwqe;
rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
- rq->mpwqe_stride_sz = BIT(priv->params.mpwqe_log_stride_sz);
- rq->mpwqe_num_strides = BIT(priv->params.mpwqe_log_num_strides);
+ rq->mpwqe_stride_sz = BIT(params->mpwqe_log_stride_sz);
+ rq->mpwqe_num_strides = BIT(params->mpwqe_log_num_strides);
rq->buff.wqe_sz = rq->mpwqe_stride_sz * rq->mpwqe_num_strides;
byte_count = rq->buff.wqe_sz;
- err = mlx5e_create_rq_umr_mkey(rq);
+ err = mlx5e_create_rq_umr_mkey(mdev, rq);
if (err)
goto err_rq_wq_destroy;
rq->mkey_be = cpu_to_be32(rq->umr_mkey.key);
@@ -622,7 +618,7 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
goto err_rq_wq_destroy;
}
- if (mlx5e_is_vf_vport_rep(priv))
+ if (mlx5e_is_vf_vport_rep(c->priv))
rq->handle_rx_cqe = mlx5e_handle_rx_cqe_rep;
else
rq->handle_rx_cqe = mlx5e_handle_rx_cqe;
@@ -630,9 +626,9 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
rq->alloc_wqe = mlx5e_alloc_rx_wqe;
rq->dealloc_wqe = mlx5e_dealloc_rx_wqe;
- rq->buff.wqe_sz = (priv->params.lro_en) ?
- priv->params.lro_wqe_sz :
- MLX5E_SW2HW_MTU(priv->netdev->mtu);
+ rq->buff.wqe_sz = params->lro_en ?
+ params->lro_wqe_sz :
+ MLX5E_SW2HW_MTU(c->netdev->mtu);
byte_count = rq->buff.wqe_sz;
/* calc the required page order */
@@ -656,8 +652,7 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
}
INIT_WORK(&rq->am.work, mlx5e_rx_am_work);
- rq->am.mode = priv->params.rx_cq_period_mode;
-
+ rq->am.mode = params->rx_cq_period_mode;
rq->page_cache.head = 0;
rq->page_cache.tail = 0;
@@ -674,7 +669,7 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
return err;
}
-static void mlx5e_destroy_rq(struct mlx5e_rq *rq)
+static void mlx5e_free_rq(struct mlx5e_rq *rq)
{
int i;
@@ -684,7 +679,7 @@ static void mlx5e_destroy_rq(struct mlx5e_rq *rq)
switch (rq->wq_type) {
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
mlx5e_rq_free_mpwqe_info(rq);
- mlx5_core_destroy_mkey(rq->priv->mdev, &rq->umr_mkey);
+ mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey);
break;
default: /* MLX5_WQ_TYPE_LINKED_LIST */
kfree(rq->dma_info);
@@ -699,10 +694,10 @@ static void mlx5e_destroy_rq(struct mlx5e_rq *rq)
mlx5_wq_destroy(&rq->wq_ctrl);
}
-static int mlx5e_enable_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param)
+static int mlx5e_create_rq(struct mlx5e_rq *rq,
+ struct mlx5e_rq_param *param)
{
- struct mlx5e_priv *priv = rq->priv;
- struct mlx5_core_dev *mdev = priv->mdev;
+ struct mlx5_core_dev *mdev = rq->mdev;
void *in;
void *rqc;
@@ -723,7 +718,6 @@ static int mlx5e_enable_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param)
MLX5_SET(rqc, rqc, cqn, rq->cq.mcq.cqn);
MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RST);
- MLX5_SET(rqc, rqc, vsd, priv->params.vlan_strip_disable);
MLX5_SET(wq, wq, log_wq_pg_sz, rq->wq_ctrl.buf.page_shift -
MLX5_ADAPTER_PAGE_SHIFT);
MLX5_SET64(wq, wq, dbr_addr, rq->wq_ctrl.db.dma);
@@ -742,8 +736,7 @@ static int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state,
int next_state)
{
struct mlx5e_channel *c = rq->channel;
- struct mlx5e_priv *priv = c->priv;
- struct mlx5_core_dev *mdev = priv->mdev;
+ struct mlx5_core_dev *mdev = c->mdev;
void *in;
void *rqc;
@@ -767,7 +760,7 @@ static int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state,
return err;
}
-static int mlx5e_modify_rq_vsd(struct mlx5e_rq *rq, bool vsd)
+static int mlx5e_modify_rq_scatter_fcs(struct mlx5e_rq *rq, bool enable)
{
struct mlx5e_channel *c = rq->channel;
struct mlx5e_priv *priv = c->priv;
@@ -787,6 +780,35 @@ static int mlx5e_modify_rq_vsd(struct mlx5e_rq *rq, bool vsd)
MLX5_SET(modify_rq_in, in, rq_state, MLX5_RQC_STATE_RDY);
MLX5_SET64(modify_rq_in, in, modify_bitmask,
+ MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_SCATTER_FCS);
+ MLX5_SET(rqc, rqc, scatter_fcs, enable);
+ MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RDY);
+
+ err = mlx5_core_modify_rq(mdev, rq->rqn, in, inlen);
+
+ kvfree(in);
+
+ return err;
+}
+
+static int mlx5e_modify_rq_vsd(struct mlx5e_rq *rq, bool vsd)
+{
+ struct mlx5e_channel *c = rq->channel;
+ struct mlx5_core_dev *mdev = c->mdev;
+ void *in;
+ void *rqc;
+ int inlen;
+ int err;
+
+ inlen = MLX5_ST_SZ_BYTES(modify_rq_in);
+ in = mlx5_vzalloc(inlen);
+ if (!in)
+ return -ENOMEM;
+
+ rqc = MLX5_ADDR_OF(modify_rq_in, in, ctx);
+
+ MLX5_SET(modify_rq_in, in, rq_state, MLX5_RQC_STATE_RDY);
+ MLX5_SET64(modify_rq_in, in, modify_bitmask,
MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_VSD);
MLX5_SET(rqc, rqc, vsd, vsd);
MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RDY);
@@ -798,25 +820,28 @@ static int mlx5e_modify_rq_vsd(struct mlx5e_rq *rq, bool vsd)
return err;
}
-static void mlx5e_disable_rq(struct mlx5e_rq *rq)
+static void mlx5e_destroy_rq(struct mlx5e_rq *rq)
{
- mlx5_core_destroy_rq(rq->priv->mdev, rq->rqn);
+ mlx5_core_destroy_rq(rq->mdev, rq->rqn);
}
static int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq)
{
unsigned long exp_time = jiffies + msecs_to_jiffies(20000);
struct mlx5e_channel *c = rq->channel;
- struct mlx5e_priv *priv = c->priv;
+
struct mlx5_wq_ll *wq = &rq->wq;
+ u16 min_wqes = mlx5_min_rx_wqes(rq->wq_type, mlx5_wq_ll_get_size(wq));
while (time_before(jiffies, exp_time)) {
- if (wq->cur_sz >= priv->params.min_rx_wqes)
+ if (wq->cur_sz >= min_wqes)
return 0;
msleep(20);
}
+ netdev_warn(c->netdev, "Failed to get min RX wqes on RQN[0x%x] wq cur_sz(%d) min_rx_wqes(%d)\n",
+ rq->rqn, wq->cur_sz, min_wqes);
return -ETIMEDOUT;
}
@@ -842,83 +867,128 @@ static void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
}
static int mlx5e_open_rq(struct mlx5e_channel *c,
+ struct mlx5e_params *params,
struct mlx5e_rq_param *param,
struct mlx5e_rq *rq)
{
- struct mlx5e_sq *sq = &c->icosq;
- u16 pi = sq->pc & sq->wq.sz_m1;
int err;
- err = mlx5e_create_rq(c, param, rq);
+ err = mlx5e_alloc_rq(c, params, param, rq);
if (err)
return err;
- err = mlx5e_enable_rq(rq, param);
+ err = mlx5e_create_rq(rq, param);
+ if (err)
+ goto err_free_rq;
+
+ err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RST, MLX5_RQC_STATE_RDY);
if (err)
goto err_destroy_rq;
- set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
- err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RST, MLX5_RQC_STATE_RDY);
- if (err)
- goto err_disable_rq;
-
- if (param->am_enabled)
+ if (params->rx_am_enabled)
set_bit(MLX5E_RQ_STATE_AM, &c->rq.state);
- sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP;
- sq->db.ico_wqe[pi].num_wqebbs = 1;
- mlx5e_send_nop(sq, true); /* trigger mlx5e_post_rx_wqes() */
-
return 0;
-err_disable_rq:
- clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
- mlx5e_disable_rq(rq);
err_destroy_rq:
mlx5e_destroy_rq(rq);
+err_free_rq:
+ mlx5e_free_rq(rq);
return err;
}
-static void mlx5e_close_rq(struct mlx5e_rq *rq)
+static void mlx5e_activate_rq(struct mlx5e_rq *rq)
+{
+ struct mlx5e_icosq *sq = &rq->channel->icosq;
+ u16 pi = sq->pc & sq->wq.sz_m1;
+ struct mlx5e_tx_wqe *nopwqe;
+
+ set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
+ sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP;
+ sq->db.ico_wqe[pi].num_wqebbs = 1;
+ nopwqe = mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc);
+ mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &nopwqe->ctrl);
+}
+
+static void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
{
clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */
- cancel_work_sync(&rq->am.work);
-
- mlx5e_disable_rq(rq);
- mlx5e_free_rx_descs(rq);
- mlx5e_destroy_rq(rq);
}
-static void mlx5e_free_sq_xdp_db(struct mlx5e_sq *sq)
+static void mlx5e_close_rq(struct mlx5e_rq *rq)
{
- kfree(sq->db.xdp.di);
- kfree(sq->db.xdp.wqe_info);
+ cancel_work_sync(&rq->am.work);
+ mlx5e_destroy_rq(rq);
+ mlx5e_free_rx_descs(rq);
+ mlx5e_free_rq(rq);
}
-static int mlx5e_alloc_sq_xdp_db(struct mlx5e_sq *sq, int numa)
+static void mlx5e_free_xdpsq_db(struct mlx5e_xdpsq *sq)
+{
+ kfree(sq->db.di);
+}
+
+static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa)
{
int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
- sq->db.xdp.di = kzalloc_node(sizeof(*sq->db.xdp.di) * wq_sz,
+ sq->db.di = kzalloc_node(sizeof(*sq->db.di) * wq_sz,
GFP_KERNEL, numa);
- sq->db.xdp.wqe_info = kzalloc_node(sizeof(*sq->db.xdp.wqe_info) * wq_sz,
- GFP_KERNEL, numa);
- if (!sq->db.xdp.di || !sq->db.xdp.wqe_info) {
- mlx5e_free_sq_xdp_db(sq);
+ if (!sq->db.di) {
+ mlx5e_free_xdpsq_db(sq);
return -ENOMEM;
}
return 0;
}
-static void mlx5e_free_sq_ico_db(struct mlx5e_sq *sq)
+static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
+ struct mlx5e_params *params,
+ struct mlx5e_sq_param *param,
+ struct mlx5e_xdpsq *sq)
+{
+ void *sqc_wq = MLX5_ADDR_OF(sqc, param->sqc, wq);
+ struct mlx5_core_dev *mdev = c->mdev;
+ int err;
+
+ sq->pdev = c->pdev;
+ sq->mkey_be = c->mkey_be;
+ sq->channel = c;
+ sq->uar_map = mdev->mlx5e_res.bfreg.map;
+ sq->min_inline_mode = params->tx_min_inline_mode;
+
+ param->wq.db_numa_node = cpu_to_node(c->cpu);
+ err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
+ if (err)
+ return err;
+ sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
+
+ err = mlx5e_alloc_xdpsq_db(sq, cpu_to_node(c->cpu));
+ if (err)
+ goto err_sq_wq_destroy;
+
+ return 0;
+
+err_sq_wq_destroy:
+ mlx5_wq_destroy(&sq->wq_ctrl);
+
+ return err;
+}
+
+static void mlx5e_free_xdpsq(struct mlx5e_xdpsq *sq)
+{
+ mlx5e_free_xdpsq_db(sq);
+ mlx5_wq_destroy(&sq->wq_ctrl);
+}
+
+static void mlx5e_free_icosq_db(struct mlx5e_icosq *sq)
{
kfree(sq->db.ico_wqe);
}
-static int mlx5e_alloc_sq_ico_db(struct mlx5e_sq *sq, int numa)
+static int mlx5e_alloc_icosq_db(struct mlx5e_icosq *sq, int numa)
{
u8 wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
@@ -930,26 +1000,65 @@ static int mlx5e_alloc_sq_ico_db(struct mlx5e_sq *sq, int numa)
return 0;
}
-static void mlx5e_free_sq_txq_db(struct mlx5e_sq *sq)
+static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
+ struct mlx5e_sq_param *param,
+ struct mlx5e_icosq *sq)
{
- kfree(sq->db.txq.wqe_info);
- kfree(sq->db.txq.dma_fifo);
- kfree(sq->db.txq.skb);
+ void *sqc_wq = MLX5_ADDR_OF(sqc, param->sqc, wq);
+ struct mlx5_core_dev *mdev = c->mdev;
+ int err;
+
+ sq->pdev = c->pdev;
+ sq->mkey_be = c->mkey_be;
+ sq->channel = c;
+ sq->uar_map = mdev->mlx5e_res.bfreg.map;
+
+ param->wq.db_numa_node = cpu_to_node(c->cpu);
+ err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
+ if (err)
+ return err;
+ sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
+
+ err = mlx5e_alloc_icosq_db(sq, cpu_to_node(c->cpu));
+ if (err)
+ goto err_sq_wq_destroy;
+
+ sq->edge = (sq->wq.sz_m1 + 1) - MLX5E_ICOSQ_MAX_WQEBBS;
+
+ return 0;
+
+err_sq_wq_destroy:
+ mlx5_wq_destroy(&sq->wq_ctrl);
+
+ return err;
}
-static int mlx5e_alloc_sq_txq_db(struct mlx5e_sq *sq, int numa)
+static void mlx5e_free_icosq(struct mlx5e_icosq *sq)
+{
+ mlx5e_free_icosq_db(sq);
+ mlx5_wq_destroy(&sq->wq_ctrl);
+}
+
+static void mlx5e_free_txqsq_db(struct mlx5e_txqsq *sq)
+{
+ kfree(sq->db.wqe_info);
+ kfree(sq->db.dma_fifo);
+ kfree(sq->db.skb);
+}
+
+static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa)
{
int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
int df_sz = wq_sz * MLX5_SEND_WQEBB_NUM_DS;
- sq->db.txq.skb = kzalloc_node(wq_sz * sizeof(*sq->db.txq.skb),
+ sq->db.skb = kzalloc_node(wq_sz * sizeof(*sq->db.skb),
GFP_KERNEL, numa);
- sq->db.txq.dma_fifo = kzalloc_node(df_sz * sizeof(*sq->db.txq.dma_fifo),
+ sq->db.dma_fifo = kzalloc_node(df_sz * sizeof(*sq->db.dma_fifo),
GFP_KERNEL, numa);
- sq->db.txq.wqe_info = kzalloc_node(wq_sz * sizeof(*sq->db.txq.wqe_info),
+ sq->db.wqe_info = kzalloc_node(wq_sz * sizeof(*sq->db.wqe_info),
GFP_KERNEL, numa);
- if (!sq->db.txq.skb || !sq->db.txq.dma_fifo || !sq->db.txq.wqe_info) {
- mlx5e_free_sq_txq_db(sq);
+ if (!sq->db.skb || !sq->db.dma_fifo || !sq->db.wqe_info) {
+ mlx5e_free_txqsq_db(sq);
return -ENOMEM;
}
@@ -958,127 +1067,64 @@ static int mlx5e_alloc_sq_txq_db(struct mlx5e_sq *sq, int numa)
return 0;
}
-static void mlx5e_free_sq_db(struct mlx5e_sq *sq)
+static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
+ int txq_ix,
+ struct mlx5e_params *params,
+ struct mlx5e_sq_param *param,
+ struct mlx5e_txqsq *sq)
{
- switch (sq->type) {
- case MLX5E_SQ_TXQ:
- mlx5e_free_sq_txq_db(sq);
- break;
- case MLX5E_SQ_ICO:
- mlx5e_free_sq_ico_db(sq);
- break;
- case MLX5E_SQ_XDP:
- mlx5e_free_sq_xdp_db(sq);
- break;
- }
-}
-
-static int mlx5e_alloc_sq_db(struct mlx5e_sq *sq, int numa)
-{
- switch (sq->type) {
- case MLX5E_SQ_TXQ:
- return mlx5e_alloc_sq_txq_db(sq, numa);
- case MLX5E_SQ_ICO:
- return mlx5e_alloc_sq_ico_db(sq, numa);
- case MLX5E_SQ_XDP:
- return mlx5e_alloc_sq_xdp_db(sq, numa);
- }
-
- return 0;
-}
-
-static int mlx5e_sq_get_max_wqebbs(u8 sq_type)
-{
- switch (sq_type) {
- case MLX5E_SQ_ICO:
- return MLX5E_ICOSQ_MAX_WQEBBS;
- case MLX5E_SQ_XDP:
- return MLX5E_XDP_TX_WQEBBS;
- }
- return MLX5_SEND_WQE_MAX_WQEBBS;
-}
-
-static int mlx5e_create_sq(struct mlx5e_channel *c,
- int tc,
- struct mlx5e_sq_param *param,
- struct mlx5e_sq *sq)
-{
- struct mlx5e_priv *priv = c->priv;
- struct mlx5_core_dev *mdev = priv->mdev;
-
- void *sqc = param->sqc;
- void *sqc_wq = MLX5_ADDR_OF(sqc, sqc, wq);
+ void *sqc_wq = MLX5_ADDR_OF(sqc, param->sqc, wq);
+ struct mlx5_core_dev *mdev = c->mdev;
int err;
- sq->type = param->type;
sq->pdev = c->pdev;
- sq->tstamp = &priv->tstamp;
+ sq->tstamp = c->tstamp;
sq->mkey_be = c->mkey_be;
sq->channel = c;
- sq->tc = tc;
+ sq->txq_ix = txq_ix;
+ sq->uar_map = mdev->mlx5e_res.bfreg.map;
+ sq->max_inline = params->tx_max_inline;
+ sq->min_inline_mode = params->tx_min_inline_mode;
- err = mlx5_alloc_bfreg(mdev, &sq->bfreg, MLX5_CAP_GEN(mdev, bf), false);
+ param->wq.db_numa_node = cpu_to_node(c->cpu);
+ err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
if (err)
return err;
+ sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
- sq->uar_map = sq->bfreg.map;
- param->wq.db_numa_node = cpu_to_node(c->cpu);
-
- err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq,
- &sq->wq_ctrl);
- if (err)
- goto err_unmap_free_uar;
-
- sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
- if (sq->bfreg.wc)
- set_bit(MLX5E_SQ_STATE_BF_ENABLE, &sq->state);
-
- sq->bf_buf_size = (1 << MLX5_CAP_GEN(mdev, log_bf_reg_size)) / 2;
- sq->max_inline = param->max_inline;
- sq->min_inline_mode = param->min_inline_mode;
-
- err = mlx5e_alloc_sq_db(sq, cpu_to_node(c->cpu));
+ err = mlx5e_alloc_txqsq_db(sq, cpu_to_node(c->cpu));
if (err)
goto err_sq_wq_destroy;
- if (sq->type == MLX5E_SQ_TXQ) {
- int txq_ix;
-
- txq_ix = c->ix + tc * priv->params.num_channels;
- sq->txq = netdev_get_tx_queue(priv->netdev, txq_ix);
- priv->txq_to_sq_map[txq_ix] = sq;
- }
-
- sq->edge = (sq->wq.sz_m1 + 1) - mlx5e_sq_get_max_wqebbs(sq->type);
- sq->bf_budget = MLX5E_SQ_BF_BUDGET;
+ sq->edge = (sq->wq.sz_m1 + 1) - MLX5_SEND_WQE_MAX_WQEBBS;
return 0;
err_sq_wq_destroy:
mlx5_wq_destroy(&sq->wq_ctrl);
-err_unmap_free_uar:
- mlx5_free_bfreg(mdev, &sq->bfreg);
-
return err;
}
-static void mlx5e_destroy_sq(struct mlx5e_sq *sq)
+static void mlx5e_free_txqsq(struct mlx5e_txqsq *sq)
{
- struct mlx5e_channel *c = sq->channel;
- struct mlx5e_priv *priv = c->priv;
-
- mlx5e_free_sq_db(sq);
+ mlx5e_free_txqsq_db(sq);
mlx5_wq_destroy(&sq->wq_ctrl);
- mlx5_free_bfreg(priv->mdev, &sq->bfreg);
}
-static int mlx5e_enable_sq(struct mlx5e_sq *sq, struct mlx5e_sq_param *param)
-{
- struct mlx5e_channel *c = sq->channel;
- struct mlx5e_priv *priv = c->priv;
- struct mlx5_core_dev *mdev = priv->mdev;
+struct mlx5e_create_sq_param {
+ struct mlx5_wq_ctrl *wq_ctrl;
+ u32 cqn;
+ u32 tisn;
+ u8 tis_lst_sz;
+ u8 min_inline_mode;
+};
+static int mlx5e_create_sq(struct mlx5_core_dev *mdev,
+ struct mlx5e_sq_param *param,
+ struct mlx5e_create_sq_param *csp,
+ u32 *sqn)
+{
void *in;
void *sqc;
void *wq;
@@ -1086,7 +1132,7 @@ static int mlx5e_enable_sq(struct mlx5e_sq *sq, struct mlx5e_sq_param *param)
int err;
inlen = MLX5_ST_SZ_BYTES(create_sq_in) +
- sizeof(u64) * sq->wq_ctrl.buf.npages;
+ sizeof(u64) * csp->wq_ctrl->buf.npages;
in = mlx5_vzalloc(inlen);
if (!in)
return -ENOMEM;
@@ -1095,40 +1141,40 @@ static int mlx5e_enable_sq(struct mlx5e_sq *sq, struct mlx5e_sq_param *param)
wq = MLX5_ADDR_OF(sqc, sqc, wq);
memcpy(sqc, param->sqc, sizeof(param->sqc));
-
- MLX5_SET(sqc, sqc, tis_num_0, param->type == MLX5E_SQ_ICO ?
- 0 : priv->tisn[sq->tc]);
- MLX5_SET(sqc, sqc, cqn, sq->cq.mcq.cqn);
+ MLX5_SET(sqc, sqc, tis_lst_sz, csp->tis_lst_sz);
+ MLX5_SET(sqc, sqc, tis_num_0, csp->tisn);
+ MLX5_SET(sqc, sqc, cqn, csp->cqn);
if (MLX5_CAP_ETH(mdev, wqe_inline_mode) == MLX5_CAP_INLINE_MODE_VPORT_CONTEXT)
- MLX5_SET(sqc, sqc, min_wqe_inline_mode, sq->min_inline_mode);
+ MLX5_SET(sqc, sqc, min_wqe_inline_mode, csp->min_inline_mode);
- MLX5_SET(sqc, sqc, state, MLX5_SQC_STATE_RST);
- MLX5_SET(sqc, sqc, tis_lst_sz, param->type == MLX5E_SQ_ICO ? 0 : 1);
+ MLX5_SET(sqc, sqc, state, MLX5_SQC_STATE_RST);
MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC);
- MLX5_SET(wq, wq, uar_page, sq->bfreg.index);
- MLX5_SET(wq, wq, log_wq_pg_sz, sq->wq_ctrl.buf.page_shift -
+ MLX5_SET(wq, wq, uar_page, mdev->mlx5e_res.bfreg.index);
+ MLX5_SET(wq, wq, log_wq_pg_sz, csp->wq_ctrl->buf.page_shift -
MLX5_ADAPTER_PAGE_SHIFT);
- MLX5_SET64(wq, wq, dbr_addr, sq->wq_ctrl.db.dma);
+ MLX5_SET64(wq, wq, dbr_addr, csp->wq_ctrl->db.dma);
- mlx5_fill_page_array(&sq->wq_ctrl.buf,
- (__be64 *)MLX5_ADDR_OF(wq, wq, pas));
+ mlx5_fill_page_array(&csp->wq_ctrl->buf, (__be64 *)MLX5_ADDR_OF(wq, wq, pas));
- err = mlx5_core_create_sq(mdev, in, inlen, &sq->sqn);
+ err = mlx5_core_create_sq(mdev, in, inlen, sqn);
kvfree(in);
return err;
}
-static int mlx5e_modify_sq(struct mlx5e_sq *sq, int curr_state,
- int next_state, bool update_rl, int rl_index)
-{
- struct mlx5e_channel *c = sq->channel;
- struct mlx5e_priv *priv = c->priv;
- struct mlx5_core_dev *mdev = priv->mdev;
+struct mlx5e_modify_sq_param {
+ int curr_state;
+ int next_state;
+ bool rl_update;
+ int rl_index;
+};
+static int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn,
+ struct mlx5e_modify_sq_param *p)
+{
void *in;
void *sqc;
int inlen;
@@ -1141,68 +1187,94 @@ static int mlx5e_modify_sq(struct mlx5e_sq *sq, int curr_state,
sqc = MLX5_ADDR_OF(modify_sq_in, in, ctx);
- MLX5_SET(modify_sq_in, in, sq_state, curr_state);
- MLX5_SET(sqc, sqc, state, next_state);
- if (update_rl && next_state == MLX5_SQC_STATE_RDY) {
+ MLX5_SET(modify_sq_in, in, sq_state, p->curr_state);
+ MLX5_SET(sqc, sqc, state, p->next_state);
+ if (p->rl_update && p->next_state == MLX5_SQC_STATE_RDY) {
MLX5_SET64(modify_sq_in, in, modify_bitmask, 1);
- MLX5_SET(sqc, sqc, packet_pacing_rate_limit_index, rl_index);
+ MLX5_SET(sqc, sqc, packet_pacing_rate_limit_index, p->rl_index);
}
- err = mlx5_core_modify_sq(mdev, sq->sqn, in, inlen);
+ err = mlx5_core_modify_sq(mdev, sqn, in, inlen);
kvfree(in);
return err;
}
-static void mlx5e_disable_sq(struct mlx5e_sq *sq)
+static void mlx5e_destroy_sq(struct mlx5_core_dev *mdev, u32 sqn)
{
- struct mlx5e_channel *c = sq->channel;
- struct mlx5e_priv *priv = c->priv;
- struct mlx5_core_dev *mdev = priv->mdev;
-
- mlx5_core_destroy_sq(mdev, sq->sqn);
- if (sq->rate_limit)
- mlx5_rl_remove_rate(mdev, sq->rate_limit);
+ mlx5_core_destroy_sq(mdev, sqn);
}
-static int mlx5e_open_sq(struct mlx5e_channel *c,
- int tc,
- struct mlx5e_sq_param *param,
- struct mlx5e_sq *sq)
+static int mlx5e_create_sq_rdy(struct mlx5_core_dev *mdev,
+ struct mlx5e_sq_param *param,
+ struct mlx5e_create_sq_param *csp,
+ u32 *sqn)
{
+ struct mlx5e_modify_sq_param msp = {0};
int err;
- err = mlx5e_create_sq(c, tc, param, sq);
+ err = mlx5e_create_sq(mdev, param, csp, sqn);
if (err)
return err;
- err = mlx5e_enable_sq(sq, param);
+ msp.curr_state = MLX5_SQC_STATE_RST;
+ msp.next_state = MLX5_SQC_STATE_RDY;
+ err = mlx5e_modify_sq(mdev, *sqn, &msp);
if (err)
- goto err_destroy_sq;
+ mlx5e_destroy_sq(mdev, *sqn);
- set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
- err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RST, MLX5_SQC_STATE_RDY,
- false, 0);
+ return err;
+}
+
+static int mlx5e_set_sq_maxrate(struct net_device *dev,
+ struct mlx5e_txqsq *sq, u32 rate);
+
+static int mlx5e_open_txqsq(struct mlx5e_channel *c,
+ u32 tisn,
+ int txq_ix,
+ struct mlx5e_params *params,
+ struct mlx5e_sq_param *param,
+ struct mlx5e_txqsq *sq)
+{
+ struct mlx5e_create_sq_param csp = {};
+ u32 tx_rate;
+ int err;
+
+ err = mlx5e_alloc_txqsq(c, txq_ix, params, param, sq);
if (err)
- goto err_disable_sq;
+ return err;
- if (sq->txq) {
- netdev_tx_reset_queue(sq->txq);
- netif_tx_start_queue(sq->txq);
- }
+ csp.tisn = tisn;
+ csp.tis_lst_sz = 1;
+ csp.cqn = sq->cq.mcq.cqn;
+ csp.wq_ctrl = &sq->wq_ctrl;
+ csp.min_inline_mode = sq->min_inline_mode;
+ err = mlx5e_create_sq_rdy(c->mdev, param, &csp, &sq->sqn);
+ if (err)
+ goto err_free_txqsq;
+
+ tx_rate = c->priv->tx_rates[sq->txq_ix];
+ if (tx_rate)
+ mlx5e_set_sq_maxrate(c->netdev, sq, tx_rate);
return 0;
-err_disable_sq:
+err_free_txqsq:
clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
- mlx5e_disable_sq(sq);
-err_destroy_sq:
- mlx5e_destroy_sq(sq);
+ mlx5e_free_txqsq(sq);
return err;
}
+static void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq)
+{
+ sq->txq = netdev_get_tx_queue(sq->channel->netdev, sq->txq_ix);
+ set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+ netdev_tx_reset_queue(sq->txq);
+ netif_tx_start_queue(sq->txq);
+}
+
static inline void netif_tx_disable_queue(struct netdev_queue *txq)
{
__netif_tx_lock_bh(txq);
@@ -1210,43 +1282,153 @@ static inline void netif_tx_disable_queue(struct netdev_queue *txq)
__netif_tx_unlock_bh(txq);
}
-static void mlx5e_close_sq(struct mlx5e_sq *sq)
+static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq)
{
+ struct mlx5e_channel *c = sq->channel;
+
clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
/* prevent netif_tx_wake_queue */
- napi_synchronize(&sq->channel->napi);
+ napi_synchronize(&c->napi);
- if (sq->txq) {
- netif_tx_disable_queue(sq->txq);
+ netif_tx_disable_queue(sq->txq);
- /* last doorbell out, godspeed .. */
- if (mlx5e_sq_has_room_for(sq, 1)) {
- sq->db.txq.skb[(sq->pc & sq->wq.sz_m1)] = NULL;
- mlx5e_send_nop(sq, true);
- }
+ /* last doorbell out, godspeed .. */
+ if (mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1)) {
+ struct mlx5e_tx_wqe *nop;
+
+ sq->db.skb[(sq->pc & sq->wq.sz_m1)] = NULL;
+ nop = mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc);
+ mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &nop->ctrl);
}
-
- mlx5e_disable_sq(sq);
- mlx5e_free_sq_descs(sq);
- mlx5e_destroy_sq(sq);
}
-static int mlx5e_create_cq(struct mlx5e_channel *c,
- struct mlx5e_cq_param *param,
- struct mlx5e_cq *cq)
+static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq)
{
- struct mlx5e_priv *priv = c->priv;
- struct mlx5_core_dev *mdev = priv->mdev;
+ struct mlx5e_channel *c = sq->channel;
+ struct mlx5_core_dev *mdev = c->mdev;
+
+ mlx5e_destroy_sq(mdev, sq->sqn);
+ if (sq->rate_limit)
+ mlx5_rl_remove_rate(mdev, sq->rate_limit);
+ mlx5e_free_txqsq_descs(sq);
+ mlx5e_free_txqsq(sq);
+}
+
+static int mlx5e_open_icosq(struct mlx5e_channel *c,
+ struct mlx5e_params *params,
+ struct mlx5e_sq_param *param,
+ struct mlx5e_icosq *sq)
+{
+ struct mlx5e_create_sq_param csp = {};
+ int err;
+
+ err = mlx5e_alloc_icosq(c, param, sq);
+ if (err)
+ return err;
+
+ csp.cqn = sq->cq.mcq.cqn;
+ csp.wq_ctrl = &sq->wq_ctrl;
+ csp.min_inline_mode = params->tx_min_inline_mode;
+ set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+ err = mlx5e_create_sq_rdy(c->mdev, param, &csp, &sq->sqn);
+ if (err)
+ goto err_free_icosq;
+
+ return 0;
+
+err_free_icosq:
+ clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+ mlx5e_free_icosq(sq);
+
+ return err;
+}
+
+static void mlx5e_close_icosq(struct mlx5e_icosq *sq)
+{
+ struct mlx5e_channel *c = sq->channel;
+
+ clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+ napi_synchronize(&c->napi);
+
+ mlx5e_destroy_sq(c->mdev, sq->sqn);
+ mlx5e_free_icosq(sq);
+}
+
+static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
+ struct mlx5e_params *params,
+ struct mlx5e_sq_param *param,
+ struct mlx5e_xdpsq *sq)
+{
+ unsigned int ds_cnt = MLX5E_XDP_TX_DS_COUNT;
+ struct mlx5e_create_sq_param csp = {};
+ unsigned int inline_hdr_sz = 0;
+ int err;
+ int i;
+
+ err = mlx5e_alloc_xdpsq(c, params, param, sq);
+ if (err)
+ return err;
+
+ csp.tis_lst_sz = 1;
+ csp.tisn = c->priv->tisn[0]; /* tc = 0 */
+ csp.cqn = sq->cq.mcq.cqn;
+ csp.wq_ctrl = &sq->wq_ctrl;
+ csp.min_inline_mode = sq->min_inline_mode;
+ set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+ err = mlx5e_create_sq_rdy(c->mdev, param, &csp, &sq->sqn);
+ if (err)
+ goto err_free_xdpsq;
+
+ if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
+ inline_hdr_sz = MLX5E_XDP_MIN_INLINE;
+ ds_cnt++;
+ }
+
+ /* Pre initialize fixed WQE fields */
+ for (i = 0; i < mlx5_wq_cyc_get_size(&sq->wq); i++) {
+ struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(&sq->wq, i);
+ struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
+ struct mlx5_wqe_eth_seg *eseg = &wqe->eth;
+ struct mlx5_wqe_data_seg *dseg;
+
+ cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
+ eseg->inline_hdr.sz = cpu_to_be16(inline_hdr_sz);
+
+ dseg = (struct mlx5_wqe_data_seg *)cseg + (ds_cnt - 1);
+ dseg->lkey = sq->mkey_be;
+ }
+
+ return 0;
+
+err_free_xdpsq:
+ clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+ mlx5e_free_xdpsq(sq);
+
+ return err;
+}
+
+static void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq)
+{
+ struct mlx5e_channel *c = sq->channel;
+
+ clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+ napi_synchronize(&c->napi);
+
+ mlx5e_destroy_sq(c->mdev, sq->sqn);
+ mlx5e_free_xdpsq_descs(sq);
+ mlx5e_free_xdpsq(sq);
+}
+
+static int mlx5e_alloc_cq_common(struct mlx5_core_dev *mdev,
+ struct mlx5e_cq_param *param,
+ struct mlx5e_cq *cq)
+{
struct mlx5_core_cq *mcq = &cq->mcq;
int eqn_not_used;
unsigned int irqn;
int err;
u32 i;
- param->wq.buf_numa_node = cpu_to_node(c->cpu);
- param->wq.db_numa_node = cpu_to_node(c->cpu);
- param->eq_ix = c->ix;
-
err = mlx5_cqwq_create(mdev, ¶m->wq, param->cqc, &cq->wq,
&cq->wq_ctrl);
if (err)
@@ -1254,8 +1436,6 @@ static int mlx5e_create_cq(struct mlx5e_channel *c,
mlx5_vector2eqn(mdev, param->eq_ix, &eqn_not_used, &irqn);
- cq->napi = &c->napi;
-
mcq->cqe_sz = 64;
mcq->set_ci_db = cq->wq_ctrl.db.db;
mcq->arm_db = cq->wq_ctrl.db.db + 1;
@@ -1272,21 +1452,38 @@ static int mlx5e_create_cq(struct mlx5e_channel *c,
cqe->op_own = 0xf1;
}
- cq->channel = c;
- cq->priv = priv;
+ cq->mdev = mdev;
return 0;
}
-static void mlx5e_destroy_cq(struct mlx5e_cq *cq)
+static int mlx5e_alloc_cq(struct mlx5e_channel *c,
+ struct mlx5e_cq_param *param,
+ struct mlx5e_cq *cq)
+{
+ struct mlx5_core_dev *mdev = c->priv->mdev;
+ int err;
+
+ param->wq.buf_numa_node = cpu_to_node(c->cpu);
+ param->wq.db_numa_node = cpu_to_node(c->cpu);
+ param->eq_ix = c->ix;
+
+ err = mlx5e_alloc_cq_common(mdev, param, cq);
+
+ cq->napi = &c->napi;
+ cq->channel = c;
+
+ return err;
+}
+
+static void mlx5e_free_cq(struct mlx5e_cq *cq)
{
mlx5_cqwq_destroy(&cq->wq_ctrl);
}
-static int mlx5e_enable_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
+static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
{
- struct mlx5e_priv *priv = cq->priv;
- struct mlx5_core_dev *mdev = priv->mdev;
+ struct mlx5_core_dev *mdev = cq->mdev;
struct mlx5_core_cq *mcq = &cq->mcq;
void *in;
@@ -1330,47 +1527,41 @@ static int mlx5e_enable_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
return 0;
}
-static void mlx5e_disable_cq(struct mlx5e_cq *cq)
+static void mlx5e_destroy_cq(struct mlx5e_cq *cq)
{
- struct mlx5e_priv *priv = cq->priv;
- struct mlx5_core_dev *mdev = priv->mdev;
-
- mlx5_core_destroy_cq(mdev, &cq->mcq);
+ mlx5_core_destroy_cq(cq->mdev, &cq->mcq);
}
static int mlx5e_open_cq(struct mlx5e_channel *c,
+ struct mlx5e_cq_moder moder,
struct mlx5e_cq_param *param,
- struct mlx5e_cq *cq,
- struct mlx5e_cq_moder moderation)
+ struct mlx5e_cq *cq)
{
+ struct mlx5_core_dev *mdev = c->mdev;
int err;
- struct mlx5e_priv *priv = c->priv;
- struct mlx5_core_dev *mdev = priv->mdev;
- err = mlx5e_create_cq(c, param, cq);
+ err = mlx5e_alloc_cq(c, param, cq);
if (err)
return err;
- err = mlx5e_enable_cq(cq, param);
+ err = mlx5e_create_cq(cq, param);
if (err)
- goto err_destroy_cq;
+ goto err_free_cq;
if (MLX5_CAP_GEN(mdev, cq_moderation))
- mlx5_core_modify_cq_moderation(mdev, &cq->mcq,
- moderation.usec,
- moderation.pkts);
+ mlx5_core_modify_cq_moderation(mdev, &cq->mcq, moder.usec, moder.pkts);
return 0;
-err_destroy_cq:
- mlx5e_destroy_cq(cq);
+err_free_cq:
+ mlx5e_free_cq(cq);
return err;
}
static void mlx5e_close_cq(struct mlx5e_cq *cq)
{
- mlx5e_disable_cq(cq);
mlx5e_destroy_cq(cq);
+ mlx5e_free_cq(cq);
}
static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix)
@@ -1379,15 +1570,15 @@ static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix)
}
static int mlx5e_open_tx_cqs(struct mlx5e_channel *c,
+ struct mlx5e_params *params,
struct mlx5e_channel_param *cparam)
{
- struct mlx5e_priv *priv = c->priv;
int err;
int tc;
for (tc = 0; tc < c->num_tc; tc++) {
- err = mlx5e_open_cq(c, &cparam->tx_cq, &c->sq[tc].cq,
- priv->params.tx_cq_moderation);
+ err = mlx5e_open_cq(c, params->tx_cq_moderation,
+ &cparam->tx_cq, &c->sq[tc].cq);
if (err)
goto err_close_tx_cqs;
}
@@ -1410,13 +1601,17 @@ static void mlx5e_close_tx_cqs(struct mlx5e_channel *c)
}
static int mlx5e_open_sqs(struct mlx5e_channel *c,
+ struct mlx5e_params *params,
struct mlx5e_channel_param *cparam)
{
int err;
int tc;
- for (tc = 0; tc < c->num_tc; tc++) {
- err = mlx5e_open_sq(c, tc, &cparam->sq, &c->sq[tc]);
+ for (tc = 0; tc < params->num_tc; tc++) {
+ int txq_ix = c->ix + tc * params->num_channels;
+
+ err = mlx5e_open_txqsq(c, c->priv->tisn[tc], txq_ix,
+ params, &cparam->sq, &c->sq[tc]);
if (err)
goto err_close_sqs;
}
@@ -1425,7 +1620,7 @@ static int mlx5e_open_sqs(struct mlx5e_channel *c,
err_close_sqs:
for (tc--; tc >= 0; tc--)
- mlx5e_close_sq(&c->sq[tc]);
+ mlx5e_close_txqsq(&c->sq[tc]);
return err;
}
@@ -1435,23 +1630,15 @@ static void mlx5e_close_sqs(struct mlx5e_channel *c)
int tc;
for (tc = 0; tc < c->num_tc; tc++)
- mlx5e_close_sq(&c->sq[tc]);
-}
-
-static void mlx5e_build_channeltc_to_txq_map(struct mlx5e_priv *priv, int ix)
-{
- int i;
-
- for (i = 0; i < priv->profile->max_tc; i++)
- priv->channeltc_to_txq_map[ix][i] =
- ix + i * priv->params.num_channels;
+ mlx5e_close_txqsq(&c->sq[tc]);
}
static int mlx5e_set_sq_maxrate(struct net_device *dev,
- struct mlx5e_sq *sq, u32 rate)
+ struct mlx5e_txqsq *sq, u32 rate)
{
struct mlx5e_priv *priv = netdev_priv(dev);
struct mlx5_core_dev *mdev = priv->mdev;
+ struct mlx5e_modify_sq_param msp = {0};
u16 rl_index = 0;
int err;
@@ -1474,8 +1661,11 @@ static int mlx5e_set_sq_maxrate(struct net_device *dev,
}
}
- err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY,
- MLX5_SQC_STATE_RDY, true, rl_index);
+ msp.curr_state = MLX5_SQC_STATE_RDY;
+ msp.next_state = MLX5_SQC_STATE_RDY;
+ msp.rl_index = rl_index;
+ msp.rl_update = true;
+ err = mlx5e_modify_sq(mdev, sq->sqn, &msp);
if (err) {
netdev_err(dev, "Failed configuring rate %u: %d\n",
rate, err);
@@ -1493,7 +1683,7 @@ static int mlx5e_set_tx_maxrate(struct net_device *dev, int index, u32 rate)
{
struct mlx5e_priv *priv = netdev_priv(dev);
struct mlx5_core_dev *mdev = priv->mdev;
- struct mlx5e_sq *sq = priv->txq_to_sq_map[index];
+ struct mlx5e_txqsq *sq = priv->txq2sq[index];
int err = 0;
if (!mlx5_rl_is_supported(mdev)) {
@@ -1529,105 +1719,86 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev)
}
static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
+ struct mlx5e_params *params,
struct mlx5e_channel_param *cparam,
struct mlx5e_channel **cp)
{
- struct mlx5e_cq_moder icosq_cq_moder = {0, 0};
+ struct mlx5e_cq_moder icocq_moder = {0, 0};
struct net_device *netdev = priv->netdev;
- struct mlx5e_cq_moder rx_cq_profile;
int cpu = mlx5e_get_cpu(priv, ix);
struct mlx5e_channel *c;
- struct mlx5e_sq *sq;
int err;
- int i;
c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
if (!c)
return -ENOMEM;
c->priv = priv;
+ c->mdev = priv->mdev;
+ c->tstamp = &priv->tstamp;
c->ix = ix;
c->cpu = cpu;
c->pdev = &priv->mdev->pdev->dev;
c->netdev = priv->netdev;
c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);
- c->num_tc = priv->params.num_tc;
- c->xdp = !!priv->xdp_prog;
-
- if (priv->params.rx_am_enabled)
- rx_cq_profile = mlx5e_am_get_def_profile(priv->params.rx_cq_period_mode);
- else
- rx_cq_profile = priv->params.rx_cq_moderation;
-
- mlx5e_build_channeltc_to_txq_map(priv, ix);
+ c->num_tc = params->num_tc;
+ c->xdp = !!params->xdp_prog;
netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64);
- err = mlx5e_open_cq(c, &cparam->icosq_cq, &c->icosq.cq, icosq_cq_moder);
+ err = mlx5e_open_cq(c, icocq_moder, &cparam->icosq_cq, &c->icosq.cq);
if (err)
goto err_napi_del;
- err = mlx5e_open_tx_cqs(c, cparam);
+ err = mlx5e_open_tx_cqs(c, params, cparam);
if (err)
goto err_close_icosq_cq;
- err = mlx5e_open_cq(c, &cparam->rx_cq, &c->rq.cq,
- rx_cq_profile);
+ err = mlx5e_open_cq(c, params->rx_cq_moderation, &cparam->rx_cq, &c->rq.cq);
if (err)
goto err_close_tx_cqs;
/* XDP SQ CQ params are same as normal TXQ sq CQ params */
- err = c->xdp ? mlx5e_open_cq(c, &cparam->tx_cq, &c->xdp_sq.cq,
- priv->params.tx_cq_moderation) : 0;
+ err = c->xdp ? mlx5e_open_cq(c, params->tx_cq_moderation,
+ &cparam->tx_cq, &c->rq.xdpsq.cq) : 0;
if (err)
goto err_close_rx_cq;
napi_enable(&c->napi);
- err = mlx5e_open_sq(c, 0, &cparam->icosq, &c->icosq);
+ err = mlx5e_open_icosq(c, params, &cparam->icosq, &c->icosq);
if (err)
goto err_disable_napi;
- err = mlx5e_open_sqs(c, cparam);
+ err = mlx5e_open_sqs(c, params, cparam);
if (err)
goto err_close_icosq;
- for (i = 0; i < priv->params.num_tc; i++) {
- u32 txq_ix = priv->channeltc_to_txq_map[ix][i];
-
- if (priv->tx_rates[txq_ix]) {
- sq = priv->txq_to_sq_map[txq_ix];
- mlx5e_set_sq_maxrate(priv->netdev, sq,
- priv->tx_rates[txq_ix]);
- }
- }
-
- err = c->xdp ? mlx5e_open_sq(c, 0, &cparam->xdp_sq, &c->xdp_sq) : 0;
+ err = c->xdp ? mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->rq.xdpsq) : 0;
if (err)
goto err_close_sqs;
- err = mlx5e_open_rq(c, &cparam->rq, &c->rq);
+ err = mlx5e_open_rq(c, params, &cparam->rq, &c->rq);
if (err)
goto err_close_xdp_sq;
- netif_set_xps_queue(netdev, get_cpu_mask(c->cpu), ix);
*cp = c;
return 0;
err_close_xdp_sq:
if (c->xdp)
- mlx5e_close_sq(&c->xdp_sq);
+ mlx5e_close_xdpsq(&c->rq.xdpsq);
err_close_sqs:
mlx5e_close_sqs(c);
err_close_icosq:
- mlx5e_close_sq(&c->icosq);
+ mlx5e_close_icosq(&c->icosq);
err_disable_napi:
napi_disable(&c->napi);
if (c->xdp)
- mlx5e_close_cq(&c->xdp_sq.cq);
+ mlx5e_close_cq(&c->rq.xdpsq.cq);
err_close_rx_cq:
mlx5e_close_cq(&c->rq.cq);
@@ -1645,16 +1816,35 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
return err;
}
+static void mlx5e_activate_channel(struct mlx5e_channel *c)
+{
+ int tc;
+
+ for (tc = 0; tc < c->num_tc; tc++)
+ mlx5e_activate_txqsq(&c->sq[tc]);
+ mlx5e_activate_rq(&c->rq);
+ netif_set_xps_queue(c->netdev, get_cpu_mask(c->cpu), c->ix);
+}
+
+static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
+{
+ int tc;
+
+ mlx5e_deactivate_rq(&c->rq);
+ for (tc = 0; tc < c->num_tc; tc++)
+ mlx5e_deactivate_txqsq(&c->sq[tc]);
+}
+
static void mlx5e_close_channel(struct mlx5e_channel *c)
{
mlx5e_close_rq(&c->rq);
if (c->xdp)
- mlx5e_close_sq(&c->xdp_sq);
+ mlx5e_close_xdpsq(&c->rq.xdpsq);
mlx5e_close_sqs(c);
- mlx5e_close_sq(&c->icosq);
+ mlx5e_close_icosq(&c->icosq);
napi_disable(&c->napi);
if (c->xdp)
- mlx5e_close_cq(&c->xdp_sq.cq);
+ mlx5e_close_cq(&c->rq.xdpsq.cq);
mlx5e_close_cq(&c->rq.cq);
mlx5e_close_tx_cqs(c);
mlx5e_close_cq(&c->icosq.cq);
@@ -1664,17 +1854,16 @@ static void mlx5e_close_channel(struct mlx5e_channel *c)
}
static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
+ struct mlx5e_params *params,
struct mlx5e_rq_param *param)
{
void *rqc = param->rqc;
void *wq = MLX5_ADDR_OF(rqc, rqc, wq);
- switch (priv->params.rq_wq_type) {
+ switch (params->rq_wq_type) {
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
- MLX5_SET(wq, wq, log_wqe_num_of_strides,
- priv->params.mpwqe_log_num_strides - 9);
- MLX5_SET(wq, wq, log_wqe_stride_size,
- priv->params.mpwqe_log_stride_sz - 6);
+ MLX5_SET(wq, wq, log_wqe_num_of_strides, params->mpwqe_log_num_strides - 9);
+ MLX5_SET(wq, wq, log_wqe_stride_size, params->mpwqe_log_stride_sz - 6);
MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ);
break;
default: /* MLX5_WQ_TYPE_LINKED_LIST */
@@ -1683,14 +1872,14 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
MLX5_SET(wq, wq, end_padding_mode, MLX5_WQ_END_PAD_MODE_ALIGN);
MLX5_SET(wq, wq, log_wq_stride, ilog2(sizeof(struct mlx5e_rx_wqe)));
- MLX5_SET(wq, wq, log_wq_sz, priv->params.log_rq_size);
+ MLX5_SET(wq, wq, log_wq_sz, params->log_rq_size);
MLX5_SET(wq, wq, pd, priv->mdev->mlx5e_res.pdn);
MLX5_SET(rqc, rqc, counter_set_id, priv->q_counter);
+ MLX5_SET(rqc, rqc, vsd, params->vlan_strip_disable);
+ MLX5_SET(rqc, rqc, scatter_fcs, params->scatter_fcs_en);
param->wq.buf_numa_node = dev_to_node(&priv->mdev->pdev->dev);
param->wq.linear = 1;
-
- param->am_enabled = priv->params.rx_am_enabled;
}
static void mlx5e_build_drop_rq_param(struct mlx5e_rq_param *param)
@@ -1715,17 +1904,14 @@ static void mlx5e_build_sq_param_common(struct mlx5e_priv *priv,
}
static void mlx5e_build_sq_param(struct mlx5e_priv *priv,
+ struct mlx5e_params *params,
struct mlx5e_sq_param *param)
{
void *sqc = param->sqc;
void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
mlx5e_build_sq_param_common(priv, param);
- MLX5_SET(wq, wq, log_wq_sz, priv->params.log_sq_size);
-
- param->max_inline = priv->params.tx_max_inline;
- param->min_inline_mode = priv->params.tx_min_inline_mode;
- param->type = MLX5E_SQ_TXQ;
+ MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
}
static void mlx5e_build_common_cq_param(struct mlx5e_priv *priv,
@@ -1737,37 +1923,36 @@ static void mlx5e_build_common_cq_param(struct mlx5e_priv *priv,
}
static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
+ struct mlx5e_params *params,
struct mlx5e_cq_param *param)
{
void *cqc = param->cqc;
u8 log_cq_size;
- switch (priv->params.rq_wq_type) {
+ switch (params->rq_wq_type) {
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
- log_cq_size = priv->params.log_rq_size +
- priv->params.mpwqe_log_num_strides;
+ log_cq_size = params->log_rq_size + params->mpwqe_log_num_strides;
break;
default: /* MLX5_WQ_TYPE_LINKED_LIST */
- log_cq_size = priv->params.log_rq_size;
+ log_cq_size = params->log_rq_size;
}
MLX5_SET(cqc, cqc, log_cq_size, log_cq_size);
- if (MLX5E_GET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS)) {
+ if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)) {
MLX5_SET(cqc, cqc, mini_cqe_res_format, MLX5_CQE_FORMAT_CSUM);
MLX5_SET(cqc, cqc, cqe_comp_en, 1);
}
mlx5e_build_common_cq_param(priv, param);
-
- param->cq_period_mode = priv->params.rx_cq_period_mode;
}
static void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv,
+ struct mlx5e_params *params,
struct mlx5e_cq_param *param)
{
void *cqc = param->cqc;
- MLX5_SET(cqc, cqc, log_cq_size, priv->params.log_sq_size);
+ MLX5_SET(cqc, cqc, log_cq_size, params->log_sq_size);
mlx5e_build_common_cq_param(priv, param);
@@ -1775,8 +1960,8 @@ static void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv,
}
static void mlx5e_build_ico_cq_param(struct mlx5e_priv *priv,
- struct mlx5e_cq_param *param,
- u8 log_wq_size)
+ u8 log_wq_size,
+ struct mlx5e_cq_param *param)
{
void *cqc = param->cqc;
@@ -1788,8 +1973,8 @@ static void mlx5e_build_ico_cq_param(struct mlx5e_priv *priv,
}
static void mlx5e_build_icosq_param(struct mlx5e_priv *priv,
- struct mlx5e_sq_param *param,
- u8 log_wq_size)
+ u8 log_wq_size,
+ struct mlx5e_sq_param *param)
{
void *sqc = param->sqc;
void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
@@ -1798,105 +1983,174 @@ static void mlx5e_build_icosq_param(struct mlx5e_priv *priv,
MLX5_SET(wq, wq, log_wq_sz, log_wq_size);
MLX5_SET(sqc, sqc, reg_umr, MLX5_CAP_ETH(priv->mdev, reg_umr_sq));
-
- param->type = MLX5E_SQ_ICO;
}
static void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv,
+ struct mlx5e_params *params,
struct mlx5e_sq_param *param)
{
void *sqc = param->sqc;
void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
mlx5e_build_sq_param_common(priv, param);
- MLX5_SET(wq, wq, log_wq_sz, priv->params.log_sq_size);
-
- param->max_inline = priv->params.tx_max_inline;
- param->min_inline_mode = priv->params.tx_min_inline_mode;
- param->type = MLX5E_SQ_XDP;
+ MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
}
-static void mlx5e_build_channel_param(struct mlx5e_priv *priv, struct mlx5e_channel_param *cparam)
+static void mlx5e_build_channel_param(struct mlx5e_priv *priv,
+ struct mlx5e_params *params,
+ struct mlx5e_channel_param *cparam)
{
u8 icosq_log_wq_sz = MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
- mlx5e_build_rq_param(priv, &cparam->rq);
- mlx5e_build_sq_param(priv, &cparam->sq);
- mlx5e_build_xdpsq_param(priv, &cparam->xdp_sq);
- mlx5e_build_icosq_param(priv, &cparam->icosq, icosq_log_wq_sz);
- mlx5e_build_rx_cq_param(priv, &cparam->rx_cq);
- mlx5e_build_tx_cq_param(priv, &cparam->tx_cq);
- mlx5e_build_ico_cq_param(priv, &cparam->icosq_cq, icosq_log_wq_sz);
+ mlx5e_build_rq_param(priv, params, &cparam->rq);
+ mlx5e_build_sq_param(priv, params, &cparam->sq);
+ mlx5e_build_xdpsq_param(priv, params, &cparam->xdp_sq);
+ mlx5e_build_icosq_param(priv, icosq_log_wq_sz, &cparam->icosq);
+ mlx5e_build_rx_cq_param(priv, params, &cparam->rx_cq);
+ mlx5e_build_tx_cq_param(priv, params, &cparam->tx_cq);
+ mlx5e_build_ico_cq_param(priv, icosq_log_wq_sz, &cparam->icosq_cq);
}
-static int mlx5e_open_channels(struct mlx5e_priv *priv)
+int mlx5e_open_channels(struct mlx5e_priv *priv,
+ struct mlx5e_channels *chs)
{
struct mlx5e_channel_param *cparam;
- int nch = priv->params.num_channels;
int err = -ENOMEM;
int i;
- int j;
- priv->channel = kcalloc(nch, sizeof(struct mlx5e_channel *),
- GFP_KERNEL);
+ chs->num = chs->params.num_channels;
- priv->txq_to_sq_map = kcalloc(nch * priv->params.num_tc,
- sizeof(struct mlx5e_sq *), GFP_KERNEL);
-
+ chs->c = kcalloc(chs->num, sizeof(struct mlx5e_channel *), GFP_KERNEL);
cparam = kzalloc(sizeof(struct mlx5e_channel_param), GFP_KERNEL);
+ if (!chs->c || !cparam)
+ goto err_free;
- if (!priv->channel || !priv->txq_to_sq_map || !cparam)
- goto err_free_txq_to_sq_map;
-
- mlx5e_build_channel_param(priv, cparam);
-
- for (i = 0; i < nch; i++) {
- err = mlx5e_open_channel(priv, i, cparam, &priv->channel[i]);
+ mlx5e_build_channel_param(priv, &chs->params, cparam);
+ for (i = 0; i < chs->num; i++) {
+ err = mlx5e_open_channel(priv, i, &chs->params, cparam, &chs->c[i]);
if (err)
goto err_close_channels;
}
- for (j = 0; j < nch; j++) {
- err = mlx5e_wait_for_min_rx_wqes(&priv->channel[j]->rq);
- if (err)
- goto err_close_channels;
- }
-
- /* FIXME: This is a W/A for tx timeout watch dog false alarm when
- * polling for inactive tx queues.
- */
- netif_tx_start_all_queues(priv->netdev);
-
kfree(cparam);
return 0;
err_close_channels:
for (i--; i >= 0; i--)
- mlx5e_close_channel(priv->channel[i]);
+ mlx5e_close_channel(chs->c[i]);
-err_free_txq_to_sq_map:
- kfree(priv->txq_to_sq_map);
- kfree(priv->channel);
+err_free:
+ kfree(chs->c);
kfree(cparam);
+ chs->num = 0;
+ return err;
+}
+
+static void mlx5e_activate_channels(struct mlx5e_channels *chs)
+{
+ int i;
+
+ for (i = 0; i < chs->num; i++)
+ mlx5e_activate_channel(chs->c[i]);
+}
+
+static int mlx5e_wait_channels_min_rx_wqes(struct mlx5e_channels *chs)
+{
+ int err = 0;
+ int i;
+
+ for (i = 0; i < chs->num; i++) {
+ err = mlx5e_wait_for_min_rx_wqes(&chs->c[i]->rq);
+ if (err)
+ break;
+ }
return err;
}
-static void mlx5e_close_channels(struct mlx5e_priv *priv)
+static void mlx5e_deactivate_channels(struct mlx5e_channels *chs)
{
int i;
- /* FIXME: This is a W/A only for tx timeout watch dog false alarm when
- * polling for inactive tx queues.
- */
- netif_tx_stop_all_queues(priv->netdev);
- netif_tx_disable(priv->netdev);
+ for (i = 0; i < chs->num; i++)
+ mlx5e_deactivate_channel(chs->c[i]);
+}
- for (i = 0; i < priv->params.num_channels; i++)
- mlx5e_close_channel(priv->channel[i]);
+void mlx5e_close_channels(struct mlx5e_channels *chs)
+{
+ int i;
- kfree(priv->txq_to_sq_map);
- kfree(priv->channel);
+ for (i = 0; i < chs->num; i++)
+ mlx5e_close_channel(chs->c[i]);
+
+ kfree(chs->c);
+ chs->num = 0;
+}
+
+static int
+mlx5e_create_rqt(struct mlx5e_priv *priv, int sz, struct mlx5e_rqt *rqt)
+{
+ struct mlx5_core_dev *mdev = priv->mdev;
+ void *rqtc;
+ int inlen;
+ int err;
+ u32 *in;
+ int i;
+
+ inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + sizeof(u32) * sz;
+ in = mlx5_vzalloc(inlen);
+ if (!in)
+ return -ENOMEM;
+
+ rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context);
+
+ MLX5_SET(rqtc, rqtc, rqt_actual_size, sz);
+ MLX5_SET(rqtc, rqtc, rqt_max_size, sz);
+
+ for (i = 0; i < sz; i++)
+ MLX5_SET(rqtc, rqtc, rq_num[i], priv->drop_rq.rqn);
+
+ err = mlx5_core_create_rqt(mdev, in, inlen, &rqt->rqtn);
+ if (!err)
+ rqt->enabled = true;
+
+ kvfree(in);
+ return err;
+}
+
+void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt)
+{
+ rqt->enabled = false;
+ mlx5_core_destroy_rqt(priv->mdev, rqt->rqtn);
+}
+
+static int mlx5e_create_indirect_rqts(struct mlx5e_priv *priv)
+{
+ struct mlx5e_rqt *rqt = &priv->indir_rqt;
+
+ return mlx5e_create_rqt(priv, MLX5E_INDIR_RQT_SIZE, rqt);
+}
+
+int mlx5e_create_direct_rqts(struct mlx5e_priv *priv)
+{
+ struct mlx5e_rqt *rqt;
+ int err;
+ int ix;
+
+ for (ix = 0; ix < priv->profile->max_nch(priv->mdev); ix++) {
+ rqt = &priv->direct_tir[ix].rqt;
+ err = mlx5e_create_rqt(priv, 1 /*size */, rqt);
+ if (err)
+ goto err_destroy_rqts;
+ }
+
+ return 0;
+
+err_destroy_rqts:
+ for (ix--; ix >= 0; ix--)
+ mlx5e_destroy_rqt(priv, &priv->direct_tir[ix].rqt);
+
+ return err;
}
static int mlx5e_rx_hash_fn(int hfunc)
@@ -1917,103 +2171,31 @@ static int mlx5e_bits_invert(unsigned long a, int size)
return inv;
}
-static void mlx5e_fill_indir_rqt_rqns(struct mlx5e_priv *priv, void *rqtc)
+static void mlx5e_fill_rqt_rqns(struct mlx5e_priv *priv, int sz,
+ struct mlx5e_redirect_rqt_param rrp, void *rqtc)
{
int i;
- for (i = 0; i < MLX5E_INDIR_RQT_SIZE; i++) {
- int ix = i;
+ for (i = 0; i < sz; i++) {
u32 rqn;
- if (priv->params.rss_hfunc == ETH_RSS_HASH_XOR)
- ix = mlx5e_bits_invert(i, MLX5E_LOG_INDIR_RQT_SIZE);
+ if (rrp.is_rss) {
+ int ix = i;
- ix = priv->params.indirection_rqt[ix];
- rqn = test_bit(MLX5E_STATE_OPENED, &priv->state) ?
- priv->channel[ix]->rq.rqn :
- priv->drop_rq.rqn;
+ if (rrp.rss.hfunc == ETH_RSS_HASH_XOR)
+ ix = mlx5e_bits_invert(i, ilog2(sz));
+
+ ix = priv->channels.params.indirection_rqt[ix];
+ rqn = rrp.rss.channels->c[ix]->rq.rqn;
+ } else {
+ rqn = rrp.rqn;
+ }
MLX5_SET(rqtc, rqtc, rq_num[i], rqn);
}
}
-static void mlx5e_fill_direct_rqt_rqn(struct mlx5e_priv *priv, void *rqtc,
- int ix)
-{
- u32 rqn = test_bit(MLX5E_STATE_OPENED, &priv->state) ?
- priv->channel[ix]->rq.rqn :
- priv->drop_rq.rqn;
-
- MLX5_SET(rqtc, rqtc, rq_num[0], rqn);
-}
-
-static int mlx5e_create_rqt(struct mlx5e_priv *priv, int sz,
- int ix, struct mlx5e_rqt *rqt)
-{
- struct mlx5_core_dev *mdev = priv->mdev;
- void *rqtc;
- int inlen;
- int err;
- u32 *in;
-
- inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + sizeof(u32) * sz;
- in = mlx5_vzalloc(inlen);
- if (!in)
- return -ENOMEM;
-
- rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context);
-
- MLX5_SET(rqtc, rqtc, rqt_actual_size, sz);
- MLX5_SET(rqtc, rqtc, rqt_max_size, sz);
-
- if (sz > 1) /* RSS */
- mlx5e_fill_indir_rqt_rqns(priv, rqtc);
- else
- mlx5e_fill_direct_rqt_rqn(priv, rqtc, ix);
-
- err = mlx5_core_create_rqt(mdev, in, inlen, &rqt->rqtn);
- if (!err)
- rqt->enabled = true;
-
- kvfree(in);
- return err;
-}
-
-void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt)
-{
- rqt->enabled = false;
- mlx5_core_destroy_rqt(priv->mdev, rqt->rqtn);
-}
-
-static int mlx5e_create_indirect_rqts(struct mlx5e_priv *priv)
-{
- struct mlx5e_rqt *rqt = &priv->indir_rqt;
-
- return mlx5e_create_rqt(priv, MLX5E_INDIR_RQT_SIZE, 0, rqt);
-}
-
-int mlx5e_create_direct_rqts(struct mlx5e_priv *priv)
-{
- struct mlx5e_rqt *rqt;
- int err;
- int ix;
-
- for (ix = 0; ix < priv->profile->max_nch(priv->mdev); ix++) {
- rqt = &priv->direct_tir[ix].rqt;
- err = mlx5e_create_rqt(priv, 1 /*size */, ix, rqt);
- if (err)
- goto err_destroy_rqts;
- }
-
- return 0;
-
-err_destroy_rqts:
- for (ix--; ix >= 0; ix--)
- mlx5e_destroy_rqt(priv, &priv->direct_tir[ix].rqt);
-
- return err;
-}
-
-int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz, int ix)
+int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz,
+ struct mlx5e_redirect_rqt_param rrp)
{
struct mlx5_core_dev *mdev = priv->mdev;
void *rqtc;
@@ -2029,41 +2211,86 @@ int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz, int ix)
rqtc = MLX5_ADDR_OF(modify_rqt_in, in, ctx);
MLX5_SET(rqtc, rqtc, rqt_actual_size, sz);
- if (sz > 1) /* RSS */
- mlx5e_fill_indir_rqt_rqns(priv, rqtc);
- else
- mlx5e_fill_direct_rqt_rqn(priv, rqtc, ix);
-
MLX5_SET(modify_rqt_in, in, bitmask.rqn_list, 1);
-
+ mlx5e_fill_rqt_rqns(priv, sz, rrp, rqtc);
err = mlx5_core_modify_rqt(mdev, rqtn, in, inlen);
kvfree(in);
-
return err;
}
-static void mlx5e_redirect_rqts(struct mlx5e_priv *priv)
+static u32 mlx5e_get_direct_rqn(struct mlx5e_priv *priv, int ix,
+ struct mlx5e_redirect_rqt_param rrp)
+{
+ if (!rrp.is_rss)
+ return rrp.rqn;
+
+ if (ix >= rrp.rss.channels->num)
+ return priv->drop_rq.rqn;
+
+ return rrp.rss.channels->c[ix]->rq.rqn;
+}
+
+static void mlx5e_redirect_rqts(struct mlx5e_priv *priv,
+ struct mlx5e_redirect_rqt_param rrp)
{
u32 rqtn;
int ix;
if (priv->indir_rqt.enabled) {
+ /* RSS RQ table */
rqtn = priv->indir_rqt.rqtn;
- mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, 0);
+ mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, rrp);
}
- for (ix = 0; ix < priv->params.num_channels; ix++) {
+ for (ix = 0; ix < priv->profile->max_nch(priv->mdev); ix++) {
+ struct mlx5e_redirect_rqt_param direct_rrp = {
+ .is_rss = false,
+ {
+ .rqn = mlx5e_get_direct_rqn(priv, ix, rrp)
+ },
+ };
+
+ /* Direct RQ Tables */
if (!priv->direct_tir[ix].rqt.enabled)
continue;
+
rqtn = priv->direct_tir[ix].rqt.rqtn;
- mlx5e_redirect_rqt(priv, rqtn, 1, ix);
+ mlx5e_redirect_rqt(priv, rqtn, 1, direct_rrp);
}
}
-static void mlx5e_build_tir_ctx_lro(void *tirc, struct mlx5e_priv *priv)
+static void mlx5e_redirect_rqts_to_channels(struct mlx5e_priv *priv,
+ struct mlx5e_channels *chs)
{
- if (!priv->params.lro_en)
+ struct mlx5e_redirect_rqt_param rrp = {
+ .is_rss = true,
+ {
+ .rss = {
+ .channels = chs,
+ .hfunc = chs->params.rss_hfunc,
+ }
+ },
+ };
+
+ mlx5e_redirect_rqts(priv, rrp);
+}
+
+static void mlx5e_redirect_rqts_to_drop(struct mlx5e_priv *priv)
+{
+ struct mlx5e_redirect_rqt_param drop_rrp = {
+ .is_rss = false,
+ {
+ .rqn = priv->drop_rq.rqn,
+ },
+ };
+
+ mlx5e_redirect_rqts(priv, drop_rrp);
+}
+
+static void mlx5e_build_tir_ctx_lro(struct mlx5e_params *params, void *tirc)
+{
+ if (!params->lro_en)
return;
#define ROUGH_MAX_L2_L3_HDR_SZ 256
@@ -2072,13 +2299,13 @@ static void mlx5e_build_tir_ctx_lro(void *tirc, struct mlx5e_priv *priv)
MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO |
MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO);
MLX5_SET(tirc, tirc, lro_max_ip_payload_size,
- (priv->params.lro_wqe_sz -
- ROUGH_MAX_L2_L3_HDR_SZ) >> 8);
- MLX5_SET(tirc, tirc, lro_timeout_period_usecs, priv->params.lro_timeout);
+ (params->lro_wqe_sz - ROUGH_MAX_L2_L3_HDR_SZ) >> 8);
+ MLX5_SET(tirc, tirc, lro_timeout_period_usecs, params->lro_timeout);
}
-void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_priv *priv, void *tirc,
- enum mlx5e_traffic_types tt)
+void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_params *params,
+ enum mlx5e_traffic_types tt,
+ void *tirc)
{
void *hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
@@ -2094,16 +2321,15 @@ void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_priv *priv, void *tirc,
MLX5_HASH_FIELD_SEL_DST_IP |\
MLX5_HASH_FIELD_SEL_IPSEC_SPI)
- MLX5_SET(tirc, tirc, rx_hash_fn,
- mlx5e_rx_hash_fn(priv->params.rss_hfunc));
- if (priv->params.rss_hfunc == ETH_RSS_HASH_TOP) {
+ MLX5_SET(tirc, tirc, rx_hash_fn, mlx5e_rx_hash_fn(params->rss_hfunc));
+ if (params->rss_hfunc == ETH_RSS_HASH_TOP) {
void *rss_key = MLX5_ADDR_OF(tirc, tirc,
rx_hash_toeplitz_key);
size_t len = MLX5_FLD_SZ_BYTES(tirc,
rx_hash_toeplitz_key);
MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
- memcpy(rss_key, priv->params.toeplitz_hash_key, len);
+ memcpy(rss_key, params->toeplitz_hash_key, len);
}
switch (tt) {
@@ -2208,7 +2434,7 @@ static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv)
MLX5_SET(modify_tir_in, in, bitmask.lro, 1);
tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx);
- mlx5e_build_tir_ctx_lro(tirc, priv);
+ mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc);
for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
err = mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in,
@@ -2258,9 +2484,9 @@ static void mlx5e_query_mtu(struct mlx5e_priv *priv, u16 *mtu)
*mtu = MLX5E_HW2SW_MTU(hw_mtu);
}
-static int mlx5e_set_dev_port_mtu(struct net_device *netdev)
+static int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv)
{
- struct mlx5e_priv *priv = netdev_priv(netdev);
+ struct net_device *netdev = priv->netdev;
u16 mtu;
int err;
@@ -2280,8 +2506,8 @@ static int mlx5e_set_dev_port_mtu(struct net_device *netdev)
static void mlx5e_netdev_set_tcs(struct net_device *netdev)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
- int nch = priv->params.num_channels;
- int ntc = priv->params.num_tc;
+ int nch = priv->channels.params.num_channels;
+ int ntc = priv->channels.params.num_tc;
int tc;
netdev_reset_tc(netdev);
@@ -2298,53 +2524,110 @@ static void mlx5e_netdev_set_tcs(struct net_device *netdev)
netdev_set_tc_queue(netdev, tc, nch, 0);
}
+static void mlx5e_build_channels_tx_maps(struct mlx5e_priv *priv)
+{
+ struct mlx5e_channel *c;
+ struct mlx5e_txqsq *sq;
+ int i, tc;
+
+ for (i = 0; i < priv->channels.num; i++)
+ for (tc = 0; tc < priv->profile->max_tc; tc++)
+ priv->channel_tc2txq[i][tc] = i + tc * priv->channels.num;
+
+ for (i = 0; i < priv->channels.num; i++) {
+ c = priv->channels.c[i];
+ for (tc = 0; tc < c->num_tc; tc++) {
+ sq = &c->sq[tc];
+ priv->txq2sq[sq->txq_ix] = sq;
+ }
+ }
+}
+
+static void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
+{
+ int num_txqs = priv->channels.num * priv->channels.params.num_tc;
+ struct net_device *netdev = priv->netdev;
+
+ mlx5e_netdev_set_tcs(netdev);
+ netif_set_real_num_tx_queues(netdev, num_txqs);
+ netif_set_real_num_rx_queues(netdev, priv->channels.num);
+
+ mlx5e_build_channels_tx_maps(priv);
+ mlx5e_activate_channels(&priv->channels);
+ netif_tx_start_all_queues(priv->netdev);
+
+ if (MLX5_CAP_GEN(priv->mdev, vport_group_manager))
+ mlx5e_add_sqs_fwd_rules(priv);
+
+ mlx5e_wait_channels_min_rx_wqes(&priv->channels);
+ mlx5e_redirect_rqts_to_channels(priv, &priv->channels);
+}
+
+static void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
+{
+ mlx5e_redirect_rqts_to_drop(priv);
+
+ if (MLX5_CAP_GEN(priv->mdev, vport_group_manager))
+ mlx5e_remove_sqs_fwd_rules(priv);
+
+ /* FIXME: This is a W/A only for tx timeout watch dog false alarm when
+ * polling for inactive tx queues.
+ */
+ netif_tx_stop_all_queues(priv->netdev);
+ netif_tx_disable(priv->netdev);
+ mlx5e_deactivate_channels(&priv->channels);
+}
+
+void mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
+ struct mlx5e_channels *new_chs,
+ mlx5e_fp_hw_modify hw_modify)
+{
+ struct net_device *netdev = priv->netdev;
+ int new_num_txqs;
+
+ new_num_txqs = new_chs->num * new_chs->params.num_tc;
+
+ netif_carrier_off(netdev);
+
+ if (new_num_txqs < netdev->real_num_tx_queues)
+ netif_set_real_num_tx_queues(netdev, new_num_txqs);
+
+ mlx5e_deactivate_priv_channels(priv);
+ mlx5e_close_channels(&priv->channels);
+
+ priv->channels = *new_chs;
+
+ /* New channels are ready to roll, modify HW settings if needed */
+ if (hw_modify)
+ hw_modify(priv);
+
+ mlx5e_refresh_tirs(priv, false);
+ mlx5e_activate_priv_channels(priv);
+
+ mlx5e_update_carrier(priv);
+}
+
int mlx5e_open_locked(struct net_device *netdev)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
- struct mlx5_core_dev *mdev = priv->mdev;
- int num_txqs;
int err;
set_bit(MLX5E_STATE_OPENED, &priv->state);
- mlx5e_netdev_set_tcs(netdev);
-
- num_txqs = priv->params.num_channels * priv->params.num_tc;
- netif_set_real_num_tx_queues(netdev, num_txqs);
- netif_set_real_num_rx_queues(netdev, priv->params.num_channels);
-
- err = mlx5e_open_channels(priv);
- if (err) {
- netdev_err(netdev, "%s: mlx5e_open_channels failed, %d\n",
- __func__, err);
+ err = mlx5e_open_channels(priv, &priv->channels);
+ if (err)
goto err_clear_state_opened_flag;
- }
- err = mlx5e_refresh_tirs_self_loopback(priv->mdev, false);
- if (err) {
- netdev_err(netdev, "%s: mlx5e_refresh_tirs_self_loopback_enable failed, %d\n",
- __func__, err);
- goto err_close_channels;
- }
-
- mlx5e_redirect_rqts(priv);
+ mlx5e_refresh_tirs(priv, false);
+ mlx5e_activate_priv_channels(priv);
mlx5e_update_carrier(priv);
mlx5e_timestamp_init(priv);
-#ifdef CONFIG_RFS_ACCEL
- priv->netdev->rx_cpu_rmap = priv->mdev->rmap;
-#endif
+
if (priv->profile->update_stats)
queue_delayed_work(priv->wq, &priv->update_stats_work, 0);
- if (MLX5_CAP_GEN(mdev, vport_group_manager)) {
- err = mlx5e_add_sqs_fwd_rules(priv);
- if (err)
- goto err_close_channels;
- }
return 0;
-err_close_channels:
- mlx5e_close_channels(priv);
err_clear_state_opened_flag:
clear_bit(MLX5E_STATE_OPENED, &priv->state);
return err;
@@ -2365,7 +2648,6 @@ int mlx5e_open(struct net_device *netdev)
int mlx5e_close_locked(struct net_device *netdev)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
- struct mlx5_core_dev *mdev = priv->mdev;
/* May already be CLOSED in case a previous configuration operation
* (e.g RX/TX queue size change) that involves close&open failed.
@@ -2375,13 +2657,10 @@ int mlx5e_close_locked(struct net_device *netdev)
clear_bit(MLX5E_STATE_OPENED, &priv->state);
- if (MLX5_CAP_GEN(mdev, vport_group_manager))
- mlx5e_remove_sqs_fwd_rules(priv);
-
mlx5e_timestamp_cleanup(priv);
netif_carrier_off(priv->netdev);
- mlx5e_redirect_rqts(priv);
- mlx5e_close_channels(priv);
+ mlx5e_deactivate_priv_channels(priv);
+ mlx5e_close_channels(&priv->channels);
return 0;
}
@@ -2401,11 +2680,10 @@ int mlx5e_close(struct net_device *netdev)
return err;
}
-static int mlx5e_create_drop_rq(struct mlx5e_priv *priv,
- struct mlx5e_rq *rq,
- struct mlx5e_rq_param *param)
+static int mlx5e_alloc_drop_rq(struct mlx5_core_dev *mdev,
+ struct mlx5e_rq *rq,
+ struct mlx5e_rq_param *param)
{
- struct mlx5_core_dev *mdev = priv->mdev;
void *rqc = param->rqc;
void *rqc_wq = MLX5_ADDR_OF(rqc, rqc, wq);
int err;
@@ -2417,91 +2695,64 @@ static int mlx5e_create_drop_rq(struct mlx5e_priv *priv,
if (err)
return err;
- rq->priv = priv;
+ rq->mdev = mdev;
return 0;
}
-static int mlx5e_create_drop_cq(struct mlx5e_priv *priv,
- struct mlx5e_cq *cq,
- struct mlx5e_cq_param *param)
+static int mlx5e_alloc_drop_cq(struct mlx5_core_dev *mdev,
+ struct mlx5e_cq *cq,
+ struct mlx5e_cq_param *param)
{
- struct mlx5_core_dev *mdev = priv->mdev;
- struct mlx5_core_cq *mcq = &cq->mcq;
- int eqn_not_used;
- unsigned int irqn;
- int err;
-
- err = mlx5_cqwq_create(mdev, ¶m->wq, param->cqc, &cq->wq,
- &cq->wq_ctrl);
- if (err)
- return err;
-
- mlx5_vector2eqn(mdev, param->eq_ix, &eqn_not_used, &irqn);
-
- mcq->cqe_sz = 64;
- mcq->set_ci_db = cq->wq_ctrl.db.db;
- mcq->arm_db = cq->wq_ctrl.db.db + 1;
- *mcq->set_ci_db = 0;
- *mcq->arm_db = 0;
- mcq->vector = param->eq_ix;
- mcq->comp = mlx5e_completion_event;
- mcq->event = mlx5e_cq_error_event;
- mcq->irqn = irqn;
-
- cq->priv = priv;
-
- return 0;
+ return mlx5e_alloc_cq_common(mdev, param, cq);
}
-static int mlx5e_open_drop_rq(struct mlx5e_priv *priv)
+static int mlx5e_open_drop_rq(struct mlx5_core_dev *mdev,
+ struct mlx5e_rq *drop_rq)
{
- struct mlx5e_cq_param cq_param;
- struct mlx5e_rq_param rq_param;
- struct mlx5e_rq *rq = &priv->drop_rq;
- struct mlx5e_cq *cq = &priv->drop_rq.cq;
+ struct mlx5e_cq_param cq_param = {};
+ struct mlx5e_rq_param rq_param = {};
+ struct mlx5e_cq *cq = &drop_rq->cq;
int err;
- memset(&cq_param, 0, sizeof(cq_param));
- memset(&rq_param, 0, sizeof(rq_param));
mlx5e_build_drop_rq_param(&rq_param);
- err = mlx5e_create_drop_cq(priv, cq, &cq_param);
+ err = mlx5e_alloc_drop_cq(mdev, cq, &cq_param);
if (err)
return err;
- err = mlx5e_enable_cq(cq, &cq_param);
+ err = mlx5e_create_cq(cq, &cq_param);
+ if (err)
+ goto err_free_cq;
+
+ err = mlx5e_alloc_drop_rq(mdev, drop_rq, &rq_param);
if (err)
goto err_destroy_cq;
- err = mlx5e_create_drop_rq(priv, rq, &rq_param);
+ err = mlx5e_create_rq(drop_rq, &rq_param);
if (err)
- goto err_disable_cq;
-
- err = mlx5e_enable_rq(rq, &rq_param);
- if (err)
- goto err_destroy_rq;
+ goto err_free_rq;
return 0;
-err_destroy_rq:
- mlx5e_destroy_rq(&priv->drop_rq);
-
-err_disable_cq:
- mlx5e_disable_cq(&priv->drop_rq.cq);
+err_free_rq:
+ mlx5e_free_rq(drop_rq);
err_destroy_cq:
- mlx5e_destroy_cq(&priv->drop_rq.cq);
+ mlx5e_destroy_cq(cq);
+
+err_free_cq:
+ mlx5e_free_cq(cq);
return err;
}
-static void mlx5e_close_drop_rq(struct mlx5e_priv *priv)
+static void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq)
{
- mlx5e_disable_rq(&priv->drop_rq);
- mlx5e_destroy_rq(&priv->drop_rq);
- mlx5e_disable_cq(&priv->drop_rq.cq);
- mlx5e_destroy_cq(&priv->drop_rq.cq);
+ mlx5e_destroy_rq(drop_rq);
+ mlx5e_free_rq(drop_rq);
+ mlx5e_destroy_cq(&drop_rq->cq);
+ mlx5e_free_cq(&drop_rq->cq);
}
static int mlx5e_create_tis(struct mlx5e_priv *priv, int tc)
@@ -2552,24 +2803,24 @@ void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv)
mlx5e_destroy_tis(priv, tc);
}
-static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv, u32 *tirc,
- enum mlx5e_traffic_types tt)
+static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv,
+ enum mlx5e_traffic_types tt,
+ u32 *tirc)
{
MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.td.tdn);
- mlx5e_build_tir_ctx_lro(tirc, priv);
+ mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc);
MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqt.rqtn);
- mlx5e_build_indir_tir_ctx_hash(priv, tirc, tt);
+ mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc);
}
-static void mlx5e_build_direct_tir_ctx(struct mlx5e_priv *priv, u32 *tirc,
- u32 rqtn)
+static void mlx5e_build_direct_tir_ctx(struct mlx5e_priv *priv, u32 rqtn, u32 *tirc)
{
MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.td.tdn);
- mlx5e_build_tir_ctx_lro(tirc, priv);
+ mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc);
MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
MLX5_SET(tirc, tirc, indirect_table, rqtn);
@@ -2594,7 +2845,7 @@ static int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv)
memset(in, 0, inlen);
tir = &priv->indir_tir[tt];
tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
- mlx5e_build_indir_tir_ctx(priv, tirc, tt);
+ mlx5e_build_indir_tir_ctx(priv, tt, tirc);
err = mlx5e_create_tir(priv->mdev, tir, in, inlen);
if (err)
goto err_destroy_tirs;
@@ -2632,8 +2883,7 @@ int mlx5e_create_direct_tirs(struct mlx5e_priv *priv)
memset(in, 0, inlen);
tir = &priv->direct_tir[ix];
tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
- mlx5e_build_direct_tir_ctx(priv, tirc,
- priv->direct_tir[ix].rqt.rqtn);
+ mlx5e_build_direct_tir_ctx(priv, priv->direct_tir[ix].rqt.rqtn, tirc);
err = mlx5e_create_tir(priv->mdev, tir, in, inlen);
if (err)
goto err_destroy_ch_tirs;
@@ -2669,16 +2919,27 @@ void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv)
mlx5e_destroy_tir(priv->mdev, &priv->direct_tir[i]);
}
-int mlx5e_modify_rqs_vsd(struct mlx5e_priv *priv, bool vsd)
+static int mlx5e_modify_channels_scatter_fcs(struct mlx5e_channels *chs, bool enable)
{
int err = 0;
int i;
- if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
- return 0;
+ for (i = 0; i < chs->num; i++) {
+ err = mlx5e_modify_rq_scatter_fcs(&chs->c[i]->rq, enable);
+ if (err)
+ return err;
+ }
- for (i = 0; i < priv->params.num_channels; i++) {
- err = mlx5e_modify_rq_vsd(&priv->channel[i]->rq, vsd);
+ return 0;
+}
+
+static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd)
+{
+ int err = 0;
+ int i;
+
+ for (i = 0; i < chs->num; i++) {
+ err = mlx5e_modify_rq_vsd(&chs->c[i]->rq, vsd);
if (err)
return err;
}
@@ -2689,7 +2950,7 @@ int mlx5e_modify_rqs_vsd(struct mlx5e_priv *priv, bool vsd)
static int mlx5e_setup_tc(struct net_device *netdev, u8 tc)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
- bool was_opened;
+ struct mlx5e_channels new_channels = {};
int err = 0;
if (tc && tc != MLX5E_MAX_NUM_TC)
@@ -2697,17 +2958,21 @@ static int mlx5e_setup_tc(struct net_device *netdev, u8 tc)
mutex_lock(&priv->state_lock);
- was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
- if (was_opened)
- mlx5e_close_locked(priv->netdev);
+ new_channels.params = priv->channels.params;
+ new_channels.params.num_tc = tc ? tc : 1;
- priv->params.num_tc = tc ? tc : 1;
+ if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+ priv->channels.params = new_channels.params;
+ goto out;
+ }
- if (was_opened)
- err = mlx5e_open_locked(priv->netdev);
+ err = mlx5e_open_channels(priv, &new_channels);
+ if (err)
+ goto out;
+ mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+out:
mutex_unlock(&priv->state_lock);
-
return err;
}
@@ -2737,7 +3002,9 @@ static int mlx5e_ndo_setup_tc(struct net_device *dev, u32 handle,
if (tc->type != TC_SETUP_MQPRIO)
return -EINVAL;
- return mlx5e_setup_tc(dev, tc->tc);
+ tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+ return mlx5e_setup_tc(dev, tc->mqprio->num_tc);
}
static void
@@ -2822,26 +3089,31 @@ typedef int (*mlx5e_feature_handler)(struct net_device *netdev, bool enable);
static int set_feature_lro(struct net_device *netdev, bool enable)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
- bool was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
- int err;
+ struct mlx5e_channels new_channels = {};
+ int err = 0;
+ bool reset;
mutex_lock(&priv->state_lock);
- if (was_opened && (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST))
- mlx5e_close_locked(priv->netdev);
+ reset = (priv->channels.params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST);
+ reset = reset && test_bit(MLX5E_STATE_OPENED, &priv->state);
- priv->params.lro_en = enable;
- err = mlx5e_modify_tirs_lro(priv);
- if (err) {
- netdev_err(netdev, "lro modify failed, %d\n", err);
- priv->params.lro_en = !enable;
+ new_channels.params = priv->channels.params;
+ new_channels.params.lro_en = enable;
+
+ if (!reset) {
+ priv->channels.params = new_channels.params;
+ err = mlx5e_modify_tirs_lro(priv);
+ goto out;
}
- if (was_opened && (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST))
- mlx5e_open_locked(priv->netdev);
+ err = mlx5e_open_channels(priv, &new_channels);
+ if (err)
+ goto out;
+ mlx5e_switch_priv_channels(priv, &new_channels, mlx5e_modify_tirs_lro);
+out:
mutex_unlock(&priv->state_lock);
-
return err;
}
@@ -2878,23 +3150,44 @@ static int set_feature_rx_all(struct net_device *netdev, bool enable)
return mlx5_set_port_fcs(mdev, !enable);
}
-static int set_feature_rx_vlan(struct net_device *netdev, bool enable)
+static int set_feature_rx_fcs(struct net_device *netdev, bool enable)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
int err;
mutex_lock(&priv->state_lock);
- priv->params.vlan_strip_disable = !enable;
- err = mlx5e_modify_rqs_vsd(priv, !enable);
+ priv->channels.params.scatter_fcs_en = enable;
+ err = mlx5e_modify_channels_scatter_fcs(&priv->channels, enable);
if (err)
- priv->params.vlan_strip_disable = enable;
+ priv->channels.params.scatter_fcs_en = !enable;
mutex_unlock(&priv->state_lock);
return err;
}
+static int set_feature_rx_vlan(struct net_device *netdev, bool enable)
+{
+ struct mlx5e_priv *priv = netdev_priv(netdev);
+ int err = 0;
+
+ mutex_lock(&priv->state_lock);
+
+ priv->channels.params.vlan_strip_disable = !enable;
+ if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+ goto unlock;
+
+ err = mlx5e_modify_channels_vsd(&priv->channels, !enable);
+ if (err)
+ priv->channels.params.vlan_strip_disable = enable;
+
+unlock:
+ mutex_unlock(&priv->state_lock);
+
+ return err;
+}
+
#ifdef CONFIG_RFS_ACCEL
static int set_feature_arfs(struct net_device *netdev, bool enable)
{
@@ -2947,6 +3240,8 @@ static int mlx5e_set_features(struct net_device *netdev,
set_feature_tc_num_filters);
err |= mlx5e_handle_feature(netdev, features, NETIF_F_RXALL,
set_feature_rx_all);
+ err |= mlx5e_handle_feature(netdev, features, NETIF_F_RXFCS,
+ set_feature_rx_fcs);
err |= mlx5e_handle_feature(netdev, features, NETIF_F_HW_VLAN_CTAG_RX,
set_feature_rx_vlan);
#ifdef CONFIG_RFS_ACCEL
@@ -2960,28 +3255,38 @@ static int mlx5e_set_features(struct net_device *netdev,
static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
- bool was_opened;
+ struct mlx5e_channels new_channels = {};
+ int curr_mtu;
int err = 0;
bool reset;
mutex_lock(&priv->state_lock);
- reset = !priv->params.lro_en &&
- (priv->params.rq_wq_type !=
+ reset = !priv->channels.params.lro_en &&
+ (priv->channels.params.rq_wq_type !=
MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ);
- was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
- if (was_opened && reset)
- mlx5e_close_locked(netdev);
+ reset = reset && test_bit(MLX5E_STATE_OPENED, &priv->state);
+ curr_mtu = netdev->mtu;
netdev->mtu = new_mtu;
- mlx5e_set_dev_port_mtu(netdev);
- if (was_opened && reset)
- err = mlx5e_open_locked(netdev);
+ if (!reset) {
+ mlx5e_set_dev_port_mtu(priv);
+ goto out;
+ }
+ new_channels.params = priv->channels.params;
+ err = mlx5e_open_channels(priv, &new_channels);
+ if (err) {
+ netdev->mtu = curr_mtu;
+ goto out;
+ }
+
+ mlx5e_switch_priv_channels(priv, &new_channels, mlx5e_set_dev_port_mtu);
+
+out:
mutex_unlock(&priv->state_lock);
-
return err;
}
@@ -3100,8 +3405,8 @@ static int mlx5e_get_vf_stats(struct net_device *dev,
vf_stats);
}
-void mlx5e_add_vxlan_port(struct net_device *netdev,
- struct udp_tunnel_info *ti)
+static void mlx5e_add_vxlan_port(struct net_device *netdev,
+ struct udp_tunnel_info *ti)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -3114,8 +3419,8 @@ void mlx5e_add_vxlan_port(struct net_device *netdev,
mlx5e_vxlan_queue_work(priv, ti->sa_family, be16_to_cpu(ti->port), 1);
}
-void mlx5e_del_vxlan_port(struct net_device *netdev,
- struct udp_tunnel_info *ti)
+static void mlx5e_del_vxlan_port(struct net_device *netdev,
+ struct udp_tunnel_info *ti)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -3186,8 +3491,8 @@ static void mlx5e_tx_timeout(struct net_device *dev)
netdev_err(dev, "TX timeout detected\n");
- for (i = 0; i < priv->params.num_channels * priv->params.num_tc; i++) {
- struct mlx5e_sq *sq = priv->txq_to_sq_map[i];
+ for (i = 0; i < priv->channels.num * priv->channels.params.num_tc; i++) {
+ struct mlx5e_txqsq *sq = priv->txq2sq[i];
if (!netif_xmit_stopped(netdev_get_tx_queue(dev, i)))
continue;
@@ -3219,7 +3524,7 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
/* no need for full reset when exchanging programs */
- reset = (!priv->xdp_prog || !prog);
+ reset = (!priv->channels.params.xdp_prog || !prog);
if (was_opened && reset)
mlx5e_close_locked(netdev);
@@ -3227,7 +3532,7 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
/* num_channels is invariant here, so we can take the
* batched reference right upfront.
*/
- prog = bpf_prog_add(prog, priv->params.num_channels);
+ prog = bpf_prog_add(prog, priv->channels.num);
if (IS_ERR(prog)) {
err = PTR_ERR(prog);
goto unlock;
@@ -3237,12 +3542,12 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
/* exchange programs, extra prog reference we got from caller
* as long as we don't fail from this point onwards.
*/
- old_prog = xchg(&priv->xdp_prog, prog);
+ old_prog = xchg(&priv->channels.params.xdp_prog, prog);
if (old_prog)
bpf_prog_put(old_prog);
if (reset) /* change RQ type according to priv->xdp_prog */
- mlx5e_set_rq_priv_params(priv);
+ mlx5e_set_rq_params(priv->mdev, &priv->channels.params);
if (was_opened && reset)
mlx5e_open_locked(netdev);
@@ -3253,8 +3558,8 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
/* exchanging programs w/o reset, we update ref counts on behalf
* of the channels RQs here.
*/
- for (i = 0; i < priv->params.num_channels; i++) {
- struct mlx5e_channel *c = priv->channel[i];
+ for (i = 0; i < priv->channels.num; i++) {
+ struct mlx5e_channel *c = priv->channels.c[i];
clear_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state);
napi_synchronize(&c->napi);
@@ -3280,7 +3585,7 @@ static bool mlx5e_xdp_attached(struct net_device *dev)
{
struct mlx5e_priv *priv = netdev_priv(dev);
- return !!priv->xdp_prog;
+ return !!priv->channels.params.xdp_prog;
}
static int mlx5e_xdp(struct net_device *dev, struct netdev_xdp *xdp)
@@ -3303,10 +3608,12 @@ static int mlx5e_xdp(struct net_device *dev, struct netdev_xdp *xdp)
static void mlx5e_netpoll(struct net_device *dev)
{
struct mlx5e_priv *priv = netdev_priv(dev);
+ struct mlx5e_channels *chs = &priv->channels;
+
int i;
- for (i = 0; i < priv->params.num_channels; i++)
- napi_schedule(&priv->channel[i]->napi);
+ for (i = 0; i < chs->num; i++)
+ napi_schedule(&chs->c[i]->napi);
}
#endif
@@ -3475,6 +3782,13 @@ void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
if (cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE)
params->rx_cq_moderation.usec =
MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE;
+
+ if (params->rx_am_enabled)
+ params->rx_cq_moderation =
+ mlx5e_am_get_def_profile(params->rx_cq_period_mode);
+
+ MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_BASED_MODER,
+ params->rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE);
}
u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout)
@@ -3489,75 +3803,79 @@ u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout)
return MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]);
}
+static void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
+ struct mlx5e_params *params,
+ u16 max_channels)
+{
+ u8 cq_period_mode = 0;
+ u32 link_speed = 0;
+ u32 pci_bw = 0;
+
+ params->num_channels = max_channels;
+ params->num_tc = 1;
+
+ /* SQ */
+ params->log_sq_size = is_kdump_kernel() ?
+ MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE :
+ MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
+
+ /* set CQE compression */
+ params->rx_cqe_compress_def = false;
+ if (MLX5_CAP_GEN(mdev, cqe_compression) &&
+ MLX5_CAP_GEN(mdev, vport_group_manager)) {
+ mlx5e_get_max_linkspeed(mdev, &link_speed);
+ mlx5e_get_pci_bw(mdev, &pci_bw);
+ mlx5_core_dbg(mdev, "Max link speed = %d, PCI BW = %d\n",
+ link_speed, pci_bw);
+ params->rx_cqe_compress_def = cqe_compress_heuristic(link_speed, pci_bw);
+ }
+ MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS, params->rx_cqe_compress_def);
+
+ /* RQ */
+ mlx5e_set_rq_params(mdev, params);
+
+ /* HW LRO */
+ if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
+ params->lro_en = true;
+ params->lro_timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
+
+ /* CQ moderation params */
+ cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
+ MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
+ MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
+ params->rx_am_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
+ mlx5e_set_rx_cq_mode_params(params, cq_period_mode);
+
+ params->tx_cq_moderation.usec = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC;
+ params->tx_cq_moderation.pkts = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS;
+
+ /* TX inline */
+ params->tx_max_inline = mlx5e_get_max_inline_cap(mdev);
+ mlx5_query_min_inline(mdev, ¶ms->tx_min_inline_mode);
+ if (params->tx_min_inline_mode == MLX5_INLINE_MODE_NONE &&
+ !MLX5_CAP_ETH(mdev, wqe_vlan_insert))
+ params->tx_min_inline_mode = MLX5_INLINE_MODE_L2;
+
+ /* RSS */
+ params->rss_hfunc = ETH_RSS_HASH_XOR;
+ netdev_rss_key_fill(params->toeplitz_hash_key, sizeof(params->toeplitz_hash_key));
+ mlx5e_build_default_indir_rqt(mdev, params->indirection_rqt,
+ MLX5E_INDIR_RQT_SIZE, max_channels);
+}
+
static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev,
struct net_device *netdev,
const struct mlx5e_profile *profile,
void *ppriv)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
- u32 link_speed = 0;
- u32 pci_bw = 0;
- u8 cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
- MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
- MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
- priv->mdev = mdev;
- priv->netdev = netdev;
- priv->params.num_channels = profile->max_nch(mdev);
- priv->profile = profile;
- priv->ppriv = ppriv;
+ priv->mdev = mdev;
+ priv->netdev = netdev;
+ priv->profile = profile;
+ priv->ppriv = ppriv;
- priv->params.lro_timeout =
- mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
-
- priv->params.log_sq_size = is_kdump_kernel() ?
- MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE :
- MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
-
- /* set CQE compression */
- priv->params.rx_cqe_compress_def = false;
- if (MLX5_CAP_GEN(mdev, cqe_compression) &&
- MLX5_CAP_GEN(mdev, vport_group_manager)) {
- mlx5e_get_max_linkspeed(mdev, &link_speed);
- mlx5e_get_pci_bw(mdev, &pci_bw);
- mlx5_core_dbg(mdev, "Max link speed = %d, PCI BW = %d\n",
- link_speed, pci_bw);
- priv->params.rx_cqe_compress_def =
- cqe_compress_heuristic(link_speed, pci_bw);
- }
-
- MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS,
- priv->params.rx_cqe_compress_def);
-
- mlx5e_set_rq_priv_params(priv);
- if (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
- priv->params.lro_en = true;
-
- priv->params.rx_am_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
- mlx5e_set_rx_cq_mode_params(&priv->params, cq_period_mode);
-
- priv->params.tx_cq_moderation.usec =
- MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC;
- priv->params.tx_cq_moderation.pkts =
- MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS;
- priv->params.tx_max_inline = mlx5e_get_max_inline_cap(mdev);
- mlx5_query_min_inline(mdev, &priv->params.tx_min_inline_mode);
- if (priv->params.tx_min_inline_mode == MLX5_INLINE_MODE_NONE &&
- !MLX5_CAP_ETH(mdev, wqe_vlan_insert))
- priv->params.tx_min_inline_mode = MLX5_INLINE_MODE_L2;
-
- priv->params.num_tc = 1;
- priv->params.rss_hfunc = ETH_RSS_HASH_XOR;
-
- netdev_rss_key_fill(priv->params.toeplitz_hash_key,
- sizeof(priv->params.toeplitz_hash_key));
-
- mlx5e_build_default_indir_rqt(mdev, priv->params.indirection_rqt,
- MLX5E_INDIR_RQT_SIZE, profile->max_nch(mdev));
-
- /* Initialize pflags */
- MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_BASED_MODER,
- priv->params.rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE);
+ mlx5e_build_nic_params(mdev, &priv->channels.params, profile->max_nch(mdev));
mutex_init(&priv->state_lock);
@@ -3642,13 +3960,19 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
if (fcs_supported)
netdev->hw_features |= NETIF_F_RXALL;
+ if (MLX5_CAP_ETH(mdev, scatter_fcs))
+ netdev->hw_features |= NETIF_F_RXFCS;
+
netdev->features = netdev->hw_features;
- if (!priv->params.lro_en)
+ if (!priv->channels.params.lro_en)
netdev->features &= ~NETIF_F_LRO;
if (fcs_enabled)
netdev->features &= ~NETIF_F_RXALL;
+ if (!priv->channels.params.scatter_fcs_en)
+ netdev->features &= ~NETIF_F_RXFCS;
+
#define FT_CAP(f) MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.f)
if (FT_CAP(flow_modify_en) &&
FT_CAP(modify_root) &&
@@ -3708,8 +4032,8 @@ static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
{
mlx5e_vxlan_cleanup(priv);
- if (priv->xdp_prog)
- bpf_prog_put(priv->xdp_prog);
+ if (priv->channels.params.xdp_prog)
+ bpf_prog_put(priv->channels.params.xdp_prog);
}
static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
@@ -3872,6 +4196,10 @@ struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev,
return NULL;
}
+#ifdef CONFIG_RFS_ACCEL
+ netdev->rx_cpu_rmap = mdev->rmap;
+#endif
+
profile->init(mdev, netdev, profile, ppriv);
netif_carrier_off(netdev);
@@ -3906,7 +4234,7 @@ int mlx5e_attach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev)
if (err)
goto out;
- err = mlx5e_open_drop_rq(priv);
+ err = mlx5e_open_drop_rq(mdev, &priv->drop_rq);
if (err) {
mlx5_core_err(mdev, "open drop rq failed, %d\n", err);
goto err_cleanup_tx;
@@ -3925,7 +4253,7 @@ int mlx5e_attach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev)
mlx5_query_port_max_mtu(priv->mdev, &max_mtu, 1);
netdev->max_mtu = MLX5E_HW2SW_MTU(max_mtu);
- mlx5e_set_dev_port_mtu(netdev);
+ mlx5e_set_dev_port_mtu(priv);
if (profile->enable)
profile->enable(priv);
@@ -3939,7 +4267,7 @@ int mlx5e_attach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev)
return 0;
err_close_drop_rq:
- mlx5e_close_drop_rq(priv);
+ mlx5e_close_drop_rq(&priv->drop_rq);
err_cleanup_tx:
profile->cleanup_tx(priv);
@@ -4003,7 +4331,7 @@ void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev)
mlx5e_destroy_q_counter(priv);
profile->cleanup_rx(priv);
- mlx5e_close_drop_rq(priv);
+ mlx5e_close_drop_rq(&priv->drop_rq);
profile->cleanup_tx(priv);
cancel_delayed_work_sync(&priv->update_stats_work);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 2c86457..53db5ec 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -102,14 +102,16 @@ static void mlx5e_rep_update_sw_counters(struct mlx5e_priv *priv)
int i, j;
memset(s, 0, sizeof(*s));
- for (i = 0; i < priv->params.num_channels; i++) {
- rq_stats = &priv->channel[i]->rq.stats;
+ for (i = 0; i < priv->channels.num; i++) {
+ struct mlx5e_channel *c = priv->channels.c[i];
+
+ rq_stats = &c->rq.stats;
s->rx_packets += rq_stats->packets;
s->rx_bytes += rq_stats->bytes;
- for (j = 0; j < priv->params.num_tc; j++) {
- sq_stats = &priv->channel[i]->sq[j].stats;
+ for (j = 0; j < priv->channels.params.num_tc; j++) {
+ sq_stats = &c->sq[j].stats;
s->tx_packets += sq_stats->packets;
s->tx_bytes += sq_stats->bytes;
@@ -187,22 +189,26 @@ int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv)
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
struct mlx5_eswitch_rep *rep = priv->ppriv;
struct mlx5e_channel *c;
- int n, tc, err, num_sqs = 0;
+ int n, tc, num_sqs = 0;
+ int err = -ENOMEM;
u16 *sqs;
- sqs = kcalloc(priv->params.num_channels * priv->params.num_tc, sizeof(u16), GFP_KERNEL);
+ sqs = kcalloc(priv->channels.num * priv->channels.params.num_tc, sizeof(u16), GFP_KERNEL);
if (!sqs)
- return -ENOMEM;
+ goto out;
- for (n = 0; n < priv->params.num_channels; n++) {
- c = priv->channel[n];
+ for (n = 0; n < priv->channels.num; n++) {
+ c = priv->channels.c[n];
for (tc = 0; tc < c->num_tc; tc++)
sqs[num_sqs++] = c->sq[tc].sqn;
}
err = mlx5_eswitch_sqs2vport_start(esw, rep, sqs, num_sqs);
-
kfree(sqs);
+
+out:
+ if (err)
+ netdev_warn(priv->netdev, "Failed to add SQs FWD rules %d\n", err);
return err;
}
@@ -393,48 +399,27 @@ static const struct net_device_ops mlx5e_netdev_ops_rep = {
.ndo_get_phys_port_name = mlx5e_rep_get_phys_port_name,
.ndo_setup_tc = mlx5e_rep_ndo_setup_tc,
.ndo_get_stats64 = mlx5e_rep_get_stats,
- .ndo_udp_tunnel_add = mlx5e_add_vxlan_port,
- .ndo_udp_tunnel_del = mlx5e_del_vxlan_port,
.ndo_has_offload_stats = mlx5e_has_offload_stats,
.ndo_get_offload_stats = mlx5e_get_offload_stats,
};
-static void mlx5e_build_rep_netdev_priv(struct mlx5_core_dev *mdev,
- struct net_device *netdev,
- const struct mlx5e_profile *profile,
- void *ppriv)
+static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
+ struct mlx5e_params *params)
{
- struct mlx5e_priv *priv = netdev_priv(netdev);
u8 cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
- priv->params.log_sq_size =
- MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
- priv->params.rq_wq_type = MLX5_WQ_TYPE_LINKED_LIST;
- priv->params.log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
+ params->log_sq_size = MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
+ params->rq_wq_type = MLX5_WQ_TYPE_LINKED_LIST;
+ params->log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
- priv->params.min_rx_wqes = mlx5_min_rx_wqes(priv->params.rq_wq_type,
- BIT(priv->params.log_rq_size));
+ params->rx_am_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
+ mlx5e_set_rx_cq_mode_params(params, cq_period_mode);
- priv->params.rx_am_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
- mlx5e_set_rx_cq_mode_params(&priv->params, cq_period_mode);
-
- priv->params.tx_max_inline = mlx5e_get_max_inline_cap(mdev);
- priv->params.num_tc = 1;
-
- priv->params.lro_wqe_sz =
- MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
-
- priv->mdev = mdev;
- priv->netdev = netdev;
- priv->params.num_channels = profile->max_nch(mdev);
- priv->profile = profile;
- priv->ppriv = ppriv;
-
- mutex_init(&priv->state_lock);
-
- INIT_DELAYED_WORK(&priv->update_stats_work, mlx5e_update_stats_work);
+ params->tx_max_inline = mlx5e_get_max_inline_cap(mdev);
+ params->num_tc = 1;
+ params->lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
}
static void mlx5e_build_rep_netdev(struct net_device *netdev)
@@ -460,7 +445,19 @@ static void mlx5e_init_rep(struct mlx5_core_dev *mdev,
const struct mlx5e_profile *profile,
void *ppriv)
{
- mlx5e_build_rep_netdev_priv(mdev, netdev, profile, ppriv);
+ struct mlx5e_priv *priv = netdev_priv(netdev);
+
+ priv->mdev = mdev;
+ priv->netdev = netdev;
+ priv->profile = profile;
+ priv->ppriv = ppriv;
+
+ mutex_init(&priv->state_lock);
+
+ INIT_DELAYED_WORK(&priv->update_stats_work, mlx5e_update_stats_work);
+
+ priv->channels.params.num_channels = profile->max_nch(mdev);
+ mlx5e_build_rep_params(mdev, &priv->channels.params);
mlx5e_build_rep_netdev(netdev);
}
@@ -505,7 +502,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
err_destroy_direct_tirs:
mlx5e_destroy_direct_tirs(priv);
err_destroy_direct_rqts:
- for (i = 0; i < priv->params.num_channels; i++)
+ for (i = 0; i < priv->channels.params.num_channels; i++)
mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt);
return err;
}
@@ -518,7 +515,7 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
mlx5e_tc_cleanup(priv);
mlx5_del_flow_rules(rep->vport_rx_rule);
mlx5e_destroy_direct_tirs(priv);
- for (i = 0; i < priv->params.num_channels; i++)
+ for (i = 0; i < priv->channels.params.num_channels; i++)
mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 3d37168..1a9532b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -156,28 +156,6 @@ static inline u32 mlx5e_decompress_cqes_start(struct mlx5e_rq *rq,
return mlx5e_decompress_cqes_cont(rq, cq, 1, budget_rem) - 1;
}
-void mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool val)
-{
- bool was_opened;
-
- if (!MLX5_CAP_GEN(priv->mdev, cqe_compression))
- return;
-
- if (MLX5E_GET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS) == val)
- return;
-
- was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
- if (was_opened)
- mlx5e_close_locked(priv->netdev);
-
- MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS, val);
- mlx5e_set_rq_type_params(priv, priv->params.rq_wq_type);
-
- if (was_opened)
- mlx5e_open_locked(priv->netdev);
-
-}
-
#define RQ_PAGE_SIZE(rq) ((1 << rq->buff.page_order) << PAGE_SHIFT)
static inline bool mlx5e_rx_cache_put(struct mlx5e_rq *rq,
@@ -331,7 +309,7 @@ mlx5e_copy_skb_header_mpwqe(struct device *pdev,
static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix)
{
struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
- struct mlx5e_sq *sq = &rq->channel->icosq;
+ struct mlx5e_icosq *sq = &rq->channel->icosq;
struct mlx5_wq_cyc *wq = &sq->wq;
struct mlx5e_umr_wqe *wqe;
u8 num_wqebbs = DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_BB);
@@ -341,7 +319,7 @@ static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix)
while ((pi = (sq->pc & wq->sz_m1)) > sq->edge) {
sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP;
sq->db.ico_wqe[pi].num_wqebbs = 1;
- mlx5e_send_nop(sq, false);
+ mlx5e_post_nop(wq, sq->sqn, &sq->pc);
}
wqe = mlx5_wq_cyc_get_wqe(wq, pi);
@@ -353,7 +331,7 @@ static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix)
sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
sq->db.ico_wqe[pi].num_wqebbs = num_wqebbs;
sq->pc += num_wqebbs;
- mlx5e_tx_notify_hw(sq, &wqe->ctrl, 0);
+ mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &wqe->ctrl);
}
static int mlx5e_alloc_rx_umr_mpwqe(struct mlx5e_rq *rq,
@@ -601,6 +579,10 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
if (lro_num_seg > 1) {
mlx5e_lro_update_hdr(skb, cqe, cqe_bcnt);
skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt, lro_num_seg);
+ /* Subtract one since we already counted this as one
+ * "regular" packet in mlx5e_complete_rx_cqe()
+ */
+ rq->stats.packets += lro_num_seg - 1;
rq->stats.lro_packets++;
rq->stats.lro_bytes += cqe_bcnt;
}
@@ -633,37 +615,36 @@ static inline void mlx5e_complete_rx_cqe(struct mlx5e_rq *rq,
mlx5e_build_rx_skb(cqe, cqe_bcnt, rq, skb);
}
-static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_sq *sq)
+static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
{
struct mlx5_wq_cyc *wq = &sq->wq;
struct mlx5e_tx_wqe *wqe;
- u16 pi = (sq->pc - MLX5E_XDP_TX_WQEBBS) & wq->sz_m1; /* last pi */
+ u16 pi = (sq->pc - 1) & wq->sz_m1; /* last pi */
wqe = mlx5_wq_cyc_get_wqe(wq, pi);
- wqe->ctrl.fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE;
- mlx5e_tx_notify_hw(sq, &wqe->ctrl, 0);
+ mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &wqe->ctrl);
}
static inline bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq,
struct mlx5e_dma_info *di,
const struct xdp_buff *xdp)
{
- struct mlx5e_sq *sq = &rq->channel->xdp_sq;
+ struct mlx5e_xdpsq *sq = &rq->xdpsq;
struct mlx5_wq_cyc *wq = &sq->wq;
- u16 pi = sq->pc & wq->sz_m1;
+ u16 pi = sq->pc & wq->sz_m1;
struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi);
- struct mlx5e_sq_wqe_info *wi = &sq->db.xdp.wqe_info[pi];
struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
struct mlx5_wqe_eth_seg *eseg = &wqe->eth;
struct mlx5_wqe_data_seg *dseg;
- u8 ds_cnt = MLX5E_XDP_TX_DS_COUNT;
ptrdiff_t data_offset = xdp->data - xdp->data_hard_start;
dma_addr_t dma_addr = di->addr + data_offset;
unsigned int dma_len = xdp->data_end - xdp->data;
+ prefetchw(wqe);
+
if (unlikely(dma_len < MLX5E_XDP_MIN_INLINE ||
MLX5E_SW2HW_MTU(rq->netdev->mtu) < dma_len)) {
rq->stats.xdp_drop++;
@@ -671,48 +652,42 @@ static inline bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq,
return false;
}
- if (unlikely(!mlx5e_sq_has_room_for(sq, MLX5E_XDP_TX_WQEBBS))) {
- if (sq->db.xdp.doorbell) {
+ if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1))) {
+ if (sq->db.doorbell) {
/* SQ is full, ring doorbell */
mlx5e_xmit_xdp_doorbell(sq);
- sq->db.xdp.doorbell = false;
+ sq->db.doorbell = false;
}
rq->stats.xdp_tx_full++;
mlx5e_page_release(rq, di, true);
return false;
}
- dma_sync_single_for_device(sq->pdev, dma_addr, dma_len,
- PCI_DMA_TODEVICE);
+ dma_sync_single_for_device(sq->pdev, dma_addr, dma_len, PCI_DMA_TODEVICE);
- memset(wqe, 0, sizeof(*wqe));
+ cseg->fm_ce_se = 0;
dseg = (struct mlx5_wqe_data_seg *)eseg + 1;
+
/* copy the inline part if required */
if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
memcpy(eseg->inline_hdr.start, xdp->data, MLX5E_XDP_MIN_INLINE);
eseg->inline_hdr.sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE);
dma_len -= MLX5E_XDP_MIN_INLINE;
dma_addr += MLX5E_XDP_MIN_INLINE;
-
- ds_cnt += MLX5E_XDP_IHS_DS_COUNT;
dseg++;
}
/* write the dma part */
dseg->addr = cpu_to_be64(dma_addr);
dseg->byte_count = cpu_to_be32(dma_len);
- dseg->lkey = sq->mkey_be;
cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_SEND);
- cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
- sq->db.xdp.di[pi] = *di;
- wi->opcode = MLX5_OPCODE_SEND;
- wi->num_wqebbs = MLX5E_XDP_TX_WQEBBS;
- sq->pc += MLX5E_XDP_TX_WQEBBS;
+ sq->db.di[pi] = *di;
+ sq->pc++;
- sq->db.xdp.doorbell = true;
+ sq->db.doorbell = true;
rq->stats.xdp_tx++;
return true;
}
@@ -946,7 +921,7 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
{
struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq);
- struct mlx5e_sq *xdp_sq = &rq->channel->xdp_sq;
+ struct mlx5e_xdpsq *xdpsq = &rq->xdpsq;
int work_done = 0;
if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state)))
@@ -973,9 +948,9 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
rq->handle_rx_cqe(rq, cqe);
}
- if (xdp_sq->db.xdp.doorbell) {
- mlx5e_xmit_xdp_doorbell(xdp_sq);
- xdp_sq->db.xdp.doorbell = false;
+ if (xdpsq->db.doorbell) {
+ mlx5e_xmit_xdp_doorbell(xdpsq);
+ xdpsq->db.doorbell = false;
}
mlx5_cqwq_update_db_record(&cq->wq);
@@ -985,3 +960,74 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
return work_done;
}
+
+bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
+{
+ struct mlx5e_xdpsq *sq;
+ struct mlx5e_rq *rq;
+ u16 sqcc;
+ int i;
+
+ sq = container_of(cq, struct mlx5e_xdpsq, cq);
+
+ if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
+ return false;
+
+ rq = container_of(sq, struct mlx5e_rq, xdpsq);
+
+ /* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
+ * otherwise a cq overrun may occur
+ */
+ sqcc = sq->cc;
+
+ for (i = 0; i < MLX5E_TX_CQ_POLL_BUDGET; i++) {
+ struct mlx5_cqe64 *cqe;
+ u16 wqe_counter;
+ bool last_wqe;
+
+ cqe = mlx5e_get_cqe(cq);
+ if (!cqe)
+ break;
+
+ mlx5_cqwq_pop(&cq->wq);
+
+ wqe_counter = be16_to_cpu(cqe->wqe_counter);
+
+ do {
+ struct mlx5e_dma_info *di;
+ u16 ci;
+
+ last_wqe = (sqcc == wqe_counter);
+
+ ci = sqcc & sq->wq.sz_m1;
+ di = &sq->db.di[ci];
+
+ sqcc++;
+ /* Recycle RX page */
+ mlx5e_page_release(rq, di, true);
+ } while (!last_wqe);
+ }
+
+ mlx5_cqwq_update_db_record(&cq->wq);
+
+ /* ensure cq space is freed before enabling more cqes */
+ wmb();
+
+ sq->cc = sqcc;
+ return (i == MLX5E_TX_CQ_POLL_BUDGET);
+}
+
+void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
+{
+ struct mlx5e_rq *rq = container_of(sq, struct mlx5e_rq, xdpsq);
+ struct mlx5e_dma_info *di;
+ u16 ci;
+
+ while (sq->cc != sq->pc) {
+ ci = sq->cc & sq->wq.sz_m1;
+ di = &sq->db.di[ci];
+ sq->cc++;
+
+ mlx5e_page_release(rq, di, false);
+ }
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
index cbfac06..02dd3a9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
@@ -293,7 +293,7 @@ void mlx5e_rx_am_work(struct work_struct *work)
struct mlx5e_rq *rq = container_of(am, struct mlx5e_rq, am);
struct mlx5e_cq_moder cur_profile = profile[am->mode][am->profile_ix];
- mlx5_core_modify_cq_moderation(rq->priv->mdev, &rq->cq.mcq,
+ mlx5_core_modify_cq_moderation(rq->mdev, &rq->cq.mcq,
cur_profile.usec, cur_profile.pkts);
am->state = MLX5E_AM_START_MEASURE;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 31e3cb7..5225f22 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -204,9 +204,6 @@ mlx5e_test_loopback_validate(struct sk_buff *skb,
struct iphdr *iph;
/* We are only going to peek, no need to clone the SKB */
- if (skb->protocol != htons(ETH_P_IP))
- goto out;
-
if (MLX5E_TEST_PKT_SIZE - ETH_HLEN > skb_headlen(skb))
goto out;
@@ -239,17 +236,14 @@ static int mlx5e_test_loopback_setup(struct mlx5e_priv *priv,
{
int err = 0;
- err = mlx5e_refresh_tirs_self_loopback(priv->mdev, true);
- if (err) {
- netdev_err(priv->netdev,
- "\tFailed to enable UC loopback err(%d)\n", err);
+ err = mlx5e_refresh_tirs(priv, true);
+ if (err)
return err;
- }
lbtp->loopback_ok = false;
init_completion(&lbtp->comp);
- lbtp->pt.type = htons(ETH_P_ALL);
+ lbtp->pt.type = htons(ETH_P_IP);
lbtp->pt.func = mlx5e_test_loopback_validate;
lbtp->pt.dev = priv->netdev;
lbtp->pt.af_packet_priv = lbtp;
@@ -261,7 +255,7 @@ static void mlx5e_test_loopback_cleanup(struct mlx5e_priv *priv,
struct mlx5e_lbt_priv *lbtp)
{
dev_remove_pack(&lbtp->pt);
- mlx5e_refresh_tirs_self_loopback(priv->mdev, false);
+ mlx5e_refresh_tirs(priv, false);
}
#define MLX5E_LB_VERIFY_TIMEOUT (msecs_to_jiffies(200))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 44406a5..9dec11c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -42,18 +42,40 @@
#include <net/tc_act/tc_mirred.h>
#include <net/tc_act/tc_vlan.h>
#include <net/tc_act/tc_tunnel_key.h>
+#include <net/tc_act/tc_pedit.h>
#include <net/vxlan.h>
#include "en.h"
#include "en_tc.h"
#include "eswitch.h"
#include "vxlan.h"
+struct mlx5_nic_flow_attr {
+ u32 action;
+ u32 flow_tag;
+ u32 mod_hdr_id;
+};
+
+enum {
+ MLX5E_TC_FLOW_ESWITCH = BIT(0),
+ MLX5E_TC_FLOW_NIC = BIT(1),
+};
+
struct mlx5e_tc_flow {
struct rhash_head node;
u64 cookie;
+ u8 flags;
struct mlx5_flow_handle *rule;
struct list_head encap; /* flows sharing the same encap */
- struct mlx5_esw_flow_attr *attr;
+ union {
+ struct mlx5_esw_flow_attr esw_attr[0];
+ struct mlx5_nic_flow_attr nic_attr[0];
+ };
+};
+
+struct mlx5e_tc_flow_parse_attr {
+ struct mlx5_flow_spec spec;
+ int num_mod_hdr_actions;
+ void *mod_hdr_actions;
};
enum {
@@ -66,24 +88,26 @@ enum {
static struct mlx5_flow_handle *
mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
- struct mlx5_flow_spec *spec,
- u32 action, u32 flow_tag)
+ struct mlx5e_tc_flow_parse_attr *parse_attr,
+ struct mlx5e_tc_flow *flow)
{
+ struct mlx5_nic_flow_attr *attr = flow->nic_attr;
struct mlx5_core_dev *dev = priv->mdev;
- struct mlx5_flow_destination dest = { 0 };
+ struct mlx5_flow_destination dest = {};
struct mlx5_flow_act flow_act = {
- .action = action,
- .flow_tag = flow_tag,
+ .action = attr->action,
+ .flow_tag = attr->flow_tag,
.encap_id = 0,
};
struct mlx5_fc *counter = NULL;
struct mlx5_flow_handle *rule;
bool table_created = false;
+ int err;
- if (action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
+ if (attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
dest.ft = priv->fs.vlan.ft.t;
- } else if (action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
+ } else if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
counter = mlx5_fc_create(dev, true);
if (IS_ERR(counter))
return ERR_CAST(counter);
@@ -92,6 +116,19 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
dest.counter = counter;
}
+ if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
+ err = mlx5_modify_header_alloc(dev, MLX5_FLOW_NAMESPACE_KERNEL,
+ parse_attr->num_mod_hdr_actions,
+ parse_attr->mod_hdr_actions,
+ &attr->mod_hdr_id);
+ flow_act.modify_id = attr->mod_hdr_id;
+ kfree(parse_attr->mod_hdr_actions);
+ if (err) {
+ rule = ERR_PTR(err);
+ goto err_create_mod_hdr_id;
+ }
+ }
+
if (IS_ERR_OR_NULL(priv->fs.tc.t)) {
priv->fs.tc.t =
mlx5_create_auto_grouped_flow_table(priv->fs.ns,
@@ -109,8 +146,9 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
table_created = true;
}
- spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
- rule = mlx5_add_flow_rules(priv->fs.tc.t, spec, &flow_act, &dest, 1);
+ parse_attr->spec.match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+ rule = mlx5_add_flow_rules(priv->fs.tc.t, &parse_attr->spec,
+ &flow_act, &dest, 1);
if (IS_ERR(rule))
goto err_add_rule;
@@ -123,28 +161,104 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
priv->fs.tc.t = NULL;
}
err_create_ft:
+ if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+ mlx5_modify_header_dealloc(priv->mdev,
+ attr->mod_hdr_id);
+err_create_mod_hdr_id:
mlx5_fc_destroy(dev, counter);
return rule;
}
-static struct mlx5_flow_handle *
-mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
- struct mlx5_flow_spec *spec,
- struct mlx5_esw_flow_attr *attr)
+static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv,
+ struct mlx5e_tc_flow *flow)
{
- struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
- int err;
+ struct mlx5_fc *counter = NULL;
- err = mlx5_eswitch_add_vlan_action(esw, attr);
- if (err)
- return ERR_PTR(err);
+ counter = mlx5_flow_rule_counter(flow->rule);
+ mlx5_del_flow_rules(flow->rule);
+ mlx5_fc_destroy(priv->mdev, counter);
- return mlx5_eswitch_add_offloaded_rule(esw, spec, attr);
+ if (!mlx5e_tc_num_filters(priv) && (priv->fs.tc.t)) {
+ mlx5_destroy_flow_table(priv->fs.tc.t);
+ priv->fs.tc.t = NULL;
+ }
+
+ if (flow->nic_attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+ mlx5_modify_header_dealloc(priv->mdev,
+ flow->nic_attr->mod_hdr_id);
}
static void mlx5e_detach_encap(struct mlx5e_priv *priv,
- struct mlx5e_tc_flow *flow) {
+ struct mlx5e_tc_flow *flow);
+
+static struct mlx5_flow_handle *
+mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
+ struct mlx5e_tc_flow_parse_attr *parse_attr,
+ struct mlx5e_tc_flow *flow)
+{
+ struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+ struct mlx5_esw_flow_attr *attr = flow->esw_attr;
+ struct mlx5_flow_handle *rule;
+ int err;
+
+ err = mlx5_eswitch_add_vlan_action(esw, attr);
+ if (err) {
+ rule = ERR_PTR(err);
+ goto err_add_vlan;
+ }
+
+ if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
+ err = mlx5_modify_header_alloc(priv->mdev, MLX5_FLOW_NAMESPACE_FDB,
+ parse_attr->num_mod_hdr_actions,
+ parse_attr->mod_hdr_actions,
+ &attr->mod_hdr_id);
+ kfree(parse_attr->mod_hdr_actions);
+ if (err) {
+ rule = ERR_PTR(err);
+ goto err_mod_hdr;
+ }
+ }
+
+ rule = mlx5_eswitch_add_offloaded_rule(esw, &parse_attr->spec, attr);
+ if (IS_ERR(rule))
+ goto err_add_rule;
+
+ return rule;
+
+err_add_rule:
+ if (flow->esw_attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+ mlx5_modify_header_dealloc(priv->mdev,
+ attr->mod_hdr_id);
+err_mod_hdr:
+ mlx5_eswitch_del_vlan_action(esw, attr);
+err_add_vlan:
+ if (attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP)
+ mlx5e_detach_encap(priv, flow);
+ return rule;
+}
+
+static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
+ struct mlx5e_tc_flow *flow)
+{
+ struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+ struct mlx5_esw_flow_attr *attr = flow->esw_attr;
+
+ mlx5_eswitch_del_offloaded_rule(esw, flow->rule, flow->esw_attr);
+
+ mlx5_eswitch_del_vlan_action(esw, flow->esw_attr);
+
+ if (flow->esw_attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP)
+ mlx5e_detach_encap(priv, flow);
+
+ if (flow->esw_attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+ mlx5_modify_header_dealloc(priv->mdev,
+ attr->mod_hdr_id);
+}
+
+static void mlx5e_detach_encap(struct mlx5e_priv *priv,
+ struct mlx5e_tc_flow *flow)
+{
struct list_head *next = flow->encap.next;
list_del(&flow->encap);
@@ -161,32 +275,13 @@ static void mlx5e_detach_encap(struct mlx5e_priv *priv,
}
}
-/* we get here also when setting rule to the FW failed, etc. It means that the
- * flow rule itself might not exist, but some offloading related to the actions
- * should be cleaned.
- */
static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
struct mlx5e_tc_flow *flow)
{
- struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
- struct mlx5_fc *counter = NULL;
-
- if (!IS_ERR(flow->rule)) {
- counter = mlx5_flow_rule_counter(flow->rule);
- mlx5_del_flow_rules(flow->rule);
- mlx5_fc_destroy(priv->mdev, counter);
- }
-
- if (esw && esw->mode == SRIOV_OFFLOADS) {
- mlx5_eswitch_del_vlan_action(esw, flow->attr);
- if (flow->attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP)
- mlx5e_detach_encap(priv, flow);
- }
-
- if (!mlx5e_tc_num_filters(priv) && (priv->fs.tc.t)) {
- mlx5_destroy_flow_table(priv->fs.tc.t);
- priv->fs.tc.t = NULL;
- }
+ if (flow->flags & MLX5E_TC_FLOW_ESWITCH)
+ mlx5e_tc_del_fdb_flow(priv, flow);
+ else
+ mlx5e_tc_del_nic_flow(priv, flow);
}
static void parse_vxlan_attr(struct mlx5_flow_spec *spec,
@@ -243,12 +338,15 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
skb_flow_dissector_target(f->dissector,
FLOW_DISSECTOR_KEY_ENC_PORTS,
f->mask);
+ struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+ struct net_device *up_dev = mlx5_eswitch_get_uplink_netdev(esw);
+ struct mlx5e_priv *up_priv = netdev_priv(up_dev);
/* Full udp dst port must be given */
if (memchr_inv(&mask->dst, 0xff, sizeof(mask->dst)))
goto vxlan_match_offload_err;
- if (mlx5e_vxlan_lookup_port(priv, be16_to_cpu(key->dst)) &&
+ if (mlx5e_vxlan_lookup_port(up_priv, be16_to_cpu(key->dst)) &&
MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap))
parse_vxlan_attr(spec, f);
else {
@@ -598,6 +696,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
}
static int parse_cls_flower(struct mlx5e_priv *priv,
+ struct mlx5e_tc_flow *flow,
struct mlx5_flow_spec *spec,
struct tc_cls_flower_offload *f)
{
@@ -609,7 +708,7 @@ static int parse_cls_flower(struct mlx5e_priv *priv,
err = __parse_cls_flower(priv, spec, f, &min_inline);
- if (!err && esw->mode == SRIOV_OFFLOADS &&
+ if (!err && (flow->flags & MLX5E_TC_FLOW_ESWITCH) &&
rep->vport != FDB_UPLINK_VPORT) {
if (min_inline > esw->offloads.inline_mode) {
netdev_warn(priv->netdev,
@@ -622,29 +721,313 @@ static int parse_cls_flower(struct mlx5e_priv *priv,
return err;
}
-static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
- u32 *action, u32 *flow_tag)
+struct pedit_headers {
+ struct ethhdr eth;
+ struct iphdr ip4;
+ struct ipv6hdr ip6;
+ struct tcphdr tcp;
+ struct udphdr udp;
+};
+
+static int pedit_header_offsets[] = {
+ [TCA_PEDIT_KEY_EX_HDR_TYPE_ETH] = offsetof(struct pedit_headers, eth),
+ [TCA_PEDIT_KEY_EX_HDR_TYPE_IP4] = offsetof(struct pedit_headers, ip4),
+ [TCA_PEDIT_KEY_EX_HDR_TYPE_IP6] = offsetof(struct pedit_headers, ip6),
+ [TCA_PEDIT_KEY_EX_HDR_TYPE_TCP] = offsetof(struct pedit_headers, tcp),
+ [TCA_PEDIT_KEY_EX_HDR_TYPE_UDP] = offsetof(struct pedit_headers, udp),
+};
+
+#define pedit_header(_ph, _htype) ((void *)(_ph) + pedit_header_offsets[_htype])
+
+static int set_pedit_val(u8 hdr_type, u32 mask, u32 val, u32 offset,
+ struct pedit_headers *masks,
+ struct pedit_headers *vals)
{
+ u32 *curr_pmask, *curr_pval;
+
+ if (hdr_type >= __PEDIT_HDR_TYPE_MAX)
+ goto out_err;
+
+ curr_pmask = (u32 *)(pedit_header(masks, hdr_type) + offset);
+ curr_pval = (u32 *)(pedit_header(vals, hdr_type) + offset);
+
+ if (*curr_pmask & mask) /* disallow acting twice on the same location */
+ goto out_err;
+
+ *curr_pmask |= mask;
+ *curr_pval |= (val & mask);
+
+ return 0;
+
+out_err:
+ return -EOPNOTSUPP;
+}
+
+struct mlx5_fields {
+ u8 field;
+ u8 size;
+ u32 offset;
+};
+
+static struct mlx5_fields fields[] = {
+ {MLX5_ACTION_IN_FIELD_OUT_DMAC_47_16, 4, offsetof(struct pedit_headers, eth.h_dest[0])},
+ {MLX5_ACTION_IN_FIELD_OUT_DMAC_15_0, 2, offsetof(struct pedit_headers, eth.h_dest[4])},
+ {MLX5_ACTION_IN_FIELD_OUT_SMAC_47_16, 4, offsetof(struct pedit_headers, eth.h_source[0])},
+ {MLX5_ACTION_IN_FIELD_OUT_SMAC_15_0, 2, offsetof(struct pedit_headers, eth.h_source[4])},
+ {MLX5_ACTION_IN_FIELD_OUT_ETHERTYPE, 2, offsetof(struct pedit_headers, eth.h_proto)},
+
+ {MLX5_ACTION_IN_FIELD_OUT_IP_DSCP, 1, offsetof(struct pedit_headers, ip4.tos)},
+ {MLX5_ACTION_IN_FIELD_OUT_IP_TTL, 1, offsetof(struct pedit_headers, ip4.ttl)},
+ {MLX5_ACTION_IN_FIELD_OUT_SIPV4, 4, offsetof(struct pedit_headers, ip4.saddr)},
+ {MLX5_ACTION_IN_FIELD_OUT_DIPV4, 4, offsetof(struct pedit_headers, ip4.daddr)},
+
+ {MLX5_ACTION_IN_FIELD_OUT_SIPV6_127_96, 4, offsetof(struct pedit_headers, ip6.saddr.s6_addr32[0])},
+ {MLX5_ACTION_IN_FIELD_OUT_SIPV6_95_64, 4, offsetof(struct pedit_headers, ip6.saddr.s6_addr32[1])},
+ {MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32, 4, offsetof(struct pedit_headers, ip6.saddr.s6_addr32[2])},
+ {MLX5_ACTION_IN_FIELD_OUT_SIPV6_31_0, 4, offsetof(struct pedit_headers, ip6.saddr.s6_addr32[3])},
+ {MLX5_ACTION_IN_FIELD_OUT_DIPV6_127_96, 4, offsetof(struct pedit_headers, ip6.daddr.s6_addr32[0])},
+ {MLX5_ACTION_IN_FIELD_OUT_DIPV6_95_64, 4, offsetof(struct pedit_headers, ip6.daddr.s6_addr32[1])},
+ {MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32, 4, offsetof(struct pedit_headers, ip6.daddr.s6_addr32[2])},
+ {MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0, 4, offsetof(struct pedit_headers, ip6.daddr.s6_addr32[3])},
+
+ {MLX5_ACTION_IN_FIELD_OUT_TCP_SPORT, 2, offsetof(struct pedit_headers, tcp.source)},
+ {MLX5_ACTION_IN_FIELD_OUT_TCP_DPORT, 2, offsetof(struct pedit_headers, tcp.dest)},
+ {MLX5_ACTION_IN_FIELD_OUT_TCP_FLAGS, 1, offsetof(struct pedit_headers, tcp.ack_seq) + 5},
+
+ {MLX5_ACTION_IN_FIELD_OUT_UDP_SPORT, 2, offsetof(struct pedit_headers, udp.source)},
+ {MLX5_ACTION_IN_FIELD_OUT_UDP_DPORT, 2, offsetof(struct pedit_headers, udp.dest)},
+};
+
+/* On input attr->num_mod_hdr_actions tells how many HW actions can be parsed at
+ * max from the SW pedit action. On success, it says how many HW actions were
+ * actually parsed.
+ */
+static int offload_pedit_fields(struct pedit_headers *masks,
+ struct pedit_headers *vals,
+ struct mlx5e_tc_flow_parse_attr *parse_attr)
+{
+ struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals;
+ int i, action_size, nactions, max_actions, first, last;
+ void *s_masks_p, *a_masks_p, *vals_p;
+ u32 s_mask, a_mask, val;
+ struct mlx5_fields *f;
+ u8 cmd, field_bsize;
+ unsigned long mask;
+ void *action;
+
+ set_masks = &masks[TCA_PEDIT_KEY_EX_CMD_SET];
+ add_masks = &masks[TCA_PEDIT_KEY_EX_CMD_ADD];
+ set_vals = &vals[TCA_PEDIT_KEY_EX_CMD_SET];
+ add_vals = &vals[TCA_PEDIT_KEY_EX_CMD_ADD];
+
+ action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto);
+ action = parse_attr->mod_hdr_actions;
+ max_actions = parse_attr->num_mod_hdr_actions;
+ nactions = 0;
+
+ for (i = 0; i < ARRAY_SIZE(fields); i++) {
+ f = &fields[i];
+ /* avoid seeing bits set from previous iterations */
+ s_mask = a_mask = mask = val = 0;
+
+ s_masks_p = (void *)set_masks + f->offset;
+ a_masks_p = (void *)add_masks + f->offset;
+
+ memcpy(&s_mask, s_masks_p, f->size);
+ memcpy(&a_mask, a_masks_p, f->size);
+
+ if (!s_mask && !a_mask) /* nothing to offload here */
+ continue;
+
+ if (s_mask && a_mask) {
+ printk(KERN_WARNING "mlx5: can't set and add to the same HW field (%x)\n", f->field);
+ return -EOPNOTSUPP;
+ }
+
+ if (nactions == max_actions) {
+ printk(KERN_WARNING "mlx5: parsed %d pedit actions, can't do more\n", nactions);
+ return -EOPNOTSUPP;
+ }
+
+ if (s_mask) {
+ cmd = MLX5_ACTION_TYPE_SET;
+ mask = s_mask;
+ vals_p = (void *)set_vals + f->offset;
+ /* clear to denote we consumed this field */
+ memset(s_masks_p, 0, f->size);
+ } else {
+ cmd = MLX5_ACTION_TYPE_ADD;
+ mask = a_mask;
+ vals_p = (void *)add_vals + f->offset;
+ /* clear to denote we consumed this field */
+ memset(a_masks_p, 0, f->size);
+ }
+
+ memcpy(&val, vals_p, f->size);
+
+ field_bsize = f->size * BITS_PER_BYTE;
+ first = find_first_bit(&mask, field_bsize);
+ last = find_last_bit(&mask, field_bsize);
+ if (first > 0 || last != (field_bsize - 1)) {
+ printk(KERN_WARNING "mlx5: partial rewrite (mask %lx) is currently not offloaded\n",
+ mask);
+ return -EOPNOTSUPP;
+ }
+
+ MLX5_SET(set_action_in, action, action_type, cmd);
+ MLX5_SET(set_action_in, action, field, f->field);
+
+ if (cmd == MLX5_ACTION_TYPE_SET) {
+ MLX5_SET(set_action_in, action, offset, 0);
+ /* length is num of bits to be written, zero means length of 32 */
+ MLX5_SET(set_action_in, action, length, field_bsize);
+ }
+
+ if (field_bsize == 32)
+ MLX5_SET(set_action_in, action, data, ntohl(val));
+ else if (field_bsize == 16)
+ MLX5_SET(set_action_in, action, data, ntohs(val));
+ else if (field_bsize == 8)
+ MLX5_SET(set_action_in, action, data, val);
+
+ action += action_size;
+ nactions++;
+ }
+
+ parse_attr->num_mod_hdr_actions = nactions;
+ return 0;
+}
+
+static int alloc_mod_hdr_actions(struct mlx5e_priv *priv,
+ const struct tc_action *a, int namespace,
+ struct mlx5e_tc_flow_parse_attr *parse_attr)
+{
+ int nkeys, action_size, max_actions;
+
+ nkeys = tcf_pedit_nkeys(a);
+ action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto);
+
+ if (namespace == MLX5_FLOW_NAMESPACE_FDB) /* FDB offloading */
+ max_actions = MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev, max_modify_header_actions);
+ else /* namespace is MLX5_FLOW_NAMESPACE_KERNEL - NIC offloading */
+ max_actions = MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, max_modify_header_actions);
+
+ /* can get up to crazingly 16 HW actions in 32 bits pedit SW key */
+ max_actions = min(max_actions, nkeys * 16);
+
+ parse_attr->mod_hdr_actions = kcalloc(max_actions, action_size, GFP_KERNEL);
+ if (!parse_attr->mod_hdr_actions)
+ return -ENOMEM;
+
+ parse_attr->num_mod_hdr_actions = max_actions;
+ return 0;
+}
+
+static const struct pedit_headers zero_masks = {};
+
+static int parse_tc_pedit_action(struct mlx5e_priv *priv,
+ const struct tc_action *a, int namespace,
+ struct mlx5e_tc_flow_parse_attr *parse_attr)
+{
+ struct pedit_headers masks[__PEDIT_CMD_MAX], vals[__PEDIT_CMD_MAX], *cmd_masks;
+ int nkeys, i, err = -EOPNOTSUPP;
+ u32 mask, val, offset;
+ u8 cmd, htype;
+
+ nkeys = tcf_pedit_nkeys(a);
+
+ memset(masks, 0, sizeof(struct pedit_headers) * __PEDIT_CMD_MAX);
+ memset(vals, 0, sizeof(struct pedit_headers) * __PEDIT_CMD_MAX);
+
+ for (i = 0; i < nkeys; i++) {
+ htype = tcf_pedit_htype(a, i);
+ cmd = tcf_pedit_cmd(a, i);
+ err = -EOPNOTSUPP; /* can't be all optimistic */
+
+ if (htype == TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK) {
+ printk(KERN_WARNING "mlx5: legacy pedit isn't offloaded\n");
+ goto out_err;
+ }
+
+ if (cmd != TCA_PEDIT_KEY_EX_CMD_SET && cmd != TCA_PEDIT_KEY_EX_CMD_ADD) {
+ printk(KERN_WARNING "mlx5: pedit cmd %d isn't offloaded\n", cmd);
+ goto out_err;
+ }
+
+ mask = tcf_pedit_mask(a, i);
+ val = tcf_pedit_val(a, i);
+ offset = tcf_pedit_offset(a, i);
+
+ err = set_pedit_val(htype, ~mask, val, offset, &masks[cmd], &vals[cmd]);
+ if (err)
+ goto out_err;
+ }
+
+ err = alloc_mod_hdr_actions(priv, a, namespace, parse_attr);
+ if (err)
+ goto out_err;
+
+ err = offload_pedit_fields(masks, vals, parse_attr);
+ if (err < 0)
+ goto out_dealloc_parsed_actions;
+
+ for (cmd = 0; cmd < __PEDIT_CMD_MAX; cmd++) {
+ cmd_masks = &masks[cmd];
+ if (memcmp(cmd_masks, &zero_masks, sizeof(zero_masks))) {
+ printk(KERN_WARNING "mlx5: attempt to offload an unsupported field (cmd %d)\n",
+ cmd);
+ print_hex_dump(KERN_WARNING, "mask: ", DUMP_PREFIX_ADDRESS,
+ 16, 1, cmd_masks, sizeof(zero_masks), true);
+ err = -EOPNOTSUPP;
+ goto out_dealloc_parsed_actions;
+ }
+ }
+
+ return 0;
+
+out_dealloc_parsed_actions:
+ kfree(parse_attr->mod_hdr_actions);
+out_err:
+ return err;
+}
+
+static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
+ struct mlx5e_tc_flow_parse_attr *parse_attr,
+ struct mlx5e_tc_flow *flow)
+{
+ struct mlx5_nic_flow_attr *attr = flow->nic_attr;
const struct tc_action *a;
LIST_HEAD(actions);
+ int err;
if (tc_no_actions(exts))
return -EINVAL;
- *flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
- *action = 0;
+ attr->flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
+ attr->action = 0;
tcf_exts_to_list(exts, &actions);
list_for_each_entry(a, &actions, list) {
/* Only support a single action per rule */
- if (*action)
+ if (attr->action)
return -EINVAL;
if (is_tcf_gact_shot(a)) {
- *action |= MLX5_FLOW_CONTEXT_ACTION_DROP;
+ attr->action |= MLX5_FLOW_CONTEXT_ACTION_DROP;
if (MLX5_CAP_FLOWTABLE(priv->mdev,
flow_table_properties_nic_receive.flow_counter))
- *action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
+ attr->action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
+ continue;
+ }
+
+ if (is_tcf_pedit(a)) {
+ err = parse_tc_pedit_action(priv, a, MLX5_FLOW_NAMESPACE_KERNEL,
+ parse_attr);
+ if (err)
+ return err;
+
+ attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR |
+ MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
continue;
}
@@ -657,8 +1040,8 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
return -EINVAL;
}
- *flow_tag = mark;
- *action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+ attr->flow_tag = mark;
+ attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
continue;
}
@@ -970,6 +1353,8 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
struct mlx5_esw_flow_attr *attr)
{
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+ struct net_device *up_dev = mlx5_eswitch_get_uplink_netdev(esw);
+ struct mlx5e_priv *up_priv = netdev_priv(up_dev);
unsigned short family = ip_tunnel_info_af(tun_info);
struct ip_tunnel_key *key = &tun_info->key;
struct mlx5_encap_entry *e;
@@ -990,7 +1375,7 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
return -EOPNOTSUPP;
}
- if (mlx5e_vxlan_lookup_port(priv, be16_to_cpu(key->tp_dst)) &&
+ if (mlx5e_vxlan_lookup_port(up_priv, be16_to_cpu(key->tp_dst)) &&
MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) {
tunnel_type = MLX5_HEADER_TYPE_VXLAN;
} else {
@@ -1041,9 +1426,10 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
}
static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
+ struct mlx5e_tc_flow_parse_attr *parse_attr,
struct mlx5e_tc_flow *flow)
{
- struct mlx5_esw_flow_attr *attr = flow->attr;
+ struct mlx5_esw_flow_attr *attr = flow->esw_attr;
struct ip_tunnel_info *info = NULL;
const struct tc_action *a;
LIST_HEAD(actions);
@@ -1064,6 +1450,16 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
continue;
}
+ if (is_tcf_pedit(a)) {
+ err = parse_tc_pedit_action(priv, a, MLX5_FLOW_NAMESPACE_FDB,
+ parse_attr);
+ if (err)
+ return err;
+
+ attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+ continue;
+ }
+
if (is_tcf_mirred_egress_redirect(a)) {
int ifindex = tcf_mirred_ifindex(a);
struct net_device *out_dev;
@@ -1106,14 +1502,16 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
}
if (is_tcf_vlan(a)) {
- if (tcf_vlan_action(a) == VLAN_F_POP) {
+ if (tcf_vlan_action(a) == TCA_VLAN_ACT_POP) {
attr->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
- } else if (tcf_vlan_action(a) == VLAN_F_PUSH) {
+ } else if (tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) {
if (tcf_vlan_push_proto(a) != htons(ETH_P_8021Q))
return -EOPNOTSUPP;
attr->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
attr->vlan = tcf_vlan_push_vid(a);
+ } else { /* action is TCA_VLAN_ACT_MODIFY */
+ return -EOPNOTSUPP;
}
continue;
}
@@ -1131,52 +1529,50 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
struct tc_cls_flower_offload *f)
{
- struct mlx5e_tc_table *tc = &priv->fs.tc;
- int err = 0;
- bool fdb_flow = false;
- u32 flow_tag, action;
- struct mlx5e_tc_flow *flow;
- struct mlx5_flow_spec *spec;
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+ struct mlx5e_tc_flow_parse_attr *parse_attr;
+ struct mlx5e_tc_table *tc = &priv->fs.tc;
+ struct mlx5e_tc_flow *flow;
+ int attr_size, err = 0;
+ u8 flow_flags = 0;
- if (esw && esw->mode == SRIOV_OFFLOADS)
- fdb_flow = true;
+ if (esw && esw->mode == SRIOV_OFFLOADS) {
+ flow_flags = MLX5E_TC_FLOW_ESWITCH;
+ attr_size = sizeof(struct mlx5_esw_flow_attr);
+ } else {
+ flow_flags = MLX5E_TC_FLOW_NIC;
+ attr_size = sizeof(struct mlx5_nic_flow_attr);
+ }
- if (fdb_flow)
- flow = kzalloc(sizeof(*flow) +
- sizeof(struct mlx5_esw_flow_attr),
- GFP_KERNEL);
- else
- flow = kzalloc(sizeof(*flow), GFP_KERNEL);
-
- spec = mlx5_vzalloc(sizeof(*spec));
- if (!spec || !flow) {
+ flow = kzalloc(sizeof(*flow) + attr_size, GFP_KERNEL);
+ parse_attr = mlx5_vzalloc(sizeof(*parse_attr));
+ if (!parse_attr || !flow) {
err = -ENOMEM;
goto err_free;
}
flow->cookie = f->cookie;
+ flow->flags = flow_flags;
- err = parse_cls_flower(priv, spec, f);
+ err = parse_cls_flower(priv, flow, &parse_attr->spec, f);
if (err < 0)
goto err_free;
- if (fdb_flow) {
- flow->attr = (struct mlx5_esw_flow_attr *)(flow + 1);
- err = parse_tc_fdb_actions(priv, f->exts, flow);
+ if (flow->flags & MLX5E_TC_FLOW_ESWITCH) {
+ err = parse_tc_fdb_actions(priv, f->exts, parse_attr, flow);
if (err < 0)
goto err_free;
- flow->rule = mlx5e_tc_add_fdb_flow(priv, spec, flow->attr);
+ flow->rule = mlx5e_tc_add_fdb_flow(priv, parse_attr, flow);
} else {
- err = parse_tc_nic_actions(priv, f->exts, &action, &flow_tag);
+ err = parse_tc_nic_actions(priv, f->exts, parse_attr, flow);
if (err < 0)
goto err_free;
- flow->rule = mlx5e_tc_add_nic_flow(priv, spec, action, flow_tag);
+ flow->rule = mlx5e_tc_add_nic_flow(priv, parse_attr, flow);
}
if (IS_ERR(flow->rule)) {
err = PTR_ERR(flow->rule);
- goto err_del_rule;
+ goto err_free;
}
err = rhashtable_insert_fast(&tc->ht, &flow->node,
@@ -1192,7 +1588,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
err_free:
kfree(flow);
out:
- kvfree(spec);
+ kvfree(parse_attr);
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index f193128..5bbc313 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -38,29 +38,6 @@
#define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\
MLX5E_SQ_NOPS_ROOM)
-void mlx5e_send_nop(struct mlx5e_sq *sq, bool notify_hw)
-{
- struct mlx5_wq_cyc *wq = &sq->wq;
-
- u16 pi = sq->pc & wq->sz_m1;
- struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi);
-
- struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
-
- memset(cseg, 0, sizeof(*cseg));
-
- cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_NOP);
- cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | 0x01);
-
- sq->pc++;
- sq->stats.nop++;
-
- if (notify_hw) {
- cseg->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE;
- mlx5e_tx_notify_hw(sq, &wqe->ctrl, 0);
- }
-}
-
static inline void mlx5e_tx_dma_unmap(struct device *pdev,
struct mlx5e_sq_dma *dma)
{
@@ -76,25 +53,25 @@ static inline void mlx5e_tx_dma_unmap(struct device *pdev,
}
}
-static inline void mlx5e_dma_push(struct mlx5e_sq *sq,
+static inline void mlx5e_dma_push(struct mlx5e_txqsq *sq,
dma_addr_t addr,
u32 size,
enum mlx5e_dma_map_type map_type)
{
u32 i = sq->dma_fifo_pc & sq->dma_fifo_mask;
- sq->db.txq.dma_fifo[i].addr = addr;
- sq->db.txq.dma_fifo[i].size = size;
- sq->db.txq.dma_fifo[i].type = map_type;
+ sq->db.dma_fifo[i].addr = addr;
+ sq->db.dma_fifo[i].size = size;
+ sq->db.dma_fifo[i].type = map_type;
sq->dma_fifo_pc++;
}
-static inline struct mlx5e_sq_dma *mlx5e_dma_get(struct mlx5e_sq *sq, u32 i)
+static inline struct mlx5e_sq_dma *mlx5e_dma_get(struct mlx5e_txqsq *sq, u32 i)
{
- return &sq->db.txq.dma_fifo[i & sq->dma_fifo_mask];
+ return &sq->db.dma_fifo[i & sq->dma_fifo_mask];
}
-static void mlx5e_dma_unmap_wqe_err(struct mlx5e_sq *sq, u8 num_dma)
+static void mlx5e_dma_unmap_wqe_err(struct mlx5e_txqsq *sq, u8 num_dma)
{
int i;
@@ -111,6 +88,7 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
{
struct mlx5e_priv *priv = netdev_priv(dev);
int channel_ix = fallback(dev, skb);
+ u16 num_channels;
int up = 0;
if (!netdev_get_num_tc(dev))
@@ -122,11 +100,11 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
/* channel_ix can be larger than num_channels since
* dev->num_real_tx_queues = num_channels * num_tc
*/
- if (channel_ix >= priv->params.num_channels)
- channel_ix = reciprocal_scale(channel_ix,
- priv->params.num_channels);
+ num_channels = priv->channels.params.num_channels;
+ if (channel_ix >= num_channels)
+ channel_ix = reciprocal_scale(channel_ix, num_channels);
- return priv->channeltc_to_txq_map[channel_ix][up];
+ return priv->channel_tc2txq[channel_ix][up];
}
static inline int mlx5e_skb_l2_header_offset(struct sk_buff *skb)
@@ -175,25 +153,6 @@ static inline unsigned int mlx5e_calc_min_inline(enum mlx5_inline_modes mode,
}
}
-static inline u16 mlx5e_get_inline_hdr_size(struct mlx5e_sq *sq,
- struct sk_buff *skb, bool bf)
-{
- /* Some NIC TX decisions, e.g loopback, are based on the packet
- * headers and occur before the data gather.
- * Therefore these headers must be copied into the WQE
- */
- if (bf) {
- u16 ihs = skb_headlen(skb);
-
- if (skb_vlan_tag_present(skb))
- ihs += VLAN_HLEN;
-
- if (ihs <= sq->max_inline)
- return skb_headlen(skb);
- }
- return mlx5e_calc_min_inline(sq->min_inline_mode, skb);
-}
-
static inline void mlx5e_tx_skb_pull_inline(unsigned char **skb_data,
unsigned int *skb_len,
unsigned int len)
@@ -218,13 +177,13 @@ static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs,
mlx5e_tx_skb_pull_inline(skb_data, skb_len, cpy2_sz);
}
-static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
+static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb)
{
struct mlx5_wq_cyc *wq = &sq->wq;
u16 pi = sq->pc & wq->sz_m1;
struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi);
- struct mlx5e_tx_wqe_info *wi = &sq->db.txq.wqe_info[pi];
+ struct mlx5e_tx_wqe_info *wi = &sq->db.wqe_info[pi];
struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
struct mlx5_wqe_eth_seg *eseg = &wqe->eth;
@@ -235,7 +194,6 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
u8 opcode = MLX5_OPCODE_SEND;
dma_addr_t dma_addr = 0;
unsigned int num_bytes;
- bool bf = false;
u16 headlen;
u16 ds_cnt;
u16 ihs;
@@ -255,11 +213,6 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
} else
sq->stats.csum_none++;
- if (sq->cc != sq->prev_cc) {
- sq->prev_cc = sq->cc;
- sq->bf_budget = (sq->cc == sq->pc) ? MLX5E_SQ_BF_BUDGET : 0;
- }
-
if (skb_is_gso(skb)) {
eseg->mss = cpu_to_be16(skb_shinfo(skb)->gso_size);
opcode = MLX5_OPCODE_LSO;
@@ -274,15 +227,15 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
sq->stats.tso_bytes += skb->len - ihs;
}
+ sq->stats.packets += skb_shinfo(skb)->gso_segs;
num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs;
} else {
- bf = sq->bf_budget &&
- !skb->xmit_more &&
- !skb_shinfo(skb)->nr_frags;
- ihs = mlx5e_get_inline_hdr_size(sq, skb, bf);
+ ihs = mlx5e_calc_min_inline(sq->min_inline_mode, skb);
+ sq->stats.packets++;
num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
}
+ sq->stats.bytes += num_bytes;
wi->num_bytes = num_bytes;
ds_cnt = sizeof(*wqe) / MLX5_SEND_WQE_DS;
@@ -346,7 +299,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | opcode);
cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
- sq->db.txq.skb[pi] = skb;
+ sq->db.skb[pi] = skb;
wi->num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS);
sq->pc += wi->num_wqebbs;
@@ -356,33 +309,23 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
- if (unlikely(!mlx5e_sq_has_room_for(sq, MLX5E_SQ_STOP_ROOM))) {
+ if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc,
+ MLX5E_SQ_STOP_ROOM))) {
netif_tx_stop_queue(sq->txq);
sq->stats.stopped++;
}
sq->stats.xmit_more += skb->xmit_more;
- if (!skb->xmit_more || netif_xmit_stopped(sq->txq)) {
- int bf_sz = 0;
-
- if (bf && test_bit(MLX5E_SQ_STATE_BF_ENABLE, &sq->state))
- bf_sz = wi->num_wqebbs << 3;
-
- cseg->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE;
- mlx5e_tx_notify_hw(sq, &wqe->ctrl, bf_sz);
- }
+ if (!skb->xmit_more || netif_xmit_stopped(sq->txq))
+ mlx5e_notify_hw(wq, sq->pc, sq->uar_map, cseg);
/* fill sq edge with nops to avoid wqe wrap around */
while ((pi = (sq->pc & wq->sz_m1)) > sq->edge) {
- sq->db.txq.skb[pi] = NULL;
- mlx5e_send_nop(sq, false);
+ sq->db.skb[pi] = NULL;
+ mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc);
+ sq->stats.nop++;
}
- if (bf)
- sq->bf_budget--;
-
- sq->stats.packets++;
- sq->stats.bytes += num_bytes;
return NETDEV_TX_OK;
dma_unmap_wqe_err:
@@ -397,21 +340,21 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct mlx5e_priv *priv = netdev_priv(dev);
- struct mlx5e_sq *sq = priv->txq_to_sq_map[skb_get_queue_mapping(skb)];
+ struct mlx5e_txqsq *sq = priv->txq2sq[skb_get_queue_mapping(skb)];
return mlx5e_sq_xmit(sq, skb);
}
bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
{
- struct mlx5e_sq *sq;
+ struct mlx5e_txqsq *sq;
u32 dma_fifo_cc;
u32 nbytes;
u16 npkts;
u16 sqcc;
int i;
- sq = container_of(cq, struct mlx5e_sq, cq);
+ sq = container_of(cq, struct mlx5e_txqsq, cq);
if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
return false;
@@ -449,8 +392,8 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
last_wqe = (sqcc == wqe_counter);
ci = sqcc & sq->wq.sz_m1;
- skb = sq->db.txq.skb[ci];
- wi = &sq->db.txq.wqe_info[ci];
+ skb = sq->db.skb[ci];
+ wi = &sq->db.wqe_info[ci];
if (unlikely(!skb)) { /* nop */
sqcc++;
@@ -491,7 +434,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
netdev_tx_completed_queue(sq->txq, npkts, nbytes);
if (netif_tx_queue_stopped(sq->txq) &&
- mlx5e_sq_has_room_for(sq, MLX5E_SQ_STOP_ROOM)) {
+ mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, MLX5E_SQ_STOP_ROOM)) {
netif_tx_wake_queue(sq->txq);
sq->stats.wake++;
}
@@ -499,7 +442,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
return (i == MLX5E_TX_CQ_POLL_BUDGET);
}
-static void mlx5e_free_txq_sq_descs(struct mlx5e_sq *sq)
+void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq)
{
struct mlx5e_tx_wqe_info *wi;
struct sk_buff *skb;
@@ -508,8 +451,8 @@ static void mlx5e_free_txq_sq_descs(struct mlx5e_sq *sq)
while (sq->cc != sq->pc) {
ci = sq->cc & sq->wq.sz_m1;
- skb = sq->db.txq.skb[ci];
- wi = &sq->db.txq.wqe_info[ci];
+ skb = sq->db.skb[ci];
+ wi = &sq->db.wqe_info[ci];
if (!skb) { /* nop */
sq->cc++;
@@ -527,37 +470,3 @@ static void mlx5e_free_txq_sq_descs(struct mlx5e_sq *sq)
sq->cc += wi->num_wqebbs;
}
}
-
-static void mlx5e_free_xdp_sq_descs(struct mlx5e_sq *sq)
-{
- struct mlx5e_sq_wqe_info *wi;
- struct mlx5e_dma_info *di;
- u16 ci;
-
- while (sq->cc != sq->pc) {
- ci = sq->cc & sq->wq.sz_m1;
- di = &sq->db.xdp.di[ci];
- wi = &sq->db.xdp.wqe_info[ci];
-
- if (wi->opcode == MLX5_OPCODE_NOP) {
- sq->cc++;
- continue;
- }
-
- sq->cc += wi->num_wqebbs;
-
- mlx5e_page_release(&sq->channel->rq, di, false);
- }
-}
-
-void mlx5e_free_sq_descs(struct mlx5e_sq *sq)
-{
- switch (sq->type) {
- case MLX5E_SQ_TXQ:
- mlx5e_free_txq_sq_descs(sq);
- break;
- case MLX5E_SQ_XDP:
- mlx5e_free_xdp_sq_descs(sq);
- break;
- }
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index e5c12a7..43729ec 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -44,14 +44,14 @@ struct mlx5_cqe64 *mlx5e_get_cqe(struct mlx5e_cq *cq)
return NULL;
/* ensure cqe content is read after cqe ownership bit */
- rmb();
+ dma_rmb();
return cqe;
}
static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
{
- struct mlx5e_sq *sq = container_of(cq, struct mlx5e_sq, cq);
+ struct mlx5e_icosq *sq = container_of(cq, struct mlx5e_icosq, cq);
struct mlx5_wq_cyc *wq;
struct mlx5_cqe64 *cqe;
u16 sqcc;
@@ -105,66 +105,6 @@ static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
sq->cc = sqcc;
}
-static inline bool mlx5e_poll_xdp_tx_cq(struct mlx5e_cq *cq)
-{
- struct mlx5e_sq *sq;
- u16 sqcc;
- int i;
-
- sq = container_of(cq, struct mlx5e_sq, cq);
-
- if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
- return false;
-
- /* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
- * otherwise a cq overrun may occur
- */
- sqcc = sq->cc;
-
- for (i = 0; i < MLX5E_TX_CQ_POLL_BUDGET; i++) {
- struct mlx5_cqe64 *cqe;
- u16 wqe_counter;
- bool last_wqe;
-
- cqe = mlx5e_get_cqe(cq);
- if (!cqe)
- break;
-
- mlx5_cqwq_pop(&cq->wq);
-
- wqe_counter = be16_to_cpu(cqe->wqe_counter);
-
- do {
- struct mlx5e_sq_wqe_info *wi;
- struct mlx5e_dma_info *di;
- u16 ci;
-
- last_wqe = (sqcc == wqe_counter);
-
- ci = sqcc & sq->wq.sz_m1;
- di = &sq->db.xdp.di[ci];
- wi = &sq->db.xdp.wqe_info[ci];
-
- if (unlikely(wi->opcode == MLX5_OPCODE_NOP)) {
- sqcc++;
- continue;
- }
-
- sqcc += wi->num_wqebbs;
- /* Recycle RX page */
- mlx5e_page_release(&sq->channel->rq, di, true);
- } while (!last_wqe);
- }
-
- mlx5_cqwq_update_db_record(&cq->wq);
-
- /* ensure cq space is freed before enabling more cqes */
- wmb();
-
- sq->cc = sqcc;
- return (i == MLX5E_TX_CQ_POLL_BUDGET);
-}
-
int mlx5e_napi_poll(struct napi_struct *napi, int budget)
{
struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel,
@@ -178,12 +118,12 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
for (i = 0; i < c->num_tc; i++)
busy |= mlx5e_poll_tx_cq(&c->sq[i].cq, budget);
+ if (c->xdp)
+ busy |= mlx5e_poll_xdpsq_cq(&c->rq.xdpsq.cq);
+
work_done = mlx5e_poll_rx_cq(&c->rq.cq, budget);
busy |= work_done == budget;
- if (c->xdp)
- busy |= mlx5e_poll_xdp_tx_cq(&c->xdp_sq.cq);
-
mlx5e_poll_ico_cq(&c->icosq.cq);
busy |= mlx5e_post_rx_wqes(&c->rq);
@@ -224,8 +164,7 @@ void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event)
{
struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq);
struct mlx5e_channel *c = cq->channel;
- struct mlx5e_priv *priv = c->priv;
- struct net_device *netdev = priv->netdev;
+ struct net_device *netdev = c->netdev;
netdev_err(netdev, "%s: cqn=0x%.6x event=0x%.2x\n",
__func__, mcq->cqn, event);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 5b78883..1f56ed9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -209,6 +209,7 @@ struct mlx5_esw_offload {
struct mlx5_eswitch_rep *vport_reps;
DECLARE_HASHTABLE(encap_tbl, 8);
u8 inline_mode;
+ u64 num_flows;
};
struct mlx5_eswitch {
@@ -271,6 +272,11 @@ struct mlx5_flow_handle *
mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
struct mlx5_flow_spec *spec,
struct mlx5_esw_flow_attr *attr);
+void
+mlx5_eswitch_del_offloaded_rule(struct mlx5_eswitch *esw,
+ struct mlx5_flow_handle *rule,
+ struct mlx5_esw_flow_attr *attr);
+
struct mlx5_flow_handle *
mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport, u32 tirn);
@@ -279,8 +285,8 @@ enum {
SET_VLAN_INSERT = BIT(1)
};
-#define MLX5_FLOW_CONTEXT_ACTION_VLAN_POP 0x40
-#define MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH 0x80
+#define MLX5_FLOW_CONTEXT_ACTION_VLAN_POP 0x4000
+#define MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH 0x8000
struct mlx5_encap_entry {
struct hlist_node encap_hlist;
@@ -302,6 +308,7 @@ struct mlx5_esw_flow_attr {
u16 vlan;
bool vlan_handled;
struct mlx5_encap_entry *encap;
+ u32 mod_hdr_id;
};
int mlx5_eswitch_sqs2vport_start(struct mlx5_eswitch *esw,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 4f5b0d4..fff962d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -68,8 +68,10 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
}
if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
counter = mlx5_fc_create(esw->dev, true);
- if (IS_ERR(counter))
- return ERR_CAST(counter);
+ if (IS_ERR(counter)) {
+ rule = ERR_CAST(counter);
+ goto err_counter_alloc;
+ }
dest[i].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
dest[i].counter = counter;
i++;
@@ -86,15 +88,38 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP)
spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS;
- if (attr->encap)
+ if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+ flow_act.modify_id = attr->mod_hdr_id;
+
+ if (attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP)
flow_act.encap_id = attr->encap->encap_id;
rule = mlx5_add_flow_rules((struct mlx5_flow_table *)esw->fdb_table.fdb,
spec, &flow_act, dest, i);
if (IS_ERR(rule))
- mlx5_fc_destroy(esw->dev, counter);
+ goto err_add_rule;
+ else
+ esw->offloads.num_flows++;
return rule;
+
+err_add_rule:
+ mlx5_fc_destroy(esw->dev, counter);
+err_counter_alloc:
+ return rule;
+}
+
+void
+mlx5_eswitch_del_offloaded_rule(struct mlx5_eswitch *esw,
+ struct mlx5_flow_handle *rule,
+ struct mlx5_esw_flow_attr *attr)
+{
+ struct mlx5_fc *counter = NULL;
+
+ counter = mlx5_flow_rule_counter(rule);
+ mlx5_del_flow_rules(rule);
+ mlx5_fc_destroy(esw->dev, counter);
+ esw->offloads.num_flows--;
}
static int esw_set_global_vlan_pop(struct mlx5_eswitch *esw, u8 val)
@@ -908,6 +933,11 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode)
MLX5_CAP_INLINE_MODE_VPORT_CONTEXT)
return -EOPNOTSUPP;
+ if (esw->offloads.num_flows > 0) {
+ esw_warn(dev, "Can't set inline mode when flows are configured\n");
+ return -EOPNOTSUPP;
+ }
+
err = esw_inline_mode_from_devlink(mode, &mlx5_mode);
if (err)
goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index b64a781..c6178ea1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -249,6 +249,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
MLX5_SET(flow_context, in_flow_context, flow_tag, fte->flow_tag);
MLX5_SET(flow_context, in_flow_context, action, fte->action);
MLX5_SET(flow_context, in_flow_context, encap_id, fte->encap_id);
+ MLX5_SET(flow_context, in_flow_context, modify_header_id, fte->modify_id);
in_match_value = MLX5_ADDR_OF(flow_context, in_flow_context,
match_value);
memcpy(in_match_value, &fte->val, MLX5_ST_SZ_BYTES(fte_match_param));
@@ -515,3 +516,69 @@ void mlx5_encap_dealloc(struct mlx5_core_dev *dev, u32 encap_id)
mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
}
+
+int mlx5_modify_header_alloc(struct mlx5_core_dev *dev,
+ u8 namespace, u8 num_actions,
+ void *modify_actions, u32 *modify_header_id)
+{
+ u32 out[MLX5_ST_SZ_DW(alloc_modify_header_context_out)];
+ int max_actions, actions_size, inlen, err;
+ void *actions_in;
+ u8 table_type;
+ u32 *in;
+
+ switch (namespace) {
+ case MLX5_FLOW_NAMESPACE_FDB:
+ max_actions = MLX5_CAP_ESW_FLOWTABLE_FDB(dev, max_modify_header_actions);
+ table_type = FS_FT_FDB;
+ break;
+ case MLX5_FLOW_NAMESPACE_KERNEL:
+ max_actions = MLX5_CAP_FLOWTABLE_NIC_RX(dev, max_modify_header_actions);
+ table_type = FS_FT_NIC_RX;
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ if (num_actions > max_actions) {
+ mlx5_core_warn(dev, "too many modify header actions %d, max supported %d\n",
+ num_actions, max_actions);
+ return -EOPNOTSUPP;
+ }
+
+ actions_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto) * num_actions;
+ inlen = MLX5_ST_SZ_BYTES(alloc_modify_header_context_in) + actions_size;
+
+ in = kzalloc(inlen, GFP_KERNEL);
+ if (!in)
+ return -ENOMEM;
+
+ MLX5_SET(alloc_modify_header_context_in, in, opcode,
+ MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT);
+ MLX5_SET(alloc_modify_header_context_in, in, table_type, table_type);
+ MLX5_SET(alloc_modify_header_context_in, in, num_of_actions, num_actions);
+
+ actions_in = MLX5_ADDR_OF(alloc_modify_header_context_in, in, actions);
+ memcpy(actions_in, modify_actions, actions_size);
+
+ memset(out, 0, sizeof(out));
+ err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+
+ *modify_header_id = MLX5_GET(alloc_modify_header_context_out, out, modify_header_id);
+ kfree(in);
+ return err;
+}
+
+void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, u32 modify_header_id)
+{
+ u32 in[MLX5_ST_SZ_DW(dealloc_modify_header_context_in)];
+ u32 out[MLX5_ST_SZ_DW(dealloc_modify_header_context_out)];
+
+ memset(in, 0, sizeof(in));
+ MLX5_SET(dealloc_modify_header_context_in, in, opcode,
+ MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT);
+ MLX5_SET(dealloc_modify_header_context_in, in, modify_header_id,
+ modify_header_id);
+
+ mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 2478516..27ff815 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -476,6 +476,7 @@ static struct fs_fte *alloc_fte(struct mlx5_flow_act *flow_act,
fte->index = index;
fte->action = flow_act->action;
fte->encap_id = flow_act->encap_id;
+ fte->modify_id = flow_act->modify_id;
return fte;
}
@@ -1136,7 +1137,7 @@ static struct mlx5_flow_group *create_autogroup(struct mlx5_flow_table *ft,
u32 *match_criteria)
{
int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
- struct list_head *prev = ft->node.children.prev;
+ struct list_head *prev = &ft->node.children;
unsigned int candidate_index = 0;
struct mlx5_flow_group *fg;
void *match_criteria_addr;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 8e668c6..03af2e7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -152,6 +152,7 @@ struct fs_fte {
u32 index;
u32 action;
u32 encap_id;
+ u32 modify_id;
enum fs_fte_status status;
struct mlx5_fc *counter;
};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index 5595724..b5d5519 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -294,7 +294,7 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev,
struct netdev_notifier_changeupper_info *info)
{
struct net_device *upper = info->upper_dev, *ndev_tmp;
- struct netdev_lag_upper_info *lag_upper_info;
+ struct netdev_lag_upper_info *lag_upper_info = NULL;
bool is_bonded;
int bond_status = 0;
int num_slaves = 0;
@@ -303,7 +303,8 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev,
if (!netif_is_lag_master(upper))
return 0;
- lag_upper_info = info->upper_info;
+ if (info->linking)
+ lag_upper_info = info->upper_info;
/* The event may still be of interest if the slave does not belong to
* us, but is enslaved to a master which has one or more of our netdevs
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index c4242a4..9c2bec7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -87,7 +87,7 @@ static struct mlx5_profile profile[] = {
[2] = {
.mask = MLX5_PROF_MASK_QP_SIZE |
MLX5_PROF_MASK_MR_CACHE,
- .log_max_qp = 17,
+ .log_max_qp = 18,
.mr_cache[0] = {
.size = 500,
.limit = 250
@@ -1352,6 +1352,7 @@ static int init_one(struct pci_dev *pdev,
if (err)
goto clean_load;
+ pci_save_state(pdev);
return 0;
clean_load:
@@ -1407,9 +1408,8 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev,
mlx5_enter_error_state(dev);
mlx5_unload_one(dev, priv, false);
- /* In case of kernel call save the pci state and drain the health wq */
+ /* In case of kernel call drain the health wq */
if (state) {
- pci_save_state(pdev);
mlx5_drain_health_wq(dev);
mlx5_pci_disable_device(dev);
}
@@ -1461,6 +1461,7 @@ static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev)
pci_set_master(pdev);
pci_restore_state(pdev);
+ pci_save_state(pdev);
if (wait_vital(pdev)) {
dev_err(&pdev->dev, "%s: wait_vital timed out\n", __func__);
@@ -1513,8 +1514,10 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
{ PCI_VDEVICE(MELLANOX, 0x1016), MLX5_PCI_DEV_IS_VF}, /* ConnectX-4LX VF */
{ PCI_VDEVICE(MELLANOX, 0x1017) }, /* ConnectX-5, PCIe 3.0 */
{ PCI_VDEVICE(MELLANOX, 0x1018), MLX5_PCI_DEV_IS_VF}, /* ConnectX-5 VF */
- { PCI_VDEVICE(MELLANOX, 0x1019) }, /* ConnectX-5, PCIe 4.0 */
- { PCI_VDEVICE(MELLANOX, 0x101a), MLX5_PCI_DEV_IS_VF}, /* ConnectX-5, PCIe 4.0 VF */
+ { PCI_VDEVICE(MELLANOX, 0x1019) }, /* ConnectX-5 Ex */
+ { PCI_VDEVICE(MELLANOX, 0x101a), MLX5_PCI_DEV_IS_VF}, /* ConnectX-5 Ex VF */
+ { PCI_VDEVICE(MELLANOX, 0x101b) }, /* ConnectX-6 */
+ { PCI_VDEVICE(MELLANOX, 0x101c), MLX5_PCI_DEV_IS_VF}, /* ConnectX-6 VF */
{ 0, }
};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index b3dabe6..fbc6e9e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -141,6 +141,11 @@ int mlx5_encap_alloc(struct mlx5_core_dev *dev,
u32 *encap_id);
void mlx5_encap_dealloc(struct mlx5_core_dev *dev, u32 encap_id);
+int mlx5_modify_header_alloc(struct mlx5_core_dev *dev,
+ u8 namespace, u8 num_actions,
+ void *modify_actions, u32 *modify_header_id);
+void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, u32 modify_header_id);
+
bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv);
int mlx5_query_mtpps(struct mlx5_core_dev *dev, u32 *mtpps, u32 mtpps_size);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index 6b6c30d..2fb8c65 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -15,7 +15,8 @@
mlxsw_spectrum-objs := spectrum.o spectrum_buffers.o \
spectrum_switchdev.o spectrum_router.o \
spectrum_kvdl.o spectrum_acl_tcam.o \
- spectrum_acl.o spectrum_flower.o
+ spectrum_acl.o spectrum_flower.o \
+ spectrum_cnt.o spectrum_dpipe.o
mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB) += spectrum_dcb.o
obj-$(CONFIG_MLXSW_MINIMAL) += mlxsw_minimal.o
mlxsw_minimal-objs := minimal.o
diff --git a/drivers/net/ethernet/mellanox/mlxsw/cmd.h b/drivers/net/ethernet/mellanox/mlxsw/cmd.h
index a1b4842..479511c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/cmd.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/cmd.h
@@ -1043,13 +1043,6 @@ MLXSW_ITEM32(cmd_mbox, sw2hw_cq, cv, 0x00, 28, 4);
*/
MLXSW_ITEM32(cmd_mbox, sw2hw_cq, c_eqn, 0x00, 24, 1);
-/* cmd_mbox_sw2hw_cq_oi
- * When set, overrun ignore is enabled. When set, updates of
- * CQ consumer counter (poll for completion) or Request completion
- * notifications (Arm CQ) DoorBells should not be rung on that CQ.
- */
-MLXSW_ITEM32(cmd_mbox, sw2hw_cq, oi, 0x00, 12, 1);
-
/* cmd_mbox_sw2hw_cq_st
* Event delivery state machine
* 0x0 - FIRED
@@ -1132,11 +1125,6 @@ static inline int mlxsw_cmd_sw2hw_eq(struct mlxsw_core *mlxsw_core,
*/
MLXSW_ITEM32(cmd_mbox, sw2hw_eq, int_msix, 0x00, 24, 1);
-/* cmd_mbox_sw2hw_eq_oi
- * When set, overrun ignore is enabled.
- */
-MLXSW_ITEM32(cmd_mbox, sw2hw_eq, oi, 0x00, 12, 1);
-
/* cmd_mbox_sw2hw_eq_st
* Event delivery state machine
* 0x0 - FIRED
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index a4c0784..affe84e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -40,9 +40,6 @@
#include <linux/export.h>
#include <linux/err.h>
#include <linux/if_link.h>
-#include <linux/debugfs.h>
-#include <linux/seq_file.h>
-#include <linux/u64_stats_sync.h>
#include <linux/netdevice.h>
#include <linux/completion.h>
#include <linux/skbuff.h>
@@ -74,23 +71,9 @@ static DEFINE_SPINLOCK(mlxsw_core_driver_list_lock);
static const char mlxsw_core_driver_name[] = "mlxsw_core";
-static struct dentry *mlxsw_core_dbg_root;
-
static struct workqueue_struct *mlxsw_wq;
static struct workqueue_struct *mlxsw_owq;
-struct mlxsw_core_pcpu_stats {
- u64 trap_rx_packets[MLXSW_TRAP_ID_MAX];
- u64 trap_rx_bytes[MLXSW_TRAP_ID_MAX];
- u64 port_rx_packets[MLXSW_PORT_MAX_PORTS];
- u64 port_rx_bytes[MLXSW_PORT_MAX_PORTS];
- struct u64_stats_sync syncp;
- u32 trap_rx_dropped[MLXSW_TRAP_ID_MAX];
- u32 port_rx_dropped[MLXSW_PORT_MAX_PORTS];
- u32 trap_rx_invalid;
- u32 port_rx_invalid;
-};
-
struct mlxsw_core_port {
struct devlink_port devlink_port;
void *port_driver_priv;
@@ -121,23 +104,48 @@ struct mlxsw_core {
spinlock_t trans_list_lock; /* protects trans_list writes */
bool use_emad;
} emad;
- struct mlxsw_core_pcpu_stats __percpu *pcpu_stats;
- struct dentry *dbg_dir;
- struct {
- struct debugfs_blob_wrapper vsd_blob;
- struct debugfs_blob_wrapper psid_blob;
- } dbg;
struct {
u8 *mapping; /* lag_id+port_index to local_port mapping */
} lag;
struct mlxsw_res res;
struct mlxsw_hwmon *hwmon;
struct mlxsw_thermal *thermal;
- struct mlxsw_core_port ports[MLXSW_PORT_MAX_PORTS];
+ struct mlxsw_core_port *ports;
+ unsigned int max_ports;
unsigned long driver_priv[0];
/* driver_priv has to be always the last item */
};
+#define MLXSW_PORT_MAX_PORTS_DEFAULT 0x40
+
+static int mlxsw_ports_init(struct mlxsw_core *mlxsw_core)
+{
+ /* Switch ports are numbered from 1 to queried value */
+ if (MLXSW_CORE_RES_VALID(mlxsw_core, MAX_SYSTEM_PORT))
+ mlxsw_core->max_ports = MLXSW_CORE_RES_GET(mlxsw_core,
+ MAX_SYSTEM_PORT) + 1;
+ else
+ mlxsw_core->max_ports = MLXSW_PORT_MAX_PORTS_DEFAULT + 1;
+
+ mlxsw_core->ports = kcalloc(mlxsw_core->max_ports,
+ sizeof(struct mlxsw_core_port), GFP_KERNEL);
+ if (!mlxsw_core->ports)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void mlxsw_ports_fini(struct mlxsw_core *mlxsw_core)
+{
+ kfree(mlxsw_core->ports);
+}
+
+unsigned int mlxsw_core_max_ports(const struct mlxsw_core *mlxsw_core)
+{
+ return mlxsw_core->max_ports;
+}
+EXPORT_SYMBOL(mlxsw_core_max_ports);
+
void *mlxsw_core_driver_priv(struct mlxsw_core *mlxsw_core)
{
return mlxsw_core->driver_priv;
@@ -703,91 +711,6 @@ static int mlxsw_emad_reg_access(struct mlxsw_core *mlxsw_core,
* Core functions
*****************/
-static int mlxsw_core_rx_stats_dbg_read(struct seq_file *file, void *data)
-{
- struct mlxsw_core *mlxsw_core = file->private;
- struct mlxsw_core_pcpu_stats *p;
- u64 rx_packets, rx_bytes;
- u64 tmp_rx_packets, tmp_rx_bytes;
- u32 rx_dropped, rx_invalid;
- unsigned int start;
- int i;
- int j;
- static const char hdr[] =
- " NUM RX_PACKETS RX_BYTES RX_DROPPED\n";
-
- seq_printf(file, hdr);
- for (i = 0; i < MLXSW_TRAP_ID_MAX; i++) {
- rx_packets = 0;
- rx_bytes = 0;
- rx_dropped = 0;
- for_each_possible_cpu(j) {
- p = per_cpu_ptr(mlxsw_core->pcpu_stats, j);
- do {
- start = u64_stats_fetch_begin(&p->syncp);
- tmp_rx_packets = p->trap_rx_packets[i];
- tmp_rx_bytes = p->trap_rx_bytes[i];
- } while (u64_stats_fetch_retry(&p->syncp, start));
-
- rx_packets += tmp_rx_packets;
- rx_bytes += tmp_rx_bytes;
- rx_dropped += p->trap_rx_dropped[i];
- }
- seq_printf(file, "trap %3d %12llu %12llu %10u\n",
- i, rx_packets, rx_bytes, rx_dropped);
- }
- rx_invalid = 0;
- for_each_possible_cpu(j) {
- p = per_cpu_ptr(mlxsw_core->pcpu_stats, j);
- rx_invalid += p->trap_rx_invalid;
- }
- seq_printf(file, "trap INV %10u\n",
- rx_invalid);
-
- for (i = 0; i < MLXSW_PORT_MAX_PORTS; i++) {
- rx_packets = 0;
- rx_bytes = 0;
- rx_dropped = 0;
- for_each_possible_cpu(j) {
- p = per_cpu_ptr(mlxsw_core->pcpu_stats, j);
- do {
- start = u64_stats_fetch_begin(&p->syncp);
- tmp_rx_packets = p->port_rx_packets[i];
- tmp_rx_bytes = p->port_rx_bytes[i];
- } while (u64_stats_fetch_retry(&p->syncp, start));
-
- rx_packets += tmp_rx_packets;
- rx_bytes += tmp_rx_bytes;
- rx_dropped += p->port_rx_dropped[i];
- }
- seq_printf(file, "port %3d %12llu %12llu %10u\n",
- i, rx_packets, rx_bytes, rx_dropped);
- }
- rx_invalid = 0;
- for_each_possible_cpu(j) {
- p = per_cpu_ptr(mlxsw_core->pcpu_stats, j);
- rx_invalid += p->port_rx_invalid;
- }
- seq_printf(file, "port INV %10u\n",
- rx_invalid);
- return 0;
-}
-
-static int mlxsw_core_rx_stats_dbg_open(struct inode *inode, struct file *f)
-{
- struct mlxsw_core *mlxsw_core = inode->i_private;
-
- return single_open(f, mlxsw_core_rx_stats_dbg_read, mlxsw_core);
-}
-
-static const struct file_operations mlxsw_core_rx_stats_dbg_ops = {
- .owner = THIS_MODULE,
- .open = mlxsw_core_rx_stats_dbg_open,
- .release = single_release,
- .read = seq_read,
- .llseek = seq_lseek
-};
-
int mlxsw_core_driver_register(struct mlxsw_driver *mlxsw_driver)
{
spin_lock(&mlxsw_core_driver_list_lock);
@@ -835,39 +758,13 @@ static void mlxsw_core_driver_put(const char *kind)
spin_unlock(&mlxsw_core_driver_list_lock);
}
-static int mlxsw_core_debugfs_init(struct mlxsw_core *mlxsw_core)
-{
- const struct mlxsw_bus_info *bus_info = mlxsw_core->bus_info;
-
- mlxsw_core->dbg_dir = debugfs_create_dir(bus_info->device_name,
- mlxsw_core_dbg_root);
- if (!mlxsw_core->dbg_dir)
- return -ENOMEM;
- debugfs_create_file("rx_stats", S_IRUGO, mlxsw_core->dbg_dir,
- mlxsw_core, &mlxsw_core_rx_stats_dbg_ops);
- mlxsw_core->dbg.vsd_blob.data = (void *) &bus_info->vsd;
- mlxsw_core->dbg.vsd_blob.size = sizeof(bus_info->vsd);
- debugfs_create_blob("vsd", S_IRUGO, mlxsw_core->dbg_dir,
- &mlxsw_core->dbg.vsd_blob);
- mlxsw_core->dbg.psid_blob.data = (void *) &bus_info->psid;
- mlxsw_core->dbg.psid_blob.size = sizeof(bus_info->psid);
- debugfs_create_blob("psid", S_IRUGO, mlxsw_core->dbg_dir,
- &mlxsw_core->dbg.psid_blob);
- return 0;
-}
-
-static void mlxsw_core_debugfs_fini(struct mlxsw_core *mlxsw_core)
-{
- debugfs_remove_recursive(mlxsw_core->dbg_dir);
-}
-
static int mlxsw_devlink_port_split(struct devlink *devlink,
unsigned int port_index,
unsigned int count)
{
struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
- if (port_index >= MLXSW_PORT_MAX_PORTS)
+ if (port_index >= mlxsw_core->max_ports)
return -EINVAL;
if (!mlxsw_core->driver->port_split)
return -EOPNOTSUPP;
@@ -879,7 +776,7 @@ static int mlxsw_devlink_port_unsplit(struct devlink *devlink,
{
struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
- if (port_index >= MLXSW_PORT_MAX_PORTS)
+ if (port_index >= mlxsw_core->max_ports)
return -EINVAL;
if (!mlxsw_core->driver->port_unsplit)
return -EOPNOTSUPP;
@@ -1101,18 +998,15 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
mlxsw_core->bus_priv = bus_priv;
mlxsw_core->bus_info = mlxsw_bus_info;
- mlxsw_core->pcpu_stats =
- netdev_alloc_pcpu_stats(struct mlxsw_core_pcpu_stats);
- if (!mlxsw_core->pcpu_stats) {
- err = -ENOMEM;
- goto err_alloc_stats;
- }
-
err = mlxsw_bus->init(bus_priv, mlxsw_core, mlxsw_driver->profile,
&mlxsw_core->res);
if (err)
goto err_bus_init;
+ err = mlxsw_ports_init(mlxsw_core);
+ if (err)
+ goto err_ports_init;
+
if (MLXSW_CORE_RES_VALID(mlxsw_core, MAX_LAG) &&
MLXSW_CORE_RES_VALID(mlxsw_core, MAX_LAG_MEMBERS)) {
alloc_size = sizeof(u8) *
@@ -1148,15 +1042,8 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
goto err_driver_init;
}
- err = mlxsw_core_debugfs_init(mlxsw_core);
- if (err)
- goto err_debugfs_init;
-
return 0;
-err_debugfs_init:
- if (mlxsw_core->driver->fini)
- mlxsw_core->driver->fini(mlxsw_core);
err_driver_init:
mlxsw_thermal_fini(mlxsw_core->thermal);
err_thermal_init:
@@ -1167,10 +1054,10 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
err_emad_init:
kfree(mlxsw_core->lag.mapping);
err_alloc_lag_mapping:
+ mlxsw_ports_fini(mlxsw_core);
+err_ports_init:
mlxsw_bus->fini(bus_priv);
err_bus_init:
- free_percpu(mlxsw_core->pcpu_stats);
-err_alloc_stats:
devlink_free(devlink);
err_devlink_alloc:
mlxsw_core_driver_put(device_kind);
@@ -1183,15 +1070,14 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core)
const char *device_kind = mlxsw_core->bus_info->device_kind;
struct devlink *devlink = priv_to_devlink(mlxsw_core);
- mlxsw_core_debugfs_fini(mlxsw_core);
if (mlxsw_core->driver->fini)
mlxsw_core->driver->fini(mlxsw_core);
mlxsw_thermal_fini(mlxsw_core->thermal);
devlink_unregister(devlink);
mlxsw_emad_fini(mlxsw_core);
kfree(mlxsw_core->lag.mapping);
+ mlxsw_ports_fini(mlxsw_core);
mlxsw_core->bus->fini(mlxsw_core->bus_priv);
- free_percpu(mlxsw_core->pcpu_stats);
devlink_free(devlink);
mlxsw_core_driver_put(device_kind);
}
@@ -1639,7 +1525,6 @@ void mlxsw_core_skb_receive(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
{
struct mlxsw_rx_listener_item *rxl_item;
const struct mlxsw_rx_listener *rxl;
- struct mlxsw_core_pcpu_stats *pcpu_stats;
u8 local_port;
bool found = false;
@@ -1661,7 +1546,7 @@ void mlxsw_core_skb_receive(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
__func__, local_port, rx_info->trap_id);
if ((rx_info->trap_id >= MLXSW_TRAP_ID_MAX) ||
- (local_port >= MLXSW_PORT_MAX_PORTS))
+ (local_port >= mlxsw_core->max_ports))
goto drop;
rcu_read_lock();
@@ -1678,26 +1563,10 @@ void mlxsw_core_skb_receive(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
if (!found)
goto drop;
- pcpu_stats = this_cpu_ptr(mlxsw_core->pcpu_stats);
- u64_stats_update_begin(&pcpu_stats->syncp);
- pcpu_stats->port_rx_packets[local_port]++;
- pcpu_stats->port_rx_bytes[local_port] += skb->len;
- pcpu_stats->trap_rx_packets[rx_info->trap_id]++;
- pcpu_stats->trap_rx_bytes[rx_info->trap_id] += skb->len;
- u64_stats_update_end(&pcpu_stats->syncp);
-
rxl->func(skb, local_port, rxl_item->priv);
return;
drop:
- if (rx_info->trap_id >= MLXSW_TRAP_ID_MAX)
- this_cpu_inc(mlxsw_core->pcpu_stats->trap_rx_invalid);
- else
- this_cpu_inc(mlxsw_core->pcpu_stats->trap_rx_dropped[rx_info->trap_id]);
- if (local_port >= MLXSW_PORT_MAX_PORTS)
- this_cpu_inc(mlxsw_core->pcpu_stats->port_rx_invalid);
- else
- this_cpu_inc(mlxsw_core->pcpu_stats->port_rx_dropped[local_port]);
dev_kfree_skb(skb);
}
EXPORT_SYMBOL(mlxsw_core_skb_receive);
@@ -1926,15 +1795,8 @@ static int __init mlxsw_core_module_init(void)
err = -ENOMEM;
goto err_alloc_ordered_workqueue;
}
- mlxsw_core_dbg_root = debugfs_create_dir(mlxsw_core_driver_name, NULL);
- if (!mlxsw_core_dbg_root) {
- err = -ENOMEM;
- goto err_debugfs_create_dir;
- }
return 0;
-err_debugfs_create_dir:
- destroy_workqueue(mlxsw_owq);
err_alloc_ordered_workqueue:
destroy_workqueue(mlxsw_wq);
return err;
@@ -1942,7 +1804,6 @@ static int __init mlxsw_core_module_init(void)
static void __exit mlxsw_core_module_exit(void)
{
- debugfs_remove_recursive(mlxsw_core_dbg_root);
destroy_workqueue(mlxsw_owq);
destroy_workqueue(mlxsw_wq);
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index cf38cf9..7fb3539 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -57,6 +57,8 @@ struct mlxsw_driver;
struct mlxsw_bus;
struct mlxsw_bus_info;
+unsigned int mlxsw_core_max_ports(const struct mlxsw_core *mlxsw_core);
+
void *mlxsw_core_driver_priv(struct mlxsw_core *mlxsw_core);
int mlxsw_core_driver_register(struct mlxsw_driver *mlxsw_driver);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index 5f337715..a984c36 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -567,6 +567,89 @@ static char *mlxsw_afa_block_append_action(struct mlxsw_afa_block *block,
return oneact + MLXSW_AFA_PAYLOAD_OFFSET;
}
+/* VLAN Action
+ * -----------
+ * VLAN action is used for manipulating VLANs. It can be used to implement QinQ,
+ * VLAN translation, change of PCP bits of the VLAN tag, push, pop as swap VLANs
+ * and more.
+ */
+
+#define MLXSW_AFA_VLAN_CODE 0x02
+#define MLXSW_AFA_VLAN_SIZE 1
+
+enum mlxsw_afa_vlan_vlan_tag_cmd {
+ MLXSW_AFA_VLAN_VLAN_TAG_CMD_NOP,
+ MLXSW_AFA_VLAN_VLAN_TAG_CMD_PUSH_TAG,
+ MLXSW_AFA_VLAN_VLAN_TAG_CMD_POP_TAG,
+};
+
+enum mlxsw_afa_vlan_cmd {
+ MLXSW_AFA_VLAN_CMD_NOP,
+ MLXSW_AFA_VLAN_CMD_SET_OUTER,
+ MLXSW_AFA_VLAN_CMD_SET_INNER,
+ MLXSW_AFA_VLAN_CMD_COPY_OUTER_TO_INNER,
+ MLXSW_AFA_VLAN_CMD_COPY_INNER_TO_OUTER,
+ MLXSW_AFA_VLAN_CMD_SWAP,
+};
+
+/* afa_vlan_vlan_tag_cmd
+ * Tag command: push, pop, nop VLAN header.
+ */
+MLXSW_ITEM32(afa, vlan, vlan_tag_cmd, 0x00, 29, 3);
+
+/* afa_vlan_vid_cmd */
+MLXSW_ITEM32(afa, vlan, vid_cmd, 0x04, 29, 3);
+
+/* afa_vlan_vid */
+MLXSW_ITEM32(afa, vlan, vid, 0x04, 0, 12);
+
+/* afa_vlan_ethertype_cmd */
+MLXSW_ITEM32(afa, vlan, ethertype_cmd, 0x08, 29, 3);
+
+/* afa_vlan_ethertype
+ * Index to EtherTypes in Switch VLAN EtherType Register (SVER).
+ */
+MLXSW_ITEM32(afa, vlan, ethertype, 0x08, 24, 3);
+
+/* afa_vlan_pcp_cmd */
+MLXSW_ITEM32(afa, vlan, pcp_cmd, 0x08, 13, 3);
+
+/* afa_vlan_pcp */
+MLXSW_ITEM32(afa, vlan, pcp, 0x08, 8, 3);
+
+static inline void
+mlxsw_afa_vlan_pack(char *payload,
+ enum mlxsw_afa_vlan_vlan_tag_cmd vlan_tag_cmd,
+ enum mlxsw_afa_vlan_cmd vid_cmd, u16 vid,
+ enum mlxsw_afa_vlan_cmd pcp_cmd, u8 pcp,
+ enum mlxsw_afa_vlan_cmd ethertype_cmd, u8 ethertype)
+{
+ mlxsw_afa_vlan_vlan_tag_cmd_set(payload, vlan_tag_cmd);
+ mlxsw_afa_vlan_vid_cmd_set(payload, vid_cmd);
+ mlxsw_afa_vlan_vid_set(payload, vid);
+ mlxsw_afa_vlan_pcp_cmd_set(payload, pcp_cmd);
+ mlxsw_afa_vlan_pcp_set(payload, pcp);
+ mlxsw_afa_vlan_ethertype_cmd_set(payload, ethertype_cmd);
+ mlxsw_afa_vlan_ethertype_set(payload, ethertype);
+}
+
+int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block,
+ u16 vid, u8 pcp, u8 et)
+{
+ char *act = mlxsw_afa_block_append_action(block,
+ MLXSW_AFA_VLAN_CODE,
+ MLXSW_AFA_VLAN_SIZE);
+
+ if (!act)
+ return -ENOBUFS;
+ mlxsw_afa_vlan_pack(act, MLXSW_AFA_VLAN_VLAN_TAG_CMD_NOP,
+ MLXSW_AFA_VLAN_CMD_SET_OUTER, vid,
+ MLXSW_AFA_VLAN_CMD_SET_OUTER, pcp,
+ MLXSW_AFA_VLAN_CMD_SET_OUTER, et);
+ return 0;
+}
+EXPORT_SYMBOL(mlxsw_afa_block_append_vlan_modify);
+
/* Trap / Discard Action
* ---------------------
* The Trap / Discard action enables trapping / mirroring packets to the CPU
@@ -677,3 +760,54 @@ int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block,
return err;
}
EXPORT_SYMBOL(mlxsw_afa_block_append_fwd);
+
+/* Policing and Counting Action
+ * ----------------------------
+ * Policing and Counting action is used for binding policer and counter
+ * to ACL rules.
+ */
+
+#define MLXSW_AFA_POLCNT_CODE 0x08
+#define MLXSW_AFA_POLCNT_SIZE 1
+
+enum mlxsw_afa_polcnt_counter_set_type {
+ /* No count */
+ MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_NO_COUNT = 0x00,
+ /* Count packets and bytes */
+ MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_PACKETS_BYTES = 0x03,
+ /* Count only packets */
+ MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_PACKETS = 0x05,
+};
+
+/* afa_polcnt_counter_set_type
+ * Counter set type for flow counters.
+ */
+MLXSW_ITEM32(afa, polcnt, counter_set_type, 0x04, 24, 8);
+
+/* afa_polcnt_counter_index
+ * Counter index for flow counters.
+ */
+MLXSW_ITEM32(afa, polcnt, counter_index, 0x04, 0, 24);
+
+static inline void
+mlxsw_afa_polcnt_pack(char *payload,
+ enum mlxsw_afa_polcnt_counter_set_type set_type,
+ u32 counter_index)
+{
+ mlxsw_afa_polcnt_counter_set_type_set(payload, set_type);
+ mlxsw_afa_polcnt_counter_index_set(payload, counter_index);
+}
+
+int mlxsw_afa_block_append_counter(struct mlxsw_afa_block *block,
+ u32 counter_index)
+{
+ char *act = mlxsw_afa_block_append_action(block,
+ MLXSW_AFA_POLCNT_CODE,
+ MLXSW_AFA_POLCNT_SIZE);
+ if (!act)
+ return -ENOBUFS;
+ mlxsw_afa_polcnt_pack(act, MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_PACKETS_BYTES,
+ counter_index);
+ return 0;
+}
+EXPORT_SYMBOL(mlxsw_afa_block_append_counter);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
index 43f78dc..a03362c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
@@ -62,5 +62,9 @@ void mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id);
int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block);
int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block,
u8 local_port, bool in_port);
+int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block,
+ u16 vid, u8 pcp, u8 et);
+int mlxsw_afa_block_append_counter(struct mlxsw_afa_block *block,
+ u32 counter_index);
#endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
index e4fcba7..c75e914 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
@@ -54,6 +54,8 @@ enum mlxsw_afk_element {
MLXSW_AFK_ELEMENT_DST_IP6_LO,
MLXSW_AFK_ELEMENT_DST_L4_PORT,
MLXSW_AFK_ELEMENT_SRC_L4_PORT,
+ MLXSW_AFK_ELEMENT_VID,
+ MLXSW_AFK_ELEMENT_PCP,
MLXSW_AFK_ELEMENT_MAX,
};
@@ -88,7 +90,7 @@ struct mlxsw_afk_element_info {
MLXSW_AFK_ELEMENT_INFO(MLXSW_AFK_ELEMENT_TYPE_BUF, \
_element, _offset, 0, _size)
-/* For the purpose of the driver, define a internal storage scratchpad
+/* For the purpose of the driver, define an internal storage scratchpad
* that will be used to store key/mask values. For each defined element type
* define an internal storage geometry.
*/
@@ -98,6 +100,8 @@ static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = {
MLXSW_AFK_ELEMENT_INFO_BUF(SMAC, 0x0A, 6),
MLXSW_AFK_ELEMENT_INFO_U32(ETHERTYPE, 0x00, 0, 16),
MLXSW_AFK_ELEMENT_INFO_U32(IP_PROTO, 0x10, 0, 8),
+ MLXSW_AFK_ELEMENT_INFO_U32(VID, 0x10, 8, 12),
+ MLXSW_AFK_ELEMENT_INFO_U32(PCP, 0x10, 20, 3),
MLXSW_AFK_ELEMENT_INFO_U32(SRC_IP4, 0x18, 0, 32),
MLXSW_AFK_ELEMENT_INFO_U32(DST_IP4, 0x1C, 0, 32),
MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP6_HI, 0x18, 8),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index a223c85..eaa3e3b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -44,8 +44,6 @@
#include <linux/skbuff.h>
#include <linux/if_vlan.h>
#include <linux/log2.h>
-#include <linux/debugfs.h>
-#include <linux/seq_file.h>
#include <linux/string.h>
#include "pci_hw.h"
@@ -57,8 +55,6 @@
static const char mlxsw_pci_driver_name[] = "mlxsw_pci";
-static struct dentry *mlxsw_pci_dbg_root;
-
#define mlxsw_pci_write32(mlxsw_pci, reg, val) \
iowrite32be(val, (mlxsw_pci)->hw_addr + (MLXSW_PCI_ ## reg))
#define mlxsw_pci_read32(mlxsw_pci, reg) \
@@ -71,21 +67,6 @@ enum mlxsw_pci_queue_type {
MLXSW_PCI_QUEUE_TYPE_EQ,
};
-static const char *mlxsw_pci_queue_type_str(enum mlxsw_pci_queue_type q_type)
-{
- switch (q_type) {
- case MLXSW_PCI_QUEUE_TYPE_SDQ:
- return "sdq";
- case MLXSW_PCI_QUEUE_TYPE_RDQ:
- return "rdq";
- case MLXSW_PCI_QUEUE_TYPE_CQ:
- return "cq";
- case MLXSW_PCI_QUEUE_TYPE_EQ:
- return "eq";
- }
- BUG();
-}
-
#define MLXSW_PCI_QUEUE_TYPE_COUNT 4
static const u16 mlxsw_pci_doorbell_type_offset[] = {
@@ -174,7 +155,6 @@ struct mlxsw_pci {
} comp;
} cmd;
struct mlxsw_bus_info bus_info;
- struct dentry *dbg_dir;
};
static void mlxsw_pci_queue_tasklet_schedule(struct mlxsw_pci_queue *q)
@@ -261,21 +241,11 @@ static u8 mlxsw_pci_sdq_count(struct mlxsw_pci *mlxsw_pci)
return __mlxsw_pci_queue_count(mlxsw_pci, MLXSW_PCI_QUEUE_TYPE_SDQ);
}
-static u8 mlxsw_pci_rdq_count(struct mlxsw_pci *mlxsw_pci)
-{
- return __mlxsw_pci_queue_count(mlxsw_pci, MLXSW_PCI_QUEUE_TYPE_RDQ);
-}
-
static u8 mlxsw_pci_cq_count(struct mlxsw_pci *mlxsw_pci)
{
return __mlxsw_pci_queue_count(mlxsw_pci, MLXSW_PCI_QUEUE_TYPE_CQ);
}
-static u8 mlxsw_pci_eq_count(struct mlxsw_pci *mlxsw_pci)
-{
- return __mlxsw_pci_queue_count(mlxsw_pci, MLXSW_PCI_QUEUE_TYPE_EQ);
-}
-
static struct mlxsw_pci_queue *
__mlxsw_pci_queue_get(struct mlxsw_pci *mlxsw_pci,
enum mlxsw_pci_queue_type q_type, u8 q_num)
@@ -390,26 +360,6 @@ static void mlxsw_pci_sdq_fini(struct mlxsw_pci *mlxsw_pci,
mlxsw_cmd_hw2sw_sdq(mlxsw_pci->core, q->num);
}
-static int mlxsw_pci_sdq_dbg_read(struct seq_file *file, void *data)
-{
- struct mlxsw_pci *mlxsw_pci = dev_get_drvdata(file->private);
- struct mlxsw_pci_queue *q;
- int i;
- static const char hdr[] =
- "NUM PROD_COUNT CONS_COUNT COUNT\n";
-
- seq_printf(file, hdr);
- for (i = 0; i < mlxsw_pci_sdq_count(mlxsw_pci); i++) {
- q = mlxsw_pci_sdq_get(mlxsw_pci, i);
- spin_lock_bh(&q->lock);
- seq_printf(file, "%3d %10d %10d %5d\n",
- i, q->producer_counter, q->consumer_counter,
- q->count);
- spin_unlock_bh(&q->lock);
- }
- return 0;
-}
-
static int mlxsw_pci_wqe_frag_map(struct mlxsw_pci *mlxsw_pci, char *wqe,
int index, char *frag_data, size_t frag_len,
int direction)
@@ -544,26 +494,6 @@ static void mlxsw_pci_rdq_fini(struct mlxsw_pci *mlxsw_pci,
}
}
-static int mlxsw_pci_rdq_dbg_read(struct seq_file *file, void *data)
-{
- struct mlxsw_pci *mlxsw_pci = dev_get_drvdata(file->private);
- struct mlxsw_pci_queue *q;
- int i;
- static const char hdr[] =
- "NUM PROD_COUNT CONS_COUNT COUNT\n";
-
- seq_printf(file, hdr);
- for (i = 0; i < mlxsw_pci_rdq_count(mlxsw_pci); i++) {
- q = mlxsw_pci_rdq_get(mlxsw_pci, i);
- spin_lock_bh(&q->lock);
- seq_printf(file, "%3d %10d %10d %5d\n",
- i, q->producer_counter, q->consumer_counter,
- q->count);
- spin_unlock_bh(&q->lock);
- }
- return 0;
-}
-
static int mlxsw_pci_cq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
struct mlxsw_pci_queue *q)
{
@@ -580,7 +510,6 @@ static int mlxsw_pci_cq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
mlxsw_cmd_mbox_sw2hw_cq_cv_set(mbox, 0); /* CQE ver 0 */
mlxsw_cmd_mbox_sw2hw_cq_c_eqn_set(mbox, MLXSW_PCI_EQ_COMP_NUM);
- mlxsw_cmd_mbox_sw2hw_cq_oi_set(mbox, 0);
mlxsw_cmd_mbox_sw2hw_cq_st_set(mbox, 0);
mlxsw_cmd_mbox_sw2hw_cq_log_cq_size_set(mbox, ilog2(q->count));
for (i = 0; i < MLXSW_PCI_AQ_PAGES; i++) {
@@ -602,27 +531,6 @@ static void mlxsw_pci_cq_fini(struct mlxsw_pci *mlxsw_pci,
mlxsw_cmd_hw2sw_cq(mlxsw_pci->core, q->num);
}
-static int mlxsw_pci_cq_dbg_read(struct seq_file *file, void *data)
-{
- struct mlxsw_pci *mlxsw_pci = dev_get_drvdata(file->private);
-
- struct mlxsw_pci_queue *q;
- int i;
- static const char hdr[] =
- "NUM CONS_INDEX SDQ_COUNT RDQ_COUNT COUNT\n";
-
- seq_printf(file, hdr);
- for (i = 0; i < mlxsw_pci_cq_count(mlxsw_pci); i++) {
- q = mlxsw_pci_cq_get(mlxsw_pci, i);
- spin_lock_bh(&q->lock);
- seq_printf(file, "%3d %10d %10d %10d %5d\n",
- i, q->consumer_counter, q->u.cq.comp_sdq_count,
- q->u.cq.comp_rdq_count, q->count);
- spin_unlock_bh(&q->lock);
- }
- return 0;
-}
-
static void mlxsw_pci_cqe_sdq_handle(struct mlxsw_pci *mlxsw_pci,
struct mlxsw_pci_queue *q,
u16 consumer_counter_limit,
@@ -755,7 +663,6 @@ static int mlxsw_pci_eq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
}
mlxsw_cmd_mbox_sw2hw_eq_int_msix_set(mbox, 1); /* MSI-X used */
- mlxsw_cmd_mbox_sw2hw_eq_oi_set(mbox, 0);
mlxsw_cmd_mbox_sw2hw_eq_st_set(mbox, 1); /* armed */
mlxsw_cmd_mbox_sw2hw_eq_log_eq_size_set(mbox, ilog2(q->count));
for (i = 0; i < MLXSW_PCI_AQ_PAGES; i++) {
@@ -777,27 +684,6 @@ static void mlxsw_pci_eq_fini(struct mlxsw_pci *mlxsw_pci,
mlxsw_cmd_hw2sw_eq(mlxsw_pci->core, q->num);
}
-static int mlxsw_pci_eq_dbg_read(struct seq_file *file, void *data)
-{
- struct mlxsw_pci *mlxsw_pci = dev_get_drvdata(file->private);
- struct mlxsw_pci_queue *q;
- int i;
- static const char hdr[] =
- "NUM CONS_COUNT EV_CMD EV_COMP EV_OTHER COUNT\n";
-
- seq_printf(file, hdr);
- for (i = 0; i < mlxsw_pci_eq_count(mlxsw_pci); i++) {
- q = mlxsw_pci_eq_get(mlxsw_pci, i);
- spin_lock_bh(&q->lock);
- seq_printf(file, "%3d %10d %10d %10d %10d %5d\n",
- i, q->consumer_counter, q->u.eq.ev_cmd_count,
- q->u.eq.ev_comp_count, q->u.eq.ev_other_count,
- q->count);
- spin_unlock_bh(&q->lock);
- }
- return 0;
-}
-
static void mlxsw_pci_eq_cmd_event(struct mlxsw_pci *mlxsw_pci, char *eqe)
{
mlxsw_pci->cmd.comp.status = mlxsw_pci_eqe_cmd_status_get(eqe);
@@ -868,7 +754,6 @@ struct mlxsw_pci_queue_ops {
void (*fini)(struct mlxsw_pci *mlxsw_pci,
struct mlxsw_pci_queue *q);
void (*tasklet)(unsigned long data);
- int (*dbg_read)(struct seq_file *s, void *data);
u16 elem_count;
u8 elem_size;
};
@@ -877,7 +762,6 @@ static const struct mlxsw_pci_queue_ops mlxsw_pci_sdq_ops = {
.type = MLXSW_PCI_QUEUE_TYPE_SDQ,
.init = mlxsw_pci_sdq_init,
.fini = mlxsw_pci_sdq_fini,
- .dbg_read = mlxsw_pci_sdq_dbg_read,
.elem_count = MLXSW_PCI_WQE_COUNT,
.elem_size = MLXSW_PCI_WQE_SIZE,
};
@@ -886,7 +770,6 @@ static const struct mlxsw_pci_queue_ops mlxsw_pci_rdq_ops = {
.type = MLXSW_PCI_QUEUE_TYPE_RDQ,
.init = mlxsw_pci_rdq_init,
.fini = mlxsw_pci_rdq_fini,
- .dbg_read = mlxsw_pci_rdq_dbg_read,
.elem_count = MLXSW_PCI_WQE_COUNT,
.elem_size = MLXSW_PCI_WQE_SIZE
};
@@ -896,7 +779,6 @@ static const struct mlxsw_pci_queue_ops mlxsw_pci_cq_ops = {
.init = mlxsw_pci_cq_init,
.fini = mlxsw_pci_cq_fini,
.tasklet = mlxsw_pci_cq_tasklet,
- .dbg_read = mlxsw_pci_cq_dbg_read,
.elem_count = MLXSW_PCI_CQE_COUNT,
.elem_size = MLXSW_PCI_CQE_SIZE
};
@@ -906,7 +788,6 @@ static const struct mlxsw_pci_queue_ops mlxsw_pci_eq_ops = {
.init = mlxsw_pci_eq_init,
.fini = mlxsw_pci_eq_fini,
.tasklet = mlxsw_pci_eq_tasklet,
- .dbg_read = mlxsw_pci_eq_dbg_read,
.elem_count = MLXSW_PCI_EQE_COUNT,
.elem_size = MLXSW_PCI_EQE_SIZE
};
@@ -984,9 +865,7 @@ static int mlxsw_pci_queue_group_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
const struct mlxsw_pci_queue_ops *q_ops,
u8 num_qs)
{
- struct pci_dev *pdev = mlxsw_pci->pdev;
struct mlxsw_pci_queue_type_group *queue_group;
- char tmp[16];
int i;
int err;
@@ -1003,10 +882,6 @@ static int mlxsw_pci_queue_group_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
}
queue_group->count = num_qs;
- sprintf(tmp, "%s_stats", mlxsw_pci_queue_type_str(q_ops->type));
- debugfs_create_devm_seqfile(&pdev->dev, tmp, mlxsw_pci->dbg_dir,
- q_ops->dbg_read);
-
return 0;
err_queue_init:
@@ -1852,14 +1727,6 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
mlxsw_pci->bus_info.device_name = pci_name(mlxsw_pci->pdev);
mlxsw_pci->bus_info.dev = &pdev->dev;
- mlxsw_pci->dbg_dir = debugfs_create_dir(mlxsw_pci->bus_info.device_name,
- mlxsw_pci_dbg_root);
- if (!mlxsw_pci->dbg_dir) {
- dev_err(&pdev->dev, "Failed to create debugfs dir\n");
- err = -ENOMEM;
- goto err_dbg_create_dir;
- }
-
err = mlxsw_core_bus_device_register(&mlxsw_pci->bus_info,
&mlxsw_pci_bus, mlxsw_pci);
if (err) {
@@ -1870,8 +1737,6 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
return 0;
err_bus_device_register:
- debugfs_remove_recursive(mlxsw_pci->dbg_dir);
-err_dbg_create_dir:
pci_disable_msix(mlxsw_pci->pdev);
err_msix_init:
err_sw_reset:
@@ -1892,7 +1757,6 @@ static void mlxsw_pci_remove(struct pci_dev *pdev)
struct mlxsw_pci *mlxsw_pci = pci_get_drvdata(pdev);
mlxsw_core_bus_device_unregister(mlxsw_pci->core);
- debugfs_remove_recursive(mlxsw_pci->dbg_dir);
pci_disable_msix(mlxsw_pci->pdev);
iounmap(mlxsw_pci->hw_addr);
pci_release_regions(mlxsw_pci->pdev);
@@ -1916,15 +1780,11 @@ EXPORT_SYMBOL(mlxsw_pci_driver_unregister);
static int __init mlxsw_pci_module_init(void)
{
- mlxsw_pci_dbg_root = debugfs_create_dir(mlxsw_pci_driver_name, NULL);
- if (!mlxsw_pci_dbg_root)
- return -ENOMEM;
return 0;
}
static void __exit mlxsw_pci_module_exit(void)
{
- debugfs_remove_recursive(mlxsw_pci_dbg_root);
}
module_init(mlxsw_pci_module_init);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/port.h b/drivers/net/ethernet/mellanox/mlxsw/port.h
index 3d42146..c580abb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/port.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/port.h
@@ -49,20 +49,12 @@
#define MLXSW_PORT_MID 0xd000
-#define MLXSW_PORT_MAX_PHY_PORTS 0x40
-#define MLXSW_PORT_MAX_PORTS (MLXSW_PORT_MAX_PHY_PORTS + 1)
-
#define MLXSW_PORT_MAX_IB_PHY_PORTS 36
#define MLXSW_PORT_MAX_IB_PORTS (MLXSW_PORT_MAX_IB_PHY_PORTS + 1)
-#define MLXSW_PORT_DEVID_BITS_OFFSET 10
-#define MLXSW_PORT_PHY_BITS_OFFSET 4
-#define MLXSW_PORT_PHY_BITS_MASK (MLXSW_PORT_MAX_PHY_PORTS - 1)
-
#define MLXSW_PORT_CPU_PORT 0x0
-#define MLXSW_PORT_ROUTER_PORT (MLXSW_PORT_MAX_PHY_PORTS + 2)
-#define MLXSW_PORT_DONT_CARE (MLXSW_PORT_MAX_PORTS)
+#define MLXSW_PORT_DONT_CARE 0xFF
#define MLXSW_PORT_MODULE_MAX_WIDTH 4
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 0899e2d..83b277c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -769,7 +769,7 @@ static inline void mlxsw_reg_spvid_pack(char *payload, u8 local_port, u16 pvid)
#define MLXSW_REG_SPVM_ID 0x200F
#define MLXSW_REG_SPVM_BASE_LEN 0x04 /* base length, without records */
#define MLXSW_REG_SPVM_REC_LEN 0x04 /* record length */
-#define MLXSW_REG_SPVM_REC_MAX_COUNT 256
+#define MLXSW_REG_SPVM_REC_MAX_COUNT 255
#define MLXSW_REG_SPVM_LEN (MLXSW_REG_SPVM_BASE_LEN + \
MLXSW_REG_SPVM_REC_LEN * MLXSW_REG_SPVM_REC_MAX_COUNT)
@@ -1702,7 +1702,7 @@ static inline void mlxsw_reg_sfmr_pack(char *payload,
#define MLXSW_REG_SPVMLR_ID 0x2020
#define MLXSW_REG_SPVMLR_BASE_LEN 0x04 /* base length, without records */
#define MLXSW_REG_SPVMLR_REC_LEN 0x04 /* record length */
-#define MLXSW_REG_SPVMLR_REC_MAX_COUNT 256
+#define MLXSW_REG_SPVMLR_REC_MAX_COUNT 255
#define MLXSW_REG_SPVMLR_LEN (MLXSW_REG_SPVMLR_BASE_LEN + \
MLXSW_REG_SPVMLR_REC_LEN * \
MLXSW_REG_SPVMLR_REC_MAX_COUNT)
@@ -4125,6 +4125,60 @@ MLXSW_ITEM32(reg, ritr, sp_if_system_port, 0x08, 0, 16);
*/
MLXSW_ITEM32(reg, ritr, sp_if_vid, 0x18, 0, 12);
+/* Shared between ingress/egress */
+enum mlxsw_reg_ritr_counter_set_type {
+ /* No Count. */
+ MLXSW_REG_RITR_COUNTER_SET_TYPE_NO_COUNT = 0x0,
+ /* Basic. Used for router interfaces, counting the following:
+ * - Error and Discard counters.
+ * - Unicast, Multicast and Broadcast counters. Sharing the
+ * same set of counters for the different type of traffic
+ * (IPv4, IPv6 and mpls).
+ */
+ MLXSW_REG_RITR_COUNTER_SET_TYPE_BASIC = 0x9,
+};
+
+/* reg_ritr_ingress_counter_index
+ * Counter Index for flow counter.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, ingress_counter_index, 0x38, 0, 24);
+
+/* reg_ritr_ingress_counter_set_type
+ * Igress Counter Set Type for router interface counter.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, ingress_counter_set_type, 0x38, 24, 8);
+
+/* reg_ritr_egress_counter_index
+ * Counter Index for flow counter.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, egress_counter_index, 0x3C, 0, 24);
+
+/* reg_ritr_egress_counter_set_type
+ * Egress Counter Set Type for router interface counter.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, egress_counter_set_type, 0x3C, 24, 8);
+
+static inline void mlxsw_reg_ritr_counter_pack(char *payload, u32 index,
+ bool enable, bool egress)
+{
+ enum mlxsw_reg_ritr_counter_set_type set_type;
+
+ if (enable)
+ set_type = MLXSW_REG_RITR_COUNTER_SET_TYPE_BASIC;
+ else
+ set_type = MLXSW_REG_RITR_COUNTER_SET_TYPE_NO_COUNT;
+ mlxsw_reg_ritr_egress_counter_set_type_set(payload, set_type);
+
+ if (egress)
+ mlxsw_reg_ritr_egress_counter_index_set(payload, index);
+ else
+ mlxsw_reg_ritr_ingress_counter_index_set(payload, index);
+}
+
static inline void mlxsw_reg_ritr_rif_pack(char *payload, u16 rif)
{
MLXSW_REG_ZERO(ritr, payload);
@@ -4141,7 +4195,8 @@ static inline void mlxsw_reg_ritr_sp_if_pack(char *payload, bool lag,
static inline void mlxsw_reg_ritr_pack(char *payload, bool enable,
enum mlxsw_reg_ritr_if_type type,
- u16 rif, u16 mtu, const char *mac)
+ u16 rif, u16 vr_id, u16 mtu,
+ const char *mac)
{
bool op = enable ? MLXSW_REG_RITR_RIF_CREATE : MLXSW_REG_RITR_RIF_DEL;
@@ -4153,6 +4208,7 @@ static inline void mlxsw_reg_ritr_pack(char *payload, bool enable,
mlxsw_reg_ritr_rif_set(payload, rif);
mlxsw_reg_ritr_ipv4_fe_set(payload, 1);
mlxsw_reg_ritr_lb_en_set(payload, 1);
+ mlxsw_reg_ritr_virtual_router_set(payload, vr_id);
mlxsw_reg_ritr_mtu_set(payload, mtu);
mlxsw_reg_ritr_if_mac_memcpy_to(payload, mac);
}
@@ -4285,6 +4341,129 @@ static inline void mlxsw_reg_ratr_eth_entry_pack(char *payload,
mlxsw_reg_ratr_eth_destination_mac_memcpy_to(payload, dest_mac);
}
+/* RICNT - Router Interface Counter Register
+ * -----------------------------------------
+ * The RICNT register retrieves per port performance counters
+ */
+#define MLXSW_REG_RICNT_ID 0x800B
+#define MLXSW_REG_RICNT_LEN 0x100
+
+MLXSW_REG_DEFINE(ricnt, MLXSW_REG_RICNT_ID, MLXSW_REG_RICNT_LEN);
+
+/* reg_ricnt_counter_index
+ * Counter index
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ricnt, counter_index, 0x04, 0, 24);
+
+enum mlxsw_reg_ricnt_counter_set_type {
+ /* No Count. */
+ MLXSW_REG_RICNT_COUNTER_SET_TYPE_NO_COUNT = 0x00,
+ /* Basic. Used for router interfaces, counting the following:
+ * - Error and Discard counters.
+ * - Unicast, Multicast and Broadcast counters. Sharing the
+ * same set of counters for the different type of traffic
+ * (IPv4, IPv6 and mpls).
+ */
+ MLXSW_REG_RICNT_COUNTER_SET_TYPE_BASIC = 0x09,
+};
+
+/* reg_ricnt_counter_set_type
+ * Counter Set Type for router interface counter
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ricnt, counter_set_type, 0x04, 24, 8);
+
+enum mlxsw_reg_ricnt_opcode {
+ /* Nop. Supported only for read access*/
+ MLXSW_REG_RICNT_OPCODE_NOP = 0x00,
+ /* Clear. Setting the clr bit will reset the counter value for
+ * all counters of the specified Router Interface.
+ */
+ MLXSW_REG_RICNT_OPCODE_CLEAR = 0x08,
+};
+
+/* reg_ricnt_opcode
+ * Opcode
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ricnt, op, 0x00, 28, 4);
+
+/* reg_ricnt_good_unicast_packets
+ * good unicast packets.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, good_unicast_packets, 0x08, 0, 64);
+
+/* reg_ricnt_good_multicast_packets
+ * good multicast packets.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, good_multicast_packets, 0x10, 0, 64);
+
+/* reg_ricnt_good_broadcast_packets
+ * good broadcast packets
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, good_broadcast_packets, 0x18, 0, 64);
+
+/* reg_ricnt_good_unicast_bytes
+ * A count of L3 data and padding octets not including L2 headers
+ * for good unicast frames.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, good_unicast_bytes, 0x20, 0, 64);
+
+/* reg_ricnt_good_multicast_bytes
+ * A count of L3 data and padding octets not including L2 headers
+ * for good multicast frames.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, good_multicast_bytes, 0x28, 0, 64);
+
+/* reg_ritr_good_broadcast_bytes
+ * A count of L3 data and padding octets not including L2 headers
+ * for good broadcast frames.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, good_broadcast_bytes, 0x30, 0, 64);
+
+/* reg_ricnt_error_packets
+ * A count of errored frames that do not pass the router checks.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, error_packets, 0x38, 0, 64);
+
+/* reg_ricnt_discrad_packets
+ * A count of non-errored frames that do not pass the router checks.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, discard_packets, 0x40, 0, 64);
+
+/* reg_ricnt_error_bytes
+ * A count of L3 data and padding octets not including L2 headers
+ * for errored frames.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, error_bytes, 0x48, 0, 64);
+
+/* reg_ricnt_discard_bytes
+ * A count of L3 data and padding octets not including L2 headers
+ * for non-errored frames that do not pass the router checks.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, ricnt, discard_bytes, 0x50, 0, 64);
+
+static inline void mlxsw_reg_ricnt_pack(char *payload, u32 index,
+ enum mlxsw_reg_ricnt_opcode op)
+{
+ MLXSW_REG_ZERO(ricnt, payload);
+ mlxsw_reg_ricnt_op_set(payload, op);
+ mlxsw_reg_ricnt_counter_index_set(payload, index);
+ mlxsw_reg_ricnt_counter_set_type_set(payload,
+ MLXSW_REG_RICNT_COUNTER_SET_TYPE_BASIC);
+}
+
/* RALTA - Router Algorithmic LPM Tree Allocation Register
* -------------------------------------------------------
* RALTA is used to allocate the LPM trees of the SHSPM method.
@@ -5504,6 +5683,70 @@ static inline void mlxsw_reg_mpsc_pack(char *payload, u8 local_port, bool e,
mlxsw_reg_mpsc_rate_set(payload, rate);
}
+/* MGPC - Monitoring General Purpose Counter Set Register
+ * The MGPC register retrieves and sets the General Purpose Counter Set.
+ */
+#define MLXSW_REG_MGPC_ID 0x9081
+#define MLXSW_REG_MGPC_LEN 0x18
+
+MLXSW_REG_DEFINE(mgpc, MLXSW_REG_MGPC_ID, MLXSW_REG_MGPC_LEN);
+
+enum mlxsw_reg_mgpc_counter_set_type {
+ /* No count */
+ MLXSW_REG_MGPC_COUNTER_SET_TYPE_NO_COUT = 0x00,
+ /* Count packets and bytes */
+ MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS_BYTES = 0x03,
+ /* Count only packets */
+ MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS = 0x05,
+};
+
+/* reg_mgpc_counter_set_type
+ * Counter set type.
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, mgpc, counter_set_type, 0x00, 24, 8);
+
+/* reg_mgpc_counter_index
+ * Counter index.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, mgpc, counter_index, 0x00, 0, 24);
+
+enum mlxsw_reg_mgpc_opcode {
+ /* Nop */
+ MLXSW_REG_MGPC_OPCODE_NOP = 0x00,
+ /* Clear counters */
+ MLXSW_REG_MGPC_OPCODE_CLEAR = 0x08,
+};
+
+/* reg_mgpc_opcode
+ * Opcode.
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, mgpc, opcode, 0x04, 28, 4);
+
+/* reg_mgpc_byte_counter
+ * Byte counter value.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, mgpc, byte_counter, 0x08, 0, 64);
+
+/* reg_mgpc_packet_counter
+ * Packet counter value.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, mgpc, packet_counter, 0x10, 0, 64);
+
+static inline void mlxsw_reg_mgpc_pack(char *payload, u32 counter_index,
+ enum mlxsw_reg_mgpc_opcode opcode,
+ enum mlxsw_reg_mgpc_counter_set_type set_type)
+{
+ MLXSW_REG_ZERO(mgpc, payload);
+ mlxsw_reg_mgpc_counter_index_set(payload, counter_index);
+ mlxsw_reg_mgpc_counter_set_type_set(payload, set_type);
+ mlxsw_reg_mgpc_opcode_set(payload, opcode);
+}
+
/* SBPR - Shared Buffer Pools Register
* -----------------------------------
* The SBPR configures and retrieves the shared buffer pools and configuration.
@@ -5960,6 +6203,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
MLXSW_REG(rgcr),
MLXSW_REG(ritr),
MLXSW_REG(ratr),
+ MLXSW_REG(ricnt),
MLXSW_REG(ralta),
MLXSW_REG(ralst),
MLXSW_REG(raltb),
@@ -5977,6 +6221,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
MLXSW_REG(mpar),
MLXSW_REG(mlcr),
MLXSW_REG(mpsc),
+ MLXSW_REG(mgpc),
MLXSW_REG(sbpr),
MLXSW_REG(sbcm),
MLXSW_REG(sbpm),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h
index bce8c2e..9556d93 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/resources.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h
@@ -43,11 +43,15 @@ enum mlxsw_res_id {
MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE,
MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE,
MLXSW_RES_ID_MAX_TRAP_GROUPS,
+ MLXSW_RES_ID_COUNTER_POOL_SIZE,
MLXSW_RES_ID_MAX_SPAN,
+ MLXSW_RES_ID_COUNTER_SIZE_PACKETS_BYTES,
+ MLXSW_RES_ID_COUNTER_SIZE_ROUTER_BASIC,
MLXSW_RES_ID_MAX_SYSTEM_PORT,
MLXSW_RES_ID_MAX_LAG,
MLXSW_RES_ID_MAX_LAG_MEMBERS,
MLXSW_RES_ID_MAX_BUFFER_SIZE,
+ MLXSW_RES_ID_CELL_SIZE,
MLXSW_RES_ID_ACL_MAX_TCAM_REGIONS,
MLXSW_RES_ID_ACL_MAX_TCAM_RULES,
MLXSW_RES_ID_ACL_MAX_REGIONS,
@@ -59,6 +63,7 @@ enum mlxsw_res_id {
MLXSW_RES_ID_MAX_CPU_POLICERS,
MLXSW_RES_ID_MAX_VRS,
MLXSW_RES_ID_MAX_RIFS,
+ MLXSW_RES_ID_MAX_LPM_TREES,
/* Internal resources.
* Determined by the SW, not queried from the HW.
@@ -75,11 +80,15 @@ static u16 mlxsw_res_ids[] = {
[MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE] = 0x1002,
[MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE] = 0x1003,
[MLXSW_RES_ID_MAX_TRAP_GROUPS] = 0x2201,
+ [MLXSW_RES_ID_COUNTER_POOL_SIZE] = 0x2410,
[MLXSW_RES_ID_MAX_SPAN] = 0x2420,
+ [MLXSW_RES_ID_COUNTER_SIZE_PACKETS_BYTES] = 0x2443,
+ [MLXSW_RES_ID_COUNTER_SIZE_ROUTER_BASIC] = 0x2449,
[MLXSW_RES_ID_MAX_SYSTEM_PORT] = 0x2502,
[MLXSW_RES_ID_MAX_LAG] = 0x2520,
[MLXSW_RES_ID_MAX_LAG_MEMBERS] = 0x2521,
[MLXSW_RES_ID_MAX_BUFFER_SIZE] = 0x2802, /* Bytes */
+ [MLXSW_RES_ID_CELL_SIZE] = 0x2803, /* Bytes */
[MLXSW_RES_ID_ACL_MAX_TCAM_REGIONS] = 0x2901,
[MLXSW_RES_ID_ACL_MAX_TCAM_RULES] = 0x2902,
[MLXSW_RES_ID_ACL_MAX_REGIONS] = 0x2903,
@@ -91,6 +100,7 @@ static u16 mlxsw_res_ids[] = {
[MLXSW_RES_ID_MAX_CPU_POLICERS] = 0x2A13,
[MLXSW_RES_ID_MAX_VRS] = 0x2C01,
[MLXSW_RES_ID_MAX_RIFS] = 0x2C02,
+ [MLXSW_RES_ID_MAX_LPM_TREES] = 0x2C30,
};
struct mlxsw_res {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 16484f2..b031f09 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -66,6 +66,8 @@
#include "port.h"
#include "trap.h"
#include "txheader.h"
+#include "spectrum_cnt.h"
+#include "spectrum_dpipe.h"
static const char mlxsw_sp_driver_name[] = "mlxsw_spectrum";
static const char mlxsw_sp_driver_version[] = "1.0";
@@ -138,6 +140,60 @@ MLXSW_ITEM32(tx, hdr, fid, 0x08, 0, 16);
*/
MLXSW_ITEM32(tx, hdr, type, 0x0C, 0, 4);
+int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp,
+ unsigned int counter_index, u64 *packets,
+ u64 *bytes)
+{
+ char mgpc_pl[MLXSW_REG_MGPC_LEN];
+ int err;
+
+ mlxsw_reg_mgpc_pack(mgpc_pl, counter_index, MLXSW_REG_MGPC_OPCODE_NOP,
+ MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS_BYTES);
+ err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(mgpc), mgpc_pl);
+ if (err)
+ return err;
+ *packets = mlxsw_reg_mgpc_packet_counter_get(mgpc_pl);
+ *bytes = mlxsw_reg_mgpc_byte_counter_get(mgpc_pl);
+ return 0;
+}
+
+static int mlxsw_sp_flow_counter_clear(struct mlxsw_sp *mlxsw_sp,
+ unsigned int counter_index)
+{
+ char mgpc_pl[MLXSW_REG_MGPC_LEN];
+
+ mlxsw_reg_mgpc_pack(mgpc_pl, counter_index, MLXSW_REG_MGPC_OPCODE_CLEAR,
+ MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS_BYTES);
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mgpc), mgpc_pl);
+}
+
+int mlxsw_sp_flow_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+ unsigned int *p_counter_index)
+{
+ int err;
+
+ err = mlxsw_sp_counter_alloc(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_FLOW,
+ p_counter_index);
+ if (err)
+ return err;
+ err = mlxsw_sp_flow_counter_clear(mlxsw_sp, *p_counter_index);
+ if (err)
+ goto err_counter_clear;
+ return 0;
+
+err_counter_clear:
+ mlxsw_sp_counter_free(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_FLOW,
+ *p_counter_index);
+ return err;
+}
+
+void mlxsw_sp_flow_counter_free(struct mlxsw_sp *mlxsw_sp,
+ unsigned int counter_index)
+{
+ mlxsw_sp_counter_free(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_FLOW,
+ counter_index);
+}
+
static void mlxsw_sp_txhdr_construct(struct sk_buff *skb,
const struct mlxsw_tx_info *tx_info)
{
@@ -304,9 +360,10 @@ static bool mlxsw_sp_span_is_egress_mirror(struct mlxsw_sp_port *port)
return false;
}
-static int mlxsw_sp_span_mtu_to_buffsize(int mtu)
+static int mlxsw_sp_span_mtu_to_buffsize(const struct mlxsw_sp *mlxsw_sp,
+ int mtu)
{
- return MLXSW_SP_BYTES_TO_CELLS(mtu * 5 / 2) + 1;
+ return mlxsw_sp_bytes_cells(mlxsw_sp, mtu * 5 / 2) + 1;
}
static int mlxsw_sp_span_port_mtu_update(struct mlxsw_sp_port *port, u16 mtu)
@@ -319,8 +376,9 @@ static int mlxsw_sp_span_port_mtu_update(struct mlxsw_sp_port *port, u16 mtu)
* updated according to the mtu value
*/
if (mlxsw_sp_span_is_egress_mirror(port)) {
- mlxsw_reg_sbib_pack(sbib_pl, port->local_port,
- mlxsw_sp_span_mtu_to_buffsize(mtu));
+ u32 buffsize = mlxsw_sp_span_mtu_to_buffsize(mlxsw_sp, mtu);
+
+ mlxsw_reg_sbib_pack(sbib_pl, port->local_port, buffsize);
err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl);
if (err) {
netdev_err(port->dev, "Could not update shared buffer for mirroring\n");
@@ -357,8 +415,10 @@ mlxsw_sp_span_inspected_port_bind(struct mlxsw_sp_port *port,
/* if it is an egress SPAN, bind a shared buffer to it */
if (type == MLXSW_SP_SPAN_EGRESS) {
- mlxsw_reg_sbib_pack(sbib_pl, port->local_port,
- mlxsw_sp_span_mtu_to_buffsize(port->dev->mtu));
+ u32 buffsize = mlxsw_sp_span_mtu_to_buffsize(mlxsw_sp,
+ port->dev->mtu);
+
+ mlxsw_reg_sbib_pack(sbib_pl, port->local_port, buffsize);
err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl);
if (err) {
netdev_err(port->dev, "Could not create shared buffer for mirroring\n");
@@ -745,19 +805,47 @@ static int mlxsw_sp_port_set_mac_address(struct net_device *dev, void *p)
return 0;
}
-static void mlxsw_sp_pg_buf_pack(char *pbmc_pl, int pg_index, int mtu,
- bool pause_en, bool pfc_en, u16 delay)
+static u16 mlxsw_sp_pg_buf_threshold_get(const struct mlxsw_sp *mlxsw_sp,
+ int mtu)
{
- u16 pg_size = 2 * MLXSW_SP_BYTES_TO_CELLS(mtu);
+ return 2 * mlxsw_sp_bytes_cells(mlxsw_sp, mtu);
+}
- delay = pfc_en ? mlxsw_sp_pfc_delay_get(mtu, delay) :
- MLXSW_SP_PAUSE_DELAY;
+#define MLXSW_SP_CELL_FACTOR 2 /* 2 * cell_size / (IPG + cell_size + 1) */
- if (pause_en || pfc_en)
- mlxsw_reg_pbmc_lossless_buffer_pack(pbmc_pl, pg_index,
- pg_size + delay, pg_size);
+static u16 mlxsw_sp_pfc_delay_get(const struct mlxsw_sp *mlxsw_sp, int mtu,
+ u16 delay)
+{
+ delay = mlxsw_sp_bytes_cells(mlxsw_sp, DIV_ROUND_UP(delay,
+ BITS_PER_BYTE));
+ return MLXSW_SP_CELL_FACTOR * delay + mlxsw_sp_bytes_cells(mlxsw_sp,
+ mtu);
+}
+
+/* Maximum delay buffer needed in case of PAUSE frames, in bytes.
+ * Assumes 100m cable and maximum MTU.
+ */
+#define MLXSW_SP_PAUSE_DELAY 58752
+
+static u16 mlxsw_sp_pg_buf_delay_get(const struct mlxsw_sp *mlxsw_sp, int mtu,
+ u16 delay, bool pfc, bool pause)
+{
+ if (pfc)
+ return mlxsw_sp_pfc_delay_get(mlxsw_sp, mtu, delay);
+ else if (pause)
+ return mlxsw_sp_bytes_cells(mlxsw_sp, MLXSW_SP_PAUSE_DELAY);
else
- mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, pg_index, pg_size);
+ return 0;
+}
+
+static void mlxsw_sp_pg_buf_pack(char *pbmc_pl, int index, u16 size, u16 thres,
+ bool lossy)
+{
+ if (lossy)
+ mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, index, size);
+ else
+ mlxsw_reg_pbmc_lossless_buffer_pack(pbmc_pl, index, size,
+ thres);
}
int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
@@ -778,6 +866,8 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
bool configure = false;
bool pfc = false;
+ bool lossy;
+ u16 thres;
for (j = 0; j < IEEE_8021QAZ_MAX_TCS; j++) {
if (prio_tc[j] == i) {
@@ -789,7 +879,12 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
if (!configure)
continue;
- mlxsw_sp_pg_buf_pack(pbmc_pl, i, mtu, pause_en, pfc, delay);
+
+ lossy = !(pfc || pause_en);
+ thres = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu);
+ delay = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay, pfc,
+ pause_en);
+ mlxsw_sp_pg_buf_pack(pbmc_pl, i, thres + delay, thres, lossy);
}
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl);
@@ -1368,7 +1463,7 @@ static int mlxsw_sp_setup_tc(struct net_device *dev, u32 handle,
tc->cls_mall);
return 0;
default:
- return -EINVAL;
+ return -EOPNOTSUPP;
}
case TC_SETUP_CLSFLOWER:
switch (tc->cls_flower->command) {
@@ -1379,6 +1474,9 @@ static int mlxsw_sp_setup_tc(struct net_device *dev, u32 handle,
mlxsw_sp_flower_destroy(mlxsw_sp_port, ingress,
tc->cls_flower);
return 0;
+ case TC_CLSFLOWER_STATS:
+ return mlxsw_sp_flower_stats(mlxsw_sp_port, ingress,
+ tc->cls_flower);
default:
return -EOPNOTSUPP;
}
@@ -1492,6 +1590,7 @@ static int mlxsw_sp_port_set_pauseparam(struct net_device *dev,
struct mlxsw_sp_port_hw_stats {
char str[ETH_GSTRING_LEN];
u64 (*getter)(const char *payload);
+ bool cells_bytes;
};
static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_stats[] = {
@@ -1612,17 +1711,11 @@ static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_prio_stats[] = {
#define MLXSW_SP_PORT_HW_PRIO_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_hw_prio_stats)
-static u64 mlxsw_reg_ppcnt_tc_transmit_queue_bytes_get(const char *ppcnt_pl)
-{
- u64 transmit_queue = mlxsw_reg_ppcnt_tc_transmit_queue_get(ppcnt_pl);
-
- return MLXSW_SP_CELLS_TO_BYTES(transmit_queue);
-}
-
static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_tc_stats[] = {
{
.str = "tc_transmit_queue_tc",
- .getter = mlxsw_reg_ppcnt_tc_transmit_queue_bytes_get,
+ .getter = mlxsw_reg_ppcnt_tc_transmit_queue_get,
+ .cells_bytes = true,
},
{
.str = "tc_no_buffer_discard_uc_tc",
@@ -1734,6 +1827,8 @@ static void __mlxsw_sp_port_get_stats(struct net_device *dev,
enum mlxsw_reg_ppcnt_grp grp, int prio,
u64 *data, int data_index)
{
+ struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
struct mlxsw_sp_port_hw_stats *hw_stats;
char ppcnt_pl[MLXSW_REG_PPCNT_LEN];
int i, len;
@@ -1743,8 +1838,13 @@ static void __mlxsw_sp_port_get_stats(struct net_device *dev,
if (err)
return;
mlxsw_sp_port_get_stats_raw(dev, grp, prio, ppcnt_pl);
- for (i = 0; i < len; i++)
+ for (i = 0; i < len; i++) {
data[data_index + i] = hw_stats[i].getter(ppcnt_pl);
+ if (!hw_stats[i].cells_bytes)
+ continue;
+ data[data_index + i] = mlxsw_sp_cells_bytes(mlxsw_sp,
+ data[data_index + i]);
+ }
}
static void mlxsw_sp_port_get_stats(struct net_device *dev,
@@ -2537,25 +2637,33 @@ static void mlxsw_sp_ports_remove(struct mlxsw_sp *mlxsw_sp)
{
int i;
- for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++)
+ for (i = 1; i < mlxsw_core_max_ports(mlxsw_sp->core); i++)
if (mlxsw_sp_port_created(mlxsw_sp, i))
mlxsw_sp_port_remove(mlxsw_sp, i);
+ kfree(mlxsw_sp->port_to_module);
kfree(mlxsw_sp->ports);
}
static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp)
{
+ unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
u8 module, width, lane;
size_t alloc_size;
int i;
int err;
- alloc_size = sizeof(struct mlxsw_sp_port *) * MLXSW_PORT_MAX_PORTS;
+ alloc_size = sizeof(struct mlxsw_sp_port *) * max_ports;
mlxsw_sp->ports = kzalloc(alloc_size, GFP_KERNEL);
if (!mlxsw_sp->ports)
return -ENOMEM;
- for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++) {
+ mlxsw_sp->port_to_module = kcalloc(max_ports, sizeof(u8), GFP_KERNEL);
+ if (!mlxsw_sp->port_to_module) {
+ err = -ENOMEM;
+ goto err_port_to_module_alloc;
+ }
+
+ for (i = 1; i < max_ports; i++) {
err = mlxsw_sp_port_module_info_get(mlxsw_sp, i, &module,
&width, &lane);
if (err)
@@ -2575,6 +2683,8 @@ static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp)
for (i--; i >= 1; i--)
if (mlxsw_sp_port_created(mlxsw_sp, i))
mlxsw_sp_port_remove(mlxsw_sp, i);
+ kfree(mlxsw_sp->port_to_module);
+err_port_to_module_alloc:
kfree(mlxsw_sp->ports);
return err;
}
@@ -3224,6 +3334,18 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
goto err_acl_init;
}
+ err = mlxsw_sp_counter_pool_init(mlxsw_sp);
+ if (err) {
+ dev_err(mlxsw_sp->bus_info->dev, "Failed to init counter pool\n");
+ goto err_counter_pool_init;
+ }
+
+ err = mlxsw_sp_dpipe_init(mlxsw_sp);
+ if (err) {
+ dev_err(mlxsw_sp->bus_info->dev, "Failed to init pipeline debug\n");
+ goto err_dpipe_init;
+ }
+
err = mlxsw_sp_ports_create(mlxsw_sp);
if (err) {
dev_err(mlxsw_sp->bus_info->dev, "Failed to create ports\n");
@@ -3233,6 +3355,10 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
return 0;
err_ports_create:
+ mlxsw_sp_dpipe_fini(mlxsw_sp);
+err_dpipe_init:
+ mlxsw_sp_counter_pool_fini(mlxsw_sp);
+err_counter_pool_init:
mlxsw_sp_acl_fini(mlxsw_sp);
err_acl_init:
mlxsw_sp_span_fini(mlxsw_sp);
@@ -3255,6 +3381,8 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
mlxsw_sp_ports_remove(mlxsw_sp);
+ mlxsw_sp_dpipe_fini(mlxsw_sp);
+ mlxsw_sp_counter_pool_fini(mlxsw_sp);
mlxsw_sp_acl_fini(mlxsw_sp);
mlxsw_sp_span_fini(mlxsw_sp);
mlxsw_sp_router_fini(mlxsw_sp);
@@ -3326,13 +3454,13 @@ bool mlxsw_sp_port_dev_check(const struct net_device *dev)
return dev->netdev_ops == &mlxsw_sp_port_netdev_ops;
}
-static int mlxsw_lower_dev_walk(struct net_device *lower_dev, void *data)
+static int mlxsw_sp_lower_dev_walk(struct net_device *lower_dev, void *data)
{
- struct mlxsw_sp_port **port = data;
+ struct mlxsw_sp_port **p_mlxsw_sp_port = data;
int ret = 0;
if (mlxsw_sp_port_dev_check(lower_dev)) {
- *port = netdev_priv(lower_dev);
+ *p_mlxsw_sp_port = netdev_priv(lower_dev);
ret = 1;
}
@@ -3341,18 +3469,18 @@ static int mlxsw_lower_dev_walk(struct net_device *lower_dev, void *data)
static struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev)
{
- struct mlxsw_sp_port *port;
+ struct mlxsw_sp_port *mlxsw_sp_port;
if (mlxsw_sp_port_dev_check(dev))
return netdev_priv(dev);
- port = NULL;
- netdev_walk_all_lower_dev(dev, mlxsw_lower_dev_walk, &port);
+ mlxsw_sp_port = NULL;
+ netdev_walk_all_lower_dev(dev, mlxsw_sp_lower_dev_walk, &mlxsw_sp_port);
- return port;
+ return mlxsw_sp_port;
}
-static struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev)
+struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev)
{
struct mlxsw_sp_port *mlxsw_sp_port;
@@ -3362,15 +3490,16 @@ static struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev)
static struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find_rcu(struct net_device *dev)
{
- struct mlxsw_sp_port *port;
+ struct mlxsw_sp_port *mlxsw_sp_port;
if (mlxsw_sp_port_dev_check(dev))
return netdev_priv(dev);
- port = NULL;
- netdev_walk_all_lower_dev_rcu(dev, mlxsw_lower_dev_walk, &port);
+ mlxsw_sp_port = NULL;
+ netdev_walk_all_lower_dev_rcu(dev, mlxsw_sp_lower_dev_walk,
+ &mlxsw_sp_port);
- return port;
+ return mlxsw_sp_port;
}
struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev)
@@ -3390,546 +3519,6 @@ void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port)
dev_put(mlxsw_sp_port->dev);
}
-static bool mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *r,
- unsigned long event)
-{
- switch (event) {
- case NETDEV_UP:
- if (!r)
- return true;
- r->ref_count++;
- return false;
- case NETDEV_DOWN:
- if (r && --r->ref_count == 0)
- return true;
- /* It is possible we already removed the RIF ourselves
- * if it was assigned to a netdev that is now a bridge
- * or LAG slave.
- */
- return false;
- }
-
- return false;
-}
-
-static int mlxsw_sp_avail_rif_get(struct mlxsw_sp *mlxsw_sp)
-{
- int i;
-
- for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++)
- if (!mlxsw_sp->rifs[i])
- return i;
-
- return MLXSW_SP_INVALID_RIF;
-}
-
-static void mlxsw_sp_vport_rif_sp_attr_get(struct mlxsw_sp_port *mlxsw_sp_vport,
- bool *p_lagged, u16 *p_system_port)
-{
- u8 local_port = mlxsw_sp_vport->local_port;
-
- *p_lagged = mlxsw_sp_vport->lagged;
- *p_system_port = *p_lagged ? mlxsw_sp_vport->lag_id : local_port;
-}
-
-static int mlxsw_sp_vport_rif_sp_op(struct mlxsw_sp_port *mlxsw_sp_vport,
- struct net_device *l3_dev, u16 rif,
- bool create)
-{
- struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
- bool lagged = mlxsw_sp_vport->lagged;
- char ritr_pl[MLXSW_REG_RITR_LEN];
- u16 system_port;
-
- mlxsw_reg_ritr_pack(ritr_pl, create, MLXSW_REG_RITR_SP_IF, rif,
- l3_dev->mtu, l3_dev->dev_addr);
-
- mlxsw_sp_vport_rif_sp_attr_get(mlxsw_sp_vport, &lagged, &system_port);
- mlxsw_reg_ritr_sp_if_pack(ritr_pl, lagged, system_port,
- mlxsw_sp_vport_vid_get(mlxsw_sp_vport));
-
- return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
-}
-
-static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport);
-
-static struct mlxsw_sp_fid *
-mlxsw_sp_rfid_alloc(u16 fid, struct net_device *l3_dev)
-{
- struct mlxsw_sp_fid *f;
-
- f = kzalloc(sizeof(*f), GFP_KERNEL);
- if (!f)
- return NULL;
-
- f->leave = mlxsw_sp_vport_rif_sp_leave;
- f->ref_count = 0;
- f->dev = l3_dev;
- f->fid = fid;
-
- return f;
-}
-
-static struct mlxsw_sp_rif *
-mlxsw_sp_rif_alloc(u16 rif, struct net_device *l3_dev, struct mlxsw_sp_fid *f)
-{
- struct mlxsw_sp_rif *r;
-
- r = kzalloc(sizeof(*r), GFP_KERNEL);
- if (!r)
- return NULL;
-
- INIT_LIST_HEAD(&r->nexthop_list);
- INIT_LIST_HEAD(&r->neigh_list);
- ether_addr_copy(r->addr, l3_dev->dev_addr);
- r->mtu = l3_dev->mtu;
- r->ref_count = 1;
- r->dev = l3_dev;
- r->rif = rif;
- r->f = f;
-
- return r;
-}
-
-static struct mlxsw_sp_rif *
-mlxsw_sp_vport_rif_sp_create(struct mlxsw_sp_port *mlxsw_sp_vport,
- struct net_device *l3_dev)
-{
- struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
- struct mlxsw_sp_fid *f;
- struct mlxsw_sp_rif *r;
- u16 fid, rif;
- int err;
-
- rif = mlxsw_sp_avail_rif_get(mlxsw_sp);
- if (rif == MLXSW_SP_INVALID_RIF)
- return ERR_PTR(-ERANGE);
-
- err = mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, true);
- if (err)
- return ERR_PTR(err);
-
- fid = mlxsw_sp_rif_sp_to_fid(rif);
- err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, true);
- if (err)
- goto err_rif_fdb_op;
-
- f = mlxsw_sp_rfid_alloc(fid, l3_dev);
- if (!f) {
- err = -ENOMEM;
- goto err_rfid_alloc;
- }
-
- r = mlxsw_sp_rif_alloc(rif, l3_dev, f);
- if (!r) {
- err = -ENOMEM;
- goto err_rif_alloc;
- }
-
- f->r = r;
- mlxsw_sp->rifs[rif] = r;
-
- return r;
-
-err_rif_alloc:
- kfree(f);
-err_rfid_alloc:
- mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false);
-err_rif_fdb_op:
- mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, false);
- return ERR_PTR(err);
-}
-
-static void mlxsw_sp_vport_rif_sp_destroy(struct mlxsw_sp_port *mlxsw_sp_vport,
- struct mlxsw_sp_rif *r)
-{
- struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
- struct net_device *l3_dev = r->dev;
- struct mlxsw_sp_fid *f = r->f;
- u16 fid = f->fid;
- u16 rif = r->rif;
-
- mlxsw_sp_router_rif_gone_sync(mlxsw_sp, r);
-
- mlxsw_sp->rifs[rif] = NULL;
- f->r = NULL;
-
- kfree(r);
-
- kfree(f);
-
- mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false);
-
- mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, l3_dev, rif, false);
-}
-
-static int mlxsw_sp_vport_rif_sp_join(struct mlxsw_sp_port *mlxsw_sp_vport,
- struct net_device *l3_dev)
-{
- struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
- struct mlxsw_sp_rif *r;
-
- r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
- if (!r) {
- r = mlxsw_sp_vport_rif_sp_create(mlxsw_sp_vport, l3_dev);
- if (IS_ERR(r))
- return PTR_ERR(r);
- }
-
- mlxsw_sp_vport_fid_set(mlxsw_sp_vport, r->f);
- r->f->ref_count++;
-
- netdev_dbg(mlxsw_sp_vport->dev, "Joined FID=%d\n", r->f->fid);
-
- return 0;
-}
-
-static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport)
-{
- struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport);
-
- netdev_dbg(mlxsw_sp_vport->dev, "Left FID=%d\n", f->fid);
-
- mlxsw_sp_vport_fid_set(mlxsw_sp_vport, NULL);
- if (--f->ref_count == 0)
- mlxsw_sp_vport_rif_sp_destroy(mlxsw_sp_vport, f->r);
-}
-
-static int mlxsw_sp_inetaddr_vport_event(struct net_device *l3_dev,
- struct net_device *port_dev,
- unsigned long event, u16 vid)
-{
- struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(port_dev);
- struct mlxsw_sp_port *mlxsw_sp_vport;
-
- mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid);
- if (WARN_ON(!mlxsw_sp_vport))
- return -EINVAL;
-
- switch (event) {
- case NETDEV_UP:
- return mlxsw_sp_vport_rif_sp_join(mlxsw_sp_vport, l3_dev);
- case NETDEV_DOWN:
- mlxsw_sp_vport_rif_sp_leave(mlxsw_sp_vport);
- break;
- }
-
- return 0;
-}
-
-static int mlxsw_sp_inetaddr_port_event(struct net_device *port_dev,
- unsigned long event)
-{
- if (netif_is_bridge_port(port_dev) || netif_is_lag_port(port_dev))
- return 0;
-
- return mlxsw_sp_inetaddr_vport_event(port_dev, port_dev, event, 1);
-}
-
-static int __mlxsw_sp_inetaddr_lag_event(struct net_device *l3_dev,
- struct net_device *lag_dev,
- unsigned long event, u16 vid)
-{
- struct net_device *port_dev;
- struct list_head *iter;
- int err;
-
- netdev_for_each_lower_dev(lag_dev, port_dev, iter) {
- if (mlxsw_sp_port_dev_check(port_dev)) {
- err = mlxsw_sp_inetaddr_vport_event(l3_dev, port_dev,
- event, vid);
- if (err)
- return err;
- }
- }
-
- return 0;
-}
-
-static int mlxsw_sp_inetaddr_lag_event(struct net_device *lag_dev,
- unsigned long event)
-{
- if (netif_is_bridge_port(lag_dev))
- return 0;
-
- return __mlxsw_sp_inetaddr_lag_event(lag_dev, lag_dev, event, 1);
-}
-
-static struct mlxsw_sp_fid *mlxsw_sp_bridge_fid_get(struct mlxsw_sp *mlxsw_sp,
- struct net_device *l3_dev)
-{
- u16 fid;
-
- if (is_vlan_dev(l3_dev))
- fid = vlan_dev_vlan_id(l3_dev);
- else if (mlxsw_sp->master_bridge.dev == l3_dev)
- fid = 1;
- else
- return mlxsw_sp_vfid_find(mlxsw_sp, l3_dev);
-
- return mlxsw_sp_fid_find(mlxsw_sp, fid);
-}
-
-static enum mlxsw_flood_table_type mlxsw_sp_flood_table_type_get(u16 fid)
-{
- return mlxsw_sp_fid_is_vfid(fid) ? MLXSW_REG_SFGC_TABLE_TYPE_FID :
- MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST;
-}
-
-static u16 mlxsw_sp_flood_table_index_get(u16 fid)
-{
- return mlxsw_sp_fid_is_vfid(fid) ? mlxsw_sp_fid_to_vfid(fid) : fid;
-}
-
-static int mlxsw_sp_router_port_flood_set(struct mlxsw_sp *mlxsw_sp, u16 fid,
- bool set)
-{
- enum mlxsw_flood_table_type table_type;
- char *sftr_pl;
- u16 index;
- int err;
-
- sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL);
- if (!sftr_pl)
- return -ENOMEM;
-
- table_type = mlxsw_sp_flood_table_type_get(fid);
- index = mlxsw_sp_flood_table_index_get(fid);
- mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_BC, index, table_type,
- 1, MLXSW_PORT_ROUTER_PORT, set);
- err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl);
-
- kfree(sftr_pl);
- return err;
-}
-
-static enum mlxsw_reg_ritr_if_type mlxsw_sp_rif_type_get(u16 fid)
-{
- if (mlxsw_sp_fid_is_vfid(fid))
- return MLXSW_REG_RITR_FID_IF;
- else
- return MLXSW_REG_RITR_VLAN_IF;
-}
-
-static int mlxsw_sp_rif_bridge_op(struct mlxsw_sp *mlxsw_sp,
- struct net_device *l3_dev,
- u16 fid, u16 rif,
- bool create)
-{
- enum mlxsw_reg_ritr_if_type rif_type;
- char ritr_pl[MLXSW_REG_RITR_LEN];
-
- rif_type = mlxsw_sp_rif_type_get(fid);
- mlxsw_reg_ritr_pack(ritr_pl, create, rif_type, rif, l3_dev->mtu,
- l3_dev->dev_addr);
- mlxsw_reg_ritr_fid_set(ritr_pl, rif_type, fid);
-
- return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
-}
-
-static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp,
- struct net_device *l3_dev,
- struct mlxsw_sp_fid *f)
-{
- struct mlxsw_sp_rif *r;
- u16 rif;
- int err;
-
- rif = mlxsw_sp_avail_rif_get(mlxsw_sp);
- if (rif == MLXSW_SP_INVALID_RIF)
- return -ERANGE;
-
- err = mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, true);
- if (err)
- return err;
-
- err = mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, true);
- if (err)
- goto err_rif_bridge_op;
-
- err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, true);
- if (err)
- goto err_rif_fdb_op;
-
- r = mlxsw_sp_rif_alloc(rif, l3_dev, f);
- if (!r) {
- err = -ENOMEM;
- goto err_rif_alloc;
- }
-
- f->r = r;
- mlxsw_sp->rifs[rif] = r;
-
- netdev_dbg(l3_dev, "RIF=%d created\n", rif);
-
- return 0;
-
-err_rif_alloc:
- mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false);
-err_rif_fdb_op:
- mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false);
-err_rif_bridge_op:
- mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false);
- return err;
-}
-
-void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_rif *r)
-{
- struct net_device *l3_dev = r->dev;
- struct mlxsw_sp_fid *f = r->f;
- u16 rif = r->rif;
-
- mlxsw_sp_router_rif_gone_sync(mlxsw_sp, r);
-
- mlxsw_sp->rifs[rif] = NULL;
- f->r = NULL;
-
- kfree(r);
-
- mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false);
-
- mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false);
-
- mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false);
-
- netdev_dbg(l3_dev, "RIF=%d destroyed\n", rif);
-}
-
-static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev,
- struct net_device *br_dev,
- unsigned long event)
-{
- struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev);
- struct mlxsw_sp_fid *f;
-
- /* FID can either be an actual FID if the L3 device is the
- * VLAN-aware bridge or a VLAN device on top. Otherwise, the
- * L3 device is a VLAN-unaware bridge and we get a vFID.
- */
- f = mlxsw_sp_bridge_fid_get(mlxsw_sp, l3_dev);
- if (WARN_ON(!f))
- return -EINVAL;
-
- switch (event) {
- case NETDEV_UP:
- return mlxsw_sp_rif_bridge_create(mlxsw_sp, l3_dev, f);
- case NETDEV_DOWN:
- mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r);
- break;
- }
-
- return 0;
-}
-
-static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev,
- unsigned long event)
-{
- struct net_device *real_dev = vlan_dev_real_dev(vlan_dev);
- struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(vlan_dev);
- u16 vid = vlan_dev_vlan_id(vlan_dev);
-
- if (mlxsw_sp_port_dev_check(real_dev))
- return mlxsw_sp_inetaddr_vport_event(vlan_dev, real_dev, event,
- vid);
- else if (netif_is_lag_master(real_dev))
- return __mlxsw_sp_inetaddr_lag_event(vlan_dev, real_dev, event,
- vid);
- else if (netif_is_bridge_master(real_dev) &&
- mlxsw_sp->master_bridge.dev == real_dev)
- return mlxsw_sp_inetaddr_bridge_event(vlan_dev, real_dev,
- event);
-
- return 0;
-}
-
-static int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
- unsigned long event, void *ptr)
-{
- struct in_ifaddr *ifa = (struct in_ifaddr *) ptr;
- struct net_device *dev = ifa->ifa_dev->dev;
- struct mlxsw_sp *mlxsw_sp;
- struct mlxsw_sp_rif *r;
- int err = 0;
-
- mlxsw_sp = mlxsw_sp_lower_get(dev);
- if (!mlxsw_sp)
- goto out;
-
- r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
- if (!mlxsw_sp_rif_should_config(r, event))
- goto out;
-
- if (mlxsw_sp_port_dev_check(dev))
- err = mlxsw_sp_inetaddr_port_event(dev, event);
- else if (netif_is_lag_master(dev))
- err = mlxsw_sp_inetaddr_lag_event(dev, event);
- else if (netif_is_bridge_master(dev))
- err = mlxsw_sp_inetaddr_bridge_event(dev, dev, event);
- else if (is_vlan_dev(dev))
- err = mlxsw_sp_inetaddr_vlan_event(dev, event);
-
-out:
- return notifier_from_errno(err);
-}
-
-static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif,
- const char *mac, int mtu)
-{
- char ritr_pl[MLXSW_REG_RITR_LEN];
- int err;
-
- mlxsw_reg_ritr_rif_pack(ritr_pl, rif);
- err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
- if (err)
- return err;
-
- mlxsw_reg_ritr_mtu_set(ritr_pl, mtu);
- mlxsw_reg_ritr_if_mac_memcpy_to(ritr_pl, mac);
- mlxsw_reg_ritr_op_set(ritr_pl, MLXSW_REG_RITR_RIF_CREATE);
- return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
-}
-
-static int mlxsw_sp_netdevice_router_port_event(struct net_device *dev)
-{
- struct mlxsw_sp *mlxsw_sp;
- struct mlxsw_sp_rif *r;
- int err;
-
- mlxsw_sp = mlxsw_sp_lower_get(dev);
- if (!mlxsw_sp)
- return 0;
-
- r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
- if (!r)
- return 0;
-
- err = mlxsw_sp_rif_fdb_op(mlxsw_sp, r->addr, r->f->fid, false);
- if (err)
- return err;
-
- err = mlxsw_sp_rif_edit(mlxsw_sp, r->rif, dev->dev_addr, dev->mtu);
- if (err)
- goto err_rif_edit;
-
- err = mlxsw_sp_rif_fdb_op(mlxsw_sp, dev->dev_addr, r->f->fid, true);
- if (err)
- goto err_rif_fdb_op;
-
- ether_addr_copy(r->addr, dev->dev_addr);
- r->mtu = dev->mtu;
-
- netdev_dbg(dev, "Updated RIF=%d\n", r->rif);
-
- return 0;
-
-err_rif_fdb_op:
- mlxsw_sp_rif_edit(mlxsw_sp, r->rif, r->addr, r->mtu);
-err_rif_edit:
- mlxsw_sp_rif_fdb_op(mlxsw_sp, r->addr, r->f->fid, true);
- return err;
-}
-
static bool mlxsw_sp_lag_port_fid_member(struct mlxsw_sp_port *lag_port,
u16 fid)
{
@@ -4220,7 +3809,7 @@ static int mlxsw_sp_port_lag_index_get(struct mlxsw_sp *mlxsw_sp,
static void
mlxsw_sp_port_pvid_vport_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
- u16 lag_id)
+ struct net_device *lag_dev, u16 lag_id)
{
struct mlxsw_sp_port *mlxsw_sp_vport;
struct mlxsw_sp_fid *f;
@@ -4238,6 +3827,7 @@ mlxsw_sp_port_pvid_vport_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
mlxsw_sp_vport->lag_id = lag_id;
mlxsw_sp_vport->lagged = 1;
+ mlxsw_sp_vport->dev = lag_dev;
}
static void
@@ -4254,6 +3844,7 @@ mlxsw_sp_port_pvid_vport_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port)
if (f)
f->leave(mlxsw_sp_vport);
+ mlxsw_sp_vport->dev = mlxsw_sp_port->dev;
mlxsw_sp_vport->lagged = 0;
}
@@ -4293,7 +3884,7 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
mlxsw_sp_port->lagged = 1;
lag->ref_count++;
- mlxsw_sp_port_pvid_vport_lag_join(mlxsw_sp_port, lag_id);
+ mlxsw_sp_port_pvid_vport_lag_join(mlxsw_sp_port, lag_dev, lag_id);
return 0;
@@ -4421,7 +4012,8 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
upper_dev = info->upper_dev;
if (!is_vlan_dev(upper_dev) &&
!netif_is_lag_master(upper_dev) &&
- !netif_is_bridge_master(upper_dev))
+ !netif_is_bridge_master(upper_dev) &&
+ !netif_is_l3_master(upper_dev))
return -EINVAL;
if (!info->linking)
break;
@@ -4461,6 +4053,11 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
else
mlxsw_sp_port_lag_leave(mlxsw_sp_port,
upper_dev);
+ } else if (netif_is_l3_master(upper_dev)) {
+ if (info->linking)
+ err = mlxsw_sp_port_vrf_join(mlxsw_sp_port);
+ else
+ mlxsw_sp_port_vrf_leave(mlxsw_sp_port);
} else {
err = -EINVAL;
WARN_ON(1);
@@ -4552,8 +4149,8 @@ static void mlxsw_sp_master_bridge_vlan_unlink(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fid *f;
f = mlxsw_sp_fid_find(mlxsw_sp, fid);
- if (f && f->r)
- mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r);
+ if (f && f->rif)
+ mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif);
if (f && --f->ref_count == 0)
mlxsw_sp_fid_destroy(mlxsw_sp, f);
}
@@ -4564,33 +4161,46 @@ static int mlxsw_sp_netdevice_bridge_event(struct net_device *br_dev,
struct netdev_notifier_changeupper_info *info;
struct net_device *upper_dev;
struct mlxsw_sp *mlxsw_sp;
- int err;
+ int err = 0;
mlxsw_sp = mlxsw_sp_lower_get(br_dev);
if (!mlxsw_sp)
return 0;
- if (br_dev != mlxsw_sp->master_bridge.dev)
- return 0;
info = ptr;
switch (event) {
+ case NETDEV_PRECHANGEUPPER:
+ upper_dev = info->upper_dev;
+ if (!is_vlan_dev(upper_dev) && !netif_is_l3_master(upper_dev))
+ return -EINVAL;
+ if (is_vlan_dev(upper_dev) &&
+ br_dev != mlxsw_sp->master_bridge.dev)
+ return -EINVAL;
+ break;
case NETDEV_CHANGEUPPER:
upper_dev = info->upper_dev;
- if (!is_vlan_dev(upper_dev))
- break;
- if (info->linking) {
- err = mlxsw_sp_master_bridge_vlan_link(mlxsw_sp,
- upper_dev);
- if (err)
- return err;
+ if (is_vlan_dev(upper_dev)) {
+ if (info->linking)
+ err = mlxsw_sp_master_bridge_vlan_link(mlxsw_sp,
+ upper_dev);
+ else
+ mlxsw_sp_master_bridge_vlan_unlink(mlxsw_sp,
+ upper_dev);
+ } else if (netif_is_l3_master(upper_dev)) {
+ if (info->linking)
+ err = mlxsw_sp_bridge_vrf_join(mlxsw_sp,
+ br_dev);
+ else
+ mlxsw_sp_bridge_vrf_leave(mlxsw_sp, br_dev);
} else {
- mlxsw_sp_master_bridge_vlan_unlink(mlxsw_sp, upper_dev);
+ err = -EINVAL;
+ WARN_ON(1);
}
break;
}
- return 0;
+ return err;
}
static u16 mlxsw_sp_avail_vfid_get(const struct mlxsw_sp *mlxsw_sp)
@@ -4657,8 +4267,8 @@ static void mlxsw_sp_vfid_destroy(struct mlxsw_sp *mlxsw_sp,
clear_bit(vfid, mlxsw_sp->vfids.mapped);
list_del(&f->list);
- if (f->r)
- mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r);
+ if (f->rif)
+ mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif);
kfree(f);
@@ -4810,33 +4420,43 @@ static int mlxsw_sp_netdevice_vport_event(struct net_device *dev,
int err = 0;
mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid);
+ if (!mlxsw_sp_vport)
+ return 0;
switch (event) {
case NETDEV_PRECHANGEUPPER:
upper_dev = info->upper_dev;
- if (!netif_is_bridge_master(upper_dev))
+ if (!netif_is_bridge_master(upper_dev) &&
+ !netif_is_l3_master(upper_dev))
return -EINVAL;
if (!info->linking)
break;
/* We can't have multiple VLAN interfaces configured on
* the same port and being members in the same bridge.
*/
- if (!mlxsw_sp_port_master_bridge_check(mlxsw_sp_port,
+ if (netif_is_bridge_master(upper_dev) &&
+ !mlxsw_sp_port_master_bridge_check(mlxsw_sp_port,
upper_dev))
return -EINVAL;
break;
case NETDEV_CHANGEUPPER:
upper_dev = info->upper_dev;
- if (info->linking) {
- if (WARN_ON(!mlxsw_sp_vport))
- return -EINVAL;
- err = mlxsw_sp_vport_bridge_join(mlxsw_sp_vport,
- upper_dev);
+ if (netif_is_bridge_master(upper_dev)) {
+ if (info->linking)
+ err = mlxsw_sp_vport_bridge_join(mlxsw_sp_vport,
+ upper_dev);
+ else
+ mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport);
+ } else if (netif_is_l3_master(upper_dev)) {
+ if (info->linking)
+ err = mlxsw_sp_vport_vrf_join(mlxsw_sp_vport);
+ else
+ mlxsw_sp_vport_vrf_leave(mlxsw_sp_vport);
} else {
- if (!mlxsw_sp_vport)
- return 0;
- mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport);
+ err = -EINVAL;
+ WARN_ON(1);
}
+ break;
}
return err;
@@ -4862,6 +4482,47 @@ static int mlxsw_sp_netdevice_lag_vport_event(struct net_device *lag_dev,
return 0;
}
+static int mlxsw_sp_netdevice_bridge_vlan_event(struct net_device *vlan_dev,
+ unsigned long event, void *ptr)
+{
+ struct netdev_notifier_changeupper_info *info;
+ struct mlxsw_sp *mlxsw_sp;
+ int err = 0;
+
+ mlxsw_sp = mlxsw_sp_lower_get(vlan_dev);
+ if (!mlxsw_sp)
+ return 0;
+
+ info = ptr;
+
+ switch (event) {
+ case NETDEV_PRECHANGEUPPER:
+ /* VLAN devices are only allowed on top of the
+ * VLAN-aware bridge.
+ */
+ if (WARN_ON(vlan_dev_real_dev(vlan_dev) !=
+ mlxsw_sp->master_bridge.dev))
+ return -EINVAL;
+ if (!netif_is_l3_master(info->upper_dev))
+ return -EINVAL;
+ break;
+ case NETDEV_CHANGEUPPER:
+ if (netif_is_l3_master(info->upper_dev)) {
+ if (info->linking)
+ err = mlxsw_sp_bridge_vrf_join(mlxsw_sp,
+ vlan_dev);
+ else
+ mlxsw_sp_bridge_vrf_leave(mlxsw_sp, vlan_dev);
+ } else {
+ err = -EINVAL;
+ WARN_ON(1);
+ }
+ break;
+ }
+
+ return err;
+}
+
static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev,
unsigned long event, void *ptr)
{
@@ -4874,6 +4535,9 @@ static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev,
else if (netif_is_lag_master(real_dev))
return mlxsw_sp_netdevice_lag_vport_event(real_dev, event, ptr,
vid);
+ else if (netif_is_bridge_master(real_dev))
+ return mlxsw_sp_netdevice_bridge_vlan_event(vlan_dev, event,
+ ptr);
return 0;
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 13ec85e..c245e4c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -58,40 +58,18 @@
#define MLXSW_SP_VFID_MAX 1024 /* Bridged VLAN interfaces */
#define MLXSW_SP_RFID_BASE 15360
-#define MLXSW_SP_INVALID_RIF 0xffff
#define MLXSW_SP_MID_MAX 7000
#define MLXSW_SP_PORTS_PER_CLUSTER_MAX 4
-#define MLXSW_SP_LPM_TREE_MIN 2 /* trees 0 and 1 are reserved */
-#define MLXSW_SP_LPM_TREE_MAX 22
-#define MLXSW_SP_LPM_TREE_COUNT (MLXSW_SP_LPM_TREE_MAX - MLXSW_SP_LPM_TREE_MIN)
-
#define MLXSW_SP_PORT_BASE_SPEED 25000 /* Mb/s */
-#define MLXSW_SP_BYTES_PER_CELL 96
-
-#define MLXSW_SP_BYTES_TO_CELLS(b) DIV_ROUND_UP(b, MLXSW_SP_BYTES_PER_CELL)
-#define MLXSW_SP_CELLS_TO_BYTES(c) (c * MLXSW_SP_BYTES_PER_CELL)
-
#define MLXSW_SP_KVD_LINEAR_SIZE 65536 /* entries */
#define MLXSW_SP_KVD_GRANULARITY 128
-/* Maximum delay buffer needed in case of PAUSE frames, in cells.
- * Assumes 100m cable and maximum MTU.
- */
-#define MLXSW_SP_PAUSE_DELAY 612
-
-#define MLXSW_SP_CELL_FACTOR 2 /* 2 * cell_size / (IPG + cell_size + 1) */
-
-static inline u16 mlxsw_sp_pfc_delay_get(int mtu, u16 delay)
-{
- delay = MLXSW_SP_BYTES_TO_CELLS(DIV_ROUND_UP(delay, BITS_PER_BYTE));
- return MLXSW_SP_CELL_FACTOR * delay + MLXSW_SP_BYTES_TO_CELLS(mtu);
-}
-
struct mlxsw_sp_port;
+struct mlxsw_sp_rif;
struct mlxsw_sp_upper {
struct net_device *dev;
@@ -103,21 +81,10 @@ struct mlxsw_sp_fid {
struct list_head list;
unsigned int ref_count;
struct net_device *dev;
- struct mlxsw_sp_rif *r;
+ struct mlxsw_sp_rif *rif;
u16 fid;
};
-struct mlxsw_sp_rif {
- struct list_head nexthop_list;
- struct list_head neigh_list;
- struct net_device *dev;
- unsigned int ref_count;
- struct mlxsw_sp_fid *f;
- unsigned char addr[ETH_ALEN];
- int mtu;
- u16 rif;
-};
-
struct mlxsw_sp_mid {
struct list_head list;
unsigned char addr[ETH_ALEN];
@@ -141,16 +108,6 @@ static inline bool mlxsw_sp_fid_is_vfid(u16 fid)
return fid >= MLXSW_SP_VFID_BASE && fid < MLXSW_SP_RFID_BASE;
}
-static inline bool mlxsw_sp_fid_is_rfid(u16 fid)
-{
- return fid >= MLXSW_SP_RFID_BASE;
-}
-
-static inline u16 mlxsw_sp_rif_sp_to_fid(u16 rif)
-{
- return MLXSW_SP_RFID_BASE + rif;
-}
-
struct mlxsw_sp_sb_pr {
enum mlxsw_reg_sbpr_mode mode;
u32 size;
@@ -177,12 +134,15 @@ struct mlxsw_sp_sb_pm {
#define MLXSW_SP_SB_POOL_COUNT 4
#define MLXSW_SP_SB_TC_COUNT 8
+struct mlxsw_sp_sb_port {
+ struct mlxsw_sp_sb_cm cms[2][MLXSW_SP_SB_TC_COUNT];
+ struct mlxsw_sp_sb_pm pms[2][MLXSW_SP_SB_POOL_COUNT];
+};
+
struct mlxsw_sp_sb {
struct mlxsw_sp_sb_pr prs[2][MLXSW_SP_SB_POOL_COUNT];
- struct {
- struct mlxsw_sp_sb_cm cms[2][MLXSW_SP_SB_TC_COUNT];
- struct mlxsw_sp_sb_pm pms[2][MLXSW_SP_SB_POOL_COUNT];
- } ports[MLXSW_PORT_MAX_PORTS];
+ struct mlxsw_sp_sb_port *ports;
+ u32 cell_size;
};
#define MLXSW_SP_PREFIX_COUNT (sizeof(struct in6_addr) * BITS_PER_BYTE)
@@ -207,11 +167,9 @@ struct mlxsw_sp_fib;
struct mlxsw_sp_vr {
u16 id; /* virtual router ID */
- bool used;
- enum mlxsw_sp_l3proto proto;
u32 tb_id; /* kernel fib table id */
- struct mlxsw_sp_lpm_tree *lpm_tree;
- struct mlxsw_sp_fib *fib;
+ unsigned int rif_count;
+ struct mlxsw_sp_fib *fib4;
};
enum mlxsw_sp_span_type {
@@ -253,12 +211,15 @@ struct mlxsw_sp_port_mall_tc_entry {
};
struct mlxsw_sp_router {
- struct mlxsw_sp_lpm_tree lpm_trees[MLXSW_SP_LPM_TREE_COUNT];
struct mlxsw_sp_vr *vrs;
struct rhashtable neigh_ht;
struct rhashtable nexthop_group_ht;
struct rhashtable nexthop_ht;
struct {
+ struct mlxsw_sp_lpm_tree *trees;
+ unsigned int tree_count;
+ } lpm;
+ struct {
struct delayed_work dw;
unsigned long interval; /* ms */
} neighs_update;
@@ -269,6 +230,7 @@ struct mlxsw_sp_router {
};
struct mlxsw_sp_acl;
+struct mlxsw_sp_counter_pool;
struct mlxsw_sp {
struct {
@@ -296,7 +258,7 @@ struct mlxsw_sp {
u32 ageing_time;
struct mlxsw_sp_upper master_bridge;
struct mlxsw_sp_upper *lags;
- u8 port_to_module[MLXSW_PORT_MAX_PORTS];
+ u8 *port_to_module;
struct mlxsw_sp_sb sb;
struct mlxsw_sp_router router;
struct mlxsw_sp_acl *acl;
@@ -304,6 +266,7 @@ struct mlxsw_sp {
DECLARE_BITMAP(usage, MLXSW_SP_KVD_LINEAR_SIZE);
} kvdl;
+ struct mlxsw_sp_counter_pool *counter_pool;
struct {
struct mlxsw_sp_span_entry *entries;
int entries_count;
@@ -317,6 +280,18 @@ mlxsw_sp_lag_get(struct mlxsw_sp *mlxsw_sp, u16 lag_id)
return &mlxsw_sp->lags[lag_id];
}
+static inline u32 mlxsw_sp_cells_bytes(const struct mlxsw_sp *mlxsw_sp,
+ u32 cells)
+{
+ return mlxsw_sp->sb.cell_size * cells;
+}
+
+static inline u32 mlxsw_sp_bytes_cells(const struct mlxsw_sp *mlxsw_sp,
+ u32 bytes)
+{
+ return DIV_ROUND_UP(bytes, mlxsw_sp->sb.cell_size);
+}
+
struct mlxsw_sp_port_pcpu_stats {
u64 rx_packets;
u64 rx_bytes;
@@ -386,6 +361,7 @@ struct mlxsw_sp_port {
};
bool mlxsw_sp_port_dev_check(const struct net_device *dev);
+struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev);
struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev);
void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port);
@@ -497,19 +473,6 @@ mlxsw_sp_vfid_find(const struct mlxsw_sp *mlxsw_sp,
return NULL;
}
-static inline struct mlxsw_sp_rif *
-mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
- const struct net_device *dev)
-{
- int i;
-
- for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++)
- if (mlxsw_sp->rifs[i] && mlxsw_sp->rifs[i]->dev == dev)
- return mlxsw_sp->rifs[i];
-
- return NULL;
-}
-
enum mlxsw_sp_flood_table {
MLXSW_SP_FLOOD_TABLE_UC,
MLXSW_SP_FLOOD_TABLE_BC,
@@ -570,8 +533,6 @@ int mlxsw_sp_rif_fdb_op(struct mlxsw_sp *mlxsw_sp, const char *mac, u16 fid,
bool adding);
struct mlxsw_sp_fid *mlxsw_sp_fid_create(struct mlxsw_sp *mlxsw_sp, u16 fid);
void mlxsw_sp_fid_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *f);
-void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_rif *r);
int mlxsw_sp_port_ets_set(struct mlxsw_sp_port *mlxsw_sp_port,
enum mlxsw_reg_qeec_hr hr, u8 index, u8 next_index,
bool dwrr, u8 dwrr_weight);
@@ -608,10 +569,22 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp);
void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp);
int mlxsw_sp_router_netevent_event(struct notifier_block *unused,
unsigned long event, void *ptr);
-void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_rif *r);
+int mlxsw_sp_netdevice_router_port_event(struct net_device *dev);
+int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
+ unsigned long event, void *ptr);
+void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_rif *rif);
+int mlxsw_sp_vport_vrf_join(struct mlxsw_sp_port *mlxsw_sp_vport);
+void mlxsw_sp_vport_vrf_leave(struct mlxsw_sp_port *mlxsw_sp_vport);
+int mlxsw_sp_port_vrf_join(struct mlxsw_sp_port *mlxsw_sp_port);
+void mlxsw_sp_port_vrf_leave(struct mlxsw_sp_port *mlxsw_sp_port);
+int mlxsw_sp_bridge_vrf_join(struct mlxsw_sp *mlxsw_sp,
+ struct net_device *l3_dev);
+void mlxsw_sp_bridge_vrf_leave(struct mlxsw_sp *mlxsw_sp,
+ struct net_device *l3_dev);
-int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count);
+int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count,
+ u32 *p_entry_index);
void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index);
struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl);
@@ -620,6 +593,8 @@ struct mlxsw_sp_acl_rule_info {
unsigned int priority;
struct mlxsw_afk_element_values values;
struct mlxsw_afa_block *act_block;
+ unsigned int counter_index;
+ bool counter_valid;
};
enum mlxsw_sp_acl_profile {
@@ -639,6 +614,8 @@ struct mlxsw_sp_acl_profile_ops {
void *ruleset_priv, void *rule_priv,
struct mlxsw_sp_acl_rule_info *rulei);
void (*rule_del)(struct mlxsw_sp *mlxsw_sp, void *rule_priv);
+ int (*rule_activity_get)(struct mlxsw_sp *mlxsw_sp, void *rule_priv,
+ bool *activity);
};
struct mlxsw_sp_acl_ops {
@@ -679,6 +656,11 @@ int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei);
int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_acl_rule_info *rulei,
struct net_device *out_dev);
+int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_rule_info *rulei,
+ u32 action, u16 vid, u16 proto, u8 prio);
+int mlxsw_sp_acl_rulei_act_count(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_rule_info *rulei);
struct mlxsw_sp_acl_rule;
@@ -698,6 +680,9 @@ mlxsw_sp_acl_rule_lookup(struct mlxsw_sp *mlxsw_sp,
unsigned long cookie);
struct mlxsw_sp_acl_rule_info *
mlxsw_sp_acl_rule_rulei(struct mlxsw_sp_acl_rule *rule);
+int mlxsw_sp_acl_rule_get_stats(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_rule *rule,
+ u64 *packets, u64 *bytes, u64 *last_use);
int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp);
void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp);
@@ -708,5 +693,14 @@ int mlxsw_sp_flower_replace(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress,
__be16 protocol, struct tc_cls_flower_offload *f);
void mlxsw_sp_flower_destroy(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress,
struct tc_cls_flower_offload *f);
+int mlxsw_sp_flower_stats(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress,
+ struct tc_cls_flower_offload *f);
+int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp,
+ unsigned int counter_index, u64 *packets,
+ u64 *bytes);
+int mlxsw_sp_flow_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+ unsigned int *p_counter_index);
+void mlxsw_sp_flow_counter_free(struct mlxsw_sp *mlxsw_sp,
+ unsigned int counter_index);
#endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 8a18b3a..d3b791f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -39,6 +39,7 @@
#include <linux/string.h>
#include <linux/rhashtable.h>
#include <linux/netdevice.h>
+#include <net/tc_act/tc_vlan.h>
#include "reg.h"
#include "core.h"
@@ -49,10 +50,17 @@
#include "spectrum_acl_flex_keys.h"
struct mlxsw_sp_acl {
+ struct mlxsw_sp *mlxsw_sp;
struct mlxsw_afk *afk;
struct mlxsw_afa *afa;
const struct mlxsw_sp_acl_ops *ops;
struct rhashtable ruleset_ht;
+ struct list_head rules;
+ struct {
+ struct delayed_work dw;
+ unsigned long interval; /* ms */
+#define MLXSW_SP_ACL_RULE_ACTIVITY_UPDATE_PERIOD_MS 1000
+ } rule_activity_update;
unsigned long priv[0];
/* priv has to be always the last item */
};
@@ -79,9 +87,13 @@ struct mlxsw_sp_acl_ruleset {
struct mlxsw_sp_acl_rule {
struct rhash_head ht_node; /* Member of rule HT */
+ struct list_head list;
unsigned long cookie; /* HT key */
struct mlxsw_sp_acl_ruleset *ruleset;
struct mlxsw_sp_acl_rule_info *rulei;
+ u64 last_used;
+ u64 last_packets;
+ u64 last_bytes;
unsigned long priv[0];
/* priv has to be always the last item */
};
@@ -237,6 +249,27 @@ void mlxsw_sp_acl_ruleset_put(struct mlxsw_sp *mlxsw_sp,
mlxsw_sp_acl_ruleset_ref_dec(mlxsw_sp, ruleset);
}
+static int
+mlxsw_sp_acl_rulei_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_rule_info *rulei)
+{
+ int err;
+
+ err = mlxsw_sp_flow_counter_alloc(mlxsw_sp, &rulei->counter_index);
+ if (err)
+ return err;
+ rulei->counter_valid = true;
+ return 0;
+}
+
+static void
+mlxsw_sp_acl_rulei_counter_free(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_rule_info *rulei)
+{
+ rulei->counter_valid = false;
+ mlxsw_sp_flow_counter_free(mlxsw_sp, rulei->counter_index);
+}
+
struct mlxsw_sp_acl_rule_info *
mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl)
{
@@ -335,6 +368,41 @@ int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp,
local_port, in_port);
}
+int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_rule_info *rulei,
+ u32 action, u16 vid, u16 proto, u8 prio)
+{
+ u8 ethertype;
+
+ if (action == TCA_VLAN_ACT_MODIFY) {
+ switch (proto) {
+ case ETH_P_8021Q:
+ ethertype = 0;
+ break;
+ case ETH_P_8021AD:
+ ethertype = 1;
+ break;
+ default:
+ dev_err(mlxsw_sp->bus_info->dev, "Unsupported VLAN protocol %#04x\n",
+ proto);
+ return -EINVAL;
+ }
+
+ return mlxsw_afa_block_append_vlan_modify(rulei->act_block,
+ vid, prio, ethertype);
+ } else {
+ dev_err(mlxsw_sp->bus_info->dev, "Unsupported VLAN action\n");
+ return -EINVAL;
+ }
+}
+
+int mlxsw_sp_acl_rulei_act_count(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_rule_info *rulei)
+{
+ return mlxsw_afa_block_append_counter(rulei->act_block,
+ rulei->counter_index);
+}
+
struct mlxsw_sp_acl_rule *
mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_acl_ruleset *ruleset,
@@ -358,8 +426,14 @@ mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp,
err = PTR_ERR(rule->rulei);
goto err_rulei_create;
}
+
+ err = mlxsw_sp_acl_rulei_counter_alloc(mlxsw_sp, rule->rulei);
+ if (err)
+ goto err_counter_alloc;
return rule;
+err_counter_alloc:
+ mlxsw_sp_acl_rulei_destroy(rule->rulei);
err_rulei_create:
kfree(rule);
err_alloc:
@@ -372,6 +446,7 @@ void mlxsw_sp_acl_rule_destroy(struct mlxsw_sp *mlxsw_sp,
{
struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset;
+ mlxsw_sp_acl_rulei_counter_free(mlxsw_sp, rule->rulei);
mlxsw_sp_acl_rulei_destroy(rule->rulei);
kfree(rule);
mlxsw_sp_acl_ruleset_ref_dec(mlxsw_sp, ruleset);
@@ -393,6 +468,7 @@ int mlxsw_sp_acl_rule_add(struct mlxsw_sp *mlxsw_sp,
if (err)
goto err_rhashtable_insert;
+ list_add_tail(&rule->list, &mlxsw_sp->acl->rules);
return 0;
err_rhashtable_insert:
@@ -406,6 +482,7 @@ void mlxsw_sp_acl_rule_del(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset;
const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops;
+ list_del(&rule->list);
rhashtable_remove_fast(&ruleset->rule_ht, &rule->ht_node,
mlxsw_sp_acl_rule_ht_params);
ops->rule_del(mlxsw_sp, rule->priv);
@@ -426,6 +503,90 @@ mlxsw_sp_acl_rule_rulei(struct mlxsw_sp_acl_rule *rule)
return rule->rulei;
}
+static int mlxsw_sp_acl_rule_activity_update(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_rule *rule)
+{
+ struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset;
+ const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops;
+ bool active;
+ int err;
+
+ err = ops->rule_activity_get(mlxsw_sp, rule->priv, &active);
+ if (err)
+ return err;
+ if (active)
+ rule->last_used = jiffies;
+ return 0;
+}
+
+static int mlxsw_sp_acl_rules_activity_update(struct mlxsw_sp_acl *acl)
+{
+ struct mlxsw_sp_acl_rule *rule;
+ int err;
+
+ /* Protect internal structures from changes */
+ rtnl_lock();
+ list_for_each_entry(rule, &acl->rules, list) {
+ err = mlxsw_sp_acl_rule_activity_update(acl->mlxsw_sp,
+ rule);
+ if (err)
+ goto err_rule_update;
+ }
+ rtnl_unlock();
+ return 0;
+
+err_rule_update:
+ rtnl_unlock();
+ return err;
+}
+
+static void mlxsw_sp_acl_rule_activity_work_schedule(struct mlxsw_sp_acl *acl)
+{
+ unsigned long interval = acl->rule_activity_update.interval;
+
+ mlxsw_core_schedule_dw(&acl->rule_activity_update.dw,
+ msecs_to_jiffies(interval));
+}
+
+static void mlxsw_sp_acl_rul_activity_update_work(struct work_struct *work)
+{
+ struct mlxsw_sp_acl *acl = container_of(work, struct mlxsw_sp_acl,
+ rule_activity_update.dw.work);
+ int err;
+
+ err = mlxsw_sp_acl_rules_activity_update(acl);
+ if (err)
+ dev_err(acl->mlxsw_sp->bus_info->dev, "Could not update acl activity");
+
+ mlxsw_sp_acl_rule_activity_work_schedule(acl);
+}
+
+int mlxsw_sp_acl_rule_get_stats(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_rule *rule,
+ u64 *packets, u64 *bytes, u64 *last_use)
+
+{
+ struct mlxsw_sp_acl_rule_info *rulei;
+ u64 current_packets;
+ u64 current_bytes;
+ int err;
+
+ rulei = mlxsw_sp_acl_rule_rulei(rule);
+ err = mlxsw_sp_flow_counter_get(mlxsw_sp, rulei->counter_index,
+ ¤t_packets, ¤t_bytes);
+ if (err)
+ return err;
+
+ *packets = current_packets - rule->last_packets;
+ *bytes = current_bytes - rule->last_bytes;
+ *last_use = rule->last_used;
+
+ rule->last_bytes = current_bytes;
+ rule->last_packets = current_packets;
+
+ return 0;
+}
+
#define MLXSW_SP_KDVL_ACT_EXT_SIZE 1
static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
@@ -434,7 +595,6 @@ static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
struct mlxsw_sp *mlxsw_sp = priv;
char pefa_pl[MLXSW_REG_PEFA_LEN];
u32 kvdl_index;
- int ret;
int err;
/* The first action set of a TCAM entry is stored directly in TCAM,
@@ -443,10 +603,10 @@ static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
if (is_first)
return 0;
- ret = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KDVL_ACT_EXT_SIZE);
- if (ret < 0)
- return ret;
- kvdl_index = ret;
+ err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KDVL_ACT_EXT_SIZE,
+ &kvdl_index);
+ if (err)
+ return err;
mlxsw_reg_pefa_pack(pefa_pl, kvdl_index, enc_actions);
err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pefa), pefa_pl);
if (err)
@@ -475,13 +635,11 @@ static int mlxsw_sp_act_kvdl_fwd_entry_add(void *priv, u32 *p_kvdl_index,
struct mlxsw_sp *mlxsw_sp = priv;
char ppbs_pl[MLXSW_REG_PPBS_LEN];
u32 kvdl_index;
- int ret;
int err;
- ret = mlxsw_sp_kvdl_alloc(mlxsw_sp, 1);
- if (ret < 0)
- return ret;
- kvdl_index = ret;
+ err = mlxsw_sp_kvdl_alloc(mlxsw_sp, 1, &kvdl_index);
+ if (err)
+ return err;
mlxsw_reg_ppbs_pack(ppbs_pl, kvdl_index, local_port);
err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ppbs), ppbs_pl);
if (err)
@@ -518,7 +676,7 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
if (!acl)
return -ENOMEM;
mlxsw_sp->acl = acl;
-
+ acl->mlxsw_sp = mlxsw_sp;
acl->afk = mlxsw_afk_create(MLXSW_CORE_RES_GET(mlxsw_sp->core,
ACL_FLEX_KEYS),
mlxsw_sp_afk_blocks,
@@ -541,11 +699,18 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
if (err)
goto err_rhashtable_init;
+ INIT_LIST_HEAD(&acl->rules);
err = acl_ops->init(mlxsw_sp, acl->priv);
if (err)
goto err_acl_ops_init;
acl->ops = acl_ops;
+
+ /* Create the delayed work for the rule activity_update */
+ INIT_DELAYED_WORK(&acl->rule_activity_update.dw,
+ mlxsw_sp_acl_rul_activity_update_work);
+ acl->rule_activity_update.interval = MLXSW_SP_ACL_RULE_ACTIVITY_UPDATE_PERIOD_MS;
+ mlxsw_core_schedule_dw(&acl->rule_activity_update.dw, 0);
return 0;
err_acl_ops_init:
@@ -564,7 +729,9 @@ void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp)
struct mlxsw_sp_acl *acl = mlxsw_sp->acl;
const struct mlxsw_sp_acl_ops *acl_ops = acl->ops;
+ cancel_delayed_work_sync(&mlxsw_sp->acl->rule_activity_update.dw);
acl_ops->fini(mlxsw_sp, acl->priv);
+ WARN_ON(!list_empty(&acl->rules));
rhashtable_destroy(&acl->ruleset_ht);
mlxsw_afa_destroy(acl->afa);
mlxsw_afk_destroy(acl->afk);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
index 82b81cf..af7b7ba 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
@@ -39,11 +39,15 @@
static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_dmac[] = {
MLXSW_AFK_ELEMENT_INST_BUF(DMAC, 0x00, 6),
+ MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3),
+ MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12),
MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
};
static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac[] = {
MLXSW_AFK_ELEMENT_INST_BUF(SMAC, 0x00, 6),
+ MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3),
+ MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12),
MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
};
@@ -65,6 +69,8 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_dip[] = {
};
static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_ex[] = {
+ MLXSW_AFK_ELEMENT_INST_U32(VID, 0x00, 0, 12),
+ MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 29, 3),
MLXSW_AFK_ELEMENT_INST_U32(SRC_L4_PORT, 0x08, 0, 16),
MLXSW_AFK_ELEMENT_INST_U32(DST_L4_PORT, 0x0C, 0, 16),
};
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index 7382832..3a24289 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -561,6 +561,24 @@ mlxsw_sp_acl_tcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
}
+static int
+mlxsw_sp_acl_tcam_region_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_tcam_region *region,
+ unsigned int offset,
+ bool *activity)
+{
+ char ptce2_pl[MLXSW_REG_PTCE2_LEN];
+ int err;
+
+ mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_QUERY_CLEAR_ON_READ,
+ region->tcam_region_info, offset);
+ err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
+ if (err)
+ return err;
+ *activity = mlxsw_reg_ptce2_a_get(ptce2_pl);
+ return 0;
+}
+
#define MLXSW_SP_ACL_TCAM_CATCHALL_PRIO (~0U)
static int
@@ -940,6 +958,19 @@ static void mlxsw_sp_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, chunk);
}
+static int
+mlxsw_sp_acl_tcam_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_acl_tcam_entry *entry,
+ bool *activity)
+{
+ struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk;
+ struct mlxsw_sp_acl_tcam_region *region = chunk->region;
+
+ return mlxsw_sp_acl_tcam_region_entry_activity_get(mlxsw_sp, region,
+ entry->parman_item.index,
+ activity);
+}
+
static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = {
MLXSW_AFK_ELEMENT_SRC_SYS_PORT,
MLXSW_AFK_ELEMENT_DMAC,
@@ -950,6 +981,8 @@ static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = {
MLXSW_AFK_ELEMENT_DST_IP4,
MLXSW_AFK_ELEMENT_DST_L4_PORT,
MLXSW_AFK_ELEMENT_SRC_L4_PORT,
+ MLXSW_AFK_ELEMENT_VID,
+ MLXSW_AFK_ELEMENT_PCP,
};
static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv6[] = {
@@ -1046,6 +1079,16 @@ mlxsw_sp_acl_tcam_flower_rule_del(struct mlxsw_sp *mlxsw_sp, void *rule_priv)
mlxsw_sp_acl_tcam_entry_del(mlxsw_sp, &rule->entry);
}
+static int
+mlxsw_sp_acl_tcam_flower_rule_activity_get(struct mlxsw_sp *mlxsw_sp,
+ void *rule_priv, bool *activity)
+{
+ struct mlxsw_sp_acl_tcam_flower_rule *rule = rule_priv;
+
+ return mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp, &rule->entry,
+ activity);
+}
+
static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = {
.ruleset_priv_size = sizeof(struct mlxsw_sp_acl_tcam_flower_ruleset),
.ruleset_add = mlxsw_sp_acl_tcam_flower_ruleset_add,
@@ -1055,6 +1098,7 @@ static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = {
.rule_priv_size = sizeof(struct mlxsw_sp_acl_tcam_flower_rule),
.rule_add = mlxsw_sp_acl_tcam_flower_rule_add,
.rule_del = mlxsw_sp_acl_tcam_flower_rule_del,
+ .rule_activity_get = mlxsw_sp_acl_tcam_flower_rule_activity_get,
};
static const struct mlxsw_sp_acl_profile_ops *
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
index a746826..997189c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
@@ -162,8 +162,8 @@ static int mlxsw_sp_sb_pm_occ_query(struct mlxsw_sp *mlxsw_sp, u8 local_port,
}
static const u16 mlxsw_sp_pbs[] = {
- [0] = 2 * MLXSW_SP_BYTES_TO_CELLS(ETH_FRAME_LEN),
- [9] = 2 * MLXSW_SP_BYTES_TO_CELLS(MLXSW_PORT_MAX_MTU),
+ [0] = 2 * ETH_FRAME_LEN,
+ [9] = 2 * MLXSW_PORT_MAX_MTU,
};
#define MLXSW_SP_PBS_LEN ARRAY_SIZE(mlxsw_sp_pbs)
@@ -171,20 +171,22 @@ static const u16 mlxsw_sp_pbs[] = {
static int mlxsw_sp_port_pb_init(struct mlxsw_sp_port *mlxsw_sp_port)
{
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
char pbmc_pl[MLXSW_REG_PBMC_LEN];
int i;
mlxsw_reg_pbmc_pack(pbmc_pl, mlxsw_sp_port->local_port,
0xffff, 0xffff / 2);
for (i = 0; i < MLXSW_SP_PBS_LEN; i++) {
+ u16 size = mlxsw_sp_bytes_cells(mlxsw_sp, mlxsw_sp_pbs[i]);
+
if (i == MLXSW_SP_PB_UNUSED)
continue;
- mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, i, mlxsw_sp_pbs[i]);
+ mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, i, size);
}
mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl,
MLXSW_REG_PBMC_PORT_SHARED_BUF_IDX, 0);
- return mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core,
- MLXSW_REG(pbmc), pbmc_pl);
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl);
}
static int mlxsw_sp_port_pb_prio_init(struct mlxsw_sp_port *mlxsw_sp_port)
@@ -209,11 +211,25 @@ static int mlxsw_sp_port_headroom_init(struct mlxsw_sp_port *mlxsw_sp_port)
return mlxsw_sp_port_pb_prio_init(mlxsw_sp_port);
}
-#define MLXSW_SP_SB_PR_INGRESS_SIZE \
- (15000000 - (2 * 20000 * MLXSW_PORT_MAX_PORTS))
+static int mlxsw_sp_sb_ports_init(struct mlxsw_sp *mlxsw_sp)
+{
+ unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
+
+ mlxsw_sp->sb.ports = kcalloc(max_ports, sizeof(struct mlxsw_sp_sb_port),
+ GFP_KERNEL);
+ if (!mlxsw_sp->sb.ports)
+ return -ENOMEM;
+ return 0;
+}
+
+static void mlxsw_sp_sb_ports_fini(struct mlxsw_sp *mlxsw_sp)
+{
+ kfree(mlxsw_sp->sb.ports);
+}
+
+#define MLXSW_SP_SB_PR_INGRESS_SIZE 12440000
#define MLXSW_SP_SB_PR_INGRESS_MNG_SIZE (200 * 1000)
-#define MLXSW_SP_SB_PR_EGRESS_SIZE \
- (14000000 - (8 * 1500 * MLXSW_PORT_MAX_PORTS))
+#define MLXSW_SP_SB_PR_EGRESS_SIZE 13232000
#define MLXSW_SP_SB_PR(_mode, _size) \
{ \
@@ -223,18 +239,17 @@ static int mlxsw_sp_port_headroom_init(struct mlxsw_sp_port *mlxsw_sp_port)
static const struct mlxsw_sp_sb_pr mlxsw_sp_sb_prs_ingress[] = {
MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC,
- MLXSW_SP_BYTES_TO_CELLS(MLXSW_SP_SB_PR_INGRESS_SIZE)),
+ MLXSW_SP_SB_PR_INGRESS_SIZE),
MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC,
- MLXSW_SP_BYTES_TO_CELLS(MLXSW_SP_SB_PR_INGRESS_MNG_SIZE)),
+ MLXSW_SP_SB_PR_INGRESS_MNG_SIZE),
};
#define MLXSW_SP_SB_PRS_INGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_prs_ingress)
static const struct mlxsw_sp_sb_pr mlxsw_sp_sb_prs_egress[] = {
- MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC,
- MLXSW_SP_BYTES_TO_CELLS(MLXSW_SP_SB_PR_EGRESS_SIZE)),
+ MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, MLXSW_SP_SB_PR_EGRESS_SIZE),
MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
@@ -251,11 +266,9 @@ static int __mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp,
int err;
for (i = 0; i < prs_len; i++) {
- const struct mlxsw_sp_sb_pr *pr;
+ u32 size = mlxsw_sp_bytes_cells(mlxsw_sp, prs[i].size);
- pr = &prs[i];
- err = mlxsw_sp_sb_pr_write(mlxsw_sp, i, dir,
- pr->mode, pr->size);
+ err = mlxsw_sp_sb_pr_write(mlxsw_sp, i, dir, prs[i].mode, size);
if (err)
return err;
}
@@ -284,7 +297,7 @@ static int mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp)
}
static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_ingress[] = {
- MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(10000), 8, 0),
+ MLXSW_SP_SB_CM(10000, 8, 0),
MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
@@ -293,20 +306,20 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_ingress[] = {
MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
MLXSW_SP_SB_CM(0, 0, 0), /* dummy, this PG does not exist */
- MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(20000), 1, 3),
+ MLXSW_SP_SB_CM(20000, 1, 3),
};
#define MLXSW_SP_SB_CMS_INGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_cms_ingress)
static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_egress[] = {
- MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
- MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
- MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
- MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
- MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
- MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
- MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
- MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(1500), 9, 0),
+ MLXSW_SP_SB_CM(1500, 9, 0),
+ MLXSW_SP_SB_CM(1500, 9, 0),
+ MLXSW_SP_SB_CM(1500, 9, 0),
+ MLXSW_SP_SB_CM(1500, 9, 0),
+ MLXSW_SP_SB_CM(1500, 9, 0),
+ MLXSW_SP_SB_CM(1500, 9, 0),
+ MLXSW_SP_SB_CM(1500, 9, 0),
+ MLXSW_SP_SB_CM(1500, 9, 0),
MLXSW_SP_SB_CM(0, 0, 0),
MLXSW_SP_SB_CM(0, 0, 0),
MLXSW_SP_SB_CM(0, 0, 0),
@@ -330,7 +343,7 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp_cpu_port_sb_cms[] = {
MLXSW_SP_CPU_PORT_SB_CM,
MLXSW_SP_CPU_PORT_SB_CM,
MLXSW_SP_CPU_PORT_SB_CM,
- MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(10000), 0, 0),
+ MLXSW_SP_SB_CM(10000, 0, 0),
MLXSW_SP_CPU_PORT_SB_CM,
MLXSW_SP_CPU_PORT_SB_CM,
MLXSW_SP_CPU_PORT_SB_CM,
@@ -370,13 +383,17 @@ static int __mlxsw_sp_sb_cms_init(struct mlxsw_sp *mlxsw_sp, u8 local_port,
for (i = 0; i < cms_len; i++) {
const struct mlxsw_sp_sb_cm *cm;
+ u32 min_buff;
if (i == 8 && dir == MLXSW_REG_SBXX_DIR_INGRESS)
continue; /* PG number 8 does not exist, skip it */
cm = &cms[i];
+ /* All pools are initialized using dynamic thresholds,
+ * therefore 'max_buff' isn't specified in cells.
+ */
+ min_buff = mlxsw_sp_bytes_cells(mlxsw_sp, cm->min_buff);
err = mlxsw_sp_sb_cm_write(mlxsw_sp, local_port, i, dir,
- cm->min_buff, cm->max_buff,
- cm->pool);
+ min_buff, cm->max_buff, cm->pool);
if (err)
return err;
}
@@ -484,21 +501,21 @@ struct mlxsw_sp_sb_mm {
}
static const struct mlxsw_sp_sb_mm mlxsw_sp_sb_mms[] = {
- MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
- MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
- MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
- MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
- MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
- MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
- MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
- MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
- MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
- MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
- MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
- MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
- MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
- MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
- MLXSW_SP_SB_MM(MLXSW_SP_BYTES_TO_CELLS(20000), 0xff, 0),
+ MLXSW_SP_SB_MM(20000, 0xff, 0),
+ MLXSW_SP_SB_MM(20000, 0xff, 0),
+ MLXSW_SP_SB_MM(20000, 0xff, 0),
+ MLXSW_SP_SB_MM(20000, 0xff, 0),
+ MLXSW_SP_SB_MM(20000, 0xff, 0),
+ MLXSW_SP_SB_MM(20000, 0xff, 0),
+ MLXSW_SP_SB_MM(20000, 0xff, 0),
+ MLXSW_SP_SB_MM(20000, 0xff, 0),
+ MLXSW_SP_SB_MM(20000, 0xff, 0),
+ MLXSW_SP_SB_MM(20000, 0xff, 0),
+ MLXSW_SP_SB_MM(20000, 0xff, 0),
+ MLXSW_SP_SB_MM(20000, 0xff, 0),
+ MLXSW_SP_SB_MM(20000, 0xff, 0),
+ MLXSW_SP_SB_MM(20000, 0xff, 0),
+ MLXSW_SP_SB_MM(20000, 0xff, 0),
};
#define MLXSW_SP_SB_MMS_LEN ARRAY_SIZE(mlxsw_sp_sb_mms)
@@ -511,10 +528,15 @@ static int mlxsw_sp_sb_mms_init(struct mlxsw_sp *mlxsw_sp)
for (i = 0; i < MLXSW_SP_SB_MMS_LEN; i++) {
const struct mlxsw_sp_sb_mm *mc;
+ u32 min_buff;
mc = &mlxsw_sp_sb_mms[i];
- mlxsw_reg_sbmm_pack(sbmm_pl, i, mc->min_buff,
- mc->max_buff, mc->pool);
+ /* All pools are initialized using dynamic thresholds,
+ * therefore 'max_buff' isn't specified in cells.
+ */
+ min_buff = mlxsw_sp_bytes_cells(mlxsw_sp, mc->min_buff);
+ mlxsw_reg_sbmm_pack(sbmm_pl, i, min_buff, mc->max_buff,
+ mc->pool);
err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbmm), sbmm_pl);
if (err)
return err;
@@ -522,32 +544,53 @@ static int mlxsw_sp_sb_mms_init(struct mlxsw_sp *mlxsw_sp)
return 0;
}
-#define MLXSW_SP_SB_SIZE (16 * 1024 * 1024)
-
int mlxsw_sp_buffers_init(struct mlxsw_sp *mlxsw_sp)
{
+ u64 sb_size;
int err;
+ if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, CELL_SIZE))
+ return -EIO;
+ mlxsw_sp->sb.cell_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, CELL_SIZE);
+
+ if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_BUFFER_SIZE))
+ return -EIO;
+ sb_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_BUFFER_SIZE);
+
+ err = mlxsw_sp_sb_ports_init(mlxsw_sp);
+ if (err)
+ return err;
err = mlxsw_sp_sb_prs_init(mlxsw_sp);
if (err)
- return err;
+ goto err_sb_prs_init;
err = mlxsw_sp_cpu_port_sb_cms_init(mlxsw_sp);
if (err)
- return err;
+ goto err_sb_cpu_port_sb_cms_init;
err = mlxsw_sp_sb_mms_init(mlxsw_sp);
if (err)
- return err;
- return devlink_sb_register(priv_to_devlink(mlxsw_sp->core), 0,
- MLXSW_SP_SB_SIZE,
- MLXSW_SP_SB_POOL_COUNT,
- MLXSW_SP_SB_POOL_COUNT,
- MLXSW_SP_SB_TC_COUNT,
- MLXSW_SP_SB_TC_COUNT);
+ goto err_sb_mms_init;
+ err = devlink_sb_register(priv_to_devlink(mlxsw_sp->core), 0, sb_size,
+ MLXSW_SP_SB_POOL_COUNT,
+ MLXSW_SP_SB_POOL_COUNT,
+ MLXSW_SP_SB_TC_COUNT,
+ MLXSW_SP_SB_TC_COUNT);
+ if (err)
+ goto err_devlink_sb_register;
+
+ return 0;
+
+err_devlink_sb_register:
+err_sb_mms_init:
+err_sb_cpu_port_sb_cms_init:
+err_sb_prs_init:
+ mlxsw_sp_sb_ports_fini(mlxsw_sp);
+ return err;
}
void mlxsw_sp_buffers_fini(struct mlxsw_sp *mlxsw_sp)
{
devlink_sb_unregister(priv_to_devlink(mlxsw_sp->core), 0);
+ mlxsw_sp_sb_ports_fini(mlxsw_sp);
}
int mlxsw_sp_port_buffers_init(struct mlxsw_sp_port *mlxsw_sp_port)
@@ -596,7 +639,7 @@ int mlxsw_sp_sb_pool_get(struct mlxsw_core *mlxsw_core,
struct mlxsw_sp_sb_pr *pr = mlxsw_sp_sb_pr_get(mlxsw_sp, pool, dir);
pool_info->pool_type = (enum devlink_sb_pool_type) dir;
- pool_info->size = MLXSW_SP_CELLS_TO_BYTES(pr->size);
+ pool_info->size = mlxsw_sp_cells_bytes(mlxsw_sp, pr->size);
pool_info->threshold_type = (enum devlink_sb_threshold_type) pr->mode;
return 0;
}
@@ -606,9 +649,9 @@ int mlxsw_sp_sb_pool_set(struct mlxsw_core *mlxsw_core,
enum devlink_sb_threshold_type threshold_type)
{
struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+ u32 pool_size = mlxsw_sp_bytes_cells(mlxsw_sp, size);
u8 pool = pool_get(pool_index);
enum mlxsw_reg_sbxx_dir dir = dir_get(pool_index);
- u32 pool_size = MLXSW_SP_BYTES_TO_CELLS(size);
enum mlxsw_reg_sbpr_mode mode;
if (size > MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_BUFFER_SIZE))
@@ -627,7 +670,7 @@ static u32 mlxsw_sp_sb_threshold_out(struct mlxsw_sp *mlxsw_sp, u8 pool,
if (pr->mode == MLXSW_REG_SBPR_MODE_DYNAMIC)
return max_buff - MLXSW_SP_SB_THRESHOLD_TO_ALPHA_OFFSET;
- return MLXSW_SP_CELLS_TO_BYTES(max_buff);
+ return mlxsw_sp_cells_bytes(mlxsw_sp, max_buff);
}
static int mlxsw_sp_sb_threshold_in(struct mlxsw_sp *mlxsw_sp, u8 pool,
@@ -645,7 +688,7 @@ static int mlxsw_sp_sb_threshold_in(struct mlxsw_sp *mlxsw_sp, u8 pool,
return -EINVAL;
*p_max_buff = val;
} else {
- *p_max_buff = MLXSW_SP_BYTES_TO_CELLS(threshold);
+ *p_max_buff = mlxsw_sp_bytes_cells(mlxsw_sp, threshold);
}
return 0;
}
@@ -761,7 +804,7 @@ static void mlxsw_sp_sb_sr_occ_query_cb(struct mlxsw_core *mlxsw_core,
masked_count = 0;
for (local_port = cb_ctx.local_port_1;
- local_port < MLXSW_PORT_MAX_PORTS; local_port++) {
+ local_port < mlxsw_core_max_ports(mlxsw_core); local_port++) {
if (!mlxsw_sp->ports[local_port])
continue;
for (i = 0; i < MLXSW_SP_SB_TC_COUNT; i++) {
@@ -775,7 +818,7 @@ static void mlxsw_sp_sb_sr_occ_query_cb(struct mlxsw_core *mlxsw_core,
}
masked_count = 0;
for (local_port = cb_ctx.local_port_1;
- local_port < MLXSW_PORT_MAX_PORTS; local_port++) {
+ local_port < mlxsw_core_max_ports(mlxsw_core); local_port++) {
if (!mlxsw_sp->ports[local_port])
continue;
for (i = 0; i < MLXSW_SP_SB_TC_COUNT; i++) {
@@ -817,7 +860,7 @@ int mlxsw_sp_sb_occ_snapshot(struct mlxsw_core *mlxsw_core,
mlxsw_reg_sbsr_pg_buff_mask_set(sbsr_pl, i, 1);
mlxsw_reg_sbsr_tclass_mask_set(sbsr_pl, i, 1);
}
- for (; local_port < MLXSW_PORT_MAX_PORTS; local_port++) {
+ for (; local_port < mlxsw_core_max_ports(mlxsw_core); local_port++) {
if (!mlxsw_sp->ports[local_port])
continue;
mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl, local_port, 1);
@@ -847,7 +890,7 @@ int mlxsw_sp_sb_occ_snapshot(struct mlxsw_core *mlxsw_core,
cb_priv);
if (err)
goto out;
- if (local_port < MLXSW_PORT_MAX_PORTS)
+ if (local_port < mlxsw_core_max_ports(mlxsw_core))
goto next_batch;
out:
@@ -882,7 +925,7 @@ int mlxsw_sp_sb_occ_max_clear(struct mlxsw_core *mlxsw_core,
mlxsw_reg_sbsr_pg_buff_mask_set(sbsr_pl, i, 1);
mlxsw_reg_sbsr_tclass_mask_set(sbsr_pl, i, 1);
}
- for (; local_port < MLXSW_PORT_MAX_PORTS; local_port++) {
+ for (; local_port < mlxsw_core_max_ports(mlxsw_core); local_port++) {
if (!mlxsw_sp->ports[local_port])
continue;
mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl, local_port, 1);
@@ -908,7 +951,7 @@ int mlxsw_sp_sb_occ_max_clear(struct mlxsw_core *mlxsw_core,
&bulk_list, NULL, 0);
if (err)
goto out;
- if (local_port < MLXSW_PORT_MAX_PORTS)
+ if (local_port < mlxsw_core_max_ports(mlxsw_core))
goto next_batch;
out:
@@ -932,8 +975,8 @@ int mlxsw_sp_sb_occ_port_pool_get(struct mlxsw_core_port *mlxsw_core_port,
struct mlxsw_sp_sb_pm *pm = mlxsw_sp_sb_pm_get(mlxsw_sp, local_port,
pool, dir);
- *p_cur = MLXSW_SP_CELLS_TO_BYTES(pm->occ.cur);
- *p_max = MLXSW_SP_CELLS_TO_BYTES(pm->occ.max);
+ *p_cur = mlxsw_sp_cells_bytes(mlxsw_sp, pm->occ.cur);
+ *p_max = mlxsw_sp_cells_bytes(mlxsw_sp, pm->occ.max);
return 0;
}
@@ -951,7 +994,7 @@ int mlxsw_sp_sb_occ_tc_port_bind_get(struct mlxsw_core_port *mlxsw_core_port,
struct mlxsw_sp_sb_cm *cm = mlxsw_sp_sb_cm_get(mlxsw_sp, local_port,
pg_buff, dir);
- *p_cur = MLXSW_SP_CELLS_TO_BYTES(cm->occ.cur);
- *p_max = MLXSW_SP_CELLS_TO_BYTES(cm->occ.max);
+ *p_cur = mlxsw_sp_cells_bytes(mlxsw_sp, cm->occ.cur);
+ *p_max = mlxsw_sp_cells_bytes(mlxsw_sp, cm->occ.max);
return 0;
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c
new file mode 100644
index 0000000..0f46775
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c
@@ -0,0 +1,207 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Arkadi Sharshevsky <arkadis@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+
+#include "spectrum_cnt.h"
+
+#define MLXSW_SP_COUNTER_POOL_BANK_SIZE 4096
+
+struct mlxsw_sp_counter_sub_pool {
+ unsigned int base_index;
+ unsigned int size;
+ unsigned int entry_size;
+ unsigned int bank_count;
+};
+
+struct mlxsw_sp_counter_pool {
+ unsigned int pool_size;
+ unsigned long *usage; /* Usage bitmap */
+ struct mlxsw_sp_counter_sub_pool *sub_pools;
+};
+
+static struct mlxsw_sp_counter_sub_pool mlxsw_sp_counter_sub_pools[] = {
+ [MLXSW_SP_COUNTER_SUB_POOL_FLOW] = {
+ .bank_count = 6,
+ },
+ [MLXSW_SP_COUNTER_SUB_POOL_RIF] = {
+ .bank_count = 2,
+ }
+};
+
+static int mlxsw_sp_counter_pool_validate(struct mlxsw_sp *mlxsw_sp)
+{
+ unsigned int total_bank_config = 0;
+ unsigned int pool_size;
+ int i;
+
+ pool_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, COUNTER_POOL_SIZE);
+ /* Check config is valid, no bank over subscription */
+ for (i = 0; i < ARRAY_SIZE(mlxsw_sp_counter_sub_pools); i++)
+ total_bank_config += mlxsw_sp_counter_sub_pools[i].bank_count;
+ if (total_bank_config > pool_size / MLXSW_SP_COUNTER_POOL_BANK_SIZE + 1)
+ return -EINVAL;
+ return 0;
+}
+
+static int mlxsw_sp_counter_sub_pools_prepare(struct mlxsw_sp *mlxsw_sp)
+{
+ struct mlxsw_sp_counter_sub_pool *sub_pool;
+
+ /* Prepare generic flow pool*/
+ sub_pool = &mlxsw_sp_counter_sub_pools[MLXSW_SP_COUNTER_SUB_POOL_FLOW];
+ if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, COUNTER_SIZE_PACKETS_BYTES))
+ return -EIO;
+ sub_pool->entry_size = MLXSW_CORE_RES_GET(mlxsw_sp->core,
+ COUNTER_SIZE_PACKETS_BYTES);
+ /* Prepare erif pool*/
+ sub_pool = &mlxsw_sp_counter_sub_pools[MLXSW_SP_COUNTER_SUB_POOL_RIF];
+ if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, COUNTER_SIZE_ROUTER_BASIC))
+ return -EIO;
+ sub_pool->entry_size = MLXSW_CORE_RES_GET(mlxsw_sp->core,
+ COUNTER_SIZE_ROUTER_BASIC);
+ return 0;
+}
+
+int mlxsw_sp_counter_pool_init(struct mlxsw_sp *mlxsw_sp)
+{
+ struct mlxsw_sp_counter_sub_pool *sub_pool;
+ struct mlxsw_sp_counter_pool *pool;
+ unsigned int base_index;
+ unsigned int map_size;
+ int i;
+ int err;
+
+ if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, COUNTER_POOL_SIZE))
+ return -EIO;
+
+ err = mlxsw_sp_counter_pool_validate(mlxsw_sp);
+ if (err)
+ return err;
+
+ err = mlxsw_sp_counter_sub_pools_prepare(mlxsw_sp);
+ if (err)
+ return err;
+
+ pool = kzalloc(sizeof(*pool), GFP_KERNEL);
+ if (!pool)
+ return -ENOMEM;
+
+ pool->pool_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, COUNTER_POOL_SIZE);
+ map_size = BITS_TO_LONGS(pool->pool_size) * sizeof(unsigned long);
+
+ pool->usage = kzalloc(map_size, GFP_KERNEL);
+ if (!pool->usage) {
+ err = -ENOMEM;
+ goto err_usage_alloc;
+ }
+
+ pool->sub_pools = mlxsw_sp_counter_sub_pools;
+ /* Allocation is based on bank count which should be
+ * specified for each sub pool statically.
+ */
+ base_index = 0;
+ for (i = 0; i < ARRAY_SIZE(mlxsw_sp_counter_sub_pools); i++) {
+ sub_pool = &pool->sub_pools[i];
+ sub_pool->size = sub_pool->bank_count *
+ MLXSW_SP_COUNTER_POOL_BANK_SIZE;
+ sub_pool->base_index = base_index;
+ base_index += sub_pool->size;
+ /* The last bank can't be fully used */
+ if (sub_pool->base_index + sub_pool->size > pool->pool_size)
+ sub_pool->size = pool->pool_size - sub_pool->base_index;
+ }
+
+ mlxsw_sp->counter_pool = pool;
+ return 0;
+
+err_usage_alloc:
+ kfree(pool);
+ return err;
+}
+
+void mlxsw_sp_counter_pool_fini(struct mlxsw_sp *mlxsw_sp)
+{
+ struct mlxsw_sp_counter_pool *pool = mlxsw_sp->counter_pool;
+
+ WARN_ON(find_first_bit(pool->usage, pool->pool_size) !=
+ pool->pool_size);
+ kfree(pool->usage);
+ kfree(pool);
+}
+
+int mlxsw_sp_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+ enum mlxsw_sp_counter_sub_pool_id sub_pool_id,
+ unsigned int *p_counter_index)
+{
+ struct mlxsw_sp_counter_pool *pool = mlxsw_sp->counter_pool;
+ struct mlxsw_sp_counter_sub_pool *sub_pool;
+ unsigned int entry_index;
+ unsigned int stop_index;
+ int i;
+
+ sub_pool = &mlxsw_sp_counter_sub_pools[sub_pool_id];
+ stop_index = sub_pool->base_index + sub_pool->size;
+ entry_index = sub_pool->base_index;
+
+ entry_index = find_next_zero_bit(pool->usage, stop_index, entry_index);
+ if (entry_index == stop_index)
+ return -ENOBUFS;
+ /* The sub-pools can contain non-integer number of entries
+ * so we must check for overflow
+ */
+ if (entry_index + sub_pool->entry_size > stop_index)
+ return -ENOBUFS;
+ for (i = 0; i < sub_pool->entry_size; i++)
+ __set_bit(entry_index + i, pool->usage);
+
+ *p_counter_index = entry_index;
+ return 0;
+}
+
+void mlxsw_sp_counter_free(struct mlxsw_sp *mlxsw_sp,
+ enum mlxsw_sp_counter_sub_pool_id sub_pool_id,
+ unsigned int counter_index)
+{
+ struct mlxsw_sp_counter_pool *pool = mlxsw_sp->counter_pool;
+ struct mlxsw_sp_counter_sub_pool *sub_pool;
+ int i;
+
+ if (WARN_ON(counter_index >= pool->pool_size))
+ return;
+ sub_pool = &mlxsw_sp_counter_sub_pools[sub_pool_id];
+ for (i = 0; i < sub_pool->entry_size; i++)
+ __clear_bit(counter_index + i, pool->usage);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h
new file mode 100644
index 0000000..fd34d0a
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h
@@ -0,0 +1,54 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Arkadi Sharshevsky <arkdis@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _MLXSW_SPECTRUM_CNT_H
+#define _MLXSW_SPECTRUM_CNT_H
+
+#include "spectrum.h"
+
+enum mlxsw_sp_counter_sub_pool_id {
+ MLXSW_SP_COUNTER_SUB_POOL_FLOW,
+ MLXSW_SP_COUNTER_SUB_POOL_RIF,
+};
+
+int mlxsw_sp_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+ enum mlxsw_sp_counter_sub_pool_id sub_pool_id,
+ unsigned int *p_counter_index);
+void mlxsw_sp_counter_free(struct mlxsw_sp *mlxsw_sp,
+ enum mlxsw_sp_counter_sub_pool_id sub_pool_id,
+ unsigned int counter_index);
+int mlxsw_sp_counter_pool_init(struct mlxsw_sp *mlxsw_sp);
+void mlxsw_sp_counter_pool_fini(struct mlxsw_sp *mlxsw_sp);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
new file mode 100644
index 0000000..ea56f6a
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
@@ -0,0 +1,351 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Arkadi Sharshevsky <arakdis@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <net/devlink.h>
+
+#include "spectrum.h"
+#include "spectrum_dpipe.h"
+#include "spectrum_router.h"
+
+enum mlxsw_sp_field_metadata_id {
+ MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT,
+ MLXSW_SP_DPIPE_FIELD_METADATA_L3_FORWARD,
+ MLXSW_SP_DPIPE_FIELD_METADATA_L3_DROP,
+};
+
+static struct devlink_dpipe_field mlxsw_sp_dpipe_fields_metadata[] = {
+ { .name = "erif_port",
+ .id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT,
+ .bitwidth = 32,
+ .mapping_type = DEVLINK_DPIPE_FIELD_MAPPING_TYPE_IFINDEX,
+ },
+ { .name = "l3_forward",
+ .id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_FORWARD,
+ .bitwidth = 1,
+ },
+ { .name = "l3_drop",
+ .id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_DROP,
+ .bitwidth = 1,
+ },
+};
+
+enum mlxsw_sp_dpipe_header_id {
+ MLXSW_SP_DPIPE_HEADER_METADATA,
+};
+
+static struct devlink_dpipe_header mlxsw_sp_dpipe_header_metadata = {
+ .name = "mlxsw_meta",
+ .id = MLXSW_SP_DPIPE_HEADER_METADATA,
+ .fields = mlxsw_sp_dpipe_fields_metadata,
+ .fields_count = ARRAY_SIZE(mlxsw_sp_dpipe_fields_metadata),
+};
+
+static struct devlink_dpipe_header *mlxsw_dpipe_headers[] = {
+ &mlxsw_sp_dpipe_header_metadata,
+};
+
+static struct devlink_dpipe_headers mlxsw_sp_dpipe_headers = {
+ .headers = mlxsw_dpipe_headers,
+ .headers_count = ARRAY_SIZE(mlxsw_dpipe_headers),
+};
+
+static int mlxsw_sp_dpipe_table_erif_actions_dump(void *priv,
+ struct sk_buff *skb)
+{
+ struct devlink_dpipe_action action = {0};
+ int err;
+
+ action.type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY;
+ action.header = &mlxsw_sp_dpipe_header_metadata;
+ action.field_id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_FORWARD;
+
+ err = devlink_dpipe_action_put(skb, &action);
+ if (err)
+ return err;
+
+ action.type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY;
+ action.header = &mlxsw_sp_dpipe_header_metadata;
+ action.field_id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_DROP;
+
+ return devlink_dpipe_action_put(skb, &action);
+}
+
+static int mlxsw_sp_dpipe_table_erif_matches_dump(void *priv,
+ struct sk_buff *skb)
+{
+ struct devlink_dpipe_match match = {0};
+
+ match.type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT;
+ match.header = &mlxsw_sp_dpipe_header_metadata;
+ match.field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT;
+
+ return devlink_dpipe_match_put(skb, &match);
+}
+
+static void mlxsw_sp_erif_entry_clear(struct devlink_dpipe_entry *entry)
+{
+ unsigned int value_count, value_index;
+ struct devlink_dpipe_value *value;
+
+ value = entry->action_values;
+ value_count = entry->action_values_count;
+ for (value_index = 0; value_index < value_count; value_index++) {
+ kfree(value[value_index].value);
+ kfree(value[value_index].mask);
+ }
+
+ value = entry->match_values;
+ value_count = entry->match_values_count;
+ for (value_index = 0; value_index < value_count; value_index++) {
+ kfree(value[value_index].value);
+ kfree(value[value_index].mask);
+ }
+}
+
+static void
+mlxsw_sp_erif_match_action_prepare(struct devlink_dpipe_match *match,
+ struct devlink_dpipe_action *action)
+{
+ action->type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY;
+ action->header = &mlxsw_sp_dpipe_header_metadata;
+ action->field_id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_FORWARD;
+
+ match->type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT;
+ match->header = &mlxsw_sp_dpipe_header_metadata;
+ match->field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT;
+}
+
+static int mlxsw_sp_erif_entry_prepare(struct devlink_dpipe_entry *entry,
+ struct devlink_dpipe_value *match_value,
+ struct devlink_dpipe_match *match,
+ struct devlink_dpipe_value *action_value,
+ struct devlink_dpipe_action *action)
+{
+ entry->match_values = match_value;
+ entry->match_values_count = 1;
+
+ entry->action_values = action_value;
+ entry->action_values_count = 1;
+
+ match_value->match = match;
+ match_value->value_size = sizeof(u32);
+ match_value->value = kmalloc(match_value->value_size, GFP_KERNEL);
+ if (!match_value->value)
+ return -ENOMEM;
+
+ action_value->action = action;
+ action_value->value_size = sizeof(u32);
+ action_value->value = kmalloc(action_value->value_size, GFP_KERNEL);
+ if (!action_value->value)
+ goto err_action_alloc;
+ return 0;
+
+err_action_alloc:
+ kfree(match_value->value);
+ return -ENOMEM;
+}
+
+static int mlxsw_sp_erif_entry_get(struct mlxsw_sp *mlxsw_sp,
+ struct devlink_dpipe_entry *entry,
+ struct mlxsw_sp_rif *rif,
+ bool counters_enabled)
+{
+ u32 *action_value;
+ u32 *rif_value;
+ u64 cnt;
+ int err;
+
+ /* Set Match RIF index */
+ rif_value = entry->match_values->value;
+ *rif_value = mlxsw_sp_rif_index(rif);
+ entry->match_values->mapping_value = mlxsw_sp_rif_dev_ifindex(rif);
+ entry->match_values->mapping_valid = true;
+
+ /* Set Action Forwarding */
+ action_value = entry->action_values->value;
+ *action_value = 1;
+
+ entry->counter_valid = false;
+ entry->counter = 0;
+ if (!counters_enabled)
+ return 0;
+
+ entry->index = mlxsw_sp_rif_index(rif);
+ err = mlxsw_sp_rif_counter_value_get(mlxsw_sp, rif,
+ MLXSW_SP_RIF_COUNTER_EGRESS,
+ &cnt);
+ if (!err) {
+ entry->counter = cnt;
+ entry->counter_valid = true;
+ }
+ return 0;
+}
+
+static int
+mlxsw_sp_table_erif_entries_dump(void *priv, bool counters_enabled,
+ struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+ struct devlink_dpipe_value match_value = {{0}}, action_value = {{0}};
+ struct devlink_dpipe_action action = {0};
+ struct devlink_dpipe_match match = {0};
+ struct devlink_dpipe_entry entry = {0};
+ struct mlxsw_sp *mlxsw_sp = priv;
+ unsigned int rif_count;
+ int i, j;
+ int err;
+
+ mlxsw_sp_erif_match_action_prepare(&match, &action);
+ err = mlxsw_sp_erif_entry_prepare(&entry, &match_value, &match,
+ &action_value, &action);
+ if (err)
+ return err;
+
+ rif_count = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS);
+ rtnl_lock();
+ i = 0;
+start_again:
+ err = devlink_dpipe_entry_ctx_prepare(dump_ctx);
+ if (err)
+ return err;
+ j = 0;
+ for (; i < rif_count; i++) {
+ if (!mlxsw_sp->rifs[i])
+ continue;
+ err = mlxsw_sp_erif_entry_get(mlxsw_sp, &entry,
+ mlxsw_sp->rifs[i],
+ counters_enabled);
+ if (err)
+ goto err_entry_get;
+ err = devlink_dpipe_entry_ctx_append(dump_ctx, &entry);
+ if (err) {
+ if (err == -EMSGSIZE) {
+ if (!j)
+ goto err_entry_append;
+ break;
+ }
+ goto err_entry_append;
+ }
+ j++;
+ }
+
+ devlink_dpipe_entry_ctx_close(dump_ctx);
+ if (i != rif_count)
+ goto start_again;
+ rtnl_unlock();
+
+ mlxsw_sp_erif_entry_clear(&entry);
+ return 0;
+err_entry_append:
+err_entry_get:
+ rtnl_unlock();
+ mlxsw_sp_erif_entry_clear(&entry);
+ return err;
+}
+
+static int mlxsw_sp_table_erif_counters_update(void *priv, bool enable)
+{
+ struct mlxsw_sp *mlxsw_sp = priv;
+ int i;
+
+ rtnl_lock();
+ for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) {
+ if (!mlxsw_sp->rifs[i])
+ continue;
+ if (enable)
+ mlxsw_sp_rif_counter_alloc(mlxsw_sp,
+ mlxsw_sp->rifs[i],
+ MLXSW_SP_RIF_COUNTER_EGRESS);
+ else
+ mlxsw_sp_rif_counter_free(mlxsw_sp,
+ mlxsw_sp->rifs[i],
+ MLXSW_SP_RIF_COUNTER_EGRESS);
+ }
+ rtnl_unlock();
+ return 0;
+}
+
+static struct devlink_dpipe_table_ops mlxsw_sp_erif_ops = {
+ .matches_dump = mlxsw_sp_dpipe_table_erif_matches_dump,
+ .actions_dump = mlxsw_sp_dpipe_table_erif_actions_dump,
+ .entries_dump = mlxsw_sp_table_erif_entries_dump,
+ .counters_set_update = mlxsw_sp_table_erif_counters_update,
+};
+
+static int mlxsw_sp_dpipe_erif_table_init(struct mlxsw_sp *mlxsw_sp)
+{
+ struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+ u64 table_size;
+
+ table_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS);
+ return devlink_dpipe_table_register(devlink,
+ MLXSW_SP_DPIPE_TABLE_NAME_ERIF,
+ &mlxsw_sp_erif_ops,
+ mlxsw_sp, table_size,
+ false);
+}
+
+static void mlxsw_sp_dpipe_erif_table_fini(struct mlxsw_sp *mlxsw_sp)
+{
+ struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+
+ devlink_dpipe_table_unregister(devlink, MLXSW_SP_DPIPE_TABLE_NAME_ERIF);
+}
+
+int mlxsw_sp_dpipe_init(struct mlxsw_sp *mlxsw_sp)
+{
+ struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+ int err;
+
+ err = devlink_dpipe_headers_register(devlink,
+ &mlxsw_sp_dpipe_headers);
+ if (err)
+ return err;
+ err = mlxsw_sp_dpipe_erif_table_init(mlxsw_sp);
+ if (err)
+ goto err_erif_register;
+ return 0;
+
+err_erif_register:
+ devlink_dpipe_headers_unregister(priv_to_devlink(mlxsw_sp->core));
+ return err;
+}
+
+void mlxsw_sp_dpipe_fini(struct mlxsw_sp *mlxsw_sp)
+{
+ struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+
+ mlxsw_sp_dpipe_erif_table_fini(mlxsw_sp);
+ devlink_dpipe_headers_unregister(devlink);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
new file mode 100644
index 0000000..d208929
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
@@ -0,0 +1,43 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Arkadi Sharshevsky <arkadis@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _MLXSW_PIPELINE_H_
+#define _MLXSW_PIPELINE_H_
+
+int mlxsw_sp_dpipe_init(struct mlxsw_sp *mlxsw_sp);
+void mlxsw_sp_dpipe_fini(struct mlxsw_sp *mlxsw_sp);
+
+#define MLXSW_SP_DPIPE_TABLE_NAME_ERIF "mlxsw_erif"
+
+#endif /* _MLXSW_PIPELINE_H_*/
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 22ab429..3e7a0bc 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -39,6 +39,7 @@
#include <net/pkt_cls.h>
#include <net/tc_act/tc_gact.h>
#include <net/tc_act/tc_mirred.h>
+#include <net/tc_act/tc_vlan.h>
#include "spectrum.h"
#include "core_acl_flex_keys.h"
@@ -55,6 +56,11 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
if (tc_no_actions(exts))
return 0;
+ /* Count action is inserted first */
+ err = mlxsw_sp_acl_rulei_act_count(mlxsw_sp, rulei);
+ if (err)
+ return err;
+
tcf_exts_to_list(exts, &actions);
list_for_each_entry(a, &actions, list) {
if (is_tcf_gact_shot(a)) {
@@ -73,6 +79,15 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
out_dev);
if (err)
return err;
+ } else if (is_tcf_vlan(a)) {
+ u16 proto = be16_to_cpu(tcf_vlan_push_proto(a));
+ u32 action = tcf_vlan_action(a);
+ u8 prio = tcf_vlan_push_prio(a);
+ u16 vid = tcf_vlan_push_vid(a);
+
+ return mlxsw_sp_acl_rulei_act_vlan(mlxsw_sp, rulei,
+ action, vid,
+ proto, prio);
} else {
dev_err(mlxsw_sp->bus_info->dev, "Unsupported action\n");
return -EOPNOTSUPP;
@@ -173,7 +188,8 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
- BIT(FLOW_DISSECTOR_KEY_PORTS))) {
+ BIT(FLOW_DISSECTOR_KEY_PORTS) |
+ BIT(FLOW_DISSECTOR_KEY_VLAN))) {
dev_err(mlxsw_sp->bus_info->dev, "Unsupported key\n");
return -EOPNOTSUPP;
}
@@ -234,6 +250,27 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
sizeof(key->src));
}
+ if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
+ struct flow_dissector_key_vlan *key =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_VLAN,
+ f->key);
+ struct flow_dissector_key_vlan *mask =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_VLAN,
+ f->mask);
+ if (mask->vlan_id != 0)
+ mlxsw_sp_acl_rulei_keymask_u32(rulei,
+ MLXSW_AFK_ELEMENT_VID,
+ key->vlan_id,
+ mask->vlan_id);
+ if (mask->vlan_priority != 0)
+ mlxsw_sp_acl_rulei_keymask_u32(rulei,
+ MLXSW_AFK_ELEMENT_PCP,
+ key->vlan_priority,
+ mask->vlan_priority);
+ }
+
if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS)
mlxsw_sp_flower_parse_ipv4(rulei, f);
@@ -303,14 +340,58 @@ void mlxsw_sp_flower_destroy(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress,
ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, mlxsw_sp_port->dev,
ingress,
MLXSW_SP_ACL_PROFILE_FLOWER);
- if (WARN_ON(IS_ERR(ruleset)))
+ if (IS_ERR(ruleset))
return;
rule = mlxsw_sp_acl_rule_lookup(mlxsw_sp, ruleset, f->cookie);
- if (!WARN_ON(!rule)) {
+ if (rule) {
mlxsw_sp_acl_rule_del(mlxsw_sp, rule);
mlxsw_sp_acl_rule_destroy(mlxsw_sp, rule);
}
mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
}
+
+int mlxsw_sp_flower_stats(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress,
+ struct tc_cls_flower_offload *f)
+{
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+ struct mlxsw_sp_acl_ruleset *ruleset;
+ struct mlxsw_sp_acl_rule *rule;
+ struct tc_action *a;
+ LIST_HEAD(actions);
+ u64 packets;
+ u64 lastuse;
+ u64 bytes;
+ int err;
+
+ ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, mlxsw_sp_port->dev,
+ ingress,
+ MLXSW_SP_ACL_PROFILE_FLOWER);
+ if (WARN_ON(IS_ERR(ruleset)))
+ return -EINVAL;
+
+ rule = mlxsw_sp_acl_rule_lookup(mlxsw_sp, ruleset, f->cookie);
+ if (!rule)
+ return -EINVAL;
+
+ err = mlxsw_sp_acl_rule_get_stats(mlxsw_sp, rule, &packets, &bytes,
+ &lastuse);
+ if (err)
+ goto err_rule_get_stats;
+
+ preempt_disable();
+
+ tcf_exts_to_list(f->exts, &actions);
+ list_for_each_entry(a, &actions, list)
+ tcf_action_stats_update(a, bytes, packets, lastuse);
+
+ preempt_enable();
+
+ mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
+ return 0;
+
+err_rule_get_stats:
+ mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
+ return err;
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
index ac321e8..26c26cd 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
@@ -45,7 +45,8 @@
(MLXSW_SP_KVD_LINEAR_SIZE - MLXSW_SP_KVDL_CHUNKS_BASE)
#define MLXSW_SP_CHUNK_MAX 32
-int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count)
+int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count,
+ u32 *p_entry_index)
{
int entry_index;
int size;
@@ -72,7 +73,8 @@ int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count)
for (i = 0; i < type_entries; i++)
set_bit(entry_index + i, mlxsw_sp->kvdl.usage);
- return entry_index;
+ *p_entry_index = entry_index;
+ return 0;
}
return -ENOBUFS;
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index bd8de6b..c70c591 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -41,14 +41,184 @@
#include <linux/in6.h>
#include <linux/notifier.h>
#include <linux/inetdevice.h>
+#include <linux/netdevice.h>
#include <net/netevent.h>
#include <net/neighbour.h>
#include <net/arp.h>
#include <net/ip_fib.h>
+#include <net/fib_rules.h>
+#include <net/l3mdev.h>
#include "spectrum.h"
#include "core.h"
#include "reg.h"
+#include "spectrum_cnt.h"
+#include "spectrum_dpipe.h"
+#include "spectrum_router.h"
+
+struct mlxsw_sp_rif {
+ struct list_head nexthop_list;
+ struct list_head neigh_list;
+ struct net_device *dev;
+ struct mlxsw_sp_fid *f;
+ unsigned char addr[ETH_ALEN];
+ int mtu;
+ u16 rif_index;
+ u16 vr_id;
+ unsigned int counter_ingress;
+ bool counter_ingress_valid;
+ unsigned int counter_egress;
+ bool counter_egress_valid;
+};
+
+static unsigned int *
+mlxsw_sp_rif_p_counter_get(struct mlxsw_sp_rif *rif,
+ enum mlxsw_sp_rif_counter_dir dir)
+{
+ switch (dir) {
+ case MLXSW_SP_RIF_COUNTER_EGRESS:
+ return &rif->counter_egress;
+ case MLXSW_SP_RIF_COUNTER_INGRESS:
+ return &rif->counter_ingress;
+ }
+ return NULL;
+}
+
+static bool
+mlxsw_sp_rif_counter_valid_get(struct mlxsw_sp_rif *rif,
+ enum mlxsw_sp_rif_counter_dir dir)
+{
+ switch (dir) {
+ case MLXSW_SP_RIF_COUNTER_EGRESS:
+ return rif->counter_egress_valid;
+ case MLXSW_SP_RIF_COUNTER_INGRESS:
+ return rif->counter_ingress_valid;
+ }
+ return false;
+}
+
+static void
+mlxsw_sp_rif_counter_valid_set(struct mlxsw_sp_rif *rif,
+ enum mlxsw_sp_rif_counter_dir dir,
+ bool valid)
+{
+ switch (dir) {
+ case MLXSW_SP_RIF_COUNTER_EGRESS:
+ rif->counter_egress_valid = valid;
+ break;
+ case MLXSW_SP_RIF_COUNTER_INGRESS:
+ rif->counter_ingress_valid = valid;
+ break;
+ }
+}
+
+static int mlxsw_sp_rif_counter_edit(struct mlxsw_sp *mlxsw_sp, u16 rif_index,
+ unsigned int counter_index, bool enable,
+ enum mlxsw_sp_rif_counter_dir dir)
+{
+ char ritr_pl[MLXSW_REG_RITR_LEN];
+ bool is_egress = false;
+ int err;
+
+ if (dir == MLXSW_SP_RIF_COUNTER_EGRESS)
+ is_egress = true;
+ mlxsw_reg_ritr_rif_pack(ritr_pl, rif_index);
+ err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+ if (err)
+ return err;
+
+ mlxsw_reg_ritr_counter_pack(ritr_pl, counter_index, enable,
+ is_egress);
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+int mlxsw_sp_rif_counter_value_get(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_rif *rif,
+ enum mlxsw_sp_rif_counter_dir dir, u64 *cnt)
+{
+ char ricnt_pl[MLXSW_REG_RICNT_LEN];
+ unsigned int *p_counter_index;
+ bool valid;
+ int err;
+
+ valid = mlxsw_sp_rif_counter_valid_get(rif, dir);
+ if (!valid)
+ return -EINVAL;
+
+ p_counter_index = mlxsw_sp_rif_p_counter_get(rif, dir);
+ if (!p_counter_index)
+ return -EINVAL;
+ mlxsw_reg_ricnt_pack(ricnt_pl, *p_counter_index,
+ MLXSW_REG_RICNT_OPCODE_NOP);
+ err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ricnt), ricnt_pl);
+ if (err)
+ return err;
+ *cnt = mlxsw_reg_ricnt_good_unicast_packets_get(ricnt_pl);
+ return 0;
+}
+
+static int mlxsw_sp_rif_counter_clear(struct mlxsw_sp *mlxsw_sp,
+ unsigned int counter_index)
+{
+ char ricnt_pl[MLXSW_REG_RICNT_LEN];
+
+ mlxsw_reg_ricnt_pack(ricnt_pl, counter_index,
+ MLXSW_REG_RICNT_OPCODE_CLEAR);
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ricnt), ricnt_pl);
+}
+
+int mlxsw_sp_rif_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_rif *rif,
+ enum mlxsw_sp_rif_counter_dir dir)
+{
+ unsigned int *p_counter_index;
+ int err;
+
+ p_counter_index = mlxsw_sp_rif_p_counter_get(rif, dir);
+ if (!p_counter_index)
+ return -EINVAL;
+ err = mlxsw_sp_counter_alloc(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_RIF,
+ p_counter_index);
+ if (err)
+ return err;
+
+ err = mlxsw_sp_rif_counter_clear(mlxsw_sp, *p_counter_index);
+ if (err)
+ goto err_counter_clear;
+
+ err = mlxsw_sp_rif_counter_edit(mlxsw_sp, rif->rif_index,
+ *p_counter_index, true, dir);
+ if (err)
+ goto err_counter_edit;
+ mlxsw_sp_rif_counter_valid_set(rif, dir, true);
+ return 0;
+
+err_counter_edit:
+err_counter_clear:
+ mlxsw_sp_counter_free(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_RIF,
+ *p_counter_index);
+ return err;
+}
+
+void mlxsw_sp_rif_counter_free(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_rif *rif,
+ enum mlxsw_sp_rif_counter_dir dir)
+{
+ unsigned int *p_counter_index;
+
+ p_counter_index = mlxsw_sp_rif_p_counter_get(rif, dir);
+ if (WARN_ON(!p_counter_index))
+ return;
+ mlxsw_sp_rif_counter_edit(mlxsw_sp, rif->rif_index,
+ *p_counter_index, false, dir);
+ mlxsw_sp_counter_free(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_RIF,
+ *p_counter_index);
+ mlxsw_sp_rif_counter_valid_set(rif, dir, false);
+}
+
+static struct mlxsw_sp_rif *
+mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
+ const struct net_device *dev);
#define mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage) \
for_each_set_bit(prefix, (prefix_usage)->b, MLXSW_SP_PREFIX_COUNT)
@@ -89,12 +259,6 @@ mlxsw_sp_prefix_usage_cpy(struct mlxsw_sp_prefix_usage *prefix_usage1,
}
static void
-mlxsw_sp_prefix_usage_zero(struct mlxsw_sp_prefix_usage *prefix_usage)
-{
- memset(prefix_usage, 0, sizeof(*prefix_usage));
-}
-
-static void
mlxsw_sp_prefix_usage_set(struct mlxsw_sp_prefix_usage *prefix_usage,
unsigned char prefix_len)
{
@@ -125,7 +289,7 @@ struct mlxsw_sp_fib_node {
struct list_head entry_list;
struct list_head list;
struct rhash_head ht_node;
- struct mlxsw_sp_vr *vr;
+ struct mlxsw_sp_fib *fib;
struct mlxsw_sp_fib_key key;
};
@@ -149,13 +313,17 @@ struct mlxsw_sp_fib_entry {
struct mlxsw_sp_fib {
struct rhashtable ht;
struct list_head node_list;
+ struct mlxsw_sp_vr *vr;
+ struct mlxsw_sp_lpm_tree *lpm_tree;
unsigned long prefix_ref_count[MLXSW_SP_PREFIX_COUNT];
struct mlxsw_sp_prefix_usage prefix_usage;
+ enum mlxsw_sp_l3proto proto;
};
static const struct rhashtable_params mlxsw_sp_fib_ht_params;
-static struct mlxsw_sp_fib *mlxsw_sp_fib_create(void)
+static struct mlxsw_sp_fib *mlxsw_sp_fib_create(struct mlxsw_sp_vr *vr,
+ enum mlxsw_sp_l3proto proto)
{
struct mlxsw_sp_fib *fib;
int err;
@@ -167,6 +335,8 @@ static struct mlxsw_sp_fib *mlxsw_sp_fib_create(void)
if (err)
goto err_rhashtable_init;
INIT_LIST_HEAD(&fib->node_list);
+ fib->proto = proto;
+ fib->vr = vr;
return fib;
err_rhashtable_init:
@@ -177,24 +347,21 @@ static struct mlxsw_sp_fib *mlxsw_sp_fib_create(void)
static void mlxsw_sp_fib_destroy(struct mlxsw_sp_fib *fib)
{
WARN_ON(!list_empty(&fib->node_list));
+ WARN_ON(fib->lpm_tree);
rhashtable_destroy(&fib->ht);
kfree(fib);
}
static struct mlxsw_sp_lpm_tree *
-mlxsw_sp_lpm_tree_find_unused(struct mlxsw_sp *mlxsw_sp, bool one_reserved)
+mlxsw_sp_lpm_tree_find_unused(struct mlxsw_sp *mlxsw_sp)
{
static struct mlxsw_sp_lpm_tree *lpm_tree;
int i;
- for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) {
- lpm_tree = &mlxsw_sp->router.lpm_trees[i];
- if (lpm_tree->ref_count == 0) {
- if (one_reserved)
- one_reserved = false;
- else
- return lpm_tree;
- }
+ for (i = 0; i < mlxsw_sp->router.lpm.tree_count; i++) {
+ lpm_tree = &mlxsw_sp->router.lpm.trees[i];
+ if (lpm_tree->ref_count == 0)
+ return lpm_tree;
}
return NULL;
}
@@ -248,12 +415,12 @@ mlxsw_sp_lpm_tree_left_struct_set(struct mlxsw_sp *mlxsw_sp,
static struct mlxsw_sp_lpm_tree *
mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_prefix_usage *prefix_usage,
- enum mlxsw_sp_l3proto proto, bool one_reserved)
+ enum mlxsw_sp_l3proto proto)
{
struct mlxsw_sp_lpm_tree *lpm_tree;
int err;
- lpm_tree = mlxsw_sp_lpm_tree_find_unused(mlxsw_sp, one_reserved);
+ lpm_tree = mlxsw_sp_lpm_tree_find_unused(mlxsw_sp);
if (!lpm_tree)
return ERR_PTR(-EBUSY);
lpm_tree->proto = proto;
@@ -283,13 +450,13 @@ static int mlxsw_sp_lpm_tree_destroy(struct mlxsw_sp *mlxsw_sp,
static struct mlxsw_sp_lpm_tree *
mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_prefix_usage *prefix_usage,
- enum mlxsw_sp_l3proto proto, bool one_reserved)
+ enum mlxsw_sp_l3proto proto)
{
struct mlxsw_sp_lpm_tree *lpm_tree;
int i;
- for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) {
- lpm_tree = &mlxsw_sp->router.lpm_trees[i];
+ for (i = 0; i < mlxsw_sp->router.lpm.tree_count; i++) {
+ lpm_tree = &mlxsw_sp->router.lpm.trees[i];
if (lpm_tree->ref_count != 0 &&
lpm_tree->proto == proto &&
mlxsw_sp_prefix_usage_eq(&lpm_tree->prefix_usage,
@@ -297,7 +464,7 @@ mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp,
goto inc_ref_count;
}
lpm_tree = mlxsw_sp_lpm_tree_create(mlxsw_sp, prefix_usage,
- proto, one_reserved);
+ proto);
if (IS_ERR(lpm_tree))
return lpm_tree;
@@ -314,15 +481,41 @@ static int mlxsw_sp_lpm_tree_put(struct mlxsw_sp *mlxsw_sp,
return 0;
}
-static void mlxsw_sp_lpm_init(struct mlxsw_sp *mlxsw_sp)
+#define MLXSW_SP_LPM_TREE_MIN 2 /* trees 0 and 1 are reserved */
+
+static int mlxsw_sp_lpm_init(struct mlxsw_sp *mlxsw_sp)
{
struct mlxsw_sp_lpm_tree *lpm_tree;
+ u64 max_trees;
int i;
- for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) {
- lpm_tree = &mlxsw_sp->router.lpm_trees[i];
+ if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_LPM_TREES))
+ return -EIO;
+
+ max_trees = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_LPM_TREES);
+ mlxsw_sp->router.lpm.tree_count = max_trees - MLXSW_SP_LPM_TREE_MIN;
+ mlxsw_sp->router.lpm.trees = kcalloc(mlxsw_sp->router.lpm.tree_count,
+ sizeof(struct mlxsw_sp_lpm_tree),
+ GFP_KERNEL);
+ if (!mlxsw_sp->router.lpm.trees)
+ return -ENOMEM;
+
+ for (i = 0; i < mlxsw_sp->router.lpm.tree_count; i++) {
+ lpm_tree = &mlxsw_sp->router.lpm.trees[i];
lpm_tree->id = i + MLXSW_SP_LPM_TREE_MIN;
}
+
+ return 0;
+}
+
+static void mlxsw_sp_lpm_fini(struct mlxsw_sp *mlxsw_sp)
+{
+ kfree(mlxsw_sp->router.lpm.trees);
+}
+
+static bool mlxsw_sp_vr_is_used(const struct mlxsw_sp_vr *vr)
+{
+ return !!vr->fib4;
}
static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp)
@@ -332,31 +525,31 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp)
for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) {
vr = &mlxsw_sp->router.vrs[i];
- if (!vr->used)
+ if (!mlxsw_sp_vr_is_used(vr))
return vr;
}
return NULL;
}
static int mlxsw_sp_vr_lpm_tree_bind(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_vr *vr)
+ const struct mlxsw_sp_fib *fib)
{
char raltb_pl[MLXSW_REG_RALTB_LEN];
- mlxsw_reg_raltb_pack(raltb_pl, vr->id,
- (enum mlxsw_reg_ralxx_protocol) vr->proto,
- vr->lpm_tree->id);
+ mlxsw_reg_raltb_pack(raltb_pl, fib->vr->id,
+ (enum mlxsw_reg_ralxx_protocol) fib->proto,
+ fib->lpm_tree->id);
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl);
}
static int mlxsw_sp_vr_lpm_tree_unbind(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_vr *vr)
+ const struct mlxsw_sp_fib *fib)
{
char raltb_pl[MLXSW_REG_RALTB_LEN];
/* Bind to tree 0 which is default */
- mlxsw_reg_raltb_pack(raltb_pl, vr->id,
- (enum mlxsw_reg_ralxx_protocol) vr->proto, 0);
+ mlxsw_reg_raltb_pack(raltb_pl, fib->vr->id,
+ (enum mlxsw_reg_ralxx_protocol) fib->proto, 0);
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl);
}
@@ -369,8 +562,7 @@ static u32 mlxsw_sp_fix_tb_id(u32 tb_id)
}
static struct mlxsw_sp_vr *mlxsw_sp_vr_find(struct mlxsw_sp *mlxsw_sp,
- u32 tb_id,
- enum mlxsw_sp_l3proto proto)
+ u32 tb_id)
{
struct mlxsw_sp_vr *vr;
int i;
@@ -379,69 +571,50 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_find(struct mlxsw_sp *mlxsw_sp,
for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) {
vr = &mlxsw_sp->router.vrs[i];
- if (vr->used && vr->proto == proto && vr->tb_id == tb_id)
+ if (mlxsw_sp_vr_is_used(vr) && vr->tb_id == tb_id)
return vr;
}
return NULL;
}
-static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp,
- unsigned char prefix_len,
- u32 tb_id,
- enum mlxsw_sp_l3proto proto)
+static struct mlxsw_sp_fib *mlxsw_sp_vr_fib(const struct mlxsw_sp_vr *vr,
+ enum mlxsw_sp_l3proto proto)
{
- struct mlxsw_sp_prefix_usage req_prefix_usage;
- struct mlxsw_sp_lpm_tree *lpm_tree;
+ switch (proto) {
+ case MLXSW_SP_L3_PROTO_IPV4:
+ return vr->fib4;
+ case MLXSW_SP_L3_PROTO_IPV6:
+ BUG_ON(1);
+ }
+ return NULL;
+}
+
+static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp,
+ u32 tb_id)
+{
struct mlxsw_sp_vr *vr;
- int err;
vr = mlxsw_sp_vr_find_unused(mlxsw_sp);
if (!vr)
return ERR_PTR(-EBUSY);
- vr->fib = mlxsw_sp_fib_create();
- if (IS_ERR(vr->fib))
- return ERR_CAST(vr->fib);
-
- vr->proto = proto;
+ vr->fib4 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV4);
+ if (IS_ERR(vr->fib4))
+ return ERR_CAST(vr->fib4);
vr->tb_id = tb_id;
- mlxsw_sp_prefix_usage_zero(&req_prefix_usage);
- mlxsw_sp_prefix_usage_set(&req_prefix_usage, prefix_len);
- lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage,
- proto, true);
- if (IS_ERR(lpm_tree)) {
- err = PTR_ERR(lpm_tree);
- goto err_tree_get;
- }
- vr->lpm_tree = lpm_tree;
- err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr);
- if (err)
- goto err_tree_bind;
-
- vr->used = true;
return vr;
-
-err_tree_bind:
- mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree);
-err_tree_get:
- mlxsw_sp_fib_destroy(vr->fib);
-
- return ERR_PTR(err);
}
-static void mlxsw_sp_vr_destroy(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_vr *vr)
+static void mlxsw_sp_vr_destroy(struct mlxsw_sp_vr *vr)
{
- mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, vr);
- mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree);
- mlxsw_sp_fib_destroy(vr->fib);
- vr->used = false;
+ mlxsw_sp_fib_destroy(vr->fib4);
+ vr->fib4 = NULL;
}
static int
-mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr,
+mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib *fib,
struct mlxsw_sp_prefix_usage *req_prefix_usage)
{
- struct mlxsw_sp_lpm_tree *lpm_tree = vr->lpm_tree;
+ struct mlxsw_sp_lpm_tree *lpm_tree = fib->lpm_tree;
struct mlxsw_sp_lpm_tree *new_tree;
int err;
@@ -449,7 +622,7 @@ mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr,
return 0;
new_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage,
- vr->proto, false);
+ fib->proto);
if (IS_ERR(new_tree)) {
/* We failed to get a tree according to the required
* prefix usage. However, the current tree might be still good
@@ -463,8 +636,8 @@ mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr,
}
/* Prevent packet loss by overwriting existing binding */
- vr->lpm_tree = new_tree;
- err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr);
+ fib->lpm_tree = new_tree;
+ err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, fib);
if (err)
goto err_tree_bind;
mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree);
@@ -472,53 +645,26 @@ mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr,
return 0;
err_tree_bind:
- vr->lpm_tree = lpm_tree;
+ fib->lpm_tree = lpm_tree;
mlxsw_sp_lpm_tree_put(mlxsw_sp, new_tree);
return err;
}
-static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp,
- unsigned char prefix_len,
- u32 tb_id,
- enum mlxsw_sp_l3proto proto)
+static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id)
{
struct mlxsw_sp_vr *vr;
- int err;
tb_id = mlxsw_sp_fix_tb_id(tb_id);
- vr = mlxsw_sp_vr_find(mlxsw_sp, tb_id, proto);
- if (!vr) {
- vr = mlxsw_sp_vr_create(mlxsw_sp, prefix_len, tb_id, proto);
- if (IS_ERR(vr))
- return vr;
- } else {
- struct mlxsw_sp_prefix_usage req_prefix_usage;
-
- mlxsw_sp_prefix_usage_cpy(&req_prefix_usage,
- &vr->fib->prefix_usage);
- mlxsw_sp_prefix_usage_set(&req_prefix_usage, prefix_len);
- /* Need to replace LPM tree in case new prefix is required. */
- err = mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, vr,
- &req_prefix_usage);
- if (err)
- return ERR_PTR(err);
- }
+ vr = mlxsw_sp_vr_find(mlxsw_sp, tb_id);
+ if (!vr)
+ vr = mlxsw_sp_vr_create(mlxsw_sp, tb_id);
return vr;
}
-static void mlxsw_sp_vr_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr)
+static void mlxsw_sp_vr_put(struct mlxsw_sp_vr *vr)
{
- /* Destroy virtual router entity in case the associated FIB is empty
- * and allow it to be used for other tables in future. Otherwise,
- * check if some prefix usage did not disappear and change tree if
- * that is the case. Note that in case new, smaller tree cannot be
- * allocated, the original one will be kept being used.
- */
- if (mlxsw_sp_prefix_usage_none(&vr->fib->prefix_usage))
- mlxsw_sp_vr_destroy(mlxsw_sp, vr);
- else
- mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, vr,
- &vr->fib->prefix_usage);
+ if (!vr->rif_count && list_empty(&vr->fib4->node_list))
+ mlxsw_sp_vr_destroy(vr);
}
static int mlxsw_sp_vrs_init(struct mlxsw_sp *mlxsw_sp)
@@ -627,14 +773,14 @@ static struct mlxsw_sp_neigh_entry *
mlxsw_sp_neigh_entry_create(struct mlxsw_sp *mlxsw_sp, struct neighbour *n)
{
struct mlxsw_sp_neigh_entry *neigh_entry;
- struct mlxsw_sp_rif *r;
+ struct mlxsw_sp_rif *rif;
int err;
- r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, n->dev);
- if (!r)
+ rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, n->dev);
+ if (!rif)
return ERR_PTR(-EINVAL);
- neigh_entry = mlxsw_sp_neigh_entry_alloc(mlxsw_sp, n, r->rif);
+ neigh_entry = mlxsw_sp_neigh_entry_alloc(mlxsw_sp, n, rif->rif_index);
if (!neigh_entry)
return ERR_PTR(-ENOMEM);
@@ -642,7 +788,7 @@ mlxsw_sp_neigh_entry_create(struct mlxsw_sp *mlxsw_sp, struct neighbour *n)
if (err)
goto err_neigh_entry_insert;
- list_add(&neigh_entry->rif_list_node, &r->neigh_list);
+ list_add(&neigh_entry->rif_list_node, &rif->neigh_list);
return neigh_entry;
@@ -1050,22 +1196,22 @@ static void mlxsw_sp_neigh_fini(struct mlxsw_sp *mlxsw_sp)
}
static int mlxsw_sp_neigh_rif_flush(struct mlxsw_sp *mlxsw_sp,
- const struct mlxsw_sp_rif *r)
+ const struct mlxsw_sp_rif *rif)
{
char rauht_pl[MLXSW_REG_RAUHT_LEN];
mlxsw_reg_rauht_pack(rauht_pl, MLXSW_REG_RAUHT_OP_WRITE_DELETE_ALL,
- r->rif, r->addr);
+ rif->rif_index, rif->addr);
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl);
}
static void mlxsw_sp_neigh_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_rif *r)
+ struct mlxsw_sp_rif *rif)
{
struct mlxsw_sp_neigh_entry *neigh_entry, *tmp;
- mlxsw_sp_neigh_rif_flush(mlxsw_sp, r);
- list_for_each_entry_safe(neigh_entry, tmp, &r->neigh_list,
+ mlxsw_sp_neigh_rif_flush(mlxsw_sp, rif);
+ list_for_each_entry_safe(neigh_entry, tmp, &rif->neigh_list,
rif_list_node)
mlxsw_sp_neigh_entry_destroy(mlxsw_sp, neigh_entry);
}
@@ -1082,7 +1228,7 @@ struct mlxsw_sp_nexthop {
*/
struct rhash_head ht_node;
struct mlxsw_sp_nexthop_key key;
- struct mlxsw_sp_rif *r;
+ struct mlxsw_sp_rif *rif;
u8 should_offload:1, /* set indicates this neigh is connected and
* should be put to KVD linear area of this group.
*/
@@ -1109,7 +1255,7 @@ struct mlxsw_sp_nexthop_group {
u16 ecmp_size;
u16 count;
struct mlxsw_sp_nexthop nexthops[0];
-#define nh_rif nexthops[0].r
+#define nh_rif nexthops[0].rif
};
static const struct rhashtable_params mlxsw_sp_nexthop_group_ht_params = {
@@ -1171,7 +1317,7 @@ mlxsw_sp_nexthop_lookup(struct mlxsw_sp *mlxsw_sp,
}
static int mlxsw_sp_adj_index_mass_update_vr(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_vr *vr,
+ const struct mlxsw_sp_fib *fib,
u32 adj_index, u16 ecmp_size,
u32 new_adj_index,
u16 new_ecmp_size)
@@ -1179,8 +1325,8 @@ static int mlxsw_sp_adj_index_mass_update_vr(struct mlxsw_sp *mlxsw_sp,
char raleu_pl[MLXSW_REG_RALEU_LEN];
mlxsw_reg_raleu_pack(raleu_pl,
- (enum mlxsw_reg_ralxx_protocol) vr->proto, vr->id,
- adj_index, ecmp_size, new_adj_index,
+ (enum mlxsw_reg_ralxx_protocol) fib->proto,
+ fib->vr->id, adj_index, ecmp_size, new_adj_index,
new_ecmp_size);
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raleu), raleu_pl);
}
@@ -1190,14 +1336,14 @@ static int mlxsw_sp_adj_index_mass_update(struct mlxsw_sp *mlxsw_sp,
u32 old_adj_index, u16 old_ecmp_size)
{
struct mlxsw_sp_fib_entry *fib_entry;
- struct mlxsw_sp_vr *vr = NULL;
+ struct mlxsw_sp_fib *fib = NULL;
int err;
list_for_each_entry(fib_entry, &nh_grp->fib_list, nexthop_group_node) {
- if (vr == fib_entry->fib_node->vr)
+ if (fib == fib_entry->fib_node->fib)
continue;
- vr = fib_entry->fib_node->vr;
- err = mlxsw_sp_adj_index_mass_update_vr(mlxsw_sp, vr,
+ fib = fib_entry->fib_node->fib;
+ err = mlxsw_sp_adj_index_mass_update_vr(mlxsw_sp, fib,
old_adj_index,
old_ecmp_size,
nh_grp->adj_index,
@@ -1280,7 +1426,6 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
bool old_adj_index_valid;
u32 old_adj_index;
u16 old_ecmp_size;
- int ret;
int i;
int err;
@@ -1318,15 +1463,14 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
*/
goto set_trap;
- ret = mlxsw_sp_kvdl_alloc(mlxsw_sp, ecmp_size);
- if (ret < 0) {
+ err = mlxsw_sp_kvdl_alloc(mlxsw_sp, ecmp_size, &adj_index);
+ if (err) {
/* We ran out of KVD linear space, just set the
* trap and let everything flow through kernel.
*/
dev_warn(mlxsw_sp->bus_info->dev, "Failed to allocate KVD linear area for nexthop group.\n");
goto set_trap;
}
- adj_index = ret;
old_adj_index_valid = nh_grp->adj_index_valid;
old_adj_index = nh_grp->adj_index;
old_ecmp_size = nh_grp->ecmp_size;
@@ -1399,22 +1543,22 @@ mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp *mlxsw_sp,
}
static void mlxsw_sp_nexthop_rif_init(struct mlxsw_sp_nexthop *nh,
- struct mlxsw_sp_rif *r)
+ struct mlxsw_sp_rif *rif)
{
- if (nh->r)
+ if (nh->rif)
return;
- nh->r = r;
- list_add(&nh->rif_list_node, &r->nexthop_list);
+ nh->rif = rif;
+ list_add(&nh->rif_list_node, &rif->nexthop_list);
}
static void mlxsw_sp_nexthop_rif_fini(struct mlxsw_sp_nexthop *nh)
{
- if (!nh->r)
+ if (!nh->rif)
return;
list_del(&nh->rif_list_node);
- nh->r = NULL;
+ nh->rif = NULL;
}
static int mlxsw_sp_nexthop_neigh_init(struct mlxsw_sp *mlxsw_sp,
@@ -1505,7 +1649,7 @@ static int mlxsw_sp_nexthop_init(struct mlxsw_sp *mlxsw_sp,
{
struct net_device *dev = fib_nh->nh_dev;
struct in_device *in_dev;
- struct mlxsw_sp_rif *r;
+ struct mlxsw_sp_rif *rif;
int err;
nh->nh_grp = nh_grp;
@@ -1514,15 +1658,18 @@ static int mlxsw_sp_nexthop_init(struct mlxsw_sp *mlxsw_sp,
if (err)
return err;
+ if (!dev)
+ return 0;
+
in_dev = __in_dev_get_rtnl(dev);
if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
fib_nh->nh_flags & RTNH_F_LINKDOWN)
return 0;
- r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
- if (!r)
+ rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+ if (!rif)
return 0;
- mlxsw_sp_nexthop_rif_init(nh, r);
+ mlxsw_sp_nexthop_rif_init(nh, rif);
err = mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh);
if (err)
@@ -1548,7 +1695,7 @@ static void mlxsw_sp_nexthop_event(struct mlxsw_sp *mlxsw_sp,
{
struct mlxsw_sp_nexthop_key key;
struct mlxsw_sp_nexthop *nh;
- struct mlxsw_sp_rif *r;
+ struct mlxsw_sp_rif *rif;
if (mlxsw_sp->router.aborted)
return;
@@ -1558,13 +1705,13 @@ static void mlxsw_sp_nexthop_event(struct mlxsw_sp *mlxsw_sp,
if (WARN_ON_ONCE(!nh))
return;
- r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, fib_nh->nh_dev);
- if (!r)
+ rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, fib_nh->nh_dev);
+ if (!rif)
return;
switch (event) {
case FIB_EVENT_NH_ADD:
- mlxsw_sp_nexthop_rif_init(nh, r);
+ mlxsw_sp_nexthop_rif_init(nh, rif);
mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh);
break;
case FIB_EVENT_NH_DEL:
@@ -1577,11 +1724,11 @@ static void mlxsw_sp_nexthop_event(struct mlxsw_sp *mlxsw_sp,
}
static void mlxsw_sp_nexthop_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_rif *r)
+ struct mlxsw_sp_rif *rif)
{
struct mlxsw_sp_nexthop *nh, *tmp;
- list_for_each_entry_safe(nh, tmp, &r->nexthop_list, rif_list_node) {
+ list_for_each_entry_safe(nh, tmp, &rif->nexthop_list, rif_list_node) {
mlxsw_sp_nexthop_neigh_fini(mlxsw_sp, nh);
mlxsw_sp_nexthop_rif_fini(nh);
mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp);
@@ -1699,7 +1846,7 @@ static void mlxsw_sp_fib_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
{
fib_entry->offloaded = true;
- switch (fib_entry->fib_node->vr->proto) {
+ switch (fib_entry->fib_node->fib->proto) {
case MLXSW_SP_L3_PROTO_IPV4:
fib_info_offload_inc(fib_entry->nh_group->key.fi);
break;
@@ -1711,7 +1858,7 @@ static void mlxsw_sp_fib_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
static void
mlxsw_sp_fib_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry)
{
- switch (fib_entry->fib_node->vr->proto) {
+ switch (fib_entry->fib_node->fib->proto) {
case MLXSW_SP_L3_PROTO_IPV4:
fib_info_offload_dec(fib_entry->nh_group->key.fi);
break;
@@ -1751,8 +1898,8 @@ static int mlxsw_sp_fib_entry_op4_remote(struct mlxsw_sp *mlxsw_sp,
enum mlxsw_reg_ralue_op op)
{
char ralue_pl[MLXSW_REG_RALUE_LEN];
+ struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib;
u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr;
- struct mlxsw_sp_vr *vr = fib_entry->fib_node->vr;
enum mlxsw_reg_ralue_trap_action trap_action;
u16 trap_id = 0;
u32 adjacency_index = 0;
@@ -1772,8 +1919,8 @@ static int mlxsw_sp_fib_entry_op4_remote(struct mlxsw_sp *mlxsw_sp,
}
mlxsw_reg_ralue_pack4(ralue_pl,
- (enum mlxsw_reg_ralxx_protocol) vr->proto, op,
- vr->id, fib_entry->fib_node->key.prefix_len,
+ (enum mlxsw_reg_ralxx_protocol) fib->proto, op,
+ fib->vr->id, fib_entry->fib_node->key.prefix_len,
*p_dip);
mlxsw_reg_ralue_act_remote_pack(ralue_pl, trap_action, trap_id,
adjacency_index, ecmp_size);
@@ -1784,27 +1931,28 @@ static int mlxsw_sp_fib_entry_op4_local(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib_entry *fib_entry,
enum mlxsw_reg_ralue_op op)
{
- struct mlxsw_sp_rif *r = fib_entry->nh_group->nh_rif;
+ struct mlxsw_sp_rif *rif = fib_entry->nh_group->nh_rif;
+ struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib;
enum mlxsw_reg_ralue_trap_action trap_action;
char ralue_pl[MLXSW_REG_RALUE_LEN];
u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr;
- struct mlxsw_sp_vr *vr = fib_entry->fib_node->vr;
u16 trap_id = 0;
- u16 rif = 0;
+ u16 rif_index = 0;
if (mlxsw_sp_fib_entry_should_offload(fib_entry)) {
trap_action = MLXSW_REG_RALUE_TRAP_ACTION_NOP;
- rif = r->rif;
+ rif_index = rif->rif_index;
} else {
trap_action = MLXSW_REG_RALUE_TRAP_ACTION_TRAP;
trap_id = MLXSW_TRAP_ID_RTR_INGRESS0;
}
mlxsw_reg_ralue_pack4(ralue_pl,
- (enum mlxsw_reg_ralxx_protocol) vr->proto, op,
- vr->id, fib_entry->fib_node->key.prefix_len,
+ (enum mlxsw_reg_ralxx_protocol) fib->proto, op,
+ fib->vr->id, fib_entry->fib_node->key.prefix_len,
*p_dip);
- mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, trap_id, rif);
+ mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, trap_id,
+ rif_index);
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
}
@@ -1812,13 +1960,13 @@ static int mlxsw_sp_fib_entry_op4_trap(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib_entry *fib_entry,
enum mlxsw_reg_ralue_op op)
{
+ struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib;
char ralue_pl[MLXSW_REG_RALUE_LEN];
u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr;
- struct mlxsw_sp_vr *vr = fib_entry->fib_node->vr;
mlxsw_reg_ralue_pack4(ralue_pl,
- (enum mlxsw_reg_ralxx_protocol) vr->proto, op,
- vr->id, fib_entry->fib_node->key.prefix_len,
+ (enum mlxsw_reg_ralxx_protocol) fib->proto, op,
+ fib->vr->id, fib_entry->fib_node->key.prefix_len,
*p_dip);
mlxsw_reg_ralue_act_ip2me_pack(ralue_pl);
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
@@ -1845,7 +1993,7 @@ static int mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp,
{
int err = -EINVAL;
- switch (fib_entry->fib_node->vr->proto) {
+ switch (fib_entry->fib_node->fib->proto) {
case MLXSW_SP_L3_PROTO_IPV4:
err = mlxsw_sp_fib_entry_op4(mlxsw_sp, fib_entry, op);
break;
@@ -1877,17 +2025,29 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp,
{
struct fib_info *fi = fen_info->fi;
- if (fen_info->type == RTN_LOCAL || fen_info->type == RTN_BROADCAST) {
+ switch (fen_info->type) {
+ case RTN_BROADCAST: /* fall through */
+ case RTN_LOCAL:
fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP;
return 0;
- }
- if (fen_info->type != RTN_UNICAST)
- return -EINVAL;
- if (fi->fib_nh->nh_scope != RT_SCOPE_LINK)
+ case RTN_UNREACHABLE: /* fall through */
+ case RTN_BLACKHOLE: /* fall through */
+ case RTN_PROHIBIT:
+ /* Packets hitting these routes need to be trapped, but
+ * can do so with a lower priority than packets directed
+ * at the host, so use action type local instead of trap.
+ */
fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL;
- else
- fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE;
- return 0;
+ return 0;
+ case RTN_UNICAST:
+ if (fi->fib_nh->nh_scope != RT_SCOPE_LINK)
+ fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL;
+ else
+ fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE;
+ return 0;
+ default:
+ return -EINVAL;
+ }
}
static struct mlxsw_sp_fib_entry *
@@ -1996,7 +2156,7 @@ mlxsw_sp_fib_node_lookup(struct mlxsw_sp_fib *fib, const void *addr,
}
static struct mlxsw_sp_fib_node *
-mlxsw_sp_fib_node_create(struct mlxsw_sp_vr *vr, const void *addr,
+mlxsw_sp_fib_node_create(struct mlxsw_sp_fib *fib, const void *addr,
size_t addr_len, unsigned char prefix_len)
{
struct mlxsw_sp_fib_node *fib_node;
@@ -2006,18 +2166,15 @@ mlxsw_sp_fib_node_create(struct mlxsw_sp_vr *vr, const void *addr,
return NULL;
INIT_LIST_HEAD(&fib_node->entry_list);
- list_add(&fib_node->list, &vr->fib->node_list);
+ list_add(&fib_node->list, &fib->node_list);
memcpy(fib_node->key.addr, addr, addr_len);
fib_node->key.prefix_len = prefix_len;
- mlxsw_sp_fib_node_insert(vr->fib, fib_node);
- fib_node->vr = vr;
return fib_node;
}
static void mlxsw_sp_fib_node_destroy(struct mlxsw_sp_fib_node *fib_node)
{
- mlxsw_sp_fib_node_remove(fib_node->vr->fib, fib_node);
list_del(&fib_node->list);
WARN_ON(!list_empty(&fib_node->entry_list));
kfree(fib_node);
@@ -2034,7 +2191,7 @@ mlxsw_sp_fib_node_entry_is_first(const struct mlxsw_sp_fib_node *fib_node,
static void mlxsw_sp_fib_node_prefix_inc(struct mlxsw_sp_fib_node *fib_node)
{
unsigned char prefix_len = fib_node->key.prefix_len;
- struct mlxsw_sp_fib *fib = fib_node->vr->fib;
+ struct mlxsw_sp_fib *fib = fib_node->fib;
if (fib->prefix_ref_count[prefix_len]++ == 0)
mlxsw_sp_prefix_usage_set(&fib->prefix_usage, prefix_len);
@@ -2043,32 +2200,98 @@ static void mlxsw_sp_fib_node_prefix_inc(struct mlxsw_sp_fib_node *fib_node)
static void mlxsw_sp_fib_node_prefix_dec(struct mlxsw_sp_fib_node *fib_node)
{
unsigned char prefix_len = fib_node->key.prefix_len;
- struct mlxsw_sp_fib *fib = fib_node->vr->fib;
+ struct mlxsw_sp_fib *fib = fib_node->fib;
if (--fib->prefix_ref_count[prefix_len] == 0)
mlxsw_sp_prefix_usage_clear(&fib->prefix_usage, prefix_len);
}
+static int mlxsw_sp_fib_node_init(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_node *fib_node,
+ struct mlxsw_sp_fib *fib)
+{
+ struct mlxsw_sp_prefix_usage req_prefix_usage;
+ struct mlxsw_sp_lpm_tree *lpm_tree;
+ int err;
+
+ err = mlxsw_sp_fib_node_insert(fib, fib_node);
+ if (err)
+ return err;
+ fib_node->fib = fib;
+
+ mlxsw_sp_prefix_usage_cpy(&req_prefix_usage, &fib->prefix_usage);
+ mlxsw_sp_prefix_usage_set(&req_prefix_usage, fib_node->key.prefix_len);
+
+ if (!mlxsw_sp_prefix_usage_none(&fib->prefix_usage)) {
+ err = mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, fib,
+ &req_prefix_usage);
+ if (err)
+ goto err_tree_check;
+ } else {
+ lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage,
+ fib->proto);
+ if (IS_ERR(lpm_tree))
+ return PTR_ERR(lpm_tree);
+ fib->lpm_tree = lpm_tree;
+ err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, fib);
+ if (err)
+ goto err_tree_bind;
+ }
+
+ mlxsw_sp_fib_node_prefix_inc(fib_node);
+
+ return 0;
+
+err_tree_bind:
+ fib->lpm_tree = NULL;
+ mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree);
+err_tree_check:
+ fib_node->fib = NULL;
+ mlxsw_sp_fib_node_remove(fib, fib_node);
+ return err;
+}
+
+static void mlxsw_sp_fib_node_fini(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_node *fib_node)
+{
+ struct mlxsw_sp_lpm_tree *lpm_tree = fib_node->fib->lpm_tree;
+ struct mlxsw_sp_fib *fib = fib_node->fib;
+
+ mlxsw_sp_fib_node_prefix_dec(fib_node);
+
+ if (mlxsw_sp_prefix_usage_none(&fib->prefix_usage)) {
+ mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, fib);
+ fib->lpm_tree = NULL;
+ mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree);
+ } else {
+ mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, fib, &fib->prefix_usage);
+ }
+
+ fib_node->fib = NULL;
+ mlxsw_sp_fib_node_remove(fib, fib_node);
+}
+
static struct mlxsw_sp_fib_node *
mlxsw_sp_fib4_node_get(struct mlxsw_sp *mlxsw_sp,
const struct fib_entry_notifier_info *fen_info)
{
struct mlxsw_sp_fib_node *fib_node;
+ struct mlxsw_sp_fib *fib;
struct mlxsw_sp_vr *vr;
int err;
- vr = mlxsw_sp_vr_get(mlxsw_sp, fen_info->dst_len, fen_info->tb_id,
- MLXSW_SP_L3_PROTO_IPV4);
+ vr = mlxsw_sp_vr_get(mlxsw_sp, fen_info->tb_id);
if (IS_ERR(vr))
return ERR_CAST(vr);
+ fib = mlxsw_sp_vr_fib(vr, MLXSW_SP_L3_PROTO_IPV4);
- fib_node = mlxsw_sp_fib_node_lookup(vr->fib, &fen_info->dst,
+ fib_node = mlxsw_sp_fib_node_lookup(fib, &fen_info->dst,
sizeof(fen_info->dst),
fen_info->dst_len);
if (fib_node)
return fib_node;
- fib_node = mlxsw_sp_fib_node_create(vr, &fen_info->dst,
+ fib_node = mlxsw_sp_fib_node_create(fib, &fen_info->dst,
sizeof(fen_info->dst),
fen_info->dst_len);
if (!fib_node) {
@@ -2076,22 +2299,29 @@ mlxsw_sp_fib4_node_get(struct mlxsw_sp *mlxsw_sp,
goto err_fib_node_create;
}
+ err = mlxsw_sp_fib_node_init(mlxsw_sp, fib_node, fib);
+ if (err)
+ goto err_fib_node_init;
+
return fib_node;
+err_fib_node_init:
+ mlxsw_sp_fib_node_destroy(fib_node);
err_fib_node_create:
- mlxsw_sp_vr_put(mlxsw_sp, vr);
+ mlxsw_sp_vr_put(vr);
return ERR_PTR(err);
}
static void mlxsw_sp_fib4_node_put(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib_node *fib_node)
{
- struct mlxsw_sp_vr *vr = fib_node->vr;
+ struct mlxsw_sp_vr *vr = fib_node->fib->vr;
if (!list_empty(&fib_node->entry_list))
return;
+ mlxsw_sp_fib_node_fini(mlxsw_sp, fib_node);
mlxsw_sp_fib_node_destroy(fib_node);
- mlxsw_sp_vr_put(mlxsw_sp, vr);
+ mlxsw_sp_vr_put(vr);
}
static struct mlxsw_sp_fib_entry *
@@ -2236,8 +2466,6 @@ static int mlxsw_sp_fib4_node_entry_link(struct mlxsw_sp *mlxsw_sp,
if (err)
goto err_fib4_node_entry_add;
- mlxsw_sp_fib_node_prefix_inc(fib_node);
-
return 0;
err_fib4_node_entry_add:
@@ -2251,7 +2479,6 @@ mlxsw_sp_fib4_node_entry_unlink(struct mlxsw_sp *mlxsw_sp,
{
struct mlxsw_sp_fib_node *fib_node = fib_entry->fib_node;
- mlxsw_sp_fib_node_prefix_dec(fib_node);
mlxsw_sp_fib4_node_entry_del(mlxsw_sp, fib_node, fib_entry);
mlxsw_sp_fib4_node_list_remove(fib_entry);
}
@@ -2340,9 +2567,7 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp)
{
char ralta_pl[MLXSW_REG_RALTA_LEN];
char ralst_pl[MLXSW_REG_RALST_LEN];
- char raltb_pl[MLXSW_REG_RALTB_LEN];
- char ralue_pl[MLXSW_REG_RALUE_LEN];
- int err;
+ int i, err;
mlxsw_reg_ralta_pack(ralta_pl, true, MLXSW_REG_RALXX_PROTOCOL_IPV4,
MLXSW_SP_LPM_TREE_MIN);
@@ -2355,16 +2580,33 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp)
if (err)
return err;
- mlxsw_reg_raltb_pack(raltb_pl, 0, MLXSW_REG_RALXX_PROTOCOL_IPV4,
- MLXSW_SP_LPM_TREE_MIN);
- err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl);
- if (err)
- return err;
+ for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) {
+ struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[i];
+ char raltb_pl[MLXSW_REG_RALTB_LEN];
+ char ralue_pl[MLXSW_REG_RALUE_LEN];
- mlxsw_reg_ralue_pack4(ralue_pl, MLXSW_SP_L3_PROTO_IPV4,
- MLXSW_REG_RALUE_OP_WRITE_WRITE, 0, 0, 0);
- mlxsw_reg_ralue_act_ip2me_pack(ralue_pl);
- return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
+ if (!mlxsw_sp_vr_is_used(vr))
+ continue;
+
+ mlxsw_reg_raltb_pack(raltb_pl, vr->id,
+ MLXSW_REG_RALXX_PROTOCOL_IPV4,
+ MLXSW_SP_LPM_TREE_MIN);
+ err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb),
+ raltb_pl);
+ if (err)
+ return err;
+
+ mlxsw_reg_ralue_pack4(ralue_pl, MLXSW_SP_L3_PROTO_IPV4,
+ MLXSW_REG_RALUE_OP_WRITE_WRITE, vr->id, 0,
+ 0);
+ mlxsw_reg_ralue_act_ip2me_pack(ralue_pl);
+ err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue),
+ ralue_pl);
+ if (err)
+ return err;
+ }
+
+ return 0;
}
static void mlxsw_sp_fib4_node_flush(struct mlxsw_sp *mlxsw_sp,
@@ -2390,7 +2632,7 @@ static void mlxsw_sp_fib4_node_flush(struct mlxsw_sp *mlxsw_sp,
static void mlxsw_sp_fib_node_flush(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib_node *fib_node)
{
- switch (fib_node->vr->proto) {
+ switch (fib_node->fib->proto) {
case MLXSW_SP_L3_PROTO_IPV4:
mlxsw_sp_fib4_node_flush(mlxsw_sp, fib_node);
break;
@@ -2400,26 +2642,32 @@ static void mlxsw_sp_fib_node_flush(struct mlxsw_sp *mlxsw_sp,
}
}
+static void mlxsw_sp_vr_fib_flush(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_vr *vr,
+ enum mlxsw_sp_l3proto proto)
+{
+ struct mlxsw_sp_fib *fib = mlxsw_sp_vr_fib(vr, proto);
+ struct mlxsw_sp_fib_node *fib_node, *tmp;
+
+ list_for_each_entry_safe(fib_node, tmp, &fib->node_list, list) {
+ bool do_break = &tmp->list == &fib->node_list;
+
+ mlxsw_sp_fib_node_flush(mlxsw_sp, fib_node);
+ if (do_break)
+ break;
+ }
+}
+
static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp)
{
- struct mlxsw_sp_fib_node *fib_node, *tmp;
- struct mlxsw_sp_vr *vr;
int i;
for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) {
- vr = &mlxsw_sp->router.vrs[i];
+ struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[i];
- if (!vr->used)
+ if (!mlxsw_sp_vr_is_used(vr))
continue;
-
- list_for_each_entry_safe(fib_node, tmp, &vr->fib->node_list,
- list) {
- bool do_break = &tmp->list == &vr->fib->node_list;
-
- mlxsw_sp_fib_node_flush(mlxsw_sp, fib_node);
- if (do_break)
- break;
- }
+ mlxsw_sp_vr_fib_flush(mlxsw_sp, vr, MLXSW_SP_L3_PROTO_IPV4);
}
}
@@ -2437,6 +2685,122 @@ static void mlxsw_sp_router_fib4_abort(struct mlxsw_sp *mlxsw_sp)
dev_warn(mlxsw_sp->bus_info->dev, "Failed to set abort trap.\n");
}
+struct mlxsw_sp_fib_event_work {
+ struct work_struct work;
+ union {
+ struct fib_entry_notifier_info fen_info;
+ struct fib_rule_notifier_info fr_info;
+ struct fib_nh_notifier_info fnh_info;
+ };
+ struct mlxsw_sp *mlxsw_sp;
+ unsigned long event;
+};
+
+static void mlxsw_sp_router_fib_event_work(struct work_struct *work)
+{
+ struct mlxsw_sp_fib_event_work *fib_work =
+ container_of(work, struct mlxsw_sp_fib_event_work, work);
+ struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp;
+ struct fib_rule *rule;
+ bool replace, append;
+ int err;
+
+ /* Protect internal structures from changes */
+ rtnl_lock();
+ switch (fib_work->event) {
+ case FIB_EVENT_ENTRY_REPLACE: /* fall through */
+ case FIB_EVENT_ENTRY_APPEND: /* fall through */
+ case FIB_EVENT_ENTRY_ADD:
+ replace = fib_work->event == FIB_EVENT_ENTRY_REPLACE;
+ append = fib_work->event == FIB_EVENT_ENTRY_APPEND;
+ err = mlxsw_sp_router_fib4_add(mlxsw_sp, &fib_work->fen_info,
+ replace, append);
+ if (err)
+ mlxsw_sp_router_fib4_abort(mlxsw_sp);
+ fib_info_put(fib_work->fen_info.fi);
+ break;
+ case FIB_EVENT_ENTRY_DEL:
+ mlxsw_sp_router_fib4_del(mlxsw_sp, &fib_work->fen_info);
+ fib_info_put(fib_work->fen_info.fi);
+ break;
+ case FIB_EVENT_RULE_ADD: /* fall through */
+ case FIB_EVENT_RULE_DEL:
+ rule = fib_work->fr_info.rule;
+ if (!fib4_rule_default(rule) && !rule->l3mdev)
+ mlxsw_sp_router_fib4_abort(mlxsw_sp);
+ fib_rule_put(rule);
+ break;
+ case FIB_EVENT_NH_ADD: /* fall through */
+ case FIB_EVENT_NH_DEL:
+ mlxsw_sp_nexthop_event(mlxsw_sp, fib_work->event,
+ fib_work->fnh_info.fib_nh);
+ fib_info_put(fib_work->fnh_info.fib_nh->nh_parent);
+ break;
+ }
+ rtnl_unlock();
+ kfree(fib_work);
+}
+
+/* Called with rcu_read_lock() */
+static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
+ unsigned long event, void *ptr)
+{
+ struct mlxsw_sp *mlxsw_sp = container_of(nb, struct mlxsw_sp, fib_nb);
+ struct mlxsw_sp_fib_event_work *fib_work;
+ struct fib_notifier_info *info = ptr;
+
+ if (!net_eq(info->net, &init_net))
+ return NOTIFY_DONE;
+
+ fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC);
+ if (WARN_ON(!fib_work))
+ return NOTIFY_BAD;
+
+ INIT_WORK(&fib_work->work, mlxsw_sp_router_fib_event_work);
+ fib_work->mlxsw_sp = mlxsw_sp;
+ fib_work->event = event;
+
+ switch (event) {
+ case FIB_EVENT_ENTRY_REPLACE: /* fall through */
+ case FIB_EVENT_ENTRY_APPEND: /* fall through */
+ case FIB_EVENT_ENTRY_ADD: /* fall through */
+ case FIB_EVENT_ENTRY_DEL:
+ memcpy(&fib_work->fen_info, ptr, sizeof(fib_work->fen_info));
+ /* Take referece on fib_info to prevent it from being
+ * freed while work is queued. Release it afterwards.
+ */
+ fib_info_hold(fib_work->fen_info.fi);
+ break;
+ case FIB_EVENT_RULE_ADD: /* fall through */
+ case FIB_EVENT_RULE_DEL:
+ memcpy(&fib_work->fr_info, ptr, sizeof(fib_work->fr_info));
+ fib_rule_get(fib_work->fr_info.rule);
+ break;
+ case FIB_EVENT_NH_ADD: /* fall through */
+ case FIB_EVENT_NH_DEL:
+ memcpy(&fib_work->fnh_info, ptr, sizeof(fib_work->fnh_info));
+ fib_info_hold(fib_work->fnh_info.fib_nh->nh_parent);
+ break;
+ }
+
+ mlxsw_core_schedule_work(&fib_work->work);
+
+ return NOTIFY_DONE;
+}
+
+static struct mlxsw_sp_rif *
+mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
+ const struct net_device *dev)
+{
+ int i;
+
+ for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++)
+ if (mlxsw_sp->rifs[i] && mlxsw_sp->rifs[i]->dev == dev)
+ return mlxsw_sp->rifs[i];
+
+ return NULL;
+}
+
static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif)
{
char ritr_pl[MLXSW_REG_RITR_LEN];
@@ -2451,12 +2815,699 @@ static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif)
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
}
-void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp_rif *r)
+static void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_rif *rif)
{
- mlxsw_sp_router_rif_disable(mlxsw_sp, r->rif);
- mlxsw_sp_nexthop_rif_gone_sync(mlxsw_sp, r);
- mlxsw_sp_neigh_rif_gone_sync(mlxsw_sp, r);
+ mlxsw_sp_router_rif_disable(mlxsw_sp, rif->rif_index);
+ mlxsw_sp_nexthop_rif_gone_sync(mlxsw_sp, rif);
+ mlxsw_sp_neigh_rif_gone_sync(mlxsw_sp, rif);
+}
+
+static bool mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *rif,
+ const struct in_device *in_dev,
+ unsigned long event)
+{
+ switch (event) {
+ case NETDEV_UP:
+ if (!rif)
+ return true;
+ return false;
+ case NETDEV_DOWN:
+ if (rif && !in_dev->ifa_list &&
+ !netif_is_l3_slave(rif->dev))
+ return true;
+ /* It is possible we already removed the RIF ourselves
+ * if it was assigned to a netdev that is now a bridge
+ * or LAG slave.
+ */
+ return false;
+ }
+
+ return false;
+}
+
+#define MLXSW_SP_INVALID_INDEX_RIF 0xffff
+static int mlxsw_sp_avail_rif_get(struct mlxsw_sp *mlxsw_sp)
+{
+ int i;
+
+ for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++)
+ if (!mlxsw_sp->rifs[i])
+ return i;
+
+ return MLXSW_SP_INVALID_INDEX_RIF;
+}
+
+static void mlxsw_sp_vport_rif_sp_attr_get(struct mlxsw_sp_port *mlxsw_sp_vport,
+ bool *p_lagged, u16 *p_system_port)
+{
+ u8 local_port = mlxsw_sp_vport->local_port;
+
+ *p_lagged = mlxsw_sp_vport->lagged;
+ *p_system_port = *p_lagged ? mlxsw_sp_vport->lag_id : local_port;
+}
+
+static int mlxsw_sp_vport_rif_sp_op(struct mlxsw_sp_port *mlxsw_sp_vport,
+ u16 vr_id, struct net_device *l3_dev,
+ u16 rif_index, bool create)
+{
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
+ bool lagged = mlxsw_sp_vport->lagged;
+ char ritr_pl[MLXSW_REG_RITR_LEN];
+ u16 system_port;
+
+ mlxsw_reg_ritr_pack(ritr_pl, create, MLXSW_REG_RITR_SP_IF, rif_index,
+ vr_id, l3_dev->mtu, l3_dev->dev_addr);
+
+ mlxsw_sp_vport_rif_sp_attr_get(mlxsw_sp_vport, &lagged, &system_port);
+ mlxsw_reg_ritr_sp_if_pack(ritr_pl, lagged, system_port,
+ mlxsw_sp_vport_vid_get(mlxsw_sp_vport));
+
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport);
+
+static u16 mlxsw_sp_rif_sp_to_fid(u16 rif_index)
+{
+ return MLXSW_SP_RFID_BASE + rif_index;
+}
+
+static struct mlxsw_sp_fid *
+mlxsw_sp_rfid_alloc(u16 fid, struct net_device *l3_dev)
+{
+ struct mlxsw_sp_fid *f;
+
+ f = kzalloc(sizeof(*f), GFP_KERNEL);
+ if (!f)
+ return NULL;
+
+ f->leave = mlxsw_sp_vport_rif_sp_leave;
+ f->ref_count = 0;
+ f->dev = l3_dev;
+ f->fid = fid;
+
+ return f;
+}
+
+static struct mlxsw_sp_rif *
+mlxsw_sp_rif_alloc(u16 rif_index, u16 vr_id, struct net_device *l3_dev,
+ struct mlxsw_sp_fid *f)
+{
+ struct mlxsw_sp_rif *rif;
+
+ rif = kzalloc(sizeof(*rif), GFP_KERNEL);
+ if (!rif)
+ return NULL;
+
+ INIT_LIST_HEAD(&rif->nexthop_list);
+ INIT_LIST_HEAD(&rif->neigh_list);
+ ether_addr_copy(rif->addr, l3_dev->dev_addr);
+ rif->mtu = l3_dev->mtu;
+ rif->vr_id = vr_id;
+ rif->dev = l3_dev;
+ rif->rif_index = rif_index;
+ rif->f = f;
+
+ return rif;
+}
+
+u16 mlxsw_sp_rif_index(const struct mlxsw_sp_rif *rif)
+{
+ return rif->rif_index;
+}
+
+int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif)
+{
+ return rif->dev->ifindex;
+}
+
+static struct mlxsw_sp_rif *
+mlxsw_sp_vport_rif_sp_create(struct mlxsw_sp_port *mlxsw_sp_vport,
+ struct net_device *l3_dev)
+{
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
+ u32 tb_id = l3mdev_fib_table(l3_dev);
+ struct mlxsw_sp_vr *vr;
+ struct mlxsw_sp_fid *f;
+ struct mlxsw_sp_rif *rif;
+ u16 fid, rif_index;
+ int err;
+
+ rif_index = mlxsw_sp_avail_rif_get(mlxsw_sp);
+ if (rif_index == MLXSW_SP_INVALID_INDEX_RIF)
+ return ERR_PTR(-ERANGE);
+
+ vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN);
+ if (IS_ERR(vr))
+ return ERR_CAST(vr);
+
+ err = mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev,
+ rif_index, true);
+ if (err)
+ goto err_vport_rif_sp_op;
+
+ fid = mlxsw_sp_rif_sp_to_fid(rif_index);
+ err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, true);
+ if (err)
+ goto err_rif_fdb_op;
+
+ f = mlxsw_sp_rfid_alloc(fid, l3_dev);
+ if (!f) {
+ err = -ENOMEM;
+ goto err_rfid_alloc;
+ }
+
+ rif = mlxsw_sp_rif_alloc(rif_index, vr->id, l3_dev, f);
+ if (!rif) {
+ err = -ENOMEM;
+ goto err_rif_alloc;
+ }
+
+ if (devlink_dpipe_table_counter_enabled(priv_to_devlink(mlxsw_sp->core),
+ MLXSW_SP_DPIPE_TABLE_NAME_ERIF)) {
+ err = mlxsw_sp_rif_counter_alloc(mlxsw_sp, rif,
+ MLXSW_SP_RIF_COUNTER_EGRESS);
+ if (err)
+ netdev_dbg(mlxsw_sp_vport->dev,
+ "Counter alloc Failed err=%d\n", err);
+ }
+
+ f->rif = rif;
+ mlxsw_sp->rifs[rif_index] = rif;
+ vr->rif_count++;
+
+ return rif;
+
+err_rif_alloc:
+ kfree(f);
+err_rfid_alloc:
+ mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false);
+err_rif_fdb_op:
+ mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev, rif_index,
+ false);
+err_vport_rif_sp_op:
+ mlxsw_sp_vr_put(vr);
+ return ERR_PTR(err);
+}
+
+static void mlxsw_sp_vport_rif_sp_destroy(struct mlxsw_sp_port *mlxsw_sp_vport,
+ struct mlxsw_sp_rif *rif)
+{
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
+ struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[rif->vr_id];
+ struct net_device *l3_dev = rif->dev;
+ struct mlxsw_sp_fid *f = rif->f;
+ u16 rif_index = rif->rif_index;
+ u16 fid = f->fid;
+
+ mlxsw_sp_router_rif_gone_sync(mlxsw_sp, rif);
+
+ mlxsw_sp_rif_counter_free(mlxsw_sp, rif, MLXSW_SP_RIF_COUNTER_EGRESS);
+ mlxsw_sp_rif_counter_free(mlxsw_sp, rif, MLXSW_SP_RIF_COUNTER_INGRESS);
+
+ vr->rif_count--;
+ mlxsw_sp->rifs[rif_index] = NULL;
+ f->rif = NULL;
+
+ kfree(rif);
+
+ kfree(f);
+
+ mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false);
+
+ mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev, rif_index,
+ false);
+ mlxsw_sp_vr_put(vr);
+}
+
+static int mlxsw_sp_vport_rif_sp_join(struct mlxsw_sp_port *mlxsw_sp_vport,
+ struct net_device *l3_dev)
+{
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
+ struct mlxsw_sp_rif *rif;
+
+ rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
+ if (!rif) {
+ rif = mlxsw_sp_vport_rif_sp_create(mlxsw_sp_vport, l3_dev);
+ if (IS_ERR(rif))
+ return PTR_ERR(rif);
+ }
+
+ mlxsw_sp_vport_fid_set(mlxsw_sp_vport, rif->f);
+ rif->f->ref_count++;
+
+ netdev_dbg(mlxsw_sp_vport->dev, "Joined FID=%d\n", rif->f->fid);
+
+ return 0;
+}
+
+static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport)
+{
+ struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport);
+
+ netdev_dbg(mlxsw_sp_vport->dev, "Left FID=%d\n", f->fid);
+
+ mlxsw_sp_vport_fid_set(mlxsw_sp_vport, NULL);
+ if (--f->ref_count == 0)
+ mlxsw_sp_vport_rif_sp_destroy(mlxsw_sp_vport, f->rif);
+}
+
+static int mlxsw_sp_inetaddr_vport_event(struct net_device *l3_dev,
+ struct net_device *port_dev,
+ unsigned long event, u16 vid)
+{
+ struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(port_dev);
+ struct mlxsw_sp_port *mlxsw_sp_vport;
+
+ mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid);
+ if (WARN_ON(!mlxsw_sp_vport))
+ return -EINVAL;
+
+ switch (event) {
+ case NETDEV_UP:
+ return mlxsw_sp_vport_rif_sp_join(mlxsw_sp_vport, l3_dev);
+ case NETDEV_DOWN:
+ mlxsw_sp_vport_rif_sp_leave(mlxsw_sp_vport);
+ break;
+ }
+
+ return 0;
+}
+
+static int mlxsw_sp_inetaddr_port_event(struct net_device *port_dev,
+ unsigned long event)
+{
+ if (netif_is_bridge_port(port_dev) || netif_is_lag_port(port_dev))
+ return 0;
+
+ return mlxsw_sp_inetaddr_vport_event(port_dev, port_dev, event, 1);
+}
+
+static int __mlxsw_sp_inetaddr_lag_event(struct net_device *l3_dev,
+ struct net_device *lag_dev,
+ unsigned long event, u16 vid)
+{
+ struct net_device *port_dev;
+ struct list_head *iter;
+ int err;
+
+ netdev_for_each_lower_dev(lag_dev, port_dev, iter) {
+ if (mlxsw_sp_port_dev_check(port_dev)) {
+ err = mlxsw_sp_inetaddr_vport_event(l3_dev, port_dev,
+ event, vid);
+ if (err)
+ return err;
+ }
+ }
+
+ return 0;
+}
+
+static int mlxsw_sp_inetaddr_lag_event(struct net_device *lag_dev,
+ unsigned long event)
+{
+ if (netif_is_bridge_port(lag_dev))
+ return 0;
+
+ return __mlxsw_sp_inetaddr_lag_event(lag_dev, lag_dev, event, 1);
+}
+
+static struct mlxsw_sp_fid *mlxsw_sp_bridge_fid_get(struct mlxsw_sp *mlxsw_sp,
+ struct net_device *l3_dev)
+{
+ u16 fid;
+
+ if (is_vlan_dev(l3_dev))
+ fid = vlan_dev_vlan_id(l3_dev);
+ else if (mlxsw_sp->master_bridge.dev == l3_dev)
+ fid = 1;
+ else
+ return mlxsw_sp_vfid_find(mlxsw_sp, l3_dev);
+
+ return mlxsw_sp_fid_find(mlxsw_sp, fid);
+}
+
+static u8 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp)
+{
+ return mlxsw_core_max_ports(mlxsw_sp->core) + 1;
+}
+
+static enum mlxsw_flood_table_type mlxsw_sp_flood_table_type_get(u16 fid)
+{
+ return mlxsw_sp_fid_is_vfid(fid) ? MLXSW_REG_SFGC_TABLE_TYPE_FID :
+ MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST;
+}
+
+static u16 mlxsw_sp_flood_table_index_get(u16 fid)
+{
+ return mlxsw_sp_fid_is_vfid(fid) ? mlxsw_sp_fid_to_vfid(fid) : fid;
+}
+
+static int mlxsw_sp_router_port_flood_set(struct mlxsw_sp *mlxsw_sp, u16 fid,
+ bool set)
+{
+ u8 router_port = mlxsw_sp_router_port(mlxsw_sp);
+ enum mlxsw_flood_table_type table_type;
+ char *sftr_pl;
+ u16 index;
+ int err;
+
+ sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL);
+ if (!sftr_pl)
+ return -ENOMEM;
+
+ table_type = mlxsw_sp_flood_table_type_get(fid);
+ index = mlxsw_sp_flood_table_index_get(fid);
+ mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_BC, index, table_type,
+ 1, router_port, set);
+ err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl);
+
+ kfree(sftr_pl);
+ return err;
+}
+
+static enum mlxsw_reg_ritr_if_type mlxsw_sp_rif_type_get(u16 fid)
+{
+ if (mlxsw_sp_fid_is_vfid(fid))
+ return MLXSW_REG_RITR_FID_IF;
+ else
+ return MLXSW_REG_RITR_VLAN_IF;
+}
+
+static int mlxsw_sp_rif_bridge_op(struct mlxsw_sp *mlxsw_sp, u16 vr_id,
+ struct net_device *l3_dev,
+ u16 fid, u16 rif,
+ bool create)
+{
+ enum mlxsw_reg_ritr_if_type rif_type;
+ char ritr_pl[MLXSW_REG_RITR_LEN];
+
+ rif_type = mlxsw_sp_rif_type_get(fid);
+ mlxsw_reg_ritr_pack(ritr_pl, create, rif_type, rif, vr_id, l3_dev->mtu,
+ l3_dev->dev_addr);
+ mlxsw_reg_ritr_fid_set(ritr_pl, rif_type, fid);
+
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp,
+ struct net_device *l3_dev,
+ struct mlxsw_sp_fid *f)
+{
+ u32 tb_id = l3mdev_fib_table(l3_dev);
+ struct mlxsw_sp_rif *rif;
+ struct mlxsw_sp_vr *vr;
+ u16 rif_index;
+ int err;
+
+ rif_index = mlxsw_sp_avail_rif_get(mlxsw_sp);
+ if (rif_index == MLXSW_SP_INVALID_INDEX_RIF)
+ return -ERANGE;
+
+ vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN);
+ if (IS_ERR(vr))
+ return PTR_ERR(vr);
+
+ err = mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, true);
+ if (err)
+ goto err_port_flood_set;
+
+ err = mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid,
+ rif_index, true);
+ if (err)
+ goto err_rif_bridge_op;
+
+ err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, true);
+ if (err)
+ goto err_rif_fdb_op;
+
+ rif = mlxsw_sp_rif_alloc(rif_index, vr->id, l3_dev, f);
+ if (!rif) {
+ err = -ENOMEM;
+ goto err_rif_alloc;
+ }
+
+ f->rif = rif;
+ mlxsw_sp->rifs[rif_index] = rif;
+ vr->rif_count++;
+
+ netdev_dbg(l3_dev, "RIF=%d created\n", rif_index);
+
+ return 0;
+
+err_rif_alloc:
+ mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false);
+err_rif_fdb_op:
+ mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid, rif_index,
+ false);
+err_rif_bridge_op:
+ mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false);
+err_port_flood_set:
+ mlxsw_sp_vr_put(vr);
+ return err;
+}
+
+void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_rif *rif)
+{
+ struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[rif->vr_id];
+ struct net_device *l3_dev = rif->dev;
+ struct mlxsw_sp_fid *f = rif->f;
+ u16 rif_index = rif->rif_index;
+
+ mlxsw_sp_router_rif_gone_sync(mlxsw_sp, rif);
+
+ vr->rif_count--;
+ mlxsw_sp->rifs[rif_index] = NULL;
+ f->rif = NULL;
+
+ kfree(rif);
+
+ mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false);
+
+ mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid, rif_index,
+ false);
+
+ mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false);
+
+ mlxsw_sp_vr_put(vr);
+
+ netdev_dbg(l3_dev, "RIF=%d destroyed\n", rif_index);
+}
+
+static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev,
+ struct net_device *br_dev,
+ unsigned long event)
+{
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev);
+ struct mlxsw_sp_fid *f;
+
+ /* FID can either be an actual FID if the L3 device is the
+ * VLAN-aware bridge or a VLAN device on top. Otherwise, the
+ * L3 device is a VLAN-unaware bridge and we get a vFID.
+ */
+ f = mlxsw_sp_bridge_fid_get(mlxsw_sp, l3_dev);
+ if (WARN_ON(!f))
+ return -EINVAL;
+
+ switch (event) {
+ case NETDEV_UP:
+ return mlxsw_sp_rif_bridge_create(mlxsw_sp, l3_dev, f);
+ case NETDEV_DOWN:
+ mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif);
+ break;
+ }
+
+ return 0;
+}
+
+static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev,
+ unsigned long event)
+{
+ struct net_device *real_dev = vlan_dev_real_dev(vlan_dev);
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(vlan_dev);
+ u16 vid = vlan_dev_vlan_id(vlan_dev);
+
+ if (mlxsw_sp_port_dev_check(real_dev))
+ return mlxsw_sp_inetaddr_vport_event(vlan_dev, real_dev, event,
+ vid);
+ else if (netif_is_lag_master(real_dev))
+ return __mlxsw_sp_inetaddr_lag_event(vlan_dev, real_dev, event,
+ vid);
+ else if (netif_is_bridge_master(real_dev) &&
+ mlxsw_sp->master_bridge.dev == real_dev)
+ return mlxsw_sp_inetaddr_bridge_event(vlan_dev, real_dev,
+ event);
+
+ return 0;
+}
+
+int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct in_ifaddr *ifa = (struct in_ifaddr *) ptr;
+ struct net_device *dev = ifa->ifa_dev->dev;
+ struct mlxsw_sp *mlxsw_sp;
+ struct mlxsw_sp_rif *rif;
+ int err = 0;
+
+ mlxsw_sp = mlxsw_sp_lower_get(dev);
+ if (!mlxsw_sp)
+ goto out;
+
+ rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+ if (!mlxsw_sp_rif_should_config(rif, ifa->ifa_dev, event))
+ goto out;
+
+ if (mlxsw_sp_port_dev_check(dev))
+ err = mlxsw_sp_inetaddr_port_event(dev, event);
+ else if (netif_is_lag_master(dev))
+ err = mlxsw_sp_inetaddr_lag_event(dev, event);
+ else if (netif_is_bridge_master(dev))
+ err = mlxsw_sp_inetaddr_bridge_event(dev, dev, event);
+ else if (is_vlan_dev(dev))
+ err = mlxsw_sp_inetaddr_vlan_event(dev, event);
+
+out:
+ return notifier_from_errno(err);
+}
+
+static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif_index,
+ const char *mac, int mtu)
+{
+ char ritr_pl[MLXSW_REG_RITR_LEN];
+ int err;
+
+ mlxsw_reg_ritr_rif_pack(ritr_pl, rif_index);
+ err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+ if (err)
+ return err;
+
+ mlxsw_reg_ritr_mtu_set(ritr_pl, mtu);
+ mlxsw_reg_ritr_if_mac_memcpy_to(ritr_pl, mac);
+ mlxsw_reg_ritr_op_set(ritr_pl, MLXSW_REG_RITR_RIF_CREATE);
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+int mlxsw_sp_netdevice_router_port_event(struct net_device *dev)
+{
+ struct mlxsw_sp *mlxsw_sp;
+ struct mlxsw_sp_rif *rif;
+ int err;
+
+ mlxsw_sp = mlxsw_sp_lower_get(dev);
+ if (!mlxsw_sp)
+ return 0;
+
+ rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+ if (!rif)
+ return 0;
+
+ err = mlxsw_sp_rif_fdb_op(mlxsw_sp, rif->addr, rif->f->fid, false);
+ if (err)
+ return err;
+
+ err = mlxsw_sp_rif_edit(mlxsw_sp, rif->rif_index, dev->dev_addr,
+ dev->mtu);
+ if (err)
+ goto err_rif_edit;
+
+ err = mlxsw_sp_rif_fdb_op(mlxsw_sp, dev->dev_addr, rif->f->fid, true);
+ if (err)
+ goto err_rif_fdb_op;
+
+ ether_addr_copy(rif->addr, dev->dev_addr);
+ rif->mtu = dev->mtu;
+
+ netdev_dbg(dev, "Updated RIF=%d\n", rif->rif_index);
+
+ return 0;
+
+err_rif_fdb_op:
+ mlxsw_sp_rif_edit(mlxsw_sp, rif->rif_index, rif->addr, rif->mtu);
+err_rif_edit:
+ mlxsw_sp_rif_fdb_op(mlxsw_sp, rif->addr, rif->f->fid, true);
+ return err;
+}
+
+int mlxsw_sp_vport_vrf_join(struct mlxsw_sp_port *mlxsw_sp_vport)
+{
+ struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport);
+ struct net_device *dev = mlxsw_sp_vport->dev;
+
+ /* In case vPort already has a RIF, then we need to drop it.
+ * A new one will be created using the VRF's VR.
+ */
+ if (f && f->rif)
+ mlxsw_sp_vport_rif_sp_leave(mlxsw_sp_vport);
+
+ return mlxsw_sp_vport_rif_sp_join(mlxsw_sp_vport, dev);
+}
+
+void mlxsw_sp_vport_vrf_leave(struct mlxsw_sp_port *mlxsw_sp_vport)
+{
+ mlxsw_sp_vport_rif_sp_leave(mlxsw_sp_vport);
+}
+
+int mlxsw_sp_port_vrf_join(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+ struct mlxsw_sp_port *mlxsw_sp_vport;
+
+ mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, 1);
+ if (WARN_ON(!mlxsw_sp_vport))
+ return -EINVAL;
+
+ return mlxsw_sp_vport_vrf_join(mlxsw_sp_vport);
+}
+
+void mlxsw_sp_port_vrf_leave(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+ struct mlxsw_sp_port *mlxsw_sp_vport;
+
+ mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, 1);
+ if (WARN_ON(!mlxsw_sp_vport))
+ return;
+
+ mlxsw_sp_vport_vrf_leave(mlxsw_sp_vport);
+}
+
+int mlxsw_sp_bridge_vrf_join(struct mlxsw_sp *mlxsw_sp,
+ struct net_device *l3_dev)
+{
+ struct mlxsw_sp_fid *f;
+
+ f = mlxsw_sp_bridge_fid_get(mlxsw_sp, l3_dev);
+ if (WARN_ON(!f))
+ return -EINVAL;
+
+ if (f->rif)
+ mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif);
+
+ return mlxsw_sp_rif_bridge_create(mlxsw_sp, l3_dev, f);
+}
+
+void mlxsw_sp_bridge_vrf_leave(struct mlxsw_sp *mlxsw_sp,
+ struct net_device *l3_dev)
+{
+ struct mlxsw_sp_fid *f;
+
+ f = mlxsw_sp_bridge_fid_get(mlxsw_sp, l3_dev);
+ if (WARN_ON(!f))
+ return;
+ mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif);
+}
+
+static void mlxsw_sp_router_fib_dump_flush(struct notifier_block *nb)
+{
+ struct mlxsw_sp *mlxsw_sp = container_of(nb, struct mlxsw_sp, fib_nb);
+
+ /* Flush pending FIB notifications and then flush the device's
+ * table before requesting another dump. The FIB notification
+ * block is unregistered, so no need to take RTNL.
+ */
+ mlxsw_core_flush_owq();
+ mlxsw_sp_router_fib_flush(mlxsw_sp);
}
static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
@@ -2501,111 +3552,6 @@ static void __mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
kfree(mlxsw_sp->rifs);
}
-struct mlxsw_sp_fib_event_work {
- struct work_struct work;
- union {
- struct fib_entry_notifier_info fen_info;
- struct fib_nh_notifier_info fnh_info;
- };
- struct mlxsw_sp *mlxsw_sp;
- unsigned long event;
-};
-
-static void mlxsw_sp_router_fib_event_work(struct work_struct *work)
-{
- struct mlxsw_sp_fib_event_work *fib_work =
- container_of(work, struct mlxsw_sp_fib_event_work, work);
- struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp;
- bool replace, append;
- int err;
-
- /* Protect internal structures from changes */
- rtnl_lock();
- switch (fib_work->event) {
- case FIB_EVENT_ENTRY_REPLACE: /* fall through */
- case FIB_EVENT_ENTRY_APPEND: /* fall through */
- case FIB_EVENT_ENTRY_ADD:
- replace = fib_work->event == FIB_EVENT_ENTRY_REPLACE;
- append = fib_work->event == FIB_EVENT_ENTRY_APPEND;
- err = mlxsw_sp_router_fib4_add(mlxsw_sp, &fib_work->fen_info,
- replace, append);
- if (err)
- mlxsw_sp_router_fib4_abort(mlxsw_sp);
- fib_info_put(fib_work->fen_info.fi);
- break;
- case FIB_EVENT_ENTRY_DEL:
- mlxsw_sp_router_fib4_del(mlxsw_sp, &fib_work->fen_info);
- fib_info_put(fib_work->fen_info.fi);
- break;
- case FIB_EVENT_RULE_ADD: /* fall through */
- case FIB_EVENT_RULE_DEL:
- mlxsw_sp_router_fib4_abort(mlxsw_sp);
- break;
- case FIB_EVENT_NH_ADD: /* fall through */
- case FIB_EVENT_NH_DEL:
- mlxsw_sp_nexthop_event(mlxsw_sp, fib_work->event,
- fib_work->fnh_info.fib_nh);
- fib_info_put(fib_work->fnh_info.fib_nh->nh_parent);
- break;
- }
- rtnl_unlock();
- kfree(fib_work);
-}
-
-/* Called with rcu_read_lock() */
-static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
- unsigned long event, void *ptr)
-{
- struct mlxsw_sp *mlxsw_sp = container_of(nb, struct mlxsw_sp, fib_nb);
- struct mlxsw_sp_fib_event_work *fib_work;
- struct fib_notifier_info *info = ptr;
-
- if (!net_eq(info->net, &init_net))
- return NOTIFY_DONE;
-
- fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC);
- if (WARN_ON(!fib_work))
- return NOTIFY_BAD;
-
- INIT_WORK(&fib_work->work, mlxsw_sp_router_fib_event_work);
- fib_work->mlxsw_sp = mlxsw_sp;
- fib_work->event = event;
-
- switch (event) {
- case FIB_EVENT_ENTRY_REPLACE: /* fall through */
- case FIB_EVENT_ENTRY_APPEND: /* fall through */
- case FIB_EVENT_ENTRY_ADD: /* fall through */
- case FIB_EVENT_ENTRY_DEL:
- memcpy(&fib_work->fen_info, ptr, sizeof(fib_work->fen_info));
- /* Take referece on fib_info to prevent it from being
- * freed while work is queued. Release it afterwards.
- */
- fib_info_hold(fib_work->fen_info.fi);
- break;
- case FIB_EVENT_NH_ADD: /* fall through */
- case FIB_EVENT_NH_DEL:
- memcpy(&fib_work->fnh_info, ptr, sizeof(fib_work->fnh_info));
- fib_info_hold(fib_work->fnh_info.fib_nh->nh_parent);
- break;
- }
-
- mlxsw_core_schedule_work(&fib_work->work);
-
- return NOTIFY_DONE;
-}
-
-static void mlxsw_sp_router_fib_dump_flush(struct notifier_block *nb)
-{
- struct mlxsw_sp *mlxsw_sp = container_of(nb, struct mlxsw_sp, fib_nb);
-
- /* Flush pending FIB notifications and then flush the device's
- * table before requesting another dump. The FIB notification
- * block is unregistered, so no need to take RTNL.
- */
- mlxsw_core_flush_owq();
- mlxsw_sp_router_fib_flush(mlxsw_sp);
-}
-
int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
{
int err;
@@ -2625,7 +3571,10 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
if (err)
goto err_nexthop_group_ht_init;
- mlxsw_sp_lpm_init(mlxsw_sp);
+ err = mlxsw_sp_lpm_init(mlxsw_sp);
+ if (err)
+ goto err_lpm_init;
+
err = mlxsw_sp_vrs_init(mlxsw_sp);
if (err)
goto err_vrs_init;
@@ -2647,6 +3596,8 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
err_neigh_init:
mlxsw_sp_vrs_fini(mlxsw_sp);
err_vrs_init:
+ mlxsw_sp_lpm_fini(mlxsw_sp);
+err_lpm_init:
rhashtable_destroy(&mlxsw_sp->router.nexthop_group_ht);
err_nexthop_group_ht_init:
rhashtable_destroy(&mlxsw_sp->router.nexthop_ht);
@@ -2660,6 +3611,7 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
unregister_fib_notifier(&mlxsw_sp->fib_nb);
mlxsw_sp_neigh_fini(mlxsw_sp);
mlxsw_sp_vrs_fini(mlxsw_sp);
+ mlxsw_sp_lpm_fini(mlxsw_sp);
rhashtable_destroy(&mlxsw_sp->router.nexthop_group_ht);
rhashtable_destroy(&mlxsw_sp->router.nexthop_ht);
__mlxsw_sp_router_fini(mlxsw_sp);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
new file mode 100644
index 0000000..c3095fe
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -0,0 +1,58 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Arkadi Sharshevsky <arkadis@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _MLXSW_ROUTER_H_
+#define _MLXSW_ROUTER_H_
+
+#include "spectrum.h"
+
+enum mlxsw_sp_rif_counter_dir {
+ MLXSW_SP_RIF_COUNTER_INGRESS,
+ MLXSW_SP_RIF_COUNTER_EGRESS,
+};
+
+u16 mlxsw_sp_rif_index(const struct mlxsw_sp_rif *rif);
+int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif);
+int mlxsw_sp_rif_counter_value_get(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_rif *rif,
+ enum mlxsw_sp_rif_counter_dir dir,
+ u64 *cnt);
+void mlxsw_sp_rif_counter_free(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_rif *rif,
+ enum mlxsw_sp_rif_counter_dir dir);
+int mlxsw_sp_rif_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_rif *rif,
+ enum mlxsw_sp_rif_counter_dir dir);
+
+#endif /* _MLXSW_ROUTER_H_*/
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 598727d..05eaa15 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -568,8 +568,8 @@ void mlxsw_sp_fid_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *f)
list_del(&f->list);
- if (f->r)
- mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->r);
+ if (f->rif)
+ mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif);
kfree(f);
@@ -1012,7 +1012,7 @@ static int mlxsw_sp_port_smid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 mid,
mlxsw_reg_smid_pack(smid_pl, mid, mlxsw_sp_port->local_port, add);
if (clear_all_ports) {
- for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++)
+ for (i = 1; i < mlxsw_core_max_ports(mlxsw_sp->core); i++)
if (mlxsw_sp->ports[i])
mlxsw_reg_smid_port_mask_set(smid_pl, i, 1);
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index ec1e886..3b0f724 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -1321,7 +1321,7 @@ static void mlxsw_sx_ports_remove(struct mlxsw_sx *mlxsw_sx)
{
int i;
- for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++)
+ for (i = 1; i < mlxsw_core_max_ports(mlxsw_sx->core); i++)
if (mlxsw_sx_port_created(mlxsw_sx, i))
mlxsw_sx_port_remove(mlxsw_sx, i);
kfree(mlxsw_sx->ports);
@@ -1329,17 +1329,18 @@ static void mlxsw_sx_ports_remove(struct mlxsw_sx *mlxsw_sx)
static int mlxsw_sx_ports_create(struct mlxsw_sx *mlxsw_sx)
{
+ unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sx->core);
size_t alloc_size;
u8 module, width;
int i;
int err;
- alloc_size = sizeof(struct mlxsw_sx_port *) * MLXSW_PORT_MAX_PORTS;
+ alloc_size = sizeof(struct mlxsw_sx_port *) * max_ports;
mlxsw_sx->ports = kzalloc(alloc_size, GFP_KERNEL);
if (!mlxsw_sx->ports)
return -ENOMEM;
- for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++) {
+ for (i = 1; i < max_ports; i++) {
err = mlxsw_sx_port_module_info_get(mlxsw_sx, i, &module,
&width);
if (err)
diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index 279ee46..20358f8 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -212,25 +212,6 @@ static void ks8851_wrreg8(struct ks8851_net *ks, unsigned reg, unsigned val)
}
/**
- * ks8851_rx_1msg - select whether to use one or two messages for spi read
- * @ks: The device structure
- *
- * Return whether to generate a single message with a tx and rx buffer
- * supplied to spi_sync(), or alternatively send the tx and rx buffers
- * as separate messages.
- *
- * Depending on the hardware in use, a single message may be more efficient
- * on interrupts or work done by the driver.
- *
- * This currently always returns true until we add some per-device data passed
- * from the platform code to specify which mode is better.
- */
-static inline bool ks8851_rx_1msg(struct ks8851_net *ks)
-{
- return true;
-}
-
-/**
* ks8851_rdreg - issue read register command and return the data
* @ks: The device state
* @op: The register address and byte enables in message format.
@@ -251,14 +232,7 @@ static void ks8851_rdreg(struct ks8851_net *ks, unsigned op,
txb[0] = cpu_to_le16(op | KS_SPIOP_RD);
- if (ks8851_rx_1msg(ks)) {
- msg = &ks->spi_msg1;
- xfer = &ks->spi_xfer1;
-
- xfer->tx_buf = txb;
- xfer->rx_buf = trx;
- xfer->len = rxl + 2;
- } else {
+ if (ks->spidev->master->flags & SPI_MASTER_HALF_DUPLEX) {
msg = &ks->spi_msg2;
xfer = ks->spi_xfer2;
@@ -270,15 +244,22 @@ static void ks8851_rdreg(struct ks8851_net *ks, unsigned op,
xfer->tx_buf = NULL;
xfer->rx_buf = trx;
xfer->len = rxl;
+ } else {
+ msg = &ks->spi_msg1;
+ xfer = &ks->spi_xfer1;
+
+ xfer->tx_buf = txb;
+ xfer->rx_buf = trx;
+ xfer->len = rxl + 2;
}
ret = spi_sync(ks->spidev, msg);
if (ret < 0)
netdev_err(ks->netdev, "read: spi_sync() failed\n");
- else if (ks8851_rx_1msg(ks))
- memcpy(rxb, trx + 2, rxl);
- else
+ else if (ks->spidev->master->flags & SPI_MASTER_HALF_DUPLEX)
memcpy(rxb, trx, rxl);
+ else
+ memcpy(rxb, trx + 2, rxl);
}
/**
diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c
index 06c9f41..c0d7d5e 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.c
+++ b/drivers/net/ethernet/moxa/moxart_ether.c
@@ -25,6 +25,7 @@
#include <linux/of_irq.h>
#include <linux/crc32.h>
#include <linux/crc32c.h>
+#include <linux/circ_buf.h>
#include "moxart_ether.h"
@@ -227,8 +228,8 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget)
if (desc0 & (RX_DESC0_ERR | RX_DESC0_CRC_ERR | RX_DESC0_FTL |
RX_DESC0_RUNT | RX_DESC0_ODD_NB)) {
net_dbg_ratelimited("packet error\n");
- priv->stats.rx_dropped++;
- priv->stats.rx_errors++;
+ ndev->stats.rx_dropped++;
+ ndev->stats.rx_errors++;
goto rx_next;
}
@@ -244,8 +245,8 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget)
if (unlikely(!skb)) {
net_dbg_ratelimited("netdev_alloc_skb_ip_align failed\n");
- priv->stats.rx_dropped++;
- priv->stats.rx_errors++;
+ ndev->stats.rx_dropped++;
+ ndev->stats.rx_errors++;
goto rx_next;
}
@@ -255,10 +256,10 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget)
napi_gro_receive(&priv->napi, skb);
rx++;
- priv->stats.rx_packets++;
- priv->stats.rx_bytes += len;
+ ndev->stats.rx_packets++;
+ ndev->stats.rx_bytes += len;
if (desc0 & RX_DESC0_MULTICAST)
- priv->stats.multicast++;
+ ndev->stats.multicast++;
rx_next:
wmb(); /* prevent setting ownership back too early */
@@ -278,6 +279,13 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget)
return rx;
}
+static int moxart_tx_queue_space(struct net_device *ndev)
+{
+ struct moxart_mac_priv_t *priv = netdev_priv(ndev);
+
+ return CIRC_SPACE(priv->tx_head, priv->tx_tail, TX_DESC_NUM);
+}
+
static void moxart_tx_finished(struct net_device *ndev)
{
struct moxart_mac_priv_t *priv = netdev_priv(ndev);
@@ -288,8 +296,8 @@ static void moxart_tx_finished(struct net_device *ndev)
dma_unmap_single(&ndev->dev, priv->tx_mapping[tx_tail],
priv->tx_len[tx_tail], DMA_TO_DEVICE);
- priv->stats.tx_packets++;
- priv->stats.tx_bytes += priv->tx_skb[tx_tail]->len;
+ ndev->stats.tx_packets++;
+ ndev->stats.tx_bytes += priv->tx_skb[tx_tail]->len;
dev_kfree_skb_irq(priv->tx_skb[tx_tail]);
priv->tx_skb[tx_tail] = NULL;
@@ -297,6 +305,9 @@ static void moxart_tx_finished(struct net_device *ndev)
tx_tail = TX_NEXT(tx_tail);
}
priv->tx_tail = tx_tail;
+ if (netif_queue_stopped(ndev) &&
+ moxart_tx_queue_space(ndev) >= TX_WAKE_THRESHOLD)
+ netif_wake_queue(ndev);
}
static irqreturn_t moxart_mac_interrupt(int irq, void *dev_id)
@@ -324,16 +335,21 @@ static int moxart_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
struct moxart_mac_priv_t *priv = netdev_priv(ndev);
void *desc;
unsigned int len;
- unsigned int tx_head = priv->tx_head;
+ unsigned int tx_head;
u32 txdes1;
int ret = NETDEV_TX_BUSY;
+ spin_lock_irq(&priv->txlock);
+
+ tx_head = priv->tx_head;
desc = priv->tx_desc_base + (TX_REG_DESC_SIZE * tx_head);
- spin_lock_irq(&priv->txlock);
+ if (moxart_tx_queue_space(ndev) == 1)
+ netif_stop_queue(ndev);
+
if (moxart_desc_read(desc + TX_REG_OFFSET_DESC0) & TX_DESC0_DMA_OWN) {
net_dbg_ratelimited("no TX space for packet\n");
- priv->stats.tx_dropped++;
+ ndev->stats.tx_dropped++;
goto out_unlock;
}
rmb(); /* ensure data is only read that had TX_DESC0_DMA_OWN cleared */
@@ -384,13 +400,6 @@ static int moxart_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
return ret;
}
-static struct net_device_stats *moxart_mac_get_stats(struct net_device *ndev)
-{
- struct moxart_mac_priv_t *priv = netdev_priv(ndev);
-
- return &priv->stats;
-}
-
static void moxart_mac_setmulticast(struct net_device *ndev)
{
struct moxart_mac_priv_t *priv = netdev_priv(ndev);
@@ -440,7 +449,6 @@ static const struct net_device_ops moxart_netdev_ops = {
.ndo_open = moxart_mac_open,
.ndo_stop = moxart_mac_stop,
.ndo_start_xmit = moxart_mac_start_xmit,
- .ndo_get_stats = moxart_mac_get_stats,
.ndo_set_rx_mode = moxart_mac_set_rx_mode,
.ndo_set_mac_address = moxart_set_mac_address,
.ndo_validate_addr = eth_validate_addr,
diff --git a/drivers/net/ethernet/moxa/moxart_ether.h b/drivers/net/ethernet/moxa/moxart_ether.h
index 93a9563..686b895 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.h
+++ b/drivers/net/ethernet/moxa/moxart_ether.h
@@ -59,6 +59,7 @@
#define TX_NEXT(N) (((N) + 1) & (TX_DESC_NUM_MASK))
#define TX_BUF_SIZE 1600
#define TX_BUF_SIZE_MAX (TX_DESC1_BUF_SIZE_MASK+1)
+#define TX_WAKE_THRESHOLD 16
#define RX_DESC_NUM 64
#define RX_DESC_NUM_MASK (RX_DESC_NUM-1)
@@ -292,7 +293,6 @@
struct moxart_mac_priv_t {
void __iomem *base;
- struct net_device_stats stats;
unsigned int reg_maccr;
unsigned int reg_imr;
struct napi_struct napi;
diff --git a/drivers/net/ethernet/netronome/nfp/Makefile b/drivers/net/ethernet/netronome/nfp/Makefile
index 6933afa..4a5d13e 100644
--- a/drivers/net/ethernet/netronome/nfp/Makefile
+++ b/drivers/net/ethernet/netronome/nfp/Makefile
@@ -6,6 +6,7 @@
nfpcore/nfp_cpplib.o \
nfpcore/nfp_hwinfo.o \
nfpcore/nfp_mip.o \
+ nfpcore/nfp_mutex.o \
nfpcore/nfp_nffw.o \
nfpcore/nfp_nsp.o \
nfpcore/nfp_nsp_eth.o \
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c
index dedac72..bea2a1a 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c
@@ -48,7 +48,7 @@
#include "nfpcore/nfp.h"
#include "nfpcore/nfp_cpp.h"
#include "nfpcore/nfp_nffw.h"
-#include "nfpcore/nfp_nsp_eth.h"
+#include "nfpcore/nfp_nsp.h"
#include "nfpcore/nfp6000_pcie.h"
@@ -385,8 +385,7 @@ static void nfp_pci_remove(struct pci_dev *pdev)
{
struct nfp_pf *pf = pci_get_drvdata(pdev);
- if (!list_empty(&pf->ports))
- nfp_net_pci_remove(pf);
+ nfp_net_pci_remove(pf);
nfp_pcie_sriov_disable(pdev);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.h b/drivers/net/ethernet/netronome/nfp/nfp_main.h
index 39105d0..b57de04 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_main.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_main.h
@@ -42,7 +42,9 @@
#include <linux/list.h>
#include <linux/types.h>
#include <linux/msi.h>
+#include <linux/mutex.h>
#include <linux/pci.h>
+#include <linux/workqueue.h>
struct dentry;
struct pci_dev;
@@ -64,8 +66,11 @@ struct nfp_eth_table;
* @fw_loaded: Is the firmware loaded?
* @eth_tbl: NSP ETH table
* @ddir: Per-device debugfs directory
- * @num_ports: Number of adapter ports
+ * @num_ports: Number of adapter ports app firmware supports
+ * @num_netdevs: Number of netdevs spawned
* @ports: Linked list of port structures (struct nfp_net)
+ * @port_lock: Protects @ports, @num_ports, @num_netdevs
+ * @port_refresh_work: Work entry for taking netdevs out
*/
struct nfp_pf {
struct pci_dev *pdev;
@@ -88,7 +93,11 @@ struct nfp_pf {
struct dentry *ddir;
unsigned int num_ports;
+ unsigned int num_netdevs;
+
struct list_head ports;
+ struct work_struct port_refresh_work;
+ struct mutex port_lock;
};
extern struct pci_driver nfp_netvf_pci_driver;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index e614a37..052db92 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -50,14 +50,14 @@
#include "nfp_net_ctrl.h"
-#define nn_err(nn, fmt, args...) netdev_err((nn)->netdev, fmt, ## args)
-#define nn_warn(nn, fmt, args...) netdev_warn((nn)->netdev, fmt, ## args)
-#define nn_info(nn, fmt, args...) netdev_info((nn)->netdev, fmt, ## args)
-#define nn_dbg(nn, fmt, args...) netdev_dbg((nn)->netdev, fmt, ## args)
-#define nn_warn_ratelimit(nn, fmt, args...) \
+#define nn_err(nn, fmt, args...) netdev_err((nn)->dp.netdev, fmt, ## args)
+#define nn_warn(nn, fmt, args...) netdev_warn((nn)->dp.netdev, fmt, ## args)
+#define nn_info(nn, fmt, args...) netdev_info((nn)->dp.netdev, fmt, ## args)
+#define nn_dbg(nn, fmt, args...) netdev_dbg((nn)->dp.netdev, fmt, ## args)
+#define nn_dp_warn(dp, fmt, args...) \
do { \
if (unlikely(net_ratelimit())) \
- netdev_warn((nn)->netdev, fmt, ## args); \
+ netdev_warn((dp)->netdev, fmt, ## args); \
} while (0)
/* Max time to wait for NFP to respond on updates (in seconds) */
@@ -112,6 +112,7 @@
/* Forward declarations */
struct nfp_cpp;
+struct nfp_eth_table_port;
struct nfp_net;
struct nfp_net_r_vector;
@@ -306,17 +307,13 @@ struct nfp_net_rx_buf {
* @rd_p: FL/RX ring read pointer (free running)
* @idx: Ring index from Linux's perspective
* @fl_qcidx: Queue Controller Peripheral (QCP) queue index for the freelist
- * @rx_qcidx: Queue Controller Peripheral (QCP) queue index for the RX queue
* @qcp_fl: Pointer to base of the QCP freelist queue
- * @qcp_rx: Pointer to base of the QCP RX queue
* @wr_ptr_add: Accumulated number of buffers to add to QCP write pointer
* (used for free list batching)
* @rxbufs: Array of transmitted FL/RX buffers
* @rxds: Virtual address of FL/RX ring in host memory
* @dma: DMA address of the FL/RX ring
* @size: Size, in bytes, of the FL/RX ring (needed to free)
- * @bufsz: Buffer allocation size for convenience of management routines
- * (NOTE: this is in second cache line, do not use on fast path!)
*/
struct nfp_net_rx_ring {
struct nfp_net_r_vector *r_vec;
@@ -325,20 +322,17 @@ struct nfp_net_rx_ring {
u32 wr_p;
u32 rd_p;
- u16 idx;
- u16 wr_ptr_add;
+ u32 idx;
+ u32 wr_ptr_add;
int fl_qcidx;
- int rx_qcidx;
u8 __iomem *qcp_fl;
- u8 __iomem *qcp_rx;
struct nfp_net_rx_buf *rxbufs;
struct nfp_net_rx_desc *rxds;
dma_addr_t dma;
unsigned int size;
- unsigned int bufsz;
} ____cacheline_aligned;
/**
@@ -433,19 +427,76 @@ struct nfp_stat_pair {
};
/**
- * struct nfp_net - NFP network device structure
- * @pdev: Backpointer to PCI device
- * @netdev: Backpointer to net_device structure
- * @is_vf: Is the driver attached to a VF?
+ * struct nfp_net_dp - NFP network device datapath data structure
+ * @dev: Backpointer to struct device
+ * @netdev: Backpointer to net_device structure
+ * @is_vf: Is the driver attached to a VF?
* @bpf_offload_skip_sw: Offloaded BPF program will not be rerun by cls_bpf
* @bpf_offload_xdp: Offloaded BPF program is XDP
- * @ctrl: Local copy of the control register/word.
- * @fl_bufsz: Currently configured size of the freelist buffers
+ * @chained_metadata_format: Firemware will use new metadata format
+ * @rx_dma_dir: Mapping direction for RX buffers
+ * @rx_dma_off: Offset at which DMA packets (for XDP headroom)
* @rx_offset: Offset in the RX buffers where packet data starts
+ * @ctrl: Local copy of the control register/word.
+ * @fl_bufsz: Currently configured size of the freelist buffers
* @xdp_prog: Installed XDP program
- * @fw_ver: Firmware version
+ * @tx_rings: Array of pre-allocated TX ring structures
+ * @rx_rings: Array of pre-allocated RX ring structures
+ * @ctrl_bar: Pointer to mapped control BAR
+ *
+ * @txd_cnt: Size of the TX ring in number of descriptors
+ * @rxd_cnt: Size of the RX ring in number of descriptors
+ * @num_r_vecs: Number of used ring vectors
+ * @num_tx_rings: Currently configured number of TX rings
+ * @num_stack_tx_rings: Number of TX rings used by the stack (not XDP)
+ * @num_rx_rings: Currently configured number of RX rings
+ * @mtu: Device MTU
+ */
+struct nfp_net_dp {
+ struct device *dev;
+ struct net_device *netdev;
+
+ u8 is_vf:1;
+ u8 bpf_offload_skip_sw:1;
+ u8 bpf_offload_xdp:1;
+ u8 chained_metadata_format:1;
+
+ u8 rx_dma_dir;
+ u8 rx_dma_off;
+
+ u8 rx_offset;
+
+ u32 ctrl;
+ u32 fl_bufsz;
+
+ struct bpf_prog *xdp_prog;
+
+ struct nfp_net_tx_ring *tx_rings;
+ struct nfp_net_rx_ring *rx_rings;
+
+ u8 __iomem *ctrl_bar;
+
+ /* Cold data follows */
+
+ unsigned int txd_cnt;
+ unsigned int rxd_cnt;
+
+ unsigned int num_r_vecs;
+
+ unsigned int num_tx_rings;
+ unsigned int num_stack_tx_rings;
+ unsigned int num_rx_rings;
+
+ unsigned int mtu;
+};
+
+/**
+ * struct nfp_net - NFP network device structure
+ * @dp: Datapath structure
+ * @fw_ver: Firmware version
* @cap: Capabilities advertised by the Firmware
* @max_mtu: Maximum support MTU advertised by the Firmware
+ * @rss_hfunc: RSS selected hash function
* @rss_cfg: RSS configuration
* @rss_key: RSS secret key
* @rss_itbl: RSS indirection table
@@ -454,17 +505,9 @@ struct nfp_stat_pair {
* @rx_filter_change: Jiffies when statistics last changed
* @rx_filter_stats_timer: Timer for polling filter offload statistics
* @rx_filter_lock: Lock protecting timer state changes (teardown)
+ * @max_r_vecs: Number of allocated interrupt vectors for RX/TX
* @max_tx_rings: Maximum number of TX rings supported by the Firmware
* @max_rx_rings: Maximum number of RX rings supported by the Firmware
- * @num_tx_rings: Currently configured number of TX rings
- * @num_stack_tx_rings: Number of TX rings used by the stack (not XDP)
- * @num_rx_rings: Currently configured number of RX rings
- * @txd_cnt: Size of the TX ring in number of descriptors
- * @rxd_cnt: Size of the RX ring in number of descriptors
- * @tx_rings: Array of pre-allocated TX ring structures
- * @rx_rings: Array of pre-allocated RX ring structures
- * @max_r_vecs: Number of allocated interrupt vectors for RX/TX
- * @num_r_vecs: Number of used ring vectors
* @r_vecs: Pre-allocated array of ring vectors
* @irq_entries: Pre-allocated array of MSI-X entries
* @lsc_handler: Handler for Link State Change interrupt
@@ -480,7 +523,8 @@ struct nfp_stat_pair {
* @reconfig_sync_present: Some thread is performing synchronous reconfig
* @reconfig_timer: Timer for async reading of reconfig results
* @link_up: Is the link up?
- * @link_status_lock: Protects @link_up and ensures atomicity with BAR reading
+ * @link_changed: Has link state changes since last port refresh?
+ * @link_status_lock: Protects @link_* and ensures atomicity with BAR reading
* @rx_coalesce_usecs: RX interrupt moderation usecs delay parameter
* @rx_coalesce_max_frames: RX interrupt moderation frame count parameter
* @tx_coalesce_usecs: TX interrupt moderation usecs delay parameter
@@ -488,36 +532,24 @@ struct nfp_stat_pair {
* @vxlan_ports: VXLAN ports for RX inner csum offload communicated to HW
* @vxlan_usecnt: IPv4/IPv6 VXLAN port use counts
* @qcp_cfg: Pointer to QCP queue used for configuration notification
- * @ctrl_bar: Pointer to mapped control BAR
* @tx_bar: Pointer to mapped TX queues
* @rx_bar: Pointer to mapped FL/RX queues
* @debugfs_dir: Device directory in debugfs
* @ethtool_dump_flag: Ethtool dump flag
* @port_list: Entry on device port list
+ * @pdev: Backpointer to PCI device
* @cpp: CPP device handle if available
+ * @eth_port: Translated ETH Table port entry
*/
struct nfp_net {
- struct pci_dev *pdev;
- struct net_device *netdev;
-
- unsigned is_vf:1;
- unsigned bpf_offload_skip_sw:1;
- unsigned bpf_offload_xdp:1;
-
- u32 ctrl;
- u32 fl_bufsz;
-
- u32 rx_offset;
-
- struct bpf_prog *xdp_prog;
-
- struct nfp_net_tx_ring *tx_rings;
- struct nfp_net_rx_ring *rx_rings;
+ struct nfp_net_dp dp;
struct nfp_net_fw_version fw_ver;
+
u32 cap;
u32 max_mtu;
+ u8 rss_hfunc;
u32 rss_cfg;
u8 rss_key[NFP_NET_CFG_RSS_KEY_SZ];
u8 rss_itbl[NFP_NET_CFG_RSS_ITBL_SZ];
@@ -530,18 +562,10 @@ struct nfp_net {
unsigned int max_tx_rings;
unsigned int max_rx_rings;
- unsigned int num_tx_rings;
- unsigned int num_stack_tx_rings;
- unsigned int num_rx_rings;
-
int stride_tx;
int stride_rx;
- int txd_cnt;
- int rxd_cnt;
-
unsigned int max_r_vecs;
- unsigned int num_r_vecs;
struct nfp_net_r_vector r_vecs[NFP_NET_MAX_R_VECS];
struct msix_entry irq_entries[NFP_NET_MAX_IRQS];
@@ -557,6 +581,7 @@ struct nfp_net {
u32 me_freq_mhz;
bool link_up;
+ bool link_changed;
spinlock_t link_status_lock;
spinlock_t reconfig_lock;
@@ -575,7 +600,6 @@ struct nfp_net {
u8 __iomem *qcp_cfg;
- u8 __iomem *ctrl_bar;
u8 __iomem *tx_bar;
u8 __iomem *rx_bar;
@@ -584,14 +608,10 @@ struct nfp_net {
struct list_head port_list;
+ struct pci_dev *pdev;
struct nfp_cpp *cpp;
-};
-struct nfp_net_ring_set {
- unsigned int n_rings;
- unsigned int mtu;
- unsigned int dcnt;
- void *rings;
+ struct nfp_eth_table_port *eth_port;
};
/* Functions to read/write from/to a BAR
@@ -599,42 +619,42 @@ struct nfp_net_ring_set {
*/
static inline u16 nn_readb(struct nfp_net *nn, int off)
{
- return readb(nn->ctrl_bar + off);
+ return readb(nn->dp.ctrl_bar + off);
}
static inline void nn_writeb(struct nfp_net *nn, int off, u8 val)
{
- writeb(val, nn->ctrl_bar + off);
+ writeb(val, nn->dp.ctrl_bar + off);
}
static inline u16 nn_readw(struct nfp_net *nn, int off)
{
- return readw(nn->ctrl_bar + off);
+ return readw(nn->dp.ctrl_bar + off);
}
static inline void nn_writew(struct nfp_net *nn, int off, u16 val)
{
- writew(val, nn->ctrl_bar + off);
+ writew(val, nn->dp.ctrl_bar + off);
}
static inline u32 nn_readl(struct nfp_net *nn, int off)
{
- return readl(nn->ctrl_bar + off);
+ return readl(nn->dp.ctrl_bar + off);
}
static inline void nn_writel(struct nfp_net *nn, int off, u32 val)
{
- writel(val, nn->ctrl_bar + off);
+ writel(val, nn->dp.ctrl_bar + off);
}
static inline u64 nn_readq(struct nfp_net *nn, int off)
{
- return readq(nn->ctrl_bar + off);
+ return readq(nn->dp.ctrl_bar + off);
}
static inline void nn_writeq(struct nfp_net *nn, int off, u64 val)
{
- writeq(val, nn->ctrl_bar + off);
+ writeq(val, nn->dp.ctrl_bar + off);
}
/* Flush posted PCI writes by reading something without side effects */
@@ -776,6 +796,7 @@ void nfp_net_netdev_clean(struct net_device *netdev);
void nfp_net_set_ethtool_ops(struct net_device *netdev);
void nfp_net_info(struct nfp_net *nn);
int nfp_net_reconfig(struct nfp_net *nn, u32 update);
+unsigned int nfp_net_rss_key_sz(struct nfp_net *nn);
void nfp_net_rss_write_itbl(struct nfp_net *nn);
void nfp_net_rss_write_key(struct nfp_net *nn);
void nfp_net_coalesce_write_cfg(struct nfp_net *nn);
@@ -787,9 +808,12 @@ void nfp_net_irqs_disable(struct pci_dev *pdev);
void
nfp_net_irqs_assign(struct nfp_net *nn, struct msix_entry *irq_entries,
unsigned int n);
-int
-nfp_net_ring_reconfig(struct nfp_net *nn, struct bpf_prog **xdp_prog,
- struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx);
+
+struct nfp_net_dp *nfp_net_clone_dp(struct nfp_net *nn);
+int nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *new);
+
+bool nfp_net_link_changed_read_clear(struct nfp_net *nn);
+void nfp_net_refresh_port_config(struct nfp_net *nn);
#ifdef CONFIG_NFP_DEBUG
void nfp_net_debugfs_create(void);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 9179a99..e219716 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -41,6 +41,7 @@
* Chris Telfer <chris.telfer@netronome.com>
*/
+#include <linux/bitfield.h>
#include <linux/bpf.h>
#include <linux/bpf_trace.h>
#include <linux/module.h>
@@ -66,6 +67,7 @@
#include <net/pkt_cls.h>
#include <net/vxlan.h>
+#include "nfpcore/nfp_nsp.h"
#include "nfp_net_ctrl.h"
#include "nfp_net.h"
@@ -83,20 +85,18 @@ void nfp_net_get_fw_version(struct nfp_net_fw_version *fw_ver,
put_unaligned_le32(reg, fw_ver);
}
-static dma_addr_t
-nfp_net_dma_map_rx(struct nfp_net *nn, void *frag, unsigned int bufsz,
- int direction)
+static dma_addr_t nfp_net_dma_map_rx(struct nfp_net_dp *dp, void *frag)
{
- return dma_map_single(&nn->pdev->dev, frag + NFP_NET_RX_BUF_HEADROOM,
- bufsz - NFP_NET_RX_BUF_NON_DATA, direction);
+ return dma_map_single(dp->dev, frag + NFP_NET_RX_BUF_HEADROOM,
+ dp->fl_bufsz - NFP_NET_RX_BUF_NON_DATA,
+ dp->rx_dma_dir);
}
-static void
-nfp_net_dma_unmap_rx(struct nfp_net *nn, dma_addr_t dma_addr,
- unsigned int bufsz, int direction)
+static void nfp_net_dma_unmap_rx(struct nfp_net_dp *dp, dma_addr_t dma_addr)
{
- dma_unmap_single(&nn->pdev->dev, dma_addr,
- bufsz - NFP_NET_RX_BUF_NON_DATA, direction);
+ dma_unmap_single(dp->dev, dma_addr,
+ dp->fl_bufsz - NFP_NET_RX_BUF_NON_DATA,
+ dp->rx_dma_dir);
}
/* Firmware reconfig
@@ -327,19 +327,22 @@ void
nfp_net_irqs_assign(struct nfp_net *nn, struct msix_entry *irq_entries,
unsigned int n)
{
+ struct nfp_net_dp *dp = &nn->dp;
+
nn->max_r_vecs = n - NFP_NET_NON_Q_VECTORS;
- nn->num_r_vecs = nn->max_r_vecs;
+ dp->num_r_vecs = nn->max_r_vecs;
memcpy(nn->irq_entries, irq_entries, sizeof(*irq_entries) * n);
- if (nn->num_rx_rings > nn->num_r_vecs ||
- nn->num_tx_rings > nn->num_r_vecs)
- nn_warn(nn, "More rings (%d,%d) than vectors (%d).\n",
- nn->num_rx_rings, nn->num_tx_rings, nn->num_r_vecs);
+ if (dp->num_rx_rings > dp->num_r_vecs ||
+ dp->num_tx_rings > dp->num_r_vecs)
+ dev_warn(nn->dp.dev, "More rings (%d,%d) than vectors (%d).\n",
+ dp->num_rx_rings, dp->num_tx_rings,
+ dp->num_r_vecs);
- nn->num_rx_rings = min(nn->num_r_vecs, nn->num_rx_rings);
- nn->num_tx_rings = min(nn->num_r_vecs, nn->num_tx_rings);
- nn->num_stack_tx_rings = nn->num_tx_rings;
+ dp->num_rx_rings = min(dp->num_r_vecs, dp->num_rx_rings);
+ dp->num_tx_rings = min(dp->num_r_vecs, dp->num_tx_rings);
+ dp->num_stack_tx_rings = dp->num_tx_rings;
}
/**
@@ -373,6 +376,19 @@ static irqreturn_t nfp_net_irq_rxtx(int irq, void *data)
return IRQ_HANDLED;
}
+bool nfp_net_link_changed_read_clear(struct nfp_net *nn)
+{
+ unsigned long flags;
+ bool ret;
+
+ spin_lock_irqsave(&nn->link_status_lock, flags);
+ ret = nn->link_changed;
+ nn->link_changed = false;
+ spin_unlock_irqrestore(&nn->link_status_lock, flags);
+
+ return ret;
+}
+
/**
* nfp_net_read_link_status() - Reread link status from control BAR
* @nn: NFP Network structure
@@ -392,13 +408,14 @@ static void nfp_net_read_link_status(struct nfp_net *nn)
goto out;
nn->link_up = link_up;
+ nn->link_changed = true;
if (nn->link_up) {
- netif_carrier_on(nn->netdev);
- netdev_info(nn->netdev, "NIC Link is Up\n");
+ netif_carrier_on(nn->dp.netdev);
+ netdev_info(nn->dp.netdev, "NIC Link is Up\n");
} else {
- netif_carrier_off(nn->netdev);
- netdev_info(nn->netdev, "NIC Link is Down\n");
+ netif_carrier_off(nn->dp.netdev);
+ netdev_info(nn->dp.netdev, "NIC Link is Down\n");
}
out:
spin_unlock_irqrestore(&nn->link_status_lock, flags);
@@ -476,10 +493,7 @@ nfp_net_rx_ring_init(struct nfp_net_rx_ring *rx_ring,
rx_ring->r_vec = r_vec;
rx_ring->fl_qcidx = rx_ring->idx * nn->stride_rx;
- rx_ring->rx_qcidx = rx_ring->fl_qcidx + (nn->stride_rx - 1);
-
rx_ring->qcp_fl = nn->rx_bar + NFP_QCP_QUEUE_OFF(rx_ring->fl_qcidx);
- rx_ring->qcp_rx = nn->rx_bar + NFP_QCP_QUEUE_OFF(rx_ring->rx_qcidx);
}
/**
@@ -530,7 +544,7 @@ nfp_net_aux_irq_request(struct nfp_net *nn, u32 ctrl_offset,
entry = &nn->irq_entries[vector_idx];
- snprintf(name, name_sz, format, netdev_name(nn->netdev));
+ snprintf(name, name_sz, format, netdev_name(nn->dp.netdev));
err = request_irq(entry->vector, handler, 0, name, nn);
if (err) {
nn_err(nn, "Failed to request IRQ %d (err=%d).\n",
@@ -617,7 +631,6 @@ static void nfp_net_tx_ring_stop(struct netdev_queue *nd_q,
/**
* nfp_net_tx_tso() - Set up Tx descriptor for LSO
- * @nn: NFP Net device
* @r_vec: per-ring structure
* @txbuf: Pointer to driver soft TX descriptor
* @txd: Pointer to HW TX descriptor
@@ -626,7 +639,7 @@ static void nfp_net_tx_ring_stop(struct netdev_queue *nd_q,
* Set up Tx descriptor for LSO, do nothing for non-LSO skbs.
* Return error on packet header greater than maximum supported LSO header size.
*/
-static void nfp_net_tx_tso(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
+static void nfp_net_tx_tso(struct nfp_net_r_vector *r_vec,
struct nfp_net_tx_buf *txbuf,
struct nfp_net_tx_desc *txd, struct sk_buff *skb)
{
@@ -657,7 +670,7 @@ static void nfp_net_tx_tso(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
/**
* nfp_net_tx_csum() - Set TX CSUM offload flags in TX descriptor
- * @nn: NFP Net device
+ * @dp: NFP Net data path struct
* @r_vec: per-ring structure
* @txbuf: Pointer to driver soft TX descriptor
* @txd: Pointer to TX descriptor
@@ -666,7 +679,8 @@ static void nfp_net_tx_tso(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
* This function sets the TX checksum flags in the TX descriptor based
* on the configuration and the protocol of the packet to be transmitted.
*/
-static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
+static void nfp_net_tx_csum(struct nfp_net_dp *dp,
+ struct nfp_net_r_vector *r_vec,
struct nfp_net_tx_buf *txbuf,
struct nfp_net_tx_desc *txd, struct sk_buff *skb)
{
@@ -674,7 +688,7 @@ static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
struct iphdr *iph;
u8 l4_hdr;
- if (!(nn->ctrl & NFP_NET_CFG_CTRL_TXCSUM))
+ if (!(dp->ctrl & NFP_NET_CFG_CTRL_TXCSUM))
return;
if (skb->ip_summed != CHECKSUM_PARTIAL)
@@ -693,8 +707,7 @@ static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
} else if (ipv6h->version == 6) {
l4_hdr = ipv6h->nexthdr;
} else {
- nn_warn_ratelimit(nn, "partial checksum but ipv=%x!\n",
- iph->version);
+ nn_dp_warn(dp, "partial checksum but ipv=%x!\n", iph->version);
return;
}
@@ -706,8 +719,7 @@ static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
txd->flags |= PCIE_DESC_TX_UDP_CSUM;
break;
default:
- nn_warn_ratelimit(nn, "partial checksum but l4 proto=%x!\n",
- l4_hdr);
+ nn_dp_warn(dp, "partial checksum but l4 proto=%x!\n", l4_hdr);
return;
}
@@ -737,28 +749,31 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
{
struct nfp_net *nn = netdev_priv(netdev);
const struct skb_frag_struct *frag;
- struct nfp_net_r_vector *r_vec;
struct nfp_net_tx_desc *txd, txdg;
- struct nfp_net_tx_buf *txbuf;
struct nfp_net_tx_ring *tx_ring;
+ struct nfp_net_r_vector *r_vec;
+ struct nfp_net_tx_buf *txbuf;
struct netdev_queue *nd_q;
+ struct nfp_net_dp *dp;
dma_addr_t dma_addr;
unsigned int fsize;
int f, nr_frags;
int wr_idx;
u16 qidx;
+ dp = &nn->dp;
qidx = skb_get_queue_mapping(skb);
- tx_ring = &nn->tx_rings[qidx];
+ tx_ring = &dp->tx_rings[qidx];
r_vec = tx_ring->r_vec;
- nd_q = netdev_get_tx_queue(nn->netdev, qidx);
+ nd_q = netdev_get_tx_queue(dp->netdev, qidx);
nr_frags = skb_shinfo(skb)->nr_frags;
if (unlikely(nfp_net_tx_full(tx_ring, nr_frags + 1))) {
- nn_warn_ratelimit(nn, "TX ring %d busy. wrp=%u rdp=%u\n",
- qidx, tx_ring->wr_p, tx_ring->rd_p);
+ nn_dp_warn(dp, "TX ring %d busy. wrp=%u rdp=%u\n",
+ qidx, tx_ring->wr_p, tx_ring->rd_p);
netif_tx_stop_queue(nd_q);
+ nfp_net_tx_xmit_more_flush(tx_ring);
u64_stats_update_begin(&r_vec->tx_sync);
r_vec->tx_busy++;
u64_stats_update_end(&r_vec->tx_sync);
@@ -766,9 +781,9 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
}
/* Start with the head skbuf */
- dma_addr = dma_map_single(&nn->pdev->dev, skb->data, skb_headlen(skb),
+ dma_addr = dma_map_single(dp->dev, skb->data, skb_headlen(skb),
DMA_TO_DEVICE);
- if (dma_mapping_error(&nn->pdev->dev, dma_addr))
+ if (dma_mapping_error(dp->dev, dma_addr))
goto err_free;
wr_idx = tx_ring->wr_p & (tx_ring->cnt - 1);
@@ -792,11 +807,11 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
txd->mss = 0;
txd->l4_offset = 0;
- nfp_net_tx_tso(nn, r_vec, txbuf, txd, skb);
+ nfp_net_tx_tso(r_vec, txbuf, txd, skb);
- nfp_net_tx_csum(nn, r_vec, txbuf, txd, skb);
+ nfp_net_tx_csum(dp, r_vec, txbuf, txd, skb);
- if (skb_vlan_tag_present(skb) && nn->ctrl & NFP_NET_CFG_CTRL_TXVLAN) {
+ if (skb_vlan_tag_present(skb) && dp->ctrl & NFP_NET_CFG_CTRL_TXVLAN) {
txd->flags |= PCIE_DESC_TX_VLAN;
txd->vlan = cpu_to_le16(skb_vlan_tag_get(skb));
}
@@ -810,9 +825,9 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
frag = &skb_shinfo(skb)->frags[f];
fsize = skb_frag_size(frag);
- dma_addr = skb_frag_dma_map(&nn->pdev->dev, frag, 0,
+ dma_addr = skb_frag_dma_map(dp->dev, frag, 0,
fsize, DMA_TO_DEVICE);
- if (dma_mapping_error(&nn->pdev->dev, dma_addr))
+ if (dma_mapping_error(dp->dev, dma_addr))
goto err_unmap;
wr_idx = (wr_idx + 1) & (tx_ring->cnt - 1);
@@ -851,8 +866,7 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
--f;
while (f >= 0) {
frag = &skb_shinfo(skb)->frags[f];
- dma_unmap_page(&nn->pdev->dev,
- tx_ring->txbufs[wr_idx].dma_addr,
+ dma_unmap_page(dp->dev, tx_ring->txbufs[wr_idx].dma_addr,
skb_frag_size(frag), DMA_TO_DEVICE);
tx_ring->txbufs[wr_idx].skb = NULL;
tx_ring->txbufs[wr_idx].dma_addr = 0;
@@ -861,13 +875,14 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
if (wr_idx < 0)
wr_idx += tx_ring->cnt;
}
- dma_unmap_single(&nn->pdev->dev, tx_ring->txbufs[wr_idx].dma_addr,
+ dma_unmap_single(dp->dev, tx_ring->txbufs[wr_idx].dma_addr,
skb_headlen(skb), DMA_TO_DEVICE);
tx_ring->txbufs[wr_idx].skb = NULL;
tx_ring->txbufs[wr_idx].dma_addr = 0;
tx_ring->txbufs[wr_idx].fidx = -2;
err_free:
- nn_warn_ratelimit(nn, "Failed to map DMA TX buffer\n");
+ nn_dp_warn(dp, "Failed to map DMA TX buffer\n");
+ nfp_net_tx_xmit_more_flush(tx_ring);
u64_stats_update_begin(&r_vec->tx_sync);
r_vec->tx_errors++;
u64_stats_update_end(&r_vec->tx_sync);
@@ -884,7 +899,7 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
{
struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
- struct nfp_net *nn = r_vec->nfp_net;
+ struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
const struct skb_frag_struct *frag;
struct netdev_queue *nd_q;
u32 done_pkts = 0, done_bytes = 0;
@@ -918,8 +933,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
if (fidx == -1) {
/* unmap head */
- dma_unmap_single(&nn->pdev->dev,
- tx_ring->txbufs[idx].dma_addr,
+ dma_unmap_single(dp->dev, tx_ring->txbufs[idx].dma_addr,
skb_headlen(skb), DMA_TO_DEVICE);
done_pkts += tx_ring->txbufs[idx].pkt_cnt;
@@ -927,8 +941,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
} else {
/* unmap fragment */
frag = &skb_shinfo(skb)->frags[fidx];
- dma_unmap_page(&nn->pdev->dev,
- tx_ring->txbufs[idx].dma_addr,
+ dma_unmap_page(dp->dev, tx_ring->txbufs[idx].dma_addr,
skb_frag_size(frag), DMA_TO_DEVICE);
}
@@ -948,7 +961,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
r_vec->tx_pkts += done_pkts;
u64_stats_update_end(&r_vec->tx_sync);
- nd_q = netdev_get_tx_queue(nn->netdev, tx_ring->idx);
+ nd_q = netdev_get_tx_queue(dp->netdev, tx_ring->idx);
netdev_tx_completed_queue(nd_q, done_pkts, done_bytes);
if (nfp_net_tx_ring_should_wake(tx_ring)) {
/* Make sure TX thread will see updated tx_ring->rd_p */
@@ -966,7 +979,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
static void nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring)
{
struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
- struct nfp_net *nn = r_vec->nfp_net;
+ struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
u32 done_pkts = 0, done_bytes = 0;
int idx, todo;
u32 qcp_rd_p;
@@ -989,8 +1002,7 @@ static void nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring)
if (!tx_ring->txbufs[idx].frag)
continue;
- nfp_net_dma_unmap_rx(nn, tx_ring->txbufs[idx].dma_addr,
- nn->fl_bufsz, DMA_BIDIRECTIONAL);
+ nfp_net_dma_unmap_rx(dp, tx_ring->txbufs[idx].dma_addr);
__free_page(virt_to_page(tx_ring->txbufs[idx].frag));
done_pkts++;
@@ -1015,17 +1027,16 @@ static void nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring)
/**
* nfp_net_tx_ring_reset() - Free any untransmitted buffers and reset pointers
- * @nn: NFP Net device
+ * @dp: NFP Net data path struct
* @tx_ring: TX ring structure
*
* Assumes that the device is stopped
*/
static void
-nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring)
+nfp_net_tx_ring_reset(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring)
{
struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
const struct skb_frag_struct *frag;
- struct pci_dev *pdev = nn->pdev;
struct netdev_queue *nd_q;
while (tx_ring->rd_p != tx_ring->wr_p) {
@@ -1036,8 +1047,7 @@ nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring)
tx_buf = &tx_ring->txbufs[idx];
if (tx_ring == r_vec->xdp_ring) {
- nfp_net_dma_unmap_rx(nn, tx_buf->dma_addr,
- nn->fl_bufsz, DMA_BIDIRECTIONAL);
+ nfp_net_dma_unmap_rx(dp, tx_buf->dma_addr);
__free_page(virt_to_page(tx_ring->txbufs[idx].frag));
} else {
struct sk_buff *skb = tx_ring->txbufs[idx].skb;
@@ -1045,13 +1055,13 @@ nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring)
if (tx_buf->fidx == -1) {
/* unmap head */
- dma_unmap_single(&pdev->dev, tx_buf->dma_addr,
+ dma_unmap_single(dp->dev, tx_buf->dma_addr,
skb_headlen(skb),
DMA_TO_DEVICE);
} else {
/* unmap fragment */
frag = &skb_shinfo(skb)->frags[tx_buf->fidx];
- dma_unmap_page(&pdev->dev, tx_buf->dma_addr,
+ dma_unmap_page(dp->dev, tx_buf->dma_addr,
skb_frag_size(frag),
DMA_TO_DEVICE);
}
@@ -1078,7 +1088,7 @@ nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring)
if (tx_ring == r_vec->xdp_ring)
return;
- nd_q = netdev_get_tx_queue(nn->netdev, tx_ring->idx);
+ nd_q = netdev_get_tx_queue(dp->netdev, tx_ring->idx);
netdev_tx_reset_queue(nd_q);
}
@@ -1087,7 +1097,7 @@ static void nfp_net_tx_timeout(struct net_device *netdev)
struct nfp_net *nn = netdev_priv(netdev);
int i;
- for (i = 0; i < nn->netdev->real_num_tx_queues; i++) {
+ for (i = 0; i < nn->dp.netdev->real_num_tx_queues; i++) {
if (!netif_tx_queue_stopped(netdev_get_tx_queue(netdev, i)))
continue;
nn_warn(nn, "TX timeout on ring: %d\n", i);
@@ -1098,16 +1108,17 @@ static void nfp_net_tx_timeout(struct net_device *netdev)
/* Receive processing
*/
static unsigned int
-nfp_net_calc_fl_bufsz(struct nfp_net *nn, unsigned int mtu)
+nfp_net_calc_fl_bufsz(struct nfp_net_dp *dp)
{
unsigned int fl_bufsz;
fl_bufsz = NFP_NET_RX_BUF_HEADROOM;
- if (nn->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC)
+ fl_bufsz += dp->rx_dma_off;
+ if (dp->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC)
fl_bufsz += NFP_NET_MAX_PREPEND;
else
- fl_bufsz += nn->rx_offset;
- fl_bufsz += ETH_HLEN + VLAN_HLEN * 2 + mtu;
+ fl_bufsz += dp->rx_offset;
+ fl_bufsz += ETH_HLEN + VLAN_HLEN * 2 + dp->mtu;
fl_bufsz = SKB_DATA_ALIGN(fl_bufsz);
fl_bufsz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
@@ -1126,62 +1137,56 @@ nfp_net_free_frag(void *frag, bool xdp)
/**
* nfp_net_rx_alloc_one() - Allocate and map page frag for RX
+ * @dp: NFP Net data path struct
* @rx_ring: RX ring structure of the skb
* @dma_addr: Pointer to storage for DMA address (output param)
- * @fl_bufsz: size of freelist buffers
- * @xdp: Whether XDP is enabled
*
* This function will allcate a new page frag, map it for DMA.
*
* Return: allocated page frag or NULL on failure.
*/
static void *
-nfp_net_rx_alloc_one(struct nfp_net_rx_ring *rx_ring, dma_addr_t *dma_addr,
- unsigned int fl_bufsz, bool xdp)
+nfp_net_rx_alloc_one(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring,
+ dma_addr_t *dma_addr)
{
- struct nfp_net *nn = rx_ring->r_vec->nfp_net;
- int direction;
void *frag;
- if (!xdp)
- frag = netdev_alloc_frag(fl_bufsz);
+ if (!dp->xdp_prog)
+ frag = netdev_alloc_frag(dp->fl_bufsz);
else
frag = page_address(alloc_page(GFP_KERNEL | __GFP_COLD));
if (!frag) {
- nn_warn_ratelimit(nn, "Failed to alloc receive page frag\n");
+ nn_dp_warn(dp, "Failed to alloc receive page frag\n");
return NULL;
}
- direction = xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
-
- *dma_addr = nfp_net_dma_map_rx(nn, frag, fl_bufsz, direction);
- if (dma_mapping_error(&nn->pdev->dev, *dma_addr)) {
- nfp_net_free_frag(frag, xdp);
- nn_warn_ratelimit(nn, "Failed to map DMA RX buffer\n");
+ *dma_addr = nfp_net_dma_map_rx(dp, frag);
+ if (dma_mapping_error(dp->dev, *dma_addr)) {
+ nfp_net_free_frag(frag, dp->xdp_prog);
+ nn_dp_warn(dp, "Failed to map DMA RX buffer\n");
return NULL;
}
return frag;
}
-static void *
-nfp_net_napi_alloc_one(struct nfp_net *nn, int direction, dma_addr_t *dma_addr)
+static void *nfp_net_napi_alloc_one(struct nfp_net_dp *dp, dma_addr_t *dma_addr)
{
void *frag;
- if (!nn->xdp_prog)
- frag = napi_alloc_frag(nn->fl_bufsz);
+ if (!dp->xdp_prog)
+ frag = napi_alloc_frag(dp->fl_bufsz);
else
frag = page_address(alloc_page(GFP_ATOMIC | __GFP_COLD));
if (!frag) {
- nn_warn_ratelimit(nn, "Failed to alloc receive page frag\n");
+ nn_dp_warn(dp, "Failed to alloc receive page frag\n");
return NULL;
}
- *dma_addr = nfp_net_dma_map_rx(nn, frag, nn->fl_bufsz, direction);
- if (dma_mapping_error(&nn->pdev->dev, *dma_addr)) {
- nfp_net_free_frag(frag, nn->xdp_prog);
- nn_warn_ratelimit(nn, "Failed to map DMA RX buffer\n");
+ *dma_addr = nfp_net_dma_map_rx(dp, frag);
+ if (dma_mapping_error(dp->dev, *dma_addr)) {
+ nfp_net_free_frag(frag, dp->xdp_prog);
+ nn_dp_warn(dp, "Failed to map DMA RX buffer\n");
return NULL;
}
@@ -1190,11 +1195,13 @@ nfp_net_napi_alloc_one(struct nfp_net *nn, int direction, dma_addr_t *dma_addr)
/**
* nfp_net_rx_give_one() - Put mapped skb on the software and hardware rings
+ * @dp: NFP Net data path struct
* @rx_ring: RX ring structure
* @frag: page fragment buffer
* @dma_addr: DMA address of skb mapping
*/
-static void nfp_net_rx_give_one(struct nfp_net_rx_ring *rx_ring,
+static void nfp_net_rx_give_one(const struct nfp_net_dp *dp,
+ struct nfp_net_rx_ring *rx_ring,
void *frag, dma_addr_t dma_addr)
{
unsigned int wr_idx;
@@ -1208,7 +1215,8 @@ static void nfp_net_rx_give_one(struct nfp_net_rx_ring *rx_ring,
/* Fill freelist descriptor */
rx_ring->rxds[wr_idx].fld.reserved = 0;
rx_ring->rxds[wr_idx].fld.meta_len_dd = 0;
- nfp_desc_set_dma_addr(&rx_ring->rxds[wr_idx].fld, dma_addr);
+ nfp_desc_set_dma_addr(&rx_ring->rxds[wr_idx].fld,
+ dma_addr + dp->rx_dma_off);
rx_ring->wr_p++;
rx_ring->wr_ptr_add++;
@@ -1249,19 +1257,17 @@ static void nfp_net_rx_ring_reset(struct nfp_net_rx_ring *rx_ring)
/**
* nfp_net_rx_ring_bufs_free() - Free any buffers currently on the RX ring
- * @nn: NFP Net device
+ * @dp: NFP Net data path struct
* @rx_ring: RX ring to remove buffers from
- * @xdp: Whether XDP is enabled
*
* Assumes that the device is stopped and buffers are in [0, ring->cnt - 1)
* entries. After device is disabled nfp_net_rx_ring_reset() must be called
* to restore required ring geometry.
*/
static void
-nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
- bool xdp)
+nfp_net_rx_ring_bufs_free(struct nfp_net_dp *dp,
+ struct nfp_net_rx_ring *rx_ring)
{
- int direction = xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
unsigned int i;
for (i = 0; i < rx_ring->cnt - 1; i++) {
@@ -1272,9 +1278,8 @@ nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
if (!rx_ring->rxbufs[i].frag)
continue;
- nfp_net_dma_unmap_rx(nn, rx_ring->rxbufs[i].dma_addr,
- rx_ring->bufsz, direction);
- nfp_net_free_frag(rx_ring->rxbufs[i].frag, xdp);
+ nfp_net_dma_unmap_rx(dp, rx_ring->rxbufs[i].dma_addr);
+ nfp_net_free_frag(rx_ring->rxbufs[i].frag, dp->xdp_prog);
rx_ring->rxbufs[i].dma_addr = 0;
rx_ring->rxbufs[i].frag = NULL;
}
@@ -1282,13 +1287,12 @@ nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
/**
* nfp_net_rx_ring_bufs_alloc() - Fill RX ring with buffers (don't give to FW)
- * @nn: NFP Net device
+ * @dp: NFP Net data path struct
* @rx_ring: RX ring to remove buffers from
- * @xdp: Whether XDP is enabled
*/
static int
-nfp_net_rx_ring_bufs_alloc(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
- bool xdp)
+nfp_net_rx_ring_bufs_alloc(struct nfp_net_dp *dp,
+ struct nfp_net_rx_ring *rx_ring)
{
struct nfp_net_rx_buf *rxbufs;
unsigned int i;
@@ -1297,10 +1301,9 @@ nfp_net_rx_ring_bufs_alloc(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
for (i = 0; i < rx_ring->cnt - 1; i++) {
rxbufs[i].frag =
- nfp_net_rx_alloc_one(rx_ring, &rxbufs[i].dma_addr,
- rx_ring->bufsz, xdp);
+ nfp_net_rx_alloc_one(dp, rx_ring, &rxbufs[i].dma_addr);
if (!rxbufs[i].frag) {
- nfp_net_rx_ring_bufs_free(nn, rx_ring, xdp);
+ nfp_net_rx_ring_bufs_free(dp, rx_ring);
return -ENOMEM;
}
}
@@ -1310,14 +1313,17 @@ nfp_net_rx_ring_bufs_alloc(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
/**
* nfp_net_rx_ring_fill_freelist() - Give buffers from the ring to FW
+ * @dp: NFP Net data path struct
* @rx_ring: RX ring to fill
*/
-static void nfp_net_rx_ring_fill_freelist(struct nfp_net_rx_ring *rx_ring)
+static void
+nfp_net_rx_ring_fill_freelist(struct nfp_net_dp *dp,
+ struct nfp_net_rx_ring *rx_ring)
{
unsigned int i;
for (i = 0; i < rx_ring->cnt - 1; i++)
- nfp_net_rx_give_one(rx_ring, rx_ring->rxbufs[i].frag,
+ nfp_net_rx_give_one(dp, rx_ring, rx_ring->rxbufs[i].frag,
rx_ring->rxbufs[i].dma_addr);
}
@@ -1337,17 +1343,18 @@ static int nfp_net_rx_csum_has_errors(u16 flags)
/**
* nfp_net_rx_csum() - set SKB checksum field based on RX descriptor flags
- * @nn: NFP Net device
+ * @dp: NFP Net data path struct
* @r_vec: per-ring structure
* @rxd: Pointer to RX descriptor
* @skb: Pointer to SKB
*/
-static void nfp_net_rx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
+static void nfp_net_rx_csum(struct nfp_net_dp *dp,
+ struct nfp_net_r_vector *r_vec,
struct nfp_net_rx_desc *rxd, struct sk_buff *skb)
{
skb_checksum_none_assert(skb);
- if (!(nn->netdev->features & NETIF_F_RXCSUM))
+ if (!(dp->netdev->features & NETIF_F_RXCSUM))
return;
if (nfp_net_rx_csum_has_errors(le16_to_cpu(rxd->rxd.flags))) {
@@ -1398,24 +1405,21 @@ static void nfp_net_set_hash(struct net_device *netdev, struct sk_buff *skb,
static void
nfp_net_set_hash_desc(struct net_device *netdev, struct sk_buff *skb,
- struct nfp_net_rx_desc *rxd)
+ void *data, struct nfp_net_rx_desc *rxd)
{
- struct nfp_net_rx_hash *rx_hash;
+ struct nfp_net_rx_hash *rx_hash = data;
if (!(rxd->rxd.flags & PCIE_DESC_RX_RSS))
return;
- rx_hash = (struct nfp_net_rx_hash *)(skb->data - sizeof(*rx_hash));
-
nfp_net_set_hash(netdev, skb, get_unaligned_be32(&rx_hash->hash_type),
&rx_hash->hash);
}
static void *
nfp_net_parse_meta(struct net_device *netdev, struct sk_buff *skb,
- int meta_len)
+ void *data, int meta_len)
{
- u8 *data = skb->data - meta_len;
u32 meta_info;
meta_info = get_unaligned_be32(data);
@@ -1445,8 +1449,9 @@ nfp_net_parse_meta(struct net_device *netdev, struct sk_buff *skb,
}
static void
-nfp_net_rx_drop(struct nfp_net_r_vector *r_vec, struct nfp_net_rx_ring *rx_ring,
- struct nfp_net_rx_buf *rxbuf, struct sk_buff *skb)
+nfp_net_rx_drop(const struct nfp_net_dp *dp, struct nfp_net_r_vector *r_vec,
+ struct nfp_net_rx_ring *rx_ring, struct nfp_net_rx_buf *rxbuf,
+ struct sk_buff *skb)
{
u64_stats_update_begin(&r_vec->rx_sync);
r_vec->rx_drops++;
@@ -1458,15 +1463,15 @@ nfp_net_rx_drop(struct nfp_net_r_vector *r_vec, struct nfp_net_rx_ring *rx_ring,
if (skb && rxbuf && skb->head == rxbuf->frag)
page_ref_inc(virt_to_head_page(rxbuf->frag));
if (rxbuf)
- nfp_net_rx_give_one(rx_ring, rxbuf->frag, rxbuf->dma_addr);
+ nfp_net_rx_give_one(dp, rx_ring, rxbuf->frag, rxbuf->dma_addr);
if (skb)
dev_kfree_skb_any(skb);
}
static bool
-nfp_net_tx_xdp_buf(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
+nfp_net_tx_xdp_buf(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring,
struct nfp_net_tx_ring *tx_ring,
- struct nfp_net_rx_buf *rxbuf, unsigned int pkt_off,
+ struct nfp_net_rx_buf *rxbuf, unsigned int dma_off,
unsigned int pkt_len)
{
struct nfp_net_tx_buf *txbuf;
@@ -1476,16 +1481,16 @@ nfp_net_tx_xdp_buf(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
int wr_idx;
if (unlikely(nfp_net_tx_full(tx_ring, 1))) {
- nfp_net_rx_drop(rx_ring->r_vec, rx_ring, rxbuf, NULL);
+ nfp_net_rx_drop(dp, rx_ring->r_vec, rx_ring, rxbuf, NULL);
return false;
}
- new_frag = nfp_net_napi_alloc_one(nn, DMA_BIDIRECTIONAL, &new_dma_addr);
+ new_frag = nfp_net_napi_alloc_one(dp, &new_dma_addr);
if (unlikely(!new_frag)) {
- nfp_net_rx_drop(rx_ring->r_vec, rx_ring, rxbuf, NULL);
+ nfp_net_rx_drop(dp, rx_ring->r_vec, rx_ring, rxbuf, NULL);
return false;
}
- nfp_net_rx_give_one(rx_ring, new_frag, new_dma_addr);
+ nfp_net_rx_give_one(dp, rx_ring, new_frag, new_dma_addr);
wr_idx = tx_ring->wr_p & (tx_ring->cnt - 1);
@@ -1497,14 +1502,14 @@ nfp_net_tx_xdp_buf(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
txbuf->pkt_cnt = 1;
txbuf->real_len = pkt_len;
- dma_sync_single_for_device(&nn->pdev->dev, rxbuf->dma_addr + pkt_off,
+ dma_sync_single_for_device(dp->dev, rxbuf->dma_addr + dma_off,
pkt_len, DMA_BIDIRECTIONAL);
/* Build TX descriptor */
txd = &tx_ring->txds[wr_idx];
txd->offset_eop = PCIE_DESC_TX_EOP;
txd->dma_len = cpu_to_le16(pkt_len);
- nfp_desc_set_dma_addr(txd, rxbuf->dma_addr + pkt_off);
+ nfp_desc_set_dma_addr(txd, rxbuf->dma_addr + dma_off);
txd->data_len = cpu_to_le16(pkt_len);
txd->flags = 0;
@@ -1516,14 +1521,24 @@ nfp_net_tx_xdp_buf(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
return true;
}
-static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, unsigned int len)
+static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, void *hard_start,
+ unsigned int *off, unsigned int *len)
{
struct xdp_buff xdp;
+ void *orig_data;
+ int ret;
- xdp.data = data;
- xdp.data_end = data + len;
+ xdp.data_hard_start = hard_start;
+ xdp.data = data + *off;
+ xdp.data_end = data + *off + *len;
- return bpf_prog_run_xdp(prog, &xdp);
+ orig_data = xdp.data;
+ ret = bpf_prog_run_xdp(prog, &xdp);
+
+ *len -= xdp.data - orig_data;
+ *off += xdp.data - orig_data;
+
+ return ret;
}
/**
@@ -1540,27 +1555,27 @@ static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, unsigned int len)
static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
{
struct nfp_net_r_vector *r_vec = rx_ring->r_vec;
- struct nfp_net *nn = r_vec->nfp_net;
+ struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
struct nfp_net_tx_ring *tx_ring;
struct bpf_prog *xdp_prog;
unsigned int true_bufsz;
struct sk_buff *skb;
int pkts_polled = 0;
- int rx_dma_map_dir;
int idx;
rcu_read_lock();
- xdp_prog = READ_ONCE(nn->xdp_prog);
- rx_dma_map_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
- true_bufsz = xdp_prog ? PAGE_SIZE : nn->fl_bufsz;
+ xdp_prog = READ_ONCE(dp->xdp_prog);
+ true_bufsz = xdp_prog ? PAGE_SIZE : dp->fl_bufsz;
tx_ring = r_vec->xdp_ring;
while (pkts_polled < budget) {
- unsigned int meta_len, data_len, data_off, pkt_len, pkt_off;
+ unsigned int meta_len, data_len, data_off, pkt_len;
+ u8 meta_prepend[NFP_NET_MAX_PREPEND];
struct nfp_net_rx_buf *rxbuf;
struct nfp_net_rx_desc *rxd;
dma_addr_t new_dma_addr;
void *new_frag;
+ u8 *meta;
idx = rx_ring->rd_p & (rx_ring->cnt - 1);
@@ -1593,11 +1608,11 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
data_len = le16_to_cpu(rxd->rxd.data_len);
pkt_len = data_len - meta_len;
- if (nn->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC)
- pkt_off = meta_len;
+ if (dp->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC)
+ data_off = NFP_NET_RX_BUF_HEADROOM + meta_len;
else
- pkt_off = nn->rx_offset;
- data_off = NFP_NET_RX_BUF_HEADROOM + pkt_off;
+ data_off = NFP_NET_RX_BUF_HEADROOM + dp->rx_offset;
+ data_off += dp->rx_dma_off;
/* Stats update */
u64_stats_update_begin(&r_vec->rx_sync);
@@ -1605,30 +1620,55 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
r_vec->rx_bytes += pkt_len;
u64_stats_update_end(&r_vec->rx_sync);
+ /* Pointer to start of metadata */
+ meta = rxbuf->frag + data_off - meta_len;
+
+ if (unlikely(meta_len > NFP_NET_MAX_PREPEND ||
+ (dp->rx_offset && meta_len > dp->rx_offset))) {
+ nn_dp_warn(dp, "oversized RX packet metadata %u\n",
+ meta_len);
+ nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf, NULL);
+ continue;
+ }
+
if (xdp_prog && !(rxd->rxd.flags & PCIE_DESC_RX_BPF &&
- nn->bpf_offload_xdp)) {
+ dp->bpf_offload_xdp)) {
+ unsigned int dma_off;
+ void *hard_start;
int act;
- dma_sync_single_for_cpu(&nn->pdev->dev,
- rxbuf->dma_addr + pkt_off,
- pkt_len, DMA_BIDIRECTIONAL);
- act = nfp_net_run_xdp(xdp_prog, rxbuf->frag + data_off,
- pkt_len);
+ hard_start = rxbuf->frag + NFP_NET_RX_BUF_HEADROOM;
+ dma_off = data_off - NFP_NET_RX_BUF_HEADROOM;
+ dma_sync_single_for_cpu(dp->dev, rxbuf->dma_addr,
+ dma_off + pkt_len,
+ DMA_BIDIRECTIONAL);
+
+ /* Move prepend out of the way */
+ if (xdp_prog->xdp_adjust_head) {
+ memcpy(meta_prepend, meta, meta_len);
+ meta = meta_prepend;
+ }
+
+ act = nfp_net_run_xdp(xdp_prog, rxbuf->frag, hard_start,
+ &data_off, &pkt_len);
switch (act) {
case XDP_PASS:
break;
case XDP_TX:
- if (unlikely(!nfp_net_tx_xdp_buf(nn, rx_ring,
+ dma_off = data_off - NFP_NET_RX_BUF_HEADROOM;
+ if (unlikely(!nfp_net_tx_xdp_buf(dp, rx_ring,
tx_ring, rxbuf,
- pkt_off, pkt_len)))
- trace_xdp_exception(nn->netdev, xdp_prog, act);
+ dma_off,
+ pkt_len)))
+ trace_xdp_exception(dp->netdev,
+ xdp_prog, act);
continue;
default:
bpf_warn_invalid_xdp_action(act);
case XDP_ABORTED:
- trace_xdp_exception(nn->netdev, xdp_prog, act);
+ trace_xdp_exception(dp->netdev, xdp_prog, act);
case XDP_DROP:
- nfp_net_rx_give_one(rx_ring, rxbuf->frag,
+ nfp_net_rx_give_one(dp, rx_ring, rxbuf->frag,
rxbuf->dma_addr);
continue;
}
@@ -1636,41 +1676,40 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
skb = build_skb(rxbuf->frag, true_bufsz);
if (unlikely(!skb)) {
- nfp_net_rx_drop(r_vec, rx_ring, rxbuf, NULL);
+ nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf, NULL);
continue;
}
- new_frag = nfp_net_napi_alloc_one(nn, rx_dma_map_dir,
- &new_dma_addr);
+ new_frag = nfp_net_napi_alloc_one(dp, &new_dma_addr);
if (unlikely(!new_frag)) {
- nfp_net_rx_drop(r_vec, rx_ring, rxbuf, skb);
+ nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf, skb);
continue;
}
- nfp_net_dma_unmap_rx(nn, rxbuf->dma_addr, nn->fl_bufsz,
- rx_dma_map_dir);
+ nfp_net_dma_unmap_rx(dp, rxbuf->dma_addr);
- nfp_net_rx_give_one(rx_ring, new_frag, new_dma_addr);
+ nfp_net_rx_give_one(dp, rx_ring, new_frag, new_dma_addr);
skb_reserve(skb, data_off);
skb_put(skb, pkt_len);
- if (nn->fw_ver.major <= 3) {
- nfp_net_set_hash_desc(nn->netdev, skb, rxd);
+ if (!dp->chained_metadata_format) {
+ nfp_net_set_hash_desc(dp->netdev, skb, meta, rxd);
} else if (meta_len) {
void *end;
- end = nfp_net_parse_meta(nn->netdev, skb, meta_len);
- if (unlikely(end != skb->data)) {
- nn_warn_ratelimit(nn, "invalid RX packet metadata\n");
- nfp_net_rx_drop(r_vec, rx_ring, NULL, skb);
+ end = nfp_net_parse_meta(dp->netdev, skb, meta,
+ meta_len);
+ if (unlikely(end != meta + meta_len)) {
+ nn_dp_warn(dp, "invalid RX packet metadata\n");
+ nfp_net_rx_drop(dp, r_vec, rx_ring, NULL, skb);
continue;
}
}
skb_record_rx_queue(skb, rx_ring->idx);
- skb->protocol = eth_type_trans(skb, nn->netdev);
+ skb->protocol = eth_type_trans(skb, dp->netdev);
- nfp_net_rx_csum(nn, r_vec, rxd, skb);
+ nfp_net_rx_csum(dp, r_vec, rxd, skb);
if (rxd->rxd.flags & PCIE_DESC_RX_VLAN)
__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
@@ -1707,10 +1746,9 @@ static int nfp_net_poll(struct napi_struct *napi, int budget)
nfp_net_xdp_complete(r_vec->xdp_ring);
}
- if (pkts_polled < budget) {
- napi_complete_done(napi, pkts_polled);
- nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry);
- }
+ if (pkts_polled < budget)
+ if (napi_complete_done(napi, pkts_polled))
+ nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry);
return pkts_polled;
}
@@ -1725,13 +1763,12 @@ static int nfp_net_poll(struct napi_struct *napi, int budget)
static void nfp_net_tx_ring_free(struct nfp_net_tx_ring *tx_ring)
{
struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
- struct nfp_net *nn = r_vec->nfp_net;
- struct pci_dev *pdev = nn->pdev;
+ struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
kfree(tx_ring->txbufs);
if (tx_ring->txds)
- dma_free_coherent(&pdev->dev, tx_ring->size,
+ dma_free_coherent(dp->dev, tx_ring->size,
tx_ring->txds, tx_ring->dma);
tx_ring->cnt = 0;
@@ -1743,24 +1780,23 @@ static void nfp_net_tx_ring_free(struct nfp_net_tx_ring *tx_ring)
/**
* nfp_net_tx_ring_alloc() - Allocate resource for a TX ring
+ * @dp: NFP Net data path struct
* @tx_ring: TX Ring structure to allocate
- * @cnt: Ring buffer count
* @is_xdp: True if ring will be used for XDP
*
* Return: 0 on success, negative errno otherwise.
*/
static int
-nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring, u32 cnt, bool is_xdp)
+nfp_net_tx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring,
+ bool is_xdp)
{
struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
- struct nfp_net *nn = r_vec->nfp_net;
- struct pci_dev *pdev = nn->pdev;
int sz;
- tx_ring->cnt = cnt;
+ tx_ring->cnt = dp->txd_cnt;
tx_ring->size = sizeof(*tx_ring->txds) * tx_ring->cnt;
- tx_ring->txds = dma_zalloc_coherent(&pdev->dev, tx_ring->size,
+ tx_ring->txds = dma_zalloc_coherent(dp->dev, tx_ring->size,
&tx_ring->dma, GFP_KERNEL);
if (!tx_ring->txds)
goto err_alloc;
@@ -1771,14 +1807,9 @@ nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring, u32 cnt, bool is_xdp)
goto err_alloc;
if (!is_xdp)
- netif_set_xps_queue(nn->netdev, &r_vec->affinity_mask,
+ netif_set_xps_queue(dp->netdev, &r_vec->affinity_mask,
tx_ring->idx);
- nn_dbg(nn, "TxQ%02d: QCidx=%02d cnt=%d dma=%#llx host=%p %s\n",
- tx_ring->idx, tx_ring->qcidx,
- tx_ring->cnt, (unsigned long long)tx_ring->dma, tx_ring->txds,
- is_xdp ? "XDP" : "");
-
return 0;
err_alloc:
@@ -1786,62 +1817,45 @@ nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring, u32 cnt, bool is_xdp)
return -ENOMEM;
}
-static struct nfp_net_tx_ring *
-nfp_net_tx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_ring_set *s,
- unsigned int num_stack_tx_rings)
+static int nfp_net_tx_rings_prepare(struct nfp_net *nn, struct nfp_net_dp *dp)
{
- struct nfp_net_tx_ring *rings;
unsigned int r;
- rings = kcalloc(s->n_rings, sizeof(*rings), GFP_KERNEL);
- if (!rings)
- return NULL;
+ dp->tx_rings = kcalloc(dp->num_tx_rings, sizeof(*dp->tx_rings),
+ GFP_KERNEL);
+ if (!dp->tx_rings)
+ return -ENOMEM;
- for (r = 0; r < s->n_rings; r++) {
+ for (r = 0; r < dp->num_tx_rings; r++) {
int bias = 0;
- if (r >= num_stack_tx_rings)
- bias = num_stack_tx_rings;
+ if (r >= dp->num_stack_tx_rings)
+ bias = dp->num_stack_tx_rings;
- nfp_net_tx_ring_init(&rings[r], &nn->r_vecs[r - bias], r);
+ nfp_net_tx_ring_init(&dp->tx_rings[r], &nn->r_vecs[r - bias],
+ r);
- if (nfp_net_tx_ring_alloc(&rings[r], s->dcnt, bias))
+ if (nfp_net_tx_ring_alloc(dp, &dp->tx_rings[r], bias))
goto err_free_prev;
}
- return s->rings = rings;
+ return 0;
err_free_prev:
while (r--)
- nfp_net_tx_ring_free(&rings[r]);
- kfree(rings);
- return NULL;
+ nfp_net_tx_ring_free(&dp->tx_rings[r]);
+ kfree(dp->tx_rings);
+ return -ENOMEM;
}
-static void
-nfp_net_tx_ring_set_swap(struct nfp_net *nn, struct nfp_net_ring_set *s)
+static void nfp_net_tx_rings_free(struct nfp_net_dp *dp)
{
- struct nfp_net_ring_set new = *s;
-
- s->dcnt = nn->txd_cnt;
- s->rings = nn->tx_rings;
- s->n_rings = nn->num_tx_rings;
-
- nn->txd_cnt = new.dcnt;
- nn->tx_rings = new.rings;
- nn->num_tx_rings = new.n_rings;
-}
-
-static void
-nfp_net_tx_ring_set_free(struct nfp_net *nn, struct nfp_net_ring_set *s)
-{
- struct nfp_net_tx_ring *rings = s->rings;
unsigned int r;
- for (r = 0; r < s->n_rings; r++)
- nfp_net_tx_ring_free(&rings[r]);
+ for (r = 0; r < dp->num_tx_rings; r++)
+ nfp_net_tx_ring_free(&dp->tx_rings[r]);
- kfree(rings);
+ kfree(dp->tx_rings);
}
/**
@@ -1851,13 +1865,12 @@ nfp_net_tx_ring_set_free(struct nfp_net *nn, struct nfp_net_ring_set *s)
static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring)
{
struct nfp_net_r_vector *r_vec = rx_ring->r_vec;
- struct nfp_net *nn = r_vec->nfp_net;
- struct pci_dev *pdev = nn->pdev;
+ struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
kfree(rx_ring->rxbufs);
if (rx_ring->rxds)
- dma_free_coherent(&pdev->dev, rx_ring->size,
+ dma_free_coherent(dp->dev, rx_ring->size,
rx_ring->rxds, rx_ring->dma);
rx_ring->cnt = 0;
@@ -1869,26 +1882,19 @@ static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring)
/**
* nfp_net_rx_ring_alloc() - Allocate resource for a RX ring
+ * @dp: NFP Net data path struct
* @rx_ring: RX ring to allocate
- * @fl_bufsz: Size of buffers to allocate
- * @cnt: Ring buffer count
*
* Return: 0 on success, negative errno otherwise.
*/
static int
-nfp_net_rx_ring_alloc(struct nfp_net_rx_ring *rx_ring, unsigned int fl_bufsz,
- u32 cnt)
+nfp_net_rx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring)
{
- struct nfp_net_r_vector *r_vec = rx_ring->r_vec;
- struct nfp_net *nn = r_vec->nfp_net;
- struct pci_dev *pdev = nn->pdev;
int sz;
- rx_ring->cnt = cnt;
- rx_ring->bufsz = fl_bufsz;
-
+ rx_ring->cnt = dp->rxd_cnt;
rx_ring->size = sizeof(*rx_ring->rxds) * rx_ring->cnt;
- rx_ring->rxds = dma_zalloc_coherent(&pdev->dev, rx_ring->size,
+ rx_ring->rxds = dma_zalloc_coherent(dp->dev, rx_ring->size,
&rx_ring->dma, GFP_KERNEL);
if (!rx_ring->rxds)
goto err_alloc;
@@ -1898,10 +1904,6 @@ nfp_net_rx_ring_alloc(struct nfp_net_rx_ring *rx_ring, unsigned int fl_bufsz,
if (!rx_ring->rxbufs)
goto err_alloc;
- nn_dbg(nn, "RxQ%02d: FlQCidx=%02d RxQCidx=%02d cnt=%d dma=%#llx host=%p\n",
- rx_ring->idx, rx_ring->fl_qcidx, rx_ring->rx_qcidx,
- rx_ring->cnt, (unsigned long long)rx_ring->dma, rx_ring->rxds);
-
return 0;
err_alloc:
@@ -1909,82 +1911,59 @@ nfp_net_rx_ring_alloc(struct nfp_net_rx_ring *rx_ring, unsigned int fl_bufsz,
return -ENOMEM;
}
-static struct nfp_net_rx_ring *
-nfp_net_rx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_ring_set *s,
- bool xdp)
+static int nfp_net_rx_rings_prepare(struct nfp_net *nn, struct nfp_net_dp *dp)
{
- unsigned int fl_bufsz = nfp_net_calc_fl_bufsz(nn, s->mtu);
- struct nfp_net_rx_ring *rings;
unsigned int r;
- rings = kcalloc(s->n_rings, sizeof(*rings), GFP_KERNEL);
- if (!rings)
- return NULL;
+ dp->rx_rings = kcalloc(dp->num_rx_rings, sizeof(*dp->rx_rings),
+ GFP_KERNEL);
+ if (!dp->rx_rings)
+ return -ENOMEM;
- for (r = 0; r < s->n_rings; r++) {
- nfp_net_rx_ring_init(&rings[r], &nn->r_vecs[r], r);
+ for (r = 0; r < dp->num_rx_rings; r++) {
+ nfp_net_rx_ring_init(&dp->rx_rings[r], &nn->r_vecs[r], r);
- if (nfp_net_rx_ring_alloc(&rings[r], fl_bufsz, s->dcnt))
+ if (nfp_net_rx_ring_alloc(dp, &dp->rx_rings[r]))
goto err_free_prev;
- if (nfp_net_rx_ring_bufs_alloc(nn, &rings[r], xdp))
+ if (nfp_net_rx_ring_bufs_alloc(dp, &dp->rx_rings[r]))
goto err_free_ring;
}
- return s->rings = rings;
+ return 0;
err_free_prev:
while (r--) {
- nfp_net_rx_ring_bufs_free(nn, &rings[r], xdp);
+ nfp_net_rx_ring_bufs_free(dp, &dp->rx_rings[r]);
err_free_ring:
- nfp_net_rx_ring_free(&rings[r]);
+ nfp_net_rx_ring_free(&dp->rx_rings[r]);
}
- kfree(rings);
- return NULL;
+ kfree(dp->rx_rings);
+ return -ENOMEM;
}
-static void
-nfp_net_rx_ring_set_swap(struct nfp_net *nn, struct nfp_net_ring_set *s)
+static void nfp_net_rx_rings_free(struct nfp_net_dp *dp)
{
- struct nfp_net_ring_set new = *s;
-
- s->mtu = nn->netdev->mtu;
- s->dcnt = nn->rxd_cnt;
- s->rings = nn->rx_rings;
- s->n_rings = nn->num_rx_rings;
-
- nn->netdev->mtu = new.mtu;
- nn->fl_bufsz = nfp_net_calc_fl_bufsz(nn, new.mtu);
- nn->rxd_cnt = new.dcnt;
- nn->rx_rings = new.rings;
- nn->num_rx_rings = new.n_rings;
-}
-
-static void
-nfp_net_rx_ring_set_free(struct nfp_net *nn, struct nfp_net_ring_set *s,
- bool xdp)
-{
- struct nfp_net_rx_ring *rings = s->rings;
unsigned int r;
- for (r = 0; r < s->n_rings; r++) {
- nfp_net_rx_ring_bufs_free(nn, &rings[r], xdp);
- nfp_net_rx_ring_free(&rings[r]);
+ for (r = 0; r < dp->num_rx_rings; r++) {
+ nfp_net_rx_ring_bufs_free(dp, &dp->rx_rings[r]);
+ nfp_net_rx_ring_free(&dp->rx_rings[r]);
}
- kfree(rings);
+ kfree(dp->rx_rings);
}
static void
-nfp_net_vector_assign_rings(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
- int idx)
+nfp_net_vector_assign_rings(struct nfp_net_dp *dp,
+ struct nfp_net_r_vector *r_vec, int idx)
{
- r_vec->rx_ring = idx < nn->num_rx_rings ? &nn->rx_rings[idx] : NULL;
+ r_vec->rx_ring = idx < dp->num_rx_rings ? &dp->rx_rings[idx] : NULL;
r_vec->tx_ring =
- idx < nn->num_stack_tx_rings ? &nn->tx_rings[idx] : NULL;
+ idx < dp->num_stack_tx_rings ? &dp->tx_rings[idx] : NULL;
- r_vec->xdp_ring = idx < nn->num_tx_rings - nn->num_stack_tx_rings ?
- &nn->tx_rings[nn->num_stack_tx_rings + idx] : NULL;
+ r_vec->xdp_ring = idx < dp->num_tx_rings - dp->num_stack_tx_rings ?
+ &dp->tx_rings[dp->num_stack_tx_rings + idx] : NULL;
}
static int
@@ -1994,11 +1973,11 @@ nfp_net_prepare_vector(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
int err;
/* Setup NAPI */
- netif_napi_add(nn->netdev, &r_vec->napi,
+ netif_napi_add(nn->dp.netdev, &r_vec->napi,
nfp_net_poll, NAPI_POLL_WEIGHT);
snprintf(r_vec->name, sizeof(r_vec->name),
- "%s-rxtx-%d", nn->netdev->name, idx);
+ "%s-rxtx-%d", nn->dp.netdev->name, idx);
err = request_irq(r_vec->irq_vector, r_vec->handler, 0, r_vec->name,
r_vec);
if (err) {
@@ -2045,7 +2024,7 @@ void nfp_net_rss_write_key(struct nfp_net *nn)
{
int i;
- for (i = 0; i < NFP_NET_CFG_RSS_KEY_SZ; i += 4)
+ for (i = 0; i < nfp_net_rss_key_sz(nn); i += 4)
nn_writel(nn, NFP_NET_CFG_RSS_KEY + i,
get_unaligned_le32(nn->rss_key + i));
}
@@ -2069,13 +2048,13 @@ void nfp_net_coalesce_write_cfg(struct nfp_net *nn)
/* copy RX interrupt coalesce parameters */
value = (nn->rx_coalesce_max_frames << 16) |
(factor * nn->rx_coalesce_usecs);
- for (i = 0; i < nn->num_rx_rings; i++)
+ for (i = 0; i < nn->dp.num_rx_rings; i++)
nn_writel(nn, NFP_NET_CFG_RXR_IRQ_MOD(i), value);
/* copy TX interrupt coalesce parameters */
value = (nn->tx_coalesce_max_frames << 16) |
(factor * nn->tx_coalesce_usecs);
- for (i = 0; i < nn->num_tx_rings; i++)
+ for (i = 0; i < nn->dp.num_tx_rings; i++)
nn_writel(nn, NFP_NET_CFG_TXR_IRQ_MOD(i), value);
}
@@ -2090,9 +2069,9 @@ void nfp_net_coalesce_write_cfg(struct nfp_net *nn)
static void nfp_net_write_mac_addr(struct nfp_net *nn)
{
nn_writel(nn, NFP_NET_CFG_MACADDR + 0,
- get_unaligned_be32(nn->netdev->dev_addr));
+ get_unaligned_be32(nn->dp.netdev->dev_addr));
nn_writew(nn, NFP_NET_CFG_MACADDR + 6,
- get_unaligned_be16(nn->netdev->dev_addr + 4));
+ get_unaligned_be16(nn->dp.netdev->dev_addr + 4));
}
static void nfp_net_vec_clear_ring_data(struct nfp_net *nn, unsigned int idx)
@@ -2116,7 +2095,7 @@ static void nfp_net_clear_config_and_disable(struct nfp_net *nn)
unsigned int r;
int err;
- new_ctrl = nn->ctrl;
+ new_ctrl = nn->dp.ctrl;
new_ctrl &= ~NFP_NET_CFG_CTRL_ENABLE;
update = NFP_NET_CFG_UPDATE_GEN;
update |= NFP_NET_CFG_UPDATE_MSIX;
@@ -2133,14 +2112,14 @@ static void nfp_net_clear_config_and_disable(struct nfp_net *nn)
if (err)
nn_err(nn, "Could not disable device: %d\n", err);
- for (r = 0; r < nn->num_rx_rings; r++)
- nfp_net_rx_ring_reset(&nn->rx_rings[r]);
- for (r = 0; r < nn->num_tx_rings; r++)
- nfp_net_tx_ring_reset(nn, &nn->tx_rings[r]);
- for (r = 0; r < nn->num_r_vecs; r++)
+ for (r = 0; r < nn->dp.num_rx_rings; r++)
+ nfp_net_rx_ring_reset(&nn->dp.rx_rings[r]);
+ for (r = 0; r < nn->dp.num_tx_rings; r++)
+ nfp_net_tx_ring_reset(&nn->dp, &nn->dp.tx_rings[r]);
+ for (r = 0; r < nn->dp.num_r_vecs; r++)
nfp_net_vec_clear_ring_data(nn, r);
- nn->ctrl = new_ctrl;
+ nn->dp.ctrl = new_ctrl;
}
static void
@@ -2162,13 +2141,17 @@ nfp_net_tx_ring_hw_cfg_write(struct nfp_net *nn,
nn_writeb(nn, NFP_NET_CFG_TXR_VEC(idx), tx_ring->r_vec->irq_entry);
}
-static int __nfp_net_set_config_and_enable(struct nfp_net *nn)
+/**
+ * nfp_net_set_config_and_enable() - Write control BAR and enable NFP
+ * @nn: NFP Net device to reconfigure
+ */
+static int nfp_net_set_config_and_enable(struct nfp_net *nn)
{
u32 new_ctrl, update = 0;
unsigned int r;
int err;
- new_ctrl = nn->ctrl;
+ new_ctrl = nn->dp.ctrl;
if (nn->cap & NFP_NET_CFG_CTRL_RSS) {
nfp_net_rss_write_key(nn);
@@ -2184,22 +2167,22 @@ static int __nfp_net_set_config_and_enable(struct nfp_net *nn)
update |= NFP_NET_CFG_UPDATE_IRQMOD;
}
- for (r = 0; r < nn->num_tx_rings; r++)
- nfp_net_tx_ring_hw_cfg_write(nn, &nn->tx_rings[r], r);
- for (r = 0; r < nn->num_rx_rings; r++)
- nfp_net_rx_ring_hw_cfg_write(nn, &nn->rx_rings[r], r);
+ for (r = 0; r < nn->dp.num_tx_rings; r++)
+ nfp_net_tx_ring_hw_cfg_write(nn, &nn->dp.tx_rings[r], r);
+ for (r = 0; r < nn->dp.num_rx_rings; r++)
+ nfp_net_rx_ring_hw_cfg_write(nn, &nn->dp.rx_rings[r], r);
- nn_writeq(nn, NFP_NET_CFG_TXRS_ENABLE, nn->num_tx_rings == 64 ?
- 0xffffffffffffffffULL : ((u64)1 << nn->num_tx_rings) - 1);
+ nn_writeq(nn, NFP_NET_CFG_TXRS_ENABLE, nn->dp.num_tx_rings == 64 ?
+ 0xffffffffffffffffULL : ((u64)1 << nn->dp.num_tx_rings) - 1);
- nn_writeq(nn, NFP_NET_CFG_RXRS_ENABLE, nn->num_rx_rings == 64 ?
- 0xffffffffffffffffULL : ((u64)1 << nn->num_rx_rings) - 1);
+ nn_writeq(nn, NFP_NET_CFG_RXRS_ENABLE, nn->dp.num_rx_rings == 64 ?
+ 0xffffffffffffffffULL : ((u64)1 << nn->dp.num_rx_rings) - 1);
nfp_net_write_mac_addr(nn);
- nn_writel(nn, NFP_NET_CFG_MTU, nn->netdev->mtu);
+ nn_writel(nn, NFP_NET_CFG_MTU, nn->dp.netdev->mtu);
nn_writel(nn, NFP_NET_CFG_FLBUFSZ,
- nn->fl_bufsz - NFP_NET_RX_BUF_NON_DATA);
+ nn->dp.fl_bufsz - NFP_NET_RX_BUF_NON_DATA);
/* Enable device */
new_ctrl |= NFP_NET_CFG_CTRL_ENABLE;
@@ -2211,37 +2194,26 @@ static int __nfp_net_set_config_and_enable(struct nfp_net *nn)
nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl);
err = nfp_net_reconfig(nn, update);
+ if (err) {
+ nfp_net_clear_config_and_disable(nn);
+ return err;
+ }
- nn->ctrl = new_ctrl;
+ nn->dp.ctrl = new_ctrl;
- for (r = 0; r < nn->num_rx_rings; r++)
- nfp_net_rx_ring_fill_freelist(&nn->rx_rings[r]);
+ for (r = 0; r < nn->dp.num_rx_rings; r++)
+ nfp_net_rx_ring_fill_freelist(&nn->dp, &nn->dp.rx_rings[r]);
/* Since reconfiguration requests while NFP is down are ignored we
* have to wipe the entire VXLAN configuration and reinitialize it.
*/
- if (nn->ctrl & NFP_NET_CFG_CTRL_VXLAN) {
+ if (nn->dp.ctrl & NFP_NET_CFG_CTRL_VXLAN) {
memset(&nn->vxlan_ports, 0, sizeof(nn->vxlan_ports));
memset(&nn->vxlan_usecnt, 0, sizeof(nn->vxlan_usecnt));
- udp_tunnel_get_rx_info(nn->netdev);
+ udp_tunnel_get_rx_info(nn->dp.netdev);
}
- return err;
-}
-
-/**
- * nfp_net_set_config_and_enable() - Write control BAR and enable NFP
- * @nn: NFP Net device to reconfigure
- */
-static int nfp_net_set_config_and_enable(struct nfp_net *nn)
-{
- int err;
-
- err = __nfp_net_set_config_and_enable(nn);
- if (err)
- nfp_net_clear_config_and_disable(nn);
-
- return err;
+ return 0;
}
/**
@@ -2252,12 +2224,12 @@ static void nfp_net_open_stack(struct nfp_net *nn)
{
unsigned int r;
- for (r = 0; r < nn->num_r_vecs; r++) {
+ for (r = 0; r < nn->dp.num_r_vecs; r++) {
napi_enable(&nn->r_vecs[r].napi);
enable_irq(nn->r_vecs[r].irq_vector);
}
- netif_tx_wake_all_queues(nn->netdev);
+ netif_tx_wake_all_queues(nn->dp.netdev);
enable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector);
nfp_net_read_link_status(nn);
@@ -2266,22 +2238,8 @@ static void nfp_net_open_stack(struct nfp_net *nn)
static int nfp_net_netdev_open(struct net_device *netdev)
{
struct nfp_net *nn = netdev_priv(netdev);
- struct nfp_net_ring_set rx = {
- .n_rings = nn->num_rx_rings,
- .mtu = nn->netdev->mtu,
- .dcnt = nn->rxd_cnt,
- };
- struct nfp_net_ring_set tx = {
- .n_rings = nn->num_tx_rings,
- .dcnt = nn->txd_cnt,
- };
int err, r;
- if (nn->ctrl & NFP_NET_CFG_CTRL_ENABLE) {
- nn_err(nn, "Dev is already enabled: 0x%08x\n", nn->ctrl);
- return -EBUSY;
- }
-
/* Step 1: Allocate resources for rings and the like
* - Request interrupts
* - Allocate RX and TX ring resources
@@ -2299,33 +2257,28 @@ static int nfp_net_netdev_open(struct net_device *netdev)
goto err_free_exn;
disable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector);
- for (r = 0; r < nn->num_r_vecs; r++) {
+ for (r = 0; r < nn->dp.num_r_vecs; r++) {
err = nfp_net_prepare_vector(nn, &nn->r_vecs[r], r);
if (err)
goto err_cleanup_vec_p;
}
- nn->rx_rings = nfp_net_rx_ring_set_prepare(nn, &rx, nn->xdp_prog);
- if (!nn->rx_rings) {
- err = -ENOMEM;
+ err = nfp_net_rx_rings_prepare(nn, &nn->dp);
+ if (err)
goto err_cleanup_vec;
- }
- nn->tx_rings = nfp_net_tx_ring_set_prepare(nn, &tx,
- nn->num_stack_tx_rings);
- if (!nn->tx_rings) {
- err = -ENOMEM;
+ err = nfp_net_tx_rings_prepare(nn, &nn->dp);
+ if (err)
goto err_free_rx_rings;
- }
for (r = 0; r < nn->max_r_vecs; r++)
- nfp_net_vector_assign_rings(nn, &nn->r_vecs[r], r);
+ nfp_net_vector_assign_rings(&nn->dp, &nn->r_vecs[r], r);
- err = netif_set_real_num_tx_queues(netdev, nn->num_stack_tx_rings);
+ err = netif_set_real_num_tx_queues(netdev, nn->dp.num_stack_tx_rings);
if (err)
goto err_free_rings;
- err = netif_set_real_num_rx_queues(netdev, nn->num_rx_rings);
+ err = netif_set_real_num_rx_queues(netdev, nn->dp.num_rx_rings);
if (err)
goto err_free_rings;
@@ -2351,11 +2304,11 @@ static int nfp_net_netdev_open(struct net_device *netdev)
return 0;
err_free_rings:
- nfp_net_tx_ring_set_free(nn, &tx);
+ nfp_net_tx_rings_free(&nn->dp);
err_free_rx_rings:
- nfp_net_rx_ring_set_free(nn, &rx, nn->xdp_prog);
+ nfp_net_rx_rings_free(&nn->dp);
err_cleanup_vec:
- r = nn->num_r_vecs;
+ r = nn->dp.num_r_vecs;
err_cleanup_vec_p:
while (r--)
nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
@@ -2374,15 +2327,15 @@ static void nfp_net_close_stack(struct nfp_net *nn)
unsigned int r;
disable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector);
- netif_carrier_off(nn->netdev);
+ netif_carrier_off(nn->dp.netdev);
nn->link_up = false;
- for (r = 0; r < nn->num_r_vecs; r++) {
+ for (r = 0; r < nn->dp.num_r_vecs; r++) {
disable_irq(nn->r_vecs[r].irq_vector);
napi_disable(&nn->r_vecs[r].napi);
}
- netif_tx_disable(nn->netdev);
+ netif_tx_disable(nn->dp.netdev);
}
/**
@@ -2393,17 +2346,17 @@ static void nfp_net_close_free_all(struct nfp_net *nn)
{
unsigned int r;
- for (r = 0; r < nn->num_rx_rings; r++) {
- nfp_net_rx_ring_bufs_free(nn, &nn->rx_rings[r], nn->xdp_prog);
- nfp_net_rx_ring_free(&nn->rx_rings[r]);
+ for (r = 0; r < nn->dp.num_rx_rings; r++) {
+ nfp_net_rx_ring_bufs_free(&nn->dp, &nn->dp.rx_rings[r]);
+ nfp_net_rx_ring_free(&nn->dp.rx_rings[r]);
}
- for (r = 0; r < nn->num_tx_rings; r++)
- nfp_net_tx_ring_free(&nn->tx_rings[r]);
- for (r = 0; r < nn->num_r_vecs; r++)
+ for (r = 0; r < nn->dp.num_tx_rings; r++)
+ nfp_net_tx_ring_free(&nn->dp.tx_rings[r]);
+ for (r = 0; r < nn->dp.num_r_vecs; r++)
nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
- kfree(nn->rx_rings);
- kfree(nn->tx_rings);
+ kfree(nn->dp.rx_rings);
+ kfree(nn->dp.tx_rings);
nfp_net_aux_irq_free(nn, NFP_NET_CFG_LSC, NFP_NET_IRQ_LSC_IDX);
nfp_net_aux_irq_free(nn, NFP_NET_CFG_EXN, NFP_NET_IRQ_EXN_IDX);
@@ -2417,11 +2370,6 @@ static int nfp_net_netdev_close(struct net_device *netdev)
{
struct nfp_net *nn = netdev_priv(netdev);
- if (!(nn->ctrl & NFP_NET_CFG_CTRL_ENABLE)) {
- nn_err(nn, "Dev is not up: 0x%08x\n", nn->ctrl);
- return 0;
- }
-
/* Step 1: Disable RX and TX rings from the Linux kernel perspective
*/
nfp_net_close_stack(nn);
@@ -2443,7 +2391,7 @@ static void nfp_net_set_rx_mode(struct net_device *netdev)
struct nfp_net *nn = netdev_priv(netdev);
u32 new_ctrl;
- new_ctrl = nn->ctrl;
+ new_ctrl = nn->dp.ctrl;
if (netdev->flags & IFF_PROMISC) {
if (nn->cap & NFP_NET_CFG_CTRL_PROMISC)
@@ -2454,13 +2402,13 @@ static void nfp_net_set_rx_mode(struct net_device *netdev)
new_ctrl &= ~NFP_NET_CFG_CTRL_PROMISC;
}
- if (new_ctrl == nn->ctrl)
+ if (new_ctrl == nn->dp.ctrl)
return;
nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl);
nfp_net_reconfig_post(nn, NFP_NET_CFG_UPDATE_GEN);
- nn->ctrl = new_ctrl;
+ nn->dp.ctrl = new_ctrl;
}
static void nfp_net_rss_init_itbl(struct nfp_net *nn)
@@ -2469,61 +2417,76 @@ static void nfp_net_rss_init_itbl(struct nfp_net *nn)
for (i = 0; i < sizeof(nn->rss_itbl); i++)
nn->rss_itbl[i] =
- ethtool_rxfh_indir_default(i, nn->num_rx_rings);
+ ethtool_rxfh_indir_default(i, nn->dp.num_rx_rings);
}
-static int
-nfp_net_ring_swap_enable(struct nfp_net *nn, unsigned int *num_vecs,
- unsigned int *stack_tx_rings,
- struct bpf_prog **xdp_prog,
- struct nfp_net_ring_set *rx,
- struct nfp_net_ring_set *tx)
+static void nfp_net_dp_swap(struct nfp_net *nn, struct nfp_net_dp *dp)
+{
+ struct nfp_net_dp new_dp = *dp;
+
+ *dp = nn->dp;
+ nn->dp = new_dp;
+
+ nn->dp.netdev->mtu = new_dp.mtu;
+
+ if (!netif_is_rxfh_configured(nn->dp.netdev))
+ nfp_net_rss_init_itbl(nn);
+}
+
+static int nfp_net_dp_swap_enable(struct nfp_net *nn, struct nfp_net_dp *dp)
{
unsigned int r;
int err;
- if (rx)
- nfp_net_rx_ring_set_swap(nn, rx);
- if (tx)
- nfp_net_tx_ring_set_swap(nn, tx);
-
- swap(*num_vecs, nn->num_r_vecs);
- swap(*stack_tx_rings, nn->num_stack_tx_rings);
- *xdp_prog = xchg(&nn->xdp_prog, *xdp_prog);
+ nfp_net_dp_swap(nn, dp);
for (r = 0; r < nn->max_r_vecs; r++)
- nfp_net_vector_assign_rings(nn, &nn->r_vecs[r], r);
+ nfp_net_vector_assign_rings(&nn->dp, &nn->r_vecs[r], r);
- if (!netif_is_rxfh_configured(nn->netdev))
- nfp_net_rss_init_itbl(nn);
-
- err = netif_set_real_num_rx_queues(nn->netdev,
- nn->num_rx_rings);
+ err = netif_set_real_num_rx_queues(nn->dp.netdev, nn->dp.num_rx_rings);
if (err)
return err;
- if (nn->netdev->real_num_tx_queues != nn->num_stack_tx_rings) {
- err = netif_set_real_num_tx_queues(nn->netdev,
- nn->num_stack_tx_rings);
+ if (nn->dp.netdev->real_num_tx_queues != nn->dp.num_stack_tx_rings) {
+ err = netif_set_real_num_tx_queues(nn->dp.netdev,
+ nn->dp.num_stack_tx_rings);
if (err)
return err;
}
- return __nfp_net_set_config_and_enable(nn);
+ return nfp_net_set_config_and_enable(nn);
}
-static int
-nfp_net_check_config(struct nfp_net *nn, struct bpf_prog *xdp_prog,
- struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx)
+struct nfp_net_dp *nfp_net_clone_dp(struct nfp_net *nn)
+{
+ struct nfp_net_dp *new;
+
+ new = kmalloc(sizeof(*new), GFP_KERNEL);
+ if (!new)
+ return NULL;
+
+ *new = nn->dp;
+
+ /* Clear things which need to be recomputed */
+ new->fl_bufsz = 0;
+ new->tx_rings = NULL;
+ new->rx_rings = NULL;
+ new->num_r_vecs = 0;
+ new->num_stack_tx_rings = 0;
+
+ return new;
+}
+
+static int nfp_net_check_config(struct nfp_net *nn, struct nfp_net_dp *dp)
{
/* XDP-enabled tests */
- if (!xdp_prog)
+ if (!dp->xdp_prog)
return 0;
- if (rx && nfp_net_calc_fl_bufsz(nn, rx->mtu) > PAGE_SIZE) {
+ if (dp->fl_bufsz > PAGE_SIZE) {
nn_warn(nn, "MTU too large w/ XDP enabled\n");
return -EINVAL;
}
- if (tx && tx->n_rings > nn->max_tx_rings) {
+ if (dp->num_tx_rings > nn->max_tx_rings) {
nn_warn(nn, "Insufficient number of TX rings w/ XDP enabled\n");
return -EINVAL;
}
@@ -2531,119 +2494,94 @@ nfp_net_check_config(struct nfp_net *nn, struct bpf_prog *xdp_prog,
return 0;
}
-static void
-nfp_net_ring_reconfig_down(struct nfp_net *nn, struct bpf_prog **xdp_prog,
- struct nfp_net_ring_set *rx,
- struct nfp_net_ring_set *tx,
- unsigned int stack_tx_rings, unsigned int num_vecs)
+int nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *dp)
{
- nn->netdev->mtu = rx ? rx->mtu : nn->netdev->mtu;
- nn->fl_bufsz = nfp_net_calc_fl_bufsz(nn, nn->netdev->mtu);
- nn->rxd_cnt = rx ? rx->dcnt : nn->rxd_cnt;
- nn->txd_cnt = tx ? tx->dcnt : nn->txd_cnt;
- nn->num_rx_rings = rx ? rx->n_rings : nn->num_rx_rings;
- nn->num_tx_rings = tx ? tx->n_rings : nn->num_tx_rings;
- nn->num_stack_tx_rings = stack_tx_rings;
- nn->num_r_vecs = num_vecs;
- *xdp_prog = xchg(&nn->xdp_prog, *xdp_prog);
+ int r, err;
- if (!netif_is_rxfh_configured(nn->netdev))
- nfp_net_rss_init_itbl(nn);
-}
+ dp->fl_bufsz = nfp_net_calc_fl_bufsz(dp);
-int
-nfp_net_ring_reconfig(struct nfp_net *nn, struct bpf_prog **xdp_prog,
- struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx)
-{
- unsigned int stack_tx_rings, num_vecs, r;
- int err;
+ dp->num_stack_tx_rings = dp->num_tx_rings;
+ if (dp->xdp_prog)
+ dp->num_stack_tx_rings -= dp->num_rx_rings;
- stack_tx_rings = tx ? tx->n_rings : nn->num_tx_rings;
- if (*xdp_prog)
- stack_tx_rings -= rx ? rx->n_rings : nn->num_rx_rings;
+ dp->num_r_vecs = max(dp->num_rx_rings, dp->num_stack_tx_rings);
- num_vecs = max(rx ? rx->n_rings : nn->num_rx_rings, stack_tx_rings);
-
- err = nfp_net_check_config(nn, *xdp_prog, rx, tx);
+ err = nfp_net_check_config(nn, dp);
if (err)
- return err;
+ goto exit_free_dp;
- if (!netif_running(nn->netdev)) {
- nfp_net_ring_reconfig_down(nn, xdp_prog, rx, tx,
- stack_tx_rings, num_vecs);
- return 0;
+ if (!netif_running(dp->netdev)) {
+ nfp_net_dp_swap(nn, dp);
+ err = 0;
+ goto exit_free_dp;
}
/* Prepare new rings */
- for (r = nn->num_r_vecs; r < num_vecs; r++) {
+ for (r = nn->dp.num_r_vecs; r < dp->num_r_vecs; r++) {
err = nfp_net_prepare_vector(nn, &nn->r_vecs[r], r);
if (err) {
- num_vecs = r;
+ dp->num_r_vecs = r;
goto err_cleanup_vecs;
}
}
- if (rx) {
- if (!nfp_net_rx_ring_set_prepare(nn, rx, *xdp_prog)) {
- err = -ENOMEM;
- goto err_cleanup_vecs;
- }
- }
- if (tx) {
- if (!nfp_net_tx_ring_set_prepare(nn, tx, stack_tx_rings)) {
- err = -ENOMEM;
- goto err_free_rx;
- }
- }
+
+ err = nfp_net_rx_rings_prepare(nn, dp);
+ if (err)
+ goto err_cleanup_vecs;
+
+ err = nfp_net_tx_rings_prepare(nn, dp);
+ if (err)
+ goto err_free_rx;
/* Stop device, swap in new rings, try to start the firmware */
nfp_net_close_stack(nn);
nfp_net_clear_config_and_disable(nn);
- err = nfp_net_ring_swap_enable(nn, &num_vecs, &stack_tx_rings,
- xdp_prog, rx, tx);
+ err = nfp_net_dp_swap_enable(nn, dp);
if (err) {
int err2;
nfp_net_clear_config_and_disable(nn);
/* Try with old configuration and old rings */
- err2 = nfp_net_ring_swap_enable(nn, &num_vecs, &stack_tx_rings,
- xdp_prog, rx, tx);
+ err2 = nfp_net_dp_swap_enable(nn, dp);
if (err2)
nn_err(nn, "Can't restore ring config - FW communication failed (%d,%d)\n",
err, err2);
}
- for (r = num_vecs - 1; r >= nn->num_r_vecs; r--)
+ for (r = dp->num_r_vecs - 1; r >= nn->dp.num_r_vecs; r--)
nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
- if (rx)
- nfp_net_rx_ring_set_free(nn, rx, *xdp_prog);
- if (tx)
- nfp_net_tx_ring_set_free(nn, tx);
+ nfp_net_rx_rings_free(dp);
+ nfp_net_tx_rings_free(dp);
nfp_net_open_stack(nn);
+exit_free_dp:
+ kfree(dp);
return err;
err_free_rx:
- if (rx)
- nfp_net_rx_ring_set_free(nn, rx, *xdp_prog);
+ nfp_net_rx_rings_free(dp);
err_cleanup_vecs:
- for (r = num_vecs - 1; r >= nn->num_r_vecs; r--)
+ for (r = dp->num_r_vecs - 1; r >= nn->dp.num_r_vecs; r--)
nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
+ kfree(dp);
return err;
}
static int nfp_net_change_mtu(struct net_device *netdev, int new_mtu)
{
struct nfp_net *nn = netdev_priv(netdev);
- struct nfp_net_ring_set rx = {
- .n_rings = nn->num_rx_rings,
- .mtu = new_mtu,
- .dcnt = nn->rxd_cnt,
- };
+ struct nfp_net_dp *dp;
- return nfp_net_ring_reconfig(nn, &nn->xdp_prog, &rx, NULL);
+ dp = nfp_net_clone_dp(nn);
+ if (!dp)
+ return -ENOMEM;
+
+ dp->mtu = new_mtu;
+
+ return nfp_net_ring_reconfig(nn, dp);
}
static void nfp_net_stat64(struct net_device *netdev,
@@ -2652,7 +2590,7 @@ static void nfp_net_stat64(struct net_device *netdev,
struct nfp_net *nn = netdev_priv(netdev);
int r;
- for (r = 0; r < nn->num_r_vecs; r++) {
+ for (r = 0; r < nn->dp.num_r_vecs; r++) {
struct nfp_net_r_vector *r_vec = &nn->r_vecs[r];
u64 data[3];
unsigned int start;
@@ -2699,7 +2637,7 @@ nfp_net_setup_tc(struct net_device *netdev, u32 handle, __be16 proto,
return -ENOTSUPP;
if (tc->type == TC_SETUP_CLSBPF && nfp_net_ebpf_capable(nn)) {
- if (!nn->bpf_offload_xdp)
+ if (!nn->dp.bpf_offload_xdp)
return nfp_net_bpf_offload(nn, tc->cls_bpf);
else
return -EBUSY;
@@ -2718,7 +2656,7 @@ static int nfp_net_set_features(struct net_device *netdev,
/* Assume this is not called with features we have not advertised */
- new_ctrl = nn->ctrl;
+ new_ctrl = nn->dp.ctrl;
if (changed & NETIF_F_RXCSUM) {
if (features & NETIF_F_RXCSUM)
@@ -2762,7 +2700,7 @@ static int nfp_net_set_features(struct net_device *netdev,
new_ctrl &= ~NFP_NET_CFG_CTRL_GATHER;
}
- if (changed & NETIF_F_HW_TC && nn->ctrl & NFP_NET_CFG_CTRL_BPF) {
+ if (changed & NETIF_F_HW_TC && nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF) {
nn_err(nn, "Cannot disable HW TC offload while in use\n");
return -EBUSY;
}
@@ -2770,16 +2708,16 @@ static int nfp_net_set_features(struct net_device *netdev,
nn_dbg(nn, "Feature change 0x%llx -> 0x%llx (changed=0x%llx)\n",
netdev->features, features, changed);
- if (new_ctrl == nn->ctrl)
+ if (new_ctrl == nn->dp.ctrl)
return 0;
- nn_dbg(nn, "NIC ctrl: 0x%x -> 0x%x\n", nn->ctrl, new_ctrl);
+ nn_dbg(nn, "NIC ctrl: 0x%x -> 0x%x\n", nn->dp.ctrl, new_ctrl);
nn_writel(nn, NFP_NET_CFG_CTRL, new_ctrl);
err = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_GEN);
if (err)
return err;
- nn->ctrl = new_ctrl;
+ nn->dp.ctrl = new_ctrl;
return 0;
}
@@ -2830,6 +2768,26 @@ nfp_net_features_check(struct sk_buff *skb, struct net_device *dev,
return features;
}
+static int
+nfp_net_get_phys_port_name(struct net_device *netdev, char *name, size_t len)
+{
+ struct nfp_net *nn = netdev_priv(netdev);
+ int err;
+
+ if (!nn->eth_port)
+ return -EOPNOTSUPP;
+
+ if (!nn->eth_port->is_split)
+ err = snprintf(name, len, "p%d", nn->eth_port->label_port);
+ else
+ err = snprintf(name, len, "p%ds%d", nn->eth_port->label_port,
+ nn->eth_port->label_subport);
+ if (err >= len)
+ return -EINVAL;
+
+ return 0;
+}
+
/**
* nfp_net_set_vxlan_port() - set vxlan port in SW and reconfigure HW
* @nn: NFP Net device to reconfigure
@@ -2842,7 +2800,7 @@ static void nfp_net_set_vxlan_port(struct nfp_net *nn, int idx, __be16 port)
nn->vxlan_ports[idx] = port;
- if (!(nn->ctrl & NFP_NET_CFG_CTRL_VXLAN))
+ if (!(nn->dp.ctrl & NFP_NET_CFG_CTRL_VXLAN))
return;
BUILD_BUG_ON(NFP_NET_N_VXLAN_PORTS & 1);
@@ -2921,8 +2879,8 @@ static int nfp_net_xdp_offload(struct nfp_net *nn, struct bpf_prog *prog)
if (!nfp_net_ebpf_capable(nn))
return -EINVAL;
- if (nn->ctrl & NFP_NET_CFG_CTRL_BPF) {
- if (!nn->bpf_offload_xdp)
+ if (nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF) {
+ if (!nn->dp.bpf_offload_xdp)
return prog ? -EBUSY : 0;
cmd.command = prog ? TC_CLSBPF_REPLACE : TC_CLSBPF_DESTROY;
} else {
@@ -2935,48 +2893,47 @@ static int nfp_net_xdp_offload(struct nfp_net *nn, struct bpf_prog *prog)
/* Stop offload if replace not possible */
if (ret && cmd.command == TC_CLSBPF_REPLACE)
nfp_net_xdp_offload(nn, NULL);
- nn->bpf_offload_xdp = prog && !ret;
+ nn->dp.bpf_offload_xdp = prog && !ret;
return ret;
}
static int nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog)
{
- struct nfp_net_ring_set rx = {
- .n_rings = nn->num_rx_rings,
- .mtu = nn->netdev->mtu,
- .dcnt = nn->rxd_cnt,
- };
- struct nfp_net_ring_set tx = {
- .n_rings = nn->num_tx_rings,
- .dcnt = nn->txd_cnt,
- };
+ struct bpf_prog *old_prog = nn->dp.xdp_prog;
+ struct nfp_net_dp *dp;
int err;
- if (prog && prog->xdp_adjust_head) {
- nn_err(nn, "Does not support bpf_xdp_adjust_head()\n");
- return -EOPNOTSUPP;
- }
- if (!prog && !nn->xdp_prog)
+ if (!prog && !nn->dp.xdp_prog)
return 0;
- if (prog && nn->xdp_prog) {
- prog = xchg(&nn->xdp_prog, prog);
+ if (prog && nn->dp.xdp_prog) {
+ prog = xchg(&nn->dp.xdp_prog, prog);
bpf_prog_put(prog);
- nfp_net_xdp_offload(nn, nn->xdp_prog);
+ nfp_net_xdp_offload(nn, nn->dp.xdp_prog);
return 0;
}
- tx.n_rings += prog ? nn->num_rx_rings : -nn->num_rx_rings;
+ dp = nfp_net_clone_dp(nn);
+ if (!dp)
+ return -ENOMEM;
+
+ dp->xdp_prog = prog;
+ dp->num_tx_rings += prog ? nn->dp.num_rx_rings : -nn->dp.num_rx_rings;
+ dp->rx_dma_dir = prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
+ if (prog)
+ dp->rx_dma_off = XDP_PACKET_HEADROOM -
+ (nn->dp.rx_offset ?: NFP_NET_MAX_PREPEND);
+ else
+ dp->rx_dma_off = 0;
/* We need RX reconfig to remap the buffers (BIDIR vs FROM_DEV) */
- err = nfp_net_ring_reconfig(nn, &prog, &rx, &tx);
+ err = nfp_net_ring_reconfig(nn, dp);
if (err)
return err;
- /* @prog got swapped and is now the old one */
- if (prog)
- bpf_prog_put(prog);
+ if (old_prog)
+ bpf_prog_put(old_prog);
- nfp_net_xdp_offload(nn, nn->xdp_prog);
+ nfp_net_xdp_offload(nn, nn->dp.xdp_prog);
return 0;
}
@@ -2989,7 +2946,7 @@ static int nfp_net_xdp(struct net_device *netdev, struct netdev_xdp *xdp)
case XDP_SETUP_PROG:
return nfp_net_xdp_setup(nn, xdp->prog);
case XDP_QUERY_PROG:
- xdp->prog_attached = !!nn->xdp_prog;
+ xdp->prog_attached = !!nn->dp.xdp_prog;
return 0;
default:
return -EINVAL;
@@ -3008,6 +2965,7 @@ static const struct net_device_ops nfp_net_netdev_ops = {
.ndo_set_mac_address = eth_mac_addr,
.ndo_set_features = nfp_net_set_features,
.ndo_features_check = nfp_net_features_check,
+ .ndo_get_phys_port_name = nfp_net_get_phys_port_name,
.ndo_udp_tunnel_add = nfp_net_add_vxlan_port,
.ndo_udp_tunnel_del = nfp_net_del_vxlan_port,
.ndo_xdp = nfp_net_xdp,
@@ -3020,9 +2978,9 @@ static const struct net_device_ops nfp_net_netdev_ops = {
void nfp_net_info(struct nfp_net *nn)
{
nn_info(nn, "Netronome NFP-6xxx %sNetdev: TxQs=%d/%d RxQs=%d/%d\n",
- nn->is_vf ? "VF " : "",
- nn->num_tx_rings, nn->max_tx_rings,
- nn->num_rx_rings, nn->max_rx_rings);
+ nn->dp.is_vf ? "VF " : "",
+ nn->dp.num_tx_rings, nn->max_tx_rings,
+ nn->dp.num_rx_rings, nn->max_rx_rings);
nn_info(nn, "VER: %d.%d.%d.%d, Maximum supported MTU: %d\n",
nn->fw_ver.resv, nn->fw_ver.class,
nn->fw_ver.major, nn->fw_ver.minor,
@@ -3074,21 +3032,24 @@ struct nfp_net *nfp_net_netdev_alloc(struct pci_dev *pdev,
SET_NETDEV_DEV(netdev, &pdev->dev);
nn = netdev_priv(netdev);
- nn->netdev = netdev;
+ nn->dp.netdev = netdev;
+ nn->dp.dev = &pdev->dev;
nn->pdev = pdev;
nn->max_tx_rings = max_tx_rings;
nn->max_rx_rings = max_rx_rings;
- nn->num_tx_rings = min_t(unsigned int, max_tx_rings, num_online_cpus());
- nn->num_rx_rings = min_t(unsigned int, max_rx_rings,
+ nn->dp.num_tx_rings = min_t(unsigned int,
+ max_tx_rings, num_online_cpus());
+ nn->dp.num_rx_rings = min_t(unsigned int, max_rx_rings,
netif_get_num_default_rss_queues());
- nn->num_r_vecs = max(nn->num_tx_rings, nn->num_rx_rings);
- nn->num_r_vecs = min_t(unsigned int, nn->num_r_vecs, num_online_cpus());
+ nn->dp.num_r_vecs = max(nn->dp.num_tx_rings, nn->dp.num_rx_rings);
+ nn->dp.num_r_vecs = min_t(unsigned int,
+ nn->dp.num_r_vecs, num_online_cpus());
- nn->txd_cnt = NFP_NET_TX_DESCS_DEFAULT;
- nn->rxd_cnt = NFP_NET_RX_DESCS_DEFAULT;
+ nn->dp.txd_cnt = NFP_NET_TX_DESCS_DEFAULT;
+ nn->dp.rxd_cnt = NFP_NET_RX_DESCS_DEFAULT;
spin_lock_init(&nn->reconfig_lock);
spin_lock_init(&nn->rx_filter_lock);
@@ -3108,7 +3069,28 @@ struct nfp_net *nfp_net_netdev_alloc(struct pci_dev *pdev,
*/
void nfp_net_netdev_free(struct nfp_net *nn)
{
- free_netdev(nn->netdev);
+ free_netdev(nn->dp.netdev);
+}
+
+/**
+ * nfp_net_rss_key_sz() - Get current size of the RSS key
+ * @nn: NFP Net device instance
+ *
+ * Return: size of the RSS key for currently selected hash function.
+ */
+unsigned int nfp_net_rss_key_sz(struct nfp_net *nn)
+{
+ switch (nn->rss_hfunc) {
+ case ETH_RSS_HASH_TOP:
+ return NFP_NET_CFG_RSS_KEY_SZ;
+ case ETH_RSS_HASH_XOR:
+ return 0;
+ case ETH_RSS_HASH_CRC32:
+ return 4;
+ }
+
+ nn_warn(nn, "Unknown hash function: %u\n", nn->rss_hfunc);
+ return 0;
}
/**
@@ -3117,14 +3099,32 @@ void nfp_net_netdev_free(struct nfp_net *nn)
*/
static void nfp_net_rss_init(struct nfp_net *nn)
{
- netdev_rss_key_fill(nn->rss_key, NFP_NET_CFG_RSS_KEY_SZ);
+ unsigned long func_bit, rss_cap_hfunc;
+ u32 reg;
+
+ /* Read the RSS function capability and select first supported func */
+ reg = nn_readl(nn, NFP_NET_CFG_RSS_CAP);
+ rss_cap_hfunc = FIELD_GET(NFP_NET_CFG_RSS_CAP_HFUNC, reg);
+ if (!rss_cap_hfunc)
+ rss_cap_hfunc = FIELD_GET(NFP_NET_CFG_RSS_CAP_HFUNC,
+ NFP_NET_CFG_RSS_TOEPLITZ);
+
+ func_bit = find_first_bit(&rss_cap_hfunc, NFP_NET_CFG_RSS_HFUNCS);
+ if (func_bit == NFP_NET_CFG_RSS_HFUNCS) {
+ dev_warn(nn->dp.dev,
+ "Bad RSS config, defaulting to Toeplitz hash\n");
+ func_bit = ETH_RSS_HASH_TOP_BIT;
+ }
+ nn->rss_hfunc = 1 << func_bit;
+
+ netdev_rss_key_fill(nn->rss_key, nfp_net_rss_key_sz(nn));
nfp_net_rss_init_itbl(nn);
/* Enable IPv4/IPv6 TCP by default */
nn->rss_cfg = NFP_NET_CFG_RSS_IPV4_TCP |
NFP_NET_CFG_RSS_IPV6_TCP |
- NFP_NET_CFG_RSS_TOEPLITZ |
+ FIELD_PREP(NFP_NET_CFG_RSS_HFUNC, nn->rss_hfunc) |
NFP_NET_CFG_RSS_MASK;
}
@@ -3151,6 +3151,17 @@ int nfp_net_netdev_init(struct net_device *netdev)
struct nfp_net *nn = netdev_priv(netdev);
int err;
+ /* XDP calls for 256 byte packet headroom which wouldn't fit in a u8.
+ * We, however, reuse the metadata prepend space for XDP buffers which
+ * is at least 1 byte long and as long as XDP headroom doesn't increase
+ * above 256 the *extra* XDP headroom will fit on 8 bits.
+ */
+ BUILD_BUG_ON(XDP_PACKET_HEADROOM > 256);
+
+ nn->dp.chained_metadata_format = nn->fw_ver.major > 3;
+
+ nn->dp.rx_dma_dir = DMA_FROM_DEVICE;
+
/* Get some of the read-only fields from the BAR */
nn->cap = nn_readl(nn, NFP_NET_CFG_CAP);
nn->max_mtu = nn_readl(nn, NFP_NET_CFG_MAX_MTU);
@@ -3158,17 +3169,26 @@ int nfp_net_netdev_init(struct net_device *netdev)
nfp_net_write_mac_addr(nn);
/* Determine RX packet/metadata boundary offset */
- if (nn->fw_ver.major >= 2)
- nn->rx_offset = nn_readl(nn, NFP_NET_CFG_RX_OFFSET);
- else
- nn->rx_offset = NFP_NET_RX_OFFSET;
+ if (nn->fw_ver.major >= 2) {
+ u32 reg;
+
+ reg = nn_readl(nn, NFP_NET_CFG_RX_OFFSET);
+ if (reg > NFP_NET_MAX_PREPEND) {
+ nn_err(nn, "Invalid rx offset: %d\n", reg);
+ return -EINVAL;
+ }
+ nn->dp.rx_offset = reg;
+ } else {
+ nn->dp.rx_offset = NFP_NET_RX_OFFSET;
+ }
/* Set default MTU and Freelist buffer size */
if (nn->max_mtu < NFP_NET_DEFAULT_MTU)
netdev->mtu = nn->max_mtu;
else
netdev->mtu = NFP_NET_DEFAULT_MTU;
- nn->fl_bufsz = nfp_net_calc_fl_bufsz(nn, netdev->mtu);
+ nn->dp.mtu = netdev->mtu;
+ nn->dp.fl_bufsz = nfp_net_calc_fl_bufsz(&nn->dp);
/* Advertise/enable offloads based on capabilities
*
@@ -3179,31 +3199,31 @@ int nfp_net_netdev_init(struct net_device *netdev)
netdev->hw_features = NETIF_F_HIGHDMA;
if (nn->cap & NFP_NET_CFG_CTRL_RXCSUM) {
netdev->hw_features |= NETIF_F_RXCSUM;
- nn->ctrl |= NFP_NET_CFG_CTRL_RXCSUM;
+ nn->dp.ctrl |= NFP_NET_CFG_CTRL_RXCSUM;
}
if (nn->cap & NFP_NET_CFG_CTRL_TXCSUM) {
netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
- nn->ctrl |= NFP_NET_CFG_CTRL_TXCSUM;
+ nn->dp.ctrl |= NFP_NET_CFG_CTRL_TXCSUM;
}
if (nn->cap & NFP_NET_CFG_CTRL_GATHER) {
netdev->hw_features |= NETIF_F_SG;
- nn->ctrl |= NFP_NET_CFG_CTRL_GATHER;
+ nn->dp.ctrl |= NFP_NET_CFG_CTRL_GATHER;
}
if ((nn->cap & NFP_NET_CFG_CTRL_LSO) && nn->fw_ver.major > 2) {
netdev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6;
- nn->ctrl |= NFP_NET_CFG_CTRL_LSO;
+ nn->dp.ctrl |= NFP_NET_CFG_CTRL_LSO;
}
if (nn->cap & NFP_NET_CFG_CTRL_RSS) {
netdev->hw_features |= NETIF_F_RXHASH;
nfp_net_rss_init(nn);
- nn->ctrl |= NFP_NET_CFG_CTRL_RSS;
+ nn->dp.ctrl |= NFP_NET_CFG_CTRL_RSS;
}
if (nn->cap & NFP_NET_CFG_CTRL_VXLAN &&
nn->cap & NFP_NET_CFG_CTRL_NVGRE) {
if (nn->cap & NFP_NET_CFG_CTRL_LSO)
netdev->hw_features |= NETIF_F_GSO_GRE |
NETIF_F_GSO_UDP_TUNNEL;
- nn->ctrl |= NFP_NET_CFG_CTRL_VXLAN | NFP_NET_CFG_CTRL_NVGRE;
+ nn->dp.ctrl |= NFP_NET_CFG_CTRL_VXLAN | NFP_NET_CFG_CTRL_NVGRE;
netdev->hw_enc_features = netdev->hw_features;
}
@@ -3212,11 +3232,11 @@ int nfp_net_netdev_init(struct net_device *netdev)
if (nn->cap & NFP_NET_CFG_CTRL_RXVLAN) {
netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX;
- nn->ctrl |= NFP_NET_CFG_CTRL_RXVLAN;
+ nn->dp.ctrl |= NFP_NET_CFG_CTRL_RXVLAN;
}
if (nn->cap & NFP_NET_CFG_CTRL_TXVLAN) {
netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX;
- nn->ctrl |= NFP_NET_CFG_CTRL_TXVLAN;
+ nn->dp.ctrl |= NFP_NET_CFG_CTRL_TXVLAN;
}
netdev->features = netdev->hw_features;
@@ -3229,14 +3249,14 @@ int nfp_net_netdev_init(struct net_device *netdev)
/* Allow L2 Broadcast and Multicast through by default, if supported */
if (nn->cap & NFP_NET_CFG_CTRL_L2BC)
- nn->ctrl |= NFP_NET_CFG_CTRL_L2BC;
+ nn->dp.ctrl |= NFP_NET_CFG_CTRL_L2BC;
if (nn->cap & NFP_NET_CFG_CTRL_L2MC)
- nn->ctrl |= NFP_NET_CFG_CTRL_L2MC;
+ nn->dp.ctrl |= NFP_NET_CFG_CTRL_L2MC;
/* Allow IRQ moderation, if supported */
if (nn->cap & NFP_NET_CFG_CTRL_IRQMOD) {
nfp_net_irqmod_init(nn);
- nn->ctrl |= NFP_NET_CFG_CTRL_IRQMOD;
+ nn->dp.ctrl |= NFP_NET_CFG_CTRL_IRQMOD;
}
/* Stash the re-configuration queue away. First odd queue in TX Bar */
@@ -3275,9 +3295,10 @@ void nfp_net_netdev_clean(struct net_device *netdev)
{
struct nfp_net *nn = netdev_priv(netdev);
- if (nn->xdp_prog)
- bpf_prog_put(nn->xdp_prog);
- if (nn->bpf_offload_xdp)
+ unregister_netdev(nn->dp.netdev);
+
+ if (nn->dp.xdp_prog)
+ bpf_prog_put(nn->dp.xdp_prog);
+ if (nn->dp.bpf_offload_xdp)
nfp_net_xdp_offload(nn, NULL);
- unregister_netdev(nn->netdev);
}
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
index 385ba35..d04ccc9 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
@@ -1,5 +1,5 @@
/*
- * Copyright (C) 2015 Netronome Systems, Inc.
+ * Copyright (C) 2015-2017 Netronome Systems, Inc.
*
* This software is dual licensed under the GNU General License Version 2,
* June 1991 as shown in the file COPYING in the top-level directory of this
@@ -177,6 +177,19 @@
#define NFP_NET_CFG_VERSION_MINOR(x) (((x) & 0xff) << 0)
#define NFP_NET_CFG_STS 0x0034
#define NFP_NET_CFG_STS_LINK (0x1 << 0) /* Link up or down */
+/* Link rate */
+#define NFP_NET_CFG_STS_LINK_RATE_SHIFT 1
+#define NFP_NET_CFG_STS_LINK_RATE_MASK 0xF
+#define NFP_NET_CFG_STS_LINK_RATE \
+ (NFP_NET_CFG_STS_LINK_RATE_MASK << NFP_NET_CFG_STS_LINK_RATE_SHIFT)
+#define NFP_NET_CFG_STS_LINK_RATE_UNSUPPORTED 0
+#define NFP_NET_CFG_STS_LINK_RATE_UNKNOWN 1
+#define NFP_NET_CFG_STS_LINK_RATE_1G 2
+#define NFP_NET_CFG_STS_LINK_RATE_10G 3
+#define NFP_NET_CFG_STS_LINK_RATE_25G 4
+#define NFP_NET_CFG_STS_LINK_RATE_40G 5
+#define NFP_NET_CFG_STS_LINK_RATE_50G 6
+#define NFP_NET_CFG_STS_LINK_RATE_100G 7
#define NFP_NET_CFG_CAP 0x0038
#define NFP_NET_CFG_MAX_TXRINGS 0x003c
#define NFP_NET_CFG_MAX_RXRINGS 0x0040
@@ -192,6 +205,14 @@
#define NFP_NET_CFG_RX_OFFSET_DYNAMIC 0 /* Prepend mode */
/**
+ * RSS capabilities
+ * @NFP_NET_CFG_RSS_CAP_HFUNC: supported hash functions (same bits as
+ * @NFP_NET_CFG_RSS_HFUNC)
+ */
+#define NFP_NET_CFG_RSS_CAP 0x0054
+#define NFP_NET_CFG_RSS_CAP_HFUNC 0xff000000
+
+/**
* VXLAN/UDP encap configuration
* @NFP_NET_CFG_VXLAN_PORT: Base address of table of tunnels' UDP dst ports
* @NFP_NET_CFG_VXLAN_SZ: Size of the UDP port table in bytes
@@ -249,7 +270,11 @@
#define NFP_NET_CFG_RSS_IPV4_UDP (1 << 11) /* RSS for IPv4/UDP */
#define NFP_NET_CFG_RSS_IPV6_TCP (1 << 12) /* RSS for IPv6/TCP */
#define NFP_NET_CFG_RSS_IPV6_UDP (1 << 13) /* RSS for IPv6/UDP */
+#define NFP_NET_CFG_RSS_HFUNC 0xff000000
#define NFP_NET_CFG_RSS_TOEPLITZ (1 << 24) /* Use Toeplitz hash */
+#define NFP_NET_CFG_RSS_XOR (1 << 25) /* Use XOR as hash */
+#define NFP_NET_CFG_RSS_CRC32 (1 << 26) /* Use CRC32 as hash */
+#define NFP_NET_CFG_RSS_HFUNCS 3
#define NFP_NET_CFG_RSS_KEY (NFP_NET_CFG_RSS_BASE + 0x4)
#define NFP_NET_CFG_RSS_KEY_SZ 0x28
#define NFP_NET_CFG_RSS_ITBL (NFP_NET_CFG_RSS_BASE + 0x4 + \
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c
index 6e9372a..4077c59 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c
@@ -40,9 +40,9 @@ static struct dentry *nfp_dir;
static int nfp_net_debugfs_rx_q_read(struct seq_file *file, void *data)
{
- int fl_rd_p, fl_wr_p, rx_rd_p, rx_wr_p, rxd_cnt;
struct nfp_net_r_vector *r_vec = file->private;
struct nfp_net_rx_ring *rx_ring;
+ int fl_rd_p, fl_wr_p, rxd_cnt;
struct nfp_net_rx_desc *rxd;
struct nfp_net *nn;
void *frag;
@@ -54,19 +54,18 @@ static int nfp_net_debugfs_rx_q_read(struct seq_file *file, void *data)
goto out;
nn = r_vec->nfp_net;
rx_ring = r_vec->rx_ring;
- if (!netif_running(nn->netdev))
+ if (!netif_running(nn->dp.netdev))
goto out;
rxd_cnt = rx_ring->cnt;
fl_rd_p = nfp_qcp_rd_ptr_read(rx_ring->qcp_fl);
fl_wr_p = nfp_qcp_wr_ptr_read(rx_ring->qcp_fl);
- rx_rd_p = nfp_qcp_rd_ptr_read(rx_ring->qcp_rx);
- rx_wr_p = nfp_qcp_wr_ptr_read(rx_ring->qcp_rx);
- seq_printf(file, "RX[%02d]: H_RD=%d H_WR=%d FL_RD=%d FL_WR=%d RX_RD=%d RX_WR=%d\n",
- rx_ring->idx, rx_ring->rd_p, rx_ring->wr_p,
- fl_rd_p, fl_wr_p, rx_rd_p, rx_wr_p);
+ seq_printf(file, "RX[%02d,%02d]: cnt=%d dma=%pad host=%p H_RD=%d H_WR=%d FL_RD=%d FL_WR=%d\n",
+ rx_ring->idx, rx_ring->fl_qcidx,
+ rx_ring->cnt, &rx_ring->dma, rx_ring->rxds,
+ rx_ring->rd_p, rx_ring->wr_p, fl_rd_p, fl_wr_p);
for (i = 0; i < rxd_cnt; i++) {
rxd = &rx_ring->rxds[i];
@@ -89,10 +88,6 @@ static int nfp_net_debugfs_rx_q_read(struct seq_file *file, void *data)
seq_puts(file, " FL_RD");
if (i == fl_wr_p % rxd_cnt)
seq_puts(file, " FL_WR");
- if (i == rx_rd_p % rxd_cnt)
- seq_puts(file, " RX_RD");
- if (i == rx_wr_p % rxd_cnt)
- seq_puts(file, " RX_WR");
seq_putc(file, '\n');
}
@@ -143,7 +138,7 @@ static int nfp_net_debugfs_tx_q_read(struct seq_file *file, void *data)
if (!r_vec->nfp_net || !tx_ring)
goto out;
nn = r_vec->nfp_net;
- if (!netif_running(nn->netdev))
+ if (!netif_running(nn->dp.netdev))
goto out;
txd_cnt = tx_ring->cnt;
@@ -151,8 +146,11 @@ static int nfp_net_debugfs_tx_q_read(struct seq_file *file, void *data)
d_rd_p = nfp_qcp_rd_ptr_read(tx_ring->qcp_q);
d_wr_p = nfp_qcp_wr_ptr_read(tx_ring->qcp_q);
- seq_printf(file, "TX[%02d]: H_RD=%d H_WR=%d D_RD=%d D_WR=%d\n",
- tx_ring->idx, tx_ring->rd_p, tx_ring->wr_p, d_rd_p, d_wr_p);
+ seq_printf(file, "TX[%02d,%02d%s]: cnt=%d dma=%pad host=%p H_RD=%d H_WR=%d D_RD=%d D_WR=%d\n",
+ tx_ring->idx, tx_ring->qcidx,
+ tx_ring == r_vec->tx_ring ? "" : "xdp",
+ tx_ring->cnt, &tx_ring->dma, tx_ring->txds,
+ tx_ring->rd_p, tx_ring->wr_p, d_rd_p, d_wr_p);
for (i = 0; i < txd_cnt; i++) {
txd = &tx_ring->txds[i];
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index 2649f75..3328041 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -40,6 +40,7 @@
* Brad Petrus <brad.petrus@netronome.com>
*/
+#include <linux/bitfield.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
@@ -48,6 +49,7 @@
#include <linux/ethtool.h>
#include "nfpcore/nfp.h"
+#include "nfpcore/nfp_nsp.h"
#include "nfp_net_ctrl.h"
#include "nfp_net.h"
@@ -126,9 +128,9 @@ static const struct _nfp_net_et_stats nfp_net_et_stats[] = {
};
#define NN_ET_GLOBAL_STATS_LEN ARRAY_SIZE(nfp_net_et_stats)
-#define NN_ET_RVEC_STATS_LEN (nn->num_r_vecs * 3)
+#define NN_ET_RVEC_STATS_LEN (nn->dp.num_r_vecs * 3)
#define NN_ET_RVEC_GATHER_STATS 7
-#define NN_ET_QUEUE_STATS_LEN ((nn->num_tx_rings + nn->num_rx_rings) * 2)
+#define NN_ET_QUEUE_STATS_LEN ((nn->dp.num_tx_rings + nn->dp.num_rx_rings) * 2)
#define NN_ET_STATS_LEN (NN_ET_GLOBAL_STATS_LEN + NN_ET_RVEC_GATHER_STATS + \
NN_ET_RVEC_STATS_LEN + NN_ET_QUEUE_STATS_LEN)
@@ -172,6 +174,114 @@ static void nfp_net_get_drvinfo(struct net_device *netdev,
drvinfo->regdump_len = NFP_NET_CFG_BAR_SZ;
}
+/**
+ * nfp_net_get_link_ksettings - Get Link Speed settings
+ * @netdev: network interface device structure
+ * @cmd: ethtool command
+ *
+ * Reports speed settings based on info in the BAR provided by the fw.
+ */
+static int
+nfp_net_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *cmd)
+{
+ static const u32 ls_to_ethtool[] = {
+ [NFP_NET_CFG_STS_LINK_RATE_UNSUPPORTED] = 0,
+ [NFP_NET_CFG_STS_LINK_RATE_UNKNOWN] = SPEED_UNKNOWN,
+ [NFP_NET_CFG_STS_LINK_RATE_1G] = SPEED_1000,
+ [NFP_NET_CFG_STS_LINK_RATE_10G] = SPEED_10000,
+ [NFP_NET_CFG_STS_LINK_RATE_25G] = SPEED_25000,
+ [NFP_NET_CFG_STS_LINK_RATE_40G] = SPEED_40000,
+ [NFP_NET_CFG_STS_LINK_RATE_50G] = SPEED_50000,
+ [NFP_NET_CFG_STS_LINK_RATE_100G] = SPEED_100000,
+ };
+ struct nfp_net *nn = netdev_priv(netdev);
+ u32 sts, ls;
+
+ ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
+ cmd->base.port = PORT_OTHER;
+ cmd->base.speed = SPEED_UNKNOWN;
+ cmd->base.duplex = DUPLEX_UNKNOWN;
+
+ if (nn->eth_port)
+ cmd->base.autoneg = nn->eth_port->aneg != NFP_ANEG_DISABLED ?
+ AUTONEG_ENABLE : AUTONEG_DISABLE;
+
+ if (!netif_carrier_ok(netdev))
+ return 0;
+
+ /* Use link speed from ETH table if available, otherwise try the BAR */
+ if (nn->eth_port && nfp_net_link_changed_read_clear(nn))
+ nfp_net_refresh_port_config(nn);
+ /* Separate if - on FW error the port could've disappeared from table */
+ if (nn->eth_port) {
+ cmd->base.port = nn->eth_port->port_type;
+ cmd->base.speed = nn->eth_port->speed;
+ cmd->base.duplex = DUPLEX_FULL;
+ return 0;
+ }
+
+ sts = nn_readl(nn, NFP_NET_CFG_STS);
+
+ ls = FIELD_GET(NFP_NET_CFG_STS_LINK_RATE, sts);
+ if (ls == NFP_NET_CFG_STS_LINK_RATE_UNSUPPORTED)
+ return -EOPNOTSUPP;
+
+ if (ls == NFP_NET_CFG_STS_LINK_RATE_UNKNOWN ||
+ ls >= ARRAY_SIZE(ls_to_ethtool))
+ return 0;
+
+ cmd->base.speed = ls_to_ethtool[sts];
+ cmd->base.duplex = DUPLEX_FULL;
+
+ return 0;
+}
+
+static int
+nfp_net_set_link_ksettings(struct net_device *netdev,
+ const struct ethtool_link_ksettings *cmd)
+{
+ struct nfp_net *nn = netdev_priv(netdev);
+ struct nfp_nsp *nsp;
+ int err;
+
+ if (!nn->eth_port)
+ return -EOPNOTSUPP;
+
+ if (netif_running(netdev)) {
+ nn_warn(nn, "Changing settings not allowed on an active interface. It may cause the port to be disabled until reboot.\n");
+ return -EBUSY;
+ }
+
+ nsp = nfp_eth_config_start(nn->cpp, nn->eth_port->index);
+ if (IS_ERR(nsp))
+ return PTR_ERR(nsp);
+
+ err = __nfp_eth_set_aneg(nsp, cmd->base.autoneg == AUTONEG_ENABLE ?
+ NFP_ANEG_AUTO : NFP_ANEG_DISABLED);
+ if (err)
+ goto err_bad_set;
+ if (cmd->base.speed != SPEED_UNKNOWN) {
+ u32 speed = cmd->base.speed / nn->eth_port->lanes;
+
+ err = __nfp_eth_set_speed(nsp, speed);
+ if (err)
+ goto err_bad_set;
+ }
+
+ err = nfp_eth_config_commit_end(nsp);
+ if (err > 0)
+ return 0; /* no change */
+
+ nfp_net_refresh_port_config(nn);
+
+ return err;
+
+err_bad_set:
+ nfp_eth_config_cleanup_end(nsp);
+ return err;
+}
+
static void nfp_net_get_ringparam(struct net_device *netdev,
struct ethtool_ringparam *ring)
{
@@ -179,30 +289,22 @@ static void nfp_net_get_ringparam(struct net_device *netdev,
ring->rx_max_pending = NFP_NET_MAX_RX_DESCS;
ring->tx_max_pending = NFP_NET_MAX_TX_DESCS;
- ring->rx_pending = nn->rxd_cnt;
- ring->tx_pending = nn->txd_cnt;
+ ring->rx_pending = nn->dp.rxd_cnt;
+ ring->tx_pending = nn->dp.txd_cnt;
}
static int nfp_net_set_ring_size(struct nfp_net *nn, u32 rxd_cnt, u32 txd_cnt)
{
- struct nfp_net_ring_set *reconfig_rx = NULL, *reconfig_tx = NULL;
- struct nfp_net_ring_set rx = {
- .n_rings = nn->num_rx_rings,
- .mtu = nn->netdev->mtu,
- .dcnt = rxd_cnt,
- };
- struct nfp_net_ring_set tx = {
- .n_rings = nn->num_tx_rings,
- .dcnt = txd_cnt,
- };
+ struct nfp_net_dp *dp;
- if (nn->rxd_cnt != rxd_cnt)
- reconfig_rx = ℞
- if (nn->txd_cnt != txd_cnt)
- reconfig_tx = &tx;
+ dp = nfp_net_clone_dp(nn);
+ if (!dp)
+ return -ENOMEM;
- return nfp_net_ring_reconfig(nn, &nn->xdp_prog,
- reconfig_rx, reconfig_tx);
+ dp->rxd_cnt = rxd_cnt;
+ dp->txd_cnt = txd_cnt;
+
+ return nfp_net_ring_reconfig(nn, dp);
}
static int nfp_net_set_ringparam(struct net_device *netdev,
@@ -223,11 +325,11 @@ static int nfp_net_set_ringparam(struct net_device *netdev,
txd_cnt < NFP_NET_MIN_TX_DESCS || txd_cnt > NFP_NET_MAX_TX_DESCS)
return -EINVAL;
- if (nn->rxd_cnt == rxd_cnt && nn->txd_cnt == txd_cnt)
+ if (nn->dp.rxd_cnt == rxd_cnt && nn->dp.txd_cnt == txd_cnt)
return 0;
nn_dbg(nn, "Change ring size: RxQ %u->%u, TxQ %u->%u\n",
- nn->rxd_cnt, rxd_cnt, nn->txd_cnt, txd_cnt);
+ nn->dp.rxd_cnt, rxd_cnt, nn->dp.txd_cnt, txd_cnt);
return nfp_net_set_ring_size(nn, rxd_cnt, txd_cnt);
}
@@ -245,7 +347,7 @@ static void nfp_net_get_strings(struct net_device *netdev,
memcpy(p, nfp_net_et_stats[i].name, ETH_GSTRING_LEN);
p += ETH_GSTRING_LEN;
}
- for (i = 0; i < nn->num_r_vecs; i++) {
+ for (i = 0; i < nn->dp.num_r_vecs; i++) {
sprintf(p, "rvec_%u_rx_pkts", i);
p += ETH_GSTRING_LEN;
sprintf(p, "rvec_%u_tx_pkts", i);
@@ -267,13 +369,13 @@ static void nfp_net_get_strings(struct net_device *netdev,
p += ETH_GSTRING_LEN;
strncpy(p, "tx_lso", ETH_GSTRING_LEN);
p += ETH_GSTRING_LEN;
- for (i = 0; i < nn->num_tx_rings; i++) {
+ for (i = 0; i < nn->dp.num_tx_rings; i++) {
sprintf(p, "txq_%u_pkts", i);
p += ETH_GSTRING_LEN;
sprintf(p, "txq_%u_bytes", i);
p += ETH_GSTRING_LEN;
}
- for (i = 0; i < nn->num_rx_rings; i++) {
+ for (i = 0; i < nn->dp.num_rx_rings; i++) {
sprintf(p, "rxq_%u_pkts", i);
p += ETH_GSTRING_LEN;
sprintf(p, "rxq_%u_bytes", i);
@@ -306,12 +408,12 @@ static void nfp_net_get_stats(struct net_device *netdev,
break;
case NFP_NET_DEV_ET_STATS:
- io_p = nn->ctrl_bar + nfp_net_et_stats[i].off;
+ io_p = nn->dp.ctrl_bar + nfp_net_et_stats[i].off;
data[i] = readq(io_p);
break;
}
}
- for (j = 0; j < nn->num_r_vecs; j++) {
+ for (j = 0; j < nn->dp.num_r_vecs; j++) {
unsigned int start;
do {
@@ -337,16 +439,16 @@ static void nfp_net_get_stats(struct net_device *netdev,
}
for (j = 0; j < NN_ET_RVEC_GATHER_STATS; j++)
data[i++] = gathered_stats[j];
- for (j = 0; j < nn->num_tx_rings; j++) {
- io_p = nn->ctrl_bar + NFP_NET_CFG_TXR_STATS(j);
+ for (j = 0; j < nn->dp.num_tx_rings; j++) {
+ io_p = nn->dp.ctrl_bar + NFP_NET_CFG_TXR_STATS(j);
data[i++] = readq(io_p);
- io_p = nn->ctrl_bar + NFP_NET_CFG_TXR_STATS(j) + 8;
+ io_p = nn->dp.ctrl_bar + NFP_NET_CFG_TXR_STATS(j) + 8;
data[i++] = readq(io_p);
}
- for (j = 0; j < nn->num_rx_rings; j++) {
- io_p = nn->ctrl_bar + NFP_NET_CFG_RXR_STATS(j);
+ for (j = 0; j < nn->dp.num_rx_rings; j++) {
+ io_p = nn->dp.ctrl_bar + NFP_NET_CFG_RXR_STATS(j);
data[i++] = readq(io_p);
- io_p = nn->ctrl_bar + NFP_NET_CFG_RXR_STATS(j) + 8;
+ io_p = nn->dp.ctrl_bar + NFP_NET_CFG_RXR_STATS(j) + 8;
data[i++] = readq(io_p);
}
}
@@ -410,7 +512,7 @@ static int nfp_net_get_rxnfc(struct net_device *netdev,
switch (cmd->cmd) {
case ETHTOOL_GRXRINGS:
- cmd->data = nn->num_rx_rings;
+ cmd->data = nn->dp.num_rx_rings;
return 0;
case ETHTOOL_GRXFH:
return nfp_net_get_rss_hash_opts(nn, cmd);
@@ -454,13 +556,13 @@ static int nfp_net_set_rss_hash_opt(struct nfp_net *nn,
return -EINVAL;
}
- new_rss_cfg |= NFP_NET_CFG_RSS_TOEPLITZ;
+ new_rss_cfg |= FIELD_PREP(NFP_NET_CFG_RSS_HFUNC, nn->rss_hfunc);
new_rss_cfg |= NFP_NET_CFG_RSS_MASK;
if (new_rss_cfg == nn->rss_cfg)
return 0;
- writel(new_rss_cfg, nn->ctrl_bar + NFP_NET_CFG_RSS_CTRL);
+ writel(new_rss_cfg, nn->dp.ctrl_bar + NFP_NET_CFG_RSS_CTRL);
err = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_RSS);
if (err)
return err;
@@ -496,7 +598,12 @@ static u32 nfp_net_get_rxfh_indir_size(struct net_device *netdev)
static u32 nfp_net_get_rxfh_key_size(struct net_device *netdev)
{
- return NFP_NET_CFG_RSS_KEY_SZ;
+ struct nfp_net *nn = netdev_priv(netdev);
+
+ if (!(nn->cap & NFP_NET_CFG_CTRL_RSS))
+ return -EOPNOTSUPP;
+
+ return nfp_net_rss_key_sz(nn);
}
static int nfp_net_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
@@ -512,9 +619,12 @@ static int nfp_net_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
for (i = 0; i < ARRAY_SIZE(nn->rss_itbl); i++)
indir[i] = nn->rss_itbl[i];
if (key)
- memcpy(key, nn->rss_key, NFP_NET_CFG_RSS_KEY_SZ);
- if (hfunc)
- *hfunc = ETH_RSS_HASH_TOP;
+ memcpy(key, nn->rss_key, nfp_net_rss_key_sz(nn));
+ if (hfunc) {
+ *hfunc = nn->rss_hfunc;
+ if (*hfunc >= 1 << ETH_RSS_HASH_FUNCS_COUNT)
+ *hfunc = ETH_RSS_HASH_UNKNOWN;
+ }
return 0;
}
@@ -527,14 +637,14 @@ static int nfp_net_set_rxfh(struct net_device *netdev,
int i;
if (!(nn->cap & NFP_NET_CFG_CTRL_RSS) ||
- !(hfunc == ETH_RSS_HASH_NO_CHANGE || hfunc == ETH_RSS_HASH_TOP))
+ !(hfunc == ETH_RSS_HASH_NO_CHANGE || hfunc == nn->rss_hfunc))
return -EOPNOTSUPP;
if (!key && !indir)
return 0;
if (key) {
- memcpy(nn->rss_key, key, NFP_NET_CFG_RSS_KEY_SZ);
+ memcpy(nn->rss_key, key, nfp_net_rss_key_sz(nn));
nfp_net_rss_write_key(nn);
}
if (indir) {
@@ -564,7 +674,7 @@ static void nfp_net_get_regs(struct net_device *netdev,
regs->version = nn_readl(nn, NFP_NET_CFG_VERSION);
for (i = 0; i < NFP_NET_CFG_BAR_SZ / sizeof(u32); i++)
- regs_buf[i] = readl(nn->ctrl_bar + (i * sizeof(u32)));
+ regs_buf[i] = readl(nn->dp.ctrl_bar + (i * sizeof(u32)));
}
static int nfp_net_get_coalesce(struct net_device *netdev,
@@ -736,16 +846,16 @@ static void nfp_net_get_channels(struct net_device *netdev,
struct nfp_net *nn = netdev_priv(netdev);
unsigned int num_tx_rings;
- num_tx_rings = nn->num_tx_rings;
- if (nn->xdp_prog)
- num_tx_rings -= nn->num_rx_rings;
+ num_tx_rings = nn->dp.num_tx_rings;
+ if (nn->dp.xdp_prog)
+ num_tx_rings -= nn->dp.num_rx_rings;
channel->max_rx = min(nn->max_rx_rings, nn->max_r_vecs);
channel->max_tx = min(nn->max_tx_rings, nn->max_r_vecs);
channel->max_combined = min(channel->max_rx, channel->max_tx);
channel->max_other = NFP_NET_NON_Q_VECTORS;
- channel->combined_count = min(nn->num_rx_rings, num_tx_rings);
- channel->rx_count = nn->num_rx_rings - channel->combined_count;
+ channel->combined_count = min(nn->dp.num_rx_rings, num_tx_rings);
+ channel->rx_count = nn->dp.num_rx_rings - channel->combined_count;
channel->tx_count = num_tx_rings - channel->combined_count;
channel->other_count = NFP_NET_NON_Q_VECTORS;
}
@@ -753,29 +863,19 @@ static void nfp_net_get_channels(struct net_device *netdev,
static int nfp_net_set_num_rings(struct nfp_net *nn, unsigned int total_rx,
unsigned int total_tx)
{
- struct nfp_net_ring_set *reconfig_rx = NULL, *reconfig_tx = NULL;
- struct nfp_net_ring_set rx = {
- .n_rings = total_rx,
- .mtu = nn->netdev->mtu,
- .dcnt = nn->rxd_cnt,
- };
- struct nfp_net_ring_set tx = {
- .n_rings = total_tx,
- .dcnt = nn->txd_cnt,
- };
+ struct nfp_net_dp *dp;
- if (nn->num_rx_rings != total_rx)
- reconfig_rx = ℞
- if (nn->num_stack_tx_rings != total_tx ||
- (nn->xdp_prog && reconfig_rx))
- reconfig_tx = &tx;
+ dp = nfp_net_clone_dp(nn);
+ if (!dp)
+ return -ENOMEM;
- /* nfp_net_check_config() will catch tx.n_rings > nn->max_tx_rings */
- if (nn->xdp_prog)
- tx.n_rings += total_rx;
+ dp->num_rx_rings = total_rx;
+ dp->num_tx_rings = total_tx;
+ /* nfp_net_check_config() will catch num_tx_rings > nn->max_tx_rings */
+ if (dp->xdp_prog)
+ dp->num_tx_rings += total_rx;
- return nfp_net_ring_reconfig(nn, &nn->xdp_prog,
- reconfig_rx, reconfig_tx);
+ return nfp_net_ring_reconfig(nn, dp);
}
static int nfp_net_set_channels(struct net_device *netdev,
@@ -823,6 +923,8 @@ static const struct ethtool_ops nfp_net_ethtool_ops = {
.set_coalesce = nfp_net_set_coalesce,
.get_channels = nfp_net_get_channels,
.set_channels = nfp_net_set_channels,
+ .get_link_ksettings = nfp_net_get_link_ksettings,
+ .set_link_ksettings = nfp_net_set_link_ksettings,
};
void nfp_net_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
index 3afcdc1..4c6863a 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
@@ -47,11 +47,12 @@
#include <linux/pci_regs.h>
#include <linux/msi.h>
#include <linux/random.h>
+#include <linux/rtnetlink.h>
#include "nfpcore/nfp.h"
#include "nfpcore/nfp_cpp.h"
#include "nfpcore/nfp_nffw.h"
-#include "nfpcore/nfp_nsp_eth.h"
+#include "nfpcore/nfp_nsp.h"
#include "nfpcore/nfp6000_pcie.h"
#include "nfp_net_ctrl.h"
@@ -129,61 +130,61 @@ static u8 __iomem *nfp_net_map_area(struct nfp_cpp *cpp,
return (u8 __iomem *)ERR_PTR(err);
}
-static void
-nfp_net_get_mac_addr_hwinfo(struct nfp_net *nn, struct nfp_cpp *cpp,
- unsigned int id)
-{
- u8 mac_addr[ETH_ALEN];
- const char *mac_str;
- char name[32];
-
- snprintf(name, sizeof(name), "eth%d.mac", id);
-
- mac_str = nfp_hwinfo_lookup(cpp, name);
- if (!mac_str) {
- dev_warn(&nn->pdev->dev,
- "Can't lookup MAC address. Generate\n");
- eth_hw_addr_random(nn->netdev);
- return;
- }
-
- if (sscanf(mac_str, "%02hhx:%02hhx:%02hhx:%02hhx:%02hhx:%02hhx",
- &mac_addr[0], &mac_addr[1], &mac_addr[2],
- &mac_addr[3], &mac_addr[4], &mac_addr[5]) != 6) {
- dev_warn(&nn->pdev->dev,
- "Can't parse MAC address (%s). Generate.\n", mac_str);
- eth_hw_addr_random(nn->netdev);
- return;
- }
-
- ether_addr_copy(nn->netdev->dev_addr, mac_addr);
- ether_addr_copy(nn->netdev->perm_addr, mac_addr);
-}
-
/**
* nfp_net_get_mac_addr() - Get the MAC address.
* @nn: NFP Network structure
- * @pf: NFP PF device structure
+ * @cpp: NFP CPP handle
* @id: NFP port id
*
* First try to get the MAC address from NSP ETH table. If that
* fails try HWInfo. As a last resort generate a random address.
*/
static void
-nfp_net_get_mac_addr(struct nfp_net *nn, struct nfp_pf *pf, unsigned int id)
+nfp_net_get_mac_addr(struct nfp_net *nn, struct nfp_cpp *cpp, unsigned int id)
+{
+ struct nfp_net_dp *dp = &nn->dp;
+ u8 mac_addr[ETH_ALEN];
+ const char *mac_str;
+ char name[32];
+
+ if (nn->eth_port) {
+ ether_addr_copy(dp->netdev->dev_addr, nn->eth_port->mac_addr);
+ ether_addr_copy(dp->netdev->perm_addr, nn->eth_port->mac_addr);
+ return;
+ }
+
+ snprintf(name, sizeof(name), "eth%d.mac", id);
+
+ mac_str = nfp_hwinfo_lookup(cpp, name);
+ if (!mac_str) {
+ dev_warn(dp->dev, "Can't lookup MAC address. Generate\n");
+ eth_hw_addr_random(dp->netdev);
+ return;
+ }
+
+ if (sscanf(mac_str, "%02hhx:%02hhx:%02hhx:%02hhx:%02hhx:%02hhx",
+ &mac_addr[0], &mac_addr[1], &mac_addr[2],
+ &mac_addr[3], &mac_addr[4], &mac_addr[5]) != 6) {
+ dev_warn(dp->dev,
+ "Can't parse MAC address (%s). Generate.\n", mac_str);
+ eth_hw_addr_random(dp->netdev);
+ return;
+ }
+
+ ether_addr_copy(dp->netdev->dev_addr, mac_addr);
+ ether_addr_copy(dp->netdev->perm_addr, mac_addr);
+}
+
+static struct nfp_eth_table_port *
+nfp_net_find_port(struct nfp_pf *pf, unsigned int id)
{
int i;
for (i = 0; pf->eth_tbl && i < pf->eth_tbl->count; i++)
- if (pf->eth_tbl->ports[i].eth_index == id) {
- const u8 *mac_addr = pf->eth_tbl->ports[i].mac_addr;
+ if (pf->eth_tbl->ports[i].eth_index == id)
+ return &pf->eth_tbl->ports[i];
- ether_addr_copy(nn->netdev->dev_addr, mac_addr);
- ether_addr_copy(nn->netdev->perm_addr, mac_addr);
- return;
- }
-
- nfp_net_get_mac_addr_hwinfo(nn, pf->cpp, id);
+ return NULL;
}
static unsigned int nfp_net_pf_get_num_ports(struct nfp_pf *pf)
@@ -282,6 +283,7 @@ static void nfp_net_pf_free_netdevs(struct nfp_pf *pf)
while (!list_empty(&pf->ports)) {
nn = list_first_entry(&pf->ports, struct nfp_net, port_list);
list_del(&nn->port_list);
+ pf->num_netdevs--;
nfp_net_netdev_free(nn);
}
@@ -290,7 +292,8 @@ static void nfp_net_pf_free_netdevs(struct nfp_pf *pf)
static struct nfp_net *
nfp_net_pf_alloc_port_netdev(struct nfp_pf *pf, void __iomem *ctrl_bar,
void __iomem *tx_bar, void __iomem *rx_bar,
- int stride, struct nfp_net_fw_version *fw_ver)
+ int stride, struct nfp_net_fw_version *fw_ver,
+ struct nfp_eth_table_port *eth_port)
{
u32 n_tx_rings, n_rx_rings;
struct nfp_net *nn;
@@ -305,12 +308,13 @@ nfp_net_pf_alloc_port_netdev(struct nfp_pf *pf, void __iomem *ctrl_bar,
nn->cpp = pf->cpp;
nn->fw_ver = *fw_ver;
- nn->ctrl_bar = ctrl_bar;
+ nn->dp.ctrl_bar = ctrl_bar;
nn->tx_bar = tx_bar;
nn->rx_bar = rx_bar;
- nn->is_vf = 0;
+ nn->dp.is_vf = 0;
nn->stride_rx = stride;
nn->stride_tx = stride;
+ nn->eth_port = eth_port;
return nn;
}
@@ -322,7 +326,7 @@ nfp_net_pf_init_port_netdev(struct nfp_pf *pf, struct nfp_net *nn,
int err;
/* Get MAC address */
- nfp_net_get_mac_addr(nn, pf, id);
+ nfp_net_get_mac_addr(nn, pf->cpp, id);
/* Get ME clock frequency from ctrl BAR
* XXX for now frequency is hardcoded until we figure out how
@@ -330,7 +334,7 @@ nfp_net_pf_init_port_netdev(struct nfp_pf *pf, struct nfp_net *nn,
*/
nn->me_freq_mhz = 1200;
- err = nfp_net_netdev_init(nn->netdev);
+ err = nfp_net_netdev_init(nn->dp.netdev);
if (err)
return err;
@@ -347,6 +351,7 @@ nfp_net_pf_alloc_netdevs(struct nfp_pf *pf, void __iomem *ctrl_bar,
int stride, struct nfp_net_fw_version *fw_ver)
{
u32 prev_tx_base, prev_rx_base, tgt_tx_base, tgt_rx_base;
+ struct nfp_eth_table_port *eth_port;
struct nfp_net *nn;
unsigned int i;
int err;
@@ -362,17 +367,27 @@ nfp_net_pf_alloc_netdevs(struct nfp_pf *pf, void __iomem *ctrl_bar,
prev_tx_base = tgt_tx_base;
prev_rx_base = tgt_rx_base;
- nn = nfp_net_pf_alloc_port_netdev(pf, ctrl_bar, tx_bar, rx_bar,
- stride, fw_ver);
- if (IS_ERR(nn)) {
- err = PTR_ERR(nn);
- goto err_free_prev;
+ eth_port = nfp_net_find_port(pf, i);
+ if (eth_port && eth_port->override_changed) {
+ nfp_warn(pf->cpp, "Config changed for port #%d, reboot required before port will be operational\n", i);
+ } else {
+ nn = nfp_net_pf_alloc_port_netdev(pf, ctrl_bar, tx_bar,
+ rx_bar, stride,
+ fw_ver, eth_port);
+ if (IS_ERR(nn)) {
+ err = PTR_ERR(nn);
+ goto err_free_prev;
+ }
+ list_add_tail(&nn->port_list, &pf->ports);
+ pf->num_netdevs++;
}
- list_add_tail(&nn->port_list, &pf->ports);
ctrl_bar += NFP_PF_CSR_SLICE_SIZE;
}
+ if (list_empty(&pf->ports))
+ return -ENODEV;
+
return 0;
err_free_prev:
@@ -399,7 +414,7 @@ nfp_net_pf_spawn_netdevs(struct nfp_pf *pf,
/* Get MSI-X vectors */
wanted_irqs = 0;
list_for_each_entry(nn, &pf->ports, port_list)
- wanted_irqs += NFP_NET_NON_Q_VECTORS + nn->num_r_vecs;
+ wanted_irqs += NFP_NET_NON_Q_VECTORS + nn->dp.num_r_vecs;
pf->irq_entries = kcalloc(wanted_irqs, sizeof(*pf->irq_entries),
GFP_KERNEL);
if (!pf->irq_entries) {
@@ -408,7 +423,7 @@ nfp_net_pf_spawn_netdevs(struct nfp_pf *pf,
}
num_irqs = nfp_net_irqs_alloc(pf->pdev, pf->irq_entries,
- NFP_NET_MIN_PORT_IRQS * pf->num_ports,
+ NFP_NET_MIN_PORT_IRQS * pf->num_netdevs,
wanted_irqs);
if (!num_irqs) {
nn_warn(nn, "Unable to allocate MSI-X Vectors. Exiting\n");
@@ -418,7 +433,7 @@ nfp_net_pf_spawn_netdevs(struct nfp_pf *pf,
/* Distribute IRQs to ports */
irqs_left = num_irqs;
- ports_left = pf->num_ports;
+ ports_left = pf->num_netdevs;
list_for_each_entry(nn, &pf->ports, port_list) {
unsigned int n;
@@ -444,7 +459,7 @@ nfp_net_pf_spawn_netdevs(struct nfp_pf *pf,
err_prev_deinit:
list_for_each_entry_continue_reverse(nn, &pf->ports, port_list) {
nfp_net_debugfs_dir_clean(&nn->debugfs_dir);
- nfp_net_netdev_clean(nn->netdev);
+ nfp_net_netdev_clean(nn->dp.netdev);
}
nfp_net_irqs_disable(pf->pdev);
err_vec_free:
@@ -454,6 +469,81 @@ nfp_net_pf_spawn_netdevs(struct nfp_pf *pf,
return err;
}
+static void nfp_net_pci_remove_finish(struct nfp_pf *pf)
+{
+ nfp_net_debugfs_dir_clean(&pf->ddir);
+
+ nfp_net_irqs_disable(pf->pdev);
+ kfree(pf->irq_entries);
+
+ nfp_cpp_area_release_free(pf->rx_area);
+ nfp_cpp_area_release_free(pf->tx_area);
+ nfp_cpp_area_release_free(pf->ctrl_area);
+}
+
+static void nfp_net_refresh_netdevs(struct work_struct *work)
+{
+ struct nfp_pf *pf = container_of(work, struct nfp_pf,
+ port_refresh_work);
+ struct nfp_net *nn, *next;
+
+ mutex_lock(&pf->port_lock);
+
+ /* Check for nfp_net_pci_remove() racing against us */
+ if (list_empty(&pf->ports))
+ goto out;
+
+ list_for_each_entry_safe(nn, next, &pf->ports, port_list) {
+ if (!nn->eth_port) {
+ nfp_warn(pf->cpp, "Warning: port not present after reconfig\n");
+ continue;
+ }
+ if (!nn->eth_port->override_changed)
+ continue;
+
+ nn_warn(nn, "Port config changed, unregistering. Reboot required before port will be operational again.\n");
+
+ nfp_net_debugfs_dir_clean(&nn->debugfs_dir);
+ nfp_net_netdev_clean(nn->dp.netdev);
+
+ list_del(&nn->port_list);
+ pf->num_netdevs--;
+ nfp_net_netdev_free(nn);
+ }
+
+ if (list_empty(&pf->ports))
+ nfp_net_pci_remove_finish(pf);
+out:
+ mutex_unlock(&pf->port_lock);
+}
+
+void nfp_net_refresh_port_config(struct nfp_net *nn)
+{
+ struct nfp_pf *pf = pci_get_drvdata(nn->pdev);
+ struct nfp_eth_table *old_table;
+
+ ASSERT_RTNL();
+
+ old_table = pf->eth_tbl;
+
+ list_for_each_entry(nn, &pf->ports, port_list)
+ nfp_net_link_changed_read_clear(nn);
+
+ pf->eth_tbl = nfp_eth_read_ports(pf->cpp);
+ if (!pf->eth_tbl) {
+ pf->eth_tbl = old_table;
+ nfp_err(pf->cpp, "Error refreshing port config!\n");
+ return;
+ }
+
+ list_for_each_entry(nn, &pf->ports, port_list)
+ nn->eth_port = nfp_net_find_port(pf, nn->eth_port->eth_index);
+
+ kfree(old_table);
+
+ schedule_work(&pf->port_refresh_work);
+}
+
/*
* PCI device functions
*/
@@ -467,17 +557,23 @@ int nfp_net_pci_probe(struct nfp_pf *pf)
int stride;
int err;
+ INIT_WORK(&pf->port_refresh_work, nfp_net_refresh_netdevs);
+ mutex_init(&pf->port_lock);
+
/* Verify that the board has completed initialization */
if (!nfp_is_ready(pf->cpp)) {
nfp_err(pf->cpp, "NFP is not ready for NIC operation.\n");
return -EINVAL;
}
+ mutex_lock(&pf->port_lock);
pf->num_ports = nfp_net_pf_get_num_ports(pf);
ctrl_bar = nfp_net_pf_map_ctrl_bar(pf);
- if (!ctrl_bar)
- return pf->fw_loaded ? -EINVAL : -EPROBE_DEFER;
+ if (!ctrl_bar) {
+ err = pf->fw_loaded ? -EINVAL : -EPROBE_DEFER;
+ goto err_unlock;
+ }
nfp_net_get_fw_version(&fw_ver, ctrl_bar);
if (fw_ver.resv || fw_ver.class != NFP_NET_CFG_VERSION_CLASS_GENERIC) {
@@ -551,6 +647,8 @@ int nfp_net_pci_probe(struct nfp_pf *pf)
if (err)
goto err_clean_ddir;
+ mutex_unlock(&pf->port_lock);
+
return 0;
err_clean_ddir:
@@ -560,6 +658,8 @@ int nfp_net_pci_probe(struct nfp_pf *pf)
nfp_cpp_area_release_free(pf->tx_area);
err_ctrl_unmap:
nfp_cpp_area_release_free(pf->ctrl_area);
+err_unlock:
+ mutex_unlock(&pf->port_lock);
return err;
}
@@ -567,20 +667,21 @@ void nfp_net_pci_remove(struct nfp_pf *pf)
{
struct nfp_net *nn;
+ mutex_lock(&pf->port_lock);
+ if (list_empty(&pf->ports))
+ goto out;
+
list_for_each_entry(nn, &pf->ports, port_list) {
nfp_net_debugfs_dir_clean(&nn->debugfs_dir);
- nfp_net_netdev_clean(nn->netdev);
+ nfp_net_netdev_clean(nn->dp.netdev);
}
nfp_net_pf_free_netdevs(pf);
- nfp_net_debugfs_dir_clean(&pf->ddir);
+ nfp_net_pci_remove_finish(pf);
+out:
+ mutex_unlock(&pf->port_lock);
- nfp_net_irqs_disable(pf->pdev);
- kfree(pf->irq_entries);
-
- nfp_cpp_area_release_free(pf->rx_area);
- nfp_cpp_area_release_free(pf->tx_area);
- nfp_cpp_area_release_free(pf->ctrl_area);
+ cancel_work_sync(&pf->port_refresh_work);
}
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c b/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c
index 18a851e..b5b6f69 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c
@@ -58,7 +58,7 @@ void nfp_net_filter_stats_timer(unsigned long data)
spin_lock_bh(&nn->rx_filter_lock);
- if (nn->ctrl & NFP_NET_CFG_CTRL_BPF)
+ if (nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF)
mod_timer(&nn->rx_filter_stats_timer,
jiffies + NFP_NET_STAT_POLL_IVL);
@@ -132,7 +132,7 @@ nfp_net_bpf_get_act(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf)
return NN_ACT_TC_DROP;
if (is_tcf_mirred_egress_redirect(a) &&
- tcf_mirred_ifindex(a) == nn->netdev->ifindex)
+ tcf_mirred_ifindex(a) == nn->dp.netdev->ifindex)
return NN_ACT_TC_REDIR;
}
@@ -160,7 +160,7 @@ nfp_net_bpf_offload_prepare(struct nfp_net *nn,
act = ret;
max_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32;
- if (max_mtu < nn->netdev->mtu) {
+ if (max_mtu < nn->dp.netdev->mtu) {
nn_info(nn, "BPF offload not supported with MTU larger than HW packet split boundary\n");
return -ENOTSUPP;
}
@@ -168,8 +168,7 @@ nfp_net_bpf_offload_prepare(struct nfp_net *nn,
start_off = nn_readw(nn, NFP_NET_CFG_BPF_START);
done_off = nn_readw(nn, NFP_NET_CFG_BPF_DONE);
- *code = dma_zalloc_coherent(&nn->pdev->dev, code_sz, dma_addr,
- GFP_KERNEL);
+ *code = dma_zalloc_coherent(nn->dp.dev, code_sz, dma_addr, GFP_KERNEL);
if (!*code)
return -ENOMEM;
@@ -181,7 +180,7 @@ nfp_net_bpf_offload_prepare(struct nfp_net *nn,
return 0;
out:
- dma_free_coherent(&nn->pdev->dev, code_sz, *code, *dma_addr);
+ dma_free_coherent(nn->dp.dev, code_sz, *code, *dma_addr);
return ret;
}
@@ -194,7 +193,7 @@ nfp_net_bpf_load_and_start(struct nfp_net *nn, u32 tc_flags,
u64 bpf_addr = dma_addr;
int err;
- nn->bpf_offload_skip_sw = !!(tc_flags & TCA_CLS_FLAGS_SKIP_SW);
+ nn->dp.bpf_offload_skip_sw = !!(tc_flags & TCA_CLS_FLAGS_SKIP_SW);
if (dense_mode)
bpf_addr |= NFP_NET_CFG_BPF_CFG_8CTX;
@@ -208,13 +207,13 @@ nfp_net_bpf_load_and_start(struct nfp_net *nn, u32 tc_flags,
nn_err(nn, "FW command error while loading BPF: %d\n", err);
/* Enable passing packets through BPF function */
- nn->ctrl |= NFP_NET_CFG_CTRL_BPF;
- nn_writel(nn, NFP_NET_CFG_CTRL, nn->ctrl);
+ nn->dp.ctrl |= NFP_NET_CFG_CTRL_BPF;
+ nn_writel(nn, NFP_NET_CFG_CTRL, nn->dp.ctrl);
err = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_GEN);
if (err)
nn_err(nn, "FW command error while enabling BPF: %d\n", err);
- dma_free_coherent(&nn->pdev->dev, code_sz, code, dma_addr);
+ dma_free_coherent(nn->dp.dev, code_sz, code, dma_addr);
nfp_net_bpf_stats_reset(nn);
mod_timer(&nn->rx_filter_stats_timer, jiffies + NFP_NET_STAT_POLL_IVL);
@@ -222,16 +221,16 @@ nfp_net_bpf_load_and_start(struct nfp_net *nn, u32 tc_flags,
static int nfp_net_bpf_stop(struct nfp_net *nn)
{
- if (!(nn->ctrl & NFP_NET_CFG_CTRL_BPF))
+ if (!(nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF))
return 0;
spin_lock_bh(&nn->rx_filter_lock);
- nn->ctrl &= ~NFP_NET_CFG_CTRL_BPF;
+ nn->dp.ctrl &= ~NFP_NET_CFG_CTRL_BPF;
spin_unlock_bh(&nn->rx_filter_lock);
- nn_writel(nn, NFP_NET_CFG_CTRL, nn->ctrl);
+ nn_writel(nn, NFP_NET_CFG_CTRL, nn->dp.ctrl);
del_timer_sync(&nn->rx_filter_stats_timer);
- nn->bpf_offload_skip_sw = 0;
+ nn->dp.bpf_offload_skip_sw = 0;
return nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_GEN);
}
@@ -255,7 +254,7 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf)
* frames which didn't have BPF applied in the hardware should
* be fine if software fallback is available, though.
*/
- if (nn->bpf_offload_skip_sw)
+ if (nn->dp.bpf_offload_skip_sw)
return -EBUSY;
err = nfp_net_bpf_offload_prepare(nn, cls_bpf, &res, &code,
@@ -270,7 +269,7 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf)
return 0;
case TC_CLSBPF_ADD:
- if (nn->ctrl & NFP_NET_CFG_CTRL_BPF)
+ if (nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF)
return -EBUSY;
err = nfp_net_bpf_offload_prepare(nn, cls_bpf, &res, &code,
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
index 39407f7..86e61be 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
@@ -84,12 +84,12 @@ static void nfp_netvf_get_mac_addr(struct nfp_net *nn)
put_unaligned_be16(nn_readw(nn, NFP_NET_CFG_MACADDR + 6), &mac_addr[4]);
if (!is_valid_ether_addr(mac_addr)) {
- eth_hw_addr_random(nn->netdev);
+ eth_hw_addr_random(nn->dp.netdev);
return;
}
- ether_addr_copy(nn->netdev->dev_addr, mac_addr);
- ether_addr_copy(nn->netdev->perm_addr, mac_addr);
+ ether_addr_copy(nn->dp.netdev->dev_addr, mac_addr);
+ ether_addr_copy(nn->dp.netdev->perm_addr, mac_addr);
}
static int nfp_netvf_pci_probe(struct pci_dev *pdev,
@@ -210,8 +210,8 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
vf->nn = nn;
nn->fw_ver = fw_ver;
- nn->ctrl_bar = ctrl_bar;
- nn->is_vf = 1;
+ nn->dp.ctrl_bar = ctrl_bar;
+ nn->dp.is_vf = 1;
nn->stride_tx = stride;
nn->stride_rx = stride;
@@ -268,7 +268,8 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
num_irqs = nfp_net_irqs_alloc(pdev, vf->irq_entries,
NFP_NET_MIN_PORT_IRQS,
- NFP_NET_NON_Q_VECTORS + nn->num_r_vecs);
+ NFP_NET_NON_Q_VECTORS +
+ nn->dp.num_r_vecs);
if (!num_irqs) {
nn_warn(nn, "Unable to allocate MSI-X Vectors. Exiting\n");
err = -EIO;
@@ -282,7 +283,7 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
*/
nn->me_freq_mhz = 1200;
- err = nfp_net_netdev_init(nn->netdev);
+ err = nfp_net_netdev_init(nn->dp.netdev);
if (err)
goto err_irqs_disable;
@@ -327,7 +328,7 @@ static void nfp_netvf_pci_remove(struct pci_dev *pdev)
nfp_net_debugfs_dir_clean(&nn->debugfs_dir);
nfp_net_debugfs_dir_clean(&vf->ddir);
- nfp_net_netdev_clean(nn->netdev);
+ nfp_net_netdev_clean(nn->dp.netdev);
nfp_net_irqs_disable(pdev);
@@ -337,7 +338,7 @@ static void nfp_netvf_pci_remove(struct pci_dev *pdev)
} else {
iounmap(vf->q_bar);
}
- iounmap(nn->ctrl_bar);
+ iounmap(nn->dp.ctrl_bar);
nfp_net_netdev_free(nn);
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h
index 42cb720..8afef75 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h
@@ -48,32 +48,25 @@
const char *nfp_hwinfo_lookup(struct nfp_cpp *cpp, const char *lookup);
-/* Implemented in nfp_nsp.c */
+/* Implemented in nfp_nsp.c, low level functions */
struct nfp_nsp;
-struct firmware;
-struct nfp_nsp *nfp_nsp_open(struct nfp_cpp *cpp);
-void nfp_nsp_close(struct nfp_nsp *state);
-u16 nfp_nsp_get_abi_ver_major(struct nfp_nsp *state);
-u16 nfp_nsp_get_abi_ver_minor(struct nfp_nsp *state);
-int nfp_nsp_wait(struct nfp_nsp *state);
-int nfp_nsp_device_soft_reset(struct nfp_nsp *state);
-int nfp_nsp_load_fw(struct nfp_nsp *state, const struct firmware *fw);
+struct nfp_cpp *nfp_nsp_cpp(struct nfp_nsp *state);
+bool nfp_nsp_config_modified(struct nfp_nsp *state);
+void nfp_nsp_config_set_modified(struct nfp_nsp *state, bool modified);
+void *nfp_nsp_config_entries(struct nfp_nsp *state);
+unsigned int nfp_nsp_config_idx(struct nfp_nsp *state);
+void nfp_nsp_config_set_state(struct nfp_nsp *state, void *entries,
+ unsigned int idx);
+void nfp_nsp_config_clear_state(struct nfp_nsp *state);
int nfp_nsp_read_eth_table(struct nfp_nsp *state, void *buf, unsigned int size);
int nfp_nsp_write_eth_table(struct nfp_nsp *state,
const void *buf, unsigned int size);
/* Implemented in nfp_resource.c */
-#define NFP_RESOURCE_TBL_TARGET NFP_CPP_TARGET_MU
-#define NFP_RESOURCE_TBL_BASE 0x8100000000ULL
-
-/* NFP Resource Table self-identifier */
-#define NFP_RESOURCE_TBL_NAME "nfp.res"
-#define NFP_RESOURCE_TBL_KEY 0x00000000 /* Special key for entry 0 */
-
-/* All other keys are CRC32-POSIX of the 8-byte identification string */
+/* All keys are CRC32-POSIX of the 8-byte identification string */
/* ARM/PCI vNIC Interfaces 0..3 */
#define NFP_RESOURCE_VNIC_PCI_0 "vnic.p0"
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
index 15cc3e7..43dc68e 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
@@ -217,7 +217,7 @@ static resource_size_t nfp_bar_resource_start(struct nfp_bar *bar)
#define TARGET_WIDTH_64 8
static int
-compute_bar(struct nfp6000_pcie *nfp, struct nfp_bar *bar,
+compute_bar(const struct nfp6000_pcie *nfp, const struct nfp_bar *bar,
u32 *bar_config, u64 *bar_base,
int tgt, int act, int tok, u64 offset, size_t size, int width)
{
@@ -410,35 +410,36 @@ find_matching_bar(struct nfp6000_pcie *nfp,
/* Return EAGAIN if no resource is available */
static int
-find_unused_bar_noblock(struct nfp6000_pcie *nfp,
+find_unused_bar_noblock(const struct nfp6000_pcie *nfp,
int tgt, int act, int tok,
u64 offset, size_t size, int width)
{
- int n, invalid = 0;
+ int n, busy = 0;
for (n = 0; n < nfp->bars; n++) {
- struct nfp_bar *bar = &nfp->bar[n];
+ const struct nfp_bar *bar = &nfp->bar[n];
int err;
- if (bar->bitsize == 0) {
- invalid++;
- continue;
- }
-
- if (atomic_read(&bar->refcnt) != 0)
+ if (!bar->bitsize)
continue;
/* Just check to see if we can make it fit... */
err = compute_bar(nfp, bar, NULL, NULL,
tgt, act, tok, offset, size, width);
+ if (err)
+ continue;
- if (err < 0)
- invalid++;
- else
+ if (!atomic_read(&bar->refcnt))
return n;
+
+ busy++;
}
- return (n == invalid) ? -EINVAL : -EAGAIN;
+ if (WARN(!busy, "No suitable BAR found for request tgt:0x%x act:0x%x tok:0x%x off:0x%llx size:%zd width:%d\n",
+ tgt, act, tok, offset, size, width))
+ return -EINVAL;
+
+ return -EAGAIN;
}
static int
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c
index 40108e6..e2abba4 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c
@@ -65,39 +65,49 @@ struct nfp_cpp_resource {
u64 end;
};
-struct nfp_cpp_mutex {
- struct list_head list;
- struct nfp_cpp *cpp;
- int target;
- u16 usage;
- u16 depth;
- unsigned long long address;
- u32 key;
-};
-
+/**
+ * struct nfp_cpp - main nfpcore device structure
+ * Following fields are read-only after probe() exits or netdevs are spawned.
+ * @dev: embedded device structure
+ * @op: low-level implementation ops
+ * @priv: private data of the low-level implementation
+ * @model: chip model
+ * @interface: chip interface id we are using to reach it
+ * @serial: chip serial number
+ * @imb_cat_table: CPP Mapping Table
+ *
+ * Following fields can be used only in probe() or with rtnl held:
+ * @hwinfo: HWInfo database fetched from the device
+ * @rtsym: firmware run time symbols
+ *
+ * Following fields use explicit locking:
+ * @resource_list: NFP CPP resource list
+ * @resource_lock: protects @resource_list
+ *
+ * @area_cache_list: cached areas for cpp/xpb read/write speed up
+ * @area_cache_mutex: protects @area_cache_list
+ *
+ * @waitq: area wait queue
+ */
struct nfp_cpp {
struct device dev;
- void *priv; /* Private data of the low-level implementation */
+ void *priv;
u32 model;
u16 interface;
u8 serial[NFP_SERIAL_LEN];
const struct nfp_cpp_operations *op;
- struct list_head resource_list; /* NFP CPP resource list */
- struct list_head mutex_cache; /* Mutex cache */
+ struct list_head resource_list;
rwlock_t resource_lock;
wait_queue_head_t waitq;
- /* NFP6000 CPP Mapping Table */
u32 imb_cat_table[16];
- /* Cached areas for cpp/xpb readl/writel speedups */
- struct mutex area_cache_mutex; /* Lock for the area cache */
+ struct mutex area_cache_mutex;
struct list_head area_cache_list;
- /* Cached information */
void *hwinfo;
void *rtsym;
};
@@ -187,24 +197,6 @@ void nfp_cpp_free(struct nfp_cpp *cpp)
{
struct nfp_cpp_area_cache *cache, *ctmp;
struct nfp_cpp_resource *res, *rtmp;
- struct nfp_cpp_mutex *mutex, *mtmp;
-
- /* There should be no mutexes in the cache at this point. */
- WARN_ON(!list_empty(&cpp->mutex_cache));
- /* .. but if there are, unlock them and complain. */
- list_for_each_entry_safe(mutex, mtmp, &cpp->mutex_cache, list) {
- dev_err(cpp->dev.parent, "Dangling mutex: @%d::0x%llx, %d locks held by %d owners\n",
- mutex->target, (unsigned long long)mutex->address,
- mutex->depth, mutex->usage);
-
- /* Forcing an unlock */
- mutex->depth = 1;
- nfp_cpp_mutex_unlock(mutex);
-
- /* Forcing a free */
- mutex->usage = 1;
- nfp_cpp_mutex_free(mutex);
- }
/* Remove all caches */
list_for_each_entry_safe(cache, ctmp, &cpp->area_cache_list, entry) {
@@ -419,9 +411,43 @@ nfp_cpp_area_alloc(struct nfp_cpp *cpp, u32 dest,
*/
void nfp_cpp_area_free(struct nfp_cpp_area *area)
{
+ if (atomic_read(&area->refcount))
+ nfp_warn(area->cpp, "Warning: freeing busy area\n");
nfp_cpp_area_put(area);
}
+static bool nfp_cpp_area_acquire_try(struct nfp_cpp_area *area, int *status)
+{
+ *status = area->cpp->op->area_acquire(area);
+
+ return *status != -EAGAIN;
+}
+
+static int __nfp_cpp_area_acquire(struct nfp_cpp_area *area)
+{
+ int err, status;
+
+ if (atomic_inc_return(&area->refcount) > 1)
+ return 0;
+
+ if (!area->cpp->op->area_acquire)
+ return 0;
+
+ err = wait_event_interruptible(area->cpp->waitq,
+ nfp_cpp_area_acquire_try(area, &status));
+ if (!err)
+ err = status;
+ if (err) {
+ nfp_warn(area->cpp, "Warning: area wait failed: %d\n", err);
+ atomic_dec(&area->refcount);
+ return err;
+ }
+
+ nfp_cpp_area_get(area);
+
+ return 0;
+}
+
/**
* nfp_cpp_area_acquire() - lock down a CPP area for access
* @area: CPP area handle
@@ -433,27 +459,13 @@ void nfp_cpp_area_free(struct nfp_cpp_area *area)
*/
int nfp_cpp_area_acquire(struct nfp_cpp_area *area)
{
+ int ret;
+
mutex_lock(&area->mutex);
- if (atomic_inc_return(&area->refcount) == 1) {
- int (*a_a)(struct nfp_cpp_area *);
-
- a_a = area->cpp->op->area_acquire;
- if (a_a) {
- int err;
-
- wait_event_interruptible(area->cpp->waitq,
- (err = a_a(area)) != -EAGAIN);
- if (err < 0) {
- atomic_dec(&area->refcount);
- mutex_unlock(&area->mutex);
- return err;
- }
- }
- }
+ ret = __nfp_cpp_area_acquire(area);
mutex_unlock(&area->mutex);
- nfp_cpp_area_get(area);
- return 0;
+ return ret;
}
/**
@@ -829,10 +841,7 @@ area_cache_get(struct nfp_cpp *cpp, u32 id,
* the need for special case code below when
* checking against available cache size.
*/
- if (length == 0)
- return NULL;
-
- if (list_empty(&cpp->area_cache_list) || id == 0)
+ if (length == 0 || id == 0)
return NULL;
/* Remap from cpp_island to cpp_target */
@@ -840,10 +849,15 @@ area_cache_get(struct nfp_cpp *cpp, u32 id,
if (err < 0)
return NULL;
- addr += *offset;
-
mutex_lock(&cpp->area_cache_mutex);
+ if (list_empty(&cpp->area_cache_list)) {
+ mutex_unlock(&cpp->area_cache_mutex);
+ return NULL;
+ }
+
+ addr += *offset;
+
/* See if we have a match */
list_for_each_entry(cache, &cpp->area_cache_list, entry) {
if (id == cache->id &&
@@ -937,12 +951,14 @@ int nfp_cpp_read(struct nfp_cpp *cpp, u32 destination,
return -ENOMEM;
err = nfp_cpp_area_acquire(area);
- if (err)
- goto out;
+ if (err) {
+ nfp_cpp_area_free(area);
+ return err;
+ }
}
err = nfp_cpp_area_read(area, offset, kernel_vaddr, length);
-out:
+
if (cache)
area_cache_put(cpp, cache);
else
@@ -979,13 +995,14 @@ int nfp_cpp_write(struct nfp_cpp *cpp, u32 destination,
return -ENOMEM;
err = nfp_cpp_area_acquire(area);
- if (err)
- goto out;
+ if (err) {
+ nfp_cpp_area_free(area);
+ return err;
+ }
}
err = nfp_cpp_area_write(area, offset, kernel_vaddr, length);
-out:
if (cache)
area_cache_put(cpp, cache);
else
@@ -1127,7 +1144,6 @@ nfp_cpp_from_operations(const struct nfp_cpp_operations *ops,
rwlock_init(&cpp->resource_lock);
init_waitqueue_head(&cpp->waitq);
lockdep_set_class(&cpp->resource_lock, &nfp_cpp_resource_lock_key);
- INIT_LIST_HEAD(&cpp->mutex_cache);
INIT_LIST_HEAD(&cpp->resource_list);
INIT_LIST_HEAD(&cpp->area_cache_list);
mutex_init(&cpp->area_cache_mutex);
@@ -1425,322 +1441,3 @@ void *nfp_cpp_explicit_priv(struct nfp_cpp_explicit *cpp_explicit)
{
return &cpp_explicit[1];
}
-
-/* THIS FUNCTION IS NOT EXPORTED */
-static u32 nfp_mutex_locked(u16 interface)
-{
- return (u32)interface << 16 | 0x000f;
-}
-
-static u32 nfp_mutex_unlocked(u16 interface)
-{
- return (u32)interface << 16 | 0x0000;
-}
-
-static bool nfp_mutex_is_locked(u32 val)
-{
- return (val & 0xffff) == 0x000f;
-}
-
-static bool nfp_mutex_is_unlocked(u32 val)
-{
- return (val & 0xffff) == 0000;
-}
-
-/* If you need more than 65536 recursive locks, please rethink your code. */
-#define MUTEX_DEPTH_MAX 0xffff
-
-static int
-nfp_cpp_mutex_validate(u16 interface, int *target, unsigned long long address)
-{
- /* Not permitted on invalid interfaces */
- if (NFP_CPP_INTERFACE_TYPE_of(interface) ==
- NFP_CPP_INTERFACE_TYPE_INVALID)
- return -EINVAL;
-
- /* Address must be 64-bit aligned */
- if (address & 7)
- return -EINVAL;
-
- if (*target != NFP_CPP_TARGET_MU)
- return -EINVAL;
-
- return 0;
-}
-
-/**
- * nfp_cpp_mutex_init() - Initialize a mutex location
- * @cpp: NFP CPP handle
- * @target: NFP CPP target ID (ie NFP_CPP_TARGET_CLS or NFP_CPP_TARGET_MU)
- * @address: Offset into the address space of the NFP CPP target ID
- * @key: Unique 32-bit value for this mutex
- *
- * The CPP target:address must point to a 64-bit aligned location, and
- * will initialize 64 bits of data at the location.
- *
- * This creates the initial mutex state, as locked by this
- * nfp_cpp_interface().
- *
- * This function should only be called when setting up
- * the initial lock state upon boot-up of the system.
- *
- * Return: 0 on success, or -errno on failure
- */
-int nfp_cpp_mutex_init(struct nfp_cpp *cpp,
- int target, unsigned long long address, u32 key)
-{
- const u32 muw = NFP_CPP_ID(target, 4, 0); /* atomic_write */
- u16 interface = nfp_cpp_interface(cpp);
- int err;
-
- err = nfp_cpp_mutex_validate(interface, &target, address);
- if (err)
- return err;
-
- err = nfp_cpp_writel(cpp, muw, address + 4, key);
- if (err)
- return err;
-
- err = nfp_cpp_writel(cpp, muw, address, nfp_mutex_locked(interface));
- if (err)
- return err;
-
- return 0;
-}
-
-/**
- * nfp_cpp_mutex_alloc() - Create a mutex handle
- * @cpp: NFP CPP handle
- * @target: NFP CPP target ID (ie NFP_CPP_TARGET_CLS or NFP_CPP_TARGET_MU)
- * @address: Offset into the address space of the NFP CPP target ID
- * @key: 32-bit unique key (must match the key at this location)
- *
- * The CPP target:address must point to a 64-bit aligned location, and
- * reserve 64 bits of data at the location for use by the handle.
- *
- * Only target/address pairs that point to entities that support the
- * MU Atomic Engine's CmpAndSwap32 command are supported.
- *
- * Return: A non-NULL struct nfp_cpp_mutex * on success, NULL on failure.
- */
-struct nfp_cpp_mutex *nfp_cpp_mutex_alloc(struct nfp_cpp *cpp, int target,
- unsigned long long address, u32 key)
-{
- const u32 mur = NFP_CPP_ID(target, 3, 0); /* atomic_read */
- u16 interface = nfp_cpp_interface(cpp);
- struct nfp_cpp_mutex *mutex;
- int err;
- u32 tmp;
-
- err = nfp_cpp_mutex_validate(interface, &target, address);
- if (err)
- return NULL;
-
- /* Look for mutex on cache list */
- list_for_each_entry(mutex, &cpp->mutex_cache, list) {
- if (mutex->target == target && mutex->address == address) {
- mutex->usage++;
- return mutex;
- }
- }
-
- err = nfp_cpp_readl(cpp, mur, address + 4, &tmp);
- if (err < 0)
- return NULL;
-
- if (tmp != key)
- return NULL;
-
- mutex = kzalloc(sizeof(*mutex), GFP_KERNEL);
- if (!mutex)
- return NULL;
-
- mutex->cpp = cpp;
- mutex->target = target;
- mutex->address = address;
- mutex->key = key;
- mutex->depth = 0;
- mutex->usage = 1;
-
- /* Add mutex to cache list */
- list_add(&mutex->list, &cpp->mutex_cache);
-
- return mutex;
-}
-
-/**
- * nfp_cpp_mutex_free() - Free a mutex handle - does not alter the lock state
- * @mutex: NFP CPP Mutex handle
- */
-void nfp_cpp_mutex_free(struct nfp_cpp_mutex *mutex)
-{
- if (--mutex->usage)
- return;
-
- /* Remove mutex from cache */
- list_del(&mutex->list);
- kfree(mutex);
-}
-
-/**
- * nfp_cpp_mutex_lock() - Lock a mutex handle, using the NFP MU Atomic Engine
- * @mutex: NFP CPP Mutex handle
- *
- * Return: 0 on success, or -errno on failure
- */
-int nfp_cpp_mutex_lock(struct nfp_cpp_mutex *mutex)
-{
- unsigned long warn_at = jiffies + 15 * HZ;
- unsigned int timeout_ms = 1;
- int err;
-
- /* We can't use a waitqueue here, because the unlocker
- * might be on a separate CPU.
- *
- * So just wait for now.
- */
- for (;;) {
- err = nfp_cpp_mutex_trylock(mutex);
- if (err != -EBUSY)
- break;
-
- err = msleep_interruptible(timeout_ms);
- if (err != 0)
- return -ERESTARTSYS;
-
- if (time_is_before_eq_jiffies(warn_at)) {
- warn_at = jiffies + 60 * HZ;
- dev_warn(mutex->cpp->dev.parent,
- "Warning: waiting for NFP mutex [usage:%hd depth:%hd target:%d addr:%llx key:%08x]\n",
- mutex->usage, mutex->depth,
- mutex->target, mutex->address, mutex->key);
- }
- }
-
- return err;
-}
-
-/**
- * nfp_cpp_mutex_unlock() - Unlock a mutex handle, using the MU Atomic Engine
- * @mutex: NFP CPP Mutex handle
- *
- * Return: 0 on success, or -errno on failure
- */
-int nfp_cpp_mutex_unlock(struct nfp_cpp_mutex *mutex)
-{
- const u32 muw = NFP_CPP_ID(mutex->target, 4, 0); /* atomic_write */
- const u32 mur = NFP_CPP_ID(mutex->target, 3, 0); /* atomic_read */
- struct nfp_cpp *cpp = mutex->cpp;
- u32 key, value;
- u16 interface;
- int err;
-
- interface = nfp_cpp_interface(cpp);
-
- if (mutex->depth > 1) {
- mutex->depth--;
- return 0;
- }
-
- err = nfp_cpp_readl(mutex->cpp, mur, mutex->address + 4, &key);
- if (err < 0)
- return err;
-
- if (key != mutex->key)
- return -EPERM;
-
- err = nfp_cpp_readl(mutex->cpp, mur, mutex->address, &value);
- if (err < 0)
- return err;
-
- if (value != nfp_mutex_locked(interface))
- return -EACCES;
-
- err = nfp_cpp_writel(cpp, muw, mutex->address,
- nfp_mutex_unlocked(interface));
- if (err < 0)
- return err;
-
- mutex->depth = 0;
- return 0;
-}
-
-/**
- * nfp_cpp_mutex_trylock() - Attempt to lock a mutex handle
- * @mutex: NFP CPP Mutex handle
- *
- * Return: 0 if the lock succeeded, -errno on failure
- */
-int nfp_cpp_mutex_trylock(struct nfp_cpp_mutex *mutex)
-{
- const u32 muw = NFP_CPP_ID(mutex->target, 4, 0); /* atomic_write */
- const u32 mus = NFP_CPP_ID(mutex->target, 5, 3); /* test_set_imm */
- const u32 mur = NFP_CPP_ID(mutex->target, 3, 0); /* atomic_read */
- struct nfp_cpp *cpp = mutex->cpp;
- u32 key, value, tmp;
- int err;
-
- if (mutex->depth > 0) {
- if (mutex->depth == MUTEX_DEPTH_MAX)
- return -E2BIG;
- mutex->depth++;
- return 0;
- }
-
- /* Verify that the lock marker is not damaged */
- err = nfp_cpp_readl(cpp, mur, mutex->address + 4, &key);
- if (err < 0)
- return err;
-
- if (key != mutex->key)
- return -EPERM;
-
- /* Compare against the unlocked state, and if true,
- * write the interface id into the top 16 bits, and
- * mark as locked.
- */
- value = nfp_mutex_locked(nfp_cpp_interface(cpp));
-
- /* We use test_set_imm here, as it implies a read
- * of the current state, and sets the bits in the
- * bytemask of the command to 1s. Since the mutex
- * is guaranteed to be 64-bit aligned, the bytemask
- * of this 32-bit command is ensured to be 8'b00001111,
- * which implies that the lower 4 bits will be set to
- * ones regardless of the initial state.
- *
- * Since this is a 'Readback' operation, with no Pull
- * data, we can treat this as a normal Push (read)
- * atomic, which returns the original value.
- */
- err = nfp_cpp_readl(cpp, mus, mutex->address, &tmp);
- if (err < 0)
- return err;
-
- /* Was it unlocked? */
- if (nfp_mutex_is_unlocked(tmp)) {
- /* The read value can only be 0x....0000 in the unlocked state.
- * If there was another contending for this lock, then
- * the lock state would be 0x....000f
- */
-
- /* Write our owner ID into the lock
- * While not strictly necessary, this helps with
- * debug and bookkeeping.
- */
- err = nfp_cpp_writel(cpp, muw, mutex->address, value);
- if (err < 0)
- return err;
-
- mutex->depth = 1;
- return 0;
- }
-
- /* Already locked by us? Success! */
- if (tmp == value) {
- mutex->depth = 1;
- return 0;
- }
-
- return nfp_mutex_is_locked(tmp) ? -EBUSY : -EINVAL;
-}
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c
new file mode 100644
index 0000000..8a99c18
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c
@@ -0,0 +1,345 @@
+/*
+ * Copyright (C) 2015-2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below. You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * 2. Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/jiffies.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/wait.h>
+
+#include "nfp_cpp.h"
+#include "nfp6000/nfp6000.h"
+
+struct nfp_cpp_mutex {
+ struct nfp_cpp *cpp;
+ int target;
+ u16 depth;
+ unsigned long long address;
+ u32 key;
+};
+
+static u32 nfp_mutex_locked(u16 interface)
+{
+ return (u32)interface << 16 | 0x000f;
+}
+
+static u32 nfp_mutex_unlocked(u16 interface)
+{
+ return (u32)interface << 16 | 0x0000;
+}
+
+static bool nfp_mutex_is_locked(u32 val)
+{
+ return (val & 0xffff) == 0x000f;
+}
+
+static bool nfp_mutex_is_unlocked(u32 val)
+{
+ return (val & 0xffff) == 0000;
+}
+
+/* If you need more than 65536 recursive locks, please rethink your code. */
+#define NFP_MUTEX_DEPTH_MAX 0xffff
+
+static int
+nfp_cpp_mutex_validate(u16 interface, int *target, unsigned long long address)
+{
+ /* Not permitted on invalid interfaces */
+ if (NFP_CPP_INTERFACE_TYPE_of(interface) ==
+ NFP_CPP_INTERFACE_TYPE_INVALID)
+ return -EINVAL;
+
+ /* Address must be 64-bit aligned */
+ if (address & 7)
+ return -EINVAL;
+
+ if (*target != NFP_CPP_TARGET_MU)
+ return -EINVAL;
+
+ return 0;
+}
+
+/**
+ * nfp_cpp_mutex_init() - Initialize a mutex location
+ * @cpp: NFP CPP handle
+ * @target: NFP CPP target ID (ie NFP_CPP_TARGET_CLS or NFP_CPP_TARGET_MU)
+ * @address: Offset into the address space of the NFP CPP target ID
+ * @key: Unique 32-bit value for this mutex
+ *
+ * The CPP target:address must point to a 64-bit aligned location, and
+ * will initialize 64 bits of data at the location.
+ *
+ * This creates the initial mutex state, as locked by this
+ * nfp_cpp_interface().
+ *
+ * This function should only be called when setting up
+ * the initial lock state upon boot-up of the system.
+ *
+ * Return: 0 on success, or -errno on failure
+ */
+int nfp_cpp_mutex_init(struct nfp_cpp *cpp,
+ int target, unsigned long long address, u32 key)
+{
+ const u32 muw = NFP_CPP_ID(target, 4, 0); /* atomic_write */
+ u16 interface = nfp_cpp_interface(cpp);
+ int err;
+
+ err = nfp_cpp_mutex_validate(interface, &target, address);
+ if (err)
+ return err;
+
+ err = nfp_cpp_writel(cpp, muw, address + 4, key);
+ if (err)
+ return err;
+
+ err = nfp_cpp_writel(cpp, muw, address, nfp_mutex_locked(interface));
+ if (err)
+ return err;
+
+ return 0;
+}
+
+/**
+ * nfp_cpp_mutex_alloc() - Create a mutex handle
+ * @cpp: NFP CPP handle
+ * @target: NFP CPP target ID (ie NFP_CPP_TARGET_CLS or NFP_CPP_TARGET_MU)
+ * @address: Offset into the address space of the NFP CPP target ID
+ * @key: 32-bit unique key (must match the key at this location)
+ *
+ * The CPP target:address must point to a 64-bit aligned location, and
+ * reserve 64 bits of data at the location for use by the handle.
+ *
+ * Only target/address pairs that point to entities that support the
+ * MU Atomic Engine's CmpAndSwap32 command are supported.
+ *
+ * Return: A non-NULL struct nfp_cpp_mutex * on success, NULL on failure.
+ */
+struct nfp_cpp_mutex *nfp_cpp_mutex_alloc(struct nfp_cpp *cpp, int target,
+ unsigned long long address, u32 key)
+{
+ const u32 mur = NFP_CPP_ID(target, 3, 0); /* atomic_read */
+ u16 interface = nfp_cpp_interface(cpp);
+ struct nfp_cpp_mutex *mutex;
+ int err;
+ u32 tmp;
+
+ err = nfp_cpp_mutex_validate(interface, &target, address);
+ if (err)
+ return NULL;
+
+ err = nfp_cpp_readl(cpp, mur, address + 4, &tmp);
+ if (err < 0)
+ return NULL;
+
+ if (tmp != key)
+ return NULL;
+
+ mutex = kzalloc(sizeof(*mutex), GFP_KERNEL);
+ if (!mutex)
+ return NULL;
+
+ mutex->cpp = cpp;
+ mutex->target = target;
+ mutex->address = address;
+ mutex->key = key;
+ mutex->depth = 0;
+
+ return mutex;
+}
+
+/**
+ * nfp_cpp_mutex_free() - Free a mutex handle - does not alter the lock state
+ * @mutex: NFP CPP Mutex handle
+ */
+void nfp_cpp_mutex_free(struct nfp_cpp_mutex *mutex)
+{
+ kfree(mutex);
+}
+
+/**
+ * nfp_cpp_mutex_lock() - Lock a mutex handle, using the NFP MU Atomic Engine
+ * @mutex: NFP CPP Mutex handle
+ *
+ * Return: 0 on success, or -errno on failure
+ */
+int nfp_cpp_mutex_lock(struct nfp_cpp_mutex *mutex)
+{
+ unsigned long warn_at = jiffies + 15 * HZ;
+ unsigned int timeout_ms = 1;
+ int err;
+
+ /* We can't use a waitqueue here, because the unlocker
+ * might be on a separate CPU.
+ *
+ * So just wait for now.
+ */
+ for (;;) {
+ err = nfp_cpp_mutex_trylock(mutex);
+ if (err != -EBUSY)
+ break;
+
+ err = msleep_interruptible(timeout_ms);
+ if (err != 0)
+ return -ERESTARTSYS;
+
+ if (time_is_before_eq_jiffies(warn_at)) {
+ warn_at = jiffies + 60 * HZ;
+ nfp_warn(mutex->cpp,
+ "Warning: waiting for NFP mutex [depth:%hd target:%d addr:%llx key:%08x]\n",
+ mutex->depth,
+ mutex->target, mutex->address, mutex->key);
+ }
+ }
+
+ return err;
+}
+
+/**
+ * nfp_cpp_mutex_unlock() - Unlock a mutex handle, using the MU Atomic Engine
+ * @mutex: NFP CPP Mutex handle
+ *
+ * Return: 0 on success, or -errno on failure
+ */
+int nfp_cpp_mutex_unlock(struct nfp_cpp_mutex *mutex)
+{
+ const u32 muw = NFP_CPP_ID(mutex->target, 4, 0); /* atomic_write */
+ const u32 mur = NFP_CPP_ID(mutex->target, 3, 0); /* atomic_read */
+ struct nfp_cpp *cpp = mutex->cpp;
+ u32 key, value;
+ u16 interface;
+ int err;
+
+ interface = nfp_cpp_interface(cpp);
+
+ if (mutex->depth > 1) {
+ mutex->depth--;
+ return 0;
+ }
+
+ err = nfp_cpp_readl(mutex->cpp, mur, mutex->address + 4, &key);
+ if (err < 0)
+ return err;
+
+ if (key != mutex->key)
+ return -EPERM;
+
+ err = nfp_cpp_readl(mutex->cpp, mur, mutex->address, &value);
+ if (err < 0)
+ return err;
+
+ if (value != nfp_mutex_locked(interface))
+ return -EACCES;
+
+ err = nfp_cpp_writel(cpp, muw, mutex->address,
+ nfp_mutex_unlocked(interface));
+ if (err < 0)
+ return err;
+
+ mutex->depth = 0;
+ return 0;
+}
+
+/**
+ * nfp_cpp_mutex_trylock() - Attempt to lock a mutex handle
+ * @mutex: NFP CPP Mutex handle
+ *
+ * Return: 0 if the lock succeeded, -errno on failure
+ */
+int nfp_cpp_mutex_trylock(struct nfp_cpp_mutex *mutex)
+{
+ const u32 muw = NFP_CPP_ID(mutex->target, 4, 0); /* atomic_write */
+ const u32 mus = NFP_CPP_ID(mutex->target, 5, 3); /* test_set_imm */
+ const u32 mur = NFP_CPP_ID(mutex->target, 3, 0); /* atomic_read */
+ struct nfp_cpp *cpp = mutex->cpp;
+ u32 key, value, tmp;
+ int err;
+
+ if (mutex->depth > 0) {
+ if (mutex->depth == NFP_MUTEX_DEPTH_MAX)
+ return -E2BIG;
+ mutex->depth++;
+ return 0;
+ }
+
+ /* Verify that the lock marker is not damaged */
+ err = nfp_cpp_readl(cpp, mur, mutex->address + 4, &key);
+ if (err < 0)
+ return err;
+
+ if (key != mutex->key)
+ return -EPERM;
+
+ /* Compare against the unlocked state, and if true,
+ * write the interface id into the top 16 bits, and
+ * mark as locked.
+ */
+ value = nfp_mutex_locked(nfp_cpp_interface(cpp));
+
+ /* We use test_set_imm here, as it implies a read
+ * of the current state, and sets the bits in the
+ * bytemask of the command to 1s. Since the mutex
+ * is guaranteed to be 64-bit aligned, the bytemask
+ * of this 32-bit command is ensured to be 8'b00001111,
+ * which implies that the lower 4 bits will be set to
+ * ones regardless of the initial state.
+ *
+ * Since this is a 'Readback' operation, with no Pull
+ * data, we can treat this as a normal Push (read)
+ * atomic, which returns the original value.
+ */
+ err = nfp_cpp_readl(cpp, mus, mutex->address, &tmp);
+ if (err < 0)
+ return err;
+
+ /* Was it unlocked? */
+ if (nfp_mutex_is_unlocked(tmp)) {
+ /* The read value can only be 0x....0000 in the unlocked state.
+ * If there was another contending for this lock, then
+ * the lock state would be 0x....000f
+ */
+
+ /* Write our owner ID into the lock
+ * While not strictly necessary, this helps with
+ * debug and bookkeeping.
+ */
+ err = nfp_cpp_writel(cpp, muw, mutex->address, value);
+ if (err < 0)
+ return err;
+
+ mutex->depth = 1;
+ return 0;
+ }
+
+ return nfp_mutex_is_locked(tmp) ? -EBUSY : -EINVAL;
+}
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
index 34c5098..4635f42 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
@@ -49,6 +49,7 @@
#include "nfp.h"
#include "nfp_cpp.h"
+#include "nfp_nsp.h"
/* Offsets relative to the CSR base */
#define NSP_STATUS 0x00
@@ -96,6 +97,17 @@ enum nfp_nsp_cmd {
__MAX_SPCODE,
};
+static const struct {
+ int code;
+ const char *msg;
+} nsp_errors[] = {
+ { 6010, "could not map to phy for port" },
+ { 6011, "not an allowed rate/lanes for port" },
+ { 6012, "not an allowed rate/lanes for port" },
+ { 6013, "high/low error, change other port first" },
+ { 6014, "config not found in flash" },
+};
+
struct nfp_nsp {
struct nfp_cpp *cpp;
struct nfp_resource *res;
@@ -103,8 +115,63 @@ struct nfp_nsp {
u16 major;
u16 minor;
} ver;
+
+ /* Eth table config state */
+ bool modified;
+ unsigned int idx;
+ void *entries;
};
+struct nfp_cpp *nfp_nsp_cpp(struct nfp_nsp *state)
+{
+ return state->cpp;
+}
+
+bool nfp_nsp_config_modified(struct nfp_nsp *state)
+{
+ return state->modified;
+}
+
+void nfp_nsp_config_set_modified(struct nfp_nsp *state, bool modified)
+{
+ state->modified = modified;
+}
+
+void *nfp_nsp_config_entries(struct nfp_nsp *state)
+{
+ return state->entries;
+}
+
+unsigned int nfp_nsp_config_idx(struct nfp_nsp *state)
+{
+ return state->idx;
+}
+
+void
+nfp_nsp_config_set_state(struct nfp_nsp *state, void *entries, unsigned int idx)
+{
+ state->entries = entries;
+ state->idx = idx;
+}
+
+void nfp_nsp_config_clear_state(struct nfp_nsp *state)
+{
+ state->entries = NULL;
+ state->idx = 0;
+}
+
+static void nfp_nsp_print_extended_error(struct nfp_nsp *state, u32 ret_val)
+{
+ int i;
+
+ if (!ret_val)
+ return;
+
+ for (i = 0; i < ARRAY_SIZE(nsp_errors); i++)
+ if (ret_val == nsp_errors[i].code)
+ nfp_err(state->cpp, "err msg: %s\n", nsp_errors[i].msg);
+}
+
static int nfp_nsp_check(struct nfp_nsp *state)
{
struct nfp_cpp *cpp = state->cpp;
@@ -209,9 +276,8 @@ nfp_nsp_wait_reg(struct nfp_cpp *cpp, u64 *reg,
if ((*reg & mask) == val)
return 0;
- err = msleep_interruptible(100);
- if (err)
- return err;
+ if (msleep_interruptible(25))
+ return -ERESTARTSYS;
if (time_after(start_time, wait_until))
return -ETIMEDOUT;
@@ -228,7 +294,7 @@ nfp_nsp_wait_reg(struct nfp_cpp *cpp, u64 *reg,
*
* Return: 0 for success with no result
*
- * 1..255 for NSP completion with a result code
+ * positive value for NSP completion with a result code
*
* -EAGAIN if the NSP is not yet present
* -ENODEV if the NSP is not a supported model
@@ -239,7 +305,7 @@ nfp_nsp_wait_reg(struct nfp_cpp *cpp, u64 *reg,
static int nfp_nsp_command(struct nfp_nsp *state, u16 code, u32 option,
u32 buff_cpp, u64 buff_addr)
{
- u64 reg, nsp_base, nsp_buffer, nsp_status, nsp_command;
+ u64 reg, ret_val, nsp_base, nsp_buffer, nsp_status, nsp_command;
struct nfp_cpp *cpp = state->cpp;
u32 nsp_cpp;
int err;
@@ -292,18 +358,20 @@ static int nfp_nsp_command(struct nfp_nsp *state, u16 code, u32 option,
return err;
}
+ err = nfp_cpp_readq(cpp, nsp_cpp, nsp_command, &ret_val);
+ if (err < 0)
+ return err;
+ ret_val = FIELD_GET(NSP_COMMAND_OPTION, ret_val);
+
err = FIELD_GET(NSP_STATUS_RESULT, reg);
if (err) {
- nfp_warn(cpp, "Result (error) code set: %d command: %d\n",
- -err, code);
+ nfp_warn(cpp, "Result (error) code set: %d (%d) command: %d\n",
+ -err, (int)ret_val, code);
+ nfp_nsp_print_extended_error(state, ret_val);
return -err;
}
- err = nfp_cpp_readq(cpp, nsp_cpp, nsp_command, ®);
- if (err < 0)
- return err;
-
- return FIELD_GET(NSP_COMMAND_OPTION, reg);
+ return ret_val;
}
static int nfp_nsp_command_buf(struct nfp_nsp *nsp, u16 code, u32 option,
@@ -380,9 +448,10 @@ int nfp_nsp_wait(struct nfp_nsp *state)
if (err != -EAGAIN)
break;
- err = msleep_interruptible(100);
- if (err)
+ if (msleep_interruptible(25)) {
+ err = -ERESTARTSYS;
break;
+ }
if (time_after(start_time, wait_until)) {
err = -ETIMEDOUT;
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h
new file mode 100644
index 0000000..7d34ff1
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h
@@ -0,0 +1,150 @@
+/*
+ * Copyright (C) 2015-2017 Netronome Systems, Inc.
+ *
+ * This software is dual licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree or the BSD 2-Clause License provided below. You have the
+ * option to license this software under the complete terms of either license.
+ *
+ * The BSD 2-Clause License:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * 2. Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef NSP_NSP_H
+#define NSP_NSP_H 1
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+
+struct firmware;
+struct nfp_cpp;
+struct nfp_nsp;
+
+struct nfp_nsp *nfp_nsp_open(struct nfp_cpp *cpp);
+void nfp_nsp_close(struct nfp_nsp *state);
+u16 nfp_nsp_get_abi_ver_major(struct nfp_nsp *state);
+u16 nfp_nsp_get_abi_ver_minor(struct nfp_nsp *state);
+int nfp_nsp_wait(struct nfp_nsp *state);
+int nfp_nsp_device_soft_reset(struct nfp_nsp *state);
+int nfp_nsp_load_fw(struct nfp_nsp *state, const struct firmware *fw);
+
+enum nfp_eth_interface {
+ NFP_INTERFACE_NONE = 0,
+ NFP_INTERFACE_SFP = 1,
+ NFP_INTERFACE_SFPP = 10,
+ NFP_INTERFACE_SFP28 = 28,
+ NFP_INTERFACE_QSFP = 40,
+ NFP_INTERFACE_CXP = 100,
+ NFP_INTERFACE_QSFP28 = 112,
+};
+
+enum nfp_eth_media {
+ NFP_MEDIA_DAC_PASSIVE = 0,
+ NFP_MEDIA_DAC_ACTIVE,
+ NFP_MEDIA_FIBRE,
+};
+
+enum nfp_eth_aneg {
+ NFP_ANEG_AUTO = 0,
+ NFP_ANEG_SEARCH,
+ NFP_ANEG_25G_CONSORTIUM,
+ NFP_ANEG_25G_IEEE,
+ NFP_ANEG_DISABLED,
+};
+
+/**
+ * struct nfp_eth_table - ETH table information
+ * @count: number of table entries
+ * @ports: table of ports
+ *
+ * @eth_index: port index according to legacy ethX numbering
+ * @index: chip-wide first channel index
+ * @nbi: NBI index
+ * @base: first channel index (within NBI)
+ * @lanes: number of channels
+ * @speed: interface speed (in Mbps)
+ * @interface: interface (module) plugged in
+ * @media: media type of the @interface
+ * @aneg: auto negotiation mode
+ * @mac_addr: interface MAC address
+ * @label_port: port id
+ * @label_subport: id of interface within port (for split ports)
+ * @enabled: is enabled?
+ * @tx_enabled: is TX enabled?
+ * @rx_enabled: is RX enabled?
+ * @override_changed: is media reconfig pending?
+ *
+ * @port_type: one of %PORT_* defines for ethtool
+ * @is_split: is interface part of a split port
+ */
+struct nfp_eth_table {
+ unsigned int count;
+ struct nfp_eth_table_port {
+ unsigned int eth_index;
+ unsigned int index;
+ unsigned int nbi;
+ unsigned int base;
+ unsigned int lanes;
+ unsigned int speed;
+
+ unsigned int interface;
+ enum nfp_eth_media media;
+
+ enum nfp_eth_aneg aneg;
+
+ u8 mac_addr[ETH_ALEN];
+
+ u8 label_port;
+ u8 label_subport;
+
+ bool enabled;
+ bool tx_enabled;
+ bool rx_enabled;
+
+ bool override_changed;
+
+ /* Computed fields */
+ u8 port_type;
+
+ bool is_split;
+ } ports[0];
+};
+
+struct nfp_eth_table *nfp_eth_read_ports(struct nfp_cpp *cpp);
+struct nfp_eth_table *
+__nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp);
+
+int nfp_eth_set_mod_enable(struct nfp_cpp *cpp, unsigned int idx, bool enable);
+int nfp_eth_set_configured(struct nfp_cpp *cpp, unsigned int idx,
+ bool configed);
+
+struct nfp_nsp *nfp_eth_config_start(struct nfp_cpp *cpp, unsigned int idx);
+int nfp_eth_config_commit_end(struct nfp_nsp *nsp);
+void nfp_eth_config_cleanup_end(struct nfp_nsp *nsp);
+
+int __nfp_eth_set_aneg(struct nfp_nsp *nsp, enum nfp_eth_aneg mode);
+int __nfp_eth_set_speed(struct nfp_nsp *nsp, unsigned int speed);
+int __nfp_eth_set_split(struct nfp_nsp *nsp, unsigned int lanes);
+
+#endif
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c
index 1ece1f8..639438d 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c
@@ -43,13 +43,13 @@
#include <linux/module.h>
#include "nfp.h"
-#include "nfp_nsp_eth.h"
+#include "nfp_nsp.h"
#include "nfp6000/nfp6000.h"
#define NSP_ETH_NBI_PORT_COUNT 24
#define NSP_ETH_MAX_COUNT (2 * NSP_ETH_NBI_PORT_COUNT)
#define NSP_ETH_TABLE_SIZE (NSP_ETH_MAX_COUNT * \
- sizeof(struct eth_table_entry))
+ sizeof(union eth_table_entry))
#define NSP_ETH_PORT_LANES GENMASK_ULL(3, 0)
#define NSP_ETH_PORT_INDEX GENMASK_ULL(15, 8)
@@ -58,14 +58,32 @@
#define NSP_ETH_PORT_LANES_MASK cpu_to_le64(NSP_ETH_PORT_LANES)
+#define NSP_ETH_STATE_CONFIGURED BIT_ULL(0)
#define NSP_ETH_STATE_ENABLED BIT_ULL(1)
#define NSP_ETH_STATE_TX_ENABLED BIT_ULL(2)
#define NSP_ETH_STATE_RX_ENABLED BIT_ULL(3)
#define NSP_ETH_STATE_RATE GENMASK_ULL(11, 8)
+#define NSP_ETH_STATE_INTERFACE GENMASK_ULL(19, 12)
+#define NSP_ETH_STATE_MEDIA GENMASK_ULL(21, 20)
+#define NSP_ETH_STATE_OVRD_CHNG BIT_ULL(22)
+#define NSP_ETH_STATE_ANEG GENMASK_ULL(25, 23)
+#define NSP_ETH_CTRL_CONFIGURED BIT_ULL(0)
#define NSP_ETH_CTRL_ENABLED BIT_ULL(1)
#define NSP_ETH_CTRL_TX_ENABLED BIT_ULL(2)
#define NSP_ETH_CTRL_RX_ENABLED BIT_ULL(3)
+#define NSP_ETH_CTRL_SET_RATE BIT_ULL(4)
+#define NSP_ETH_CTRL_SET_LANES BIT_ULL(5)
+#define NSP_ETH_CTRL_SET_ANEG BIT_ULL(6)
+
+enum nfp_eth_raw {
+ NSP_ETH_RAW_PORT = 0,
+ NSP_ETH_RAW_STATE,
+ NSP_ETH_RAW_MAC,
+ NSP_ETH_RAW_CONTROL,
+
+ NSP_ETH_NUM_RAW
+};
enum nfp_eth_rate {
RATE_INVALID = 0,
@@ -76,29 +94,49 @@ enum nfp_eth_rate {
RATE_25G,
};
-struct eth_table_entry {
- __le64 port;
- __le64 state;
- u8 mac_addr[6];
- u8 resv[2];
- __le64 control;
+union eth_table_entry {
+ struct {
+ __le64 port;
+ __le64 state;
+ u8 mac_addr[6];
+ u8 resv[2];
+ __le64 control;
+ };
+ __le64 raw[NSP_ETH_NUM_RAW];
};
-static unsigned int nfp_eth_rate(enum nfp_eth_rate rate)
+static const struct {
+ enum nfp_eth_rate rate;
+ unsigned int speed;
+} nsp_eth_rate_tbl[] = {
+ { RATE_INVALID, 0, },
+ { RATE_10M, SPEED_10, },
+ { RATE_100M, SPEED_100, },
+ { RATE_1G, SPEED_1000, },
+ { RATE_10G, SPEED_10000, },
+ { RATE_25G, SPEED_25000, },
+};
+
+static unsigned int nfp_eth_rate2speed(enum nfp_eth_rate rate)
{
- unsigned int rate_xlate[] = {
- [RATE_INVALID] = 0,
- [RATE_10M] = SPEED_10,
- [RATE_100M] = SPEED_100,
- [RATE_1G] = SPEED_1000,
- [RATE_10G] = SPEED_10000,
- [RATE_25G] = SPEED_25000,
- };
+ int i;
- if (rate >= ARRAY_SIZE(rate_xlate))
- return 0;
+ for (i = 0; i < ARRAY_SIZE(nsp_eth_rate_tbl); i++)
+ if (nsp_eth_rate_tbl[i].rate == rate)
+ return nsp_eth_rate_tbl[i].speed;
- return rate_xlate[rate];
+ return 0;
+}
+
+static unsigned int nfp_eth_speed2rate(unsigned int speed)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(nsp_eth_rate_tbl); i++)
+ if (nsp_eth_rate_tbl[i].speed == speed)
+ return nsp_eth_rate_tbl[i].rate;
+
+ return RATE_INVALID;
}
static void nfp_eth_copy_mac_reverse(u8 *dst, const u8 *src)
@@ -110,8 +148,8 @@ static void nfp_eth_copy_mac_reverse(u8 *dst, const u8 *src)
}
static void
-nfp_eth_port_translate(const struct eth_table_entry *src, unsigned int index,
- struct nfp_eth_table_port *dst)
+nfp_eth_port_translate(struct nfp_nsp *nsp, const union eth_table_entry *src,
+ unsigned int index, struct nfp_eth_table_port *dst)
{
unsigned int rate;
u64 port, state;
@@ -129,14 +167,60 @@ nfp_eth_port_translate(const struct eth_table_entry *src, unsigned int index,
dst->tx_enabled = FIELD_GET(NSP_ETH_STATE_TX_ENABLED, state);
dst->rx_enabled = FIELD_GET(NSP_ETH_STATE_RX_ENABLED, state);
- rate = nfp_eth_rate(FIELD_GET(NSP_ETH_STATE_RATE, state));
+ rate = nfp_eth_rate2speed(FIELD_GET(NSP_ETH_STATE_RATE, state));
dst->speed = dst->lanes * rate;
+ dst->interface = FIELD_GET(NSP_ETH_STATE_INTERFACE, state);
+ dst->media = FIELD_GET(NSP_ETH_STATE_MEDIA, state);
+
nfp_eth_copy_mac_reverse(dst->mac_addr, src->mac_addr);
- snprintf(dst->label, sizeof(dst->label) - 1, "%llu.%llu",
- FIELD_GET(NSP_ETH_PORT_PHYLABEL, port),
- FIELD_GET(NSP_ETH_PORT_LABEL, port));
+ dst->label_port = FIELD_GET(NSP_ETH_PORT_PHYLABEL, port);
+ dst->label_subport = FIELD_GET(NSP_ETH_PORT_LABEL, port);
+
+ if (nfp_nsp_get_abi_ver_minor(nsp) < 17)
+ return;
+
+ dst->override_changed = FIELD_GET(NSP_ETH_STATE_OVRD_CHNG, state);
+ dst->aneg = FIELD_GET(NSP_ETH_STATE_ANEG, state);
+}
+
+static void
+nfp_eth_mark_split_ports(struct nfp_cpp *cpp, struct nfp_eth_table *table)
+{
+ unsigned int i, j;
+
+ for (i = 0; i < table->count; i++)
+ for (j = 0; j < table->count; j++) {
+ if (i == j)
+ continue;
+ if (table->ports[i].label_port !=
+ table->ports[j].label_port)
+ continue;
+ if (table->ports[i].label_subport ==
+ table->ports[j].label_subport)
+ nfp_warn(cpp,
+ "Port %d subport %d is a duplicate\n",
+ table->ports[i].label_port,
+ table->ports[i].label_subport);
+
+ table->ports[i].is_split = true;
+ break;
+ }
+}
+
+static void
+nfp_eth_calc_port_type(struct nfp_cpp *cpp, struct nfp_eth_table_port *entry)
+{
+ if (entry->interface == NFP_INTERFACE_NONE) {
+ entry->port_type = PORT_NONE;
+ return;
+ }
+
+ if (entry->media == NFP_MEDIA_FIBRE)
+ entry->port_type = PORT_FIBRE;
+ else
+ entry->port_type = PORT_DA;
}
/**
@@ -166,10 +250,9 @@ struct nfp_eth_table *nfp_eth_read_ports(struct nfp_cpp *cpp)
struct nfp_eth_table *
__nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp)
{
- struct eth_table_entry *entries;
+ union eth_table_entry *entries;
struct nfp_eth_table *table;
- unsigned int cnt;
- int i, j, ret;
+ int i, j, ret, cnt = 0;
entries = kzalloc(NSP_ETH_TABLE_SIZE, GFP_KERNEL);
if (!entries)
@@ -178,34 +261,121 @@ __nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp)
ret = nfp_nsp_read_eth_table(nsp, entries, NSP_ETH_TABLE_SIZE);
if (ret < 0) {
nfp_err(cpp, "reading port table failed %d\n", ret);
- kfree(entries);
- return NULL;
+ goto err;
}
- /* Some versions of flash will give us 0 instead of port count */
- cnt = ret;
- if (!cnt) {
- for (i = 0; i < NSP_ETH_MAX_COUNT; i++)
- if (entries[i].port & NSP_ETH_PORT_LANES_MASK)
- cnt++;
+ for (i = 0; i < NSP_ETH_MAX_COUNT; i++)
+ if (entries[i].port & NSP_ETH_PORT_LANES_MASK)
+ cnt++;
+
+ /* Some versions of flash will give us 0 instead of port count.
+ * For those that give a port count, verify it against the value
+ * calculated above.
+ */
+ if (ret && ret != cnt) {
+ nfp_err(cpp, "table entry count reported (%d) does not match entries present (%d)\n",
+ ret, cnt);
+ goto err;
}
table = kzalloc(sizeof(*table) +
sizeof(struct nfp_eth_table_port) * cnt, GFP_KERNEL);
- if (!table) {
- kfree(entries);
- return NULL;
- }
+ if (!table)
+ goto err;
table->count = cnt;
for (i = 0, j = 0; i < NSP_ETH_MAX_COUNT; i++)
if (entries[i].port & NSP_ETH_PORT_LANES_MASK)
- nfp_eth_port_translate(&entries[i], i,
+ nfp_eth_port_translate(nsp, &entries[i], i,
&table->ports[j++]);
+ nfp_eth_mark_split_ports(cpp, table);
+ for (i = 0; i < table->count; i++)
+ nfp_eth_calc_port_type(cpp, &table->ports[i]);
+
kfree(entries);
return table;
+
+err:
+ kfree(entries);
+ return NULL;
+}
+
+struct nfp_nsp *nfp_eth_config_start(struct nfp_cpp *cpp, unsigned int idx)
+{
+ union eth_table_entry *entries;
+ struct nfp_nsp *nsp;
+ int ret;
+
+ entries = kzalloc(NSP_ETH_TABLE_SIZE, GFP_KERNEL);
+ if (!entries)
+ return ERR_PTR(-ENOMEM);
+
+ nsp = nfp_nsp_open(cpp);
+ if (IS_ERR(nsp)) {
+ kfree(entries);
+ return nsp;
+ }
+
+ ret = nfp_nsp_read_eth_table(nsp, entries, NSP_ETH_TABLE_SIZE);
+ if (ret < 0) {
+ nfp_err(cpp, "reading port table failed %d\n", ret);
+ goto err;
+ }
+
+ if (!(entries[idx].port & NSP_ETH_PORT_LANES_MASK)) {
+ nfp_warn(cpp, "trying to set port state on disabled port %d\n",
+ idx);
+ goto err;
+ }
+
+ nfp_nsp_config_set_state(nsp, entries, idx);
+ return nsp;
+
+err:
+ nfp_nsp_close(nsp);
+ kfree(entries);
+ return ERR_PTR(-EIO);
+}
+
+void nfp_eth_config_cleanup_end(struct nfp_nsp *nsp)
+{
+ union eth_table_entry *entries = nfp_nsp_config_entries(nsp);
+
+ nfp_nsp_config_set_modified(nsp, false);
+ nfp_nsp_config_clear_state(nsp);
+ nfp_nsp_close(nsp);
+ kfree(entries);
+}
+
+/**
+ * nfp_eth_config_commit_end() - perform recorded configuration changes
+ * @nsp: NFP NSP handle returned from nfp_eth_config_start()
+ *
+ * Perform the configuration which was requested with __nfp_eth_set_*()
+ * helpers and recorded in @nsp state. If device was already configured
+ * as requested or no __nfp_eth_set_*() operations were made no NSP command
+ * will be performed.
+ *
+ * Return:
+ * 0 - configuration successful;
+ * 1 - no changes were needed;
+ * -ERRNO - configuration failed.
+ */
+int nfp_eth_config_commit_end(struct nfp_nsp *nsp)
+{
+ union eth_table_entry *entries = nfp_nsp_config_entries(nsp);
+ int ret = 1;
+
+ if (nfp_nsp_config_modified(nsp)) {
+ ret = nfp_nsp_write_eth_table(nsp, entries, NSP_ETH_TABLE_SIZE);
+ ret = ret < 0 ? ret : 0;
+ }
+
+ nfp_eth_config_cleanup_end(nsp);
+
+ return ret;
}
/**
@@ -221,50 +391,158 @@ __nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp)
*/
int nfp_eth_set_mod_enable(struct nfp_cpp *cpp, unsigned int idx, bool enable)
{
- struct eth_table_entry *entries;
+ union eth_table_entry *entries;
struct nfp_nsp *nsp;
u64 reg;
- int ret;
- entries = kzalloc(NSP_ETH_TABLE_SIZE, GFP_KERNEL);
- if (!entries)
- return -ENOMEM;
-
- nsp = nfp_nsp_open(cpp);
- if (IS_ERR(nsp)) {
- kfree(entries);
+ nsp = nfp_eth_config_start(cpp, idx);
+ if (IS_ERR(nsp))
return PTR_ERR(nsp);
- }
- ret = nfp_nsp_read_eth_table(nsp, entries, NSP_ETH_TABLE_SIZE);
- if (ret < 0) {
- nfp_err(cpp, "reading port table failed %d\n", ret);
- goto exit_close_nsp;
- }
-
- if (!(entries[idx].port & NSP_ETH_PORT_LANES_MASK)) {
- nfp_warn(cpp, "trying to set port state on disabled port %d\n",
- idx);
- ret = -EINVAL;
- goto exit_close_nsp;
- }
+ entries = nfp_nsp_config_entries(nsp);
/* Check if we are already in requested state */
reg = le64_to_cpu(entries[idx].state);
- if (enable == FIELD_GET(NSP_ETH_CTRL_ENABLED, reg)) {
- ret = 0;
- goto exit_close_nsp;
+ if (enable != FIELD_GET(NSP_ETH_CTRL_ENABLED, reg)) {
+ reg = le64_to_cpu(entries[idx].control);
+ reg &= ~NSP_ETH_CTRL_ENABLED;
+ reg |= FIELD_PREP(NSP_ETH_CTRL_ENABLED, enable);
+ entries[idx].control = cpu_to_le64(reg);
+
+ nfp_nsp_config_set_modified(nsp, true);
}
- reg = le64_to_cpu(entries[idx].control);
- reg &= ~NSP_ETH_CTRL_ENABLED;
- reg |= FIELD_PREP(NSP_ETH_CTRL_ENABLED, enable);
- entries[idx].control = cpu_to_le64(reg);
+ return nfp_eth_config_commit_end(nsp);
+}
- ret = nfp_nsp_write_eth_table(nsp, entries, NSP_ETH_TABLE_SIZE);
-exit_close_nsp:
- nfp_nsp_close(nsp);
- kfree(entries);
+/**
+ * nfp_eth_set_configured() - set PHY module configured control bit
+ * @cpp: NFP CPP handle
+ * @idx: NFP chip-wide port index
+ * @configed: Desired state
+ *
+ * Set the ifup/ifdown state on the PHY.
+ *
+ * Return: 0 or -ERRNO.
+ */
+int nfp_eth_set_configured(struct nfp_cpp *cpp, unsigned int idx, bool configed)
+{
+ union eth_table_entry *entries;
+ struct nfp_nsp *nsp;
+ u64 reg;
- return ret < 0 ? ret : 0;
+ nsp = nfp_eth_config_start(cpp, idx);
+ if (IS_ERR(nsp))
+ return PTR_ERR(nsp);
+
+ entries = nfp_nsp_config_entries(nsp);
+
+ /* Check if we are already in requested state */
+ reg = le64_to_cpu(entries[idx].state);
+ if (configed != FIELD_GET(NSP_ETH_STATE_CONFIGURED, reg)) {
+ reg = le64_to_cpu(entries[idx].control);
+ reg &= ~NSP_ETH_CTRL_CONFIGURED;
+ reg |= FIELD_PREP(NSP_ETH_CTRL_CONFIGURED, configed);
+ entries[idx].control = cpu_to_le64(reg);
+
+ nfp_nsp_config_set_modified(nsp, true);
+ }
+
+ return nfp_eth_config_commit_end(nsp);
+}
+
+/* Force inline, FIELD_* macroes require masks to be compilation-time known */
+static __always_inline int
+nfp_eth_set_bit_config(struct nfp_nsp *nsp, unsigned int raw_idx,
+ const u64 mask, unsigned int val, const u64 ctrl_bit)
+{
+ union eth_table_entry *entries = nfp_nsp_config_entries(nsp);
+ unsigned int idx = nfp_nsp_config_idx(nsp);
+ u64 reg;
+
+ /* Note: set features were added in ABI 0.14 but the error
+ * codes were initially not populated correctly.
+ */
+ if (nfp_nsp_get_abi_ver_minor(nsp) < 17) {
+ nfp_err(nfp_nsp_cpp(nsp),
+ "set operations not supported, please update flash\n");
+ return -EOPNOTSUPP;
+ }
+
+ /* Check if we are already in requested state */
+ reg = le64_to_cpu(entries[idx].raw[raw_idx]);
+ if (val == FIELD_GET(mask, reg))
+ return 0;
+
+ reg &= ~mask;
+ reg |= FIELD_PREP(mask, val);
+ entries[idx].raw[raw_idx] = cpu_to_le64(reg);
+
+ entries[idx].control |= cpu_to_le64(ctrl_bit);
+
+ nfp_nsp_config_set_modified(nsp, true);
+
+ return 0;
+}
+
+/**
+ * __nfp_eth_set_aneg() - set PHY autonegotiation control bit
+ * @nsp: NFP NSP handle returned from nfp_eth_config_start()
+ * @mode: Desired autonegotiation mode
+ *
+ * Allow/disallow PHY module to advertise/perform autonegotiation.
+ * Will write to hwinfo overrides in the flash (persistent config).
+ *
+ * Return: 0 or -ERRNO.
+ */
+int __nfp_eth_set_aneg(struct nfp_nsp *nsp, enum nfp_eth_aneg mode)
+{
+ return nfp_eth_set_bit_config(nsp, NSP_ETH_RAW_STATE,
+ NSP_ETH_STATE_ANEG, mode,
+ NSP_ETH_CTRL_SET_ANEG);
+}
+
+/**
+ * __nfp_eth_set_speed() - set interface speed/rate
+ * @nsp: NFP NSP handle returned from nfp_eth_config_start()
+ * @speed: Desired speed (per lane)
+ *
+ * Set lane speed. Provided @speed value should be subport speed divided
+ * by number of lanes this subport is spanning (i.e. 10000 for 40G, 25000 for
+ * 50G, etc.)
+ * Will write to hwinfo overrides in the flash (persistent config).
+ *
+ * Return: 0 or -ERRNO.
+ */
+int __nfp_eth_set_speed(struct nfp_nsp *nsp, unsigned int speed)
+{
+ enum nfp_eth_rate rate;
+
+ rate = nfp_eth_speed2rate(speed);
+ if (rate == RATE_INVALID) {
+ nfp_warn(nfp_nsp_cpp(nsp),
+ "could not find matching lane rate for speed %u\n",
+ speed);
+ return -EINVAL;
+ }
+
+ return nfp_eth_set_bit_config(nsp, NSP_ETH_RAW_STATE,
+ NSP_ETH_STATE_RATE, rate,
+ NSP_ETH_CTRL_SET_RATE);
+}
+
+/**
+ * __nfp_eth_set_split() - set interface lane split
+ * @nsp: NFP NSP handle returned from nfp_eth_config_start()
+ * @lanes: Desired lanes per port
+ *
+ * Set number of lanes in the port.
+ * Will write to hwinfo overrides in the flash (persistent config).
+ *
+ * Return: 0 or -ERRNO.
+ */
+int __nfp_eth_set_split(struct nfp_nsp *nsp, unsigned int lanes)
+{
+ return nfp_eth_set_bit_config(nsp, NSP_ETH_RAW_PORT, NSP_ETH_PORT_LANES,
+ lanes, NSP_ETH_CTRL_SET_LANES);
}
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.h
deleted file mode 100644
index edf703d..0000000
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.h
+++ /dev/null
@@ -1,81 +0,0 @@
-/*
- * Copyright (C) 2015-2017 Netronome Systems, Inc.
- *
- * This software is dual licensed under the GNU General License Version 2,
- * June 1991 as shown in the file COPYING in the top-level directory of this
- * source tree or the BSD 2-Clause License provided below. You have the
- * option to license this software under the complete terms of either license.
- *
- * The BSD 2-Clause License:
- *
- * Redistribution and use in source and binary forms, with or
- * without modification, are permitted provided that the following
- * conditions are met:
- *
- * 1. Redistributions of source code must retain the above
- * copyright notice, this list of conditions and the following
- * disclaimer.
- *
- * 2. Redistributions in binary form must reproduce the above
- * copyright notice, this list of conditions and the following
- * disclaimer in the documentation and/or other materials
- * provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#ifndef NSP_NSP_ETH_H
-#define NSP_NSP_ETH_H 1
-
-#include <linux/types.h>
-#include <linux/if_ether.h>
-
-/**
- * struct nfp_eth_table - ETH table information
- * @count: number of table entries
- * @ports: table of ports
- *
- * @eth_index: port index according to legacy ethX numbering
- * @index: chip-wide first channel index
- * @nbi: NBI index
- * @base: first channel index (within NBI)
- * @lanes: number of channels
- * @speed: interface speed (in Mbps)
- * @mac_addr: interface MAC address
- * @label: interface id string
- * @enabled: is enabled?
- * @tx_enabled: is TX enabled?
- * @rx_enabled: is RX enabled?
- */
-struct nfp_eth_table {
- unsigned int count;
- struct nfp_eth_table_port {
- unsigned int eth_index;
- unsigned int index;
- unsigned int nbi;
- unsigned int base;
- unsigned int lanes;
- unsigned int speed;
-
- u8 mac_addr[ETH_ALEN];
- char label[8];
-
- bool enabled;
- bool tx_enabled;
- bool rx_enabled;
- } ports[0];
-};
-
-struct nfp_eth_table *nfp_eth_read_ports(struct nfp_cpp *cpp);
-struct nfp_eth_table *
-__nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp);
-int nfp_eth_set_mod_enable(struct nfp_cpp *cpp, unsigned int idx, bool enable);
-
-#endif
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c
index a2850344..2d15a7c9 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c
@@ -45,6 +45,13 @@
#include "nfp_cpp.h"
#include "nfp6000/nfp6000.h"
+#define NFP_RESOURCE_TBL_TARGET NFP_CPP_TARGET_MU
+#define NFP_RESOURCE_TBL_BASE 0x8100000000ULL
+
+/* NFP Resource Table self-identifier */
+#define NFP_RESOURCE_TBL_NAME "nfp.res"
+#define NFP_RESOURCE_TBL_KEY 0x00000000 /* Special key for entry 0 */
+
#define NFP_RESOURCE_ENTRY_NAME_SZ 8
/**
@@ -100,9 +107,11 @@ static int nfp_cpp_resource_find(struct nfp_cpp *cpp, struct nfp_resource *res)
strncpy(name_pad, res->name, sizeof(name_pad));
/* Search for a matching entry */
- key = NFP_RESOURCE_TBL_KEY;
- if (memcmp(name_pad, NFP_RESOURCE_TBL_NAME "\0\0\0\0\0\0\0\0", 8))
- key = crc32_posix(name_pad, sizeof(name_pad));
+ if (!memcmp(name_pad, NFP_RESOURCE_TBL_NAME "\0\0\0\0\0\0\0\0", 8)) {
+ nfp_err(cpp, "Grabbing device lock not supported\n");
+ return -EOPNOTSUPP;
+ }
+ key = crc32_posix(name_pad, sizeof(name_pad));
for (i = 0; i < NFP_RESOURCE_TBL_ENTRIES; i++) {
u64 addr = NFP_RESOURCE_TBL_BASE +
diff --git a/drivers/net/ethernet/nuvoton/w90p910_ether.c b/drivers/net/ethernet/nuvoton/w90p910_ether.c
index 9709c8c..159564d 100644
--- a/drivers/net/ethernet/nuvoton/w90p910_ether.c
+++ b/drivers/net/ethernet/nuvoton/w90p910_ether.c
@@ -152,7 +152,6 @@ struct w90p910_ether {
struct tran_pdesc *tdesc;
dma_addr_t rdesc_phys;
dma_addr_t tdesc_phys;
- struct net_device_stats stats;
struct platform_device *pdev;
struct resource *res;
struct sk_buff *skb;
@@ -584,15 +583,6 @@ static int w90p910_ether_close(struct net_device *dev)
return 0;
}
-static struct net_device_stats *w90p910_ether_stats(struct net_device *dev)
-{
- struct w90p910_ether *ether;
-
- ether = netdev_priv(dev);
-
- return ðer->stats;
-}
-
static int w90p910_send_frame(struct net_device *dev,
unsigned char *data, int length)
{
@@ -671,10 +661,10 @@ static irqreturn_t w90p910_tx_interrupt(int irq, void *dev_id)
ether->finish_tx = 0;
if (txbd->sl & TXDS_TXCP) {
- ether->stats.tx_packets++;
- ether->stats.tx_bytes += txbd->sl & 0xFFFF;
+ dev->stats.tx_packets++;
+ dev->stats.tx_bytes += txbd->sl & 0xFFFF;
} else {
- ether->stats.tx_errors++;
+ dev->stats.tx_errors++;
}
txbd->sl = 0x0;
@@ -730,7 +720,7 @@ static void netdev_rx(struct net_device *dev)
data = ether->rdesc->recv_buf[ether->cur_rx];
skb = netdev_alloc_skb(dev, length + 2);
if (!skb) {
- ether->stats.rx_dropped++;
+ dev->stats.rx_dropped++;
return;
}
@@ -738,24 +728,24 @@ static void netdev_rx(struct net_device *dev)
skb_put(skb, length);
skb_copy_to_linear_data(skb, data, length);
skb->protocol = eth_type_trans(skb, dev);
- ether->stats.rx_packets++;
- ether->stats.rx_bytes += length;
+ dev->stats.rx_packets++;
+ dev->stats.rx_bytes += length;
netif_rx(skb);
} else {
- ether->stats.rx_errors++;
+ dev->stats.rx_errors++;
if (status & RXDS_RP) {
dev_err(&pdev->dev, "rx runt err\n");
- ether->stats.rx_length_errors++;
+ dev->stats.rx_length_errors++;
} else if (status & RXDS_CRCE) {
dev_err(&pdev->dev, "rx crc err\n");
- ether->stats.rx_crc_errors++;
+ dev->stats.rx_crc_errors++;
} else if (status & RXDS_ALIE) {
dev_err(&pdev->dev, "rx alignment err\n");
- ether->stats.rx_frame_errors++;
+ dev->stats.rx_frame_errors++;
} else if (status & RXDS_PTLE) {
dev_err(&pdev->dev, "rx longer err\n");
- ether->stats.rx_over_errors++;
+ dev->stats.rx_over_errors++;
}
}
@@ -912,7 +902,6 @@ static const struct net_device_ops w90p910_ether_netdev_ops = {
.ndo_open = w90p910_ether_open,
.ndo_stop = w90p910_ether_close,
.ndo_start_xmit = w90p910_ether_start_xmit,
- .ndo_get_stats = w90p910_ether_stats,
.ndo_set_rx_mode = w90p910_ether_set_multicast_list,
.ndo_set_mac_address = w90p910_set_mac_address,
.ndo_do_ioctl = w90p910_ether_ioctl,
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
index 7b43a3b..3dd9734 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
@@ -1375,13 +1375,8 @@ netxen_receive_peg_ready(struct netxen_adapter *adapter)
} while (--retries);
- if (!retries) {
- printk(KERN_ERR "Receive Peg initialization not "
- "complete, state: 0x%x.\n", val);
- return -EIO;
- }
-
- return 0;
+ pr_err("Receive Peg initialization not complete, state: 0x%x.\n", val);
+ return -EIO;
}
int netxen_init_firmware(struct netxen_adapter *adapter)
diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index 00c17fa..4896ee0 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -51,7 +51,19 @@
#include "qed_hsi.h"
extern const struct qed_common_ops qed_common_ops_pass;
-#define DRV_MODULE_VERSION "8.10.10.20"
+
+#define QED_MAJOR_VERSION 8
+#define QED_MINOR_VERSION 10
+#define QED_REVISION_VERSION 10
+#define QED_ENGINEERING_VERSION 21
+
+#define QED_VERSION \
+ ((QED_MAJOR_VERSION << 24) | (QED_MINOR_VERSION << 16) | \
+ (QED_REVISION_VERSION << 8) | QED_ENGINEERING_VERSION)
+
+#define STORM_FW_VERSION \
+ ((FW_MAJOR_VERSION << 24) | (FW_MINOR_VERSION << 16) | \
+ (FW_REVISION_VERSION << 8) | FW_ENGINEERING_VERSION)
#define MAX_HWFNS_PER_DEVICE (4)
#define NAME_SIZE 16
@@ -59,8 +71,6 @@ extern const struct qed_common_ops qed_common_ops_pass;
#define QED_WFQ_UNIT 100
-#define ISCSI_BDQ_ID(_port_id) (_port_id)
-#define FCOE_BDQ_ID(_port_id) ((_port_id) + 2)
#define QED_WID_SIZE (1024)
#define QED_PF_DEMS_SIZE (4)
@@ -76,6 +86,15 @@ union qed_mcp_protocol_stats;
enum qed_mcp_protocol_type;
/* helpers */
+#define QED_MFW_GET_FIELD(name, field) \
+ (((name) & (field ## _MASK)) >> (field ## _SHIFT))
+
+#define QED_MFW_SET_FIELD(name, field, value) \
+ do { \
+ (name) &= ~((field ## _MASK) << (field ## _SHIFT)); \
+ (name) |= (((value) << (field ## _SHIFT)) & (field ## _MASK));\
+ } while (0)
+
static inline u32 qed_db_addr(u32 cid, u32 DEMS)
{
u32 db_addr = FIELD_VALUE(DB_LEGACY_ADDR_DEMS, DEMS) |
@@ -198,6 +217,7 @@ enum qed_resources {
QED_LL2_QUEUE,
QED_CMDQS_CQS,
QED_RDMA_STATS_QUEUE,
+ QED_BDQ,
QED_MAX_RESC,
};
@@ -205,8 +225,9 @@ enum QED_FEATURE {
QED_PF_L2_QUE,
QED_VF,
QED_RDMA_CNQ,
- QED_VF_L2_QUE,
+ QED_ISCSI_CQ,
QED_FCOE_CQ,
+ QED_VF_L2_QUE,
QED_MAX_FEATURES,
};
@@ -219,7 +240,9 @@ enum QED_PORT_MODE {
QED_PORT_MODE_DE_4X20G,
QED_PORT_MODE_DE_1X40G,
QED_PORT_MODE_DE_2X25G,
- QED_PORT_MODE_DE_1X25G
+ QED_PORT_MODE_DE_1X25G,
+ QED_PORT_MODE_DE_4X25G,
+ QED_PORT_MODE_DE_2X10G,
};
enum qed_dev_cap {
@@ -249,9 +272,14 @@ struct qed_hw_info {
RESC_NUM(_p_hwfn, resc))
#define FEAT_NUM(_p_hwfn, resc) ((_p_hwfn)->hw_info.feat_num[resc])
- u8 num_tc;
+ /* Amount of traffic classes HW supports */
+ u8 num_hw_tc;
+
+ /* Amount of TCs which should be active according to DCBx or upper
+ * layer driver configuration.
+ */
+ u8 num_active_tc;
u8 offload_tc;
- u8 non_offload_tc;
u32 concrete_fid;
u16 opaque_fid;
@@ -314,15 +342,19 @@ struct qed_qm_info {
struct init_qm_port_params *qm_port_params;
u16 start_pq;
u8 start_vport;
- u8 pure_lb_pq;
- u8 offload_pq;
- u8 pure_ack_pq;
- u8 ooo_pq;
- u8 vf_queues_offset;
+ u16 pure_lb_pq;
+ u16 offload_pq;
+ u16 low_latency_pq;
+ u16 pure_ack_pq;
+ u16 ooo_pq;
+ u16 first_vf_pq;
+ u16 first_mcos_pq;
+ u16 first_rl_pq;
u16 num_pqs;
u16 num_vf_pqs;
u8 num_vports;
u8 max_phys_tcs_per_port;
+ u8 ooo_tc;
bool pf_rl_en;
bool pf_wfq_en;
bool vport_rl_en;
@@ -353,6 +385,12 @@ struct qed_fw_data {
u32 init_ops_size;
};
+#define DRV_MODULE_VERSION \
+ __stringify(QED_MAJOR_VERSION) "." \
+ __stringify(QED_MINOR_VERSION) "." \
+ __stringify(QED_REVISION_VERSION) "." \
+ __stringify(QED_ENGINEERING_VERSION)
+
struct qed_simd_fp_handler {
void *token;
void (*func)(void *);
@@ -364,7 +402,8 @@ struct qed_hwfn {
#define IS_LEAD_HWFN(edev) (!((edev)->my_id))
u8 rel_pf_id; /* Relative to engine*/
u8 abs_pf_id;
-#define QED_PATH_ID(_p_hwfn) ((_p_hwfn)->abs_pf_id & 1)
+#define QED_PATH_ID(_p_hwfn) \
+ (QED_IS_K2((_p_hwfn)->cdev) ? 0 : ((_p_hwfn)->abs_pf_id & 1))
u8 port_id;
bool b_active;
@@ -523,9 +562,7 @@ struct qed_dev {
u8 dp_level;
char name[NAME_SIZE];
- u8 type;
-#define QED_DEV_TYPE_BB (0 << 0)
-#define QED_DEV_TYPE_AH BIT(0)
+ enum qed_dev_type type;
/* Translate type/revision combo into the proper conditions */
#define QED_IS_BB(dev) ((dev)->type == QED_DEV_TYPE_BB)
#define QED_IS_BB_A0(dev) (QED_IS_BB(dev) && \
@@ -540,6 +577,9 @@ struct qed_dev {
u16 vendor_id;
u16 device_id;
+#define QED_DEV_ID_MASK 0xff00
+#define QED_DEV_ID_MASK_BB 0x1600
+#define QED_DEV_ID_MASK_AH 0x8000
u16 chip_num;
#define CHIP_NUM_MASK 0xffff
@@ -654,10 +694,16 @@ struct qed_dev {
u32 rdma_max_srq_sge;
};
-#define NUM_OF_VFS(dev) MAX_NUM_VFS_BB
-#define NUM_OF_L2_QUEUES(dev) MAX_NUM_L2_QUEUES_BB
-#define NUM_OF_SBS(dev) MAX_SB_PER_PATH_BB
-#define NUM_OF_ENG_PFS(dev) MAX_NUM_PFS_BB
+#define NUM_OF_VFS(dev) (QED_IS_BB(dev) ? MAX_NUM_VFS_BB \
+ : MAX_NUM_VFS_K2)
+#define NUM_OF_L2_QUEUES(dev) (QED_IS_BB(dev) ? MAX_NUM_L2_QUEUES_BB \
+ : MAX_NUM_L2_QUEUES_K2)
+#define NUM_OF_PORTS(dev) (QED_IS_BB(dev) ? MAX_NUM_PORTS_BB \
+ : MAX_NUM_PORTS_K2)
+#define NUM_OF_SBS(dev) (QED_IS_BB(dev) ? MAX_SB_PER_PATH_BB \
+ : MAX_SB_PER_PATH_K2)
+#define NUM_OF_ENG_PFS(dev) (QED_IS_BB(dev) ? MAX_NUM_PFS_BB \
+ : MAX_NUM_PFS_K2)
/**
* @brief qed_concrete_to_sw_fid - get the sw function id from
@@ -693,6 +739,25 @@ void qed_configure_vp_wfq_on_link_change(struct qed_dev *cdev,
u32 min_pf_rate);
void qed_clean_wfq_db(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+int qed_device_num_engines(struct qed_dev *cdev);
+
+#define QED_LEADING_HWFN(dev) (&dev->hwfns[0])
+
+/* Flags for indication of required queues */
+#define PQ_FLAGS_RLS (BIT(0))
+#define PQ_FLAGS_MCOS (BIT(1))
+#define PQ_FLAGS_LB (BIT(2))
+#define PQ_FLAGS_OOO (BIT(3))
+#define PQ_FLAGS_ACK (BIT(4))
+#define PQ_FLAGS_OFLD (BIT(5))
+#define PQ_FLAGS_VFS (BIT(6))
+#define PQ_FLAGS_LLT (BIT(7))
+
+/* physical queue index for cm context intialization */
+u16 qed_get_cm_pq_idx(struct qed_hwfn *p_hwfn, u32 pq_flags);
+u16 qed_get_cm_pq_idx_mcos(struct qed_hwfn *p_hwfn, u8 tc);
+u16 qed_get_cm_pq_idx_vf(struct qed_hwfn *p_hwfn, u16 vf);
+
#define QED_LEADING_HWFN(dev) (&dev->hwfns[0])
/* Other Linux specific common definitions */
@@ -721,5 +786,6 @@ void qed_get_protocol_stats(struct qed_dev *cdev,
enum qed_mcp_protocol_type type,
union qed_mcp_protocol_stats *stats);
int qed_slowpath_irq_req(struct qed_hwfn *hwfn);
+void qed_slowpath_irq_sync(struct qed_hwfn *p_hwfn);
#endif /* _QED_H */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index d42d03d..15ef6eb 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -71,8 +71,7 @@
#define TM_ALIGN BIT(TM_SHIFT)
#define TM_ELEM_SIZE 4
-/* For RoCE we configure to 64K to cover for RoCE max tasks 256K purpose. */
-#define ILT_DEFAULT_HW_P_SIZE (IS_ENABLED(CONFIG_QED_RDMA) ? 4 : 3)
+#define ILT_DEFAULT_HW_P_SIZE 4
#define ILT_PAGE_IN_BYTES(hw_p_size) (1U << ((hw_p_size) + 12))
#define ILT_CFG_REG(cli, reg) PSWRQ2_REG_ ## cli ## _ ## reg ## _RT_OFFSET
@@ -242,8 +241,7 @@ struct qed_cxt_mngr {
static bool src_proto(enum protocol_type type)
{
return type == PROTOCOLID_ISCSI ||
- type == PROTOCOLID_FCOE ||
- type == PROTOCOLID_ROCE;
+ type == PROTOCOLID_FCOE;
}
static bool tm_cid_proto(enum protocol_type type)
@@ -304,16 +302,34 @@ struct qed_tm_iids {
u32 per_vf_tids;
};
-static void qed_cxt_tm_iids(struct qed_cxt_mngr *p_mngr,
+static void qed_cxt_tm_iids(struct qed_hwfn *p_hwfn,
+ struct qed_cxt_mngr *p_mngr,
struct qed_tm_iids *iids)
{
- u32 i, j;
+ bool tm_vf_required = false;
+ bool tm_required = false;
+ int i, j;
- for (i = 0; i < MAX_CONN_TYPES; i++) {
+ /* Timers is a special case -> we don't count how many cids require
+ * timers but what's the max cid that will be used by the timer block.
+ * therefore we traverse in reverse order, and once we hit a protocol
+ * that requires the timers memory, we'll sum all the protocols up
+ * to that one.
+ */
+ for (i = MAX_CONN_TYPES - 1; i >= 0; i--) {
struct qed_conn_type_cfg *p_cfg = &p_mngr->conn_cfg[i];
- if (tm_cid_proto(i)) {
+ if (tm_cid_proto(i) || tm_required) {
+ if (p_cfg->cid_count)
+ tm_required = true;
+
iids->pf_cids += p_cfg->cid_count;
+ }
+
+ if (tm_cid_proto(i) || tm_vf_required) {
+ if (p_cfg->cids_per_vf)
+ tm_vf_required = true;
+
iids->per_vf_cids += p_cfg->cids_per_vf;
}
@@ -422,8 +438,9 @@ static void qed_cxt_set_proto_cid_count(struct qed_hwfn *p_hwfn,
u32 page_sz = p_mgr->clients[ILT_CLI_CDUC].p_size.val;
u32 cxt_size = CONN_CXT_SIZE(p_hwfn);
u32 elems_per_page = ILT_PAGE_IN_BYTES(page_sz) / cxt_size;
+ u32 align = elems_per_page * DQ_RANGE_ALIGN;
- p_conn->cid_count = roundup(p_conn->cid_count, elems_per_page);
+ p_conn->cid_count = roundup(p_conn->cid_count, align);
}
}
@@ -526,7 +543,22 @@ static u32 qed_ilt_get_dynamic_line_cnt(struct qed_hwfn *p_hwfn,
return lines_to_skip;
}
-int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
+static struct qed_ilt_client_cfg *qed_cxt_set_cli(struct qed_ilt_client_cfg
+ *p_cli)
+{
+ p_cli->active = false;
+ p_cli->first.val = 0;
+ p_cli->last.val = 0;
+ return p_cli;
+}
+
+static struct qed_ilt_cli_blk *qed_cxt_set_blk(struct qed_ilt_cli_blk *p_blk)
+{
+ p_blk->total_size = 0;
+ return p_blk;
+}
+
+int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn, u32 *line_count)
{
struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
u32 curr_line, total, i, task_size, line;
@@ -550,7 +582,8 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
p_hwfn->my_id, p_hwfn->p_cxt_mngr->pf_start_line);
/* CDUC */
- p_cli = &p_mngr->clients[ILT_CLI_CDUC];
+ p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_CDUC]);
+
curr_line = p_mngr->pf_start_line;
/* CDUC PF */
@@ -559,7 +592,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
/* get the counters for the CDUC and QM clients */
qed_cxt_cdu_iids(p_mngr, &cdu_iids);
- p_blk = &p_cli->pf_blks[CDUC_BLK];
+ p_blk = qed_cxt_set_blk(&p_cli->pf_blks[CDUC_BLK]);
total = cdu_iids.pf_cids * CONN_CXT_SIZE(p_hwfn);
@@ -573,7 +606,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
ILT_CLI_CDUC);
/* CDUC VF */
- p_blk = &p_cli->vf_blks[CDUC_BLK];
+ p_blk = qed_cxt_set_blk(&p_cli->vf_blks[CDUC_BLK]);
total = cdu_iids.per_vf_cids * CONN_CXT_SIZE(p_hwfn);
qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line,
@@ -587,7 +620,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
ILT_CLI_CDUC);
/* CDUT PF */
- p_cli = &p_mngr->clients[ILT_CLI_CDUT];
+ p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_CDUT]);
p_cli->first.val = curr_line;
/* first the 'working' task memory */
@@ -596,7 +629,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
if (!p_seg || p_seg->count == 0)
continue;
- p_blk = &p_cli->pf_blks[CDUT_SEG_BLK(i)];
+ p_blk = qed_cxt_set_blk(&p_cli->pf_blks[CDUT_SEG_BLK(i)]);
total = p_seg->count * p_mngr->task_type_size[p_seg->type];
qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line, total,
p_mngr->task_type_size[p_seg->type]);
@@ -611,7 +644,8 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
if (!p_seg || p_seg->count == 0)
continue;
- p_blk = &p_cli->pf_blks[CDUT_FL_SEG_BLK(i, PF)];
+ p_blk =
+ qed_cxt_set_blk(&p_cli->pf_blks[CDUT_FL_SEG_BLK(i, PF)]);
if (!p_seg->has_fl_mem) {
/* The segment is active (total size pf 'working'
@@ -656,7 +690,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
/* 'working' memory */
total = p_seg->count * p_mngr->task_type_size[p_seg->type];
- p_blk = &p_cli->vf_blks[CDUT_SEG_BLK(0)];
+ p_blk = qed_cxt_set_blk(&p_cli->vf_blks[CDUT_SEG_BLK(0)]);
qed_ilt_cli_blk_fill(p_cli, p_blk,
curr_line, total,
p_mngr->task_type_size[p_seg->type]);
@@ -665,7 +699,8 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
ILT_CLI_CDUT);
/* 'init' memory */
- p_blk = &p_cli->vf_blks[CDUT_FL_SEG_BLK(0, VF)];
+ p_blk =
+ qed_cxt_set_blk(&p_cli->vf_blks[CDUT_FL_SEG_BLK(0, VF)]);
if (!p_seg->has_fl_mem) {
/* see comment above */
line = p_cli->vf_blks[CDUT_SEG_BLK(0)].start_line;
@@ -693,8 +728,8 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
}
/* QM */
- p_cli = &p_mngr->clients[ILT_CLI_QM];
- p_blk = &p_cli->pf_blks[0];
+ p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_QM]);
+ p_blk = qed_cxt_set_blk(&p_cli->pf_blks[0]);
qed_cxt_qm_iids(p_hwfn, &qm_iids);
total = qed_qm_pf_mem_size(p_hwfn->rel_pf_id, qm_iids.cids,
@@ -718,7 +753,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
p_cli->pf_total_lines = curr_line - p_blk->start_line;
/* SRC */
- p_cli = &p_mngr->clients[ILT_CLI_SRC];
+ p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_SRC]);
qed_cxt_src_iids(p_mngr, &src_iids);
/* Both the PF and VFs searcher connections are stored in the per PF
@@ -732,7 +767,7 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
total = roundup_pow_of_two(local_max);
- p_blk = &p_cli->pf_blks[0];
+ p_blk = qed_cxt_set_blk(&p_cli->pf_blks[0]);
qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line,
total * sizeof(struct src_ent),
sizeof(struct src_ent));
@@ -743,11 +778,11 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
}
/* TM PF */
- p_cli = &p_mngr->clients[ILT_CLI_TM];
- qed_cxt_tm_iids(p_mngr, &tm_iids);
+ p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_TM]);
+ qed_cxt_tm_iids(p_hwfn, p_mngr, &tm_iids);
total = tm_iids.pf_cids + tm_iids.pf_tids_total;
if (total) {
- p_blk = &p_cli->pf_blks[0];
+ p_blk = qed_cxt_set_blk(&p_cli->pf_blks[0]);
qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line,
total * TM_ELEM_SIZE, TM_ELEM_SIZE);
@@ -759,14 +794,14 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
/* TM VF */
total = tm_iids.per_vf_cids + tm_iids.per_vf_tids;
if (total) {
- p_blk = &p_cli->vf_blks[0];
+ p_blk = qed_cxt_set_blk(&p_cli->vf_blks[0]);
qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line,
total * TM_ELEM_SIZE, TM_ELEM_SIZE);
qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line,
ILT_CLI_TM);
- p_cli->pf_total_lines = curr_line - p_blk->start_line;
+ p_cli->vf_total_lines = curr_line - p_blk->start_line;
for (i = 1; i < p_mngr->vf_count; i++)
qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line,
ILT_CLI_TM);
@@ -776,8 +811,8 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
total = qed_cxt_get_srq_count(p_hwfn);
if (total) {
- p_cli = &p_mngr->clients[ILT_CLI_TSDM];
- p_blk = &p_cli->pf_blks[SRQ_BLK];
+ p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_TSDM]);
+ p_blk = qed_cxt_set_blk(&p_cli->pf_blks[SRQ_BLK]);
qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line,
total * SRQ_CXT_SIZE, SRQ_CXT_SIZE);
@@ -786,13 +821,50 @@ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn)
p_cli->pf_total_lines = curr_line - p_blk->start_line;
}
+ *line_count = curr_line - p_hwfn->p_cxt_mngr->pf_start_line;
+
if (curr_line - p_hwfn->p_cxt_mngr->pf_start_line >
- RESC_NUM(p_hwfn, QED_ILT)) {
- DP_ERR(p_hwfn, "too many ilt lines...#lines=%d\n",
- curr_line - p_hwfn->p_cxt_mngr->pf_start_line);
+ RESC_NUM(p_hwfn, QED_ILT))
return -EINVAL;
+
+ return 0;
+}
+
+u32 qed_cxt_cfg_ilt_compute_excess(struct qed_hwfn *p_hwfn, u32 used_lines)
+{
+ struct qed_ilt_client_cfg *p_cli;
+ u32 excess_lines, available_lines;
+ struct qed_cxt_mngr *p_mngr;
+ u32 ilt_page_size, elem_size;
+ struct qed_tid_seg *p_seg;
+ int i;
+
+ available_lines = RESC_NUM(p_hwfn, QED_ILT);
+ excess_lines = used_lines - available_lines;
+
+ if (!excess_lines)
+ return 0;
+
+ if (p_hwfn->hw_info.personality != QED_PCI_ETH_ROCE)
+ return 0;
+
+ p_mngr = p_hwfn->p_cxt_mngr;
+ p_cli = &p_mngr->clients[ILT_CLI_CDUT];
+ ilt_page_size = ILT_PAGE_IN_BYTES(p_cli->p_size.val);
+
+ for (i = 0; i < NUM_TASK_PF_SEGMENTS; i++) {
+ p_seg = qed_cxt_tid_seg_info(p_hwfn, i);
+ if (!p_seg || p_seg->count == 0)
+ continue;
+
+ elem_size = p_mngr->task_type_size[p_seg->type];
+ if (!elem_size)
+ continue;
+
+ return (ilt_page_size / elem_size) * excess_lines;
}
+ DP_NOTICE(p_hwfn, "failed computing excess ILT lines\n");
return 0;
}
@@ -1126,7 +1198,7 @@ int qed_cxt_mngr_alloc(struct qed_hwfn *p_hwfn)
clients[ILT_CLI_TSDM].first.reg = ILT_CFG_REG(TSDM, FIRST_ILT);
clients[ILT_CLI_TSDM].last.reg = ILT_CFG_REG(TSDM, LAST_ILT);
clients[ILT_CLI_TSDM].p_size.reg = ILT_CFG_REG(TSDM, P_SIZE);
- /* default ILT page size for all clients is 32K */
+ /* default ILT page size for all clients is 64K */
for (i = 0; i < ILT_CLI_MAX; i++)
p_mngr->clients[i].p_size.val = ILT_DEFAULT_HW_P_SIZE;
@@ -1366,7 +1438,7 @@ static void qed_cdu_init_pf(struct qed_hwfn *p_hwfn)
}
}
-void qed_qm_init_pf(struct qed_hwfn *p_hwfn)
+void qed_qm_init_pf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
{
struct qed_qm_pf_rt_init_params params;
struct qed_qm_info *qm_info = &p_hwfn->qm_info;
@@ -1392,22 +1464,15 @@ void qed_qm_init_pf(struct qed_hwfn *p_hwfn)
params.pq_params = qm_info->qm_pq_params;
params.vport_params = qm_info->qm_vport_params;
- qed_qm_pf_rt_init(p_hwfn, p_hwfn->p_main_ptt, ¶ms);
+ qed_qm_pf_rt_init(p_hwfn, p_ptt, ¶ms);
}
/* CM PF */
-static int qed_cm_init_pf(struct qed_hwfn *p_hwfn)
+void qed_cm_init_pf(struct qed_hwfn *p_hwfn)
{
- union qed_qm_pq_params pq_params;
- u16 pq;
-
/* XCM pure-LB queue */
- memset(&pq_params, 0, sizeof(pq_params));
- pq_params.core.tc = LB_TC;
- pq = qed_get_qm_pq(p_hwfn, PROTOCOLID_CORE, &pq_params);
- STORE_RT_REG(p_hwfn, XCM_REG_CON_PHY_Q3_RT_OFFSET, pq);
-
- return 0;
+ STORE_RT_REG(p_hwfn, XCM_REG_CON_PHY_Q3_RT_OFFSET,
+ qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_LB));
}
/* DQ PF */
@@ -1639,7 +1704,7 @@ static void qed_tm_init_pf(struct qed_hwfn *p_hwfn)
u8 i;
memset(&tm_iids, 0, sizeof(tm_iids));
- qed_cxt_tm_iids(p_mngr, &tm_iids);
+ qed_cxt_tm_iids(p_hwfn, p_mngr, &tm_iids);
/* @@@TBD No pre-scan for now */
@@ -1757,9 +1822,9 @@ void qed_cxt_hw_init_common(struct qed_hwfn *p_hwfn)
qed_prs_init_common(p_hwfn);
}
-void qed_cxt_hw_init_pf(struct qed_hwfn *p_hwfn)
+void qed_cxt_hw_init_pf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
{
- qed_qm_init_pf(p_hwfn);
+ qed_qm_init_pf(p_hwfn, p_ptt);
qed_cm_init_pf(p_hwfn);
qed_dq_init_pf(p_hwfn);
qed_cdu_init_pf(p_hwfn);
@@ -1883,13 +1948,12 @@ int qed_cxt_get_cid_info(struct qed_hwfn *p_hwfn, struct qed_cxt_info *p_info)
}
static void qed_rdma_set_pf_params(struct qed_hwfn *p_hwfn,
- struct qed_rdma_pf_params *p_params)
+ struct qed_rdma_pf_params *p_params,
+ u32 num_tasks)
{
- u32 num_cons, num_tasks, num_qps, num_mrs, num_srqs;
+ u32 num_cons, num_qps, num_srqs;
enum protocol_type proto;
- num_mrs = min_t(u32, RDMA_MAX_TIDS, p_params->num_mrs);
- num_tasks = num_mrs; /* each mr uses a single task id */
num_srqs = min_t(u32, 32 * 1024, p_params->num_srqs);
switch (p_hwfn->hw_info.personality) {
@@ -1918,7 +1982,7 @@ static void qed_rdma_set_pf_params(struct qed_hwfn *p_hwfn,
}
}
-int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn)
+int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks)
{
/* Set the number of required CORE connections */
u32 core_cids = 1; /* SPQ */
@@ -1930,9 +1994,10 @@ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn)
switch (p_hwfn->hw_info.personality) {
case QED_PCI_ETH_ROCE:
{
- qed_rdma_set_pf_params(p_hwfn,
- &p_hwfn->
- pf_params.rdma_pf_params);
+ qed_rdma_set_pf_params(p_hwfn,
+ &p_hwfn->
+ pf_params.rdma_pf_params,
+ rdma_tasks);
/* no need for break since RoCE coexist with Ethernet */
}
case QED_PCI_ETH:
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.h b/drivers/net/ethernet/qlogic/qed/qed_cxt.h
index 8b01032..53ad532 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.h
@@ -105,19 +105,28 @@ u32 qed_cxt_get_proto_cid_count(struct qed_hwfn *p_hwfn,
* @brief qed_cxt_set_pf_params - Set the PF params for cxt init
*
* @param p_hwfn
- *
+ * @param rdma_tasks - requested maximum
* @return int
*/
-int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn);
+int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks);
/**
* @brief qed_cxt_cfg_ilt_compute - compute ILT init parameters
*
* @param p_hwfn
+ * @param last_line
*
* @return int
*/
-int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn);
+int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn, u32 *last_line);
+
+/**
+ * @brief qed_cxt_cfg_ilt_compute_excess - how many lines can be decreased
+ *
+ * @param p_hwfn
+ * @param used_lines
+ */
+u32 qed_cxt_cfg_ilt_compute_excess(struct qed_hwfn *p_hwfn, u32 used_lines);
/**
* @brief qed_cxt_mngr_alloc - Allocate and init the context manager struct
@@ -163,19 +172,18 @@ void qed_cxt_hw_init_common(struct qed_hwfn *p_hwfn);
/**
* @brief qed_cxt_hw_init_pf - Initailze ILT and DQ, PF phase, per path.
*
- *
- *
* @param p_hwfn
+ * @param p_ptt
*/
-void qed_cxt_hw_init_pf(struct qed_hwfn *p_hwfn);
+void qed_cxt_hw_init_pf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
/**
* @brief qed_qm_init_pf - Initailze the QM PF phase, per path
*
* @param p_hwfn
+ * @param p_ptt
*/
-
-void qed_qm_init_pf(struct qed_hwfn *p_hwfn);
+void qed_qm_init_pf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
/**
* @brief Reconfigures QM pf on the fly
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index 5bd36a4..2fc1fde 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -183,7 +183,7 @@ qed_dcbx_dp_protocol(struct qed_hwfn *p_hwfn, struct qed_dcbx_results *p_data)
"%s info: update %d, enable %d, prio %d, tc %d, num_tc %d\n",
qed_dcbx_app_update[i].name, p_data->arr[id].update,
p_data->arr[id].enable, p_data->arr[id].priority,
- p_data->arr[id].tc, p_hwfn->hw_info.num_tc);
+ p_data->arr[id].tc, p_hwfn->hw_info.num_active_tc);
}
}
@@ -204,12 +204,8 @@ qed_dcbx_set_params(struct qed_dcbx_results *p_data,
p_data->arr[type].tc = tc;
/* QM reconf data */
- if (p_info->personality == personality) {
- if (personality == QED_PCI_ETH)
- p_info->non_offload_tc = tc;
- else
- p_info->offload_tc = tc;
- }
+ if (p_info->personality == personality)
+ p_info->offload_tc = tc;
}
/* Update app protocol data and hw_info fields with the TLV info */
@@ -376,7 +372,9 @@ static int qed_dcbx_process_mib_info(struct qed_hwfn *p_hwfn)
if (rc)
return rc;
- p_info->num_tc = QED_MFW_GET_FIELD(p_ets->flags, DCBX_ETS_MAX_TCS);
+ p_info->num_active_tc = QED_MFW_GET_FIELD(p_ets->flags,
+ DCBX_ETS_MAX_TCS);
+ p_hwfn->qm_info.ooo_tc = QED_MFW_GET_FIELD(p_ets->flags, DCBX_OOO_TC);
data.pf_id = p_hwfn->rel_pf_id;
data.dcbx_enabled = !!dcbx_version;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.h b/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
index 0fabe97..2eb988f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
@@ -85,9 +85,6 @@ struct qed_dcbx_app_metadata {
enum qed_pci_personality personality;
};
-#define QED_MFW_GET_FIELD(name, field) \
- (((name) & (field ## _MASK)) >> (field ## _SHIFT))
-
struct qed_dcbx_info {
struct lldp_status_params_s lldp_remote[LLDP_MAX_LLDP_AGENTS];
struct lldp_config_params_s lldp_local[LLDP_MAX_LLDP_AGENTS];
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index 68f19ca..483241b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -17,7 +17,6 @@
/* Chip IDs enum */
enum chip_ids {
- CHIP_RESERVED,
CHIP_BB_B0,
CHIP_K2,
MAX_CHIP_IDS
@@ -40,6 +39,7 @@ enum mem_groups {
MEM_GROUP_BTB_RAM,
MEM_GROUP_RDIF_CTX,
MEM_GROUP_TDIF_CTX,
+ MEM_GROUP_CFC_MEM,
MEM_GROUP_CONN_CFC_MEM,
MEM_GROUP_TASK_CFC_MEM,
MEM_GROUP_CAU_PI,
@@ -72,6 +72,7 @@ static const char * const s_mem_group_names[] = {
"BTB_RAM",
"RDIF_CTX",
"TDIF_CTX",
+ "CFC_MEM",
"CONN_CFC_MEM",
"TASK_CFC_MEM",
"CAU_PI",
@@ -185,13 +186,16 @@ struct dbg_array {
u32 size_in_dwords;
};
+struct chip_platform_defs {
+ u8 num_ports;
+ u8 num_pfs;
+ u8 num_vfs;
+};
+
/* Chip constant definitions */
struct chip_defs {
const char *name;
- struct {
- u8 num_ports;
- u8 num_pfs;
- } per_platform[MAX_PLATFORM_IDS];
+ struct chip_platform_defs per_platform[MAX_PLATFORM_IDS];
};
/* Platform constant definitions */
@@ -405,22 +409,23 @@ struct phy_defs {
/***************************** Constant Arrays *******************************/
/* Debug arrays */
-static struct dbg_array s_dbg_arrays[MAX_BIN_DBG_BUFFER_TYPE] = { {NULL} };
+static struct dbg_array s_dbg_arrays[MAX_BIN_DBG_BUFFER_TYPE] = { {0} };
/* Chip constant definitions array */
static struct chip_defs s_chip_defs[MAX_CHIP_IDS] = {
- { "reserved", { {0, 0}, {0, 0}, {0, 0}, {0, 0} } },
{ "bb_b0",
- { {MAX_NUM_PORTS_BB, MAX_NUM_PFS_BB}, {0, 0}, {0, 0}, {0, 0} } },
- { "k2", { {MAX_NUM_PORTS_K2, MAX_NUM_PFS_K2}, {0, 0}, {0, 0}, {0, 0} } }
+ { {MAX_NUM_PORTS_BB, MAX_NUM_PFS_BB, MAX_NUM_VFS_BB}, {0, 0, 0},
+ {0, 0, 0}, {0, 0, 0} } },
+ { "k2",
+ { {MAX_NUM_PORTS_K2, MAX_NUM_PFS_K2, MAX_NUM_VFS_K2}, {0, 0, 0},
+ {0, 0, 0}, {0, 0, 0} } }
};
/* Storm constant definitions array */
static struct storm_defs s_storm_defs[] = {
/* Tstorm */
{'T', BLOCK_TSEM,
- {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT,
- DBG_BUS_CLIENT_RBCT}, true,
+ {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT}, true,
TSEM_REG_FAST_MEMORY,
TSEM_REG_DBG_FRAME_MODE, TSEM_REG_SLOW_DBG_ACTIVE,
TSEM_REG_SLOW_DBG_MODE, TSEM_REG_DBG_MODE1_CFG,
@@ -432,8 +437,7 @@ static struct storm_defs s_storm_defs[] = {
4, TCM_REG_SM_TASK_CTX},
/* Mstorm */
{'M', BLOCK_MSEM,
- {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT,
- DBG_BUS_CLIENT_RBCM}, false,
+ {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM}, false,
MSEM_REG_FAST_MEMORY,
MSEM_REG_DBG_FRAME_MODE, MSEM_REG_SLOW_DBG_ACTIVE,
MSEM_REG_SLOW_DBG_MODE, MSEM_REG_DBG_MODE1_CFG,
@@ -445,8 +449,7 @@ static struct storm_defs s_storm_defs[] = {
7, MCM_REG_SM_TASK_CTX},
/* Ustorm */
{'U', BLOCK_USEM,
- {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU,
- DBG_BUS_CLIENT_RBCU}, false,
+ {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU}, false,
USEM_REG_FAST_MEMORY,
USEM_REG_DBG_FRAME_MODE, USEM_REG_SLOW_DBG_ACTIVE,
USEM_REG_SLOW_DBG_MODE, USEM_REG_DBG_MODE1_CFG,
@@ -458,8 +461,7 @@ static struct storm_defs s_storm_defs[] = {
3, UCM_REG_SM_TASK_CTX},
/* Xstorm */
{'X', BLOCK_XSEM,
- {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX,
- DBG_BUS_CLIENT_RBCX}, false,
+ {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX}, false,
XSEM_REG_FAST_MEMORY,
XSEM_REG_DBG_FRAME_MODE, XSEM_REG_SLOW_DBG_ACTIVE,
XSEM_REG_SLOW_DBG_MODE, XSEM_REG_DBG_MODE1_CFG,
@@ -471,8 +473,7 @@ static struct storm_defs s_storm_defs[] = {
0, 0},
/* Ystorm */
{'Y', BLOCK_YSEM,
- {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX,
- DBG_BUS_CLIENT_RBCY}, false,
+ {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY}, false,
YSEM_REG_FAST_MEMORY,
YSEM_REG_DBG_FRAME_MODE, YSEM_REG_SLOW_DBG_ACTIVE,
YSEM_REG_SLOW_DBG_MODE, YSEM_REG_DBG_MODE1_CFG,
@@ -484,8 +485,7 @@ static struct storm_defs s_storm_defs[] = {
12, YCM_REG_SM_TASK_CTX},
/* Pstorm */
{'P', BLOCK_PSEM,
- {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS,
- DBG_BUS_CLIENT_RBCS}, true,
+ {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS}, true,
PSEM_REG_FAST_MEMORY,
PSEM_REG_DBG_FRAME_MODE, PSEM_REG_SLOW_DBG_ACTIVE,
PSEM_REG_SLOW_DBG_MODE, PSEM_REG_DBG_MODE1_CFG,
@@ -499,8 +499,9 @@ static struct storm_defs s_storm_defs[] = {
/* Block definitions array */
static struct block_defs block_grc_defs = {
- "grc", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN},
+ "grc",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN},
GRC_REG_DBG_SELECT, GRC_REG_DBG_DWORD_ENABLE,
GRC_REG_DBG_SHIFT, GRC_REG_DBG_FORCE_VALID,
GRC_REG_DBG_FORCE_FRAME,
@@ -508,29 +509,30 @@ static struct block_defs block_grc_defs = {
};
static struct block_defs block_miscs_defs = {
- "miscs", {false, false, false}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+ "miscs", {false, false}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
0, 0, 0, 0, 0,
false, false, MAX_DBG_RESET_REGS, 0
};
static struct block_defs block_misc_defs = {
- "misc", {false, false, false}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+ "misc", {false, false}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
0, 0, 0, 0, 0,
false, false, MAX_DBG_RESET_REGS, 0
};
static struct block_defs block_dbu_defs = {
- "dbu", {false, false, false}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+ "dbu", {false, false}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
0, 0, 0, 0, 0,
false, false, MAX_DBG_RESET_REGS, 0
};
static struct block_defs block_pglue_b_defs = {
- "pglue_b", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCH, DBG_BUS_CLIENT_RBCH, DBG_BUS_CLIENT_RBCH},
+ "pglue_b",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCH, DBG_BUS_CLIENT_RBCH},
PGLUE_B_REG_DBG_SELECT, PGLUE_B_REG_DBG_DWORD_ENABLE,
PGLUE_B_REG_DBG_SHIFT, PGLUE_B_REG_DBG_FORCE_VALID,
PGLUE_B_REG_DBG_FORCE_FRAME,
@@ -538,8 +540,9 @@ static struct block_defs block_pglue_b_defs = {
};
static struct block_defs block_cnig_defs = {
- "cnig", {false, false, true}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW},
+ "cnig",
+ {false, true}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW},
CNIG_REG_DBG_SELECT_K2, CNIG_REG_DBG_DWORD_ENABLE_K2,
CNIG_REG_DBG_SHIFT_K2, CNIG_REG_DBG_FORCE_VALID_K2,
CNIG_REG_DBG_FORCE_FRAME_K2,
@@ -547,15 +550,16 @@ static struct block_defs block_cnig_defs = {
};
static struct block_defs block_cpmu_defs = {
- "cpmu", {false, false, false}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+ "cpmu", {false, false}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
0, 0, 0, 0, 0,
true, false, DBG_RESET_REG_MISCS_PL_HV, 8
};
static struct block_defs block_ncsi_defs = {
- "ncsi", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ},
+ "ncsi",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ},
NCSI_REG_DBG_SELECT, NCSI_REG_DBG_DWORD_ENABLE,
NCSI_REG_DBG_SHIFT, NCSI_REG_DBG_FORCE_VALID,
NCSI_REG_DBG_FORCE_FRAME,
@@ -563,15 +567,16 @@ static struct block_defs block_ncsi_defs = {
};
static struct block_defs block_opte_defs = {
- "opte", {false, false, false}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+ "opte", {false, false}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
0, 0, 0, 0, 0,
true, false, DBG_RESET_REG_MISCS_PL_HV, 4
};
static struct block_defs block_bmb_defs = {
- "bmb", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCB},
+ "bmb",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCB},
BMB_REG_DBG_SELECT, BMB_REG_DBG_DWORD_ENABLE,
BMB_REG_DBG_SHIFT, BMB_REG_DBG_FORCE_VALID,
BMB_REG_DBG_FORCE_FRAME,
@@ -579,8 +584,9 @@ static struct block_defs block_bmb_defs = {
};
static struct block_defs block_pcie_defs = {
- "pcie", {false, false, true}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH},
+ "pcie",
+ {false, true}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH},
PCIE_REG_DBG_COMMON_SELECT, PCIE_REG_DBG_COMMON_DWORD_ENABLE,
PCIE_REG_DBG_COMMON_SHIFT, PCIE_REG_DBG_COMMON_FORCE_VALID,
PCIE_REG_DBG_COMMON_FORCE_FRAME,
@@ -588,15 +594,16 @@ static struct block_defs block_pcie_defs = {
};
static struct block_defs block_mcp_defs = {
- "mcp", {false, false, false}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+ "mcp", {false, false}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
0, 0, 0, 0, 0,
false, false, MAX_DBG_RESET_REGS, 0
};
static struct block_defs block_mcp2_defs = {
- "mcp2", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ},
+ "mcp2",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCZ, DBG_BUS_CLIENT_RBCZ},
MCP2_REG_DBG_SELECT, MCP2_REG_DBG_DWORD_ENABLE,
MCP2_REG_DBG_SHIFT, MCP2_REG_DBG_FORCE_VALID,
MCP2_REG_DBG_FORCE_FRAME,
@@ -604,8 +611,9 @@ static struct block_defs block_mcp2_defs = {
};
static struct block_defs block_pswhst_defs = {
- "pswhst", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+ "pswhst",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
PSWHST_REG_DBG_SELECT, PSWHST_REG_DBG_DWORD_ENABLE,
PSWHST_REG_DBG_SHIFT, PSWHST_REG_DBG_FORCE_VALID,
PSWHST_REG_DBG_FORCE_FRAME,
@@ -613,8 +621,9 @@ static struct block_defs block_pswhst_defs = {
};
static struct block_defs block_pswhst2_defs = {
- "pswhst2", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+ "pswhst2",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
PSWHST2_REG_DBG_SELECT, PSWHST2_REG_DBG_DWORD_ENABLE,
PSWHST2_REG_DBG_SHIFT, PSWHST2_REG_DBG_FORCE_VALID,
PSWHST2_REG_DBG_FORCE_FRAME,
@@ -622,8 +631,9 @@ static struct block_defs block_pswhst2_defs = {
};
static struct block_defs block_pswrd_defs = {
- "pswrd", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+ "pswrd",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
PSWRD_REG_DBG_SELECT, PSWRD_REG_DBG_DWORD_ENABLE,
PSWRD_REG_DBG_SHIFT, PSWRD_REG_DBG_FORCE_VALID,
PSWRD_REG_DBG_FORCE_FRAME,
@@ -631,8 +641,9 @@ static struct block_defs block_pswrd_defs = {
};
static struct block_defs block_pswrd2_defs = {
- "pswrd2", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+ "pswrd2",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
PSWRD2_REG_DBG_SELECT, PSWRD2_REG_DBG_DWORD_ENABLE,
PSWRD2_REG_DBG_SHIFT, PSWRD2_REG_DBG_FORCE_VALID,
PSWRD2_REG_DBG_FORCE_FRAME,
@@ -640,8 +651,9 @@ static struct block_defs block_pswrd2_defs = {
};
static struct block_defs block_pswwr_defs = {
- "pswwr", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+ "pswwr",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
PSWWR_REG_DBG_SELECT, PSWWR_REG_DBG_DWORD_ENABLE,
PSWWR_REG_DBG_SHIFT, PSWWR_REG_DBG_FORCE_VALID,
PSWWR_REG_DBG_FORCE_FRAME,
@@ -649,15 +661,16 @@ static struct block_defs block_pswwr_defs = {
};
static struct block_defs block_pswwr2_defs = {
- "pswwr2", {false, false, false}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+ "pswwr2", {false, false}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
0, 0, 0, 0, 0,
true, false, DBG_RESET_REG_MISC_PL_HV, 3
};
static struct block_defs block_pswrq_defs = {
- "pswrq", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+ "pswrq",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
PSWRQ_REG_DBG_SELECT, PSWRQ_REG_DBG_DWORD_ENABLE,
PSWRQ_REG_DBG_SHIFT, PSWRQ_REG_DBG_FORCE_VALID,
PSWRQ_REG_DBG_FORCE_FRAME,
@@ -665,8 +678,9 @@ static struct block_defs block_pswrq_defs = {
};
static struct block_defs block_pswrq2_defs = {
- "pswrq2", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+ "pswrq2",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
PSWRQ2_REG_DBG_SELECT, PSWRQ2_REG_DBG_DWORD_ENABLE,
PSWRQ2_REG_DBG_SHIFT, PSWRQ2_REG_DBG_FORCE_VALID,
PSWRQ2_REG_DBG_FORCE_FRAME,
@@ -674,8 +688,9 @@ static struct block_defs block_pswrq2_defs = {
};
static struct block_defs block_pglcs_defs = {
- "pglcs", {false, false, true}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH},
+ "pglcs",
+ {false, true}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH},
PGLCS_REG_DBG_SELECT, PGLCS_REG_DBG_DWORD_ENABLE,
PGLCS_REG_DBG_SHIFT, PGLCS_REG_DBG_FORCE_VALID,
PGLCS_REG_DBG_FORCE_FRAME,
@@ -683,8 +698,9 @@ static struct block_defs block_pglcs_defs = {
};
static struct block_defs block_ptu_defs = {
- "ptu", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+ "ptu",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
PTU_REG_DBG_SELECT, PTU_REG_DBG_DWORD_ENABLE,
PTU_REG_DBG_SHIFT, PTU_REG_DBG_FORCE_VALID,
PTU_REG_DBG_FORCE_FRAME,
@@ -692,8 +708,9 @@ static struct block_defs block_ptu_defs = {
};
static struct block_defs block_dmae_defs = {
- "dmae", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+ "dmae",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
DMAE_REG_DBG_SELECT, DMAE_REG_DBG_DWORD_ENABLE,
DMAE_REG_DBG_SHIFT, DMAE_REG_DBG_FORCE_VALID,
DMAE_REG_DBG_FORCE_FRAME,
@@ -701,8 +718,9 @@ static struct block_defs block_dmae_defs = {
};
static struct block_defs block_tcm_defs = {
- "tcm", {true, true, true}, true, DBG_TSTORM_ID,
- {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
+ "tcm",
+ {true, true}, true, DBG_TSTORM_ID,
+ {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
TCM_REG_DBG_SELECT, TCM_REG_DBG_DWORD_ENABLE,
TCM_REG_DBG_SHIFT, TCM_REG_DBG_FORCE_VALID,
TCM_REG_DBG_FORCE_FRAME,
@@ -710,8 +728,9 @@ static struct block_defs block_tcm_defs = {
};
static struct block_defs block_mcm_defs = {
- "mcm", {true, true, true}, true, DBG_MSTORM_ID,
- {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
+ "mcm",
+ {true, true}, true, DBG_MSTORM_ID,
+ {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
MCM_REG_DBG_SELECT, MCM_REG_DBG_DWORD_ENABLE,
MCM_REG_DBG_SHIFT, MCM_REG_DBG_FORCE_VALID,
MCM_REG_DBG_FORCE_FRAME,
@@ -719,8 +738,9 @@ static struct block_defs block_mcm_defs = {
};
static struct block_defs block_ucm_defs = {
- "ucm", {true, true, true}, true, DBG_USTORM_ID,
- {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
+ "ucm",
+ {true, true}, true, DBG_USTORM_ID,
+ {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
UCM_REG_DBG_SELECT, UCM_REG_DBG_DWORD_ENABLE,
UCM_REG_DBG_SHIFT, UCM_REG_DBG_FORCE_VALID,
UCM_REG_DBG_FORCE_FRAME,
@@ -728,8 +748,9 @@ static struct block_defs block_ucm_defs = {
};
static struct block_defs block_xcm_defs = {
- "xcm", {true, true, true}, true, DBG_XSTORM_ID,
- {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
+ "xcm",
+ {true, true}, true, DBG_XSTORM_ID,
+ {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
XCM_REG_DBG_SELECT, XCM_REG_DBG_DWORD_ENABLE,
XCM_REG_DBG_SHIFT, XCM_REG_DBG_FORCE_VALID,
XCM_REG_DBG_FORCE_FRAME,
@@ -737,8 +758,9 @@ static struct block_defs block_xcm_defs = {
};
static struct block_defs block_ycm_defs = {
- "ycm", {true, true, true}, true, DBG_YSTORM_ID,
- {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
+ "ycm",
+ {true, true}, true, DBG_YSTORM_ID,
+ {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
YCM_REG_DBG_SELECT, YCM_REG_DBG_DWORD_ENABLE,
YCM_REG_DBG_SHIFT, YCM_REG_DBG_FORCE_VALID,
YCM_REG_DBG_FORCE_FRAME,
@@ -746,8 +768,9 @@ static struct block_defs block_ycm_defs = {
};
static struct block_defs block_pcm_defs = {
- "pcm", {true, true, true}, true, DBG_PSTORM_ID,
- {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
+ "pcm",
+ {true, true}, true, DBG_PSTORM_ID,
+ {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
PCM_REG_DBG_SELECT, PCM_REG_DBG_DWORD_ENABLE,
PCM_REG_DBG_SHIFT, PCM_REG_DBG_FORCE_VALID,
PCM_REG_DBG_FORCE_FRAME,
@@ -755,8 +778,9 @@ static struct block_defs block_pcm_defs = {
};
static struct block_defs block_qm_defs = {
- "qm", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCQ},
+ "qm",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCQ},
QM_REG_DBG_SELECT, QM_REG_DBG_DWORD_ENABLE,
QM_REG_DBG_SHIFT, QM_REG_DBG_FORCE_VALID,
QM_REG_DBG_FORCE_FRAME,
@@ -764,8 +788,9 @@ static struct block_defs block_qm_defs = {
};
static struct block_defs block_tm_defs = {
- "tm", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
+ "tm",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
TM_REG_DBG_SELECT, TM_REG_DBG_DWORD_ENABLE,
TM_REG_DBG_SHIFT, TM_REG_DBG_FORCE_VALID,
TM_REG_DBG_FORCE_FRAME,
@@ -773,8 +798,9 @@ static struct block_defs block_tm_defs = {
};
static struct block_defs block_dorq_defs = {
- "dorq", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
+ "dorq",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
DORQ_REG_DBG_SELECT, DORQ_REG_DBG_DWORD_ENABLE,
DORQ_REG_DBG_SHIFT, DORQ_REG_DBG_FORCE_VALID,
DORQ_REG_DBG_FORCE_FRAME,
@@ -782,8 +808,9 @@ static struct block_defs block_dorq_defs = {
};
static struct block_defs block_brb_defs = {
- "brb", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR},
+ "brb",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR},
BRB_REG_DBG_SELECT, BRB_REG_DBG_DWORD_ENABLE,
BRB_REG_DBG_SHIFT, BRB_REG_DBG_FORCE_VALID,
BRB_REG_DBG_FORCE_FRAME,
@@ -791,8 +818,9 @@ static struct block_defs block_brb_defs = {
};
static struct block_defs block_src_defs = {
- "src", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
+ "src",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
SRC_REG_DBG_SELECT, SRC_REG_DBG_DWORD_ENABLE,
SRC_REG_DBG_SHIFT, SRC_REG_DBG_FORCE_VALID,
SRC_REG_DBG_FORCE_FRAME,
@@ -800,8 +828,9 @@ static struct block_defs block_src_defs = {
};
static struct block_defs block_prs_defs = {
- "prs", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR},
+ "prs",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR},
PRS_REG_DBG_SELECT, PRS_REG_DBG_DWORD_ENABLE,
PRS_REG_DBG_SHIFT, PRS_REG_DBG_FORCE_VALID,
PRS_REG_DBG_FORCE_FRAME,
@@ -809,8 +838,9 @@ static struct block_defs block_prs_defs = {
};
static struct block_defs block_tsdm_defs = {
- "tsdm", {true, true, true}, true, DBG_TSTORM_ID,
- {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
+ "tsdm",
+ {true, true}, true, DBG_TSTORM_ID,
+ {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
TSDM_REG_DBG_SELECT, TSDM_REG_DBG_DWORD_ENABLE,
TSDM_REG_DBG_SHIFT, TSDM_REG_DBG_FORCE_VALID,
TSDM_REG_DBG_FORCE_FRAME,
@@ -818,8 +848,9 @@ static struct block_defs block_tsdm_defs = {
};
static struct block_defs block_msdm_defs = {
- "msdm", {true, true, true}, true, DBG_MSTORM_ID,
- {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
+ "msdm",
+ {true, true}, true, DBG_MSTORM_ID,
+ {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
MSDM_REG_DBG_SELECT, MSDM_REG_DBG_DWORD_ENABLE,
MSDM_REG_DBG_SHIFT, MSDM_REG_DBG_FORCE_VALID,
MSDM_REG_DBG_FORCE_FRAME,
@@ -827,8 +858,9 @@ static struct block_defs block_msdm_defs = {
};
static struct block_defs block_usdm_defs = {
- "usdm", {true, true, true}, true, DBG_USTORM_ID,
- {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
+ "usdm",
+ {true, true}, true, DBG_USTORM_ID,
+ {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
USDM_REG_DBG_SELECT, USDM_REG_DBG_DWORD_ENABLE,
USDM_REG_DBG_SHIFT, USDM_REG_DBG_FORCE_VALID,
USDM_REG_DBG_FORCE_FRAME,
@@ -836,8 +868,9 @@ static struct block_defs block_usdm_defs = {
};
static struct block_defs block_xsdm_defs = {
- "xsdm", {true, true, true}, true, DBG_XSTORM_ID,
- {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
+ "xsdm",
+ {true, true}, true, DBG_XSTORM_ID,
+ {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
XSDM_REG_DBG_SELECT, XSDM_REG_DBG_DWORD_ENABLE,
XSDM_REG_DBG_SHIFT, XSDM_REG_DBG_FORCE_VALID,
XSDM_REG_DBG_FORCE_FRAME,
@@ -845,8 +878,9 @@ static struct block_defs block_xsdm_defs = {
};
static struct block_defs block_ysdm_defs = {
- "ysdm", {true, true, true}, true, DBG_YSTORM_ID,
- {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
+ "ysdm",
+ {true, true}, true, DBG_YSTORM_ID,
+ {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
YSDM_REG_DBG_SELECT, YSDM_REG_DBG_DWORD_ENABLE,
YSDM_REG_DBG_SHIFT, YSDM_REG_DBG_FORCE_VALID,
YSDM_REG_DBG_FORCE_FRAME,
@@ -854,8 +888,9 @@ static struct block_defs block_ysdm_defs = {
};
static struct block_defs block_psdm_defs = {
- "psdm", {true, true, true}, true, DBG_PSTORM_ID,
- {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
+ "psdm",
+ {true, true}, true, DBG_PSTORM_ID,
+ {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
PSDM_REG_DBG_SELECT, PSDM_REG_DBG_DWORD_ENABLE,
PSDM_REG_DBG_SHIFT, PSDM_REG_DBG_FORCE_VALID,
PSDM_REG_DBG_FORCE_FRAME,
@@ -863,8 +898,9 @@ static struct block_defs block_psdm_defs = {
};
static struct block_defs block_tsem_defs = {
- "tsem", {true, true, true}, true, DBG_TSTORM_ID,
- {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
+ "tsem",
+ {true, true}, true, DBG_TSTORM_ID,
+ {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
TSEM_REG_DBG_SELECT, TSEM_REG_DBG_DWORD_ENABLE,
TSEM_REG_DBG_SHIFT, TSEM_REG_DBG_FORCE_VALID,
TSEM_REG_DBG_FORCE_FRAME,
@@ -872,8 +908,9 @@ static struct block_defs block_tsem_defs = {
};
static struct block_defs block_msem_defs = {
- "msem", {true, true, true}, true, DBG_MSTORM_ID,
- {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
+ "msem",
+ {true, true}, true, DBG_MSTORM_ID,
+ {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
MSEM_REG_DBG_SELECT, MSEM_REG_DBG_DWORD_ENABLE,
MSEM_REG_DBG_SHIFT, MSEM_REG_DBG_FORCE_VALID,
MSEM_REG_DBG_FORCE_FRAME,
@@ -881,8 +918,9 @@ static struct block_defs block_msem_defs = {
};
static struct block_defs block_usem_defs = {
- "usem", {true, true, true}, true, DBG_USTORM_ID,
- {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
+ "usem",
+ {true, true}, true, DBG_USTORM_ID,
+ {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
USEM_REG_DBG_SELECT, USEM_REG_DBG_DWORD_ENABLE,
USEM_REG_DBG_SHIFT, USEM_REG_DBG_FORCE_VALID,
USEM_REG_DBG_FORCE_FRAME,
@@ -890,8 +928,9 @@ static struct block_defs block_usem_defs = {
};
static struct block_defs block_xsem_defs = {
- "xsem", {true, true, true}, true, DBG_XSTORM_ID,
- {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
+ "xsem",
+ {true, true}, true, DBG_XSTORM_ID,
+ {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
XSEM_REG_DBG_SELECT, XSEM_REG_DBG_DWORD_ENABLE,
XSEM_REG_DBG_SHIFT, XSEM_REG_DBG_FORCE_VALID,
XSEM_REG_DBG_FORCE_FRAME,
@@ -899,8 +938,9 @@ static struct block_defs block_xsem_defs = {
};
static struct block_defs block_ysem_defs = {
- "ysem", {true, true, true}, true, DBG_YSTORM_ID,
- {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
+ "ysem",
+ {true, true}, true, DBG_YSTORM_ID,
+ {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCY},
YSEM_REG_DBG_SELECT, YSEM_REG_DBG_DWORD_ENABLE,
YSEM_REG_DBG_SHIFT, YSEM_REG_DBG_FORCE_VALID,
YSEM_REG_DBG_FORCE_FRAME,
@@ -908,8 +948,9 @@ static struct block_defs block_ysem_defs = {
};
static struct block_defs block_psem_defs = {
- "psem", {true, true, true}, true, DBG_PSTORM_ID,
- {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
+ "psem",
+ {true, true}, true, DBG_PSTORM_ID,
+ {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
PSEM_REG_DBG_SELECT, PSEM_REG_DBG_DWORD_ENABLE,
PSEM_REG_DBG_SHIFT, PSEM_REG_DBG_FORCE_VALID,
PSEM_REG_DBG_FORCE_FRAME,
@@ -917,8 +958,9 @@ static struct block_defs block_psem_defs = {
};
static struct block_defs block_rss_defs = {
- "rss", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
+ "rss",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT},
RSS_REG_DBG_SELECT, RSS_REG_DBG_DWORD_ENABLE,
RSS_REG_DBG_SHIFT, RSS_REG_DBG_FORCE_VALID,
RSS_REG_DBG_FORCE_FRAME,
@@ -926,8 +968,9 @@ static struct block_defs block_rss_defs = {
};
static struct block_defs block_tmld_defs = {
- "tmld", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
+ "tmld",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
TMLD_REG_DBG_SELECT, TMLD_REG_DBG_DWORD_ENABLE,
TMLD_REG_DBG_SHIFT, TMLD_REG_DBG_FORCE_VALID,
TMLD_REG_DBG_FORCE_FRAME,
@@ -935,8 +978,9 @@ static struct block_defs block_tmld_defs = {
};
static struct block_defs block_muld_defs = {
- "muld", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
+ "muld",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
MULD_REG_DBG_SELECT, MULD_REG_DBG_DWORD_ENABLE,
MULD_REG_DBG_SHIFT, MULD_REG_DBG_FORCE_VALID,
MULD_REG_DBG_FORCE_FRAME,
@@ -944,8 +988,9 @@ static struct block_defs block_muld_defs = {
};
static struct block_defs block_yuld_defs = {
- "yuld", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
+ "yuld",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCU, DBG_BUS_CLIENT_RBCU},
YULD_REG_DBG_SELECT, YULD_REG_DBG_DWORD_ENABLE,
YULD_REG_DBG_SHIFT, YULD_REG_DBG_FORCE_VALID,
YULD_REG_DBG_FORCE_FRAME,
@@ -953,8 +998,9 @@ static struct block_defs block_yuld_defs = {
};
static struct block_defs block_xyld_defs = {
- "xyld", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
+ "xyld",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCX, DBG_BUS_CLIENT_RBCX},
XYLD_REG_DBG_SELECT, XYLD_REG_DBG_DWORD_ENABLE,
XYLD_REG_DBG_SHIFT, XYLD_REG_DBG_FORCE_VALID,
XYLD_REG_DBG_FORCE_FRAME,
@@ -962,8 +1008,9 @@ static struct block_defs block_xyld_defs = {
};
static struct block_defs block_prm_defs = {
- "prm", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
+ "prm",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
PRM_REG_DBG_SELECT, PRM_REG_DBG_DWORD_ENABLE,
PRM_REG_DBG_SHIFT, PRM_REG_DBG_FORCE_VALID,
PRM_REG_DBG_FORCE_FRAME,
@@ -971,8 +1018,9 @@ static struct block_defs block_prm_defs = {
};
static struct block_defs block_pbf_pb1_defs = {
- "pbf_pb1", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV},
+ "pbf_pb1",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV},
PBF_PB1_REG_DBG_SELECT, PBF_PB1_REG_DBG_DWORD_ENABLE,
PBF_PB1_REG_DBG_SHIFT, PBF_PB1_REG_DBG_FORCE_VALID,
PBF_PB1_REG_DBG_FORCE_FRAME,
@@ -981,8 +1029,9 @@ static struct block_defs block_pbf_pb1_defs = {
};
static struct block_defs block_pbf_pb2_defs = {
- "pbf_pb2", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV},
+ "pbf_pb2",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV},
PBF_PB2_REG_DBG_SELECT, PBF_PB2_REG_DBG_DWORD_ENABLE,
PBF_PB2_REG_DBG_SHIFT, PBF_PB2_REG_DBG_FORCE_VALID,
PBF_PB2_REG_DBG_FORCE_FRAME,
@@ -991,8 +1040,9 @@ static struct block_defs block_pbf_pb2_defs = {
};
static struct block_defs block_rpb_defs = {
- "rpb", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
+ "rpb",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
RPB_REG_DBG_SELECT, RPB_REG_DBG_DWORD_ENABLE,
RPB_REG_DBG_SHIFT, RPB_REG_DBG_FORCE_VALID,
RPB_REG_DBG_FORCE_FRAME,
@@ -1000,8 +1050,9 @@ static struct block_defs block_rpb_defs = {
};
static struct block_defs block_btb_defs = {
- "btb", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCV},
+ "btb",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCR, DBG_BUS_CLIENT_RBCV},
BTB_REG_DBG_SELECT, BTB_REG_DBG_DWORD_ENABLE,
BTB_REG_DBG_SHIFT, BTB_REG_DBG_FORCE_VALID,
BTB_REG_DBG_FORCE_FRAME,
@@ -1009,8 +1060,9 @@ static struct block_defs block_btb_defs = {
};
static struct block_defs block_pbf_defs = {
- "pbf", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV},
+ "pbf",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCV},
PBF_REG_DBG_SELECT, PBF_REG_DBG_DWORD_ENABLE,
PBF_REG_DBG_SHIFT, PBF_REG_DBG_FORCE_VALID,
PBF_REG_DBG_FORCE_FRAME,
@@ -1018,8 +1070,9 @@ static struct block_defs block_pbf_defs = {
};
static struct block_defs block_rdif_defs = {
- "rdif", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
+ "rdif",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCT, DBG_BUS_CLIENT_RBCM},
RDIF_REG_DBG_SELECT, RDIF_REG_DBG_DWORD_ENABLE,
RDIF_REG_DBG_SHIFT, RDIF_REG_DBG_FORCE_VALID,
RDIF_REG_DBG_FORCE_FRAME,
@@ -1027,8 +1080,9 @@ static struct block_defs block_rdif_defs = {
};
static struct block_defs block_tdif_defs = {
- "tdif", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
+ "tdif",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCS, DBG_BUS_CLIENT_RBCS},
TDIF_REG_DBG_SELECT, TDIF_REG_DBG_DWORD_ENABLE,
TDIF_REG_DBG_SHIFT, TDIF_REG_DBG_FORCE_VALID,
TDIF_REG_DBG_FORCE_FRAME,
@@ -1036,8 +1090,9 @@ static struct block_defs block_tdif_defs = {
};
static struct block_defs block_cdu_defs = {
- "cdu", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
+ "cdu",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
CDU_REG_DBG_SELECT, CDU_REG_DBG_DWORD_ENABLE,
CDU_REG_DBG_SHIFT, CDU_REG_DBG_FORCE_VALID,
CDU_REG_DBG_FORCE_FRAME,
@@ -1045,8 +1100,9 @@ static struct block_defs block_cdu_defs = {
};
static struct block_defs block_ccfc_defs = {
- "ccfc", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
+ "ccfc",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
CCFC_REG_DBG_SELECT, CCFC_REG_DBG_DWORD_ENABLE,
CCFC_REG_DBG_SHIFT, CCFC_REG_DBG_FORCE_VALID,
CCFC_REG_DBG_FORCE_FRAME,
@@ -1054,8 +1110,9 @@ static struct block_defs block_ccfc_defs = {
};
static struct block_defs block_tcfc_defs = {
- "tcfc", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
+ "tcfc",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCF, DBG_BUS_CLIENT_RBCF},
TCFC_REG_DBG_SELECT, TCFC_REG_DBG_DWORD_ENABLE,
TCFC_REG_DBG_SHIFT, TCFC_REG_DBG_FORCE_VALID,
TCFC_REG_DBG_FORCE_FRAME,
@@ -1063,8 +1120,9 @@ static struct block_defs block_tcfc_defs = {
};
static struct block_defs block_igu_defs = {
- "igu", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+ "igu",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
IGU_REG_DBG_SELECT, IGU_REG_DBG_DWORD_ENABLE,
IGU_REG_DBG_SHIFT, IGU_REG_DBG_FORCE_VALID,
IGU_REG_DBG_FORCE_FRAME,
@@ -1072,8 +1130,9 @@ static struct block_defs block_igu_defs = {
};
static struct block_defs block_cau_defs = {
- "cau", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
+ "cau",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCP, DBG_BUS_CLIENT_RBCP},
CAU_REG_DBG_SELECT, CAU_REG_DBG_DWORD_ENABLE,
CAU_REG_DBG_SHIFT, CAU_REG_DBG_FORCE_VALID,
CAU_REG_DBG_FORCE_FRAME,
@@ -1081,8 +1140,9 @@ static struct block_defs block_cau_defs = {
};
static struct block_defs block_umac_defs = {
- "umac", {false, false, true}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ},
+ "umac",
+ {false, true}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ},
UMAC_REG_DBG_SELECT, UMAC_REG_DBG_DWORD_ENABLE,
UMAC_REG_DBG_SHIFT, UMAC_REG_DBG_FORCE_VALID,
UMAC_REG_DBG_FORCE_FRAME,
@@ -1090,22 +1150,23 @@ static struct block_defs block_umac_defs = {
};
static struct block_defs block_xmac_defs = {
- "xmac", {false, false, false}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+ "xmac", {false, false}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
0, 0, 0, 0, 0,
false, false, MAX_DBG_RESET_REGS, 0
};
static struct block_defs block_dbg_defs = {
- "dbg", {false, false, false}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+ "dbg", {false, false}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
0, 0, 0, 0, 0,
true, true, DBG_RESET_REG_MISC_PL_PDA_VAUX, 3
};
static struct block_defs block_nig_defs = {
- "nig", {true, true, true}, false, 0,
- {DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN},
+ "nig",
+ {true, true}, false, 0,
+ {DBG_BUS_CLIENT_RBCN, DBG_BUS_CLIENT_RBCN},
NIG_REG_DBG_SELECT, NIG_REG_DBG_DWORD_ENABLE,
NIG_REG_DBG_SHIFT, NIG_REG_DBG_FORCE_VALID,
NIG_REG_DBG_FORCE_FRAME,
@@ -1113,8 +1174,9 @@ static struct block_defs block_nig_defs = {
};
static struct block_defs block_wol_defs = {
- "wol", {false, false, true}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ},
+ "wol",
+ {false, true}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ},
WOL_REG_DBG_SELECT, WOL_REG_DBG_DWORD_ENABLE,
WOL_REG_DBG_SHIFT, WOL_REG_DBG_FORCE_VALID,
WOL_REG_DBG_FORCE_FRAME,
@@ -1122,8 +1184,9 @@ static struct block_defs block_wol_defs = {
};
static struct block_defs block_bmbn_defs = {
- "bmbn", {false, false, true}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCB},
+ "bmbn",
+ {false, true}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCB},
BMBN_REG_DBG_SELECT, BMBN_REG_DBG_DWORD_ENABLE,
BMBN_REG_DBG_SHIFT, BMBN_REG_DBG_FORCE_VALID,
BMBN_REG_DBG_FORCE_FRAME,
@@ -1131,15 +1194,16 @@ static struct block_defs block_bmbn_defs = {
};
static struct block_defs block_ipc_defs = {
- "ipc", {false, false, false}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+ "ipc", {false, false}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
0, 0, 0, 0, 0,
true, false, DBG_RESET_REG_MISCS_PL_UA, 8
};
static struct block_defs block_nwm_defs = {
- "nwm", {false, false, true}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW},
+ "nwm",
+ {false, true}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW},
NWM_REG_DBG_SELECT, NWM_REG_DBG_DWORD_ENABLE,
NWM_REG_DBG_SHIFT, NWM_REG_DBG_FORCE_VALID,
NWM_REG_DBG_FORCE_FRAME,
@@ -1147,22 +1211,29 @@ static struct block_defs block_nwm_defs = {
};
static struct block_defs block_nws_defs = {
- "nws", {false, false, false}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
- 0, 0, 0, 0, 0,
+ "nws",
+ {false, true}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCW},
+ NWS_REG_DBG_SELECT, NWS_REG_DBG_DWORD_ENABLE,
+ NWS_REG_DBG_SHIFT, NWS_REG_DBG_FORCE_VALID,
+ NWS_REG_DBG_FORCE_FRAME,
true, false, DBG_RESET_REG_MISCS_PL_HV, 12
};
static struct block_defs block_ms_defs = {
- "ms", {false, false, false}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
- 0, 0, 0, 0, 0,
+ "ms",
+ {false, true}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCZ},
+ MS_REG_DBG_SELECT, MS_REG_DBG_DWORD_ENABLE,
+ MS_REG_DBG_SHIFT, MS_REG_DBG_FORCE_VALID,
+ MS_REG_DBG_FORCE_FRAME,
true, false, DBG_RESET_REG_MISCS_PL_HV, 13
};
static struct block_defs block_phy_pcie_defs = {
- "phy_pcie", {false, false, true}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH},
+ "phy_pcie",
+ {false, true}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, DBG_BUS_CLIENT_RBCH},
PCIE_REG_DBG_COMMON_SELECT, PCIE_REG_DBG_COMMON_DWORD_ENABLE,
PCIE_REG_DBG_COMMON_SHIFT, PCIE_REG_DBG_COMMON_FORCE_VALID,
PCIE_REG_DBG_COMMON_FORCE_FRAME,
@@ -1170,22 +1241,57 @@ static struct block_defs block_phy_pcie_defs = {
};
static struct block_defs block_led_defs = {
- "led", {false, false, false}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+ "led", {false, false}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
0, 0, 0, 0, 0,
- true, true, DBG_RESET_REG_MISCS_PL_HV, 14
+ true, false, DBG_RESET_REG_MISCS_PL_HV, 14
+};
+
+static struct block_defs block_avs_wrap_defs = {
+ "avs_wrap", {false, false}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+ 0, 0, 0, 0, 0,
+ true, false, DBG_RESET_REG_MISCS_PL_UA, 11
+};
+
+static struct block_defs block_rgfs_defs = {
+ "rgfs", {false, false}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+ 0, 0, 0, 0, 0,
+ false, false, MAX_DBG_RESET_REGS, 0
+};
+
+static struct block_defs block_tgfs_defs = {
+ "tgfs", {false, false}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+ 0, 0, 0, 0, 0,
+ false, false, MAX_DBG_RESET_REGS, 0
+};
+
+static struct block_defs block_ptld_defs = {
+ "ptld", {false, false}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+ 0, 0, 0, 0, 0,
+ false, false, MAX_DBG_RESET_REGS, 0
+};
+
+static struct block_defs block_ypld_defs = {
+ "ypld", {false, false}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+ 0, 0, 0, 0, 0,
+ false, false, MAX_DBG_RESET_REGS, 0
};
static struct block_defs block_misc_aeu_defs = {
- "misc_aeu", {false, false, false}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+ "misc_aeu", {false, false}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
0, 0, 0, 0, 0,
false, false, MAX_DBG_RESET_REGS, 0
};
static struct block_defs block_bar0_map_defs = {
- "bar0_map", {false, false, false}, false, 0,
- {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
+ "bar0_map", {false, false}, false, 0,
+ {MAX_DBG_BUS_CLIENTS, MAX_DBG_BUS_CLIENTS},
0, 0, 0, 0, 0,
false, false, MAX_DBG_RESET_REGS, 0
};
@@ -1269,6 +1375,11 @@ static struct block_defs *s_block_defs[MAX_BLOCK_ID] = {
&block_ms_defs,
&block_phy_pcie_defs,
&block_led_defs,
+ &block_avs_wrap_defs,
+ &block_rgfs_defs,
+ &block_tgfs_defs,
+ &block_ptld_defs,
+ &block_ypld_defs,
&block_misc_aeu_defs,
&block_bar0_map_defs,
};
@@ -1281,65 +1392,67 @@ static struct platform_defs s_platform_defs[] = {
};
static struct grc_param_defs s_grc_param_defs[] = {
- {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_TSTORM */
- {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_MSTORM */
- {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_USTORM */
- {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_XSTORM */
- {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_YSTORM */
- {{1, 1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_PSTORM */
- {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_REGS */
- {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_RAM */
- {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_PBUF */
- {{0, 0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_IOR */
- {{0, 0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_VFC */
- {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CM_CTX */
- {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_ILT */
- {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_RSS */
- {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CAU */
- {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_QM */
- {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_MCP */
- {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_RESERVED */
- {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CFC */
- {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_IGU */
- {{0, 0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_BRB */
- {{0, 0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_BTB */
- {{0, 0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_BMB */
- {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_NIG */
- {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_MULD */
- {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_PRS */
- {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_DMAE */
- {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_TM */
- {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_SDM */
- {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_DIF */
- {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_STATIC */
- {{0, 0, 0}, 0, 1, false, 0, 0}, /* DBG_GRC_PARAM_UNSTALL */
- {{MAX_LCIDS, MAX_LCIDS, MAX_LCIDS}, 1, MAX_LCIDS, false, MAX_LCIDS,
+ {{1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_TSTORM */
+ {{1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_MSTORM */
+ {{1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_USTORM */
+ {{1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_XSTORM */
+ {{1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_YSTORM */
+ {{1, 1}, 0, 1, false, 1, 1}, /* DBG_GRC_PARAM_DUMP_PSTORM */
+ {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_REGS */
+ {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_RAM */
+ {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_PBUF */
+ {{0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_IOR */
+ {{0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_VFC */
+ {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CM_CTX */
+ {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_ILT */
+ {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_RSS */
+ {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CAU */
+ {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_QM */
+ {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_MCP */
+ {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_RESERVED */
+ {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CFC */
+ {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_IGU */
+ {{0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_BRB */
+ {{0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_BTB */
+ {{0, 0}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_BMB */
+ {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_NIG */
+ {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_MULD */
+ {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_PRS */
+ {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_DMAE */
+ {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_TM */
+ {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_SDM */
+ {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_DIF */
+ {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_STATIC */
+ {{0, 0}, 0, 1, false, 0, 0}, /* DBG_GRC_PARAM_UNSTALL */
+ {{MAX_LCIDS, MAX_LCIDS}, 1, MAX_LCIDS, false, MAX_LCIDS,
MAX_LCIDS}, /* DBG_GRC_PARAM_NUM_LCIDS */
- {{MAX_LTIDS, MAX_LTIDS, MAX_LTIDS}, 1, MAX_LTIDS, false, MAX_LTIDS,
+ {{MAX_LTIDS, MAX_LTIDS}, 1, MAX_LTIDS, false, MAX_LTIDS,
MAX_LTIDS}, /* DBG_GRC_PARAM_NUM_LTIDS */
- {{0, 0, 0}, 0, 1, true, 0, 0}, /* DBG_GRC_PARAM_EXCLUDE_ALL */
- {{0, 0, 0}, 0, 1, true, 0, 0}, /* DBG_GRC_PARAM_CRASH */
- {{0, 0, 0}, 0, 1, false, 1, 0}, /* DBG_GRC_PARAM_PARITY_SAFE */
- {{1, 1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CM */
- {{1, 1, 1}, 0, 1, false, 0, 1} /* DBG_GRC_PARAM_DUMP_PHY */
+ {{0, 0}, 0, 1, true, 0, 0}, /* DBG_GRC_PARAM_EXCLUDE_ALL */
+ {{0, 0}, 0, 1, true, 0, 0}, /* DBG_GRC_PARAM_CRASH */
+ {{0, 0}, 0, 1, false, 1, 0}, /* DBG_GRC_PARAM_PARITY_SAFE */
+ {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_CM */
+ {{1, 1}, 0, 1, false, 0, 1}, /* DBG_GRC_PARAM_DUMP_PHY */
+ {{0, 0}, 0, 1, false, 0, 0}, /* DBG_GRC_PARAM_NO_MCP */
+ {{0, 0}, 0, 1, false, 0, 0} /* DBG_GRC_PARAM_NO_FW_VER */
};
static struct rss_mem_defs s_rss_mem_defs[] = {
{ "rss_mem_cid", "rss_cid", 0,
- {256, 256, 320},
- {32, 32, 32} },
+ {256, 320},
+ {32, 32} },
{ "rss_mem_key_msb", "rss_key", 1024,
- {128, 128, 208},
- {256, 256, 256} },
+ {128, 208},
+ {256, 256} },
{ "rss_mem_key_lsb", "rss_key", 2048,
- {128, 128, 208},
- {64, 64, 64} },
+ {128, 208},
+ {64, 64} },
{ "rss_mem_info", "rss_info", 3072,
- {128, 128, 208},
- {16, 16, 16} },
+ {128, 208},
+ {16, 16} },
{ "rss_mem_ind", "rss_ind", 4096,
- {(128 * 128), (128 * 128), (128 * 208)},
- {16, 16, 16} }
+ {(128 * 128), (128 * 208)},
+ {16, 16} }
};
static struct vfc_ram_defs s_vfc_ram_defs[] = {
@@ -1352,32 +1465,32 @@ static struct vfc_ram_defs s_vfc_ram_defs[] = {
static struct big_ram_defs s_big_ram_defs[] = {
{ "BRB", MEM_GROUP_BRB_MEM, MEM_GROUP_BRB_RAM, DBG_GRC_PARAM_DUMP_BRB,
BRB_REG_BIG_RAM_ADDRESS, BRB_REG_BIG_RAM_DATA,
- {4800, 4800, 5632} },
+ {4800, 5632} },
{ "BTB", MEM_GROUP_BTB_MEM, MEM_GROUP_BTB_RAM, DBG_GRC_PARAM_DUMP_BTB,
BTB_REG_BIG_RAM_ADDRESS, BTB_REG_BIG_RAM_DATA,
- {2880, 2880, 3680} },
+ {2880, 3680} },
{ "BMB", MEM_GROUP_BMB_MEM, MEM_GROUP_BMB_RAM, DBG_GRC_PARAM_DUMP_BMB,
BMB_REG_BIG_RAM_ADDRESS, BMB_REG_BIG_RAM_DATA,
- {1152, 1152, 1152} }
+ {1152, 1152} }
};
static struct reset_reg_defs s_reset_regs_defs[] = {
{ MISCS_REG_RESET_PL_UA, 0x0,
- {true, true, true} }, /* DBG_RESET_REG_MISCS_PL_UA */
+ {true, true} }, /* DBG_RESET_REG_MISCS_PL_UA */
{ MISCS_REG_RESET_PL_HV, 0x0,
- {true, true, true} }, /* DBG_RESET_REG_MISCS_PL_HV */
+ {true, true} }, /* DBG_RESET_REG_MISCS_PL_HV */
{ MISCS_REG_RESET_PL_HV_2, 0x0,
- {false, false, true} }, /* DBG_RESET_REG_MISCS_PL_HV_2 */
+ {false, true} }, /* DBG_RESET_REG_MISCS_PL_HV_2 */
{ MISC_REG_RESET_PL_UA, 0x0,
- {true, true, true} }, /* DBG_RESET_REG_MISC_PL_UA */
+ {true, true} }, /* DBG_RESET_REG_MISC_PL_UA */
{ MISC_REG_RESET_PL_HV, 0x0,
- {true, true, true} }, /* DBG_RESET_REG_MISC_PL_HV */
+ {true, true} }, /* DBG_RESET_REG_MISC_PL_HV */
{ MISC_REG_RESET_PL_PDA_VMAIN_1, 0x4404040,
- {true, true, true} }, /* DBG_RESET_REG_MISC_PL_PDA_VMAIN_1 */
+ {true, true} }, /* DBG_RESET_REG_MISC_PL_PDA_VMAIN_1 */
{ MISC_REG_RESET_PL_PDA_VMAIN_2, 0x7c00007,
- {true, true, true} }, /* DBG_RESET_REG_MISC_PL_PDA_VMAIN_2 */
+ {true, true} }, /* DBG_RESET_REG_MISC_PL_PDA_VMAIN_2 */
{ MISC_REG_RESET_PL_PDA_VAUX, 0x2,
- {true, true, true} }, /* DBG_RESET_REG_MISC_PL_PDA_VAUX */
+ {true, true} }, /* DBG_RESET_REG_MISC_PL_PDA_VAUX */
};
static struct phy_defs s_phy_defs[] = {
@@ -1410,6 +1523,26 @@ static u32 qed_read_unaligned_dword(u8 *buf)
return dword;
}
+/* Returns the value of the specified GRC param */
+static u32 qed_grc_get_param(struct qed_hwfn *p_hwfn,
+ enum dbg_grc_params grc_param)
+{
+ struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
+
+ return dev_data->grc.param_val[grc_param];
+}
+
+/* Initializes the GRC parameters */
+static void qed_dbg_grc_init_params(struct qed_hwfn *p_hwfn)
+{
+ struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
+
+ if (!dev_data->grc.params_initialized) {
+ qed_dbg_grc_set_params_default(p_hwfn);
+ dev_data->grc.params_initialized = 1;
+ }
+}
+
/* Initializes debug data for the specified device */
static enum dbg_status qed_dbg_dev_init(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt)
@@ -1424,13 +1557,17 @@ static enum dbg_status qed_dbg_dev_init(struct qed_hwfn *p_hwfn,
dev_data->mode_enable[MODE_K2] = 1;
} else if (QED_IS_BB_B0(p_hwfn->cdev)) {
dev_data->chip_id = CHIP_BB_B0;
- dev_data->mode_enable[MODE_BB_B0] = 1;
+ dev_data->mode_enable[MODE_BB] = 1;
} else {
return DBG_STATUS_UNKNOWN_CHIP;
}
dev_data->platform_id = PLATFORM_ASIC;
dev_data->mode_enable[MODE_ASIC] = 1;
+
+ /* Initializes the GRC parameters */
+ qed_dbg_grc_init_params(p_hwfn);
+
dev_data->initialized = true;
return DBG_STATUS_OK;
}
@@ -1561,7 +1698,7 @@ static u32 qed_dump_fw_ver_param(struct qed_hwfn *p_hwfn,
int printed_chars;
u32 offset = 0;
- if (dump) {
+ if (dump && !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_FW_VER)) {
/* Read FW image/version from PRAM in a non-reset SEMI */
bool found = false;
u8 storm_id;
@@ -1622,7 +1759,7 @@ static u32 qed_dump_mfw_ver_param(struct qed_hwfn *p_hwfn,
{
char mfw_ver_str[16] = EMPTY_FW_VERSION_STR;
- if (dump) {
+ if (dump && !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_FW_VER)) {
u32 global_section_offsize, global_section_addr, mfw_ver;
u32 public_data_addr, global_section_offsize_addr;
int printed_chars;
@@ -1683,15 +1820,13 @@ static u32 qed_dump_common_global_params(struct qed_hwfn *p_hwfn,
bool dump,
u8 num_specific_global_params)
{
+ u8 num_params = NUM_COMMON_GLOBAL_PARAMS + num_specific_global_params;
struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
u32 offset = 0;
/* Find platform string and dump global params section header */
offset += qed_dump_section_hdr(dump_buf + offset,
- dump,
- "global_params",
- NUM_COMMON_GLOBAL_PARAMS +
- num_specific_global_params);
+ dump, "global_params", num_params);
/* Store params */
offset += qed_dump_fw_ver_param(p_hwfn, p_ptt, dump_buf + offset, dump);
@@ -1815,37 +1950,6 @@ static bool qed_is_mode_match(struct qed_hwfn *p_hwfn, u16 *modes_buf_offset)
}
}
-/* Returns the value of the specified GRC param */
-static u32 qed_grc_get_param(struct qed_hwfn *p_hwfn,
- enum dbg_grc_params grc_param)
-{
- struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
-
- return dev_data->grc.param_val[grc_param];
-}
-
-/* Clear all GRC params */
-static void qed_dbg_grc_clear_params(struct qed_hwfn *p_hwfn)
-{
- struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
- u32 i;
-
- for (i = 0; i < MAX_DBG_GRC_PARAMS; i++)
- dev_data->grc.param_set_by_user[i] = 0;
-}
-
-/* Assign default GRC param values */
-static void qed_dbg_grc_set_params_default(struct qed_hwfn *p_hwfn)
-{
- struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
- u32 i;
-
- for (i = 0; i < MAX_DBG_GRC_PARAMS; i++)
- if (!dev_data->grc.param_set_by_user[i])
- dev_data->grc.param_val[i] =
- s_grc_param_defs[i].default_val[dev_data->chip_id];
-}
-
/* Returns true if the specified entity (indicated by GRC param) should be
* included in the dump, false otherwise.
*/
@@ -1971,7 +2075,7 @@ static void qed_grc_unreset_blocks(struct qed_hwfn *p_hwfn,
}
}
-/* Returns the attention name offsets of the specified block */
+/* Returns the attention block data of the specified block */
static const struct dbg_attn_block_type_data *
qed_get_block_attn_data(enum block_id block_id, enum dbg_attn_type attn_type)
{
@@ -2040,7 +2144,7 @@ static void qed_grc_clear_all_prty(struct qed_hwfn *p_hwfn,
* The following parameters are dumped:
* - 'count' = num_dumped_entries
* - 'split' = split_type
- * - 'id'i = split_id (dumped only if split_id >= 0)
+ * - 'id' = split_id (dumped only if split_id >= 0)
* - 'param_name' = param_val (user param, dumped only if param_name != NULL and
* param_val != NULL)
*/
@@ -2069,21 +2173,81 @@ static u32 qed_grc_dump_regs_hdr(u32 *dump_buf,
return offset;
}
-/* Dumps GRC register/memory. Returns the dumped size in dwords. */
+/* Dumps the GRC registers in the specified address range.
+ * Returns the dumped size in dwords.
+ */
+static u32 qed_grc_dump_addr_range(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt, u32 *dump_buf,
+ bool dump, u32 addr, u32 len)
+{
+ u32 byte_addr = DWORDS_TO_BYTES(addr), offset = 0, i;
+
+ if (dump)
+ for (i = 0; i < len; i++, byte_addr += BYTES_IN_DWORD, offset++)
+ *(dump_buf + offset) = qed_rd(p_hwfn, p_ptt, byte_addr);
+ else
+ offset += len;
+ return offset;
+}
+
+/* Dumps GRC registers sequence header. Returns the dumped size in dwords. */
+static u32 qed_grc_dump_reg_entry_hdr(u32 *dump_buf, bool dump, u32 addr,
+ u32 len)
+{
+ if (dump)
+ *dump_buf = addr | (len << REG_DUMP_LEN_SHIFT);
+ return 1;
+}
+
+/* Dumps GRC registers sequence. Returns the dumped size in dwords. */
static u32 qed_grc_dump_reg_entry(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt, u32 *dump_buf,
bool dump, u32 addr, u32 len)
{
- u32 offset = 0, i;
+ u32 offset = 0;
+ offset += qed_grc_dump_reg_entry_hdr(dump_buf, dump, addr, len);
+ offset += qed_grc_dump_addr_range(p_hwfn,
+ p_ptt,
+ dump_buf + offset, dump, addr, len);
+ return offset;
+}
+
+/* Dumps GRC registers sequence with skip cycle.
+ * Returns the dumped size in dwords.
+ */
+static u32 qed_grc_dump_reg_entry_skip(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt, u32 *dump_buf,
+ bool dump, u32 addr, u32 total_len,
+ u32 read_len, u32 skip_len)
+{
+ u32 offset = 0, reg_offset = 0;
+
+ offset += qed_grc_dump_reg_entry_hdr(dump_buf, dump, addr, total_len);
if (dump) {
- *(dump_buf + offset++) = addr | (len << REG_DUMP_LEN_SHIFT);
- for (i = 0; i < len; i++, addr++, offset++)
- *(dump_buf + offset) = qed_rd(p_hwfn,
- p_ptt,
- DWORDS_TO_BYTES(addr));
+ while (reg_offset < total_len) {
+ u32 curr_len = min_t(u32,
+ read_len,
+ total_len - reg_offset);
+ offset += qed_grc_dump_addr_range(p_hwfn,
+ p_ptt,
+ dump_buf + offset,
+ dump, addr, curr_len);
+ reg_offset += curr_len;
+ addr += curr_len;
+ if (reg_offset < total_len) {
+ curr_len = min_t(u32,
+ skip_len,
+ total_len - skip_len);
+ memset(dump_buf + offset, 0,
+ DWORDS_TO_BYTES(curr_len));
+ offset += curr_len;
+ reg_offset += curr_len;
+ addr += curr_len;
+ }
+ }
} else {
- offset += len + 1;
+ offset += total_len;
}
return offset;
@@ -2124,14 +2288,17 @@ static u32 qed_grc_dump_regs_entries(struct qed_hwfn *p_hwfn,
const struct dbg_dump_reg *reg =
(const struct dbg_dump_reg *)
&input_regs_arr.ptr[input_offset];
+ u32 addr, len;
+ addr = GET_FIELD(reg->data,
+ DBG_DUMP_REG_ADDRESS);
+ len = GET_FIELD(reg->data, DBG_DUMP_REG_LENGTH);
offset +=
- qed_grc_dump_reg_entry(p_hwfn, p_ptt,
- dump_buf + offset, dump,
- GET_FIELD(reg->data,
- DBG_DUMP_REG_ADDRESS),
- GET_FIELD(reg->data,
- DBG_DUMP_REG_LENGTH));
+ qed_grc_dump_reg_entry(p_hwfn, p_ptt,
+ dump_buf + offset,
+ dump,
+ addr,
+ len);
(*num_dumped_reg_entries)++;
}
} else {
@@ -2194,8 +2361,14 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn,
const char *param_name, const char *param_val)
{
struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
+ struct chip_platform_defs *p_platform_defs;
u32 offset = 0, input_offset = 0;
- u8 port_id, pf_id;
+ struct chip_defs *p_chip_defs;
+ u8 port_id, pf_id, vf_id;
+ u16 fid;
+
+ p_chip_defs = &s_chip_defs[dev_data->chip_id];
+ p_platform_defs = &p_chip_defs->per_platform[dev_data->platform_id];
if (dump)
DP_VERBOSE(p_hwfn, QED_MSG_DEBUG, "Dumping registers...\n");
@@ -2214,7 +2387,6 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn,
switch (split_type_id) {
case SPLIT_TYPE_NONE:
- case SPLIT_TYPE_VF:
offset += qed_grc_dump_split_data(p_hwfn,
p_ptt,
curr_input_regs_arr,
@@ -2227,10 +2399,7 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn,
param_val);
break;
case SPLIT_TYPE_PORT:
- for (port_id = 0;
- port_id <
- s_chip_defs[dev_data->chip_id].
- per_platform[dev_data->platform_id].num_ports;
+ for (port_id = 0; port_id < p_platform_defs->num_ports;
port_id++) {
if (dump)
qed_port_pretend(p_hwfn, p_ptt,
@@ -2247,20 +2416,48 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn,
break;
case SPLIT_TYPE_PF:
case SPLIT_TYPE_PORT_PF:
- for (pf_id = 0;
- pf_id <
- s_chip_defs[dev_data->chip_id].
- per_platform[dev_data->platform_id].num_pfs;
+ for (pf_id = 0; pf_id < p_platform_defs->num_pfs;
pf_id++) {
- if (dump)
- qed_fid_pretend(p_hwfn, p_ptt, pf_id);
- offset += qed_grc_dump_split_data(p_hwfn,
- p_ptt,
- curr_input_regs_arr,
- dump_buf + offset,
- dump, block_enable,
- "pf", pf_id, param_name,
- param_val);
+ u8 pfid_shift =
+ PXP_PRETEND_CONCRETE_FID_PFID_SHIFT;
+
+ if (dump) {
+ fid = pf_id << pfid_shift;
+ qed_fid_pretend(p_hwfn, p_ptt, fid);
+ }
+
+ offset +=
+ qed_grc_dump_split_data(p_hwfn, p_ptt,
+ curr_input_regs_arr,
+ dump_buf + offset,
+ dump, block_enable,
+ "pf", pf_id,
+ param_name,
+ param_val);
+ }
+ break;
+ case SPLIT_TYPE_VF:
+ for (vf_id = 0; vf_id < p_platform_defs->num_vfs;
+ vf_id++) {
+ u8 vfvalid_shift =
+ PXP_PRETEND_CONCRETE_FID_VFVALID_SHIFT;
+ u8 vfid_shift =
+ PXP_PRETEND_CONCRETE_FID_VFID_SHIFT;
+
+ if (dump) {
+ fid = BIT(vfvalid_shift) |
+ (vf_id << vfid_shift);
+ qed_fid_pretend(p_hwfn, p_ptt, fid);
+ }
+
+ offset +=
+ qed_grc_dump_split_data(p_hwfn, p_ptt,
+ curr_input_regs_arr,
+ dump_buf + offset,
+ dump, block_enable,
+ "vf", vf_id,
+ param_name,
+ param_val);
}
break;
default:
@@ -2271,8 +2468,11 @@ static u32 qed_grc_dump_registers(struct qed_hwfn *p_hwfn,
}
/* Pretend to original PF */
- if (dump)
- qed_fid_pretend(p_hwfn, p_ptt, p_hwfn->rel_pf_id);
+ if (dump) {
+ fid = p_hwfn->rel_pf_id << PXP_PRETEND_CONCRETE_FID_PFID_SHIFT;
+ qed_fid_pretend(p_hwfn, p_ptt, fid);
+ }
+
return offset;
}
@@ -2291,13 +2491,14 @@ static u32 qed_grc_dump_reset_regs(struct qed_hwfn *p_hwfn,
/* Write reset registers */
for (i = 0; i < MAX_DBG_RESET_REGS; i++) {
if (s_reset_regs_defs[i].exists[dev_data->chip_id]) {
+ u32 addr = BYTES_TO_DWORDS(s_reset_regs_defs[i].addr);
+
offset += qed_grc_dump_reg_entry(p_hwfn,
p_ptt,
dump_buf + offset,
dump,
- BYTES_TO_DWORDS
- (s_reset_regs_defs
- [i].addr), 1);
+ addr,
+ 1);
num_regs++;
}
}
@@ -2339,6 +2540,7 @@ static u32 qed_grc_dump_modified_regs(struct qed_hwfn *p_hwfn,
&attn_reg_arr[reg_idx];
u16 modes_buf_offset;
bool eval_mode;
+ u32 addr;
/* Check mode */
eval_mode = GET_FIELD(reg_data->mode.data,
@@ -2349,19 +2551,23 @@ static u32 qed_grc_dump_modified_regs(struct qed_hwfn *p_hwfn,
if (!eval_mode ||
qed_is_mode_match(p_hwfn, &modes_buf_offset)) {
/* Mode match - read and dump registers */
- offset += qed_grc_dump_reg_entry(p_hwfn,
- p_ptt,
- dump_buf + offset,
- dump,
- reg_data->mask_address,
- 1);
- offset += qed_grc_dump_reg_entry(p_hwfn,
- p_ptt,
- dump_buf + offset,
- dump,
- GET_FIELD(reg_data->data,
- DBG_ATTN_REG_STS_ADDRESS),
- 1);
+ addr = reg_data->mask_address;
+ offset +=
+ qed_grc_dump_reg_entry(p_hwfn,
+ p_ptt,
+ dump_buf + offset,
+ dump,
+ addr,
+ 1);
+ addr = GET_FIELD(reg_data->data,
+ DBG_ATTN_REG_STS_ADDRESS);
+ offset +=
+ qed_grc_dump_reg_entry(p_hwfn,
+ p_ptt,
+ dump_buf + offset,
+ dump,
+ addr,
+ 1);
num_reg_entries += 2;
}
}
@@ -2369,18 +2575,21 @@ static u32 qed_grc_dump_modified_regs(struct qed_hwfn *p_hwfn,
/* Write storm stall status registers */
for (storm_id = 0; storm_id < MAX_DBG_STORMS; storm_id++) {
+ u32 addr;
+
if (dev_data->block_in_reset[s_storm_defs[storm_id].block_id] &&
dump)
continue;
+ addr =
+ BYTES_TO_DWORDS(s_storm_defs[storm_id].sem_fast_mem_addr +
+ SEM_FAST_REG_STALLED);
offset += qed_grc_dump_reg_entry(p_hwfn,
- p_ptt,
- dump_buf + offset,
- dump,
- BYTES_TO_DWORDS(s_storm_defs[storm_id].
- sem_fast_mem_addr +
- SEM_FAST_REG_STALLED),
- 1);
+ p_ptt,
+ dump_buf + offset,
+ dump,
+ addr,
+ 1);
num_reg_entries++;
}
@@ -2392,11 +2601,47 @@ static u32 qed_grc_dump_modified_regs(struct qed_hwfn *p_hwfn,
return offset;
}
+/* Dumps registers that can't be represented in the debug arrays */
+static u32 qed_grc_dump_special_regs(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ u32 *dump_buf, bool dump)
+{
+ u32 offset = 0, addr;
+
+ offset += qed_grc_dump_regs_hdr(dump_buf,
+ dump, 2, "eng", -1, NULL, NULL);
+
+ /* Dump R/TDIF_REG_DEBUG_ERROR_INFO_SIZE (every 8'th register should be
+ * skipped).
+ */
+ addr = BYTES_TO_DWORDS(RDIF_REG_DEBUG_ERROR_INFO);
+ offset += qed_grc_dump_reg_entry_skip(p_hwfn,
+ p_ptt,
+ dump_buf + offset,
+ dump,
+ addr,
+ RDIF_REG_DEBUG_ERROR_INFO_SIZE,
+ 7,
+ 1);
+ addr = BYTES_TO_DWORDS(TDIF_REG_DEBUG_ERROR_INFO);
+ offset +=
+ qed_grc_dump_reg_entry_skip(p_hwfn,
+ p_ptt,
+ dump_buf + offset,
+ dump,
+ addr,
+ TDIF_REG_DEBUG_ERROR_INFO_SIZE,
+ 7,
+ 1);
+
+ return offset;
+}
+
/* Dumps a GRC memory header (section and params).
* The following parameters are dumped:
* name - name is dumped only if it's not NULL.
- * addr - byte_addr is dumped only if name is NULL.
- * len - dword_len is always dumped.
+ * addr - addr is dumped only if name is NULL.
+ * len - len is always dumped.
* width - bit_width is dumped if it's not zero.
* packed - packed=1 is dumped if it's not false.
* mem_group - mem_group is always dumped.
@@ -2408,8 +2653,8 @@ static u32 qed_grc_dump_mem_hdr(struct qed_hwfn *p_hwfn,
u32 *dump_buf,
bool dump,
const char *name,
- u32 byte_addr,
- u32 dword_len,
+ u32 addr,
+ u32 len,
u32 bit_width,
bool packed,
const char *mem_group,
@@ -2419,7 +2664,7 @@ static u32 qed_grc_dump_mem_hdr(struct qed_hwfn *p_hwfn,
u32 offset = 0;
char buf[64];
- if (!dword_len)
+ if (!len)
DP_NOTICE(p_hwfn,
"Unexpected GRC Dump error: dumped memory size must be non-zero\n");
if (bit_width)
@@ -2446,20 +2691,21 @@ static u32 qed_grc_dump_mem_hdr(struct qed_hwfn *p_hwfn,
DP_VERBOSE(p_hwfn,
QED_MSG_DEBUG,
"Dumping %d registers from %s...\n",
- dword_len, buf);
+ len, buf);
} else {
/* Dump address */
offset += qed_dump_num_param(dump_buf + offset,
- dump, "addr", byte_addr);
- if (dump && dword_len > 64)
+ dump, "addr",
+ DWORDS_TO_BYTES(addr));
+ if (dump && len > 64)
DP_VERBOSE(p_hwfn,
QED_MSG_DEBUG,
"Dumping %d registers from address 0x%x...\n",
- dword_len, byte_addr);
+ len, (u32)DWORDS_TO_BYTES(addr));
}
/* Dump len */
- offset += qed_dump_num_param(dump_buf + offset, dump, "len", dword_len);
+ offset += qed_dump_num_param(dump_buf + offset, dump, "len", len);
/* Dump bit width */
if (bit_width)
@@ -2492,8 +2738,8 @@ static u32 qed_grc_dump_mem(struct qed_hwfn *p_hwfn,
u32 *dump_buf,
bool dump,
const char *name,
- u32 byte_addr,
- u32 dword_len,
+ u32 addr,
+ u32 len,
u32 bit_width,
bool packed,
const char *mem_group,
@@ -2505,21 +2751,14 @@ static u32 qed_grc_dump_mem(struct qed_hwfn *p_hwfn,
dump_buf + offset,
dump,
name,
- byte_addr,
- dword_len,
+ addr,
+ len,
bit_width,
packed,
mem_group, is_storm, storm_letter);
- if (dump) {
- u32 i;
-
- for (i = 0; i < dword_len;
- i++, byte_addr += BYTES_IN_DWORD, offset++)
- *(dump_buf + offset) = qed_rd(p_hwfn, p_ptt, byte_addr);
- } else {
- offset += dword_len;
- }
-
+ offset += qed_grc_dump_addr_range(p_hwfn,
+ p_ptt,
+ dump_buf + offset, dump, addr, len);
return offset;
}
@@ -2575,25 +2814,41 @@ static u32 qed_grc_dump_mem_entries(struct qed_hwfn *p_hwfn,
if (qed_grc_is_mem_included(p_hwfn,
(enum block_id)cond_hdr->block_id,
mem_group_id)) {
- u32 mem_byte_addr =
- DWORDS_TO_BYTES(GET_FIELD(mem->dword0,
- DBG_DUMP_MEM_ADDRESS));
+ u32 mem_addr = GET_FIELD(mem->dword0,
+ DBG_DUMP_MEM_ADDRESS);
u32 mem_len = GET_FIELD(mem->dword1,
DBG_DUMP_MEM_LENGTH);
+ enum dbg_grc_params grc_param;
char storm_letter = 'a';
bool is_storm = false;
/* Update memory length for CCFC/TCFC memories
* according to number of LCIDs/LTIDs.
*/
- if (mem_group_id == MEM_GROUP_CONN_CFC_MEM)
+ if (mem_group_id == MEM_GROUP_CONN_CFC_MEM) {
+ if (mem_len % MAX_LCIDS != 0) {
+ DP_NOTICE(p_hwfn,
+ "Invalid CCFC connection memory size\n");
+ return 0;
+ }
+
+ grc_param = DBG_GRC_PARAM_NUM_LCIDS;
mem_len = qed_grc_get_param(p_hwfn,
- DBG_GRC_PARAM_NUM_LCIDS)
- * (mem_len / MAX_LCIDS);
- else if (mem_group_id == MEM_GROUP_TASK_CFC_MEM)
+ grc_param) *
+ (mem_len / MAX_LCIDS);
+ } else if (mem_group_id ==
+ MEM_GROUP_TASK_CFC_MEM) {
+ if (mem_len % MAX_LTIDS != 0) {
+ DP_NOTICE(p_hwfn,
+ "Invalid TCFC task memory size\n");
+ return 0;
+ }
+
+ grc_param = DBG_GRC_PARAM_NUM_LTIDS;
mem_len = qed_grc_get_param(p_hwfn,
- DBG_GRC_PARAM_NUM_LTIDS)
- * (mem_len / MAX_LTIDS);
+ grc_param) *
+ (mem_len / MAX_LTIDS);
+ }
/* If memory is associated with Storm, update
* Storm details.
@@ -2610,7 +2865,7 @@ static u32 qed_grc_dump_mem_entries(struct qed_hwfn *p_hwfn,
/* Dump memory */
offset += qed_grc_dump_mem(p_hwfn, p_ptt,
dump_buf + offset, dump, NULL,
- mem_byte_addr, mem_len, 0,
+ mem_addr, mem_len, 0,
false,
s_mem_group_names[mem_group_id],
is_storm, storm_letter);
@@ -2799,29 +3054,31 @@ static u32 qed_grc_dump_iors(struct qed_hwfn *p_hwfn,
u32 offset = 0;
for (storm_id = 0; storm_id < MAX_DBG_STORMS; storm_id++) {
- if (qed_grc_is_storm_included(p_hwfn,
- (enum dbg_storms)storm_id)) {
- for (set_id = 0; set_id < NUM_IOR_SETS; set_id++) {
- u32 addr =
- s_storm_defs[storm_id].sem_fast_mem_addr +
- SEM_FAST_REG_STORM_REG_FILE +
- DWORDS_TO_BYTES(IOR_SET_OFFSET(set_id));
+ struct storm_defs *storm = &s_storm_defs[storm_id];
- buf[strlen(buf) - 1] = '0' + set_id;
- offset += qed_grc_dump_mem(p_hwfn,
- p_ptt,
- dump_buf + offset,
- dump,
- buf,
- addr,
- IORS_PER_SET,
- 32,
- false,
- "ior",
- true,
- s_storm_defs
- [storm_id].letter);
- }
+ if (!qed_grc_is_storm_included(p_hwfn,
+ (enum dbg_storms)storm_id))
+ continue;
+
+ for (set_id = 0; set_id < NUM_IOR_SETS; set_id++) {
+ u32 dwords, addr;
+
+ dwords = storm->sem_fast_mem_addr +
+ SEM_FAST_REG_STORM_REG_FILE;
+ addr = BYTES_TO_DWORDS(dwords) + IOR_SET_OFFSET(set_id);
+ buf[strlen(buf) - 1] = '0' + set_id;
+ offset += qed_grc_dump_mem(p_hwfn,
+ p_ptt,
+ dump_buf + offset,
+ dump,
+ buf,
+ addr,
+ IORS_PER_SET,
+ 32,
+ false,
+ "ior",
+ true,
+ storm->letter);
}
}
@@ -2990,34 +3247,39 @@ static u32 qed_grc_dump_rss(struct qed_hwfn *p_hwfn,
struct rss_mem_defs *rss_defs = &s_rss_mem_defs[rss_mem_id];
u32 num_entries = rss_defs->num_entries[dev_data->chip_id];
u32 entry_width = rss_defs->entry_width[dev_data->chip_id];
- u32 total_size = (num_entries * entry_width) / 32;
+ u32 total_dwords = (num_entries * entry_width) / 32;
+ u32 size = RSS_REG_RSS_RAM_DATA_SIZE;
bool packed = (entry_width == 16);
- u32 addr = rss_defs->addr;
- u32 i, j;
+ u32 rss_addr = rss_defs->addr;
+ u32 i, addr;
offset += qed_grc_dump_mem_hdr(p_hwfn,
dump_buf + offset,
dump,
rss_defs->mem_name,
- addr,
- total_size,
+ 0,
+ total_dwords,
entry_width,
packed,
rss_defs->type_name, false, 0);
if (!dump) {
- offset += total_size;
+ offset += total_dwords;
continue;
}
/* Dump RSS data */
- for (i = 0; i < BYTES_TO_DWORDS(total_size); i++, addr++) {
- qed_wr(p_hwfn, p_ptt, RSS_REG_RSS_RAM_ADDR, addr);
- for (j = 0; j < BYTES_IN_DWORD; j++, offset++)
- *(dump_buf + offset) =
- qed_rd(p_hwfn, p_ptt,
- RSS_REG_RSS_RAM_DATA +
- DWORDS_TO_BYTES(j));
+ for (i = 0; i < total_dwords;
+ i += RSS_REG_RSS_RAM_DATA_SIZE, rss_addr++) {
+ addr = BYTES_TO_DWORDS(RSS_REG_RSS_RAM_DATA);
+ qed_wr(p_hwfn, p_ptt, RSS_REG_RSS_RAM_ADDR, rss_addr);
+ offset += qed_grc_dump_addr_range(p_hwfn,
+ p_ptt,
+ dump_buf +
+ offset,
+ dump,
+ addr,
+ size);
}
}
@@ -3030,19 +3292,19 @@ static u32 qed_grc_dump_big_ram(struct qed_hwfn *p_hwfn,
u32 *dump_buf, bool dump, u8 big_ram_id)
{
struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
+ u32 total_blocks, ram_size, offset = 0, i;
char mem_name[12] = "???_BIG_RAM";
char type_name[8] = "???_RAM";
- u32 ram_size, total_blocks;
- u32 offset = 0, i, j;
+ struct big_ram_defs *big_ram;
- total_blocks =
- s_big_ram_defs[big_ram_id].num_of_blocks[dev_data->chip_id];
+ big_ram = &s_big_ram_defs[big_ram_id];
+ total_blocks = big_ram->num_of_blocks[dev_data->chip_id];
ram_size = total_blocks * BIG_RAM_BLOCK_SIZE_DWORDS;
- strncpy(type_name, s_big_ram_defs[big_ram_id].instance_name,
- strlen(s_big_ram_defs[big_ram_id].instance_name));
- strncpy(mem_name, s_big_ram_defs[big_ram_id].instance_name,
- strlen(s_big_ram_defs[big_ram_id].instance_name));
+ strncpy(type_name, big_ram->instance_name,
+ strlen(big_ram->instance_name));
+ strncpy(mem_name, big_ram->instance_name,
+ strlen(big_ram->instance_name));
/* Dump memory header */
offset += qed_grc_dump_mem_hdr(p_hwfn,
@@ -3059,13 +3321,17 @@ static u32 qed_grc_dump_big_ram(struct qed_hwfn *p_hwfn,
/* Read and dump Big RAM data */
for (i = 0; i < total_blocks / 2; i++) {
- qed_wr(p_hwfn, p_ptt, s_big_ram_defs[big_ram_id].addr_reg_addr,
- i);
- for (j = 0; j < 2 * BIG_RAM_BLOCK_SIZE_DWORDS; j++, offset++)
- *(dump_buf + offset) = qed_rd(p_hwfn, p_ptt,
- s_big_ram_defs[big_ram_id].
- data_reg_addr +
- DWORDS_TO_BYTES(j));
+ u32 addr, len;
+
+ qed_wr(p_hwfn, p_ptt, big_ram->addr_reg_addr, i);
+ addr = BYTES_TO_DWORDS(big_ram->data_reg_addr);
+ len = 2 * BIG_RAM_BLOCK_SIZE_DWORDS;
+ offset += qed_grc_dump_addr_range(p_hwfn,
+ p_ptt,
+ dump_buf + offset,
+ dump,
+ addr,
+ len);
}
return offset;
@@ -3075,11 +3341,11 @@ static u32 qed_grc_dump_mcp(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt, u32 *dump_buf, bool dump)
{
bool block_enable[MAX_BLOCK_ID] = { 0 };
+ u32 offset = 0, addr;
bool halted = false;
- u32 offset = 0;
/* Halt MCP */
- if (dump) {
+ if (dump && !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_MCP)) {
halted = !qed_mcp_halt(p_hwfn, p_ptt);
if (!halted)
DP_NOTICE(p_hwfn, "MCP halt failed!\n");
@@ -3091,7 +3357,7 @@ static u32 qed_grc_dump_mcp(struct qed_hwfn *p_hwfn,
dump_buf + offset,
dump,
NULL,
- MCP_REG_SCRATCH,
+ BYTES_TO_DWORDS(MCP_REG_SCRATCH),
MCP_REG_SCRATCH_SIZE,
0, false, "MCP", false, 0);
@@ -3101,7 +3367,7 @@ static u32 qed_grc_dump_mcp(struct qed_hwfn *p_hwfn,
dump_buf + offset,
dump,
NULL,
- MCP_REG_CPU_REG_FILE,
+ BYTES_TO_DWORDS(MCP_REG_CPU_REG_FILE),
MCP_REG_CPU_REG_FILE_SIZE,
0, false, "MCP", false, 0);
@@ -3115,12 +3381,13 @@ static u32 qed_grc_dump_mcp(struct qed_hwfn *p_hwfn,
/* Dump required non-MCP registers */
offset += qed_grc_dump_regs_hdr(dump_buf + offset,
dump, 1, "eng", -1, "block", "MCP");
+ addr = BYTES_TO_DWORDS(MISC_REG_SHARED_MEM_ADDR);
offset += qed_grc_dump_reg_entry(p_hwfn,
p_ptt,
dump_buf + offset,
dump,
- BYTES_TO_DWORDS
- (MISC_REG_SHARED_MEM_ADDR), 1);
+ addr,
+ 1);
/* Release MCP */
if (halted && qed_mcp_resume(p_hwfn, p_ptt))
@@ -3212,7 +3479,7 @@ static u32 qed_grc_dump_static_debug(struct qed_hwfn *p_hwfn,
{
u32 block_dwords = NUM_DBG_BUS_LINES * STATIC_DEBUG_LINE_DWORDS;
struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
- u32 offset = 0, block_id, line_id, addr, i;
+ u32 offset = 0, block_id, line_id;
struct block_defs *p_block_defs;
if (dump) {
@@ -3255,6 +3522,8 @@ static u32 qed_grc_dump_static_debug(struct qed_hwfn *p_hwfn,
if (dump && !dev_data->block_in_reset[block_id]) {
u8 dbg_client_id =
p_block_defs->dbg_client_id[dev_data->chip_id];
+ u32 addr = BYTES_TO_DWORDS(DBG_REG_CALENDAR_OUT_DATA);
+ u32 len = STATIC_DEBUG_LINE_DWORDS;
/* Enable block's client */
qed_bus_enable_clients(p_hwfn, p_ptt,
@@ -3270,11 +3539,13 @@ static u32 qed_grc_dump_static_debug(struct qed_hwfn *p_hwfn,
0xf, 0, 0, 0);
/* Read debug line info */
- for (i = 0, addr = DBG_REG_CALENDAR_OUT_DATA;
- i < STATIC_DEBUG_LINE_DWORDS;
- i++, offset++, addr += BYTES_IN_DWORD)
- dump_buf[offset] = qed_rd(p_hwfn, p_ptt,
- addr);
+ offset +=
+ qed_grc_dump_addr_range(p_hwfn,
+ p_ptt,
+ dump_buf + offset,
+ dump,
+ addr,
+ len);
}
/* Disable block's client and debug output */
@@ -3311,14 +3582,8 @@ static enum dbg_status qed_grc_dump(struct qed_hwfn *p_hwfn,
u8 i, port_mode = 0;
u32 offset = 0;
- /* Check if emulation platform */
*num_dumped_dwords = 0;
- /* Fill GRC parameters that were not set by the user with their default
- * value.
- */
- qed_dbg_grc_set_params_default(p_hwfn);
-
/* Find port mode */
if (dump) {
switch (qed_rd(p_hwfn, p_ptt, MISC_REG_PORT_MODE)) {
@@ -3370,15 +3635,14 @@ static enum dbg_status qed_grc_dump(struct qed_hwfn *p_hwfn,
}
/* Disable all parities using MFW command */
- if (dump) {
+ if (dump && !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_MCP)) {
parities_masked = !qed_mcp_mask_parities(p_hwfn, p_ptt, 1);
if (!parities_masked) {
+ DP_NOTICE(p_hwfn,
+ "Failed to mask parities using MFW\n");
if (qed_grc_get_param
(p_hwfn, DBG_GRC_PARAM_PARITY_SAFE))
return DBG_STATUS_MCP_COULD_NOT_MASK_PRTY;
- else
- DP_NOTICE(p_hwfn,
- "Failed to mask parities using MFW\n");
}
}
@@ -3409,6 +3673,11 @@ static enum dbg_status qed_grc_dump(struct qed_hwfn *p_hwfn,
offset,
dump,
block_enable, NULL, NULL);
+
+ /* Dump special registers */
+ offset += qed_grc_dump_special_regs(p_hwfn,
+ p_ptt,
+ dump_buf + offset, dump);
}
/* Dump memories */
@@ -3583,9 +3852,9 @@ static u32 qed_idle_chk_dump_failure(struct qed_hwfn *p_hwfn,
}
if (mode_match) {
- u32 grc_addr =
- DWORDS_TO_BYTES(GET_FIELD(reg->data,
- DBG_IDLE_CHK_INFO_REG_ADDRESS));
+ u32 addr =
+ GET_FIELD(reg->data,
+ DBG_IDLE_CHK_INFO_REG_ADDRESS);
/* Write register header */
struct dbg_idle_chk_result_reg_hdr *reg_hdr =
@@ -3597,16 +3866,19 @@ static u32 qed_idle_chk_dump_failure(struct qed_hwfn *p_hwfn,
memset(reg_hdr, 0, sizeof(*reg_hdr));
reg_hdr->size = reg->size;
SET_FIELD(reg_hdr->data,
- DBG_IDLE_CHK_RESULT_REG_HDR_REG_ID,
- rule->num_cond_regs + reg_id);
+ DBG_IDLE_CHK_RESULT_REG_HDR_REG_ID,
+ rule->num_cond_regs + reg_id);
/* Write register values */
- for (i = 0; i < reg->size;
- i++, offset++, grc_addr += 4)
- dump_buf[offset] =
- qed_rd(p_hwfn, p_ptt, grc_addr);
- }
+ offset +=
+ qed_grc_dump_addr_range(p_hwfn,
+ p_ptt,
+ dump_buf + offset,
+ dump,
+ addr,
+ reg->size);
}
+ }
}
return offset;
@@ -3621,7 +3893,7 @@ qed_idle_chk_dump_rule_entries(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
{
struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
u32 cond_reg_values[IDLE_CHK_MAX_ENTRIES_SIZE];
- u32 i, j, offset = 0;
+ u32 i, offset = 0;
u16 entry_id;
u8 reg_id;
@@ -3664,73 +3936,83 @@ qed_idle_chk_dump_rule_entries(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
if (!check_rule && dump)
continue;
+ if (!dump) {
+ u32 entry_dump_size =
+ qed_idle_chk_dump_failure(p_hwfn,
+ p_ptt,
+ dump_buf + offset,
+ false,
+ rule->rule_id,
+ rule,
+ 0,
+ NULL);
+
+ offset += num_reg_entries * entry_dump_size;
+ (*num_failing_rules) += num_reg_entries;
+ continue;
+ }
+
/* Go over all register entries (number of entries is the same
* for all condition registers).
*/
for (entry_id = 0; entry_id < num_reg_entries; entry_id++) {
/* Read current entry of all condition registers */
- if (dump) {
- u32 next_reg_offset = 0;
+ u32 next_reg_offset = 0;
- for (reg_id = 0;
- reg_id < rule->num_cond_regs;
- reg_id++) {
- const struct dbg_idle_chk_cond_reg
- *reg = &cond_regs[reg_id];
+ for (reg_id = 0; reg_id < rule->num_cond_regs;
+ reg_id++) {
+ const struct dbg_idle_chk_cond_reg *reg =
+ &cond_regs[reg_id];
- /* Find GRC address (if it's a memory,
- * the address of the specific entry is
- * calculated).
- */
- u32 grc_addr =
- DWORDS_TO_BYTES(
- GET_FIELD(reg->data,
- DBG_IDLE_CHK_COND_REG_ADDRESS));
+ /* Find GRC address (if it's a memory,the
+ * address of the specific entry is calculated).
+ */
+ u32 addr =
+ GET_FIELD(reg->data,
+ DBG_IDLE_CHK_COND_REG_ADDRESS);
- if (reg->num_entries > 1 ||
- reg->start_entry > 0) {
- u32 padded_entry_size =
- reg->entry_size > 1 ?
- roundup_pow_of_two
- (reg->entry_size) : 1;
+ if (reg->num_entries > 1 ||
+ reg->start_entry > 0) {
+ u32 padded_entry_size =
+ reg->entry_size > 1 ?
+ roundup_pow_of_two(reg->entry_size) :
+ 1;
- grc_addr +=
- DWORDS_TO_BYTES(
- (reg->start_entry +
- entry_id)
- * padded_entry_size);
- }
-
- /* Read registers */
- if (next_reg_offset + reg->entry_size >=
- IDLE_CHK_MAX_ENTRIES_SIZE) {
- DP_NOTICE(p_hwfn,
- "idle check registers entry is too large\n");
- return 0;
- }
-
- for (j = 0; j < reg->entry_size;
- j++, next_reg_offset++,
- grc_addr += 4)
- cond_reg_values[next_reg_offset] =
- qed_rd(p_hwfn, p_ptt, grc_addr);
+ addr += (reg->start_entry + entry_id) *
+ padded_entry_size;
}
+
+ /* Read registers */
+ if (next_reg_offset + reg->entry_size >=
+ IDLE_CHK_MAX_ENTRIES_SIZE) {
+ DP_NOTICE(p_hwfn,
+ "idle check registers entry is too large\n");
+ return 0;
+ }
+
+ next_reg_offset +=
+ qed_grc_dump_addr_range(p_hwfn,
+ p_ptt,
+ cond_reg_values +
+ next_reg_offset,
+ dump, addr,
+ reg->entry_size);
}
/* Call rule's condition function - a return value of
* true indicates failure.
*/
if ((*cond_arr[rule->cond_id])(cond_reg_values,
- imm_values) || !dump) {
+ imm_values)) {
offset +=
- qed_idle_chk_dump_failure(p_hwfn,
- p_ptt,
- dump_buf + offset,
- dump,
- rule->rule_id,
- rule,
- entry_id,
- cond_reg_values);
+ qed_idle_chk_dump_failure(p_hwfn,
+ p_ptt,
+ dump_buf + offset,
+ dump,
+ rule->rule_id,
+ rule,
+ entry_id,
+ cond_reg_values);
(*num_failing_rules)++;
break;
}
@@ -3818,13 +4100,18 @@ static enum dbg_status qed_find_nvram_image(struct qed_hwfn *p_hwfn,
struct mcp_file_att file_att;
/* Call NVRAM get file command */
- if (qed_mcp_nvm_rd_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_NVM_GET_FILE_ATT,
- image_type, &ret_mcp_resp, &ret_mcp_param,
- &ret_txn_size, (u32 *)&file_att) != 0)
- return DBG_STATUS_NVRAM_GET_IMAGE_FAILED;
+ int nvm_result = qed_mcp_nvm_rd_cmd(p_hwfn,
+ p_ptt,
+ DRV_MSG_CODE_NVM_GET_FILE_ATT,
+ image_type,
+ &ret_mcp_resp,
+ &ret_mcp_param,
+ &ret_txn_size,
+ (u32 *)&file_att);
/* Check response */
- if ((ret_mcp_resp & FW_MSG_CODE_MASK) != FW_MSG_CODE_NVM_OK)
+ if (nvm_result ||
+ (ret_mcp_resp & FW_MSG_CODE_MASK) != FW_MSG_CODE_NVM_OK)
return DBG_STATUS_NVRAM_GET_IMAGE_FAILED;
/* Update return values */
@@ -3944,7 +4231,6 @@ static enum dbg_status qed_mcp_trace_get_meta_info(struct qed_hwfn *p_hwfn,
u32 running_mfw_addr =
MCP_REG_SCRATCH + SECTION_OFFSET(spad_trace_offsize) +
QED_SECTION_SIZE(spad_trace_offsize) + trace_data_size_bytes;
- enum dbg_status status;
u32 nvram_image_type;
*running_bundle_id = qed_rd(p_hwfn, p_ptt, running_mfw_addr);
@@ -3955,30 +4241,12 @@ static enum dbg_status qed_mcp_trace_get_meta_info(struct qed_hwfn *p_hwfn,
nvram_image_type =
(*running_bundle_id ==
DIR_ID_1) ? NVM_TYPE_MFW_TRACE1 : NVM_TYPE_MFW_TRACE2;
- status = qed_find_nvram_image(p_hwfn,
- p_ptt,
- nvram_image_type,
- trace_meta_offset_bytes,
- trace_meta_size_bytes);
- return status;
-}
-
-/* Reads the MCP Trace data from the specified GRC address into the specified
- * buffer.
- */
-static void qed_mcp_trace_read_data(struct qed_hwfn *p_hwfn,
- struct qed_ptt *p_ptt,
- u32 grc_addr, u32 size_in_dwords, u32 *buf)
-{
- u32 i;
-
- DP_VERBOSE(p_hwfn,
- QED_MSG_DEBUG,
- "mcp_trace_read_data: reading trace data of size %d dwords from GRC address 0x%x\n",
- size_in_dwords, grc_addr);
- for (i = 0; i < size_in_dwords; i++, grc_addr += BYTES_IN_DWORD)
- buf[i] = qed_rd(p_hwfn, p_ptt, grc_addr);
+ return qed_find_nvram_image(p_hwfn,
+ p_ptt,
+ nvram_image_type,
+ trace_meta_offset_bytes,
+ trace_meta_size_bytes);
}
/* Reads the MCP Trace meta data (from NVRAM or buffer) into the specified
@@ -4034,11 +4302,14 @@ static enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn,
bool dump, u32 *num_dumped_dwords)
{
u32 trace_data_grc_addr, trace_data_size_bytes, trace_data_size_dwords;
- u32 trace_meta_size_dwords, running_bundle_id, offset = 0;
- u32 trace_meta_offset_bytes, trace_meta_size_bytes;
+ u32 trace_meta_size_dwords = 0, running_bundle_id, offset = 0;
+ u32 trace_meta_offset_bytes = 0, trace_meta_size_bytes = 0;
enum dbg_status status;
+ bool mcp_access;
int halted = 0;
+ mcp_access = !qed_grc_get_param(p_hwfn, DBG_GRC_PARAM_NO_MCP);
+
*num_dumped_dwords = 0;
/* Get trace data info */
@@ -4060,7 +4331,7 @@ static enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn,
* consistent if halt fails, MCP trace is taken anyway, with a small
* risk that it may be corrupt.
*/
- if (dump) {
+ if (dump && mcp_access) {
halted = !qed_mcp_halt(p_hwfn, p_ptt);
if (!halted)
DP_NOTICE(p_hwfn, "MCP halt failed!\n");
@@ -4078,13 +4349,12 @@ static enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn,
dump, "size", trace_data_size_dwords);
/* Read trace data from scratchpad into dump buffer */
- if (dump)
- qed_mcp_trace_read_data(p_hwfn,
- p_ptt,
- trace_data_grc_addr,
- trace_data_size_dwords,
- dump_buf + offset);
- offset += trace_data_size_dwords;
+ offset += qed_grc_dump_addr_range(p_hwfn,
+ p_ptt,
+ dump_buf + offset,
+ dump,
+ BYTES_TO_DWORDS(trace_data_grc_addr),
+ trace_data_size_dwords);
/* Resume MCP (only if halt succeeded) */
if (halted && qed_mcp_resume(p_hwfn, p_ptt) != 0)
@@ -4095,38 +4365,38 @@ static enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn,
dump, "mcp_trace_meta", 1);
/* Read trace meta info */
- status = qed_mcp_trace_get_meta_info(p_hwfn,
- p_ptt,
- trace_data_size_bytes,
- &running_bundle_id,
- &trace_meta_offset_bytes,
- &trace_meta_size_bytes);
- if (status != DBG_STATUS_OK)
- return status;
-
- /* Dump trace meta size param (trace_meta_size_bytes is always
- * dword-aligned).
- */
- trace_meta_size_dwords = BYTES_TO_DWORDS(trace_meta_size_bytes);
- offset += qed_dump_num_param(dump_buf + offset, dump, "size",
- trace_meta_size_dwords);
-
- /* Read trace meta image into dump buffer */
- if (dump) {
- status = qed_mcp_trace_read_meta(p_hwfn,
- p_ptt,
- trace_meta_offset_bytes,
- trace_meta_size_bytes,
- dump_buf + offset);
- if (status != DBG_STATUS_OK)
- return status;
+ if (mcp_access) {
+ status = qed_mcp_trace_get_meta_info(p_hwfn,
+ p_ptt,
+ trace_data_size_bytes,
+ &running_bundle_id,
+ &trace_meta_offset_bytes,
+ &trace_meta_size_bytes);
+ if (status == DBG_STATUS_OK)
+ trace_meta_size_dwords =
+ BYTES_TO_DWORDS(trace_meta_size_bytes);
}
- offset += trace_meta_size_dwords;
+ /* Dump trace meta size param */
+ offset += qed_dump_num_param(dump_buf + offset,
+ dump, "size", trace_meta_size_dwords);
+
+ /* Read trace meta image into dump buffer */
+ if (dump && trace_meta_size_dwords)
+ status = qed_mcp_trace_read_meta(p_hwfn,
+ p_ptt,
+ trace_meta_offset_bytes,
+ trace_meta_size_bytes,
+ dump_buf + offset);
+ if (status == DBG_STATUS_OK)
+ offset += trace_meta_size_dwords;
*num_dumped_dwords = offset;
- return DBG_STATUS_OK;
+ /* If no mcp access, indicate that the dump doesn't contain the meta
+ * data from NVRAM.
+ */
+ return mcp_access ? status : DBG_STATUS_NVRAM_GET_IMAGE_FAILED;
}
/* Dump GRC FIFO */
@@ -4311,9 +4581,10 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt, u32 *dump_buf, bool dump)
{
struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
+ struct fw_asserts_ram_section *asserts;
char storm_letter_str[2] = "?";
struct fw_info fw_info;
- u32 offset = 0, i;
+ u32 offset = 0;
u8 storm_id;
/* Dump global params */
@@ -4323,8 +4594,8 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn,
offset += qed_dump_str_param(dump_buf + offset,
dump, "dump-type", "fw-asserts");
for (storm_id = 0; storm_id < MAX_DBG_STORMS; storm_id++) {
- u32 fw_asserts_section_addr, next_list_idx_addr, next_list_idx,
- last_list_idx, element_addr;
+ u32 fw_asserts_section_addr, next_list_idx_addr, next_list_idx;
+ u32 last_list_idx, addr;
if (dev_data->block_in_reset[s_storm_defs[storm_id].block_id])
continue;
@@ -4332,6 +4603,8 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn,
/* Read FW info for the current Storm */
qed_read_fw_info(p_hwfn, p_ptt, storm_id, &fw_info);
+ asserts = &fw_info.fw_asserts_section;
+
/* Dump FW Asserts section header and params */
storm_letter_str[0] = s_storm_defs[storm_id].letter;
offset += qed_dump_section_hdr(dump_buf + offset, dump,
@@ -4339,12 +4612,10 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn,
offset += qed_dump_str_param(dump_buf + offset, dump, "storm",
storm_letter_str);
offset += qed_dump_num_param(dump_buf + offset, dump, "size",
- fw_info.fw_asserts_section.
- list_element_dword_size);
+ asserts->list_element_dword_size);
if (!dump) {
- offset += fw_info.fw_asserts_section.
- list_element_dword_size;
+ offset += asserts->list_element_dword_size;
continue;
}
@@ -4352,28 +4623,22 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn,
fw_asserts_section_addr =
s_storm_defs[storm_id].sem_fast_mem_addr +
SEM_FAST_REG_INT_RAM +
- RAM_LINES_TO_BYTES(fw_info.fw_asserts_section.
- section_ram_line_offset);
+ RAM_LINES_TO_BYTES(asserts->section_ram_line_offset);
next_list_idx_addr =
fw_asserts_section_addr +
- DWORDS_TO_BYTES(fw_info.fw_asserts_section.
- list_next_index_dword_offset);
+ DWORDS_TO_BYTES(asserts->list_next_index_dword_offset);
next_list_idx = qed_rd(p_hwfn, p_ptt, next_list_idx_addr);
last_list_idx = (next_list_idx > 0
? next_list_idx
- : fw_info.fw_asserts_section.list_num_elements)
- - 1;
- element_addr =
- fw_asserts_section_addr +
- DWORDS_TO_BYTES(fw_info.fw_asserts_section.
- list_dword_offset) +
- last_list_idx *
- DWORDS_TO_BYTES(fw_info.fw_asserts_section.
- list_element_dword_size);
- for (i = 0;
- i < fw_info.fw_asserts_section.list_element_dword_size;
- i++, offset++, element_addr += BYTES_IN_DWORD)
- dump_buf[offset] = qed_rd(p_hwfn, p_ptt, element_addr);
+ : asserts->list_num_elements) - 1;
+ addr = BYTES_TO_DWORDS(fw_asserts_section_addr) +
+ asserts->list_dword_offset +
+ last_list_idx * asserts->list_element_dword_size;
+ offset +=
+ qed_grc_dump_addr_range(p_hwfn, p_ptt,
+ dump_buf + offset,
+ dump, addr,
+ asserts->list_element_dword_size);
}
/* Dump last section */
@@ -4386,13 +4651,10 @@ static u32 qed_fw_asserts_dump(struct qed_hwfn *p_hwfn,
enum dbg_status qed_dbg_set_bin_ptr(const u8 * const bin_ptr)
{
/* Convert binary data to debug arrays */
- u32 num_of_buffers = *(u32 *)bin_ptr;
- struct bin_buffer_hdr *buf_array;
+ struct bin_buffer_hdr *buf_array = (struct bin_buffer_hdr *)bin_ptr;
u8 buf_id;
- buf_array = (struct bin_buffer_hdr *)((u32 *)bin_ptr + 1);
-
- for (buf_id = 0; buf_id < num_of_buffers; buf_id++) {
+ for (buf_id = 0; buf_id < MAX_BIN_DBG_BUFFER_TYPE; buf_id++) {
s_dbg_arrays[buf_id].ptr =
(u32 *)(bin_ptr + buf_array[buf_id].offset);
s_dbg_arrays[buf_id].size_in_dwords =
@@ -4402,6 +4664,17 @@ enum dbg_status qed_dbg_set_bin_ptr(const u8 * const bin_ptr)
return DBG_STATUS_OK;
}
+/* Assign default GRC param values */
+void qed_dbg_grc_set_params_default(struct qed_hwfn *p_hwfn)
+{
+ struct dbg_tools_data *dev_data = &p_hwfn->dbg_info;
+ u32 i;
+
+ for (i = 0; i < MAX_DBG_GRC_PARAMS; i++)
+ dev_data->grc.param_val[i] =
+ s_grc_param_defs[i].default_val[dev_data->chip_id];
+}
+
enum dbg_status qed_dbg_grc_get_dump_buf_size(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt,
u32 *buf_size)
@@ -4441,8 +4714,9 @@ enum dbg_status qed_dbg_grc_dump(struct qed_hwfn *p_hwfn,
/* GRC Dump */
status = qed_grc_dump(p_hwfn, p_ptt, dump_buf, true, num_dumped_dwords);
- /* Clear all GRC params */
- qed_dbg_grc_clear_params(p_hwfn);
+ /* Revert GRC params to their default */
+ qed_dbg_grc_set_params_default(p_hwfn);
+
return status;
}
@@ -4495,6 +4769,10 @@ enum dbg_status qed_dbg_idle_chk_dump(struct qed_hwfn *p_hwfn,
/* Idle Check Dump */
*num_dumped_dwords = qed_idle_chk_dump(p_hwfn, p_ptt, dump_buf, true);
+
+ /* Revert GRC params to their default */
+ qed_dbg_grc_set_params_default(p_hwfn);
+
return DBG_STATUS_OK;
}
@@ -4519,11 +4797,15 @@ enum dbg_status qed_dbg_mcp_trace_dump(struct qed_hwfn *p_hwfn,
u32 needed_buf_size_in_dwords;
enum dbg_status status;
- status = qed_dbg_mcp_trace_get_dump_buf_size(p_hwfn, p_ptt,
+ /* validate buffer size */
+ status =
+ qed_dbg_mcp_trace_get_dump_buf_size(p_hwfn, p_ptt,
&needed_buf_size_in_dwords);
- if (status != DBG_STATUS_OK)
+ if (status != DBG_STATUS_OK &&
+ status != DBG_STATUS_NVRAM_GET_IMAGE_FAILED)
return status;
+
if (buf_size_in_dwords < needed_buf_size_in_dwords)
return DBG_STATUS_DUMP_BUF_TOO_SMALL;
@@ -4531,8 +4813,13 @@ enum dbg_status qed_dbg_mcp_trace_dump(struct qed_hwfn *p_hwfn,
qed_update_blocks_reset_state(p_hwfn, p_ptt);
/* Perform dump */
- return qed_mcp_trace_dump(p_hwfn,
- p_ptt, dump_buf, true, num_dumped_dwords);
+ status = qed_mcp_trace_dump(p_hwfn,
+ p_ptt, dump_buf, true, num_dumped_dwords);
+
+ /* Revert GRC params to their default */
+ qed_dbg_grc_set_params_default(p_hwfn);
+
+ return status;
}
enum dbg_status qed_dbg_reg_fifo_get_dump_buf_size(struct qed_hwfn *p_hwfn,
@@ -4567,8 +4854,14 @@ enum dbg_status qed_dbg_reg_fifo_dump(struct qed_hwfn *p_hwfn,
/* Update reset state */
qed_update_blocks_reset_state(p_hwfn, p_ptt);
- return qed_reg_fifo_dump(p_hwfn,
- p_ptt, dump_buf, true, num_dumped_dwords);
+
+ status = qed_reg_fifo_dump(p_hwfn,
+ p_ptt, dump_buf, true, num_dumped_dwords);
+
+ /* Revert GRC params to their default */
+ qed_dbg_grc_set_params_default(p_hwfn);
+
+ return status;
}
enum dbg_status qed_dbg_igu_fifo_get_dump_buf_size(struct qed_hwfn *p_hwfn,
@@ -4603,8 +4896,13 @@ enum dbg_status qed_dbg_igu_fifo_dump(struct qed_hwfn *p_hwfn,
/* Update reset state */
qed_update_blocks_reset_state(p_hwfn, p_ptt);
- return qed_igu_fifo_dump(p_hwfn,
- p_ptt, dump_buf, true, num_dumped_dwords);
+
+ status = qed_igu_fifo_dump(p_hwfn,
+ p_ptt, dump_buf, true, num_dumped_dwords);
+ /* Revert GRC params to their default */
+ qed_dbg_grc_set_params_default(p_hwfn);
+
+ return status;
}
enum dbg_status
@@ -4641,9 +4939,16 @@ enum dbg_status qed_dbg_protection_override_dump(struct qed_hwfn *p_hwfn,
/* Update reset state */
qed_update_blocks_reset_state(p_hwfn, p_ptt);
- return qed_protection_override_dump(p_hwfn,
- p_ptt,
- dump_buf, true, num_dumped_dwords);
+
+ status = qed_protection_override_dump(p_hwfn,
+ p_ptt,
+ dump_buf,
+ true, num_dumped_dwords);
+
+ /* Revert GRC params to their default */
+ qed_dbg_grc_set_params_default(p_hwfn);
+
+ return status;
}
enum dbg_status qed_dbg_fw_asserts_get_dump_buf_size(struct qed_hwfn *p_hwfn,
@@ -5045,13 +5350,10 @@ static char s_temp_buf[MAX_MSG_LEN];
enum dbg_status qed_dbg_user_set_bin_ptr(const u8 * const bin_ptr)
{
/* Convert binary data to debug arrays */
- u32 num_of_buffers = *(u32 *)bin_ptr;
- struct bin_buffer_hdr *buf_array;
+ struct bin_buffer_hdr *buf_array = (struct bin_buffer_hdr *)bin_ptr;
u8 buf_id;
- buf_array = (struct bin_buffer_hdr *)((u32 *)bin_ptr + 1);
-
- for (buf_id = 0; buf_id < num_of_buffers; buf_id++) {
+ for (buf_id = 0; buf_id < MAX_BIN_DBG_BUFFER_TYPE; buf_id++) {
s_dbg_arrays[buf_id].ptr =
(u32 *)(bin_ptr + buf_array[buf_id].offset);
s_dbg_arrays[buf_id].size_in_dwords =
@@ -5874,16 +6176,16 @@ static enum dbg_status qed_parse_reg_fifo_dump(struct qed_hwfn *p_hwfn,
results_offset +=
sprintf(qed_get_buf_ptr(results_buf,
results_offset),
- "raw: 0x%016llx, address: 0x%07llx, access: %-5s, pf: %2lld, vf: %s, port: %lld, privilege: %-3s, protection: %-12s, master: %-4s, errors: ",
+ "raw: 0x%016llx, address: 0x%07x, access: %-5s, pf: %2d, vf: %s, port: %d, privilege: %-3s, protection: %-12s, master: %-4s, errors: ",
elements[i].data,
- GET_FIELD(elements[i].data,
+ (u32)GET_FIELD(elements[i].data,
REG_FIFO_ELEMENT_ADDRESS) *
REG_FIFO_ELEMENT_ADDR_FACTOR,
s_access_strs[GET_FIELD(elements[i].data,
REG_FIFO_ELEMENT_ACCESS)],
- GET_FIELD(elements[i].data,
- REG_FIFO_ELEMENT_PF), vf_str,
- GET_FIELD(elements[i].data,
+ (u32)GET_FIELD(elements[i].data,
+ REG_FIFO_ELEMENT_PF), vf_str,
+ (u32)GET_FIELD(elements[i].data,
REG_FIFO_ELEMENT_PORT),
s_privilege_strs[GET_FIELD(elements[i].
data,
@@ -6189,13 +6491,13 @@ qed_parse_protection_override_dump(struct qed_hwfn *p_hwfn,
results_offset +=
sprintf(qed_get_buf_ptr(results_buf,
results_offset),
- "window %2d, address: 0x%07x, size: %7lld regs, read: %lld, write: %lld, read protection: %-12s, write protection: %-12s\n",
+ "window %2d, address: 0x%07x, size: %7d regs, read: %d, write: %d, read protection: %-12s, write protection: %-12s\n",
i, address,
- GET_FIELD(elements[i].data,
+ (u32)GET_FIELD(elements[i].data,
PROTECTION_OVERRIDE_ELEMENT_WINDOW_SIZE),
- GET_FIELD(elements[i].data,
+ (u32)GET_FIELD(elements[i].data,
PROTECTION_OVERRIDE_ELEMENT_READ),
- GET_FIELD(elements[i].data,
+ (u32)GET_FIELD(elements[i].data,
PROTECTION_OVERRIDE_ELEMENT_WRITE),
s_protection_strs[GET_FIELD(elements[i].data,
PROTECTION_OVERRIDE_ELEMENT_READ_PROTECTION)],
@@ -6508,7 +6810,7 @@ static enum dbg_status qed_dbg_dump(struct qed_hwfn *p_hwfn,
*/
rc = qed_features_lookup[feature_idx].get_size(p_hwfn, p_ptt,
&buf_size_dwords);
- if (rc != DBG_STATUS_OK)
+ if (rc != DBG_STATUS_OK && rc != DBG_STATUS_NVRAM_GET_IMAGE_FAILED)
return rc;
feature->buf_size = buf_size_dwords * sizeof(u32);
feature->dump_buf = vmalloc(feature->buf_size);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index e2a081c..fad7319 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -75,7 +75,8 @@ enum BAR_ID {
BAR_ID_1 /* Used for doorbells */
};
-static u32 qed_hw_bar_size(struct qed_hwfn *p_hwfn, enum BAR_ID bar_id)
+static u32 qed_hw_bar_size(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt, enum BAR_ID bar_id)
{
u32 bar_reg = (bar_id == BAR_ID_0 ?
PGLUE_B_REG_PF_BAR0_SIZE : PGLUE_B_REG_PF_BAR1_SIZE);
@@ -84,7 +85,7 @@ static u32 qed_hw_bar_size(struct qed_hwfn *p_hwfn, enum BAR_ID bar_id)
if (IS_VF(p_hwfn->cdev))
return 1 << 17;
- val = qed_rd(p_hwfn, p_hwfn->p_main_ptt, bar_reg);
+ val = qed_rd(p_hwfn, p_ptt, bar_reg);
if (val)
return 1 << (val + 15);
@@ -186,195 +187,569 @@ void qed_resc_free(struct qed_dev *cdev)
}
}
-static int qed_init_qm_info(struct qed_hwfn *p_hwfn, bool b_sleepable)
+/******************** QM initialization *******************/
+#define ACTIVE_TCS_BMAP 0x9f
+#define ACTIVE_TCS_BMAP_4PORT_K2 0xf
+
+/* determines the physical queue flags for a given PF. */
+static u32 qed_get_pq_flags(struct qed_hwfn *p_hwfn)
{
- u8 num_vports, vf_offset = 0, i, vport_id, num_ports, curr_queue = 0;
- struct qed_qm_info *qm_info = &p_hwfn->qm_info;
- struct init_qm_port_params *p_qm_port;
- bool init_rdma_offload_pq = false;
- bool init_pure_ack_pq = false;
- bool init_ooo_pq = false;
- u16 num_pqs, multi_cos_tcs = 1;
- u8 pf_wfq = qm_info->pf_wfq;
- u32 pf_rl = qm_info->pf_rl;
- u16 num_pf_rls = 0;
- u16 num_vfs = 0;
+ u32 flags;
-#ifdef CONFIG_QED_SRIOV
- if (p_hwfn->cdev->p_iov_info)
- num_vfs = p_hwfn->cdev->p_iov_info->total_vfs;
-#endif
- memset(qm_info, 0, sizeof(*qm_info));
+ /* common flags */
+ flags = PQ_FLAGS_LB;
- num_pqs = multi_cos_tcs + num_vfs + 1; /* The '1' is for pure-LB */
- num_vports = (u8)RESC_NUM(p_hwfn, QED_VPORT);
+ /* feature flags */
+ if (IS_QED_SRIOV(p_hwfn->cdev))
+ flags |= PQ_FLAGS_VFS;
- if (p_hwfn->hw_info.personality == QED_PCI_ETH_ROCE) {
- num_pqs++; /* for RoCE queue */
- init_rdma_offload_pq = true;
- /* we subtract num_vfs because each require a rate limiter,
- * and one default rate limiter
- */
- if (p_hwfn->pf_params.rdma_pf_params.enable_dcqcn)
- num_pf_rls = RESC_NUM(p_hwfn, QED_RL) - num_vfs - 1;
-
- num_pqs += num_pf_rls;
- qm_info->num_pf_rls = (u8) num_pf_rls;
- }
-
- if (p_hwfn->hw_info.personality == QED_PCI_ISCSI) {
- num_pqs += 2; /* for iSCSI pure-ACK / OOO queue */
- init_pure_ack_pq = true;
- init_ooo_pq = true;
- }
-
- /* Sanity checking that setup requires legal number of resources */
- if (num_pqs > RESC_NUM(p_hwfn, QED_PQ)) {
+ /* protocol flags */
+ switch (p_hwfn->hw_info.personality) {
+ case QED_PCI_ETH:
+ flags |= PQ_FLAGS_MCOS;
+ break;
+ case QED_PCI_FCOE:
+ flags |= PQ_FLAGS_OFLD;
+ break;
+ case QED_PCI_ISCSI:
+ flags |= PQ_FLAGS_ACK | PQ_FLAGS_OOO | PQ_FLAGS_OFLD;
+ break;
+ case QED_PCI_ETH_ROCE:
+ flags |= PQ_FLAGS_MCOS | PQ_FLAGS_OFLD | PQ_FLAGS_LLT;
+ break;
+ default:
DP_ERR(p_hwfn,
- "Need too many Physical queues - 0x%04x when only %04x are available\n",
- num_pqs, RESC_NUM(p_hwfn, QED_PQ));
- return -EINVAL;
+ "unknown personality %d\n", p_hwfn->hw_info.personality);
+ return 0;
}
- /* PQs will be arranged as follows: First per-TC PQ then pure-LB quete.
+ return flags;
+}
+
+/* Getters for resource amounts necessary for qm initialization */
+u8 qed_init_qm_get_num_tcs(struct qed_hwfn *p_hwfn)
+{
+ return p_hwfn->hw_info.num_hw_tc;
+}
+
+u16 qed_init_qm_get_num_vfs(struct qed_hwfn *p_hwfn)
+{
+ return IS_QED_SRIOV(p_hwfn->cdev) ?
+ p_hwfn->cdev->p_iov_info->total_vfs : 0;
+}
+
+#define NUM_DEFAULT_RLS 1
+
+u16 qed_init_qm_get_num_pf_rls(struct qed_hwfn *p_hwfn)
+{
+ u16 num_pf_rls, num_vfs = qed_init_qm_get_num_vfs(p_hwfn);
+
+ /* num RLs can't exceed resource amount of rls or vports */
+ num_pf_rls = (u16) min_t(u32, RESC_NUM(p_hwfn, QED_RL),
+ RESC_NUM(p_hwfn, QED_VPORT));
+
+ /* Make sure after we reserve there's something left */
+ if (num_pf_rls < num_vfs + NUM_DEFAULT_RLS)
+ return 0;
+
+ /* subtract rls necessary for VFs and one default one for the PF */
+ num_pf_rls -= num_vfs + NUM_DEFAULT_RLS;
+
+ return num_pf_rls;
+}
+
+u16 qed_init_qm_get_num_vports(struct qed_hwfn *p_hwfn)
+{
+ u32 pq_flags = qed_get_pq_flags(p_hwfn);
+
+ /* all pqs share the same vport, except for vfs and pf_rl pqs */
+ return (!!(PQ_FLAGS_RLS & pq_flags)) *
+ qed_init_qm_get_num_pf_rls(p_hwfn) +
+ (!!(PQ_FLAGS_VFS & pq_flags)) *
+ qed_init_qm_get_num_vfs(p_hwfn) + 1;
+}
+
+/* calc amount of PQs according to the requested flags */
+u16 qed_init_qm_get_num_pqs(struct qed_hwfn *p_hwfn)
+{
+ u32 pq_flags = qed_get_pq_flags(p_hwfn);
+
+ return (!!(PQ_FLAGS_RLS & pq_flags)) *
+ qed_init_qm_get_num_pf_rls(p_hwfn) +
+ (!!(PQ_FLAGS_MCOS & pq_flags)) *
+ qed_init_qm_get_num_tcs(p_hwfn) +
+ (!!(PQ_FLAGS_LB & pq_flags)) + (!!(PQ_FLAGS_OOO & pq_flags)) +
+ (!!(PQ_FLAGS_ACK & pq_flags)) + (!!(PQ_FLAGS_OFLD & pq_flags)) +
+ (!!(PQ_FLAGS_LLT & pq_flags)) +
+ (!!(PQ_FLAGS_VFS & pq_flags)) * qed_init_qm_get_num_vfs(p_hwfn);
+}
+
+/* initialize the top level QM params */
+static void qed_init_qm_params(struct qed_hwfn *p_hwfn)
+{
+ struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+ bool four_port;
+
+ /* pq and vport bases for this PF */
+ qm_info->start_pq = (u16) RESC_START(p_hwfn, QED_PQ);
+ qm_info->start_vport = (u8) RESC_START(p_hwfn, QED_VPORT);
+
+ /* rate limiting and weighted fair queueing are always enabled */
+ qm_info->vport_rl_en = 1;
+ qm_info->vport_wfq_en = 1;
+
+ /* TC config is different for AH 4 port */
+ four_port = p_hwfn->cdev->num_ports_in_engines == MAX_NUM_PORTS_K2;
+
+ /* in AH 4 port we have fewer TCs per port */
+ qm_info->max_phys_tcs_per_port = four_port ? NUM_PHYS_TCS_4PORT_K2 :
+ NUM_OF_PHYS_TCS;
+
+ /* unless MFW indicated otherwise, ooo_tc == 3 for
+ * AH 4-port and 4 otherwise.
*/
- qm_info->qm_pq_params = kcalloc(num_pqs,
- sizeof(struct init_qm_pq_params),
- b_sleepable ? GFP_KERNEL : GFP_ATOMIC);
- if (!qm_info->qm_pq_params)
- goto alloc_err;
+ if (!qm_info->ooo_tc)
+ qm_info->ooo_tc = four_port ? DCBX_TCP_OOO_K2_4PORT_TC :
+ DCBX_TCP_OOO_TC;
+}
- qm_info->qm_vport_params = kcalloc(num_vports,
- sizeof(struct init_qm_vport_params),
- b_sleepable ? GFP_KERNEL
- : GFP_ATOMIC);
- if (!qm_info->qm_vport_params)
- goto alloc_err;
+/* initialize qm vport params */
+static void qed_init_qm_vport_params(struct qed_hwfn *p_hwfn)
+{
+ struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+ u8 i;
- qm_info->qm_port_params = kcalloc(MAX_NUM_PORTS,
- sizeof(struct init_qm_port_params),
- b_sleepable ? GFP_KERNEL
- : GFP_ATOMIC);
- if (!qm_info->qm_port_params)
- goto alloc_err;
+ /* all vports participate in weighted fair queueing */
+ for (i = 0; i < qed_init_qm_get_num_vports(p_hwfn); i++)
+ qm_info->qm_vport_params[i].vport_wfq = 1;
+}
- qm_info->wfq_data = kcalloc(num_vports, sizeof(struct qed_wfq_data),
- b_sleepable ? GFP_KERNEL : GFP_ATOMIC);
- if (!qm_info->wfq_data)
- goto alloc_err;
-
- vport_id = (u8)RESC_START(p_hwfn, QED_VPORT);
-
- /* First init rate limited queues */
- for (curr_queue = 0; curr_queue < num_pf_rls; curr_queue++) {
- qm_info->qm_pq_params[curr_queue].vport_id = vport_id++;
- qm_info->qm_pq_params[curr_queue].tc_id =
- p_hwfn->hw_info.non_offload_tc;
- qm_info->qm_pq_params[curr_queue].wrr_group = 1;
- qm_info->qm_pq_params[curr_queue].rl_valid = 1;
- }
-
- /* First init per-TC PQs */
- for (i = 0; i < multi_cos_tcs; i++) {
- struct init_qm_pq_params *params =
- &qm_info->qm_pq_params[curr_queue++];
-
- if (p_hwfn->hw_info.personality == QED_PCI_ETH_ROCE ||
- p_hwfn->hw_info.personality == QED_PCI_ETH) {
- params->vport_id = vport_id;
- params->tc_id = p_hwfn->hw_info.non_offload_tc;
- params->wrr_group = 1;
- } else {
- params->vport_id = vport_id;
- params->tc_id = p_hwfn->hw_info.offload_tc;
- params->wrr_group = 1;
- }
- }
-
- /* Then init pure-LB PQ */
- qm_info->pure_lb_pq = curr_queue;
- qm_info->qm_pq_params[curr_queue].vport_id =
- (u8) RESC_START(p_hwfn, QED_VPORT);
- qm_info->qm_pq_params[curr_queue].tc_id = PURE_LB_TC;
- qm_info->qm_pq_params[curr_queue].wrr_group = 1;
- curr_queue++;
-
- qm_info->offload_pq = 0;
- if (init_rdma_offload_pq) {
- qm_info->offload_pq = curr_queue;
- qm_info->qm_pq_params[curr_queue].vport_id = vport_id;
- qm_info->qm_pq_params[curr_queue].tc_id =
- p_hwfn->hw_info.offload_tc;
- qm_info->qm_pq_params[curr_queue].wrr_group = 1;
- curr_queue++;
- }
-
- if (init_pure_ack_pq) {
- qm_info->pure_ack_pq = curr_queue;
- qm_info->qm_pq_params[curr_queue].vport_id = vport_id;
- qm_info->qm_pq_params[curr_queue].tc_id =
- p_hwfn->hw_info.offload_tc;
- qm_info->qm_pq_params[curr_queue].wrr_group = 1;
- curr_queue++;
- }
-
- if (init_ooo_pq) {
- qm_info->ooo_pq = curr_queue;
- qm_info->qm_pq_params[curr_queue].vport_id = vport_id;
- qm_info->qm_pq_params[curr_queue].tc_id = DCBX_ISCSI_OOO_TC;
- qm_info->qm_pq_params[curr_queue].wrr_group = 1;
- curr_queue++;
- }
-
- /* Then init per-VF PQs */
- vf_offset = curr_queue;
- for (i = 0; i < num_vfs; i++) {
- /* First vport is used by the PF */
- qm_info->qm_pq_params[curr_queue].vport_id = vport_id + i + 1;
- qm_info->qm_pq_params[curr_queue].tc_id =
- p_hwfn->hw_info.non_offload_tc;
- qm_info->qm_pq_params[curr_queue].wrr_group = 1;
- qm_info->qm_pq_params[curr_queue].rl_valid = 1;
- curr_queue++;
- }
-
- qm_info->vf_queues_offset = vf_offset;
- qm_info->num_pqs = num_pqs;
- qm_info->num_vports = num_vports;
-
+/* initialize qm port params */
+static void qed_init_qm_port_params(struct qed_hwfn *p_hwfn)
+{
/* Initialize qm port parameters */
- num_ports = p_hwfn->cdev->num_ports_in_engines;
+ u8 i, active_phys_tcs, num_ports = p_hwfn->cdev->num_ports_in_engines;
+
+ /* indicate how ooo and high pri traffic is dealt with */
+ active_phys_tcs = num_ports == MAX_NUM_PORTS_K2 ?
+ ACTIVE_TCS_BMAP_4PORT_K2 :
+ ACTIVE_TCS_BMAP;
+
for (i = 0; i < num_ports; i++) {
- p_qm_port = &qm_info->qm_port_params[i];
+ struct init_qm_port_params *p_qm_port =
+ &p_hwfn->qm_info.qm_port_params[i];
+
p_qm_port->active = 1;
- if (num_ports == 4)
- p_qm_port->active_phys_tcs = 0x7;
- else
- p_qm_port->active_phys_tcs = 0x9f;
+ p_qm_port->active_phys_tcs = active_phys_tcs;
p_qm_port->num_pbf_cmd_lines = PBF_MAX_CMD_LINES / num_ports;
p_qm_port->num_btb_blocks = BTB_MAX_BLOCKS / num_ports;
}
+}
- qm_info->max_phys_tcs_per_port = NUM_OF_PHYS_TCS;
+/* Reset the params which must be reset for qm init. QM init may be called as
+ * a result of flows other than driver load (e.g. dcbx renegotiation). Other
+ * params may be affected by the init but would simply recalculate to the same
+ * values. The allocations made for QM init, ports, vports, pqs and vfqs are not
+ * affected as these amounts stay the same.
+ */
+static void qed_init_qm_reset_params(struct qed_hwfn *p_hwfn)
+{
+ struct qed_qm_info *qm_info = &p_hwfn->qm_info;
- qm_info->start_pq = (u16)RESC_START(p_hwfn, QED_PQ);
+ qm_info->num_pqs = 0;
+ qm_info->num_vports = 0;
+ qm_info->num_pf_rls = 0;
+ qm_info->num_vf_pqs = 0;
+ qm_info->first_vf_pq = 0;
+ qm_info->first_mcos_pq = 0;
+ qm_info->first_rl_pq = 0;
+}
+static void qed_init_qm_advance_vport(struct qed_hwfn *p_hwfn)
+{
+ struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+
+ qm_info->num_vports++;
+
+ if (qm_info->num_vports > qed_init_qm_get_num_vports(p_hwfn))
+ DP_ERR(p_hwfn,
+ "vport overflow! qm_info->num_vports %d, qm_init_get_num_vports() %d\n",
+ qm_info->num_vports, qed_init_qm_get_num_vports(p_hwfn));
+}
+
+/* initialize a single pq and manage qm_info resources accounting.
+ * The pq_init_flags param determines whether the PQ is rate limited
+ * (for VF or PF) and whether a new vport is allocated to the pq or not
+ * (i.e. vport will be shared).
+ */
+
+/* flags for pq init */
+#define PQ_INIT_SHARE_VPORT (1 << 0)
+#define PQ_INIT_PF_RL (1 << 1)
+#define PQ_INIT_VF_RL (1 << 2)
+
+/* defines for pq init */
+#define PQ_INIT_DEFAULT_WRR_GROUP 1
+#define PQ_INIT_DEFAULT_TC 0
+#define PQ_INIT_OFLD_TC (p_hwfn->hw_info.offload_tc)
+
+static void qed_init_qm_pq(struct qed_hwfn *p_hwfn,
+ struct qed_qm_info *qm_info,
+ u8 tc, u32 pq_init_flags)
+{
+ u16 pq_idx = qm_info->num_pqs, max_pq = qed_init_qm_get_num_pqs(p_hwfn);
+
+ if (pq_idx > max_pq)
+ DP_ERR(p_hwfn,
+ "pq overflow! pq %d, max pq %d\n", pq_idx, max_pq);
+
+ /* init pq params */
+ qm_info->qm_pq_params[pq_idx].vport_id = qm_info->start_vport +
+ qm_info->num_vports;
+ qm_info->qm_pq_params[pq_idx].tc_id = tc;
+ qm_info->qm_pq_params[pq_idx].wrr_group = PQ_INIT_DEFAULT_WRR_GROUP;
+ qm_info->qm_pq_params[pq_idx].rl_valid =
+ (pq_init_flags & PQ_INIT_PF_RL || pq_init_flags & PQ_INIT_VF_RL);
+
+ /* qm params accounting */
+ qm_info->num_pqs++;
+ if (!(pq_init_flags & PQ_INIT_SHARE_VPORT))
+ qm_info->num_vports++;
+
+ if (pq_init_flags & PQ_INIT_PF_RL)
+ qm_info->num_pf_rls++;
+
+ if (qm_info->num_vports > qed_init_qm_get_num_vports(p_hwfn))
+ DP_ERR(p_hwfn,
+ "vport overflow! qm_info->num_vports %d, qm_init_get_num_vports() %d\n",
+ qm_info->num_vports, qed_init_qm_get_num_vports(p_hwfn));
+
+ if (qm_info->num_pf_rls > qed_init_qm_get_num_pf_rls(p_hwfn))
+ DP_ERR(p_hwfn,
+ "rl overflow! qm_info->num_pf_rls %d, qm_init_get_num_pf_rls() %d\n",
+ qm_info->num_pf_rls, qed_init_qm_get_num_pf_rls(p_hwfn));
+}
+
+/* get pq index according to PQ_FLAGS */
+static u16 *qed_init_qm_get_idx_from_flags(struct qed_hwfn *p_hwfn,
+ u32 pq_flags)
+{
+ struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+
+ /* Can't have multiple flags set here */
+ if (bitmap_weight((unsigned long *)&pq_flags, sizeof(pq_flags)) > 1)
+ goto err;
+
+ switch (pq_flags) {
+ case PQ_FLAGS_RLS:
+ return &qm_info->first_rl_pq;
+ case PQ_FLAGS_MCOS:
+ return &qm_info->first_mcos_pq;
+ case PQ_FLAGS_LB:
+ return &qm_info->pure_lb_pq;
+ case PQ_FLAGS_OOO:
+ return &qm_info->ooo_pq;
+ case PQ_FLAGS_ACK:
+ return &qm_info->pure_ack_pq;
+ case PQ_FLAGS_OFLD:
+ return &qm_info->offload_pq;
+ case PQ_FLAGS_LLT:
+ return &qm_info->low_latency_pq;
+ case PQ_FLAGS_VFS:
+ return &qm_info->first_vf_pq;
+ default:
+ goto err;
+ }
+
+err:
+ DP_ERR(p_hwfn, "BAD pq flags %d\n", pq_flags);
+ return NULL;
+}
+
+/* save pq index in qm info */
+static void qed_init_qm_set_idx(struct qed_hwfn *p_hwfn,
+ u32 pq_flags, u16 pq_val)
+{
+ u16 *base_pq_idx = qed_init_qm_get_idx_from_flags(p_hwfn, pq_flags);
+
+ *base_pq_idx = p_hwfn->qm_info.start_pq + pq_val;
+}
+
+/* get tx pq index, with the PQ TX base already set (ready for context init) */
+u16 qed_get_cm_pq_idx(struct qed_hwfn *p_hwfn, u32 pq_flags)
+{
+ u16 *base_pq_idx = qed_init_qm_get_idx_from_flags(p_hwfn, pq_flags);
+
+ return *base_pq_idx + CM_TX_PQ_BASE;
+}
+
+u16 qed_get_cm_pq_idx_mcos(struct qed_hwfn *p_hwfn, u8 tc)
+{
+ u8 max_tc = qed_init_qm_get_num_tcs(p_hwfn);
+
+ if (tc > max_tc)
+ DP_ERR(p_hwfn, "tc %d must be smaller than %d\n", tc, max_tc);
+
+ return qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_MCOS) + tc;
+}
+
+u16 qed_get_cm_pq_idx_vf(struct qed_hwfn *p_hwfn, u16 vf)
+{
+ u16 max_vf = qed_init_qm_get_num_vfs(p_hwfn);
+
+ if (vf > max_vf)
+ DP_ERR(p_hwfn, "vf %d must be smaller than %d\n", vf, max_vf);
+
+ return qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_VFS) + vf;
+}
+
+u16 qed_get_cm_pq_idx_rl(struct qed_hwfn *p_hwfn, u8 rl)
+{
+ u16 max_rl = qed_init_qm_get_num_pf_rls(p_hwfn);
+
+ if (rl > max_rl)
+ DP_ERR(p_hwfn, "rl %d must be smaller than %d\n", rl, max_rl);
+
+ return qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_RLS) + rl;
+}
+
+/* Functions for creating specific types of pqs */
+static void qed_init_qm_lb_pq(struct qed_hwfn *p_hwfn)
+{
+ struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+
+ if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_LB))
+ return;
+
+ qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_LB, qm_info->num_pqs);
+ qed_init_qm_pq(p_hwfn, qm_info, PURE_LB_TC, PQ_INIT_SHARE_VPORT);
+}
+
+static void qed_init_qm_ooo_pq(struct qed_hwfn *p_hwfn)
+{
+ struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+
+ if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_OOO))
+ return;
+
+ qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_OOO, qm_info->num_pqs);
+ qed_init_qm_pq(p_hwfn, qm_info, qm_info->ooo_tc, PQ_INIT_SHARE_VPORT);
+}
+
+static void qed_init_qm_pure_ack_pq(struct qed_hwfn *p_hwfn)
+{
+ struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+
+ if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_ACK))
+ return;
+
+ qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_ACK, qm_info->num_pqs);
+ qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_SHARE_VPORT);
+}
+
+static void qed_init_qm_offload_pq(struct qed_hwfn *p_hwfn)
+{
+ struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+
+ if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_OFLD))
+ return;
+
+ qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_OFLD, qm_info->num_pqs);
+ qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_SHARE_VPORT);
+}
+
+static void qed_init_qm_low_latency_pq(struct qed_hwfn *p_hwfn)
+{
+ struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+
+ if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_LLT))
+ return;
+
+ qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_LLT, qm_info->num_pqs);
+ qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_SHARE_VPORT);
+}
+
+static void qed_init_qm_mcos_pqs(struct qed_hwfn *p_hwfn)
+{
+ struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+ u8 tc_idx;
+
+ if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_MCOS))
+ return;
+
+ qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_MCOS, qm_info->num_pqs);
+ for (tc_idx = 0; tc_idx < qed_init_qm_get_num_tcs(p_hwfn); tc_idx++)
+ qed_init_qm_pq(p_hwfn, qm_info, tc_idx, PQ_INIT_SHARE_VPORT);
+}
+
+static void qed_init_qm_vf_pqs(struct qed_hwfn *p_hwfn)
+{
+ struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+ u16 vf_idx, num_vfs = qed_init_qm_get_num_vfs(p_hwfn);
+
+ if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_VFS))
+ return;
+
+ qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_VFS, qm_info->num_pqs);
qm_info->num_vf_pqs = num_vfs;
- qm_info->start_vport = (u8) RESC_START(p_hwfn, QED_VPORT);
+ for (vf_idx = 0; vf_idx < num_vfs; vf_idx++)
+ qed_init_qm_pq(p_hwfn,
+ qm_info, PQ_INIT_DEFAULT_TC, PQ_INIT_VF_RL);
+}
- for (i = 0; i < qm_info->num_vports; i++)
- qm_info->qm_vport_params[i].vport_wfq = 1;
+static void qed_init_qm_rl_pqs(struct qed_hwfn *p_hwfn)
+{
+ u16 pf_rls_idx, num_pf_rls = qed_init_qm_get_num_pf_rls(p_hwfn);
+ struct qed_qm_info *qm_info = &p_hwfn->qm_info;
- qm_info->vport_rl_en = 1;
- qm_info->vport_wfq_en = 1;
- qm_info->pf_rl = pf_rl;
- qm_info->pf_wfq = pf_wfq;
+ if (!(qed_get_pq_flags(p_hwfn) & PQ_FLAGS_RLS))
+ return;
+
+ qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_RLS, qm_info->num_pqs);
+ for (pf_rls_idx = 0; pf_rls_idx < num_pf_rls; pf_rls_idx++)
+ qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_PF_RL);
+}
+
+static void qed_init_qm_pq_params(struct qed_hwfn *p_hwfn)
+{
+ /* rate limited pqs, must come first (FW assumption) */
+ qed_init_qm_rl_pqs(p_hwfn);
+
+ /* pqs for multi cos */
+ qed_init_qm_mcos_pqs(p_hwfn);
+
+ /* pure loopback pq */
+ qed_init_qm_lb_pq(p_hwfn);
+
+ /* out of order pq */
+ qed_init_qm_ooo_pq(p_hwfn);
+
+ /* pure ack pq */
+ qed_init_qm_pure_ack_pq(p_hwfn);
+
+ /* pq for offloaded protocol */
+ qed_init_qm_offload_pq(p_hwfn);
+
+ /* low latency pq */
+ qed_init_qm_low_latency_pq(p_hwfn);
+
+ /* done sharing vports */
+ qed_init_qm_advance_vport(p_hwfn);
+
+ /* pqs for vfs */
+ qed_init_qm_vf_pqs(p_hwfn);
+}
+
+/* compare values of getters against resources amounts */
+static int qed_init_qm_sanity(struct qed_hwfn *p_hwfn)
+{
+ if (qed_init_qm_get_num_vports(p_hwfn) > RESC_NUM(p_hwfn, QED_VPORT)) {
+ DP_ERR(p_hwfn, "requested amount of vports exceeds resource\n");
+ return -EINVAL;
+ }
+
+ if (qed_init_qm_get_num_pqs(p_hwfn) > RESC_NUM(p_hwfn, QED_PQ)) {
+ DP_ERR(p_hwfn, "requested amount of pqs exceeds resource\n");
+ return -EINVAL;
+ }
return 0;
+}
-alloc_err:
- qed_qm_info_free(p_hwfn);
- return -ENOMEM;
+static void qed_dp_init_qm_params(struct qed_hwfn *p_hwfn)
+{
+ struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+ struct init_qm_vport_params *vport;
+ struct init_qm_port_params *port;
+ struct init_qm_pq_params *pq;
+ int i, tc;
+
+ /* top level params */
+ DP_VERBOSE(p_hwfn,
+ NETIF_MSG_HW,
+ "qm init top level params: start_pq %d, start_vport %d, pure_lb_pq %d, offload_pq %d, pure_ack_pq %d\n",
+ qm_info->start_pq,
+ qm_info->start_vport,
+ qm_info->pure_lb_pq,
+ qm_info->offload_pq, qm_info->pure_ack_pq);
+ DP_VERBOSE(p_hwfn,
+ NETIF_MSG_HW,
+ "ooo_pq %d, first_vf_pq %d, num_pqs %d, num_vf_pqs %d, num_vports %d, max_phys_tcs_per_port %d\n",
+ qm_info->ooo_pq,
+ qm_info->first_vf_pq,
+ qm_info->num_pqs,
+ qm_info->num_vf_pqs,
+ qm_info->num_vports, qm_info->max_phys_tcs_per_port);
+ DP_VERBOSE(p_hwfn,
+ NETIF_MSG_HW,
+ "pf_rl_en %d, pf_wfq_en %d, vport_rl_en %d, vport_wfq_en %d, pf_wfq %d, pf_rl %d, num_pf_rls %d, pq_flags %x\n",
+ qm_info->pf_rl_en,
+ qm_info->pf_wfq_en,
+ qm_info->vport_rl_en,
+ qm_info->vport_wfq_en,
+ qm_info->pf_wfq,
+ qm_info->pf_rl,
+ qm_info->num_pf_rls, qed_get_pq_flags(p_hwfn));
+
+ /* port table */
+ for (i = 0; i < p_hwfn->cdev->num_ports_in_engines; i++) {
+ port = &(qm_info->qm_port_params[i]);
+ DP_VERBOSE(p_hwfn,
+ NETIF_MSG_HW,
+ "port idx %d, active %d, active_phys_tcs %d, num_pbf_cmd_lines %d, num_btb_blocks %d, reserved %d\n",
+ i,
+ port->active,
+ port->active_phys_tcs,
+ port->num_pbf_cmd_lines,
+ port->num_btb_blocks, port->reserved);
+ }
+
+ /* vport table */
+ for (i = 0; i < qm_info->num_vports; i++) {
+ vport = &(qm_info->qm_vport_params[i]);
+ DP_VERBOSE(p_hwfn,
+ NETIF_MSG_HW,
+ "vport idx %d, vport_rl %d, wfq %d, first_tx_pq_id [ ",
+ qm_info->start_vport + i,
+ vport->vport_rl, vport->vport_wfq);
+ for (tc = 0; tc < NUM_OF_TCS; tc++)
+ DP_VERBOSE(p_hwfn,
+ NETIF_MSG_HW,
+ "%d ", vport->first_tx_pq_id[tc]);
+ DP_VERBOSE(p_hwfn, NETIF_MSG_HW, "]\n");
+ }
+
+ /* pq table */
+ for (i = 0; i < qm_info->num_pqs; i++) {
+ pq = &(qm_info->qm_pq_params[i]);
+ DP_VERBOSE(p_hwfn,
+ NETIF_MSG_HW,
+ "pq idx %d, vport_id %d, tc %d, wrr_grp %d, rl_valid %d\n",
+ qm_info->start_pq + i,
+ pq->vport_id,
+ pq->tc_id, pq->wrr_group, pq->rl_valid);
+ }
+}
+
+static void qed_init_qm_info(struct qed_hwfn *p_hwfn)
+{
+ /* reset params required for init run */
+ qed_init_qm_reset_params(p_hwfn);
+
+ /* init QM top level params */
+ qed_init_qm_params(p_hwfn);
+
+ /* init QM port params */
+ qed_init_qm_port_params(p_hwfn);
+
+ /* init QM vport params */
+ qed_init_qm_vport_params(p_hwfn);
+
+ /* init QM physical queue params */
+ qed_init_qm_pq_params(p_hwfn);
+
+ /* display all that init */
+ qed_dp_init_qm_params(p_hwfn);
}
/* This function reconfigures the QM pf on the fly.
@@ -391,17 +766,8 @@ int qed_qm_reconf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
bool b_rc;
int rc;
- /* qm_info is allocated in qed_init_qm_info() which is already called
- * from qed_resc_alloc() or previous call of qed_qm_reconf().
- * The allocated size may change each init, so we free it before next
- * allocation.
- */
- qed_qm_info_free(p_hwfn);
-
/* initialize qed's qm data structure */
- rc = qed_init_qm_info(p_hwfn, false);
- if (rc)
- return rc;
+ qed_init_qm_info(p_hwfn);
/* stop PF's qm queues */
spin_lock_bh(&qm_lock);
@@ -415,7 +781,7 @@ int qed_qm_reconf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
qed_init_clear_rt_data(p_hwfn);
/* prepare QM portion of runtime array */
- qed_qm_init_pf(p_hwfn);
+ qed_qm_init_pf(p_hwfn, p_ptt);
/* activate init tool on runtime array */
rc = qed_init_run(p_hwfn, p_ptt, PHASE_QM_PF, p_hwfn->rel_pf_id,
@@ -434,6 +800,47 @@ int qed_qm_reconf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
return 0;
}
+static int qed_alloc_qm_data(struct qed_hwfn *p_hwfn)
+{
+ struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+ int rc;
+
+ rc = qed_init_qm_sanity(p_hwfn);
+ if (rc)
+ goto alloc_err;
+
+ qm_info->qm_pq_params = kzalloc(sizeof(*qm_info->qm_pq_params) *
+ qed_init_qm_get_num_pqs(p_hwfn),
+ GFP_KERNEL);
+ if (!qm_info->qm_pq_params)
+ goto alloc_err;
+
+ qm_info->qm_vport_params = kzalloc(sizeof(*qm_info->qm_vport_params) *
+ qed_init_qm_get_num_vports(p_hwfn),
+ GFP_KERNEL);
+ if (!qm_info->qm_vport_params)
+ goto alloc_err;
+
+ qm_info->qm_port_params = kzalloc(sizeof(qm_info->qm_port_params) *
+ p_hwfn->cdev->num_ports_in_engines,
+ GFP_KERNEL);
+ if (!qm_info->qm_port_params)
+ goto alloc_err;
+
+ qm_info->wfq_data = kzalloc(sizeof(*qm_info->wfq_data) *
+ qed_init_qm_get_num_vports(p_hwfn),
+ GFP_KERNEL);
+ if (!qm_info->wfq_data)
+ goto alloc_err;
+
+ return 0;
+
+alloc_err:
+ DP_NOTICE(p_hwfn, "Failed to allocate memory for QM params\n");
+ qed_qm_info_free(p_hwfn);
+ return -ENOMEM;
+}
+
int qed_resc_alloc(struct qed_dev *cdev)
{
struct qed_iscsi_info *p_iscsi_info;
@@ -442,8 +849,10 @@ int qed_resc_alloc(struct qed_dev *cdev)
#ifdef CONFIG_QED_LL2
struct qed_ll2_info *p_ll2_info;
#endif
+ u32 rdma_tasks, excess_tasks;
struct qed_consq *p_consq;
struct qed_eq *p_eq;
+ u32 line_count;
int i, rc = 0;
if (IS_VF(cdev))
@@ -465,19 +874,44 @@ int qed_resc_alloc(struct qed_dev *cdev)
/* Set the HW cid/tid numbers (in the contest manager)
* Must be done prior to any further computations.
*/
- rc = qed_cxt_set_pf_params(p_hwfn);
+ rc = qed_cxt_set_pf_params(p_hwfn, RDMA_MAX_TIDS);
if (rc)
goto alloc_err;
- /* Prepare and process QM requirements */
- rc = qed_init_qm_info(p_hwfn, true);
+ rc = qed_alloc_qm_data(p_hwfn);
if (rc)
goto alloc_err;
+ /* init qm info */
+ qed_init_qm_info(p_hwfn);
+
/* Compute the ILT client partition */
- rc = qed_cxt_cfg_ilt_compute(p_hwfn);
- if (rc)
- goto alloc_err;
+ rc = qed_cxt_cfg_ilt_compute(p_hwfn, &line_count);
+ if (rc) {
+ DP_NOTICE(p_hwfn,
+ "too many ILT lines; re-computing with less lines\n");
+ /* In case there are not enough ILT lines we reduce the
+ * number of RDMA tasks and re-compute.
+ */
+ excess_tasks =
+ qed_cxt_cfg_ilt_compute_excess(p_hwfn, line_count);
+ if (!excess_tasks)
+ goto alloc_err;
+
+ rdma_tasks = RDMA_MAX_TIDS - excess_tasks;
+ rc = qed_cxt_set_pf_params(p_hwfn, rdma_tasks);
+ if (rc)
+ goto alloc_err;
+
+ rc = qed_cxt_cfg_ilt_compute(p_hwfn, &line_count);
+ if (rc) {
+ DP_ERR(p_hwfn,
+ "failed ILT compute. Requested too many lines: %u\n",
+ line_count);
+
+ goto alloc_err;
+ }
+ }
/* CID map / ILT shadow table / T2
* The talbes sizes are determined by the computations above
@@ -674,11 +1108,19 @@ int qed_final_cleanup(struct qed_hwfn *p_hwfn,
return rc;
}
-static void qed_calc_hw_mode(struct qed_hwfn *p_hwfn)
+static int qed_calc_hw_mode(struct qed_hwfn *p_hwfn)
{
int hw_mode = 0;
- hw_mode = (1 << MODE_BB_B0);
+ if (QED_IS_BB_B0(p_hwfn->cdev)) {
+ hw_mode |= 1 << MODE_BB;
+ } else if (QED_IS_AH(p_hwfn->cdev)) {
+ hw_mode |= 1 << MODE_K2;
+ } else {
+ DP_NOTICE(p_hwfn, "Unknown chip type %#x\n",
+ p_hwfn->cdev->type);
+ return -EINVAL;
+ }
switch (p_hwfn->cdev->num_ports_in_engines) {
case 1:
@@ -693,7 +1135,7 @@ static void qed_calc_hw_mode(struct qed_hwfn *p_hwfn)
default:
DP_NOTICE(p_hwfn, "num_ports_in_engine = %d not supported\n",
p_hwfn->cdev->num_ports_in_engines);
- return;
+ return -EINVAL;
}
switch (p_hwfn->cdev->mf_mode) {
@@ -719,6 +1161,8 @@ static void qed_calc_hw_mode(struct qed_hwfn *p_hwfn)
DP_VERBOSE(p_hwfn, (NETIF_MSG_PROBE | NETIF_MSG_IFUP),
"Configuring function for hw_mode: 0x%08x\n",
p_hwfn->hw_info.hw_mode);
+
+ return 0;
}
/* Init run time data for all PFs on an engine. */
@@ -748,16 +1192,67 @@ static void qed_init_cau_rt_data(struct qed_dev *cdev)
}
}
+static void qed_init_cache_line_size(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt)
+{
+ u32 val, wr_mbs, cache_line_size;
+
+ val = qed_rd(p_hwfn, p_ptt, PSWRQ2_REG_WR_MBS0);
+ switch (val) {
+ case 0:
+ wr_mbs = 128;
+ break;
+ case 1:
+ wr_mbs = 256;
+ break;
+ case 2:
+ wr_mbs = 512;
+ break;
+ default:
+ DP_INFO(p_hwfn,
+ "Unexpected value of PSWRQ2_REG_WR_MBS0 [0x%x]. Avoid configuring PGLUE_B_REG_CACHE_LINE_SIZE.\n",
+ val);
+ return;
+ }
+
+ cache_line_size = min_t(u32, L1_CACHE_BYTES, wr_mbs);
+ switch (cache_line_size) {
+ case 32:
+ val = 0;
+ break;
+ case 64:
+ val = 1;
+ break;
+ case 128:
+ val = 2;
+ break;
+ case 256:
+ val = 3;
+ break;
+ default:
+ DP_INFO(p_hwfn,
+ "Unexpected value of cache line size [0x%x]. Avoid configuring PGLUE_B_REG_CACHE_LINE_SIZE.\n",
+ cache_line_size);
+ }
+
+ if (L1_CACHE_BYTES > wr_mbs)
+ DP_INFO(p_hwfn,
+ "The cache line size for padding is suboptimal for performance [OS cache line size 0x%x, wr mbs 0x%x]\n",
+ L1_CACHE_BYTES, wr_mbs);
+
+ STORE_RT_REG(p_hwfn, PGLUE_REG_B_CACHE_LINE_SIZE_RT_OFFSET, val);
+}
+
static int qed_hw_init_common(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt, int hw_mode)
{
struct qed_qm_info *qm_info = &p_hwfn->qm_info;
struct qed_qm_common_rt_init_params params;
struct qed_dev *cdev = p_hwfn->cdev;
+ u8 vf_id, max_num_vfs;
u16 num_pfs, pf_id;
u32 concrete_fid;
int rc = 0;
- u8 vf_id;
qed_init_cau_rt_data(cdev);
@@ -784,17 +1279,7 @@ static int qed_hw_init_common(struct qed_hwfn *p_hwfn,
qed_cxt_hw_init_common(p_hwfn);
- /* Close gate from NIG to BRB/Storm; By default they are open, but
- * we close them to prevent NIG from passing data to reset blocks.
- * Should have been done in the ENGINE phase, but init-tool lacks
- * proper port-pretend capabilities.
- */
- qed_wr(p_hwfn, p_ptt, NIG_REG_RX_BRB_OUT_EN, 0);
- qed_wr(p_hwfn, p_ptt, NIG_REG_STORM_OUT_EN, 0);
- qed_port_pretend(p_hwfn, p_ptt, p_hwfn->port_id ^ 1);
- qed_wr(p_hwfn, p_ptt, NIG_REG_RX_BRB_OUT_EN, 0);
- qed_wr(p_hwfn, p_ptt, NIG_REG_STORM_OUT_EN, 0);
- qed_port_unpretend(p_hwfn, p_ptt);
+ qed_init_cache_line_size(p_hwfn, p_ptt);
rc = qed_init_run(p_hwfn, p_ptt, PHASE_ENGINE, ANY_PHASE_ID, hw_mode);
if (rc)
@@ -814,7 +1299,8 @@ static int qed_hw_init_common(struct qed_hwfn *p_hwfn,
qed_fid_pretend(p_hwfn, p_ptt, p_hwfn->rel_pf_id);
}
- for (vf_id = 0; vf_id < MAX_NUM_VFS_BB; vf_id++) {
+ max_num_vfs = QED_IS_AH(cdev) ? MAX_NUM_VFS_K2 : MAX_NUM_VFS_BB;
+ for (vf_id = 0; vf_id < max_num_vfs; vf_id++) {
concrete_fid = qed_vfid_to_concrete(p_hwfn, vf_id);
qed_fid_pretend(p_hwfn, p_ptt, (u16) concrete_fid);
qed_wr(p_hwfn, p_ptt, CCFC_REG_STRONG_ENABLE_VF, 0x1);
@@ -876,7 +1362,7 @@ qed_hw_init_pf_doorbell_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
int rc = 0;
u8 cond;
- db_bar_size = qed_hw_bar_size(p_hwfn, BAR_ID_1);
+ db_bar_size = qed_hw_bar_size(p_hwfn, p_ptt, BAR_ID_1);
if (p_hwfn->cdev->num_hwfns > 1)
db_bar_size /= 2;
@@ -987,7 +1473,7 @@ static int qed_hw_init_pf(struct qed_hwfn *p_hwfn,
p_hwfn->qm_info.pf_rl = 100000;
}
- qed_cxt_hw_init_pf(p_hwfn);
+ qed_cxt_hw_init_pf(p_hwfn, p_ptt);
qed_int_igu_init_rt(p_hwfn);
@@ -1095,25 +1581,34 @@ static void qed_reset_mb_shadow(struct qed_hwfn *p_hwfn,
p_hwfn->mcp_info->mfw_mb_cur, p_hwfn->mcp_info->mfw_mb_length);
}
-int qed_hw_init(struct qed_dev *cdev,
- struct qed_tunn_start_params *p_tunn,
- bool b_hw_start,
- enum qed_int_mode int_mode,
- bool allow_npar_tx_switch,
- const u8 *bin_fw_data)
+static void
+qed_fill_load_req_params(struct qed_load_req_params *p_load_req,
+ struct qed_drv_load_params *p_drv_load)
{
+ memset(p_load_req, 0, sizeof(*p_load_req));
+
+ p_load_req->drv_role = p_drv_load->is_crash_kernel ?
+ QED_DRV_ROLE_KDUMP : QED_DRV_ROLE_OS;
+ p_load_req->timeout_val = p_drv_load->mfw_timeout_val;
+ p_load_req->avoid_eng_reset = p_drv_load->avoid_eng_reset;
+ p_load_req->override_force_load = p_drv_load->override_force_load;
+}
+
+int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
+{
+ struct qed_load_req_params load_req_params;
u32 load_code, param, drv_mb_param;
bool b_default_mtu = true;
struct qed_hwfn *p_hwfn;
int rc = 0, mfw_rc, i;
- if ((int_mode == QED_INT_MODE_MSI) && (cdev->num_hwfns > 1)) {
+ if ((p_params->int_mode == QED_INT_MODE_MSI) && (cdev->num_hwfns > 1)) {
DP_NOTICE(cdev, "MSI mode is not supported for CMT devices\n");
return -EINVAL;
}
if (IS_PF(cdev)) {
- rc = qed_init_fw_data(cdev, bin_fw_data);
+ rc = qed_init_fw_data(cdev, p_params->bin_fw_data);
if (rc)
return rc;
}
@@ -1135,19 +1630,25 @@ int qed_hw_init(struct qed_dev *cdev,
/* Enable DMAE in PXP */
rc = qed_change_pci_hwfn(p_hwfn, p_hwfn->p_main_ptt, true);
- qed_calc_hw_mode(p_hwfn);
+ rc = qed_calc_hw_mode(p_hwfn);
+ if (rc)
+ return rc;
- rc = qed_mcp_load_req(p_hwfn, p_hwfn->p_main_ptt, &load_code);
+ qed_fill_load_req_params(&load_req_params,
+ p_params->p_drv_load_params);
+ rc = qed_mcp_load_req(p_hwfn, p_hwfn->p_main_ptt,
+ &load_req_params);
if (rc) {
- DP_NOTICE(p_hwfn, "Failed sending LOAD_REQ command\n");
+ DP_NOTICE(p_hwfn, "Failed sending a LOAD_REQ command\n");
return rc;
}
- qed_reset_mb_shadow(p_hwfn, p_hwfn->p_main_ptt);
-
+ load_code = load_req_params.load_code;
DP_VERBOSE(p_hwfn, QED_MSG_SP,
- "Load request was sent. Resp:0x%x, Load code: 0x%x\n",
- rc, load_code);
+ "Load request was sent. Load code: 0x%x\n",
+ load_code);
+
+ qed_reset_mb_shadow(p_hwfn, p_hwfn->p_main_ptt);
p_hwfn->first_on_engine = (load_code ==
FW_MSG_CODE_DRV_LOAD_ENGINE);
@@ -1168,11 +1669,15 @@ int qed_hw_init(struct qed_dev *cdev,
/* Fall into */
case FW_MSG_CODE_DRV_LOAD_FUNCTION:
rc = qed_hw_init_pf(p_hwfn, p_hwfn->p_main_ptt,
- p_tunn, p_hwfn->hw_info.hw_mode,
- b_hw_start, int_mode,
- allow_npar_tx_switch);
+ p_params->p_tunn,
+ p_hwfn->hw_info.hw_mode,
+ p_params->b_hw_start,
+ p_params->int_mode,
+ p_params->allow_npar_tx_switch);
break;
default:
+ DP_NOTICE(p_hwfn,
+ "Unexpected load code [0x%08x]", load_code);
rc = -EINVAL;
break;
}
@@ -1212,10 +1717,7 @@ int qed_hw_init(struct qed_dev *cdev,
if (IS_PF(cdev)) {
p_hwfn = QED_LEADING_HWFN(cdev);
- drv_mb_param = (FW_MAJOR_VERSION << 24) |
- (FW_MINOR_VERSION << 16) |
- (FW_REVISION_VERSION << 8) |
- (FW_ENGINEERING_VERSION);
+ drv_mb_param = STORM_FW_VERSION;
rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
DRV_MSG_CODE_OV_UPDATE_STORM_FW_VER,
drv_mb_param, &load_code, ¶m);
@@ -1290,27 +1792,53 @@ void qed_hw_timers_stop_all(struct qed_dev *cdev)
int qed_hw_stop(struct qed_dev *cdev)
{
- int rc = 0, t_rc;
+ struct qed_hwfn *p_hwfn;
+ struct qed_ptt *p_ptt;
+ int rc, rc2 = 0;
int j;
for_each_hwfn(cdev, j) {
- struct qed_hwfn *p_hwfn = &cdev->hwfns[j];
- struct qed_ptt *p_ptt = p_hwfn->p_main_ptt;
+ p_hwfn = &cdev->hwfns[j];
+ p_ptt = p_hwfn->p_main_ptt;
DP_VERBOSE(p_hwfn, NETIF_MSG_IFDOWN, "Stopping hw/fw\n");
if (IS_VF(cdev)) {
qed_vf_pf_int_cleanup(p_hwfn);
+ rc = qed_vf_pf_reset(p_hwfn);
+ if (rc) {
+ DP_NOTICE(p_hwfn,
+ "qed_vf_pf_reset failed. rc = %d.\n",
+ rc);
+ rc2 = -EINVAL;
+ }
continue;
}
/* mark the hw as uninitialized... */
p_hwfn->hw_init_done = false;
- rc = qed_sp_pf_stop(p_hwfn);
- if (rc)
+ /* Send unload command to MCP */
+ rc = qed_mcp_unload_req(p_hwfn, p_ptt);
+ if (rc) {
DP_NOTICE(p_hwfn,
- "Failed to close PF against FW. Continue to stop HW to prevent illegal host access by the device\n");
+ "Failed sending a UNLOAD_REQ command. rc = %d.\n",
+ rc);
+ rc2 = -EINVAL;
+ }
+
+ qed_slowpath_irq_sync(p_hwfn);
+
+ /* After this point no MFW attentions are expected, e.g. prevent
+ * race between pf stop and dcbx pf update.
+ */
+ rc = qed_sp_pf_stop(p_hwfn);
+ if (rc) {
+ DP_NOTICE(p_hwfn,
+ "Failed to close PF against FW [rc = %d]. Continue to stop HW to prevent illegal host access by the device.\n",
+ rc);
+ rc2 = -EINVAL;
+ }
qed_wr(p_hwfn, p_ptt,
NIG_REG_RX_LLH_BRB_GATE_DNTFWD_PERPF, 0x1);
@@ -1333,34 +1861,54 @@ int qed_hw_stop(struct qed_dev *cdev)
/* Need to wait 1ms to guarantee SBs are cleared */
usleep_range(1000, 2000);
+
+ /* Disable PF in HW blocks */
+ qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_DB_ENABLE, 0);
+ qed_wr(p_hwfn, p_ptt, QM_REG_PF_EN, 0);
+
+ qed_mcp_unload_done(p_hwfn, p_ptt);
+ if (rc) {
+ DP_NOTICE(p_hwfn,
+ "Failed sending a UNLOAD_DONE command. rc = %d.\n",
+ rc);
+ rc2 = -EINVAL;
+ }
}
if (IS_PF(cdev)) {
+ p_hwfn = QED_LEADING_HWFN(cdev);
+ p_ptt = QED_LEADING_HWFN(cdev)->p_main_ptt;
+
/* Disable DMAE in PXP - in CMT, this should only be done for
* first hw-function, and only after all transactions have
* stopped for all active hw-functions.
*/
- t_rc = qed_change_pci_hwfn(&cdev->hwfns[0],
- cdev->hwfns[0].p_main_ptt, false);
- if (t_rc != 0)
- rc = t_rc;
+ rc = qed_change_pci_hwfn(p_hwfn, p_ptt, false);
+ if (rc) {
+ DP_NOTICE(p_hwfn,
+ "qed_change_pci_hwfn failed. rc = %d.\n", rc);
+ rc2 = -EINVAL;
+ }
}
- return rc;
+ return rc2;
}
-void qed_hw_stop_fastpath(struct qed_dev *cdev)
+int qed_hw_stop_fastpath(struct qed_dev *cdev)
{
int j;
for_each_hwfn(cdev, j) {
struct qed_hwfn *p_hwfn = &cdev->hwfns[j];
- struct qed_ptt *p_ptt = p_hwfn->p_main_ptt;
+ struct qed_ptt *p_ptt;
if (IS_VF(cdev)) {
qed_vf_pf_int_cleanup(p_hwfn);
continue;
}
+ p_ptt = qed_ptt_acquire(p_hwfn);
+ if (!p_ptt)
+ return -EAGAIN;
DP_VERBOSE(p_hwfn,
NETIF_MSG_IFDOWN, "Shutting down the fastpath\n");
@@ -1378,100 +1926,28 @@ void qed_hw_stop_fastpath(struct qed_dev *cdev)
/* Need to wait 1ms to guarantee SBs are cleared */
usleep_range(1000, 2000);
- }
-}
-
-void qed_hw_start_fastpath(struct qed_hwfn *p_hwfn)
-{
- if (IS_VF(p_hwfn->cdev))
- return;
-
- /* Re-open incoming traffic */
- qed_wr(p_hwfn, p_hwfn->p_main_ptt,
- NIG_REG_RX_LLH_BRB_GATE_DNTFWD_PERPF, 0x0);
-}
-
-static int qed_reg_assert(struct qed_hwfn *p_hwfn,
- struct qed_ptt *p_ptt, u32 reg, bool expected)
-{
- u32 assert_val = qed_rd(p_hwfn, p_ptt, reg);
-
- if (assert_val != expected) {
- DP_NOTICE(p_hwfn, "Value at address 0x%08x != 0x%08x\n",
- reg, expected);
- return -EINVAL;
+ qed_ptt_release(p_hwfn, p_ptt);
}
return 0;
}
-int qed_hw_reset(struct qed_dev *cdev)
+int qed_hw_start_fastpath(struct qed_hwfn *p_hwfn)
{
- int rc = 0;
- u32 unload_resp, unload_param;
- u32 wol_param;
- int i;
+ struct qed_ptt *p_ptt;
- switch (cdev->wol_config) {
- case QED_OV_WOL_DISABLED:
- wol_param = DRV_MB_PARAM_UNLOAD_WOL_DISABLED;
- break;
- case QED_OV_WOL_ENABLED:
- wol_param = DRV_MB_PARAM_UNLOAD_WOL_ENABLED;
- break;
- default:
- DP_NOTICE(cdev,
- "Unknown WoL configuration %02x\n", cdev->wol_config);
- /* Fallthrough */
- case QED_OV_WOL_DEFAULT:
- wol_param = DRV_MB_PARAM_UNLOAD_WOL_MCP;
- }
+ if (IS_VF(p_hwfn->cdev))
+ return 0;
- for_each_hwfn(cdev, i) {
- struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
+ p_ptt = qed_ptt_acquire(p_hwfn);
+ if (!p_ptt)
+ return -EAGAIN;
- if (IS_VF(cdev)) {
- rc = qed_vf_pf_reset(p_hwfn);
- if (rc)
- return rc;
- continue;
- }
+ /* Re-open incoming traffic */
+ qed_wr(p_hwfn, p_ptt, NIG_REG_RX_LLH_BRB_GATE_DNTFWD_PERPF, 0x0);
+ qed_ptt_release(p_hwfn, p_ptt);
- DP_VERBOSE(p_hwfn, NETIF_MSG_IFDOWN, "Resetting hw/fw\n");
-
- /* Check for incorrect states */
- qed_reg_assert(p_hwfn, p_hwfn->p_main_ptt,
- QM_REG_USG_CNT_PF_TX, 0);
- qed_reg_assert(p_hwfn, p_hwfn->p_main_ptt,
- QM_REG_USG_CNT_PF_OTHER, 0);
-
- /* Disable PF in HW blocks */
- qed_wr(p_hwfn, p_hwfn->p_main_ptt, DORQ_REG_PF_DB_ENABLE, 0);
- qed_wr(p_hwfn, p_hwfn->p_main_ptt, QM_REG_PF_EN, 0);
- qed_wr(p_hwfn, p_hwfn->p_main_ptt,
- TCFC_REG_STRONG_ENABLE_PF, 0);
- qed_wr(p_hwfn, p_hwfn->p_main_ptt,
- CCFC_REG_STRONG_ENABLE_PF, 0);
-
- /* Send unload command to MCP */
- rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
- DRV_MSG_CODE_UNLOAD_REQ, wol_param,
- &unload_resp, &unload_param);
- if (rc) {
- DP_NOTICE(p_hwfn, "qed_hw_reset: UNLOAD_REQ failed\n");
- unload_resp = FW_MSG_CODE_DRV_UNLOAD_ENGINE;
- }
-
- rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
- DRV_MSG_CODE_UNLOAD_DONE,
- 0, &unload_resp, &unload_param);
- if (rc) {
- DP_NOTICE(p_hwfn, "qed_hw_reset: UNLOAD_DONE failed\n");
- return rc;
- }
- }
-
- return rc;
+ return 0;
}
/* Free hwfn memory and resources acquired in hw_hwfn_prepare */
@@ -1485,10 +1961,25 @@ static void qed_hw_hwfn_free(struct qed_hwfn *p_hwfn)
static void qed_hw_hwfn_prepare(struct qed_hwfn *p_hwfn)
{
/* clear indirect access */
- qed_wr(p_hwfn, p_hwfn->p_main_ptt, PGLUE_B_REG_PGL_ADDR_88_F0, 0);
- qed_wr(p_hwfn, p_hwfn->p_main_ptt, PGLUE_B_REG_PGL_ADDR_8C_F0, 0);
- qed_wr(p_hwfn, p_hwfn->p_main_ptt, PGLUE_B_REG_PGL_ADDR_90_F0, 0);
- qed_wr(p_hwfn, p_hwfn->p_main_ptt, PGLUE_B_REG_PGL_ADDR_94_F0, 0);
+ if (QED_IS_AH(p_hwfn->cdev)) {
+ qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+ PGLUE_B_REG_PGL_ADDR_E8_F0_K2, 0);
+ qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+ PGLUE_B_REG_PGL_ADDR_EC_F0_K2, 0);
+ qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+ PGLUE_B_REG_PGL_ADDR_F0_F0_K2, 0);
+ qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+ PGLUE_B_REG_PGL_ADDR_F4_F0_K2, 0);
+ } else {
+ qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+ PGLUE_B_REG_PGL_ADDR_88_F0_BB, 0);
+ qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+ PGLUE_B_REG_PGL_ADDR_8C_F0_BB, 0);
+ qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+ PGLUE_B_REG_PGL_ADDR_90_F0_BB, 0);
+ qed_wr(p_hwfn, p_hwfn->p_main_ptt,
+ PGLUE_B_REG_PGL_ADDR_94_F0_BB, 0);
+ }
/* Clean Previous errors if such exist */
qed_wr(p_hwfn, p_hwfn->p_main_ptt,
@@ -1522,7 +2013,7 @@ static void qed_hw_set_feat(struct qed_hwfn *p_hwfn)
{
u32 *feat_num = p_hwfn->hw_info.feat_num;
struct qed_sb_cnt_info sb_cnt_info;
- int num_features = 1;
+ u32 non_l2_sbs = 0;
if (IS_ENABLED(CONFIG_QED_RDMA) &&
p_hwfn->hw_info.personality == QED_PCI_ETH_ROCE) {
@@ -1530,143 +2021,47 @@ static void qed_hw_set_feat(struct qed_hwfn *p_hwfn)
* the status blocks equally between L2 / RoCE but with
* consideration as to how many l2 queues / cnqs we have.
*/
- num_features++;
-
feat_num[QED_RDMA_CNQ] =
- min_t(u32, RESC_NUM(p_hwfn, QED_SB) / num_features,
+ min_t(u32, RESC_NUM(p_hwfn, QED_SB) / 2,
RESC_NUM(p_hwfn, QED_RDMA_CNQ_RAM));
+
+ non_l2_sbs = feat_num[QED_RDMA_CNQ];
}
- feat_num[QED_PF_L2_QUE] = min_t(u32, RESC_NUM(p_hwfn, QED_SB) /
- num_features,
- RESC_NUM(p_hwfn, QED_L2_QUEUE));
+ if (p_hwfn->hw_info.personality == QED_PCI_ETH_ROCE ||
+ p_hwfn->hw_info.personality == QED_PCI_ETH) {
+ /* Start by allocating VF queues, then PF's */
+ memset(&sb_cnt_info, 0, sizeof(sb_cnt_info));
+ qed_int_get_num_sbs(p_hwfn, &sb_cnt_info);
+ feat_num[QED_VF_L2_QUE] = min_t(u32,
+ RESC_NUM(p_hwfn, QED_L2_QUEUE),
+ sb_cnt_info.sb_iov_cnt);
+ feat_num[QED_PF_L2_QUE] = min_t(u32,
+ RESC_NUM(p_hwfn, QED_SB) -
+ non_l2_sbs,
+ RESC_NUM(p_hwfn,
+ QED_L2_QUEUE) -
+ FEAT_NUM(p_hwfn,
+ QED_VF_L2_QUE));
+ }
- memset(&sb_cnt_info, 0, sizeof(sb_cnt_info));
- qed_int_get_num_sbs(p_hwfn, &sb_cnt_info);
- feat_num[QED_VF_L2_QUE] =
- min_t(u32,
- RESC_NUM(p_hwfn, QED_L2_QUEUE) -
- FEAT_NUM(p_hwfn, QED_PF_L2_QUE), sb_cnt_info.sb_iov_cnt);
-
+ if (p_hwfn->hw_info.personality == QED_PCI_ISCSI)
+ feat_num[QED_ISCSI_CQ] = min_t(u32, RESC_NUM(p_hwfn, QED_SB),
+ RESC_NUM(p_hwfn,
+ QED_CMDQS_CQS));
DP_VERBOSE(p_hwfn,
NETIF_MSG_PROBE,
- "#PF_L2_QUEUES=%d VF_L2_QUEUES=%d #ROCE_CNQ=%d #SBS=%d num_features=%d\n",
+ "#PF_L2_QUEUES=%d VF_L2_QUEUES=%d #ROCE_CNQ=%d ISCSI_CQ=%d #SBS=%d\n",
(int)FEAT_NUM(p_hwfn, QED_PF_L2_QUE),
(int)FEAT_NUM(p_hwfn, QED_VF_L2_QUE),
(int)FEAT_NUM(p_hwfn, QED_RDMA_CNQ),
- RESC_NUM(p_hwfn, QED_SB), num_features);
+ (int)FEAT_NUM(p_hwfn, QED_ISCSI_CQ),
+ RESC_NUM(p_hwfn, QED_SB));
}
-static enum resource_id_enum qed_hw_get_mfw_res_id(enum qed_resources res_id)
-{
- enum resource_id_enum mfw_res_id = RESOURCE_NUM_INVALID;
-
- switch (res_id) {
- case QED_SB:
- mfw_res_id = RESOURCE_NUM_SB_E;
- break;
- case QED_L2_QUEUE:
- mfw_res_id = RESOURCE_NUM_L2_QUEUE_E;
- break;
- case QED_VPORT:
- mfw_res_id = RESOURCE_NUM_VPORT_E;
- break;
- case QED_RSS_ENG:
- mfw_res_id = RESOURCE_NUM_RSS_ENGINES_E;
- break;
- case QED_PQ:
- mfw_res_id = RESOURCE_NUM_PQ_E;
- break;
- case QED_RL:
- mfw_res_id = RESOURCE_NUM_RL_E;
- break;
- case QED_MAC:
- case QED_VLAN:
- /* Each VFC resource can accommodate both a MAC and a VLAN */
- mfw_res_id = RESOURCE_VFC_FILTER_E;
- break;
- case QED_ILT:
- mfw_res_id = RESOURCE_ILT_E;
- break;
- case QED_LL2_QUEUE:
- mfw_res_id = RESOURCE_LL2_QUEUE_E;
- break;
- case QED_RDMA_CNQ_RAM:
- case QED_CMDQS_CQS:
- /* CNQ/CMDQS are the same resource */
- mfw_res_id = RESOURCE_CQS_E;
- break;
- case QED_RDMA_STATS_QUEUE:
- mfw_res_id = RESOURCE_RDMA_STATS_QUEUE_E;
- break;
- default:
- break;
- }
-
- return mfw_res_id;
-}
-
-static u32 qed_hw_get_dflt_resc_num(struct qed_hwfn *p_hwfn,
- enum qed_resources res_id)
-{
- u8 num_funcs = p_hwfn->num_funcs_on_engine;
- struct qed_sb_cnt_info sb_cnt_info;
- u32 dflt_resc_num = 0;
-
- switch (res_id) {
- case QED_SB:
- memset(&sb_cnt_info, 0, sizeof(sb_cnt_info));
- qed_int_get_num_sbs(p_hwfn, &sb_cnt_info);
- dflt_resc_num = sb_cnt_info.sb_cnt;
- break;
- case QED_L2_QUEUE:
- dflt_resc_num = MAX_NUM_L2_QUEUES_BB / num_funcs;
- break;
- case QED_VPORT:
- dflt_resc_num = MAX_NUM_VPORTS_BB / num_funcs;
- break;
- case QED_RSS_ENG:
- dflt_resc_num = ETH_RSS_ENGINE_NUM_BB / num_funcs;
- break;
- case QED_PQ:
- /* The granularity of the PQs is 8 */
- dflt_resc_num = MAX_QM_TX_QUEUES_BB / num_funcs;
- dflt_resc_num &= ~0x7;
- break;
- case QED_RL:
- dflt_resc_num = MAX_QM_GLOBAL_RLS / num_funcs;
- break;
- case QED_MAC:
- case QED_VLAN:
- /* Each VFC resource can accommodate both a MAC and a VLAN */
- dflt_resc_num = ETH_NUM_MAC_FILTERS / num_funcs;
- break;
- case QED_ILT:
- dflt_resc_num = PXP_NUM_ILT_RECORDS_BB / num_funcs;
- break;
- case QED_LL2_QUEUE:
- dflt_resc_num = MAX_NUM_LL2_RX_QUEUES / num_funcs;
- break;
- case QED_RDMA_CNQ_RAM:
- case QED_CMDQS_CQS:
- /* CNQ/CMDQS are the same resource */
- dflt_resc_num = NUM_OF_CMDQS_CQS / num_funcs;
- break;
- case QED_RDMA_STATS_QUEUE:
- dflt_resc_num = RDMA_NUM_STATISTIC_COUNTERS_BB / num_funcs;
- break;
- default:
- break;
- }
-
- return dflt_resc_num;
-}
-
-static const char *qed_hw_get_resc_name(enum qed_resources res_id)
+const char *qed_hw_get_resc_name(enum qed_resources res_id)
{
switch (res_id) {
- case QED_SB:
- return "SB";
case QED_L2_QUEUE:
return "L2_QUEUE";
case QED_VPORT:
@@ -1691,43 +2086,195 @@ static const char *qed_hw_get_resc_name(enum qed_resources res_id)
return "CMDQS_CQS";
case QED_RDMA_STATS_QUEUE:
return "RDMA_STATS_QUEUE";
+ case QED_BDQ:
+ return "BDQ";
+ case QED_SB:
+ return "SB";
default:
return "UNKNOWN_RESOURCE";
}
}
-static int qed_hw_set_resc_info(struct qed_hwfn *p_hwfn,
- enum qed_resources res_id)
+static int
+__qed_hw_set_soft_resc_size(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ enum qed_resources res_id,
+ u32 resc_max_val, u32 *p_mcp_resp)
{
- u32 dflt_resc_num = 0, dflt_resc_start = 0, mcp_resp, mcp_param;
- u32 *p_resc_num, *p_resc_start;
- struct resource_info resc_info;
+ int rc;
+
+ rc = qed_mcp_set_resc_max_val(p_hwfn, p_ptt, res_id,
+ resc_max_val, p_mcp_resp);
+ if (rc) {
+ DP_NOTICE(p_hwfn,
+ "MFW response failure for a max value setting of resource %d [%s]\n",
+ res_id, qed_hw_get_resc_name(res_id));
+ return rc;
+ }
+
+ if (*p_mcp_resp != FW_MSG_CODE_RESOURCE_ALLOC_OK)
+ DP_INFO(p_hwfn,
+ "Failed to set the max value of resource %d [%s]. mcp_resp = 0x%08x.\n",
+ res_id, qed_hw_get_resc_name(res_id), *p_mcp_resp);
+
+ return 0;
+}
+
+static int
+qed_hw_set_soft_resc_size(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+ bool b_ah = QED_IS_AH(p_hwfn->cdev);
+ u32 resc_max_val, mcp_resp;
+ u8 res_id;
+ int rc;
+
+ for (res_id = 0; res_id < QED_MAX_RESC; res_id++) {
+ switch (res_id) {
+ case QED_LL2_QUEUE:
+ resc_max_val = MAX_NUM_LL2_RX_QUEUES;
+ break;
+ case QED_RDMA_CNQ_RAM:
+ /* No need for a case for QED_CMDQS_CQS since
+ * CNQ/CMDQS are the same resource.
+ */
+ resc_max_val = NUM_OF_CMDQS_CQS;
+ break;
+ case QED_RDMA_STATS_QUEUE:
+ resc_max_val = b_ah ? RDMA_NUM_STATISTIC_COUNTERS_K2
+ : RDMA_NUM_STATISTIC_COUNTERS_BB;
+ break;
+ case QED_BDQ:
+ resc_max_val = BDQ_NUM_RESOURCES;
+ break;
+ default:
+ continue;
+ }
+
+ rc = __qed_hw_set_soft_resc_size(p_hwfn, p_ptt, res_id,
+ resc_max_val, &mcp_resp);
+ if (rc)
+ return rc;
+
+ /* There's no point to continue to the next resource if the
+ * command is not supported by the MFW.
+ * We do continue if the command is supported but the resource
+ * is unknown to the MFW. Such a resource will be later
+ * configured with the default allocation values.
+ */
+ if (mcp_resp == FW_MSG_CODE_UNSUPPORTED)
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static
+int qed_hw_get_dflt_resc(struct qed_hwfn *p_hwfn,
+ enum qed_resources res_id,
+ u32 *p_resc_num, u32 *p_resc_start)
+{
+ u8 num_funcs = p_hwfn->num_funcs_on_engine;
+ bool b_ah = QED_IS_AH(p_hwfn->cdev);
+ struct qed_sb_cnt_info sb_cnt_info;
+
+ switch (res_id) {
+ case QED_L2_QUEUE:
+ *p_resc_num = (b_ah ? MAX_NUM_L2_QUEUES_K2 :
+ MAX_NUM_L2_QUEUES_BB) / num_funcs;
+ break;
+ case QED_VPORT:
+ *p_resc_num = (b_ah ? MAX_NUM_VPORTS_K2 :
+ MAX_NUM_VPORTS_BB) / num_funcs;
+ break;
+ case QED_RSS_ENG:
+ *p_resc_num = (b_ah ? ETH_RSS_ENGINE_NUM_K2 :
+ ETH_RSS_ENGINE_NUM_BB) / num_funcs;
+ break;
+ case QED_PQ:
+ *p_resc_num = (b_ah ? MAX_QM_TX_QUEUES_K2 :
+ MAX_QM_TX_QUEUES_BB) / num_funcs;
+ *p_resc_num &= ~0x7; /* The granularity of the PQs is 8 */
+ break;
+ case QED_RL:
+ *p_resc_num = MAX_QM_GLOBAL_RLS / num_funcs;
+ break;
+ case QED_MAC:
+ case QED_VLAN:
+ /* Each VFC resource can accommodate both a MAC and a VLAN */
+ *p_resc_num = ETH_NUM_MAC_FILTERS / num_funcs;
+ break;
+ case QED_ILT:
+ *p_resc_num = (b_ah ? PXP_NUM_ILT_RECORDS_K2 :
+ PXP_NUM_ILT_RECORDS_BB) / num_funcs;
+ break;
+ case QED_LL2_QUEUE:
+ *p_resc_num = MAX_NUM_LL2_RX_QUEUES / num_funcs;
+ break;
+ case QED_RDMA_CNQ_RAM:
+ case QED_CMDQS_CQS:
+ /* CNQ/CMDQS are the same resource */
+ *p_resc_num = NUM_OF_CMDQS_CQS / num_funcs;
+ break;
+ case QED_RDMA_STATS_QUEUE:
+ *p_resc_num = (b_ah ? RDMA_NUM_STATISTIC_COUNTERS_K2 :
+ RDMA_NUM_STATISTIC_COUNTERS_BB) / num_funcs;
+ break;
+ case QED_BDQ:
+ if (p_hwfn->hw_info.personality != QED_PCI_ISCSI &&
+ p_hwfn->hw_info.personality != QED_PCI_FCOE)
+ *p_resc_num = 0;
+ else
+ *p_resc_num = 1;
+ break;
+ case QED_SB:
+ memset(&sb_cnt_info, 0, sizeof(sb_cnt_info));
+ qed_int_get_num_sbs(p_hwfn, &sb_cnt_info);
+ *p_resc_num = sb_cnt_info.sb_cnt;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ switch (res_id) {
+ case QED_BDQ:
+ if (!*p_resc_num)
+ *p_resc_start = 0;
+ else if (p_hwfn->cdev->num_ports_in_engines == 4)
+ *p_resc_start = p_hwfn->port_id;
+ else if (p_hwfn->hw_info.personality == QED_PCI_ISCSI)
+ *p_resc_start = p_hwfn->port_id;
+ else if (p_hwfn->hw_info.personality == QED_PCI_FCOE)
+ *p_resc_start = p_hwfn->port_id + 2;
+ break;
+ default:
+ *p_resc_start = *p_resc_num * p_hwfn->enabled_func_idx;
+ break;
+ }
+
+ return 0;
+}
+
+static int __qed_hw_set_resc_info(struct qed_hwfn *p_hwfn,
+ enum qed_resources res_id)
+{
+ u32 dflt_resc_num = 0, dflt_resc_start = 0;
+ u32 mcp_resp, *p_resc_num, *p_resc_start;
int rc;
p_resc_num = &RESC_NUM(p_hwfn, res_id);
p_resc_start = &RESC_START(p_hwfn, res_id);
- /* Default values assumes that each function received equal share */
- dflt_resc_num = qed_hw_get_dflt_resc_num(p_hwfn, res_id);
- if (!dflt_resc_num) {
+ rc = qed_hw_get_dflt_resc(p_hwfn, res_id, &dflt_resc_num,
+ &dflt_resc_start);
+ if (rc) {
DP_ERR(p_hwfn,
"Failed to get default amount for resource %d [%s]\n",
res_id, qed_hw_get_resc_name(res_id));
- return -EINVAL;
- }
- dflt_resc_start = dflt_resc_num * p_hwfn->enabled_func_idx;
-
- memset(&resc_info, 0, sizeof(resc_info));
- resc_info.res_id = qed_hw_get_mfw_res_id(res_id);
- if (resc_info.res_id == RESOURCE_NUM_INVALID) {
- DP_ERR(p_hwfn,
- "Failed to match resource %d [%s] with the MFW resources\n",
- res_id, qed_hw_get_resc_name(res_id));
- return -EINVAL;
+ return rc;
}
- rc = qed_mcp_get_resc_info(p_hwfn, p_hwfn->p_main_ptt, &resc_info,
- &mcp_resp, &mcp_param);
+ rc = qed_mcp_get_resc_info(p_hwfn, p_hwfn->p_main_ptt, res_id,
+ &mcp_resp, p_resc_num, p_resc_start);
if (rc) {
DP_NOTICE(p_hwfn,
"MFW response failure for an allocation request for resource %d [%s]\n",
@@ -1740,13 +2287,12 @@ static int qed_hw_set_resc_info(struct qed_hwfn *p_hwfn,
* - There is an internal error in the MFW while processing the request
* - The resource ID is unknown to the MFW
*/
- if (mcp_resp != FW_MSG_CODE_RESOURCE_ALLOC_OK &&
- mcp_resp != FW_MSG_CODE_RESOURCE_ALLOC_DEPRECATED) {
- DP_NOTICE(p_hwfn,
- "Resource %d [%s]: No allocation info was received [mcp_resp 0x%x]. Applying default values [num %d, start %d].\n",
- res_id,
- qed_hw_get_resc_name(res_id),
- mcp_resp, dflt_resc_num, dflt_resc_start);
+ if (mcp_resp != FW_MSG_CODE_RESOURCE_ALLOC_OK) {
+ DP_INFO(p_hwfn,
+ "Failed to receive allocation info for resource %d [%s]. mcp_resp = 0x%x. Applying default values [%d,%d].\n",
+ res_id,
+ qed_hw_get_resc_name(res_id),
+ mcp_resp, dflt_resc_num, dflt_resc_start);
*p_resc_num = dflt_resc_num;
*p_resc_start = dflt_resc_start;
goto out;
@@ -1754,13 +2300,9 @@ static int qed_hw_set_resc_info(struct qed_hwfn *p_hwfn,
/* Special handling for status blocks; Would be revised in future */
if (res_id == QED_SB) {
- resc_info.size -= 1;
- resc_info.offset -= p_hwfn->enabled_func_idx;
+ *p_resc_num -= 1;
+ *p_resc_start -= p_hwfn->enabled_func_idx;
}
-
- *p_resc_num = resc_info.size;
- *p_resc_start = resc_info.offset;
-
out:
/* PQs have to divide by 8 [that's the HW granularity].
* Reduce number so it would fit.
@@ -1778,19 +2320,88 @@ static int qed_hw_set_resc_info(struct qed_hwfn *p_hwfn,
return 0;
}
-static int qed_hw_get_resc(struct qed_hwfn *p_hwfn)
+static int qed_hw_set_resc_info(struct qed_hwfn *p_hwfn)
{
- u8 res_id;
int rc;
+ u8 res_id;
for (res_id = 0; res_id < QED_MAX_RESC; res_id++) {
- rc = qed_hw_set_resc_info(p_hwfn, res_id);
+ rc = __qed_hw_set_resc_info(p_hwfn, res_id);
if (rc)
return rc;
}
+ return 0;
+}
+
+#define QED_RESC_ALLOC_LOCK_RETRY_CNT 10
+#define QED_RESC_ALLOC_LOCK_RETRY_INTVL_US 10000 /* 10 msec */
+
+static int qed_hw_get_resc(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+ struct qed_resc_unlock_params resc_unlock_params;
+ struct qed_resc_lock_params resc_lock_params;
+ bool b_ah = QED_IS_AH(p_hwfn->cdev);
+ u8 res_id;
+ int rc;
+
+ /* Setting the max values of the soft resources and the following
+ * resources allocation queries should be atomic. Since several PFs can
+ * run in parallel - a resource lock is needed.
+ * If either the resource lock or resource set value commands are not
+ * supported - skip the the max values setting, release the lock if
+ * needed, and proceed to the queries. Other failures, including a
+ * failure to acquire the lock, will cause this function to fail.
+ */
+ memset(&resc_lock_params, 0, sizeof(resc_lock_params));
+ resc_lock_params.resource = QED_RESC_LOCK_RESC_ALLOC;
+ resc_lock_params.retry_num = QED_RESC_ALLOC_LOCK_RETRY_CNT;
+ resc_lock_params.retry_interval = QED_RESC_ALLOC_LOCK_RETRY_INTVL_US;
+ resc_lock_params.sleep_b4_retry = true;
+ memset(&resc_unlock_params, 0, sizeof(resc_unlock_params));
+ resc_unlock_params.resource = QED_RESC_LOCK_RESC_ALLOC;
+
+ rc = qed_mcp_resc_lock(p_hwfn, p_ptt, &resc_lock_params);
+ if (rc && rc != -EINVAL) {
+ return rc;
+ } else if (rc == -EINVAL) {
+ DP_INFO(p_hwfn,
+ "Skip the max values setting of the soft resources since the resource lock is not supported by the MFW\n");
+ } else if (!rc && !resc_lock_params.b_granted) {
+ DP_NOTICE(p_hwfn,
+ "Failed to acquire the resource lock for the resource allocation commands\n");
+ return -EBUSY;
+ } else {
+ rc = qed_hw_set_soft_resc_size(p_hwfn, p_ptt);
+ if (rc && rc != -EINVAL) {
+ DP_NOTICE(p_hwfn,
+ "Failed to set the max values of the soft resources\n");
+ goto unlock_and_exit;
+ } else if (rc == -EINVAL) {
+ DP_INFO(p_hwfn,
+ "Skip the max values setting of the soft resources since it is not supported by the MFW\n");
+ rc = qed_mcp_resc_unlock(p_hwfn, p_ptt,
+ &resc_unlock_params);
+ if (rc)
+ DP_INFO(p_hwfn,
+ "Failed to release the resource lock for the resource allocation commands\n");
+ }
+ }
+
+ rc = qed_hw_set_resc_info(p_hwfn);
+ if (rc)
+ goto unlock_and_exit;
+
+ if (resc_lock_params.b_granted && !resc_unlock_params.b_released) {
+ rc = qed_mcp_resc_unlock(p_hwfn, p_ptt, &resc_unlock_params);
+ if (rc)
+ DP_INFO(p_hwfn,
+ "Failed to release the resource lock for the resource allocation commands\n");
+ }
+
/* Sanity for ILT */
- if ((RESC_END(p_hwfn, QED_ILT) > PXP_NUM_ILT_RECORDS_BB)) {
+ if ((b_ah && (RESC_END(p_hwfn, QED_ILT) > PXP_NUM_ILT_RECORDS_K2)) ||
+ (!b_ah && (RESC_END(p_hwfn, QED_ILT) > PXP_NUM_ILT_RECORDS_BB))) {
DP_NOTICE(p_hwfn, "Can't assign ILT pages [%08x,...,%08x]\n",
RESC_START(p_hwfn, QED_ILT),
RESC_END(p_hwfn, QED_ILT) - 1);
@@ -1799,8 +2410,6 @@ static int qed_hw_get_resc(struct qed_hwfn *p_hwfn)
qed_hw_set_feat(p_hwfn);
- DP_VERBOSE(p_hwfn, NETIF_MSG_PROBE,
- "The numbers for each resource are:\n");
for (res_id = 0; res_id < QED_MAX_RESC; res_id++)
DP_VERBOSE(p_hwfn, NETIF_MSG_PROBE, "%s = %d start = %d\n",
qed_hw_get_resc_name(res_id),
@@ -1808,6 +2417,11 @@ static int qed_hw_get_resc(struct qed_hwfn *p_hwfn)
RESC_START(p_hwfn, res_id));
return 0;
+
+unlock_and_exit:
+ if (resc_lock_params.b_granted && !resc_unlock_params.b_released)
+ qed_mcp_resc_unlock(p_hwfn, p_ptt, &resc_unlock_params);
+ return rc;
}
static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
@@ -1860,9 +2474,15 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
case NVM_CFG1_GLOB_NETWORK_PORT_MODE_2X25G:
p_hwfn->hw_info.port_mode = QED_PORT_MODE_DE_2X25G;
break;
+ case NVM_CFG1_GLOB_NETWORK_PORT_MODE_2X10G:
+ p_hwfn->hw_info.port_mode = QED_PORT_MODE_DE_2X10G;
+ break;
case NVM_CFG1_GLOB_NETWORK_PORT_MODE_1X25G:
p_hwfn->hw_info.port_mode = QED_PORT_MODE_DE_1X25G;
break;
+ case NVM_CFG1_GLOB_NETWORK_PORT_MODE_4X25G:
+ p_hwfn->hw_info.port_mode = QED_PORT_MODE_DE_4X25G;
+ break;
default:
DP_NOTICE(p_hwfn, "Unknown port mode in 0x%08x\n", core_cfg);
break;
@@ -1976,8 +2596,9 @@ static void qed_get_num_funcs(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
{
u8 num_funcs, enabled_func_idx = p_hwfn->rel_pf_id;
u32 reg_function_hide, tmp, eng_mask, low_pfs_mask;
+ struct qed_dev *cdev = p_hwfn->cdev;
- num_funcs = MAX_NUM_PFS_BB;
+ num_funcs = QED_IS_AH(cdev) ? MAX_NUM_PFS_K2 : MAX_NUM_PFS_BB;
/* Bit 0 of MISCS_REG_FUNCTION_HIDE indicates whether the bypass values
* in the other bits are selected.
@@ -1990,12 +2611,17 @@ static void qed_get_num_funcs(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
reg_function_hide = qed_rd(p_hwfn, p_ptt, MISCS_REG_FUNCTION_HIDE);
if (reg_function_hide & 0x1) {
- if (QED_PATH_ID(p_hwfn) && p_hwfn->cdev->num_hwfns == 1) {
- num_funcs = 0;
- eng_mask = 0xaaaa;
+ if (QED_IS_BB(cdev)) {
+ if (QED_PATH_ID(p_hwfn) && cdev->num_hwfns == 1) {
+ num_funcs = 0;
+ eng_mask = 0xaaaa;
+ } else {
+ num_funcs = 1;
+ eng_mask = 0x5554;
+ }
} else {
num_funcs = 1;
- eng_mask = 0x5554;
+ eng_mask = 0xfffe;
}
/* Get the number of the enabled functions on the engine */
@@ -2027,24 +2653,12 @@ static void qed_get_num_funcs(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
p_hwfn->enabled_func_idx, p_hwfn->num_funcs_on_engine);
}
-static int
-qed_get_hw_info(struct qed_hwfn *p_hwfn,
- struct qed_ptt *p_ptt,
- enum qed_pci_personality personality)
+static void qed_hw_info_port_num_bb(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt)
{
u32 port_mode;
- int rc;
- /* Since all information is common, only first hwfns should do this */
- if (IS_LEAD_HWFN(p_hwfn)) {
- rc = qed_iov_hw_info(p_hwfn);
- if (rc)
- return rc;
- }
-
- /* Read the port mode */
- port_mode = qed_rd(p_hwfn, p_ptt,
- CNIG_REG_NW_PORT_MODE_BB_B0);
+ port_mode = qed_rd(p_hwfn, p_ptt, CNIG_REG_NW_PORT_MODE_BB_B0);
if (port_mode < 3) {
p_hwfn->cdev->num_ports_in_engines = 1;
@@ -2057,6 +2671,54 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn,
/* Default num_ports_in_engines to something */
p_hwfn->cdev->num_ports_in_engines = 1;
}
+}
+
+static void qed_hw_info_port_num_ah(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt)
+{
+ u32 port;
+ int i;
+
+ p_hwfn->cdev->num_ports_in_engines = 0;
+
+ for (i = 0; i < MAX_NUM_PORTS_K2; i++) {
+ port = qed_rd(p_hwfn, p_ptt,
+ CNIG_REG_NIG_PORT0_CONF_K2 + (i * 4));
+ if (port & 1)
+ p_hwfn->cdev->num_ports_in_engines++;
+ }
+
+ if (!p_hwfn->cdev->num_ports_in_engines) {
+ DP_NOTICE(p_hwfn, "All NIG ports are inactive\n");
+
+ /* Default num_ports_in_engine to something */
+ p_hwfn->cdev->num_ports_in_engines = 1;
+ }
+}
+
+static void qed_hw_info_port_num(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+ if (QED_IS_BB(p_hwfn->cdev))
+ qed_hw_info_port_num_bb(p_hwfn, p_ptt);
+ else
+ qed_hw_info_port_num_ah(p_hwfn, p_ptt);
+}
+
+static int
+qed_get_hw_info(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ enum qed_pci_personality personality)
+{
+ int rc;
+
+ /* Since all information is common, only first hwfns should do this */
+ if (IS_LEAD_HWFN(p_hwfn)) {
+ rc = qed_iov_hw_info(p_hwfn);
+ if (rc)
+ return rc;
+ }
+
+ qed_hw_info_port_num(p_hwfn, p_ptt);
qed_hw_get_nvm_info(p_hwfn, p_ptt);
@@ -2085,33 +2747,48 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn,
p_hwfn->hw_info.personality = protocol;
}
+ p_hwfn->hw_info.num_hw_tc = NUM_PHYS_TCS_4PORT_K2;
+ p_hwfn->hw_info.num_active_tc = 1;
+
qed_get_num_funcs(p_hwfn, p_ptt);
if (qed_mcp_is_init(p_hwfn))
p_hwfn->hw_info.mtu = p_hwfn->mcp_info->func_info.mtu;
- return qed_hw_get_resc(p_hwfn);
+ return qed_hw_get_resc(p_hwfn, p_ptt);
}
-static int qed_get_dev_info(struct qed_dev *cdev)
+static int qed_get_dev_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
{
- struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
+ struct qed_dev *cdev = p_hwfn->cdev;
+ u16 device_id_mask;
u32 tmp;
/* Read Vendor Id / Device Id */
pci_read_config_word(cdev->pdev, PCI_VENDOR_ID, &cdev->vendor_id);
pci_read_config_word(cdev->pdev, PCI_DEVICE_ID, &cdev->device_id);
- cdev->chip_num = (u16)qed_rd(p_hwfn, p_hwfn->p_main_ptt,
- MISCS_REG_CHIP_NUM);
- cdev->chip_rev = (u16)qed_rd(p_hwfn, p_hwfn->p_main_ptt,
- MISCS_REG_CHIP_REV);
+ /* Determine type */
+ device_id_mask = cdev->device_id & QED_DEV_ID_MASK;
+ switch (device_id_mask) {
+ case QED_DEV_ID_MASK_BB:
+ cdev->type = QED_DEV_TYPE_BB;
+ break;
+ case QED_DEV_ID_MASK_AH:
+ cdev->type = QED_DEV_TYPE_AH;
+ break;
+ default:
+ DP_NOTICE(p_hwfn, "Unknown device id 0x%x\n", cdev->device_id);
+ return -EBUSY;
+ }
+
+ cdev->chip_num = (u16)qed_rd(p_hwfn, p_ptt, MISCS_REG_CHIP_NUM);
+ cdev->chip_rev = (u16)qed_rd(p_hwfn, p_ptt, MISCS_REG_CHIP_REV);
+
MASK_FIELD(CHIP_REV, cdev->chip_rev);
- cdev->type = QED_DEV_TYPE_BB;
/* Learn number of HW-functions */
- tmp = qed_rd(p_hwfn, p_hwfn->p_main_ptt,
- MISCS_REG_CMT_ENABLED_FOR_PAIR);
+ tmp = qed_rd(p_hwfn, p_ptt, MISCS_REG_CMT_ENABLED_FOR_PAIR);
if (tmp & (1 << p_hwfn->rel_pf_id)) {
DP_NOTICE(cdev->hwfns, "device in CMT mode\n");
@@ -2120,15 +2797,17 @@ static int qed_get_dev_info(struct qed_dev *cdev)
cdev->num_hwfns = 1;
}
- cdev->chip_bond_id = qed_rd(p_hwfn, p_hwfn->p_main_ptt,
+ cdev->chip_bond_id = qed_rd(p_hwfn, p_ptt,
MISCS_REG_CHIP_TEST_REG) >> 4;
MASK_FIELD(CHIP_BOND_ID, cdev->chip_bond_id);
- cdev->chip_metal = (u16)qed_rd(p_hwfn, p_hwfn->p_main_ptt,
- MISCS_REG_CHIP_METAL);
+ cdev->chip_metal = (u16)qed_rd(p_hwfn, p_ptt, MISCS_REG_CHIP_METAL);
MASK_FIELD(CHIP_METAL, cdev->chip_metal);
DP_INFO(cdev->hwfns,
- "Chip details - Num: %04x Rev: %04x Bond id: %04x Metal: %04x\n",
+ "Chip details - %s %c%d, Num: %04x Rev: %04x Bond id: %04x Metal: %04x\n",
+ QED_IS_BB(cdev) ? "BB" : "AH",
+ 'A' + cdev->chip_rev,
+ (int)cdev->chip_metal,
cdev->chip_num, cdev->chip_rev,
cdev->chip_bond_id, cdev->chip_metal);
@@ -2174,7 +2853,7 @@ static int qed_hw_prepare_single(struct qed_hwfn *p_hwfn,
/* First hwfn learns basic information, e.g., number of hwfns */
if (!p_hwfn->my_id) {
- rc = qed_get_dev_info(p_hwfn->cdev);
+ rc = qed_get_dev_info(p_hwfn, p_hwfn->p_main_ptt);
if (rc)
goto err1;
}
@@ -2195,6 +2874,15 @@ static int qed_hw_prepare_single(struct qed_hwfn *p_hwfn,
goto err2;
}
+ /* Sending a mailbox to the MFW should be done after qed_get_hw_info()
+ * is called as it sets the ports number in an engine.
+ */
+ if (IS_LEAD_HWFN(p_hwfn)) {
+ rc = qed_mcp_initiate_pf_flr(p_hwfn, p_hwfn->p_main_ptt);
+ if (rc)
+ DP_NOTICE(p_hwfn, "Failed to initiate PF FLR\n");
+ }
+
/* Allocate the init RT array and initialize the init-ops engine */
rc = qed_init_alloc(p_hwfn);
if (rc)
@@ -2236,11 +2924,14 @@ int qed_hw_prepare(struct qed_dev *cdev,
u8 __iomem *addr;
/* adjust bar offset for second engine */
- addr = cdev->regview + qed_hw_bar_size(p_hwfn, BAR_ID_0) / 2;
+ addr = cdev->regview +
+ qed_hw_bar_size(p_hwfn, p_hwfn->p_main_ptt,
+ BAR_ID_0) / 2;
p_regview = addr;
- /* adjust doorbell bar offset for second engine */
- addr = cdev->doorbells + qed_hw_bar_size(p_hwfn, BAR_ID_1) / 2;
+ addr = cdev->doorbells +
+ qed_hw_bar_size(p_hwfn, p_hwfn->p_main_ptt,
+ BAR_ID_1) / 2;
p_doorbell = addr;
/* prepare second hw function */
@@ -2389,9 +3080,8 @@ qed_chain_alloc_sanity_check(struct qed_dev *cdev,
* size/capacity fields are of a u32 type.
*/
if ((cnt_type == QED_CHAIN_CNT_TYPE_U16 &&
- chain_size > 0x10000) ||
- (cnt_type == QED_CHAIN_CNT_TYPE_U32 &&
- chain_size > 0x100000000ULL)) {
+ chain_size > ((u32)U16_MAX + 1)) ||
+ (cnt_type == QED_CHAIN_CNT_TYPE_U32 && chain_size > U32_MAX)) {
DP_NOTICE(cdev,
"The actual chain size (0x%llx) is larger than the maximal possible value\n",
chain_size);
@@ -3364,3 +4054,8 @@ void qed_clean_wfq_db(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
memset(p_hwfn->qm_info.wfq_data, 0,
sizeof(*p_hwfn->qm_info.wfq_data) * p_hwfn->qm_info.num_vports);
}
+
+int qed_device_num_engines(struct qed_dev *cdev)
+{
+ return QED_IS_BB(cdev) ? 2 : 1;
+}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
index 6812003..341636d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
@@ -82,26 +82,63 @@ int qed_resc_alloc(struct qed_dev *cdev);
*/
void qed_resc_setup(struct qed_dev *cdev);
+enum qed_override_force_load {
+ QED_OVERRIDE_FORCE_LOAD_NONE,
+ QED_OVERRIDE_FORCE_LOAD_ALWAYS,
+ QED_OVERRIDE_FORCE_LOAD_NEVER,
+};
+
+struct qed_drv_load_params {
+ /* Indicates whether the driver is running over a crash kernel.
+ * As part of the load request, this will be used for providing the
+ * driver role to the MFW.
+ * In case of a crash kernel over PDA - this should be set to false.
+ */
+ bool is_crash_kernel;
+
+ /* The timeout value that the MFW should use when locking the engine for
+ * the driver load process.
+ * A value of '0' means the default value, and '255' means no timeout.
+ */
+ u8 mfw_timeout_val;
+#define QED_LOAD_REQ_LOCK_TO_DEFAULT 0
+#define QED_LOAD_REQ_LOCK_TO_NONE 255
+
+ /* Avoid engine reset when first PF loads on it */
+ bool avoid_eng_reset;
+
+ /* Allow overriding the default force load behavior */
+ enum qed_override_force_load override_force_load;
+};
+
+struct qed_hw_init_params {
+ /* Tunneling parameters */
+ struct qed_tunn_start_params *p_tunn;
+
+ bool b_hw_start;
+
+ /* Interrupt mode [msix, inta, etc.] to use */
+ enum qed_int_mode int_mode;
+
+ /* NPAR tx switching to be used for vports for tx-switching */
+ bool allow_npar_tx_switch;
+
+ /* Binary fw data pointer in binary fw file */
+ const u8 *bin_fw_data;
+
+ /* Driver load parameters */
+ struct qed_drv_load_params *p_drv_load_params;
+};
+
/**
* @brief qed_hw_init -
*
* @param cdev
- * @param p_tunn
- * @param b_hw_start
- * @param int_mode - interrupt mode [msix, inta, etc.] to use.
- * @param allow_npar_tx_switch - npar tx switching to be used
- * for vports configured for tx-switching.
- * @param bin_fw_data - binary fw data pointer in binary fw file.
- * Pass NULL if not using binary fw file.
+ * @param p_params
*
* @return int
*/
-int qed_hw_init(struct qed_dev *cdev,
- struct qed_tunn_start_params *p_tunn,
- bool b_hw_start,
- enum qed_int_mode int_mode,
- bool allow_npar_tx_switch,
- const u8 *bin_fw_data);
+int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params);
/**
* @brief qed_hw_timers_stop_all - stop the timers HW block
@@ -128,26 +165,20 @@ int qed_hw_stop(struct qed_dev *cdev);
*
* @param cdev
*
+ * @return int
*/
-void qed_hw_stop_fastpath(struct qed_dev *cdev);
+int qed_hw_stop_fastpath(struct qed_dev *cdev);
/**
* @brief qed_hw_start_fastpath -restart fastpath traffic,
* only if hw_stop_fastpath was called
*
- * @param cdev
- *
- */
-void qed_hw_start_fastpath(struct qed_hwfn *p_hwfn);
-
-/**
- * @brief qed_hw_reset -
- *
- * @param cdev
+ * @param p_hwfn
*
* @return int
*/
-int qed_hw_reset(struct qed_dev *cdev);
+int qed_hw_start_fastpath(struct qed_hwfn *p_hwfn);
+
/**
* @brief qed_hw_prepare -
@@ -441,4 +472,6 @@ int qed_set_rxq_coalesce(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
*/
int qed_set_txq_coalesce(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
u16 coalesce, u8 qid, u16 sb_id);
+
+const char *qed_hw_get_resc_name(enum qed_resources res_id);
#endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c
index cbc8141..21a58ff 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c
@@ -191,7 +191,7 @@ qed_sp_fcoe_func_start(struct qed_hwfn *p_hwfn,
p_data->q_params.cq_sb_pi = fcoe_pf_params->gl_rq_pi;
p_data->q_params.cmdq_sb_pi = fcoe_pf_params->gl_cmd_pi;
- p_data->q_params.bdq_resource_id = FCOE_BDQ_ID(p_hwfn->port_id);
+ p_data->q_params.bdq_resource_id = (u8)RESC_START(p_hwfn, QED_BDQ);
DMA_REGPAIR_LE(p_data->q_params.bdq_pbl_base_address[BDQ_ID_RQ],
fcoe_pf_params->bdq_pbl_base_addr[BDQ_ID_RQ]);
@@ -241,7 +241,7 @@ qed_sp_fcoe_conn_offload(struct qed_hwfn *p_hwfn,
struct fcoe_conn_offload_ramrod_data *p_data;
struct qed_spq_entry *p_ent = NULL;
struct qed_sp_init_data init_data;
- u16 pq_id = 0, tmp;
+ u16 physical_q0, tmp;
int rc;
/* Get SPQ entry */
@@ -261,9 +261,9 @@ qed_sp_fcoe_conn_offload(struct qed_hwfn *p_hwfn,
p_data = &p_ramrod->offload_ramrod_data;
/* Transmission PQ is the first of the PF */
- pq_id = qed_get_qm_pq(p_hwfn, PROTOCOLID_FCOE, NULL);
- p_conn->physical_q0 = cpu_to_le16(pq_id);
- p_data->physical_q0 = cpu_to_le16(pq_id);
+ physical_q0 = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
+ p_conn->physical_q0 = cpu_to_le16(physical_q0);
+ p_data->physical_q0 = cpu_to_le16(physical_q0);
p_data->conn_id = cpu_to_le16(p_conn->conn_id);
DMA_REGPAIR_LE(p_data->sq_pbl_addr, p_conn->sq_pbl_addr);
@@ -340,10 +340,10 @@ qed_sp_fcoe_conn_destroy(struct qed_hwfn *p_hwfn,
static int
qed_sp_fcoe_func_stop(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
enum spq_mode comp_mode,
struct qed_spq_comp_cb *p_comp_addr)
{
- struct qed_ptt *p_ptt = p_hwfn->p_main_ptt;
struct qed_spq_entry *p_ent = NULL;
struct qed_sp_init_data init_data;
u32 active_segs = 0;
@@ -512,19 +512,31 @@ static void __iomem *qed_fcoe_get_db_addr(struct qed_hwfn *p_hwfn, u32 cid)
static void __iomem *qed_fcoe_get_primary_bdq_prod(struct qed_hwfn *p_hwfn,
u8 bdq_id)
{
- u8 bdq_function_id = FCOE_BDQ_ID(p_hwfn->port_id);
-
- return (u8 __iomem *)p_hwfn->regview + GTT_BAR0_MAP_REG_MSDM_RAM +
- MSTORM_SCSI_BDQ_EXT_PROD_OFFSET(bdq_function_id, bdq_id);
+ if (RESC_NUM(p_hwfn, QED_BDQ)) {
+ return (u8 __iomem *)p_hwfn->regview +
+ GTT_BAR0_MAP_REG_MSDM_RAM +
+ MSTORM_SCSI_BDQ_EXT_PROD_OFFSET(RESC_START(p_hwfn,
+ QED_BDQ),
+ bdq_id);
+ } else {
+ DP_NOTICE(p_hwfn, "BDQ is not allocated!\n");
+ return NULL;
+ }
}
static void __iomem *qed_fcoe_get_secondary_bdq_prod(struct qed_hwfn *p_hwfn,
u8 bdq_id)
{
- u8 bdq_function_id = FCOE_BDQ_ID(p_hwfn->port_id);
-
- return (u8 __iomem *)p_hwfn->regview + GTT_BAR0_MAP_REG_TSDM_RAM +
- TSTORM_SCSI_BDQ_EXT_PROD_OFFSET(bdq_function_id, bdq_id);
+ if (RESC_NUM(p_hwfn, QED_BDQ)) {
+ return (u8 __iomem *)p_hwfn->regview +
+ GTT_BAR0_MAP_REG_TSDM_RAM +
+ TSTORM_SCSI_BDQ_EXT_PROD_OFFSET(RESC_START(p_hwfn,
+ QED_BDQ),
+ bdq_id);
+ } else {
+ DP_NOTICE(p_hwfn, "BDQ is not allocated!\n");
+ return NULL;
+ }
}
struct qed_fcoe_info *qed_fcoe_alloc(struct qed_hwfn *p_hwfn)
@@ -753,6 +765,7 @@ static struct qed_hash_fcoe_con *qed_fcoe_get_hash(struct qed_dev *cdev,
static int qed_fcoe_stop(struct qed_dev *cdev)
{
+ struct qed_ptt *p_ptt;
int rc;
if (!(cdev->flags & QED_FLAG_STORAGE_STARTED)) {
@@ -766,10 +779,15 @@ static int qed_fcoe_stop(struct qed_dev *cdev)
return -EINVAL;
}
+ p_ptt = qed_ptt_acquire(QED_LEADING_HWFN(cdev));
+ if (!p_ptt)
+ return -EAGAIN;
+
/* Stop the fcoe */
- rc = qed_sp_fcoe_func_stop(QED_LEADING_HWFN(cdev),
+ rc = qed_sp_fcoe_func_stop(QED_LEADING_HWFN(cdev), p_ptt,
QED_SPQ_MODE_EBLOCK, NULL);
cdev->flags &= ~QED_FLAG_STORAGE_STARTED;
+ qed_ptt_release(QED_LEADING_HWFN(cdev), p_ptt);
return rc;
}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index 37c2bfb..815c4ec 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -574,6 +574,7 @@ enum core_event_opcode {
CORE_EVENT_TX_QUEUE_STOP,
CORE_EVENT_RX_QUEUE_START,
CORE_EVENT_RX_QUEUE_STOP,
+ CORE_EVENT_RX_QUEUE_FLUSH,
MAX_CORE_EVENT_OPCODE
};
@@ -625,6 +626,7 @@ enum core_ramrod_cmd_id {
CORE_RAMROD_TX_QUEUE_START,
CORE_RAMROD_RX_QUEUE_STOP,
CORE_RAMROD_TX_QUEUE_STOP,
+ CORE_RAMROD_RX_QUEUE_FLUSH,
MAX_CORE_RAMROD_CMD_ID
};
@@ -698,7 +700,8 @@ struct core_rx_slow_path_cqe {
u8 type;
u8 ramrod_cmd_id;
__le16 echo;
- __le32 reserved1[7];
+ struct core_rx_cqe_opaque_data opaque_data;
+ __le32 reserved1[5];
};
union core_rx_cqe_union {
@@ -735,45 +738,46 @@ struct core_rx_stop_ramrod_data {
__le16 reserved2[2];
};
-struct core_tx_bd_flags {
- u8 as_bitfield;
-#define CORE_TX_BD_FLAGS_FORCE_VLAN_MODE_MASK 0x1
-#define CORE_TX_BD_FLAGS_FORCE_VLAN_MODE_SHIFT 0
-#define CORE_TX_BD_FLAGS_VLAN_INSERTION_MASK 0x1
-#define CORE_TX_BD_FLAGS_VLAN_INSERTION_SHIFT 1
-#define CORE_TX_BD_FLAGS_START_BD_MASK 0x1
-#define CORE_TX_BD_FLAGS_START_BD_SHIFT 2
-#define CORE_TX_BD_FLAGS_IP_CSUM_MASK 0x1
-#define CORE_TX_BD_FLAGS_IP_CSUM_SHIFT 3
-#define CORE_TX_BD_FLAGS_L4_CSUM_MASK 0x1
-#define CORE_TX_BD_FLAGS_L4_CSUM_SHIFT 4
-#define CORE_TX_BD_FLAGS_IPV6_EXT_MASK 0x1
-#define CORE_TX_BD_FLAGS_IPV6_EXT_SHIFT 5
-#define CORE_TX_BD_FLAGS_L4_PROTOCOL_MASK 0x1
-#define CORE_TX_BD_FLAGS_L4_PROTOCOL_SHIFT 6
-#define CORE_TX_BD_FLAGS_L4_PSEUDO_CSUM_MODE_MASK 0x1
-#define CORE_TX_BD_FLAGS_L4_PSEUDO_CSUM_MODE_SHIFT 7
+struct core_tx_bd_data {
+ __le16 as_bitfield;
+#define CORE_TX_BD_DATA_FORCE_VLAN_MODE_MASK 0x1
+#define CORE_TX_BD_DATA_FORCE_VLAN_MODE_SHIFT 0
+#define CORE_TX_BD_DATA_VLAN_INSERTION_MASK 0x1
+#define CORE_TX_BD_DATA_VLAN_INSERTION_SHIFT 1
+#define CORE_TX_BD_DATA_START_BD_MASK 0x1
+#define CORE_TX_BD_DATA_START_BD_SHIFT 2
+#define CORE_TX_BD_DATA_IP_CSUM_MASK 0x1
+#define CORE_TX_BD_DATA_IP_CSUM_SHIFT 3
+#define CORE_TX_BD_DATA_L4_CSUM_MASK 0x1
+#define CORE_TX_BD_DATA_L4_CSUM_SHIFT 4
+#define CORE_TX_BD_DATA_IPV6_EXT_MASK 0x1
+#define CORE_TX_BD_DATA_IPV6_EXT_SHIFT 5
+#define CORE_TX_BD_DATA_L4_PROTOCOL_MASK 0x1
+#define CORE_TX_BD_DATA_L4_PROTOCOL_SHIFT 6
+#define CORE_TX_BD_DATA_L4_PSEUDO_CSUM_MODE_MASK 0x1
+#define CORE_TX_BD_DATA_L4_PSEUDO_CSUM_MODE_SHIFT 7
+#define CORE_TX_BD_DATA_NBDS_MASK 0xF
+#define CORE_TX_BD_DATA_NBDS_SHIFT 8
+#define CORE_TX_BD_DATA_ROCE_FLAV_MASK 0x1
+#define CORE_TX_BD_DATA_ROCE_FLAV_SHIFT 12
+#define CORE_TX_BD_DATA_IP_LEN_MASK 0x1
+#define CORE_TX_BD_DATA_IP_LEN_SHIFT 13
+#define CORE_TX_BD_DATA_RESERVED0_MASK 0x3
+#define CORE_TX_BD_DATA_RESERVED0_SHIFT 14
};
struct core_tx_bd {
struct regpair addr;
__le16 nbytes;
__le16 nw_vlan_or_lb_echo;
- u8 bitfield0;
-#define CORE_TX_BD_NBDS_MASK 0xF
-#define CORE_TX_BD_NBDS_SHIFT 0
-#define CORE_TX_BD_ROCE_FLAV_MASK 0x1
-#define CORE_TX_BD_ROCE_FLAV_SHIFT 4
-#define CORE_TX_BD_RESERVED0_MASK 0x7
-#define CORE_TX_BD_RESERVED0_SHIFT 5
- struct core_tx_bd_flags bd_flags;
+ struct core_tx_bd_data bd_data;
__le16 bitfield1;
#define CORE_TX_BD_L4_HDR_OFFSET_W_MASK 0x3FFF
#define CORE_TX_BD_L4_HDR_OFFSET_W_SHIFT 0
#define CORE_TX_BD_TX_DST_MASK 0x1
#define CORE_TX_BD_TX_DST_SHIFT 14
-#define CORE_TX_BD_RESERVED1_MASK 0x1
-#define CORE_TX_BD_RESERVED1_SHIFT 15
+#define CORE_TX_BD_RESERVED_MASK 0x1
+#define CORE_TX_BD_RESERVED_SHIFT 15
};
enum core_tx_dest {
@@ -800,6 +804,14 @@ struct core_tx_stop_ramrod_data {
__le32 reserved0[2];
};
+enum dcb_dhcp_update_flag {
+ DONT_UPDATE_DCB_DHCP,
+ UPDATE_DCB,
+ UPDATE_DSCP,
+ UPDATE_DCB_DSCP,
+ MAX_DCB_DHCP_UPDATE_FLAG
+};
+
struct eth_mstorm_per_pf_stat {
struct regpair gre_discard_pkts;
struct regpair vxlan_discard_pkts;
@@ -893,6 +905,12 @@ union event_ring_element {
struct event_ring_next_addr next_addr;
};
+enum fw_flow_ctrl_mode {
+ flow_ctrl_pause,
+ flow_ctrl_pfc,
+ MAX_FW_FLOW_CTRL_MODE
+};
+
/* Major and Minor hsi Versions */
struct hsi_fp_ver_struct {
u8 minor_ver_arr[2];
@@ -921,6 +939,7 @@ enum malicious_vf_error_id {
ETH_EDPM_OUT_OF_SYNC,
ETH_TUNN_IPV6_EXT_NBD_ERR,
ETH_CONTROL_PACKET_VIOLATION,
+ ETH_ANTI_SPOOFING_ERR,
MAX_MALICIOUS_VF_ERROR_ID
};
@@ -1106,8 +1125,9 @@ struct tstorm_per_port_stat {
struct regpair ll2_mac_filter_discard;
struct regpair ll2_conn_disabled_discard;
struct regpair iscsi_irregular_pkt;
- struct regpair reserved;
+ struct regpair fcoe_irregular_pkt;
struct regpair roce_irregular_pkt;
+ struct regpair reserved;
struct regpair eth_irregular_pkt;
struct regpair reserved1;
struct regpair preroce_irregular_pkt;
@@ -1648,6 +1668,11 @@ enum block_addr {
GRCBASE_MS = 0x6a0000,
GRCBASE_PHY_PCIE = 0x620000,
GRCBASE_LED = 0x6b8000,
+ GRCBASE_AVS_WRAP = 0x6b0000,
+ GRCBASE_RGFS = 0x19d0000,
+ GRCBASE_TGFS = 0x19e0000,
+ GRCBASE_PTLD = 0x19f0000,
+ GRCBASE_YPLD = 0x1a10000,
GRCBASE_MISC_AEU = 0x8000,
GRCBASE_BAR0_MAP = 0x1c00000,
MAX_BLOCK_ADDR
@@ -1732,6 +1757,11 @@ enum block_id {
BLOCK_MS,
BLOCK_PHY_PCIE,
BLOCK_LED,
+ BLOCK_AVS_WRAP,
+ BLOCK_RGFS,
+ BLOCK_TGFS,
+ BLOCK_PTLD,
+ BLOCK_YPLD,
BLOCK_MISC_AEU,
BLOCK_BAR0_MAP,
MAX_BLOCK_ID
@@ -1783,9 +1813,9 @@ struct dbg_attn_reg_result {
__le32 data;
#define DBG_ATTN_REG_RESULT_STS_ADDRESS_MASK 0xFFFFFF
#define DBG_ATTN_REG_RESULT_STS_ADDRESS_SHIFT 0
-#define DBG_ATTN_REG_RESULT_NUM_ATTN_IDX_MASK 0xFF
-#define DBG_ATTN_REG_RESULT_NUM_ATTN_IDX_SHIFT 24
- __le16 attn_idx_offset;
+#define DBG_ATTN_REG_RESULT_NUM_REG_ATTN_MASK 0xFF
+#define DBG_ATTN_REG_RESULT_NUM_REG_ATTN_SHIFT 24
+ __le16 block_attn_offset;
__le16 reserved;
__le32 sts_val;
__le32 mask_val;
@@ -1815,12 +1845,12 @@ struct dbg_mode_hdr {
/* Attention register */
struct dbg_attn_reg {
struct dbg_mode_hdr mode;
- __le16 attn_idx_offset;
+ __le16 block_attn_offset;
__le32 data;
#define DBG_ATTN_REG_STS_ADDRESS_MASK 0xFFFFFF
#define DBG_ATTN_REG_STS_ADDRESS_SHIFT 0
-#define DBG_ATTN_REG_NUM_ATTN_IDX_MASK 0xFF
-#define DBG_ATTN_REG_NUM_ATTN_IDX_SHIFT 24
+#define DBG_ATTN_REG_NUM_REG_ATTN_MASK 0xFF
+#define DBG_ATTN_REG_NUM_REG_ATTN_SHIFT 24
__le32 sts_clr_address;
__le32 mask_address;
};
@@ -2001,6 +2031,20 @@ enum dbg_bus_clients {
MAX_DBG_BUS_CLIENTS
};
+enum dbg_bus_constraint_ops {
+ DBG_BUS_CONSTRAINT_OP_EQ,
+ DBG_BUS_CONSTRAINT_OP_NE,
+ DBG_BUS_CONSTRAINT_OP_LT,
+ DBG_BUS_CONSTRAINT_OP_LTC,
+ DBG_BUS_CONSTRAINT_OP_LE,
+ DBG_BUS_CONSTRAINT_OP_LEC,
+ DBG_BUS_CONSTRAINT_OP_GT,
+ DBG_BUS_CONSTRAINT_OP_GTC,
+ DBG_BUS_CONSTRAINT_OP_GE,
+ DBG_BUS_CONSTRAINT_OP_GEC,
+ MAX_DBG_BUS_CONSTRAINT_OPS
+};
+
/* Debug Bus memory address */
struct dbg_bus_mem_addr {
__le32 lo;
@@ -2092,10 +2136,18 @@ struct dbg_bus_data {
* DBG_BUS_TARGET_ID_PCI.
*/
__le16 reserved;
- struct dbg_bus_block_data blocks[80];/* Debug Bus data for each block */
+ struct dbg_bus_block_data blocks[88];/* Debug Bus data for each block */
struct dbg_bus_storm_data storms[6]; /* Debug Bus data for each block */
};
+enum dbg_bus_filter_types {
+ DBG_BUS_FILTER_TYPE_OFF,
+ DBG_BUS_FILTER_TYPE_PRE,
+ DBG_BUS_FILTER_TYPE_POST,
+ DBG_BUS_FILTER_TYPE_ON,
+ MAX_DBG_BUS_FILTER_TYPES
+};
+
/* Debug bus frame modes */
enum dbg_bus_frame_modes {
DBG_BUS_FRAME_MODE_0HW_4ST = 0, /* 0 HW dwords, 4 Storm dwords */
@@ -2104,6 +2156,40 @@ enum dbg_bus_frame_modes {
MAX_DBG_BUS_FRAME_MODES
};
+enum dbg_bus_input_types {
+ DBG_BUS_INPUT_TYPE_STORM,
+ DBG_BUS_INPUT_TYPE_BLOCK,
+ MAX_DBG_BUS_INPUT_TYPES
+};
+
+enum dbg_bus_other_engine_modes {
+ DBG_BUS_OTHER_ENGINE_MODE_NONE,
+ DBG_BUS_OTHER_ENGINE_MODE_DOUBLE_BW_TX,
+ DBG_BUS_OTHER_ENGINE_MODE_DOUBLE_BW_RX,
+ DBG_BUS_OTHER_ENGINE_MODE_CROSS_ENGINE_TX,
+ DBG_BUS_OTHER_ENGINE_MODE_CROSS_ENGINE_RX,
+ MAX_DBG_BUS_OTHER_ENGINE_MODES
+};
+
+enum dbg_bus_post_trigger_types {
+ DBG_BUS_POST_TRIGGER_RECORD,
+ DBG_BUS_POST_TRIGGER_DROP,
+ MAX_DBG_BUS_POST_TRIGGER_TYPES
+};
+
+enum dbg_bus_pre_trigger_types {
+ DBG_BUS_PRE_TRIGGER_START_FROM_ZERO,
+ DBG_BUS_PRE_TRIGGER_NUM_CHUNKS,
+ DBG_BUS_PRE_TRIGGER_DROP,
+ MAX_DBG_BUS_PRE_TRIGGER_TYPES
+};
+
+enum dbg_bus_semi_frame_modes {
+ DBG_BUS_SEMI_FRAME_MODE_0SLOW_4FAST = 0,
+ DBG_BUS_SEMI_FRAME_MODE_4SLOW_0FAST = 3,
+ MAX_DBG_BUS_SEMI_FRAME_MODES
+};
+
/* Debug bus states */
enum dbg_bus_states {
DBG_BUS_STATE_IDLE, /* debug bus idle state (not recording) */
@@ -2115,6 +2201,19 @@ enum dbg_bus_states {
MAX_DBG_BUS_STATES
};
+enum dbg_bus_storm_modes {
+ DBG_BUS_STORM_MODE_PRINTF,
+ DBG_BUS_STORM_MODE_PRAM_ADDR,
+ DBG_BUS_STORM_MODE_DRA_RW,
+ DBG_BUS_STORM_MODE_DRA_W,
+ DBG_BUS_STORM_MODE_LD_ST_ADDR,
+ DBG_BUS_STORM_MODE_DRA_FSM,
+ DBG_BUS_STORM_MODE_RH,
+ DBG_BUS_STORM_MODE_FOC,
+ DBG_BUS_STORM_MODE_EXT_STORE,
+ MAX_DBG_BUS_STORM_MODES
+};
+
/* Debug bus target IDs */
enum dbg_bus_targets {
/* records debug bus to DBG block internal buffer */
@@ -2128,13 +2227,10 @@ enum dbg_bus_targets {
/* GRC Dump data */
struct dbg_grc_data {
- __le32 param_val[40]; /* Value of each GRC parameter. Array size must
- * match the enum dbg_grc_params.
- */
- u8 param_set_by_user[40]; /* Indicates for each GRC parameter if it was
- * set by the user (0/1). Array size must
- * match the enum dbg_grc_params.
- */
+ u8 params_initialized;
+ u8 reserved1;
+ __le16 reserved2;
+ __le32 param_val[48];
};
/* Debug GRC params */
@@ -2181,6 +2277,8 @@ enum dbg_grc_params {
DBG_GRC_PARAM_PARITY_SAFE,
DBG_GRC_PARAM_DUMP_CM, /* dump CM memories (0/1) */
DBG_GRC_PARAM_DUMP_PHY, /* dump PHY memories (0/1) */
+ DBG_GRC_PARAM_NO_MCP,
+ DBG_GRC_PARAM_NO_FW_VER,
MAX_DBG_GRC_PARAMS
};
@@ -2280,7 +2378,7 @@ struct dbg_tools_data {
struct dbg_bus_data bus; /* Debug Bus data */
struct idle_chk_data idle_chk; /* Idle Check data */
u8 mode_enable[40]; /* Indicates if a mode is enabled (0/1) */
- u8 block_in_reset[80]; /* Indicates if a block is in reset state (0/1).
+ u8 block_in_reset[88]; /* Indicates if a block is in reset state (0/1).
*/
u8 chip_id; /* Chip ID (from enum chip_ids) */
u8 platform_id; /* Platform ID (from enum platform_ids) */
@@ -2404,7 +2502,7 @@ struct fw_info_location {
enum init_modes {
MODE_RESERVED,
- MODE_BB_B0,
+ MODE_BB,
MODE_K2,
MODE_ASIC,
MODE_RESERVED2,
@@ -2418,7 +2516,6 @@ enum init_modes {
MODE_PORTS_PER_ENG_2,
MODE_PORTS_PER_ENG_4,
MODE_100G,
- MODE_40G,
MODE_RESERVED6,
MAX_INIT_MODES
};
@@ -2686,6 +2783,13 @@ struct iro {
*/
enum dbg_status qed_dbg_set_bin_ptr(const u8 * const bin_ptr);
/**
+ * @brief qed_dbg_grc_set_params_default - Reverts all GRC parameters to their
+ * default value.
+ *
+ * @param p_hwfn - HW device data
+ */
+void qed_dbg_grc_set_params_default(struct qed_hwfn *p_hwfn);
+/**
* @brief qed_dbg_grc_get_dump_buf_size - Returns the required buffer size for
* GRC Dump.
*
@@ -3418,7 +3522,7 @@ void qed_set_geneve_enable(struct qed_hwfn *p_hwfn,
#define MSTORM_TPA_TIMEOUT_US_SIZE (IRO[21].size)
#define MSTORM_ETH_PF_STAT_OFFSET(pf_id) \
(IRO[22].base + ((pf_id) * IRO[22].m1))
-#define MSTORM_ETH_PF_STAT_SIZE (IRO[21].size)
+#define MSTORM_ETH_PF_STAT_SIZE (IRO[22].size)
#define USTORM_QUEUE_STAT_OFFSET(stat_counter_id) \
(IRO[23].base + ((stat_counter_id) * IRO[23].m1))
#define USTORM_QUEUE_STAT_SIZE (IRO[23].size)
@@ -3482,7 +3586,7 @@ void qed_set_geneve_enable(struct qed_hwfn *p_hwfn,
static const struct iro iro_arr[47] = {
{0x0, 0x0, 0x0, 0x0, 0x8},
- {0x4cb0, 0x78, 0x0, 0x0, 0x78},
+ {0x4cb0, 0x80, 0x0, 0x0, 0x80},
{0x6318, 0x20, 0x0, 0x0, 0x20},
{0xb00, 0x8, 0x0, 0x0, 0x4},
{0xa80, 0x8, 0x0, 0x0, 0x4},
@@ -3521,13 +3625,13 @@ static const struct iro iro_arr[47] = {
{0xd888, 0x38, 0x0, 0x0, 0x24},
{0x12c38, 0x10, 0x0, 0x0, 0x8},
{0x11aa0, 0x38, 0x0, 0x0, 0x18},
- {0xa8c0, 0x30, 0x0, 0x0, 0x10},
- {0x86f8, 0x28, 0x0, 0x0, 0x18},
+ {0xa8c0, 0x38, 0x0, 0x0, 0x10},
+ {0x86f8, 0x30, 0x0, 0x0, 0x18},
{0x101f8, 0x10, 0x0, 0x0, 0x10},
{0xdd08, 0x48, 0x0, 0x0, 0x38},
{0x10660, 0x20, 0x0, 0x0, 0x20},
{0x2b80, 0x80, 0x0, 0x0, 0x10},
- {0x5000, 0x10, 0x0, 0x0, 0x10},
+ {0x5020, 0x10, 0x0, 0x0, 0x10},
};
/* Runtime array offsets */
@@ -4595,6 +4699,12 @@ enum eth_ipv4_frag_type {
MAX_ETH_IPV4_FRAG_TYPE
};
+enum eth_ip_type {
+ ETH_IPV4,
+ ETH_IPV6,
+ MAX_ETH_IP_TYPE
+};
+
enum eth_ramrod_cmd_id {
ETH_RAMROD_UNUSED,
ETH_RAMROD_VPORT_START,
@@ -4944,7 +5054,10 @@ struct vport_update_ramrod_data_cmn {
u8 update_mtu_flg;
__le16 mtu;
- u8 reserved[2];
+ u8 update_ctl_frame_checks_en_flg;
+ u8 ctl_frame_mac_check_en;
+ u8 ctl_frame_ethtype_check_en;
+ u8 reserved[15];
};
struct vport_update_ramrod_mcast {
@@ -4962,6 +5075,492 @@ struct vport_update_ramrod_data {
struct eth_vport_rss_config rss_config;
};
+struct mstorm_eth_conn_ag_ctx {
+ u8 byte0;
+ u8 byte1;
+ u8 flags0;
+#define MSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1
+#define MSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0
+#define MSTORM_ETH_CONN_AG_CTX_BIT1_MASK 0x1
+#define MSTORM_ETH_CONN_AG_CTX_BIT1_SHIFT 1
+#define MSTORM_ETH_CONN_AG_CTX_CF0_MASK 0x3
+#define MSTORM_ETH_CONN_AG_CTX_CF0_SHIFT 2
+#define MSTORM_ETH_CONN_AG_CTX_CF1_MASK 0x3
+#define MSTORM_ETH_CONN_AG_CTX_CF1_SHIFT 4
+#define MSTORM_ETH_CONN_AG_CTX_CF2_MASK 0x3
+#define MSTORM_ETH_CONN_AG_CTX_CF2_SHIFT 6
+ u8 flags1;
+#define MSTORM_ETH_CONN_AG_CTX_CF0EN_MASK 0x1
+#define MSTORM_ETH_CONN_AG_CTX_CF0EN_SHIFT 0
+#define MSTORM_ETH_CONN_AG_CTX_CF1EN_MASK 0x1
+#define MSTORM_ETH_CONN_AG_CTX_CF1EN_SHIFT 1
+#define MSTORM_ETH_CONN_AG_CTX_CF2EN_MASK 0x1
+#define MSTORM_ETH_CONN_AG_CTX_CF2EN_SHIFT 2
+#define MSTORM_ETH_CONN_AG_CTX_RULE0EN_MASK 0x1
+#define MSTORM_ETH_CONN_AG_CTX_RULE0EN_SHIFT 3
+#define MSTORM_ETH_CONN_AG_CTX_RULE1EN_MASK 0x1
+#define MSTORM_ETH_CONN_AG_CTX_RULE1EN_SHIFT 4
+#define MSTORM_ETH_CONN_AG_CTX_RULE2EN_MASK 0x1
+#define MSTORM_ETH_CONN_AG_CTX_RULE2EN_SHIFT 5
+#define MSTORM_ETH_CONN_AG_CTX_RULE3EN_MASK 0x1
+#define MSTORM_ETH_CONN_AG_CTX_RULE3EN_SHIFT 6
+#define MSTORM_ETH_CONN_AG_CTX_RULE4EN_MASK 0x1
+#define MSTORM_ETH_CONN_AG_CTX_RULE4EN_SHIFT 7
+ __le16 word0;
+ __le16 word1;
+ __le32 reg0;
+ __le32 reg1;
+};
+
+struct xstorm_eth_conn_agctxdq_ext_ldpart {
+ u8 reserved0;
+ u8 eth_state;
+ u8 flags0;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EXIST_IN_QM0_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EXIST_IN_QM0_SHIFT 0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED1_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED1_SHIFT 1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED2_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED2_SHIFT 2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EXIST_IN_QM3_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EXIST_IN_QM3_SHIFT 3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED3_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED3_SHIFT 4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED4_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED4_SHIFT 5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED5_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED5_SHIFT 6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED6_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED6_SHIFT 7
+ u8 flags1;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED7_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED7_SHIFT 0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED8_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED8_SHIFT 1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED9_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED9_SHIFT 2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT11_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT11_SHIFT 3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT12_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT12_SHIFT 4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT13_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_BIT13_SHIFT 5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TX_RULE_ACTIVE_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TX_RULE_ACTIVE_SHIFT 6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_ACTIVE_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_ACTIVE_SHIFT 7
+ u8 flags2;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF0_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF0_SHIFT 0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF1_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF1_SHIFT 2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF2_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF2_SHIFT 4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF3_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF3_SHIFT 6
+ u8 flags3;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF4_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF4_SHIFT 0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF5_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF5_SHIFT 2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF6_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF6_SHIFT 4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF7_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF7_SHIFT 6
+ u8 flags4;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF8_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF8_SHIFT 0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF9_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF9_SHIFT 2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF10_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF10_SHIFT 4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF11_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF11_SHIFT 6
+ u8 flags5;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF12_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF12_SHIFT 0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF13_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF13_SHIFT 2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF14_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF14_SHIFT 4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF15_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF15_SHIFT 6
+ u8 flags6;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_GO_TO_BD_CONS_CF_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_GO_TO_BD_CONS_CF_SHIFT 0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_MULTI_UNICAST_CF_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_MULTI_UNICAST_CF_SHIFT 2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_SHIFT 4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TERMINATE_CF_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TERMINATE_CF_SHIFT 6
+ u8 flags7;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_FLUSH_Q0_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_FLUSH_Q0_SHIFT 0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED10_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED10_SHIFT 2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_SLOW_PATH_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_SLOW_PATH_SHIFT 4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF0EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF0EN_SHIFT 6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF1EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF1EN_SHIFT 7
+ u8 flags8;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF2EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF2EN_SHIFT 0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF3EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF3EN_SHIFT 1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF4EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF4EN_SHIFT 2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF5EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF5EN_SHIFT 3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF6EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF6EN_SHIFT 4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF7EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF7EN_SHIFT 5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF8EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF8EN_SHIFT 6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF9EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF9EN_SHIFT 7
+ u8 flags9;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF10EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF10EN_SHIFT 0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF11EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF11EN_SHIFT 1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF12EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF12EN_SHIFT 2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF13EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF13EN_SHIFT 3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF14EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF14EN_SHIFT 4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF15EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_CF15EN_SHIFT 5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_GO_TO_BD_CONS_CF_EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_GO_TO_BD_CONS_CF_EN_SHIFT 6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_MULTI_UNICAST_CF_EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_MULTI_UNICAST_CF_EN_SHIFT 7
+ u8 flags10;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_DQ_CF_EN_SHIFT 0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TERMINATE_CF_EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TERMINATE_CF_EN_SHIFT 1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_FLUSH_Q0_EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_FLUSH_Q0_EN_SHIFT 2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED11_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED11_SHIFT 3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_SLOW_PATH_EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_SLOW_PATH_EN_SHIFT 4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TPH_ENABLE_EN_RESERVED_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TPH_ENABLE_EN_RESERVED_SHIFT 5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED12_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED12_SHIFT 6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED13_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED13_SHIFT 7
+ u8 flags11;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED14_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED14_SHIFT 0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED15_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RESERVED15_SHIFT 1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TX_DEC_RULE_EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TX_DEC_RULE_EN_SHIFT 2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE5EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE5EN_SHIFT 3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE6EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE6EN_SHIFT 4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE7EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE7EN_SHIFT 5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED1_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED1_SHIFT 6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE9EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE9EN_SHIFT 7
+ u8 flags12;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE10EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE10EN_SHIFT 0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE11EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE11EN_SHIFT 1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED2_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED2_SHIFT 2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED3_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED3_SHIFT 3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE14EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE14EN_SHIFT 4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE15EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE15EN_SHIFT 5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE16EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE16EN_SHIFT 6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE17EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE17EN_SHIFT 7
+ u8 flags13;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE18EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE18EN_SHIFT 0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE19EN_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_RULE19EN_SHIFT 1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED4_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED4_SHIFT 2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED5_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED5_SHIFT 3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED6_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED6_SHIFT 4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED7_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED7_SHIFT 5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED8_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED8_SHIFT 6
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED9_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_A0_RESERVED9_SHIFT 7
+ u8 flags14;
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_USE_EXT_HDR_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_USE_EXT_HDR_SHIFT 0
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_SEND_RAW_L3L4_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_SEND_RAW_L3L4_SHIFT 1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_INBAND_PROP_HDR_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_INBAND_PROP_HDR_SHIFT 2
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_SEND_EXT_TUNNEL_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_EDPM_SEND_EXT_TUNNEL_SHIFT 3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_L2_EDPM_ENABLE_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_L2_EDPM_ENABLE_SHIFT 4
+#define XSTORMETHCONNAGCTXDQEXTLDPART_ROCE_EDPM_ENABLE_MASK 0x1
+#define XSTORMETHCONNAGCTXDQEXTLDPART_ROCE_EDPM_ENABLE_SHIFT 5
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TPH_ENABLE_MASK 0x3
+#define XSTORMETHCONNAGCTXDQEXTLDPART_TPH_ENABLE_SHIFT 6
+ u8 edpm_event_id;
+ __le16 physical_q0;
+ __le16 quota;
+ __le16 edpm_num_bds;
+ __le16 tx_bd_cons;
+ __le16 tx_bd_prod;
+ __le16 tx_class;
+ __le16 conn_dpi;
+ u8 byte3;
+ u8 byte4;
+ u8 byte5;
+ u8 byte6;
+ __le32 reg0;
+ __le32 reg1;
+ __le32 reg2;
+ __le32 reg3;
+ __le32 reg4;
+};
+
+struct xstorm_eth_hw_conn_ag_ctx {
+ u8 reserved0;
+ u8 eth_state;
+ u8 flags0;
+#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED1_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED1_SHIFT 1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED2_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED2_SHIFT 2
+#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED3_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED3_SHIFT 4
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED4_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED4_SHIFT 5
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED5_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED5_SHIFT 6
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED6_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED6_SHIFT 7
+ u8 flags1;
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED7_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED7_SHIFT 0
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED8_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED8_SHIFT 1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED9_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED9_SHIFT 2
+#define XSTORM_ETH_HW_CONN_AG_CTX_BIT11_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_BIT11_SHIFT 3
+#define XSTORM_ETH_HW_CONN_AG_CTX_BIT12_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_BIT12_SHIFT 4
+#define XSTORM_ETH_HW_CONN_AG_CTX_BIT13_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_BIT13_SHIFT 5
+#define XSTORM_ETH_HW_CONN_AG_CTX_TX_RULE_ACTIVE_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_TX_RULE_ACTIVE_SHIFT 6
+#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_ACTIVE_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_ACTIVE_SHIFT 7
+ u8 flags2;
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF0_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF0_SHIFT 0
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF1_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF1_SHIFT 2
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF2_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF2_SHIFT 4
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF3_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF3_SHIFT 6
+ u8 flags3;
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF4_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF4_SHIFT 0
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF5_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF5_SHIFT 2
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF6_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF6_SHIFT 4
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF7_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF7_SHIFT 6
+ u8 flags4;
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF8_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF8_SHIFT 0
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF9_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF9_SHIFT 2
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF10_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF10_SHIFT 4
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF11_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF11_SHIFT 6
+ u8 flags5;
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF12_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF12_SHIFT 0
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF13_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF13_SHIFT 2
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF14_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF14_SHIFT 4
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF15_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF15_SHIFT 6
+ u8 flags6;
+#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_SHIFT 0
+#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_SHIFT 2
+#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_SHIFT 4
+#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_SHIFT 6
+ u8 flags7;
+#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_SHIFT 0
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED10_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED10_SHIFT 2
+#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_SHIFT 4
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF0EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF0EN_SHIFT 6
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF1EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF1EN_SHIFT 7
+ u8 flags8;
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF2EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF2EN_SHIFT 0
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF3EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF3EN_SHIFT 1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF4EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF4EN_SHIFT 2
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF5EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF5EN_SHIFT 3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF6EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF6EN_SHIFT 4
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF7EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF7EN_SHIFT 5
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF8EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF8EN_SHIFT 6
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF9EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF9EN_SHIFT 7
+ u8 flags9;
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF10EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF10EN_SHIFT 0
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF11EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF11EN_SHIFT 1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF12EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF12EN_SHIFT 2
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF13EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF13EN_SHIFT 3
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF14EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF14EN_SHIFT 4
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF15EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_CF15EN_SHIFT 5
+#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_EN_SHIFT 6
+#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_EN_SHIFT 7
+ u8 flags10;
+#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_EN_SHIFT 0
+#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_EN_SHIFT 1
+#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT 2
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED11_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED11_SHIFT 3
+#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4
+#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_EN_RESERVED_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_EN_RESERVED_SHIFT 5
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED12_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED12_SHIFT 6
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED13_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED13_SHIFT 7
+ u8 flags11;
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED14_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED14_SHIFT 0
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED15_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED15_SHIFT 1
+#define XSTORM_ETH_HW_CONN_AG_CTX_TX_DEC_RULE_EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_TX_DEC_RULE_EN_SHIFT 2
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE5EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE5EN_SHIFT 3
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE6EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE6EN_SHIFT 4
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE7EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE7EN_SHIFT 5
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED1_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED1_SHIFT 6
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE9EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE9EN_SHIFT 7
+ u8 flags12;
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE10EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE10EN_SHIFT 0
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE11EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE11EN_SHIFT 1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED2_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED2_SHIFT 2
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED3_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED3_SHIFT 3
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE14EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE14EN_SHIFT 4
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE15EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE15EN_SHIFT 5
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE16EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE16EN_SHIFT 6
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE17EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE17EN_SHIFT 7
+ u8 flags13;
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE18EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE18EN_SHIFT 0
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE19EN_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_RULE19EN_SHIFT 1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED4_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED4_SHIFT 2
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED5_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED5_SHIFT 3
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED6_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED6_SHIFT 4
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED7_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED7_SHIFT 5
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED8_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED8_SHIFT 6
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED9_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED9_SHIFT 7
+ u8 flags14;
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_USE_EXT_HDR_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_USE_EXT_HDR_SHIFT 0
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_RAW_L3L4_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_RAW_L3L4_SHIFT 1
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_INBAND_PROP_HDR_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_INBAND_PROP_HDR_SHIFT 2
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_EXT_TUNNEL_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_EXT_TUNNEL_SHIFT 3
+#define XSTORM_ETH_HW_CONN_AG_CTX_L2_EDPM_ENABLE_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_L2_EDPM_ENABLE_SHIFT 4
+#define XSTORM_ETH_HW_CONN_AG_CTX_ROCE_EDPM_ENABLE_MASK 0x1
+#define XSTORM_ETH_HW_CONN_AG_CTX_ROCE_EDPM_ENABLE_SHIFT 5
+#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_MASK 0x3
+#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_SHIFT 6
+ u8 edpm_event_id;
+ __le16 physical_q0;
+ __le16 quota;
+ __le16 edpm_num_bds;
+ __le16 tx_bd_cons;
+ __le16 tx_bd_prod;
+ __le16 tx_class;
+ __le16 conn_dpi;
+};
+
struct mstorm_rdma_task_st_ctx {
struct regpair temp[4];
};
@@ -6165,7 +6764,7 @@ struct ystorm_roce_conn_st_ctx {
};
struct xstorm_roce_conn_st_ctx {
- struct regpair temp[22];
+ struct regpair temp[24];
};
struct tstorm_roce_conn_st_ctx {
@@ -6220,7 +6819,7 @@ struct roce_create_qp_req_ramrod_data {
__le16 mtu;
__le16 pd;
__le16 sq_num_pages;
- __le16 reseved2;
+ __le16 low_latency_phy_queue;
struct regpair sq_pbl_addr;
struct regpair orq_pbl_addr;
__le16 local_mac_addr[3];
@@ -6234,7 +6833,7 @@ struct roce_create_qp_req_ramrod_data {
u8 stats_counter_id;
u8 reserved3[7];
__le32 cq_cid;
- __le16 physical_queue0;
+ __le16 regular_latency_phy_queue;
__le16 dpi;
};
@@ -6282,15 +6881,16 @@ struct roce_create_qp_resp_ramrod_data {
__le32 dst_gid[4];
struct regpair qp_handle_for_cqe;
struct regpair qp_handle_for_async;
- __le32 reserved2[2];
+ __le16 low_latency_phy_queue;
+ u8 reserved2[6];
__le32 cq_cid;
- __le16 physical_queue0;
+ __le16 regular_latency_phy_queue;
__le16 dpi;
};
struct roce_destroy_qp_req_output_params {
__le32 num_bound_mw;
- __le32 reserved;
+ __le32 cq_prod;
};
struct roce_destroy_qp_req_ramrod_data {
@@ -6299,7 +6899,7 @@ struct roce_destroy_qp_req_ramrod_data {
struct roce_destroy_qp_resp_output_params {
__le32 num_invalidated_mw;
- __le32 reserved;
+ __le32 cq_prod;
};
struct roce_destroy_qp_resp_ramrod_data {
@@ -7426,6 +8026,7 @@ struct ystorm_fcoe_conn_st_ctx {
u8 fcp_rsp_size;
__le16 mss;
struct regpair reserved;
+ __le16 min_frame_size;
u8 protection_info_flags;
#define YSTORM_FCOE_CONN_ST_CTX_SUPPORT_PROTECTION_MASK 0x1
#define YSTORM_FCOE_CONN_ST_CTX_SUPPORT_PROTECTION_SHIFT 0
@@ -7444,7 +8045,6 @@ struct ystorm_fcoe_conn_st_ctx {
#define YSTORM_FCOE_CONN_ST_CTX_RSRV_MASK 0x3F
#define YSTORM_FCOE_CONN_ST_CTX_RSRV_SHIFT 2
u8 fcp_xfer_size;
- u8 reserved3[2];
};
struct fcoe_vlan_fields {
@@ -8273,10 +8873,10 @@ struct xstorm_iscsi_conn_ag_ctx {
#define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_MASK 0x3
#define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_SHIFT 6
u8 flags7;
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_MASK 0x3
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_SHIFT 0
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q1_MASK 0x3
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q1_SHIFT 2
+#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_MASK 0x3
+#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_SHIFT 0
+#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_MASK 0x3
+#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_SHIFT 2
#define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_MASK 0x3
#define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_SHIFT 4
#define XSTORM_ISCSI_CONN_AG_CTX_CF0EN_MASK 0x1
@@ -8322,10 +8922,10 @@ struct xstorm_iscsi_conn_ag_ctx {
#define XSTORM_ISCSI_CONN_AG_CTX_CF18EN_SHIFT 0
#define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_EN_MASK 0x1
#define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_EN_SHIFT 1
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_EN_MASK 0x1
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT 2
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q1_EN_MASK 0x1
-#define XSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q1_EN_SHIFT 3
+#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_EN_MASK 0x1
+#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_EN_SHIFT 2
+#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_EN_MASK 0x1
+#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_EN_SHIFT 3
#define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1
#define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4
#define XSTORM_ISCSI_CONN_AG_CTX_PROC_ONLY_CLEANUP_EN_MASK 0x1
@@ -8335,8 +8935,8 @@ struct xstorm_iscsi_conn_ag_ctx {
#define XSTORM_ISCSI_CONN_AG_CTX_MORE_TO_SEND_DEC_RULE_EN_MASK 0x1
#define XSTORM_ISCSI_CONN_AG_CTX_MORE_TO_SEND_DEC_RULE_EN_SHIFT 7
u8 flags11;
-#define XSTORM_ISCSI_CONN_AG_CTX_RULE2EN_MASK 0x1
-#define XSTORM_ISCSI_CONN_AG_CTX_RULE2EN_SHIFT 0
+#define XSTORM_ISCSI_CONN_AG_CTX_TX_BLOCKED_EN_MASK 0x1
+#define XSTORM_ISCSI_CONN_AG_CTX_TX_BLOCKED_EN_SHIFT 0
#define XSTORM_ISCSI_CONN_AG_CTX_RULE3EN_MASK 0x1
#define XSTORM_ISCSI_CONN_AG_CTX_RULE3EN_SHIFT 1
#define XSTORM_ISCSI_CONN_AG_CTX_RESERVED3_MASK 0x1
@@ -8440,7 +9040,7 @@ struct xstorm_iscsi_conn_ag_ctx {
__le32 reg10;
__le32 reg11;
__le32 exp_stat_sn;
- __le32 reg13;
+ __le32 ongoing_fast_rxmit_seq;
__le32 reg14;
__le32 reg15;
__le32 reg16;
@@ -8466,10 +9066,10 @@ struct tstorm_iscsi_conn_ag_ctx {
#define TSTORM_ISCSI_CONN_AG_CTX_CF0_MASK 0x3
#define TSTORM_ISCSI_CONN_AG_CTX_CF0_SHIFT 6
u8 flags1;
-#define TSTORM_ISCSI_CONN_AG_CTX_CF1_MASK 0x3
-#define TSTORM_ISCSI_CONN_AG_CTX_CF1_SHIFT 0
-#define TSTORM_ISCSI_CONN_AG_CTX_CF2_MASK 0x3
-#define TSTORM_ISCSI_CONN_AG_CTX_CF2_SHIFT 2
+#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_MASK 0x3
+#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_SHIFT 0
+#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_MASK 0x3
+#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_SHIFT 2
#define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_MASK 0x3
#define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_SHIFT 4
#define TSTORM_ISCSI_CONN_AG_CTX_CF4_MASK 0x3
@@ -8490,10 +9090,10 @@ struct tstorm_iscsi_conn_ag_ctx {
#define TSTORM_ISCSI_CONN_AG_CTX_CF10_SHIFT 2
#define TSTORM_ISCSI_CONN_AG_CTX_CF0EN_MASK 0x1
#define TSTORM_ISCSI_CONN_AG_CTX_CF0EN_SHIFT 4
-#define TSTORM_ISCSI_CONN_AG_CTX_CF1EN_MASK 0x1
-#define TSTORM_ISCSI_CONN_AG_CTX_CF1EN_SHIFT 5
-#define TSTORM_ISCSI_CONN_AG_CTX_CF2EN_MASK 0x1
-#define TSTORM_ISCSI_CONN_AG_CTX_CF2EN_SHIFT 6
+#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_EN_MASK 0x1
+#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_EN_SHIFT 5
+#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_EN_MASK 0x1
+#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_EN_SHIFT 6
#define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_EN_MASK 0x1
#define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_EN_SHIFT 7
u8 flags4;
@@ -8539,7 +9139,7 @@ struct tstorm_iscsi_conn_ag_ctx {
__le32 reg6;
__le32 reg7;
__le32 reg8;
- u8 byte2;
+ u8 cid_offload_cnt;
u8 byte3;
__le16 word0;
};
@@ -8831,11 +9431,24 @@ struct eth_stats {
u64 r511;
u64 r1023;
u64 r1518;
- u64 r1522;
- u64 r2047;
- u64 r4095;
- u64 r9216;
- u64 r16383;
+
+ union {
+ struct {
+ u64 r1522;
+ u64 r2047;
+ u64 r4095;
+ u64 r9216;
+ u64 r16383;
+ } bb0;
+ struct {
+ u64 unused1;
+ u64 r1519_to_max;
+ u64 unused2;
+ u64 unused3;
+ u64 unused4;
+ } ah0;
+ } u0;
+
u64 rfcs;
u64 rxcf;
u64 rxpf;
@@ -8852,14 +9465,36 @@ struct eth_stats {
u64 t511;
u64 t1023;
u64 t1518;
- u64 t2047;
- u64 t4095;
- u64 t9216;
- u64 t16383;
+
+ union {
+ struct {
+ u64 t2047;
+ u64 t4095;
+ u64 t9216;
+ u64 t16383;
+ } bb1;
+ struct {
+ u64 t1519_to_max;
+ u64 unused6;
+ u64 unused7;
+ u64 unused8;
+ } ah1;
+ } u1;
+
u64 txpf;
u64 txpp;
- u64 tlpiec;
- u64 tncl;
+
+ union {
+ struct {
+ u64 tlpiec;
+ u64 tncl;
+ } bb2;
+ struct {
+ u64 unused9;
+ u64 unused10;
+ } ah2;
+ } u2;
+
u64 rbyte;
u64 rxuca;
u64 rxmca;
@@ -8943,12 +9578,12 @@ struct dcbx_ets_feature {
#define DCBX_ETS_CBS_SHIFT 3
#define DCBX_ETS_MAX_TCS_MASK 0x000000f0
#define DCBX_ETS_MAX_TCS_SHIFT 4
-#define DCBX_ISCSI_OOO_TC_MASK 0x00000f00
-#define DCBX_ISCSI_OOO_TC_SHIFT 8
+#define DCBX_OOO_TC_MASK 0x00000f00
+#define DCBX_OOO_TC_SHIFT 8
u32 pri_tc_tbl[1];
-#define DCBX_ISCSI_OOO_TC (4)
+#define DCBX_TCP_OOO_TC (4)
-#define NIG_ETS_ISCSI_OOO_CLIENT_OFFSET (DCBX_ISCSI_OOO_TC + 1)
+#define NIG_ETS_ISCSI_OOO_CLIENT_OFFSET (DCBX_TCP_OOO_TC + 1)
#define DCBX_CEE_STRICT_PRIORITY 0xf
u32 tc_bw_tbl[2];
u32 tc_tsa_tbl[2];
@@ -8957,6 +9592,9 @@ struct dcbx_ets_feature {
#define DCBX_ETS_TSA_ETS 2
};
+#define DCBX_TCP_OOO_TC (4)
+#define DCBX_TCP_OOO_K2_4PORT_TC (3)
+
struct dcbx_app_priority_entry {
u32 entry;
#define DCBX_APP_PRI_MAP_MASK 0x000000ff
@@ -9067,6 +9705,10 @@ struct dcb_dscp_map {
struct public_global {
u32 max_path;
u32 max_ports;
+#define MODE_1P 1
+#define MODE_2P 2
+#define MODE_3P 3
+#define MODE_4P 4
u32 debug_mb_offset;
u32 phymod_dbg_mb_offset;
struct couple_mode_teaming cmt;
@@ -9248,9 +9890,11 @@ struct public_func {
#define DRV_ID_PDA_COMP_VER_MASK 0x0000ffff
#define DRV_ID_PDA_COMP_VER_SHIFT 0
+#define LOAD_REQ_HSI_VERSION 2
#define DRV_ID_MCP_HSI_VER_MASK 0x00ff0000
#define DRV_ID_MCP_HSI_VER_SHIFT 16
-#define DRV_ID_MCP_HSI_VER_CURRENT (1 << DRV_ID_MCP_HSI_VER_SHIFT)
+#define DRV_ID_MCP_HSI_VER_CURRENT (LOAD_REQ_HSI_VERSION << \
+ DRV_ID_MCP_HSI_VER_SHIFT)
#define DRV_ID_DRV_TYPE_MASK 0x7f000000
#define DRV_ID_DRV_TYPE_SHIFT 24
@@ -9345,6 +9989,7 @@ enum resource_id_enum {
RESOURCE_NUM_RSS_ENGINES_E = 14,
RESOURCE_LL2_QUEUE_E = 15,
RESOURCE_RDMA_STATS_QUEUE_E = 16,
+ RESOURCE_BDQ_E = 17,
RESOURCE_MAX_NUM,
RESOURCE_NUM_INVALID = 0xFFFFFFFF
};
@@ -9362,6 +10007,46 @@ struct resource_info {
#define RESOURCE_ELEMENT_STRICT (1 << 0)
};
+#define DRV_ROLE_NONE 0
+#define DRV_ROLE_PREBOOT 1
+#define DRV_ROLE_OS 2
+#define DRV_ROLE_KDUMP 3
+
+struct load_req_stc {
+ u32 drv_ver_0;
+ u32 drv_ver_1;
+ u32 fw_ver;
+ u32 misc0;
+#define LOAD_REQ_ROLE_MASK 0x000000FF
+#define LOAD_REQ_ROLE_SHIFT 0
+#define LOAD_REQ_LOCK_TO_MASK 0x0000FF00
+#define LOAD_REQ_LOCK_TO_SHIFT 8
+#define LOAD_REQ_LOCK_TO_DEFAULT 0
+#define LOAD_REQ_LOCK_TO_NONE 255
+#define LOAD_REQ_FORCE_MASK 0x000F0000
+#define LOAD_REQ_FORCE_SHIFT 16
+#define LOAD_REQ_FORCE_NONE 0
+#define LOAD_REQ_FORCE_PF 1
+#define LOAD_REQ_FORCE_ALL 2
+#define LOAD_REQ_FLAGS0_MASK 0x00F00000
+#define LOAD_REQ_FLAGS0_SHIFT 20
+#define LOAD_REQ_FLAGS0_AVOID_RESET (0x1 << 0)
+};
+
+struct load_rsp_stc {
+ u32 drv_ver_0;
+ u32 drv_ver_1;
+ u32 fw_ver;
+ u32 misc0;
+#define LOAD_RSP_ROLE_MASK 0x000000FF
+#define LOAD_RSP_ROLE_SHIFT 0
+#define LOAD_RSP_HSI_MASK 0x0000FF00
+#define LOAD_RSP_HSI_SHIFT 8
+#define LOAD_RSP_FLAGS0_MASK 0x000F0000
+#define LOAD_RSP_FLAGS0_SHIFT 16
+#define LOAD_RSP_FLAGS0_DRV_EXISTS (0x1 << 0)
+};
+
union drv_union_data {
u32 ver_str[MCP_DRV_VER_STR_SIZE_DWORD];
struct mcp_mac wol_mac;
@@ -9393,6 +10078,7 @@ struct public_drv_mb {
#define DRV_MSG_CODE_LOAD_REQ 0x10000000
#define DRV_MSG_CODE_LOAD_DONE 0x11000000
#define DRV_MSG_CODE_INIT_HW 0x12000000
+#define DRV_MSG_CODE_CANCEL_LOAD_REQ 0x13000000
#define DRV_MSG_CODE_UNLOAD_REQ 0x20000000
#define DRV_MSG_CODE_UNLOAD_DONE 0x21000000
#define DRV_MSG_CODE_INIT_PHY 0x22000000
@@ -9405,12 +10091,14 @@ struct public_drv_mb {
#define DRV_MSG_CODE_OV_UPDATE_DRIVER_STATE 0x31000000
#define DRV_MSG_CODE_BW_UPDATE_ACK 0x32000000
#define DRV_MSG_CODE_OV_UPDATE_MTU 0x33000000
+#define DRV_MSG_GET_RESOURCE_ALLOC_MSG 0x34000000
+#define DRV_MSG_SET_RESOURCE_VALUE_MSG 0x35000000
#define DRV_MSG_CODE_OV_UPDATE_WOL 0x38000000
#define DRV_MSG_CODE_OV_UPDATE_ESWITCH_MODE 0x39000000
#define DRV_MSG_CODE_BW_UPDATE_ACK 0x32000000
#define DRV_MSG_CODE_NIG_DRAIN 0x30000000
-#define DRV_MSG_GET_RESOURCE_ALLOC_MSG 0x34000000
+#define DRV_MSG_CODE_INITIATE_PF_FLR 0x02010000
#define DRV_MSG_CODE_VF_DISABLED_DONE 0xc0000000
#define DRV_MSG_CODE_CFG_VF_MSIX 0xc0010000
#define DRV_MSG_CODE_NVM_GET_FILE_ATT 0x00030000
@@ -9436,6 +10124,33 @@ struct public_drv_mb {
#define DRV_MSG_CODE_BIST_TEST 0x001e0000
#define DRV_MSG_CODE_SET_LED_MODE 0x00200000
+#define DRV_MSG_CODE_RESOURCE_CMD 0x00230000
+
+#define RESOURCE_CMD_REQ_RESC_MASK 0x0000001F
+#define RESOURCE_CMD_REQ_RESC_SHIFT 0
+#define RESOURCE_CMD_REQ_OPCODE_MASK 0x000000E0
+#define RESOURCE_CMD_REQ_OPCODE_SHIFT 5
+#define RESOURCE_OPCODE_REQ 1
+#define RESOURCE_OPCODE_REQ_WO_AGING 2
+#define RESOURCE_OPCODE_REQ_W_AGING 3
+#define RESOURCE_OPCODE_RELEASE 4
+#define RESOURCE_OPCODE_FORCE_RELEASE 5
+#define RESOURCE_CMD_REQ_AGE_MASK 0x0000FF00
+#define RESOURCE_CMD_REQ_AGE_SHIFT 8
+
+#define RESOURCE_CMD_RSP_OWNER_MASK 0x000000FF
+#define RESOURCE_CMD_RSP_OWNER_SHIFT 0
+#define RESOURCE_CMD_RSP_OPCODE_MASK 0x00000700
+#define RESOURCE_CMD_RSP_OPCODE_SHIFT 8
+#define RESOURCE_OPCODE_GNT 1
+#define RESOURCE_OPCODE_BUSY 2
+#define RESOURCE_OPCODE_RELEASED 3
+#define RESOURCE_OPCODE_RELEASED_PREVIOUS 4
+#define RESOURCE_OPCODE_WRONG_OWNER 5
+#define RESOURCE_OPCODE_UNKNOWN_CMD 255
+
+#define RESOURCE_DUMP 0
+
#define DRV_MSG_CODE_GET_PF_RDMA_PROTOCOL 0x002b0000
#define DRV_MSG_CODE_OS_WOL 0x002e0000
@@ -9524,12 +10239,16 @@ struct public_drv_mb {
u32 fw_mb_header;
#define FW_MSG_CODE_MASK 0xffff0000
+#define FW_MSG_CODE_UNSUPPORTED 0x00000000
#define FW_MSG_CODE_DRV_LOAD_ENGINE 0x10100000
#define FW_MSG_CODE_DRV_LOAD_PORT 0x10110000
#define FW_MSG_CODE_DRV_LOAD_FUNCTION 0x10120000
#define FW_MSG_CODE_DRV_LOAD_REFUSED_PDA 0x10200000
-#define FW_MSG_CODE_DRV_LOAD_REFUSED_HSI 0x10210000
+#define FW_MSG_CODE_DRV_LOAD_REFUSED_HSI_1 0x10210000
#define FW_MSG_CODE_DRV_LOAD_REFUSED_DIAG 0x10220000
+#define FW_MSG_CODE_DRV_LOAD_REFUSED_HSI 0x10230000
+#define FW_MSG_CODE_DRV_LOAD_REFUSED_REQUIRES_FORCE 0x10300000
+#define FW_MSG_CODE_DRV_LOAD_REFUSED_REJECT 0x10310000
#define FW_MSG_CODE_DRV_LOAD_DONE 0x11100000
#define FW_MSG_CODE_DRV_UNLOAD_ENGINE 0x20110000
#define FW_MSG_CODE_DRV_UNLOAD_PORT 0x20120000
@@ -9549,6 +10268,10 @@ struct public_drv_mb {
#define FW_MSG_SEQ_NUMBER_MASK 0x0000ffff
u32 fw_mb_param;
+#define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_MASK 0xFFFF0000
+#define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_SHIFT 16
+#define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MINOR_MASK 0x0000FFFF
+#define FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MINOR_SHIFT 0
/* get pf rdma protocol command responce */
#define FW_MB_PARAM_GET_PF_RDMA_NONE 0x0
@@ -9659,6 +10382,8 @@ struct nvm_cfg1_glob {
#define NVM_CFG1_GLOB_NETWORK_PORT_MODE_2X25G 0xC
#define NVM_CFG1_GLOB_NETWORK_PORT_MODE_1X25G 0xD
#define NVM_CFG1_GLOB_NETWORK_PORT_MODE_4X25G 0xE
+#define NVM_CFG1_GLOB_NETWORK_PORT_MODE_2X10G 0xF
+
u32 e_lane_cfg1;
u32 e_lane_cfg2;
u32 f_lane_cfg1;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.c b/drivers/net/ethernet/qlogic/qed/qed_hw.c
index 899cad7..a05feb3 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hw.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_hw.c
@@ -58,6 +58,7 @@ struct qed_ptt {
struct list_head list_entry;
unsigned int idx;
struct pxp_ptt_entry pxp;
+ u8 hwfn_id;
};
struct qed_ptt_pool {
@@ -79,6 +80,7 @@ int qed_ptt_pool_alloc(struct qed_hwfn *p_hwfn)
p_pool->ptts[i].idx = i;
p_pool->ptts[i].pxp.offset = QED_BAR_INVALID_OFFSET;
p_pool->ptts[i].pxp.pretend.control = 0;
+ p_pool->ptts[i].hwfn_id = p_hwfn->my_id;
if (i >= RESERVED_PTT_MAX)
list_add(&p_pool->ptts[i].list_entry,
&p_pool->free_list);
@@ -193,6 +195,11 @@ static u32 qed_set_ptt(struct qed_hwfn *p_hwfn,
offset = hw_addr - win_hw_addr;
+ if (p_ptt->hwfn_id != p_hwfn->my_id)
+ DP_NOTICE(p_hwfn,
+ "ptt[%d] of hwfn[%02x] is used by hwfn[%02x]!\n",
+ p_ptt->idx, p_ptt->hwfn_id, p_hwfn->my_id);
+
/* Verify the address is within the window */
if (hw_addr < win_hw_addr ||
offset >= PXP_EXTERNAL_BAR_PF_WINDOW_SINGLE_SIZE) {
@@ -800,55 +807,3 @@ int qed_dmae_host2host(struct qed_hwfn *p_hwfn,
return rc;
}
-u16 qed_get_qm_pq(struct qed_hwfn *p_hwfn,
- enum protocol_type proto, union qed_qm_pq_params *p_params)
-{
- u16 pq_id = 0;
-
- if ((proto == PROTOCOLID_CORE ||
- proto == PROTOCOLID_ETH ||
- proto == PROTOCOLID_ISCSI ||
- proto == PROTOCOLID_ROCE) && !p_params) {
- DP_NOTICE(p_hwfn,
- "Protocol %d received NULL PQ params\n", proto);
- return 0;
- }
-
- switch (proto) {
- case PROTOCOLID_CORE:
- if (p_params->core.tc == LB_TC)
- pq_id = p_hwfn->qm_info.pure_lb_pq;
- else if (p_params->core.tc == OOO_LB_TC)
- pq_id = p_hwfn->qm_info.ooo_pq;
- else
- pq_id = p_hwfn->qm_info.offload_pq;
- break;
- case PROTOCOLID_ETH:
- pq_id = p_params->eth.tc;
- if (p_params->eth.is_vf)
- pq_id += p_hwfn->qm_info.vf_queues_offset +
- p_params->eth.vf_id;
- break;
- case PROTOCOLID_ISCSI:
- if (p_params->iscsi.q_idx == 1)
- pq_id = p_hwfn->qm_info.pure_ack_pq;
- break;
- case PROTOCOLID_ROCE:
- if (p_params->roce.dcqcn)
- pq_id = p_params->roce.qpid;
- else
- pq_id = p_hwfn->qm_info.offload_pq;
- if (pq_id > p_hwfn->qm_info.num_pf_rls)
- pq_id = p_hwfn->qm_info.offload_pq;
- break;
- case PROTOCOLID_FCOE:
- pq_id = p_hwfn->qm_info.offload_pq;
- break;
- default:
- pq_id = 0;
- }
-
- pq_id = CM_TX_PQ_BASE + pq_id + RESC_START(p_hwfn, QED_PQ);
-
- return pq_id;
-}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.h b/drivers/net/ethernet/qlogic/qed/qed_hw.h
index 9277264..f2505c6 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hw.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hw.h
@@ -297,9 +297,6 @@ union qed_qm_pq_params {
} roce;
};
-u16 qed_get_qm_pq(struct qed_hwfn *p_hwfn,
- enum protocol_type proto, union qed_qm_pq_params *params);
-
int qed_init_fw_data(struct qed_dev *cdev,
const u8 *fw_data);
#endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
index d891a68..2a50e2b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
@@ -215,13 +215,6 @@ static void qed_cmdq_lines_voq_rt_init(struct qed_hwfn *p_hwfn,
{
u32 qm_line_crd;
- /* In A0 - Limit the size of pbf queue so that only 511 commands with
- * the minimum size of 4 (FCoE minimum size)
- */
- bool is_bb_a0 = QED_IS_BB_A0(p_hwfn->cdev);
-
- if (is_bb_a0)
- cmdq_lines = min_t(u32, cmdq_lines, 1022);
qm_line_crd = QM_VOQ_LINE_CRD(cmdq_lines);
OVERWRITE_RT_REG(p_hwfn, PBF_CMDQ_LINES_RT_OFFSET(voq),
(u32)cmdq_lines);
@@ -343,13 +336,11 @@ static void qed_tx_pq_map_rt_init(
u16 first_pq_group = p_params->start_pq / QM_PF_QUEUE_GROUP_SIZE;
u16 last_pq_group = (p_params->start_pq + num_pqs - 1) /
QM_PF_QUEUE_GROUP_SIZE;
- bool is_bb_a0 = QED_IS_BB_A0(p_hwfn->cdev);
u16 i, pq_id, pq_group;
/* a bit per Tx PQ indicating if the PQ is associated with a VF */
u32 tx_pq_vf_mask[MAX_QM_TX_QUEUES / QM_PF_QUEUE_GROUP_SIZE] = { 0 };
- u32 tx_pq_vf_mask_width = is_bb_a0 ? 32 : QM_PF_QUEUE_GROUP_SIZE;
- u32 num_tx_pq_vf_masks = MAX_QM_TX_QUEUES / tx_pq_vf_mask_width;
+ u32 num_tx_pq_vf_masks = MAX_QM_TX_QUEUES / QM_PF_QUEUE_GROUP_SIZE;
u32 pq_mem_4kb = QM_PQ_MEM_4KB(p_params->num_pf_cids);
u32 vport_pq_mem_4kb = QM_PQ_MEM_4KB(p_params->num_vf_cids);
u32 mem_addr_4kb = base_mem_addr_4kb;
@@ -371,6 +362,10 @@ static void qed_tx_pq_map_rt_init(
bool is_vf_pq = (i >= p_params->num_pf_pqs);
struct qm_rf_pq_map tx_pq_map;
+ bool rl_valid = p_params->pq_params[i].rl_valid &&
+ (p_params->pq_params[i].vport_id <
+ MAX_QM_GLOBAL_RLS);
+
/* update first Tx PQ of VPORT/TC */
u8 vport_id_in_pf = p_params->pq_params[i].vport_id -
p_params->start_vport;
@@ -389,14 +384,18 @@ static void qed_tx_pq_map_rt_init(
(p_params->pf_id <<
QM_WFQ_VP_PQ_PF_SHIFT));
}
+
+ if (p_params->pq_params[i].rl_valid && !rl_valid)
+ DP_NOTICE(p_hwfn,
+ "Invalid VPORT ID for rate limiter configuration");
/* fill PQ map entry */
memset(&tx_pq_map, 0, sizeof(tx_pq_map));
SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_PQ_VALID, 1);
- SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_RL_VALID,
- p_params->pq_params[i].rl_valid ? 1 : 0);
+ SET_FIELD(tx_pq_map.reg,
+ QM_RF_PQ_MAP_RL_VALID, rl_valid ? 1 : 0);
SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_VP_PQ_ID, first_tx_pq_id);
SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_RL_ID,
- p_params->pq_params[i].rl_valid ?
+ rl_valid ?
p_params->pq_params[i].vport_id : 0);
SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_VOQ, voq);
SET_FIELD(tx_pq_map.reg, QM_RF_PQ_MAP_WRR_WEIGHT_GROUP,
@@ -413,8 +412,9 @@ static void qed_tx_pq_map_rt_init(
/* if PQ is associated with a VF, add indication
* to PQ VF mask
*/
- tx_pq_vf_mask[pq_id / tx_pq_vf_mask_width] |=
- (1 << (pq_id % tx_pq_vf_mask_width));
+ tx_pq_vf_mask[pq_id /
+ QM_PF_QUEUE_GROUP_SIZE] |=
+ BIT((pq_id % QM_PF_QUEUE_GROUP_SIZE));
mem_addr_4kb += vport_pq_mem_4kb;
} else {
mem_addr_4kb += pq_mem_4kb;
@@ -480,8 +480,8 @@ static int qed_pf_wfq_rt_init(struct qed_hwfn *p_hwfn,
if (p_params->pf_id < MAX_NUM_PFS_BB)
crd_reg_offset = QM_REG_WFQPFCRD_RT_OFFSET;
else
- crd_reg_offset = QM_REG_WFQPFCRD_MSB_RT_OFFSET +
- (p_params->pf_id % MAX_NUM_PFS_BB);
+ crd_reg_offset = QM_REG_WFQPFCRD_MSB_RT_OFFSET;
+ crd_reg_offset += p_params->pf_id % MAX_NUM_PFS_BB;
inc_val = QM_WFQ_INC_VAL(p_params->pf_wfq);
if (!inc_val || inc_val > QM_WFQ_MAX_INC_VAL) {
@@ -498,11 +498,11 @@ static int qed_pf_wfq_rt_init(struct qed_hwfn *p_hwfn,
QM_WFQ_CRD_REG_SIGN_BIT);
}
- STORE_RT_REG(p_hwfn, QM_REG_WFQPFWEIGHT_RT_OFFSET + p_params->pf_id,
- inc_val);
STORE_RT_REG(p_hwfn,
QM_REG_WFQPFUPPERBOUND_RT_OFFSET + p_params->pf_id,
QM_WFQ_UPPER_BOUND | QM_WFQ_CRD_REG_SIGN_BIT);
+ STORE_RT_REG(p_hwfn, QM_REG_WFQPFWEIGHT_RT_OFFSET + p_params->pf_id,
+ inc_val);
return 0;
}
@@ -576,6 +576,12 @@ static int qed_vport_rl_rt_init(struct qed_hwfn *p_hwfn,
{
u8 i, vport_id;
+ if (start_vport + num_vports >= MAX_QM_GLOBAL_RLS) {
+ DP_NOTICE(p_hwfn,
+ "Invalid VPORT ID for rate limiter configuration");
+ return -1;
+ }
+
/* go over all PF VPORTs */
for (i = 0, vport_id = start_vport; i < num_vports; i++, vport_id++) {
u32 inc_val = QM_RL_INC_VAL(vport_params[i].vport_rl);
@@ -785,6 +791,12 @@ int qed_init_vport_rl(struct qed_hwfn *p_hwfn,
{
u32 inc_val = QM_RL_INC_VAL(vport_rl);
+ if (vport_id >= MAX_QM_GLOBAL_RLS) {
+ DP_NOTICE(p_hwfn,
+ "Invalid VPORT ID for rate limiter configuration");
+ return -1;
+ }
+
if (inc_val > QM_RL_MAX_INC_VAL) {
DP_NOTICE(p_hwfn, "Invalid VPORT rate-limit configuration");
return -1;
@@ -940,12 +952,6 @@ void qed_set_geneve_enable(struct qed_hwfn *p_hwfn,
eth_geneve_enable ? 1 : 0);
qed_wr(p_hwfn, p_ptt, NIG_REG_NGE_IP_ENABLE, ip_geneve_enable ? 1 : 0);
- /* comp ver */
- reg_val = (ip_geneve_enable || eth_geneve_enable) ? 1 : 0;
- qed_wr(p_hwfn, p_ptt, NIG_REG_NGE_COMP_VER, reg_val);
- qed_wr(p_hwfn, p_ptt, PBF_REG_NGE_COMP_VER, reg_val);
- qed_wr(p_hwfn, p_ptt, PRS_REG_NGE_COMP_VER, reg_val);
-
/* EDPM with geneve tunnel not supported in BB_B0 */
if (QED_IS_BB_B0(p_hwfn->cdev))
return;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_ops.c b/drivers/net/ethernet/qlogic/qed/qed_init_ops.c
index 243b64e..4a2e7be 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_init_ops.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_init_ops.c
@@ -554,7 +554,7 @@ int qed_init_fw_data(struct qed_dev *cdev, const u8 *data)
}
/* First Dword contains metadata and should be skipped */
- buf_hdr = (struct bin_buffer_hdr *)(data + sizeof(u32));
+ buf_hdr = (struct bin_buffer_hdr *)data;
offset = buf_hdr[BIN_BUF_INIT_FW_VER_INFO].offset;
fw->fw_ver_info = (struct fw_ver_info *)(data + offset);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
index 84310b6..0ed24d6 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
@@ -2500,8 +2500,9 @@ void qed_int_cau_conf_sb(struct qed_hwfn *p_hwfn,
/* Configure pi coalescing if set */
if (p_hwfn->cdev->int_coalescing_mode == QED_COAL_MODE_ENABLE) {
+ u8 num_tc = p_hwfn->hw_info.num_hw_tc;
u8 timeset, timer_res;
- u8 num_tc = 1, i;
+ u8 i;
/* timeset = (coalesce >> timer-res), timeset is 7bit wide */
if (p_hwfn->cdev->rx_coalesce_usecs <= 0x7F)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
index 3a44d6b..339c91d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
@@ -181,6 +181,15 @@ qed_sp_iscsi_func_start(struct qed_hwfn *p_hwfn,
p_params = &p_hwfn->pf_params.iscsi_pf_params;
p_queue = &p_init->q_params;
+ /* Sanity */
+ if (p_params->num_queues > p_hwfn->hw_info.feat_num[QED_ISCSI_CQ]) {
+ DP_ERR(p_hwfn,
+ "Cannot satisfy CQ amount. Queues requested %d, CQs available %d. Aborting function start\n",
+ p_params->num_queues,
+ p_hwfn->hw_info.resc_num[QED_ISCSI_CQ]);
+ return -EINVAL;
+ }
+
SET_FIELD(p_init->hdr.flags,
ISCSI_SLOW_PATH_HDR_LAYER_CODE, ISCSI_SLOW_PATH_LAYER_CODE);
p_init->hdr.op_code = ISCSI_RAMROD_CMD_ID_INIT_FUNC;
@@ -190,6 +199,9 @@ qed_sp_iscsi_func_start(struct qed_hwfn *p_hwfn,
p_init->num_sq_pages_in_ring = p_params->num_sq_pages_in_ring;
p_init->num_r2tq_pages_in_ring = p_params->num_r2tq_pages_in_ring;
p_init->num_uhq_pages_in_ring = p_params->num_uhq_pages_in_ring;
+ p_init->ooo_enable = p_params->ooo_enable;
+ p_init->ll2_rx_queue_id = p_hwfn->hw_info.resc_start[QED_LL2_QUEUE] +
+ p_params->ll2_ooo_queue_id;
p_init->func_params.log_page_size = p_params->log_page_size;
val = p_params->num_tasks;
p_init->func_params.num_tasks = cpu_to_le16(val);
@@ -213,7 +225,7 @@ qed_sp_iscsi_func_start(struct qed_hwfn *p_hwfn,
p_queue->cq_cmdq_sb_num_arr[i] = cpu_to_le16(val);
}
- p_queue->bdq_resource_id = ISCSI_BDQ_ID(p_hwfn->port_id);
+ p_queue->bdq_resource_id = (u8)RESC_START(p_hwfn, QED_BDQ);
DMA_REGPAIR_LE(p_queue->bdq_pbl_base_address[BDQ_ID_RQ],
p_params->bdq_pbl_base_addr[BDQ_ID_RQ]);
@@ -267,11 +279,10 @@ static int qed_sp_iscsi_conn_offload(struct qed_hwfn *p_hwfn,
struct tcp_offload_params *p_tcp = NULL;
struct qed_spq_entry *p_ent = NULL;
struct qed_sp_init_data init_data;
- union qed_qm_pq_params pq_params;
- u16 pq0_id = 0, pq1_id = 0;
dma_addr_t r2tq_pbl_addr;
dma_addr_t xhq_pbl_addr;
dma_addr_t uhq_pbl_addr;
+ u16 physical_q;
int rc = 0;
u32 dval;
u16 wval;
@@ -294,16 +305,14 @@ static int qed_sp_iscsi_conn_offload(struct qed_hwfn *p_hwfn,
p_ramrod = &p_ent->ramrod.iscsi_conn_offload;
/* Transmission PQ is the first of the PF */
- memset(&pq_params, 0, sizeof(pq_params));
- pq0_id = qed_get_qm_pq(p_hwfn, PROTOCOLID_ISCSI, &pq_params);
- p_conn->physical_q0 = cpu_to_le16(pq0_id);
- p_ramrod->iscsi.physical_q0 = cpu_to_le16(pq0_id);
+ physical_q = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
+ p_conn->physical_q0 = cpu_to_le16(physical_q);
+ p_ramrod->iscsi.physical_q0 = cpu_to_le16(physical_q);
/* iSCSI Pure-ACK PQ */
- pq_params.iscsi.q_idx = 1;
- pq1_id = qed_get_qm_pq(p_hwfn, PROTOCOLID_ISCSI, &pq_params);
- p_conn->physical_q1 = cpu_to_le16(pq1_id);
- p_ramrod->iscsi.physical_q1 = cpu_to_le16(pq1_id);
+ physical_q = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_ACK);
+ p_conn->physical_q1 = cpu_to_le16(physical_q);
+ p_ramrod->iscsi.physical_q1 = cpu_to_le16(physical_q);
p_ramrod->hdr.op_code = ISCSI_RAMROD_CMD_ID_OFFLOAD_CONN;
SET_FIELD(p_ramrod->hdr.flags, ISCSI_SLOW_PATH_HDR_LAYER_CODE,
@@ -590,21 +599,31 @@ static void __iomem *qed_iscsi_get_db_addr(struct qed_hwfn *p_hwfn, u32 cid)
static void __iomem *qed_iscsi_get_primary_bdq_prod(struct qed_hwfn *p_hwfn,
u8 bdq_id)
{
- u8 bdq_function_id = ISCSI_BDQ_ID(p_hwfn->port_id);
-
- return (u8 __iomem *)p_hwfn->regview + GTT_BAR0_MAP_REG_MSDM_RAM +
- MSTORM_SCSI_BDQ_EXT_PROD_OFFSET(bdq_function_id,
- bdq_id);
+ if (RESC_NUM(p_hwfn, QED_BDQ)) {
+ return (u8 __iomem *)p_hwfn->regview +
+ GTT_BAR0_MAP_REG_MSDM_RAM +
+ MSTORM_SCSI_BDQ_EXT_PROD_OFFSET(RESC_START(p_hwfn,
+ QED_BDQ),
+ bdq_id);
+ } else {
+ DP_NOTICE(p_hwfn, "BDQ is not allocated!\n");
+ return NULL;
+ }
}
static void __iomem *qed_iscsi_get_secondary_bdq_prod(struct qed_hwfn *p_hwfn,
u8 bdq_id)
{
- u8 bdq_function_id = ISCSI_BDQ_ID(p_hwfn->port_id);
-
- return (u8 __iomem *)p_hwfn->regview + GTT_BAR0_MAP_REG_TSDM_RAM +
- TSTORM_SCSI_BDQ_EXT_PROD_OFFSET(bdq_function_id,
- bdq_id);
+ if (RESC_NUM(p_hwfn, QED_BDQ)) {
+ return (u8 __iomem *)p_hwfn->regview +
+ GTT_BAR0_MAP_REG_TSDM_RAM +
+ TSTORM_SCSI_BDQ_EXT_PROD_OFFSET(RESC_START(p_hwfn,
+ QED_BDQ),
+ bdq_id);
+ } else {
+ DP_NOTICE(p_hwfn, "BDQ is not allocated!\n");
+ return NULL;
+ }
}
static int qed_iscsi_setup_connection(struct qed_hwfn *p_hwfn,
@@ -786,6 +805,23 @@ static void qed_iscsi_release_connection(struct qed_hwfn *p_hwfn,
spin_unlock_bh(&p_hwfn->p_iscsi_info->lock);
}
+void qed_iscsi_free_connection(struct qed_hwfn *p_hwfn,
+ struct qed_iscsi_conn *p_conn)
+{
+ qed_chain_free(p_hwfn->cdev, &p_conn->xhq);
+ qed_chain_free(p_hwfn->cdev, &p_conn->uhq);
+ qed_chain_free(p_hwfn->cdev, &p_conn->r2tq);
+ dma_free_coherent(&p_hwfn->cdev->pdev->dev,
+ sizeof(struct tcp_upload_params),
+ p_conn->tcp_upload_params_virt_addr,
+ p_conn->tcp_upload_params_phys_addr);
+ dma_free_coherent(&p_hwfn->cdev->pdev->dev,
+ sizeof(struct scsi_terminate_extra_params),
+ p_conn->queue_cnts_virt_addr,
+ p_conn->queue_cnts_phys_addr);
+ kfree(p_conn);
+}
+
struct qed_iscsi_info *qed_iscsi_alloc(struct qed_hwfn *p_hwfn)
{
struct qed_iscsi_info *p_iscsi_info;
@@ -807,6 +843,17 @@ void qed_iscsi_setup(struct qed_hwfn *p_hwfn,
void qed_iscsi_free(struct qed_hwfn *p_hwfn,
struct qed_iscsi_info *p_iscsi_info)
{
+ struct qed_iscsi_conn *p_conn = NULL;
+
+ while (!list_empty(&p_hwfn->p_iscsi_info->free_list)) {
+ p_conn = list_first_entry(&p_hwfn->p_iscsi_info->free_list,
+ struct qed_iscsi_conn, list_entry);
+ if (p_conn) {
+ list_del(&p_conn->list_entry);
+ qed_iscsi_free_connection(p_hwfn, p_conn);
+ }
+ }
+
kfree(p_iscsi_info);
}
@@ -826,6 +873,8 @@ static void _qed_iscsi_get_tstats(struct qed_hwfn *p_hwfn,
HILO_64_REGPAIR(tstats.iscsi_rx_bytes_cnt);
p_stats->iscsi_rx_packet_cnt =
HILO_64_REGPAIR(tstats.iscsi_rx_packet_cnt);
+ p_stats->iscsi_rx_new_ooo_isle_events_cnt =
+ HILO_64_REGPAIR(tstats.iscsi_rx_new_ooo_isle_events_cnt);
p_stats->iscsi_cmdq_threshold_cnt =
le32_to_cpu(tstats.iscsi_cmdq_threshold_cnt);
p_stats->iscsi_rq_threshold_cnt =
@@ -972,6 +1021,8 @@ static int qed_fill_iscsi_dev_info(struct qed_dev *cdev,
info->secondary_bdq_rq_addr =
qed_iscsi_get_secondary_bdq_prod(hwfn, BDQ_ID_RQ);
+ info->num_cqs = FEAT_NUM(hwfn, QED_ISCSI_CQ);
+
return rc;
}
@@ -1273,6 +1324,26 @@ static int qed_iscsi_stats(struct qed_dev *cdev, struct qed_iscsi_stats *stats)
return qed_iscsi_get_stats(QED_LEADING_HWFN(cdev), stats);
}
+void qed_get_protocol_stats_iscsi(struct qed_dev *cdev,
+ struct qed_mcp_iscsi_stats *stats)
+{
+ struct qed_iscsi_stats proto_stats;
+
+ /* Retrieve FW statistics */
+ memset(&proto_stats, 0, sizeof(proto_stats));
+ if (qed_iscsi_stats(cdev, &proto_stats)) {
+ DP_VERBOSE(cdev, QED_MSG_STORAGE,
+ "Failed to collect ISCSI statistics\n");
+ return;
+ }
+
+ /* Translate FW statistics into struct */
+ stats->rx_pdus = proto_stats.iscsi_rx_total_pdu_cnt;
+ stats->tx_pdus = proto_stats.iscsi_tx_total_pdu_cnt;
+ stats->rx_bytes = proto_stats.iscsi_rx_bytes_cnt;
+ stats->tx_bytes = proto_stats.iscsi_tx_bytes_cnt;
+}
+
static const struct qed_iscsi_ops qed_iscsi_ops_pass = {
.common = &qed_common_ops_pass,
.ll2 = &qed_ll2_ops_pass,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.h b/drivers/net/ethernet/qlogic/qed/qed_iscsi.h
index 20c187f..ae98f77 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.h
@@ -64,13 +64,25 @@ void qed_iscsi_setup(struct qed_hwfn *p_hwfn,
void qed_iscsi_free(struct qed_hwfn *p_hwfn,
struct qed_iscsi_info *p_iscsi_info);
+
+/**
+ * @brief - Fills provided statistics struct with statistics.
+ *
+ * @param cdev
+ * @param stats - points to struct that will be filled with statistics.
+ */
+void qed_get_protocol_stats_iscsi(struct qed_dev *cdev,
+ struct qed_mcp_iscsi_stats *stats);
#else /* IS_ENABLED(CONFIG_QED_ISCSI) */
static inline struct qed_iscsi_info *qed_iscsi_alloc(
struct qed_hwfn *p_hwfn) { return NULL; }
static inline void qed_iscsi_setup(struct qed_hwfn *p_hwfn,
struct qed_iscsi_info *p_iscsi_info) {}
static inline void qed_iscsi_free(struct qed_hwfn *p_hwfn,
- struct qed_iscsi_info *p_iscsi_info) {}
+ struct qed_iscsi_info *p_iscsi_info) {}
+static inline void
+qed_get_protocol_stats_iscsi(struct qed_dev *cdev,
+ struct qed_mcp_iscsi_stats *stats) {}
#endif /* IS_ENABLED(CONFIG_QED_ISCSI) */
#endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index df932be..d56441d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -938,15 +938,12 @@ qed_eth_pf_tx_queue_start(struct qed_hwfn *p_hwfn,
dma_addr_t pbl_addr,
u16 pbl_size, void __iomem **pp_doorbell)
{
- union qed_qm_pq_params pq_params;
int rc;
- memset(&pq_params, 0, sizeof(pq_params));
rc = qed_eth_txq_start_ramrod(p_hwfn, p_cid,
pbl_addr, pbl_size,
- qed_get_qm_pq(p_hwfn, PROTOCOLID_ETH,
- &pq_params));
+ qed_get_cm_pq_idx_mcos(p_hwfn, tc));
if (rc)
return rc;
@@ -1470,13 +1467,20 @@ static void __qed_get_vport_pstats(struct qed_hwfn *p_hwfn,
memset(&pstats, 0, sizeof(pstats));
qed_memcpy_from(p_hwfn, p_ptt, &pstats, pstats_addr, pstats_len);
- p_stats->tx_ucast_bytes += HILO_64_REGPAIR(pstats.sent_ucast_bytes);
- p_stats->tx_mcast_bytes += HILO_64_REGPAIR(pstats.sent_mcast_bytes);
- p_stats->tx_bcast_bytes += HILO_64_REGPAIR(pstats.sent_bcast_bytes);
- p_stats->tx_ucast_pkts += HILO_64_REGPAIR(pstats.sent_ucast_pkts);
- p_stats->tx_mcast_pkts += HILO_64_REGPAIR(pstats.sent_mcast_pkts);
- p_stats->tx_bcast_pkts += HILO_64_REGPAIR(pstats.sent_bcast_pkts);
- p_stats->tx_err_drop_pkts += HILO_64_REGPAIR(pstats.error_drop_pkts);
+ p_stats->common.tx_ucast_bytes +=
+ HILO_64_REGPAIR(pstats.sent_ucast_bytes);
+ p_stats->common.tx_mcast_bytes +=
+ HILO_64_REGPAIR(pstats.sent_mcast_bytes);
+ p_stats->common.tx_bcast_bytes +=
+ HILO_64_REGPAIR(pstats.sent_bcast_bytes);
+ p_stats->common.tx_ucast_pkts +=
+ HILO_64_REGPAIR(pstats.sent_ucast_pkts);
+ p_stats->common.tx_mcast_pkts +=
+ HILO_64_REGPAIR(pstats.sent_mcast_pkts);
+ p_stats->common.tx_bcast_pkts +=
+ HILO_64_REGPAIR(pstats.sent_bcast_pkts);
+ p_stats->common.tx_err_drop_pkts +=
+ HILO_64_REGPAIR(pstats.error_drop_pkts);
}
static void __qed_get_vport_tstats(struct qed_hwfn *p_hwfn,
@@ -1502,10 +1506,10 @@ static void __qed_get_vport_tstats(struct qed_hwfn *p_hwfn,
memset(&tstats, 0, sizeof(tstats));
qed_memcpy_from(p_hwfn, p_ptt, &tstats, tstats_addr, tstats_len);
- p_stats->mftag_filter_discards +=
- HILO_64_REGPAIR(tstats.mftag_filter_discard);
- p_stats->mac_filter_discards +=
- HILO_64_REGPAIR(tstats.eth_mac_filter_discard);
+ p_stats->common.mftag_filter_discards +=
+ HILO_64_REGPAIR(tstats.mftag_filter_discard);
+ p_stats->common.mac_filter_discards +=
+ HILO_64_REGPAIR(tstats.eth_mac_filter_discard);
}
static void __qed_get_vport_ustats_addrlen(struct qed_hwfn *p_hwfn,
@@ -1539,12 +1543,15 @@ static void __qed_get_vport_ustats(struct qed_hwfn *p_hwfn,
memset(&ustats, 0, sizeof(ustats));
qed_memcpy_from(p_hwfn, p_ptt, &ustats, ustats_addr, ustats_len);
- p_stats->rx_ucast_bytes += HILO_64_REGPAIR(ustats.rcv_ucast_bytes);
- p_stats->rx_mcast_bytes += HILO_64_REGPAIR(ustats.rcv_mcast_bytes);
- p_stats->rx_bcast_bytes += HILO_64_REGPAIR(ustats.rcv_bcast_bytes);
- p_stats->rx_ucast_pkts += HILO_64_REGPAIR(ustats.rcv_ucast_pkts);
- p_stats->rx_mcast_pkts += HILO_64_REGPAIR(ustats.rcv_mcast_pkts);
- p_stats->rx_bcast_pkts += HILO_64_REGPAIR(ustats.rcv_bcast_pkts);
+ p_stats->common.rx_ucast_bytes +=
+ HILO_64_REGPAIR(ustats.rcv_ucast_bytes);
+ p_stats->common.rx_mcast_bytes +=
+ HILO_64_REGPAIR(ustats.rcv_mcast_bytes);
+ p_stats->common.rx_bcast_bytes +=
+ HILO_64_REGPAIR(ustats.rcv_bcast_bytes);
+ p_stats->common.rx_ucast_pkts += HILO_64_REGPAIR(ustats.rcv_ucast_pkts);
+ p_stats->common.rx_mcast_pkts += HILO_64_REGPAIR(ustats.rcv_mcast_pkts);
+ p_stats->common.rx_bcast_pkts += HILO_64_REGPAIR(ustats.rcv_bcast_pkts);
}
static void __qed_get_vport_mstats_addrlen(struct qed_hwfn *p_hwfn,
@@ -1578,23 +1585,26 @@ static void __qed_get_vport_mstats(struct qed_hwfn *p_hwfn,
memset(&mstats, 0, sizeof(mstats));
qed_memcpy_from(p_hwfn, p_ptt, &mstats, mstats_addr, mstats_len);
- p_stats->no_buff_discards += HILO_64_REGPAIR(mstats.no_buff_discard);
- p_stats->packet_too_big_discard +=
- HILO_64_REGPAIR(mstats.packet_too_big_discard);
- p_stats->ttl0_discard += HILO_64_REGPAIR(mstats.ttl0_discard);
- p_stats->tpa_coalesced_pkts +=
- HILO_64_REGPAIR(mstats.tpa_coalesced_pkts);
- p_stats->tpa_coalesced_events +=
- HILO_64_REGPAIR(mstats.tpa_coalesced_events);
- p_stats->tpa_aborts_num += HILO_64_REGPAIR(mstats.tpa_aborts_num);
- p_stats->tpa_coalesced_bytes +=
- HILO_64_REGPAIR(mstats.tpa_coalesced_bytes);
+ p_stats->common.no_buff_discards +=
+ HILO_64_REGPAIR(mstats.no_buff_discard);
+ p_stats->common.packet_too_big_discard +=
+ HILO_64_REGPAIR(mstats.packet_too_big_discard);
+ p_stats->common.ttl0_discard += HILO_64_REGPAIR(mstats.ttl0_discard);
+ p_stats->common.tpa_coalesced_pkts +=
+ HILO_64_REGPAIR(mstats.tpa_coalesced_pkts);
+ p_stats->common.tpa_coalesced_events +=
+ HILO_64_REGPAIR(mstats.tpa_coalesced_events);
+ p_stats->common.tpa_aborts_num +=
+ HILO_64_REGPAIR(mstats.tpa_aborts_num);
+ p_stats->common.tpa_coalesced_bytes +=
+ HILO_64_REGPAIR(mstats.tpa_coalesced_bytes);
}
static void __qed_get_vport_port_stats(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt,
struct qed_eth_stats *p_stats)
{
+ struct qed_eth_stats_common *p_common = &p_stats->common;
struct port_stats port_stats;
int j;
@@ -1605,54 +1615,75 @@ static void __qed_get_vport_port_stats(struct qed_hwfn *p_hwfn,
offsetof(struct public_port, stats),
sizeof(port_stats));
- p_stats->rx_64_byte_packets += port_stats.eth.r64;
- p_stats->rx_65_to_127_byte_packets += port_stats.eth.r127;
- p_stats->rx_128_to_255_byte_packets += port_stats.eth.r255;
- p_stats->rx_256_to_511_byte_packets += port_stats.eth.r511;
- p_stats->rx_512_to_1023_byte_packets += port_stats.eth.r1023;
- p_stats->rx_1024_to_1518_byte_packets += port_stats.eth.r1518;
- p_stats->rx_1519_to_1522_byte_packets += port_stats.eth.r1522;
- p_stats->rx_1519_to_2047_byte_packets += port_stats.eth.r2047;
- p_stats->rx_2048_to_4095_byte_packets += port_stats.eth.r4095;
- p_stats->rx_4096_to_9216_byte_packets += port_stats.eth.r9216;
- p_stats->rx_9217_to_16383_byte_packets += port_stats.eth.r16383;
- p_stats->rx_crc_errors += port_stats.eth.rfcs;
- p_stats->rx_mac_crtl_frames += port_stats.eth.rxcf;
- p_stats->rx_pause_frames += port_stats.eth.rxpf;
- p_stats->rx_pfc_frames += port_stats.eth.rxpp;
- p_stats->rx_align_errors += port_stats.eth.raln;
- p_stats->rx_carrier_errors += port_stats.eth.rfcr;
- p_stats->rx_oversize_packets += port_stats.eth.rovr;
- p_stats->rx_jabbers += port_stats.eth.rjbr;
- p_stats->rx_undersize_packets += port_stats.eth.rund;
- p_stats->rx_fragments += port_stats.eth.rfrg;
- p_stats->tx_64_byte_packets += port_stats.eth.t64;
- p_stats->tx_65_to_127_byte_packets += port_stats.eth.t127;
- p_stats->tx_128_to_255_byte_packets += port_stats.eth.t255;
- p_stats->tx_256_to_511_byte_packets += port_stats.eth.t511;
- p_stats->tx_512_to_1023_byte_packets += port_stats.eth.t1023;
- p_stats->tx_1024_to_1518_byte_packets += port_stats.eth.t1518;
- p_stats->tx_1519_to_2047_byte_packets += port_stats.eth.t2047;
- p_stats->tx_2048_to_4095_byte_packets += port_stats.eth.t4095;
- p_stats->tx_4096_to_9216_byte_packets += port_stats.eth.t9216;
- p_stats->tx_9217_to_16383_byte_packets += port_stats.eth.t16383;
- p_stats->tx_pause_frames += port_stats.eth.txpf;
- p_stats->tx_pfc_frames += port_stats.eth.txpp;
- p_stats->tx_lpi_entry_count += port_stats.eth.tlpiec;
- p_stats->tx_total_collisions += port_stats.eth.tncl;
- p_stats->rx_mac_bytes += port_stats.eth.rbyte;
- p_stats->rx_mac_uc_packets += port_stats.eth.rxuca;
- p_stats->rx_mac_mc_packets += port_stats.eth.rxmca;
- p_stats->rx_mac_bc_packets += port_stats.eth.rxbca;
- p_stats->rx_mac_frames_ok += port_stats.eth.rxpok;
- p_stats->tx_mac_bytes += port_stats.eth.tbyte;
- p_stats->tx_mac_uc_packets += port_stats.eth.txuca;
- p_stats->tx_mac_mc_packets += port_stats.eth.txmca;
- p_stats->tx_mac_bc_packets += port_stats.eth.txbca;
- p_stats->tx_mac_ctrl_frames += port_stats.eth.txcf;
+ p_common->rx_64_byte_packets += port_stats.eth.r64;
+ p_common->rx_65_to_127_byte_packets += port_stats.eth.r127;
+ p_common->rx_128_to_255_byte_packets += port_stats.eth.r255;
+ p_common->rx_256_to_511_byte_packets += port_stats.eth.r511;
+ p_common->rx_512_to_1023_byte_packets += port_stats.eth.r1023;
+ p_common->rx_1024_to_1518_byte_packets += port_stats.eth.r1518;
+ p_common->rx_crc_errors += port_stats.eth.rfcs;
+ p_common->rx_mac_crtl_frames += port_stats.eth.rxcf;
+ p_common->rx_pause_frames += port_stats.eth.rxpf;
+ p_common->rx_pfc_frames += port_stats.eth.rxpp;
+ p_common->rx_align_errors += port_stats.eth.raln;
+ p_common->rx_carrier_errors += port_stats.eth.rfcr;
+ p_common->rx_oversize_packets += port_stats.eth.rovr;
+ p_common->rx_jabbers += port_stats.eth.rjbr;
+ p_common->rx_undersize_packets += port_stats.eth.rund;
+ p_common->rx_fragments += port_stats.eth.rfrg;
+ p_common->tx_64_byte_packets += port_stats.eth.t64;
+ p_common->tx_65_to_127_byte_packets += port_stats.eth.t127;
+ p_common->tx_128_to_255_byte_packets += port_stats.eth.t255;
+ p_common->tx_256_to_511_byte_packets += port_stats.eth.t511;
+ p_common->tx_512_to_1023_byte_packets += port_stats.eth.t1023;
+ p_common->tx_1024_to_1518_byte_packets += port_stats.eth.t1518;
+ p_common->tx_pause_frames += port_stats.eth.txpf;
+ p_common->tx_pfc_frames += port_stats.eth.txpp;
+ p_common->rx_mac_bytes += port_stats.eth.rbyte;
+ p_common->rx_mac_uc_packets += port_stats.eth.rxuca;
+ p_common->rx_mac_mc_packets += port_stats.eth.rxmca;
+ p_common->rx_mac_bc_packets += port_stats.eth.rxbca;
+ p_common->rx_mac_frames_ok += port_stats.eth.rxpok;
+ p_common->tx_mac_bytes += port_stats.eth.tbyte;
+ p_common->tx_mac_uc_packets += port_stats.eth.txuca;
+ p_common->tx_mac_mc_packets += port_stats.eth.txmca;
+ p_common->tx_mac_bc_packets += port_stats.eth.txbca;
+ p_common->tx_mac_ctrl_frames += port_stats.eth.txcf;
for (j = 0; j < 8; j++) {
- p_stats->brb_truncates += port_stats.brb.brb_truncate[j];
- p_stats->brb_discards += port_stats.brb.brb_discard[j];
+ p_common->brb_truncates += port_stats.brb.brb_truncate[j];
+ p_common->brb_discards += port_stats.brb.brb_discard[j];
+ }
+
+ if (QED_IS_BB(p_hwfn->cdev)) {
+ struct qed_eth_stats_bb *p_bb = &p_stats->bb;
+
+ p_bb->rx_1519_to_1522_byte_packets +=
+ port_stats.eth.u0.bb0.r1522;
+ p_bb->rx_1519_to_2047_byte_packets +=
+ port_stats.eth.u0.bb0.r2047;
+ p_bb->rx_2048_to_4095_byte_packets +=
+ port_stats.eth.u0.bb0.r4095;
+ p_bb->rx_4096_to_9216_byte_packets +=
+ port_stats.eth.u0.bb0.r9216;
+ p_bb->rx_9217_to_16383_byte_packets +=
+ port_stats.eth.u0.bb0.r16383;
+ p_bb->tx_1519_to_2047_byte_packets +=
+ port_stats.eth.u1.bb1.t2047;
+ p_bb->tx_2048_to_4095_byte_packets +=
+ port_stats.eth.u1.bb1.t4095;
+ p_bb->tx_4096_to_9216_byte_packets +=
+ port_stats.eth.u1.bb1.t9216;
+ p_bb->tx_9217_to_16383_byte_packets +=
+ port_stats.eth.u1.bb1.t16383;
+ p_bb->tx_lpi_entry_count += port_stats.eth.u2.bb2.tlpiec;
+ p_bb->tx_total_collisions += port_stats.eth.u2.bb2.tncl;
+ } else {
+ struct qed_eth_stats_ah *p_ah = &p_stats->ah;
+
+ p_ah->rx_1519_to_max_byte_packets +=
+ port_stats.eth.u0.ah0.r1519_to_max;
+ p_ah->tx_1519_to_max_byte_packets =
+ port_stats.eth.u1.ah1.t1519_to_max;
}
}
@@ -1898,7 +1929,11 @@ static int qed_start_vport(struct qed_dev *cdev,
return rc;
}
- qed_hw_start_fastpath(p_hwfn);
+ rc = qed_hw_start_fastpath(p_hwfn);
+ if (rc) {
+ DP_ERR(cdev, "Failed to start VPORT fastpath\n");
+ return rc;
+ }
DP_VERBOSE(cdev, (QED_MSG_SPQ | NETIF_MSG_IFUP),
"Started V-PORT %d with MTU %d\n",
@@ -2141,7 +2176,13 @@ static int qed_start_txq(struct qed_dev *cdev,
#define QED_HW_STOP_RETRY_LIMIT (10)
static int qed_fastpath_stop(struct qed_dev *cdev)
{
- qed_hw_stop_fastpath(cdev);
+ int rc;
+
+ rc = qed_hw_stop_fastpath(cdev);
+ if (rc) {
+ DP_ERR(cdev, "Failed to stop Fastpath\n");
+ return rc;
+ }
return 0;
}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index 9a0b9af..09c8641 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -211,6 +211,8 @@ static void qed_ll2b_complete_rx_packet(struct qed_hwfn *p_hwfn,
/* If need to reuse or there's no replacement buffer, repost this */
if (rc)
goto out_post;
+ dma_unmap_single(&cdev->pdev->dev, buffer->phys_addr,
+ cdev->ll2->rx_size, DMA_FROM_DEVICE);
skb = build_skb(buffer->data, 0);
if (!skb) {
@@ -474,7 +476,7 @@ qed_ll2_rxq_completion_gsi(struct qed_hwfn *p_hwfn,
static int qed_ll2_rxq_completion_reg(struct qed_hwfn *p_hwfn,
struct qed_ll2_info *p_ll2_conn,
union core_rx_cqe_union *p_cqe,
- unsigned long lock_flags,
+ unsigned long *p_lock_flags,
bool b_last_cqe)
{
struct qed_ll2_rx_queue *p_rx = &p_ll2_conn->rx_queue;
@@ -495,10 +497,10 @@ static int qed_ll2_rxq_completion_reg(struct qed_hwfn *p_hwfn,
"Mismatch between active_descq and the LL2 Rx chain\n");
list_add_tail(&p_pkt->list_entry, &p_rx->free_descq);
- spin_unlock_irqrestore(&p_rx->lock, lock_flags);
+ spin_unlock_irqrestore(&p_rx->lock, *p_lock_flags);
qed_ll2b_complete_rx_packet(p_hwfn, p_ll2_conn->my_id,
p_pkt, &p_cqe->rx_cqe_fp, b_last_cqe);
- spin_lock_irqsave(&p_rx->lock, lock_flags);
+ spin_lock_irqsave(&p_rx->lock, *p_lock_flags);
return 0;
}
@@ -538,7 +540,8 @@ static int qed_ll2_rxq_completion(struct qed_hwfn *p_hwfn, void *cookie)
break;
case CORE_RX_CQE_TYPE_REGULAR:
rc = qed_ll2_rxq_completion_reg(p_hwfn, p_ll2_conn,
- cqe, flags, b_last_cqe);
+ cqe, &flags,
+ b_last_cqe);
break;
default:
rc = -EIO;
@@ -594,7 +597,7 @@ static u8 qed_ll2_convert_rx_parse_to_tx_flags(u16 parse_flags)
u8 bd_flags = 0;
if (GET_FIELD(parse_flags, PARSING_AND_ERR_FLAGS_TAG8021QEXIST))
- SET_FIELD(bd_flags, CORE_TX_BD_FLAGS_VLAN_INSERTION, 1);
+ SET_FIELD(bd_flags, CORE_TX_BD_DATA_VLAN_INSERTION, 1);
return bd_flags;
}
@@ -755,8 +758,8 @@ qed_ooo_submit_tx_buffers(struct qed_hwfn *p_hwfn,
p_buffer->placement_offset;
parse_flags = p_buffer->parse_flags;
bd_flags = qed_ll2_convert_rx_parse_to_tx_flags(parse_flags);
- SET_FIELD(bd_flags, CORE_TX_BD_FLAGS_FORCE_VLAN_MODE, 1);
- SET_FIELD(bd_flags, CORE_TX_BD_FLAGS_L4_PROTOCOL, 1);
+ SET_FIELD(bd_flags, CORE_TX_BD_DATA_FORCE_VLAN_MODE, 1);
+ SET_FIELD(bd_flags, CORE_TX_BD_DATA_L4_PROTOCOL, 1);
rc = qed_ll2_prepare_tx_packet(p_hwfn, p_ll2_conn->my_id, 1,
p_buffer->vlan, bd_flags,
@@ -968,7 +971,7 @@ static int qed_ll2_start_ooo(struct qed_dev *cdev,
{
struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
u8 *handle = &hwfn->pf_params.iscsi_pf_params.ll2_ooo_queue_id;
- struct qed_ll2_conn ll2_info;
+ struct qed_ll2_conn ll2_info = { 0 };
int rc;
ll2_info.conn_type = QED_LL2_TYPE_ISCSI_OOO;
@@ -1087,7 +1090,6 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn,
struct core_tx_start_ramrod_data *p_ramrod = NULL;
struct qed_spq_entry *p_ent = NULL;
struct qed_sp_init_data init_data;
- union qed_qm_pq_params pq_params;
u16 pq_id = 0, pbl_size;
int rc = -EINVAL;
@@ -1124,9 +1126,18 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn,
pbl_size = qed_chain_get_page_cnt(&p_tx->txq_chain);
p_ramrod->pbl_size = cpu_to_le16(pbl_size);
- memset(&pq_params, 0, sizeof(pq_params));
- pq_params.core.tc = p_ll2_conn->conn.tx_tc;
- pq_id = qed_get_qm_pq(p_hwfn, PROTOCOLID_CORE, &pq_params);
+ switch (p_ll2_conn->conn.tx_tc) {
+ case LB_TC:
+ pq_id = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_LB);
+ break;
+ case OOO_LB_TC:
+ pq_id = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OOO);
+ break;
+ default:
+ pq_id = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
+ break;
+ }
+
p_ramrod->qm_pq_id = cpu_to_le16(pq_id);
switch (conn_type) {
@@ -1397,13 +1408,21 @@ int qed_ll2_establish_connection(struct qed_hwfn *p_hwfn, u8 connection_handle)
struct qed_ll2_info *p_ll2_conn;
struct qed_ll2_rx_queue *p_rx;
struct qed_ll2_tx_queue *p_tx;
+ struct qed_ptt *p_ptt;
int rc = -EINVAL;
u32 i, capacity;
u8 qid;
+ p_ptt = qed_ptt_acquire(p_hwfn);
+ if (!p_ptt)
+ return -EAGAIN;
+
p_ll2_conn = qed_ll2_handle_sanity_lock(p_hwfn, connection_handle);
- if (!p_ll2_conn)
- return -EINVAL;
+ if (!p_ll2_conn) {
+ rc = -EINVAL;
+ goto out;
+ }
+
p_rx = &p_ll2_conn->rx_queue;
p_tx = &p_ll2_conn->tx_queue;
@@ -1436,7 +1455,9 @@ int qed_ll2_establish_connection(struct qed_hwfn *p_hwfn, u8 connection_handle)
p_tx->cur_completing_frag_num = 0;
*p_tx->p_fw_cons = 0;
- qed_cxt_acquire_cid(p_hwfn, PROTOCOLID_CORE, &p_ll2_conn->cid);
+ rc = qed_cxt_acquire_cid(p_hwfn, PROTOCOLID_CORE, &p_ll2_conn->cid);
+ if (rc)
+ goto out;
qid = p_hwfn->hw_info.resc_start[QED_LL2_QUEUE] + connection_handle;
p_ll2_conn->queue_id = qid;
@@ -1450,26 +1471,28 @@ int qed_ll2_establish_connection(struct qed_hwfn *p_hwfn, u8 connection_handle)
rc = qed_ll2_establish_connection_rx(p_hwfn, p_ll2_conn);
if (rc)
- return rc;
+ goto out;
rc = qed_sp_ll2_tx_queue_start(p_hwfn, p_ll2_conn);
if (rc)
- return rc;
+ goto out;
if (p_hwfn->hw_info.personality != QED_PCI_ETH_ROCE)
- qed_wr(p_hwfn, p_hwfn->p_main_ptt, PRS_REG_USE_LIGHT_L2, 1);
+ qed_wr(p_hwfn, p_ptt, PRS_REG_USE_LIGHT_L2, 1);
qed_ll2_establish_connection_ooo(p_hwfn, p_ll2_conn);
if (p_ll2_conn->conn.conn_type == QED_LL2_TYPE_FCOE) {
- qed_llh_add_protocol_filter(p_hwfn, p_hwfn->p_main_ptt,
+ qed_llh_add_protocol_filter(p_hwfn, p_ptt,
0x8906, 0,
QED_LLH_FILTER_ETHERTYPE);
- qed_llh_add_protocol_filter(p_hwfn, p_hwfn->p_main_ptt,
+ qed_llh_add_protocol_filter(p_hwfn, p_ptt,
0x8914, 0,
QED_LLH_FILTER_ETHERTYPE);
}
+out:
+ qed_ptt_release(p_hwfn, p_ptt);
return rc;
}
@@ -1588,33 +1611,34 @@ static void qed_ll2_prepare_tx_packet_set(struct qed_hwfn *p_hwfn,
p_tx->cur_send_frag_num++;
}
-static void qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn,
- struct qed_ll2_info *p_ll2,
- struct qed_ll2_tx_packet *p_curp,
- u8 num_of_bds,
- enum core_tx_dest tx_dest,
- u16 vlan,
- u8 bd_flags,
- u16 l4_hdr_offset_w,
- enum core_roce_flavor_type type,
- dma_addr_t first_frag,
- u16 first_frag_len)
+static void
+qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn,
+ struct qed_ll2_info *p_ll2,
+ struct qed_ll2_tx_packet *p_curp,
+ u8 num_of_bds,
+ enum core_tx_dest tx_dest,
+ u16 vlan,
+ u8 bd_flags,
+ u16 l4_hdr_offset_w,
+ enum core_roce_flavor_type roce_flavor,
+ dma_addr_t first_frag,
+ u16 first_frag_len)
{
struct qed_chain *p_tx_chain = &p_ll2->tx_queue.txq_chain;
u16 prod_idx = qed_chain_get_prod_idx(p_tx_chain);
struct core_tx_bd *start_bd = NULL;
- u16 frag_idx;
+ u16 bd_data = 0, frag_idx;
start_bd = (struct core_tx_bd *)qed_chain_produce(p_tx_chain);
start_bd->nw_vlan_or_lb_echo = cpu_to_le16(vlan);
SET_FIELD(start_bd->bitfield1, CORE_TX_BD_L4_HDR_OFFSET_W,
cpu_to_le16(l4_hdr_offset_w));
SET_FIELD(start_bd->bitfield1, CORE_TX_BD_TX_DST, tx_dest);
- start_bd->bd_flags.as_bitfield = bd_flags;
- start_bd->bd_flags.as_bitfield |= CORE_TX_BD_FLAGS_START_BD_MASK <<
- CORE_TX_BD_FLAGS_START_BD_SHIFT;
- SET_FIELD(start_bd->bitfield0, CORE_TX_BD_NBDS, num_of_bds);
- SET_FIELD(start_bd->bitfield0, CORE_TX_BD_ROCE_FLAV, type);
+ bd_data |= bd_flags;
+ SET_FIELD(bd_data, CORE_TX_BD_DATA_START_BD, 0x1);
+ SET_FIELD(bd_data, CORE_TX_BD_DATA_NBDS, num_of_bds);
+ SET_FIELD(bd_data, CORE_TX_BD_DATA_ROCE_FLAV, roce_flavor);
+ start_bd->bd_data.as_bitfield = cpu_to_le16(bd_data);
DMA_REGPAIR_LE(start_bd->addr, first_frag);
start_bd->nbytes = cpu_to_le16(first_frag_len);
@@ -1639,9 +1663,8 @@ static void qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn,
struct core_tx_bd **p_bd = &p_curp->bds_set[frag_idx].txq_bd;
*p_bd = (struct core_tx_bd *)qed_chain_produce(p_tx_chain);
- (*p_bd)->bd_flags.as_bitfield = 0;
+ (*p_bd)->bd_data.as_bitfield = 0;
(*p_bd)->bitfield1 = 0;
- (*p_bd)->bitfield0 = 0;
p_curp->bds_set[frag_idx].tx_frag = 0;
p_curp->bds_set[frag_idx].frag_len = 0;
}
@@ -1820,23 +1843,30 @@ int qed_ll2_terminate_connection(struct qed_hwfn *p_hwfn, u8 connection_handle)
{
struct qed_ll2_info *p_ll2_conn = NULL;
int rc = -EINVAL;
+ struct qed_ptt *p_ptt;
+
+ p_ptt = qed_ptt_acquire(p_hwfn);
+ if (!p_ptt)
+ return -EAGAIN;
p_ll2_conn = qed_ll2_handle_sanity_lock(p_hwfn, connection_handle);
- if (!p_ll2_conn)
- return -EINVAL;
+ if (!p_ll2_conn) {
+ rc = -EINVAL;
+ goto out;
+ }
/* Stop Tx & Rx of connection, if needed */
if (QED_LL2_TX_REGISTERED(p_ll2_conn)) {
rc = qed_sp_ll2_tx_queue_stop(p_hwfn, p_ll2_conn);
if (rc)
- return rc;
+ goto out;
qed_ll2_txq_flush(p_hwfn, connection_handle);
}
if (QED_LL2_RX_REGISTERED(p_ll2_conn)) {
rc = qed_sp_ll2_rx_queue_stop(p_hwfn, p_ll2_conn);
if (rc)
- return rc;
+ goto out;
qed_ll2_rxq_flush(p_hwfn, connection_handle);
}
@@ -1844,14 +1874,16 @@ int qed_ll2_terminate_connection(struct qed_hwfn *p_hwfn, u8 connection_handle)
qed_ooo_release_all_isles(p_hwfn, p_hwfn->p_ooo_info);
if (p_ll2_conn->conn.conn_type == QED_LL2_TYPE_FCOE) {
- qed_llh_remove_protocol_filter(p_hwfn, p_hwfn->p_main_ptt,
+ qed_llh_remove_protocol_filter(p_hwfn, p_ptt,
0x8906, 0,
QED_LLH_FILTER_ETHERTYPE);
- qed_llh_remove_protocol_filter(p_hwfn, p_hwfn->p_main_ptt,
+ qed_llh_remove_protocol_filter(p_hwfn, p_ptt,
0x8914, 0,
QED_LLH_FILTER_ETHERTYPE);
}
+out:
+ qed_ptt_release(p_hwfn, p_ptt);
return rc;
}
@@ -2238,11 +2270,11 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb)
/* Request HW to calculate IP csum */
if (!((vlan_get_protocol(skb) == htons(ETH_P_IPV6)) &&
ipv6_hdr(skb)->nexthdr == NEXTHDR_IPV6))
- flags |= BIT(CORE_TX_BD_FLAGS_IP_CSUM_SHIFT);
+ flags |= BIT(CORE_TX_BD_DATA_IP_CSUM_SHIFT);
if (skb_vlan_tag_present(skb)) {
vlan = skb_vlan_tag_get(skb);
- flags |= BIT(CORE_TX_BD_FLAGS_VLAN_INSERTION_SHIFT);
+ flags |= BIT(CORE_TX_BD_DATA_VLAN_INSERTION_SHIFT);
}
rc = qed_ll2_prepare_tx_packet(QED_LEADING_HWFN(cdev),
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index eef30a5..029f431 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -45,6 +45,7 @@
#include <linux/ethtool.h>
#include <linux/etherdevice.h>
#include <linux/vmalloc.h>
+#include <linux/crash_dump.h>
#include <linux/qed/qed_if.h>
#include <linux/qed/qed_ll2_if.h>
@@ -54,6 +55,8 @@
#include "qed_dev_api.h"
#include "qed_ll2.h"
#include "qed_fcoe.h"
+#include "qed_iscsi.h"
+
#include "qed_mcp.h"
#include "qed_hw.h"
#include "qed_selftest.h"
@@ -238,6 +241,7 @@ int qed_fill_dev_info(struct qed_dev *cdev,
dev_info->rdma_supported = (cdev->hwfns[0].hw_info.personality ==
QED_PCI_ETH_ROCE);
dev_info->is_mf_default = IS_MF_DEFAULT(&cdev->hwfns[0]);
+ dev_info->dev_type = cdev->type;
ether_addr_copy(dev_info->hw_mac, cdev->hwfns[0].hw_info.hw_mac_addr);
if (IS_PF(cdev)) {
@@ -588,6 +592,19 @@ int qed_slowpath_irq_req(struct qed_hwfn *hwfn)
return rc;
}
+void qed_slowpath_irq_sync(struct qed_hwfn *p_hwfn)
+{
+ struct qed_dev *cdev = p_hwfn->cdev;
+ u8 id = p_hwfn->my_id;
+ u32 int_mode;
+
+ int_mode = cdev->int_params.out.int_mode;
+ if (int_mode == QED_INT_MODE_MSIX)
+ synchronize_irq(cdev->int_params.msix_table[id].vector);
+ else
+ synchronize_irq(cdev->pdev->irq);
+}
+
static void qed_slowpath_irq_free(struct qed_dev *cdev)
{
int i;
@@ -630,19 +647,6 @@ static int qed_nic_stop(struct qed_dev *cdev)
return rc;
}
-static int qed_nic_reset(struct qed_dev *cdev)
-{
- int rc;
-
- rc = qed_hw_reset(cdev);
- if (rc)
- return rc;
-
- qed_resc_free(cdev);
-
- return 0;
-}
-
static int qed_nic_setup(struct qed_dev *cdev)
{
int rc, i;
@@ -743,7 +747,8 @@ static int qed_slowpath_setup_int(struct qed_dev *cdev,
cdev->int_params.fp_msix_cnt = cdev->int_params.out.num_vectors -
cdev->num_hwfns;
- if (!IS_ENABLED(CONFIG_QED_RDMA))
+ if (!IS_ENABLED(CONFIG_QED_RDMA) ||
+ QED_LEADING_HWFN(cdev)->hw_info.personality != QED_PCI_ETH_ROCE)
return 0;
for_each_hwfn(cdev, i)
@@ -875,7 +880,6 @@ static void qed_update_pf_params(struct qed_dev *cdev,
params->rdma_pf_params.num_qps = QED_ROCE_QPS;
params->rdma_pf_params.min_dpis = QED_ROCE_DPIS;
/* divide by 3 the MRs to avoid MF ILT overflow */
- params->rdma_pf_params.num_mrs = RDMA_MAX_TIDS;
params->rdma_pf_params.gl_pi = QED_ROCE_PROTOCOL_INDEX;
}
@@ -900,6 +904,8 @@ static void qed_update_pf_params(struct qed_dev *cdev,
static int qed_slowpath_start(struct qed_dev *cdev,
struct qed_slowpath_params *params)
{
+ struct qed_drv_load_params drv_load_params;
+ struct qed_hw_init_params hw_init_params;
struct qed_tunn_start_params tunn_info;
struct qed_mcp_drv_version drv_version;
const u8 *data = NULL;
@@ -965,9 +971,21 @@ static int qed_slowpath_start(struct qed_dev *cdev,
tunn_info.tunn_clss_ipgre = QED_TUNN_CLSS_MAC_VLAN;
/* Start the slowpath */
- rc = qed_hw_init(cdev, &tunn_info, true,
- cdev->int_params.out.int_mode,
- true, data);
+ memset(&hw_init_params, 0, sizeof(hw_init_params));
+ hw_init_params.p_tunn = &tunn_info;
+ hw_init_params.b_hw_start = true;
+ hw_init_params.int_mode = cdev->int_params.out.int_mode;
+ hw_init_params.allow_npar_tx_switch = true;
+ hw_init_params.bin_fw_data = data;
+
+ memset(&drv_load_params, 0, sizeof(drv_load_params));
+ drv_load_params.is_crash_kernel = is_kdump_kernel();
+ drv_load_params.mfw_timeout_val = QED_LOAD_REQ_LOCK_TO_DEFAULT;
+ drv_load_params.avoid_eng_reset = false;
+ drv_load_params.override_force_load = QED_OVERRIDE_FORCE_LOAD_NONE;
+ hw_init_params.p_drv_load_params = &drv_load_params;
+
+ rc = qed_hw_init(cdev, &hw_init_params);
if (rc)
goto err2;
@@ -1042,7 +1060,8 @@ static int qed_slowpath_stop(struct qed_dev *cdev)
}
qed_disable_msix(cdev);
- qed_nic_reset(cdev);
+
+ qed_resc_free(cdev);
qed_iov_wq_stop(cdev, true);
@@ -1653,13 +1672,18 @@ void qed_get_protocol_stats(struct qed_dev *cdev,
switch (type) {
case QED_MCP_LAN_STATS:
qed_get_vport_stats(cdev, ð_stats);
- stats->lan_stats.ucast_rx_pkts = eth_stats.rx_ucast_pkts;
- stats->lan_stats.ucast_tx_pkts = eth_stats.tx_ucast_pkts;
+ stats->lan_stats.ucast_rx_pkts =
+ eth_stats.common.rx_ucast_pkts;
+ stats->lan_stats.ucast_tx_pkts =
+ eth_stats.common.tx_ucast_pkts;
stats->lan_stats.fcs_err = -1;
break;
case QED_MCP_FCOE_STATS:
qed_get_protocol_stats_fcoe(cdev, &stats->fcoe_stats);
break;
+ case QED_MCP_ISCSI_STATS:
+ qed_get_protocol_stats_iscsi(cdev, &stats->iscsi_stats);
+ break;
default:
DP_ERR(cdev, "Invalid protocol type = %d\n", type);
return;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index 87fde20..ff6080d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -111,12 +111,71 @@ void qed_mcp_read_mb(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
}
}
+struct qed_mcp_cmd_elem {
+ struct list_head list;
+ struct qed_mcp_mb_params *p_mb_params;
+ u16 expected_seq_num;
+ bool b_is_completed;
+};
+
+/* Must be called while cmd_lock is acquired */
+static struct qed_mcp_cmd_elem *
+qed_mcp_cmd_add_elem(struct qed_hwfn *p_hwfn,
+ struct qed_mcp_mb_params *p_mb_params,
+ u16 expected_seq_num)
+{
+ struct qed_mcp_cmd_elem *p_cmd_elem = NULL;
+
+ p_cmd_elem = kzalloc(sizeof(*p_cmd_elem), GFP_ATOMIC);
+ if (!p_cmd_elem)
+ goto out;
+
+ p_cmd_elem->p_mb_params = p_mb_params;
+ p_cmd_elem->expected_seq_num = expected_seq_num;
+ list_add(&p_cmd_elem->list, &p_hwfn->mcp_info->cmd_list);
+out:
+ return p_cmd_elem;
+}
+
+/* Must be called while cmd_lock is acquired */
+static void qed_mcp_cmd_del_elem(struct qed_hwfn *p_hwfn,
+ struct qed_mcp_cmd_elem *p_cmd_elem)
+{
+ list_del(&p_cmd_elem->list);
+ kfree(p_cmd_elem);
+}
+
+/* Must be called while cmd_lock is acquired */
+static struct qed_mcp_cmd_elem *qed_mcp_cmd_get_elem(struct qed_hwfn *p_hwfn,
+ u16 seq_num)
+{
+ struct qed_mcp_cmd_elem *p_cmd_elem = NULL;
+
+ list_for_each_entry(p_cmd_elem, &p_hwfn->mcp_info->cmd_list, list) {
+ if (p_cmd_elem->expected_seq_num == seq_num)
+ return p_cmd_elem;
+ }
+
+ return NULL;
+}
+
int qed_mcp_free(struct qed_hwfn *p_hwfn)
{
if (p_hwfn->mcp_info) {
+ struct qed_mcp_cmd_elem *p_cmd_elem, *p_tmp;
+
kfree(p_hwfn->mcp_info->mfw_mb_cur);
kfree(p_hwfn->mcp_info->mfw_mb_shadow);
+
+ spin_lock_bh(&p_hwfn->mcp_info->cmd_lock);
+ list_for_each_entry_safe(p_cmd_elem,
+ p_tmp,
+ &p_hwfn->mcp_info->cmd_list, list) {
+ qed_mcp_cmd_del_elem(p_hwfn, p_cmd_elem);
+ }
+ spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
}
+
kfree(p_hwfn->mcp_info);
return 0;
@@ -160,7 +219,7 @@ static int qed_load_mcp_offsets(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
p_info->drv_pulse_seq = DRV_MB_RD(p_hwfn, p_ptt, drv_pulse_mb) &
DRV_PULSE_SEQ_MASK;
- p_info->mcp_hist = (u16)qed_rd(p_hwfn, p_ptt, MISCS_REG_GENERIC_POR_0);
+ p_info->mcp_hist = qed_rd(p_hwfn, p_ptt, MISCS_REG_GENERIC_POR_0);
return 0;
}
@@ -176,6 +235,12 @@ int qed_mcp_cmd_init(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
goto err;
p_info = p_hwfn->mcp_info;
+ /* Initialize the MFW spinlock */
+ spin_lock_init(&p_info->cmd_lock);
+ spin_lock_init(&p_info->link_lock);
+
+ INIT_LIST_HEAD(&p_info->cmd_list);
+
if (qed_load_mcp_offsets(p_hwfn, p_ptt) != 0) {
DP_NOTICE(p_hwfn, "MCP is not initialized\n");
/* Do not free mcp_info here, since public_base indicate that
@@ -190,10 +255,6 @@ int qed_mcp_cmd_init(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
if (!p_info->mfw_mb_shadow || !p_info->mfw_mb_addr)
goto err;
- /* Initialize the MFW spinlock */
- spin_lock_init(&p_info->lock);
- spin_lock_init(&p_info->link_lock);
-
return 0;
err:
@@ -201,68 +262,39 @@ int qed_mcp_cmd_init(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
return -ENOMEM;
}
-/* Locks the MFW mailbox of a PF to ensure a single access.
- * The lock is achieved in most cases by holding a spinlock, causing other
- * threads to wait till a previous access is done.
- * In some cases (currently when a [UN]LOAD_REQ commands are sent), the single
- * access is achieved by setting a blocking flag, which will fail other
- * competing contexts to send their mailboxes.
- */
-static int qed_mcp_mb_lock(struct qed_hwfn *p_hwfn, u32 cmd)
+static void qed_mcp_reread_offsets(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt)
{
- spin_lock_bh(&p_hwfn->mcp_info->lock);
+ u32 generic_por_0 = qed_rd(p_hwfn, p_ptt, MISCS_REG_GENERIC_POR_0);
- /* The spinlock shouldn't be acquired when the mailbox command is
- * [UN]LOAD_REQ, since the engine is locked by the MFW, and a parallel
- * pending [UN]LOAD_REQ command of another PF together with a spinlock
- * (i.e. interrupts are disabled) - can lead to a deadlock.
- * It is assumed that for a single PF, no other mailbox commands can be
- * sent from another context while sending LOAD_REQ, and that any
- * parallel commands to UNLOAD_REQ can be cancelled.
+ /* Use MCP history register to check if MCP reset occurred between init
+ * time and now.
*/
- if (cmd == DRV_MSG_CODE_LOAD_DONE || cmd == DRV_MSG_CODE_UNLOAD_DONE)
- p_hwfn->mcp_info->block_mb_sending = false;
+ if (p_hwfn->mcp_info->mcp_hist != generic_por_0) {
+ DP_VERBOSE(p_hwfn,
+ QED_MSG_SP,
+ "Rereading MCP offsets [mcp_hist 0x%08x, generic_por_0 0x%08x]\n",
+ p_hwfn->mcp_info->mcp_hist, generic_por_0);
- if (p_hwfn->mcp_info->block_mb_sending) {
- DP_NOTICE(p_hwfn,
- "Trying to send a MFW mailbox command [0x%x] in parallel to [UN]LOAD_REQ. Aborting.\n",
- cmd);
- spin_unlock_bh(&p_hwfn->mcp_info->lock);
- return -EBUSY;
+ qed_load_mcp_offsets(p_hwfn, p_ptt);
+ qed_mcp_cmd_port_init(p_hwfn, p_ptt);
}
-
- if (cmd == DRV_MSG_CODE_LOAD_REQ || cmd == DRV_MSG_CODE_UNLOAD_REQ) {
- p_hwfn->mcp_info->block_mb_sending = true;
- spin_unlock_bh(&p_hwfn->mcp_info->lock);
- }
-
- return 0;
-}
-
-static void qed_mcp_mb_unlock(struct qed_hwfn *p_hwfn, u32 cmd)
-{
- if (cmd != DRV_MSG_CODE_LOAD_REQ && cmd != DRV_MSG_CODE_UNLOAD_REQ)
- spin_unlock_bh(&p_hwfn->mcp_info->lock);
}
int qed_mcp_reset(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
{
- u32 seq = ++p_hwfn->mcp_info->drv_mb_seq;
- u8 delay = CHIP_MCP_RESP_ITER_US;
- u32 org_mcp_reset_seq, cnt = 0;
+ u32 org_mcp_reset_seq, seq, delay = CHIP_MCP_RESP_ITER_US, cnt = 0;
int rc = 0;
- /* Ensure that only a single thread is accessing the mailbox at a
- * certain time.
- */
- rc = qed_mcp_mb_lock(p_hwfn, DRV_MSG_CODE_MCP_RESET);
- if (rc != 0)
- return rc;
+ /* Ensure that only a single thread is accessing the mailbox */
+ spin_lock_bh(&p_hwfn->mcp_info->cmd_lock);
+
+ org_mcp_reset_seq = qed_rd(p_hwfn, p_ptt, MISCS_REG_GENERIC_POR_0);
/* Set drv command along with the updated sequence */
- org_mcp_reset_seq = qed_rd(p_hwfn, p_ptt, MISCS_REG_GENERIC_POR_0);
- DRV_MB_WR(p_hwfn, p_ptt, drv_mb_header,
- (DRV_MSG_CODE_MCP_RESET | seq));
+ qed_mcp_reread_offsets(p_hwfn, p_ptt);
+ seq = ++p_hwfn->mcp_info->drv_mb_seq;
+ DRV_MB_WR(p_hwfn, p_ptt, drv_mb_header, (DRV_MSG_CODE_MCP_RESET | seq));
do {
/* Wait for MFW response */
@@ -281,72 +313,207 @@ int qed_mcp_reset(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
rc = -EAGAIN;
}
- qed_mcp_mb_unlock(p_hwfn, DRV_MSG_CODE_MCP_RESET);
+ spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
return rc;
}
-static int qed_do_mcp_cmd(struct qed_hwfn *p_hwfn,
- struct qed_ptt *p_ptt,
- u32 cmd,
- u32 param,
- u32 *o_mcp_resp,
- u32 *o_mcp_param)
+/* Must be called while cmd_lock is acquired */
+static bool qed_mcp_has_pending_cmd(struct qed_hwfn *p_hwfn)
{
- u8 delay = CHIP_MCP_RESP_ITER_US;
- u32 seq, cnt = 1, actual_mb_seq;
+ struct qed_mcp_cmd_elem *p_cmd_elem;
+
+ /* There is at most one pending command at a certain time, and if it
+ * exists - it is placed at the HEAD of the list.
+ */
+ if (!list_empty(&p_hwfn->mcp_info->cmd_list)) {
+ p_cmd_elem = list_first_entry(&p_hwfn->mcp_info->cmd_list,
+ struct qed_mcp_cmd_elem, list);
+ return !p_cmd_elem->b_is_completed;
+ }
+
+ return false;
+}
+
+/* Must be called while cmd_lock is acquired */
+static int
+qed_mcp_update_pending_cmd(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+ struct qed_mcp_mb_params *p_mb_params;
+ struct qed_mcp_cmd_elem *p_cmd_elem;
+ u32 mcp_resp;
+ u16 seq_num;
+
+ mcp_resp = DRV_MB_RD(p_hwfn, p_ptt, fw_mb_header);
+ seq_num = (u16)(mcp_resp & FW_MSG_SEQ_NUMBER_MASK);
+
+ /* Return if no new non-handled response has been received */
+ if (seq_num != p_hwfn->mcp_info->drv_mb_seq)
+ return -EAGAIN;
+
+ p_cmd_elem = qed_mcp_cmd_get_elem(p_hwfn, seq_num);
+ if (!p_cmd_elem) {
+ DP_ERR(p_hwfn,
+ "Failed to find a pending mailbox cmd that expects sequence number %d\n",
+ seq_num);
+ return -EINVAL;
+ }
+
+ p_mb_params = p_cmd_elem->p_mb_params;
+
+ /* Get the MFW response along with the sequence number */
+ p_mb_params->mcp_resp = mcp_resp;
+
+ /* Get the MFW param */
+ p_mb_params->mcp_param = DRV_MB_RD(p_hwfn, p_ptt, fw_mb_param);
+
+ /* Get the union data */
+ if (p_mb_params->p_data_dst != NULL && p_mb_params->data_dst_size) {
+ u32 union_data_addr = p_hwfn->mcp_info->drv_mb_addr +
+ offsetof(struct public_drv_mb,
+ union_data);
+ qed_memcpy_from(p_hwfn, p_ptt, p_mb_params->p_data_dst,
+ union_data_addr, p_mb_params->data_dst_size);
+ }
+
+ p_cmd_elem->b_is_completed = true;
+
+ return 0;
+}
+
+/* Must be called while cmd_lock is acquired */
+static void __qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ struct qed_mcp_mb_params *p_mb_params,
+ u16 seq_num)
+{
+ union drv_union_data union_data;
+ u32 union_data_addr;
+
+ /* Set the union data */
+ union_data_addr = p_hwfn->mcp_info->drv_mb_addr +
+ offsetof(struct public_drv_mb, union_data);
+ memset(&union_data, 0, sizeof(union_data));
+ if (p_mb_params->p_data_src != NULL && p_mb_params->data_src_size)
+ memcpy(&union_data, p_mb_params->p_data_src,
+ p_mb_params->data_src_size);
+ qed_memcpy_to(p_hwfn, p_ptt, union_data_addr, &union_data,
+ sizeof(union_data));
+
+ /* Set the drv param */
+ DRV_MB_WR(p_hwfn, p_ptt, drv_mb_param, p_mb_params->param);
+
+ /* Set the drv command along with the sequence number */
+ DRV_MB_WR(p_hwfn, p_ptt, drv_mb_header, (p_mb_params->cmd | seq_num));
+
+ DP_VERBOSE(p_hwfn, QED_MSG_SP,
+ "MFW mailbox: command 0x%08x param 0x%08x\n",
+ (p_mb_params->cmd | seq_num), p_mb_params->param);
+}
+
+static int
+_qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ struct qed_mcp_mb_params *p_mb_params,
+ u32 max_retries, u32 delay)
+{
+ struct qed_mcp_cmd_elem *p_cmd_elem;
+ u32 cnt = 0;
+ u16 seq_num;
int rc = 0;
- /* Get actual driver mailbox sequence */
- actual_mb_seq = DRV_MB_RD(p_hwfn, p_ptt, drv_mb_header) &
- DRV_MSG_SEQ_NUMBER_MASK;
-
- /* Use MCP history register to check if MCP reset occurred between
- * init time and now.
- */
- if (p_hwfn->mcp_info->mcp_hist !=
- qed_rd(p_hwfn, p_ptt, MISCS_REG_GENERIC_POR_0)) {
- DP_VERBOSE(p_hwfn, QED_MSG_SP, "Rereading MCP offsets\n");
- qed_load_mcp_offsets(p_hwfn, p_ptt);
- qed_mcp_cmd_port_init(p_hwfn, p_ptt);
- }
- seq = ++p_hwfn->mcp_info->drv_mb_seq;
-
- /* Set drv param */
- DRV_MB_WR(p_hwfn, p_ptt, drv_mb_param, param);
-
- /* Set drv command along with the updated sequence */
- DRV_MB_WR(p_hwfn, p_ptt, drv_mb_header, (cmd | seq));
-
- DP_VERBOSE(p_hwfn, QED_MSG_SP,
- "wrote command (%x) to MFW MB param 0x%08x\n",
- (cmd | seq), param);
-
+ /* Wait until the mailbox is non-occupied */
do {
- /* Wait for MFW response */
+ /* Exit the loop if there is no pending command, or if the
+ * pending command is completed during this iteration.
+ * The spinlock stays locked until the command is sent.
+ */
+
+ spin_lock_bh(&p_hwfn->mcp_info->cmd_lock);
+
+ if (!qed_mcp_has_pending_cmd(p_hwfn))
+ break;
+
+ rc = qed_mcp_update_pending_cmd(p_hwfn, p_ptt);
+ if (!rc)
+ break;
+ else if (rc != -EAGAIN)
+ goto err;
+
+ spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
udelay(delay);
- *o_mcp_resp = DRV_MB_RD(p_hwfn, p_ptt, fw_mb_header);
+ } while (++cnt < max_retries);
- /* Give the FW up to 5 second (500*10ms) */
- } while ((seq != (*o_mcp_resp & FW_MSG_SEQ_NUMBER_MASK)) &&
- (cnt++ < QED_DRV_MB_MAX_RETRIES));
-
- DP_VERBOSE(p_hwfn, QED_MSG_SP,
- "[after %d ms] read (%x) seq is (%x) from FW MB\n",
- cnt * delay, *o_mcp_resp, seq);
-
- /* Is this a reply to our command? */
- if (seq == (*o_mcp_resp & FW_MSG_SEQ_NUMBER_MASK)) {
- *o_mcp_resp &= FW_MSG_CODE_MASK;
- /* Get the MCP param */
- *o_mcp_param = DRV_MB_RD(p_hwfn, p_ptt, fw_mb_param);
- } else {
- /* FW BUG! */
- DP_ERR(p_hwfn, "MFW failed to respond [cmd 0x%x param 0x%x]\n",
- cmd, param);
- *o_mcp_resp = 0;
- rc = -EAGAIN;
+ if (cnt >= max_retries) {
+ DP_NOTICE(p_hwfn,
+ "The MFW mailbox is occupied by an uncompleted command. Failed to send command 0x%08x [param 0x%08x].\n",
+ p_mb_params->cmd, p_mb_params->param);
+ return -EAGAIN;
}
+
+ /* Send the mailbox command */
+ qed_mcp_reread_offsets(p_hwfn, p_ptt);
+ seq_num = ++p_hwfn->mcp_info->drv_mb_seq;
+ p_cmd_elem = qed_mcp_cmd_add_elem(p_hwfn, p_mb_params, seq_num);
+ if (!p_cmd_elem) {
+ rc = -ENOMEM;
+ goto err;
+ }
+
+ __qed_mcp_cmd_and_union(p_hwfn, p_ptt, p_mb_params, seq_num);
+ spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
+
+ /* Wait for the MFW response */
+ do {
+ /* Exit the loop if the command is already completed, or if the
+ * command is completed during this iteration.
+ * The spinlock stays locked until the list element is removed.
+ */
+
+ udelay(delay);
+ spin_lock_bh(&p_hwfn->mcp_info->cmd_lock);
+
+ if (p_cmd_elem->b_is_completed)
+ break;
+
+ rc = qed_mcp_update_pending_cmd(p_hwfn, p_ptt);
+ if (!rc)
+ break;
+ else if (rc != -EAGAIN)
+ goto err;
+
+ spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
+ } while (++cnt < max_retries);
+
+ if (cnt >= max_retries) {
+ DP_NOTICE(p_hwfn,
+ "The MFW failed to respond to command 0x%08x [param 0x%08x].\n",
+ p_mb_params->cmd, p_mb_params->param);
+
+ spin_lock_bh(&p_hwfn->mcp_info->cmd_lock);
+ qed_mcp_cmd_del_elem(p_hwfn, p_cmd_elem);
+ spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
+
+ return -EAGAIN;
+ }
+
+ qed_mcp_cmd_del_elem(p_hwfn, p_cmd_elem);
+ spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
+
+ DP_VERBOSE(p_hwfn,
+ QED_MSG_SP,
+ "MFW mailbox: response 0x%08x param 0x%08x [after %d.%03d ms]\n",
+ p_mb_params->mcp_resp,
+ p_mb_params->mcp_param,
+ (cnt * delay) / 1000, (cnt * delay) % 1000);
+
+ /* Clear the sequence number from the MFW response */
+ p_mb_params->mcp_resp &= FW_MSG_CODE_MASK;
+
+ return 0;
+
+err:
+ spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock);
return rc;
}
@@ -354,9 +521,9 @@ static int qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt,
struct qed_mcp_mb_params *p_mb_params)
{
- u32 union_data_addr;
-
- int rc;
+ size_t union_data_size = sizeof(union drv_union_data);
+ u32 max_retries = QED_DRV_MB_MAX_RETRIES;
+ u32 delay = CHIP_MCP_RESP_ITER_US;
/* MCP not initialized */
if (!qed_mcp_is_init(p_hwfn)) {
@@ -364,33 +531,17 @@ static int qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn,
return -EBUSY;
}
- union_data_addr = p_hwfn->mcp_info->drv_mb_addr +
- offsetof(struct public_drv_mb, union_data);
+ if (p_mb_params->data_src_size > union_data_size ||
+ p_mb_params->data_dst_size > union_data_size) {
+ DP_ERR(p_hwfn,
+ "The provided size is larger than the union data size [src_size %u, dst_size %u, union_data_size %zu]\n",
+ p_mb_params->data_src_size,
+ p_mb_params->data_dst_size, union_data_size);
+ return -EINVAL;
+ }
- /* Ensure that only a single thread is accessing the mailbox at a
- * certain time.
- */
- rc = qed_mcp_mb_lock(p_hwfn, p_mb_params->cmd);
- if (rc)
- return rc;
-
- if (p_mb_params->p_data_src != NULL)
- qed_memcpy_to(p_hwfn, p_ptt, union_data_addr,
- p_mb_params->p_data_src,
- sizeof(*p_mb_params->p_data_src));
-
- rc = qed_do_mcp_cmd(p_hwfn, p_ptt, p_mb_params->cmd,
- p_mb_params->param, &p_mb_params->mcp_resp,
- &p_mb_params->mcp_param);
-
- if (p_mb_params->p_data_dst != NULL)
- qed_memcpy_from(p_hwfn, p_ptt, p_mb_params->p_data_dst,
- union_data_addr,
- sizeof(*p_mb_params->p_data_dst));
-
- qed_mcp_mb_unlock(p_hwfn, p_mb_params->cmd);
-
- return rc;
+ return _qed_mcp_cmd_and_union(p_hwfn, p_ptt, p_mb_params, max_retries,
+ delay);
}
int qed_mcp_cmd(struct qed_hwfn *p_hwfn,
@@ -401,32 +552,12 @@ int qed_mcp_cmd(struct qed_hwfn *p_hwfn,
u32 *o_mcp_param)
{
struct qed_mcp_mb_params mb_params;
- union drv_union_data data_src;
int rc;
memset(&mb_params, 0, sizeof(mb_params));
- memset(&data_src, 0, sizeof(data_src));
mb_params.cmd = cmd;
mb_params.param = param;
- /* In case of UNLOAD_DONE, set the primary MAC */
- if ((cmd == DRV_MSG_CODE_UNLOAD_DONE) &&
- (p_hwfn->cdev->wol_config == QED_OV_WOL_ENABLED)) {
- u8 *p_mac = p_hwfn->cdev->wol_mac;
-
- data_src.wol_mac.mac_upper = p_mac[0] << 8 | p_mac[1];
- data_src.wol_mac.mac_lower = p_mac[2] << 24 | p_mac[3] << 16 |
- p_mac[4] << 8 | p_mac[5];
-
- DP_VERBOSE(p_hwfn,
- (QED_MSG_SP | NETIF_MSG_IFDOWN),
- "Setting WoL MAC: %pM --> [%08x,%08x]\n",
- p_mac, data_src.wol_mac.mac_upper,
- data_src.wol_mac.mac_lower);
-
- mb_params.p_data_src = &data_src;
- }
-
rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
if (rc)
return rc;
@@ -445,13 +576,17 @@ int qed_mcp_nvm_rd_cmd(struct qed_hwfn *p_hwfn,
u32 *o_mcp_param, u32 *o_txn_size, u32 *o_buf)
{
struct qed_mcp_mb_params mb_params;
- union drv_union_data union_data;
+ u8 raw_data[MCP_DRV_NVM_BUF_LEN];
int rc;
memset(&mb_params, 0, sizeof(mb_params));
mb_params.cmd = cmd;
mb_params.param = param;
- mb_params.p_data_dst = &union_data;
+ mb_params.p_data_dst = raw_data;
+
+ /* Use the maximal value since the actual one is part of the response */
+ mb_params.data_dst_size = MCP_DRV_NVM_BUF_LEN;
+
rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
if (rc)
return rc;
@@ -460,55 +595,413 @@ int qed_mcp_nvm_rd_cmd(struct qed_hwfn *p_hwfn,
*o_mcp_param = mb_params.mcp_param;
*o_txn_size = *o_mcp_param;
- memcpy(o_buf, &union_data.raw_data, *o_txn_size);
+ memcpy(o_buf, raw_data, *o_txn_size);
return 0;
}
-int qed_mcp_load_req(struct qed_hwfn *p_hwfn,
- struct qed_ptt *p_ptt, u32 *p_load_code)
+static bool
+qed_mcp_can_force_load(u8 drv_role,
+ u8 exist_drv_role,
+ enum qed_override_force_load override_force_load)
{
- struct qed_dev *cdev = p_hwfn->cdev;
- struct qed_mcp_mb_params mb_params;
- union drv_union_data union_data;
+ bool can_force_load = false;
+
+ switch (override_force_load) {
+ case QED_OVERRIDE_FORCE_LOAD_ALWAYS:
+ can_force_load = true;
+ break;
+ case QED_OVERRIDE_FORCE_LOAD_NEVER:
+ can_force_load = false;
+ break;
+ default:
+ can_force_load = (drv_role == DRV_ROLE_OS &&
+ exist_drv_role == DRV_ROLE_PREBOOT) ||
+ (drv_role == DRV_ROLE_KDUMP &&
+ exist_drv_role == DRV_ROLE_OS);
+ break;
+ }
+
+ return can_force_load;
+}
+
+static int qed_mcp_cancel_load_req(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt)
+{
+ u32 resp = 0, param = 0;
int rc;
- memset(&mb_params, 0, sizeof(mb_params));
- /* Load Request */
- mb_params.cmd = DRV_MSG_CODE_LOAD_REQ;
- mb_params.param = PDA_COMP | DRV_ID_MCP_HSI_VER_CURRENT |
- cdev->drv_type;
- memcpy(&union_data.ver_str, cdev->ver_str, MCP_DRV_VER_STR_SIZE);
- mb_params.p_data_src = &union_data;
- rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
+ rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_CANCEL_LOAD_REQ, 0,
+ &resp, ¶m);
+ if (rc)
+ DP_NOTICE(p_hwfn,
+ "Failed to send cancel load request, rc = %d\n", rc);
- /* if mcp fails to respond we must abort */
+ return rc;
+}
+
+#define CONFIG_QEDE_BITMAP_IDX BIT(0)
+#define CONFIG_QED_SRIOV_BITMAP_IDX BIT(1)
+#define CONFIG_QEDR_BITMAP_IDX BIT(2)
+#define CONFIG_QEDF_BITMAP_IDX BIT(4)
+#define CONFIG_QEDI_BITMAP_IDX BIT(5)
+#define CONFIG_QED_LL2_BITMAP_IDX BIT(6)
+
+static u32 qed_get_config_bitmap(void)
+{
+ u32 config_bitmap = 0x0;
+
+ if (IS_ENABLED(CONFIG_QEDE))
+ config_bitmap |= CONFIG_QEDE_BITMAP_IDX;
+
+ if (IS_ENABLED(CONFIG_QED_SRIOV))
+ config_bitmap |= CONFIG_QED_SRIOV_BITMAP_IDX;
+
+ if (IS_ENABLED(CONFIG_QED_RDMA))
+ config_bitmap |= CONFIG_QEDR_BITMAP_IDX;
+
+ if (IS_ENABLED(CONFIG_QED_FCOE))
+ config_bitmap |= CONFIG_QEDF_BITMAP_IDX;
+
+ if (IS_ENABLED(CONFIG_QED_ISCSI))
+ config_bitmap |= CONFIG_QEDI_BITMAP_IDX;
+
+ if (IS_ENABLED(CONFIG_QED_LL2))
+ config_bitmap |= CONFIG_QED_LL2_BITMAP_IDX;
+
+ return config_bitmap;
+}
+
+struct qed_load_req_in_params {
+ u8 hsi_ver;
+#define QED_LOAD_REQ_HSI_VER_DEFAULT 0
+#define QED_LOAD_REQ_HSI_VER_1 1
+ u32 drv_ver_0;
+ u32 drv_ver_1;
+ u32 fw_ver;
+ u8 drv_role;
+ u8 timeout_val;
+ u8 force_cmd;
+ bool avoid_eng_reset;
+};
+
+struct qed_load_req_out_params {
+ u32 load_code;
+ u32 exist_drv_ver_0;
+ u32 exist_drv_ver_1;
+ u32 exist_fw_ver;
+ u8 exist_drv_role;
+ u8 mfw_hsi_ver;
+ bool drv_exists;
+};
+
+static int
+__qed_mcp_load_req(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ struct qed_load_req_in_params *p_in_params,
+ struct qed_load_req_out_params *p_out_params)
+{
+ struct qed_mcp_mb_params mb_params;
+ struct load_req_stc load_req;
+ struct load_rsp_stc load_rsp;
+ u32 hsi_ver;
+ int rc;
+
+ memset(&load_req, 0, sizeof(load_req));
+ load_req.drv_ver_0 = p_in_params->drv_ver_0;
+ load_req.drv_ver_1 = p_in_params->drv_ver_1;
+ load_req.fw_ver = p_in_params->fw_ver;
+ QED_MFW_SET_FIELD(load_req.misc0, LOAD_REQ_ROLE, p_in_params->drv_role);
+ QED_MFW_SET_FIELD(load_req.misc0, LOAD_REQ_LOCK_TO,
+ p_in_params->timeout_val);
+ QED_MFW_SET_FIELD(load_req.misc0, LOAD_REQ_FORCE,
+ p_in_params->force_cmd);
+ QED_MFW_SET_FIELD(load_req.misc0, LOAD_REQ_FLAGS0,
+ p_in_params->avoid_eng_reset);
+
+ hsi_ver = (p_in_params->hsi_ver == QED_LOAD_REQ_HSI_VER_DEFAULT) ?
+ DRV_ID_MCP_HSI_VER_CURRENT :
+ (p_in_params->hsi_ver << DRV_ID_MCP_HSI_VER_SHIFT);
+
+ memset(&mb_params, 0, sizeof(mb_params));
+ mb_params.cmd = DRV_MSG_CODE_LOAD_REQ;
+ mb_params.param = PDA_COMP | hsi_ver | p_hwfn->cdev->drv_type;
+ mb_params.p_data_src = &load_req;
+ mb_params.data_src_size = sizeof(load_req);
+ mb_params.p_data_dst = &load_rsp;
+ mb_params.data_dst_size = sizeof(load_rsp);
+
+ DP_VERBOSE(p_hwfn, QED_MSG_SP,
+ "Load Request: param 0x%08x [init_hw %d, drv_type %d, hsi_ver %d, pda 0x%04x]\n",
+ mb_params.param,
+ QED_MFW_GET_FIELD(mb_params.param, DRV_ID_DRV_INIT_HW),
+ QED_MFW_GET_FIELD(mb_params.param, DRV_ID_DRV_TYPE),
+ QED_MFW_GET_FIELD(mb_params.param, DRV_ID_MCP_HSI_VER),
+ QED_MFW_GET_FIELD(mb_params.param, DRV_ID_PDA_COMP_VER));
+
+ if (p_in_params->hsi_ver != QED_LOAD_REQ_HSI_VER_1) {
+ DP_VERBOSE(p_hwfn, QED_MSG_SP,
+ "Load Request: drv_ver 0x%08x_0x%08x, fw_ver 0x%08x, misc0 0x%08x [role %d, timeout %d, force %d, flags0 0x%x]\n",
+ load_req.drv_ver_0,
+ load_req.drv_ver_1,
+ load_req.fw_ver,
+ load_req.misc0,
+ QED_MFW_GET_FIELD(load_req.misc0, LOAD_REQ_ROLE),
+ QED_MFW_GET_FIELD(load_req.misc0,
+ LOAD_REQ_LOCK_TO),
+ QED_MFW_GET_FIELD(load_req.misc0, LOAD_REQ_FORCE),
+ QED_MFW_GET_FIELD(load_req.misc0, LOAD_REQ_FLAGS0));
+ }
+
+ rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
if (rc) {
- DP_ERR(p_hwfn, "MCP response failure, aborting\n");
+ DP_NOTICE(p_hwfn, "Failed to send load request, rc = %d\n", rc);
return rc;
}
- *p_load_code = mb_params.mcp_resp;
+ DP_VERBOSE(p_hwfn, QED_MSG_SP,
+ "Load Response: resp 0x%08x\n", mb_params.mcp_resp);
+ p_out_params->load_code = mb_params.mcp_resp;
- /* If MFW refused (e.g. other port is in diagnostic mode) we
- * must abort. This can happen in the following cases:
- * - Other port is in diagnostic mode
- * - Previously loaded function on the engine is not compliant with
- * the requester.
- * - MFW cannot cope with the requester's DRV_MFW_HSI_VERSION.
- * -
- */
- if (!(*p_load_code) ||
- ((*p_load_code) == FW_MSG_CODE_DRV_LOAD_REFUSED_HSI) ||
- ((*p_load_code) == FW_MSG_CODE_DRV_LOAD_REFUSED_PDA) ||
- ((*p_load_code) == FW_MSG_CODE_DRV_LOAD_REFUSED_DIAG)) {
- DP_ERR(p_hwfn, "MCP refused load request, aborting\n");
- return -EBUSY;
+ if (p_in_params->hsi_ver != QED_LOAD_REQ_HSI_VER_1 &&
+ p_out_params->load_code != FW_MSG_CODE_DRV_LOAD_REFUSED_HSI_1) {
+ DP_VERBOSE(p_hwfn,
+ QED_MSG_SP,
+ "Load Response: exist_drv_ver 0x%08x_0x%08x, exist_fw_ver 0x%08x, misc0 0x%08x [exist_role %d, mfw_hsi %d, flags0 0x%x]\n",
+ load_rsp.drv_ver_0,
+ load_rsp.drv_ver_1,
+ load_rsp.fw_ver,
+ load_rsp.misc0,
+ QED_MFW_GET_FIELD(load_rsp.misc0, LOAD_RSP_ROLE),
+ QED_MFW_GET_FIELD(load_rsp.misc0, LOAD_RSP_HSI),
+ QED_MFW_GET_FIELD(load_rsp.misc0, LOAD_RSP_FLAGS0));
+
+ p_out_params->exist_drv_ver_0 = load_rsp.drv_ver_0;
+ p_out_params->exist_drv_ver_1 = load_rsp.drv_ver_1;
+ p_out_params->exist_fw_ver = load_rsp.fw_ver;
+ p_out_params->exist_drv_role =
+ QED_MFW_GET_FIELD(load_rsp.misc0, LOAD_RSP_ROLE);
+ p_out_params->mfw_hsi_ver =
+ QED_MFW_GET_FIELD(load_rsp.misc0, LOAD_RSP_HSI);
+ p_out_params->drv_exists =
+ QED_MFW_GET_FIELD(load_rsp.misc0, LOAD_RSP_FLAGS0) &
+ LOAD_RSP_FLAGS0_DRV_EXISTS;
}
return 0;
}
+static int eocre_get_mfw_drv_role(struct qed_hwfn *p_hwfn,
+ enum qed_drv_role drv_role,
+ u8 *p_mfw_drv_role)
+{
+ switch (drv_role) {
+ case QED_DRV_ROLE_OS:
+ *p_mfw_drv_role = DRV_ROLE_OS;
+ break;
+ case QED_DRV_ROLE_KDUMP:
+ *p_mfw_drv_role = DRV_ROLE_KDUMP;
+ break;
+ default:
+ DP_ERR(p_hwfn, "Unexpected driver role %d\n", drv_role);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+enum qed_load_req_force {
+ QED_LOAD_REQ_FORCE_NONE,
+ QED_LOAD_REQ_FORCE_PF,
+ QED_LOAD_REQ_FORCE_ALL,
+};
+
+static void qed_get_mfw_force_cmd(struct qed_hwfn *p_hwfn,
+
+ enum qed_load_req_force force_cmd,
+ u8 *p_mfw_force_cmd)
+{
+ switch (force_cmd) {
+ case QED_LOAD_REQ_FORCE_NONE:
+ *p_mfw_force_cmd = LOAD_REQ_FORCE_NONE;
+ break;
+ case QED_LOAD_REQ_FORCE_PF:
+ *p_mfw_force_cmd = LOAD_REQ_FORCE_PF;
+ break;
+ case QED_LOAD_REQ_FORCE_ALL:
+ *p_mfw_force_cmd = LOAD_REQ_FORCE_ALL;
+ break;
+ }
+}
+
+int qed_mcp_load_req(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ struct qed_load_req_params *p_params)
+{
+ struct qed_load_req_out_params out_params;
+ struct qed_load_req_in_params in_params;
+ u8 mfw_drv_role, mfw_force_cmd;
+ int rc;
+
+ memset(&in_params, 0, sizeof(in_params));
+ in_params.hsi_ver = QED_LOAD_REQ_HSI_VER_DEFAULT;
+ in_params.drv_ver_0 = QED_VERSION;
+ in_params.drv_ver_1 = qed_get_config_bitmap();
+ in_params.fw_ver = STORM_FW_VERSION;
+ rc = eocre_get_mfw_drv_role(p_hwfn, p_params->drv_role, &mfw_drv_role);
+ if (rc)
+ return rc;
+
+ in_params.drv_role = mfw_drv_role;
+ in_params.timeout_val = p_params->timeout_val;
+ qed_get_mfw_force_cmd(p_hwfn,
+ QED_LOAD_REQ_FORCE_NONE, &mfw_force_cmd);
+
+ in_params.force_cmd = mfw_force_cmd;
+ in_params.avoid_eng_reset = p_params->avoid_eng_reset;
+
+ memset(&out_params, 0, sizeof(out_params));
+ rc = __qed_mcp_load_req(p_hwfn, p_ptt, &in_params, &out_params);
+ if (rc)
+ return rc;
+
+ /* First handle cases where another load request should/might be sent:
+ * - MFW expects the old interface [HSI version = 1]
+ * - MFW responds that a force load request is required
+ */
+ if (out_params.load_code == FW_MSG_CODE_DRV_LOAD_REFUSED_HSI_1) {
+ DP_INFO(p_hwfn,
+ "MFW refused a load request due to HSI > 1. Resending with HSI = 1\n");
+
+ in_params.hsi_ver = QED_LOAD_REQ_HSI_VER_1;
+ memset(&out_params, 0, sizeof(out_params));
+ rc = __qed_mcp_load_req(p_hwfn, p_ptt, &in_params, &out_params);
+ if (rc)
+ return rc;
+ } else if (out_params.load_code ==
+ FW_MSG_CODE_DRV_LOAD_REFUSED_REQUIRES_FORCE) {
+ if (qed_mcp_can_force_load(in_params.drv_role,
+ out_params.exist_drv_role,
+ p_params->override_force_load)) {
+ DP_INFO(p_hwfn,
+ "A force load is required [{role, fw_ver, drv_ver}: loading={%d, 0x%08x, x%08x_0x%08x}, existing={%d, 0x%08x, 0x%08x_0x%08x}]\n",
+ in_params.drv_role, in_params.fw_ver,
+ in_params.drv_ver_0, in_params.drv_ver_1,
+ out_params.exist_drv_role,
+ out_params.exist_fw_ver,
+ out_params.exist_drv_ver_0,
+ out_params.exist_drv_ver_1);
+
+ qed_get_mfw_force_cmd(p_hwfn,
+ QED_LOAD_REQ_FORCE_ALL,
+ &mfw_force_cmd);
+
+ in_params.force_cmd = mfw_force_cmd;
+ memset(&out_params, 0, sizeof(out_params));
+ rc = __qed_mcp_load_req(p_hwfn, p_ptt, &in_params,
+ &out_params);
+ if (rc)
+ return rc;
+ } else {
+ DP_NOTICE(p_hwfn,
+ "A force load is required [{role, fw_ver, drv_ver}: loading={%d, 0x%08x, x%08x_0x%08x}, existing={%d, 0x%08x, 0x%08x_0x%08x}] - Avoid\n",
+ in_params.drv_role, in_params.fw_ver,
+ in_params.drv_ver_0, in_params.drv_ver_1,
+ out_params.exist_drv_role,
+ out_params.exist_fw_ver,
+ out_params.exist_drv_ver_0,
+ out_params.exist_drv_ver_1);
+ DP_NOTICE(p_hwfn,
+ "Avoid sending a force load request to prevent disruption of active PFs\n");
+
+ qed_mcp_cancel_load_req(p_hwfn, p_ptt);
+ return -EBUSY;
+ }
+ }
+
+ /* Now handle the other types of responses.
+ * The "REFUSED_HSI_1" and "REFUSED_REQUIRES_FORCE" responses are not
+ * expected here after the additional revised load requests were sent.
+ */
+ switch (out_params.load_code) {
+ case FW_MSG_CODE_DRV_LOAD_ENGINE:
+ case FW_MSG_CODE_DRV_LOAD_PORT:
+ case FW_MSG_CODE_DRV_LOAD_FUNCTION:
+ if (out_params.mfw_hsi_ver != QED_LOAD_REQ_HSI_VER_1 &&
+ out_params.drv_exists) {
+ /* The role and fw/driver version match, but the PF is
+ * already loaded and has not been unloaded gracefully.
+ */
+ DP_NOTICE(p_hwfn,
+ "PF is already loaded\n");
+ return -EINVAL;
+ }
+ break;
+ default:
+ DP_NOTICE(p_hwfn,
+ "Unexpected refusal to load request [resp 0x%08x]. Aborting.\n",
+ out_params.load_code);
+ return -EBUSY;
+ }
+
+ p_params->load_code = out_params.load_code;
+
+ return 0;
+}
+
+int qed_mcp_unload_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+ u32 wol_param, mcp_resp, mcp_param;
+
+ switch (p_hwfn->cdev->wol_config) {
+ case QED_OV_WOL_DISABLED:
+ wol_param = DRV_MB_PARAM_UNLOAD_WOL_DISABLED;
+ break;
+ case QED_OV_WOL_ENABLED:
+ wol_param = DRV_MB_PARAM_UNLOAD_WOL_ENABLED;
+ break;
+ default:
+ DP_NOTICE(p_hwfn,
+ "Unknown WoL configuration %02x\n",
+ p_hwfn->cdev->wol_config);
+ /* Fallthrough */
+ case QED_OV_WOL_DEFAULT:
+ wol_param = DRV_MB_PARAM_UNLOAD_WOL_MCP;
+ }
+
+ return qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_UNLOAD_REQ, wol_param,
+ &mcp_resp, &mcp_param);
+}
+
+int qed_mcp_unload_done(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+ struct qed_mcp_mb_params mb_params;
+ struct mcp_mac wol_mac;
+
+ memset(&mb_params, 0, sizeof(mb_params));
+ mb_params.cmd = DRV_MSG_CODE_UNLOAD_DONE;
+
+ /* Set the primary MAC if WoL is enabled */
+ if (p_hwfn->cdev->wol_config == QED_OV_WOL_ENABLED) {
+ u8 *p_mac = p_hwfn->cdev->wol_mac;
+
+ memset(&wol_mac, 0, sizeof(wol_mac));
+ wol_mac.mac_upper = p_mac[0] << 8 | p_mac[1];
+ wol_mac.mac_lower = p_mac[2] << 24 | p_mac[3] << 16 |
+ p_mac[4] << 8 | p_mac[5];
+
+ DP_VERBOSE(p_hwfn,
+ (QED_MSG_SP | NETIF_MSG_IFDOWN),
+ "Setting WoL MAC: %pM --> [%08x,%08x]\n",
+ p_mac, wol_mac.mac_upper, wol_mac.mac_lower);
+
+ mb_params.p_data_src = &wol_mac;
+ mb_params.data_src_size = sizeof(wol_mac);
+ }
+
+ return qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
+}
+
static void qed_mcp_handle_vf_flr(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt)
{
@@ -549,7 +1042,6 @@ int qed_mcp_ack_vf_flr(struct qed_hwfn *p_hwfn,
u32 func_addr = SECTION_ADDR(mfw_func_offsize,
MCP_PF_ID(p_hwfn));
struct qed_mcp_mb_params mb_params;
- union drv_union_data union_data;
int rc;
int i;
@@ -560,8 +1052,8 @@ int qed_mcp_ack_vf_flr(struct qed_hwfn *p_hwfn,
memset(&mb_params, 0, sizeof(mb_params));
mb_params.cmd = DRV_MSG_CODE_VF_DISABLED_DONE;
- memcpy(&union_data.ack_vf_disabled, vfs_to_ack, VF_MAX_STATIC / 8);
- mb_params.p_data_src = &union_data;
+ mb_params.p_data_src = vfs_to_ack;
+ mb_params.data_src_size = VF_MAX_STATIC / 8;
rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
if (rc) {
DP_NOTICE(p_hwfn, "Failed to pass ACK for VF flr to MFW\n");
@@ -744,33 +1236,31 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up)
{
struct qed_mcp_link_params *params = &p_hwfn->mcp_info->link_input;
struct qed_mcp_mb_params mb_params;
- union drv_union_data union_data;
- struct eth_phy_cfg *phy_cfg;
+ struct eth_phy_cfg phy_cfg;
int rc = 0;
u32 cmd;
/* Set the shmem configuration according to params */
- phy_cfg = &union_data.drv_phy_cfg;
- memset(phy_cfg, 0, sizeof(*phy_cfg));
+ memset(&phy_cfg, 0, sizeof(phy_cfg));
cmd = b_up ? DRV_MSG_CODE_INIT_PHY : DRV_MSG_CODE_LINK_RESET;
if (!params->speed.autoneg)
- phy_cfg->speed = params->speed.forced_speed;
- phy_cfg->pause |= (params->pause.autoneg) ? ETH_PAUSE_AUTONEG : 0;
- phy_cfg->pause |= (params->pause.forced_rx) ? ETH_PAUSE_RX : 0;
- phy_cfg->pause |= (params->pause.forced_tx) ? ETH_PAUSE_TX : 0;
- phy_cfg->adv_speed = params->speed.advertised_speeds;
- phy_cfg->loopback_mode = params->loopback_mode;
+ phy_cfg.speed = params->speed.forced_speed;
+ phy_cfg.pause |= (params->pause.autoneg) ? ETH_PAUSE_AUTONEG : 0;
+ phy_cfg.pause |= (params->pause.forced_rx) ? ETH_PAUSE_RX : 0;
+ phy_cfg.pause |= (params->pause.forced_tx) ? ETH_PAUSE_TX : 0;
+ phy_cfg.adv_speed = params->speed.advertised_speeds;
+ phy_cfg.loopback_mode = params->loopback_mode;
p_hwfn->b_drv_link_init = b_up;
if (b_up) {
DP_VERBOSE(p_hwfn, NETIF_MSG_LINK,
"Configuring Link: Speed 0x%08x, Pause 0x%08x, adv_speed 0x%08x, loopback 0x%08x, features 0x%08x\n",
- phy_cfg->speed,
- phy_cfg->pause,
- phy_cfg->adv_speed,
- phy_cfg->loopback_mode,
- phy_cfg->feature_config_flags);
+ phy_cfg.speed,
+ phy_cfg.pause,
+ phy_cfg.adv_speed,
+ phy_cfg.loopback_mode,
+ phy_cfg.feature_config_flags);
} else {
DP_VERBOSE(p_hwfn, NETIF_MSG_LINK,
"Resetting link\n");
@@ -778,7 +1268,8 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up)
memset(&mb_params, 0, sizeof(mb_params));
mb_params.cmd = cmd;
- mb_params.p_data_src = &union_data;
+ mb_params.p_data_src = &phy_cfg;
+ mb_params.data_src_size = sizeof(phy_cfg);
rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
/* if mcp fails to respond we must abort */
@@ -805,7 +1296,6 @@ static void qed_mcp_send_protocol_stats(struct qed_hwfn *p_hwfn,
enum qed_mcp_protocol_type stats_type;
union qed_mcp_protocol_stats stats;
struct qed_mcp_mb_params mb_params;
- union drv_union_data union_data;
u32 hsi_param;
switch (type) {
@@ -835,8 +1325,8 @@ static void qed_mcp_send_protocol_stats(struct qed_hwfn *p_hwfn,
memset(&mb_params, 0, sizeof(mb_params));
mb_params.cmd = DRV_MSG_CODE_GET_STATS;
mb_params.param = hsi_param;
- memcpy(&union_data, &stats, sizeof(stats));
- mb_params.p_data_src = &union_data;
+ mb_params.p_data_src = &stats;
+ mb_params.data_src_size = sizeof(stats);
qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
}
@@ -963,7 +1453,7 @@ int qed_mcp_handle_events(struct qed_hwfn *p_hwfn,
qed_mcp_update_bw(p_hwfn, p_ptt);
break;
default:
- DP_NOTICE(p_hwfn, "Unimplemented MFW message %d\n", i);
+ DP_INFO(p_hwfn, "Unimplemented MFW message %d\n", i);
rc = -EINVAL;
}
}
@@ -1316,24 +1806,23 @@ qed_mcp_send_drv_version(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt,
struct qed_mcp_drv_version *p_ver)
{
- struct drv_version_stc *p_drv_version;
struct qed_mcp_mb_params mb_params;
- union drv_union_data union_data;
+ struct drv_version_stc drv_version;
__be32 val;
u32 i;
int rc;
- p_drv_version = &union_data.drv_version;
- p_drv_version->version = p_ver->version;
-
+ memset(&drv_version, 0, sizeof(drv_version));
+ drv_version.version = p_ver->version;
for (i = 0; i < (MCP_DRV_VER_STR_SIZE - 4) / sizeof(u32); i++) {
val = cpu_to_be32(*((u32 *)&p_ver->name[i * sizeof(u32)]));
- *(__be32 *)&p_drv_version->name[i * sizeof(u32)] = val;
+ *(__be32 *)&drv_version.name[i * sizeof(u32)] = val;
}
memset(&mb_params, 0, sizeof(mb_params));
mb_params.cmd = DRV_MSG_CODE_SET_VERSION;
- mb_params.p_data_src = &union_data;
+ mb_params.p_data_src = &drv_version;
+ mb_params.data_src_size = sizeof(drv_version);
rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
if (rc)
DP_ERR(p_hwfn, "MCP response failure, aborting\n");
@@ -1450,7 +1939,7 @@ int qed_mcp_ov_update_mac(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt, u8 *mac)
{
struct qed_mcp_mb_params mb_params;
- union drv_union_data union_data;
+ u32 mfw_mac[2];
int rc;
memset(&mb_params, 0, sizeof(mb_params));
@@ -1458,8 +1947,17 @@ int qed_mcp_ov_update_mac(struct qed_hwfn *p_hwfn,
mb_params.param = DRV_MSG_CODE_VMAC_TYPE_MAC <<
DRV_MSG_CODE_VMAC_TYPE_SHIFT;
mb_params.param |= MCP_PF_ID(p_hwfn);
- ether_addr_copy(&union_data.raw_data[0], mac);
- mb_params.p_data_src = &union_data;
+
+ /* MCP is BE, and on LE platforms PCI would swap access to SHMEM
+ * in 32-bit granularity.
+ * So the MAC has to be set in native order [and not byte order],
+ * otherwise it would be read incorrectly by MFW after swap.
+ */
+ mfw_mac[0] = mac[0] << 24 | mac[1] << 16 | mac[2] << 8 | mac[3];
+ mfw_mac[1] = mac[4] << 24 | mac[5] << 16;
+
+ mb_params.p_data_src = (u8 *)mfw_mac;
+ mb_params.data_src_size = 8;
rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
if (rc)
DP_ERR(p_hwfn, "Failed to send mac address, rc = %d\n", rc);
@@ -1724,52 +2222,396 @@ int qed_mcp_bist_nvm_test_get_image_att(struct qed_hwfn *p_hwfn,
return rc;
}
-#define QED_RESC_ALLOC_VERSION_MAJOR 1
+static enum resource_id_enum qed_mcp_get_mfw_res_id(enum qed_resources res_id)
+{
+ enum resource_id_enum mfw_res_id = RESOURCE_NUM_INVALID;
+
+ switch (res_id) {
+ case QED_SB:
+ mfw_res_id = RESOURCE_NUM_SB_E;
+ break;
+ case QED_L2_QUEUE:
+ mfw_res_id = RESOURCE_NUM_L2_QUEUE_E;
+ break;
+ case QED_VPORT:
+ mfw_res_id = RESOURCE_NUM_VPORT_E;
+ break;
+ case QED_RSS_ENG:
+ mfw_res_id = RESOURCE_NUM_RSS_ENGINES_E;
+ break;
+ case QED_PQ:
+ mfw_res_id = RESOURCE_NUM_PQ_E;
+ break;
+ case QED_RL:
+ mfw_res_id = RESOURCE_NUM_RL_E;
+ break;
+ case QED_MAC:
+ case QED_VLAN:
+ /* Each VFC resource can accommodate both a MAC and a VLAN */
+ mfw_res_id = RESOURCE_VFC_FILTER_E;
+ break;
+ case QED_ILT:
+ mfw_res_id = RESOURCE_ILT_E;
+ break;
+ case QED_LL2_QUEUE:
+ mfw_res_id = RESOURCE_LL2_QUEUE_E;
+ break;
+ case QED_RDMA_CNQ_RAM:
+ case QED_CMDQS_CQS:
+ /* CNQ/CMDQS are the same resource */
+ mfw_res_id = RESOURCE_CQS_E;
+ break;
+ case QED_RDMA_STATS_QUEUE:
+ mfw_res_id = RESOURCE_RDMA_STATS_QUEUE_E;
+ break;
+ case QED_BDQ:
+ mfw_res_id = RESOURCE_BDQ_E;
+ break;
+ default:
+ break;
+ }
+
+ return mfw_res_id;
+}
+
+#define QED_RESC_ALLOC_VERSION_MAJOR 2
#define QED_RESC_ALLOC_VERSION_MINOR 0
#define QED_RESC_ALLOC_VERSION \
((QED_RESC_ALLOC_VERSION_MAJOR << \
DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_SHIFT) | \
(QED_RESC_ALLOC_VERSION_MINOR << \
DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MINOR_SHIFT))
-int qed_mcp_get_resc_info(struct qed_hwfn *p_hwfn,
- struct qed_ptt *p_ptt,
- struct resource_info *p_resc_info,
- u32 *p_mcp_resp, u32 *p_mcp_param)
+
+struct qed_resc_alloc_in_params {
+ u32 cmd;
+ enum qed_resources res_id;
+ u32 resc_max_val;
+};
+
+struct qed_resc_alloc_out_params {
+ u32 mcp_resp;
+ u32 mcp_param;
+ u32 resc_num;
+ u32 resc_start;
+ u32 vf_resc_num;
+ u32 vf_resc_start;
+ u32 flags;
+};
+
+static int
+qed_mcp_resc_allocation_msg(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ struct qed_resc_alloc_in_params *p_in_params,
+ struct qed_resc_alloc_out_params *p_out_params)
{
struct qed_mcp_mb_params mb_params;
- union drv_union_data union_data;
+ struct resource_info mfw_resc_info;
int rc;
+ memset(&mfw_resc_info, 0, sizeof(mfw_resc_info));
+
+ mfw_resc_info.res_id = qed_mcp_get_mfw_res_id(p_in_params->res_id);
+ if (mfw_resc_info.res_id == RESOURCE_NUM_INVALID) {
+ DP_ERR(p_hwfn,
+ "Failed to match resource %d [%s] with the MFW resources\n",
+ p_in_params->res_id,
+ qed_hw_get_resc_name(p_in_params->res_id));
+ return -EINVAL;
+ }
+
+ switch (p_in_params->cmd) {
+ case DRV_MSG_SET_RESOURCE_VALUE_MSG:
+ mfw_resc_info.size = p_in_params->resc_max_val;
+ /* Fallthrough */
+ case DRV_MSG_GET_RESOURCE_ALLOC_MSG:
+ break;
+ default:
+ DP_ERR(p_hwfn, "Unexpected resource alloc command [0x%08x]\n",
+ p_in_params->cmd);
+ return -EINVAL;
+ }
+
memset(&mb_params, 0, sizeof(mb_params));
- memset(&union_data, 0, sizeof(union_data));
- mb_params.cmd = DRV_MSG_GET_RESOURCE_ALLOC_MSG;
+ mb_params.cmd = p_in_params->cmd;
mb_params.param = QED_RESC_ALLOC_VERSION;
+ mb_params.p_data_src = &mfw_resc_info;
+ mb_params.data_src_size = sizeof(mfw_resc_info);
+ mb_params.p_data_dst = mb_params.p_data_src;
+ mb_params.data_dst_size = mb_params.data_src_size;
- /* Need to have a sufficient large struct, as the cmd_and_union
- * is going to do memcpy from and to it.
- */
- memcpy(&union_data.resource, p_resc_info, sizeof(*p_resc_info));
+ DP_VERBOSE(p_hwfn,
+ QED_MSG_SP,
+ "Resource message request: cmd 0x%08x, res_id %d [%s], hsi_version %d.%d, val 0x%x\n",
+ p_in_params->cmd,
+ p_in_params->res_id,
+ qed_hw_get_resc_name(p_in_params->res_id),
+ QED_MFW_GET_FIELD(mb_params.param,
+ DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR),
+ QED_MFW_GET_FIELD(mb_params.param,
+ DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MINOR),
+ p_in_params->resc_max_val);
- mb_params.p_data_src = &union_data;
- mb_params.p_data_dst = &union_data;
rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
if (rc)
return rc;
- /* Copy the data back */
- memcpy(p_resc_info, &union_data.resource, sizeof(*p_resc_info));
- *p_mcp_resp = mb_params.mcp_resp;
- *p_mcp_param = mb_params.mcp_param;
+ p_out_params->mcp_resp = mb_params.mcp_resp;
+ p_out_params->mcp_param = mb_params.mcp_param;
+ p_out_params->resc_num = mfw_resc_info.size;
+ p_out_params->resc_start = mfw_resc_info.offset;
+ p_out_params->vf_resc_num = mfw_resc_info.vf_size;
+ p_out_params->vf_resc_start = mfw_resc_info.vf_offset;
+ p_out_params->flags = mfw_resc_info.flags;
DP_VERBOSE(p_hwfn,
QED_MSG_SP,
- "MFW resource_info: version 0x%x, res_id 0x%x, size 0x%x, offset 0x%x, vf_size 0x%x, vf_offset 0x%x, flags 0x%x\n",
- *p_mcp_param,
- p_resc_info->res_id,
- p_resc_info->size,
- p_resc_info->offset,
- p_resc_info->vf_size,
- p_resc_info->vf_offset, p_resc_info->flags);
+ "Resource message response: mfw_hsi_version %d.%d, num 0x%x, start 0x%x, vf_num 0x%x, vf_start 0x%x, flags 0x%08x\n",
+ QED_MFW_GET_FIELD(p_out_params->mcp_param,
+ FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR),
+ QED_MFW_GET_FIELD(p_out_params->mcp_param,
+ FW_MB_PARAM_RESOURCE_ALLOC_VERSION_MINOR),
+ p_out_params->resc_num,
+ p_out_params->resc_start,
+ p_out_params->vf_resc_num,
+ p_out_params->vf_resc_start, p_out_params->flags);
+
+ return 0;
+}
+
+int
+qed_mcp_set_resc_max_val(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ enum qed_resources res_id,
+ u32 resc_max_val, u32 *p_mcp_resp)
+{
+ struct qed_resc_alloc_out_params out_params;
+ struct qed_resc_alloc_in_params in_params;
+ int rc;
+
+ memset(&in_params, 0, sizeof(in_params));
+ in_params.cmd = DRV_MSG_SET_RESOURCE_VALUE_MSG;
+ in_params.res_id = res_id;
+ in_params.resc_max_val = resc_max_val;
+ memset(&out_params, 0, sizeof(out_params));
+ rc = qed_mcp_resc_allocation_msg(p_hwfn, p_ptt, &in_params,
+ &out_params);
+ if (rc)
+ return rc;
+
+ *p_mcp_resp = out_params.mcp_resp;
+
+ return 0;
+}
+
+int
+qed_mcp_get_resc_info(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ enum qed_resources res_id,
+ u32 *p_mcp_resp, u32 *p_resc_num, u32 *p_resc_start)
+{
+ struct qed_resc_alloc_out_params out_params;
+ struct qed_resc_alloc_in_params in_params;
+ int rc;
+
+ memset(&in_params, 0, sizeof(in_params));
+ in_params.cmd = DRV_MSG_GET_RESOURCE_ALLOC_MSG;
+ in_params.res_id = res_id;
+ memset(&out_params, 0, sizeof(out_params));
+ rc = qed_mcp_resc_allocation_msg(p_hwfn, p_ptt, &in_params,
+ &out_params);
+ if (rc)
+ return rc;
+
+ *p_mcp_resp = out_params.mcp_resp;
+
+ if (*p_mcp_resp == FW_MSG_CODE_RESOURCE_ALLOC_OK) {
+ *p_resc_num = out_params.resc_num;
+ *p_resc_start = out_params.resc_start;
+ }
+
+ return 0;
+}
+
+int qed_mcp_initiate_pf_flr(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+ u32 mcp_resp, mcp_param;
+
+ return qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_INITIATE_PF_FLR, 0,
+ &mcp_resp, &mcp_param);
+}
+
+static int qed_mcp_resource_cmd(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ u32 param, u32 *p_mcp_resp, u32 *p_mcp_param)
+{
+ int rc;
+
+ rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_RESOURCE_CMD, param,
+ p_mcp_resp, p_mcp_param);
+ if (rc)
+ return rc;
+
+ if (*p_mcp_resp == FW_MSG_CODE_UNSUPPORTED) {
+ DP_INFO(p_hwfn,
+ "The resource command is unsupported by the MFW\n");
+ return -EINVAL;
+ }
+
+ if (*p_mcp_param == RESOURCE_OPCODE_UNKNOWN_CMD) {
+ u8 opcode = QED_MFW_GET_FIELD(param, RESOURCE_CMD_REQ_OPCODE);
+
+ DP_NOTICE(p_hwfn,
+ "The resource command is unknown to the MFW [param 0x%08x, opcode %d]\n",
+ param, opcode);
+ return -EINVAL;
+ }
+
+ return rc;
+}
+
+int
+__qed_mcp_resc_lock(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ struct qed_resc_lock_params *p_params)
+{
+ u32 param = 0, mcp_resp, mcp_param;
+ u8 opcode;
+ int rc;
+
+ switch (p_params->timeout) {
+ case QED_MCP_RESC_LOCK_TO_DEFAULT:
+ opcode = RESOURCE_OPCODE_REQ;
+ p_params->timeout = 0;
+ break;
+ case QED_MCP_RESC_LOCK_TO_NONE:
+ opcode = RESOURCE_OPCODE_REQ_WO_AGING;
+ p_params->timeout = 0;
+ break;
+ default:
+ opcode = RESOURCE_OPCODE_REQ_W_AGING;
+ break;
+ }
+
+ QED_MFW_SET_FIELD(param, RESOURCE_CMD_REQ_RESC, p_params->resource);
+ QED_MFW_SET_FIELD(param, RESOURCE_CMD_REQ_OPCODE, opcode);
+ QED_MFW_SET_FIELD(param, RESOURCE_CMD_REQ_AGE, p_params->timeout);
+
+ DP_VERBOSE(p_hwfn,
+ QED_MSG_SP,
+ "Resource lock request: param 0x%08x [age %d, opcode %d, resource %d]\n",
+ param, p_params->timeout, opcode, p_params->resource);
+
+ /* Attempt to acquire the resource */
+ rc = qed_mcp_resource_cmd(p_hwfn, p_ptt, param, &mcp_resp, &mcp_param);
+ if (rc)
+ return rc;
+
+ /* Analyze the response */
+ p_params->owner = QED_MFW_GET_FIELD(mcp_param, RESOURCE_CMD_RSP_OWNER);
+ opcode = QED_MFW_GET_FIELD(mcp_param, RESOURCE_CMD_RSP_OPCODE);
+
+ DP_VERBOSE(p_hwfn,
+ QED_MSG_SP,
+ "Resource lock response: mcp_param 0x%08x [opcode %d, owner %d]\n",
+ mcp_param, opcode, p_params->owner);
+
+ switch (opcode) {
+ case RESOURCE_OPCODE_GNT:
+ p_params->b_granted = true;
+ break;
+ case RESOURCE_OPCODE_BUSY:
+ p_params->b_granted = false;
+ break;
+ default:
+ DP_NOTICE(p_hwfn,
+ "Unexpected opcode in resource lock response [mcp_param 0x%08x, opcode %d]\n",
+ mcp_param, opcode);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+int
+qed_mcp_resc_lock(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt, struct qed_resc_lock_params *p_params)
+{
+ u32 retry_cnt = 0;
+ int rc;
+
+ do {
+ /* No need for an interval before the first iteration */
+ if (retry_cnt) {
+ if (p_params->sleep_b4_retry) {
+ u16 retry_interval_in_ms =
+ DIV_ROUND_UP(p_params->retry_interval,
+ 1000);
+
+ msleep(retry_interval_in_ms);
+ } else {
+ udelay(p_params->retry_interval);
+ }
+ }
+
+ rc = __qed_mcp_resc_lock(p_hwfn, p_ptt, p_params);
+ if (rc)
+ return rc;
+
+ if (p_params->b_granted)
+ break;
+ } while (retry_cnt++ < p_params->retry_num);
+
+ return 0;
+}
+
+int
+qed_mcp_resc_unlock(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ struct qed_resc_unlock_params *p_params)
+{
+ u32 param = 0, mcp_resp, mcp_param;
+ u8 opcode;
+ int rc;
+
+ opcode = p_params->b_force ? RESOURCE_OPCODE_FORCE_RELEASE
+ : RESOURCE_OPCODE_RELEASE;
+ QED_MFW_SET_FIELD(param, RESOURCE_CMD_REQ_RESC, p_params->resource);
+ QED_MFW_SET_FIELD(param, RESOURCE_CMD_REQ_OPCODE, opcode);
+
+ DP_VERBOSE(p_hwfn, QED_MSG_SP,
+ "Resource unlock request: param 0x%08x [opcode %d, resource %d]\n",
+ param, opcode, p_params->resource);
+
+ /* Attempt to release the resource */
+ rc = qed_mcp_resource_cmd(p_hwfn, p_ptt, param, &mcp_resp, &mcp_param);
+ if (rc)
+ return rc;
+
+ /* Analyze the response */
+ opcode = QED_MFW_GET_FIELD(mcp_param, RESOURCE_CMD_RSP_OPCODE);
+
+ DP_VERBOSE(p_hwfn, QED_MSG_SP,
+ "Resource unlock response: mcp_param 0x%08x [opcode %d]\n",
+ mcp_param, opcode);
+
+ switch (opcode) {
+ case RESOURCE_OPCODE_RELEASED_PREVIOUS:
+ DP_INFO(p_hwfn,
+ "Resource unlock request for an already released resource [%d]\n",
+ p_params->resource);
+ /* Fallthrough */
+ case RESOURCE_OPCODE_RELEASED:
+ p_params->b_released = true;
+ break;
+ case RESOURCE_OPCODE_WRONG_OWNER:
+ p_params->b_released = false;
+ break;
+ default:
+ DP_NOTICE(p_hwfn,
+ "Unexpected opcode in resource unlock response [mcp_param 0x%08x, opcode %d]\n",
+ mcp_param, opcode);
+ return -EINVAL;
+ }
return 0;
}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
index 368e88d..ac7d406 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
@@ -39,6 +39,7 @@
#include <linux/spinlock.h>
#include <linux/qed/qed_fcoe_if.h>
#include "qed_hsi.h"
+#include "qed_dev_api.h"
struct qed_mcp_link_speed_params {
bool autoneg;
@@ -479,14 +480,18 @@ int qed_mcp_bist_nvm_test_get_image_att(struct qed_hwfn *p_hwfn,
rel_pfid)
#define MCP_PF_ID(p_hwfn) MCP_PF_ID_BY_REL(p_hwfn, (p_hwfn)->rel_pf_id)
-/* TODO - this is only correct as long as only BB is supported, and
- * no port-swapping is implemented; Afterwards we'll need to fix it.
- */
-#define MFW_PORT(_p_hwfn) ((_p_hwfn)->abs_pf_id % \
- ((_p_hwfn)->cdev->num_ports_in_engines * 2))
+#define MFW_PORT(_p_hwfn) ((_p_hwfn)->abs_pf_id % \
+ ((_p_hwfn)->cdev->num_ports_in_engines * \
+ qed_device_num_engines((_p_hwfn)->cdev)))
+
struct qed_mcp_info {
- /* Spinlock used for protecting the access to the MFW mailbox */
- spinlock_t lock;
+ /* List for mailbox commands which were sent and wait for a response */
+ struct list_head cmd_list;
+
+ /* Spinlock used for protecting the access to the mailbox commands list
+ * and the sending of the commands.
+ */
+ spinlock_t cmd_lock;
/* Spinlock used for syncing SW link-changes and link-changes
* originating from attention context.
@@ -506,14 +511,16 @@ struct qed_mcp_info {
u8 *mfw_mb_cur;
u8 *mfw_mb_shadow;
u16 mfw_mb_length;
- u16 mcp_hist;
+ u32 mcp_hist;
};
struct qed_mcp_mb_params {
u32 cmd;
u32 param;
- union drv_union_data *p_data_src;
- union drv_union_data *p_data_dst;
+ void *p_data_src;
+ u8 data_src_size;
+ void *p_data_dst;
+ u8 data_dst_size;
u32 mcp_resp;
u32 mcp_param;
};
@@ -564,27 +571,55 @@ int qed_mcp_free(struct qed_hwfn *p_hwfn);
int qed_mcp_handle_events(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt);
+enum qed_drv_role {
+ QED_DRV_ROLE_OS,
+ QED_DRV_ROLE_KDUMP,
+};
+
+struct qed_load_req_params {
+ /* Input params */
+ enum qed_drv_role drv_role;
+ u8 timeout_val;
+ bool avoid_eng_reset;
+ enum qed_override_force_load override_force_load;
+
+ /* Output params */
+ u32 load_code;
+};
+
/**
- * @brief Sends a LOAD_REQ to the MFW, and in case operation
- * succeed, returns whether this PF is the first on the
- * chip/engine/port or function. This function should be
- * called when driver is ready to accept MFW events after
- * Storms initializations are done.
+ * @brief Sends a LOAD_REQ to the MFW, and in case the operation succeeds,
+ * returns whether this PF is the first on the engine/port or function.
*
- * @param p_hwfn - hw function
- * @param p_ptt - PTT required for register access
- * @param p_load_code - The MCP response param containing one
- * of the following:
- * FW_MSG_CODE_DRV_LOAD_ENGINE
- * FW_MSG_CODE_DRV_LOAD_PORT
- * FW_MSG_CODE_DRV_LOAD_FUNCTION
- * @return int -
- * 0 - Operation was successul.
- * -EBUSY - Operation failed
+ * @param p_hwfn
+ * @param p_ptt
+ * @param p_params
+ *
+ * @return int - 0 - Operation was successful.
*/
int qed_mcp_load_req(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt,
- u32 *p_load_code);
+ struct qed_load_req_params *p_params);
+
+/**
+ * @brief Sends a UNLOAD_REQ message to the MFW
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ *
+ * @return int - 0 - Operation was successful.
+ */
+int qed_mcp_unload_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+
+/**
+ * @brief Sends a UNLOAD_DONE message to the MFW
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ *
+ * @return int - 0 - Operation was successful.
+ */
+int qed_mcp_unload_done(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
/**
* @brief Read the MFW mailbox into Current buffer.
@@ -708,6 +743,41 @@ int qed_mcp_mask_parities(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt, u32 mask_parities);
/**
+ * @brief - Sets the MFW's max value for the given resource
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param res_id
+ * @param resc_max_val
+ * @param p_mcp_resp
+ *
+ * @return int - 0 - operation was successful.
+ */
+int
+qed_mcp_set_resc_max_val(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ enum qed_resources res_id,
+ u32 resc_max_val, u32 *p_mcp_resp);
+
+/**
+ * @brief - Gets the MFW allocation info for the given resource
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param res_id
+ * @param p_mcp_resp
+ * @param p_resc_num
+ * @param p_resc_start
+ *
+ * @return int - 0 - operation was successful.
+ */
+int
+qed_mcp_get_resc_info(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ enum qed_resources res_id,
+ u32 *p_mcp_resp, u32 *p_resc_num, u32 *p_resc_start);
+
+/**
* @brief Send eswitch mode to MFW
*
* @param p_hwfn
@@ -720,19 +790,86 @@ int qed_mcp_ov_update_eswitch(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt,
enum qed_ov_eswitch eswitch);
+#define QED_MCP_RESC_LOCK_MIN_VAL RESOURCE_DUMP
+#define QED_MCP_RESC_LOCK_MAX_VAL 31
+
+enum qed_resc_lock {
+ QED_RESC_LOCK_DBG_DUMP = QED_MCP_RESC_LOCK_MIN_VAL,
+ QED_RESC_LOCK_RESC_ALLOC = QED_MCP_RESC_LOCK_MAX_VAL
+};
+
/**
- * @brief - Gets the MFW allocation info for the given resource
+ * @brief - Initiates PF FLR
*
* @param p_hwfn
* @param p_ptt
- * @param p_resc_info - descriptor of requested resource
- * @param p_mcp_resp
- * @param p_mcp_param
*
* @return int - 0 - operation was successful.
*/
-int qed_mcp_get_resc_info(struct qed_hwfn *p_hwfn,
- struct qed_ptt *p_ptt,
- struct resource_info *p_resc_info,
- u32 *p_mcp_resp, u32 *p_mcp_param);
+int qed_mcp_initiate_pf_flr(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+struct qed_resc_lock_params {
+ /* Resource number [valid values are 0..31] */
+ u8 resource;
+
+ /* Lock timeout value in seconds [default, none or 1..254] */
+ u8 timeout;
+#define QED_MCP_RESC_LOCK_TO_DEFAULT 0
+#define QED_MCP_RESC_LOCK_TO_NONE 255
+
+ /* Number of times to retry locking */
+ u8 retry_num;
+
+ /* The interval in usec between retries */
+ u16 retry_interval;
+
+ /* Use sleep or delay between retries */
+ bool sleep_b4_retry;
+
+ /* Will be set as true if the resource is free and granted */
+ bool b_granted;
+
+ /* Will be filled with the resource owner.
+ * [0..15 = PF0-15, 16 = MFW]
+ */
+ u8 owner;
+};
+
+/**
+ * @brief Acquires MFW generic resource lock
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param p_params
+ *
+ * @return int - 0 - operation was successful.
+ */
+int
+qed_mcp_resc_lock(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt, struct qed_resc_lock_params *p_params);
+
+struct qed_resc_unlock_params {
+ /* Resource number [valid values are 0..31] */
+ u8 resource;
+
+ /* Allow to release a resource even if belongs to another PF */
+ bool b_force;
+
+ /* Will be set as true if the resource is released */
+ bool b_released;
+};
+
+/**
+ * @brief Releases MFW generic resource lock
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param p_params
+ *
+ * @return int - 0 - operation was successful.
+ */
+int
+qed_mcp_resc_unlock(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ struct qed_resc_unlock_params *p_params);
+
#endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.c b/drivers/net/ethernet/qlogic/qed/qed_ooo.c
index 7d731c6..db96670 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ooo.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.c
@@ -41,6 +41,7 @@
#include "qed_iscsi.h"
#include "qed_ll2.h"
#include "qed_ooo.h"
+#include "qed_cxt.h"
static struct qed_ooo_archipelago
*qed_ooo_seek_archipelago(struct qed_hwfn *p_hwfn,
@@ -48,15 +49,18 @@ static struct qed_ooo_archipelago
*p_ooo_info,
u32 cid)
{
- struct qed_ooo_archipelago *p_archipelago = NULL;
+ u32 idx = (cid & 0xffff) - p_ooo_info->cid_base;
+ struct qed_ooo_archipelago *p_archipelago;
- list_for_each_entry(p_archipelago,
- &p_ooo_info->archipelagos_list, list_entry) {
- if (p_archipelago->cid == cid)
- return p_archipelago;
- }
+ if (idx >= p_ooo_info->max_num_archipelagos)
+ return NULL;
- return NULL;
+ p_archipelago = &p_ooo_info->p_archipelagos_mem[idx];
+
+ if (list_empty(&p_archipelago->isles_list))
+ return NULL;
+
+ return p_archipelago;
}
static struct qed_ooo_isle *qed_ooo_seek_isle(struct qed_hwfn *p_hwfn,
@@ -97,8 +101,8 @@ void qed_ooo_save_history_entry(struct qed_hwfn *p_hwfn,
struct qed_ooo_info *qed_ooo_alloc(struct qed_hwfn *p_hwfn)
{
+ u16 max_num_archipelagos = 0, cid_base;
struct qed_ooo_info *p_ooo_info;
- u16 max_num_archipelagos = 0;
u16 max_num_isles = 0;
u32 i;
@@ -110,6 +114,7 @@ struct qed_ooo_info *qed_ooo_alloc(struct qed_hwfn *p_hwfn)
max_num_archipelagos = p_hwfn->pf_params.iscsi_pf_params.num_cons;
max_num_isles = QED_MAX_NUM_ISLES + max_num_archipelagos;
+ cid_base = (u16)qed_cxt_get_proto_cid_start(p_hwfn, PROTOCOLID_ISCSI);
if (!max_num_archipelagos) {
DP_NOTICE(p_hwfn,
@@ -121,11 +126,12 @@ struct qed_ooo_info *qed_ooo_alloc(struct qed_hwfn *p_hwfn)
if (!p_ooo_info)
return NULL;
+ p_ooo_info->cid_base = cid_base;
+ p_ooo_info->max_num_archipelagos = max_num_archipelagos;
+
INIT_LIST_HEAD(&p_ooo_info->free_buffers_list);
INIT_LIST_HEAD(&p_ooo_info->ready_buffers_list);
INIT_LIST_HEAD(&p_ooo_info->free_isles_list);
- INIT_LIST_HEAD(&p_ooo_info->free_archipelagos_list);
- INIT_LIST_HEAD(&p_ooo_info->archipelagos_list);
p_ooo_info->p_isles_mem = kcalloc(max_num_isles,
sizeof(struct qed_ooo_isle),
@@ -146,11 +152,8 @@ struct qed_ooo_info *qed_ooo_alloc(struct qed_hwfn *p_hwfn)
if (!p_ooo_info->p_archipelagos_mem)
goto no_archipelagos_mem;
- for (i = 0; i < max_num_archipelagos; i++) {
+ for (i = 0; i < max_num_archipelagos; i++)
INIT_LIST_HEAD(&p_ooo_info->p_archipelagos_mem[i].isles_list);
- list_add_tail(&p_ooo_info->p_archipelagos_mem[i].list_entry,
- &p_ooo_info->free_archipelagos_list);
- }
p_ooo_info->ooo_history.p_cqes =
kcalloc(QED_MAX_NUM_OOO_HISTORY_ENTRIES,
@@ -159,6 +162,8 @@ struct qed_ooo_info *qed_ooo_alloc(struct qed_hwfn *p_hwfn)
if (!p_ooo_info->ooo_history.p_cqes)
goto no_history_mem;
+ p_ooo_info->ooo_history.num_of_cqes = QED_MAX_NUM_OOO_HISTORY_ENTRIES;
+
return p_ooo_info;
no_history_mem:
@@ -176,21 +181,9 @@ void qed_ooo_release_connection_isles(struct qed_hwfn *p_hwfn,
struct qed_ooo_archipelago *p_archipelago;
struct qed_ooo_buffer *p_buffer;
struct qed_ooo_isle *p_isle;
- bool b_found = false;
- if (list_empty(&p_ooo_info->archipelagos_list))
- return;
-
- list_for_each_entry(p_archipelago,
- &p_ooo_info->archipelagos_list, list_entry) {
- if (p_archipelago->cid == cid) {
- list_del(&p_archipelago->list_entry);
- b_found = true;
- break;
- }
- }
-
- if (!b_found)
+ p_archipelago = qed_ooo_seek_archipelago(p_hwfn, p_ooo_info, cid);
+ if (!p_archipelago)
return;
while (!list_empty(&p_archipelago->isles_list)) {
@@ -214,27 +207,21 @@ void qed_ooo_release_connection_isles(struct qed_hwfn *p_hwfn,
list_add_tail(&p_isle->list_entry,
&p_ooo_info->free_isles_list);
}
-
- list_add_tail(&p_archipelago->list_entry,
- &p_ooo_info->free_archipelagos_list);
}
void qed_ooo_release_all_isles(struct qed_hwfn *p_hwfn,
struct qed_ooo_info *p_ooo_info)
{
- struct qed_ooo_archipelago *p_arch;
+ struct qed_ooo_archipelago *p_archipelago;
struct qed_ooo_buffer *p_buffer;
struct qed_ooo_isle *p_isle;
+ u32 i;
- while (!list_empty(&p_ooo_info->archipelagos_list)) {
- p_arch = list_first_entry(&p_ooo_info->archipelagos_list,
- struct qed_ooo_archipelago,
- list_entry);
+ for (i = 0; i < p_ooo_info->max_num_archipelagos; i++) {
+ p_archipelago = &(p_ooo_info->p_archipelagos_mem[i]);
- list_del(&p_arch->list_entry);
-
- while (!list_empty(&p_arch->isles_list)) {
- p_isle = list_first_entry(&p_arch->isles_list,
+ while (!list_empty(&p_archipelago->isles_list)) {
+ p_isle = list_first_entry(&p_archipelago->isles_list,
struct qed_ooo_isle,
list_entry);
@@ -256,8 +243,6 @@ void qed_ooo_release_all_isles(struct qed_hwfn *p_hwfn,
list_add_tail(&p_isle->list_entry,
&p_ooo_info->free_isles_list);
}
- list_add_tail(&p_arch->list_entry,
- &p_ooo_info->free_archipelagos_list);
}
if (!list_empty(&p_ooo_info->ready_buffers_list))
list_splice_tail_init(&p_ooo_info->ready_buffers_list,
@@ -376,12 +361,6 @@ void qed_ooo_delete_isles(struct qed_hwfn *p_hwfn,
p_ooo_info->cur_isles_number--;
list_add(&p_isle->list_entry, &p_ooo_info->free_isles_list);
}
-
- if (list_empty(&p_archipelago->isles_list)) {
- list_del(&p_archipelago->list_entry);
- list_add(&p_archipelago->list_entry,
- &p_ooo_info->free_archipelagos_list);
- }
}
void qed_ooo_add_new_isle(struct qed_hwfn *p_hwfn,
@@ -424,28 +403,10 @@ void qed_ooo_add_new_isle(struct qed_hwfn *p_hwfn,
return;
}
- if (!p_archipelago &&
- !list_empty(&p_ooo_info->free_archipelagos_list)) {
- p_archipelago =
- list_first_entry(&p_ooo_info->free_archipelagos_list,
- struct qed_ooo_archipelago, list_entry);
+ if (!p_archipelago) {
+ u32 idx = (cid & 0xffff) - p_ooo_info->cid_base;
- list_del(&p_archipelago->list_entry);
- if (!list_empty(&p_archipelago->isles_list)) {
- DP_NOTICE(p_hwfn,
- "Free OOO connection is not empty\n");
- INIT_LIST_HEAD(&p_archipelago->isles_list);
- }
- p_archipelago->cid = cid;
- list_add(&p_archipelago->list_entry,
- &p_ooo_info->archipelagos_list);
- } else if (!p_archipelago) {
- DP_NOTICE(p_hwfn, "No more free OOO connections\n");
- list_add(&p_isle->list_entry,
- &p_ooo_info->free_isles_list);
- list_add(&p_buffer->list_entry,
- &p_ooo_info->free_buffers_list);
- return;
+ p_archipelago = &p_ooo_info->p_archipelagos_mem[idx];
}
list_add(&p_buffer->list_entry, &p_isle->buffers_list);
@@ -515,11 +476,6 @@ void qed_ooo_join_isles(struct qed_hwfn *p_hwfn,
} else {
list_splice_tail_init(&p_right_isle->buffers_list,
&p_ooo_info->ready_buffers_list);
- if (list_empty(&p_archipelago->isles_list)) {
- list_del(&p_archipelago->list_entry);
- list_add(&p_archipelago->list_entry,
- &p_ooo_info->free_archipelagos_list);
- }
}
list_add_tail(&p_right_isle->list_entry, &p_ooo_info->free_isles_list);
}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.h b/drivers/net/ethernet/qlogic/qed/qed_ooo.h
index 4f138fb..791ad0f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ooo.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.h
@@ -60,9 +60,7 @@ struct qed_ooo_isle {
};
struct qed_ooo_archipelago {
- struct list_head list_entry;
struct list_head isles_list;
- u32 cid;
};
struct qed_ooo_history {
@@ -75,14 +73,14 @@ struct qed_ooo_info {
struct list_head free_buffers_list;
struct list_head ready_buffers_list;
struct list_head free_isles_list;
- struct list_head free_archipelagos_list;
- struct list_head archipelagos_list;
struct qed_ooo_archipelago *p_archipelagos_mem;
struct qed_ooo_isle *p_isles_mem;
struct qed_ooo_history ooo_history;
u32 cur_isles_number;
u32 max_isles_number;
u32 gen_isles_number;
+ u16 max_num_archipelagos;
+ u16 cid_base;
};
#if IS_ENABLED(CONFIG_QED_ISCSI)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ptp.c b/drivers/net/ethernet/qlogic/qed/qed_ptp.c
index d27aa85..80c9c0b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ptp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ptp.c
@@ -262,12 +262,20 @@ static int qed_ptp_hw_enable(struct qed_dev *cdev)
qed_wr(p_hwfn, p_ptt, NIG_REG_TS_OUTPUT_ENABLE_PDA, 0x1);
/* Pause free running counter */
- qed_wr(p_hwfn, p_ptt, NIG_REG_TIMESYNC_GEN_REG_BB, 2);
+ if (QED_IS_BB_B0(p_hwfn->cdev))
+ qed_wr(p_hwfn, p_ptt, NIG_REG_TIMESYNC_GEN_REG_BB, 2);
+ if (QED_IS_AH(p_hwfn->cdev))
+ qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_FREECNT_UPDATE_K2, 2);
qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_FREE_CNT_VALUE_LSB, 0);
qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_FREE_CNT_VALUE_MSB, 0);
/* Resume free running counter */
- qed_wr(p_hwfn, p_ptt, NIG_REG_TIMESYNC_GEN_REG_BB, 4);
+ if (QED_IS_BB_B0(p_hwfn->cdev))
+ qed_wr(p_hwfn, p_ptt, NIG_REG_TIMESYNC_GEN_REG_BB, 4);
+ if (QED_IS_AH(p_hwfn->cdev)) {
+ qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_FREECNT_UPDATE_K2, 4);
+ qed_wr(p_hwfn, p_ptt, NIG_REG_PTP_LATCH_OSTS_PKT_TIME, 1);
+ }
/* Disable drift register */
qed_wr(p_hwfn, p_ptt, NIG_REG_TSGEN_DRIFT_CNTR_CONF, 0x0);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
index d59d9df..e65397360 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
@@ -160,13 +160,13 @@
0x2e0704UL
#define CCFC_REG_STRONG_ENABLE_PF \
0x2e0708UL
-#define PGLUE_B_REG_PGL_ADDR_88_F0 \
+#define PGLUE_B_REG_PGL_ADDR_88_F0_BB \
0x2aa404UL
-#define PGLUE_B_REG_PGL_ADDR_8C_F0 \
+#define PGLUE_B_REG_PGL_ADDR_8C_F0_BB \
0x2aa408UL
-#define PGLUE_B_REG_PGL_ADDR_90_F0 \
+#define PGLUE_B_REG_PGL_ADDR_90_F0_BB \
0x2aa40cUL
-#define PGLUE_B_REG_PGL_ADDR_94_F0 \
+#define PGLUE_B_REG_PGL_ADDR_94_F0_BB \
0x2aa410UL
#define PGLUE_B_REG_WAS_ERROR_PF_31_0_CLR \
0x2aa138UL
@@ -356,6 +356,10 @@
0x238804UL
#define RDIF_REG_STOP_ON_ERROR \
0x300040UL
+#define RDIF_REG_DEBUG_ERROR_INFO \
+ 0x300400UL
+#define RDIF_REG_DEBUG_ERROR_INFO_SIZE \
+ 64
#define SRC_REG_SOFT_RST \
0x23874cUL
#define TCFC_REG_ACTIVITY_COUNTER \
@@ -370,6 +374,10 @@
0x1700004UL
#define TDIF_REG_STOP_ON_ERROR \
0x310040UL
+#define TDIF_REG_DEBUG_ERROR_INFO \
+ 0x310400UL
+#define TDIF_REG_DEBUG_ERROR_INFO_SIZE \
+ 64
#define UCM_REG_INIT \
0x1280000UL
#define UMAC_REG_IPG_HD_BKP_CNTL_BB_B0 \
@@ -1236,6 +1244,26 @@
0x1901534UL
#define USEM_REG_DBG_FORCE_FRAME \
0x1901538UL
+#define NWS_REG_DBG_SELECT \
+ 0x700128UL
+#define NWS_REG_DBG_DWORD_ENABLE \
+ 0x70012cUL
+#define NWS_REG_DBG_SHIFT \
+ 0x700130UL
+#define NWS_REG_DBG_FORCE_VALID \
+ 0x700134UL
+#define NWS_REG_DBG_FORCE_FRAME \
+ 0x700138UL
+#define MS_REG_DBG_SELECT \
+ 0x6a0228UL
+#define MS_REG_DBG_DWORD_ENABLE \
+ 0x6a022cUL
+#define MS_REG_DBG_SHIFT \
+ 0x6a0230UL
+#define MS_REG_DBG_FORCE_VALID \
+ 0x6a0234UL
+#define MS_REG_DBG_FORCE_FRAME \
+ 0x6a0238UL
#define PCIE_REG_DBG_COMMON_SELECT \
0x054398UL
#define PCIE_REG_DBG_COMMON_DWORD_ENABLE \
@@ -1448,6 +1476,8 @@
0x000b48UL
#define RSS_REG_RSS_RAM_DATA \
0x238c20UL
+#define RSS_REG_RSS_RAM_DATA_SIZE \
+ 4
#define MISC_REG_BLOCK_256B_EN \
0x008c14UL
#define NWS_REG_NWS_CMU \
@@ -1520,4 +1550,14 @@
#define NIG_REG_TIMESYNC_GEN_REG_BB 0x500d00UL
#define NIG_REG_TSGEN_FREE_CNT_VALUE_LSB 0x5088a8UL
#define NIG_REG_TSGEN_FREE_CNT_VALUE_MSB 0x5088acUL
+#define NIG_REG_PTP_LATCH_OSTS_PKT_TIME 0x509040UL
+#define PSWRQ2_REG_WR_MBS0 0x240400UL
+
+#define PGLUE_B_REG_PGL_ADDR_E8_F0_K2 0x2aaf98UL
+#define PGLUE_B_REG_PGL_ADDR_EC_F0_K2 0x2aaf9cUL
+#define PGLUE_B_REG_PGL_ADDR_F0_F0_K2 0x2aafa0UL
+#define PGLUE_B_REG_PGL_ADDR_F4_F0_K2 0x2aafa4UL
+#define NIG_REG_TSGEN_FREECNT_UPDATE_K2 0x509008UL
+#define CNIG_REG_NIG_PORT0_CONF_K2 0x218200UL
+
#endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index d9ff6b2..b8c811f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -66,13 +66,27 @@
#include "qed_roce.h"
#include "qed_ll2.h"
-void qed_async_roce_event(struct qed_hwfn *p_hwfn,
- struct event_ring_entry *p_eqe)
-{
- struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info;
+static void qed_roce_free_real_icid(struct qed_hwfn *p_hwfn, u16 icid);
- p_rdma_info->events.affiliated_event(p_rdma_info->events.context,
- p_eqe->opcode, &p_eqe->data);
+void qed_roce_async_event(struct qed_hwfn *p_hwfn,
+ u8 fw_event_code, union rdma_eqe_data *rdma_data)
+{
+ if (fw_event_code == ROCE_ASYNC_EVENT_DESTROY_QP_DONE) {
+ u16 icid =
+ (u16)le32_to_cpu(rdma_data->rdma_destroy_qp_data.cid);
+
+ /* icid release in this async event can occur only if the icid
+ * was offloaded to the FW. In case it wasn't offloaded this is
+ * handled in qed_roce_sp_destroy_qp.
+ */
+ qed_roce_free_real_icid(p_hwfn, icid);
+ } else {
+ struct qed_rdma_events *events = &p_hwfn->p_rdma_info->events;
+
+ events->affiliated_event(p_hwfn->p_rdma_info->events.context,
+ fw_event_code,
+ &rdma_data->async_handle);
+ }
}
static int qed_rdma_bmap_alloc(struct qed_hwfn *p_hwfn,
@@ -113,6 +127,15 @@ static int qed_rdma_bmap_alloc_id(struct qed_hwfn *p_hwfn,
return 0;
}
+static void qed_bmap_set_id(struct qed_hwfn *p_hwfn,
+ struct qed_bmap *bmap, u32 id_num)
+{
+ if (id_num >= bmap->max_count)
+ return;
+
+ __set_bit(id_num, bmap->bitmap);
+}
+
static void qed_bmap_release_id(struct qed_hwfn *p_hwfn,
struct qed_bmap *bmap, u32 id_num)
{
@@ -129,6 +152,15 @@ static void qed_bmap_release_id(struct qed_hwfn *p_hwfn,
}
}
+static int qed_bmap_test_id(struct qed_hwfn *p_hwfn,
+ struct qed_bmap *bmap, u32 id_num)
+{
+ if (id_num >= bmap->max_count)
+ return -1;
+
+ return test_bit(id_num, bmap->bitmap);
+}
+
static u32 qed_rdma_get_sb_id(void *p_hwfn, u32 rel_sb_id)
{
/* First sb id for RoCE is after all the l2 sb */
@@ -170,7 +202,8 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
/* Queue zone lines are shared between RoCE and L2 in such a way that
* they can be used by each without obstructing the other.
*/
- p_rdma_info->queue_zone_base = (u16)FEAT_NUM(p_hwfn, QED_L2_QUEUE);
+ p_rdma_info->queue_zone_base = (u16)RESC_START(p_hwfn, QED_L2_QUEUE);
+ p_rdma_info->max_queue_zones = (u16)RESC_NUM(p_hwfn, QED_L2_QUEUE);
/* Allocate a struct with device params and fill it */
p_rdma_info->dev = kzalloc(sizeof(*p_rdma_info->dev), GFP_KERNEL);
@@ -248,9 +281,18 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
goto free_tid_map;
}
+ /* Allocate bitmap for cids used for responders/requesters. */
+ rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->real_cid_map, num_cons);
+ if (rc) {
+ DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
+ "Failed to allocate real cid bitmap, rc = %d\n", rc);
+ goto free_cid_map;
+ }
DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Allocation successful\n");
return 0;
+free_cid_map:
+ kfree(p_rdma_info->cid_map.bitmap);
free_tid_map:
kfree(p_rdma_info->tid_map.bitmap);
free_toggle_map:
@@ -273,7 +315,22 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
static void qed_rdma_resc_free(struct qed_hwfn *p_hwfn)
{
+ struct qed_bmap *rcid_map = &p_hwfn->p_rdma_info->real_cid_map;
struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info;
+ int wait_count = 0;
+
+ /* when destroying a_RoCE QP the control is returned to the user after
+ * the synchronous part. The asynchronous part may take a little longer.
+ * We delay for a short while if an async destroy QP is still expected.
+ * Beyond the added delay we clear the bitmap anyway.
+ */
+ while (bitmap_weight(rcid_map->bitmap, rcid_map->max_count)) {
+ msleep(100);
+ if (wait_count++ > 20) {
+ DP_NOTICE(p_hwfn, "cid bitmap wait timed out\n");
+ break;
+ }
+ }
kfree(p_rdma_info->cid_map.bitmap);
kfree(p_rdma_info->tid_map.bitmap);
@@ -724,6 +781,14 @@ static void qed_rdma_cnq_prod_update(void *rdma_cxt, u8 qz_offset, u16 prod)
u32 addr;
p_hwfn = (struct qed_hwfn *)rdma_cxt;
+
+ if (qz_offset > p_hwfn->p_rdma_info->max_queue_zones) {
+ DP_NOTICE(p_hwfn,
+ "queue zone offset %d is too large (max is %d)\n",
+ qz_offset, p_hwfn->p_rdma_info->max_queue_zones);
+ return;
+ }
+
qz_num = p_hwfn->p_rdma_info->queue_zone_base + qz_offset;
addr = GTT_BAR0_MAP_REG_USDM_RAM +
USTORM_COMMON_QUEUE_CONS_OFFSET(qz_num);
@@ -1080,6 +1145,14 @@ static enum roce_flavor qed_roce_mode_to_flavor(enum roce_mode roce_mode)
return flavor;
}
+void qed_roce_free_cid_pair(struct qed_hwfn *p_hwfn, u16 cid)
+{
+ spin_lock_bh(&p_hwfn->p_rdma_info->lock);
+ qed_bmap_release_id(p_hwfn, &p_hwfn->p_rdma_info->cid_map, cid);
+ qed_bmap_release_id(p_hwfn, &p_hwfn->p_rdma_info->cid_map, cid + 1);
+ spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
+}
+
static int qed_roce_alloc_cid(struct qed_hwfn *p_hwfn, u16 *cid)
{
struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info;
@@ -1139,15 +1212,22 @@ static int qed_roce_alloc_cid(struct qed_hwfn *p_hwfn, u16 *cid)
return rc;
}
+static void qed_roce_set_real_cid(struct qed_hwfn *p_hwfn, u32 cid)
+{
+ spin_lock_bh(&p_hwfn->p_rdma_info->lock);
+ qed_bmap_set_id(p_hwfn, &p_hwfn->p_rdma_info->real_cid_map, cid);
+ spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
+}
+
static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
struct qed_rdma_qp *qp)
{
struct roce_create_qp_resp_ramrod_data *p_ramrod;
struct qed_sp_init_data init_data;
- union qed_qm_pq_params qm_params;
enum roce_flavor roce_flavor;
struct qed_spq_entry *p_ent;
- u16 physical_queue0 = 0;
+ u16 regular_latency_queue;
+ enum protocol_type proto;
int rc;
DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
@@ -1229,15 +1309,16 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
p_ramrod->qp_handle_for_async.lo = cpu_to_le32(qp->qp_handle_async.lo);
p_ramrod->qp_handle_for_cqe.hi = cpu_to_le32(qp->qp_handle.hi);
p_ramrod->qp_handle_for_cqe.lo = cpu_to_le32(qp->qp_handle.lo);
- p_ramrod->stats_counter_id = p_hwfn->rel_pf_id;
p_ramrod->cq_cid = cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) |
qp->rq_cq_id);
- memset(&qm_params, 0, sizeof(qm_params));
- qm_params.roce.qpid = qp->icid >> 1;
- physical_queue0 = qed_get_qm_pq(p_hwfn, PROTOCOLID_ROCE, &qm_params);
+ regular_latency_queue = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
- p_ramrod->physical_queue0 = cpu_to_le16(physical_queue0);
+ p_ramrod->regular_latency_phy_queue =
+ cpu_to_le16(regular_latency_queue);
+ p_ramrod->low_latency_phy_queue =
+ cpu_to_le16(regular_latency_queue);
+
p_ramrod->dpi = cpu_to_le16(qp->dpi);
qed_rdma_set_fw_mac(p_ramrod->remote_mac_addr, qp->remote_mac_addr);
@@ -1253,13 +1334,19 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
rc = qed_spq_post(p_hwfn, p_ent, NULL);
- DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "rc = %d physical_queue0 = 0x%x\n",
- rc, physical_queue0);
+ DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
+ "rc = %d regular physical queue = 0x%x\n", rc,
+ regular_latency_queue);
if (rc)
goto err;
qp->resp_offloaded = true;
+ qp->cq_prod = 0;
+
+ proto = p_hwfn->p_rdma_info->proto;
+ qed_roce_set_real_cid(p_hwfn, qp->icid -
+ qed_cxt_get_proto_cid_start(p_hwfn, proto));
return rc;
@@ -1277,10 +1364,10 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
{
struct roce_create_qp_req_ramrod_data *p_ramrod;
struct qed_sp_init_data init_data;
- union qed_qm_pq_params qm_params;
enum roce_flavor roce_flavor;
struct qed_spq_entry *p_ent;
- u16 physical_queue0 = 0;
+ u16 regular_latency_queue;
+ enum protocol_type proto;
int rc;
DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
@@ -1351,15 +1438,16 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
p_ramrod->qp_handle_for_async.lo = cpu_to_le32(qp->qp_handle_async.lo);
p_ramrod->qp_handle_for_cqe.hi = cpu_to_le32(qp->qp_handle.hi);
p_ramrod->qp_handle_for_cqe.lo = cpu_to_le32(qp->qp_handle.lo);
- p_ramrod->stats_counter_id = p_hwfn->rel_pf_id;
- p_ramrod->cq_cid = cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) |
- qp->sq_cq_id);
+ p_ramrod->cq_cid =
+ cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) | qp->sq_cq_id);
- memset(&qm_params, 0, sizeof(qm_params));
- qm_params.roce.qpid = qp->icid >> 1;
- physical_queue0 = qed_get_qm_pq(p_hwfn, PROTOCOLID_ROCE, &qm_params);
+ regular_latency_queue = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
- p_ramrod->physical_queue0 = cpu_to_le16(physical_queue0);
+ p_ramrod->regular_latency_phy_queue =
+ cpu_to_le16(regular_latency_queue);
+ p_ramrod->low_latency_phy_queue =
+ cpu_to_le16(regular_latency_queue);
+
p_ramrod->dpi = cpu_to_le16(qp->dpi);
qed_rdma_set_fw_mac(p_ramrod->remote_mac_addr, qp->remote_mac_addr);
@@ -1378,6 +1466,10 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
goto err;
qp->req_offloaded = true;
+ proto = p_hwfn->p_rdma_info->proto;
+ qed_roce_set_real_cid(p_hwfn,
+ qp->icid + 1 -
+ qed_cxt_get_proto_cid_start(p_hwfn, proto));
return rc;
@@ -1577,7 +1669,8 @@ static int qed_roce_sp_modify_requester(struct qed_hwfn *p_hwfn,
static int qed_roce_sp_destroy_qp_responder(struct qed_hwfn *p_hwfn,
struct qed_rdma_qp *qp,
- u32 *num_invalidated_mw)
+ u32 *num_invalidated_mw,
+ u32 *cq_prod)
{
struct roce_destroy_qp_resp_output_params *p_ramrod_res;
struct roce_destroy_qp_resp_ramrod_data *p_ramrod;
@@ -1588,8 +1681,22 @@ static int qed_roce_sp_destroy_qp_responder(struct qed_hwfn *p_hwfn,
DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
- if (!qp->resp_offloaded)
+ *num_invalidated_mw = 0;
+ *cq_prod = qp->cq_prod;
+
+ if (!qp->resp_offloaded) {
+ /* If a responder was never offload, we need to free the cids
+ * allocated in create_qp as a FW async event will never arrive
+ */
+ u32 cid;
+
+ cid = qp->icid -
+ qed_cxt_get_proto_cid_start(p_hwfn,
+ p_hwfn->p_rdma_info->proto);
+ qed_roce_free_cid_pair(p_hwfn, (u16)cid);
+
return 0;
+ }
/* Get SPQ entry */
memset(&init_data, 0, sizeof(init_data));
@@ -1624,6 +1731,8 @@ static int qed_roce_sp_destroy_qp_responder(struct qed_hwfn *p_hwfn,
goto err;
*num_invalidated_mw = le32_to_cpu(p_ramrod_res->num_invalidated_mw);
+ *cq_prod = le32_to_cpu(p_ramrod_res->cq_prod);
+ qp->cq_prod = *cq_prod;
/* Free IRQ - only if ramrod succeeded, in case FW is still using it */
dma_free_coherent(&p_hwfn->cdev->pdev->dev,
@@ -1827,10 +1936,8 @@ static int qed_roce_query_qp(struct qed_hwfn *p_hwfn,
out_params->draining = false;
- if (rq_err_state)
+ if (rq_err_state || sq_err_state)
qp->cur_state = QED_ROCE_QP_STATE_ERR;
- else if (sq_err_state)
- qp->cur_state = QED_ROCE_QP_STATE_SQE;
else if (sq_draining)
out_params->draining = true;
out_params->state = qp->cur_state;
@@ -1849,10 +1956,9 @@ static int qed_roce_query_qp(struct qed_hwfn *p_hwfn,
static int qed_roce_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
{
- struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info;
u32 num_invalidated_mw = 0;
u32 num_bound_mw = 0;
- u32 start_cid;
+ u32 cq_prod;
int rc;
/* Destroys the specified QP */
@@ -1866,7 +1972,8 @@ static int qed_roce_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
if (qp->cur_state != QED_ROCE_QP_STATE_RESET) {
rc = qed_roce_sp_destroy_qp_responder(p_hwfn, qp,
- &num_invalidated_mw);
+ &num_invalidated_mw,
+ &cq_prod);
if (rc)
return rc;
@@ -1881,21 +1988,6 @@ static int qed_roce_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
"number of invalidate memory windows is different from bounded ones\n");
return -EINVAL;
}
-
- spin_lock_bh(&p_rdma_info->lock);
-
- start_cid = qed_cxt_get_proto_cid_start(p_hwfn,
- p_rdma_info->proto);
-
- /* Release responder's icid */
- qed_bmap_release_id(p_hwfn, &p_rdma_info->cid_map,
- qp->icid - start_cid);
-
- /* Release requester's icid */
- qed_bmap_release_id(p_hwfn, &p_rdma_info->cid_map,
- qp->icid + 1 - start_cid);
-
- spin_unlock_bh(&p_rdma_info->lock);
}
return 0;
@@ -2110,12 +2202,19 @@ static int qed_roce_modify_qp(struct qed_hwfn *p_hwfn,
return rc;
} else if (qp->cur_state == QED_ROCE_QP_STATE_RESET) {
/* Any state -> RESET */
+ u32 cq_prod;
- rc = qed_roce_sp_destroy_qp_responder(p_hwfn, qp,
- &num_invalidated_mw);
+ /* Send destroy responder ramrod */
+ rc = qed_roce_sp_destroy_qp_responder(p_hwfn,
+ qp,
+ &num_invalidated_mw,
+ &cq_prod);
+
if (rc)
return rc;
+ qp->cq_prod = cq_prod;
+
rc = qed_roce_sp_destroy_qp_requester(p_hwfn, qp,
&num_bound_mw);
@@ -2454,6 +2553,31 @@ static int qed_rdma_deregister_tid(void *rdma_cxt, u32 itid)
return rc;
}
+static void qed_roce_free_real_icid(struct qed_hwfn *p_hwfn, u16 icid)
+{
+ struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info;
+ u32 start_cid, cid, xcid;
+
+ /* an even icid belongs to a responder while an odd icid belongs to a
+ * requester. The 'cid' received as an input can be either. We calculate
+ * the "partner" icid and call it xcid. Only if both are free then the
+ * "cid" map can be cleared.
+ */
+ start_cid = qed_cxt_get_proto_cid_start(p_hwfn, p_rdma_info->proto);
+ cid = icid - start_cid;
+ xcid = cid ^ 1;
+
+ spin_lock_bh(&p_rdma_info->lock);
+
+ qed_bmap_release_id(p_hwfn, &p_rdma_info->real_cid_map, cid);
+ if (qed_bmap_test_id(p_hwfn, &p_rdma_info->real_cid_map, xcid) == 0) {
+ qed_bmap_release_id(p_hwfn, &p_rdma_info->cid_map, cid);
+ qed_bmap_release_id(p_hwfn, &p_rdma_info->cid_map, xcid);
+ }
+
+ spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
+}
+
static void *qed_rdma_get_rdma_ctx(struct qed_dev *cdev)
{
return QED_LEADING_HWFN(cdev);
@@ -2773,7 +2897,7 @@ static int qed_roce_ll2_tx(struct qed_dev *cdev,
: QED_LL2_RROCE;
if (pkt->roce_mode == ROCE_V2_IPV4)
- flags |= BIT(CORE_TX_BD_FLAGS_IP_CSUM_SHIFT);
+ flags |= BIT(CORE_TX_BD_DATA_IP_CSUM_SHIFT);
/* Tx header */
rc = qed_ll2_prepare_tx_packet(QED_LEADING_HWFN(cdev), roce_ll2->handle,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.h b/drivers/net/ethernet/qlogic/qed/qed_roce.h
index 36cf4b2..3ccc08a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.h
@@ -82,6 +82,7 @@ struct qed_rdma_info {
struct qed_bmap qp_map;
struct qed_bmap srq_map;
struct qed_bmap cid_map;
+ struct qed_bmap real_cid_map;
struct qed_bmap dpi_map;
struct qed_bmap toggle_bits;
struct qed_rdma_events events;
@@ -92,6 +93,7 @@ struct qed_rdma_info {
u32 num_qps;
u32 num_mrs;
u16 queue_zone_base;
+ u16 max_queue_zones;
enum protocol_type proto;
};
@@ -153,6 +155,7 @@ struct qed_rdma_qp {
dma_addr_t irq_phys_addr;
u8 irq_num_pages;
bool resp_offloaded;
+ u32 cq_prod;
u8 remote_mac_addr[6];
u8 local_mac_addr[6];
@@ -163,8 +166,8 @@ struct qed_rdma_qp {
#if IS_ENABLED(CONFIG_QED_RDMA)
void qed_rdma_dpm_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
-void qed_async_roce_event(struct qed_hwfn *p_hwfn,
- struct event_ring_entry *p_eqe);
+void qed_roce_async_event(struct qed_hwfn *p_hwfn,
+ u8 fw_event_code, union rdma_eqe_data *rdma_data);
void qed_ll2b_complete_tx_gsi_packet(struct qed_hwfn *p_hwfn,
u8 connection_handle,
void *cookie,
@@ -187,7 +190,9 @@ void qed_ll2b_complete_rx_gsi_packet(struct qed_hwfn *p_hwfn,
u16 src_mac_addr_lo, bool b_last_packet);
#else
static inline void qed_rdma_dpm_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) {}
-static inline void qed_async_roce_event(struct qed_hwfn *p_hwfn, struct event_ring_entry *p_eqe) {}
+static inline void qed_roce_async_event(struct qed_hwfn *p_hwfn,
+ u8 fw_event_code,
+ union rdma_eqe_data *rdma_data) {}
static inline void qed_ll2b_complete_tx_gsi_packet(struct qed_hwfn *p_hwfn,
u8 connection_handle,
void *cookie,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index 645328a..f6423a1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -119,6 +119,7 @@ static int qed_spq_block(struct qed_hwfn *p_hwfn,
u8 *p_fw_ret, bool skip_quick_poll)
{
struct qed_spq_comp_done *comp_done;
+ struct qed_ptt *p_ptt;
int rc;
/* A relatively short polling period w/o sleeping, to allow the FW to
@@ -135,8 +136,14 @@ static int qed_spq_block(struct qed_hwfn *p_hwfn,
if (!rc)
return 0;
+ p_ptt = qed_ptt_acquire(p_hwfn);
+ if (!p_ptt) {
+ DP_NOTICE(p_hwfn, "ptt, failed to acquire\n");
+ return -EAGAIN;
+ }
+
DP_INFO(p_hwfn, "Ramrod is stuck, requesting MCP drain\n");
- rc = qed_mcp_drain(p_hwfn, p_hwfn->p_main_ptt);
+ rc = qed_mcp_drain(p_hwfn, p_ptt);
if (rc) {
DP_NOTICE(p_hwfn, "MCP drain failed\n");
goto err;
@@ -145,15 +152,18 @@ static int qed_spq_block(struct qed_hwfn *p_hwfn,
/* Retry after drain */
rc = __qed_spq_block(p_hwfn, p_ent, p_fw_ret, true);
if (!rc)
- return 0;
+ goto out;
comp_done = (struct qed_spq_comp_done *)p_ent->comp_cb.cookie;
- if (comp_done->done == 1) {
+ if (comp_done->done == 1)
if (p_fw_ret)
*p_fw_ret = comp_done->fw_return_code;
- return 0;
- }
+out:
+ qed_ptt_release(p_hwfn, p_ptt);
+ return 0;
+
err:
+ qed_ptt_release(p_hwfn, p_ptt);
DP_NOTICE(p_hwfn,
"Ramrod is stuck [CID %08x cmd %02x protocol %02x echo %04x]\n",
le32_to_cpu(p_ent->elem.hdr.cid),
@@ -205,11 +215,10 @@ static int qed_spq_fill_entry(struct qed_hwfn *p_hwfn,
static void qed_spq_hw_initialize(struct qed_hwfn *p_hwfn,
struct qed_spq *p_spq)
{
- u16 pq;
- struct qed_cxt_info cxt_info;
- struct core_conn_context *p_cxt;
- union qed_qm_pq_params pq_params;
- int rc;
+ struct core_conn_context *p_cxt;
+ struct qed_cxt_info cxt_info;
+ u16 physical_q;
+ int rc;
cxt_info.iid = p_spq->cid;
@@ -231,10 +240,8 @@ static void qed_spq_hw_initialize(struct qed_hwfn *p_hwfn,
XSTORM_CORE_CONN_AG_CTX_CONSOLID_PROD_CF_EN, 1);
/* QM physical queue */
- memset(&pq_params, 0, sizeof(pq_params));
- pq_params.core.tc = LB_TC;
- pq = qed_get_qm_pq(p_hwfn, PROTOCOLID_CORE, &pq_params);
- p_cxt->xstorm_ag_context.physical_q0 = cpu_to_le16(pq);
+ physical_q = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_LB);
+ p_cxt->xstorm_ag_context.physical_q0 = cpu_to_le16(physical_q);
p_cxt->xstorm_st_context.spq_base_lo =
DMA_LO_LE(p_spq->chain.p_phys_addr);
@@ -296,9 +303,12 @@ qed_async_event_completion(struct qed_hwfn *p_hwfn,
struct event_ring_entry *p_eqe)
{
switch (p_eqe->protocol_id) {
+#if IS_ENABLED(CONFIG_QED_RDMA)
case PROTOCOLID_ROCE:
- qed_async_roce_event(p_hwfn, p_eqe);
+ qed_roce_async_event(p_hwfn, p_eqe->opcode,
+ &p_eqe->data.rdma_data);
return 0;
+#endif
case PROTOCOLID_COMMON:
return qed_sriov_eqe_event(p_hwfn,
p_eqe->opcode,
@@ -306,14 +316,6 @@ qed_async_event_completion(struct qed_hwfn *p_hwfn,
case PROTOCOLID_ISCSI:
if (!IS_ENABLED(CONFIG_QED_ISCSI))
return -EINVAL;
- if (p_eqe->opcode == ISCSI_EVENT_TYPE_ASYN_DELETE_OOO_ISLES) {
- u32 cid = le32_to_cpu(p_eqe->data.iscsi_info.cid);
-
- qed_ooo_release_connection_isles(p_hwfn,
- p_hwfn->p_ooo_info,
- cid);
- return 0;
- }
if (p_hwfn->p_iscsi_info->event_cb) {
struct qed_iscsi_info *p_iscsi = p_hwfn->p_iscsi_info;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index 253c2bb..92a3ee1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -178,26 +178,59 @@ static struct qed_vf_info *qed_iov_get_vf_info(struct qed_hwfn *p_hwfn,
return vf;
}
-static bool qed_iov_validate_rxq(struct qed_hwfn *p_hwfn,
- struct qed_vf_info *p_vf, u16 rx_qid)
+enum qed_iov_validate_q_mode {
+ QED_IOV_VALIDATE_Q_NA,
+ QED_IOV_VALIDATE_Q_ENABLE,
+ QED_IOV_VALIDATE_Q_DISABLE,
+};
+
+static bool qed_iov_validate_queue_mode(struct qed_hwfn *p_hwfn,
+ struct qed_vf_info *p_vf,
+ u16 qid,
+ enum qed_iov_validate_q_mode mode,
+ bool b_is_tx)
{
- if (rx_qid >= p_vf->num_rxqs)
+ if (mode == QED_IOV_VALIDATE_Q_NA)
+ return true;
+
+ if ((b_is_tx && p_vf->vf_queues[qid].p_tx_cid) ||
+ (!b_is_tx && p_vf->vf_queues[qid].p_rx_cid))
+ return mode == QED_IOV_VALIDATE_Q_ENABLE;
+
+ /* In case we haven't found any valid cid, then its disabled */
+ return mode == QED_IOV_VALIDATE_Q_DISABLE;
+}
+
+static bool qed_iov_validate_rxq(struct qed_hwfn *p_hwfn,
+ struct qed_vf_info *p_vf,
+ u16 rx_qid,
+ enum qed_iov_validate_q_mode mode)
+{
+ if (rx_qid >= p_vf->num_rxqs) {
DP_VERBOSE(p_hwfn,
QED_MSG_IOV,
"VF[0x%02x] - can't touch Rx queue[%04x]; Only 0x%04x are allocated\n",
p_vf->abs_vf_id, rx_qid, p_vf->num_rxqs);
- return rx_qid < p_vf->num_rxqs;
+ return false;
+ }
+
+ return qed_iov_validate_queue_mode(p_hwfn, p_vf, rx_qid, mode, false);
}
static bool qed_iov_validate_txq(struct qed_hwfn *p_hwfn,
- struct qed_vf_info *p_vf, u16 tx_qid)
+ struct qed_vf_info *p_vf,
+ u16 tx_qid,
+ enum qed_iov_validate_q_mode mode)
{
- if (tx_qid >= p_vf->num_txqs)
+ if (tx_qid >= p_vf->num_txqs) {
DP_VERBOSE(p_hwfn,
QED_MSG_IOV,
"VF[0x%02x] - can't touch Tx queue[%04x]; Only 0x%04x are allocated\n",
p_vf->abs_vf_id, tx_qid, p_vf->num_txqs);
- return tx_qid < p_vf->num_txqs;
+ return false;
+ }
+
+ return qed_iov_validate_queue_mode(p_hwfn, p_vf, tx_qid, mode, true);
}
static bool qed_iov_validate_sb(struct qed_hwfn *p_hwfn,
@@ -217,6 +250,34 @@ static bool qed_iov_validate_sb(struct qed_hwfn *p_hwfn,
return false;
}
+static bool qed_iov_validate_active_rxq(struct qed_hwfn *p_hwfn,
+ struct qed_vf_info *p_vf)
+{
+ u8 i;
+
+ for (i = 0; i < p_vf->num_rxqs; i++)
+ if (qed_iov_validate_queue_mode(p_hwfn, p_vf, i,
+ QED_IOV_VALIDATE_Q_ENABLE,
+ false))
+ return true;
+
+ return false;
+}
+
+static bool qed_iov_validate_active_txq(struct qed_hwfn *p_hwfn,
+ struct qed_vf_info *p_vf)
+{
+ u8 i;
+
+ for (i = 0; i < p_vf->num_txqs; i++)
+ if (qed_iov_validate_queue_mode(p_hwfn, p_vf, i,
+ QED_IOV_VALIDATE_Q_ENABLE,
+ true))
+ return true;
+
+ return false;
+}
+
static int qed_iov_post_vf_bulletin(struct qed_hwfn *p_hwfn,
int vfid, struct qed_ptt *p_ptt)
{
@@ -557,14 +618,30 @@ int qed_iov_hw_info(struct qed_hwfn *p_hwfn)
return 0;
}
- /* Calculate the first VF index - this is a bit tricky; Basically,
- * VFs start at offset 16 relative to PF0, and 2nd engine VFs begin
- * after the first engine's VFs.
+ /* First VF index based on offset is tricky:
+ * - If ARI is supported [likely], offset - (16 - pf_id) would
+ * provide the number for eng0. 2nd engine Vfs would begin
+ * after the first engine's VFs.
+ * - If !ARI, VFs would start on next device.
+ * so offset - (256 - pf_id) would provide the number.
+ * Utilize the fact that (256 - pf_id) is achieved only by later
+ * to diffrentiate between the two.
*/
- cdev->p_iov_info->first_vf_in_pf = p_hwfn->cdev->p_iov_info->offset +
- p_hwfn->abs_pf_id - 16;
- if (QED_PATH_ID(p_hwfn))
- cdev->p_iov_info->first_vf_in_pf -= MAX_NUM_VFS_BB;
+
+ if (p_hwfn->cdev->p_iov_info->offset < (256 - p_hwfn->abs_pf_id)) {
+ u32 first = p_hwfn->cdev->p_iov_info->offset +
+ p_hwfn->abs_pf_id - 16;
+
+ cdev->p_iov_info->first_vf_in_pf = first;
+
+ if (QED_PATH_ID(p_hwfn))
+ cdev->p_iov_info->first_vf_in_pf -= MAX_NUM_VFS_BB;
+ } else {
+ u32 first = p_hwfn->cdev->p_iov_info->offset +
+ p_hwfn->abs_pf_id - 256;
+
+ cdev->p_iov_info->first_vf_in_pf = first;
+ }
DP_VERBOSE(p_hwfn, QED_MSG_IOV,
"First VF in hwfn 0x%08x\n",
@@ -677,6 +754,11 @@ static int qed_iov_enable_vf_access(struct qed_hwfn *p_hwfn,
u32 igu_vf_conf = IGU_VF_CONF_FUNC_EN;
int rc;
+ /* It's possible VF was previously considered malicious -
+ * clear the indication even if we're only going to disable VF.
+ */
+ vf->b_malicious = false;
+
if (vf->to_disable)
return 0;
@@ -689,9 +771,6 @@ static int qed_iov_enable_vf_access(struct qed_hwfn *p_hwfn,
qed_iov_vf_igu_reset(p_hwfn, p_ptt, vf);
- /* It's possible VF was previously considered malicious */
- vf->b_malicious = false;
-
rc = qed_mcp_config_vf_msix(p_hwfn, p_ptt, vf->abs_vf_id, vf->num_sbs);
if (rc)
return rc;
@@ -1118,13 +1197,17 @@ static void qed_iov_send_response(struct qed_hwfn *p_hwfn,
(sizeof(union pfvf_tlvs) - sizeof(u64)) / 4,
¶ms);
- qed_dmae_host2host(p_hwfn, p_ptt, mbx->reply_phys,
- mbx->req_virt->first_tlv.reply_address,
- sizeof(u64) / 4, ¶ms);
-
+ /* Once PF copies the rc to the VF, the latter can continue
+ * and send an additional message. So we have to make sure the
+ * channel would be re-set to ready prior to that.
+ */
REG_WR(p_hwfn,
GTT_BAR0_MAP_REG_USDM_RAM +
USTORM_VF_PF_CHANNEL_READY_OFFSET(eng_vf_id), 1);
+
+ qed_dmae_host2host(p_hwfn, p_ptt, mbx->reply_phys,
+ mbx->req_virt->first_tlv.reply_address,
+ sizeof(u64) / 4, ¶ms);
}
static u16 qed_iov_vport_to_tlv(struct qed_hwfn *p_hwfn,
@@ -1733,6 +1816,8 @@ static void qed_iov_vf_mbx_start_vport(struct qed_hwfn *p_hwfn,
vf->state = VF_ENABLED;
start = &mbx->req_virt->start_vport;
+ qed_iov_enable_vf_traffic(p_hwfn, p_ptt, vf);
+
/* Initialize Status block in CAU */
for (sb_id = 0; sb_id < vf->num_sbs; sb_id++) {
if (!start->sb_addr[sb_id]) {
@@ -1746,7 +1831,6 @@ static void qed_iov_vf_mbx_start_vport(struct qed_hwfn *p_hwfn,
start->sb_addr[sb_id],
vf->igu_sbs[sb_id], vf->abs_vf_id, 1);
}
- qed_iov_enable_vf_traffic(p_hwfn, p_ptt, vf);
vf->mtu = start->mtu;
vf->shadow_config.inner_vlan_removal = start->inner_vlan_removal;
@@ -1803,6 +1887,16 @@ static void qed_iov_vf_mbx_stop_vport(struct qed_hwfn *p_hwfn,
vf->vport_instance--;
vf->spoof_chk = false;
+ if ((qed_iov_validate_active_rxq(p_hwfn, vf)) ||
+ (qed_iov_validate_active_txq(p_hwfn, vf))) {
+ vf->b_malicious = true;
+ DP_NOTICE(p_hwfn,
+ "VF [%02x] - considered malicious; Unable to stop RX/TX queuess\n",
+ vf->abs_vf_id);
+ status = PFVF_STATUS_MALICIOUS;
+ goto out;
+ }
+
rc = qed_sp_vport_stop(p_hwfn, vf->opaque_fid, vf->vport_id);
if (rc) {
DP_ERR(p_hwfn, "qed_iov_vf_mbx_stop_vport returned error %d\n",
@@ -1814,6 +1908,7 @@ static void qed_iov_vf_mbx_stop_vport(struct qed_hwfn *p_hwfn,
vf->configured_features = 0;
memset(&vf->shadow_config, 0, sizeof(vf->shadow_config));
+out:
qed_iov_prepare_resp(p_hwfn, p_ptt, vf, CHANNEL_TLV_VPORT_TEARDOWN,
sizeof(struct pfvf_def_resp_tlv), status);
}
@@ -1870,7 +1965,8 @@ static void qed_iov_vf_mbx_start_rxq(struct qed_hwfn *p_hwfn,
req = &mbx->req_virt->start_rxq;
- if (!qed_iov_validate_rxq(p_hwfn, vf, req->rx_qid) ||
+ if (!qed_iov_validate_rxq(p_hwfn, vf, req->rx_qid,
+ QED_IOV_VALIDATE_Q_DISABLE) ||
!qed_iov_validate_sb(p_hwfn, vf, req->hw_sb))
goto out;
@@ -1970,21 +2066,16 @@ static void qed_iov_vf_mbx_start_txq(struct qed_hwfn *p_hwfn,
struct qed_queue_start_common_params params;
struct qed_iov_vf_mbx *mbx = &vf->vf_mbx;
u8 status = PFVF_STATUS_NO_RESOURCE;
- union qed_qm_pq_params pq_params;
struct vfpf_start_txq_tlv *req;
struct qed_vf_q_info *p_queue;
int rc;
u16 pq;
- /* Prepare the parameters which would choose the right PQ */
- memset(&pq_params, 0, sizeof(pq_params));
- pq_params.eth.is_vf = 1;
- pq_params.eth.vf_id = vf->relative_vf_id;
-
memset(¶ms, 0, sizeof(params));
req = &mbx->req_virt->start_txq;
- if (!qed_iov_validate_txq(p_hwfn, vf, req->tx_qid) ||
+ if (!qed_iov_validate_txq(p_hwfn, vf, req->tx_qid,
+ QED_IOV_VALIDATE_Q_DISABLE) ||
!qed_iov_validate_sb(p_hwfn, vf, req->hw_sb))
goto out;
@@ -2004,7 +2095,7 @@ static void qed_iov_vf_mbx_start_txq(struct qed_hwfn *p_hwfn,
if (!p_queue->p_tx_cid)
goto out;
- pq = qed_get_qm_pq(p_hwfn, PROTOCOLID_ETH, &pq_params);
+ pq = qed_get_cm_pq_idx_vf(p_hwfn, vf->relative_vf_id);
rc = qed_eth_txq_start_ramrod(p_hwfn, p_queue->p_tx_cid,
req->pbl_addr, req->pbl_size, pq);
if (rc) {
@@ -2021,57 +2112,53 @@ static void qed_iov_vf_mbx_start_txq(struct qed_hwfn *p_hwfn,
static int qed_iov_vf_stop_rxqs(struct qed_hwfn *p_hwfn,
struct qed_vf_info *vf,
- u16 rxq_id, u8 num_rxqs, bool cqe_completion)
+ u16 rxq_id, bool cqe_completion)
{
struct qed_vf_q_info *p_queue;
int rc = 0;
- int qid;
- if (rxq_id + num_rxqs > ARRAY_SIZE(vf->vf_queues))
+ if (!qed_iov_validate_rxq(p_hwfn, vf, rxq_id,
+ QED_IOV_VALIDATE_Q_ENABLE)) {
+ DP_VERBOSE(p_hwfn,
+ QED_MSG_IOV,
+ "VF[%d] Tried Closing Rx 0x%04x which is inactive\n",
+ vf->relative_vf_id, rxq_id);
return -EINVAL;
-
- for (qid = rxq_id; qid < rxq_id + num_rxqs; qid++) {
- p_queue = &vf->vf_queues[qid];
-
- if (!p_queue->p_rx_cid)
- continue;
-
- rc = qed_eth_rx_queue_stop(p_hwfn,
- p_queue->p_rx_cid,
- false, cqe_completion);
- if (rc)
- return rc;
-
- vf->vf_queues[qid].p_rx_cid = NULL;
- vf->num_active_rxqs--;
}
- return rc;
+ p_queue = &vf->vf_queues[rxq_id];
+
+ rc = qed_eth_rx_queue_stop(p_hwfn,
+ p_queue->p_rx_cid,
+ false, cqe_completion);
+ if (rc)
+ return rc;
+
+ p_queue->p_rx_cid = NULL;
+ vf->num_active_rxqs--;
+
+ return 0;
}
static int qed_iov_vf_stop_txqs(struct qed_hwfn *p_hwfn,
- struct qed_vf_info *vf, u16 txq_id, u8 num_txqs)
+ struct qed_vf_info *vf, u16 txq_id)
{
- int rc = 0;
struct qed_vf_q_info *p_queue;
- int qid;
+ int rc = 0;
- if (txq_id + num_txqs > ARRAY_SIZE(vf->vf_queues))
+ if (!qed_iov_validate_txq(p_hwfn, vf, txq_id,
+ QED_IOV_VALIDATE_Q_ENABLE))
return -EINVAL;
- for (qid = txq_id; qid < txq_id + num_txqs; qid++) {
- p_queue = &vf->vf_queues[qid];
- if (!p_queue->p_tx_cid)
- continue;
+ p_queue = &vf->vf_queues[txq_id];
- rc = qed_eth_tx_queue_stop(p_hwfn, p_queue->p_tx_cid);
- if (rc)
- return rc;
+ rc = qed_eth_tx_queue_stop(p_hwfn, p_queue->p_tx_cid);
+ if (rc)
+ return rc;
- p_queue->p_tx_cid = NULL;
- }
+ p_queue->p_tx_cid = NULL;
- return rc;
+ return 0;
}
static void qed_iov_vf_mbx_stop_rxqs(struct qed_hwfn *p_hwfn,
@@ -2080,20 +2167,28 @@ static void qed_iov_vf_mbx_stop_rxqs(struct qed_hwfn *p_hwfn,
{
u16 length = sizeof(struct pfvf_def_resp_tlv);
struct qed_iov_vf_mbx *mbx = &vf->vf_mbx;
- u8 status = PFVF_STATUS_SUCCESS;
+ u8 status = PFVF_STATUS_FAILURE;
struct vfpf_stop_rxqs_tlv *req;
int rc;
- /* We give the option of starting from qid != 0, in this case we
- * need to make sure that qid + num_qs doesn't exceed the actual
- * amount of queues that exist.
+ /* There has never been an official driver that used this interface
+ * for stopping multiple queues, and it is now considered deprecated.
+ * Validate this isn't used here.
*/
req = &mbx->req_virt->stop_rxqs;
- rc = qed_iov_vf_stop_rxqs(p_hwfn, vf, req->rx_qid,
- req->num_rxqs, req->cqe_completion);
- if (rc)
- status = PFVF_STATUS_FAILURE;
+ if (req->num_rxqs != 1) {
+ DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+ "Odd; VF[%d] tried stopping multiple Rx queues\n",
+ vf->relative_vf_id);
+ status = PFVF_STATUS_NOT_SUPPORTED;
+ goto out;
+ }
+ rc = qed_iov_vf_stop_rxqs(p_hwfn, vf, req->rx_qid,
+ req->cqe_completion);
+ if (!rc)
+ status = PFVF_STATUS_SUCCESS;
+out:
qed_iov_prepare_resp(p_hwfn, p_ptt, vf, CHANNEL_TLV_STOP_RXQS,
length, status);
}
@@ -2104,19 +2199,27 @@ static void qed_iov_vf_mbx_stop_txqs(struct qed_hwfn *p_hwfn,
{
u16 length = sizeof(struct pfvf_def_resp_tlv);
struct qed_iov_vf_mbx *mbx = &vf->vf_mbx;
- u8 status = PFVF_STATUS_SUCCESS;
+ u8 status = PFVF_STATUS_FAILURE;
struct vfpf_stop_txqs_tlv *req;
int rc;
- /* We give the option of starting from qid != 0, in this case we
- * need to make sure that qid + num_qs doesn't exceed the actual
- * amount of queues that exist.
+ /* There has never been an official driver that used this interface
+ * for stopping multiple queues, and it is now considered deprecated.
+ * Validate this isn't used here.
*/
req = &mbx->req_virt->stop_txqs;
- rc = qed_iov_vf_stop_txqs(p_hwfn, vf, req->tx_qid, req->num_txqs);
- if (rc)
- status = PFVF_STATUS_FAILURE;
+ if (req->num_txqs != 1) {
+ DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+ "Odd; VF[%d] tried stopping multiple Tx queues\n",
+ vf->relative_vf_id);
+ status = PFVF_STATUS_NOT_SUPPORTED;
+ goto out;
+ }
+ rc = qed_iov_vf_stop_txqs(p_hwfn, vf, req->tx_qid);
+ if (!rc)
+ status = PFVF_STATUS_SUCCESS;
+out:
qed_iov_prepare_resp(p_hwfn, p_ptt, vf, CHANNEL_TLV_STOP_TXQS,
length, status);
}
@@ -2141,22 +2244,17 @@ static void qed_iov_vf_mbx_update_rxqs(struct qed_hwfn *p_hwfn,
complete_event_flg = !!(req->flags & VFPF_RXQ_UPD_COMPLETE_EVENT_FLAG);
/* Validate inputs */
- if (req->num_rxqs + req->rx_qid > QED_MAX_VF_CHAINS_PER_PF ||
- !qed_iov_validate_rxq(p_hwfn, vf, req->rx_qid)) {
- DP_INFO(p_hwfn, "VF[%d]: Incorrect Rxqs [%04x, %02x]\n",
- vf->relative_vf_id, req->rx_qid, req->num_rxqs);
- goto out;
- }
-
- for (i = 0; i < req->num_rxqs; i++) {
- qid = req->rx_qid + i;
- if (!vf->vf_queues[qid].p_rx_cid) {
- DP_INFO(p_hwfn,
- "VF[%d] rx_qid = %d isn`t active!\n",
- vf->relative_vf_id, qid);
+ for (i = req->rx_qid; i < req->rx_qid + req->num_rxqs; i++)
+ if (!qed_iov_validate_rxq(p_hwfn, vf, i,
+ QED_IOV_VALIDATE_Q_ENABLE)) {
+ DP_INFO(p_hwfn, "VF[%d]: Incorrect Rxqs [%04x, %02x]\n",
+ vf->relative_vf_id, req->rx_qid, req->num_rxqs);
goto out;
}
+ /* Prepare the handlers */
+ for (i = 0; i < req->num_rxqs; i++) {
+ qid = req->rx_qid + i;
handlers[i] = vf->vf_queues[qid].p_rx_cid;
}
@@ -2372,7 +2470,8 @@ qed_iov_vp_update_rss_param(struct qed_hwfn *p_hwfn,
for (i = 0; i < table_size; i++) {
q_idx = p_rss_tlv->rss_ind_table[i];
- if (!qed_iov_validate_rxq(p_hwfn, vf, q_idx)) {
+ if (!qed_iov_validate_rxq(p_hwfn, vf, q_idx,
+ QED_IOV_VALIDATE_Q_ENABLE)) {
DP_VERBOSE(p_hwfn,
QED_MSG_IOV,
"VF[%d]: Omitting RSS due to wrong queue %04x\n",
@@ -2381,15 +2480,6 @@ qed_iov_vp_update_rss_param(struct qed_hwfn *p_hwfn,
goto out;
}
- if (!vf->vf_queues[q_idx].p_rx_cid) {
- DP_VERBOSE(p_hwfn,
- QED_MSG_IOV,
- "VF[%d]: Omitting RSS due to inactive queue %08x\n",
- vf->relative_vf_id, q_idx);
- b_reject = true;
- goto out;
- }
-
p_rss->rss_ind_table[i] = vf->vf_queues[q_idx].p_rx_cid;
}
@@ -3042,9 +3132,10 @@ qed_iov_vf_flr_cleanup(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
return rc;
}
-int qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn, u32 *p_disabled_vfs)
+bool qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn, u32 *p_disabled_vfs)
{
- u16 i, found = 0;
+ bool found = false;
+ u16 i;
DP_VERBOSE(p_hwfn, QED_MSG_IOV, "Marking FLR-ed VFs\n");
for (i = 0; i < (VF_MAX_STATIC / 32); i++)
@@ -3054,7 +3145,7 @@ int qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn, u32 *p_disabled_vfs)
if (!p_hwfn->cdev->p_iov_info) {
DP_NOTICE(p_hwfn, "VF flr but no IOV\n");
- return 0;
+ return false;
}
/* Mark VFs */
@@ -3083,7 +3174,7 @@ int qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn, u32 *p_disabled_vfs)
* VF flr until ACKs, we're safe.
*/
p_flr[rel_vf_id / 64] |= 1ULL << (rel_vf_id % 64);
- found = 1;
+ found = true;
}
}
@@ -3289,11 +3380,17 @@ static void qed_sriov_vfpf_malicious(struct qed_hwfn *p_hwfn,
if (!p_vf)
return;
- DP_INFO(p_hwfn,
- "VF [%d] - Malicious behavior [%02x]\n",
- p_vf->abs_vf_id, p_data->err_id);
+ if (!p_vf->b_malicious) {
+ DP_NOTICE(p_hwfn,
+ "VF [%d] - Malicious behavior [%02x]\n",
+ p_vf->abs_vf_id, p_data->err_id);
- p_vf->b_malicious = true;
+ p_vf->b_malicious = true;
+ } else {
+ DP_INFO(p_hwfn,
+ "VF [%d] - Malicious behavior [%02x]\n",
+ p_vf->abs_vf_id, p_data->err_id);
+ }
}
int qed_sriov_eqe_event(struct qed_hwfn *p_hwfn,
@@ -3842,6 +3939,7 @@ static int qed_get_vf_config(struct qed_dev *cdev,
void qed_inform_vf_link_state(struct qed_hwfn *hwfn)
{
+ struct qed_hwfn *lead_hwfn = QED_LEADING_HWFN(hwfn->cdev);
struct qed_mcp_link_capabilities caps;
struct qed_mcp_link_params params;
struct qed_mcp_link_state link;
@@ -3858,9 +3956,15 @@ void qed_inform_vf_link_state(struct qed_hwfn *hwfn)
if (!vf_info)
continue;
- memcpy(¶ms, qed_mcp_get_link_params(hwfn), sizeof(params));
- memcpy(&link, qed_mcp_get_link_state(hwfn), sizeof(link));
- memcpy(&caps, qed_mcp_get_link_capabilities(hwfn),
+ /* Only hwfn0 is actually interested in the link speed.
+ * But since only it would receive an MFW indication of link,
+ * need to take configuration from it - otherwise things like
+ * rate limiting for hwfn1 VF would not work.
+ */
+ memcpy(¶ms, qed_mcp_get_link_params(lead_hwfn),
+ sizeof(params));
+ memcpy(&link, qed_mcp_get_link_state(lead_hwfn), sizeof(link));
+ memcpy(&caps, qed_mcp_get_link_capabilities(lead_hwfn),
sizeof(caps));
/* Modify link according to the VF's configured link state */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.h b/drivers/net/ethernet/qlogic/qed/qed_sriov.h
index a896058..8e96b1d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.h
@@ -348,9 +348,9 @@ int qed_sriov_eqe_event(struct qed_hwfn *p_hwfn,
* @param p_hwfn
* @param disabled_vfs - bitmask of all VFs on path that were FLRed
*
- * @return 1 iff one of the PF's vfs got FLRed. 0 otherwise.
+ * @return true iff one of the PF's vfs got FLRed. false otherwise.
*/
-int qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn, u32 *disabled_vfs);
+bool qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn, u32 *disabled_vfs);
/**
* @brief Search extended TLVs in request/reply buffer.
@@ -407,10 +407,10 @@ static inline int qed_sriov_eqe_event(struct qed_hwfn *p_hwfn,
return -EINVAL;
}
-static inline int qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn,
- u32 *disabled_vfs)
+static inline bool qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn,
+ u32 *disabled_vfs)
{
- return 0;
+ return false;
}
static inline void qed_iov_wq_stop(struct qed_dev *cdev, bool schedule_first)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c
index 15d2855..7987865 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c
@@ -134,14 +134,20 @@ static int qed_send_msg2pf(struct qed_hwfn *p_hwfn, u8 *done, u32 resp_size)
}
if (!*done) {
- DP_VERBOSE(p_hwfn, QED_MSG_IOV,
- "VF <-- PF Timeout [Type %d]\n",
- p_req->first_tlv.tl.type);
+ DP_NOTICE(p_hwfn,
+ "VF <-- PF Timeout [Type %d]\n",
+ p_req->first_tlv.tl.type);
rc = -EBUSY;
} else {
- DP_VERBOSE(p_hwfn, QED_MSG_IOV,
- "PF response: %d [Type %d]\n",
- *done, p_req->first_tlv.tl.type);
+ if ((*done != PFVF_STATUS_SUCCESS) &&
+ (*done != PFVF_STATUS_NO_RESOURCE))
+ DP_NOTICE(p_hwfn,
+ "PF response: %d [Type %d]\n",
+ *done, p_req->first_tlv.tl.type);
+ else
+ DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+ "PF response: %d [Type %d]\n",
+ *done, p_req->first_tlv.tl.type);
}
return rc;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.h b/drivers/net/ethernet/qlogic/qed/qed_vf.h
index 7da0b16..105c0ed 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.h
@@ -275,6 +275,8 @@ struct vfpf_stop_rxqs_tlv {
struct vfpf_first_tlv first_tlv;
u16 rx_qid;
+
+ /* this field is deprecated and should *always* be set to '1' */
u8 num_rxqs;
u8 cqe_completion;
u8 padding[4];
@@ -285,6 +287,8 @@ struct vfpf_stop_txqs_tlv {
struct vfpf_first_tlv first_tlv;
u16 tx_qid;
+
+ /* this field is deprecated and should *always* be set to '1' */
u8 num_txqs;
u8 padding[5];
};
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index f2aaef2..5e7ad25 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -50,7 +50,7 @@
#define QEDE_MAJOR_VERSION 8
#define QEDE_MINOR_VERSION 10
#define QEDE_REVISION_VERSION 10
-#define QEDE_ENGINEERING_VERSION 20
+#define QEDE_ENGINEERING_VERSION 21
#define DRV_MODULE_VERSION __stringify(QEDE_MAJOR_VERSION) "." \
__stringify(QEDE_MINOR_VERSION) "." \
__stringify(QEDE_REVISION_VERSION) "." \
@@ -58,7 +58,7 @@
#define DRV_MODULE_SYM qede
-struct qede_stats {
+struct qede_stats_common {
u64 no_buff_discards;
u64 packet_too_big_discard;
u64 ttl0_discard;
@@ -90,11 +90,6 @@ struct qede_stats {
u64 rx_256_to_511_byte_packets;
u64 rx_512_to_1023_byte_packets;
u64 rx_1024_to_1518_byte_packets;
- u64 rx_1519_to_1522_byte_packets;
- u64 rx_1519_to_2047_byte_packets;
- u64 rx_2048_to_4095_byte_packets;
- u64 rx_4096_to_9216_byte_packets;
- u64 rx_9217_to_16383_byte_packets;
u64 rx_crc_errors;
u64 rx_mac_crtl_frames;
u64 rx_pause_frames;
@@ -111,17 +106,39 @@ struct qede_stats {
u64 tx_256_to_511_byte_packets;
u64 tx_512_to_1023_byte_packets;
u64 tx_1024_to_1518_byte_packets;
+ u64 tx_pause_frames;
+ u64 tx_pfc_frames;
+ u64 brb_truncates;
+ u64 brb_discards;
+ u64 tx_mac_ctrl_frames;
+};
+
+struct qede_stats_bb {
+ u64 rx_1519_to_1522_byte_packets;
+ u64 rx_1519_to_2047_byte_packets;
+ u64 rx_2048_to_4095_byte_packets;
+ u64 rx_4096_to_9216_byte_packets;
+ u64 rx_9217_to_16383_byte_packets;
u64 tx_1519_to_2047_byte_packets;
u64 tx_2048_to_4095_byte_packets;
u64 tx_4096_to_9216_byte_packets;
u64 tx_9217_to_16383_byte_packets;
- u64 tx_pause_frames;
- u64 tx_pfc_frames;
u64 tx_lpi_entry_count;
u64 tx_total_collisions;
- u64 brb_truncates;
- u64 brb_discards;
- u64 tx_mac_ctrl_frames;
+};
+
+struct qede_stats_ah {
+ u64 rx_1519_to_max_byte_packets;
+ u64 tx_1519_to_max_byte_packets;
+};
+
+struct qede_stats {
+ struct qede_stats_common common;
+
+ union {
+ struct qede_stats_bb bb;
+ struct qede_stats_ah ah;
+ };
};
struct qede_vlan {
@@ -158,6 +175,10 @@ struct qede_dev {
struct qed_dev_eth_info dev_info;
#define QEDE_MAX_RSS_CNT(edev) ((edev)->dev_info.num_queues)
#define QEDE_MAX_TSS_CNT(edev) ((edev)->dev_info.num_queues)
+#define QEDE_IS_BB(edev) \
+ ((edev)->dev_info.common.dev_type == QED_DEV_TYPE_BB)
+#define QEDE_IS_AH(edev) \
+ ((edev)->dev_info.common.dev_type == QED_DEV_TYPE_AH)
struct qede_fastpath *fp_array;
u8 req_num_tx;
@@ -292,21 +313,24 @@ struct qede_rx_queue {
u8 data_direction;
u8 rxq_id;
+ /* Used once per each NAPI run */
+ u16 num_rx_buffers;
+
+ u16 rx_headroom;
+
u32 rx_buf_size;
u32 rx_buf_seg_size;
- u64 rcv_pkts;
-
struct sw_rx_data *sw_rx_ring;
struct qed_chain rx_bd_ring;
struct qed_chain rx_comp_ring ____cacheline_aligned;
- /* Used once per each NAPI run */
- u16 num_rx_buffers;
-
/* GRO */
struct qede_agg_info tpa_info[ETH_TPA_MAX_AGGS_NUM];
+ /* Used once per each NAPI run */
+ u64 rcv_pkts;
+
u64 rx_hw_errors;
u64 rx_alloc_errors;
u64 rx_ip_frags;
@@ -328,6 +352,11 @@ struct sw_tx_bd {
#define QEDE_TSO_SPLIT_BD BIT(0)
};
+struct sw_tx_xdp {
+ struct page *page;
+ dma_addr_t mapping;
+};
+
struct qede_tx_queue {
u8 is_xdp;
bool is_legacy;
@@ -351,11 +380,11 @@ struct qede_tx_queue {
#define QEDE_TXQ_IDX_TO_XDP(edev, idx) ((idx) + QEDE_MAX_TSS_CNT(edev))
/* Regular Tx requires skb + metadata for release purpose,
- * while XDP requires only the pages themselves.
+ * while XDP requires the pages and the mapped address.
*/
union {
struct sw_tx_bd *skbs;
- struct page **pages;
+ struct sw_tx_xdp *xdp;
} sw_tx_ring;
struct qed_chain tx_pbl;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index 8979531..4dcfe96 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -75,16 +75,33 @@ static const struct {
QEDE_TQSTAT(stopped_cnt),
};
-#define QEDE_STAT_OFFSET(stat_name) (offsetof(struct qede_stats, stat_name))
-#define QEDE_STAT_STRING(stat_name) (#stat_name)
-#define _QEDE_STAT(stat_name, pf_only) \
- {QEDE_STAT_OFFSET(stat_name), QEDE_STAT_STRING(stat_name), pf_only}
-#define QEDE_PF_STAT(stat_name) _QEDE_STAT(stat_name, true)
-#define QEDE_STAT(stat_name) _QEDE_STAT(stat_name, false)
+#define QEDE_STAT_OFFSET(stat_name, type, base) \
+ (offsetof(type, stat_name) + (base))
+#define QEDE_STAT_STRING(stat_name) (#stat_name)
+#define _QEDE_STAT(stat_name, type, base, attr) \
+ {QEDE_STAT_OFFSET(stat_name, type, base), \
+ QEDE_STAT_STRING(stat_name), \
+ attr}
+#define QEDE_STAT(stat_name) \
+ _QEDE_STAT(stat_name, struct qede_stats_common, 0, 0x0)
+#define QEDE_PF_STAT(stat_name) \
+ _QEDE_STAT(stat_name, struct qede_stats_common, 0, \
+ BIT(QEDE_STAT_PF_ONLY))
+#define QEDE_PF_BB_STAT(stat_name) \
+ _QEDE_STAT(stat_name, struct qede_stats_bb, \
+ offsetof(struct qede_stats, bb), \
+ BIT(QEDE_STAT_PF_ONLY) | BIT(QEDE_STAT_BB_ONLY))
+#define QEDE_PF_AH_STAT(stat_name) \
+ _QEDE_STAT(stat_name, struct qede_stats_ah, \
+ offsetof(struct qede_stats, ah), \
+ BIT(QEDE_STAT_PF_ONLY) | BIT(QEDE_STAT_AH_ONLY))
static const struct {
u64 offset;
char string[ETH_GSTRING_LEN];
- bool pf_only;
+ unsigned long attr;
+#define QEDE_STAT_PF_ONLY 0
+#define QEDE_STAT_BB_ONLY 1
+#define QEDE_STAT_AH_ONLY 2
} qede_stats_arr[] = {
QEDE_STAT(rx_ucast_bytes),
QEDE_STAT(rx_mcast_bytes),
@@ -106,22 +123,23 @@ static const struct {
QEDE_PF_STAT(rx_256_to_511_byte_packets),
QEDE_PF_STAT(rx_512_to_1023_byte_packets),
QEDE_PF_STAT(rx_1024_to_1518_byte_packets),
- QEDE_PF_STAT(rx_1519_to_1522_byte_packets),
- QEDE_PF_STAT(rx_1519_to_2047_byte_packets),
- QEDE_PF_STAT(rx_2048_to_4095_byte_packets),
- QEDE_PF_STAT(rx_4096_to_9216_byte_packets),
- QEDE_PF_STAT(rx_9217_to_16383_byte_packets),
+ QEDE_PF_BB_STAT(rx_1519_to_1522_byte_packets),
+ QEDE_PF_BB_STAT(rx_1519_to_2047_byte_packets),
+ QEDE_PF_BB_STAT(rx_2048_to_4095_byte_packets),
+ QEDE_PF_BB_STAT(rx_4096_to_9216_byte_packets),
+ QEDE_PF_BB_STAT(rx_9217_to_16383_byte_packets),
+ QEDE_PF_AH_STAT(rx_1519_to_max_byte_packets),
QEDE_PF_STAT(tx_64_byte_packets),
QEDE_PF_STAT(tx_65_to_127_byte_packets),
QEDE_PF_STAT(tx_128_to_255_byte_packets),
QEDE_PF_STAT(tx_256_to_511_byte_packets),
QEDE_PF_STAT(tx_512_to_1023_byte_packets),
QEDE_PF_STAT(tx_1024_to_1518_byte_packets),
- QEDE_PF_STAT(tx_1519_to_2047_byte_packets),
- QEDE_PF_STAT(tx_2048_to_4095_byte_packets),
- QEDE_PF_STAT(tx_4096_to_9216_byte_packets),
- QEDE_PF_STAT(tx_9217_to_16383_byte_packets),
-
+ QEDE_PF_BB_STAT(tx_1519_to_2047_byte_packets),
+ QEDE_PF_BB_STAT(tx_2048_to_4095_byte_packets),
+ QEDE_PF_BB_STAT(tx_4096_to_9216_byte_packets),
+ QEDE_PF_BB_STAT(tx_9217_to_16383_byte_packets),
+ QEDE_PF_AH_STAT(tx_1519_to_max_byte_packets),
QEDE_PF_STAT(rx_mac_crtl_frames),
QEDE_PF_STAT(tx_mac_ctrl_frames),
QEDE_PF_STAT(rx_pause_frames),
@@ -136,8 +154,8 @@ static const struct {
QEDE_PF_STAT(rx_jabbers),
QEDE_PF_STAT(rx_undersize_packets),
QEDE_PF_STAT(rx_fragments),
- QEDE_PF_STAT(tx_lpi_entry_count),
- QEDE_PF_STAT(tx_total_collisions),
+ QEDE_PF_BB_STAT(tx_lpi_entry_count),
+ QEDE_PF_BB_STAT(tx_total_collisions),
QEDE_PF_STAT(brb_truncates),
QEDE_PF_STAT(brb_discards),
QEDE_STAT(no_buff_discards),
@@ -155,6 +173,12 @@ static const struct {
};
#define QEDE_NUM_STATS ARRAY_SIZE(qede_stats_arr)
+#define QEDE_STAT_IS_PF_ONLY(i) \
+ test_bit(QEDE_STAT_PF_ONLY, &qede_stats_arr[i].attr)
+#define QEDE_STAT_IS_BB_ONLY(i) \
+ test_bit(QEDE_STAT_BB_ONLY, &qede_stats_arr[i].attr)
+#define QEDE_STAT_IS_AH_ONLY(i) \
+ test_bit(QEDE_STAT_AH_ONLY, &qede_stats_arr[i].attr)
enum {
QEDE_PRI_FLAG_CMT,
@@ -213,6 +237,13 @@ static void qede_get_strings_stats_rxq(struct qede_dev *edev,
}
}
+static bool qede_is_irrelevant_stat(struct qede_dev *edev, int stat_index)
+{
+ return (IS_VF(edev) && QEDE_STAT_IS_PF_ONLY(stat_index)) ||
+ (QEDE_IS_BB(edev) && QEDE_STAT_IS_AH_ONLY(stat_index)) ||
+ (QEDE_IS_AH(edev) && QEDE_STAT_IS_BB_ONLY(stat_index));
+}
+
static void qede_get_strings_stats(struct qede_dev *edev, u8 *buf)
{
struct qede_fastpath *fp;
@@ -234,7 +265,7 @@ static void qede_get_strings_stats(struct qede_dev *edev, u8 *buf)
/* Account for non-queue statistics */
for (i = 0; i < QEDE_NUM_STATS; i++) {
- if (IS_VF(edev) && qede_stats_arr[i].pf_only)
+ if (qede_is_irrelevant_stat(edev, i))
continue;
strcpy(buf, qede_stats_arr[i].string);
buf += ETH_GSTRING_LEN;
@@ -309,7 +340,7 @@ static void qede_get_ethtool_stats(struct net_device *dev,
}
for (i = 0; i < QEDE_NUM_STATS; i++) {
- if (IS_VF(edev) && qede_stats_arr[i].pf_only)
+ if (qede_is_irrelevant_stat(edev, i))
continue;
*buf = *((u64 *)(((void *)&edev->stats) +
qede_stats_arr[i].offset));
@@ -323,17 +354,13 @@ static void qede_get_ethtool_stats(struct net_device *dev,
static int qede_get_sset_count(struct net_device *dev, int stringset)
{
struct qede_dev *edev = netdev_priv(dev);
- int num_stats = QEDE_NUM_STATS;
+ int num_stats = QEDE_NUM_STATS, i;
switch (stringset) {
case ETH_SS_STATS:
- if (IS_VF(edev)) {
- int i;
-
- for (i = 0; i < QEDE_NUM_STATS; i++)
- if (qede_stats_arr[i].pf_only)
- num_stats--;
- }
+ for (i = 0; i < QEDE_NUM_STATS; i++)
+ if (qede_is_irrelevant_stat(edev, i))
+ num_stats--;
/* Account for the Regular Tx statistics */
num_stats += QEDE_TSS_COUNT(edev) * QEDE_NUM_TQSTATS;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index 107c3fd..b00a4fc 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -520,11 +520,6 @@ static int qede_xdp_set(struct qede_dev *edev, struct bpf_prog *prog)
{
struct qede_reload_args args;
- if (prog && prog->xdp_adjust_head) {
- DP_ERR(edev, "Does not support bpf_xdp_adjust_head()\n");
- return -EOPNOTSUPP;
- }
-
/* If we're called, there was already a bpf reference increment */
args.func = &qede_xdp_reload_func;
args.u.new_prog = prog;
@@ -537,6 +532,11 @@ int qede_xdp(struct net_device *dev, struct netdev_xdp *xdp)
{
struct qede_dev *edev = netdev_priv(dev);
+ if (IS_VF(edev)) {
+ DP_NOTICE(edev, "VFs don't support XDP\n");
+ return -EOPNOTSUPP;
+ }
+
switch (xdp->command) {
case XDP_SETUP_PROG:
return qede_xdp_set(edev, xdp->prog);
diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index 1e65038..961b1d3 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -87,7 +87,8 @@ int qede_alloc_rx_buffer(struct qede_rx_queue *rxq, bool allow_lazy)
rx_bd = (struct eth_rx_bd *)qed_chain_produce(&rxq->rx_bd_ring);
WARN_ON(!rx_bd);
rx_bd->addr.hi = cpu_to_le32(upper_32_bits(mapping));
- rx_bd->addr.lo = cpu_to_le32(lower_32_bits(mapping));
+ rx_bd->addr.lo = cpu_to_le32(lower_32_bits(mapping) +
+ rxq->rx_headroom);
rxq->sw_rx_prod++;
rxq->filled_buffers++;
@@ -360,7 +361,8 @@ static int qede_xdp_xmit(struct qede_dev *edev, struct qede_fastpath *fp,
metadata->mapping + padding,
length, PCI_DMA_TODEVICE);
- txq->sw_tx_ring.pages[idx] = metadata->data;
+ txq->sw_tx_ring.xdp[idx].page = metadata->data;
+ txq->sw_tx_ring.xdp[idx].mapping = metadata->mapping;
txq->sw_tx_prod++;
/* Mark the fastpath for future XDP doorbell */
@@ -384,19 +386,19 @@ int qede_txq_has_work(struct qede_tx_queue *txq)
static void qede_xdp_tx_int(struct qede_dev *edev, struct qede_tx_queue *txq)
{
- struct eth_tx_1st_bd *bd;
- u16 hw_bd_cons;
+ u16 hw_bd_cons, idx;
hw_bd_cons = le16_to_cpu(*txq->hw_cons_ptr);
barrier();
while (hw_bd_cons != qed_chain_get_cons_idx(&txq->tx_pbl)) {
- bd = (struct eth_tx_1st_bd *)qed_chain_consume(&txq->tx_pbl);
+ qed_chain_consume(&txq->tx_pbl);
+ idx = txq->sw_tx_cons & NUM_TX_BDS_MAX;
- dma_unmap_single(&edev->pdev->dev, BD_UNMAP_ADDR(bd),
- PAGE_SIZE, DMA_BIDIRECTIONAL);
- __free_page(txq->sw_tx_ring.pages[txq->sw_tx_cons &
- NUM_TX_BDS_MAX]);
+ dma_unmap_page(&edev->pdev->dev,
+ txq->sw_tx_ring.xdp[idx].mapping,
+ PAGE_SIZE, DMA_BIDIRECTIONAL);
+ __free_page(txq->sw_tx_ring.xdp[idx].page);
txq->sw_tx_cons++;
txq->xmit_pkts++;
@@ -508,7 +510,8 @@ static inline void qede_reuse_page(struct qede_rx_queue *rxq,
new_mapping = curr_prod->mapping + curr_prod->page_offset;
rx_bd_prod->addr.hi = cpu_to_le32(upper_32_bits(new_mapping));
- rx_bd_prod->addr.lo = cpu_to_le32(lower_32_bits(new_mapping));
+ rx_bd_prod->addr.lo = cpu_to_le32(lower_32_bits(new_mapping) +
+ rxq->rx_headroom);
rxq->sw_rx_prod++;
curr_cons->data = NULL;
@@ -624,7 +627,6 @@ static inline void qede_skb_receive(struct qede_dev *edev,
__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
napi_gro_receive(&fp->napi, skb);
- rxq->rcv_pkts++;
}
static void qede_set_gro_params(struct qede_dev *edev,
@@ -884,9 +886,9 @@ static inline void qede_tpa_cont(struct qede_dev *edev,
"Strange - TPA cont with more than a single len_list entry\n");
}
-static void qede_tpa_end(struct qede_dev *edev,
- struct qede_fastpath *fp,
- struct eth_fast_path_rx_tpa_end_cqe *cqe)
+static int qede_tpa_end(struct qede_dev *edev,
+ struct qede_fastpath *fp,
+ struct eth_fast_path_rx_tpa_end_cqe *cqe)
{
struct qede_rx_queue *rxq = fp->rxq;
struct qede_agg_info *tpa_info;
@@ -934,11 +936,12 @@ static void qede_tpa_end(struct qede_dev *edev,
tpa_info->state = QEDE_AGG_STATE_NONE;
- return;
+ return 1;
err:
tpa_info->state = QEDE_AGG_STATE_NONE;
dev_kfree_skb_any(tpa_info->skb);
tpa_info->skb = NULL;
+ return 0;
}
static u8 qede_check_notunn_csum(u16 flag)
@@ -990,14 +993,15 @@ static bool qede_rx_xdp(struct qede_dev *edev,
struct qede_rx_queue *rxq,
struct bpf_prog *prog,
struct sw_rx_data *bd,
- struct eth_fast_path_rx_reg_cqe *cqe)
+ struct eth_fast_path_rx_reg_cqe *cqe,
+ u16 *data_offset, u16 *len)
{
- u16 len = le16_to_cpu(cqe->len_on_first_bd);
struct xdp_buff xdp;
enum xdp_action act;
- xdp.data = page_address(bd->data) + cqe->placement_offset;
- xdp.data_end = xdp.data + len;
+ xdp.data_hard_start = page_address(bd->data);
+ xdp.data = xdp.data_hard_start + *data_offset;
+ xdp.data_end = xdp.data + *len;
/* Queues always have a full reset currently, so for the time
* being until there's atomic program replace just mark read
@@ -1007,6 +1011,10 @@ static bool qede_rx_xdp(struct qede_dev *edev,
act = bpf_prog_run_xdp(prog, &xdp);
rcu_read_unlock();
+ /* Recalculate, as XDP might have changed the headers */
+ *data_offset = xdp.data - xdp.data_hard_start;
+ *len = xdp.data_end - xdp.data;
+
if (act == XDP_PASS)
return true;
@@ -1025,7 +1033,7 @@ static bool qede_rx_xdp(struct qede_dev *edev,
/* Now if there's a transmission problem, we'd still have to
* throw current buffer, as replacement was already allocated.
*/
- if (qede_xdp_xmit(edev, fp, bd, cqe->placement_offset, len)) {
+ if (qede_xdp_xmit(edev, fp, bd, *data_offset, *len)) {
dma_unmap_page(rxq->dev, bd->mapping,
PAGE_SIZE, DMA_BIDIRECTIONAL);
__free_page(bd->data);
@@ -1052,7 +1060,7 @@ static struct sk_buff *qede_rx_allocate_skb(struct qede_dev *edev,
struct sw_rx_data *bd, u16 len,
u16 pad)
{
- unsigned int offset = bd->page_offset;
+ unsigned int offset = bd->page_offset + pad;
struct skb_frag_struct *frag;
struct page *page = bd->data;
unsigned int pull_len;
@@ -1069,7 +1077,7 @@ static struct sk_buff *qede_rx_allocate_skb(struct qede_dev *edev,
*/
if (len + pad <= edev->rx_copybreak) {
memcpy(skb_put(skb, len),
- page_address(page) + pad + offset, len);
+ page_address(page) + offset, len);
qede_reuse_page(rxq, bd);
goto out;
}
@@ -1077,7 +1085,7 @@ static struct sk_buff *qede_rx_allocate_skb(struct qede_dev *edev,
frag = &skb_shinfo(skb)->frags[0];
skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
- page, pad + offset, len, rxq->rx_buf_seg_size);
+ page, offset, len, rxq->rx_buf_seg_size);
va = skb_frag_address(frag);
pull_len = eth_get_headlen(va, QEDE_RX_HDR_SIZE);
@@ -1178,8 +1186,7 @@ static int qede_rx_process_tpa_cqe(struct qede_dev *edev,
qede_tpa_cont(edev, rxq, &cqe->fast_path_tpa_cont);
return 0;
case ETH_RX_CQE_TYPE_TPA_END:
- qede_tpa_end(edev, fp, &cqe->fast_path_tpa_end);
- return 1;
+ return qede_tpa_end(edev, fp, &cqe->fast_path_tpa_end);
default:
return 0;
}
@@ -1224,12 +1231,13 @@ static int qede_rx_process_cqe(struct qede_dev *edev,
fp_cqe = &cqe->fast_path_regular;
len = le16_to_cpu(fp_cqe->len_on_first_bd);
- pad = fp_cqe->placement_offset;
+ pad = fp_cqe->placement_offset + rxq->rx_headroom;
/* Run eBPF program if one is attached */
if (xdp_prog)
- if (!qede_rx_xdp(edev, fp, rxq, xdp_prog, bd, fp_cqe))
- return 1;
+ if (!qede_rx_xdp(edev, fp, rxq, xdp_prog, bd, fp_cqe,
+ &pad, &len))
+ return 0;
/* If this is an error packet then drop it */
flags = cqe->fast_path_regular.pars_flags.flags;
@@ -1290,8 +1298,8 @@ static int qede_rx_int(struct qede_fastpath *fp, int budget)
{
struct qede_rx_queue *rxq = fp->rxq;
struct qede_dev *edev = fp->edev;
+ int work_done = 0, rcv_pkts = 0;
u16 hw_comp_cons, sw_comp_cons;
- int work_done = 0;
hw_comp_cons = le16_to_cpu(*rxq->hw_cons_ptr);
sw_comp_cons = qed_chain_get_cons_idx(&rxq->rx_comp_ring);
@@ -1305,12 +1313,14 @@ static int qede_rx_int(struct qede_fastpath *fp, int budget)
/* Loop to complete all indicated BDs */
while ((sw_comp_cons != hw_comp_cons) && (work_done < budget)) {
- qede_rx_process_cqe(edev, fp, rxq);
+ rcv_pkts += qede_rx_process_cqe(edev, fp, rxq);
qed_chain_recycle_consumed(&rxq->rx_comp_ring);
sw_comp_cons = qed_chain_get_cons_idx(&rxq->rx_comp_ring);
work_done++;
}
+ rxq->rcv_pkts += rcv_pkts;
+
/* Allocate replacement buffers */
while (rxq->num_rx_buffers - rxq->filled_buffers)
if (qede_alloc_rx_buffer(rxq, false))
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 3a78c3f..8c2baf8 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -84,6 +84,8 @@ static const struct qed_eth_ops *qed_ops;
#define CHIP_NUM_57980S_50 0x1654
#define CHIP_NUM_57980S_25 0x1656
#define CHIP_NUM_57980S_IOV 0x1664
+#define CHIP_NUM_AH 0x8070
+#define CHIP_NUM_AH_IOV 0x8090
#ifndef PCI_DEVICE_ID_NX2_57980E
#define PCI_DEVICE_ID_57980S_40 CHIP_NUM_57980S_40
@@ -93,6 +95,9 @@ static const struct qed_eth_ops *qed_ops;
#define PCI_DEVICE_ID_57980S_50 CHIP_NUM_57980S_50
#define PCI_DEVICE_ID_57980S_25 CHIP_NUM_57980S_25
#define PCI_DEVICE_ID_57980S_IOV CHIP_NUM_57980S_IOV
+#define PCI_DEVICE_ID_AH CHIP_NUM_AH
+#define PCI_DEVICE_ID_AH_IOV CHIP_NUM_AH_IOV
+
#endif
enum qede_pci_private {
@@ -110,6 +115,10 @@ static const struct pci_device_id qede_pci_tbl[] = {
#ifdef CONFIG_QED_SRIOV
{PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_57980S_IOV), QEDE_PRIVATE_VF},
#endif
+ {PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_AH), QEDE_PRIVATE_PF},
+#ifdef CONFIG_QED_SRIOV
+ {PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_AH_IOV), QEDE_PRIVATE_VF},
+#endif
{ 0 }
};
@@ -314,122 +323,135 @@ static int qede_close(struct net_device *ndev);
void qede_fill_by_demand_stats(struct qede_dev *edev)
{
+ struct qede_stats_common *p_common = &edev->stats.common;
struct qed_eth_stats stats;
edev->ops->get_vport_stats(edev->cdev, &stats);
- edev->stats.no_buff_discards = stats.no_buff_discards;
- edev->stats.packet_too_big_discard = stats.packet_too_big_discard;
- edev->stats.ttl0_discard = stats.ttl0_discard;
- edev->stats.rx_ucast_bytes = stats.rx_ucast_bytes;
- edev->stats.rx_mcast_bytes = stats.rx_mcast_bytes;
- edev->stats.rx_bcast_bytes = stats.rx_bcast_bytes;
- edev->stats.rx_ucast_pkts = stats.rx_ucast_pkts;
- edev->stats.rx_mcast_pkts = stats.rx_mcast_pkts;
- edev->stats.rx_bcast_pkts = stats.rx_bcast_pkts;
- edev->stats.mftag_filter_discards = stats.mftag_filter_discards;
- edev->stats.mac_filter_discards = stats.mac_filter_discards;
- edev->stats.tx_ucast_bytes = stats.tx_ucast_bytes;
- edev->stats.tx_mcast_bytes = stats.tx_mcast_bytes;
- edev->stats.tx_bcast_bytes = stats.tx_bcast_bytes;
- edev->stats.tx_ucast_pkts = stats.tx_ucast_pkts;
- edev->stats.tx_mcast_pkts = stats.tx_mcast_pkts;
- edev->stats.tx_bcast_pkts = stats.tx_bcast_pkts;
- edev->stats.tx_err_drop_pkts = stats.tx_err_drop_pkts;
- edev->stats.coalesced_pkts = stats.tpa_coalesced_pkts;
- edev->stats.coalesced_events = stats.tpa_coalesced_events;
- edev->stats.coalesced_aborts_num = stats.tpa_aborts_num;
- edev->stats.non_coalesced_pkts = stats.tpa_not_coalesced_pkts;
- edev->stats.coalesced_bytes = stats.tpa_coalesced_bytes;
+ p_common->no_buff_discards = stats.common.no_buff_discards;
+ p_common->packet_too_big_discard = stats.common.packet_too_big_discard;
+ p_common->ttl0_discard = stats.common.ttl0_discard;
+ p_common->rx_ucast_bytes = stats.common.rx_ucast_bytes;
+ p_common->rx_mcast_bytes = stats.common.rx_mcast_bytes;
+ p_common->rx_bcast_bytes = stats.common.rx_bcast_bytes;
+ p_common->rx_ucast_pkts = stats.common.rx_ucast_pkts;
+ p_common->rx_mcast_pkts = stats.common.rx_mcast_pkts;
+ p_common->rx_bcast_pkts = stats.common.rx_bcast_pkts;
+ p_common->mftag_filter_discards = stats.common.mftag_filter_discards;
+ p_common->mac_filter_discards = stats.common.mac_filter_discards;
- edev->stats.rx_64_byte_packets = stats.rx_64_byte_packets;
- edev->stats.rx_65_to_127_byte_packets = stats.rx_65_to_127_byte_packets;
- edev->stats.rx_128_to_255_byte_packets =
- stats.rx_128_to_255_byte_packets;
- edev->stats.rx_256_to_511_byte_packets =
- stats.rx_256_to_511_byte_packets;
- edev->stats.rx_512_to_1023_byte_packets =
- stats.rx_512_to_1023_byte_packets;
- edev->stats.rx_1024_to_1518_byte_packets =
- stats.rx_1024_to_1518_byte_packets;
- edev->stats.rx_1519_to_1522_byte_packets =
- stats.rx_1519_to_1522_byte_packets;
- edev->stats.rx_1519_to_2047_byte_packets =
- stats.rx_1519_to_2047_byte_packets;
- edev->stats.rx_2048_to_4095_byte_packets =
- stats.rx_2048_to_4095_byte_packets;
- edev->stats.rx_4096_to_9216_byte_packets =
- stats.rx_4096_to_9216_byte_packets;
- edev->stats.rx_9217_to_16383_byte_packets =
- stats.rx_9217_to_16383_byte_packets;
- edev->stats.rx_crc_errors = stats.rx_crc_errors;
- edev->stats.rx_mac_crtl_frames = stats.rx_mac_crtl_frames;
- edev->stats.rx_pause_frames = stats.rx_pause_frames;
- edev->stats.rx_pfc_frames = stats.rx_pfc_frames;
- edev->stats.rx_align_errors = stats.rx_align_errors;
- edev->stats.rx_carrier_errors = stats.rx_carrier_errors;
- edev->stats.rx_oversize_packets = stats.rx_oversize_packets;
- edev->stats.rx_jabbers = stats.rx_jabbers;
- edev->stats.rx_undersize_packets = stats.rx_undersize_packets;
- edev->stats.rx_fragments = stats.rx_fragments;
- edev->stats.tx_64_byte_packets = stats.tx_64_byte_packets;
- edev->stats.tx_65_to_127_byte_packets = stats.tx_65_to_127_byte_packets;
- edev->stats.tx_128_to_255_byte_packets =
- stats.tx_128_to_255_byte_packets;
- edev->stats.tx_256_to_511_byte_packets =
- stats.tx_256_to_511_byte_packets;
- edev->stats.tx_512_to_1023_byte_packets =
- stats.tx_512_to_1023_byte_packets;
- edev->stats.tx_1024_to_1518_byte_packets =
- stats.tx_1024_to_1518_byte_packets;
- edev->stats.tx_1519_to_2047_byte_packets =
- stats.tx_1519_to_2047_byte_packets;
- edev->stats.tx_2048_to_4095_byte_packets =
- stats.tx_2048_to_4095_byte_packets;
- edev->stats.tx_4096_to_9216_byte_packets =
- stats.tx_4096_to_9216_byte_packets;
- edev->stats.tx_9217_to_16383_byte_packets =
- stats.tx_9217_to_16383_byte_packets;
- edev->stats.tx_pause_frames = stats.tx_pause_frames;
- edev->stats.tx_pfc_frames = stats.tx_pfc_frames;
- edev->stats.tx_lpi_entry_count = stats.tx_lpi_entry_count;
- edev->stats.tx_total_collisions = stats.tx_total_collisions;
- edev->stats.brb_truncates = stats.brb_truncates;
- edev->stats.brb_discards = stats.brb_discards;
- edev->stats.tx_mac_ctrl_frames = stats.tx_mac_ctrl_frames;
+ p_common->tx_ucast_bytes = stats.common.tx_ucast_bytes;
+ p_common->tx_mcast_bytes = stats.common.tx_mcast_bytes;
+ p_common->tx_bcast_bytes = stats.common.tx_bcast_bytes;
+ p_common->tx_ucast_pkts = stats.common.tx_ucast_pkts;
+ p_common->tx_mcast_pkts = stats.common.tx_mcast_pkts;
+ p_common->tx_bcast_pkts = stats.common.tx_bcast_pkts;
+ p_common->tx_err_drop_pkts = stats.common.tx_err_drop_pkts;
+ p_common->coalesced_pkts = stats.common.tpa_coalesced_pkts;
+ p_common->coalesced_events = stats.common.tpa_coalesced_events;
+ p_common->coalesced_aborts_num = stats.common.tpa_aborts_num;
+ p_common->non_coalesced_pkts = stats.common.tpa_not_coalesced_pkts;
+ p_common->coalesced_bytes = stats.common.tpa_coalesced_bytes;
+
+ p_common->rx_64_byte_packets = stats.common.rx_64_byte_packets;
+ p_common->rx_65_to_127_byte_packets =
+ stats.common.rx_65_to_127_byte_packets;
+ p_common->rx_128_to_255_byte_packets =
+ stats.common.rx_128_to_255_byte_packets;
+ p_common->rx_256_to_511_byte_packets =
+ stats.common.rx_256_to_511_byte_packets;
+ p_common->rx_512_to_1023_byte_packets =
+ stats.common.rx_512_to_1023_byte_packets;
+ p_common->rx_1024_to_1518_byte_packets =
+ stats.common.rx_1024_to_1518_byte_packets;
+ p_common->rx_crc_errors = stats.common.rx_crc_errors;
+ p_common->rx_mac_crtl_frames = stats.common.rx_mac_crtl_frames;
+ p_common->rx_pause_frames = stats.common.rx_pause_frames;
+ p_common->rx_pfc_frames = stats.common.rx_pfc_frames;
+ p_common->rx_align_errors = stats.common.rx_align_errors;
+ p_common->rx_carrier_errors = stats.common.rx_carrier_errors;
+ p_common->rx_oversize_packets = stats.common.rx_oversize_packets;
+ p_common->rx_jabbers = stats.common.rx_jabbers;
+ p_common->rx_undersize_packets = stats.common.rx_undersize_packets;
+ p_common->rx_fragments = stats.common.rx_fragments;
+ p_common->tx_64_byte_packets = stats.common.tx_64_byte_packets;
+ p_common->tx_65_to_127_byte_packets =
+ stats.common.tx_65_to_127_byte_packets;
+ p_common->tx_128_to_255_byte_packets =
+ stats.common.tx_128_to_255_byte_packets;
+ p_common->tx_256_to_511_byte_packets =
+ stats.common.tx_256_to_511_byte_packets;
+ p_common->tx_512_to_1023_byte_packets =
+ stats.common.tx_512_to_1023_byte_packets;
+ p_common->tx_1024_to_1518_byte_packets =
+ stats.common.tx_1024_to_1518_byte_packets;
+ p_common->tx_pause_frames = stats.common.tx_pause_frames;
+ p_common->tx_pfc_frames = stats.common.tx_pfc_frames;
+ p_common->brb_truncates = stats.common.brb_truncates;
+ p_common->brb_discards = stats.common.brb_discards;
+ p_common->tx_mac_ctrl_frames = stats.common.tx_mac_ctrl_frames;
+
+ if (QEDE_IS_BB(edev)) {
+ struct qede_stats_bb *p_bb = &edev->stats.bb;
+
+ p_bb->rx_1519_to_1522_byte_packets =
+ stats.bb.rx_1519_to_1522_byte_packets;
+ p_bb->rx_1519_to_2047_byte_packets =
+ stats.bb.rx_1519_to_2047_byte_packets;
+ p_bb->rx_2048_to_4095_byte_packets =
+ stats.bb.rx_2048_to_4095_byte_packets;
+ p_bb->rx_4096_to_9216_byte_packets =
+ stats.bb.rx_4096_to_9216_byte_packets;
+ p_bb->rx_9217_to_16383_byte_packets =
+ stats.bb.rx_9217_to_16383_byte_packets;
+ p_bb->tx_1519_to_2047_byte_packets =
+ stats.bb.tx_1519_to_2047_byte_packets;
+ p_bb->tx_2048_to_4095_byte_packets =
+ stats.bb.tx_2048_to_4095_byte_packets;
+ p_bb->tx_4096_to_9216_byte_packets =
+ stats.bb.tx_4096_to_9216_byte_packets;
+ p_bb->tx_9217_to_16383_byte_packets =
+ stats.bb.tx_9217_to_16383_byte_packets;
+ p_bb->tx_lpi_entry_count = stats.bb.tx_lpi_entry_count;
+ p_bb->tx_total_collisions = stats.bb.tx_total_collisions;
+ } else {
+ struct qede_stats_ah *p_ah = &edev->stats.ah;
+
+ p_ah->rx_1519_to_max_byte_packets =
+ stats.ah.rx_1519_to_max_byte_packets;
+ p_ah->tx_1519_to_max_byte_packets =
+ stats.ah.tx_1519_to_max_byte_packets;
+ }
}
static void qede_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *stats)
{
struct qede_dev *edev = netdev_priv(dev);
+ struct qede_stats_common *p_common;
qede_fill_by_demand_stats(edev);
+ p_common = &edev->stats.common;
- stats->rx_packets = edev->stats.rx_ucast_pkts +
- edev->stats.rx_mcast_pkts +
- edev->stats.rx_bcast_pkts;
- stats->tx_packets = edev->stats.tx_ucast_pkts +
- edev->stats.tx_mcast_pkts +
- edev->stats.tx_bcast_pkts;
+ stats->rx_packets = p_common->rx_ucast_pkts + p_common->rx_mcast_pkts +
+ p_common->rx_bcast_pkts;
+ stats->tx_packets = p_common->tx_ucast_pkts + p_common->tx_mcast_pkts +
+ p_common->tx_bcast_pkts;
- stats->rx_bytes = edev->stats.rx_ucast_bytes +
- edev->stats.rx_mcast_bytes +
- edev->stats.rx_bcast_bytes;
+ stats->rx_bytes = p_common->rx_ucast_bytes + p_common->rx_mcast_bytes +
+ p_common->rx_bcast_bytes;
+ stats->tx_bytes = p_common->tx_ucast_bytes + p_common->tx_mcast_bytes +
+ p_common->tx_bcast_bytes;
- stats->tx_bytes = edev->stats.tx_ucast_bytes +
- edev->stats.tx_mcast_bytes +
- edev->stats.tx_bcast_bytes;
+ stats->tx_errors = p_common->tx_err_drop_pkts;
+ stats->multicast = p_common->rx_mcast_pkts + p_common->rx_bcast_pkts;
- stats->tx_errors = edev->stats.tx_err_drop_pkts;
- stats->multicast = edev->stats.rx_mcast_pkts +
- edev->stats.rx_bcast_pkts;
+ stats->rx_fifo_errors = p_common->no_buff_discards;
- stats->rx_fifo_errors = edev->stats.no_buff_discards;
-
- stats->collisions = edev->stats.tx_total_collisions;
- stats->rx_crc_errors = edev->stats.rx_crc_errors;
- stats->rx_frame_errors = edev->stats.rx_align_errors;
+ if (QEDE_IS_BB(edev))
+ stats->collisions = edev->stats.bb.tx_total_collisions;
+ stats->rx_crc_errors = p_common->rx_crc_errors;
+ stats->rx_frame_errors = p_common->rx_align_errors;
}
#ifdef CONFIG_QED_SRIOV
@@ -1165,9 +1187,11 @@ static int qede_alloc_mem_rxq(struct qede_dev *edev, struct qede_rx_queue *rxq)
rxq->num_rx_buffers = edev->q_num_rx_buffers;
rxq->rx_buf_size = NET_IP_ALIGN + ETH_OVERHEAD + edev->ndev->mtu;
+ rxq->rx_headroom = edev->xdp_prog ? XDP_PACKET_HEADROOM : 0;
- if (rxq->rx_buf_size > PAGE_SIZE)
- rxq->rx_buf_size = PAGE_SIZE;
+ /* Make sure that the headroom and payload fit in a single page */
+ if (rxq->rx_buf_size + rxq->rx_headroom > PAGE_SIZE)
+ rxq->rx_buf_size = PAGE_SIZE - rxq->rx_headroom;
/* Segment size to spilt a page in multiple equal parts,
* unless XDP is used in which case we'd use the entire page.
@@ -1229,7 +1253,7 @@ static void qede_free_mem_txq(struct qede_dev *edev, struct qede_tx_queue *txq)
{
/* Free the parallel SW ring */
if (txq->is_xdp)
- kfree(txq->sw_tx_ring.pages);
+ kfree(txq->sw_tx_ring.xdp);
else
kfree(txq->sw_tx_ring.skbs);
@@ -1247,9 +1271,9 @@ static int qede_alloc_mem_txq(struct qede_dev *edev, struct qede_tx_queue *txq)
/* Allocate the parallel driver ring for Tx buffers */
if (txq->is_xdp) {
- size = sizeof(*txq->sw_tx_ring.pages) * TX_RING_SIZE;
- txq->sw_tx_ring.pages = kzalloc(size, GFP_KERNEL);
- if (!txq->sw_tx_ring.pages)
+ size = sizeof(*txq->sw_tx_ring.xdp) * TX_RING_SIZE;
+ txq->sw_tx_ring.xdp = kzalloc(size, GFP_KERNEL);
+ if (!txq->sw_tx_ring.xdp)
goto err;
} else {
size = sizeof(*txq->sw_tx_ring.skbs) * TX_RING_SIZE;
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge.h b/drivers/net/ethernet/qlogic/qlge/qlge.h
index 6d31f92..84ac50f 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge.h
+++ b/drivers/net/ethernet/qlogic/qlge/qlge.h
@@ -1162,8 +1162,8 @@ struct ob_mac_tso_iocb_rsp {
struct ib_mac_iocb_rsp {
u8 opcode; /* 0x20 */
u8 flags1;
-#define IB_MAC_IOCB_RSP_OI 0x01 /* Overide intr delay */
-#define IB_MAC_IOCB_RSP_I 0x02 /* Disble Intr Generation */
+#define IB_MAC_IOCB_RSP_OI 0x01 /* Override intr delay */
+#define IB_MAC_IOCB_RSP_I 0x02 /* Disable Intr Generation */
#define IB_MAC_CSUM_ERR_MASK 0x1c /* A mask to use for csum errs */
#define IB_MAC_IOCB_RSP_TE 0x04 /* Checksum error */
#define IB_MAC_IOCB_RSP_NU 0x08 /* No checksum rcvd */
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index e9e6470..1188d42 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -4686,7 +4686,8 @@ static int ql_init_device(struct pci_dev *pdev, struct net_device *ndev,
/*
* Set up the operating parameters.
*/
- qdev->workqueue = alloc_ordered_workqueue(ndev->name, WQ_MEM_RECLAIM);
+ qdev->workqueue = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM,
+ ndev->name);
INIT_DELAYED_WORK(&qdev->asic_reset_work, ql_asic_reset_work);
INIT_DELAYED_WORK(&qdev->mpi_reset_work, ql_mpi_reset_work);
INIT_DELAYED_WORK(&qdev->mpi_work, ql_mpi_work);
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c b/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c
index 040b289..18c184e 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c
@@ -13,6 +13,7 @@
/* Qualcomm Technologies, Inc. EMAC SGMII Controller driver.
*/
+#include <linux/interrupt.h>
#include <linux/iopoll.h>
#include <linux/acpi.h>
#include <linux/of_device.h>
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 24b045b..0a8f281 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -8453,9 +8453,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
tp->opts1_mask = (tp->mac_version != RTL_GIGA_MAC_VER_01) ?
~(RxBOVF | RxFOVF) : ~0;
- init_timer(&tp->timer);
- tp->timer.data = (unsigned long) dev;
- tp->timer.function = rtl8169_phy_timer;
+ setup_timer(&tp->timer, rtl8169_phy_timer, (unsigned long)dev);
tp->rtl_fw = RTL_FIRMWARE_UNKNOWN;
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index b712ec2..bab1361 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -33,6 +33,7 @@
#include <net/rtnetlink.h>
#include <net/netevent.h>
#include <net/arp.h>
+#include <net/fib_rules.h>
#include <linux/io-64-nonatomic-lo-hi.h>
#include <generated/utsrelease.h>
@@ -2175,7 +2176,10 @@ static const struct switchdev_ops rocker_port_switchdev_ops = {
struct rocker_fib_event_work {
struct work_struct work;
- struct fib_entry_notifier_info fen_info;
+ union {
+ struct fib_entry_notifier_info fen_info;
+ struct fib_rule_notifier_info fr_info;
+ };
struct rocker *rocker;
unsigned long event;
};
@@ -2185,6 +2189,7 @@ static void rocker_router_fib_event_work(struct work_struct *work)
struct rocker_fib_event_work *fib_work =
container_of(work, struct rocker_fib_event_work, work);
struct rocker *rocker = fib_work->rocker;
+ struct fib_rule *rule;
int err;
/* Protect internal structures from changes */
@@ -2202,7 +2207,10 @@ static void rocker_router_fib_event_work(struct work_struct *work)
break;
case FIB_EVENT_RULE_ADD: /* fall through */
case FIB_EVENT_RULE_DEL:
- rocker_world_fib4_abort(rocker);
+ rule = fib_work->fr_info.rule;
+ if (!fib4_rule_default(rule))
+ rocker_world_fib4_abort(rocker);
+ fib_rule_put(rule);
break;
}
rtnl_unlock();
@@ -2233,6 +2241,11 @@ static int rocker_router_fib_event(struct notifier_block *nb,
*/
fib_info_hold(fib_work->fen_info.fi);
break;
+ case FIB_EVENT_RULE_ADD: /* fall through */
+ case FIB_EVENT_RULE_DEL:
+ memcpy(&fib_work->fr_info, ptr, sizeof(fib_work->fr_info));
+ fib_rule_get(fib_work->fr_info.rule);
+ break;
}
queue_work(rocker->rocker_owq, &fib_work->work);
diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c
index 7cd76b6..2ae8524 100644
--- a/drivers/net/ethernet/rocker/rocker_ofdpa.c
+++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c
@@ -2216,18 +2216,15 @@ static int ofdpa_port_stp_update(struct ofdpa_port *ofdpa_port,
{
bool want[OFDPA_CTRL_MAX] = { 0, };
bool prev_ctrls[OFDPA_CTRL_MAX];
- u8 uninitialized_var(prev_state);
+ u8 prev_state;
int err;
int i;
- if (switchdev_trans_ph_prepare(trans)) {
- memcpy(prev_ctrls, ofdpa_port->ctrls, sizeof(prev_ctrls));
- prev_state = ofdpa_port->stp_state;
- }
-
- if (ofdpa_port->stp_state == state)
+ prev_state = ofdpa_port->stp_state;
+ if (prev_state == state)
return 0;
+ memcpy(prev_ctrls, ofdpa_port->ctrls, sizeof(prev_ctrls));
ofdpa_port->stp_state = state;
switch (state) {
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index c60c2d4..78efb28 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -119,6 +119,7 @@ struct efx_ef10_filter_table {
bool mc_promisc;
/* Whether in multicast promiscuous mode when last changed */
bool mc_promisc_last;
+ bool mc_overflow; /* Too many MC addrs; should always imply mc_promisc */
bool vlan_filter;
struct list_head vlan_list;
};
@@ -5058,6 +5059,7 @@ static void efx_ef10_filter_mc_addr_list(struct efx_nic *efx)
struct netdev_hw_addr *mc;
unsigned int i, addr_count;
+ table->mc_overflow = false;
table->mc_promisc = !!(net_dev->flags & (IFF_PROMISC | IFF_ALLMULTI));
addr_count = netdev_mc_count(net_dev);
@@ -5065,6 +5067,7 @@ static void efx_ef10_filter_mc_addr_list(struct efx_nic *efx)
netdev_for_each_mc_addr(mc, net_dev) {
if (i >= EFX_EF10_FILTER_DEV_MC_MAX) {
table->mc_promisc = true;
+ table->mc_overflow = true;
break;
}
ether_addr_copy(table->dev_mc_list[i].addr, mc->addr);
@@ -5469,12 +5472,15 @@ static void efx_ef10_filter_vlan_sync_rx_mode(struct efx_nic *efx,
}
} else {
/* If we failed to insert promiscuous filters, don't
- * rollback. Regardless, also insert the mc_list
+ * rollback. Regardless, also insert the mc_list,
+ * unless it's incomplete due to overflow
*/
efx_ef10_filter_insert_def(efx, vlan,
EFX_ENCAP_TYPE_NONE,
true, false);
- efx_ef10_filter_insert_addr_list(efx, vlan, true, false);
+ if (!table->mc_overflow)
+ efx_ef10_filter_insert_addr_list(efx, vlan,
+ true, false);
}
} else {
/* If any filters failed to insert, rollback and fall back to
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 334bcc6..50d2826 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -2404,7 +2404,7 @@ static void efx_udp_tunnel_del(struct net_device *dev, struct udp_tunnel_info *t
tnl.type = (u16)efx_tunnel_type;
tnl.port = ti->port;
- if (efx->type->udp_tnl_add_port)
+ if (efx->type->udp_tnl_del_port)
(void)efx->type->udp_tnl_del_port(efx, tnl);
}
diff --git a/drivers/net/ethernet/sfc/falcon/tx.c b/drivers/net/ethernet/sfc/falcon/tx.c
index 104fb15..f6daf09 100644
--- a/drivers/net/ethernet/sfc/falcon/tx.c
+++ b/drivers/net/ethernet/sfc/falcon/tx.c
@@ -437,11 +437,13 @@ int ef4_setup_tc(struct net_device *net_dev, u32 handle, __be16 proto,
if (ntc->type != TC_SETUP_MQPRIO)
return -EINVAL;
- num_tc = ntc->tc;
+ num_tc = ntc->mqprio->num_tc;
if (ef4_nic_rev(efx) < EF4_REV_FALCON_B0 || num_tc > EF4_MAX_TX_TC)
return -EINVAL;
+ ntc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
if (num_tc == net_dev->num_tc)
return 0;
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index ff88d60..3bdf87f 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -665,11 +665,13 @@ int efx_setup_tc(struct net_device *net_dev, u32 handle, __be16 proto,
if (ntc->type != TC_SETUP_MQPRIO)
return -EINVAL;
- num_tc = ntc->tc;
+ num_tc = ntc->mqprio->num_tc;
if (num_tc > EFX_MAX_TX_TC)
return -EINVAL;
+ ntc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
if (num_tc == net_dev->num_tc)
return 0;
diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c
index 4f19c61..36307d3 100644
--- a/drivers/net/ethernet/smsc/smc911x.c
+++ b/drivers/net/ethernet/smsc/smc911x.c
@@ -1446,40 +1446,40 @@ static int smc911x_close(struct net_device *dev)
* Ethtool support
*/
static int
-smc911x_ethtool_getsettings(struct net_device *dev, struct ethtool_cmd *cmd)
+smc911x_ethtool_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
struct smc911x_local *lp = netdev_priv(dev);
int ret, status;
unsigned long flags;
+ u32 supported;
DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__);
- cmd->maxtxpkt = 1;
- cmd->maxrxpkt = 1;
if (lp->phy_type != 0) {
spin_lock_irqsave(&lp->lock, flags);
- ret = mii_ethtool_gset(&lp->mii, cmd);
+ ret = mii_ethtool_get_link_ksettings(&lp->mii, cmd);
spin_unlock_irqrestore(&lp->lock, flags);
} else {
- cmd->supported = SUPPORTED_10baseT_Half |
+ supported = SUPPORTED_10baseT_Half |
SUPPORTED_10baseT_Full |
SUPPORTED_TP | SUPPORTED_AUI;
if (lp->ctl_rspeed == 10)
- ethtool_cmd_speed_set(cmd, SPEED_10);
+ cmd->base.speed = SPEED_10;
else if (lp->ctl_rspeed == 100)
- ethtool_cmd_speed_set(cmd, SPEED_100);
+ cmd->base.speed = SPEED_100;
- cmd->autoneg = AUTONEG_DISABLE;
- if (lp->mii.phy_id==1)
- cmd->transceiver = XCVR_INTERNAL;
- else
- cmd->transceiver = XCVR_EXTERNAL;
- cmd->port = 0;
+ cmd->base.autoneg = AUTONEG_DISABLE;
+ cmd->base.port = 0;
SMC_GET_PHY_SPECIAL(lp, lp->mii.phy_id, status);
- cmd->duplex =
+ cmd->base.duplex =
(status & (PHY_SPECIAL_SPD_10FULL_ | PHY_SPECIAL_SPD_100FULL_)) ?
DUPLEX_FULL : DUPLEX_HALF;
+
+ ethtool_convert_legacy_u32_to_link_mode(
+ cmd->link_modes.supported, supported);
+
ret = 0;
}
@@ -1487,7 +1487,8 @@ smc911x_ethtool_getsettings(struct net_device *dev, struct ethtool_cmd *cmd)
}
static int
-smc911x_ethtool_setsettings(struct net_device *dev, struct ethtool_cmd *cmd)
+smc911x_ethtool_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
{
struct smc911x_local *lp = netdev_priv(dev);
int ret;
@@ -1495,16 +1496,18 @@ smc911x_ethtool_setsettings(struct net_device *dev, struct ethtool_cmd *cmd)
if (lp->phy_type != 0) {
spin_lock_irqsave(&lp->lock, flags);
- ret = mii_ethtool_sset(&lp->mii, cmd);
+ ret = mii_ethtool_set_link_ksettings(&lp->mii, cmd);
spin_unlock_irqrestore(&lp->lock, flags);
} else {
- if (cmd->autoneg != AUTONEG_DISABLE ||
- cmd->speed != SPEED_10 ||
- (cmd->duplex != DUPLEX_HALF && cmd->duplex != DUPLEX_FULL) ||
- (cmd->port != PORT_TP && cmd->port != PORT_AUI))
+ if (cmd->base.autoneg != AUTONEG_DISABLE ||
+ cmd->base.speed != SPEED_10 ||
+ (cmd->base.duplex != DUPLEX_HALF &&
+ cmd->base.duplex != DUPLEX_FULL) ||
+ (cmd->base.port != PORT_TP &&
+ cmd->base.port != PORT_AUI))
return -EINVAL;
- lp->ctl_rfduplx = cmd->duplex == DUPLEX_FULL;
+ lp->ctl_rfduplx = cmd->base.duplex == DUPLEX_FULL;
ret = 0;
}
@@ -1686,8 +1689,6 @@ static int smc911x_ethtool_geteeprom_len(struct net_device *dev)
}
static const struct ethtool_ops smc911x_ethtool_ops = {
- .get_settings = smc911x_ethtool_getsettings,
- .set_settings = smc911x_ethtool_setsettings,
.get_drvinfo = smc911x_ethtool_getdrvinfo,
.get_msglevel = smc911x_ethtool_getmsglevel,
.set_msglevel = smc911x_ethtool_setmsglevel,
@@ -1698,6 +1699,8 @@ static const struct ethtool_ops smc911x_ethtool_ops = {
.get_eeprom_len = smc911x_ethtool_geteeprom_len,
.get_eeprom = smc911x_ethtool_geteeprom,
.set_eeprom = smc911x_ethtool_seteeprom,
+ .get_link_ksettings = smc911x_ethtool_get_link_ksettings,
+ .set_link_ksettings = smc911x_ethtool_set_link_ksettings,
};
/*
diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index 65077c7..91e9bd7 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -1535,32 +1535,33 @@ static int smc_close(struct net_device *dev)
* Ethtool support
*/
static int
-smc_ethtool_getsettings(struct net_device *dev, struct ethtool_cmd *cmd)
+smc_ethtool_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
struct smc_local *lp = netdev_priv(dev);
int ret;
- cmd->maxtxpkt = 1;
- cmd->maxrxpkt = 1;
-
if (lp->phy_type != 0) {
spin_lock_irq(&lp->lock);
- ret = mii_ethtool_gset(&lp->mii, cmd);
+ ret = mii_ethtool_get_link_ksettings(&lp->mii, cmd);
spin_unlock_irq(&lp->lock);
} else {
- cmd->supported = SUPPORTED_10baseT_Half |
+ u32 supported = SUPPORTED_10baseT_Half |
SUPPORTED_10baseT_Full |
SUPPORTED_TP | SUPPORTED_AUI;
if (lp->ctl_rspeed == 10)
- ethtool_cmd_speed_set(cmd, SPEED_10);
+ cmd->base.speed = SPEED_10;
else if (lp->ctl_rspeed == 100)
- ethtool_cmd_speed_set(cmd, SPEED_100);
+ cmd->base.speed = SPEED_100;
- cmd->autoneg = AUTONEG_DISABLE;
- cmd->transceiver = XCVR_INTERNAL;
- cmd->port = 0;
- cmd->duplex = lp->tcr_cur_mode & TCR_SWFDUP ? DUPLEX_FULL : DUPLEX_HALF;
+ cmd->base.autoneg = AUTONEG_DISABLE;
+ cmd->base.port = 0;
+ cmd->base.duplex = lp->tcr_cur_mode & TCR_SWFDUP ?
+ DUPLEX_FULL : DUPLEX_HALF;
+
+ ethtool_convert_legacy_u32_to_link_mode(
+ cmd->link_modes.supported, supported);
ret = 0;
}
@@ -1569,24 +1570,26 @@ smc_ethtool_getsettings(struct net_device *dev, struct ethtool_cmd *cmd)
}
static int
-smc_ethtool_setsettings(struct net_device *dev, struct ethtool_cmd *cmd)
+smc_ethtool_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
{
struct smc_local *lp = netdev_priv(dev);
int ret;
if (lp->phy_type != 0) {
spin_lock_irq(&lp->lock);
- ret = mii_ethtool_sset(&lp->mii, cmd);
+ ret = mii_ethtool_set_link_ksettings(&lp->mii, cmd);
spin_unlock_irq(&lp->lock);
} else {
- if (cmd->autoneg != AUTONEG_DISABLE ||
- cmd->speed != SPEED_10 ||
- (cmd->duplex != DUPLEX_HALF && cmd->duplex != DUPLEX_FULL) ||
- (cmd->port != PORT_TP && cmd->port != PORT_AUI))
+ if (cmd->base.autoneg != AUTONEG_DISABLE ||
+ cmd->base.speed != SPEED_10 ||
+ (cmd->base.duplex != DUPLEX_HALF &&
+ cmd->base.duplex != DUPLEX_FULL) ||
+ (cmd->base.port != PORT_TP && cmd->base.port != PORT_AUI))
return -EINVAL;
-// lp->port = cmd->port;
- lp->ctl_rfduplx = cmd->duplex == DUPLEX_FULL;
+// lp->port = cmd->base.port;
+ lp->ctl_rfduplx = cmd->base.duplex == DUPLEX_FULL;
// if (netif_running(dev))
// smc_set_port(dev);
@@ -1744,8 +1747,6 @@ static int smc_ethtool_seteeprom(struct net_device *dev,
static const struct ethtool_ops smc_ethtool_ops = {
- .get_settings = smc_ethtool_getsettings,
- .set_settings = smc_ethtool_setsettings,
.get_drvinfo = smc_ethtool_getdrvinfo,
.get_msglevel = smc_ethtool_getmsglevel,
@@ -1755,6 +1756,8 @@ static const struct ethtool_ops smc_ethtool_ops = {
.get_eeprom_len = smc_ethtool_geteeprom_len,
.get_eeprom = smc_ethtool_geteeprom,
.set_eeprom = smc_ethtool_seteeprom,
+ .get_link_ksettings = smc_ethtool_get_link_ksettings,
+ .set_link_ksettings = smc_ethtool_set_link_ksettings,
};
static const struct net_device_ops smc_netdev_ops = {
diff --git a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
index 01a8c02..37881f8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
@@ -26,12 +26,15 @@
static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
{
- struct stmmac_priv *priv = (struct stmmac_priv *)p;
- unsigned int entry = priv->cur_tx;
- struct dma_desc *desc = priv->dma_tx + entry;
+ struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)p;
unsigned int nopaged_len = skb_headlen(skb);
+ struct stmmac_priv *priv = tx_q->priv_data;
+ unsigned int entry = tx_q->cur_tx;
unsigned int bmax, des2;
unsigned int i = 1, len;
+ struct dma_desc *desc;
+
+ desc = tx_q->dma_tx + entry;
if (priv->plat->enh_desc)
bmax = BUF_SIZE_8KiB;
@@ -45,16 +48,16 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
desc->des2 = cpu_to_le32(des2);
if (dma_mapping_error(priv->device, des2))
return -1;
- priv->tx_skbuff_dma[entry].buf = des2;
- priv->tx_skbuff_dma[entry].len = bmax;
+ tx_q->tx_skbuff_dma[entry].buf = des2;
+ tx_q->tx_skbuff_dma[entry].len = bmax;
/* do not close the descriptor and do not set own bit */
priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, STMMAC_CHAIN_MODE,
0, false);
while (len != 0) {
- priv->tx_skbuff[entry] = NULL;
+ tx_q->tx_skbuff[entry] = NULL;
entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE);
- desc = priv->dma_tx + entry;
+ desc = tx_q->dma_tx + entry;
if (len > bmax) {
des2 = dma_map_single(priv->device,
@@ -63,8 +66,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
desc->des2 = cpu_to_le32(des2);
if (dma_mapping_error(priv->device, des2))
return -1;
- priv->tx_skbuff_dma[entry].buf = des2;
- priv->tx_skbuff_dma[entry].len = bmax;
+ tx_q->tx_skbuff_dma[entry].buf = des2;
+ tx_q->tx_skbuff_dma[entry].len = bmax;
priv->hw->desc->prepare_tx_desc(desc, 0, bmax, csum,
STMMAC_CHAIN_MODE, 1,
false);
@@ -77,8 +80,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
desc->des2 = cpu_to_le32(des2);
if (dma_mapping_error(priv->device, des2))
return -1;
- priv->tx_skbuff_dma[entry].buf = des2;
- priv->tx_skbuff_dma[entry].len = len;
+ tx_q->tx_skbuff_dma[entry].buf = des2;
+ tx_q->tx_skbuff_dma[entry].len = len;
/* last descriptor can be set now */
priv->hw->desc->prepare_tx_desc(desc, 0, len, csum,
STMMAC_CHAIN_MODE, 1,
@@ -87,7 +90,7 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
}
}
- priv->cur_tx = entry;
+ tx_q->cur_tx = entry;
return entry;
}
@@ -136,32 +139,34 @@ static void stmmac_init_dma_chain(void *des, dma_addr_t phy_addr,
static void stmmac_refill_desc3(void *priv_ptr, struct dma_desc *p)
{
- struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr;
+ struct stmmac_rx_queue *rx_q = (struct stmmac_rx_queue *)priv_ptr;
+ struct stmmac_priv *priv = rx_q->priv_data;
if (priv->hwts_rx_en && !priv->extend_desc)
/* NOTE: Device will overwrite des3 with timestamp value if
* 1588-2002 time stamping is enabled, hence reinitialize it
* to keep explicit chaining in the descriptor.
*/
- p->des3 = cpu_to_le32((unsigned int)(priv->dma_rx_phy +
- (((priv->dirty_rx) + 1) %
+ p->des3 = cpu_to_le32((unsigned int)(rx_q->dma_rx_phy +
+ (((rx_q->dirty_rx) + 1) %
DMA_RX_SIZE) *
sizeof(struct dma_desc)));
}
static void stmmac_clean_desc3(void *priv_ptr, struct dma_desc *p)
{
- struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr;
- unsigned int entry = priv->dirty_tx;
+ struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)priv_ptr;
+ struct stmmac_priv *priv = tx_q->priv_data;
+ unsigned int entry = tx_q->dirty_tx;
- if (priv->tx_skbuff_dma[entry].last_segment && !priv->extend_desc &&
+ if (tx_q->tx_skbuff_dma[entry].last_segment && !priv->extend_desc &&
priv->hwts_tx_en)
/* NOTE: Device will overwrite des3 with timestamp value if
* 1588-2002 time stamping is enabled, hence reinitialize it
* to keep explicit chaining in the descriptor.
*/
- p->des3 = cpu_to_le32((unsigned int)((priv->dma_tx_phy +
- ((priv->dirty_tx + 1) % DMA_TX_SIZE))
+ p->des3 = cpu_to_le32((unsigned int)((tx_q->dma_tx_phy +
+ ((tx_q->dirty_tx + 1) % DMA_TX_SIZE))
* sizeof(struct dma_desc)));
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 04d9245..90d28bc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -246,6 +246,15 @@ struct stmmac_extra_stats {
#define STMMAC_TX_MAX_FRAMES 256
#define STMMAC_TX_FRAMES 64
+/* Packets types */
+enum packets_types {
+ PACKET_AVCPQ = 0x1, /* AV Untagged Control packets */
+ PACKET_PTPQ = 0x2, /* PTP Packets */
+ PACKET_DCBCPQ = 0x3, /* DCB Control Packets */
+ PACKET_UPQ = 0x4, /* Untagged Packets */
+ PACKET_MCBCQ = 0x5, /* Multicast & Broadcast Packets */
+};
+
/* Rx IPC status */
enum rx_frame_status {
good_frame = 0x0,
@@ -324,6 +333,9 @@ struct dma_features {
unsigned int number_tx_queues;
/* Alternate (enhanced) DESC mode */
unsigned int enh_desc;
+ /* TX and RX FIFO sizes */
+ unsigned int tx_fifo_size;
+ unsigned int rx_fifo_size;
};
/* GMAC TX FIFO is 8K, Rx FIFO is 16K */
@@ -413,6 +425,14 @@ struct stmmac_dma_ops {
int (*reset)(void __iomem *ioaddr);
void (*init)(void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg,
u32 dma_tx, u32 dma_rx, int atds);
+ void (*init_chan)(void __iomem *ioaddr,
+ struct stmmac_dma_cfg *dma_cfg, u32 chan);
+ void (*init_rx_chan)(void __iomem *ioaddr,
+ struct stmmac_dma_cfg *dma_cfg,
+ u32 dma_rx_phy, u32 chan);
+ void (*init_tx_chan)(void __iomem *ioaddr,
+ struct stmmac_dma_cfg *dma_cfg,
+ u32 dma_tx_phy, u32 chan);
/* Configure the AXI Bus Mode Register */
void (*axi)(void __iomem *ioaddr, struct stmmac_axi *axi);
/* Dump DMA registers */
@@ -421,25 +441,28 @@ struct stmmac_dma_ops {
* An invalid value enables the store-and-forward mode */
void (*dma_mode)(void __iomem *ioaddr, int txmode, int rxmode,
int rxfifosz);
+ void (*dma_rx_mode)(void __iomem *ioaddr, int mode, u32 channel,
+ int fifosz);
+ void (*dma_tx_mode)(void __iomem *ioaddr, int mode, u32 channel);
/* To track extra statistic (if supported) */
void (*dma_diagnostic_fr) (void *data, struct stmmac_extra_stats *x,
void __iomem *ioaddr);
void (*enable_dma_transmission) (void __iomem *ioaddr);
- void (*enable_dma_irq) (void __iomem *ioaddr);
- void (*disable_dma_irq) (void __iomem *ioaddr);
- void (*start_tx) (void __iomem *ioaddr);
- void (*stop_tx) (void __iomem *ioaddr);
- void (*start_rx) (void __iomem *ioaddr);
- void (*stop_rx) (void __iomem *ioaddr);
+ void (*enable_dma_irq)(void __iomem *ioaddr, u32 chan);
+ void (*disable_dma_irq)(void __iomem *ioaddr, u32 chan);
+ void (*start_tx)(void __iomem *ioaddr, u32 chan);
+ void (*stop_tx)(void __iomem *ioaddr, u32 chan);
+ void (*start_rx)(void __iomem *ioaddr, u32 chan);
+ void (*stop_rx)(void __iomem *ioaddr, u32 chan);
int (*dma_interrupt) (void __iomem *ioaddr,
- struct stmmac_extra_stats *x);
+ struct stmmac_extra_stats *x, u32 chan);
/* If supported then get the optional core features */
void (*get_hw_feature)(void __iomem *ioaddr,
struct dma_features *dma_cap);
/* Program the HW RX Watchdog */
- void (*rx_watchdog) (void __iomem *ioaddr, u32 riwt);
- void (*set_tx_ring_len)(void __iomem *ioaddr, u32 len);
- void (*set_rx_ring_len)(void __iomem *ioaddr, u32 len);
+ void (*rx_watchdog)(void __iomem *ioaddr, u32 riwt, u32 number_chan);
+ void (*set_tx_ring_len)(void __iomem *ioaddr, u32 len, u32 chan);
+ void (*set_rx_ring_len)(void __iomem *ioaddr, u32 len, u32 chan);
void (*set_rx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
void (*set_tx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
void (*enable_tso)(void __iomem *ioaddr, bool en, u32 chan);
@@ -451,20 +474,44 @@ struct mac_device_info;
struct stmmac_ops {
/* MAC core initialization */
void (*core_init)(struct mac_device_info *hw, int mtu);
+ /* Enable the MAC RX/TX */
+ void (*set_mac)(void __iomem *ioaddr, bool enable);
/* Enable and verify that the IPC module is supported */
int (*rx_ipc)(struct mac_device_info *hw);
/* Enable RX Queues */
- void (*rx_queue_enable)(struct mac_device_info *hw, u32 queue);
+ void (*rx_queue_enable)(struct mac_device_info *hw, u8 mode, u32 queue);
+ /* RX Queues Priority */
+ void (*rx_queue_prio)(struct mac_device_info *hw, u32 prio, u32 queue);
+ /* TX Queues Priority */
+ void (*tx_queue_prio)(struct mac_device_info *hw, u32 prio, u32 queue);
+ /* RX Queues Routing */
+ void (*rx_queue_routing)(struct mac_device_info *hw, u8 packet,
+ u32 queue);
+ /* Program RX Algorithms */
+ void (*prog_mtl_rx_algorithms)(struct mac_device_info *hw, u32 rx_alg);
+ /* Program TX Algorithms */
+ void (*prog_mtl_tx_algorithms)(struct mac_device_info *hw, u32 tx_alg);
+ /* Set MTL TX queues weight */
+ void (*set_mtl_tx_queue_weight)(struct mac_device_info *hw,
+ u32 weight, u32 queue);
+ /* RX MTL queue to RX dma mapping */
+ void (*map_mtl_to_dma)(struct mac_device_info *hw, u32 queue, u32 chan);
+ /* Configure AV Algorithm */
+ void (*config_cbs)(struct mac_device_info *hw, u32 send_slope,
+ u32 idle_slope, u32 high_credit, u32 low_credit,
+ u32 queue);
/* Dump MAC registers */
void (*dump_regs)(struct mac_device_info *hw, u32 *reg_space);
/* Handle extra events on specific interrupts hw dependent */
int (*host_irq_status)(struct mac_device_info *hw,
struct stmmac_extra_stats *x);
+ /* Handle MTL interrupts */
+ int (*host_mtl_irq_status)(struct mac_device_info *hw, u32 chan);
/* Multicast filter setting */
void (*set_filter)(struct mac_device_info *hw, struct net_device *dev);
/* Flow control setting */
void (*flow_ctrl)(struct mac_device_info *hw, unsigned int duplex,
- unsigned int fc, unsigned int pause_time);
+ unsigned int fc, unsigned int pause_time, u32 tx_cnt);
/* Set power management mode (e.g. magic frame) */
void (*pmt)(struct mac_device_info *hw, unsigned long mode);
/* Set/Get Unicast MAC addresses */
@@ -477,7 +524,8 @@ struct stmmac_ops {
void (*reset_eee_mode)(struct mac_device_info *hw);
void (*set_eee_timer)(struct mac_device_info *hw, int ls, int tw);
void (*set_eee_pls)(struct mac_device_info *hw, int link);
- void (*debug)(void __iomem *ioaddr, struct stmmac_extra_stats *x);
+ void (*debug)(void __iomem *ioaddr, struct stmmac_extra_stats *x,
+ u32 rx_queues, u32 tx_queues);
/* PCS calls */
void (*pcs_ctrl_ane)(void __iomem *ioaddr, bool ane, bool srgmi_ral,
bool loopback);
@@ -547,6 +595,11 @@ struct mac_device_info {
unsigned int ps;
};
+struct stmmac_rx_routing {
+ u32 reg_mask;
+ u32 reg_shift;
+};
+
struct mac_device_info *dwmac1000_setup(void __iomem *ioaddr, int mcbins,
int perfect_uc_entries,
int *synopsys_id);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
index 1a3fa3d..dd6a2f9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
@@ -14,16 +14,34 @@
#include <linux/clk.h>
#include <linux/clk-provider.h>
#include <linux/device.h>
+#include <linux/gpio/consumer.h>
#include <linux/ethtool.h>
#include <linux/io.h>
+#include <linux/iopoll.h>
#include <linux/ioport.h>
#include <linux/module.h>
+#include <linux/of_device.h>
#include <linux/of_net.h>
#include <linux/mfd/syscon.h>
#include <linux/platform_device.h>
+#include <linux/reset.h>
#include <linux/stmmac.h>
#include "stmmac_platform.h"
+#include "dwmac4.h"
+
+struct tegra_eqos {
+ struct device *dev;
+ void __iomem *regs;
+
+ struct reset_control *rst;
+ struct clk *clk_master;
+ struct clk *clk_slave;
+ struct clk *clk_tx;
+ struct clk *clk_rx;
+
+ struct gpio_desc *reset;
+};
static int dwc_eth_dwmac_config_dt(struct platform_device *pdev,
struct plat_stmmacenet_data *plat_dat)
@@ -106,13 +124,309 @@ static int dwc_eth_dwmac_config_dt(struct platform_device *pdev,
return 0;
}
+static void *dwc_qos_probe(struct platform_device *pdev,
+ struct plat_stmmacenet_data *plat_dat,
+ struct stmmac_resources *stmmac_res)
+{
+ int err;
+
+ plat_dat->stmmac_clk = devm_clk_get(&pdev->dev, "apb_pclk");
+ if (IS_ERR(plat_dat->stmmac_clk)) {
+ dev_err(&pdev->dev, "apb_pclk clock not found.\n");
+ return ERR_CAST(plat_dat->stmmac_clk);
+ }
+
+ err = clk_prepare_enable(plat_dat->stmmac_clk);
+ if (err < 0) {
+ dev_err(&pdev->dev, "failed to enable apb_pclk clock: %d\n",
+ err);
+ return ERR_PTR(err);
+ }
+
+ plat_dat->pclk = devm_clk_get(&pdev->dev, "phy_ref_clk");
+ if (IS_ERR(plat_dat->pclk)) {
+ dev_err(&pdev->dev, "phy_ref_clk clock not found.\n");
+ err = PTR_ERR(plat_dat->pclk);
+ goto disable;
+ }
+
+ err = clk_prepare_enable(plat_dat->pclk);
+ if (err < 0) {
+ dev_err(&pdev->dev, "failed to enable phy_ref clock: %d\n",
+ err);
+ goto disable;
+ }
+
+ return NULL;
+
+disable:
+ clk_disable_unprepare(plat_dat->stmmac_clk);
+ return ERR_PTR(err);
+}
+
+static int dwc_qos_remove(struct platform_device *pdev)
+{
+ struct net_device *ndev = platform_get_drvdata(pdev);
+ struct stmmac_priv *priv = netdev_priv(ndev);
+
+ clk_disable_unprepare(priv->plat->pclk);
+ clk_disable_unprepare(priv->plat->stmmac_clk);
+
+ return 0;
+}
+
+#define SDMEMCOMPPADCTRL 0x8800
+#define SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD BIT(31)
+
+#define AUTO_CAL_CONFIG 0x8804
+#define AUTO_CAL_CONFIG_START BIT(31)
+#define AUTO_CAL_CONFIG_ENABLE BIT(29)
+
+#define AUTO_CAL_STATUS 0x880c
+#define AUTO_CAL_STATUS_ACTIVE BIT(31)
+
+static void tegra_eqos_fix_speed(void *priv, unsigned int speed)
+{
+ struct tegra_eqos *eqos = priv;
+ unsigned long rate = 125000000;
+ bool needs_calibration = false;
+ u32 value;
+ int err;
+
+ switch (speed) {
+ case SPEED_1000:
+ needs_calibration = true;
+ rate = 125000000;
+ break;
+
+ case SPEED_100:
+ needs_calibration = true;
+ rate = 25000000;
+ break;
+
+ case SPEED_10:
+ rate = 2500000;
+ break;
+
+ default:
+ dev_err(eqos->dev, "invalid speed %u\n", speed);
+ break;
+ }
+
+ if (needs_calibration) {
+ /* calibrate */
+ value = readl(eqos->regs + SDMEMCOMPPADCTRL);
+ value |= SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD;
+ writel(value, eqos->regs + SDMEMCOMPPADCTRL);
+
+ udelay(1);
+
+ value = readl(eqos->regs + AUTO_CAL_CONFIG);
+ value |= AUTO_CAL_CONFIG_START | AUTO_CAL_CONFIG_ENABLE;
+ writel(value, eqos->regs + AUTO_CAL_CONFIG);
+
+ err = readl_poll_timeout_atomic(eqos->regs + AUTO_CAL_STATUS,
+ value,
+ value & AUTO_CAL_STATUS_ACTIVE,
+ 1, 10);
+ if (err < 0) {
+ dev_err(eqos->dev, "calibration did not start\n");
+ goto failed;
+ }
+
+ err = readl_poll_timeout_atomic(eqos->regs + AUTO_CAL_STATUS,
+ value,
+ (value & AUTO_CAL_STATUS_ACTIVE) == 0,
+ 20, 200);
+ if (err < 0) {
+ dev_err(eqos->dev, "calibration didn't finish\n");
+ goto failed;
+ }
+
+ failed:
+ value = readl(eqos->regs + SDMEMCOMPPADCTRL);
+ value &= ~SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD;
+ writel(value, eqos->regs + SDMEMCOMPPADCTRL);
+ } else {
+ value = readl(eqos->regs + AUTO_CAL_CONFIG);
+ value &= ~AUTO_CAL_CONFIG_ENABLE;
+ writel(value, eqos->regs + AUTO_CAL_CONFIG);
+ }
+
+ err = clk_set_rate(eqos->clk_tx, rate);
+ if (err < 0)
+ dev_err(eqos->dev, "failed to set TX rate: %d\n", err);
+}
+
+static int tegra_eqos_init(struct platform_device *pdev, void *priv)
+{
+ struct tegra_eqos *eqos = priv;
+ unsigned long rate;
+ u32 value;
+
+ rate = clk_get_rate(eqos->clk_slave);
+
+ value = (rate / 1000000) - 1;
+ writel(value, eqos->regs + GMAC_1US_TIC_COUNTER);
+
+ return 0;
+}
+
+static void *tegra_eqos_probe(struct platform_device *pdev,
+ struct plat_stmmacenet_data *data,
+ struct stmmac_resources *res)
+{
+ struct tegra_eqos *eqos;
+ int err;
+
+ eqos = devm_kzalloc(&pdev->dev, sizeof(*eqos), GFP_KERNEL);
+ if (!eqos) {
+ err = -ENOMEM;
+ goto error;
+ }
+
+ eqos->dev = &pdev->dev;
+ eqos->regs = res->addr;
+
+ eqos->clk_master = devm_clk_get(&pdev->dev, "master_bus");
+ if (IS_ERR(eqos->clk_master)) {
+ err = PTR_ERR(eqos->clk_master);
+ goto error;
+ }
+
+ err = clk_prepare_enable(eqos->clk_master);
+ if (err < 0)
+ goto error;
+
+ eqos->clk_slave = devm_clk_get(&pdev->dev, "slave_bus");
+ if (IS_ERR(eqos->clk_slave)) {
+ err = PTR_ERR(eqos->clk_slave);
+ goto disable_master;
+ }
+
+ data->stmmac_clk = eqos->clk_slave;
+
+ err = clk_prepare_enable(eqos->clk_slave);
+ if (err < 0)
+ goto disable_master;
+
+ eqos->clk_rx = devm_clk_get(&pdev->dev, "rx");
+ if (IS_ERR(eqos->clk_rx)) {
+ err = PTR_ERR(eqos->clk_rx);
+ goto disable_slave;
+ }
+
+ err = clk_prepare_enable(eqos->clk_rx);
+ if (err < 0)
+ goto disable_slave;
+
+ eqos->clk_tx = devm_clk_get(&pdev->dev, "tx");
+ if (IS_ERR(eqos->clk_tx)) {
+ err = PTR_ERR(eqos->clk_tx);
+ goto disable_rx;
+ }
+
+ err = clk_prepare_enable(eqos->clk_tx);
+ if (err < 0)
+ goto disable_rx;
+
+ eqos->reset = devm_gpiod_get(&pdev->dev, "phy-reset", GPIOD_OUT_HIGH);
+ if (IS_ERR(eqos->reset)) {
+ err = PTR_ERR(eqos->reset);
+ goto disable_tx;
+ }
+
+ usleep_range(2000, 4000);
+ gpiod_set_value(eqos->reset, 0);
+
+ eqos->rst = devm_reset_control_get(&pdev->dev, "eqos");
+ if (IS_ERR(eqos->rst)) {
+ err = PTR_ERR(eqos->rst);
+ goto reset_phy;
+ }
+
+ err = reset_control_assert(eqos->rst);
+ if (err < 0)
+ goto reset_phy;
+
+ usleep_range(2000, 4000);
+
+ err = reset_control_deassert(eqos->rst);
+ if (err < 0)
+ goto reset_phy;
+
+ usleep_range(2000, 4000);
+
+ data->fix_mac_speed = tegra_eqos_fix_speed;
+ data->init = tegra_eqos_init;
+ data->bsp_priv = eqos;
+
+ err = tegra_eqos_init(pdev, eqos);
+ if (err < 0)
+ goto reset;
+
+out:
+ return eqos;
+
+reset:
+ reset_control_assert(eqos->rst);
+reset_phy:
+ gpiod_set_value(eqos->reset, 1);
+disable_tx:
+ clk_disable_unprepare(eqos->clk_tx);
+disable_rx:
+ clk_disable_unprepare(eqos->clk_rx);
+disable_slave:
+ clk_disable_unprepare(eqos->clk_slave);
+disable_master:
+ clk_disable_unprepare(eqos->clk_master);
+error:
+ eqos = ERR_PTR(err);
+ goto out;
+}
+
+static int tegra_eqos_remove(struct platform_device *pdev)
+{
+ struct tegra_eqos *eqos = get_stmmac_bsp_priv(&pdev->dev);
+
+ reset_control_assert(eqos->rst);
+ gpiod_set_value(eqos->reset, 1);
+ clk_disable_unprepare(eqos->clk_tx);
+ clk_disable_unprepare(eqos->clk_rx);
+ clk_disable_unprepare(eqos->clk_slave);
+ clk_disable_unprepare(eqos->clk_master);
+
+ return 0;
+}
+
+struct dwc_eth_dwmac_data {
+ void *(*probe)(struct platform_device *pdev,
+ struct plat_stmmacenet_data *data,
+ struct stmmac_resources *res);
+ int (*remove)(struct platform_device *pdev);
+};
+
+static const struct dwc_eth_dwmac_data dwc_qos_data = {
+ .probe = dwc_qos_probe,
+ .remove = dwc_qos_remove,
+};
+
+static const struct dwc_eth_dwmac_data tegra_eqos_data = {
+ .probe = tegra_eqos_probe,
+ .remove = tegra_eqos_remove,
+};
+
static int dwc_eth_dwmac_probe(struct platform_device *pdev)
{
+ const struct dwc_eth_dwmac_data *data;
struct plat_stmmacenet_data *plat_dat;
struct stmmac_resources stmmac_res;
struct resource *res;
+ void *priv;
int ret;
+ data = of_device_get_match_data(&pdev->dev);
+
memset(&stmmac_res, 0, sizeof(struct stmmac_resources));
/**
@@ -138,39 +452,26 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev)
if (IS_ERR(plat_dat))
return PTR_ERR(plat_dat);
- plat_dat->stmmac_clk = devm_clk_get(&pdev->dev, "apb_pclk");
- if (IS_ERR(plat_dat->stmmac_clk)) {
- dev_err(&pdev->dev, "apb_pclk clock not found.\n");
- ret = PTR_ERR(plat_dat->stmmac_clk);
- plat_dat->stmmac_clk = NULL;
- goto err_remove_config_dt;
+ priv = data->probe(pdev, plat_dat, &stmmac_res);
+ if (IS_ERR(priv)) {
+ ret = PTR_ERR(priv);
+ dev_err(&pdev->dev, "failed to probe subdriver: %d\n", ret);
+ goto remove_config;
}
- clk_prepare_enable(plat_dat->stmmac_clk);
-
- plat_dat->pclk = devm_clk_get(&pdev->dev, "phy_ref_clk");
- if (IS_ERR(plat_dat->pclk)) {
- dev_err(&pdev->dev, "phy_ref_clk clock not found.\n");
- ret = PTR_ERR(plat_dat->pclk);
- plat_dat->pclk = NULL;
- goto err_out_clk_dis_phy;
- }
- clk_prepare_enable(plat_dat->pclk);
ret = dwc_eth_dwmac_config_dt(pdev, plat_dat);
if (ret)
- goto err_out_clk_dis_aper;
+ goto remove;
ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
if (ret)
- goto err_out_clk_dis_aper;
+ goto remove;
- return 0;
+ return ret;
-err_out_clk_dis_aper:
- clk_disable_unprepare(plat_dat->pclk);
-err_out_clk_dis_phy:
- clk_disable_unprepare(plat_dat->stmmac_clk);
-err_remove_config_dt:
+remove:
+ data->remove(pdev);
+remove_config:
stmmac_remove_config_dt(pdev, plat_dat);
return ret;
@@ -178,11 +479,29 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev)
static int dwc_eth_dwmac_remove(struct platform_device *pdev)
{
- return stmmac_pltfr_remove(pdev);
+ struct net_device *ndev = platform_get_drvdata(pdev);
+ struct stmmac_priv *priv = netdev_priv(ndev);
+ const struct dwc_eth_dwmac_data *data;
+ int err;
+
+ data = of_device_get_match_data(&pdev->dev);
+
+ err = stmmac_dvr_remove(&pdev->dev);
+ if (err < 0)
+ dev_err(&pdev->dev, "failed to remove platform: %d\n", err);
+
+ err = data->remove(pdev);
+ if (err < 0)
+ dev_err(&pdev->dev, "failed to remove subdriver: %d\n", err);
+
+ stmmac_remove_config_dt(pdev, priv->plat);
+
+ return err;
}
static const struct of_device_id dwc_eth_dwmac_match[] = {
- { .compatible = "snps,dwc-qos-ethernet-4.10", },
+ { .compatible = "snps,dwc-qos-ethernet-4.10", .data = &dwc_qos_data },
+ { .compatible = "nvidia,tegra186-eqos", .data = &tegra_eqos_data },
{ }
};
MODULE_DEVICE_TABLE(of, dwc_eth_dwmac_match);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index e5db6ac..f0df519 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -74,6 +74,10 @@ struct rk_priv_data {
#define GRF_BIT(nr) (BIT(nr) | BIT(nr+16))
#define GRF_CLR_BIT(nr) (BIT(nr+16))
+#define DELAY_ENABLE(soc, tx, rx) \
+ (((tx) ? soc##_GMAC_TXCLK_DLY_ENABLE : soc##_GMAC_TXCLK_DLY_DISABLE) | \
+ ((rx) ? soc##_GMAC_RXCLK_DLY_ENABLE : soc##_GMAC_RXCLK_DLY_DISABLE))
+
#define RK3228_GRF_MAC_CON0 0x0900
#define RK3228_GRF_MAC_CON1 0x0904
@@ -115,8 +119,7 @@ static void rk3228_set_to_rgmii(struct rk_priv_data *bsp_priv,
regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1,
RK3228_GMAC_PHY_INTF_SEL_RGMII |
RK3228_GMAC_RMII_MODE_CLR |
- RK3228_GMAC_RXCLK_DLY_ENABLE |
- RK3228_GMAC_TXCLK_DLY_ENABLE);
+ DELAY_ENABLE(RK3228, tx_delay, rx_delay));
regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON0,
RK3228_GMAC_CLK_RX_DL_CFG(rx_delay) |
@@ -232,8 +235,7 @@ static void rk3288_set_to_rgmii(struct rk_priv_data *bsp_priv,
RK3288_GMAC_PHY_INTF_SEL_RGMII |
RK3288_GMAC_RMII_MODE_CLR);
regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON3,
- RK3288_GMAC_RXCLK_DLY_ENABLE |
- RK3288_GMAC_TXCLK_DLY_ENABLE |
+ DELAY_ENABLE(RK3288, tx_delay, rx_delay) |
RK3288_GMAC_CLK_RX_DL_CFG(rx_delay) |
RK3288_GMAC_CLK_TX_DL_CFG(tx_delay));
}
@@ -460,8 +462,7 @@ static void rk3366_set_to_rgmii(struct rk_priv_data *bsp_priv,
RK3366_GMAC_PHY_INTF_SEL_RGMII |
RK3366_GMAC_RMII_MODE_CLR);
regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON7,
- RK3366_GMAC_RXCLK_DLY_ENABLE |
- RK3366_GMAC_TXCLK_DLY_ENABLE |
+ DELAY_ENABLE(RK3366, tx_delay, rx_delay) |
RK3366_GMAC_CLK_RX_DL_CFG(rx_delay) |
RK3366_GMAC_CLK_TX_DL_CFG(tx_delay));
}
@@ -572,8 +573,7 @@ static void rk3368_set_to_rgmii(struct rk_priv_data *bsp_priv,
RK3368_GMAC_PHY_INTF_SEL_RGMII |
RK3368_GMAC_RMII_MODE_CLR);
regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON16,
- RK3368_GMAC_RXCLK_DLY_ENABLE |
- RK3368_GMAC_TXCLK_DLY_ENABLE |
+ DELAY_ENABLE(RK3368, tx_delay, rx_delay) |
RK3368_GMAC_CLK_RX_DL_CFG(rx_delay) |
RK3368_GMAC_CLK_TX_DL_CFG(tx_delay));
}
@@ -684,8 +684,7 @@ static void rk3399_set_to_rgmii(struct rk_priv_data *bsp_priv,
RK3399_GMAC_PHY_INTF_SEL_RGMII |
RK3399_GMAC_RMII_MODE_CLR);
regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON6,
- RK3399_GMAC_RXCLK_DLY_ENABLE |
- RK3399_GMAC_TXCLK_DLY_ENABLE |
+ DELAY_ENABLE(RK3399, tx_delay, rx_delay) |
RK3399_GMAC_CLK_RX_DL_CFG(rx_delay) |
RK3399_GMAC_CLK_TX_DL_CFG(tx_delay));
}
@@ -985,14 +984,29 @@ static int rk_gmac_powerup(struct rk_priv_data *bsp_priv)
return ret;
/*rmii or rgmii*/
- if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RGMII) {
+ switch (bsp_priv->phy_iface) {
+ case PHY_INTERFACE_MODE_RGMII:
dev_info(dev, "init for RGMII\n");
bsp_priv->ops->set_to_rgmii(bsp_priv, bsp_priv->tx_delay,
bsp_priv->rx_delay);
- } else if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RMII) {
+ break;
+ case PHY_INTERFACE_MODE_RGMII_ID:
+ dev_info(dev, "init for RGMII_ID\n");
+ bsp_priv->ops->set_to_rgmii(bsp_priv, 0, 0);
+ break;
+ case PHY_INTERFACE_MODE_RGMII_RXID:
+ dev_info(dev, "init for RGMII_RXID\n");
+ bsp_priv->ops->set_to_rgmii(bsp_priv, bsp_priv->tx_delay, 0);
+ break;
+ case PHY_INTERFACE_MODE_RGMII_TXID:
+ dev_info(dev, "init for RGMII_TXID\n");
+ bsp_priv->ops->set_to_rgmii(bsp_priv, 0, bsp_priv->rx_delay);
+ break;
+ case PHY_INTERFACE_MODE_RMII:
dev_info(dev, "init for RMII\n");
bsp_priv->ops->set_to_rmii(bsp_priv);
- } else {
+ break;
+ default:
dev_err(dev, "NO interface defined!\n");
}
@@ -1022,12 +1036,19 @@ static void rk_fix_speed(void *priv, unsigned int speed)
struct rk_priv_data *bsp_priv = priv;
struct device *dev = &bsp_priv->pdev->dev;
- if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RGMII)
+ switch (bsp_priv->phy_iface) {
+ case PHY_INTERFACE_MODE_RGMII:
+ case PHY_INTERFACE_MODE_RGMII_ID:
+ case PHY_INTERFACE_MODE_RGMII_RXID:
+ case PHY_INTERFACE_MODE_RGMII_TXID:
bsp_priv->ops->set_rgmii_speed(bsp_priv, speed);
- else if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RMII)
+ break;
+ case PHY_INTERFACE_MODE_RMII:
bsp_priv->ops->set_rmii_speed(bsp_priv, speed);
- else
+ break;
+ default:
dev_err(dev, "unsupported interface %d", bsp_priv->phy_iface);
+ }
}
static int rk_gmac_probe(struct platform_device *pdev)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index 19b9b30..f3d9305 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -216,7 +216,8 @@ static void dwmac1000_set_filter(struct mac_device_info *hw,
static void dwmac1000_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
- unsigned int fc, unsigned int pause_time)
+ unsigned int fc, unsigned int pause_time,
+ u32 tx_cnt)
{
void __iomem *ioaddr = hw->pcsr;
/* Set flow such that DZPQ in Mac Register 6 is 0,
@@ -412,7 +413,8 @@ static void dwmac1000_get_adv_lp(void __iomem *ioaddr, struct rgmii_adv *adv)
dwmac_get_adv_lp(ioaddr, GMAC_PCS_BASE, adv);
}
-static void dwmac1000_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x)
+static void dwmac1000_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x,
+ u32 rx_queues, u32 tx_queues)
{
u32 value = readl(ioaddr + GMAC_DEBUG);
@@ -488,6 +490,7 @@ static void dwmac1000_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x)
static const struct stmmac_ops dwmac1000_ops = {
.core_init = dwmac1000_core_init,
+ .set_mac = stmmac_set_mac,
.rx_ipc = dwmac1000_rx_ipc_enable,
.dump_regs = dwmac1000_dump_regs,
.host_irq_status = dwmac1000_irq_status,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
index d3654a4..471a9aa 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
@@ -247,7 +247,8 @@ static void dwmac1000_get_hw_feature(void __iomem *ioaddr,
dma_cap->enh_desc = (hw_cap & DMA_HW_FEAT_ENHDESSEL) >> 24;
}
-static void dwmac1000_rx_watchdog(void __iomem *ioaddr, u32 riwt)
+static void dwmac1000_rx_watchdog(void __iomem *ioaddr, u32 riwt,
+ u32 number_chan)
{
writel(riwt, ioaddr + DMA_RX_WATCHDOG);
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
index e370cce..1b36091 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
@@ -131,7 +131,8 @@ static void dwmac100_set_filter(struct mac_device_info *hw,
}
static void dwmac100_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
- unsigned int fc, unsigned int pause_time)
+ unsigned int fc, unsigned int pause_time,
+ u32 tx_cnt)
{
void __iomem *ioaddr = hw->pcsr;
unsigned int flow = MAC_FLOW_CTRL_ENABLE;
@@ -149,6 +150,7 @@ static void dwmac100_pmt(struct mac_device_info *hw, unsigned long mode)
static const struct stmmac_ops dwmac100_ops = {
.core_init = dwmac100_core_init,
+ .set_mac = stmmac_set_mac,
.rx_ipc = dwmac100_rx_ipc_enable,
.dump_regs = dwmac100_dump_mac_regs,
.host_irq_status = dwmac100_irq_status,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
index db45134..d74cedf 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -22,9 +22,15 @@
#define GMAC_HASH_TAB_32_63 0x00000014
#define GMAC_RX_FLOW_CTRL 0x00000090
#define GMAC_QX_TX_FLOW_CTRL(x) (0x70 + x * 4)
+#define GMAC_TXQ_PRTY_MAP0 0x98
+#define GMAC_TXQ_PRTY_MAP1 0x9C
#define GMAC_RXQ_CTRL0 0x000000a0
+#define GMAC_RXQ_CTRL1 0x000000a4
+#define GMAC_RXQ_CTRL2 0x000000a8
+#define GMAC_RXQ_CTRL3 0x000000ac
#define GMAC_INT_STATUS 0x000000b0
#define GMAC_INT_EN 0x000000b4
+#define GMAC_1US_TIC_COUNTER 0x000000dc
#define GMAC_PCS_BASE 0x000000e0
#define GMAC_PHYIF_CONTROL_STATUS 0x000000f8
#define GMAC_PMT 0x000000c0
@@ -38,6 +44,22 @@
#define GMAC_ADDR_HIGH(reg) (0x300 + reg * 8)
#define GMAC_ADDR_LOW(reg) (0x304 + reg * 8)
+/* RX Queues Routing */
+#define GMAC_RXQCTRL_AVCPQ_MASK GENMASK(2, 0)
+#define GMAC_RXQCTRL_AVCPQ_SHIFT 0
+#define GMAC_RXQCTRL_PTPQ_MASK GENMASK(6, 4)
+#define GMAC_RXQCTRL_PTPQ_SHIFT 4
+#define GMAC_RXQCTRL_DCBCPQ_MASK GENMASK(10, 8)
+#define GMAC_RXQCTRL_DCBCPQ_SHIFT 8
+#define GMAC_RXQCTRL_UPQ_MASK GENMASK(14, 12)
+#define GMAC_RXQCTRL_UPQ_SHIFT 12
+#define GMAC_RXQCTRL_MCBCQ_MASK GENMASK(18, 16)
+#define GMAC_RXQCTRL_MCBCQ_SHIFT 16
+#define GMAC_RXQCTRL_MCBCQEN BIT(20)
+#define GMAC_RXQCTRL_MCBCQEN_SHIFT 20
+#define GMAC_RXQCTRL_TACPQE BIT(21)
+#define GMAC_RXQCTRL_TACPQE_SHIFT 21
+
/* MAC Packet Filtering */
#define GMAC_PACKET_FILTER_PR BIT(0)
#define GMAC_PACKET_FILTER_HMC BIT(2)
@@ -53,6 +75,14 @@
/* MAC Flow Control RX */
#define GMAC_RX_FLOW_CTRL_RFE BIT(0)
+/* RX Queues Priorities */
+#define GMAC_RXQCTRL_PSRQX_MASK(x) GENMASK(7 + ((x) * 8), 0 + ((x) * 8))
+#define GMAC_RXQCTRL_PSRQX_SHIFT(x) ((x) * 8)
+
+/* TX Queues Priorities */
+#define GMAC_TXQCTRL_PSTQX_MASK(x) GENMASK(7 + ((x) * 8), 0 + ((x) * 8))
+#define GMAC_TXQCTRL_PSTQX_SHIFT(x) ((x) * 8)
+
/* MAC Flow Control TX */
#define GMAC_TX_FLOW_CTRL_TFE BIT(1)
#define GMAC_TX_FLOW_CTRL_PT_SHIFT 16
@@ -148,6 +178,8 @@ enum power_event {
/* MAC HW features1 bitmap */
#define GMAC_HW_FEAT_AVSEL BIT(20)
#define GMAC_HW_TSOEN BIT(18)
+#define GMAC_HW_TXFIFOSIZE GENMASK(10, 6)
+#define GMAC_HW_RXFIFOSIZE GENMASK(4, 0)
/* MAC HW features2 bitmap */
#define GMAC_HW_FEAT_TXCHCNT GENMASK(21, 18)
@@ -161,8 +193,25 @@ enum power_event {
#define GMAC_HI_REG_AE BIT(31)
/* MTL registers */
+#define MTL_OPERATION_MODE 0x00000c00
+#define MTL_OPERATION_SCHALG_MASK GENMASK(6, 5)
+#define MTL_OPERATION_SCHALG_WRR (0x0 << 5)
+#define MTL_OPERATION_SCHALG_WFQ (0x1 << 5)
+#define MTL_OPERATION_SCHALG_DWRR (0x2 << 5)
+#define MTL_OPERATION_SCHALG_SP (0x3 << 5)
+#define MTL_OPERATION_RAA BIT(2)
+#define MTL_OPERATION_RAA_SP (0x0 << 2)
+#define MTL_OPERATION_RAA_WSP (0x1 << 2)
+
#define MTL_INT_STATUS 0x00000c20
-#define MTL_INT_Q0 BIT(0)
+#define MTL_INT_QX(x) BIT(x)
+
+#define MTL_RXQ_DMA_MAP0 0x00000c30 /* queue 0 to 3 */
+#define MTL_RXQ_DMA_MAP1 0x00000c34 /* queue 4 to 7 */
+#define MTL_RXQ_DMA_Q04MDMACH_MASK GENMASK(3, 0)
+#define MTL_RXQ_DMA_Q04MDMACH(x) ((x) << 0)
+#define MTL_RXQ_DMA_QXMDMACH_MASK(x) GENMASK(11 + (8 * ((x) - 1)), 8 * (x))
+#define MTL_RXQ_DMA_QXMDMACH(chan, q) ((chan) << (8 * (q)))
#define MTL_CHAN_BASE_ADDR 0x00000d00
#define MTL_CHAN_BASE_OFFSET 0x40
@@ -180,6 +229,7 @@ enum power_event {
#define MTL_OP_MODE_TSF BIT(1)
#define MTL_OP_MODE_TQS_MASK GENMASK(24, 16)
+#define MTL_OP_MODE_TQS_SHIFT 16
#define MTL_OP_MODE_TTC_MASK 0x70
#define MTL_OP_MODE_TTC_SHIFT 4
@@ -193,6 +243,17 @@ enum power_event {
#define MTL_OP_MODE_TTC_384 (6 << MTL_OP_MODE_TTC_SHIFT)
#define MTL_OP_MODE_TTC_512 (7 << MTL_OP_MODE_TTC_SHIFT)
+#define MTL_OP_MODE_RQS_MASK GENMASK(29, 20)
+#define MTL_OP_MODE_RQS_SHIFT 20
+
+#define MTL_OP_MODE_RFD_MASK GENMASK(19, 14)
+#define MTL_OP_MODE_RFD_SHIFT 14
+
+#define MTL_OP_MODE_RFA_MASK GENMASK(13, 8)
+#define MTL_OP_MODE_RFA_SHIFT 8
+
+#define MTL_OP_MODE_EHFC BIT(7)
+
#define MTL_OP_MODE_RTC_MASK 0x18
#define MTL_OP_MODE_RTC_SHIFT 3
@@ -201,6 +262,46 @@ enum power_event {
#define MTL_OP_MODE_RTC_96 (2 << MTL_OP_MODE_RTC_SHIFT)
#define MTL_OP_MODE_RTC_128 (3 << MTL_OP_MODE_RTC_SHIFT)
+/* MTL ETS Control register */
+#define MTL_ETS_CTRL_BASE_ADDR 0x00000d10
+#define MTL_ETS_CTRL_BASE_OFFSET 0x40
+#define MTL_ETSX_CTRL_BASE_ADDR(x) (MTL_ETS_CTRL_BASE_ADDR + \
+ ((x) * MTL_ETS_CTRL_BASE_OFFSET))
+
+#define MTL_ETS_CTRL_CC BIT(3)
+#define MTL_ETS_CTRL_AVALG BIT(2)
+
+/* MTL Queue Quantum Weight */
+#define MTL_TXQ_WEIGHT_BASE_ADDR 0x00000d18
+#define MTL_TXQ_WEIGHT_BASE_OFFSET 0x40
+#define MTL_TXQX_WEIGHT_BASE_ADDR(x) (MTL_TXQ_WEIGHT_BASE_ADDR + \
+ ((x) * MTL_TXQ_WEIGHT_BASE_OFFSET))
+#define MTL_TXQ_WEIGHT_ISCQW_MASK GENMASK(20, 0)
+
+/* MTL sendSlopeCredit register */
+#define MTL_SEND_SLP_CRED_BASE_ADDR 0x00000d1c
+#define MTL_SEND_SLP_CRED_OFFSET 0x40
+#define MTL_SEND_SLP_CREDX_BASE_ADDR(x) (MTL_SEND_SLP_CRED_BASE_ADDR + \
+ ((x) * MTL_SEND_SLP_CRED_OFFSET))
+
+#define MTL_SEND_SLP_CRED_SSC_MASK GENMASK(13, 0)
+
+/* MTL hiCredit register */
+#define MTL_HIGH_CRED_BASE_ADDR 0x00000d20
+#define MTL_HIGH_CRED_OFFSET 0x40
+#define MTL_HIGH_CREDX_BASE_ADDR(x) (MTL_HIGH_CRED_BASE_ADDR + \
+ ((x) * MTL_HIGH_CRED_OFFSET))
+
+#define MTL_HIGH_CRED_HC_MASK GENMASK(28, 0)
+
+/* MTL loCredit register */
+#define MTL_LOW_CRED_BASE_ADDR 0x00000d24
+#define MTL_LOW_CRED_OFFSET 0x40
+#define MTL_LOW_CREDX_BASE_ADDR(x) (MTL_LOW_CRED_BASE_ADDR + \
+ ((x) * MTL_LOW_CRED_OFFSET))
+
+#define MTL_HIGH_CRED_LC_MASK GENMASK(28, 0)
+
/* MTL debug */
#define MTL_DEBUG_TXSTSFSTS BIT(5)
#define MTL_DEBUG_TXFSTS BIT(4)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 1e79e65..48793f2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -59,17 +59,211 @@ static void dwmac4_core_init(struct mac_device_info *hw, int mtu)
writel(value, ioaddr + GMAC_INT_EN);
}
-static void dwmac4_rx_queue_enable(struct mac_device_info *hw, u32 queue)
+static void dwmac4_rx_queue_enable(struct mac_device_info *hw,
+ u8 mode, u32 queue)
{
void __iomem *ioaddr = hw->pcsr;
u32 value = readl(ioaddr + GMAC_RXQ_CTRL0);
value &= GMAC_RX_QUEUE_CLEAR(queue);
- value |= GMAC_RX_AV_QUEUE_ENABLE(queue);
+ if (mode == MTL_QUEUE_AVB)
+ value |= GMAC_RX_AV_QUEUE_ENABLE(queue);
+ else if (mode == MTL_QUEUE_DCB)
+ value |= GMAC_RX_DCB_QUEUE_ENABLE(queue);
writel(value, ioaddr + GMAC_RXQ_CTRL0);
}
+static void dwmac4_rx_queue_priority(struct mac_device_info *hw,
+ u32 prio, u32 queue)
+{
+ void __iomem *ioaddr = hw->pcsr;
+ u32 base_register;
+ u32 value;
+
+ base_register = (queue < 4) ? GMAC_RXQ_CTRL2 : GMAC_RXQ_CTRL3;
+
+ value = readl(ioaddr + base_register);
+
+ value &= ~GMAC_RXQCTRL_PSRQX_MASK(queue);
+ value |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) &
+ GMAC_RXQCTRL_PSRQX_MASK(queue);
+ writel(value, ioaddr + base_register);
+}
+
+static void dwmac4_tx_queue_priority(struct mac_device_info *hw,
+ u32 prio, u32 queue)
+{
+ void __iomem *ioaddr = hw->pcsr;
+ u32 base_register;
+ u32 value;
+
+ base_register = (queue < 4) ? GMAC_TXQ_PRTY_MAP0 : GMAC_TXQ_PRTY_MAP1;
+
+ value = readl(ioaddr + base_register);
+
+ value &= ~GMAC_TXQCTRL_PSTQX_MASK(queue);
+ value |= (prio << GMAC_TXQCTRL_PSTQX_SHIFT(queue)) &
+ GMAC_TXQCTRL_PSTQX_MASK(queue);
+
+ writel(value, ioaddr + base_register);
+}
+
+static void dwmac4_tx_queue_routing(struct mac_device_info *hw,
+ u8 packet, u32 queue)
+{
+ void __iomem *ioaddr = hw->pcsr;
+ u32 value;
+
+ const struct stmmac_rx_routing route_possibilities[] = {
+ { GMAC_RXQCTRL_AVCPQ_MASK, GMAC_RXQCTRL_AVCPQ_SHIFT },
+ { GMAC_RXQCTRL_PTPQ_MASK, GMAC_RXQCTRL_PTPQ_SHIFT },
+ { GMAC_RXQCTRL_DCBCPQ_MASK, GMAC_RXQCTRL_DCBCPQ_SHIFT },
+ { GMAC_RXQCTRL_UPQ_MASK, GMAC_RXQCTRL_UPQ_SHIFT },
+ { GMAC_RXQCTRL_MCBCQ_MASK, GMAC_RXQCTRL_MCBCQ_SHIFT },
+ };
+
+ value = readl(ioaddr + GMAC_RXQ_CTRL1);
+
+ /* routing configuration */
+ value &= ~route_possibilities[packet - 1].reg_mask;
+ value |= (queue << route_possibilities[packet-1].reg_shift) &
+ route_possibilities[packet - 1].reg_mask;
+
+ /* some packets require extra ops */
+ if (packet == PACKET_AVCPQ) {
+ value &= ~GMAC_RXQCTRL_TACPQE;
+ value |= 0x1 << GMAC_RXQCTRL_TACPQE_SHIFT;
+ } else if (packet == PACKET_MCBCQ) {
+ value &= ~GMAC_RXQCTRL_MCBCQEN;
+ value |= 0x1 << GMAC_RXQCTRL_MCBCQEN_SHIFT;
+ }
+
+ writel(value, ioaddr + GMAC_RXQ_CTRL1);
+}
+
+static void dwmac4_prog_mtl_rx_algorithms(struct mac_device_info *hw,
+ u32 rx_alg)
+{
+ void __iomem *ioaddr = hw->pcsr;
+ u32 value = readl(ioaddr + MTL_OPERATION_MODE);
+
+ value &= ~MTL_OPERATION_RAA;
+ switch (rx_alg) {
+ case MTL_RX_ALGORITHM_SP:
+ value |= MTL_OPERATION_RAA_SP;
+ break;
+ case MTL_RX_ALGORITHM_WSP:
+ value |= MTL_OPERATION_RAA_WSP;
+ break;
+ default:
+ break;
+ }
+
+ writel(value, ioaddr + MTL_OPERATION_MODE);
+}
+
+static void dwmac4_prog_mtl_tx_algorithms(struct mac_device_info *hw,
+ u32 tx_alg)
+{
+ void __iomem *ioaddr = hw->pcsr;
+ u32 value = readl(ioaddr + MTL_OPERATION_MODE);
+
+ value &= ~MTL_OPERATION_SCHALG_MASK;
+ switch (tx_alg) {
+ case MTL_TX_ALGORITHM_WRR:
+ value |= MTL_OPERATION_SCHALG_WRR;
+ break;
+ case MTL_TX_ALGORITHM_WFQ:
+ value |= MTL_OPERATION_SCHALG_WFQ;
+ break;
+ case MTL_TX_ALGORITHM_DWRR:
+ value |= MTL_OPERATION_SCHALG_DWRR;
+ break;
+ case MTL_TX_ALGORITHM_SP:
+ value |= MTL_OPERATION_SCHALG_SP;
+ break;
+ default:
+ break;
+ }
+}
+
+static void dwmac4_set_mtl_tx_queue_weight(struct mac_device_info *hw,
+ u32 weight, u32 queue)
+{
+ void __iomem *ioaddr = hw->pcsr;
+ u32 value = readl(ioaddr + MTL_TXQX_WEIGHT_BASE_ADDR(queue));
+
+ value &= ~MTL_TXQ_WEIGHT_ISCQW_MASK;
+ value |= weight & MTL_TXQ_WEIGHT_ISCQW_MASK;
+ writel(value, ioaddr + MTL_TXQX_WEIGHT_BASE_ADDR(queue));
+}
+
+static void dwmac4_map_mtl_dma(struct mac_device_info *hw, u32 queue, u32 chan)
+{
+ void __iomem *ioaddr = hw->pcsr;
+ u32 value;
+
+ if (queue < 4)
+ value = readl(ioaddr + MTL_RXQ_DMA_MAP0);
+ else
+ value = readl(ioaddr + MTL_RXQ_DMA_MAP1);
+
+ if (queue == 0 || queue == 4) {
+ value &= ~MTL_RXQ_DMA_Q04MDMACH_MASK;
+ value |= MTL_RXQ_DMA_Q04MDMACH(chan);
+ } else {
+ value &= ~MTL_RXQ_DMA_QXMDMACH_MASK(queue);
+ value |= MTL_RXQ_DMA_QXMDMACH(chan, queue);
+ }
+
+ if (queue < 4)
+ writel(value, ioaddr + MTL_RXQ_DMA_MAP0);
+ else
+ writel(value, ioaddr + MTL_RXQ_DMA_MAP1);
+}
+
+static void dwmac4_config_cbs(struct mac_device_info *hw,
+ u32 send_slope, u32 idle_slope,
+ u32 high_credit, u32 low_credit, u32 queue)
+{
+ void __iomem *ioaddr = hw->pcsr;
+ u32 value;
+
+ pr_debug("Queue %d configured as AVB. Parameters:\n", queue);
+ pr_debug("\tsend_slope: 0x%08x\n", send_slope);
+ pr_debug("\tidle_slope: 0x%08x\n", idle_slope);
+ pr_debug("\thigh_credit: 0x%08x\n", high_credit);
+ pr_debug("\tlow_credit: 0x%08x\n", low_credit);
+
+ /* enable AV algorithm */
+ value = readl(ioaddr + MTL_ETSX_CTRL_BASE_ADDR(queue));
+ value |= MTL_ETS_CTRL_AVALG;
+ value |= MTL_ETS_CTRL_CC;
+ writel(value, ioaddr + MTL_ETSX_CTRL_BASE_ADDR(queue));
+
+ /* configure send slope */
+ value = readl(ioaddr + MTL_SEND_SLP_CREDX_BASE_ADDR(queue));
+ value &= ~MTL_SEND_SLP_CRED_SSC_MASK;
+ value |= send_slope & MTL_SEND_SLP_CRED_SSC_MASK;
+ writel(value, ioaddr + MTL_SEND_SLP_CREDX_BASE_ADDR(queue));
+
+ /* configure idle slope (same register as tx weight) */
+ dwmac4_set_mtl_tx_queue_weight(hw, idle_slope, queue);
+
+ /* configure high credit */
+ value = readl(ioaddr + MTL_HIGH_CREDX_BASE_ADDR(queue));
+ value &= ~MTL_HIGH_CRED_HC_MASK;
+ value |= high_credit & MTL_HIGH_CRED_HC_MASK;
+ writel(value, ioaddr + MTL_HIGH_CREDX_BASE_ADDR(queue));
+
+ /* configure high credit */
+ value = readl(ioaddr + MTL_LOW_CREDX_BASE_ADDR(queue));
+ value &= ~MTL_HIGH_CRED_LC_MASK;
+ value |= low_credit & MTL_HIGH_CRED_LC_MASK;
+ writel(value, ioaddr + MTL_LOW_CREDX_BASE_ADDR(queue));
+}
+
static void dwmac4_dump_regs(struct mac_device_info *hw, u32 *reg_space)
{
void __iomem *ioaddr = hw->pcsr;
@@ -251,11 +445,12 @@ static void dwmac4_set_filter(struct mac_device_info *hw,
}
static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
- unsigned int fc, unsigned int pause_time)
+ unsigned int fc, unsigned int pause_time,
+ u32 tx_cnt)
{
void __iomem *ioaddr = hw->pcsr;
- u32 channel = STMMAC_CHAN0; /* FIXME */
unsigned int flow = 0;
+ u32 queue = 0;
pr_debug("GMAC Flow-Control:\n");
if (fc & FLOW_RX) {
@@ -265,13 +460,18 @@ static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
}
if (fc & FLOW_TX) {
pr_debug("\tTransmit Flow-Control ON\n");
- flow |= GMAC_TX_FLOW_CTRL_TFE;
- writel(flow, ioaddr + GMAC_QX_TX_FLOW_CTRL(channel));
- if (duplex) {
+ if (duplex)
pr_debug("\tduplex mode: PAUSE %d\n", pause_time);
- flow |= (pause_time << GMAC_TX_FLOW_CTRL_PT_SHIFT);
- writel(flow, ioaddr + GMAC_QX_TX_FLOW_CTRL(channel));
+
+ for (queue = 0; queue < tx_cnt; queue++) {
+ flow |= GMAC_TX_FLOW_CTRL_TFE;
+
+ if (duplex)
+ flow |=
+ (pause_time << GMAC_TX_FLOW_CTRL_PT_SHIFT);
+
+ writel(flow, ioaddr + GMAC_QX_TX_FLOW_CTRL(queue));
}
}
}
@@ -325,11 +525,34 @@ static void dwmac4_phystatus(void __iomem *ioaddr, struct stmmac_extra_stats *x)
}
}
+static int dwmac4_irq_mtl_status(struct mac_device_info *hw, u32 chan)
+{
+ void __iomem *ioaddr = hw->pcsr;
+ u32 mtl_int_qx_status;
+ int ret = 0;
+
+ mtl_int_qx_status = readl(ioaddr + MTL_INT_STATUS);
+
+ /* Check MTL Interrupt */
+ if (mtl_int_qx_status & MTL_INT_QX(chan)) {
+ /* read Queue x Interrupt status */
+ u32 status = readl(ioaddr + MTL_CHAN_INT_CTRL(chan));
+
+ if (status & MTL_RX_OVERFLOW_INT) {
+ /* clear Interrupt */
+ writel(status | MTL_RX_OVERFLOW_INT,
+ ioaddr + MTL_CHAN_INT_CTRL(chan));
+ ret = CORE_IRQ_MTL_RX_OVERFLOW;
+ }
+ }
+
+ return ret;
+}
+
static int dwmac4_irq_status(struct mac_device_info *hw,
struct stmmac_extra_stats *x)
{
void __iomem *ioaddr = hw->pcsr;
- u32 mtl_int_qx_status;
u32 intr_status;
int ret = 0;
@@ -348,20 +571,6 @@ static int dwmac4_irq_status(struct mac_device_info *hw,
x->irq_receive_pmt_irq_n++;
}
- mtl_int_qx_status = readl(ioaddr + MTL_INT_STATUS);
- /* Check MTL Interrupt: Currently only one queue is used: Q0. */
- if (mtl_int_qx_status & MTL_INT_Q0) {
- /* read Queue 0 Interrupt status */
- u32 status = readl(ioaddr + MTL_CHAN_INT_CTRL(STMMAC_CHAN0));
-
- if (status & MTL_RX_OVERFLOW_INT) {
- /* clear Interrupt */
- writel(status | MTL_RX_OVERFLOW_INT,
- ioaddr + MTL_CHAN_INT_CTRL(STMMAC_CHAN0));
- ret = CORE_IRQ_MTL_RX_OVERFLOW;
- }
- }
-
dwmac_pcs_isr(ioaddr, GMAC_PCS_BASE, intr_status, x);
if (intr_status & PCS_RGSMIIIS_IRQ)
dwmac4_phystatus(ioaddr, x);
@@ -369,64 +578,69 @@ static int dwmac4_irq_status(struct mac_device_info *hw,
return ret;
}
-static void dwmac4_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x)
+static void dwmac4_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x,
+ u32 rx_queues, u32 tx_queues)
{
u32 value;
+ u32 queue;
- /* Currently only channel 0 is supported */
- value = readl(ioaddr + MTL_CHAN_TX_DEBUG(STMMAC_CHAN0));
+ for (queue = 0; queue < tx_queues; queue++) {
+ value = readl(ioaddr + MTL_CHAN_TX_DEBUG(queue));
- if (value & MTL_DEBUG_TXSTSFSTS)
- x->mtl_tx_status_fifo_full++;
- if (value & MTL_DEBUG_TXFSTS)
- x->mtl_tx_fifo_not_empty++;
- if (value & MTL_DEBUG_TWCSTS)
- x->mmtl_fifo_ctrl++;
- if (value & MTL_DEBUG_TRCSTS_MASK) {
- u32 trcsts = (value & MTL_DEBUG_TRCSTS_MASK)
- >> MTL_DEBUG_TRCSTS_SHIFT;
- if (trcsts == MTL_DEBUG_TRCSTS_WRITE)
- x->mtl_tx_fifo_read_ctrl_write++;
- else if (trcsts == MTL_DEBUG_TRCSTS_TXW)
- x->mtl_tx_fifo_read_ctrl_wait++;
- else if (trcsts == MTL_DEBUG_TRCSTS_READ)
- x->mtl_tx_fifo_read_ctrl_read++;
- else
- x->mtl_tx_fifo_read_ctrl_idle++;
+ if (value & MTL_DEBUG_TXSTSFSTS)
+ x->mtl_tx_status_fifo_full++;
+ if (value & MTL_DEBUG_TXFSTS)
+ x->mtl_tx_fifo_not_empty++;
+ if (value & MTL_DEBUG_TWCSTS)
+ x->mmtl_fifo_ctrl++;
+ if (value & MTL_DEBUG_TRCSTS_MASK) {
+ u32 trcsts = (value & MTL_DEBUG_TRCSTS_MASK)
+ >> MTL_DEBUG_TRCSTS_SHIFT;
+ if (trcsts == MTL_DEBUG_TRCSTS_WRITE)
+ x->mtl_tx_fifo_read_ctrl_write++;
+ else if (trcsts == MTL_DEBUG_TRCSTS_TXW)
+ x->mtl_tx_fifo_read_ctrl_wait++;
+ else if (trcsts == MTL_DEBUG_TRCSTS_READ)
+ x->mtl_tx_fifo_read_ctrl_read++;
+ else
+ x->mtl_tx_fifo_read_ctrl_idle++;
+ }
+ if (value & MTL_DEBUG_TXPAUSED)
+ x->mac_tx_in_pause++;
}
- if (value & MTL_DEBUG_TXPAUSED)
- x->mac_tx_in_pause++;
- value = readl(ioaddr + MTL_CHAN_RX_DEBUG(STMMAC_CHAN0));
+ for (queue = 0; queue < rx_queues; queue++) {
+ value = readl(ioaddr + MTL_CHAN_RX_DEBUG(queue));
- if (value & MTL_DEBUG_RXFSTS_MASK) {
- u32 rxfsts = (value & MTL_DEBUG_RXFSTS_MASK)
- >> MTL_DEBUG_RRCSTS_SHIFT;
+ if (value & MTL_DEBUG_RXFSTS_MASK) {
+ u32 rxfsts = (value & MTL_DEBUG_RXFSTS_MASK)
+ >> MTL_DEBUG_RRCSTS_SHIFT;
- if (rxfsts == MTL_DEBUG_RXFSTS_FULL)
- x->mtl_rx_fifo_fill_level_full++;
- else if (rxfsts == MTL_DEBUG_RXFSTS_AT)
- x->mtl_rx_fifo_fill_above_thresh++;
- else if (rxfsts == MTL_DEBUG_RXFSTS_BT)
- x->mtl_rx_fifo_fill_below_thresh++;
- else
- x->mtl_rx_fifo_fill_level_empty++;
+ if (rxfsts == MTL_DEBUG_RXFSTS_FULL)
+ x->mtl_rx_fifo_fill_level_full++;
+ else if (rxfsts == MTL_DEBUG_RXFSTS_AT)
+ x->mtl_rx_fifo_fill_above_thresh++;
+ else if (rxfsts == MTL_DEBUG_RXFSTS_BT)
+ x->mtl_rx_fifo_fill_below_thresh++;
+ else
+ x->mtl_rx_fifo_fill_level_empty++;
+ }
+ if (value & MTL_DEBUG_RRCSTS_MASK) {
+ u32 rrcsts = (value & MTL_DEBUG_RRCSTS_MASK) >>
+ MTL_DEBUG_RRCSTS_SHIFT;
+
+ if (rrcsts == MTL_DEBUG_RRCSTS_FLUSH)
+ x->mtl_rx_fifo_read_ctrl_flush++;
+ else if (rrcsts == MTL_DEBUG_RRCSTS_RSTAT)
+ x->mtl_rx_fifo_read_ctrl_read_data++;
+ else if (rrcsts == MTL_DEBUG_RRCSTS_RDATA)
+ x->mtl_rx_fifo_read_ctrl_status++;
+ else
+ x->mtl_rx_fifo_read_ctrl_idle++;
+ }
+ if (value & MTL_DEBUG_RWCSTS)
+ x->mtl_rx_fifo_ctrl_active++;
}
- if (value & MTL_DEBUG_RRCSTS_MASK) {
- u32 rrcsts = (value & MTL_DEBUG_RRCSTS_MASK) >>
- MTL_DEBUG_RRCSTS_SHIFT;
-
- if (rrcsts == MTL_DEBUG_RRCSTS_FLUSH)
- x->mtl_rx_fifo_read_ctrl_flush++;
- else if (rrcsts == MTL_DEBUG_RRCSTS_RSTAT)
- x->mtl_rx_fifo_read_ctrl_read_data++;
- else if (rrcsts == MTL_DEBUG_RRCSTS_RDATA)
- x->mtl_rx_fifo_read_ctrl_status++;
- else
- x->mtl_rx_fifo_read_ctrl_idle++;
- }
- if (value & MTL_DEBUG_RWCSTS)
- x->mtl_rx_fifo_ctrl_active++;
/* GMAC debug */
value = readl(ioaddr + GMAC_DEBUG);
@@ -455,10 +669,51 @@ static void dwmac4_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x)
static const struct stmmac_ops dwmac4_ops = {
.core_init = dwmac4_core_init,
+ .set_mac = stmmac_set_mac,
.rx_ipc = dwmac4_rx_ipc_enable,
.rx_queue_enable = dwmac4_rx_queue_enable,
+ .rx_queue_prio = dwmac4_rx_queue_priority,
+ .tx_queue_prio = dwmac4_tx_queue_priority,
+ .rx_queue_routing = dwmac4_tx_queue_routing,
+ .prog_mtl_rx_algorithms = dwmac4_prog_mtl_rx_algorithms,
+ .prog_mtl_tx_algorithms = dwmac4_prog_mtl_tx_algorithms,
+ .set_mtl_tx_queue_weight = dwmac4_set_mtl_tx_queue_weight,
+ .map_mtl_to_dma = dwmac4_map_mtl_dma,
+ .config_cbs = dwmac4_config_cbs,
.dump_regs = dwmac4_dump_regs,
.host_irq_status = dwmac4_irq_status,
+ .host_mtl_irq_status = dwmac4_irq_mtl_status,
+ .flow_ctrl = dwmac4_flow_ctrl,
+ .pmt = dwmac4_pmt,
+ .set_umac_addr = dwmac4_set_umac_addr,
+ .get_umac_addr = dwmac4_get_umac_addr,
+ .set_eee_mode = dwmac4_set_eee_mode,
+ .reset_eee_mode = dwmac4_reset_eee_mode,
+ .set_eee_timer = dwmac4_set_eee_timer,
+ .set_eee_pls = dwmac4_set_eee_pls,
+ .pcs_ctrl_ane = dwmac4_ctrl_ane,
+ .pcs_rane = dwmac4_rane,
+ .pcs_get_adv_lp = dwmac4_get_adv_lp,
+ .debug = dwmac4_debug,
+ .set_filter = dwmac4_set_filter,
+};
+
+static const struct stmmac_ops dwmac410_ops = {
+ .core_init = dwmac4_core_init,
+ .set_mac = stmmac_dwmac4_set_mac,
+ .rx_ipc = dwmac4_rx_ipc_enable,
+ .rx_queue_enable = dwmac4_rx_queue_enable,
+ .rx_queue_prio = dwmac4_rx_queue_priority,
+ .tx_queue_prio = dwmac4_tx_queue_priority,
+ .rx_queue_routing = dwmac4_tx_queue_routing,
+ .prog_mtl_rx_algorithms = dwmac4_prog_mtl_rx_algorithms,
+ .prog_mtl_tx_algorithms = dwmac4_prog_mtl_tx_algorithms,
+ .set_mtl_tx_queue_weight = dwmac4_set_mtl_tx_queue_weight,
+ .map_mtl_to_dma = dwmac4_map_mtl_dma,
+ .config_cbs = dwmac4_config_cbs,
+ .dump_regs = dwmac4_dump_regs,
+ .host_irq_status = dwmac4_irq_status,
+ .host_mtl_irq_status = dwmac4_irq_mtl_status,
.flow_ctrl = dwmac4_flow_ctrl,
.pmt = dwmac4_pmt,
.set_umac_addr = dwmac4_set_umac_addr,
@@ -492,8 +747,6 @@ struct mac_device_info *dwmac4_setup(void __iomem *ioaddr, int mcbins,
if (mac->multicast_filter_bins)
mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins);
- mac->mac = &dwmac4_ops;
-
mac->link.port = GMAC_CONFIG_PS;
mac->link.duplex = GMAC_CONFIG_DM;
mac->link.speed = GMAC_CONFIG_FES;
@@ -514,5 +767,10 @@ struct mac_device_info *dwmac4_setup(void __iomem *ioaddr, int mcbins,
else
mac->dma = &dwmac4_dma_ops;
+ if (*synopsys_id >= DWMAC_CORE_4_00)
+ mac->mac = &dwmac410_ops;
+ else
+ mac->mac = &dwmac4_ops;
+
return mac;
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index f97b0d5..eec8463 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -71,36 +71,48 @@ static void dwmac4_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi)
writel(value, ioaddr + DMA_SYS_BUS_MODE);
}
-static void dwmac4_dma_init_channel(void __iomem *ioaddr,
- struct stmmac_dma_cfg *dma_cfg,
- u32 dma_tx_phy, u32 dma_rx_phy,
- u32 channel)
+void dwmac4_dma_init_rx_chan(void __iomem *ioaddr,
+ struct stmmac_dma_cfg *dma_cfg,
+ u32 dma_rx_phy, u32 chan)
{
u32 value;
- int txpbl = dma_cfg->txpbl ?: dma_cfg->pbl;
- int rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl;
+ u32 rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl;
- /* set PBL for each channels. Currently we affect same configuration
- * on each channel
- */
- value = readl(ioaddr + DMA_CHAN_CONTROL(channel));
+ value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan));
+ value = value | (rxpbl << DMA_BUS_MODE_RPBL_SHIFT);
+ writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan));
+
+ writel(dma_rx_phy, ioaddr + DMA_CHAN_RX_BASE_ADDR(chan));
+}
+
+void dwmac4_dma_init_tx_chan(void __iomem *ioaddr,
+ struct stmmac_dma_cfg *dma_cfg,
+ u32 dma_tx_phy, u32 chan)
+{
+ u32 value;
+ u32 txpbl = dma_cfg->txpbl ?: dma_cfg->pbl;
+
+ value = readl(ioaddr + DMA_CHAN_TX_CONTROL(chan));
+ value = value | (txpbl << DMA_BUS_MODE_PBL_SHIFT);
+ writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan));
+
+ writel(dma_tx_phy, ioaddr + DMA_CHAN_TX_BASE_ADDR(chan));
+}
+
+void dwmac4_dma_init_channel(void __iomem *ioaddr,
+ struct stmmac_dma_cfg *dma_cfg, u32 chan)
+{
+ u32 value;
+
+ /* common channel control register config */
+ value = readl(ioaddr + DMA_CHAN_CONTROL(chan));
if (dma_cfg->pblx8)
value = value | DMA_BUS_MODE_PBL;
- writel(value, ioaddr + DMA_CHAN_CONTROL(channel));
-
- value = readl(ioaddr + DMA_CHAN_TX_CONTROL(channel));
- value = value | (txpbl << DMA_BUS_MODE_PBL_SHIFT);
- writel(value, ioaddr + DMA_CHAN_TX_CONTROL(channel));
-
- value = readl(ioaddr + DMA_CHAN_RX_CONTROL(channel));
- value = value | (rxpbl << DMA_BUS_MODE_RPBL_SHIFT);
- writel(value, ioaddr + DMA_CHAN_RX_CONTROL(channel));
+ writel(value, ioaddr + DMA_CHAN_CONTROL(chan));
/* Mask interrupts by writing to CSR7 */
- writel(DMA_CHAN_INTR_DEFAULT_MASK, ioaddr + DMA_CHAN_INTR_ENA(channel));
-
- writel(dma_tx_phy, ioaddr + DMA_CHAN_TX_BASE_ADDR(channel));
- writel(dma_rx_phy, ioaddr + DMA_CHAN_RX_BASE_ADDR(channel));
+ writel(DMA_CHAN_INTR_DEFAULT_MASK,
+ ioaddr + DMA_CHAN_INTR_ENA(chan));
}
static void dwmac4_dma_init(void __iomem *ioaddr,
@@ -108,7 +120,6 @@ static void dwmac4_dma_init(void __iomem *ioaddr,
u32 dma_tx, u32 dma_rx, int atds)
{
u32 value = readl(ioaddr + DMA_SYS_BUS_MODE);
- int i;
/* Set the Fixed burst mode */
if (dma_cfg->fixed_burst)
@@ -122,9 +133,6 @@ static void dwmac4_dma_init(void __iomem *ioaddr,
value |= DMA_SYS_BUS_AAL;
writel(value, ioaddr + DMA_SYS_BUS_MODE);
-
- for (i = 0; i < DMA_CHANNEL_NB_MAX; i++)
- dwmac4_dma_init_channel(ioaddr, dma_cfg, dma_tx, dma_rx, i);
}
static void _dwmac4_dump_dma_regs(void __iomem *ioaddr, u32 channel,
@@ -174,46 +182,121 @@ static void dwmac4_dump_dma_regs(void __iomem *ioaddr, u32 *reg_space)
_dwmac4_dump_dma_regs(ioaddr, i, reg_space);
}
-static void dwmac4_rx_watchdog(void __iomem *ioaddr, u32 riwt)
+static void dwmac4_rx_watchdog(void __iomem *ioaddr, u32 riwt, u32 number_chan)
{
- int i;
+ u32 chan;
- for (i = 0; i < DMA_CHANNEL_NB_MAX; i++)
- writel(riwt, ioaddr + DMA_CHAN_RX_WATCHDOG(i));
+ for (chan = 0; chan < number_chan; chan++)
+ writel(riwt, ioaddr + DMA_CHAN_RX_WATCHDOG(chan));
}
-static void dwmac4_dma_chan_op_mode(void __iomem *ioaddr, int txmode,
- int rxmode, u32 channel)
+static void dwmac4_dma_rx_chan_op_mode(void __iomem *ioaddr, int mode,
+ u32 channel, int fifosz)
{
- u32 mtl_tx_op, mtl_rx_op, mtl_rx_int;
+ unsigned int rqs = fifosz / 256 - 1;
+ u32 mtl_rx_op, mtl_rx_int;
- /* Following code only done for channel 0, other channels not yet
- * supported.
- */
- mtl_tx_op = readl(ioaddr + MTL_CHAN_TX_OP_MODE(channel));
+ mtl_rx_op = readl(ioaddr + MTL_CHAN_RX_OP_MODE(channel));
- if (txmode == SF_DMA_MODE) {
+ if (mode == SF_DMA_MODE) {
+ pr_debug("GMAC: enable RX store and forward mode\n");
+ mtl_rx_op |= MTL_OP_MODE_RSF;
+ } else {
+ pr_debug("GMAC: disable RX SF mode (threshold %d)\n", mode);
+ mtl_rx_op &= ~MTL_OP_MODE_RSF;
+ mtl_rx_op &= MTL_OP_MODE_RTC_MASK;
+ if (mode <= 32)
+ mtl_rx_op |= MTL_OP_MODE_RTC_32;
+ else if (mode <= 64)
+ mtl_rx_op |= MTL_OP_MODE_RTC_64;
+ else if (mode <= 96)
+ mtl_rx_op |= MTL_OP_MODE_RTC_96;
+ else
+ mtl_rx_op |= MTL_OP_MODE_RTC_128;
+ }
+
+ mtl_rx_op &= ~MTL_OP_MODE_RQS_MASK;
+ mtl_rx_op |= rqs << MTL_OP_MODE_RQS_SHIFT;
+
+ /* enable flow control only if each channel gets 4 KiB or more FIFO */
+ if (fifosz >= 4096) {
+ unsigned int rfd, rfa;
+
+ mtl_rx_op |= MTL_OP_MODE_EHFC;
+
+ /* Set Threshold for Activating Flow Control to min 2 frames,
+ * i.e. 1500 * 2 = 3000 bytes.
+ *
+ * Set Threshold for Deactivating Flow Control to min 1 frame,
+ * i.e. 1500 bytes.
+ */
+ switch (fifosz) {
+ case 4096:
+ /* This violates the above formula because of FIFO size
+ * limit therefore overflow may occur in spite of this.
+ */
+ rfd = 0x03; /* Full-2.5K */
+ rfa = 0x01; /* Full-1.5K */
+ break;
+
+ case 8192:
+ rfd = 0x06; /* Full-4K */
+ rfa = 0x0a; /* Full-6K */
+ break;
+
+ case 16384:
+ rfd = 0x06; /* Full-4K */
+ rfa = 0x12; /* Full-10K */
+ break;
+
+ default:
+ rfd = 0x06; /* Full-4K */
+ rfa = 0x1e; /* Full-16K */
+ break;
+ }
+
+ mtl_rx_op &= ~MTL_OP_MODE_RFD_MASK;
+ mtl_rx_op |= rfd << MTL_OP_MODE_RFD_SHIFT;
+
+ mtl_rx_op &= ~MTL_OP_MODE_RFA_MASK;
+ mtl_rx_op |= rfa << MTL_OP_MODE_RFA_SHIFT;
+ }
+
+ writel(mtl_rx_op, ioaddr + MTL_CHAN_RX_OP_MODE(channel));
+
+ /* Enable MTL RX overflow */
+ mtl_rx_int = readl(ioaddr + MTL_CHAN_INT_CTRL(channel));
+ writel(mtl_rx_int | MTL_RX_OVERFLOW_INT_EN,
+ ioaddr + MTL_CHAN_INT_CTRL(channel));
+}
+
+static void dwmac4_dma_tx_chan_op_mode(void __iomem *ioaddr, int mode,
+ u32 channel)
+{
+ u32 mtl_tx_op = readl(ioaddr + MTL_CHAN_TX_OP_MODE(channel));
+
+ if (mode == SF_DMA_MODE) {
pr_debug("GMAC: enable TX store and forward mode\n");
/* Transmit COE type 2 cannot be done in cut-through mode. */
mtl_tx_op |= MTL_OP_MODE_TSF;
} else {
- pr_debug("GMAC: disabling TX SF (threshold %d)\n", txmode);
+ pr_debug("GMAC: disabling TX SF (threshold %d)\n", mode);
mtl_tx_op &= ~MTL_OP_MODE_TSF;
mtl_tx_op &= MTL_OP_MODE_TTC_MASK;
/* Set the transmit threshold */
- if (txmode <= 32)
+ if (mode <= 32)
mtl_tx_op |= MTL_OP_MODE_TTC_32;
- else if (txmode <= 64)
+ else if (mode <= 64)
mtl_tx_op |= MTL_OP_MODE_TTC_64;
- else if (txmode <= 96)
+ else if (mode <= 96)
mtl_tx_op |= MTL_OP_MODE_TTC_96;
- else if (txmode <= 128)
+ else if (mode <= 128)
mtl_tx_op |= MTL_OP_MODE_TTC_128;
- else if (txmode <= 192)
+ else if (mode <= 192)
mtl_tx_op |= MTL_OP_MODE_TTC_192;
- else if (txmode <= 256)
+ else if (mode <= 256)
mtl_tx_op |= MTL_OP_MODE_TTC_256;
- else if (txmode <= 384)
+ else if (mode <= 384)
mtl_tx_op |= MTL_OP_MODE_TTC_384;
else
mtl_tx_op |= MTL_OP_MODE_TTC_512;
@@ -230,39 +313,6 @@ static void dwmac4_dma_chan_op_mode(void __iomem *ioaddr, int txmode,
*/
mtl_tx_op |= MTL_OP_MODE_TXQEN | MTL_OP_MODE_TQS_MASK;
writel(mtl_tx_op, ioaddr + MTL_CHAN_TX_OP_MODE(channel));
-
- mtl_rx_op = readl(ioaddr + MTL_CHAN_RX_OP_MODE(channel));
-
- if (rxmode == SF_DMA_MODE) {
- pr_debug("GMAC: enable RX store and forward mode\n");
- mtl_rx_op |= MTL_OP_MODE_RSF;
- } else {
- pr_debug("GMAC: disable RX SF mode (threshold %d)\n", rxmode);
- mtl_rx_op &= ~MTL_OP_MODE_RSF;
- mtl_rx_op &= MTL_OP_MODE_RTC_MASK;
- if (rxmode <= 32)
- mtl_rx_op |= MTL_OP_MODE_RTC_32;
- else if (rxmode <= 64)
- mtl_rx_op |= MTL_OP_MODE_RTC_64;
- else if (rxmode <= 96)
- mtl_rx_op |= MTL_OP_MODE_RTC_96;
- else
- mtl_rx_op |= MTL_OP_MODE_RTC_128;
- }
-
- writel(mtl_rx_op, ioaddr + MTL_CHAN_RX_OP_MODE(channel));
-
- /* Enable MTL RX overflow */
- mtl_rx_int = readl(ioaddr + MTL_CHAN_INT_CTRL(channel));
- writel(mtl_rx_int | MTL_RX_OVERFLOW_INT_EN,
- ioaddr + MTL_CHAN_INT_CTRL(channel));
-}
-
-static void dwmac4_dma_operation_mode(void __iomem *ioaddr, int txmode,
- int rxmode, int rxfifosz)
-{
- /* Only Channel 0 is actually configured and used */
- dwmac4_dma_chan_op_mode(ioaddr, txmode, rxmode, 0);
}
static void dwmac4_get_hw_feature(void __iomem *ioaddr,
@@ -294,6 +344,11 @@ static void dwmac4_get_hw_feature(void __iomem *ioaddr,
hw_cap = readl(ioaddr + GMAC_HW_FEATURE1);
dma_cap->av = (hw_cap & GMAC_HW_FEAT_AVSEL) >> 20;
dma_cap->tsoen = (hw_cap & GMAC_HW_TSOEN) >> 18;
+ /* RX and TX FIFO sizes are encoded as log2(n / 128). Undo that by
+ * shifting and store the sizes in bytes.
+ */
+ dma_cap->tx_fifo_size = 128 << ((hw_cap & GMAC_HW_TXFIFOSIZE) >> 6);
+ dma_cap->rx_fifo_size = 128 << ((hw_cap & GMAC_HW_RXFIFOSIZE) >> 0);
/* MAC HW feature2 */
hw_cap = readl(ioaddr + GMAC_HW_FEATURE2);
/* TX and RX number of channels */
@@ -332,9 +387,13 @@ static void dwmac4_enable_tso(void __iomem *ioaddr, bool en, u32 chan)
const struct stmmac_dma_ops dwmac4_dma_ops = {
.reset = dwmac4_dma_reset,
.init = dwmac4_dma_init,
+ .init_chan = dwmac4_dma_init_channel,
+ .init_rx_chan = dwmac4_dma_init_rx_chan,
+ .init_tx_chan = dwmac4_dma_init_tx_chan,
.axi = dwmac4_dma_axi,
.dump_regs = dwmac4_dump_dma_regs,
- .dma_mode = dwmac4_dma_operation_mode,
+ .dma_rx_mode = dwmac4_dma_rx_chan_op_mode,
+ .dma_tx_mode = dwmac4_dma_tx_chan_op_mode,
.enable_dma_irq = dwmac4_enable_dma_irq,
.disable_dma_irq = dwmac4_disable_dma_irq,
.start_tx = dwmac4_dma_start_tx,
@@ -354,9 +413,13 @@ const struct stmmac_dma_ops dwmac4_dma_ops = {
const struct stmmac_dma_ops dwmac410_dma_ops = {
.reset = dwmac4_dma_reset,
.init = dwmac4_dma_init,
+ .init_chan = dwmac4_dma_init_channel,
+ .init_rx_chan = dwmac4_dma_init_rx_chan,
+ .init_tx_chan = dwmac4_dma_init_tx_chan,
.axi = dwmac4_dma_axi,
.dump_regs = dwmac4_dump_dma_regs,
- .dma_mode = dwmac4_dma_operation_mode,
+ .dma_rx_mode = dwmac4_dma_rx_chan_op_mode,
+ .dma_tx_mode = dwmac4_dma_tx_chan_op_mode,
.enable_dma_irq = dwmac410_enable_dma_irq,
.disable_dma_irq = dwmac4_disable_dma_irq,
.start_tx = dwmac4_dma_start_tx,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
index 1b06df7..8474bf9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
@@ -185,17 +185,17 @@
int dwmac4_dma_reset(void __iomem *ioaddr);
void dwmac4_enable_dma_transmission(void __iomem *ioaddr, u32 tail_ptr);
-void dwmac4_enable_dma_irq(void __iomem *ioaddr);
-void dwmac410_enable_dma_irq(void __iomem *ioaddr);
-void dwmac4_disable_dma_irq(void __iomem *ioaddr);
-void dwmac4_dma_start_tx(void __iomem *ioaddr);
-void dwmac4_dma_stop_tx(void __iomem *ioaddr);
-void dwmac4_dma_start_rx(void __iomem *ioaddr);
-void dwmac4_dma_stop_rx(void __iomem *ioaddr);
+void dwmac4_enable_dma_irq(void __iomem *ioaddr, u32 chan);
+void dwmac410_enable_dma_irq(void __iomem *ioaddr, u32 chan);
+void dwmac4_disable_dma_irq(void __iomem *ioaddr, u32 chan);
+void dwmac4_dma_start_tx(void __iomem *ioaddr, u32 chan);
+void dwmac4_dma_stop_tx(void __iomem *ioaddr, u32 chan);
+void dwmac4_dma_start_rx(void __iomem *ioaddr, u32 chan);
+void dwmac4_dma_stop_rx(void __iomem *ioaddr, u32 chan);
int dwmac4_dma_interrupt(void __iomem *ioaddr,
- struct stmmac_extra_stats *x);
-void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len);
-void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len);
+ struct stmmac_extra_stats *x, u32 chan);
+void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len, u32 chan);
+void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len, u32 chan);
void dwmac4_set_rx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
void dwmac4_set_tx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
index c7326d5..49f5687 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
@@ -37,96 +37,96 @@ int dwmac4_dma_reset(void __iomem *ioaddr)
void dwmac4_set_rx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan)
{
- writel(tail_ptr, ioaddr + DMA_CHAN_RX_END_ADDR(0));
+ writel(tail_ptr, ioaddr + DMA_CHAN_RX_END_ADDR(chan));
}
void dwmac4_set_tx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan)
{
- writel(tail_ptr, ioaddr + DMA_CHAN_TX_END_ADDR(0));
+ writel(tail_ptr, ioaddr + DMA_CHAN_TX_END_ADDR(chan));
}
-void dwmac4_dma_start_tx(void __iomem *ioaddr)
+void dwmac4_dma_start_tx(void __iomem *ioaddr, u32 chan)
{
- u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0));
+ u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(chan));
value |= DMA_CONTROL_ST;
- writel(value, ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0));
+ writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan));
value = readl(ioaddr + GMAC_CONFIG);
value |= GMAC_CONFIG_TE;
writel(value, ioaddr + GMAC_CONFIG);
}
-void dwmac4_dma_stop_tx(void __iomem *ioaddr)
+void dwmac4_dma_stop_tx(void __iomem *ioaddr, u32 chan)
{
- u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0));
+ u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(chan));
value &= ~DMA_CONTROL_ST;
- writel(value, ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0));
+ writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan));
value = readl(ioaddr + GMAC_CONFIG);
value &= ~GMAC_CONFIG_TE;
writel(value, ioaddr + GMAC_CONFIG);
}
-void dwmac4_dma_start_rx(void __iomem *ioaddr)
+void dwmac4_dma_start_rx(void __iomem *ioaddr, u32 chan)
{
- u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0));
+ u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan));
value |= DMA_CONTROL_SR;
- writel(value, ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0));
+ writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan));
value = readl(ioaddr + GMAC_CONFIG);
value |= GMAC_CONFIG_RE;
writel(value, ioaddr + GMAC_CONFIG);
}
-void dwmac4_dma_stop_rx(void __iomem *ioaddr)
+void dwmac4_dma_stop_rx(void __iomem *ioaddr, u32 chan)
{
- u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0));
+ u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan));
value &= ~DMA_CONTROL_SR;
- writel(value, ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0));
+ writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan));
value = readl(ioaddr + GMAC_CONFIG);
value &= ~GMAC_CONFIG_RE;
writel(value, ioaddr + GMAC_CONFIG);
}
-void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len)
+void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len, u32 chan)
{
- writel(len, ioaddr + DMA_CHAN_TX_RING_LEN(STMMAC_CHAN0));
+ writel(len, ioaddr + DMA_CHAN_TX_RING_LEN(chan));
}
-void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len)
+void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len, u32 chan)
{
- writel(len, ioaddr + DMA_CHAN_RX_RING_LEN(STMMAC_CHAN0));
+ writel(len, ioaddr + DMA_CHAN_RX_RING_LEN(chan));
}
-void dwmac4_enable_dma_irq(void __iomem *ioaddr)
+void dwmac4_enable_dma_irq(void __iomem *ioaddr, u32 chan)
{
writel(DMA_CHAN_INTR_DEFAULT_MASK, ioaddr +
- DMA_CHAN_INTR_ENA(STMMAC_CHAN0));
+ DMA_CHAN_INTR_ENA(chan));
}
-void dwmac410_enable_dma_irq(void __iomem *ioaddr)
+void dwmac410_enable_dma_irq(void __iomem *ioaddr, u32 chan)
{
writel(DMA_CHAN_INTR_DEFAULT_MASK_4_10,
- ioaddr + DMA_CHAN_INTR_ENA(STMMAC_CHAN0));
+ ioaddr + DMA_CHAN_INTR_ENA(chan));
}
-void dwmac4_disable_dma_irq(void __iomem *ioaddr)
+void dwmac4_disable_dma_irq(void __iomem *ioaddr, u32 chan)
{
- writel(0, ioaddr + DMA_CHAN_INTR_ENA(STMMAC_CHAN0));
+ writel(0, ioaddr + DMA_CHAN_INTR_ENA(chan));
}
int dwmac4_dma_interrupt(void __iomem *ioaddr,
- struct stmmac_extra_stats *x)
+ struct stmmac_extra_stats *x, u32 chan)
{
int ret = 0;
- u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(0));
+ u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(chan));
/* ABNORMAL interrupts */
if (unlikely(intr_status & DMA_CHAN_STATUS_AIS)) {
@@ -153,7 +153,7 @@ int dwmac4_dma_interrupt(void __iomem *ioaddr,
if (likely(intr_status & DMA_CHAN_STATUS_RI)) {
u32 value;
- value = readl(ioaddr + DMA_CHAN_INTR_ENA(STMMAC_CHAN0));
+ value = readl(ioaddr + DMA_CHAN_INTR_ENA(chan));
/* to schedule NAPI on real RIE event. */
if (likely(value & DMA_CHAN_INTR_ENA_RIE)) {
x->rx_normal_irq_n++;
@@ -172,7 +172,7 @@ int dwmac4_dma_interrupt(void __iomem *ioaddr,
* status [21-0] expect reserved bits [5-3]
*/
writel((intr_status & 0x3fffc7),
- ioaddr + DMA_CHAN_STATUS(STMMAC_CHAN0));
+ ioaddr + DMA_CHAN_STATUS(chan));
return ret;
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
index 56e485f..9091df8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
@@ -137,13 +137,14 @@
#define DMA_CONTROL_FTF 0x00100000 /* Flush transmit FIFO */
void dwmac_enable_dma_transmission(void __iomem *ioaddr);
-void dwmac_enable_dma_irq(void __iomem *ioaddr);
-void dwmac_disable_dma_irq(void __iomem *ioaddr);
-void dwmac_dma_start_tx(void __iomem *ioaddr);
-void dwmac_dma_stop_tx(void __iomem *ioaddr);
-void dwmac_dma_start_rx(void __iomem *ioaddr);
-void dwmac_dma_stop_rx(void __iomem *ioaddr);
-int dwmac_dma_interrupt(void __iomem *ioaddr, struct stmmac_extra_stats *x);
+void dwmac_enable_dma_irq(void __iomem *ioaddr, u32 chan);
+void dwmac_disable_dma_irq(void __iomem *ioaddr, u32 chan);
+void dwmac_dma_start_tx(void __iomem *ioaddr, u32 chan);
+void dwmac_dma_stop_tx(void __iomem *ioaddr, u32 chan);
+void dwmac_dma_start_rx(void __iomem *ioaddr, u32 chan);
+void dwmac_dma_stop_rx(void __iomem *ioaddr, u32 chan);
+int dwmac_dma_interrupt(void __iomem *ioaddr, struct stmmac_extra_stats *x,
+ u32 chan);
int dwmac_dma_reset(void __iomem *ioaddr);
#endif /* __DWMAC_DMA_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
index e60bfca..38f9430 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
@@ -47,38 +47,38 @@ void dwmac_enable_dma_transmission(void __iomem *ioaddr)
writel(1, ioaddr + DMA_XMT_POLL_DEMAND);
}
-void dwmac_enable_dma_irq(void __iomem *ioaddr)
+void dwmac_enable_dma_irq(void __iomem *ioaddr, u32 chan)
{
writel(DMA_INTR_DEFAULT_MASK, ioaddr + DMA_INTR_ENA);
}
-void dwmac_disable_dma_irq(void __iomem *ioaddr)
+void dwmac_disable_dma_irq(void __iomem *ioaddr, u32 chan)
{
writel(0, ioaddr + DMA_INTR_ENA);
}
-void dwmac_dma_start_tx(void __iomem *ioaddr)
+void dwmac_dma_start_tx(void __iomem *ioaddr, u32 chan)
{
u32 value = readl(ioaddr + DMA_CONTROL);
value |= DMA_CONTROL_ST;
writel(value, ioaddr + DMA_CONTROL);
}
-void dwmac_dma_stop_tx(void __iomem *ioaddr)
+void dwmac_dma_stop_tx(void __iomem *ioaddr, u32 chan)
{
u32 value = readl(ioaddr + DMA_CONTROL);
value &= ~DMA_CONTROL_ST;
writel(value, ioaddr + DMA_CONTROL);
}
-void dwmac_dma_start_rx(void __iomem *ioaddr)
+void dwmac_dma_start_rx(void __iomem *ioaddr, u32 chan)
{
u32 value = readl(ioaddr + DMA_CONTROL);
value |= DMA_CONTROL_SR;
writel(value, ioaddr + DMA_CONTROL);
}
-void dwmac_dma_stop_rx(void __iomem *ioaddr)
+void dwmac_dma_stop_rx(void __iomem *ioaddr, u32 chan)
{
u32 value = readl(ioaddr + DMA_CONTROL);
value &= ~DMA_CONTROL_SR;
@@ -156,7 +156,7 @@ static void show_rx_process_state(unsigned int status)
#endif
int dwmac_dma_interrupt(void __iomem *ioaddr,
- struct stmmac_extra_stats *x)
+ struct stmmac_extra_stats *x, u32 chan)
{
int ret = 0;
/* read the status register (CSR5) */
diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
index 452f256..31213e6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
@@ -26,16 +26,17 @@
static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
{
- struct stmmac_priv *priv = (struct stmmac_priv *)p;
- unsigned int entry = priv->cur_tx;
- struct dma_desc *desc;
+ struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)p;
unsigned int nopaged_len = skb_headlen(skb);
+ struct stmmac_priv *priv = tx_q->priv_data;
+ unsigned int entry = tx_q->cur_tx;
unsigned int bmax, len, des2;
+ struct dma_desc *desc;
if (priv->extend_desc)
- desc = (struct dma_desc *)(priv->dma_etx + entry);
+ desc = (struct dma_desc *)(tx_q->dma_etx + entry);
else
- desc = priv->dma_tx + entry;
+ desc = tx_q->dma_tx + entry;
if (priv->plat->enh_desc)
bmax = BUF_SIZE_8KiB;
@@ -52,29 +53,29 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
if (dma_mapping_error(priv->device, des2))
return -1;
- priv->tx_skbuff_dma[entry].buf = des2;
- priv->tx_skbuff_dma[entry].len = bmax;
- priv->tx_skbuff_dma[entry].is_jumbo = true;
+ tx_q->tx_skbuff_dma[entry].buf = des2;
+ tx_q->tx_skbuff_dma[entry].len = bmax;
+ tx_q->tx_skbuff_dma[entry].is_jumbo = true;
desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum,
STMMAC_RING_MODE, 0, false);
- priv->tx_skbuff[entry] = NULL;
+ tx_q->tx_skbuff[entry] = NULL;
entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE);
if (priv->extend_desc)
- desc = (struct dma_desc *)(priv->dma_etx + entry);
+ desc = (struct dma_desc *)(tx_q->dma_etx + entry);
else
- desc = priv->dma_tx + entry;
+ desc = tx_q->dma_tx + entry;
des2 = dma_map_single(priv->device, skb->data + bmax, len,
DMA_TO_DEVICE);
desc->des2 = cpu_to_le32(des2);
if (dma_mapping_error(priv->device, des2))
return -1;
- priv->tx_skbuff_dma[entry].buf = des2;
- priv->tx_skbuff_dma[entry].len = len;
- priv->tx_skbuff_dma[entry].is_jumbo = true;
+ tx_q->tx_skbuff_dma[entry].buf = des2;
+ tx_q->tx_skbuff_dma[entry].len = len;
+ tx_q->tx_skbuff_dma[entry].is_jumbo = true;
desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
priv->hw->desc->prepare_tx_desc(desc, 0, len, csum,
@@ -85,15 +86,15 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
desc->des2 = cpu_to_le32(des2);
if (dma_mapping_error(priv->device, des2))
return -1;
- priv->tx_skbuff_dma[entry].buf = des2;
- priv->tx_skbuff_dma[entry].len = nopaged_len;
- priv->tx_skbuff_dma[entry].is_jumbo = true;
+ tx_q->tx_skbuff_dma[entry].buf = des2;
+ tx_q->tx_skbuff_dma[entry].len = nopaged_len;
+ tx_q->tx_skbuff_dma[entry].is_jumbo = true;
desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
priv->hw->desc->prepare_tx_desc(desc, 1, nopaged_len, csum,
STMMAC_RING_MODE, 0, true);
}
- priv->cur_tx = entry;
+ tx_q->cur_tx = entry;
return entry;
}
@@ -125,12 +126,13 @@ static void stmmac_init_desc3(struct dma_desc *p)
static void stmmac_clean_desc3(void *priv_ptr, struct dma_desc *p)
{
- struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr;
- unsigned int entry = priv->dirty_tx;
+ struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)priv_ptr;
+ struct stmmac_priv *priv = tx_q->priv_data;
+ unsigned int entry = tx_q->dirty_tx;
/* des3 is only used for jumbo frames tx or time stamping */
- if (unlikely(priv->tx_skbuff_dma[entry].is_jumbo ||
- (priv->tx_skbuff_dma[entry].last_segment &&
+ if (unlikely(tx_q->tx_skbuff_dma[entry].is_jumbo ||
+ (tx_q->tx_skbuff_dma[entry].last_segment &&
!priv->extend_desc && priv->hwts_tx_en)))
p->des3 = 0;
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index cd8fb61..33efe70 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -46,38 +46,51 @@ struct stmmac_tx_info {
bool is_jumbo;
};
-struct stmmac_priv {
- /* Frequently used values are kept adjacent for cache effect */
+/* Frequently used values are kept adjacent for cache effect */
+struct stmmac_tx_queue {
+ u32 queue_index;
+ struct stmmac_priv *priv_data;
struct dma_extended_desc *dma_etx ____cacheline_aligned_in_smp;
struct dma_desc *dma_tx;
struct sk_buff **tx_skbuff;
+ struct stmmac_tx_info *tx_skbuff_dma;
unsigned int cur_tx;
unsigned int dirty_tx;
+ dma_addr_t dma_tx_phy;
+ u32 tx_tail_addr;
+};
+
+struct stmmac_rx_queue {
+ u32 queue_index;
+ struct stmmac_priv *priv_data;
+ struct dma_extended_desc *dma_erx;
+ struct dma_desc *dma_rx ____cacheline_aligned_in_smp;
+ struct sk_buff **rx_skbuff;
+ dma_addr_t *rx_skbuff_dma;
+ unsigned int cur_rx;
+ unsigned int dirty_rx;
+ u32 rx_zeroc_thresh;
+ dma_addr_t dma_rx_phy;
+ u32 rx_tail_addr;
+ struct napi_struct napi ____cacheline_aligned_in_smp;
+};
+
+struct stmmac_priv {
+ /* Frequently used values are kept adjacent for cache effect */
u32 tx_count_frames;
u32 tx_coal_frames;
u32 tx_coal_timer;
- struct stmmac_tx_info *tx_skbuff_dma;
- dma_addr_t dma_tx_phy;
+
int tx_coalesce;
int hwts_tx_en;
bool tx_path_in_lpi_mode;
struct timer_list txtimer;
bool tso;
- struct dma_desc *dma_rx ____cacheline_aligned_in_smp;
- struct dma_extended_desc *dma_erx;
- struct sk_buff **rx_skbuff;
- unsigned int cur_rx;
- unsigned int dirty_rx;
unsigned int dma_buf_sz;
unsigned int rx_copybreak;
- unsigned int rx_zeroc_thresh;
u32 rx_riwt;
int hwts_rx_en;
- dma_addr_t *rx_skbuff_dma;
- dma_addr_t dma_rx_phy;
-
- struct napi_struct napi ____cacheline_aligned_in_smp;
void __iomem *ioaddr;
struct net_device *dev;
@@ -85,6 +98,12 @@ struct stmmac_priv {
struct mac_device_info *hw;
spinlock_t lock;
+ /* RX Queue */
+ struct stmmac_rx_queue rx_queue[MTL_MAX_RX_QUEUES];
+
+ /* TX Queue */
+ struct stmmac_tx_queue tx_queue[MTL_MAX_TX_QUEUES];
+
int oldlink;
int speed;
int oldduplex;
@@ -119,8 +138,6 @@ struct stmmac_priv {
spinlock_t ptp_lock;
void __iomem *mmcaddr;
void __iomem *ptpaddr;
- u32 rx_tail_addr;
- u32 tx_tail_addr;
u32 mss;
#ifdef CONFIG_DEBUG_FS
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 85d6411..16808e4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -481,6 +481,7 @@ stmmac_set_pauseparam(struct net_device *netdev,
struct ethtool_pauseparam *pause)
{
struct stmmac_priv *priv = netdev_priv(netdev);
+ u32 tx_cnt = priv->plat->tx_queues_to_use;
struct phy_device *phy = netdev->phydev;
int new_pause = FLOW_OFF;
@@ -511,7 +512,7 @@ stmmac_set_pauseparam(struct net_device *netdev,
}
priv->hw->mac->flow_ctrl(priv->hw, phy->duplex, priv->flow_ctrl,
- priv->pause);
+ priv->pause, tx_cnt);
return 0;
}
@@ -519,6 +520,8 @@ static void stmmac_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *dummy, u64 *data)
{
struct stmmac_priv *priv = netdev_priv(dev);
+ u32 rx_queues_count = priv->plat->rx_queues_to_use;
+ u32 tx_queues_count = priv->plat->tx_queues_to_use;
int i, j = 0;
/* Update the DMA HW counters for dwmac10/100 */
@@ -549,7 +552,8 @@ static void stmmac_get_ethtool_stats(struct net_device *dev,
if ((priv->hw->mac->debug) &&
(priv->synopsys_id >= DWMAC_CORE_3_50))
priv->hw->mac->debug(priv->ioaddr,
- (void *)&priv->xstats);
+ (void *)&priv->xstats,
+ rx_queues_count, tx_queues_count);
}
for (i = 0; i < STMMAC_STATS_LEN; i++) {
char *p = (char *)priv + stmmac_gstrings_stats[i].stat_offset;
@@ -726,6 +730,7 @@ static int stmmac_set_coalesce(struct net_device *dev,
struct ethtool_coalesce *ec)
{
struct stmmac_priv *priv = netdev_priv(dev);
+ u32 rx_cnt = priv->plat->rx_queues_to_use;
unsigned int rx_riwt;
/* Check not supported parameters */
@@ -764,7 +769,7 @@ static int stmmac_set_coalesce(struct net_device *dev,
priv->tx_coal_frames = ec->tx_max_coalesced_frames;
priv->tx_coal_timer = ec->tx_coalesce_usecs;
priv->rx_riwt = rx_riwt;
- priv->hw->dma->rx_watchdog(priv->ioaddr, priv->rx_riwt);
+ priv->hw->dma->rx_watchdog(priv->ioaddr, priv->rx_riwt, rx_cnt);
return 0;
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 4498a38..a89f76b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -139,6 +139,64 @@ static void stmmac_verify_args(void)
}
/**
+ * stmmac_disable_all_queues - Disable all queues
+ * @priv: driver private structure
+ */
+static void stmmac_disable_all_queues(struct stmmac_priv *priv)
+{
+ u32 rx_queues_cnt = priv->plat->rx_queues_to_use;
+ u32 queue;
+
+ for (queue = 0; queue < rx_queues_cnt; queue++) {
+ struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+ napi_disable(&rx_q->napi);
+ }
+}
+
+/**
+ * stmmac_enable_all_queues - Enable all queues
+ * @priv: driver private structure
+ */
+static void stmmac_enable_all_queues(struct stmmac_priv *priv)
+{
+ u32 rx_queues_cnt = priv->plat->rx_queues_to_use;
+ u32 queue;
+
+ for (queue = 0; queue < rx_queues_cnt; queue++) {
+ struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+ napi_enable(&rx_q->napi);
+ }
+}
+
+/**
+ * stmmac_stop_all_queues - Stop all queues
+ * @priv: driver private structure
+ */
+static void stmmac_stop_all_queues(struct stmmac_priv *priv)
+{
+ u32 tx_queues_cnt = priv->plat->tx_queues_to_use;
+ u32 queue;
+
+ for (queue = 0; queue < tx_queues_cnt; queue++)
+ netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue));
+}
+
+/**
+ * stmmac_start_all_queues - Start all queues
+ * @priv: driver private structure
+ */
+static void stmmac_start_all_queues(struct stmmac_priv *priv)
+{
+ u32 tx_queues_cnt = priv->plat->tx_queues_to_use;
+ u32 queue;
+
+ for (queue = 0; queue < tx_queues_cnt; queue++)
+ netif_tx_start_queue(netdev_get_tx_queue(priv->dev, queue));
+}
+
+/**
* stmmac_clk_csr_set - dynamically set the MDC clock
* @priv: driver private structure
* Description: this is to dynamically set the MDC clock according to the csr
@@ -185,26 +243,33 @@ static void print_pkt(unsigned char *buf, int len)
print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, buf, len);
}
-static inline u32 stmmac_tx_avail(struct stmmac_priv *priv)
+static inline u32 stmmac_tx_avail(struct stmmac_priv *priv, u32 queue)
{
+ struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
u32 avail;
- if (priv->dirty_tx > priv->cur_tx)
- avail = priv->dirty_tx - priv->cur_tx - 1;
+ if (tx_q->dirty_tx > tx_q->cur_tx)
+ avail = tx_q->dirty_tx - tx_q->cur_tx - 1;
else
- avail = DMA_TX_SIZE - priv->cur_tx + priv->dirty_tx - 1;
+ avail = DMA_TX_SIZE - tx_q->cur_tx + tx_q->dirty_tx - 1;
return avail;
}
-static inline u32 stmmac_rx_dirty(struct stmmac_priv *priv)
+/**
+ * stmmac_rx_dirty - Get RX queue dirty
+ * @priv: driver private structure
+ * @queue: RX queue index
+ */
+static inline u32 stmmac_rx_dirty(struct stmmac_priv *priv, u32 queue)
{
+ struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
u32 dirty;
- if (priv->dirty_rx <= priv->cur_rx)
- dirty = priv->cur_rx - priv->dirty_rx;
+ if (rx_q->dirty_rx <= rx_q->cur_rx)
+ dirty = rx_q->cur_rx - rx_q->dirty_rx;
else
- dirty = DMA_RX_SIZE - priv->dirty_rx + priv->cur_rx;
+ dirty = DMA_RX_SIZE - rx_q->dirty_rx + rx_q->cur_rx;
return dirty;
}
@@ -232,9 +297,19 @@ static inline void stmmac_hw_fix_mac_speed(struct stmmac_priv *priv)
*/
static void stmmac_enable_eee_mode(struct stmmac_priv *priv)
{
+ u32 tx_cnt = priv->plat->tx_queues_to_use;
+ u32 queue;
+
+ /* check if all TX queues have the work finished */
+ for (queue = 0; queue < tx_cnt; queue++) {
+ struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+ if (tx_q->dirty_tx != tx_q->cur_tx)
+ return; /* still unfinished work */
+ }
+
/* Check and enter in LPI mode */
- if ((priv->dirty_tx == priv->cur_tx) &&
- (priv->tx_path_in_lpi_mode == false))
+ if (!priv->tx_path_in_lpi_mode)
priv->hw->mac->set_eee_mode(priv->hw,
priv->plat->en_tx_lpi_clockgating);
}
@@ -673,6 +748,19 @@ static void stmmac_release_ptp(struct stmmac_priv *priv)
}
/**
+ * stmmac_mac_flow_ctrl - Configure flow control in all queues
+ * @priv: driver private structure
+ * Description: It is used for configuring the flow control in all queues
+ */
+static void stmmac_mac_flow_ctrl(struct stmmac_priv *priv, u32 duplex)
+{
+ u32 tx_cnt = priv->plat->tx_queues_to_use;
+
+ priv->hw->mac->flow_ctrl(priv->hw, duplex, priv->flow_ctrl,
+ priv->pause, tx_cnt);
+}
+
+/**
* stmmac_adjust_link - adjusts the link parameters
* @dev: net device structure
* Description: this is the helper called by the physical abstraction layer
@@ -687,7 +775,6 @@ static void stmmac_adjust_link(struct net_device *dev)
struct phy_device *phydev = dev->phydev;
unsigned long flags;
int new_state = 0;
- unsigned int fc = priv->flow_ctrl, pause_time = priv->pause;
if (!phydev)
return;
@@ -709,8 +796,7 @@ static void stmmac_adjust_link(struct net_device *dev)
}
/* Flow Control operation */
if (phydev->pause)
- priv->hw->mac->flow_ctrl(priv->hw, phydev->duplex,
- fc, pause_time);
+ stmmac_mac_flow_ctrl(priv, phydev->duplex);
if (phydev->speed != priv->speed) {
new_state = 1;
@@ -878,22 +964,56 @@ static int stmmac_init_phy(struct net_device *dev)
return 0;
}
+static void stmmac_display_rx_rings(struct stmmac_priv *priv)
+{
+ u32 rx_cnt = priv->plat->rx_queues_to_use;
+ void *head_rx;
+ u32 queue;
+
+ /* Display RX rings */
+ for (queue = 0; queue < rx_cnt; queue++) {
+ struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+ pr_info("\tRX Queue %u rings\n", queue);
+
+ if (priv->extend_desc)
+ head_rx = (void *)rx_q->dma_erx;
+ else
+ head_rx = (void *)rx_q->dma_rx;
+
+ /* Display RX ring */
+ priv->hw->desc->display_ring(head_rx, DMA_RX_SIZE, true);
+ }
+}
+
+static void stmmac_display_tx_rings(struct stmmac_priv *priv)
+{
+ u32 tx_cnt = priv->plat->tx_queues_to_use;
+ void *head_tx;
+ u32 queue;
+
+ /* Display TX rings */
+ for (queue = 0; queue < tx_cnt; queue++) {
+ struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+ pr_info("\tTX Queue %d rings\n", queue);
+
+ if (priv->extend_desc)
+ head_tx = (void *)tx_q->dma_etx;
+ else
+ head_tx = (void *)tx_q->dma_tx;
+
+ priv->hw->desc->display_ring(head_tx, DMA_TX_SIZE, false);
+ }
+}
+
static void stmmac_display_rings(struct stmmac_priv *priv)
{
- void *head_rx, *head_tx;
+ /* Display RX ring */
+ stmmac_display_rx_rings(priv);
- if (priv->extend_desc) {
- head_rx = (void *)priv->dma_erx;
- head_tx = (void *)priv->dma_etx;
- } else {
- head_rx = (void *)priv->dma_rx;
- head_tx = (void *)priv->dma_tx;
- }
-
- /* Display Rx ring */
- priv->hw->desc->display_ring(head_rx, DMA_RX_SIZE, true);
- /* Display Tx ring */
- priv->hw->desc->display_ring(head_tx, DMA_TX_SIZE, false);
+ /* Display TX ring */
+ stmmac_display_tx_rings(priv);
}
static int stmmac_set_bfsize(int mtu, int bufsize)
@@ -913,34 +1033,72 @@ static int stmmac_set_bfsize(int mtu, int bufsize)
}
/**
+ * stmmac_clear_rx_descriptors - clear RX descriptors
+ * @priv: driver private structure
+ * @queue: RX queue index
+ * Description: this function is called to clear the RX descriptors
+ * in case of both basic and extended descriptors are used.
+ */
+static void stmmac_clear_rx_descriptors(struct stmmac_priv *priv, u32 queue)
+{
+ struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+ int i;
+
+ /* Clear the RX descriptors */
+ for (i = 0; i < DMA_RX_SIZE; i++)
+ if (priv->extend_desc)
+ priv->hw->desc->init_rx_desc(&rx_q->dma_erx[i].basic,
+ priv->use_riwt, priv->mode,
+ (i == DMA_RX_SIZE - 1));
+ else
+ priv->hw->desc->init_rx_desc(&rx_q->dma_rx[i],
+ priv->use_riwt, priv->mode,
+ (i == DMA_RX_SIZE - 1));
+}
+
+/**
+ * stmmac_clear_tx_descriptors - clear tx descriptors
+ * @priv: driver private structure
+ * @queue: TX queue index.
+ * Description: this function is called to clear the TX descriptors
+ * in case of both basic and extended descriptors are used.
+ */
+static void stmmac_clear_tx_descriptors(struct stmmac_priv *priv, u32 queue)
+{
+ struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+ int i;
+
+ /* Clear the TX descriptors */
+ for (i = 0; i < DMA_TX_SIZE; i++)
+ if (priv->extend_desc)
+ priv->hw->desc->init_tx_desc(&tx_q->dma_etx[i].basic,
+ priv->mode,
+ (i == DMA_TX_SIZE - 1));
+ else
+ priv->hw->desc->init_tx_desc(&tx_q->dma_tx[i],
+ priv->mode,
+ (i == DMA_TX_SIZE - 1));
+}
+
+/**
* stmmac_clear_descriptors - clear descriptors
* @priv: driver private structure
- * Description: this function is called to clear the tx and rx descriptors
+ * Description: this function is called to clear the TX and RX descriptors
* in case of both basic and extended descriptors are used.
*/
static void stmmac_clear_descriptors(struct stmmac_priv *priv)
{
- int i;
+ u32 rx_queue_cnt = priv->plat->rx_queues_to_use;
+ u32 tx_queue_cnt = priv->plat->tx_queues_to_use;
+ u32 queue;
- /* Clear the Rx/Tx descriptors */
- for (i = 0; i < DMA_RX_SIZE; i++)
- if (priv->extend_desc)
- priv->hw->desc->init_rx_desc(&priv->dma_erx[i].basic,
- priv->use_riwt, priv->mode,
- (i == DMA_RX_SIZE - 1));
- else
- priv->hw->desc->init_rx_desc(&priv->dma_rx[i],
- priv->use_riwt, priv->mode,
- (i == DMA_RX_SIZE - 1));
- for (i = 0; i < DMA_TX_SIZE; i++)
- if (priv->extend_desc)
- priv->hw->desc->init_tx_desc(&priv->dma_etx[i].basic,
- priv->mode,
- (i == DMA_TX_SIZE - 1));
- else
- priv->hw->desc->init_tx_desc(&priv->dma_tx[i],
- priv->mode,
- (i == DMA_TX_SIZE - 1));
+ /* Clear the RX descriptors */
+ for (queue = 0; queue < rx_queue_cnt; queue++)
+ stmmac_clear_rx_descriptors(priv, queue);
+
+ /* Clear the TX descriptors */
+ for (queue = 0; queue < tx_queue_cnt; queue++)
+ stmmac_clear_tx_descriptors(priv, queue);
}
/**
@@ -948,13 +1106,15 @@ static void stmmac_clear_descriptors(struct stmmac_priv *priv)
* @priv: driver private structure
* @p: descriptor pointer
* @i: descriptor index
- * @flags: gfp flag.
+ * @flags: gfp flag
+ * @queue: RX queue index
* Description: this function is called to allocate a receive buffer, perform
* the DMA mapping and init the descriptor.
*/
static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
- int i, gfp_t flags)
+ int i, gfp_t flags, u32 queue)
{
+ struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
struct sk_buff *skb;
skb = __netdev_alloc_skb_ip_align(priv->dev, priv->dma_buf_sz, flags);
@@ -963,20 +1123,20 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
"%s: Rx init fails; skb is NULL\n", __func__);
return -ENOMEM;
}
- priv->rx_skbuff[i] = skb;
- priv->rx_skbuff_dma[i] = dma_map_single(priv->device, skb->data,
+ rx_q->rx_skbuff[i] = skb;
+ rx_q->rx_skbuff_dma[i] = dma_map_single(priv->device, skb->data,
priv->dma_buf_sz,
DMA_FROM_DEVICE);
- if (dma_mapping_error(priv->device, priv->rx_skbuff_dma[i])) {
+ if (dma_mapping_error(priv->device, rx_q->rx_skbuff_dma[i])) {
netdev_err(priv->dev, "%s: DMA mapping error\n", __func__);
dev_kfree_skb_any(skb);
return -EINVAL;
}
if (priv->synopsys_id >= DWMAC_CORE_4_00)
- p->des0 = cpu_to_le32(priv->rx_skbuff_dma[i]);
+ p->des0 = cpu_to_le32(rx_q->rx_skbuff_dma[i]);
else
- p->des2 = cpu_to_le32(priv->rx_skbuff_dma[i]);
+ p->des2 = cpu_to_le32(rx_q->rx_skbuff_dma[i]);
if ((priv->hw->mode->init_desc3) &&
(priv->dma_buf_sz == BUF_SIZE_16KiB))
@@ -985,14 +1145,209 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
return 0;
}
-static void stmmac_free_rx_buffers(struct stmmac_priv *priv, int i)
+/**
+ * stmmac_free_rx_buffer - free RX dma buffers
+ * @priv: private structure
+ * @queue: RX queue index
+ * @i: buffer index.
+ */
+static void stmmac_free_rx_buffer(struct stmmac_priv *priv, u32 queue, int i)
{
- if (priv->rx_skbuff[i]) {
- dma_unmap_single(priv->device, priv->rx_skbuff_dma[i],
+ struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+ if (rx_q->rx_skbuff[i]) {
+ dma_unmap_single(priv->device, rx_q->rx_skbuff_dma[i],
priv->dma_buf_sz, DMA_FROM_DEVICE);
- dev_kfree_skb_any(priv->rx_skbuff[i]);
+ dev_kfree_skb_any(rx_q->rx_skbuff[i]);
}
- priv->rx_skbuff[i] = NULL;
+ rx_q->rx_skbuff[i] = NULL;
+}
+
+/**
+ * stmmac_free_tx_buffer - free RX dma buffers
+ * @priv: private structure
+ * @queue: RX queue index
+ * @i: buffer index.
+ */
+static void stmmac_free_tx_buffer(struct stmmac_priv *priv, u32 queue, int i)
+{
+ struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+ if (tx_q->tx_skbuff_dma[i].buf) {
+ if (tx_q->tx_skbuff_dma[i].map_as_page)
+ dma_unmap_page(priv->device,
+ tx_q->tx_skbuff_dma[i].buf,
+ tx_q->tx_skbuff_dma[i].len,
+ DMA_TO_DEVICE);
+ else
+ dma_unmap_single(priv->device,
+ tx_q->tx_skbuff_dma[i].buf,
+ tx_q->tx_skbuff_dma[i].len,
+ DMA_TO_DEVICE);
+ }
+
+ if (tx_q->tx_skbuff[i]) {
+ dev_kfree_skb_any(tx_q->tx_skbuff[i]);
+ tx_q->tx_skbuff[i] = NULL;
+ tx_q->tx_skbuff_dma[i].buf = 0;
+ tx_q->tx_skbuff_dma[i].map_as_page = false;
+ }
+}
+
+/**
+ * init_dma_rx_desc_rings - init the RX descriptor rings
+ * @dev: net device structure
+ * @flags: gfp flag.
+ * Description: this function initializes the DMA RX descriptors
+ * and allocates the socket buffers. It supports the chained and ring
+ * modes.
+ */
+static int init_dma_rx_desc_rings(struct net_device *dev, gfp_t flags)
+{
+ struct stmmac_priv *priv = netdev_priv(dev);
+ u32 rx_count = priv->plat->rx_queues_to_use;
+ unsigned int bfsize = 0;
+ int ret = -ENOMEM;
+ u32 queue;
+ int i;
+
+ if (priv->hw->mode->set_16kib_bfsize)
+ bfsize = priv->hw->mode->set_16kib_bfsize(dev->mtu);
+
+ if (bfsize < BUF_SIZE_16KiB)
+ bfsize = stmmac_set_bfsize(dev->mtu, priv->dma_buf_sz);
+
+ priv->dma_buf_sz = bfsize;
+
+ /* RX INITIALIZATION */
+ netif_dbg(priv, probe, priv->dev,
+ "SKB addresses:\nskb\t\tskb data\tdma data\n");
+
+ for (queue = 0; queue < rx_count; queue++) {
+ struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+ netif_dbg(priv, probe, priv->dev,
+ "(%s) dma_rx_phy=0x%08x\n", __func__,
+ (u32)rx_q->dma_rx_phy);
+
+ for (i = 0; i < DMA_RX_SIZE; i++) {
+ struct dma_desc *p;
+
+ if (priv->extend_desc)
+ p = &((rx_q->dma_erx + i)->basic);
+ else
+ p = rx_q->dma_rx + i;
+
+ ret = stmmac_init_rx_buffers(priv, p, i, flags,
+ queue);
+ if (ret)
+ goto err_init_rx_buffers;
+
+ netif_dbg(priv, probe, priv->dev, "[%p]\t[%p]\t[%x]\n",
+ rx_q->rx_skbuff[i], rx_q->rx_skbuff[i]->data,
+ (unsigned int)rx_q->rx_skbuff_dma[i]);
+ }
+
+ rx_q->cur_rx = 0;
+ rx_q->dirty_rx = (unsigned int)(i - DMA_RX_SIZE);
+
+ stmmac_clear_rx_descriptors(priv, queue);
+
+ /* Setup the chained descriptor addresses */
+ if (priv->mode == STMMAC_CHAIN_MODE) {
+ if (priv->extend_desc)
+ priv->hw->mode->init(rx_q->dma_erx,
+ rx_q->dma_rx_phy,
+ DMA_RX_SIZE, 1);
+ else
+ priv->hw->mode->init(rx_q->dma_rx,
+ rx_q->dma_rx_phy,
+ DMA_RX_SIZE, 0);
+ }
+ }
+
+ buf_sz = bfsize;
+
+ return 0;
+
+err_init_rx_buffers:
+ while (queue >= 0) {
+ while (--i >= 0)
+ stmmac_free_rx_buffer(priv, queue, i);
+
+ if (queue == 0)
+ break;
+
+ i = DMA_RX_SIZE;
+ queue--;
+ }
+
+ return ret;
+}
+
+/**
+ * init_dma_tx_desc_rings - init the TX descriptor rings
+ * @dev: net device structure.
+ * Description: this function initializes the DMA TX descriptors
+ * and allocates the socket buffers. It supports the chained and ring
+ * modes.
+ */
+static int init_dma_tx_desc_rings(struct net_device *dev)
+{
+ struct stmmac_priv *priv = netdev_priv(dev);
+ u32 tx_queue_cnt = priv->plat->tx_queues_to_use;
+ u32 queue;
+ int i;
+
+ for (queue = 0; queue < tx_queue_cnt; queue++) {
+ struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+ netif_dbg(priv, probe, priv->dev,
+ "(%s) dma_tx_phy=0x%08x\n", __func__,
+ (u32)tx_q->dma_tx_phy);
+
+ /* Setup the chained descriptor addresses */
+ if (priv->mode == STMMAC_CHAIN_MODE) {
+ if (priv->extend_desc)
+ priv->hw->mode->init(tx_q->dma_etx,
+ tx_q->dma_tx_phy,
+ DMA_TX_SIZE, 1);
+ else
+ priv->hw->mode->init(tx_q->dma_tx,
+ tx_q->dma_tx_phy,
+ DMA_TX_SIZE, 0);
+ }
+
+ for (i = 0; i < DMA_TX_SIZE; i++) {
+ struct dma_desc *p;
+ if (priv->extend_desc)
+ p = &((tx_q->dma_etx + i)->basic);
+ else
+ p = tx_q->dma_tx + i;
+
+ if (priv->synopsys_id >= DWMAC_CORE_4_00) {
+ p->des0 = 0;
+ p->des1 = 0;
+ p->des2 = 0;
+ p->des3 = 0;
+ } else {
+ p->des2 = 0;
+ }
+
+ tx_q->tx_skbuff_dma[i].buf = 0;
+ tx_q->tx_skbuff_dma[i].map_as_page = false;
+ tx_q->tx_skbuff_dma[i].len = 0;
+ tx_q->tx_skbuff_dma[i].last_segment = false;
+ tx_q->tx_skbuff[i] = NULL;
+ }
+
+ tx_q->dirty_tx = 0;
+ tx_q->cur_tx = 0;
+
+ netdev_tx_reset_queue(netdev_get_tx_queue(priv->dev, queue));
+ }
+
+ return 0;
}
/**
@@ -1005,134 +1360,234 @@ static void stmmac_free_rx_buffers(struct stmmac_priv *priv, int i)
*/
static int init_dma_desc_rings(struct net_device *dev, gfp_t flags)
{
- int i;
struct stmmac_priv *priv = netdev_priv(dev);
- unsigned int bfsize = 0;
- int ret = -ENOMEM;
+ int ret;
- if (priv->hw->mode->set_16kib_bfsize)
- bfsize = priv->hw->mode->set_16kib_bfsize(dev->mtu);
+ ret = init_dma_rx_desc_rings(dev, flags);
+ if (ret)
+ return ret;
- if (bfsize < BUF_SIZE_16KiB)
- bfsize = stmmac_set_bfsize(dev->mtu, priv->dma_buf_sz);
-
- priv->dma_buf_sz = bfsize;
-
- netif_dbg(priv, probe, priv->dev,
- "(%s) dma_rx_phy=0x%08x dma_tx_phy=0x%08x\n",
- __func__, (u32)priv->dma_rx_phy, (u32)priv->dma_tx_phy);
-
- /* RX INITIALIZATION */
- netif_dbg(priv, probe, priv->dev,
- "SKB addresses:\nskb\t\tskb data\tdma data\n");
-
- for (i = 0; i < DMA_RX_SIZE; i++) {
- struct dma_desc *p;
- if (priv->extend_desc)
- p = &((priv->dma_erx + i)->basic);
- else
- p = priv->dma_rx + i;
-
- ret = stmmac_init_rx_buffers(priv, p, i, flags);
- if (ret)
- goto err_init_rx_buffers;
-
- netif_dbg(priv, probe, priv->dev, "[%p]\t[%p]\t[%x]\n",
- priv->rx_skbuff[i], priv->rx_skbuff[i]->data,
- (unsigned int)priv->rx_skbuff_dma[i]);
- }
- priv->cur_rx = 0;
- priv->dirty_rx = (unsigned int)(i - DMA_RX_SIZE);
- buf_sz = bfsize;
-
- /* Setup the chained descriptor addresses */
- if (priv->mode == STMMAC_CHAIN_MODE) {
- if (priv->extend_desc) {
- priv->hw->mode->init(priv->dma_erx, priv->dma_rx_phy,
- DMA_RX_SIZE, 1);
- priv->hw->mode->init(priv->dma_etx, priv->dma_tx_phy,
- DMA_TX_SIZE, 1);
- } else {
- priv->hw->mode->init(priv->dma_rx, priv->dma_rx_phy,
- DMA_RX_SIZE, 0);
- priv->hw->mode->init(priv->dma_tx, priv->dma_tx_phy,
- DMA_TX_SIZE, 0);
- }
- }
-
- /* TX INITIALIZATION */
- for (i = 0; i < DMA_TX_SIZE; i++) {
- struct dma_desc *p;
- if (priv->extend_desc)
- p = &((priv->dma_etx + i)->basic);
- else
- p = priv->dma_tx + i;
-
- if (priv->synopsys_id >= DWMAC_CORE_4_00) {
- p->des0 = 0;
- p->des1 = 0;
- p->des2 = 0;
- p->des3 = 0;
- } else {
- p->des2 = 0;
- }
-
- priv->tx_skbuff_dma[i].buf = 0;
- priv->tx_skbuff_dma[i].map_as_page = false;
- priv->tx_skbuff_dma[i].len = 0;
- priv->tx_skbuff_dma[i].last_segment = false;
- priv->tx_skbuff[i] = NULL;
- }
-
- priv->dirty_tx = 0;
- priv->cur_tx = 0;
- netdev_reset_queue(priv->dev);
+ ret = init_dma_tx_desc_rings(dev);
stmmac_clear_descriptors(priv);
if (netif_msg_hw(priv))
stmmac_display_rings(priv);
- return 0;
-err_init_rx_buffers:
- while (--i >= 0)
- stmmac_free_rx_buffers(priv, i);
return ret;
}
-static void dma_free_rx_skbufs(struct stmmac_priv *priv)
+/**
+ * dma_free_rx_skbufs - free RX dma buffers
+ * @priv: private structure
+ * @queue: RX queue index
+ */
+static void dma_free_rx_skbufs(struct stmmac_priv *priv, u32 queue)
{
int i;
for (i = 0; i < DMA_RX_SIZE; i++)
- stmmac_free_rx_buffers(priv, i);
+ stmmac_free_rx_buffer(priv, queue, i);
}
-static void dma_free_tx_skbufs(struct stmmac_priv *priv)
+/**
+ * dma_free_tx_skbufs - free TX dma buffers
+ * @priv: private structure
+ * @queue: TX queue index
+ */
+static void dma_free_tx_skbufs(struct stmmac_priv *priv, u32 queue)
{
int i;
- for (i = 0; i < DMA_TX_SIZE; i++) {
- if (priv->tx_skbuff_dma[i].buf) {
- if (priv->tx_skbuff_dma[i].map_as_page)
- dma_unmap_page(priv->device,
- priv->tx_skbuff_dma[i].buf,
- priv->tx_skbuff_dma[i].len,
- DMA_TO_DEVICE);
- else
- dma_unmap_single(priv->device,
- priv->tx_skbuff_dma[i].buf,
- priv->tx_skbuff_dma[i].len,
- DMA_TO_DEVICE);
- }
+ for (i = 0; i < DMA_TX_SIZE; i++)
+ stmmac_free_tx_buffer(priv, queue, i);
+}
- if (priv->tx_skbuff[i]) {
- dev_kfree_skb_any(priv->tx_skbuff[i]);
- priv->tx_skbuff[i] = NULL;
- priv->tx_skbuff_dma[i].buf = 0;
- priv->tx_skbuff_dma[i].map_as_page = false;
+/**
+ * free_dma_rx_desc_resources - free RX dma desc resources
+ * @priv: private structure
+ */
+static void free_dma_rx_desc_resources(struct stmmac_priv *priv)
+{
+ u32 rx_count = priv->plat->rx_queues_to_use;
+ u32 queue;
+
+ /* Free RX queue resources */
+ for (queue = 0; queue < rx_count; queue++) {
+ struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+ /* Release the DMA RX socket buffers */
+ dma_free_rx_skbufs(priv, queue);
+
+ /* Free DMA regions of consistent memory previously allocated */
+ if (!priv->extend_desc)
+ dma_free_coherent(priv->device,
+ DMA_RX_SIZE * sizeof(struct dma_desc),
+ rx_q->dma_rx, rx_q->dma_rx_phy);
+ else
+ dma_free_coherent(priv->device, DMA_RX_SIZE *
+ sizeof(struct dma_extended_desc),
+ rx_q->dma_erx, rx_q->dma_rx_phy);
+
+ kfree(rx_q->rx_skbuff_dma);
+ kfree(rx_q->rx_skbuff);
+ }
+}
+
+/**
+ * free_dma_tx_desc_resources - free TX dma desc resources
+ * @priv: private structure
+ */
+static void free_dma_tx_desc_resources(struct stmmac_priv *priv)
+{
+ u32 tx_count = priv->plat->tx_queues_to_use;
+ u32 queue = 0;
+
+ /* Free TX queue resources */
+ for (queue = 0; queue < tx_count; queue++) {
+ struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+ /* Release the DMA TX socket buffers */
+ dma_free_tx_skbufs(priv, queue);
+
+ /* Free DMA regions of consistent memory previously allocated */
+ if (!priv->extend_desc)
+ dma_free_coherent(priv->device,
+ DMA_TX_SIZE * sizeof(struct dma_desc),
+ tx_q->dma_tx, tx_q->dma_tx_phy);
+ else
+ dma_free_coherent(priv->device, DMA_TX_SIZE *
+ sizeof(struct dma_extended_desc),
+ tx_q->dma_etx, tx_q->dma_tx_phy);
+
+ kfree(tx_q->tx_skbuff_dma);
+ kfree(tx_q->tx_skbuff);
+ }
+}
+
+/**
+ * alloc_dma_rx_desc_resources - alloc RX resources.
+ * @priv: private structure
+ * Description: according to which descriptor can be used (extend or basic)
+ * this function allocates the resources for TX and RX paths. In case of
+ * reception, for example, it pre-allocated the RX socket buffer in order to
+ * allow zero-copy mechanism.
+ */
+static int alloc_dma_rx_desc_resources(struct stmmac_priv *priv)
+{
+ u32 rx_count = priv->plat->rx_queues_to_use;
+ int ret = -ENOMEM;
+ u32 queue;
+
+ /* RX queues buffers and DMA */
+ for (queue = 0; queue < rx_count; queue++) {
+ struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+ rx_q->queue_index = queue;
+ rx_q->priv_data = priv;
+
+ rx_q->rx_skbuff_dma = kmalloc_array(DMA_RX_SIZE,
+ sizeof(dma_addr_t),
+ GFP_KERNEL);
+ if (!rx_q->rx_skbuff_dma)
+ return -ENOMEM;
+
+ rx_q->rx_skbuff = kmalloc_array(DMA_RX_SIZE,
+ sizeof(struct sk_buff *),
+ GFP_KERNEL);
+ if (!rx_q->rx_skbuff)
+ goto err_dma;
+
+ if (priv->extend_desc) {
+ rx_q->dma_erx = dma_zalloc_coherent(priv->device,
+ DMA_RX_SIZE *
+ sizeof(struct
+ dma_extended_desc),
+ &rx_q->dma_rx_phy,
+ GFP_KERNEL);
+ if (!rx_q->dma_erx)
+ goto err_dma;
+
+ } else {
+ rx_q->dma_rx = dma_zalloc_coherent(priv->device,
+ DMA_RX_SIZE *
+ sizeof(struct
+ dma_desc),
+ &rx_q->dma_rx_phy,
+ GFP_KERNEL);
+ if (!rx_q->dma_rx)
+ goto err_dma;
}
}
+
+ return 0;
+
+err_dma:
+ free_dma_rx_desc_resources(priv);
+
+ return ret;
+}
+
+/**
+ * alloc_dma_tx_desc_resources - alloc TX resources.
+ * @priv: private structure
+ * Description: according to which descriptor can be used (extend or basic)
+ * this function allocates the resources for TX and RX paths. In case of
+ * reception, for example, it pre-allocated the RX socket buffer in order to
+ * allow zero-copy mechanism.
+ */
+static int alloc_dma_tx_desc_resources(struct stmmac_priv *priv)
+{
+ u32 tx_count = priv->plat->tx_queues_to_use;
+ int ret = -ENOMEM;
+ u32 queue;
+
+ /* TX queues buffers and DMA */
+ for (queue = 0; queue < tx_count; queue++) {
+ struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+ tx_q->queue_index = queue;
+ tx_q->priv_data = priv;
+
+ tx_q->tx_skbuff_dma = kmalloc_array(DMA_TX_SIZE,
+ sizeof(*tx_q->tx_skbuff_dma),
+ GFP_KERNEL);
+ if (!tx_q->tx_skbuff_dma)
+ return -ENOMEM;
+
+ tx_q->tx_skbuff = kmalloc_array(DMA_TX_SIZE,
+ sizeof(struct sk_buff *),
+ GFP_KERNEL);
+ if (!tx_q->tx_skbuff)
+ goto err_dma_buffers;
+
+ if (priv->extend_desc) {
+ tx_q->dma_etx = dma_zalloc_coherent(priv->device,
+ DMA_TX_SIZE *
+ sizeof(struct
+ dma_extended_desc),
+ &tx_q->dma_tx_phy,
+ GFP_KERNEL);
+ if (!tx_q->dma_etx)
+ goto err_dma_buffers;
+ } else {
+ tx_q->dma_tx = dma_zalloc_coherent(priv->device,
+ DMA_TX_SIZE *
+ sizeof(struct
+ dma_desc),
+ &tx_q->dma_tx_phy,
+ GFP_KERNEL);
+ if (!tx_q->dma_tx)
+ goto err_dma_buffers;
+ }
+ }
+
+ return 0;
+
+err_dma_buffers:
+ free_dma_tx_desc_resources(priv);
+
+ return ret;
}
/**
@@ -1145,108 +1600,28 @@ static void dma_free_tx_skbufs(struct stmmac_priv *priv)
*/
static int alloc_dma_desc_resources(struct stmmac_priv *priv)
{
- int ret = -ENOMEM;
+ /* RX Allocation */
+ int ret = alloc_dma_rx_desc_resources(priv);
- priv->rx_skbuff_dma = kmalloc_array(DMA_RX_SIZE, sizeof(dma_addr_t),
- GFP_KERNEL);
- if (!priv->rx_skbuff_dma)
- return -ENOMEM;
+ if (ret)
+ return ret;
- priv->rx_skbuff = kmalloc_array(DMA_RX_SIZE, sizeof(struct sk_buff *),
- GFP_KERNEL);
- if (!priv->rx_skbuff)
- goto err_rx_skbuff;
+ ret = alloc_dma_tx_desc_resources(priv);
- priv->tx_skbuff_dma = kmalloc_array(DMA_TX_SIZE,
- sizeof(*priv->tx_skbuff_dma),
- GFP_KERNEL);
- if (!priv->tx_skbuff_dma)
- goto err_tx_skbuff_dma;
-
- priv->tx_skbuff = kmalloc_array(DMA_TX_SIZE, sizeof(struct sk_buff *),
- GFP_KERNEL);
- if (!priv->tx_skbuff)
- goto err_tx_skbuff;
-
- if (priv->extend_desc) {
- priv->dma_erx = dma_zalloc_coherent(priv->device, DMA_RX_SIZE *
- sizeof(struct
- dma_extended_desc),
- &priv->dma_rx_phy,
- GFP_KERNEL);
- if (!priv->dma_erx)
- goto err_dma;
-
- priv->dma_etx = dma_zalloc_coherent(priv->device, DMA_TX_SIZE *
- sizeof(struct
- dma_extended_desc),
- &priv->dma_tx_phy,
- GFP_KERNEL);
- if (!priv->dma_etx) {
- dma_free_coherent(priv->device, DMA_RX_SIZE *
- sizeof(struct dma_extended_desc),
- priv->dma_erx, priv->dma_rx_phy);
- goto err_dma;
- }
- } else {
- priv->dma_rx = dma_zalloc_coherent(priv->device, DMA_RX_SIZE *
- sizeof(struct dma_desc),
- &priv->dma_rx_phy,
- GFP_KERNEL);
- if (!priv->dma_rx)
- goto err_dma;
-
- priv->dma_tx = dma_zalloc_coherent(priv->device, DMA_TX_SIZE *
- sizeof(struct dma_desc),
- &priv->dma_tx_phy,
- GFP_KERNEL);
- if (!priv->dma_tx) {
- dma_free_coherent(priv->device, DMA_RX_SIZE *
- sizeof(struct dma_desc),
- priv->dma_rx, priv->dma_rx_phy);
- goto err_dma;
- }
- }
-
- return 0;
-
-err_dma:
- kfree(priv->tx_skbuff);
-err_tx_skbuff:
- kfree(priv->tx_skbuff_dma);
-err_tx_skbuff_dma:
- kfree(priv->rx_skbuff);
-err_rx_skbuff:
- kfree(priv->rx_skbuff_dma);
return ret;
}
+/**
+ * free_dma_desc_resources - free dma desc resources
+ * @priv: private structure
+ */
static void free_dma_desc_resources(struct stmmac_priv *priv)
{
- /* Release the DMA TX/RX socket buffers */
- dma_free_rx_skbufs(priv);
- dma_free_tx_skbufs(priv);
+ /* Release the DMA RX socket buffers */
+ free_dma_rx_desc_resources(priv);
- /* Free DMA regions of consistent memory previously allocated */
- if (!priv->extend_desc) {
- dma_free_coherent(priv->device,
- DMA_TX_SIZE * sizeof(struct dma_desc),
- priv->dma_tx, priv->dma_tx_phy);
- dma_free_coherent(priv->device,
- DMA_RX_SIZE * sizeof(struct dma_desc),
- priv->dma_rx, priv->dma_rx_phy);
- } else {
- dma_free_coherent(priv->device, DMA_TX_SIZE *
- sizeof(struct dma_extended_desc),
- priv->dma_etx, priv->dma_tx_phy);
- dma_free_coherent(priv->device, DMA_RX_SIZE *
- sizeof(struct dma_extended_desc),
- priv->dma_erx, priv->dma_rx_phy);
- }
- kfree(priv->rx_skbuff_dma);
- kfree(priv->rx_skbuff);
- kfree(priv->tx_skbuff_dma);
- kfree(priv->tx_skbuff);
+ /* Release the DMA TX socket buffers */
+ free_dma_tx_desc_resources(priv);
}
/**
@@ -1256,19 +1631,104 @@ static void free_dma_desc_resources(struct stmmac_priv *priv)
*/
static void stmmac_mac_enable_rx_queues(struct stmmac_priv *priv)
{
- int rx_count = priv->dma_cap.number_rx_queues;
- int queue = 0;
+ u32 rx_queues_count = priv->plat->rx_queues_to_use;
+ int queue;
+ u8 mode;
- /* If GMAC does not have multiple queues, then this is not necessary*/
- if (rx_count == 1)
- return;
+ for (queue = 0; queue < rx_queues_count; queue++) {
+ mode = priv->plat->rx_queues_cfg[queue].mode_to_use;
+ priv->hw->mac->rx_queue_enable(priv->hw, mode, queue);
+ }
+}
- /**
- * If the core is synthesized with multiple rx queues / multiple
- * dma channels, then rx queues will be disabled by default.
- * For now only rx queue 0 is enabled.
- */
- priv->hw->mac->rx_queue_enable(priv->hw, queue);
+/**
+ * stmmac_start_rx_dma - start RX DMA channel
+ * @priv: driver private structure
+ * @chan: RX channel index
+ * Description:
+ * This starts a RX DMA channel
+ */
+static void stmmac_start_rx_dma(struct stmmac_priv *priv, u32 chan)
+{
+ netdev_dbg(priv->dev, "DMA RX processes started in channel %d\n", chan);
+ priv->hw->dma->start_rx(priv->ioaddr, chan);
+}
+
+/**
+ * stmmac_start_tx_dma - start TX DMA channel
+ * @priv: driver private structure
+ * @chan: TX channel index
+ * Description:
+ * This starts a TX DMA channel
+ */
+static void stmmac_start_tx_dma(struct stmmac_priv *priv, u32 chan)
+{
+ netdev_dbg(priv->dev, "DMA TX processes started in channel %d\n", chan);
+ priv->hw->dma->start_tx(priv->ioaddr, chan);
+}
+
+/**
+ * stmmac_stop_rx_dma - stop RX DMA channel
+ * @priv: driver private structure
+ * @chan: RX channel index
+ * Description:
+ * This stops a RX DMA channel
+ */
+static void stmmac_stop_rx_dma(struct stmmac_priv *priv, u32 chan)
+{
+ netdev_dbg(priv->dev, "DMA RX processes stopped in channel %d\n", chan);
+ priv->hw->dma->stop_rx(priv->ioaddr, chan);
+}
+
+/**
+ * stmmac_stop_tx_dma - stop TX DMA channel
+ * @priv: driver private structure
+ * @chan: TX channel index
+ * Description:
+ * This stops a TX DMA channel
+ */
+static void stmmac_stop_tx_dma(struct stmmac_priv *priv, u32 chan)
+{
+ netdev_dbg(priv->dev, "DMA TX processes stopped in channel %d\n", chan);
+ priv->hw->dma->stop_tx(priv->ioaddr, chan);
+}
+
+/**
+ * stmmac_start_all_dma - start all RX and TX DMA channels
+ * @priv: driver private structure
+ * Description:
+ * This starts all the RX and TX DMA channels
+ */
+static void stmmac_start_all_dma(struct stmmac_priv *priv)
+{
+ u32 rx_channels_count = priv->plat->rx_queues_to_use;
+ u32 tx_channels_count = priv->plat->tx_queues_to_use;
+ u32 chan = 0;
+
+ for (chan = 0; chan < rx_channels_count; chan++)
+ stmmac_start_rx_dma(priv, chan);
+
+ for (chan = 0; chan < tx_channels_count; chan++)
+ stmmac_start_tx_dma(priv, chan);
+}
+
+/**
+ * stmmac_stop_all_dma - stop all RX and TX DMA channels
+ * @priv: driver private structure
+ * Description:
+ * This stops the RX and TX DMA channels
+ */
+static void stmmac_stop_all_dma(struct stmmac_priv *priv)
+{
+ u32 rx_channels_count = priv->plat->rx_queues_to_use;
+ u32 tx_channels_count = priv->plat->tx_queues_to_use;
+ u32 chan = 0;
+
+ for (chan = 0; chan < rx_channels_count; chan++)
+ stmmac_stop_rx_dma(priv, chan);
+
+ for (chan = 0; chan < tx_channels_count; chan++)
+ stmmac_stop_tx_dma(priv, chan);
}
/**
@@ -1279,11 +1739,20 @@ static void stmmac_mac_enable_rx_queues(struct stmmac_priv *priv)
*/
static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
{
+ u32 rx_channels_count = priv->plat->rx_queues_to_use;
+ u32 tx_channels_count = priv->plat->tx_queues_to_use;
int rxfifosz = priv->plat->rx_fifo_size;
+ u32 txmode = 0;
+ u32 rxmode = 0;
+ u32 chan = 0;
- if (priv->plat->force_thresh_dma_mode)
- priv->hw->dma->dma_mode(priv->ioaddr, tc, tc, rxfifosz);
- else if (priv->plat->force_sf_dma_mode || priv->plat->tx_coe) {
+ if (rxfifosz == 0)
+ rxfifosz = priv->dma_cap.rx_fifo_size;
+
+ if (priv->plat->force_thresh_dma_mode) {
+ txmode = tc;
+ rxmode = tc;
+ } else if (priv->plat->force_sf_dma_mode || priv->plat->tx_coe) {
/*
* In case of GMAC, SF mode can be enabled
* to perform the TX COE in HW. This depends on:
@@ -1291,37 +1760,53 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
* 2) There is no bugged Jumbo frame support
* that needs to not insert csum in the TDES.
*/
- priv->hw->dma->dma_mode(priv->ioaddr, SF_DMA_MODE, SF_DMA_MODE,
- rxfifosz);
+ txmode = SF_DMA_MODE;
+ rxmode = SF_DMA_MODE;
priv->xstats.threshold = SF_DMA_MODE;
- } else
- priv->hw->dma->dma_mode(priv->ioaddr, tc, SF_DMA_MODE,
+ } else {
+ txmode = tc;
+ rxmode = SF_DMA_MODE;
+ }
+
+ /* configure all channels */
+ if (priv->synopsys_id >= DWMAC_CORE_4_00) {
+ for (chan = 0; chan < rx_channels_count; chan++)
+ priv->hw->dma->dma_rx_mode(priv->ioaddr, rxmode, chan,
+ rxfifosz);
+
+ for (chan = 0; chan < tx_channels_count; chan++)
+ priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan);
+ } else {
+ priv->hw->dma->dma_mode(priv->ioaddr, txmode, rxmode,
rxfifosz);
+ }
}
/**
* stmmac_tx_clean - to manage the transmission completion
* @priv: driver private structure
+ * @queue: TX queue index
* Description: it reclaims the transmit resources after transmission completes.
*/
-static void stmmac_tx_clean(struct stmmac_priv *priv)
+static void stmmac_tx_clean(struct stmmac_priv *priv, u32 queue)
{
+ struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
unsigned int bytes_compl = 0, pkts_compl = 0;
- unsigned int entry = priv->dirty_tx;
+ unsigned int entry = tx_q->dirty_tx;
netif_tx_lock(priv->dev);
priv->xstats.tx_clean++;
- while (entry != priv->cur_tx) {
- struct sk_buff *skb = priv->tx_skbuff[entry];
+ while (entry != tx_q->cur_tx) {
+ struct sk_buff *skb = tx_q->tx_skbuff[entry];
struct dma_desc *p;
int status;
if (priv->extend_desc)
- p = (struct dma_desc *)(priv->dma_etx + entry);
+ p = (struct dma_desc *)(tx_q->dma_etx + entry);
else
- p = priv->dma_tx + entry;
+ p = tx_q->dma_tx + entry;
status = priv->hw->desc->tx_status(&priv->dev->stats,
&priv->xstats, p,
@@ -1342,48 +1827,51 @@ static void stmmac_tx_clean(struct stmmac_priv *priv)
stmmac_get_tx_hwtstamp(priv, p, skb);
}
- if (likely(priv->tx_skbuff_dma[entry].buf)) {
- if (priv->tx_skbuff_dma[entry].map_as_page)
+ if (likely(tx_q->tx_skbuff_dma[entry].buf)) {
+ if (tx_q->tx_skbuff_dma[entry].map_as_page)
dma_unmap_page(priv->device,
- priv->tx_skbuff_dma[entry].buf,
- priv->tx_skbuff_dma[entry].len,
+ tx_q->tx_skbuff_dma[entry].buf,
+ tx_q->tx_skbuff_dma[entry].len,
DMA_TO_DEVICE);
else
dma_unmap_single(priv->device,
- priv->tx_skbuff_dma[entry].buf,
- priv->tx_skbuff_dma[entry].len,
+ tx_q->tx_skbuff_dma[entry].buf,
+ tx_q->tx_skbuff_dma[entry].len,
DMA_TO_DEVICE);
- priv->tx_skbuff_dma[entry].buf = 0;
- priv->tx_skbuff_dma[entry].len = 0;
- priv->tx_skbuff_dma[entry].map_as_page = false;
+ tx_q->tx_skbuff_dma[entry].buf = 0;
+ tx_q->tx_skbuff_dma[entry].len = 0;
+ tx_q->tx_skbuff_dma[entry].map_as_page = false;
}
if (priv->hw->mode->clean_desc3)
- priv->hw->mode->clean_desc3(priv, p);
+ priv->hw->mode->clean_desc3(tx_q, p);
- priv->tx_skbuff_dma[entry].last_segment = false;
- priv->tx_skbuff_dma[entry].is_jumbo = false;
+ tx_q->tx_skbuff_dma[entry].last_segment = false;
+ tx_q->tx_skbuff_dma[entry].is_jumbo = false;
if (likely(skb != NULL)) {
pkts_compl++;
bytes_compl += skb->len;
dev_consume_skb_any(skb);
- priv->tx_skbuff[entry] = NULL;
+ tx_q->tx_skbuff[entry] = NULL;
}
priv->hw->desc->release_tx_desc(p, priv->mode);
entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE);
}
- priv->dirty_tx = entry;
+ tx_q->dirty_tx = entry;
- netdev_completed_queue(priv->dev, pkts_compl, bytes_compl);
+ netdev_tx_completed_queue(netdev_get_tx_queue(priv->dev, queue),
+ pkts_compl, bytes_compl);
- if (unlikely(netif_queue_stopped(priv->dev) &&
- stmmac_tx_avail(priv) > STMMAC_TX_THRESH)) {
+ if (unlikely(netif_tx_queue_stopped(netdev_get_tx_queue(priv->dev,
+ queue))) &&
+ stmmac_tx_avail(priv, queue) > STMMAC_TX_THRESH) {
+
netif_dbg(priv, tx_done, priv->dev,
"%s: restart transmit\n", __func__);
- netif_wake_queue(priv->dev);
+ netif_tx_wake_queue(netdev_get_tx_queue(priv->dev, queue));
}
if ((priv->eee_enabled) && (!priv->tx_path_in_lpi_mode)) {
@@ -1393,45 +1881,76 @@ static void stmmac_tx_clean(struct stmmac_priv *priv)
netif_tx_unlock(priv->dev);
}
-static inline void stmmac_enable_dma_irq(struct stmmac_priv *priv)
+static inline void stmmac_enable_dma_irq(struct stmmac_priv *priv, u32 chan)
{
- priv->hw->dma->enable_dma_irq(priv->ioaddr);
+ priv->hw->dma->enable_dma_irq(priv->ioaddr, chan);
}
-static inline void stmmac_disable_dma_irq(struct stmmac_priv *priv)
+static inline void stmmac_disable_dma_irq(struct stmmac_priv *priv, u32 chan)
{
- priv->hw->dma->disable_dma_irq(priv->ioaddr);
+ priv->hw->dma->disable_dma_irq(priv->ioaddr, chan);
}
/**
* stmmac_tx_err - to manage the tx error
* @priv: driver private structure
+ * @chan: channel index
* Description: it cleans the descriptors and restarts the transmission
* in case of transmission errors.
*/
-static void stmmac_tx_err(struct stmmac_priv *priv)
+static void stmmac_tx_err(struct stmmac_priv *priv, u32 chan)
{
+ struct stmmac_tx_queue *tx_q = &priv->tx_queue[chan];
int i;
- netif_stop_queue(priv->dev);
- priv->hw->dma->stop_tx(priv->ioaddr);
- dma_free_tx_skbufs(priv);
+ netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, chan));
+
+ stmmac_stop_tx_dma(priv, chan);
+ dma_free_tx_skbufs(priv, chan);
for (i = 0; i < DMA_TX_SIZE; i++)
if (priv->extend_desc)
- priv->hw->desc->init_tx_desc(&priv->dma_etx[i].basic,
+ priv->hw->desc->init_tx_desc(&tx_q->dma_etx[i].basic,
priv->mode,
(i == DMA_TX_SIZE - 1));
else
- priv->hw->desc->init_tx_desc(&priv->dma_tx[i],
+ priv->hw->desc->init_tx_desc(&tx_q->dma_tx[i],
priv->mode,
(i == DMA_TX_SIZE - 1));
- priv->dirty_tx = 0;
- priv->cur_tx = 0;
- netdev_reset_queue(priv->dev);
- priv->hw->dma->start_tx(priv->ioaddr);
+ tx_q->dirty_tx = 0;
+ tx_q->cur_tx = 0;
+ netdev_tx_reset_queue(netdev_get_tx_queue(priv->dev, chan));
+ stmmac_start_tx_dma(priv, chan);
priv->dev->stats.tx_errors++;
- netif_wake_queue(priv->dev);
+ netif_tx_wake_queue(netdev_get_tx_queue(priv->dev, chan));
+}
+
+/**
+ * stmmac_set_dma_operation_mode - Set DMA operation mode by channel
+ * @priv: driver private structure
+ * @txmode: TX operating mode
+ * @rxmode: RX operating mode
+ * @chan: channel index
+ * Description: it is used for configuring of the DMA operation mode in
+ * runtime in order to program the tx/rx DMA thresholds or Store-And-Forward
+ * mode.
+ */
+static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode,
+ u32 rxmode, u32 chan)
+{
+ int rxfifosz = priv->plat->rx_fifo_size;
+
+ if (rxfifosz == 0)
+ rxfifosz = priv->dma_cap.rx_fifo_size;
+
+ if (priv->synopsys_id >= DWMAC_CORE_4_00) {
+ priv->hw->dma->dma_rx_mode(priv->ioaddr, rxmode, chan,
+ rxfifosz);
+ priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan);
+ } else {
+ priv->hw->dma->dma_mode(priv->ioaddr, txmode, rxmode,
+ rxfifosz);
+ }
}
/**
@@ -1443,31 +1962,43 @@ static void stmmac_tx_err(struct stmmac_priv *priv)
*/
static void stmmac_dma_interrupt(struct stmmac_priv *priv)
{
+ u32 tx_channel_count = priv->plat->tx_queues_to_use;
int status;
- int rxfifosz = priv->plat->rx_fifo_size;
+ u32 chan;
- status = priv->hw->dma->dma_interrupt(priv->ioaddr, &priv->xstats);
- if (likely((status & handle_rx)) || (status & handle_tx)) {
- if (likely(napi_schedule_prep(&priv->napi))) {
- stmmac_disable_dma_irq(priv);
- __napi_schedule(&priv->napi);
+ for (chan = 0; chan < tx_channel_count; chan++) {
+ struct stmmac_rx_queue *rx_q = &priv->rx_queue[chan];
+
+ status = priv->hw->dma->dma_interrupt(priv->ioaddr,
+ &priv->xstats, chan);
+ if (likely((status & handle_rx)) || (status & handle_tx)) {
+ if (likely(napi_schedule_prep(&rx_q->napi))) {
+ stmmac_disable_dma_irq(priv, chan);
+ __napi_schedule(&rx_q->napi);
+ }
+ }
+
+ if (unlikely(status & tx_hard_error_bump_tc)) {
+ /* Try to bump up the dma threshold on this failure */
+ if (unlikely(priv->xstats.threshold != SF_DMA_MODE) &&
+ (tc <= 256)) {
+ tc += 64;
+ if (priv->plat->force_thresh_dma_mode)
+ stmmac_set_dma_operation_mode(priv,
+ tc,
+ tc,
+ chan);
+ else
+ stmmac_set_dma_operation_mode(priv,
+ tc,
+ SF_DMA_MODE,
+ chan);
+ priv->xstats.threshold = tc;
+ }
+ } else if (unlikely(status == tx_hard_error)) {
+ stmmac_tx_err(priv, chan);
}
}
- if (unlikely(status & tx_hard_error_bump_tc)) {
- /* Try to bump up the dma threshold on this failure */
- if (unlikely(priv->xstats.threshold != SF_DMA_MODE) &&
- (tc <= 256)) {
- tc += 64;
- if (priv->plat->force_thresh_dma_mode)
- priv->hw->dma->dma_mode(priv->ioaddr, tc, tc,
- rxfifosz);
- else
- priv->hw->dma->dma_mode(priv->ioaddr, tc,
- SF_DMA_MODE, rxfifosz);
- priv->xstats.threshold = tc;
- }
- } else if (unlikely(status == tx_hard_error))
- stmmac_tx_err(priv);
}
/**
@@ -1574,6 +2105,13 @@ static void stmmac_check_ether_addr(struct stmmac_priv *priv)
*/
static int stmmac_init_dma_engine(struct stmmac_priv *priv)
{
+ u32 rx_channels_count = priv->plat->rx_queues_to_use;
+ u32 tx_channels_count = priv->plat->tx_queues_to_use;
+ struct stmmac_rx_queue *rx_q;
+ struct stmmac_tx_queue *tx_q;
+ u32 dummy_dma_rx_phy = 0;
+ u32 dummy_dma_tx_phy = 0;
+ u32 chan = 0;
int atds = 0;
int ret = 0;
@@ -1591,19 +2129,49 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
return ret;
}
- priv->hw->dma->init(priv->ioaddr, priv->plat->dma_cfg,
- priv->dma_tx_phy, priv->dma_rx_phy, atds);
-
if (priv->synopsys_id >= DWMAC_CORE_4_00) {
- priv->rx_tail_addr = priv->dma_rx_phy +
- (DMA_RX_SIZE * sizeof(struct dma_desc));
- priv->hw->dma->set_rx_tail_ptr(priv->ioaddr, priv->rx_tail_addr,
- STMMAC_CHAN0);
+ /* DMA Configuration */
+ priv->hw->dma->init(priv->ioaddr, priv->plat->dma_cfg,
+ dummy_dma_tx_phy, dummy_dma_rx_phy, atds);
- priv->tx_tail_addr = priv->dma_tx_phy +
- (DMA_TX_SIZE * sizeof(struct dma_desc));
- priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, priv->tx_tail_addr,
- STMMAC_CHAN0);
+ /* DMA RX Channel Configuration */
+ for (chan = 0; chan < rx_channels_count; chan++) {
+ rx_q = &priv->rx_queue[chan];
+
+ priv->hw->dma->init_rx_chan(priv->ioaddr,
+ priv->plat->dma_cfg,
+ rx_q->dma_rx_phy, chan);
+
+ rx_q->rx_tail_addr = rx_q->dma_rx_phy +
+ (DMA_RX_SIZE * sizeof(struct dma_desc));
+ priv->hw->dma->set_rx_tail_ptr(priv->ioaddr,
+ rx_q->rx_tail_addr,
+ chan);
+ }
+
+ /* DMA TX Channel Configuration */
+ for (chan = 0; chan < tx_channels_count; chan++) {
+ tx_q = &priv->tx_queue[chan];
+
+ priv->hw->dma->init_chan(priv->ioaddr,
+ priv->plat->dma_cfg,
+ chan);
+
+ priv->hw->dma->init_tx_chan(priv->ioaddr,
+ priv->plat->dma_cfg,
+ tx_q->dma_tx_phy, chan);
+
+ tx_q->tx_tail_addr = tx_q->dma_tx_phy +
+ (DMA_TX_SIZE * sizeof(struct dma_desc));
+ priv->hw->dma->set_tx_tail_ptr(priv->ioaddr,
+ tx_q->tx_tail_addr,
+ chan);
+ }
+ } else {
+ rx_q = &priv->rx_queue[chan];
+ tx_q = &priv->tx_queue[chan];
+ priv->hw->dma->init(priv->ioaddr, priv->plat->dma_cfg,
+ tx_q->dma_tx_phy, rx_q->dma_rx_phy, atds);
}
if (priv->plat->axi && priv->hw->dma->axi)
@@ -1621,8 +2189,12 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
static void stmmac_tx_timer(unsigned long data)
{
struct stmmac_priv *priv = (struct stmmac_priv *)data;
+ u32 tx_queues_count = priv->plat->tx_queues_to_use;
+ u32 queue;
- stmmac_tx_clean(priv);
+ /* let's scan all the tx queues */
+ for (queue = 0; queue < tx_queues_count; queue++)
+ stmmac_tx_clean(priv, queue);
}
/**
@@ -1644,6 +2216,196 @@ static void stmmac_init_tx_coalesce(struct stmmac_priv *priv)
add_timer(&priv->txtimer);
}
+static void stmmac_set_rings_length(struct stmmac_priv *priv)
+{
+ u32 rx_channels_count = priv->plat->rx_queues_to_use;
+ u32 tx_channels_count = priv->plat->tx_queues_to_use;
+ u32 chan;
+
+ /* set TX ring length */
+ if (priv->hw->dma->set_tx_ring_len) {
+ for (chan = 0; chan < tx_channels_count; chan++)
+ priv->hw->dma->set_tx_ring_len(priv->ioaddr,
+ (DMA_TX_SIZE - 1), chan);
+ }
+
+ /* set RX ring length */
+ if (priv->hw->dma->set_rx_ring_len) {
+ for (chan = 0; chan < rx_channels_count; chan++)
+ priv->hw->dma->set_rx_ring_len(priv->ioaddr,
+ (DMA_RX_SIZE - 1), chan);
+ }
+}
+
+/**
+ * stmmac_set_tx_queue_weight - Set TX queue weight
+ * @priv: driver private structure
+ * Description: It is used for setting TX queues weight
+ */
+static void stmmac_set_tx_queue_weight(struct stmmac_priv *priv)
+{
+ u32 tx_queues_count = priv->plat->tx_queues_to_use;
+ u32 weight;
+ u32 queue;
+
+ for (queue = 0; queue < tx_queues_count; queue++) {
+ weight = priv->plat->tx_queues_cfg[queue].weight;
+ priv->hw->mac->set_mtl_tx_queue_weight(priv->hw, weight, queue);
+ }
+}
+
+/**
+ * stmmac_configure_cbs - Configure CBS in TX queue
+ * @priv: driver private structure
+ * Description: It is used for configuring CBS in AVB TX queues
+ */
+static void stmmac_configure_cbs(struct stmmac_priv *priv)
+{
+ u32 tx_queues_count = priv->plat->tx_queues_to_use;
+ u32 mode_to_use;
+ u32 queue;
+
+ /* queue 0 is reserved for legacy traffic */
+ for (queue = 1; queue < tx_queues_count; queue++) {
+ mode_to_use = priv->plat->tx_queues_cfg[queue].mode_to_use;
+ if (mode_to_use == MTL_QUEUE_DCB)
+ continue;
+
+ priv->hw->mac->config_cbs(priv->hw,
+ priv->plat->tx_queues_cfg[queue].send_slope,
+ priv->plat->tx_queues_cfg[queue].idle_slope,
+ priv->plat->tx_queues_cfg[queue].high_credit,
+ priv->plat->tx_queues_cfg[queue].low_credit,
+ queue);
+ }
+}
+
+/**
+ * stmmac_rx_queue_dma_chan_map - Map RX queue to RX dma channel
+ * @priv: driver private structure
+ * Description: It is used for mapping RX queues to RX dma channels
+ */
+static void stmmac_rx_queue_dma_chan_map(struct stmmac_priv *priv)
+{
+ u32 rx_queues_count = priv->plat->rx_queues_to_use;
+ u32 queue;
+ u32 chan;
+
+ for (queue = 0; queue < rx_queues_count; queue++) {
+ chan = priv->plat->rx_queues_cfg[queue].chan;
+ priv->hw->mac->map_mtl_to_dma(priv->hw, queue, chan);
+ }
+}
+
+/**
+ * stmmac_mac_config_rx_queues_prio - Configure RX Queue priority
+ * @priv: driver private structure
+ * Description: It is used for configuring the RX Queue Priority
+ */
+static void stmmac_mac_config_rx_queues_prio(struct stmmac_priv *priv)
+{
+ u32 rx_queues_count = priv->plat->rx_queues_to_use;
+ u32 queue;
+ u32 prio;
+
+ for (queue = 0; queue < rx_queues_count; queue++) {
+ if (!priv->plat->rx_queues_cfg[queue].use_prio)
+ continue;
+
+ prio = priv->plat->rx_queues_cfg[queue].prio;
+ priv->hw->mac->rx_queue_prio(priv->hw, prio, queue);
+ }
+}
+
+/**
+ * stmmac_mac_config_tx_queues_prio - Configure TX Queue priority
+ * @priv: driver private structure
+ * Description: It is used for configuring the TX Queue Priority
+ */
+static void stmmac_mac_config_tx_queues_prio(struct stmmac_priv *priv)
+{
+ u32 tx_queues_count = priv->plat->tx_queues_to_use;
+ u32 queue;
+ u32 prio;
+
+ for (queue = 0; queue < tx_queues_count; queue++) {
+ if (!priv->plat->tx_queues_cfg[queue].use_prio)
+ continue;
+
+ prio = priv->plat->tx_queues_cfg[queue].prio;
+ priv->hw->mac->tx_queue_prio(priv->hw, prio, queue);
+ }
+}
+
+/**
+ * stmmac_mac_config_rx_queues_routing - Configure RX Queue Routing
+ * @priv: driver private structure
+ * Description: It is used for configuring the RX queue routing
+ */
+static void stmmac_mac_config_rx_queues_routing(struct stmmac_priv *priv)
+{
+ u32 rx_queues_count = priv->plat->rx_queues_to_use;
+ u32 queue;
+ u8 packet;
+
+ for (queue = 0; queue < rx_queues_count; queue++) {
+ /* no specific packet type routing specified for the queue */
+ if (priv->plat->rx_queues_cfg[queue].pkt_route == 0x0)
+ continue;
+
+ packet = priv->plat->rx_queues_cfg[queue].pkt_route;
+ priv->hw->mac->rx_queue_prio(priv->hw, packet, queue);
+ }
+}
+
+/**
+ * stmmac_mtl_configuration - Configure MTL
+ * @priv: driver private structure
+ * Description: It is used for configurring MTL
+ */
+static void stmmac_mtl_configuration(struct stmmac_priv *priv)
+{
+ u32 rx_queues_count = priv->plat->rx_queues_to_use;
+ u32 tx_queues_count = priv->plat->tx_queues_to_use;
+
+ if (tx_queues_count > 1 && priv->hw->mac->set_mtl_tx_queue_weight)
+ stmmac_set_tx_queue_weight(priv);
+
+ /* Configure MTL RX algorithms */
+ if (rx_queues_count > 1 && priv->hw->mac->prog_mtl_rx_algorithms)
+ priv->hw->mac->prog_mtl_rx_algorithms(priv->hw,
+ priv->plat->rx_sched_algorithm);
+
+ /* Configure MTL TX algorithms */
+ if (tx_queues_count > 1 && priv->hw->mac->prog_mtl_tx_algorithms)
+ priv->hw->mac->prog_mtl_tx_algorithms(priv->hw,
+ priv->plat->tx_sched_algorithm);
+
+ /* Configure CBS in AVB TX queues */
+ if (tx_queues_count > 1 && priv->hw->mac->config_cbs)
+ stmmac_configure_cbs(priv);
+
+ /* Map RX MTL to DMA channels */
+ if (priv->hw->mac->map_mtl_to_dma)
+ stmmac_rx_queue_dma_chan_map(priv);
+
+ /* Enable MAC RX Queues */
+ if (priv->hw->mac->rx_queue_enable)
+ stmmac_mac_enable_rx_queues(priv);
+
+ /* Set RX priorities */
+ if (rx_queues_count > 1 && priv->hw->mac->rx_queue_prio)
+ stmmac_mac_config_rx_queues_prio(priv);
+
+ /* Set TX priorities */
+ if (tx_queues_count > 1 && priv->hw->mac->tx_queue_prio)
+ stmmac_mac_config_tx_queues_prio(priv);
+
+ /* Set RX routing */
+ if (rx_queues_count > 1 && priv->hw->mac->rx_queue_routing)
+ stmmac_mac_config_rx_queues_routing(priv);
+}
+
/**
* stmmac_hw_setup - setup mac in a usable state.
* @dev : pointer to the device structure.
@@ -1659,6 +2421,9 @@ static void stmmac_init_tx_coalesce(struct stmmac_priv *priv)
static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
{
struct stmmac_priv *priv = netdev_priv(dev);
+ u32 rx_cnt = priv->plat->rx_queues_to_use;
+ u32 tx_cnt = priv->plat->tx_queues_to_use;
+ u32 chan;
int ret;
/* DMA initialization and SW reset */
@@ -1688,9 +2453,9 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
/* Initialize the MAC Core */
priv->hw->mac->core_init(priv->hw, dev->mtu);
- /* Initialize MAC RX Queues */
- if (priv->hw->mac->rx_queue_enable)
- stmmac_mac_enable_rx_queues(priv);
+ /* Initialize MTL*/
+ if (priv->synopsys_id >= DWMAC_CORE_4_00)
+ stmmac_mtl_configuration(priv);
ret = priv->hw->mac->rx_ipc(priv->hw);
if (!ret) {
@@ -1700,10 +2465,7 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
}
/* Enable the MAC Rx/Tx */
- if (priv->synopsys_id >= DWMAC_CORE_4_00)
- stmmac_dwmac4_set_mac(priv->ioaddr, true);
- else
- stmmac_set_mac(priv->ioaddr, true);
+ priv->hw->mac->set_mac(priv->ioaddr, true);
/* Set the HW DMA mode and the COE */
stmmac_dma_operation_mode(priv);
@@ -1711,6 +2473,10 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
stmmac_mmc_setup(priv);
if (init_ptp) {
+ ret = clk_prepare_enable(priv->plat->clk_ptp_ref);
+ if (ret < 0)
+ netdev_warn(priv->dev, "failed to enable PTP reference clock: %d\n", ret);
+
ret = stmmac_init_ptp(priv);
if (ret == -EOPNOTSUPP)
netdev_warn(priv->dev, "PTP not supported by HW\n");
@@ -1725,35 +2491,37 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
__func__);
#endif
/* Start the ball rolling... */
- netdev_dbg(priv->dev, "DMA RX/TX processes started...\n");
- priv->hw->dma->start_tx(priv->ioaddr);
- priv->hw->dma->start_rx(priv->ioaddr);
+ stmmac_start_all_dma(priv);
priv->tx_lpi_timer = STMMAC_DEFAULT_TWT_LS;
if ((priv->use_riwt) && (priv->hw->dma->rx_watchdog)) {
priv->rx_riwt = MAX_DMA_RIWT;
- priv->hw->dma->rx_watchdog(priv->ioaddr, MAX_DMA_RIWT);
+ priv->hw->dma->rx_watchdog(priv->ioaddr, MAX_DMA_RIWT, rx_cnt);
}
if (priv->hw->pcs && priv->hw->mac->pcs_ctrl_ane)
priv->hw->mac->pcs_ctrl_ane(priv->hw, 1, priv->hw->ps, 0);
- /* set TX ring length */
- if (priv->hw->dma->set_tx_ring_len)
- priv->hw->dma->set_tx_ring_len(priv->ioaddr,
- (DMA_TX_SIZE - 1));
- /* set RX ring length */
- if (priv->hw->dma->set_rx_ring_len)
- priv->hw->dma->set_rx_ring_len(priv->ioaddr,
- (DMA_RX_SIZE - 1));
+ /* set TX and RX rings length */
+ stmmac_set_rings_length(priv);
+
/* Enable TSO */
- if (priv->tso)
- priv->hw->dma->enable_tso(priv->ioaddr, 1, STMMAC_CHAN0);
+ if (priv->tso) {
+ for (chan = 0; chan < tx_cnt; chan++)
+ priv->hw->dma->enable_tso(priv->ioaddr, 1, chan);
+ }
return 0;
}
+static void stmmac_hw_teardown(struct net_device *dev)
+{
+ struct stmmac_priv *priv = netdev_priv(dev);
+
+ clk_disable_unprepare(priv->plat->clk_ptp_ref);
+}
+
/**
* stmmac_open - open entry point of the driver
* @dev : pointer to the device structure.
@@ -1821,7 +2589,7 @@ static int stmmac_open(struct net_device *dev)
netdev_err(priv->dev,
"%s: ERROR: allocating the IRQ %d (error: %d)\n",
__func__, dev->irq, ret);
- goto init_error;
+ goto irq_error;
}
/* Request the Wake IRQ in case of another line is used for WoL */
@@ -1848,8 +2616,8 @@ static int stmmac_open(struct net_device *dev)
}
}
- napi_enable(&priv->napi);
- netif_start_queue(dev);
+ stmmac_enable_all_queues(priv);
+ stmmac_start_all_queues(priv);
return 0;
@@ -1858,7 +2626,12 @@ static int stmmac_open(struct net_device *dev)
free_irq(priv->wol_irq, dev);
wolirq_error:
free_irq(dev->irq, dev);
+irq_error:
+ if (dev->phydev)
+ phy_stop(dev->phydev);
+ del_timer_sync(&priv->txtimer);
+ stmmac_hw_teardown(dev);
init_error:
free_dma_desc_resources(priv);
dma_desc_error:
@@ -1887,9 +2660,9 @@ static int stmmac_release(struct net_device *dev)
phy_disconnect(dev->phydev);
}
- netif_stop_queue(dev);
+ stmmac_stop_all_queues(priv);
- napi_disable(&priv->napi);
+ stmmac_disable_all_queues(priv);
del_timer_sync(&priv->txtimer);
@@ -1901,14 +2674,13 @@ static int stmmac_release(struct net_device *dev)
free_irq(priv->lpi_irq, dev);
/* Stop TX/RX DMA and clear the descriptors */
- priv->hw->dma->stop_tx(priv->ioaddr);
- priv->hw->dma->stop_rx(priv->ioaddr);
+ stmmac_stop_all_dma(priv);
/* Release and free the Rx/Tx resources */
free_dma_desc_resources(priv);
/* Disable the MAC Rx/Tx */
- stmmac_set_mac(priv->ioaddr, false);
+ priv->hw->mac->set_mac(priv->ioaddr, false);
netif_carrier_off(dev);
@@ -1927,22 +2699,24 @@ static int stmmac_release(struct net_device *dev)
* @des: buffer start address
* @total_len: total length to fill in descriptors
* @last_segmant: condition for the last descriptor
+ * @queue: TX queue index
* Description:
* This function fills descriptor and request new descriptors according to
* buffer length to fill
*/
static void stmmac_tso_allocator(struct stmmac_priv *priv, unsigned int des,
- int total_len, bool last_segment)
+ int total_len, bool last_segment, u32 queue)
{
+ struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
struct dma_desc *desc;
- int tmp_len;
u32 buff_size;
+ int tmp_len;
tmp_len = total_len;
while (tmp_len > 0) {
- priv->cur_tx = STMMAC_GET_ENTRY(priv->cur_tx, DMA_TX_SIZE);
- desc = priv->dma_tx + priv->cur_tx;
+ tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE);
+ desc = tx_q->dma_tx + tx_q->cur_tx;
desc->des0 = cpu_to_le32(des + (total_len - tmp_len));
buff_size = tmp_len >= TSO_MAX_BUFF_SIZE ?
@@ -1986,23 +2760,28 @@ static void stmmac_tso_allocator(struct stmmac_priv *priv, unsigned int des,
*/
static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
{
- u32 pay_len, mss;
- int tmp_pay_len = 0;
+ struct dma_desc *desc, *first, *mss_desc = NULL;
struct stmmac_priv *priv = netdev_priv(dev);
int nfrags = skb_shinfo(skb)->nr_frags;
+ u32 queue = skb_get_queue_mapping(skb);
unsigned int first_entry, des;
- struct dma_desc *desc, *first, *mss_desc = NULL;
+ struct stmmac_tx_queue *tx_q;
+ int tmp_pay_len = 0;
+ u32 pay_len, mss;
u8 proto_hdr_len;
int i;
+ tx_q = &priv->tx_queue[queue];
+
/* Compute header lengths */
proto_hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
/* Desc availability based on threshold should be enough safe */
- if (unlikely(stmmac_tx_avail(priv) <
+ if (unlikely(stmmac_tx_avail(priv, queue) <
(((skb->len - proto_hdr_len) / TSO_MAX_BUFF_SIZE + 1)))) {
- if (!netif_queue_stopped(dev)) {
- netif_stop_queue(dev);
+ if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, queue))) {
+ netif_tx_stop_queue(netdev_get_tx_queue(priv->dev,
+ queue));
/* This is a hard error, log it. */
netdev_err(priv->dev,
"%s: Tx Ring full when queue awake\n",
@@ -2017,10 +2796,10 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
/* set new MSS value if needed */
if (mss != priv->mss) {
- mss_desc = priv->dma_tx + priv->cur_tx;
+ mss_desc = tx_q->dma_tx + tx_q->cur_tx;
priv->hw->desc->set_mss(mss_desc, mss);
priv->mss = mss;
- priv->cur_tx = STMMAC_GET_ENTRY(priv->cur_tx, DMA_TX_SIZE);
+ tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE);
}
if (netif_msg_tx_queued(priv)) {
@@ -2030,9 +2809,9 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
skb->data_len);
}
- first_entry = priv->cur_tx;
+ first_entry = tx_q->cur_tx;
- desc = priv->dma_tx + first_entry;
+ desc = tx_q->dma_tx + first_entry;
first = desc;
/* first descriptor: fill Headers on Buf1 */
@@ -2041,9 +2820,9 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
if (dma_mapping_error(priv->device, des))
goto dma_map_err;
- priv->tx_skbuff_dma[first_entry].buf = des;
- priv->tx_skbuff_dma[first_entry].len = skb_headlen(skb);
- priv->tx_skbuff[first_entry] = skb;
+ tx_q->tx_skbuff_dma[first_entry].buf = des;
+ tx_q->tx_skbuff_dma[first_entry].len = skb_headlen(skb);
+ tx_q->tx_skbuff[first_entry] = skb;
first->des0 = cpu_to_le32(des);
@@ -2054,7 +2833,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
/* If needed take extra descriptors to fill the remaining payload */
tmp_pay_len = pay_len - TSO_MAX_BUFF_SIZE;
- stmmac_tso_allocator(priv, des, tmp_pay_len, (nfrags == 0));
+ stmmac_tso_allocator(priv, des, tmp_pay_len, (nfrags == 0), queue);
/* Prepare fragments */
for (i = 0; i < nfrags; i++) {
@@ -2063,24 +2842,26 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
des = skb_frag_dma_map(priv->device, frag, 0,
skb_frag_size(frag),
DMA_TO_DEVICE);
+ if (dma_mapping_error(priv->device, des))
+ goto dma_map_err;
stmmac_tso_allocator(priv, des, skb_frag_size(frag),
- (i == nfrags - 1));
+ (i == nfrags - 1), queue);
- priv->tx_skbuff_dma[priv->cur_tx].buf = des;
- priv->tx_skbuff_dma[priv->cur_tx].len = skb_frag_size(frag);
- priv->tx_skbuff[priv->cur_tx] = NULL;
- priv->tx_skbuff_dma[priv->cur_tx].map_as_page = true;
+ tx_q->tx_skbuff_dma[tx_q->cur_tx].buf = des;
+ tx_q->tx_skbuff_dma[tx_q->cur_tx].len = skb_frag_size(frag);
+ tx_q->tx_skbuff[tx_q->cur_tx] = NULL;
+ tx_q->tx_skbuff_dma[tx_q->cur_tx].map_as_page = true;
}
- priv->tx_skbuff_dma[priv->cur_tx].last_segment = true;
+ tx_q->tx_skbuff_dma[tx_q->cur_tx].last_segment = true;
- priv->cur_tx = STMMAC_GET_ENTRY(priv->cur_tx, DMA_TX_SIZE);
+ tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE);
- if (unlikely(stmmac_tx_avail(priv) <= (MAX_SKB_FRAGS + 1))) {
+ if (unlikely(stmmac_tx_avail(priv, queue) <= (MAX_SKB_FRAGS + 1))) {
netif_dbg(priv, hw, priv->dev, "%s: stop transmitted packets\n",
__func__);
- netif_stop_queue(dev);
+ netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue));
}
dev->stats.tx_bytes += skb->len;
@@ -2112,7 +2893,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
priv->hw->desc->prepare_tso_tx_desc(first, 1,
proto_hdr_len,
pay_len,
- 1, priv->tx_skbuff_dma[first_entry].last_segment,
+ 1, tx_q->tx_skbuff_dma[first_entry].last_segment,
tcp_hdrlen(skb) / 4, (skb->len - proto_hdr_len));
/* If context desc is used to change MSS */
@@ -2127,20 +2908,20 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
if (netif_msg_pktdata(priv)) {
pr_info("%s: curr=%d dirty=%d f=%d, e=%d, f_p=%p, nfrags %d\n",
- __func__, priv->cur_tx, priv->dirty_tx, first_entry,
- priv->cur_tx, first, nfrags);
+ __func__, tx_q->cur_tx, tx_q->dirty_tx, first_entry,
+ tx_q->cur_tx, first, nfrags);
- priv->hw->desc->display_ring((void *)priv->dma_tx, DMA_TX_SIZE,
+ priv->hw->desc->display_ring((void *)tx_q->dma_tx, DMA_TX_SIZE,
0);
pr_info(">>> frame to be transmitted: ");
print_pkt(skb->data, skb_headlen(skb));
}
- netdev_sent_queue(dev, skb->len);
+ netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len);
- priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, priv->tx_tail_addr,
- STMMAC_CHAN0);
+ priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, tx_q->tx_tail_addr,
+ queue);
return NETDEV_TX_OK;
@@ -2164,21 +2945,26 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
struct stmmac_priv *priv = netdev_priv(dev);
unsigned int nopaged_len = skb_headlen(skb);
int i, csum_insertion = 0, is_jumbo = 0;
+ u32 queue = skb_get_queue_mapping(skb);
int nfrags = skb_shinfo(skb)->nr_frags;
unsigned int entry, first_entry;
struct dma_desc *desc, *first;
+ struct stmmac_tx_queue *tx_q;
unsigned int enh_desc;
unsigned int des;
+ tx_q = &priv->tx_queue[queue];
+
/* Manage oversized TCP frames for GMAC4 device */
if (skb_is_gso(skb) && priv->tso) {
if (ip_hdr(skb)->protocol == IPPROTO_TCP)
return stmmac_tso_xmit(skb, dev);
}
- if (unlikely(stmmac_tx_avail(priv) < nfrags + 1)) {
- if (!netif_queue_stopped(dev)) {
- netif_stop_queue(dev);
+ if (unlikely(stmmac_tx_avail(priv, queue) < nfrags + 1)) {
+ if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, queue))) {
+ netif_tx_stop_queue(netdev_get_tx_queue(priv->dev,
+ queue));
/* This is a hard error, log it. */
netdev_err(priv->dev,
"%s: Tx Ring full when queue awake\n",
@@ -2190,19 +2976,19 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
if (priv->tx_path_in_lpi_mode)
stmmac_disable_eee_mode(priv);
- entry = priv->cur_tx;
+ entry = tx_q->cur_tx;
first_entry = entry;
csum_insertion = (skb->ip_summed == CHECKSUM_PARTIAL);
if (likely(priv->extend_desc))
- desc = (struct dma_desc *)(priv->dma_etx + entry);
+ desc = (struct dma_desc *)(tx_q->dma_etx + entry);
else
- desc = priv->dma_tx + entry;
+ desc = tx_q->dma_tx + entry;
first = desc;
- priv->tx_skbuff[first_entry] = skb;
+ tx_q->tx_skbuff[first_entry] = skb;
enh_desc = priv->plat->enh_desc;
/* To program the descriptors according to the size of the frame */
@@ -2211,7 +2997,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
if (unlikely(is_jumbo) && likely(priv->synopsys_id <
DWMAC_CORE_4_00)) {
- entry = priv->hw->mode->jumbo_frm(priv, skb, csum_insertion);
+ entry = priv->hw->mode->jumbo_frm(tx_q, skb, csum_insertion);
if (unlikely(entry < 0))
goto dma_map_err;
}
@@ -2224,26 +3010,26 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE);
if (likely(priv->extend_desc))
- desc = (struct dma_desc *)(priv->dma_etx + entry);
+ desc = (struct dma_desc *)(tx_q->dma_etx + entry);
else
- desc = priv->dma_tx + entry;
+ desc = tx_q->dma_tx + entry;
des = skb_frag_dma_map(priv->device, frag, 0, len,
DMA_TO_DEVICE);
if (dma_mapping_error(priv->device, des))
goto dma_map_err; /* should reuse desc w/o issues */
- priv->tx_skbuff[entry] = NULL;
+ tx_q->tx_skbuff[entry] = NULL;
- priv->tx_skbuff_dma[entry].buf = des;
+ tx_q->tx_skbuff_dma[entry].buf = des;
if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00))
desc->des0 = cpu_to_le32(des);
else
desc->des2 = cpu_to_le32(des);
- priv->tx_skbuff_dma[entry].map_as_page = true;
- priv->tx_skbuff_dma[entry].len = len;
- priv->tx_skbuff_dma[entry].last_segment = last_segment;
+ tx_q->tx_skbuff_dma[entry].map_as_page = true;
+ tx_q->tx_skbuff_dma[entry].len = len;
+ tx_q->tx_skbuff_dma[entry].last_segment = last_segment;
/* Prepare the descriptor and set the own bit too */
priv->hw->desc->prepare_tx_desc(desc, 0, len, csum_insertion,
@@ -2252,20 +3038,20 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE);
- priv->cur_tx = entry;
+ tx_q->cur_tx = entry;
if (netif_msg_pktdata(priv)) {
void *tx_head;
netdev_dbg(priv->dev,
"%s: curr=%d dirty=%d f=%d, e=%d, first=%p, nfrags=%d",
- __func__, priv->cur_tx, priv->dirty_tx, first_entry,
+ __func__, tx_q->cur_tx, tx_q->dirty_tx, first_entry,
entry, first, nfrags);
if (priv->extend_desc)
- tx_head = (void *)priv->dma_etx;
+ tx_head = (void *)tx_q->dma_etx;
else
- tx_head = (void *)priv->dma_tx;
+ tx_head = (void *)tx_q->dma_tx;
priv->hw->desc->display_ring(tx_head, DMA_TX_SIZE, false);
@@ -2273,10 +3059,10 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
print_pkt(skb->data, skb->len);
}
- if (unlikely(stmmac_tx_avail(priv) <= (MAX_SKB_FRAGS + 1))) {
+ if (unlikely(stmmac_tx_avail(priv, queue) <= (MAX_SKB_FRAGS + 1))) {
netif_dbg(priv, hw, priv->dev, "%s: stop transmitted packets\n",
__func__);
- netif_stop_queue(dev);
+ netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue));
}
dev->stats.tx_bytes += skb->len;
@@ -2311,14 +3097,14 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
if (dma_mapping_error(priv->device, des))
goto dma_map_err;
- priv->tx_skbuff_dma[first_entry].buf = des;
+ tx_q->tx_skbuff_dma[first_entry].buf = des;
if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00))
first->des0 = cpu_to_le32(des);
else
first->des2 = cpu_to_le32(des);
- priv->tx_skbuff_dma[first_entry].len = nopaged_len;
- priv->tx_skbuff_dma[first_entry].last_segment = last_segment;
+ tx_q->tx_skbuff_dma[first_entry].len = nopaged_len;
+ tx_q->tx_skbuff_dma[first_entry].last_segment = last_segment;
if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
priv->hwts_tx_en)) {
@@ -2339,13 +3125,13 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
dma_wmb();
}
- netdev_sent_queue(dev, skb->len);
+ netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len);
if (priv->synopsys_id < DWMAC_CORE_4_00)
priv->hw->dma->enable_dma_transmission(priv->ioaddr);
else
- priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, priv->tx_tail_addr,
- STMMAC_CHAN0);
+ priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, tx_q->tx_tail_addr,
+ queue);
return NETDEV_TX_OK;
@@ -2373,9 +3159,9 @@ static void stmmac_rx_vlan(struct net_device *dev, struct sk_buff *skb)
}
-static inline int stmmac_rx_threshold_count(struct stmmac_priv *priv)
+static inline int stmmac_rx_threshold_count(struct stmmac_rx_queue *rx_q)
{
- if (priv->rx_zeroc_thresh < STMMAC_RX_THRESH)
+ if (rx_q->rx_zeroc_thresh < STMMAC_RX_THRESH)
return 0;
return 1;
@@ -2384,30 +3170,33 @@ static inline int stmmac_rx_threshold_count(struct stmmac_priv *priv)
/**
* stmmac_rx_refill - refill used skb preallocated buffers
* @priv: driver private structure
+ * @queue: RX queue index
* Description : this is to reallocate the skb for the reception process
* that is based on zero-copy.
*/
-static inline void stmmac_rx_refill(struct stmmac_priv *priv)
+static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue)
{
+ struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+ int dirty = stmmac_rx_dirty(priv, queue);
+ unsigned int entry = rx_q->dirty_rx;
+
int bfsize = priv->dma_buf_sz;
- unsigned int entry = priv->dirty_rx;
- int dirty = stmmac_rx_dirty(priv);
while (dirty-- > 0) {
struct dma_desc *p;
if (priv->extend_desc)
- p = (struct dma_desc *)(priv->dma_erx + entry);
+ p = (struct dma_desc *)(rx_q->dma_erx + entry);
else
- p = priv->dma_rx + entry;
+ p = rx_q->dma_rx + entry;
- if (likely(priv->rx_skbuff[entry] == NULL)) {
+ if (likely(!rx_q->rx_skbuff[entry])) {
struct sk_buff *skb;
skb = netdev_alloc_skb_ip_align(priv->dev, bfsize);
if (unlikely(!skb)) {
/* so for a while no zero-copy! */
- priv->rx_zeroc_thresh = STMMAC_RX_THRESH;
+ rx_q->rx_zeroc_thresh = STMMAC_RX_THRESH;
if (unlikely(net_ratelimit()))
dev_err(priv->device,
"fail to alloc skb entry %d\n",
@@ -2415,28 +3204,28 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv)
break;
}
- priv->rx_skbuff[entry] = skb;
- priv->rx_skbuff_dma[entry] =
+ rx_q->rx_skbuff[entry] = skb;
+ rx_q->rx_skbuff_dma[entry] =
dma_map_single(priv->device, skb->data, bfsize,
DMA_FROM_DEVICE);
if (dma_mapping_error(priv->device,
- priv->rx_skbuff_dma[entry])) {
+ rx_q->rx_skbuff_dma[entry])) {
netdev_err(priv->dev, "Rx DMA map failed\n");
dev_kfree_skb(skb);
break;
}
if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00)) {
- p->des0 = cpu_to_le32(priv->rx_skbuff_dma[entry]);
+ p->des0 = cpu_to_le32(rx_q->rx_skbuff_dma[entry]);
p->des1 = 0;
} else {
- p->des2 = cpu_to_le32(priv->rx_skbuff_dma[entry]);
+ p->des2 = cpu_to_le32(rx_q->rx_skbuff_dma[entry]);
}
if (priv->hw->mode->refill_desc3)
- priv->hw->mode->refill_desc3(priv, p);
+ priv->hw->mode->refill_desc3(rx_q, p);
- if (priv->rx_zeroc_thresh > 0)
- priv->rx_zeroc_thresh--;
+ if (rx_q->rx_zeroc_thresh > 0)
+ rx_q->rx_zeroc_thresh--;
netif_dbg(priv, rx_status, priv->dev,
"refill entry #%d\n", entry);
@@ -2452,31 +3241,33 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv)
entry = STMMAC_GET_ENTRY(entry, DMA_RX_SIZE);
}
- priv->dirty_rx = entry;
+ rx_q->dirty_rx = entry;
}
/**
* stmmac_rx - manage the receive process
* @priv: driver private structure
- * @limit: napi bugget.
+ * @limit: napi bugget
+ * @queue: RX queue index.
* Description : this the function called by the napi poll method.
* It gets all the frames inside the ring.
*/
-static int stmmac_rx(struct stmmac_priv *priv, int limit)
+static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
{
- unsigned int entry = priv->cur_rx;
+ struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+ unsigned int entry = rx_q->cur_rx;
+ int coe = priv->hw->rx_csum;
unsigned int next_entry;
unsigned int count = 0;
- int coe = priv->hw->rx_csum;
if (netif_msg_rx_status(priv)) {
void *rx_head;
netdev_dbg(priv->dev, "%s: descriptor ring:\n", __func__);
if (priv->extend_desc)
- rx_head = (void *)priv->dma_erx;
+ rx_head = (void *)rx_q->dma_erx;
else
- rx_head = (void *)priv->dma_rx;
+ rx_head = (void *)rx_q->dma_rx;
priv->hw->desc->display_ring(rx_head, DMA_RX_SIZE, true);
}
@@ -2486,9 +3277,9 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
struct dma_desc *np;
if (priv->extend_desc)
- p = (struct dma_desc *)(priv->dma_erx + entry);
+ p = (struct dma_desc *)(rx_q->dma_erx + entry);
else
- p = priv->dma_rx + entry;
+ p = rx_q->dma_rx + entry;
/* read the status of the incoming frame */
status = priv->hw->desc->rx_status(&priv->dev->stats,
@@ -2499,20 +3290,20 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
count++;
- priv->cur_rx = STMMAC_GET_ENTRY(priv->cur_rx, DMA_RX_SIZE);
- next_entry = priv->cur_rx;
+ rx_q->cur_rx = STMMAC_GET_ENTRY(rx_q->cur_rx, DMA_RX_SIZE);
+ next_entry = rx_q->cur_rx;
if (priv->extend_desc)
- np = (struct dma_desc *)(priv->dma_erx + next_entry);
+ np = (struct dma_desc *)(rx_q->dma_erx + next_entry);
else
- np = priv->dma_rx + next_entry;
+ np = rx_q->dma_rx + next_entry;
prefetch(np);
if ((priv->extend_desc) && (priv->hw->desc->rx_extended_status))
priv->hw->desc->rx_extended_status(&priv->dev->stats,
&priv->xstats,
- priv->dma_erx +
+ rx_q->dma_erx +
entry);
if (unlikely(status == discard_frame)) {
priv->dev->stats.rx_errors++;
@@ -2522,9 +3313,9 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
* them in stmmac_rx_refill() function so that
* device can reuse it.
*/
- priv->rx_skbuff[entry] = NULL;
+ rx_q->rx_skbuff[entry] = NULL;
dma_unmap_single(priv->device,
- priv->rx_skbuff_dma[entry],
+ rx_q->rx_skbuff_dma[entry],
priv->dma_buf_sz,
DMA_FROM_DEVICE);
}
@@ -2572,7 +3363,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
*/
if (unlikely(!priv->plat->has_gmac4 &&
((frame_len < priv->rx_copybreak) ||
- stmmac_rx_threshold_count(priv)))) {
+ stmmac_rx_threshold_count(rx_q)))) {
skb = netdev_alloc_skb_ip_align(priv->dev,
frame_len);
if (unlikely(!skb)) {
@@ -2584,21 +3375,21 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
}
dma_sync_single_for_cpu(priv->device,
- priv->rx_skbuff_dma
+ rx_q->rx_skbuff_dma
[entry], frame_len,
DMA_FROM_DEVICE);
skb_copy_to_linear_data(skb,
- priv->
+ rx_q->
rx_skbuff[entry]->data,
frame_len);
skb_put(skb, frame_len);
dma_sync_single_for_device(priv->device,
- priv->rx_skbuff_dma
+ rx_q->rx_skbuff_dma
[entry], frame_len,
DMA_FROM_DEVICE);
} else {
- skb = priv->rx_skbuff[entry];
+ skb = rx_q->rx_skbuff[entry];
if (unlikely(!skb)) {
netdev_err(priv->dev,
"%s: Inconsistent Rx chain\n",
@@ -2607,12 +3398,12 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
break;
}
prefetch(skb->data - NET_IP_ALIGN);
- priv->rx_skbuff[entry] = NULL;
- priv->rx_zeroc_thresh++;
+ rx_q->rx_skbuff[entry] = NULL;
+ rx_q->rx_zeroc_thresh++;
skb_put(skb, frame_len);
dma_unmap_single(priv->device,
- priv->rx_skbuff_dma[entry],
+ rx_q->rx_skbuff_dma[entry],
priv->dma_buf_sz,
DMA_FROM_DEVICE);
}
@@ -2634,7 +3425,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
else
skb->ip_summed = CHECKSUM_UNNECESSARY;
- napi_gro_receive(&priv->napi, skb);
+ napi_gro_receive(&rx_q->napi, skb);
priv->dev->stats.rx_packets++;
priv->dev->stats.rx_bytes += frame_len;
@@ -2642,7 +3433,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
entry = next_entry;
}
- stmmac_rx_refill(priv);
+ stmmac_rx_refill(priv, queue);
priv->xstats.rx_pkt_n += count;
@@ -2659,16 +3450,24 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
*/
static int stmmac_poll(struct napi_struct *napi, int budget)
{
- struct stmmac_priv *priv = container_of(napi, struct stmmac_priv, napi);
+ struct stmmac_rx_queue *rx_q =
+ container_of(napi, struct stmmac_rx_queue, napi);
+ struct stmmac_priv *priv = rx_q->priv_data;
+ u32 tx_count = priv->plat->tx_queues_to_use;
+ u32 chan = rx_q->queue_index;
int work_done = 0;
+ u32 queue;
priv->xstats.napi_poll++;
- stmmac_tx_clean(priv);
- work_done = stmmac_rx(priv, budget);
+ /* check all the queues */
+ for (queue = 0; queue < tx_count; queue++)
+ stmmac_tx_clean(priv, queue);
+
+ work_done = stmmac_rx(priv, budget, rx_q->queue_index);
if (work_done < budget) {
napi_complete_done(napi, work_done);
- stmmac_enable_dma_irq(priv);
+ stmmac_enable_dma_irq(priv, chan);
}
return work_done;
}
@@ -2684,9 +3483,12 @@ static int stmmac_poll(struct napi_struct *napi, int budget)
static void stmmac_tx_timeout(struct net_device *dev)
{
struct stmmac_priv *priv = netdev_priv(dev);
+ u32 tx_count = priv->plat->tx_queues_to_use;
+ u32 chan;
/* Clear Tx resources and restart transmitting again */
- stmmac_tx_err(priv);
+ for (chan = 0; chan < tx_count; chan++)
+ stmmac_tx_err(priv, chan);
}
/**
@@ -2795,6 +3597,12 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
{
struct net_device *dev = (struct net_device *)dev_id;
struct stmmac_priv *priv = netdev_priv(dev);
+ u32 rx_cnt = priv->plat->rx_queues_to_use;
+ u32 tx_cnt = priv->plat->tx_queues_to_use;
+ u32 queues_count;
+ u32 queue;
+
+ queues_count = (rx_cnt > tx_cnt) ? rx_cnt : tx_cnt;
if (priv->irq_wake)
pm_wakeup_event(priv->device, 0);
@@ -2808,16 +3616,30 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
if ((priv->plat->has_gmac) || (priv->plat->has_gmac4)) {
int status = priv->hw->mac->host_irq_status(priv->hw,
&priv->xstats);
+
if (unlikely(status)) {
/* For LPI we need to save the tx status */
if (status & CORE_IRQ_TX_PATH_IN_LPI_MODE)
priv->tx_path_in_lpi_mode = true;
if (status & CORE_IRQ_TX_PATH_EXIT_LPI_MODE)
priv->tx_path_in_lpi_mode = false;
- if (status & CORE_IRQ_MTL_RX_OVERFLOW && priv->hw->dma->set_rx_tail_ptr)
- priv->hw->dma->set_rx_tail_ptr(priv->ioaddr,
- priv->rx_tail_addr,
- STMMAC_CHAN0);
+ }
+
+ if (priv->synopsys_id >= DWMAC_CORE_4_00) {
+ for (queue = 0; queue < queues_count; queue++) {
+ struct stmmac_rx_queue *rx_q =
+ &priv->rx_queue[queue];
+
+ status |=
+ priv->hw->mac->host_mtl_irq_status(priv->hw,
+ queue);
+
+ if (status & CORE_IRQ_MTL_RX_OVERFLOW &&
+ priv->hw->dma->set_rx_tail_ptr)
+ priv->hw->dma->set_rx_tail_ptr(priv->ioaddr,
+ rx_q->rx_tail_addr,
+ queue);
+ }
}
/* PCS link status */
@@ -2915,17 +3737,40 @@ static int stmmac_sysfs_ring_read(struct seq_file *seq, void *v)
{
struct net_device *dev = seq->private;
struct stmmac_priv *priv = netdev_priv(dev);
+ u32 rx_count = priv->plat->rx_queues_to_use;
+ u32 tx_count = priv->plat->tx_queues_to_use;
+ u32 queue;
- if (priv->extend_desc) {
- seq_printf(seq, "Extended RX descriptor ring:\n");
- sysfs_display_ring((void *)priv->dma_erx, DMA_RX_SIZE, 1, seq);
- seq_printf(seq, "Extended TX descriptor ring:\n");
- sysfs_display_ring((void *)priv->dma_etx, DMA_TX_SIZE, 1, seq);
- } else {
- seq_printf(seq, "RX descriptor ring:\n");
- sysfs_display_ring((void *)priv->dma_rx, DMA_RX_SIZE, 0, seq);
- seq_printf(seq, "TX descriptor ring:\n");
- sysfs_display_ring((void *)priv->dma_tx, DMA_TX_SIZE, 0, seq);
+ for (queue = 0; queue < rx_count; queue++) {
+ struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+ seq_printf(seq, "RX Queue %d:\n", queue);
+
+ if (priv->extend_desc) {
+ seq_printf(seq, "Extended descriptor ring:\n");
+ sysfs_display_ring((void *)rx_q->dma_erx,
+ DMA_RX_SIZE, 1, seq);
+ } else {
+ seq_printf(seq, "Descriptor ring:\n");
+ sysfs_display_ring((void *)rx_q->dma_rx,
+ DMA_RX_SIZE, 0, seq);
+ }
+ }
+
+ for (queue = 0; queue < tx_count; queue++) {
+ struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+ seq_printf(seq, "TX Queue %d:\n", queue);
+
+ if (priv->extend_desc) {
+ seq_printf(seq, "Extended descriptor ring:\n");
+ sysfs_display_ring((void *)tx_q->dma_etx,
+ DMA_TX_SIZE, 1, seq);
+ } else {
+ seq_printf(seq, "Descriptor ring:\n");
+ sysfs_display_ring((void *)tx_q->dma_tx,
+ DMA_TX_SIZE, 0, seq);
+ }
}
return 0;
@@ -3208,11 +4053,14 @@ int stmmac_dvr_probe(struct device *device,
struct plat_stmmacenet_data *plat_dat,
struct stmmac_resources *res)
{
- int ret = 0;
struct net_device *ndev = NULL;
struct stmmac_priv *priv;
+ int ret = 0;
+ u32 queue;
- ndev = alloc_etherdev(sizeof(struct stmmac_priv));
+ ndev = alloc_etherdev_mqs(sizeof(struct stmmac_priv),
+ MTL_MAX_TX_QUEUES,
+ MTL_MAX_RX_QUEUES);
if (!ndev)
return -ENOMEM;
@@ -3254,6 +4102,10 @@ int stmmac_dvr_probe(struct device *device,
if (ret)
goto error_hw_init;
+ /* Configure real RX and TX queues */
+ ndev->real_num_rx_queues = priv->plat->rx_queues_to_use;
+ ndev->real_num_tx_queues = priv->plat->tx_queues_to_use;
+
ndev->netdev_ops = &stmmac_netdev_ops;
ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
@@ -3303,7 +4155,12 @@ int stmmac_dvr_probe(struct device *device,
"Enable RX Mitigation via HW Watchdog Timer\n");
}
- netif_napi_add(ndev, &priv->napi, stmmac_poll, 64);
+ for (queue = 0; queue < priv->plat->rx_queues_to_use; queue++) {
+ struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+ netif_napi_add(ndev, &rx_q->napi, stmmac_poll,
+ (8 * priv->plat->rx_queues_to_use));
+ }
spin_lock_init(&priv->lock);
@@ -3348,7 +4205,11 @@ int stmmac_dvr_probe(struct device *device,
priv->hw->pcs != STMMAC_PCS_RTBI)
stmmac_mdio_unregister(ndev);
error_mdio_register:
- netif_napi_del(&priv->napi);
+ for (queue = 0; queue < priv->plat->rx_queues_to_use; queue++) {
+ struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+ netif_napi_del(&rx_q->napi);
+ }
error_hw_init:
free_netdev(ndev);
@@ -3369,10 +4230,9 @@ int stmmac_dvr_remove(struct device *dev)
netdev_info(priv->dev, "%s: removing driver", __func__);
- priv->hw->dma->stop_rx(priv->ioaddr);
- priv->hw->dma->stop_tx(priv->ioaddr);
+ stmmac_stop_all_dma(priv);
- stmmac_set_mac(priv->ioaddr, false);
+ priv->hw->mac->set_mac(priv->ioaddr, false);
netif_carrier_off(ndev);
unregister_netdev(ndev);
if (priv->plat->stmmac_rst)
@@ -3411,20 +4271,19 @@ int stmmac_suspend(struct device *dev)
spin_lock_irqsave(&priv->lock, flags);
netif_device_detach(ndev);
- netif_stop_queue(ndev);
+ stmmac_stop_all_queues(priv);
- napi_disable(&priv->napi);
+ stmmac_disable_all_queues(priv);
/* Stop TX/RX DMA */
- priv->hw->dma->stop_tx(priv->ioaddr);
- priv->hw->dma->stop_rx(priv->ioaddr);
+ stmmac_stop_all_dma(priv);
/* Enable Power down mode by programming the PMT regs */
if (device_may_wakeup(priv->device)) {
priv->hw->mac->pmt(priv->hw, priv->wolopts);
priv->irq_wake = 1;
} else {
- stmmac_set_mac(priv->ioaddr, false);
+ priv->hw->mac->set_mac(priv->ioaddr, false);
pinctrl_pm_select_sleep_state(priv->device);
/* Disable clock in case of PWM is off */
clk_disable(priv->plat->pclk);
@@ -3440,6 +4299,31 @@ int stmmac_suspend(struct device *dev)
EXPORT_SYMBOL_GPL(stmmac_suspend);
/**
+ * stmmac_reset_queues_param - reset queue parameters
+ * @dev: device pointer
+ */
+static void stmmac_reset_queues_param(struct stmmac_priv *priv)
+{
+ u32 rx_cnt = priv->plat->rx_queues_to_use;
+ u32 tx_cnt = priv->plat->tx_queues_to_use;
+ u32 queue;
+
+ for (queue = 0; queue < rx_cnt; queue++) {
+ struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+ rx_q->cur_rx = 0;
+ rx_q->dirty_rx = 0;
+ }
+
+ for (queue = 0; queue < tx_cnt; queue++) {
+ struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+ tx_q->cur_tx = 0;
+ tx_q->dirty_tx = 0;
+ }
+}
+
+/**
* stmmac_resume - resume callback
* @dev: device pointer
* Description: when resume this function is invoked to setup the DMA and CORE
@@ -3479,10 +4363,8 @@ int stmmac_resume(struct device *dev)
spin_lock_irqsave(&priv->lock, flags);
- priv->cur_rx = 0;
- priv->dirty_rx = 0;
- priv->dirty_tx = 0;
- priv->cur_tx = 0;
+ stmmac_reset_queues_param(priv);
+
/* reset private mss value to force mss context settings at
* next tso xmit (only used for gmac4).
*/
@@ -3494,9 +4376,9 @@ int stmmac_resume(struct device *dev)
stmmac_init_tx_coalesce(priv);
stmmac_set_rx_mode(ndev);
- napi_enable(&priv->napi);
+ stmmac_enable_all_queues(priv);
- netif_start_queue(ndev);
+ stmmac_start_all_queues(priv);
spin_unlock_irqrestore(&priv->lock, flags);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index 5c9e4622..a224d7b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -88,6 +88,17 @@ static void stmmac_default_data(struct plat_stmmacenet_data *plat)
/* Set the maxmtu to a default of JUMBO_LEN */
plat->maxmtu = JUMBO_LEN;
+
+ /* Set default number of RX and TX queues to use */
+ plat->tx_queues_to_use = 1;
+ plat->rx_queues_to_use = 1;
+
+ /* Disable Priority config by default */
+ plat->tx_queues_cfg[0].use_prio = false;
+ plat->rx_queues_cfg[0].use_prio = false;
+
+ /* Disable RX queues routing by default */
+ plat->rx_queues_cfg[0].pkt_route = 0x0;
}
static int quark_default_data(struct plat_stmmacenet_data *plat,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 433a842..7fc3a1e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -108,7 +108,7 @@ static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev)
if (!np)
return NULL;
- axi = kzalloc(sizeof(*axi), GFP_KERNEL);
+ axi = devm_kzalloc(&pdev->dev, sizeof(*axi), GFP_KERNEL);
if (!axi) {
of_node_put(np);
return ERR_PTR(-ENOMEM);
@@ -132,6 +132,155 @@ static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev)
}
/**
+ * stmmac_mtl_setup - parse DT parameters for multiple queues configuration
+ * @pdev: platform device
+ */
+static void stmmac_mtl_setup(struct platform_device *pdev,
+ struct plat_stmmacenet_data *plat)
+{
+ struct device_node *q_node;
+ struct device_node *rx_node;
+ struct device_node *tx_node;
+ u8 queue = 0;
+
+ /* For backwards-compatibility with device trees that don't have any
+ * snps,mtl-rx-config or snps,mtl-tx-config properties, we fall back
+ * to one RX and TX queues each.
+ */
+ plat->rx_queues_to_use = 1;
+ plat->tx_queues_to_use = 1;
+
+ rx_node = of_parse_phandle(pdev->dev.of_node, "snps,mtl-rx-config", 0);
+ if (!rx_node)
+ return;
+
+ tx_node = of_parse_phandle(pdev->dev.of_node, "snps,mtl-tx-config", 0);
+ if (!tx_node) {
+ of_node_put(rx_node);
+ return;
+ }
+
+ /* Processing RX queues common config */
+ if (of_property_read_u8(rx_node, "snps,rx-queues-to-use",
+ &plat->rx_queues_to_use))
+ plat->rx_queues_to_use = 1;
+
+ if (of_property_read_bool(rx_node, "snps,rx-sched-sp"))
+ plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP;
+ else if (of_property_read_bool(rx_node, "snps,rx-sched-wsp"))
+ plat->rx_sched_algorithm = MTL_RX_ALGORITHM_WSP;
+ else
+ plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP;
+
+ /* Processing individual RX queue config */
+ for_each_child_of_node(rx_node, q_node) {
+ if (queue >= plat->rx_queues_to_use)
+ break;
+
+ if (of_property_read_bool(q_node, "snps,dcb-algorithm"))
+ plat->rx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB;
+ else if (of_property_read_bool(q_node, "snps,avb-algorithm"))
+ plat->rx_queues_cfg[queue].mode_to_use = MTL_QUEUE_AVB;
+ else
+ plat->rx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB;
+
+ if (of_property_read_u8(q_node, "snps,map-to-dma-channel",
+ &plat->rx_queues_cfg[queue].chan))
+ plat->rx_queues_cfg[queue].chan = queue;
+ /* TODO: Dynamic mapping to be included in the future */
+
+ if (of_property_read_u32(q_node, "snps,priority",
+ &plat->rx_queues_cfg[queue].prio)) {
+ plat->rx_queues_cfg[queue].prio = 0;
+ plat->rx_queues_cfg[queue].use_prio = false;
+ } else {
+ plat->rx_queues_cfg[queue].use_prio = true;
+ }
+
+ /* RX queue specific packet type routing */
+ if (of_property_read_bool(q_node, "snps,route-avcp"))
+ plat->rx_queues_cfg[queue].pkt_route = PACKET_AVCPQ;
+ else if (of_property_read_bool(q_node, "snps,route-ptp"))
+ plat->rx_queues_cfg[queue].pkt_route = PACKET_PTPQ;
+ else if (of_property_read_bool(q_node, "snps,route-dcbcp"))
+ plat->rx_queues_cfg[queue].pkt_route = PACKET_DCBCPQ;
+ else if (of_property_read_bool(q_node, "snps,route-up"))
+ plat->rx_queues_cfg[queue].pkt_route = PACKET_UPQ;
+ else if (of_property_read_bool(q_node, "snps,route-multi-broad"))
+ plat->rx_queues_cfg[queue].pkt_route = PACKET_MCBCQ;
+ else
+ plat->rx_queues_cfg[queue].pkt_route = 0x0;
+
+ queue++;
+ }
+
+ /* Processing TX queues common config */
+ if (of_property_read_u8(tx_node, "snps,tx-queues-to-use",
+ &plat->tx_queues_to_use))
+ plat->tx_queues_to_use = 1;
+
+ if (of_property_read_bool(tx_node, "snps,tx-sched-wrr"))
+ plat->tx_sched_algorithm = MTL_TX_ALGORITHM_WRR;
+ else if (of_property_read_bool(tx_node, "snps,tx-sched-wfq"))
+ plat->tx_sched_algorithm = MTL_TX_ALGORITHM_WFQ;
+ else if (of_property_read_bool(tx_node, "snps,tx-sched-dwrr"))
+ plat->tx_sched_algorithm = MTL_TX_ALGORITHM_DWRR;
+ else if (of_property_read_bool(tx_node, "snps,tx-sched-sp"))
+ plat->tx_sched_algorithm = MTL_TX_ALGORITHM_SP;
+ else
+ plat->tx_sched_algorithm = MTL_TX_ALGORITHM_SP;
+
+ queue = 0;
+
+ /* Processing individual TX queue config */
+ for_each_child_of_node(tx_node, q_node) {
+ if (queue >= plat->tx_queues_to_use)
+ break;
+
+ if (of_property_read_u8(q_node, "snps,weight",
+ &plat->tx_queues_cfg[queue].weight))
+ plat->tx_queues_cfg[queue].weight = 0x10 + queue;
+
+ if (of_property_read_bool(q_node, "snps,dcb-algorithm")) {
+ plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB;
+ } else if (of_property_read_bool(q_node,
+ "snps,avb-algorithm")) {
+ plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_AVB;
+
+ /* Credit Base Shaper parameters used by AVB */
+ if (of_property_read_u32(q_node, "snps,send_slope",
+ &plat->tx_queues_cfg[queue].send_slope))
+ plat->tx_queues_cfg[queue].send_slope = 0x0;
+ if (of_property_read_u32(q_node, "snps,idle_slope",
+ &plat->tx_queues_cfg[queue].idle_slope))
+ plat->tx_queues_cfg[queue].idle_slope = 0x0;
+ if (of_property_read_u32(q_node, "snps,high_credit",
+ &plat->tx_queues_cfg[queue].high_credit))
+ plat->tx_queues_cfg[queue].high_credit = 0x0;
+ if (of_property_read_u32(q_node, "snps,low_credit",
+ &plat->tx_queues_cfg[queue].low_credit))
+ plat->tx_queues_cfg[queue].low_credit = 0x0;
+ } else {
+ plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB;
+ }
+
+ if (of_property_read_u32(q_node, "snps,priority",
+ &plat->tx_queues_cfg[queue].prio)) {
+ plat->tx_queues_cfg[queue].prio = 0;
+ plat->tx_queues_cfg[queue].use_prio = false;
+ } else {
+ plat->tx_queues_cfg[queue].use_prio = true;
+ }
+
+ queue++;
+ }
+
+ of_node_put(rx_node);
+ of_node_put(tx_node);
+ of_node_put(q_node);
+}
+
+/**
* stmmac_dt_phy - parse device-tree driver parameters to allocate PHY resources
* @plat: driver data platform structure
* @np: device tree node
@@ -340,6 +489,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
plat->axi = stmmac_axi_setup(pdev);
+ stmmac_mtl_setup(pdev, plat);
+
/* clock setup */
plat->stmmac_clk = devm_clk_get(&pdev->dev,
STMMAC_RESOURCE_NAME);
@@ -359,13 +510,12 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
clk_prepare_enable(plat->pclk);
/* Fall-back to main clock in case of no PTP ref is passed */
- plat->clk_ptp_ref = devm_clk_get(&pdev->dev, "clk_ptp_ref");
+ plat->clk_ptp_ref = devm_clk_get(&pdev->dev, "ptp_ref");
if (IS_ERR(plat->clk_ptp_ref)) {
plat->clk_ptp_rate = clk_get_rate(plat->stmmac_clk);
plat->clk_ptp_ref = NULL;
dev_warn(&pdev->dev, "PTP uses main clock\n");
} else {
- clk_prepare_enable(plat->clk_ptp_ref);
plat->clk_ptp_rate = clk_get_rate(plat->clk_ptp_ref);
dev_dbg(&pdev->dev, "PTP rate %d\n", plat->clk_ptp_rate);
}
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index 0e8e89f..382993c 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -691,7 +691,8 @@ static void cas_mif_poll(struct cas *cp, const int enable)
}
/* Must be invoked under cp->lock */
-static void cas_begin_auto_negotiation(struct cas *cp, struct ethtool_cmd *ep)
+static void cas_begin_auto_negotiation(struct cas *cp,
+ const struct ethtool_link_ksettings *ep)
{
u16 ctl;
#if 1
@@ -704,16 +705,16 @@ static void cas_begin_auto_negotiation(struct cas *cp, struct ethtool_cmd *ep)
if (!ep)
goto start_aneg;
lcntl = cp->link_cntl;
- if (ep->autoneg == AUTONEG_ENABLE)
+ if (ep->base.autoneg == AUTONEG_ENABLE) {
cp->link_cntl = BMCR_ANENABLE;
- else {
- u32 speed = ethtool_cmd_speed(ep);
+ } else {
+ u32 speed = ep->base.speed;
cp->link_cntl = 0;
if (speed == SPEED_100)
cp->link_cntl |= BMCR_SPEED100;
else if (speed == SPEED_1000)
cp->link_cntl |= CAS_BMCR_SPEED1000;
- if (ep->duplex == DUPLEX_FULL)
+ if (ep->base.duplex == DUPLEX_FULL)
cp->link_cntl |= BMCR_FULLDPLX;
}
#if 1
@@ -4528,19 +4529,21 @@ static void cas_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info
strlcpy(info->bus_info, pci_name(cp->pdev), sizeof(info->bus_info));
}
-static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int cas_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
struct cas *cp = netdev_priv(dev);
u16 bmcr;
int full_duplex, speed, pause;
unsigned long flags;
enum link_state linkstate = link_up;
+ u32 supported, advertising;
- cmd->advertising = 0;
- cmd->supported = SUPPORTED_Autoneg;
+ advertising = 0;
+ supported = SUPPORTED_Autoneg;
if (cp->cas_flags & CAS_FLAG_1000MB_CAP) {
- cmd->supported |= SUPPORTED_1000baseT_Full;
- cmd->advertising |= ADVERTISED_1000baseT_Full;
+ supported |= SUPPORTED_1000baseT_Full;
+ advertising |= ADVERTISED_1000baseT_Full;
}
/* Record PHY settings if HW is on. */
@@ -4548,17 +4551,15 @@ static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
bmcr = 0;
linkstate = cp->lstate;
if (CAS_PHY_MII(cp->phy_type)) {
- cmd->port = PORT_MII;
- cmd->transceiver = (cp->cas_flags & CAS_FLAG_SATURN) ?
- XCVR_INTERNAL : XCVR_EXTERNAL;
- cmd->phy_address = cp->phy_addr;
- cmd->advertising |= ADVERTISED_TP | ADVERTISED_MII |
+ cmd->base.port = PORT_MII;
+ cmd->base.phy_address = cp->phy_addr;
+ advertising |= ADVERTISED_TP | ADVERTISED_MII |
ADVERTISED_10baseT_Half |
ADVERTISED_10baseT_Full |
ADVERTISED_100baseT_Half |
ADVERTISED_100baseT_Full;
- cmd->supported |=
+ supported |=
(SUPPORTED_10baseT_Half |
SUPPORTED_10baseT_Full |
SUPPORTED_100baseT_Half |
@@ -4574,11 +4575,10 @@ static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
}
} else {
- cmd->port = PORT_FIBRE;
- cmd->transceiver = XCVR_INTERNAL;
- cmd->phy_address = 0;
- cmd->supported |= SUPPORTED_FIBRE;
- cmd->advertising |= ADVERTISED_FIBRE;
+ cmd->base.port = PORT_FIBRE;
+ cmd->base.phy_address = 0;
+ supported |= SUPPORTED_FIBRE;
+ advertising |= ADVERTISED_FIBRE;
if (cp->hw_running) {
/* pcs uses the same bits as mii */
@@ -4590,21 +4590,20 @@ static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
spin_unlock_irqrestore(&cp->lock, flags);
if (bmcr & BMCR_ANENABLE) {
- cmd->advertising |= ADVERTISED_Autoneg;
- cmd->autoneg = AUTONEG_ENABLE;
- ethtool_cmd_speed_set(cmd, ((speed == 10) ?
+ advertising |= ADVERTISED_Autoneg;
+ cmd->base.autoneg = AUTONEG_ENABLE;
+ cmd->base.speed = ((speed == 10) ?
SPEED_10 :
((speed == 1000) ?
- SPEED_1000 : SPEED_100)));
- cmd->duplex = full_duplex ? DUPLEX_FULL : DUPLEX_HALF;
+ SPEED_1000 : SPEED_100));
+ cmd->base.duplex = full_duplex ? DUPLEX_FULL : DUPLEX_HALF;
} else {
- cmd->autoneg = AUTONEG_DISABLE;
- ethtool_cmd_speed_set(cmd, ((bmcr & CAS_BMCR_SPEED1000) ?
+ cmd->base.autoneg = AUTONEG_DISABLE;
+ cmd->base.speed = ((bmcr & CAS_BMCR_SPEED1000) ?
SPEED_1000 :
((bmcr & BMCR_SPEED100) ?
- SPEED_100 : SPEED_10)));
- cmd->duplex =
- (bmcr & BMCR_FULLDPLX) ?
+ SPEED_100 : SPEED_10));
+ cmd->base.duplex = (bmcr & BMCR_FULLDPLX) ?
DUPLEX_FULL : DUPLEX_HALF;
}
if (linkstate != link_up) {
@@ -4619,39 +4618,46 @@ static int cas_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
* settings that we configured.
*/
if (cp->link_cntl & BMCR_ANENABLE) {
- ethtool_cmd_speed_set(cmd, 0);
- cmd->duplex = 0xff;
+ cmd->base.speed = 0;
+ cmd->base.duplex = 0xff;
} else {
- ethtool_cmd_speed_set(cmd, SPEED_10);
+ cmd->base.speed = SPEED_10;
if (cp->link_cntl & BMCR_SPEED100) {
- ethtool_cmd_speed_set(cmd, SPEED_100);
+ cmd->base.speed = SPEED_100;
} else if (cp->link_cntl & CAS_BMCR_SPEED1000) {
- ethtool_cmd_speed_set(cmd, SPEED_1000);
+ cmd->base.speed = SPEED_1000;
}
- cmd->duplex = (cp->link_cntl & BMCR_FULLDPLX)?
+ cmd->base.duplex = (cp->link_cntl & BMCR_FULLDPLX) ?
DUPLEX_FULL : DUPLEX_HALF;
}
}
+
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ supported);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+ advertising);
+
return 0;
}
-static int cas_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int cas_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
{
struct cas *cp = netdev_priv(dev);
unsigned long flags;
- u32 speed = ethtool_cmd_speed(cmd);
+ u32 speed = cmd->base.speed;
/* Verify the settings we care about. */
- if (cmd->autoneg != AUTONEG_ENABLE &&
- cmd->autoneg != AUTONEG_DISABLE)
+ if (cmd->base.autoneg != AUTONEG_ENABLE &&
+ cmd->base.autoneg != AUTONEG_DISABLE)
return -EINVAL;
- if (cmd->autoneg == AUTONEG_DISABLE &&
+ if (cmd->base.autoneg == AUTONEG_DISABLE &&
((speed != SPEED_1000 &&
speed != SPEED_100 &&
speed != SPEED_10) ||
- (cmd->duplex != DUPLEX_HALF &&
- cmd->duplex != DUPLEX_FULL)))
+ (cmd->base.duplex != DUPLEX_HALF &&
+ cmd->base.duplex != DUPLEX_FULL)))
return -EINVAL;
/* Apply settings and restart link process. */
@@ -4753,8 +4759,6 @@ static void cas_get_ethtool_stats(struct net_device *dev,
static const struct ethtool_ops cas_ethtool_ops = {
.get_drvinfo = cas_get_drvinfo,
- .get_settings = cas_get_settings,
- .set_settings = cas_set_settings,
.nway_reset = cas_nway_reset,
.get_link = cas_get_link,
.get_msglevel = cas_get_msglevel,
@@ -4764,6 +4768,8 @@ static const struct ethtool_ops cas_ethtool_ops = {
.get_sset_count = cas_get_sset_count,
.get_strings = cas_get_strings,
.get_ethtool_stats = cas_get_ethtool_stats,
+ .get_link_ksettings = cas_get_link_ksettings,
+ .set_link_ksettings = cas_set_link_ksettings,
};
static int cas_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c
index 89952de..5a90fed 100644
--- a/drivers/net/ethernet/sun/ldmvsw.c
+++ b/drivers/net/ethernet/sun/ldmvsw.c
@@ -1,6 +1,6 @@
/* ldmvsw.c: Sun4v LDOM Virtual Switch Driver.
*
- * Copyright (C) 2016 Oracle. All rights reserved.
+ * Copyright (C) 2016-2017 Oracle. All rights reserved.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -41,8 +41,8 @@
static u8 vsw_port_hwaddr[ETH_ALEN] = {0xFE, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF};
#define DRV_MODULE_NAME "ldmvsw"
-#define DRV_MODULE_VERSION "1.1"
-#define DRV_MODULE_RELDATE "February 3, 2017"
+#define DRV_MODULE_VERSION "1.2"
+#define DRV_MODULE_RELDATE "March 4, 2017"
static char version[] =
DRV_MODULE_NAME " " DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")";
@@ -123,6 +123,20 @@ static void vsw_set_rx_mode(struct net_device *dev)
return sunvnet_set_rx_mode_common(dev, port->vp);
}
+int ldmvsw_open(struct net_device *dev)
+{
+ struct vnet_port *port = netdev_priv(dev);
+ struct vio_driver_state *vio = &port->vio;
+
+ /* reset the channel */
+ vio_link_state_change(vio, LDC_EVENT_RESET);
+ vnet_port_reset(port);
+ vio_port_up(vio);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ldmvsw_open);
+
#ifdef CONFIG_NET_POLL_CONTROLLER
static void vsw_poll_controller(struct net_device *dev)
{
@@ -133,7 +147,7 @@ static void vsw_poll_controller(struct net_device *dev)
#endif
static const struct net_device_ops vsw_ops = {
- .ndo_open = sunvnet_open_common,
+ .ndo_open = ldmvsw_open,
.ndo_stop = sunvnet_close_common,
.ndo_set_rx_mode = vsw_set_rx_mode,
.ndo_set_mac_address = sunvnet_set_mac_addr_common,
@@ -365,6 +379,11 @@ static int vsw_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
napi_enable(&port->napi);
vio_port_up(&port->vio);
+ /* assure no carrier until we receive an LDC_EVENT_UP,
+ * even if the vsw config script tries to force us up
+ */
+ netif_carrier_off(dev);
+
netdev_info(dev, "LDOM vsw-port %pM\n", dev->dev_addr);
pr_info("%s: PORT ( remote-mac %pM%s )\n", dev->name,
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 5797805..2dcca24 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -6813,7 +6813,8 @@ static void niu_get_drvinfo(struct net_device *dev,
sizeof(info->bus_info));
}
-static int niu_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int niu_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
struct niu *np = netdev_priv(dev);
struct niu_link_config *lp;
@@ -6821,28 +6822,30 @@ static int niu_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
lp = &np->link_config;
memset(cmd, 0, sizeof(*cmd));
- cmd->phy_address = np->phy_addr;
- cmd->supported = lp->supported;
- cmd->advertising = lp->active_advertising;
- cmd->autoneg = lp->active_autoneg;
- ethtool_cmd_speed_set(cmd, lp->active_speed);
- cmd->duplex = lp->active_duplex;
- cmd->port = (np->flags & NIU_FLAGS_FIBER) ? PORT_FIBRE : PORT_TP;
- cmd->transceiver = (np->flags & NIU_FLAGS_XCVR_SERDES) ?
- XCVR_EXTERNAL : XCVR_INTERNAL;
+ cmd->base.phy_address = np->phy_addr;
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ lp->supported);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+ lp->active_advertising);
+ cmd->base.autoneg = lp->active_autoneg;
+ cmd->base.speed = lp->active_speed;
+ cmd->base.duplex = lp->active_duplex;
+ cmd->base.port = (np->flags & NIU_FLAGS_FIBER) ? PORT_FIBRE : PORT_TP;
return 0;
}
-static int niu_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int niu_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
{
struct niu *np = netdev_priv(dev);
struct niu_link_config *lp = &np->link_config;
- lp->advertising = cmd->advertising;
- lp->speed = ethtool_cmd_speed(cmd);
- lp->duplex = cmd->duplex;
- lp->autoneg = cmd->autoneg;
+ ethtool_convert_link_mode_to_legacy_u32(&lp->advertising,
+ cmd->link_modes.advertising);
+ lp->speed = cmd->base.speed;
+ lp->duplex = cmd->base.duplex;
+ lp->autoneg = cmd->base.autoneg;
return niu_init_link(np);
}
@@ -7902,14 +7905,14 @@ static const struct ethtool_ops niu_ethtool_ops = {
.nway_reset = niu_nway_reset,
.get_eeprom_len = niu_get_eeprom_len,
.get_eeprom = niu_get_eeprom,
- .get_settings = niu_get_settings,
- .set_settings = niu_set_settings,
.get_strings = niu_get_strings,
.get_sset_count = niu_get_sset_count,
.get_ethtool_stats = niu_get_ethtool_stats,
.set_phys_id = niu_set_phys_id,
.get_rxnfc = niu_get_nfc,
.set_rxnfc = niu_set_nfc,
+ .get_link_ksettings = niu_get_link_ksettings,
+ .set_link_ksettings = niu_set_link_ksettings,
};
static int niu_ldg_assign_ldn(struct niu *np, struct niu_parent *parent,
diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c
index c4caf48..3189722 100644
--- a/drivers/net/ethernet/sun/sunbmac.c
+++ b/drivers/net/ethernet/sun/sunbmac.c
@@ -169,7 +169,7 @@ static void bigmac_stop(struct bigmac *bp)
static void bigmac_get_counters(struct bigmac *bp, void __iomem *bregs)
{
- struct net_device_stats *stats = &bp->enet_stats;
+ struct net_device_stats *stats = &bp->dev->stats;
stats->rx_crc_errors += sbus_readl(bregs + BMAC_RCRCECTR);
sbus_writel(0, bregs + BMAC_RCRCECTR);
@@ -774,8 +774,8 @@ static void bigmac_tx(struct bigmac *bp)
if (this->tx_flags & TXD_OWN)
break;
skb = bp->tx_skbs[elem];
- bp->enet_stats.tx_packets++;
- bp->enet_stats.tx_bytes += skb->len;
+ dev->stats.tx_packets++;
+ dev->stats.tx_bytes += skb->len;
dma_unmap_single(&bp->bigmac_op->dev,
this->tx_addr, skb->len,
DMA_TO_DEVICE);
@@ -811,12 +811,12 @@ static void bigmac_rx(struct bigmac *bp)
/* Check for errors. */
if (len < ETH_ZLEN) {
- bp->enet_stats.rx_errors++;
- bp->enet_stats.rx_length_errors++;
+ bp->dev->stats.rx_errors++;
+ bp->dev->stats.rx_length_errors++;
drop_it:
/* Return it to the BigMAC. */
- bp->enet_stats.rx_dropped++;
+ bp->dev->stats.rx_dropped++;
this->rx_flags =
(RXD_OWN | ((RX_BUF_ALLOC_SIZE - 34) & RXD_LENGTH));
goto next;
@@ -875,8 +875,8 @@ static void bigmac_rx(struct bigmac *bp)
/* No checksums done by the BigMAC ;-( */
skb->protocol = eth_type_trans(skb, bp->dev);
netif_rx(skb);
- bp->enet_stats.rx_packets++;
- bp->enet_stats.rx_bytes += len;
+ bp->dev->stats.rx_packets++;
+ bp->dev->stats.rx_bytes += len;
next:
elem = NEXT_RX(elem);
this = &rxbase[elem];
@@ -987,7 +987,7 @@ static struct net_device_stats *bigmac_get_stats(struct net_device *dev)
struct bigmac *bp = netdev_priv(dev);
bigmac_get_counters(bp, bp->bregs);
- return &bp->enet_stats;
+ return &dev->stats;
}
static void bigmac_set_multicast(struct net_device *dev)
diff --git a/drivers/net/ethernet/sun/sunbmac.h b/drivers/net/ethernet/sun/sunbmac.h
index 532fc56..ee56930 100644
--- a/drivers/net/ethernet/sun/sunbmac.h
+++ b/drivers/net/ethernet/sun/sunbmac.h
@@ -311,7 +311,6 @@ struct bigmac {
enum bigmac_timer_state timer_state;
unsigned int timer_ticks;
- struct net_device_stats enet_stats;
struct platform_device *qec_op;
struct platform_device *bigmac_op;
struct net_device *dev;
diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c
index 5c5952e..fa607d0 100644
--- a/drivers/net/ethernet/sun/sungem.c
+++ b/drivers/net/ethernet/sun/sungem.c
@@ -1250,12 +1250,18 @@ static void gem_stop_dma(struct gem *gp)
// XXX dbl check what that function should do when called on PCS PHY
-static void gem_begin_auto_negotiation(struct gem *gp, struct ethtool_cmd *ep)
+static void gem_begin_auto_negotiation(struct gem *gp,
+ const struct ethtool_link_ksettings *ep)
{
u32 advertise, features;
int autoneg;
int speed;
int duplex;
+ u32 advertising;
+
+ if (ep)
+ ethtool_convert_link_mode_to_legacy_u32(
+ &advertising, ep->link_modes.advertising);
if (gp->phy_type != phy_mii_mdio0 &&
gp->phy_type != phy_mii_mdio1)
@@ -1278,13 +1284,13 @@ static void gem_begin_auto_negotiation(struct gem *gp, struct ethtool_cmd *ep)
/* Setup link parameters */
if (!ep)
goto start_aneg;
- if (ep->autoneg == AUTONEG_ENABLE) {
- advertise = ep->advertising;
+ if (ep->base.autoneg == AUTONEG_ENABLE) {
+ advertise = advertising;
autoneg = 1;
} else {
autoneg = 0;
- speed = ethtool_cmd_speed(ep);
- duplex = ep->duplex;
+ speed = ep->base.speed;
+ duplex = ep->base.duplex;
}
start_aneg:
@@ -2515,85 +2521,96 @@ static void gem_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info
strlcpy(info->bus_info, pci_name(gp->pdev), sizeof(info->bus_info));
}
-static int gem_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int gem_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
struct gem *gp = netdev_priv(dev);
+ u32 supported, advertising;
if (gp->phy_type == phy_mii_mdio0 ||
gp->phy_type == phy_mii_mdio1) {
if (gp->phy_mii.def)
- cmd->supported = gp->phy_mii.def->features;
+ supported = gp->phy_mii.def->features;
else
- cmd->supported = (SUPPORTED_10baseT_Half |
+ supported = (SUPPORTED_10baseT_Half |
SUPPORTED_10baseT_Full);
/* XXX hardcoded stuff for now */
- cmd->port = PORT_MII;
- cmd->transceiver = XCVR_EXTERNAL;
- cmd->phy_address = 0; /* XXX fixed PHYAD */
+ cmd->base.port = PORT_MII;
+ cmd->base.phy_address = 0; /* XXX fixed PHYAD */
/* Return current PHY settings */
- cmd->autoneg = gp->want_autoneg;
- ethtool_cmd_speed_set(cmd, gp->phy_mii.speed);
- cmd->duplex = gp->phy_mii.duplex;
- cmd->advertising = gp->phy_mii.advertising;
+ cmd->base.autoneg = gp->want_autoneg;
+ cmd->base.speed = gp->phy_mii.speed;
+ cmd->base.duplex = gp->phy_mii.duplex;
+ advertising = gp->phy_mii.advertising;
/* If we started with a forced mode, we don't have a default
* advertise set, we need to return something sensible so
* userland can re-enable autoneg properly.
*/
- if (cmd->advertising == 0)
- cmd->advertising = cmd->supported;
+ if (advertising == 0)
+ advertising = supported;
} else { // XXX PCS ?
- cmd->supported =
+ supported =
(SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full |
SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full |
SUPPORTED_Autoneg);
- cmd->advertising = cmd->supported;
- ethtool_cmd_speed_set(cmd, 0);
- cmd->duplex = cmd->port = cmd->phy_address =
- cmd->transceiver = cmd->autoneg = 0;
+ advertising = supported;
+ cmd->base.speed = 0;
+ cmd->base.duplex = 0;
+ cmd->base.port = 0;
+ cmd->base.phy_address = 0;
+ cmd->base.autoneg = 0;
/* serdes means usually a Fibre connector, with most fixed */
if (gp->phy_type == phy_serdes) {
- cmd->port = PORT_FIBRE;
- cmd->supported = (SUPPORTED_1000baseT_Half |
+ cmd->base.port = PORT_FIBRE;
+ supported = (SUPPORTED_1000baseT_Half |
SUPPORTED_1000baseT_Full |
SUPPORTED_FIBRE | SUPPORTED_Autoneg |
SUPPORTED_Pause | SUPPORTED_Asym_Pause);
- cmd->advertising = cmd->supported;
- cmd->transceiver = XCVR_INTERNAL;
+ advertising = supported;
if (gp->lstate == link_up)
- ethtool_cmd_speed_set(cmd, SPEED_1000);
- cmd->duplex = DUPLEX_FULL;
- cmd->autoneg = 1;
+ cmd->base.speed = SPEED_1000;
+ cmd->base.duplex = DUPLEX_FULL;
+ cmd->base.autoneg = 1;
}
}
- cmd->maxtxpkt = cmd->maxrxpkt = 0;
+
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ supported);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+ advertising);
return 0;
}
-static int gem_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int gem_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
{
struct gem *gp = netdev_priv(dev);
- u32 speed = ethtool_cmd_speed(cmd);
+ u32 speed = cmd->base.speed;
+ u32 advertising;
+
+ ethtool_convert_link_mode_to_legacy_u32(&advertising,
+ cmd->link_modes.advertising);
/* Verify the settings we care about. */
- if (cmd->autoneg != AUTONEG_ENABLE &&
- cmd->autoneg != AUTONEG_DISABLE)
+ if (cmd->base.autoneg != AUTONEG_ENABLE &&
+ cmd->base.autoneg != AUTONEG_DISABLE)
return -EINVAL;
- if (cmd->autoneg == AUTONEG_ENABLE &&
- cmd->advertising == 0)
+ if (cmd->base.autoneg == AUTONEG_ENABLE &&
+ advertising == 0)
return -EINVAL;
- if (cmd->autoneg == AUTONEG_DISABLE &&
+ if (cmd->base.autoneg == AUTONEG_DISABLE &&
((speed != SPEED_1000 &&
speed != SPEED_100 &&
speed != SPEED_10) ||
- (cmd->duplex != DUPLEX_HALF &&
- cmd->duplex != DUPLEX_FULL)))
+ (cmd->base.duplex != DUPLEX_HALF &&
+ cmd->base.duplex != DUPLEX_FULL)))
return -EINVAL;
/* Apply settings and restart link process. */
@@ -2666,13 +2683,13 @@ static int gem_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
static const struct ethtool_ops gem_ethtool_ops = {
.get_drvinfo = gem_get_drvinfo,
.get_link = ethtool_op_get_link,
- .get_settings = gem_get_settings,
- .set_settings = gem_set_settings,
.nway_reset = gem_nway_reset,
.get_msglevel = gem_get_msglevel,
.set_msglevel = gem_set_msglevel,
.get_wol = gem_get_wol,
.set_wol = gem_set_wol,
+ .get_link_ksettings = gem_get_link_ksettings,
+ .set_link_ksettings = gem_set_link_ksettings,
};
static int gem_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c
index 72ff05c..a6cc9a2d 100644
--- a/drivers/net/ethernet/sun/sunhme.c
+++ b/drivers/net/ethernet/sun/sunhme.c
@@ -933,7 +933,7 @@ static void happy_meal_stop(struct happy_meal *hp, void __iomem *gregs)
/* hp->happy_lock must be held */
static void happy_meal_get_counters(struct happy_meal *hp, void __iomem *bregs)
{
- struct net_device_stats *stats = &hp->net_stats;
+ struct net_device_stats *stats = &hp->dev->stats;
stats->rx_crc_errors += hme_read32(hp, bregs + BMAC_RCRCECTR);
hme_write32(hp, bregs + BMAC_RCRCECTR, 0);
@@ -1294,9 +1294,10 @@ static void happy_meal_init_rings(struct happy_meal *hp)
}
/* hp->happy_lock must be held */
-static void happy_meal_begin_auto_negotiation(struct happy_meal *hp,
- void __iomem *tregs,
- struct ethtool_cmd *ep)
+static void
+happy_meal_begin_auto_negotiation(struct happy_meal *hp,
+ void __iomem *tregs,
+ const struct ethtool_link_ksettings *ep)
{
int timeout;
@@ -1309,7 +1310,7 @@ static void happy_meal_begin_auto_negotiation(struct happy_meal *hp,
/* XXX Check BMSR_ANEGCAPABLE, should not be necessary though. */
hp->sw_advertise = happy_meal_tcvr_read(hp, tregs, MII_ADVERTISE);
- if (ep == NULL || ep->autoneg == AUTONEG_ENABLE) {
+ if (!ep || ep->base.autoneg == AUTONEG_ENABLE) {
/* Advertise everything we can support. */
if (hp->sw_bmsr & BMSR_10HALF)
hp->sw_advertise |= (ADVERTISE_10HALF);
@@ -1384,14 +1385,14 @@ static void happy_meal_begin_auto_negotiation(struct happy_meal *hp,
/* Disable auto-negotiation in BMCR, enable the duplex and
* speed setting, init the timer state machine, and fire it off.
*/
- if (ep == NULL || ep->autoneg == AUTONEG_ENABLE) {
+ if (!ep || ep->base.autoneg == AUTONEG_ENABLE) {
hp->sw_bmcr = BMCR_SPEED100;
} else {
- if (ethtool_cmd_speed(ep) == SPEED_100)
+ if (ep->base.speed == SPEED_100)
hp->sw_bmcr = BMCR_SPEED100;
else
hp->sw_bmcr = 0;
- if (ep->duplex == DUPLEX_FULL)
+ if (ep->base.duplex == DUPLEX_FULL)
hp->sw_bmcr |= BMCR_FULLDPLX;
}
happy_meal_tcvr_write(hp, tregs, MII_BMCR, hp->sw_bmcr);
@@ -1946,7 +1947,7 @@ static void happy_meal_tx(struct happy_meal *hp)
break;
}
hp->tx_skbs[elem] = NULL;
- hp->net_stats.tx_bytes += skb->len;
+ dev->stats.tx_bytes += skb->len;
for (frag = 0; frag <= skb_shinfo(skb)->nr_frags; frag++) {
dma_addr = hme_read_desc32(hp, &this->tx_addr);
@@ -1963,7 +1964,7 @@ static void happy_meal_tx(struct happy_meal *hp)
}
dev_kfree_skb_irq(skb);
- hp->net_stats.tx_packets++;
+ dev->stats.tx_packets++;
}
hp->tx_old = elem;
TXD((">"));
@@ -2008,17 +2009,17 @@ static void happy_meal_rx(struct happy_meal *hp, struct net_device *dev)
/* Check for errors. */
if ((len < ETH_ZLEN) || (flags & RXFLAG_OVERFLOW)) {
RXD(("ERR(%08x)]", flags));
- hp->net_stats.rx_errors++;
+ dev->stats.rx_errors++;
if (len < ETH_ZLEN)
- hp->net_stats.rx_length_errors++;
+ dev->stats.rx_length_errors++;
if (len & (RXFLAG_OVERFLOW >> 16)) {
- hp->net_stats.rx_over_errors++;
- hp->net_stats.rx_fifo_errors++;
+ dev->stats.rx_over_errors++;
+ dev->stats.rx_fifo_errors++;
}
/* Return it to the Happy meal. */
drop_it:
- hp->net_stats.rx_dropped++;
+ dev->stats.rx_dropped++;
hme_write_rxd(hp, this,
(RXFLAG_OWN|((RX_BUF_ALLOC_SIZE-RX_OFFSET)<<16)),
dma_addr);
@@ -2083,8 +2084,8 @@ static void happy_meal_rx(struct happy_meal *hp, struct net_device *dev)
skb->protocol = eth_type_trans(skb, dev);
netif_rx(skb);
- hp->net_stats.rx_packets++;
- hp->net_stats.rx_bytes += len;
+ dev->stats.rx_packets++;
+ dev->stats.rx_bytes += len;
next:
elem = NEXT_RX(elem);
this = &rxbase[elem];
@@ -2395,7 +2396,7 @@ static struct net_device_stats *happy_meal_get_stats(struct net_device *dev)
happy_meal_get_counters(hp, hp->bigmacregs);
spin_unlock_irq(&hp->happy_lock);
- return &hp->net_stats;
+ return &dev->stats;
}
static void happy_meal_set_multicast(struct net_device *dev)
@@ -2434,20 +2435,21 @@ static void happy_meal_set_multicast(struct net_device *dev)
}
/* Ethtool support... */
-static int hme_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int hme_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
struct happy_meal *hp = netdev_priv(dev);
u32 speed;
+ u32 supported;
- cmd->supported =
+ supported =
(SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full |
SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full |
SUPPORTED_Autoneg | SUPPORTED_TP | SUPPORTED_MII);
/* XXX hardcoded stuff for now */
- cmd->port = PORT_TP; /* XXX no MII support */
- cmd->transceiver = XCVR_INTERNAL; /* XXX no external xcvr support */
- cmd->phy_address = 0; /* XXX fixed PHYAD */
+ cmd->base.port = PORT_TP; /* XXX no MII support */
+ cmd->base.phy_address = 0; /* XXX fixed PHYAD */
/* Record PHY settings. */
spin_lock_irq(&hp->happy_lock);
@@ -2456,41 +2458,45 @@ static int hme_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
spin_unlock_irq(&hp->happy_lock);
if (hp->sw_bmcr & BMCR_ANENABLE) {
- cmd->autoneg = AUTONEG_ENABLE;
+ cmd->base.autoneg = AUTONEG_ENABLE;
speed = ((hp->sw_lpa & (LPA_100HALF | LPA_100FULL)) ?
SPEED_100 : SPEED_10);
if (speed == SPEED_100)
- cmd->duplex =
+ cmd->base.duplex =
(hp->sw_lpa & (LPA_100FULL)) ?
DUPLEX_FULL : DUPLEX_HALF;
else
- cmd->duplex =
+ cmd->base.duplex =
(hp->sw_lpa & (LPA_10FULL)) ?
DUPLEX_FULL : DUPLEX_HALF;
} else {
- cmd->autoneg = AUTONEG_DISABLE;
+ cmd->base.autoneg = AUTONEG_DISABLE;
speed = (hp->sw_bmcr & BMCR_SPEED100) ? SPEED_100 : SPEED_10;
- cmd->duplex =
+ cmd->base.duplex =
(hp->sw_bmcr & BMCR_FULLDPLX) ?
DUPLEX_FULL : DUPLEX_HALF;
}
- ethtool_cmd_speed_set(cmd, speed);
+ cmd->base.speed = speed;
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ supported);
+
return 0;
}
-static int hme_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int hme_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
{
struct happy_meal *hp = netdev_priv(dev);
/* Verify the settings we care about. */
- if (cmd->autoneg != AUTONEG_ENABLE &&
- cmd->autoneg != AUTONEG_DISABLE)
+ if (cmd->base.autoneg != AUTONEG_ENABLE &&
+ cmd->base.autoneg != AUTONEG_DISABLE)
return -EINVAL;
- if (cmd->autoneg == AUTONEG_DISABLE &&
- ((ethtool_cmd_speed(cmd) != SPEED_100 &&
- ethtool_cmd_speed(cmd) != SPEED_10) ||
- (cmd->duplex != DUPLEX_HALF &&
- cmd->duplex != DUPLEX_FULL)))
+ if (cmd->base.autoneg == AUTONEG_DISABLE &&
+ ((cmd->base.speed != SPEED_100 &&
+ cmd->base.speed != SPEED_10) ||
+ (cmd->base.duplex != DUPLEX_HALF &&
+ cmd->base.duplex != DUPLEX_FULL)))
return -EINVAL;
/* Ok, do it to it. */
@@ -2537,10 +2543,10 @@ static u32 hme_get_link(struct net_device *dev)
}
static const struct ethtool_ops hme_ethtool_ops = {
- .get_settings = hme_get_settings,
- .set_settings = hme_set_settings,
.get_drvinfo = hme_get_drvinfo,
.get_link = hme_get_link,
+ .get_link_ksettings = hme_get_link_ksettings,
+ .set_link_ksettings = hme_set_link_ksettings,
};
static int hme_version_printed;
diff --git a/drivers/net/ethernet/sun/sunhme.h b/drivers/net/ethernet/sun/sunhme.h
index 4a8d5b1..3af540a 100644
--- a/drivers/net/ethernet/sun/sunhme.h
+++ b/drivers/net/ethernet/sun/sunhme.h
@@ -418,8 +418,6 @@ struct happy_meal {
int rx_new, tx_new, rx_old, tx_old;
- struct net_device_stats net_stats; /* Statistical counters */
-
#if defined(CONFIG_SBUS) && defined(CONFIG_PCI)
u32 (*read32)(void __iomem *);
void (*write32)(void __iomem *, u32);
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index 4cc2571..0b95105 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -1,7 +1,7 @@
/* sunvnet.c: Sun LDOM Virtual Network Driver.
*
* Copyright (C) 2007, 2008 David S. Miller <davem@davemloft.net>
- * Copyright (C) 2016 Oracle. All rights reserved.
+ * Copyright (C) 2016-2017 Oracle. All rights reserved.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -77,11 +77,125 @@ static void vnet_set_msglevel(struct net_device *dev, u32 value)
vp->msg_enable = value;
}
+static const struct {
+ const char string[ETH_GSTRING_LEN];
+} ethtool_stats_keys[] = {
+ { "rx_packets" },
+ { "tx_packets" },
+ { "rx_bytes" },
+ { "tx_bytes" },
+ { "rx_errors" },
+ { "tx_errors" },
+ { "rx_dropped" },
+ { "tx_dropped" },
+ { "multicast" },
+ { "rx_length_errors" },
+ { "rx_frame_errors" },
+ { "rx_missed_errors" },
+ { "tx_carrier_errors" },
+ { "nports" },
+};
+
+static int vnet_get_sset_count(struct net_device *dev, int sset)
+{
+ struct vnet *vp = (struct vnet *)netdev_priv(dev);
+
+ switch (sset) {
+ case ETH_SS_STATS:
+ return ARRAY_SIZE(ethtool_stats_keys)
+ + (NUM_VNET_PORT_STATS * vp->nports);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static void vnet_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
+{
+ struct vnet *vp = (struct vnet *)netdev_priv(dev);
+ struct vnet_port *port;
+ char *p = (char *)buf;
+
+ switch (stringset) {
+ case ETH_SS_STATS:
+ memcpy(buf, ðtool_stats_keys, sizeof(ethtool_stats_keys));
+ p += sizeof(ethtool_stats_keys);
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(port, &vp->port_list, list) {
+ snprintf(p, ETH_GSTRING_LEN, "p%u.%s-%pM",
+ port->q_index, port->switch_port ? "s" : "q",
+ port->raddr);
+ p += ETH_GSTRING_LEN;
+ snprintf(p, ETH_GSTRING_LEN, "p%u.rx_packets",
+ port->q_index);
+ p += ETH_GSTRING_LEN;
+ snprintf(p, ETH_GSTRING_LEN, "p%u.tx_packets",
+ port->q_index);
+ p += ETH_GSTRING_LEN;
+ snprintf(p, ETH_GSTRING_LEN, "p%u.rx_bytes",
+ port->q_index);
+ p += ETH_GSTRING_LEN;
+ snprintf(p, ETH_GSTRING_LEN, "p%u.tx_bytes",
+ port->q_index);
+ p += ETH_GSTRING_LEN;
+ snprintf(p, ETH_GSTRING_LEN, "p%u.event_up",
+ port->q_index);
+ p += ETH_GSTRING_LEN;
+ snprintf(p, ETH_GSTRING_LEN, "p%u.event_reset",
+ port->q_index);
+ p += ETH_GSTRING_LEN;
+ }
+ rcu_read_unlock();
+ break;
+ default:
+ WARN_ON(1);
+ break;
+ }
+}
+
+static void vnet_get_ethtool_stats(struct net_device *dev,
+ struct ethtool_stats *estats, u64 *data)
+{
+ struct vnet *vp = (struct vnet *)netdev_priv(dev);
+ struct vnet_port *port;
+ int i = 0;
+
+ data[i++] = dev->stats.rx_packets;
+ data[i++] = dev->stats.tx_packets;
+ data[i++] = dev->stats.rx_bytes;
+ data[i++] = dev->stats.tx_bytes;
+ data[i++] = dev->stats.rx_errors;
+ data[i++] = dev->stats.tx_errors;
+ data[i++] = dev->stats.rx_dropped;
+ data[i++] = dev->stats.tx_dropped;
+ data[i++] = dev->stats.multicast;
+ data[i++] = dev->stats.rx_length_errors;
+ data[i++] = dev->stats.rx_frame_errors;
+ data[i++] = dev->stats.rx_missed_errors;
+ data[i++] = dev->stats.tx_carrier_errors;
+ data[i++] = vp->nports;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(port, &vp->port_list, list) {
+ data[i++] = port->q_index;
+ data[i++] = port->stats.rx_packets;
+ data[i++] = port->stats.tx_packets;
+ data[i++] = port->stats.rx_bytes;
+ data[i++] = port->stats.tx_bytes;
+ data[i++] = port->stats.event_up;
+ data[i++] = port->stats.event_reset;
+ }
+ rcu_read_unlock();
+}
+
static const struct ethtool_ops vnet_ethtool_ops = {
.get_drvinfo = vnet_get_drvinfo,
.get_msglevel = vnet_get_msglevel,
.set_msglevel = vnet_set_msglevel,
.get_link = ethtool_op_get_link,
+ .get_sset_count = vnet_get_sset_count,
+ .get_strings = vnet_get_strings,
+ .get_ethtool_stats = vnet_get_ethtool_stats,
};
static LIST_HEAD(vnet_list);
diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c
index fa2d11c..9e86833 100644
--- a/drivers/net/ethernet/sun/sunvnet_common.c
+++ b/drivers/net/ethernet/sun/sunvnet_common.c
@@ -1,7 +1,7 @@
/* sunvnet.c: Sun LDOM Virtual Network Driver.
*
* Copyright (C) 2007, 2008 David S. Miller <davem@davemloft.net>
- * Copyright (C) 2016 Oracle. All rights reserved.
+ * Copyright (C) 2016-2017 Oracle. All rights reserved.
*/
#include <linux/module.h>
@@ -43,7 +43,6 @@ MODULE_LICENSE("GPL");
MODULE_VERSION("1.1");
static int __vnet_tx_trigger(struct vnet_port *port, u32 start);
-static void vnet_port_reset(struct vnet_port *port);
static inline u32 vnet_tx_dring_avail(struct vio_dring_state *dr)
{
@@ -410,8 +409,12 @@ static int vnet_rx_one(struct vnet_port *port, struct vio_net_desc *desc)
skb->ip_summed = port->switch_port ? CHECKSUM_NONE : CHECKSUM_PARTIAL;
+ if (unlikely(is_multicast_ether_addr(eth_hdr(skb)->h_dest)))
+ dev->stats.multicast++;
dev->stats.rx_packets++;
dev->stats.rx_bytes += len;
+ port->stats.rx_packets++;
+ port->stats.rx_bytes += len;
napi_gro_receive(&port->napi, skb);
return 0;
@@ -747,6 +750,13 @@ static int vnet_event_napi(struct vnet_port *port, int budget)
/* RESET takes precedent over any other event */
if (port->rx_event & LDC_EVENT_RESET) {
+ /* a link went down */
+
+ if (port->vsw == 1) {
+ netif_tx_stop_all_queues(dev);
+ netif_carrier_off(dev);
+ }
+
vio_link_state_change(vio, LDC_EVENT_RESET);
vnet_port_reset(port);
vio_port_up(vio);
@@ -762,12 +772,21 @@ static int vnet_event_napi(struct vnet_port *port, int budget)
maybe_tx_wakeup(port);
port->rx_event = 0;
+ port->stats.event_reset++;
return 0;
}
if (port->rx_event & LDC_EVENT_UP) {
+ /* a link came up */
+
+ if (port->vsw == 1) {
+ netif_carrier_on(port->dev);
+ netif_tx_start_all_queues(port->dev);
+ }
+
vio_link_state_change(vio, LDC_EVENT_UP);
port->rx_event = 0;
+ port->stats.event_up++;
return 0;
}
@@ -1417,6 +1436,8 @@ int sunvnet_start_xmit_common(struct sk_buff *skb, struct net_device *dev,
dev->stats.tx_packets++;
dev->stats.tx_bytes += port->tx_bufs[txi].skb->len;
+ port->stats.tx_packets++;
+ port->stats.tx_bytes += port->tx_bufs[txi].skb->len;
dr->prod = (dr->prod + 1) & (VNET_TX_RING_SIZE - 1);
if (unlikely(vnet_tx_dring_avail(dr) < 1)) {
@@ -1631,7 +1652,7 @@ void sunvnet_port_free_tx_bufs_common(struct vnet_port *port)
}
EXPORT_SYMBOL_GPL(sunvnet_port_free_tx_bufs_common);
-static void vnet_port_reset(struct vnet_port *port)
+void vnet_port_reset(struct vnet_port *port)
{
del_timer(&port->clean_timer);
sunvnet_port_free_tx_bufs_common(port);
@@ -1639,6 +1660,7 @@ static void vnet_port_reset(struct vnet_port *port)
port->tso = (port->vsw == 0); /* no tso in vsw, misbehaves in bridge */
port->tsolen = 0;
}
+EXPORT_SYMBOL_GPL(vnet_port_reset);
static int vnet_port_alloc_tx_ring(struct vnet_port *port)
{
@@ -1708,20 +1730,32 @@ EXPORT_SYMBOL_GPL(sunvnet_poll_controller_common);
void sunvnet_port_add_txq_common(struct vnet_port *port)
{
struct vnet *vp = port->vp;
- int n;
+ int smallest = 0;
+ int i;
- n = vp->nports++;
- n = n & (VNET_MAX_TXQS - 1);
- port->q_index = n;
- netif_tx_wake_queue(netdev_get_tx_queue(VNET_PORT_TO_NET_DEVICE(port),
- port->q_index));
+ /* find the first least-used q
+ * When there are more ldoms than q's, we start to
+ * double up on ports per queue.
+ */
+ for (i = 0; i < VNET_MAX_TXQS; i++) {
+ if (vp->q_used[i] == 0) {
+ smallest = i;
+ break;
+ }
+ if (vp->q_used[i] < vp->q_used[smallest])
+ smallest = i;
+ }
+
+ vp->nports++;
+ vp->q_used[smallest]++;
+ port->q_index = smallest;
}
EXPORT_SYMBOL_GPL(sunvnet_port_add_txq_common);
void sunvnet_port_rm_txq_common(struct vnet_port *port)
{
port->vp->nports--;
- netif_tx_stop_queue(netdev_get_tx_queue(VNET_PORT_TO_NET_DEVICE(port),
- port->q_index));
+ port->vp->q_used[port->q_index]--;
+ port->q_index = 0;
}
EXPORT_SYMBOL_GPL(sunvnet_port_rm_txq_common);
diff --git a/drivers/net/ethernet/sun/sunvnet_common.h b/drivers/net/ethernet/sun/sunvnet_common.h
index ce5c824..b20d6fa 100644
--- a/drivers/net/ethernet/sun/sunvnet_common.h
+++ b/drivers/net/ethernet/sun/sunvnet_common.h
@@ -35,6 +35,19 @@ struct vnet_tx_entry {
struct vnet;
+struct vnet_port_stats {
+ /* keep them all the same size */
+ u32 rx_bytes;
+ u32 tx_bytes;
+ u32 rx_packets;
+ u32 tx_packets;
+ u32 event_up;
+ u32 event_reset;
+ u32 q_placeholder;
+};
+
+#define NUM_VNET_PORT_STATS (sizeof(struct vnet_port_stats) / sizeof(u32))
+
/* Structure to describe a vnet-port or vsw-port in the MD.
* If the vsw bit is set, this structure represents a vswitch
* port, and the net_device can be found from ->dev. If the
@@ -44,6 +57,8 @@ struct vnet;
struct vnet_port {
struct vio_driver_state vio;
+ struct vnet_port_stats stats;
+
struct hlist_node hash;
u8 raddr[ETH_ALEN];
unsigned switch_port:1;
@@ -97,22 +112,15 @@ struct vnet_mcast_entry {
};
struct vnet {
- /* Protects port_list and port_hash. */
- spinlock_t lock;
-
+ spinlock_t lock; /* Protects port_list and port_hash. */
struct net_device *dev;
-
u32 msg_enable;
-
+ u8 q_used[VNET_MAX_TXQS];
struct list_head port_list;
-
struct hlist_head port_hash[VNET_PORT_HASH_SIZE];
-
struct vnet_mcast_entry *mcast_list;
-
struct list_head list;
u64 local_mac;
-
int nports;
};
@@ -139,6 +147,7 @@ int sunvnet_handle_attr_common(struct vio_driver_state *vio, void *arg);
void sunvnet_handshake_complete_common(struct vio_driver_state *vio);
int sunvnet_poll_common(struct napi_struct *napi, int budget);
void sunvnet_port_free_tx_bufs_common(struct vnet_port *port);
+void vnet_port_reset(struct vnet_port *port);
bool sunvnet_port_is_up_common(struct vnet_port *vnet);
void sunvnet_port_add_txq_common(struct vnet_port *port);
void sunvnet_port_rm_txq_common(struct vnet_port *port);
diff --git a/drivers/net/ethernet/synopsys/Kconfig b/drivers/net/ethernet/synopsys/Kconfig
new file mode 100644
index 0000000..a950388
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/Kconfig
@@ -0,0 +1,41 @@
+#
+# Synopsys network device configuration
+#
+
+config NET_VENDOR_SYNOPSYS
+ bool "Synopsys devices"
+ default y
+ ---help---
+ If you have a network (Ethernet) device belonging to this class, say Y.
+
+ Note that the answer to this question doesn't directly affect the
+ kernel: saying N will just cause the configurator to skip all
+ the questions about Synopsys devices. If you say Y, you will be asked
+ for your specific device in the following questions.
+
+if NET_VENDOR_SYNOPSYS
+
+config DWC_XLGMAC
+ tristate "Synopsys DWC Enterprise Ethernet (XLGMAC) driver support"
+ depends on HAS_IOMEM && HAS_DMA
+ select BITREVERSE
+ select CRC32
+ ---help---
+ This driver supports the Synopsys DesignWare Cores Enterprise
+ Ethernet (dwc-xlgmac).
+
+if DWC_XLGMAC
+
+config DWC_XLGMAC_PCI
+ tristate "XLGMAC PCI bus support"
+ depends on DWC_XLGMAC && PCI
+ ---help---
+ This selects the pci bus support for the dwc-xlgmac driver.
+ This driver was tested on Synopsys XLGMAC IP Prototyping Kit.
+
+ If you have a controller with this interface, say Y or M here.
+ If unsure, say N.
+
+endif # DWC_XLGMAC
+
+endif # NET_VENDOR_SYNOPSYS
diff --git a/drivers/net/ethernet/synopsys/Makefile b/drivers/net/ethernet/synopsys/Makefile
new file mode 100644
index 0000000..c06e2eb
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/Makefile
@@ -0,0 +1,9 @@
+#
+# Makefile for the Synopsys network device drivers.
+#
+
+obj-$(CONFIG_DWC_XLGMAC) += dwc-xlgmac.o
+dwc-xlgmac-objs := dwc-xlgmac-net.o dwc-xlgmac-desc.o \
+ dwc-xlgmac-hw.o dwc-xlgmac-common.o
+
+dwc-xlgmac-$(CONFIG_DWC_XLGMAC_PCI) += dwc-xlgmac-pci.o
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c
new file mode 100644
index 0000000..07def2b
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c
@@ -0,0 +1,736 @@
+/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver
+ *
+ * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is dual-licensed; you may select either version 2 of
+ * the GNU General Public License ("GPL") or BSD license ("BSD").
+ *
+ * This Synopsys DWC XLGMAC software driver and associated documentation
+ * (hereinafter the "Software") is an unsupported proprietary work of
+ * Synopsys, Inc. unless otherwise expressly agreed to in writing between
+ * Synopsys and you. The Software IS NOT an item of Licensed Software or a
+ * Licensed Product under any End User Software License Agreement or
+ * Agreement for Licensed Products with Synopsys or any supplement thereto.
+ * Synopsys is a registered trademark of Synopsys, Inc. Other names included
+ * in the SOFTWARE may be the trademarks of their respective owners.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include "dwc-xlgmac.h"
+#include "dwc-xlgmac-reg.h"
+
+MODULE_LICENSE("Dual BSD/GPL");
+
+static int debug = -1;
+module_param(debug, int, 0644);
+MODULE_PARM_DESC(debug, "DWC ethernet debug level (0=none,...,16=all)");
+static const u32 default_msg_level = (NETIF_MSG_LINK | NETIF_MSG_IFDOWN |
+ NETIF_MSG_IFUP);
+
+static unsigned char dev_addr[6] = {0, 0x55, 0x7b, 0xb5, 0x7d, 0xf7};
+
+static void xlgmac_read_mac_addr(struct xlgmac_pdata *pdata)
+{
+ struct net_device *netdev = pdata->netdev;
+
+ /* Currently it uses a static mac address for test */
+ memcpy(pdata->mac_addr, dev_addr, netdev->addr_len);
+}
+
+static void xlgmac_default_config(struct xlgmac_pdata *pdata)
+{
+ pdata->tx_osp_mode = DMA_OSP_ENABLE;
+ pdata->tx_sf_mode = MTL_TSF_ENABLE;
+ pdata->rx_sf_mode = MTL_RSF_DISABLE;
+ pdata->pblx8 = DMA_PBL_X8_ENABLE;
+ pdata->tx_pbl = DMA_PBL_32;
+ pdata->rx_pbl = DMA_PBL_32;
+ pdata->tx_threshold = MTL_TX_THRESHOLD_128;
+ pdata->rx_threshold = MTL_RX_THRESHOLD_128;
+ pdata->tx_pause = 1;
+ pdata->rx_pause = 1;
+ pdata->phy_speed = SPEED_25000;
+ pdata->sysclk_rate = XLGMAC_SYSCLOCK;
+
+ strlcpy(pdata->drv_name, XLGMAC_DRV_NAME, sizeof(pdata->drv_name));
+ strlcpy(pdata->drv_ver, XLGMAC_DRV_VERSION, sizeof(pdata->drv_ver));
+}
+
+static void xlgmac_init_all_ops(struct xlgmac_pdata *pdata)
+{
+ xlgmac_init_desc_ops(&pdata->desc_ops);
+ xlgmac_init_hw_ops(&pdata->hw_ops);
+}
+
+static int xlgmac_init(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+ struct net_device *netdev = pdata->netdev;
+ unsigned int i;
+ int ret;
+
+ /* Set default configuration data */
+ xlgmac_default_config(pdata);
+
+ /* Set irq, base_addr, MAC address, */
+ netdev->irq = pdata->dev_irq;
+ netdev->base_addr = (unsigned long)pdata->mac_regs;
+ xlgmac_read_mac_addr(pdata);
+ memcpy(netdev->dev_addr, pdata->mac_addr, netdev->addr_len);
+
+ /* Set all the function pointers */
+ xlgmac_init_all_ops(pdata);
+
+ /* Issue software reset to device */
+ hw_ops->exit(pdata);
+
+ /* Populate the hardware features */
+ xlgmac_get_all_hw_features(pdata);
+ xlgmac_print_all_hw_features(pdata);
+
+ /* TODO: Set the PHY mode to XLGMII */
+
+ /* Set the DMA mask */
+ ret = dma_set_mask_and_coherent(pdata->dev,
+ DMA_BIT_MASK(pdata->hw_feat.dma_width));
+ if (ret) {
+ dev_err(pdata->dev, "dma_set_mask_and_coherent failed\n");
+ return ret;
+ }
+
+ /* Channel and ring params initializtion
+ * pdata->channel_count;
+ * pdata->tx_ring_count;
+ * pdata->rx_ring_count;
+ * pdata->tx_desc_count;
+ * pdata->rx_desc_count;
+ */
+ BUILD_BUG_ON_NOT_POWER_OF_2(XLGMAC_TX_DESC_CNT);
+ pdata->tx_desc_count = XLGMAC_TX_DESC_CNT;
+ if (pdata->tx_desc_count & (pdata->tx_desc_count - 1)) {
+ dev_err(pdata->dev, "tx descriptor count (%d) is not valid\n",
+ pdata->tx_desc_count);
+ ret = -EINVAL;
+ return ret;
+ }
+ BUILD_BUG_ON_NOT_POWER_OF_2(XLGMAC_RX_DESC_CNT);
+ pdata->rx_desc_count = XLGMAC_RX_DESC_CNT;
+ if (pdata->rx_desc_count & (pdata->rx_desc_count - 1)) {
+ dev_err(pdata->dev, "rx descriptor count (%d) is not valid\n",
+ pdata->rx_desc_count);
+ ret = -EINVAL;
+ return ret;
+ }
+
+ pdata->tx_ring_count = min_t(unsigned int, num_online_cpus(),
+ pdata->hw_feat.tx_ch_cnt);
+ pdata->tx_ring_count = min_t(unsigned int, pdata->tx_ring_count,
+ pdata->hw_feat.tx_q_cnt);
+ pdata->tx_q_count = pdata->tx_ring_count;
+ ret = netif_set_real_num_tx_queues(netdev, pdata->tx_q_count);
+ if (ret) {
+ dev_err(pdata->dev, "error setting real tx queue count\n");
+ return ret;
+ }
+
+ pdata->rx_ring_count = min_t(unsigned int,
+ netif_get_num_default_rss_queues(),
+ pdata->hw_feat.rx_ch_cnt);
+ pdata->rx_ring_count = min_t(unsigned int, pdata->rx_ring_count,
+ pdata->hw_feat.rx_q_cnt);
+ pdata->rx_q_count = pdata->rx_ring_count;
+ ret = netif_set_real_num_rx_queues(netdev, pdata->rx_q_count);
+ if (ret) {
+ dev_err(pdata->dev, "error setting real rx queue count\n");
+ return ret;
+ }
+
+ pdata->channel_count =
+ max_t(unsigned int, pdata->tx_ring_count, pdata->rx_ring_count);
+
+ /* Initialize RSS hash key and lookup table */
+ netdev_rss_key_fill(pdata->rss_key, sizeof(pdata->rss_key));
+
+ for (i = 0; i < XLGMAC_RSS_MAX_TABLE_SIZE; i++)
+ pdata->rss_table[i] = XLGMAC_SET_REG_BITS(
+ pdata->rss_table[i],
+ MAC_RSSDR_DMCH_POS,
+ MAC_RSSDR_DMCH_LEN,
+ i % pdata->rx_ring_count);
+
+ pdata->rss_options = XLGMAC_SET_REG_BITS(
+ pdata->rss_options,
+ MAC_RSSCR_IP2TE_POS,
+ MAC_RSSCR_IP2TE_LEN, 1);
+ pdata->rss_options = XLGMAC_SET_REG_BITS(
+ pdata->rss_options,
+ MAC_RSSCR_TCP4TE_POS,
+ MAC_RSSCR_TCP4TE_LEN, 1);
+ pdata->rss_options = XLGMAC_SET_REG_BITS(
+ pdata->rss_options,
+ MAC_RSSCR_UDP4TE_POS,
+ MAC_RSSCR_UDP4TE_LEN, 1);
+
+ /* Set device operations */
+ netdev->netdev_ops = xlgmac_get_netdev_ops();
+
+ /* Set device features */
+ if (pdata->hw_feat.tso) {
+ netdev->hw_features = NETIF_F_TSO;
+ netdev->hw_features |= NETIF_F_TSO6;
+ netdev->hw_features |= NETIF_F_SG;
+ netdev->hw_features |= NETIF_F_IP_CSUM;
+ netdev->hw_features |= NETIF_F_IPV6_CSUM;
+ } else if (pdata->hw_feat.tx_coe) {
+ netdev->hw_features = NETIF_F_IP_CSUM;
+ netdev->hw_features |= NETIF_F_IPV6_CSUM;
+ }
+
+ if (pdata->hw_feat.rx_coe) {
+ netdev->hw_features |= NETIF_F_RXCSUM;
+ netdev->hw_features |= NETIF_F_GRO;
+ }
+
+ if (pdata->hw_feat.rss)
+ netdev->hw_features |= NETIF_F_RXHASH;
+
+ netdev->vlan_features |= netdev->hw_features;
+
+ netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX;
+ if (pdata->hw_feat.sa_vlan_ins)
+ netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX;
+ if (pdata->hw_feat.vlhash)
+ netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+
+ netdev->features |= netdev->hw_features;
+ pdata->netdev_features = netdev->features;
+
+ netdev->priv_flags |= IFF_UNICAST_FLT;
+
+ /* Use default watchdog timeout */
+ netdev->watchdog_timeo = 0;
+
+ /* Tx coalesce parameters initialization */
+ pdata->tx_usecs = XLGMAC_INIT_DMA_TX_USECS;
+ pdata->tx_frames = XLGMAC_INIT_DMA_TX_FRAMES;
+
+ /* Rx coalesce parameters initialization */
+ pdata->rx_riwt = hw_ops->usec_to_riwt(pdata, XLGMAC_INIT_DMA_RX_USECS);
+ pdata->rx_usecs = XLGMAC_INIT_DMA_RX_USECS;
+ pdata->rx_frames = XLGMAC_INIT_DMA_RX_FRAMES;
+
+ return 0;
+}
+
+int xlgmac_drv_probe(struct device *dev, struct xlgmac_resources *res)
+{
+ struct xlgmac_pdata *pdata;
+ struct net_device *netdev;
+ int ret;
+
+ netdev = alloc_etherdev_mq(sizeof(struct xlgmac_pdata),
+ XLGMAC_MAX_DMA_CHANNELS);
+
+ if (!netdev) {
+ dev_err(dev, "alloc_etherdev failed\n");
+ return -ENOMEM;
+ }
+
+ SET_NETDEV_DEV(netdev, dev);
+ dev_set_drvdata(dev, netdev);
+ pdata = netdev_priv(netdev);
+ pdata->dev = dev;
+ pdata->netdev = netdev;
+
+ pdata->dev_irq = res->irq;
+ pdata->mac_regs = res->addr;
+
+ mutex_init(&pdata->rss_mutex);
+ pdata->msg_enable = netif_msg_init(debug, default_msg_level);
+
+ ret = xlgmac_init(pdata);
+ if (ret) {
+ dev_err(dev, "xlgmac init failed\n");
+ goto err_free_netdev;
+ }
+
+ ret = register_netdev(netdev);
+ if (ret) {
+ dev_err(dev, "net device registration failed\n");
+ goto err_free_netdev;
+ }
+
+ return 0;
+
+err_free_netdev:
+ free_netdev(netdev);
+
+ return ret;
+}
+
+int xlgmac_drv_remove(struct device *dev)
+{
+ struct net_device *netdev = dev_get_drvdata(dev);
+
+ unregister_netdev(netdev);
+ free_netdev(netdev);
+
+ return 0;
+}
+
+void xlgmac_dump_tx_desc(struct xlgmac_pdata *pdata,
+ struct xlgmac_ring *ring,
+ unsigned int idx,
+ unsigned int count,
+ unsigned int flag)
+{
+ struct xlgmac_desc_data *desc_data;
+ struct xlgmac_dma_desc *dma_desc;
+
+ while (count--) {
+ desc_data = XLGMAC_GET_DESC_DATA(ring, idx);
+ dma_desc = desc_data->dma_desc;
+
+ netdev_dbg(pdata->netdev, "TX: dma_desc=%p, dma_desc_addr=%pad\n",
+ desc_data->dma_desc, &desc_data->dma_desc_addr);
+ netdev_dbg(pdata->netdev,
+ "TX_NORMAL_DESC[%d %s] = %08x:%08x:%08x:%08x\n", idx,
+ (flag == 1) ? "QUEUED FOR TX" : "TX BY DEVICE",
+ le32_to_cpu(dma_desc->desc0),
+ le32_to_cpu(dma_desc->desc1),
+ le32_to_cpu(dma_desc->desc2),
+ le32_to_cpu(dma_desc->desc3));
+
+ idx++;
+ }
+}
+
+void xlgmac_dump_rx_desc(struct xlgmac_pdata *pdata,
+ struct xlgmac_ring *ring,
+ unsigned int idx)
+{
+ struct xlgmac_desc_data *desc_data;
+ struct xlgmac_dma_desc *dma_desc;
+
+ desc_data = XLGMAC_GET_DESC_DATA(ring, idx);
+ dma_desc = desc_data->dma_desc;
+
+ netdev_dbg(pdata->netdev, "RX: dma_desc=%p, dma_desc_addr=%pad\n",
+ desc_data->dma_desc, &desc_data->dma_desc_addr);
+ netdev_dbg(pdata->netdev,
+ "RX_NORMAL_DESC[%d RX BY DEVICE] = %08x:%08x:%08x:%08x\n",
+ idx,
+ le32_to_cpu(dma_desc->desc0),
+ le32_to_cpu(dma_desc->desc1),
+ le32_to_cpu(dma_desc->desc2),
+ le32_to_cpu(dma_desc->desc3));
+}
+
+void xlgmac_print_pkt(struct net_device *netdev,
+ struct sk_buff *skb, bool tx_rx)
+{
+ struct ethhdr *eth = (struct ethhdr *)skb->data;
+ unsigned char *buf = skb->data;
+ unsigned char buffer[128];
+ unsigned int i, j;
+
+ netdev_dbg(netdev, "\n************** SKB dump ****************\n");
+
+ netdev_dbg(netdev, "%s packet of %d bytes\n",
+ (tx_rx ? "TX" : "RX"), skb->len);
+
+ netdev_dbg(netdev, "Dst MAC addr: %pM\n", eth->h_dest);
+ netdev_dbg(netdev, "Src MAC addr: %pM\n", eth->h_source);
+ netdev_dbg(netdev, "Protocol: %#06hx\n", ntohs(eth->h_proto));
+
+ for (i = 0, j = 0; i < skb->len;) {
+ j += snprintf(buffer + j, sizeof(buffer) - j, "%02hhx",
+ buf[i++]);
+
+ if ((i % 32) == 0) {
+ netdev_dbg(netdev, " %#06x: %s\n", i - 32, buffer);
+ j = 0;
+ } else if ((i % 16) == 0) {
+ buffer[j++] = ' ';
+ buffer[j++] = ' ';
+ } else if ((i % 4) == 0) {
+ buffer[j++] = ' ';
+ }
+ }
+ if (i % 32)
+ netdev_dbg(netdev, " %#06x: %s\n", i - (i % 32), buffer);
+
+ netdev_dbg(netdev, "\n************** SKB dump ****************\n");
+}
+
+void xlgmac_get_all_hw_features(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_hw_features *hw_feat = &pdata->hw_feat;
+ unsigned int mac_hfr0, mac_hfr1, mac_hfr2;
+
+ mac_hfr0 = readl(pdata->mac_regs + MAC_HWF0R);
+ mac_hfr1 = readl(pdata->mac_regs + MAC_HWF1R);
+ mac_hfr2 = readl(pdata->mac_regs + MAC_HWF2R);
+
+ memset(hw_feat, 0, sizeof(*hw_feat));
+
+ hw_feat->version = readl(pdata->mac_regs + MAC_VR);
+
+ /* Hardware feature register 0 */
+ hw_feat->phyifsel = XLGMAC_GET_REG_BITS(mac_hfr0,
+ MAC_HWF0R_PHYIFSEL_POS,
+ MAC_HWF0R_PHYIFSEL_LEN);
+ hw_feat->vlhash = XLGMAC_GET_REG_BITS(mac_hfr0,
+ MAC_HWF0R_VLHASH_POS,
+ MAC_HWF0R_VLHASH_LEN);
+ hw_feat->sma = XLGMAC_GET_REG_BITS(mac_hfr0,
+ MAC_HWF0R_SMASEL_POS,
+ MAC_HWF0R_SMASEL_LEN);
+ hw_feat->rwk = XLGMAC_GET_REG_BITS(mac_hfr0,
+ MAC_HWF0R_RWKSEL_POS,
+ MAC_HWF0R_RWKSEL_LEN);
+ hw_feat->mgk = XLGMAC_GET_REG_BITS(mac_hfr0,
+ MAC_HWF0R_MGKSEL_POS,
+ MAC_HWF0R_MGKSEL_LEN);
+ hw_feat->mmc = XLGMAC_GET_REG_BITS(mac_hfr0,
+ MAC_HWF0R_MMCSEL_POS,
+ MAC_HWF0R_MMCSEL_LEN);
+ hw_feat->aoe = XLGMAC_GET_REG_BITS(mac_hfr0,
+ MAC_HWF0R_ARPOFFSEL_POS,
+ MAC_HWF0R_ARPOFFSEL_LEN);
+ hw_feat->ts = XLGMAC_GET_REG_BITS(mac_hfr0,
+ MAC_HWF0R_TSSEL_POS,
+ MAC_HWF0R_TSSEL_LEN);
+ hw_feat->eee = XLGMAC_GET_REG_BITS(mac_hfr0,
+ MAC_HWF0R_EEESEL_POS,
+ MAC_HWF0R_EEESEL_LEN);
+ hw_feat->tx_coe = XLGMAC_GET_REG_BITS(mac_hfr0,
+ MAC_HWF0R_TXCOESEL_POS,
+ MAC_HWF0R_TXCOESEL_LEN);
+ hw_feat->rx_coe = XLGMAC_GET_REG_BITS(mac_hfr0,
+ MAC_HWF0R_RXCOESEL_POS,
+ MAC_HWF0R_RXCOESEL_LEN);
+ hw_feat->addn_mac = XLGMAC_GET_REG_BITS(mac_hfr0,
+ MAC_HWF0R_ADDMACADRSEL_POS,
+ MAC_HWF0R_ADDMACADRSEL_LEN);
+ hw_feat->ts_src = XLGMAC_GET_REG_BITS(mac_hfr0,
+ MAC_HWF0R_TSSTSSEL_POS,
+ MAC_HWF0R_TSSTSSEL_LEN);
+ hw_feat->sa_vlan_ins = XLGMAC_GET_REG_BITS(mac_hfr0,
+ MAC_HWF0R_SAVLANINS_POS,
+ MAC_HWF0R_SAVLANINS_LEN);
+
+ /* Hardware feature register 1 */
+ hw_feat->rx_fifo_size = XLGMAC_GET_REG_BITS(mac_hfr1,
+ MAC_HWF1R_RXFIFOSIZE_POS,
+ MAC_HWF1R_RXFIFOSIZE_LEN);
+ hw_feat->tx_fifo_size = XLGMAC_GET_REG_BITS(mac_hfr1,
+ MAC_HWF1R_TXFIFOSIZE_POS,
+ MAC_HWF1R_TXFIFOSIZE_LEN);
+ hw_feat->adv_ts_hi = XLGMAC_GET_REG_BITS(mac_hfr1,
+ MAC_HWF1R_ADVTHWORD_POS,
+ MAC_HWF1R_ADVTHWORD_LEN);
+ hw_feat->dma_width = XLGMAC_GET_REG_BITS(mac_hfr1,
+ MAC_HWF1R_ADDR64_POS,
+ MAC_HWF1R_ADDR64_LEN);
+ hw_feat->dcb = XLGMAC_GET_REG_BITS(mac_hfr1,
+ MAC_HWF1R_DCBEN_POS,
+ MAC_HWF1R_DCBEN_LEN);
+ hw_feat->sph = XLGMAC_GET_REG_BITS(mac_hfr1,
+ MAC_HWF1R_SPHEN_POS,
+ MAC_HWF1R_SPHEN_LEN);
+ hw_feat->tso = XLGMAC_GET_REG_BITS(mac_hfr1,
+ MAC_HWF1R_TSOEN_POS,
+ MAC_HWF1R_TSOEN_LEN);
+ hw_feat->dma_debug = XLGMAC_GET_REG_BITS(mac_hfr1,
+ MAC_HWF1R_DBGMEMA_POS,
+ MAC_HWF1R_DBGMEMA_LEN);
+ hw_feat->rss = XLGMAC_GET_REG_BITS(mac_hfr1,
+ MAC_HWF1R_RSSEN_POS,
+ MAC_HWF1R_RSSEN_LEN);
+ hw_feat->tc_cnt = XLGMAC_GET_REG_BITS(mac_hfr1,
+ MAC_HWF1R_NUMTC_POS,
+ MAC_HWF1R_NUMTC_LEN);
+ hw_feat->hash_table_size = XLGMAC_GET_REG_BITS(mac_hfr1,
+ MAC_HWF1R_HASHTBLSZ_POS,
+ MAC_HWF1R_HASHTBLSZ_LEN);
+ hw_feat->l3l4_filter_num = XLGMAC_GET_REG_BITS(mac_hfr1,
+ MAC_HWF1R_L3L4FNUM_POS,
+ MAC_HWF1R_L3L4FNUM_LEN);
+
+ /* Hardware feature register 2 */
+ hw_feat->rx_q_cnt = XLGMAC_GET_REG_BITS(mac_hfr2,
+ MAC_HWF2R_RXQCNT_POS,
+ MAC_HWF2R_RXQCNT_LEN);
+ hw_feat->tx_q_cnt = XLGMAC_GET_REG_BITS(mac_hfr2,
+ MAC_HWF2R_TXQCNT_POS,
+ MAC_HWF2R_TXQCNT_LEN);
+ hw_feat->rx_ch_cnt = XLGMAC_GET_REG_BITS(mac_hfr2,
+ MAC_HWF2R_RXCHCNT_POS,
+ MAC_HWF2R_RXCHCNT_LEN);
+ hw_feat->tx_ch_cnt = XLGMAC_GET_REG_BITS(mac_hfr2,
+ MAC_HWF2R_TXCHCNT_POS,
+ MAC_HWF2R_TXCHCNT_LEN);
+ hw_feat->pps_out_num = XLGMAC_GET_REG_BITS(mac_hfr2,
+ MAC_HWF2R_PPSOUTNUM_POS,
+ MAC_HWF2R_PPSOUTNUM_LEN);
+ hw_feat->aux_snap_num = XLGMAC_GET_REG_BITS(mac_hfr2,
+ MAC_HWF2R_AUXSNAPNUM_POS,
+ MAC_HWF2R_AUXSNAPNUM_LEN);
+
+ /* Translate the Hash Table size into actual number */
+ switch (hw_feat->hash_table_size) {
+ case 0:
+ break;
+ case 1:
+ hw_feat->hash_table_size = 64;
+ break;
+ case 2:
+ hw_feat->hash_table_size = 128;
+ break;
+ case 3:
+ hw_feat->hash_table_size = 256;
+ break;
+ }
+
+ /* Translate the address width setting into actual number */
+ switch (hw_feat->dma_width) {
+ case 0:
+ hw_feat->dma_width = 32;
+ break;
+ case 1:
+ hw_feat->dma_width = 40;
+ break;
+ case 2:
+ hw_feat->dma_width = 48;
+ break;
+ default:
+ hw_feat->dma_width = 32;
+ }
+
+ /* The Queue, Channel and TC counts are zero based so increment them
+ * to get the actual number
+ */
+ hw_feat->rx_q_cnt++;
+ hw_feat->tx_q_cnt++;
+ hw_feat->rx_ch_cnt++;
+ hw_feat->tx_ch_cnt++;
+ hw_feat->tc_cnt++;
+}
+
+void xlgmac_print_all_hw_features(struct xlgmac_pdata *pdata)
+{
+ char *str = NULL;
+
+ XLGMAC_PR("\n");
+ XLGMAC_PR("=====================================================\n");
+ XLGMAC_PR("\n");
+ XLGMAC_PR("HW support following features\n");
+ XLGMAC_PR("\n");
+ /* HW Feature Register0 */
+ XLGMAC_PR("VLAN Hash Filter Selected : %s\n",
+ pdata->hw_feat.vlhash ? "YES" : "NO");
+ XLGMAC_PR("SMA (MDIO) Interface : %s\n",
+ pdata->hw_feat.sma ? "YES" : "NO");
+ XLGMAC_PR("PMT Remote Wake-up Packet Enable : %s\n",
+ pdata->hw_feat.rwk ? "YES" : "NO");
+ XLGMAC_PR("PMT Magic Packet Enable : %s\n",
+ pdata->hw_feat.mgk ? "YES" : "NO");
+ XLGMAC_PR("RMON/MMC Module Enable : %s\n",
+ pdata->hw_feat.mmc ? "YES" : "NO");
+ XLGMAC_PR("ARP Offload Enabled : %s\n",
+ pdata->hw_feat.aoe ? "YES" : "NO");
+ XLGMAC_PR("IEEE 1588-2008 Timestamp Enabled : %s\n",
+ pdata->hw_feat.ts ? "YES" : "NO");
+ XLGMAC_PR("Energy Efficient Ethernet Enabled : %s\n",
+ pdata->hw_feat.eee ? "YES" : "NO");
+ XLGMAC_PR("Transmit Checksum Offload Enabled : %s\n",
+ pdata->hw_feat.tx_coe ? "YES" : "NO");
+ XLGMAC_PR("Receive Checksum Offload Enabled : %s\n",
+ pdata->hw_feat.rx_coe ? "YES" : "NO");
+ XLGMAC_PR("Additional MAC Addresses 1-31 Selected : %s\n",
+ pdata->hw_feat.addn_mac ? "YES" : "NO");
+
+ switch (pdata->hw_feat.ts_src) {
+ case 0:
+ str = "RESERVED";
+ break;
+ case 1:
+ str = "INTERNAL";
+ break;
+ case 2:
+ str = "EXTERNAL";
+ break;
+ case 3:
+ str = "BOTH";
+ break;
+ }
+ XLGMAC_PR("Timestamp System Time Source : %s\n", str);
+
+ XLGMAC_PR("Source Address or VLAN Insertion Enable : %s\n",
+ pdata->hw_feat.sa_vlan_ins ? "YES" : "NO");
+
+ /* HW Feature Register1 */
+ switch (pdata->hw_feat.rx_fifo_size) {
+ case 0:
+ str = "128 bytes";
+ break;
+ case 1:
+ str = "256 bytes";
+ break;
+ case 2:
+ str = "512 bytes";
+ break;
+ case 3:
+ str = "1 KBytes";
+ break;
+ case 4:
+ str = "2 KBytes";
+ break;
+ case 5:
+ str = "4 KBytes";
+ break;
+ case 6:
+ str = "8 KBytes";
+ break;
+ case 7:
+ str = "16 KBytes";
+ break;
+ case 8:
+ str = "32 kBytes";
+ break;
+ case 9:
+ str = "64 KBytes";
+ break;
+ case 10:
+ str = "128 KBytes";
+ break;
+ case 11:
+ str = "256 KBytes";
+ break;
+ default:
+ str = "RESERVED";
+ }
+ XLGMAC_PR("MTL Receive FIFO Size : %s\n", str);
+
+ switch (pdata->hw_feat.tx_fifo_size) {
+ case 0:
+ str = "128 bytes";
+ break;
+ case 1:
+ str = "256 bytes";
+ break;
+ case 2:
+ str = "512 bytes";
+ break;
+ case 3:
+ str = "1 KBytes";
+ break;
+ case 4:
+ str = "2 KBytes";
+ break;
+ case 5:
+ str = "4 KBytes";
+ break;
+ case 6:
+ str = "8 KBytes";
+ break;
+ case 7:
+ str = "16 KBytes";
+ break;
+ case 8:
+ str = "32 kBytes";
+ break;
+ case 9:
+ str = "64 KBytes";
+ break;
+ case 10:
+ str = "128 KBytes";
+ break;
+ case 11:
+ str = "256 KBytes";
+ break;
+ default:
+ str = "RESERVED";
+ }
+ XLGMAC_PR("MTL Transmit FIFO Size : %s\n", str);
+
+ XLGMAC_PR("IEEE 1588 High Word Register Enable : %s\n",
+ pdata->hw_feat.adv_ts_hi ? "YES" : "NO");
+ XLGMAC_PR("Address width : %u\n",
+ pdata->hw_feat.dma_width);
+ XLGMAC_PR("DCB Feature Enable : %s\n",
+ pdata->hw_feat.dcb ? "YES" : "NO");
+ XLGMAC_PR("Split Header Feature Enable : %s\n",
+ pdata->hw_feat.sph ? "YES" : "NO");
+ XLGMAC_PR("TCP Segmentation Offload Enable : %s\n",
+ pdata->hw_feat.tso ? "YES" : "NO");
+ XLGMAC_PR("DMA Debug Registers Enabled : %s\n",
+ pdata->hw_feat.dma_debug ? "YES" : "NO");
+ XLGMAC_PR("RSS Feature Enabled : %s\n",
+ pdata->hw_feat.rss ? "YES" : "NO");
+ XLGMAC_PR("Number of Traffic classes : %u\n",
+ (pdata->hw_feat.tc_cnt));
+ XLGMAC_PR("Hash Table Size : %u\n",
+ pdata->hw_feat.hash_table_size);
+ XLGMAC_PR("Total number of L3 or L4 Filters : %u\n",
+ pdata->hw_feat.l3l4_filter_num);
+
+ /* HW Feature Register2 */
+ XLGMAC_PR("Number of MTL Receive Queues : %u\n",
+ pdata->hw_feat.rx_q_cnt);
+ XLGMAC_PR("Number of MTL Transmit Queues : %u\n",
+ pdata->hw_feat.tx_q_cnt);
+ XLGMAC_PR("Number of DMA Receive Channels : %u\n",
+ pdata->hw_feat.rx_ch_cnt);
+ XLGMAC_PR("Number of DMA Transmit Channels : %u\n",
+ pdata->hw_feat.tx_ch_cnt);
+
+ switch (pdata->hw_feat.pps_out_num) {
+ case 0:
+ str = "No PPS output";
+ break;
+ case 1:
+ str = "1 PPS output";
+ break;
+ case 2:
+ str = "2 PPS output";
+ break;
+ case 3:
+ str = "3 PPS output";
+ break;
+ case 4:
+ str = "4 PPS output";
+ break;
+ default:
+ str = "RESERVED";
+ }
+ XLGMAC_PR("Number of PPS Outputs : %s\n", str);
+
+ switch (pdata->hw_feat.aux_snap_num) {
+ case 0:
+ str = "No auxiliary input";
+ break;
+ case 1:
+ str = "1 auxiliary input";
+ break;
+ case 2:
+ str = "2 auxiliary input";
+ break;
+ case 3:
+ str = "3 auxiliary input";
+ break;
+ case 4:
+ str = "4 auxiliary input";
+ break;
+ default:
+ str = "RESERVED";
+ }
+ XLGMAC_PR("Number of Auxiliary Snapshot Inputs : %s", str);
+
+ XLGMAC_PR("\n");
+ XLGMAC_PR("=====================================================\n");
+ XLGMAC_PR("\n");
+}
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c
new file mode 100644
index 0000000..e9672b1
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c
@@ -0,0 +1,644 @@
+/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver
+ *
+ * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is dual-licensed; you may select either version 2 of
+ * the GNU General Public License ("GPL") or BSD license ("BSD").
+ *
+ * This Synopsys DWC XLGMAC software driver and associated documentation
+ * (hereinafter the "Software") is an unsupported proprietary work of
+ * Synopsys, Inc. unless otherwise expressly agreed to in writing between
+ * Synopsys and you. The Software IS NOT an item of Licensed Software or a
+ * Licensed Product under any End User Software License Agreement or
+ * Agreement for Licensed Products with Synopsys or any supplement thereto.
+ * Synopsys is a registered trademark of Synopsys, Inc. Other names included
+ * in the SOFTWARE may be the trademarks of their respective owners.
+ */
+
+#include "dwc-xlgmac.h"
+#include "dwc-xlgmac-reg.h"
+
+static void xlgmac_unmap_desc_data(struct xlgmac_pdata *pdata,
+ struct xlgmac_desc_data *desc_data)
+{
+ if (desc_data->skb_dma) {
+ if (desc_data->mapped_as_page) {
+ dma_unmap_page(pdata->dev, desc_data->skb_dma,
+ desc_data->skb_dma_len, DMA_TO_DEVICE);
+ } else {
+ dma_unmap_single(pdata->dev, desc_data->skb_dma,
+ desc_data->skb_dma_len, DMA_TO_DEVICE);
+ }
+ desc_data->skb_dma = 0;
+ desc_data->skb_dma_len = 0;
+ }
+
+ if (desc_data->skb) {
+ dev_kfree_skb_any(desc_data->skb);
+ desc_data->skb = NULL;
+ }
+
+ if (desc_data->rx.hdr.pa.pages)
+ put_page(desc_data->rx.hdr.pa.pages);
+
+ if (desc_data->rx.hdr.pa_unmap.pages) {
+ dma_unmap_page(pdata->dev, desc_data->rx.hdr.pa_unmap.pages_dma,
+ desc_data->rx.hdr.pa_unmap.pages_len,
+ DMA_FROM_DEVICE);
+ put_page(desc_data->rx.hdr.pa_unmap.pages);
+ }
+
+ if (desc_data->rx.buf.pa.pages)
+ put_page(desc_data->rx.buf.pa.pages);
+
+ if (desc_data->rx.buf.pa_unmap.pages) {
+ dma_unmap_page(pdata->dev, desc_data->rx.buf.pa_unmap.pages_dma,
+ desc_data->rx.buf.pa_unmap.pages_len,
+ DMA_FROM_DEVICE);
+ put_page(desc_data->rx.buf.pa_unmap.pages);
+ }
+
+ memset(&desc_data->tx, 0, sizeof(desc_data->tx));
+ memset(&desc_data->rx, 0, sizeof(desc_data->rx));
+
+ desc_data->mapped_as_page = 0;
+
+ if (desc_data->state_saved) {
+ desc_data->state_saved = 0;
+ desc_data->state.skb = NULL;
+ desc_data->state.len = 0;
+ desc_data->state.error = 0;
+ }
+}
+
+static void xlgmac_free_ring(struct xlgmac_pdata *pdata,
+ struct xlgmac_ring *ring)
+{
+ struct xlgmac_desc_data *desc_data;
+ unsigned int i;
+
+ if (!ring)
+ return;
+
+ if (ring->desc_data_head) {
+ for (i = 0; i < ring->dma_desc_count; i++) {
+ desc_data = XLGMAC_GET_DESC_DATA(ring, i);
+ xlgmac_unmap_desc_data(pdata, desc_data);
+ }
+
+ kfree(ring->desc_data_head);
+ ring->desc_data_head = NULL;
+ }
+
+ if (ring->rx_hdr_pa.pages) {
+ dma_unmap_page(pdata->dev, ring->rx_hdr_pa.pages_dma,
+ ring->rx_hdr_pa.pages_len, DMA_FROM_DEVICE);
+ put_page(ring->rx_hdr_pa.pages);
+
+ ring->rx_hdr_pa.pages = NULL;
+ ring->rx_hdr_pa.pages_len = 0;
+ ring->rx_hdr_pa.pages_offset = 0;
+ ring->rx_hdr_pa.pages_dma = 0;
+ }
+
+ if (ring->rx_buf_pa.pages) {
+ dma_unmap_page(pdata->dev, ring->rx_buf_pa.pages_dma,
+ ring->rx_buf_pa.pages_len, DMA_FROM_DEVICE);
+ put_page(ring->rx_buf_pa.pages);
+
+ ring->rx_buf_pa.pages = NULL;
+ ring->rx_buf_pa.pages_len = 0;
+ ring->rx_buf_pa.pages_offset = 0;
+ ring->rx_buf_pa.pages_dma = 0;
+ }
+
+ if (ring->dma_desc_head) {
+ dma_free_coherent(pdata->dev,
+ (sizeof(struct xlgmac_dma_desc) *
+ ring->dma_desc_count),
+ ring->dma_desc_head,
+ ring->dma_desc_head_addr);
+ ring->dma_desc_head = NULL;
+ }
+}
+
+static int xlgmac_init_ring(struct xlgmac_pdata *pdata,
+ struct xlgmac_ring *ring,
+ unsigned int dma_desc_count)
+{
+ if (!ring)
+ return 0;
+
+ /* Descriptors */
+ ring->dma_desc_count = dma_desc_count;
+ ring->dma_desc_head = dma_alloc_coherent(pdata->dev,
+ (sizeof(struct xlgmac_dma_desc) *
+ dma_desc_count),
+ &ring->dma_desc_head_addr,
+ GFP_KERNEL);
+ if (!ring->dma_desc_head)
+ return -ENOMEM;
+
+ /* Array of descriptor data */
+ ring->desc_data_head = kcalloc(dma_desc_count,
+ sizeof(struct xlgmac_desc_data),
+ GFP_KERNEL);
+ if (!ring->desc_data_head)
+ return -ENOMEM;
+
+ netif_dbg(pdata, drv, pdata->netdev,
+ "dma_desc_head=%p, dma_desc_head_addr=%pad, desc_data_head=%p\n",
+ ring->dma_desc_head,
+ &ring->dma_desc_head_addr,
+ ring->desc_data_head);
+
+ return 0;
+}
+
+static void xlgmac_free_rings(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_channel *channel;
+ unsigned int i;
+
+ if (!pdata->channel_head)
+ return;
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ xlgmac_free_ring(pdata, channel->tx_ring);
+ xlgmac_free_ring(pdata, channel->rx_ring);
+ }
+}
+
+static int xlgmac_alloc_rings(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_channel *channel;
+ unsigned int i;
+ int ret;
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ netif_dbg(pdata, drv, pdata->netdev, "%s - Tx ring:\n",
+ channel->name);
+
+ ret = xlgmac_init_ring(pdata, channel->tx_ring,
+ pdata->tx_desc_count);
+
+ if (ret) {
+ netdev_alert(pdata->netdev,
+ "error initializing Tx ring");
+ goto err_init_ring;
+ }
+
+ netif_dbg(pdata, drv, pdata->netdev, "%s - Rx ring:\n",
+ channel->name);
+
+ ret = xlgmac_init_ring(pdata, channel->rx_ring,
+ pdata->rx_desc_count);
+ if (ret) {
+ netdev_alert(pdata->netdev,
+ "error initializing Rx ring\n");
+ goto err_init_ring;
+ }
+ }
+
+ return 0;
+
+err_init_ring:
+ xlgmac_free_rings(pdata);
+
+ return ret;
+}
+
+static void xlgmac_free_channels(struct xlgmac_pdata *pdata)
+{
+ if (!pdata->channel_head)
+ return;
+
+ kfree(pdata->channel_head->tx_ring);
+ pdata->channel_head->tx_ring = NULL;
+
+ kfree(pdata->channel_head->rx_ring);
+ pdata->channel_head->rx_ring = NULL;
+
+ kfree(pdata->channel_head);
+
+ pdata->channel_head = NULL;
+ pdata->channel_count = 0;
+}
+
+static int xlgmac_alloc_channels(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_channel *channel_head, *channel;
+ struct xlgmac_ring *tx_ring, *rx_ring;
+ int ret = -ENOMEM;
+ unsigned int i;
+
+ channel_head = kcalloc(pdata->channel_count,
+ sizeof(struct xlgmac_channel), GFP_KERNEL);
+ if (!channel_head)
+ return ret;
+
+ netif_dbg(pdata, drv, pdata->netdev,
+ "channel_head=%p\n", channel_head);
+
+ tx_ring = kcalloc(pdata->tx_ring_count, sizeof(struct xlgmac_ring),
+ GFP_KERNEL);
+ if (!tx_ring)
+ goto err_tx_ring;
+
+ rx_ring = kcalloc(pdata->rx_ring_count, sizeof(struct xlgmac_ring),
+ GFP_KERNEL);
+ if (!rx_ring)
+ goto err_rx_ring;
+
+ for (i = 0, channel = channel_head; i < pdata->channel_count;
+ i++, channel++) {
+ snprintf(channel->name, sizeof(channel->name), "channel-%u", i);
+ channel->pdata = pdata;
+ channel->queue_index = i;
+ channel->dma_regs = pdata->mac_regs + DMA_CH_BASE +
+ (DMA_CH_INC * i);
+
+ if (pdata->per_channel_irq) {
+ /* Get the per DMA interrupt */
+ ret = pdata->channel_irq[i];
+ if (ret < 0) {
+ netdev_err(pdata->netdev,
+ "get_irq %u failed\n",
+ i + 1);
+ goto err_irq;
+ }
+ channel->dma_irq = ret;
+ }
+
+ if (i < pdata->tx_ring_count)
+ channel->tx_ring = tx_ring++;
+
+ if (i < pdata->rx_ring_count)
+ channel->rx_ring = rx_ring++;
+
+ netif_dbg(pdata, drv, pdata->netdev,
+ "%s: dma_regs=%p, tx_ring=%p, rx_ring=%p\n",
+ channel->name, channel->dma_regs,
+ channel->tx_ring, channel->rx_ring);
+ }
+
+ pdata->channel_head = channel_head;
+
+ return 0;
+
+err_irq:
+ kfree(rx_ring);
+
+err_rx_ring:
+ kfree(tx_ring);
+
+err_tx_ring:
+ kfree(channel_head);
+
+ return ret;
+}
+
+static void xlgmac_free_channels_and_rings(struct xlgmac_pdata *pdata)
+{
+ xlgmac_free_rings(pdata);
+
+ xlgmac_free_channels(pdata);
+}
+
+static int xlgmac_alloc_channels_and_rings(struct xlgmac_pdata *pdata)
+{
+ int ret;
+
+ ret = xlgmac_alloc_channels(pdata);
+ if (ret)
+ goto err_alloc;
+
+ ret = xlgmac_alloc_rings(pdata);
+ if (ret)
+ goto err_alloc;
+
+ return 0;
+
+err_alloc:
+ xlgmac_free_channels_and_rings(pdata);
+
+ return ret;
+}
+
+static int xlgmac_alloc_pages(struct xlgmac_pdata *pdata,
+ struct xlgmac_page_alloc *pa,
+ gfp_t gfp, int order)
+{
+ struct page *pages = NULL;
+ dma_addr_t pages_dma;
+
+ /* Try to obtain pages, decreasing order if necessary */
+ gfp |= __GFP_COLD | __GFP_COMP | __GFP_NOWARN;
+ while (order >= 0) {
+ pages = alloc_pages(gfp, order);
+ if (pages)
+ break;
+
+ order--;
+ }
+ if (!pages)
+ return -ENOMEM;
+
+ /* Map the pages */
+ pages_dma = dma_map_page(pdata->dev, pages, 0,
+ PAGE_SIZE << order, DMA_FROM_DEVICE);
+ if (dma_mapping_error(pdata->dev, pages_dma)) {
+ put_page(pages);
+ return -ENOMEM;
+ }
+
+ pa->pages = pages;
+ pa->pages_len = PAGE_SIZE << order;
+ pa->pages_offset = 0;
+ pa->pages_dma = pages_dma;
+
+ return 0;
+}
+
+static void xlgmac_set_buffer_data(struct xlgmac_buffer_data *bd,
+ struct xlgmac_page_alloc *pa,
+ unsigned int len)
+{
+ get_page(pa->pages);
+ bd->pa = *pa;
+
+ bd->dma_base = pa->pages_dma;
+ bd->dma_off = pa->pages_offset;
+ bd->dma_len = len;
+
+ pa->pages_offset += len;
+ if ((pa->pages_offset + len) > pa->pages_len) {
+ /* This data descriptor is responsible for unmapping page(s) */
+ bd->pa_unmap = *pa;
+
+ /* Get a new allocation next time */
+ pa->pages = NULL;
+ pa->pages_len = 0;
+ pa->pages_offset = 0;
+ pa->pages_dma = 0;
+ }
+}
+
+static int xlgmac_map_rx_buffer(struct xlgmac_pdata *pdata,
+ struct xlgmac_ring *ring,
+ struct xlgmac_desc_data *desc_data)
+{
+ int order, ret;
+
+ if (!ring->rx_hdr_pa.pages) {
+ ret = xlgmac_alloc_pages(pdata, &ring->rx_hdr_pa,
+ GFP_ATOMIC, 0);
+ if (ret)
+ return ret;
+ }
+
+ if (!ring->rx_buf_pa.pages) {
+ order = max_t(int, PAGE_ALLOC_COSTLY_ORDER - 1, 0);
+ ret = xlgmac_alloc_pages(pdata, &ring->rx_buf_pa,
+ GFP_ATOMIC, order);
+ if (ret)
+ return ret;
+ }
+
+ /* Set up the header page info */
+ xlgmac_set_buffer_data(&desc_data->rx.hdr, &ring->rx_hdr_pa,
+ XLGMAC_SKB_ALLOC_SIZE);
+
+ /* Set up the buffer page info */
+ xlgmac_set_buffer_data(&desc_data->rx.buf, &ring->rx_buf_pa,
+ pdata->rx_buf_size);
+
+ return 0;
+}
+
+static void xlgmac_tx_desc_init(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+ struct xlgmac_desc_data *desc_data;
+ struct xlgmac_dma_desc *dma_desc;
+ struct xlgmac_channel *channel;
+ struct xlgmac_ring *ring;
+ dma_addr_t dma_desc_addr;
+ unsigned int i, j;
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ ring = channel->tx_ring;
+ if (!ring)
+ break;
+
+ dma_desc = ring->dma_desc_head;
+ dma_desc_addr = ring->dma_desc_head_addr;
+
+ for (j = 0; j < ring->dma_desc_count; j++) {
+ desc_data = XLGMAC_GET_DESC_DATA(ring, j);
+
+ desc_data->dma_desc = dma_desc;
+ desc_data->dma_desc_addr = dma_desc_addr;
+
+ dma_desc++;
+ dma_desc_addr += sizeof(struct xlgmac_dma_desc);
+ }
+
+ ring->cur = 0;
+ ring->dirty = 0;
+ memset(&ring->tx, 0, sizeof(ring->tx));
+
+ hw_ops->tx_desc_init(channel);
+ }
+}
+
+static void xlgmac_rx_desc_init(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+ struct xlgmac_desc_data *desc_data;
+ struct xlgmac_dma_desc *dma_desc;
+ struct xlgmac_channel *channel;
+ struct xlgmac_ring *ring;
+ dma_addr_t dma_desc_addr;
+ unsigned int i, j;
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ ring = channel->rx_ring;
+ if (!ring)
+ break;
+
+ dma_desc = ring->dma_desc_head;
+ dma_desc_addr = ring->dma_desc_head_addr;
+
+ for (j = 0; j < ring->dma_desc_count; j++) {
+ desc_data = XLGMAC_GET_DESC_DATA(ring, j);
+
+ desc_data->dma_desc = dma_desc;
+ desc_data->dma_desc_addr = dma_desc_addr;
+
+ if (xlgmac_map_rx_buffer(pdata, ring, desc_data))
+ break;
+
+ dma_desc++;
+ dma_desc_addr += sizeof(struct xlgmac_dma_desc);
+ }
+
+ ring->cur = 0;
+ ring->dirty = 0;
+
+ hw_ops->rx_desc_init(channel);
+ }
+}
+
+static int xlgmac_map_tx_skb(struct xlgmac_channel *channel,
+ struct sk_buff *skb)
+{
+ struct xlgmac_pdata *pdata = channel->pdata;
+ struct xlgmac_ring *ring = channel->tx_ring;
+ unsigned int start_index, cur_index;
+ struct xlgmac_desc_data *desc_data;
+ unsigned int offset, datalen, len;
+ struct xlgmac_pkt_info *pkt_info;
+ struct skb_frag_struct *frag;
+ unsigned int tso, vlan;
+ dma_addr_t skb_dma;
+ unsigned int i;
+
+ offset = 0;
+ start_index = ring->cur;
+ cur_index = ring->cur;
+
+ pkt_info = &ring->pkt_info;
+ pkt_info->desc_count = 0;
+ pkt_info->length = 0;
+
+ tso = XLGMAC_GET_REG_BITS(pkt_info->attributes,
+ TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS,
+ TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN);
+ vlan = XLGMAC_GET_REG_BITS(pkt_info->attributes,
+ TX_PACKET_ATTRIBUTES_VLAN_CTAG_POS,
+ TX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN);
+
+ /* Save space for a context descriptor if needed */
+ if ((tso && (pkt_info->mss != ring->tx.cur_mss)) ||
+ (vlan && (pkt_info->vlan_ctag != ring->tx.cur_vlan_ctag)))
+ cur_index++;
+ desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index);
+
+ if (tso) {
+ /* Map the TSO header */
+ skb_dma = dma_map_single(pdata->dev, skb->data,
+ pkt_info->header_len, DMA_TO_DEVICE);
+ if (dma_mapping_error(pdata->dev, skb_dma)) {
+ netdev_alert(pdata->netdev, "dma_map_single failed\n");
+ goto err_out;
+ }
+ desc_data->skb_dma = skb_dma;
+ desc_data->skb_dma_len = pkt_info->header_len;
+ netif_dbg(pdata, tx_queued, pdata->netdev,
+ "skb header: index=%u, dma=%pad, len=%u\n",
+ cur_index, &skb_dma, pkt_info->header_len);
+
+ offset = pkt_info->header_len;
+
+ pkt_info->length += pkt_info->header_len;
+
+ cur_index++;
+ desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index);
+ }
+
+ /* Map the (remainder of the) packet */
+ for (datalen = skb_headlen(skb) - offset; datalen; ) {
+ len = min_t(unsigned int, datalen, XLGMAC_TX_MAX_BUF_SIZE);
+
+ skb_dma = dma_map_single(pdata->dev, skb->data + offset, len,
+ DMA_TO_DEVICE);
+ if (dma_mapping_error(pdata->dev, skb_dma)) {
+ netdev_alert(pdata->netdev, "dma_map_single failed\n");
+ goto err_out;
+ }
+ desc_data->skb_dma = skb_dma;
+ desc_data->skb_dma_len = len;
+ netif_dbg(pdata, tx_queued, pdata->netdev,
+ "skb data: index=%u, dma=%pad, len=%u\n",
+ cur_index, &skb_dma, len);
+
+ datalen -= len;
+ offset += len;
+
+ pkt_info->length += len;
+
+ cur_index++;
+ desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index);
+ }
+
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+ netif_dbg(pdata, tx_queued, pdata->netdev,
+ "mapping frag %u\n", i);
+
+ frag = &skb_shinfo(skb)->frags[i];
+ offset = 0;
+
+ for (datalen = skb_frag_size(frag); datalen; ) {
+ len = min_t(unsigned int, datalen,
+ XLGMAC_TX_MAX_BUF_SIZE);
+
+ skb_dma = skb_frag_dma_map(pdata->dev, frag, offset,
+ len, DMA_TO_DEVICE);
+ if (dma_mapping_error(pdata->dev, skb_dma)) {
+ netdev_alert(pdata->netdev,
+ "skb_frag_dma_map failed\n");
+ goto err_out;
+ }
+ desc_data->skb_dma = skb_dma;
+ desc_data->skb_dma_len = len;
+ desc_data->mapped_as_page = 1;
+ netif_dbg(pdata, tx_queued, pdata->netdev,
+ "skb frag: index=%u, dma=%pad, len=%u\n",
+ cur_index, &skb_dma, len);
+
+ datalen -= len;
+ offset += len;
+
+ pkt_info->length += len;
+
+ cur_index++;
+ desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index);
+ }
+ }
+
+ /* Save the skb address in the last entry. We always have some data
+ * that has been mapped so desc_data is always advanced past the last
+ * piece of mapped data - use the entry pointed to by cur_index - 1.
+ */
+ desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index - 1);
+ desc_data->skb = skb;
+
+ /* Save the number of descriptor entries used */
+ pkt_info->desc_count = cur_index - start_index;
+
+ return pkt_info->desc_count;
+
+err_out:
+ while (start_index < cur_index) {
+ desc_data = XLGMAC_GET_DESC_DATA(ring, start_index++);
+ xlgmac_unmap_desc_data(pdata, desc_data);
+ }
+
+ return 0;
+}
+
+void xlgmac_init_desc_ops(struct xlgmac_desc_ops *desc_ops)
+{
+ desc_ops->alloc_channles_and_rings = xlgmac_alloc_channels_and_rings;
+ desc_ops->free_channels_and_rings = xlgmac_free_channels_and_rings;
+ desc_ops->map_tx_skb = xlgmac_map_tx_skb;
+ desc_ops->map_rx_buffer = xlgmac_map_rx_buffer;
+ desc_ops->unmap_desc_data = xlgmac_unmap_desc_data;
+ desc_ops->tx_desc_init = xlgmac_tx_desc_init;
+ desc_ops->rx_desc_init = xlgmac_rx_desc_init;
+}
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c
new file mode 100644
index 0000000..0dec1dc
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c
@@ -0,0 +1,3145 @@
+/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver
+ *
+ * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is dual-licensed; you may select either version 2 of
+ * the GNU General Public License ("GPL") or BSD license ("BSD").
+ *
+ * This Synopsys DWC XLGMAC software driver and associated documentation
+ * (hereinafter the "Software") is an unsupported proprietary work of
+ * Synopsys, Inc. unless otherwise expressly agreed to in writing between
+ * Synopsys and you. The Software IS NOT an item of Licensed Software or a
+ * Licensed Product under any End User Software License Agreement or
+ * Agreement for Licensed Products with Synopsys or any supplement thereto.
+ * Synopsys is a registered trademark of Synopsys, Inc. Other names included
+ * in the SOFTWARE may be the trademarks of their respective owners.
+ */
+
+#include <linux/phy.h>
+#include <linux/mdio.h>
+#include <linux/clk.h>
+#include <linux/bitrev.h>
+#include <linux/crc32.h>
+#include <linux/dcbnl.h>
+
+#include "dwc-xlgmac.h"
+#include "dwc-xlgmac-reg.h"
+
+static int xlgmac_tx_complete(struct xlgmac_dma_desc *dma_desc)
+{
+ return !XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+ TX_NORMAL_DESC3_OWN_POS,
+ TX_NORMAL_DESC3_OWN_LEN);
+}
+
+static int xlgmac_disable_rx_csum(struct xlgmac_pdata *pdata)
+{
+ u32 regval;
+
+ regval = readl(pdata->mac_regs + MAC_RCR);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_IPC_POS,
+ MAC_RCR_IPC_LEN, 0);
+ writel(regval, pdata->mac_regs + MAC_RCR);
+
+ return 0;
+}
+
+static int xlgmac_enable_rx_csum(struct xlgmac_pdata *pdata)
+{
+ u32 regval;
+
+ regval = readl(pdata->mac_regs + MAC_RCR);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_IPC_POS,
+ MAC_RCR_IPC_LEN, 1);
+ writel(regval, pdata->mac_regs + MAC_RCR);
+
+ return 0;
+}
+
+static int xlgmac_set_mac_address(struct xlgmac_pdata *pdata, u8 *addr)
+{
+ unsigned int mac_addr_hi, mac_addr_lo;
+
+ mac_addr_hi = (addr[5] << 8) | (addr[4] << 0);
+ mac_addr_lo = (addr[3] << 24) | (addr[2] << 16) |
+ (addr[1] << 8) | (addr[0] << 0);
+
+ writel(mac_addr_hi, pdata->mac_regs + MAC_MACA0HR);
+ writel(mac_addr_lo, pdata->mac_regs + MAC_MACA0LR);
+
+ return 0;
+}
+
+static void xlgmac_set_mac_reg(struct xlgmac_pdata *pdata,
+ struct netdev_hw_addr *ha,
+ unsigned int *mac_reg)
+{
+ unsigned int mac_addr_hi, mac_addr_lo;
+ u8 *mac_addr;
+
+ mac_addr_lo = 0;
+ mac_addr_hi = 0;
+
+ if (ha) {
+ mac_addr = (u8 *)&mac_addr_lo;
+ mac_addr[0] = ha->addr[0];
+ mac_addr[1] = ha->addr[1];
+ mac_addr[2] = ha->addr[2];
+ mac_addr[3] = ha->addr[3];
+ mac_addr = (u8 *)&mac_addr_hi;
+ mac_addr[0] = ha->addr[4];
+ mac_addr[1] = ha->addr[5];
+
+ netif_dbg(pdata, drv, pdata->netdev,
+ "adding mac address %pM at %#x\n",
+ ha->addr, *mac_reg);
+
+ mac_addr_hi = XLGMAC_SET_REG_BITS(mac_addr_hi,
+ MAC_MACA1HR_AE_POS,
+ MAC_MACA1HR_AE_LEN,
+ 1);
+ }
+
+ writel(mac_addr_hi, pdata->mac_regs + *mac_reg);
+ *mac_reg += MAC_MACA_INC;
+ writel(mac_addr_lo, pdata->mac_regs + *mac_reg);
+ *mac_reg += MAC_MACA_INC;
+}
+
+static int xlgmac_enable_rx_vlan_stripping(struct xlgmac_pdata *pdata)
+{
+ u32 regval;
+
+ regval = readl(pdata->mac_regs + MAC_VLANTR);
+ /* Put the VLAN tag in the Rx descriptor */
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_EVLRXS_POS,
+ MAC_VLANTR_EVLRXS_LEN, 1);
+ /* Don't check the VLAN type */
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_DOVLTC_POS,
+ MAC_VLANTR_DOVLTC_LEN, 1);
+ /* Check only C-TAG (0x8100) packets */
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_ERSVLM_POS,
+ MAC_VLANTR_ERSVLM_LEN, 0);
+ /* Don't consider an S-TAG (0x88A8) packet as a VLAN packet */
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_ESVL_POS,
+ MAC_VLANTR_ESVL_LEN, 0);
+ /* Enable VLAN tag stripping */
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_EVLS_POS,
+ MAC_VLANTR_EVLS_LEN, 0x3);
+ writel(regval, pdata->mac_regs + MAC_VLANTR);
+
+ return 0;
+}
+
+static int xlgmac_disable_rx_vlan_stripping(struct xlgmac_pdata *pdata)
+{
+ u32 regval;
+
+ regval = readl(pdata->mac_regs + MAC_VLANTR);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_EVLS_POS,
+ MAC_VLANTR_EVLS_LEN, 0);
+ writel(regval, pdata->mac_regs + MAC_VLANTR);
+
+ return 0;
+}
+
+static int xlgmac_enable_rx_vlan_filtering(struct xlgmac_pdata *pdata)
+{
+ u32 regval;
+
+ regval = readl(pdata->mac_regs + MAC_PFR);
+ /* Enable VLAN filtering */
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_VTFE_POS,
+ MAC_PFR_VTFE_LEN, 1);
+ writel(regval, pdata->mac_regs + MAC_PFR);
+
+ regval = readl(pdata->mac_regs + MAC_VLANTR);
+ /* Enable VLAN Hash Table filtering */
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_VTHM_POS,
+ MAC_VLANTR_VTHM_LEN, 1);
+ /* Disable VLAN tag inverse matching */
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_VTIM_POS,
+ MAC_VLANTR_VTIM_LEN, 0);
+ /* Only filter on the lower 12-bits of the VLAN tag */
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_ETV_POS,
+ MAC_VLANTR_ETV_LEN, 1);
+ /* In order for the VLAN Hash Table filtering to be effective,
+ * the VLAN tag identifier in the VLAN Tag Register must not
+ * be zero. Set the VLAN tag identifier to "1" to enable the
+ * VLAN Hash Table filtering. This implies that a VLAN tag of
+ * 1 will always pass filtering.
+ */
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANTR_VL_POS,
+ MAC_VLANTR_VL_LEN, 1);
+ writel(regval, pdata->mac_regs + MAC_VLANTR);
+
+ return 0;
+}
+
+static int xlgmac_disable_rx_vlan_filtering(struct xlgmac_pdata *pdata)
+{
+ u32 regval;
+
+ regval = readl(pdata->mac_regs + MAC_PFR);
+ /* Disable VLAN filtering */
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_VTFE_POS,
+ MAC_PFR_VTFE_LEN, 0);
+ writel(regval, pdata->mac_regs + MAC_PFR);
+
+ return 0;
+}
+
+static u32 xlgmac_vid_crc32_le(__le16 vid_le)
+{
+ unsigned char *data = (unsigned char *)&vid_le;
+ unsigned char data_byte = 0;
+ u32 poly = 0xedb88320;
+ u32 crc = ~0;
+ u32 temp = 0;
+ int i, bits;
+
+ bits = get_bitmask_order(VLAN_VID_MASK);
+ for (i = 0; i < bits; i++) {
+ if ((i % 8) == 0)
+ data_byte = data[i / 8];
+
+ temp = ((crc & 1) ^ data_byte) & 1;
+ crc >>= 1;
+ data_byte >>= 1;
+
+ if (temp)
+ crc ^= poly;
+ }
+
+ return crc;
+}
+
+static int xlgmac_update_vlan_hash_table(struct xlgmac_pdata *pdata)
+{
+ u16 vlan_hash_table = 0;
+ __le16 vid_le;
+ u32 regval;
+ u32 crc;
+ u16 vid;
+
+ /* Generate the VLAN Hash Table value */
+ for_each_set_bit(vid, pdata->active_vlans, VLAN_N_VID) {
+ /* Get the CRC32 value of the VLAN ID */
+ vid_le = cpu_to_le16(vid);
+ crc = bitrev32(~xlgmac_vid_crc32_le(vid_le)) >> 28;
+
+ vlan_hash_table |= (1 << crc);
+ }
+
+ regval = readl(pdata->mac_regs + MAC_VLANHTR);
+ /* Set the VLAN Hash Table filtering register */
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANHTR_VLHT_POS,
+ MAC_VLANHTR_VLHT_LEN, vlan_hash_table);
+ writel(regval, pdata->mac_regs + MAC_VLANHTR);
+
+ return 0;
+}
+
+static int xlgmac_set_promiscuous_mode(struct xlgmac_pdata *pdata,
+ unsigned int enable)
+{
+ unsigned int val = enable ? 1 : 0;
+ u32 regval;
+
+ regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_PFR),
+ MAC_PFR_PR_POS, MAC_PFR_PR_LEN);
+ if (regval == val)
+ return 0;
+
+ netif_dbg(pdata, drv, pdata->netdev, "%s promiscuous mode\n",
+ enable ? "entering" : "leaving");
+
+ regval = readl(pdata->mac_regs + MAC_PFR);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_PR_POS,
+ MAC_PFR_PR_LEN, val);
+ writel(regval, pdata->mac_regs + MAC_PFR);
+
+ /* Hardware will still perform VLAN filtering in promiscuous mode */
+ if (enable) {
+ xlgmac_disable_rx_vlan_filtering(pdata);
+ } else {
+ if (pdata->netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
+ xlgmac_enable_rx_vlan_filtering(pdata);
+ }
+
+ return 0;
+}
+
+static int xlgmac_set_all_multicast_mode(struct xlgmac_pdata *pdata,
+ unsigned int enable)
+{
+ unsigned int val = enable ? 1 : 0;
+ u32 regval;
+
+ regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_PFR),
+ MAC_PFR_PM_POS, MAC_PFR_PM_LEN);
+ if (regval == val)
+ return 0;
+
+ netif_dbg(pdata, drv, pdata->netdev, "%s allmulti mode\n",
+ enable ? "entering" : "leaving");
+
+ regval = readl(pdata->mac_regs + MAC_PFR);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_PM_POS,
+ MAC_PFR_PM_LEN, val);
+ writel(regval, pdata->mac_regs + MAC_PFR);
+
+ return 0;
+}
+
+static void xlgmac_set_mac_addn_addrs(struct xlgmac_pdata *pdata)
+{
+ struct net_device *netdev = pdata->netdev;
+ struct netdev_hw_addr *ha;
+ unsigned int addn_macs;
+ unsigned int mac_reg;
+
+ mac_reg = MAC_MACA1HR;
+ addn_macs = pdata->hw_feat.addn_mac;
+
+ if (netdev_uc_count(netdev) > addn_macs) {
+ xlgmac_set_promiscuous_mode(pdata, 1);
+ } else {
+ netdev_for_each_uc_addr(ha, netdev) {
+ xlgmac_set_mac_reg(pdata, ha, &mac_reg);
+ addn_macs--;
+ }
+
+ if (netdev_mc_count(netdev) > addn_macs) {
+ xlgmac_set_all_multicast_mode(pdata, 1);
+ } else {
+ netdev_for_each_mc_addr(ha, netdev) {
+ xlgmac_set_mac_reg(pdata, ha, &mac_reg);
+ addn_macs--;
+ }
+ }
+ }
+
+ /* Clear remaining additional MAC address entries */
+ while (addn_macs--)
+ xlgmac_set_mac_reg(pdata, NULL, &mac_reg);
+}
+
+static void xlgmac_set_mac_hash_table(struct xlgmac_pdata *pdata)
+{
+ unsigned int hash_table_shift, hash_table_count;
+ u32 hash_table[XLGMAC_MAC_HASH_TABLE_SIZE];
+ struct net_device *netdev = pdata->netdev;
+ struct netdev_hw_addr *ha;
+ unsigned int hash_reg;
+ unsigned int i;
+ u32 crc;
+
+ hash_table_shift = 26 - (pdata->hw_feat.hash_table_size >> 7);
+ hash_table_count = pdata->hw_feat.hash_table_size / 32;
+ memset(hash_table, 0, sizeof(hash_table));
+
+ /* Build the MAC Hash Table register values */
+ netdev_for_each_uc_addr(ha, netdev) {
+ crc = bitrev32(~crc32_le(~0, ha->addr, ETH_ALEN));
+ crc >>= hash_table_shift;
+ hash_table[crc >> 5] |= (1 << (crc & 0x1f));
+ }
+
+ netdev_for_each_mc_addr(ha, netdev) {
+ crc = bitrev32(~crc32_le(~0, ha->addr, ETH_ALEN));
+ crc >>= hash_table_shift;
+ hash_table[crc >> 5] |= (1 << (crc & 0x1f));
+ }
+
+ /* Set the MAC Hash Table registers */
+ hash_reg = MAC_HTR0;
+ for (i = 0; i < hash_table_count; i++) {
+ writel(hash_table[i], pdata->mac_regs + hash_reg);
+ hash_reg += MAC_HTR_INC;
+ }
+}
+
+static int xlgmac_add_mac_addresses(struct xlgmac_pdata *pdata)
+{
+ if (pdata->hw_feat.hash_table_size)
+ xlgmac_set_mac_hash_table(pdata);
+ else
+ xlgmac_set_mac_addn_addrs(pdata);
+
+ return 0;
+}
+
+static void xlgmac_config_mac_address(struct xlgmac_pdata *pdata)
+{
+ u32 regval;
+
+ xlgmac_set_mac_address(pdata, pdata->netdev->dev_addr);
+
+ /* Filtering is done using perfect filtering and hash filtering */
+ if (pdata->hw_feat.hash_table_size) {
+ regval = readl(pdata->mac_regs + MAC_PFR);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_HPF_POS,
+ MAC_PFR_HPF_LEN, 1);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_HUC_POS,
+ MAC_PFR_HUC_LEN, 1);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_PFR_HMC_POS,
+ MAC_PFR_HMC_LEN, 1);
+ writel(regval, pdata->mac_regs + MAC_PFR);
+ }
+}
+
+static void xlgmac_config_jumbo_enable(struct xlgmac_pdata *pdata)
+{
+ unsigned int val;
+ u32 regval;
+
+ val = (pdata->netdev->mtu > XLGMAC_STD_PACKET_MTU) ? 1 : 0;
+
+ regval = readl(pdata->mac_regs + MAC_RCR);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_JE_POS,
+ MAC_RCR_JE_LEN, val);
+ writel(regval, pdata->mac_regs + MAC_RCR);
+}
+
+static void xlgmac_config_checksum_offload(struct xlgmac_pdata *pdata)
+{
+ if (pdata->netdev->features & NETIF_F_RXCSUM)
+ xlgmac_enable_rx_csum(pdata);
+ else
+ xlgmac_disable_rx_csum(pdata);
+}
+
+static void xlgmac_config_vlan_support(struct xlgmac_pdata *pdata)
+{
+ u32 regval;
+
+ regval = readl(pdata->mac_regs + MAC_VLANIR);
+ /* Indicate that VLAN Tx CTAGs come from context descriptors */
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANIR_CSVL_POS,
+ MAC_VLANIR_CSVL_LEN, 0);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_VLANIR_VLTI_POS,
+ MAC_VLANIR_VLTI_LEN, 1);
+ writel(regval, pdata->mac_regs + MAC_VLANIR);
+
+ /* Set the current VLAN Hash Table register value */
+ xlgmac_update_vlan_hash_table(pdata);
+
+ if (pdata->netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
+ xlgmac_enable_rx_vlan_filtering(pdata);
+ else
+ xlgmac_disable_rx_vlan_filtering(pdata);
+
+ if (pdata->netdev->features & NETIF_F_HW_VLAN_CTAG_RX)
+ xlgmac_enable_rx_vlan_stripping(pdata);
+ else
+ xlgmac_disable_rx_vlan_stripping(pdata);
+}
+
+static int xlgmac_config_rx_mode(struct xlgmac_pdata *pdata)
+{
+ struct net_device *netdev = pdata->netdev;
+ unsigned int pr_mode, am_mode;
+
+ pr_mode = ((netdev->flags & IFF_PROMISC) != 0);
+ am_mode = ((netdev->flags & IFF_ALLMULTI) != 0);
+
+ xlgmac_set_promiscuous_mode(pdata, pr_mode);
+ xlgmac_set_all_multicast_mode(pdata, am_mode);
+
+ xlgmac_add_mac_addresses(pdata);
+
+ return 0;
+}
+
+static void xlgmac_prepare_tx_stop(struct xlgmac_pdata *pdata,
+ struct xlgmac_channel *channel)
+{
+ unsigned int tx_dsr, tx_pos, tx_qidx;
+ unsigned long tx_timeout;
+ unsigned int tx_status;
+
+ /* Calculate the status register to read and the position within */
+ if (channel->queue_index < DMA_DSRX_FIRST_QUEUE) {
+ tx_dsr = DMA_DSR0;
+ tx_pos = (channel->queue_index * DMA_DSR_Q_LEN) +
+ DMA_DSR0_TPS_START;
+ } else {
+ tx_qidx = channel->queue_index - DMA_DSRX_FIRST_QUEUE;
+
+ tx_dsr = DMA_DSR1 + ((tx_qidx / DMA_DSRX_QPR) * DMA_DSRX_INC);
+ tx_pos = ((tx_qidx % DMA_DSRX_QPR) * DMA_DSR_Q_LEN) +
+ DMA_DSRX_TPS_START;
+ }
+
+ /* The Tx engine cannot be stopped if it is actively processing
+ * descriptors. Wait for the Tx engine to enter the stopped or
+ * suspended state. Don't wait forever though...
+ */
+ tx_timeout = jiffies + (XLGMAC_DMA_STOP_TIMEOUT * HZ);
+ while (time_before(jiffies, tx_timeout)) {
+ tx_status = readl(pdata->mac_regs + tx_dsr);
+ tx_status = XLGMAC_GET_REG_BITS(tx_status, tx_pos,
+ DMA_DSR_TPS_LEN);
+ if ((tx_status == DMA_TPS_STOPPED) ||
+ (tx_status == DMA_TPS_SUSPENDED))
+ break;
+
+ usleep_range(500, 1000);
+ }
+
+ if (!time_before(jiffies, tx_timeout))
+ netdev_info(pdata->netdev,
+ "timed out waiting for Tx DMA channel %u to stop\n",
+ channel->queue_index);
+}
+
+static void xlgmac_enable_tx(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_channel *channel;
+ unsigned int i;
+ u32 regval;
+
+ /* Enable each Tx DMA channel */
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ if (!channel->tx_ring)
+ break;
+
+ regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+ regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_ST_POS,
+ DMA_CH_TCR_ST_LEN, 1);
+ writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+ }
+
+ /* Enable each Tx queue */
+ for (i = 0; i < pdata->tx_q_count; i++) {
+ regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+ regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TXQEN_POS,
+ MTL_Q_TQOMR_TXQEN_LEN,
+ MTL_Q_ENABLED);
+ writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+ }
+
+ /* Enable MAC Tx */
+ regval = readl(pdata->mac_regs + MAC_TCR);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_TE_POS,
+ MAC_TCR_TE_LEN, 1);
+ writel(regval, pdata->mac_regs + MAC_TCR);
+}
+
+static void xlgmac_disable_tx(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_channel *channel;
+ unsigned int i;
+ u32 regval;
+
+ /* Prepare for Tx DMA channel stop */
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ if (!channel->tx_ring)
+ break;
+
+ xlgmac_prepare_tx_stop(pdata, channel);
+ }
+
+ /* Disable MAC Tx */
+ regval = readl(pdata->mac_regs + MAC_TCR);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_TE_POS,
+ MAC_TCR_TE_LEN, 0);
+ writel(regval, pdata->mac_regs + MAC_TCR);
+
+ /* Disable each Tx queue */
+ for (i = 0; i < pdata->tx_q_count; i++) {
+ regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+ regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TXQEN_POS,
+ MTL_Q_TQOMR_TXQEN_LEN, 0);
+ writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+ }
+
+ /* Disable each Tx DMA channel */
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ if (!channel->tx_ring)
+ break;
+
+ regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+ regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_ST_POS,
+ DMA_CH_TCR_ST_LEN, 0);
+ writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+ }
+}
+
+static void xlgmac_prepare_rx_stop(struct xlgmac_pdata *pdata,
+ unsigned int queue)
+{
+ unsigned int rx_status, prxq, rxqsts;
+ unsigned long rx_timeout;
+
+ /* The Rx engine cannot be stopped if it is actively processing
+ * packets. Wait for the Rx queue to empty the Rx fifo. Don't
+ * wait forever though...
+ */
+ rx_timeout = jiffies + (XLGMAC_DMA_STOP_TIMEOUT * HZ);
+ while (time_before(jiffies, rx_timeout)) {
+ rx_status = readl(XLGMAC_MTL_REG(pdata, queue, MTL_Q_RQDR));
+ prxq = XLGMAC_GET_REG_BITS(rx_status, MTL_Q_RQDR_PRXQ_POS,
+ MTL_Q_RQDR_PRXQ_LEN);
+ rxqsts = XLGMAC_GET_REG_BITS(rx_status, MTL_Q_RQDR_RXQSTS_POS,
+ MTL_Q_RQDR_RXQSTS_LEN);
+ if ((prxq == 0) && (rxqsts == 0))
+ break;
+
+ usleep_range(500, 1000);
+ }
+
+ if (!time_before(jiffies, rx_timeout))
+ netdev_info(pdata->netdev,
+ "timed out waiting for Rx queue %u to empty\n",
+ queue);
+}
+
+static void xlgmac_enable_rx(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_channel *channel;
+ unsigned int regval, i;
+
+ /* Enable each Rx DMA channel */
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ if (!channel->rx_ring)
+ break;
+
+ regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+ regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RCR_SR_POS,
+ DMA_CH_RCR_SR_LEN, 1);
+ writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+ }
+
+ /* Enable each Rx queue */
+ regval = 0;
+ for (i = 0; i < pdata->rx_q_count; i++)
+ regval |= (0x02 << (i << 1));
+ writel(regval, pdata->mac_regs + MAC_RQC0R);
+
+ /* Enable MAC Rx */
+ regval = readl(pdata->mac_regs + MAC_RCR);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_DCRCC_POS,
+ MAC_RCR_DCRCC_LEN, 1);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_CST_POS,
+ MAC_RCR_CST_LEN, 1);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_ACS_POS,
+ MAC_RCR_ACS_LEN, 1);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_RE_POS,
+ MAC_RCR_RE_LEN, 1);
+ writel(regval, pdata->mac_regs + MAC_RCR);
+}
+
+static void xlgmac_disable_rx(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_channel *channel;
+ unsigned int i;
+ u32 regval;
+
+ /* Disable MAC Rx */
+ regval = readl(pdata->mac_regs + MAC_RCR);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_DCRCC_POS,
+ MAC_RCR_DCRCC_LEN, 0);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_CST_POS,
+ MAC_RCR_CST_LEN, 0);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_ACS_POS,
+ MAC_RCR_ACS_LEN, 0);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_RE_POS,
+ MAC_RCR_RE_LEN, 0);
+ writel(regval, pdata->mac_regs + MAC_RCR);
+
+ /* Prepare for Rx DMA channel stop */
+ for (i = 0; i < pdata->rx_q_count; i++)
+ xlgmac_prepare_rx_stop(pdata, i);
+
+ /* Disable each Rx queue */
+ writel(0, pdata->mac_regs + MAC_RQC0R);
+
+ /* Disable each Rx DMA channel */
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ if (!channel->rx_ring)
+ break;
+
+ regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+ regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RCR_SR_POS,
+ DMA_CH_RCR_SR_LEN, 0);
+ writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+ }
+}
+
+static void xlgmac_tx_start_xmit(struct xlgmac_channel *channel,
+ struct xlgmac_ring *ring)
+{
+ struct xlgmac_pdata *pdata = channel->pdata;
+ struct xlgmac_desc_data *desc_data;
+
+ /* Make sure everything is written before the register write */
+ wmb();
+
+ /* Issue a poll command to Tx DMA by writing address
+ * of next immediate free descriptor
+ */
+ desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur);
+ writel(lower_32_bits(desc_data->dma_desc_addr),
+ XLGMAC_DMA_REG(channel, DMA_CH_TDTR_LO));
+
+ /* Start the Tx timer */
+ if (pdata->tx_usecs && !channel->tx_timer_active) {
+ channel->tx_timer_active = 1;
+ mod_timer(&channel->tx_timer,
+ jiffies + usecs_to_jiffies(pdata->tx_usecs));
+ }
+
+ ring->tx.xmit_more = 0;
+}
+
+static void xlgmac_dev_xmit(struct xlgmac_channel *channel)
+{
+ struct xlgmac_pdata *pdata = channel->pdata;
+ struct xlgmac_ring *ring = channel->tx_ring;
+ unsigned int tso_context, vlan_context;
+ struct xlgmac_desc_data *desc_data;
+ struct xlgmac_dma_desc *dma_desc;
+ struct xlgmac_pkt_info *pkt_info;
+ unsigned int csum, tso, vlan;
+ int start_index = ring->cur;
+ int cur_index = ring->cur;
+ unsigned int tx_set_ic;
+ int i;
+
+ pkt_info = &ring->pkt_info;
+ csum = XLGMAC_GET_REG_BITS(pkt_info->attributes,
+ TX_PACKET_ATTRIBUTES_CSUM_ENABLE_POS,
+ TX_PACKET_ATTRIBUTES_CSUM_ENABLE_LEN);
+ tso = XLGMAC_GET_REG_BITS(pkt_info->attributes,
+ TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS,
+ TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN);
+ vlan = XLGMAC_GET_REG_BITS(pkt_info->attributes,
+ TX_PACKET_ATTRIBUTES_VLAN_CTAG_POS,
+ TX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN);
+
+ if (tso && (pkt_info->mss != ring->tx.cur_mss))
+ tso_context = 1;
+ else
+ tso_context = 0;
+
+ if (vlan && (pkt_info->vlan_ctag != ring->tx.cur_vlan_ctag))
+ vlan_context = 1;
+ else
+ vlan_context = 0;
+
+ /* Determine if an interrupt should be generated for this Tx:
+ * Interrupt:
+ * - Tx frame count exceeds the frame count setting
+ * - Addition of Tx frame count to the frame count since the
+ * last interrupt was set exceeds the frame count setting
+ * No interrupt:
+ * - No frame count setting specified (ethtool -C ethX tx-frames 0)
+ * - Addition of Tx frame count to the frame count since the
+ * last interrupt was set does not exceed the frame count setting
+ */
+ ring->coalesce_count += pkt_info->tx_packets;
+ if (!pdata->tx_frames)
+ tx_set_ic = 0;
+ else if (pkt_info->tx_packets > pdata->tx_frames)
+ tx_set_ic = 1;
+ else if ((ring->coalesce_count % pdata->tx_frames) <
+ pkt_info->tx_packets)
+ tx_set_ic = 1;
+ else
+ tx_set_ic = 0;
+
+ desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index);
+ dma_desc = desc_data->dma_desc;
+
+ /* Create a context descriptor if this is a TSO pkt_info */
+ if (tso_context || vlan_context) {
+ if (tso_context) {
+ netif_dbg(pdata, tx_queued, pdata->netdev,
+ "TSO context descriptor, mss=%u\n",
+ pkt_info->mss);
+
+ /* Set the MSS size */
+ dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc2,
+ TX_CONTEXT_DESC2_MSS_POS,
+ TX_CONTEXT_DESC2_MSS_LEN,
+ pkt_info->mss);
+
+ /* Mark it as a CONTEXT descriptor */
+ dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc3,
+ TX_CONTEXT_DESC3_CTXT_POS,
+ TX_CONTEXT_DESC3_CTXT_LEN,
+ 1);
+
+ /* Indicate this descriptor contains the MSS */
+ dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc3,
+ TX_CONTEXT_DESC3_TCMSSV_POS,
+ TX_CONTEXT_DESC3_TCMSSV_LEN,
+ 1);
+
+ ring->tx.cur_mss = pkt_info->mss;
+ }
+
+ if (vlan_context) {
+ netif_dbg(pdata, tx_queued, pdata->netdev,
+ "VLAN context descriptor, ctag=%u\n",
+ pkt_info->vlan_ctag);
+
+ /* Mark it as a CONTEXT descriptor */
+ dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc3,
+ TX_CONTEXT_DESC3_CTXT_POS,
+ TX_CONTEXT_DESC3_CTXT_LEN,
+ 1);
+
+ /* Set the VLAN tag */
+ dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc3,
+ TX_CONTEXT_DESC3_VT_POS,
+ TX_CONTEXT_DESC3_VT_LEN,
+ pkt_info->vlan_ctag);
+
+ /* Indicate this descriptor contains the VLAN tag */
+ dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc3,
+ TX_CONTEXT_DESC3_VLTV_POS,
+ TX_CONTEXT_DESC3_VLTV_LEN,
+ 1);
+
+ ring->tx.cur_vlan_ctag = pkt_info->vlan_ctag;
+ }
+
+ cur_index++;
+ desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index);
+ dma_desc = desc_data->dma_desc;
+ }
+
+ /* Update buffer address (for TSO this is the header) */
+ dma_desc->desc0 = cpu_to_le32(lower_32_bits(desc_data->skb_dma));
+ dma_desc->desc1 = cpu_to_le32(upper_32_bits(desc_data->skb_dma));
+
+ /* Update the buffer length */
+ dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc2,
+ TX_NORMAL_DESC2_HL_B1L_POS,
+ TX_NORMAL_DESC2_HL_B1L_LEN,
+ desc_data->skb_dma_len);
+
+ /* VLAN tag insertion check */
+ if (vlan)
+ dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc2,
+ TX_NORMAL_DESC2_VTIR_POS,
+ TX_NORMAL_DESC2_VTIR_LEN,
+ TX_NORMAL_DESC2_VLAN_INSERT);
+
+ /* Timestamp enablement check */
+ if (XLGMAC_GET_REG_BITS(pkt_info->attributes,
+ TX_PACKET_ATTRIBUTES_PTP_POS,
+ TX_PACKET_ATTRIBUTES_PTP_LEN))
+ dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc2,
+ TX_NORMAL_DESC2_TTSE_POS,
+ TX_NORMAL_DESC2_TTSE_LEN,
+ 1);
+
+ /* Mark it as First Descriptor */
+ dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc3,
+ TX_NORMAL_DESC3_FD_POS,
+ TX_NORMAL_DESC3_FD_LEN,
+ 1);
+
+ /* Mark it as a NORMAL descriptor */
+ dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc3,
+ TX_NORMAL_DESC3_CTXT_POS,
+ TX_NORMAL_DESC3_CTXT_LEN,
+ 0);
+
+ /* Set OWN bit if not the first descriptor */
+ if (cur_index != start_index)
+ dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc3,
+ TX_NORMAL_DESC3_OWN_POS,
+ TX_NORMAL_DESC3_OWN_LEN,
+ 1);
+
+ if (tso) {
+ /* Enable TSO */
+ dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc3,
+ TX_NORMAL_DESC3_TSE_POS,
+ TX_NORMAL_DESC3_TSE_LEN, 1);
+ dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc3,
+ TX_NORMAL_DESC3_TCPPL_POS,
+ TX_NORMAL_DESC3_TCPPL_LEN,
+ pkt_info->tcp_payload_len);
+ dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc3,
+ TX_NORMAL_DESC3_TCPHDRLEN_POS,
+ TX_NORMAL_DESC3_TCPHDRLEN_LEN,
+ pkt_info->tcp_header_len / 4);
+
+ pdata->stats.tx_tso_packets++;
+ } else {
+ /* Enable CRC and Pad Insertion */
+ dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc3,
+ TX_NORMAL_DESC3_CPC_POS,
+ TX_NORMAL_DESC3_CPC_LEN, 0);
+
+ /* Enable HW CSUM */
+ if (csum)
+ dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc3,
+ TX_NORMAL_DESC3_CIC_POS,
+ TX_NORMAL_DESC3_CIC_LEN,
+ 0x3);
+
+ /* Set the total length to be transmitted */
+ dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc3,
+ TX_NORMAL_DESC3_FL_POS,
+ TX_NORMAL_DESC3_FL_LEN,
+ pkt_info->length);
+ }
+
+ for (i = cur_index - start_index + 1; i < pkt_info->desc_count; i++) {
+ cur_index++;
+ desc_data = XLGMAC_GET_DESC_DATA(ring, cur_index);
+ dma_desc = desc_data->dma_desc;
+
+ /* Update buffer address */
+ dma_desc->desc0 =
+ cpu_to_le32(lower_32_bits(desc_data->skb_dma));
+ dma_desc->desc1 =
+ cpu_to_le32(upper_32_bits(desc_data->skb_dma));
+
+ /* Update the buffer length */
+ dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc2,
+ TX_NORMAL_DESC2_HL_B1L_POS,
+ TX_NORMAL_DESC2_HL_B1L_LEN,
+ desc_data->skb_dma_len);
+
+ /* Set OWN bit */
+ dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc3,
+ TX_NORMAL_DESC3_OWN_POS,
+ TX_NORMAL_DESC3_OWN_LEN, 1);
+
+ /* Mark it as NORMAL descriptor */
+ dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc3,
+ TX_NORMAL_DESC3_CTXT_POS,
+ TX_NORMAL_DESC3_CTXT_LEN, 0);
+
+ /* Enable HW CSUM */
+ if (csum)
+ dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc3,
+ TX_NORMAL_DESC3_CIC_POS,
+ TX_NORMAL_DESC3_CIC_LEN,
+ 0x3);
+ }
+
+ /* Set LAST bit for the last descriptor */
+ dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc3,
+ TX_NORMAL_DESC3_LD_POS,
+ TX_NORMAL_DESC3_LD_LEN, 1);
+
+ /* Set IC bit based on Tx coalescing settings */
+ if (tx_set_ic)
+ dma_desc->desc2 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc2,
+ TX_NORMAL_DESC2_IC_POS,
+ TX_NORMAL_DESC2_IC_LEN, 1);
+
+ /* Save the Tx info to report back during cleanup */
+ desc_data->tx.packets = pkt_info->tx_packets;
+ desc_data->tx.bytes = pkt_info->tx_bytes;
+
+ /* In case the Tx DMA engine is running, make sure everything
+ * is written to the descriptor(s) before setting the OWN bit
+ * for the first descriptor
+ */
+ dma_wmb();
+
+ /* Set OWN bit for the first descriptor */
+ desc_data = XLGMAC_GET_DESC_DATA(ring, start_index);
+ dma_desc = desc_data->dma_desc;
+ dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc3,
+ TX_NORMAL_DESC3_OWN_POS,
+ TX_NORMAL_DESC3_OWN_LEN, 1);
+
+ if (netif_msg_tx_queued(pdata))
+ xlgmac_dump_tx_desc(pdata, ring, start_index,
+ pkt_info->desc_count, 1);
+
+ /* Make sure ownership is written to the descriptor */
+ smp_wmb();
+
+ ring->cur = cur_index + 1;
+ if (!pkt_info->skb->xmit_more ||
+ netif_xmit_stopped(netdev_get_tx_queue(pdata->netdev,
+ channel->queue_index)))
+ xlgmac_tx_start_xmit(channel, ring);
+ else
+ ring->tx.xmit_more = 1;
+
+ XLGMAC_PR("%s: descriptors %u to %u written\n",
+ channel->name, start_index & (ring->dma_desc_count - 1),
+ (ring->cur - 1) & (ring->dma_desc_count - 1));
+}
+
+static void xlgmac_get_rx_tstamp(struct xlgmac_pkt_info *pkt_info,
+ struct xlgmac_dma_desc *dma_desc)
+{
+ u32 tsa, tsd;
+ u64 nsec;
+
+ tsa = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+ RX_CONTEXT_DESC3_TSA_POS,
+ RX_CONTEXT_DESC3_TSA_LEN);
+ tsd = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+ RX_CONTEXT_DESC3_TSD_POS,
+ RX_CONTEXT_DESC3_TSD_LEN);
+ if (tsa && !tsd) {
+ nsec = le32_to_cpu(dma_desc->desc1);
+ nsec <<= 32;
+ nsec |= le32_to_cpu(dma_desc->desc0);
+ if (nsec != 0xffffffffffffffffULL) {
+ pkt_info->rx_tstamp = nsec;
+ pkt_info->attributes = XLGMAC_SET_REG_BITS(
+ pkt_info->attributes,
+ RX_PACKET_ATTRIBUTES_RX_TSTAMP_POS,
+ RX_PACKET_ATTRIBUTES_RX_TSTAMP_LEN,
+ 1);
+ }
+ }
+}
+
+static void xlgmac_tx_desc_reset(struct xlgmac_desc_data *desc_data)
+{
+ struct xlgmac_dma_desc *dma_desc = desc_data->dma_desc;
+
+ /* Reset the Tx descriptor
+ * Set buffer 1 (lo) address to zero
+ * Set buffer 1 (hi) address to zero
+ * Reset all other control bits (IC, TTSE, B2L & B1L)
+ * Reset all other control bits (OWN, CTXT, FD, LD, CPC, CIC, etc)
+ */
+ dma_desc->desc0 = 0;
+ dma_desc->desc1 = 0;
+ dma_desc->desc2 = 0;
+ dma_desc->desc3 = 0;
+
+ /* Make sure ownership is written to the descriptor */
+ dma_wmb();
+}
+
+static void xlgmac_tx_desc_init(struct xlgmac_channel *channel)
+{
+ struct xlgmac_ring *ring = channel->tx_ring;
+ struct xlgmac_desc_data *desc_data;
+ int start_index = ring->cur;
+ int i;
+
+ /* Initialze all descriptors */
+ for (i = 0; i < ring->dma_desc_count; i++) {
+ desc_data = XLGMAC_GET_DESC_DATA(ring, i);
+
+ /* Initialize Tx descriptor */
+ xlgmac_tx_desc_reset(desc_data);
+ }
+
+ /* Update the total number of Tx descriptors */
+ writel(ring->dma_desc_count - 1, XLGMAC_DMA_REG(channel, DMA_CH_TDRLR));
+
+ /* Update the starting address of descriptor ring */
+ desc_data = XLGMAC_GET_DESC_DATA(ring, start_index);
+ writel(upper_32_bits(desc_data->dma_desc_addr),
+ XLGMAC_DMA_REG(channel, DMA_CH_TDLR_HI));
+ writel(lower_32_bits(desc_data->dma_desc_addr),
+ XLGMAC_DMA_REG(channel, DMA_CH_TDLR_LO));
+}
+
+static void xlgmac_rx_desc_reset(struct xlgmac_pdata *pdata,
+ struct xlgmac_desc_data *desc_data,
+ unsigned int index)
+{
+ struct xlgmac_dma_desc *dma_desc = desc_data->dma_desc;
+ unsigned int rx_frames = pdata->rx_frames;
+ unsigned int rx_usecs = pdata->rx_usecs;
+ dma_addr_t hdr_dma, buf_dma;
+ unsigned int inte;
+
+ if (!rx_usecs && !rx_frames) {
+ /* No coalescing, interrupt for every descriptor */
+ inte = 1;
+ } else {
+ /* Set interrupt based on Rx frame coalescing setting */
+ if (rx_frames && !((index + 1) % rx_frames))
+ inte = 1;
+ else
+ inte = 0;
+ }
+
+ /* Reset the Rx descriptor
+ * Set buffer 1 (lo) address to header dma address (lo)
+ * Set buffer 1 (hi) address to header dma address (hi)
+ * Set buffer 2 (lo) address to buffer dma address (lo)
+ * Set buffer 2 (hi) address to buffer dma address (hi) and
+ * set control bits OWN and INTE
+ */
+ hdr_dma = desc_data->rx.hdr.dma_base + desc_data->rx.hdr.dma_off;
+ buf_dma = desc_data->rx.buf.dma_base + desc_data->rx.buf.dma_off;
+ dma_desc->desc0 = cpu_to_le32(lower_32_bits(hdr_dma));
+ dma_desc->desc1 = cpu_to_le32(upper_32_bits(hdr_dma));
+ dma_desc->desc2 = cpu_to_le32(lower_32_bits(buf_dma));
+ dma_desc->desc3 = cpu_to_le32(upper_32_bits(buf_dma));
+
+ dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc3,
+ RX_NORMAL_DESC3_INTE_POS,
+ RX_NORMAL_DESC3_INTE_LEN,
+ inte);
+
+ /* Since the Rx DMA engine is likely running, make sure everything
+ * is written to the descriptor(s) before setting the OWN bit
+ * for the descriptor
+ */
+ dma_wmb();
+
+ dma_desc->desc3 = XLGMAC_SET_REG_BITS_LE(
+ dma_desc->desc3,
+ RX_NORMAL_DESC3_OWN_POS,
+ RX_NORMAL_DESC3_OWN_LEN,
+ 1);
+
+ /* Make sure ownership is written to the descriptor */
+ dma_wmb();
+}
+
+static void xlgmac_rx_desc_init(struct xlgmac_channel *channel)
+{
+ struct xlgmac_pdata *pdata = channel->pdata;
+ struct xlgmac_ring *ring = channel->rx_ring;
+ unsigned int start_index = ring->cur;
+ struct xlgmac_desc_data *desc_data;
+ unsigned int i;
+
+ /* Initialize all descriptors */
+ for (i = 0; i < ring->dma_desc_count; i++) {
+ desc_data = XLGMAC_GET_DESC_DATA(ring, i);
+
+ /* Initialize Rx descriptor */
+ xlgmac_rx_desc_reset(pdata, desc_data, i);
+ }
+
+ /* Update the total number of Rx descriptors */
+ writel(ring->dma_desc_count - 1, XLGMAC_DMA_REG(channel, DMA_CH_RDRLR));
+
+ /* Update the starting address of descriptor ring */
+ desc_data = XLGMAC_GET_DESC_DATA(ring, start_index);
+ writel(upper_32_bits(desc_data->dma_desc_addr),
+ XLGMAC_DMA_REG(channel, DMA_CH_RDLR_HI));
+ writel(lower_32_bits(desc_data->dma_desc_addr),
+ XLGMAC_DMA_REG(channel, DMA_CH_RDLR_LO));
+
+ /* Update the Rx Descriptor Tail Pointer */
+ desc_data = XLGMAC_GET_DESC_DATA(ring, start_index +
+ ring->dma_desc_count - 1);
+ writel(lower_32_bits(desc_data->dma_desc_addr),
+ XLGMAC_DMA_REG(channel, DMA_CH_RDTR_LO));
+}
+
+static int xlgmac_is_context_desc(struct xlgmac_dma_desc *dma_desc)
+{
+ /* Rx and Tx share CTXT bit, so check TDES3.CTXT bit */
+ return XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+ TX_NORMAL_DESC3_CTXT_POS,
+ TX_NORMAL_DESC3_CTXT_LEN);
+}
+
+static int xlgmac_is_last_desc(struct xlgmac_dma_desc *dma_desc)
+{
+ /* Rx and Tx share LD bit, so check TDES3.LD bit */
+ return XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+ TX_NORMAL_DESC3_LD_POS,
+ TX_NORMAL_DESC3_LD_LEN);
+}
+
+static int xlgmac_disable_tx_flow_control(struct xlgmac_pdata *pdata)
+{
+ unsigned int max_q_count, q_count;
+ unsigned int reg, regval;
+ unsigned int i;
+
+ /* Clear MTL flow control */
+ for (i = 0; i < pdata->rx_q_count; i++) {
+ regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+ regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_EHFC_POS,
+ MTL_Q_RQOMR_EHFC_LEN, 0);
+ writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+ }
+
+ /* Clear MAC flow control */
+ max_q_count = XLGMAC_MAX_FLOW_CONTROL_QUEUES;
+ q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count);
+ reg = MAC_Q0TFCR;
+ for (i = 0; i < q_count; i++) {
+ regval = readl(pdata->mac_regs + reg);
+ regval = XLGMAC_SET_REG_BITS(regval,
+ MAC_Q0TFCR_TFE_POS,
+ MAC_Q0TFCR_TFE_LEN,
+ 0);
+ writel(regval, pdata->mac_regs + reg);
+
+ reg += MAC_QTFCR_INC;
+ }
+
+ return 0;
+}
+
+static int xlgmac_enable_tx_flow_control(struct xlgmac_pdata *pdata)
+{
+ unsigned int max_q_count, q_count;
+ unsigned int reg, regval;
+ unsigned int i;
+
+ /* Set MTL flow control */
+ for (i = 0; i < pdata->rx_q_count; i++) {
+ regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+ regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_EHFC_POS,
+ MTL_Q_RQOMR_EHFC_LEN, 1);
+ writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+ }
+
+ /* Set MAC flow control */
+ max_q_count = XLGMAC_MAX_FLOW_CONTROL_QUEUES;
+ q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count);
+ reg = MAC_Q0TFCR;
+ for (i = 0; i < q_count; i++) {
+ regval = readl(pdata->mac_regs + reg);
+
+ /* Enable transmit flow control */
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_Q0TFCR_TFE_POS,
+ MAC_Q0TFCR_TFE_LEN, 1);
+ /* Set pause time */
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_Q0TFCR_PT_POS,
+ MAC_Q0TFCR_PT_LEN, 0xffff);
+
+ writel(regval, pdata->mac_regs + reg);
+
+ reg += MAC_QTFCR_INC;
+ }
+
+ return 0;
+}
+
+static int xlgmac_disable_rx_flow_control(struct xlgmac_pdata *pdata)
+{
+ u32 regval;
+
+ regval = readl(pdata->mac_regs + MAC_RFCR);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_RFCR_RFE_POS,
+ MAC_RFCR_RFE_LEN, 0);
+ writel(regval, pdata->mac_regs + MAC_RFCR);
+
+ return 0;
+}
+
+static int xlgmac_enable_rx_flow_control(struct xlgmac_pdata *pdata)
+{
+ u32 regval;
+
+ regval = readl(pdata->mac_regs + MAC_RFCR);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_RFCR_RFE_POS,
+ MAC_RFCR_RFE_LEN, 1);
+ writel(regval, pdata->mac_regs + MAC_RFCR);
+
+ return 0;
+}
+
+static int xlgmac_config_tx_flow_control(struct xlgmac_pdata *pdata)
+{
+ if (pdata->tx_pause)
+ xlgmac_enable_tx_flow_control(pdata);
+ else
+ xlgmac_disable_tx_flow_control(pdata);
+
+ return 0;
+}
+
+static int xlgmac_config_rx_flow_control(struct xlgmac_pdata *pdata)
+{
+ if (pdata->rx_pause)
+ xlgmac_enable_rx_flow_control(pdata);
+ else
+ xlgmac_disable_rx_flow_control(pdata);
+
+ return 0;
+}
+
+static int xlgmac_config_rx_coalesce(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_channel *channel;
+ unsigned int i;
+ u32 regval;
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ if (!channel->rx_ring)
+ break;
+
+ regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RIWT));
+ regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RIWT_RWT_POS,
+ DMA_CH_RIWT_RWT_LEN,
+ pdata->rx_riwt);
+ writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RIWT));
+ }
+
+ return 0;
+}
+
+static void xlgmac_config_flow_control(struct xlgmac_pdata *pdata)
+{
+ xlgmac_config_tx_flow_control(pdata);
+ xlgmac_config_rx_flow_control(pdata);
+}
+
+static void xlgmac_config_rx_fep_enable(struct xlgmac_pdata *pdata)
+{
+ unsigned int i;
+ u32 regval;
+
+ for (i = 0; i < pdata->rx_q_count; i++) {
+ regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+ regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_FEP_POS,
+ MTL_Q_RQOMR_FEP_LEN, 1);
+ writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+ }
+}
+
+static void xlgmac_config_rx_fup_enable(struct xlgmac_pdata *pdata)
+{
+ unsigned int i;
+ u32 regval;
+
+ for (i = 0; i < pdata->rx_q_count; i++) {
+ regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+ regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_FUP_POS,
+ MTL_Q_RQOMR_FUP_LEN, 1);
+ writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+ }
+}
+
+static int xlgmac_config_tx_coalesce(struct xlgmac_pdata *pdata)
+{
+ return 0;
+}
+
+static void xlgmac_config_rx_buffer_size(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_channel *channel;
+ unsigned int i;
+ u32 regval;
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ if (!channel->rx_ring)
+ break;
+
+ regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+ regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RCR_RBSZ_POS,
+ DMA_CH_RCR_RBSZ_LEN,
+ pdata->rx_buf_size);
+ writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+ }
+}
+
+static void xlgmac_config_tso_mode(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_channel *channel;
+ unsigned int i;
+ u32 regval;
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ if (!channel->tx_ring)
+ break;
+
+ if (pdata->hw_feat.tso) {
+ regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+ regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_TSE_POS,
+ DMA_CH_TCR_TSE_LEN, 1);
+ writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+ }
+ }
+}
+
+static void xlgmac_config_sph_mode(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_channel *channel;
+ unsigned int i;
+ u32 regval;
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ if (!channel->rx_ring)
+ break;
+
+ regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_CR));
+ regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_CR_SPH_POS,
+ DMA_CH_CR_SPH_LEN, 1);
+ writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_CR));
+ }
+
+ regval = readl(pdata->mac_regs + MAC_RCR);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_RCR_HDSMS_POS,
+ MAC_RCR_HDSMS_LEN,
+ XLGMAC_SPH_HDSMS_SIZE);
+ writel(regval, pdata->mac_regs + MAC_RCR);
+}
+
+static unsigned int xlgmac_usec_to_riwt(struct xlgmac_pdata *pdata,
+ unsigned int usec)
+{
+ unsigned long rate;
+ unsigned int ret;
+
+ rate = pdata->sysclk_rate;
+
+ /* Convert the input usec value to the watchdog timer value. Each
+ * watchdog timer value is equivalent to 256 clock cycles.
+ * Calculate the required value as:
+ * ( usec * ( system_clock_mhz / 10^6 ) / 256
+ */
+ ret = (usec * (rate / 1000000)) / 256;
+
+ return ret;
+}
+
+static unsigned int xlgmac_riwt_to_usec(struct xlgmac_pdata *pdata,
+ unsigned int riwt)
+{
+ unsigned long rate;
+ unsigned int ret;
+
+ rate = pdata->sysclk_rate;
+
+ /* Convert the input watchdog timer value to the usec value. Each
+ * watchdog timer value is equivalent to 256 clock cycles.
+ * Calculate the required value as:
+ * ( riwt * 256 ) / ( system_clock_mhz / 10^6 )
+ */
+ ret = (riwt * 256) / (rate / 1000000);
+
+ return ret;
+}
+
+static int xlgmac_config_rx_threshold(struct xlgmac_pdata *pdata,
+ unsigned int val)
+{
+ unsigned int i;
+ u32 regval;
+
+ for (i = 0; i < pdata->rx_q_count; i++) {
+ regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+ regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_RTC_POS,
+ MTL_Q_RQOMR_RTC_LEN, val);
+ writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+ }
+
+ return 0;
+}
+
+static void xlgmac_config_mtl_mode(struct xlgmac_pdata *pdata)
+{
+ unsigned int i;
+ u32 regval;
+
+ /* Set Tx to weighted round robin scheduling algorithm */
+ regval = readl(pdata->mac_regs + MTL_OMR);
+ regval = XLGMAC_SET_REG_BITS(regval, MTL_OMR_ETSALG_POS,
+ MTL_OMR_ETSALG_LEN, MTL_ETSALG_WRR);
+ writel(regval, pdata->mac_regs + MTL_OMR);
+
+ /* Set Tx traffic classes to use WRR algorithm with equal weights */
+ for (i = 0; i < pdata->hw_feat.tc_cnt; i++) {
+ regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_TC_ETSCR));
+ regval = XLGMAC_SET_REG_BITS(regval, MTL_TC_ETSCR_TSA_POS,
+ MTL_TC_ETSCR_TSA_LEN, MTL_TSA_ETS);
+ writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_TC_ETSCR));
+
+ regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_TC_QWR));
+ regval = XLGMAC_SET_REG_BITS(regval, MTL_TC_QWR_QW_POS,
+ MTL_TC_QWR_QW_LEN, 1);
+ writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_TC_QWR));
+ }
+
+ /* Set Rx to strict priority algorithm */
+ regval = readl(pdata->mac_regs + MTL_OMR);
+ regval = XLGMAC_SET_REG_BITS(regval, MTL_OMR_RAA_POS,
+ MTL_OMR_RAA_LEN, MTL_RAA_SP);
+ writel(regval, pdata->mac_regs + MTL_OMR);
+}
+
+static void xlgmac_config_queue_mapping(struct xlgmac_pdata *pdata)
+{
+ unsigned int ppq, ppq_extra, prio, prio_queues;
+ unsigned int qptc, qptc_extra, queue;
+ unsigned int reg, regval;
+ unsigned int mask;
+ unsigned int i, j;
+
+ /* Map the MTL Tx Queues to Traffic Classes
+ * Note: Tx Queues >= Traffic Classes
+ */
+ qptc = pdata->tx_q_count / pdata->hw_feat.tc_cnt;
+ qptc_extra = pdata->tx_q_count % pdata->hw_feat.tc_cnt;
+
+ for (i = 0, queue = 0; i < pdata->hw_feat.tc_cnt; i++) {
+ for (j = 0; j < qptc; j++) {
+ netif_dbg(pdata, drv, pdata->netdev,
+ "TXq%u mapped to TC%u\n", queue, i);
+ regval = readl(XLGMAC_MTL_REG(pdata, queue,
+ MTL_Q_TQOMR));
+ regval = XLGMAC_SET_REG_BITS(regval,
+ MTL_Q_TQOMR_Q2TCMAP_POS,
+ MTL_Q_TQOMR_Q2TCMAP_LEN,
+ i);
+ writel(regval, XLGMAC_MTL_REG(pdata, queue,
+ MTL_Q_TQOMR));
+ queue++;
+ }
+
+ if (i < qptc_extra) {
+ netif_dbg(pdata, drv, pdata->netdev,
+ "TXq%u mapped to TC%u\n", queue, i);
+ regval = readl(XLGMAC_MTL_REG(pdata, queue,
+ MTL_Q_TQOMR));
+ regval = XLGMAC_SET_REG_BITS(regval,
+ MTL_Q_TQOMR_Q2TCMAP_POS,
+ MTL_Q_TQOMR_Q2TCMAP_LEN,
+ i);
+ writel(regval, XLGMAC_MTL_REG(pdata, queue,
+ MTL_Q_TQOMR));
+ queue++;
+ }
+ }
+
+ /* Map the 8 VLAN priority values to available MTL Rx queues */
+ prio_queues = min_t(unsigned int, IEEE_8021QAZ_MAX_TCS,
+ pdata->rx_q_count);
+ ppq = IEEE_8021QAZ_MAX_TCS / prio_queues;
+ ppq_extra = IEEE_8021QAZ_MAX_TCS % prio_queues;
+
+ reg = MAC_RQC2R;
+ regval = 0;
+ for (i = 0, prio = 0; i < prio_queues;) {
+ mask = 0;
+ for (j = 0; j < ppq; j++) {
+ netif_dbg(pdata, drv, pdata->netdev,
+ "PRIO%u mapped to RXq%u\n", prio, i);
+ mask |= (1 << prio);
+ prio++;
+ }
+
+ if (i < ppq_extra) {
+ netif_dbg(pdata, drv, pdata->netdev,
+ "PRIO%u mapped to RXq%u\n", prio, i);
+ mask |= (1 << prio);
+ prio++;
+ }
+
+ regval |= (mask << ((i++ % MAC_RQC2_Q_PER_REG) << 3));
+
+ if ((i % MAC_RQC2_Q_PER_REG) && (i != prio_queues))
+ continue;
+
+ writel(regval, pdata->mac_regs + reg);
+ reg += MAC_RQC2_INC;
+ regval = 0;
+ }
+
+ /* Configure one to one, MTL Rx queue to DMA Rx channel mapping
+ * ie Q0 <--> CH0, Q1 <--> CH1 ... Q11 <--> CH11
+ */
+ reg = MTL_RQDCM0R;
+ regval = readl(pdata->mac_regs + reg);
+ regval |= (MTL_RQDCM0R_Q0MDMACH | MTL_RQDCM0R_Q1MDMACH |
+ MTL_RQDCM0R_Q2MDMACH | MTL_RQDCM0R_Q3MDMACH);
+ writel(regval, pdata->mac_regs + reg);
+
+ reg += MTL_RQDCM_INC;
+ regval = readl(pdata->mac_regs + reg);
+ regval |= (MTL_RQDCM1R_Q4MDMACH | MTL_RQDCM1R_Q5MDMACH |
+ MTL_RQDCM1R_Q6MDMACH | MTL_RQDCM1R_Q7MDMACH);
+ writel(regval, pdata->mac_regs + reg);
+
+ reg += MTL_RQDCM_INC;
+ regval = readl(pdata->mac_regs + reg);
+ regval |= (MTL_RQDCM2R_Q8MDMACH | MTL_RQDCM2R_Q9MDMACH |
+ MTL_RQDCM2R_Q10MDMACH | MTL_RQDCM2R_Q11MDMACH);
+ writel(regval, pdata->mac_regs + reg);
+}
+
+static unsigned int xlgmac_calculate_per_queue_fifo(
+ unsigned int fifo_size,
+ unsigned int queue_count)
+{
+ unsigned int q_fifo_size;
+ unsigned int p_fifo;
+
+ /* Calculate the configured fifo size */
+ q_fifo_size = 1 << (fifo_size + 7);
+
+ /* The configured value may not be the actual amount of fifo RAM */
+ q_fifo_size = min_t(unsigned int, XLGMAC_MAX_FIFO, q_fifo_size);
+
+ q_fifo_size = q_fifo_size / queue_count;
+
+ /* Each increment in the queue fifo size represents 256 bytes of
+ * fifo, with 0 representing 256 bytes. Distribute the fifo equally
+ * between the queues.
+ */
+ p_fifo = q_fifo_size / 256;
+ if (p_fifo)
+ p_fifo--;
+
+ return p_fifo;
+}
+
+static void xlgmac_config_tx_fifo_size(struct xlgmac_pdata *pdata)
+{
+ unsigned int fifo_size;
+ unsigned int i;
+ u32 regval;
+
+ fifo_size = xlgmac_calculate_per_queue_fifo(
+ pdata->hw_feat.tx_fifo_size,
+ pdata->tx_q_count);
+
+ for (i = 0; i < pdata->tx_q_count; i++) {
+ regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+ regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TQS_POS,
+ MTL_Q_TQOMR_TQS_LEN, fifo_size);
+ writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+ }
+
+ netif_info(pdata, drv, pdata->netdev,
+ "%d Tx hardware queues, %d byte fifo per queue\n",
+ pdata->tx_q_count, ((fifo_size + 1) * 256));
+}
+
+static void xlgmac_config_rx_fifo_size(struct xlgmac_pdata *pdata)
+{
+ unsigned int fifo_size;
+ unsigned int i;
+ u32 regval;
+
+ fifo_size = xlgmac_calculate_per_queue_fifo(
+ pdata->hw_feat.rx_fifo_size,
+ pdata->rx_q_count);
+
+ for (i = 0; i < pdata->rx_q_count; i++) {
+ regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+ regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_RQS_POS,
+ MTL_Q_RQOMR_RQS_LEN, fifo_size);
+ writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+ }
+
+ netif_info(pdata, drv, pdata->netdev,
+ "%d Rx hardware queues, %d byte fifo per queue\n",
+ pdata->rx_q_count, ((fifo_size + 1) * 256));
+}
+
+static void xlgmac_config_flow_control_threshold(struct xlgmac_pdata *pdata)
+{
+ unsigned int i;
+ u32 regval;
+
+ for (i = 0; i < pdata->rx_q_count; i++) {
+ regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQFCR));
+ /* Activate flow control when less than 4k left in fifo */
+ regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQFCR_RFA_POS,
+ MTL_Q_RQFCR_RFA_LEN, 2);
+ /* De-activate flow control when more than 6k left in fifo */
+ regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQFCR_RFD_POS,
+ MTL_Q_RQFCR_RFD_LEN, 4);
+ writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQFCR));
+ }
+}
+
+static int xlgmac_config_tx_threshold(struct xlgmac_pdata *pdata,
+ unsigned int val)
+{
+ unsigned int i;
+ u32 regval;
+
+ for (i = 0; i < pdata->tx_q_count; i++) {
+ regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+ regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TTC_POS,
+ MTL_Q_TQOMR_TTC_LEN, val);
+ writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+ }
+
+ return 0;
+}
+
+static int xlgmac_config_rsf_mode(struct xlgmac_pdata *pdata,
+ unsigned int val)
+{
+ unsigned int i;
+ u32 regval;
+
+ for (i = 0; i < pdata->rx_q_count; i++) {
+ regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+ regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_RQOMR_RSF_POS,
+ MTL_Q_RQOMR_RSF_LEN, val);
+ writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_RQOMR));
+ }
+
+ return 0;
+}
+
+static int xlgmac_config_tsf_mode(struct xlgmac_pdata *pdata,
+ unsigned int val)
+{
+ unsigned int i;
+ u32 regval;
+
+ for (i = 0; i < pdata->tx_q_count; i++) {
+ regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+ regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_TSF_POS,
+ MTL_Q_TQOMR_TSF_LEN, val);
+ writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+ }
+
+ return 0;
+}
+
+static int xlgmac_config_osp_mode(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_channel *channel;
+ unsigned int i;
+ u32 regval;
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ if (!channel->tx_ring)
+ break;
+
+ regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+ regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_OSP_POS,
+ DMA_CH_TCR_OSP_LEN,
+ pdata->tx_osp_mode);
+ writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+ }
+
+ return 0;
+}
+
+static int xlgmac_config_pblx8(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_channel *channel;
+ unsigned int i;
+ u32 regval;
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_CR));
+ regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_CR_PBLX8_POS,
+ DMA_CH_CR_PBLX8_LEN,
+ pdata->pblx8);
+ writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_CR));
+ }
+
+ return 0;
+}
+
+static int xlgmac_get_tx_pbl_val(struct xlgmac_pdata *pdata)
+{
+ u32 regval;
+
+ regval = readl(XLGMAC_DMA_REG(pdata->channel_head, DMA_CH_TCR));
+ regval = XLGMAC_GET_REG_BITS(regval, DMA_CH_TCR_PBL_POS,
+ DMA_CH_TCR_PBL_LEN);
+ return regval;
+}
+
+static int xlgmac_config_tx_pbl_val(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_channel *channel;
+ unsigned int i;
+ u32 regval;
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ if (!channel->tx_ring)
+ break;
+
+ regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+ regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_TCR_PBL_POS,
+ DMA_CH_TCR_PBL_LEN,
+ pdata->tx_pbl);
+ writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_TCR));
+ }
+
+ return 0;
+}
+
+static int xlgmac_get_rx_pbl_val(struct xlgmac_pdata *pdata)
+{
+ u32 regval;
+
+ regval = readl(XLGMAC_DMA_REG(pdata->channel_head, DMA_CH_RCR));
+ regval = XLGMAC_GET_REG_BITS(regval, DMA_CH_RCR_PBL_POS,
+ DMA_CH_RCR_PBL_LEN);
+ return regval;
+}
+
+static int xlgmac_config_rx_pbl_val(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_channel *channel;
+ unsigned int i;
+ u32 regval;
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ if (!channel->rx_ring)
+ break;
+
+ regval = readl(XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+ regval = XLGMAC_SET_REG_BITS(regval, DMA_CH_RCR_PBL_POS,
+ DMA_CH_RCR_PBL_LEN,
+ pdata->rx_pbl);
+ writel(regval, XLGMAC_DMA_REG(channel, DMA_CH_RCR));
+ }
+
+ return 0;
+}
+
+static u64 xlgmac_mmc_read(struct xlgmac_pdata *pdata, unsigned int reg_lo)
+{
+ bool read_hi;
+ u64 val;
+
+ switch (reg_lo) {
+ /* These registers are always 64 bit */
+ case MMC_TXOCTETCOUNT_GB_LO:
+ case MMC_TXOCTETCOUNT_G_LO:
+ case MMC_RXOCTETCOUNT_GB_LO:
+ case MMC_RXOCTETCOUNT_G_LO:
+ read_hi = true;
+ break;
+
+ default:
+ read_hi = false;
+ }
+
+ val = (u64)readl(pdata->mac_regs + reg_lo);
+
+ if (read_hi)
+ val |= ((u64)readl(pdata->mac_regs + reg_lo + 4) << 32);
+
+ return val;
+}
+
+static void xlgmac_tx_mmc_int(struct xlgmac_pdata *pdata)
+{
+ unsigned int mmc_isr = readl(pdata->mac_regs + MMC_TISR);
+ struct xlgmac_stats *stats = &pdata->stats;
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_TISR_TXOCTETCOUNT_GB_POS,
+ MMC_TISR_TXOCTETCOUNT_GB_LEN))
+ stats->txoctetcount_gb +=
+ xlgmac_mmc_read(pdata, MMC_TXOCTETCOUNT_GB_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_TISR_TXFRAMECOUNT_GB_POS,
+ MMC_TISR_TXFRAMECOUNT_GB_LEN))
+ stats->txframecount_gb +=
+ xlgmac_mmc_read(pdata, MMC_TXFRAMECOUNT_GB_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_TISR_TXBROADCASTFRAMES_G_POS,
+ MMC_TISR_TXBROADCASTFRAMES_G_LEN))
+ stats->txbroadcastframes_g +=
+ xlgmac_mmc_read(pdata, MMC_TXBROADCASTFRAMES_G_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_TISR_TXMULTICASTFRAMES_G_POS,
+ MMC_TISR_TXMULTICASTFRAMES_G_LEN))
+ stats->txmulticastframes_g +=
+ xlgmac_mmc_read(pdata, MMC_TXMULTICASTFRAMES_G_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_TISR_TX64OCTETS_GB_POS,
+ MMC_TISR_TX64OCTETS_GB_LEN))
+ stats->tx64octets_gb +=
+ xlgmac_mmc_read(pdata, MMC_TX64OCTETS_GB_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_TISR_TX65TO127OCTETS_GB_POS,
+ MMC_TISR_TX65TO127OCTETS_GB_LEN))
+ stats->tx65to127octets_gb +=
+ xlgmac_mmc_read(pdata, MMC_TX65TO127OCTETS_GB_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_TISR_TX128TO255OCTETS_GB_POS,
+ MMC_TISR_TX128TO255OCTETS_GB_LEN))
+ stats->tx128to255octets_gb +=
+ xlgmac_mmc_read(pdata, MMC_TX128TO255OCTETS_GB_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_TISR_TX256TO511OCTETS_GB_POS,
+ MMC_TISR_TX256TO511OCTETS_GB_LEN))
+ stats->tx256to511octets_gb +=
+ xlgmac_mmc_read(pdata, MMC_TX256TO511OCTETS_GB_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_TISR_TX512TO1023OCTETS_GB_POS,
+ MMC_TISR_TX512TO1023OCTETS_GB_LEN))
+ stats->tx512to1023octets_gb +=
+ xlgmac_mmc_read(pdata, MMC_TX512TO1023OCTETS_GB_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_TISR_TX1024TOMAXOCTETS_GB_POS,
+ MMC_TISR_TX1024TOMAXOCTETS_GB_LEN))
+ stats->tx1024tomaxoctets_gb +=
+ xlgmac_mmc_read(pdata, MMC_TX1024TOMAXOCTETS_GB_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_TISR_TXUNICASTFRAMES_GB_POS,
+ MMC_TISR_TXUNICASTFRAMES_GB_LEN))
+ stats->txunicastframes_gb +=
+ xlgmac_mmc_read(pdata, MMC_TXUNICASTFRAMES_GB_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_TISR_TXMULTICASTFRAMES_GB_POS,
+ MMC_TISR_TXMULTICASTFRAMES_GB_LEN))
+ stats->txmulticastframes_gb +=
+ xlgmac_mmc_read(pdata, MMC_TXMULTICASTFRAMES_GB_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_TISR_TXBROADCASTFRAMES_GB_POS,
+ MMC_TISR_TXBROADCASTFRAMES_GB_LEN))
+ stats->txbroadcastframes_g +=
+ xlgmac_mmc_read(pdata, MMC_TXBROADCASTFRAMES_GB_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_TISR_TXUNDERFLOWERROR_POS,
+ MMC_TISR_TXUNDERFLOWERROR_LEN))
+ stats->txunderflowerror +=
+ xlgmac_mmc_read(pdata, MMC_TXUNDERFLOWERROR_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_TISR_TXOCTETCOUNT_G_POS,
+ MMC_TISR_TXOCTETCOUNT_G_LEN))
+ stats->txoctetcount_g +=
+ xlgmac_mmc_read(pdata, MMC_TXOCTETCOUNT_G_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_TISR_TXFRAMECOUNT_G_POS,
+ MMC_TISR_TXFRAMECOUNT_G_LEN))
+ stats->txframecount_g +=
+ xlgmac_mmc_read(pdata, MMC_TXFRAMECOUNT_G_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_TISR_TXPAUSEFRAMES_POS,
+ MMC_TISR_TXPAUSEFRAMES_LEN))
+ stats->txpauseframes +=
+ xlgmac_mmc_read(pdata, MMC_TXPAUSEFRAMES_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_TISR_TXVLANFRAMES_G_POS,
+ MMC_TISR_TXVLANFRAMES_G_LEN))
+ stats->txvlanframes_g +=
+ xlgmac_mmc_read(pdata, MMC_TXVLANFRAMES_G_LO);
+}
+
+static void xlgmac_rx_mmc_int(struct xlgmac_pdata *pdata)
+{
+ unsigned int mmc_isr = readl(pdata->mac_regs + MMC_RISR);
+ struct xlgmac_stats *stats = &pdata->stats;
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RXFRAMECOUNT_GB_POS,
+ MMC_RISR_RXFRAMECOUNT_GB_LEN))
+ stats->rxframecount_gb +=
+ xlgmac_mmc_read(pdata, MMC_RXFRAMECOUNT_GB_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RXOCTETCOUNT_GB_POS,
+ MMC_RISR_RXOCTETCOUNT_GB_LEN))
+ stats->rxoctetcount_gb +=
+ xlgmac_mmc_read(pdata, MMC_RXOCTETCOUNT_GB_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RXOCTETCOUNT_G_POS,
+ MMC_RISR_RXOCTETCOUNT_G_LEN))
+ stats->rxoctetcount_g +=
+ xlgmac_mmc_read(pdata, MMC_RXOCTETCOUNT_G_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RXBROADCASTFRAMES_G_POS,
+ MMC_RISR_RXBROADCASTFRAMES_G_LEN))
+ stats->rxbroadcastframes_g +=
+ xlgmac_mmc_read(pdata, MMC_RXBROADCASTFRAMES_G_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RXMULTICASTFRAMES_G_POS,
+ MMC_RISR_RXMULTICASTFRAMES_G_LEN))
+ stats->rxmulticastframes_g +=
+ xlgmac_mmc_read(pdata, MMC_RXMULTICASTFRAMES_G_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RXCRCERROR_POS,
+ MMC_RISR_RXCRCERROR_LEN))
+ stats->rxcrcerror +=
+ xlgmac_mmc_read(pdata, MMC_RXCRCERROR_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RXRUNTERROR_POS,
+ MMC_RISR_RXRUNTERROR_LEN))
+ stats->rxrunterror +=
+ xlgmac_mmc_read(pdata, MMC_RXRUNTERROR);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RXJABBERERROR_POS,
+ MMC_RISR_RXJABBERERROR_LEN))
+ stats->rxjabbererror +=
+ xlgmac_mmc_read(pdata, MMC_RXJABBERERROR);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RXUNDERSIZE_G_POS,
+ MMC_RISR_RXUNDERSIZE_G_LEN))
+ stats->rxundersize_g +=
+ xlgmac_mmc_read(pdata, MMC_RXUNDERSIZE_G);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RXOVERSIZE_G_POS,
+ MMC_RISR_RXOVERSIZE_G_LEN))
+ stats->rxoversize_g +=
+ xlgmac_mmc_read(pdata, MMC_RXOVERSIZE_G);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RX64OCTETS_GB_POS,
+ MMC_RISR_RX64OCTETS_GB_LEN))
+ stats->rx64octets_gb +=
+ xlgmac_mmc_read(pdata, MMC_RX64OCTETS_GB_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RX65TO127OCTETS_GB_POS,
+ MMC_RISR_RX65TO127OCTETS_GB_LEN))
+ stats->rx65to127octets_gb +=
+ xlgmac_mmc_read(pdata, MMC_RX65TO127OCTETS_GB_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RX128TO255OCTETS_GB_POS,
+ MMC_RISR_RX128TO255OCTETS_GB_LEN))
+ stats->rx128to255octets_gb +=
+ xlgmac_mmc_read(pdata, MMC_RX128TO255OCTETS_GB_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RX256TO511OCTETS_GB_POS,
+ MMC_RISR_RX256TO511OCTETS_GB_LEN))
+ stats->rx256to511octets_gb +=
+ xlgmac_mmc_read(pdata, MMC_RX256TO511OCTETS_GB_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RX512TO1023OCTETS_GB_POS,
+ MMC_RISR_RX512TO1023OCTETS_GB_LEN))
+ stats->rx512to1023octets_gb +=
+ xlgmac_mmc_read(pdata, MMC_RX512TO1023OCTETS_GB_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RX1024TOMAXOCTETS_GB_POS,
+ MMC_RISR_RX1024TOMAXOCTETS_GB_LEN))
+ stats->rx1024tomaxoctets_gb +=
+ xlgmac_mmc_read(pdata, MMC_RX1024TOMAXOCTETS_GB_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RXUNICASTFRAMES_G_POS,
+ MMC_RISR_RXUNICASTFRAMES_G_LEN))
+ stats->rxunicastframes_g +=
+ xlgmac_mmc_read(pdata, MMC_RXUNICASTFRAMES_G_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RXLENGTHERROR_POS,
+ MMC_RISR_RXLENGTHERROR_LEN))
+ stats->rxlengtherror +=
+ xlgmac_mmc_read(pdata, MMC_RXLENGTHERROR_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RXOUTOFRANGETYPE_POS,
+ MMC_RISR_RXOUTOFRANGETYPE_LEN))
+ stats->rxoutofrangetype +=
+ xlgmac_mmc_read(pdata, MMC_RXOUTOFRANGETYPE_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RXPAUSEFRAMES_POS,
+ MMC_RISR_RXPAUSEFRAMES_LEN))
+ stats->rxpauseframes +=
+ xlgmac_mmc_read(pdata, MMC_RXPAUSEFRAMES_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RXFIFOOVERFLOW_POS,
+ MMC_RISR_RXFIFOOVERFLOW_LEN))
+ stats->rxfifooverflow +=
+ xlgmac_mmc_read(pdata, MMC_RXFIFOOVERFLOW_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RXVLANFRAMES_GB_POS,
+ MMC_RISR_RXVLANFRAMES_GB_LEN))
+ stats->rxvlanframes_gb +=
+ xlgmac_mmc_read(pdata, MMC_RXVLANFRAMES_GB_LO);
+
+ if (XLGMAC_GET_REG_BITS(mmc_isr,
+ MMC_RISR_RXWATCHDOGERROR_POS,
+ MMC_RISR_RXWATCHDOGERROR_LEN))
+ stats->rxwatchdogerror +=
+ xlgmac_mmc_read(pdata, MMC_RXWATCHDOGERROR);
+}
+
+static void xlgmac_read_mmc_stats(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_stats *stats = &pdata->stats;
+ u32 regval;
+
+ /* Freeze counters */
+ regval = readl(pdata->mac_regs + MMC_CR);
+ regval = XLGMAC_SET_REG_BITS(regval, MMC_CR_MCF_POS,
+ MMC_CR_MCF_LEN, 1);
+ writel(regval, pdata->mac_regs + MMC_CR);
+
+ stats->txoctetcount_gb +=
+ xlgmac_mmc_read(pdata, MMC_TXOCTETCOUNT_GB_LO);
+
+ stats->txframecount_gb +=
+ xlgmac_mmc_read(pdata, MMC_TXFRAMECOUNT_GB_LO);
+
+ stats->txbroadcastframes_g +=
+ xlgmac_mmc_read(pdata, MMC_TXBROADCASTFRAMES_G_LO);
+
+ stats->txmulticastframes_g +=
+ xlgmac_mmc_read(pdata, MMC_TXMULTICASTFRAMES_G_LO);
+
+ stats->tx64octets_gb +=
+ xlgmac_mmc_read(pdata, MMC_TX64OCTETS_GB_LO);
+
+ stats->tx65to127octets_gb +=
+ xlgmac_mmc_read(pdata, MMC_TX65TO127OCTETS_GB_LO);
+
+ stats->tx128to255octets_gb +=
+ xlgmac_mmc_read(pdata, MMC_TX128TO255OCTETS_GB_LO);
+
+ stats->tx256to511octets_gb +=
+ xlgmac_mmc_read(pdata, MMC_TX256TO511OCTETS_GB_LO);
+
+ stats->tx512to1023octets_gb +=
+ xlgmac_mmc_read(pdata, MMC_TX512TO1023OCTETS_GB_LO);
+
+ stats->tx1024tomaxoctets_gb +=
+ xlgmac_mmc_read(pdata, MMC_TX1024TOMAXOCTETS_GB_LO);
+
+ stats->txunicastframes_gb +=
+ xlgmac_mmc_read(pdata, MMC_TXUNICASTFRAMES_GB_LO);
+
+ stats->txmulticastframes_gb +=
+ xlgmac_mmc_read(pdata, MMC_TXMULTICASTFRAMES_GB_LO);
+
+ stats->txbroadcastframes_g +=
+ xlgmac_mmc_read(pdata, MMC_TXBROADCASTFRAMES_GB_LO);
+
+ stats->txunderflowerror +=
+ xlgmac_mmc_read(pdata, MMC_TXUNDERFLOWERROR_LO);
+
+ stats->txoctetcount_g +=
+ xlgmac_mmc_read(pdata, MMC_TXOCTETCOUNT_G_LO);
+
+ stats->txframecount_g +=
+ xlgmac_mmc_read(pdata, MMC_TXFRAMECOUNT_G_LO);
+
+ stats->txpauseframes +=
+ xlgmac_mmc_read(pdata, MMC_TXPAUSEFRAMES_LO);
+
+ stats->txvlanframes_g +=
+ xlgmac_mmc_read(pdata, MMC_TXVLANFRAMES_G_LO);
+
+ stats->rxframecount_gb +=
+ xlgmac_mmc_read(pdata, MMC_RXFRAMECOUNT_GB_LO);
+
+ stats->rxoctetcount_gb +=
+ xlgmac_mmc_read(pdata, MMC_RXOCTETCOUNT_GB_LO);
+
+ stats->rxoctetcount_g +=
+ xlgmac_mmc_read(pdata, MMC_RXOCTETCOUNT_G_LO);
+
+ stats->rxbroadcastframes_g +=
+ xlgmac_mmc_read(pdata, MMC_RXBROADCASTFRAMES_G_LO);
+
+ stats->rxmulticastframes_g +=
+ xlgmac_mmc_read(pdata, MMC_RXMULTICASTFRAMES_G_LO);
+
+ stats->rxcrcerror +=
+ xlgmac_mmc_read(pdata, MMC_RXCRCERROR_LO);
+
+ stats->rxrunterror +=
+ xlgmac_mmc_read(pdata, MMC_RXRUNTERROR);
+
+ stats->rxjabbererror +=
+ xlgmac_mmc_read(pdata, MMC_RXJABBERERROR);
+
+ stats->rxundersize_g +=
+ xlgmac_mmc_read(pdata, MMC_RXUNDERSIZE_G);
+
+ stats->rxoversize_g +=
+ xlgmac_mmc_read(pdata, MMC_RXOVERSIZE_G);
+
+ stats->rx64octets_gb +=
+ xlgmac_mmc_read(pdata, MMC_RX64OCTETS_GB_LO);
+
+ stats->rx65to127octets_gb +=
+ xlgmac_mmc_read(pdata, MMC_RX65TO127OCTETS_GB_LO);
+
+ stats->rx128to255octets_gb +=
+ xlgmac_mmc_read(pdata, MMC_RX128TO255OCTETS_GB_LO);
+
+ stats->rx256to511octets_gb +=
+ xlgmac_mmc_read(pdata, MMC_RX256TO511OCTETS_GB_LO);
+
+ stats->rx512to1023octets_gb +=
+ xlgmac_mmc_read(pdata, MMC_RX512TO1023OCTETS_GB_LO);
+
+ stats->rx1024tomaxoctets_gb +=
+ xlgmac_mmc_read(pdata, MMC_RX1024TOMAXOCTETS_GB_LO);
+
+ stats->rxunicastframes_g +=
+ xlgmac_mmc_read(pdata, MMC_RXUNICASTFRAMES_G_LO);
+
+ stats->rxlengtherror +=
+ xlgmac_mmc_read(pdata, MMC_RXLENGTHERROR_LO);
+
+ stats->rxoutofrangetype +=
+ xlgmac_mmc_read(pdata, MMC_RXOUTOFRANGETYPE_LO);
+
+ stats->rxpauseframes +=
+ xlgmac_mmc_read(pdata, MMC_RXPAUSEFRAMES_LO);
+
+ stats->rxfifooverflow +=
+ xlgmac_mmc_read(pdata, MMC_RXFIFOOVERFLOW_LO);
+
+ stats->rxvlanframes_gb +=
+ xlgmac_mmc_read(pdata, MMC_RXVLANFRAMES_GB_LO);
+
+ stats->rxwatchdogerror +=
+ xlgmac_mmc_read(pdata, MMC_RXWATCHDOGERROR);
+
+ /* Un-freeze counters */
+ regval = readl(pdata->mac_regs + MMC_CR);
+ regval = XLGMAC_SET_REG_BITS(regval, MMC_CR_MCF_POS,
+ MMC_CR_MCF_LEN, 0);
+ writel(regval, pdata->mac_regs + MMC_CR);
+}
+
+static void xlgmac_config_mmc(struct xlgmac_pdata *pdata)
+{
+ u32 regval;
+
+ regval = readl(pdata->mac_regs + MMC_CR);
+ /* Set counters to reset on read */
+ regval = XLGMAC_SET_REG_BITS(regval, MMC_CR_ROR_POS,
+ MMC_CR_ROR_LEN, 1);
+ /* Reset the counters */
+ regval = XLGMAC_SET_REG_BITS(regval, MMC_CR_CR_POS,
+ MMC_CR_CR_LEN, 1);
+ writel(regval, pdata->mac_regs + MMC_CR);
+}
+
+static int xlgmac_write_rss_reg(struct xlgmac_pdata *pdata, unsigned int type,
+ unsigned int index, unsigned int val)
+{
+ unsigned int wait;
+ int ret = 0;
+ u32 regval;
+
+ mutex_lock(&pdata->rss_mutex);
+
+ regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_RSSAR),
+ MAC_RSSAR_OB_POS, MAC_RSSAR_OB_LEN);
+ if (regval) {
+ ret = -EBUSY;
+ goto unlock;
+ }
+
+ writel(val, pdata->mac_regs + MAC_RSSDR);
+
+ regval = readl(pdata->mac_regs + MAC_RSSAR);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSAR_RSSIA_POS,
+ MAC_RSSAR_RSSIA_LEN, index);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSAR_ADDRT_POS,
+ MAC_RSSAR_ADDRT_LEN, type);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSAR_CT_POS,
+ MAC_RSSAR_CT_LEN, 0);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSAR_OB_POS,
+ MAC_RSSAR_OB_LEN, 1);
+ writel(regval, pdata->mac_regs + MAC_RSSAR);
+
+ wait = 1000;
+ while (wait--) {
+ regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_RSSAR),
+ MAC_RSSAR_OB_POS,
+ MAC_RSSAR_OB_LEN);
+ if (!regval)
+ goto unlock;
+
+ usleep_range(1000, 1500);
+ }
+
+ ret = -EBUSY;
+
+unlock:
+ mutex_unlock(&pdata->rss_mutex);
+
+ return ret;
+}
+
+static int xlgmac_write_rss_hash_key(struct xlgmac_pdata *pdata)
+{
+ unsigned int key_regs = sizeof(pdata->rss_key) / sizeof(u32);
+ unsigned int *key = (unsigned int *)&pdata->rss_key;
+ int ret;
+
+ while (key_regs--) {
+ ret = xlgmac_write_rss_reg(pdata, XLGMAC_RSS_HASH_KEY_TYPE,
+ key_regs, *key++);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int xlgmac_write_rss_lookup_table(struct xlgmac_pdata *pdata)
+{
+ unsigned int i;
+ int ret;
+
+ for (i = 0; i < ARRAY_SIZE(pdata->rss_table); i++) {
+ ret = xlgmac_write_rss_reg(pdata,
+ XLGMAC_RSS_LOOKUP_TABLE_TYPE, i,
+ pdata->rss_table[i]);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int xlgmac_set_rss_hash_key(struct xlgmac_pdata *pdata, const u8 *key)
+{
+ memcpy(pdata->rss_key, key, sizeof(pdata->rss_key));
+
+ return xlgmac_write_rss_hash_key(pdata);
+}
+
+static int xlgmac_set_rss_lookup_table(struct xlgmac_pdata *pdata,
+ const u32 *table)
+{
+ unsigned int i;
+ u32 tval;
+
+ for (i = 0; i < ARRAY_SIZE(pdata->rss_table); i++) {
+ tval = table[i];
+ pdata->rss_table[i] = XLGMAC_SET_REG_BITS(
+ pdata->rss_table[i],
+ MAC_RSSDR_DMCH_POS,
+ MAC_RSSDR_DMCH_LEN,
+ tval);
+ }
+
+ return xlgmac_write_rss_lookup_table(pdata);
+}
+
+static int xlgmac_enable_rss(struct xlgmac_pdata *pdata)
+{
+ u32 regval;
+ int ret;
+
+ if (!pdata->hw_feat.rss)
+ return -EOPNOTSUPP;
+
+ /* Program the hash key */
+ ret = xlgmac_write_rss_hash_key(pdata);
+ if (ret)
+ return ret;
+
+ /* Program the lookup table */
+ ret = xlgmac_write_rss_lookup_table(pdata);
+ if (ret)
+ return ret;
+
+ /* Set the RSS options */
+ writel(pdata->rss_options, pdata->mac_regs + MAC_RSSCR);
+
+ /* Enable RSS */
+ regval = readl(pdata->mac_regs + MAC_RSSCR);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSCR_RSSE_POS,
+ MAC_RSSCR_RSSE_LEN, 1);
+ writel(regval, pdata->mac_regs + MAC_RSSCR);
+
+ return 0;
+}
+
+static int xlgmac_disable_rss(struct xlgmac_pdata *pdata)
+{
+ u32 regval;
+
+ if (!pdata->hw_feat.rss)
+ return -EOPNOTSUPP;
+
+ regval = readl(pdata->mac_regs + MAC_RSSCR);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_RSSCR_RSSE_POS,
+ MAC_RSSCR_RSSE_LEN, 0);
+ writel(regval, pdata->mac_regs + MAC_RSSCR);
+
+ return 0;
+}
+
+static void xlgmac_config_rss(struct xlgmac_pdata *pdata)
+{
+ int ret;
+
+ if (!pdata->hw_feat.rss)
+ return;
+
+ if (pdata->netdev->features & NETIF_F_RXHASH)
+ ret = xlgmac_enable_rss(pdata);
+ else
+ ret = xlgmac_disable_rss(pdata);
+
+ if (ret)
+ netdev_err(pdata->netdev,
+ "error configuring RSS, RSS disabled\n");
+}
+
+static void xlgmac_enable_dma_interrupts(struct xlgmac_pdata *pdata)
+{
+ unsigned int dma_ch_isr, dma_ch_ier;
+ struct xlgmac_channel *channel;
+ unsigned int i;
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ /* Clear all the interrupts which are set */
+ dma_ch_isr = readl(XLGMAC_DMA_REG(channel, DMA_CH_SR));
+ writel(dma_ch_isr, XLGMAC_DMA_REG(channel, DMA_CH_SR));
+
+ /* Clear all interrupt enable bits */
+ dma_ch_ier = 0;
+
+ /* Enable following interrupts
+ * NIE - Normal Interrupt Summary Enable
+ * AIE - Abnormal Interrupt Summary Enable
+ * FBEE - Fatal Bus Error Enable
+ */
+ dma_ch_ier = XLGMAC_SET_REG_BITS(dma_ch_ier,
+ DMA_CH_IER_NIE_POS,
+ DMA_CH_IER_NIE_LEN, 1);
+ dma_ch_ier = XLGMAC_SET_REG_BITS(dma_ch_ier,
+ DMA_CH_IER_AIE_POS,
+ DMA_CH_IER_AIE_LEN, 1);
+ dma_ch_ier = XLGMAC_SET_REG_BITS(dma_ch_ier,
+ DMA_CH_IER_FBEE_POS,
+ DMA_CH_IER_FBEE_LEN, 1);
+
+ if (channel->tx_ring) {
+ /* Enable the following Tx interrupts
+ * TIE - Transmit Interrupt Enable (unless using
+ * per channel interrupts)
+ */
+ if (!pdata->per_channel_irq)
+ dma_ch_ier = XLGMAC_SET_REG_BITS(
+ dma_ch_ier,
+ DMA_CH_IER_TIE_POS,
+ DMA_CH_IER_TIE_LEN,
+ 1);
+ }
+ if (channel->rx_ring) {
+ /* Enable following Rx interrupts
+ * RBUE - Receive Buffer Unavailable Enable
+ * RIE - Receive Interrupt Enable (unless using
+ * per channel interrupts)
+ */
+ dma_ch_ier = XLGMAC_SET_REG_BITS(
+ dma_ch_ier,
+ DMA_CH_IER_RBUE_POS,
+ DMA_CH_IER_RBUE_LEN,
+ 1);
+ if (!pdata->per_channel_irq)
+ dma_ch_ier = XLGMAC_SET_REG_BITS(
+ dma_ch_ier,
+ DMA_CH_IER_RIE_POS,
+ DMA_CH_IER_RIE_LEN,
+ 1);
+ }
+
+ writel(dma_ch_isr, XLGMAC_DMA_REG(channel, DMA_CH_IER));
+ }
+}
+
+static void xlgmac_enable_mtl_interrupts(struct xlgmac_pdata *pdata)
+{
+ unsigned int q_count, i;
+ unsigned int mtl_q_isr;
+
+ q_count = max(pdata->hw_feat.tx_q_cnt, pdata->hw_feat.rx_q_cnt);
+ for (i = 0; i < q_count; i++) {
+ /* Clear all the interrupts which are set */
+ mtl_q_isr = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_ISR));
+ writel(mtl_q_isr, XLGMAC_MTL_REG(pdata, i, MTL_Q_ISR));
+
+ /* No MTL interrupts to be enabled */
+ writel(0, XLGMAC_MTL_REG(pdata, i, MTL_Q_IER));
+ }
+}
+
+static void xlgmac_enable_mac_interrupts(struct xlgmac_pdata *pdata)
+{
+ unsigned int mac_ier = 0;
+ u32 regval;
+
+ /* Enable Timestamp interrupt */
+ mac_ier = XLGMAC_SET_REG_BITS(mac_ier, MAC_IER_TSIE_POS,
+ MAC_IER_TSIE_LEN, 1);
+
+ writel(mac_ier, pdata->mac_regs + MAC_IER);
+
+ /* Enable all counter interrupts */
+ regval = readl(pdata->mac_regs + MMC_RIER);
+ regval = XLGMAC_SET_REG_BITS(regval, MMC_RIER_ALL_INTERRUPTS_POS,
+ MMC_RIER_ALL_INTERRUPTS_LEN, 0xffffffff);
+ writel(regval, pdata->mac_regs + MMC_RIER);
+ regval = readl(pdata->mac_regs + MMC_TIER);
+ regval = XLGMAC_SET_REG_BITS(regval, MMC_TIER_ALL_INTERRUPTS_POS,
+ MMC_TIER_ALL_INTERRUPTS_LEN, 0xffffffff);
+ writel(regval, pdata->mac_regs + MMC_TIER);
+}
+
+static int xlgmac_set_xlgmii_25000_speed(struct xlgmac_pdata *pdata)
+{
+ u32 regval;
+
+ regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_TCR),
+ MAC_TCR_SS_POS, MAC_TCR_SS_LEN);
+ if (regval == 0x1)
+ return 0;
+
+ regval = readl(pdata->mac_regs + MAC_TCR);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_SS_POS,
+ MAC_TCR_SS_LEN, 0x1);
+ writel(regval, pdata->mac_regs + MAC_TCR);
+
+ return 0;
+}
+
+static int xlgmac_set_xlgmii_40000_speed(struct xlgmac_pdata *pdata)
+{
+ u32 regval;
+
+ regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_TCR),
+ MAC_TCR_SS_POS, MAC_TCR_SS_LEN);
+ if (regval == 0)
+ return 0;
+
+ regval = readl(pdata->mac_regs + MAC_TCR);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_SS_POS,
+ MAC_TCR_SS_LEN, 0);
+ writel(regval, pdata->mac_regs + MAC_TCR);
+
+ return 0;
+}
+
+static int xlgmac_set_xlgmii_50000_speed(struct xlgmac_pdata *pdata)
+{
+ u32 regval;
+
+ regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_TCR),
+ MAC_TCR_SS_POS, MAC_TCR_SS_LEN);
+ if (regval == 0x2)
+ return 0;
+
+ regval = readl(pdata->mac_regs + MAC_TCR);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_SS_POS,
+ MAC_TCR_SS_LEN, 0x2);
+ writel(regval, pdata->mac_regs + MAC_TCR);
+
+ return 0;
+}
+
+static int xlgmac_set_xlgmii_100000_speed(struct xlgmac_pdata *pdata)
+{
+ u32 regval;
+
+ regval = XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + MAC_TCR),
+ MAC_TCR_SS_POS, MAC_TCR_SS_LEN);
+ if (regval == 0x3)
+ return 0;
+
+ regval = readl(pdata->mac_regs + MAC_TCR);
+ regval = XLGMAC_SET_REG_BITS(regval, MAC_TCR_SS_POS,
+ MAC_TCR_SS_LEN, 0x3);
+ writel(regval, pdata->mac_regs + MAC_TCR);
+
+ return 0;
+}
+
+static void xlgmac_config_mac_speed(struct xlgmac_pdata *pdata)
+{
+ switch (pdata->phy_speed) {
+ case SPEED_100000:
+ xlgmac_set_xlgmii_100000_speed(pdata);
+ break;
+
+ case SPEED_50000:
+ xlgmac_set_xlgmii_50000_speed(pdata);
+ break;
+
+ case SPEED_40000:
+ xlgmac_set_xlgmii_40000_speed(pdata);
+ break;
+
+ case SPEED_25000:
+ xlgmac_set_xlgmii_25000_speed(pdata);
+ break;
+ }
+}
+
+static int xlgmac_dev_read(struct xlgmac_channel *channel)
+{
+ struct xlgmac_pdata *pdata = channel->pdata;
+ struct xlgmac_ring *ring = channel->rx_ring;
+ struct net_device *netdev = pdata->netdev;
+ struct xlgmac_desc_data *desc_data;
+ struct xlgmac_dma_desc *dma_desc;
+ struct xlgmac_pkt_info *pkt_info;
+ unsigned int err, etlt, l34t;
+
+ desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur);
+ dma_desc = desc_data->dma_desc;
+ pkt_info = &ring->pkt_info;
+
+ /* Check for data availability */
+ if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+ RX_NORMAL_DESC3_OWN_POS,
+ RX_NORMAL_DESC3_OWN_LEN))
+ return 1;
+
+ /* Make sure descriptor fields are read after reading the OWN bit */
+ dma_rmb();
+
+ if (netif_msg_rx_status(pdata))
+ xlgmac_dump_rx_desc(pdata, ring, ring->cur);
+
+ if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+ RX_NORMAL_DESC3_CTXT_POS,
+ RX_NORMAL_DESC3_CTXT_LEN)) {
+ /* Timestamp Context Descriptor */
+ xlgmac_get_rx_tstamp(pkt_info, dma_desc);
+
+ pkt_info->attributes = XLGMAC_SET_REG_BITS(
+ pkt_info->attributes,
+ RX_PACKET_ATTRIBUTES_CONTEXT_POS,
+ RX_PACKET_ATTRIBUTES_CONTEXT_LEN,
+ 1);
+ pkt_info->attributes = XLGMAC_SET_REG_BITS(
+ pkt_info->attributes,
+ RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_POS,
+ RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_LEN,
+ 0);
+ return 0;
+ }
+
+ /* Normal Descriptor, be sure Context Descriptor bit is off */
+ pkt_info->attributes = XLGMAC_SET_REG_BITS(
+ pkt_info->attributes,
+ RX_PACKET_ATTRIBUTES_CONTEXT_POS,
+ RX_PACKET_ATTRIBUTES_CONTEXT_LEN,
+ 0);
+
+ /* Indicate if a Context Descriptor is next */
+ if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+ RX_NORMAL_DESC3_CDA_POS,
+ RX_NORMAL_DESC3_CDA_LEN))
+ pkt_info->attributes = XLGMAC_SET_REG_BITS(
+ pkt_info->attributes,
+ RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_POS,
+ RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_LEN,
+ 1);
+
+ /* Get the header length */
+ if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+ RX_NORMAL_DESC3_FD_POS,
+ RX_NORMAL_DESC3_FD_LEN)) {
+ desc_data->rx.hdr_len = XLGMAC_GET_REG_BITS_LE(dma_desc->desc2,
+ RX_NORMAL_DESC2_HL_POS,
+ RX_NORMAL_DESC2_HL_LEN);
+ if (desc_data->rx.hdr_len)
+ pdata->stats.rx_split_header_packets++;
+ }
+
+ /* Get the RSS hash */
+ if (XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+ RX_NORMAL_DESC3_RSV_POS,
+ RX_NORMAL_DESC3_RSV_LEN)) {
+ pkt_info->attributes = XLGMAC_SET_REG_BITS(
+ pkt_info->attributes,
+ RX_PACKET_ATTRIBUTES_RSS_HASH_POS,
+ RX_PACKET_ATTRIBUTES_RSS_HASH_LEN,
+ 1);
+
+ pkt_info->rss_hash = le32_to_cpu(dma_desc->desc1);
+
+ l34t = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+ RX_NORMAL_DESC3_L34T_POS,
+ RX_NORMAL_DESC3_L34T_LEN);
+ switch (l34t) {
+ case RX_DESC3_L34T_IPV4_TCP:
+ case RX_DESC3_L34T_IPV4_UDP:
+ case RX_DESC3_L34T_IPV6_TCP:
+ case RX_DESC3_L34T_IPV6_UDP:
+ pkt_info->rss_hash_type = PKT_HASH_TYPE_L4;
+ break;
+ default:
+ pkt_info->rss_hash_type = PKT_HASH_TYPE_L3;
+ }
+ }
+
+ /* Get the pkt_info length */
+ desc_data->rx.len = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+ RX_NORMAL_DESC3_PL_POS,
+ RX_NORMAL_DESC3_PL_LEN);
+
+ if (!XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+ RX_NORMAL_DESC3_LD_POS,
+ RX_NORMAL_DESC3_LD_LEN)) {
+ /* Not all the data has been transferred for this pkt_info */
+ pkt_info->attributes = XLGMAC_SET_REG_BITS(
+ pkt_info->attributes,
+ RX_PACKET_ATTRIBUTES_INCOMPLETE_POS,
+ RX_PACKET_ATTRIBUTES_INCOMPLETE_LEN,
+ 1);
+ return 0;
+ }
+
+ /* This is the last of the data for this pkt_info */
+ pkt_info->attributes = XLGMAC_SET_REG_BITS(
+ pkt_info->attributes,
+ RX_PACKET_ATTRIBUTES_INCOMPLETE_POS,
+ RX_PACKET_ATTRIBUTES_INCOMPLETE_LEN,
+ 0);
+
+ /* Set checksum done indicator as appropriate */
+ if (netdev->features & NETIF_F_RXCSUM)
+ pkt_info->attributes = XLGMAC_SET_REG_BITS(
+ pkt_info->attributes,
+ RX_PACKET_ATTRIBUTES_CSUM_DONE_POS,
+ RX_PACKET_ATTRIBUTES_CSUM_DONE_LEN,
+ 1);
+
+ /* Check for errors (only valid in last descriptor) */
+ err = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+ RX_NORMAL_DESC3_ES_POS,
+ RX_NORMAL_DESC3_ES_LEN);
+ etlt = XLGMAC_GET_REG_BITS_LE(dma_desc->desc3,
+ RX_NORMAL_DESC3_ETLT_POS,
+ RX_NORMAL_DESC3_ETLT_LEN);
+ netif_dbg(pdata, rx_status, netdev, "err=%u, etlt=%#x\n", err, etlt);
+
+ if (!err || !etlt) {
+ /* No error if err is 0 or etlt is 0 */
+ if ((etlt == 0x09) &&
+ (netdev->features & NETIF_F_HW_VLAN_CTAG_RX)) {
+ pkt_info->attributes = XLGMAC_SET_REG_BITS(
+ pkt_info->attributes,
+ RX_PACKET_ATTRIBUTES_VLAN_CTAG_POS,
+ RX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN,
+ 1);
+ pkt_info->vlan_ctag =
+ XLGMAC_GET_REG_BITS_LE(dma_desc->desc0,
+ RX_NORMAL_DESC0_OVT_POS,
+ RX_NORMAL_DESC0_OVT_LEN);
+ netif_dbg(pdata, rx_status, netdev, "vlan-ctag=%#06x\n",
+ pkt_info->vlan_ctag);
+ }
+ } else {
+ if ((etlt == 0x05) || (etlt == 0x06))
+ pkt_info->attributes = XLGMAC_SET_REG_BITS(
+ pkt_info->attributes,
+ RX_PACKET_ATTRIBUTES_CSUM_DONE_POS,
+ RX_PACKET_ATTRIBUTES_CSUM_DONE_LEN,
+ 0);
+ else
+ pkt_info->errors = XLGMAC_SET_REG_BITS(
+ pkt_info->errors,
+ RX_PACKET_ERRORS_FRAME_POS,
+ RX_PACKET_ERRORS_FRAME_LEN,
+ 1);
+ }
+
+ XLGMAC_PR("%s - descriptor=%u (cur=%d)\n", channel->name,
+ ring->cur & (ring->dma_desc_count - 1), ring->cur);
+
+ return 0;
+}
+
+static int xlgmac_enable_int(struct xlgmac_channel *channel,
+ enum xlgmac_int int_id)
+{
+ unsigned int dma_ch_ier;
+
+ dma_ch_ier = readl(XLGMAC_DMA_REG(channel, DMA_CH_IER));
+
+ switch (int_id) {
+ case XLGMAC_INT_DMA_CH_SR_TI:
+ dma_ch_ier = XLGMAC_SET_REG_BITS(
+ dma_ch_ier, DMA_CH_IER_TIE_POS,
+ DMA_CH_IER_TIE_LEN, 1);
+ break;
+ case XLGMAC_INT_DMA_CH_SR_TPS:
+ dma_ch_ier = XLGMAC_SET_REG_BITS(
+ dma_ch_ier, DMA_CH_IER_TXSE_POS,
+ DMA_CH_IER_TXSE_LEN, 1);
+ break;
+ case XLGMAC_INT_DMA_CH_SR_TBU:
+ dma_ch_ier = XLGMAC_SET_REG_BITS(
+ dma_ch_ier, DMA_CH_IER_TBUE_POS,
+ DMA_CH_IER_TBUE_LEN, 1);
+ break;
+ case XLGMAC_INT_DMA_CH_SR_RI:
+ dma_ch_ier = XLGMAC_SET_REG_BITS(
+ dma_ch_ier, DMA_CH_IER_RIE_POS,
+ DMA_CH_IER_RIE_LEN, 1);
+ break;
+ case XLGMAC_INT_DMA_CH_SR_RBU:
+ dma_ch_ier = XLGMAC_SET_REG_BITS(
+ dma_ch_ier, DMA_CH_IER_RBUE_POS,
+ DMA_CH_IER_RBUE_LEN, 1);
+ break;
+ case XLGMAC_INT_DMA_CH_SR_RPS:
+ dma_ch_ier = XLGMAC_SET_REG_BITS(
+ dma_ch_ier, DMA_CH_IER_RSE_POS,
+ DMA_CH_IER_RSE_LEN, 1);
+ break;
+ case XLGMAC_INT_DMA_CH_SR_TI_RI:
+ dma_ch_ier = XLGMAC_SET_REG_BITS(
+ dma_ch_ier, DMA_CH_IER_TIE_POS,
+ DMA_CH_IER_TIE_LEN, 1);
+ dma_ch_ier = XLGMAC_SET_REG_BITS(
+ dma_ch_ier, DMA_CH_IER_RIE_POS,
+ DMA_CH_IER_RIE_LEN, 1);
+ break;
+ case XLGMAC_INT_DMA_CH_SR_FBE:
+ dma_ch_ier = XLGMAC_SET_REG_BITS(
+ dma_ch_ier, DMA_CH_IER_FBEE_POS,
+ DMA_CH_IER_FBEE_LEN, 1);
+ break;
+ case XLGMAC_INT_DMA_ALL:
+ dma_ch_ier |= channel->saved_ier;
+ break;
+ default:
+ return -1;
+ }
+
+ writel(dma_ch_ier, XLGMAC_DMA_REG(channel, DMA_CH_IER));
+
+ return 0;
+}
+
+static int xlgmac_disable_int(struct xlgmac_channel *channel,
+ enum xlgmac_int int_id)
+{
+ unsigned int dma_ch_ier;
+
+ dma_ch_ier = readl(XLGMAC_DMA_REG(channel, DMA_CH_IER));
+
+ switch (int_id) {
+ case XLGMAC_INT_DMA_CH_SR_TI:
+ dma_ch_ier = XLGMAC_SET_REG_BITS(
+ dma_ch_ier, DMA_CH_IER_TIE_POS,
+ DMA_CH_IER_TIE_LEN, 0);
+ break;
+ case XLGMAC_INT_DMA_CH_SR_TPS:
+ dma_ch_ier = XLGMAC_SET_REG_BITS(
+ dma_ch_ier, DMA_CH_IER_TXSE_POS,
+ DMA_CH_IER_TXSE_LEN, 0);
+ break;
+ case XLGMAC_INT_DMA_CH_SR_TBU:
+ dma_ch_ier = XLGMAC_SET_REG_BITS(
+ dma_ch_ier, DMA_CH_IER_TBUE_POS,
+ DMA_CH_IER_TBUE_LEN, 0);
+ break;
+ case XLGMAC_INT_DMA_CH_SR_RI:
+ dma_ch_ier = XLGMAC_SET_REG_BITS(
+ dma_ch_ier, DMA_CH_IER_RIE_POS,
+ DMA_CH_IER_RIE_LEN, 0);
+ break;
+ case XLGMAC_INT_DMA_CH_SR_RBU:
+ dma_ch_ier = XLGMAC_SET_REG_BITS(
+ dma_ch_ier, DMA_CH_IER_RBUE_POS,
+ DMA_CH_IER_RBUE_LEN, 0);
+ break;
+ case XLGMAC_INT_DMA_CH_SR_RPS:
+ dma_ch_ier = XLGMAC_SET_REG_BITS(
+ dma_ch_ier, DMA_CH_IER_RSE_POS,
+ DMA_CH_IER_RSE_LEN, 0);
+ break;
+ case XLGMAC_INT_DMA_CH_SR_TI_RI:
+ dma_ch_ier = XLGMAC_SET_REG_BITS(
+ dma_ch_ier, DMA_CH_IER_TIE_POS,
+ DMA_CH_IER_TIE_LEN, 0);
+ dma_ch_ier = XLGMAC_SET_REG_BITS(
+ dma_ch_ier, DMA_CH_IER_RIE_POS,
+ DMA_CH_IER_RIE_LEN, 0);
+ break;
+ case XLGMAC_INT_DMA_CH_SR_FBE:
+ dma_ch_ier = XLGMAC_SET_REG_BITS(
+ dma_ch_ier, DMA_CH_IER_FBEE_POS,
+ DMA_CH_IER_FBEE_LEN, 0);
+ break;
+ case XLGMAC_INT_DMA_ALL:
+ channel->saved_ier = dma_ch_ier & XLGMAC_DMA_INTERRUPT_MASK;
+ dma_ch_ier &= ~XLGMAC_DMA_INTERRUPT_MASK;
+ break;
+ default:
+ return -1;
+ }
+
+ writel(dma_ch_ier, XLGMAC_DMA_REG(channel, DMA_CH_IER));
+
+ return 0;
+}
+
+static int xlgmac_flush_tx_queues(struct xlgmac_pdata *pdata)
+{
+ unsigned int i, count;
+ u32 regval;
+
+ for (i = 0; i < pdata->tx_q_count; i++) {
+ regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+ regval = XLGMAC_SET_REG_BITS(regval, MTL_Q_TQOMR_FTQ_POS,
+ MTL_Q_TQOMR_FTQ_LEN, 1);
+ writel(regval, XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+ }
+
+ /* Poll Until Poll Condition */
+ for (i = 0; i < pdata->tx_q_count; i++) {
+ count = 2000;
+ regval = readl(XLGMAC_MTL_REG(pdata, i, MTL_Q_TQOMR));
+ regval = XLGMAC_GET_REG_BITS(regval, MTL_Q_TQOMR_FTQ_POS,
+ MTL_Q_TQOMR_FTQ_LEN);
+ while (--count && regval)
+ usleep_range(500, 600);
+
+ if (!count)
+ return -EBUSY;
+ }
+
+ return 0;
+}
+
+static void xlgmac_config_dma_bus(struct xlgmac_pdata *pdata)
+{
+ u32 regval;
+
+ regval = readl(pdata->mac_regs + DMA_SBMR);
+ /* Set enhanced addressing mode */
+ regval = XLGMAC_SET_REG_BITS(regval, DMA_SBMR_EAME_POS,
+ DMA_SBMR_EAME_LEN, 1);
+ /* Set the System Bus mode */
+ regval = XLGMAC_SET_REG_BITS(regval, DMA_SBMR_UNDEF_POS,
+ DMA_SBMR_UNDEF_LEN, 1);
+ regval = XLGMAC_SET_REG_BITS(regval, DMA_SBMR_BLEN_256_POS,
+ DMA_SBMR_BLEN_256_LEN, 1);
+ writel(regval, pdata->mac_regs + DMA_SBMR);
+}
+
+static int xlgmac_hw_init(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_desc_ops *desc_ops = &pdata->desc_ops;
+ int ret;
+
+ /* Flush Tx queues */
+ ret = xlgmac_flush_tx_queues(pdata);
+ if (ret)
+ return ret;
+
+ /* Initialize DMA related features */
+ xlgmac_config_dma_bus(pdata);
+ xlgmac_config_osp_mode(pdata);
+ xlgmac_config_pblx8(pdata);
+ xlgmac_config_tx_pbl_val(pdata);
+ xlgmac_config_rx_pbl_val(pdata);
+ xlgmac_config_rx_coalesce(pdata);
+ xlgmac_config_tx_coalesce(pdata);
+ xlgmac_config_rx_buffer_size(pdata);
+ xlgmac_config_tso_mode(pdata);
+ xlgmac_config_sph_mode(pdata);
+ xlgmac_config_rss(pdata);
+ desc_ops->tx_desc_init(pdata);
+ desc_ops->rx_desc_init(pdata);
+ xlgmac_enable_dma_interrupts(pdata);
+
+ /* Initialize MTL related features */
+ xlgmac_config_mtl_mode(pdata);
+ xlgmac_config_queue_mapping(pdata);
+ xlgmac_config_tsf_mode(pdata, pdata->tx_sf_mode);
+ xlgmac_config_rsf_mode(pdata, pdata->rx_sf_mode);
+ xlgmac_config_tx_threshold(pdata, pdata->tx_threshold);
+ xlgmac_config_rx_threshold(pdata, pdata->rx_threshold);
+ xlgmac_config_tx_fifo_size(pdata);
+ xlgmac_config_rx_fifo_size(pdata);
+ xlgmac_config_flow_control_threshold(pdata);
+ xlgmac_config_rx_fep_enable(pdata);
+ xlgmac_config_rx_fup_enable(pdata);
+ xlgmac_enable_mtl_interrupts(pdata);
+
+ /* Initialize MAC related features */
+ xlgmac_config_mac_address(pdata);
+ xlgmac_config_rx_mode(pdata);
+ xlgmac_config_jumbo_enable(pdata);
+ xlgmac_config_flow_control(pdata);
+ xlgmac_config_mac_speed(pdata);
+ xlgmac_config_checksum_offload(pdata);
+ xlgmac_config_vlan_support(pdata);
+ xlgmac_config_mmc(pdata);
+ xlgmac_enable_mac_interrupts(pdata);
+
+ return 0;
+}
+
+static int xlgmac_hw_exit(struct xlgmac_pdata *pdata)
+{
+ unsigned int count = 2000;
+ u32 regval;
+
+ /* Issue a software reset */
+ regval = readl(pdata->mac_regs + DMA_MR);
+ regval = XLGMAC_SET_REG_BITS(regval, DMA_MR_SWR_POS,
+ DMA_MR_SWR_LEN, 1);
+ writel(regval, pdata->mac_regs + DMA_MR);
+ usleep_range(10, 15);
+
+ /* Poll Until Poll Condition */
+ while (--count &&
+ XLGMAC_GET_REG_BITS(readl(pdata->mac_regs + DMA_MR),
+ DMA_MR_SWR_POS, DMA_MR_SWR_LEN))
+ usleep_range(500, 600);
+
+ if (!count)
+ return -EBUSY;
+
+ return 0;
+}
+
+void xlgmac_init_hw_ops(struct xlgmac_hw_ops *hw_ops)
+{
+ hw_ops->init = xlgmac_hw_init;
+ hw_ops->exit = xlgmac_hw_exit;
+
+ hw_ops->tx_complete = xlgmac_tx_complete;
+
+ hw_ops->enable_tx = xlgmac_enable_tx;
+ hw_ops->disable_tx = xlgmac_disable_tx;
+ hw_ops->enable_rx = xlgmac_enable_rx;
+ hw_ops->disable_rx = xlgmac_disable_rx;
+
+ hw_ops->dev_xmit = xlgmac_dev_xmit;
+ hw_ops->dev_read = xlgmac_dev_read;
+ hw_ops->enable_int = xlgmac_enable_int;
+ hw_ops->disable_int = xlgmac_disable_int;
+
+ hw_ops->set_mac_address = xlgmac_set_mac_address;
+ hw_ops->config_rx_mode = xlgmac_config_rx_mode;
+ hw_ops->enable_rx_csum = xlgmac_enable_rx_csum;
+ hw_ops->disable_rx_csum = xlgmac_disable_rx_csum;
+
+ /* For MII speed configuration */
+ hw_ops->set_xlgmii_25000_speed = xlgmac_set_xlgmii_25000_speed;
+ hw_ops->set_xlgmii_40000_speed = xlgmac_set_xlgmii_40000_speed;
+ hw_ops->set_xlgmii_50000_speed = xlgmac_set_xlgmii_50000_speed;
+ hw_ops->set_xlgmii_100000_speed = xlgmac_set_xlgmii_100000_speed;
+
+ /* For descriptor related operation */
+ hw_ops->tx_desc_init = xlgmac_tx_desc_init;
+ hw_ops->rx_desc_init = xlgmac_rx_desc_init;
+ hw_ops->tx_desc_reset = xlgmac_tx_desc_reset;
+ hw_ops->rx_desc_reset = xlgmac_rx_desc_reset;
+ hw_ops->is_last_desc = xlgmac_is_last_desc;
+ hw_ops->is_context_desc = xlgmac_is_context_desc;
+ hw_ops->tx_start_xmit = xlgmac_tx_start_xmit;
+
+ /* For Flow Control */
+ hw_ops->config_tx_flow_control = xlgmac_config_tx_flow_control;
+ hw_ops->config_rx_flow_control = xlgmac_config_rx_flow_control;
+
+ /* For Vlan related config */
+ hw_ops->enable_rx_vlan_stripping = xlgmac_enable_rx_vlan_stripping;
+ hw_ops->disable_rx_vlan_stripping = xlgmac_disable_rx_vlan_stripping;
+ hw_ops->enable_rx_vlan_filtering = xlgmac_enable_rx_vlan_filtering;
+ hw_ops->disable_rx_vlan_filtering = xlgmac_disable_rx_vlan_filtering;
+ hw_ops->update_vlan_hash_table = xlgmac_update_vlan_hash_table;
+
+ /* For RX coalescing */
+ hw_ops->config_rx_coalesce = xlgmac_config_rx_coalesce;
+ hw_ops->config_tx_coalesce = xlgmac_config_tx_coalesce;
+ hw_ops->usec_to_riwt = xlgmac_usec_to_riwt;
+ hw_ops->riwt_to_usec = xlgmac_riwt_to_usec;
+
+ /* For RX and TX threshold config */
+ hw_ops->config_rx_threshold = xlgmac_config_rx_threshold;
+ hw_ops->config_tx_threshold = xlgmac_config_tx_threshold;
+
+ /* For RX and TX Store and Forward Mode config */
+ hw_ops->config_rsf_mode = xlgmac_config_rsf_mode;
+ hw_ops->config_tsf_mode = xlgmac_config_tsf_mode;
+
+ /* For TX DMA Operating on Second Frame config */
+ hw_ops->config_osp_mode = xlgmac_config_osp_mode;
+
+ /* For RX and TX PBL config */
+ hw_ops->config_rx_pbl_val = xlgmac_config_rx_pbl_val;
+ hw_ops->get_rx_pbl_val = xlgmac_get_rx_pbl_val;
+ hw_ops->config_tx_pbl_val = xlgmac_config_tx_pbl_val;
+ hw_ops->get_tx_pbl_val = xlgmac_get_tx_pbl_val;
+ hw_ops->config_pblx8 = xlgmac_config_pblx8;
+
+ /* For MMC statistics support */
+ hw_ops->tx_mmc_int = xlgmac_tx_mmc_int;
+ hw_ops->rx_mmc_int = xlgmac_rx_mmc_int;
+ hw_ops->read_mmc_stats = xlgmac_read_mmc_stats;
+
+ /* For Receive Side Scaling */
+ hw_ops->enable_rss = xlgmac_enable_rss;
+ hw_ops->disable_rss = xlgmac_disable_rss;
+ hw_ops->set_rss_hash_key = xlgmac_set_rss_hash_key;
+ hw_ops->set_rss_lookup_table = xlgmac_set_rss_lookup_table;
+}
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c
new file mode 100644
index 0000000..6acf86c
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c
@@ -0,0 +1,1332 @@
+/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver
+ *
+ * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is dual-licensed; you may select either version 2 of
+ * the GNU General Public License ("GPL") or BSD license ("BSD").
+ *
+ * This Synopsys DWC XLGMAC software driver and associated documentation
+ * (hereinafter the "Software") is an unsupported proprietary work of
+ * Synopsys, Inc. unless otherwise expressly agreed to in writing between
+ * Synopsys and you. The Software IS NOT an item of Licensed Software or a
+ * Licensed Product under any End User Software License Agreement or
+ * Agreement for Licensed Products with Synopsys or any supplement thereto.
+ * Synopsys is a registered trademark of Synopsys, Inc. Other names included
+ * in the SOFTWARE may be the trademarks of their respective owners.
+ */
+
+#include <linux/netdevice.h>
+#include <linux/tcp.h>
+
+#include "dwc-xlgmac.h"
+#include "dwc-xlgmac-reg.h"
+
+static int xlgmac_one_poll(struct napi_struct *, int);
+static int xlgmac_all_poll(struct napi_struct *, int);
+
+static inline unsigned int xlgmac_tx_avail_desc(struct xlgmac_ring *ring)
+{
+ return (ring->dma_desc_count - (ring->cur - ring->dirty));
+}
+
+static inline unsigned int xlgmac_rx_dirty_desc(struct xlgmac_ring *ring)
+{
+ return (ring->cur - ring->dirty);
+}
+
+static int xlgmac_maybe_stop_tx_queue(
+ struct xlgmac_channel *channel,
+ struct xlgmac_ring *ring,
+ unsigned int count)
+{
+ struct xlgmac_pdata *pdata = channel->pdata;
+
+ if (count > xlgmac_tx_avail_desc(ring)) {
+ netif_info(pdata, drv, pdata->netdev,
+ "Tx queue stopped, not enough descriptors available\n");
+ netif_stop_subqueue(pdata->netdev, channel->queue_index);
+ ring->tx.queue_stopped = 1;
+
+ /* If we haven't notified the hardware because of xmit_more
+ * support, tell it now
+ */
+ if (ring->tx.xmit_more)
+ pdata->hw_ops.tx_start_xmit(channel, ring);
+
+ return NETDEV_TX_BUSY;
+ }
+
+ return 0;
+}
+
+static void xlgmac_prep_vlan(struct sk_buff *skb,
+ struct xlgmac_pkt_info *pkt_info)
+{
+ if (skb_vlan_tag_present(skb))
+ pkt_info->vlan_ctag = skb_vlan_tag_get(skb);
+}
+
+static int xlgmac_prep_tso(struct sk_buff *skb,
+ struct xlgmac_pkt_info *pkt_info)
+{
+ int ret;
+
+ if (!XLGMAC_GET_REG_BITS(pkt_info->attributes,
+ TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS,
+ TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN))
+ return 0;
+
+ ret = skb_cow_head(skb, 0);
+ if (ret)
+ return ret;
+
+ pkt_info->header_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+ pkt_info->tcp_header_len = tcp_hdrlen(skb);
+ pkt_info->tcp_payload_len = skb->len - pkt_info->header_len;
+ pkt_info->mss = skb_shinfo(skb)->gso_size;
+
+ XLGMAC_PR("header_len=%u\n", pkt_info->header_len);
+ XLGMAC_PR("tcp_header_len=%u, tcp_payload_len=%u\n",
+ pkt_info->tcp_header_len, pkt_info->tcp_payload_len);
+ XLGMAC_PR("mss=%u\n", pkt_info->mss);
+
+ /* Update the number of packets that will ultimately be transmitted
+ * along with the extra bytes for each extra packet
+ */
+ pkt_info->tx_packets = skb_shinfo(skb)->gso_segs;
+ pkt_info->tx_bytes += (pkt_info->tx_packets - 1) * pkt_info->header_len;
+
+ return 0;
+}
+
+static int xlgmac_is_tso(struct sk_buff *skb)
+{
+ if (skb->ip_summed != CHECKSUM_PARTIAL)
+ return 0;
+
+ if (!skb_is_gso(skb))
+ return 0;
+
+ return 1;
+}
+
+static void xlgmac_prep_tx_pkt(struct xlgmac_pdata *pdata,
+ struct xlgmac_ring *ring,
+ struct sk_buff *skb,
+ struct xlgmac_pkt_info *pkt_info)
+{
+ struct skb_frag_struct *frag;
+ unsigned int context_desc;
+ unsigned int len;
+ unsigned int i;
+
+ pkt_info->skb = skb;
+
+ context_desc = 0;
+ pkt_info->desc_count = 0;
+
+ pkt_info->tx_packets = 1;
+ pkt_info->tx_bytes = skb->len;
+
+ if (xlgmac_is_tso(skb)) {
+ /* TSO requires an extra descriptor if mss is different */
+ if (skb_shinfo(skb)->gso_size != ring->tx.cur_mss) {
+ context_desc = 1;
+ pkt_info->desc_count++;
+ }
+
+ /* TSO requires an extra descriptor for TSO header */
+ pkt_info->desc_count++;
+
+ pkt_info->attributes = XLGMAC_SET_REG_BITS(
+ pkt_info->attributes,
+ TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS,
+ TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN,
+ 1);
+ pkt_info->attributes = XLGMAC_SET_REG_BITS(
+ pkt_info->attributes,
+ TX_PACKET_ATTRIBUTES_CSUM_ENABLE_POS,
+ TX_PACKET_ATTRIBUTES_CSUM_ENABLE_LEN,
+ 1);
+ } else if (skb->ip_summed == CHECKSUM_PARTIAL)
+ pkt_info->attributes = XLGMAC_SET_REG_BITS(
+ pkt_info->attributes,
+ TX_PACKET_ATTRIBUTES_CSUM_ENABLE_POS,
+ TX_PACKET_ATTRIBUTES_CSUM_ENABLE_LEN,
+ 1);
+
+ if (skb_vlan_tag_present(skb)) {
+ /* VLAN requires an extra descriptor if tag is different */
+ if (skb_vlan_tag_get(skb) != ring->tx.cur_vlan_ctag)
+ /* We can share with the TSO context descriptor */
+ if (!context_desc) {
+ context_desc = 1;
+ pkt_info->desc_count++;
+ }
+
+ pkt_info->attributes = XLGMAC_SET_REG_BITS(
+ pkt_info->attributes,
+ TX_PACKET_ATTRIBUTES_VLAN_CTAG_POS,
+ TX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN,
+ 1);
+ }
+
+ for (len = skb_headlen(skb); len;) {
+ pkt_info->desc_count++;
+ len -= min_t(unsigned int, len, XLGMAC_TX_MAX_BUF_SIZE);
+ }
+
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+ frag = &skb_shinfo(skb)->frags[i];
+ for (len = skb_frag_size(frag); len; ) {
+ pkt_info->desc_count++;
+ len -= min_t(unsigned int, len, XLGMAC_TX_MAX_BUF_SIZE);
+ }
+ }
+}
+
+static int xlgmac_calc_rx_buf_size(struct net_device *netdev, unsigned int mtu)
+{
+ unsigned int rx_buf_size;
+
+ if (mtu > XLGMAC_JUMBO_PACKET_MTU) {
+ netdev_alert(netdev, "MTU exceeds maximum supported value\n");
+ return -EINVAL;
+ }
+
+ rx_buf_size = mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
+ rx_buf_size = clamp_val(rx_buf_size, XLGMAC_RX_MIN_BUF_SIZE, PAGE_SIZE);
+
+ rx_buf_size = (rx_buf_size + XLGMAC_RX_BUF_ALIGN - 1) &
+ ~(XLGMAC_RX_BUF_ALIGN - 1);
+
+ return rx_buf_size;
+}
+
+static void xlgmac_enable_rx_tx_ints(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+ struct xlgmac_channel *channel;
+ enum xlgmac_int int_id;
+ unsigned int i;
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ if (channel->tx_ring && channel->rx_ring)
+ int_id = XLGMAC_INT_DMA_CH_SR_TI_RI;
+ else if (channel->tx_ring)
+ int_id = XLGMAC_INT_DMA_CH_SR_TI;
+ else if (channel->rx_ring)
+ int_id = XLGMAC_INT_DMA_CH_SR_RI;
+ else
+ continue;
+
+ hw_ops->enable_int(channel, int_id);
+ }
+}
+
+static void xlgmac_disable_rx_tx_ints(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+ struct xlgmac_channel *channel;
+ enum xlgmac_int int_id;
+ unsigned int i;
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ if (channel->tx_ring && channel->rx_ring)
+ int_id = XLGMAC_INT_DMA_CH_SR_TI_RI;
+ else if (channel->tx_ring)
+ int_id = XLGMAC_INT_DMA_CH_SR_TI;
+ else if (channel->rx_ring)
+ int_id = XLGMAC_INT_DMA_CH_SR_RI;
+ else
+ continue;
+
+ hw_ops->disable_int(channel, int_id);
+ }
+}
+
+static irqreturn_t xlgmac_isr(int irq, void *data)
+{
+ unsigned int dma_isr, dma_ch_isr, mac_isr;
+ struct xlgmac_pdata *pdata = data;
+ struct xlgmac_channel *channel;
+ struct xlgmac_hw_ops *hw_ops;
+ unsigned int i, ti, ri;
+
+ hw_ops = &pdata->hw_ops;
+
+ /* The DMA interrupt status register also reports MAC and MTL
+ * interrupts. So for polling mode, we just need to check for
+ * this register to be non-zero
+ */
+ dma_isr = readl(pdata->mac_regs + DMA_ISR);
+ if (!dma_isr)
+ return IRQ_HANDLED;
+
+ netif_dbg(pdata, intr, pdata->netdev, "DMA_ISR=%#010x\n", dma_isr);
+
+ for (i = 0; i < pdata->channel_count; i++) {
+ if (!(dma_isr & (1 << i)))
+ continue;
+
+ channel = pdata->channel_head + i;
+
+ dma_ch_isr = readl(XLGMAC_DMA_REG(channel, DMA_CH_SR));
+ netif_dbg(pdata, intr, pdata->netdev, "DMA_CH%u_ISR=%#010x\n",
+ i, dma_ch_isr);
+
+ /* The TI or RI interrupt bits may still be set even if using
+ * per channel DMA interrupts. Check to be sure those are not
+ * enabled before using the private data napi structure.
+ */
+ ti = XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_TI_POS,
+ DMA_CH_SR_TI_LEN);
+ ri = XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_RI_POS,
+ DMA_CH_SR_RI_LEN);
+ if (!pdata->per_channel_irq && (ti || ri)) {
+ if (napi_schedule_prep(&pdata->napi)) {
+ /* Disable Tx and Rx interrupts */
+ xlgmac_disable_rx_tx_ints(pdata);
+
+ /* Turn on polling */
+ __napi_schedule_irqoff(&pdata->napi);
+ }
+ }
+
+ if (XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_RBU_POS,
+ DMA_CH_SR_RBU_LEN))
+ pdata->stats.rx_buffer_unavailable++;
+
+ /* Restart the device on a Fatal Bus Error */
+ if (XLGMAC_GET_REG_BITS(dma_ch_isr, DMA_CH_SR_FBE_POS,
+ DMA_CH_SR_FBE_LEN))
+ schedule_work(&pdata->restart_work);
+
+ /* Clear all interrupt signals */
+ writel(dma_ch_isr, XLGMAC_DMA_REG(channel, DMA_CH_SR));
+ }
+
+ if (XLGMAC_GET_REG_BITS(dma_isr, DMA_ISR_MACIS_POS,
+ DMA_ISR_MACIS_LEN)) {
+ mac_isr = readl(pdata->mac_regs + MAC_ISR);
+
+ if (XLGMAC_GET_REG_BITS(mac_isr, MAC_ISR_MMCTXIS_POS,
+ MAC_ISR_MMCTXIS_LEN))
+ hw_ops->tx_mmc_int(pdata);
+
+ if (XLGMAC_GET_REG_BITS(mac_isr, MAC_ISR_MMCRXIS_POS,
+ MAC_ISR_MMCRXIS_LEN))
+ hw_ops->rx_mmc_int(pdata);
+ }
+
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t xlgmac_dma_isr(int irq, void *data)
+{
+ struct xlgmac_channel *channel = data;
+
+ /* Per channel DMA interrupts are enabled, so we use the per
+ * channel napi structure and not the private data napi structure
+ */
+ if (napi_schedule_prep(&channel->napi)) {
+ /* Disable Tx and Rx interrupts */
+ disable_irq_nosync(channel->dma_irq);
+
+ /* Turn on polling */
+ __napi_schedule_irqoff(&channel->napi);
+ }
+
+ return IRQ_HANDLED;
+}
+
+static void xlgmac_tx_timer(unsigned long data)
+{
+ struct xlgmac_channel *channel = (struct xlgmac_channel *)data;
+ struct xlgmac_pdata *pdata = channel->pdata;
+ struct napi_struct *napi;
+
+ napi = (pdata->per_channel_irq) ? &channel->napi : &pdata->napi;
+
+ if (napi_schedule_prep(napi)) {
+ /* Disable Tx and Rx interrupts */
+ if (pdata->per_channel_irq)
+ disable_irq_nosync(channel->dma_irq);
+ else
+ xlgmac_disable_rx_tx_ints(pdata);
+
+ /* Turn on polling */
+ __napi_schedule(napi);
+ }
+
+ channel->tx_timer_active = 0;
+}
+
+static void xlgmac_init_timers(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_channel *channel;
+ unsigned int i;
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ if (!channel->tx_ring)
+ break;
+
+ setup_timer(&channel->tx_timer, xlgmac_tx_timer,
+ (unsigned long)channel);
+ }
+}
+
+static void xlgmac_stop_timers(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_channel *channel;
+ unsigned int i;
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ if (!channel->tx_ring)
+ break;
+
+ del_timer_sync(&channel->tx_timer);
+ }
+}
+
+static void xlgmac_napi_enable(struct xlgmac_pdata *pdata, unsigned int add)
+{
+ struct xlgmac_channel *channel;
+ unsigned int i;
+
+ if (pdata->per_channel_irq) {
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ if (add)
+ netif_napi_add(pdata->netdev, &channel->napi,
+ xlgmac_one_poll,
+ NAPI_POLL_WEIGHT);
+
+ napi_enable(&channel->napi);
+ }
+ } else {
+ if (add)
+ netif_napi_add(pdata->netdev, &pdata->napi,
+ xlgmac_all_poll, NAPI_POLL_WEIGHT);
+
+ napi_enable(&pdata->napi);
+ }
+}
+
+static void xlgmac_napi_disable(struct xlgmac_pdata *pdata, unsigned int del)
+{
+ struct xlgmac_channel *channel;
+ unsigned int i;
+
+ if (pdata->per_channel_irq) {
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ napi_disable(&channel->napi);
+
+ if (del)
+ netif_napi_del(&channel->napi);
+ }
+ } else {
+ napi_disable(&pdata->napi);
+
+ if (del)
+ netif_napi_del(&pdata->napi);
+ }
+}
+
+static int xlgmac_request_irqs(struct xlgmac_pdata *pdata)
+{
+ struct net_device *netdev = pdata->netdev;
+ struct xlgmac_channel *channel;
+ unsigned int i;
+ int ret;
+
+ ret = devm_request_irq(pdata->dev, pdata->dev_irq, xlgmac_isr,
+ IRQF_SHARED, netdev->name, pdata);
+ if (ret) {
+ netdev_alert(netdev, "error requesting irq %d\n",
+ pdata->dev_irq);
+ return ret;
+ }
+
+ if (!pdata->per_channel_irq)
+ return 0;
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ snprintf(channel->dma_irq_name,
+ sizeof(channel->dma_irq_name) - 1,
+ "%s-TxRx-%u", netdev_name(netdev),
+ channel->queue_index);
+
+ ret = devm_request_irq(pdata->dev, channel->dma_irq,
+ xlgmac_dma_isr, 0,
+ channel->dma_irq_name, channel);
+ if (ret) {
+ netdev_alert(netdev, "error requesting irq %d\n",
+ channel->dma_irq);
+ goto err_irq;
+ }
+ }
+
+ return 0;
+
+err_irq:
+ /* Using an unsigned int, 'i' will go to UINT_MAX and exit */
+ for (i--, channel--; i < pdata->channel_count; i--, channel--)
+ devm_free_irq(pdata->dev, channel->dma_irq, channel);
+
+ devm_free_irq(pdata->dev, pdata->dev_irq, pdata);
+
+ return ret;
+}
+
+static void xlgmac_free_irqs(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_channel *channel;
+ unsigned int i;
+
+ devm_free_irq(pdata->dev, pdata->dev_irq, pdata);
+
+ if (!pdata->per_channel_irq)
+ return;
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++)
+ devm_free_irq(pdata->dev, channel->dma_irq, channel);
+}
+
+static void xlgmac_free_tx_data(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_desc_ops *desc_ops = &pdata->desc_ops;
+ struct xlgmac_desc_data *desc_data;
+ struct xlgmac_channel *channel;
+ struct xlgmac_ring *ring;
+ unsigned int i, j;
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ ring = channel->tx_ring;
+ if (!ring)
+ break;
+
+ for (j = 0; j < ring->dma_desc_count; j++) {
+ desc_data = XLGMAC_GET_DESC_DATA(ring, j);
+ desc_ops->unmap_desc_data(pdata, desc_data);
+ }
+ }
+}
+
+static void xlgmac_free_rx_data(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_desc_ops *desc_ops = &pdata->desc_ops;
+ struct xlgmac_desc_data *desc_data;
+ struct xlgmac_channel *channel;
+ struct xlgmac_ring *ring;
+ unsigned int i, j;
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ ring = channel->rx_ring;
+ if (!ring)
+ break;
+
+ for (j = 0; j < ring->dma_desc_count; j++) {
+ desc_data = XLGMAC_GET_DESC_DATA(ring, j);
+ desc_ops->unmap_desc_data(pdata, desc_data);
+ }
+ }
+}
+
+static int xlgmac_start(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+ struct net_device *netdev = pdata->netdev;
+ int ret;
+
+ hw_ops->init(pdata);
+ xlgmac_napi_enable(pdata, 1);
+
+ ret = xlgmac_request_irqs(pdata);
+ if (ret)
+ goto err_napi;
+
+ hw_ops->enable_tx(pdata);
+ hw_ops->enable_rx(pdata);
+ netif_tx_start_all_queues(netdev);
+
+ return 0;
+
+err_napi:
+ xlgmac_napi_disable(pdata, 1);
+ hw_ops->exit(pdata);
+
+ return ret;
+}
+
+static void xlgmac_stop(struct xlgmac_pdata *pdata)
+{
+ struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+ struct net_device *netdev = pdata->netdev;
+ struct xlgmac_channel *channel;
+ struct netdev_queue *txq;
+ unsigned int i;
+
+ netif_tx_stop_all_queues(netdev);
+ xlgmac_stop_timers(pdata);
+ hw_ops->disable_tx(pdata);
+ hw_ops->disable_rx(pdata);
+ xlgmac_free_irqs(pdata);
+ xlgmac_napi_disable(pdata, 1);
+ hw_ops->exit(pdata);
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ if (!channel->tx_ring)
+ continue;
+
+ txq = netdev_get_tx_queue(netdev, channel->queue_index);
+ netdev_tx_reset_queue(txq);
+ }
+}
+
+static void xlgmac_restart_dev(struct xlgmac_pdata *pdata)
+{
+ /* If not running, "restart" will happen on open */
+ if (!netif_running(pdata->netdev))
+ return;
+
+ xlgmac_stop(pdata);
+
+ xlgmac_free_tx_data(pdata);
+ xlgmac_free_rx_data(pdata);
+
+ xlgmac_start(pdata);
+}
+
+static void xlgmac_restart(struct work_struct *work)
+{
+ struct xlgmac_pdata *pdata = container_of(work,
+ struct xlgmac_pdata,
+ restart_work);
+
+ rtnl_lock();
+
+ xlgmac_restart_dev(pdata);
+
+ rtnl_unlock();
+}
+
+static int xlgmac_open(struct net_device *netdev)
+{
+ struct xlgmac_pdata *pdata = netdev_priv(netdev);
+ struct xlgmac_desc_ops *desc_ops;
+ int ret;
+
+ desc_ops = &pdata->desc_ops;
+
+ /* TODO: Initialize the phy */
+
+ /* Calculate the Rx buffer size before allocating rings */
+ ret = xlgmac_calc_rx_buf_size(netdev, netdev->mtu);
+ if (ret < 0)
+ return ret;
+ pdata->rx_buf_size = ret;
+
+ /* Allocate the channels and rings */
+ ret = desc_ops->alloc_channles_and_rings(pdata);
+ if (ret)
+ return ret;
+
+ INIT_WORK(&pdata->restart_work, xlgmac_restart);
+ xlgmac_init_timers(pdata);
+
+ ret = xlgmac_start(pdata);
+ if (ret)
+ goto err_channels_and_rings;
+
+ return 0;
+
+err_channels_and_rings:
+ desc_ops->free_channels_and_rings(pdata);
+
+ return ret;
+}
+
+static int xlgmac_close(struct net_device *netdev)
+{
+ struct xlgmac_pdata *pdata = netdev_priv(netdev);
+ struct xlgmac_desc_ops *desc_ops;
+
+ desc_ops = &pdata->desc_ops;
+
+ /* Stop the device */
+ xlgmac_stop(pdata);
+
+ /* Free the channels and rings */
+ desc_ops->free_channels_and_rings(pdata);
+
+ return 0;
+}
+
+static void xlgmac_tx_timeout(struct net_device *netdev)
+{
+ struct xlgmac_pdata *pdata = netdev_priv(netdev);
+
+ netdev_warn(netdev, "tx timeout, device restarting\n");
+ schedule_work(&pdata->restart_work);
+}
+
+static int xlgmac_xmit(struct sk_buff *skb, struct net_device *netdev)
+{
+ struct xlgmac_pdata *pdata = netdev_priv(netdev);
+ struct xlgmac_pkt_info *tx_pkt_info;
+ struct xlgmac_desc_ops *desc_ops;
+ struct xlgmac_channel *channel;
+ struct xlgmac_hw_ops *hw_ops;
+ struct netdev_queue *txq;
+ struct xlgmac_ring *ring;
+ int ret;
+
+ desc_ops = &pdata->desc_ops;
+ hw_ops = &pdata->hw_ops;
+
+ XLGMAC_PR("skb->len = %d\n", skb->len);
+
+ channel = pdata->channel_head + skb->queue_mapping;
+ txq = netdev_get_tx_queue(netdev, channel->queue_index);
+ ring = channel->tx_ring;
+ tx_pkt_info = &ring->pkt_info;
+
+ if (skb->len == 0) {
+ netif_err(pdata, tx_err, netdev,
+ "empty skb received from stack\n");
+ dev_kfree_skb_any(skb);
+ return NETDEV_TX_OK;
+ }
+
+ /* Prepare preliminary packet info for TX */
+ memset(tx_pkt_info, 0, sizeof(*tx_pkt_info));
+ xlgmac_prep_tx_pkt(pdata, ring, skb, tx_pkt_info);
+
+ /* Check that there are enough descriptors available */
+ ret = xlgmac_maybe_stop_tx_queue(channel, ring,
+ tx_pkt_info->desc_count);
+ if (ret)
+ return ret;
+
+ ret = xlgmac_prep_tso(skb, tx_pkt_info);
+ if (ret) {
+ netif_err(pdata, tx_err, netdev,
+ "error processing TSO packet\n");
+ dev_kfree_skb_any(skb);
+ return ret;
+ }
+ xlgmac_prep_vlan(skb, tx_pkt_info);
+
+ if (!desc_ops->map_tx_skb(channel, skb)) {
+ dev_kfree_skb_any(skb);
+ return NETDEV_TX_OK;
+ }
+
+ /* Report on the actual number of bytes (to be) sent */
+ netdev_tx_sent_queue(txq, tx_pkt_info->tx_bytes);
+
+ /* Configure required descriptor fields for transmission */
+ hw_ops->dev_xmit(channel);
+
+ if (netif_msg_pktdata(pdata))
+ xlgmac_print_pkt(netdev, skb, true);
+
+ /* Stop the queue in advance if there may not be enough descriptors */
+ xlgmac_maybe_stop_tx_queue(channel, ring, XLGMAC_TX_MAX_DESC_NR);
+
+ return NETDEV_TX_OK;
+}
+
+static void xlgmac_get_stats64(struct net_device *netdev,
+ struct rtnl_link_stats64 *s)
+{
+ struct xlgmac_pdata *pdata = netdev_priv(netdev);
+ struct xlgmac_stats *pstats = &pdata->stats;
+
+ pdata->hw_ops.read_mmc_stats(pdata);
+
+ s->rx_packets = pstats->rxframecount_gb;
+ s->rx_bytes = pstats->rxoctetcount_gb;
+ s->rx_errors = pstats->rxframecount_gb -
+ pstats->rxbroadcastframes_g -
+ pstats->rxmulticastframes_g -
+ pstats->rxunicastframes_g;
+ s->multicast = pstats->rxmulticastframes_g;
+ s->rx_length_errors = pstats->rxlengtherror;
+ s->rx_crc_errors = pstats->rxcrcerror;
+ s->rx_fifo_errors = pstats->rxfifooverflow;
+
+ s->tx_packets = pstats->txframecount_gb;
+ s->tx_bytes = pstats->txoctetcount_gb;
+ s->tx_errors = pstats->txframecount_gb - pstats->txframecount_g;
+ s->tx_dropped = netdev->stats.tx_dropped;
+}
+
+static int xlgmac_set_mac_address(struct net_device *netdev, void *addr)
+{
+ struct xlgmac_pdata *pdata = netdev_priv(netdev);
+ struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+ struct sockaddr *saddr = addr;
+
+ if (!is_valid_ether_addr(saddr->sa_data))
+ return -EADDRNOTAVAIL;
+
+ memcpy(netdev->dev_addr, saddr->sa_data, netdev->addr_len);
+
+ hw_ops->set_mac_address(pdata, netdev->dev_addr);
+
+ return 0;
+}
+
+static int xlgmac_ioctl(struct net_device *netdev,
+ struct ifreq *ifreq, int cmd)
+{
+ if (!netif_running(netdev))
+ return -ENODEV;
+
+ return 0;
+}
+
+static int xlgmac_change_mtu(struct net_device *netdev, int mtu)
+{
+ struct xlgmac_pdata *pdata = netdev_priv(netdev);
+ int ret;
+
+ ret = xlgmac_calc_rx_buf_size(netdev, mtu);
+ if (ret < 0)
+ return ret;
+
+ pdata->rx_buf_size = ret;
+ netdev->mtu = mtu;
+
+ xlgmac_restart_dev(pdata);
+
+ return 0;
+}
+
+static int xlgmac_vlan_rx_add_vid(struct net_device *netdev,
+ __be16 proto,
+ u16 vid)
+{
+ struct xlgmac_pdata *pdata = netdev_priv(netdev);
+ struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+
+ set_bit(vid, pdata->active_vlans);
+ hw_ops->update_vlan_hash_table(pdata);
+
+ return 0;
+}
+
+static int xlgmac_vlan_rx_kill_vid(struct net_device *netdev,
+ __be16 proto,
+ u16 vid)
+{
+ struct xlgmac_pdata *pdata = netdev_priv(netdev);
+ struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+
+ clear_bit(vid, pdata->active_vlans);
+ hw_ops->update_vlan_hash_table(pdata);
+
+ return 0;
+}
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void xlgmac_poll_controller(struct net_device *netdev)
+{
+ struct xlgmac_pdata *pdata = netdev_priv(netdev);
+ struct xlgmac_channel *channel;
+ unsigned int i;
+
+ if (pdata->per_channel_irq) {
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++)
+ xlgmac_dma_isr(channel->dma_irq, channel);
+ } else {
+ disable_irq(pdata->dev_irq);
+ xlgmac_isr(pdata->dev_irq, pdata);
+ enable_irq(pdata->dev_irq);
+ }
+}
+#endif /* CONFIG_NET_POLL_CONTROLLER */
+
+static int xlgmac_set_features(struct net_device *netdev,
+ netdev_features_t features)
+{
+ netdev_features_t rxhash, rxcsum, rxvlan, rxvlan_filter;
+ struct xlgmac_pdata *pdata = netdev_priv(netdev);
+ struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+ int ret = 0;
+
+ rxhash = pdata->netdev_features & NETIF_F_RXHASH;
+ rxcsum = pdata->netdev_features & NETIF_F_RXCSUM;
+ rxvlan = pdata->netdev_features & NETIF_F_HW_VLAN_CTAG_RX;
+ rxvlan_filter = pdata->netdev_features & NETIF_F_HW_VLAN_CTAG_FILTER;
+
+ if ((features & NETIF_F_RXHASH) && !rxhash)
+ ret = hw_ops->enable_rss(pdata);
+ else if (!(features & NETIF_F_RXHASH) && rxhash)
+ ret = hw_ops->disable_rss(pdata);
+ if (ret)
+ return ret;
+
+ if ((features & NETIF_F_RXCSUM) && !rxcsum)
+ hw_ops->enable_rx_csum(pdata);
+ else if (!(features & NETIF_F_RXCSUM) && rxcsum)
+ hw_ops->disable_rx_csum(pdata);
+
+ if ((features & NETIF_F_HW_VLAN_CTAG_RX) && !rxvlan)
+ hw_ops->enable_rx_vlan_stripping(pdata);
+ else if (!(features & NETIF_F_HW_VLAN_CTAG_RX) && rxvlan)
+ hw_ops->disable_rx_vlan_stripping(pdata);
+
+ if ((features & NETIF_F_HW_VLAN_CTAG_FILTER) && !rxvlan_filter)
+ hw_ops->enable_rx_vlan_filtering(pdata);
+ else if (!(features & NETIF_F_HW_VLAN_CTAG_FILTER) && rxvlan_filter)
+ hw_ops->disable_rx_vlan_filtering(pdata);
+
+ pdata->netdev_features = features;
+
+ return 0;
+}
+
+static void xlgmac_set_rx_mode(struct net_device *netdev)
+{
+ struct xlgmac_pdata *pdata = netdev_priv(netdev);
+ struct xlgmac_hw_ops *hw_ops = &pdata->hw_ops;
+
+ hw_ops->config_rx_mode(pdata);
+}
+
+static const struct net_device_ops xlgmac_netdev_ops = {
+ .ndo_open = xlgmac_open,
+ .ndo_stop = xlgmac_close,
+ .ndo_start_xmit = xlgmac_xmit,
+ .ndo_tx_timeout = xlgmac_tx_timeout,
+ .ndo_get_stats64 = xlgmac_get_stats64,
+ .ndo_change_mtu = xlgmac_change_mtu,
+ .ndo_set_mac_address = xlgmac_set_mac_address,
+ .ndo_validate_addr = eth_validate_addr,
+ .ndo_do_ioctl = xlgmac_ioctl,
+ .ndo_vlan_rx_add_vid = xlgmac_vlan_rx_add_vid,
+ .ndo_vlan_rx_kill_vid = xlgmac_vlan_rx_kill_vid,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ .ndo_poll_controller = xlgmac_poll_controller,
+#endif
+ .ndo_set_features = xlgmac_set_features,
+ .ndo_set_rx_mode = xlgmac_set_rx_mode,
+};
+
+const struct net_device_ops *xlgmac_get_netdev_ops(void)
+{
+ return &xlgmac_netdev_ops;
+}
+
+static void xlgmac_rx_refresh(struct xlgmac_channel *channel)
+{
+ struct xlgmac_pdata *pdata = channel->pdata;
+ struct xlgmac_ring *ring = channel->rx_ring;
+ struct xlgmac_desc_data *desc_data;
+ struct xlgmac_desc_ops *desc_ops;
+ struct xlgmac_hw_ops *hw_ops;
+
+ desc_ops = &pdata->desc_ops;
+ hw_ops = &pdata->hw_ops;
+
+ while (ring->dirty != ring->cur) {
+ desc_data = XLGMAC_GET_DESC_DATA(ring, ring->dirty);
+
+ /* Reset desc_data values */
+ desc_ops->unmap_desc_data(pdata, desc_data);
+
+ if (desc_ops->map_rx_buffer(pdata, ring, desc_data))
+ break;
+
+ hw_ops->rx_desc_reset(pdata, desc_data, ring->dirty);
+
+ ring->dirty++;
+ }
+
+ /* Make sure everything is written before the register write */
+ wmb();
+
+ /* Update the Rx Tail Pointer Register with address of
+ * the last cleaned entry
+ */
+ desc_data = XLGMAC_GET_DESC_DATA(ring, ring->dirty - 1);
+ writel(lower_32_bits(desc_data->dma_desc_addr),
+ XLGMAC_DMA_REG(channel, DMA_CH_RDTR_LO));
+}
+
+static struct sk_buff *xlgmac_create_skb(struct xlgmac_pdata *pdata,
+ struct napi_struct *napi,
+ struct xlgmac_desc_data *desc_data,
+ unsigned int len)
+{
+ unsigned int copy_len;
+ struct sk_buff *skb;
+ u8 *packet;
+
+ skb = napi_alloc_skb(napi, desc_data->rx.hdr.dma_len);
+ if (!skb)
+ return NULL;
+
+ /* Start with the header buffer which may contain just the header
+ * or the header plus data
+ */
+ dma_sync_single_range_for_cpu(pdata->dev, desc_data->rx.hdr.dma_base,
+ desc_data->rx.hdr.dma_off,
+ desc_data->rx.hdr.dma_len,
+ DMA_FROM_DEVICE);
+
+ packet = page_address(desc_data->rx.hdr.pa.pages) +
+ desc_data->rx.hdr.pa.pages_offset;
+ copy_len = (desc_data->rx.hdr_len) ? desc_data->rx.hdr_len : len;
+ copy_len = min(desc_data->rx.hdr.dma_len, copy_len);
+ skb_copy_to_linear_data(skb, packet, copy_len);
+ skb_put(skb, copy_len);
+
+ len -= copy_len;
+ if (len) {
+ /* Add the remaining data as a frag */
+ dma_sync_single_range_for_cpu(pdata->dev,
+ desc_data->rx.buf.dma_base,
+ desc_data->rx.buf.dma_off,
+ desc_data->rx.buf.dma_len,
+ DMA_FROM_DEVICE);
+
+ skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+ desc_data->rx.buf.pa.pages,
+ desc_data->rx.buf.pa.pages_offset,
+ len, desc_data->rx.buf.dma_len);
+ desc_data->rx.buf.pa.pages = NULL;
+ }
+
+ return skb;
+}
+
+static int xlgmac_tx_poll(struct xlgmac_channel *channel)
+{
+ struct xlgmac_pdata *pdata = channel->pdata;
+ struct xlgmac_ring *ring = channel->tx_ring;
+ struct net_device *netdev = pdata->netdev;
+ unsigned int tx_packets = 0, tx_bytes = 0;
+ struct xlgmac_desc_data *desc_data;
+ struct xlgmac_dma_desc *dma_desc;
+ struct xlgmac_desc_ops *desc_ops;
+ struct xlgmac_hw_ops *hw_ops;
+ struct netdev_queue *txq;
+ int processed = 0;
+ unsigned int cur;
+
+ desc_ops = &pdata->desc_ops;
+ hw_ops = &pdata->hw_ops;
+
+ /* Nothing to do if there isn't a Tx ring for this channel */
+ if (!ring)
+ return 0;
+
+ cur = ring->cur;
+
+ /* Be sure we get ring->cur before accessing descriptor data */
+ smp_rmb();
+
+ txq = netdev_get_tx_queue(netdev, channel->queue_index);
+
+ while ((processed < XLGMAC_TX_DESC_MAX_PROC) &&
+ (ring->dirty != cur)) {
+ desc_data = XLGMAC_GET_DESC_DATA(ring, ring->dirty);
+ dma_desc = desc_data->dma_desc;
+
+ if (!hw_ops->tx_complete(dma_desc))
+ break;
+
+ /* Make sure descriptor fields are read after reading
+ * the OWN bit
+ */
+ dma_rmb();
+
+ if (netif_msg_tx_done(pdata))
+ xlgmac_dump_tx_desc(pdata, ring, ring->dirty, 1, 0);
+
+ if (hw_ops->is_last_desc(dma_desc)) {
+ tx_packets += desc_data->tx.packets;
+ tx_bytes += desc_data->tx.bytes;
+ }
+
+ /* Free the SKB and reset the descriptor for re-use */
+ desc_ops->unmap_desc_data(pdata, desc_data);
+ hw_ops->tx_desc_reset(desc_data);
+
+ processed++;
+ ring->dirty++;
+ }
+
+ if (!processed)
+ return 0;
+
+ netdev_tx_completed_queue(txq, tx_packets, tx_bytes);
+
+ if ((ring->tx.queue_stopped == 1) &&
+ (xlgmac_tx_avail_desc(ring) > XLGMAC_TX_DESC_MIN_FREE)) {
+ ring->tx.queue_stopped = 0;
+ netif_tx_wake_queue(txq);
+ }
+
+ XLGMAC_PR("processed=%d\n", processed);
+
+ return processed;
+}
+
+static int xlgmac_rx_poll(struct xlgmac_channel *channel, int budget)
+{
+ struct xlgmac_pdata *pdata = channel->pdata;
+ struct xlgmac_ring *ring = channel->rx_ring;
+ struct net_device *netdev = pdata->netdev;
+ unsigned int len, dma_desc_len, max_len;
+ unsigned int context_next, context;
+ struct xlgmac_desc_data *desc_data;
+ struct xlgmac_pkt_info *pkt_info;
+ unsigned int incomplete, error;
+ struct xlgmac_hw_ops *hw_ops;
+ unsigned int received = 0;
+ struct napi_struct *napi;
+ struct sk_buff *skb;
+ int packet_count = 0;
+
+ hw_ops = &pdata->hw_ops;
+
+ /* Nothing to do if there isn't a Rx ring for this channel */
+ if (!ring)
+ return 0;
+
+ incomplete = 0;
+ context_next = 0;
+
+ napi = (pdata->per_channel_irq) ? &channel->napi : &pdata->napi;
+
+ desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur);
+ pkt_info = &ring->pkt_info;
+ while (packet_count < budget) {
+ /* First time in loop see if we need to restore state */
+ if (!received && desc_data->state_saved) {
+ skb = desc_data->state.skb;
+ error = desc_data->state.error;
+ len = desc_data->state.len;
+ } else {
+ memset(pkt_info, 0, sizeof(*pkt_info));
+ skb = NULL;
+ error = 0;
+ len = 0;
+ }
+
+read_again:
+ desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur);
+
+ if (xlgmac_rx_dirty_desc(ring) > XLGMAC_RX_DESC_MAX_DIRTY)
+ xlgmac_rx_refresh(channel);
+
+ if (hw_ops->dev_read(channel))
+ break;
+
+ received++;
+ ring->cur++;
+
+ incomplete = XLGMAC_GET_REG_BITS(
+ pkt_info->attributes,
+ RX_PACKET_ATTRIBUTES_INCOMPLETE_POS,
+ RX_PACKET_ATTRIBUTES_INCOMPLETE_LEN);
+ context_next = XLGMAC_GET_REG_BITS(
+ pkt_info->attributes,
+ RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_POS,
+ RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_LEN);
+ context = XLGMAC_GET_REG_BITS(
+ pkt_info->attributes,
+ RX_PACKET_ATTRIBUTES_CONTEXT_POS,
+ RX_PACKET_ATTRIBUTES_CONTEXT_LEN);
+
+ /* Earlier error, just drain the remaining data */
+ if ((incomplete || context_next) && error)
+ goto read_again;
+
+ if (error || pkt_info->errors) {
+ if (pkt_info->errors)
+ netif_err(pdata, rx_err, netdev,
+ "error in received packet\n");
+ dev_kfree_skb(skb);
+ goto next_packet;
+ }
+
+ if (!context) {
+ /* Length is cumulative, get this descriptor's length */
+ dma_desc_len = desc_data->rx.len - len;
+ len += dma_desc_len;
+
+ if (dma_desc_len && !skb) {
+ skb = xlgmac_create_skb(pdata, napi, desc_data,
+ dma_desc_len);
+ if (!skb)
+ error = 1;
+ } else if (dma_desc_len) {
+ dma_sync_single_range_for_cpu(
+ pdata->dev,
+ desc_data->rx.buf.dma_base,
+ desc_data->rx.buf.dma_off,
+ desc_data->rx.buf.dma_len,
+ DMA_FROM_DEVICE);
+
+ skb_add_rx_frag(
+ skb, skb_shinfo(skb)->nr_frags,
+ desc_data->rx.buf.pa.pages,
+ desc_data->rx.buf.pa.pages_offset,
+ dma_desc_len,
+ desc_data->rx.buf.dma_len);
+ desc_data->rx.buf.pa.pages = NULL;
+ }
+ }
+
+ if (incomplete || context_next)
+ goto read_again;
+
+ if (!skb)
+ goto next_packet;
+
+ /* Be sure we don't exceed the configured MTU */
+ max_len = netdev->mtu + ETH_HLEN;
+ if (!(netdev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
+ (skb->protocol == htons(ETH_P_8021Q)))
+ max_len += VLAN_HLEN;
+
+ if (skb->len > max_len) {
+ netif_err(pdata, rx_err, netdev,
+ "packet length exceeds configured MTU\n");
+ dev_kfree_skb(skb);
+ goto next_packet;
+ }
+
+ if (netif_msg_pktdata(pdata))
+ xlgmac_print_pkt(netdev, skb, false);
+
+ skb_checksum_none_assert(skb);
+ if (XLGMAC_GET_REG_BITS(pkt_info->attributes,
+ RX_PACKET_ATTRIBUTES_CSUM_DONE_POS,
+ RX_PACKET_ATTRIBUTES_CSUM_DONE_LEN))
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+ if (XLGMAC_GET_REG_BITS(pkt_info->attributes,
+ RX_PACKET_ATTRIBUTES_VLAN_CTAG_POS,
+ RX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN))
+ __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+ pkt_info->vlan_ctag);
+
+ if (XLGMAC_GET_REG_BITS(pkt_info->attributes,
+ RX_PACKET_ATTRIBUTES_RSS_HASH_POS,
+ RX_PACKET_ATTRIBUTES_RSS_HASH_LEN))
+ skb_set_hash(skb, pkt_info->rss_hash,
+ pkt_info->rss_hash_type);
+
+ skb->dev = netdev;
+ skb->protocol = eth_type_trans(skb, netdev);
+ skb_record_rx_queue(skb, channel->queue_index);
+
+ napi_gro_receive(napi, skb);
+
+next_packet:
+ packet_count++;
+ }
+
+ /* Check if we need to save state before leaving */
+ if (received && (incomplete || context_next)) {
+ desc_data = XLGMAC_GET_DESC_DATA(ring, ring->cur);
+ desc_data->state_saved = 1;
+ desc_data->state.skb = skb;
+ desc_data->state.len = len;
+ desc_data->state.error = error;
+ }
+
+ XLGMAC_PR("packet_count = %d\n", packet_count);
+
+ return packet_count;
+}
+
+static int xlgmac_one_poll(struct napi_struct *napi, int budget)
+{
+ struct xlgmac_channel *channel = container_of(napi,
+ struct xlgmac_channel,
+ napi);
+ int processed = 0;
+
+ XLGMAC_PR("budget=%d\n", budget);
+
+ /* Cleanup Tx ring first */
+ xlgmac_tx_poll(channel);
+
+ /* Process Rx ring next */
+ processed = xlgmac_rx_poll(channel, budget);
+
+ /* If we processed everything, we are done */
+ if (processed < budget) {
+ /* Turn off polling */
+ napi_complete_done(napi, processed);
+
+ /* Enable Tx and Rx interrupts */
+ enable_irq(channel->dma_irq);
+ }
+
+ XLGMAC_PR("received = %d\n", processed);
+
+ return processed;
+}
+
+static int xlgmac_all_poll(struct napi_struct *napi, int budget)
+{
+ struct xlgmac_pdata *pdata = container_of(napi,
+ struct xlgmac_pdata,
+ napi);
+ struct xlgmac_channel *channel;
+ int processed, last_processed;
+ int ring_budget;
+ unsigned int i;
+
+ XLGMAC_PR("budget=%d\n", budget);
+
+ processed = 0;
+ ring_budget = budget / pdata->rx_ring_count;
+ do {
+ last_processed = processed;
+
+ channel = pdata->channel_head;
+ for (i = 0; i < pdata->channel_count; i++, channel++) {
+ /* Cleanup Tx ring first */
+ xlgmac_tx_poll(channel);
+
+ /* Process Rx ring next */
+ if (ring_budget > (budget - processed))
+ ring_budget = budget - processed;
+ processed += xlgmac_rx_poll(channel, ring_budget);
+ }
+ } while ((processed < budget) && (processed != last_processed));
+
+ /* If we processed everything, we are done */
+ if (processed < budget) {
+ /* Turn off polling */
+ napi_complete_done(napi, processed);
+
+ /* Enable Tx and Rx interrupts */
+ xlgmac_enable_rx_tx_ints(pdata);
+ }
+
+ XLGMAC_PR("received = %d\n", processed);
+
+ return processed;
+}
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c
new file mode 100644
index 0000000..386bafe
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c
@@ -0,0 +1,78 @@
+/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver
+ *
+ * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is dual-licensed; you may select either version 2 of
+ * the GNU General Public License ("GPL") or BSD license ("BSD").
+ *
+ * This Synopsys DWC XLGMAC software driver and associated documentation
+ * (hereinafter the "Software") is an unsupported proprietary work of
+ * Synopsys, Inc. unless otherwise expressly agreed to in writing between
+ * Synopsys and you. The Software IS NOT an item of Licensed Software or a
+ * Licensed Product under any End User Software License Agreement or
+ * Agreement for Licensed Products with Synopsys or any supplement thereto.
+ * Synopsys is a registered trademark of Synopsys, Inc. Other names included
+ * in the SOFTWARE may be the trademarks of their respective owners.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+
+#include "dwc-xlgmac.h"
+#include "dwc-xlgmac-reg.h"
+
+static int xlgmac_probe(struct pci_dev *pcidev, const struct pci_device_id *id)
+{
+ struct device *dev = &pcidev->dev;
+ struct xlgmac_resources res;
+ int i, ret;
+
+ ret = pcim_enable_device(pcidev);
+ if (ret) {
+ dev_err(dev, "ERROR: failed to enable device\n");
+ return ret;
+ }
+
+ for (i = 0; i <= PCI_STD_RESOURCE_END; i++) {
+ if (pci_resource_len(pcidev, i) == 0)
+ continue;
+ ret = pcim_iomap_regions(pcidev, BIT(i), XLGMAC_DRV_NAME);
+ if (ret)
+ return ret;
+ break;
+ }
+
+ pci_set_master(pcidev);
+
+ memset(&res, 0, sizeof(res));
+ res.irq = pcidev->irq;
+ res.addr = pcim_iomap_table(pcidev)[i];
+
+ return xlgmac_drv_probe(&pcidev->dev, &res);
+}
+
+static void xlgmac_remove(struct pci_dev *pcidev)
+{
+ xlgmac_drv_remove(&pcidev->dev);
+}
+
+static const struct pci_device_id xlgmac_pci_tbl[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_SYNOPSYS, 0x7302) },
+ { 0 }
+};
+MODULE_DEVICE_TABLE(pci, xlgmac_pci_tbl);
+
+static struct pci_driver xlgmac_pci_driver = {
+ .name = XLGMAC_DRV_NAME,
+ .id_table = xlgmac_pci_tbl,
+ .probe = xlgmac_probe,
+ .remove = xlgmac_remove,
+};
+
+module_pci_driver(xlgmac_pci_driver);
+
+MODULE_DESCRIPTION(XLGMAC_DRV_DESC);
+MODULE_VERSION(XLGMAC_DRV_VERSION);
+MODULE_AUTHOR("Jie Deng <jiedeng@synopsys.com>");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-reg.h b/drivers/net/ethernet/synopsys/dwc-xlgmac-reg.h
new file mode 100644
index 0000000..3754f22
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-reg.h
@@ -0,0 +1,744 @@
+/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver
+ *
+ * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is dual-licensed; you may select either version 2 of
+ * the GNU General Public License ("GPL") or BSD license ("BSD").
+ *
+ * This Synopsys DWC XLGMAC software driver and associated documentation
+ * (hereinafter the "Software") is an unsupported proprietary work of
+ * Synopsys, Inc. unless otherwise expressly agreed to in writing between
+ * Synopsys and you. The Software IS NOT an item of Licensed Software or a
+ * Licensed Product under any End User Software License Agreement or
+ * Agreement for Licensed Products with Synopsys or any supplement thereto.
+ * Synopsys is a registered trademark of Synopsys, Inc. Other names included
+ * in the SOFTWARE may be the trademarks of their respective owners.
+ */
+
+#ifndef __DWC_XLGMAC_REG_H__
+#define __DWC_XLGMAC_REG_H__
+
+/* MAC register offsets */
+#define MAC_TCR 0x0000
+#define MAC_RCR 0x0004
+#define MAC_PFR 0x0008
+#define MAC_HTR0 0x0010
+#define MAC_VLANTR 0x0050
+#define MAC_VLANHTR 0x0058
+#define MAC_VLANIR 0x0060
+#define MAC_Q0TFCR 0x0070
+#define MAC_RFCR 0x0090
+#define MAC_RQC0R 0x00a0
+#define MAC_RQC1R 0x00a4
+#define MAC_RQC2R 0x00a8
+#define MAC_RQC3R 0x00ac
+#define MAC_ISR 0x00b0
+#define MAC_IER 0x00b4
+#define MAC_VR 0x0110
+#define MAC_HWF0R 0x011c
+#define MAC_HWF1R 0x0120
+#define MAC_HWF2R 0x0124
+#define MAC_MACA0HR 0x0300
+#define MAC_MACA0LR 0x0304
+#define MAC_MACA1HR 0x0308
+#define MAC_MACA1LR 0x030c
+#define MAC_RSSCR 0x0c80
+#define MAC_RSSAR 0x0c88
+#define MAC_RSSDR 0x0c8c
+
+#define MAC_QTFCR_INC 4
+#define MAC_MACA_INC 4
+#define MAC_HTR_INC 4
+#define MAC_RQC2_INC 4
+#define MAC_RQC2_Q_PER_REG 4
+
+/* MAC register entry bit positions and sizes */
+#define MAC_HWF0R_ADDMACADRSEL_POS 18
+#define MAC_HWF0R_ADDMACADRSEL_LEN 5
+#define MAC_HWF0R_ARPOFFSEL_POS 9
+#define MAC_HWF0R_ARPOFFSEL_LEN 1
+#define MAC_HWF0R_EEESEL_POS 13
+#define MAC_HWF0R_EEESEL_LEN 1
+#define MAC_HWF0R_PHYIFSEL_POS 1
+#define MAC_HWF0R_PHYIFSEL_LEN 2
+#define MAC_HWF0R_MGKSEL_POS 7
+#define MAC_HWF0R_MGKSEL_LEN 1
+#define MAC_HWF0R_MMCSEL_POS 8
+#define MAC_HWF0R_MMCSEL_LEN 1
+#define MAC_HWF0R_RWKSEL_POS 6
+#define MAC_HWF0R_RWKSEL_LEN 1
+#define MAC_HWF0R_RXCOESEL_POS 16
+#define MAC_HWF0R_RXCOESEL_LEN 1
+#define MAC_HWF0R_SAVLANINS_POS 27
+#define MAC_HWF0R_SAVLANINS_LEN 1
+#define MAC_HWF0R_SMASEL_POS 5
+#define MAC_HWF0R_SMASEL_LEN 1
+#define MAC_HWF0R_TSSEL_POS 12
+#define MAC_HWF0R_TSSEL_LEN 1
+#define MAC_HWF0R_TSSTSSEL_POS 25
+#define MAC_HWF0R_TSSTSSEL_LEN 2
+#define MAC_HWF0R_TXCOESEL_POS 14
+#define MAC_HWF0R_TXCOESEL_LEN 1
+#define MAC_HWF0R_VLHASH_POS 4
+#define MAC_HWF0R_VLHASH_LEN 1
+#define MAC_HWF1R_ADDR64_POS 14
+#define MAC_HWF1R_ADDR64_LEN 2
+#define MAC_HWF1R_ADVTHWORD_POS 13
+#define MAC_HWF1R_ADVTHWORD_LEN 1
+#define MAC_HWF1R_DBGMEMA_POS 19
+#define MAC_HWF1R_DBGMEMA_LEN 1
+#define MAC_HWF1R_DCBEN_POS 16
+#define MAC_HWF1R_DCBEN_LEN 1
+#define MAC_HWF1R_HASHTBLSZ_POS 24
+#define MAC_HWF1R_HASHTBLSZ_LEN 3
+#define MAC_HWF1R_L3L4FNUM_POS 27
+#define MAC_HWF1R_L3L4FNUM_LEN 4
+#define MAC_HWF1R_NUMTC_POS 21
+#define MAC_HWF1R_NUMTC_LEN 3
+#define MAC_HWF1R_RSSEN_POS 20
+#define MAC_HWF1R_RSSEN_LEN 1
+#define MAC_HWF1R_RXFIFOSIZE_POS 0
+#define MAC_HWF1R_RXFIFOSIZE_LEN 5
+#define MAC_HWF1R_SPHEN_POS 17
+#define MAC_HWF1R_SPHEN_LEN 1
+#define MAC_HWF1R_TSOEN_POS 18
+#define MAC_HWF1R_TSOEN_LEN 1
+#define MAC_HWF1R_TXFIFOSIZE_POS 6
+#define MAC_HWF1R_TXFIFOSIZE_LEN 5
+#define MAC_HWF2R_AUXSNAPNUM_POS 28
+#define MAC_HWF2R_AUXSNAPNUM_LEN 3
+#define MAC_HWF2R_PPSOUTNUM_POS 24
+#define MAC_HWF2R_PPSOUTNUM_LEN 3
+#define MAC_HWF2R_RXCHCNT_POS 12
+#define MAC_HWF2R_RXCHCNT_LEN 4
+#define MAC_HWF2R_RXQCNT_POS 0
+#define MAC_HWF2R_RXQCNT_LEN 4
+#define MAC_HWF2R_TXCHCNT_POS 18
+#define MAC_HWF2R_TXCHCNT_LEN 4
+#define MAC_HWF2R_TXQCNT_POS 6
+#define MAC_HWF2R_TXQCNT_LEN 4
+#define MAC_IER_TSIE_POS 12
+#define MAC_IER_TSIE_LEN 1
+#define MAC_ISR_MMCRXIS_POS 9
+#define MAC_ISR_MMCRXIS_LEN 1
+#define MAC_ISR_MMCTXIS_POS 10
+#define MAC_ISR_MMCTXIS_LEN 1
+#define MAC_ISR_PMTIS_POS 4
+#define MAC_ISR_PMTIS_LEN 1
+#define MAC_ISR_TSIS_POS 12
+#define MAC_ISR_TSIS_LEN 1
+#define MAC_MACA1HR_AE_POS 31
+#define MAC_MACA1HR_AE_LEN 1
+#define MAC_PFR_HMC_POS 2
+#define MAC_PFR_HMC_LEN 1
+#define MAC_PFR_HPF_POS 10
+#define MAC_PFR_HPF_LEN 1
+#define MAC_PFR_HUC_POS 1
+#define MAC_PFR_HUC_LEN 1
+#define MAC_PFR_PM_POS 4
+#define MAC_PFR_PM_LEN 1
+#define MAC_PFR_PR_POS 0
+#define MAC_PFR_PR_LEN 1
+#define MAC_PFR_VTFE_POS 16
+#define MAC_PFR_VTFE_LEN 1
+#define MAC_Q0TFCR_PT_POS 16
+#define MAC_Q0TFCR_PT_LEN 16
+#define MAC_Q0TFCR_TFE_POS 1
+#define MAC_Q0TFCR_TFE_LEN 1
+#define MAC_RCR_ACS_POS 1
+#define MAC_RCR_ACS_LEN 1
+#define MAC_RCR_CST_POS 2
+#define MAC_RCR_CST_LEN 1
+#define MAC_RCR_DCRCC_POS 3
+#define MAC_RCR_DCRCC_LEN 1
+#define MAC_RCR_HDSMS_POS 12
+#define MAC_RCR_HDSMS_LEN 3
+#define MAC_RCR_IPC_POS 9
+#define MAC_RCR_IPC_LEN 1
+#define MAC_RCR_JE_POS 8
+#define MAC_RCR_JE_LEN 1
+#define MAC_RCR_LM_POS 10
+#define MAC_RCR_LM_LEN 1
+#define MAC_RCR_RE_POS 0
+#define MAC_RCR_RE_LEN 1
+#define MAC_RFCR_PFCE_POS 8
+#define MAC_RFCR_PFCE_LEN 1
+#define MAC_RFCR_RFE_POS 0
+#define MAC_RFCR_RFE_LEN 1
+#define MAC_RFCR_UP_POS 1
+#define MAC_RFCR_UP_LEN 1
+#define MAC_RQC0R_RXQ0EN_POS 0
+#define MAC_RQC0R_RXQ0EN_LEN 2
+#define MAC_RSSAR_ADDRT_POS 2
+#define MAC_RSSAR_ADDRT_LEN 1
+#define MAC_RSSAR_CT_POS 1
+#define MAC_RSSAR_CT_LEN 1
+#define MAC_RSSAR_OB_POS 0
+#define MAC_RSSAR_OB_LEN 1
+#define MAC_RSSAR_RSSIA_POS 8
+#define MAC_RSSAR_RSSIA_LEN 8
+#define MAC_RSSCR_IP2TE_POS 1
+#define MAC_RSSCR_IP2TE_LEN 1
+#define MAC_RSSCR_RSSE_POS 0
+#define MAC_RSSCR_RSSE_LEN 1
+#define MAC_RSSCR_TCP4TE_POS 2
+#define MAC_RSSCR_TCP4TE_LEN 1
+#define MAC_RSSCR_UDP4TE_POS 3
+#define MAC_RSSCR_UDP4TE_LEN 1
+#define MAC_RSSDR_DMCH_POS 0
+#define MAC_RSSDR_DMCH_LEN 4
+#define MAC_TCR_SS_POS 28
+#define MAC_TCR_SS_LEN 3
+#define MAC_TCR_TE_POS 0
+#define MAC_TCR_TE_LEN 1
+#define MAC_VLANHTR_VLHT_POS 0
+#define MAC_VLANHTR_VLHT_LEN 16
+#define MAC_VLANIR_VLTI_POS 20
+#define MAC_VLANIR_VLTI_LEN 1
+#define MAC_VLANIR_CSVL_POS 19
+#define MAC_VLANIR_CSVL_LEN 1
+#define MAC_VLANTR_DOVLTC_POS 20
+#define MAC_VLANTR_DOVLTC_LEN 1
+#define MAC_VLANTR_ERSVLM_POS 19
+#define MAC_VLANTR_ERSVLM_LEN 1
+#define MAC_VLANTR_ESVL_POS 18
+#define MAC_VLANTR_ESVL_LEN 1
+#define MAC_VLANTR_ETV_POS 16
+#define MAC_VLANTR_ETV_LEN 1
+#define MAC_VLANTR_EVLS_POS 21
+#define MAC_VLANTR_EVLS_LEN 2
+#define MAC_VLANTR_EVLRXS_POS 24
+#define MAC_VLANTR_EVLRXS_LEN 1
+#define MAC_VLANTR_VL_POS 0
+#define MAC_VLANTR_VL_LEN 16
+#define MAC_VLANTR_VTHM_POS 25
+#define MAC_VLANTR_VTHM_LEN 1
+#define MAC_VLANTR_VTIM_POS 17
+#define MAC_VLANTR_VTIM_LEN 1
+#define MAC_VR_DEVID_POS 8
+#define MAC_VR_DEVID_LEN 8
+#define MAC_VR_SNPSVER_POS 0
+#define MAC_VR_SNPSVER_LEN 8
+#define MAC_VR_USERVER_POS 16
+#define MAC_VR_USERVER_LEN 8
+
+/* MMC register offsets */
+#define MMC_CR 0x0800
+#define MMC_RISR 0x0804
+#define MMC_TISR 0x0808
+#define MMC_RIER 0x080c
+#define MMC_TIER 0x0810
+#define MMC_TXOCTETCOUNT_GB_LO 0x0814
+#define MMC_TXFRAMECOUNT_GB_LO 0x081c
+#define MMC_TXBROADCASTFRAMES_G_LO 0x0824
+#define MMC_TXMULTICASTFRAMES_G_LO 0x082c
+#define MMC_TX64OCTETS_GB_LO 0x0834
+#define MMC_TX65TO127OCTETS_GB_LO 0x083c
+#define MMC_TX128TO255OCTETS_GB_LO 0x0844
+#define MMC_TX256TO511OCTETS_GB_LO 0x084c
+#define MMC_TX512TO1023OCTETS_GB_LO 0x0854
+#define MMC_TX1024TOMAXOCTETS_GB_LO 0x085c
+#define MMC_TXUNICASTFRAMES_GB_LO 0x0864
+#define MMC_TXMULTICASTFRAMES_GB_LO 0x086c
+#define MMC_TXBROADCASTFRAMES_GB_LO 0x0874
+#define MMC_TXUNDERFLOWERROR_LO 0x087c
+#define MMC_TXOCTETCOUNT_G_LO 0x0884
+#define MMC_TXFRAMECOUNT_G_LO 0x088c
+#define MMC_TXPAUSEFRAMES_LO 0x0894
+#define MMC_TXVLANFRAMES_G_LO 0x089c
+#define MMC_RXFRAMECOUNT_GB_LO 0x0900
+#define MMC_RXOCTETCOUNT_GB_LO 0x0908
+#define MMC_RXOCTETCOUNT_G_LO 0x0910
+#define MMC_RXBROADCASTFRAMES_G_LO 0x0918
+#define MMC_RXMULTICASTFRAMES_G_LO 0x0920
+#define MMC_RXCRCERROR_LO 0x0928
+#define MMC_RXRUNTERROR 0x0930
+#define MMC_RXJABBERERROR 0x0934
+#define MMC_RXUNDERSIZE_G 0x0938
+#define MMC_RXOVERSIZE_G 0x093c
+#define MMC_RX64OCTETS_GB_LO 0x0940
+#define MMC_RX65TO127OCTETS_GB_LO 0x0948
+#define MMC_RX128TO255OCTETS_GB_LO 0x0950
+#define MMC_RX256TO511OCTETS_GB_LO 0x0958
+#define MMC_RX512TO1023OCTETS_GB_LO 0x0960
+#define MMC_RX1024TOMAXOCTETS_GB_LO 0x0968
+#define MMC_RXUNICASTFRAMES_G_LO 0x0970
+#define MMC_RXLENGTHERROR_LO 0x0978
+#define MMC_RXOUTOFRANGETYPE_LO 0x0980
+#define MMC_RXPAUSEFRAMES_LO 0x0988
+#define MMC_RXFIFOOVERFLOW_LO 0x0990
+#define MMC_RXVLANFRAMES_GB_LO 0x0998
+#define MMC_RXWATCHDOGERROR 0x09a0
+
+/* MMC register entry bit positions and sizes */
+#define MMC_CR_CR_POS 0
+#define MMC_CR_CR_LEN 1
+#define MMC_CR_CSR_POS 1
+#define MMC_CR_CSR_LEN 1
+#define MMC_CR_ROR_POS 2
+#define MMC_CR_ROR_LEN 1
+#define MMC_CR_MCF_POS 3
+#define MMC_CR_MCF_LEN 1
+#define MMC_CR_MCT_POS 4
+#define MMC_CR_MCT_LEN 2
+#define MMC_RIER_ALL_INTERRUPTS_POS 0
+#define MMC_RIER_ALL_INTERRUPTS_LEN 23
+#define MMC_RISR_RXFRAMECOUNT_GB_POS 0
+#define MMC_RISR_RXFRAMECOUNT_GB_LEN 1
+#define MMC_RISR_RXOCTETCOUNT_GB_POS 1
+#define MMC_RISR_RXOCTETCOUNT_GB_LEN 1
+#define MMC_RISR_RXOCTETCOUNT_G_POS 2
+#define MMC_RISR_RXOCTETCOUNT_G_LEN 1
+#define MMC_RISR_RXBROADCASTFRAMES_G_POS 3
+#define MMC_RISR_RXBROADCASTFRAMES_G_LEN 1
+#define MMC_RISR_RXMULTICASTFRAMES_G_POS 4
+#define MMC_RISR_RXMULTICASTFRAMES_G_LEN 1
+#define MMC_RISR_RXCRCERROR_POS 5
+#define MMC_RISR_RXCRCERROR_LEN 1
+#define MMC_RISR_RXRUNTERROR_POS 6
+#define MMC_RISR_RXRUNTERROR_LEN 1
+#define MMC_RISR_RXJABBERERROR_POS 7
+#define MMC_RISR_RXJABBERERROR_LEN 1
+#define MMC_RISR_RXUNDERSIZE_G_POS 8
+#define MMC_RISR_RXUNDERSIZE_G_LEN 1
+#define MMC_RISR_RXOVERSIZE_G_POS 9
+#define MMC_RISR_RXOVERSIZE_G_LEN 1
+#define MMC_RISR_RX64OCTETS_GB_POS 10
+#define MMC_RISR_RX64OCTETS_GB_LEN 1
+#define MMC_RISR_RX65TO127OCTETS_GB_POS 11
+#define MMC_RISR_RX65TO127OCTETS_GB_LEN 1
+#define MMC_RISR_RX128TO255OCTETS_GB_POS 12
+#define MMC_RISR_RX128TO255OCTETS_GB_LEN 1
+#define MMC_RISR_RX256TO511OCTETS_GB_POS 13
+#define MMC_RISR_RX256TO511OCTETS_GB_LEN 1
+#define MMC_RISR_RX512TO1023OCTETS_GB_POS 14
+#define MMC_RISR_RX512TO1023OCTETS_GB_LEN 1
+#define MMC_RISR_RX1024TOMAXOCTETS_GB_POS 15
+#define MMC_RISR_RX1024TOMAXOCTETS_GB_LEN 1
+#define MMC_RISR_RXUNICASTFRAMES_G_POS 16
+#define MMC_RISR_RXUNICASTFRAMES_G_LEN 1
+#define MMC_RISR_RXLENGTHERROR_POS 17
+#define MMC_RISR_RXLENGTHERROR_LEN 1
+#define MMC_RISR_RXOUTOFRANGETYPE_POS 18
+#define MMC_RISR_RXOUTOFRANGETYPE_LEN 1
+#define MMC_RISR_RXPAUSEFRAMES_POS 19
+#define MMC_RISR_RXPAUSEFRAMES_LEN 1
+#define MMC_RISR_RXFIFOOVERFLOW_POS 20
+#define MMC_RISR_RXFIFOOVERFLOW_LEN 1
+#define MMC_RISR_RXVLANFRAMES_GB_POS 21
+#define MMC_RISR_RXVLANFRAMES_GB_LEN 1
+#define MMC_RISR_RXWATCHDOGERROR_POS 22
+#define MMC_RISR_RXWATCHDOGERROR_LEN 1
+#define MMC_TIER_ALL_INTERRUPTS_POS 0
+#define MMC_TIER_ALL_INTERRUPTS_LEN 18
+#define MMC_TISR_TXOCTETCOUNT_GB_POS 0
+#define MMC_TISR_TXOCTETCOUNT_GB_LEN 1
+#define MMC_TISR_TXFRAMECOUNT_GB_POS 1
+#define MMC_TISR_TXFRAMECOUNT_GB_LEN 1
+#define MMC_TISR_TXBROADCASTFRAMES_G_POS 2
+#define MMC_TISR_TXBROADCASTFRAMES_G_LEN 1
+#define MMC_TISR_TXMULTICASTFRAMES_G_POS 3
+#define MMC_TISR_TXMULTICASTFRAMES_G_LEN 1
+#define MMC_TISR_TX64OCTETS_GB_POS 4
+#define MMC_TISR_TX64OCTETS_GB_LEN 1
+#define MMC_TISR_TX65TO127OCTETS_GB_POS 5
+#define MMC_TISR_TX65TO127OCTETS_GB_LEN 1
+#define MMC_TISR_TX128TO255OCTETS_GB_POS 6
+#define MMC_TISR_TX128TO255OCTETS_GB_LEN 1
+#define MMC_TISR_TX256TO511OCTETS_GB_POS 7
+#define MMC_TISR_TX256TO511OCTETS_GB_LEN 1
+#define MMC_TISR_TX512TO1023OCTETS_GB_POS 8
+#define MMC_TISR_TX512TO1023OCTETS_GB_LEN 1
+#define MMC_TISR_TX1024TOMAXOCTETS_GB_POS 9
+#define MMC_TISR_TX1024TOMAXOCTETS_GB_LEN 1
+#define MMC_TISR_TXUNICASTFRAMES_GB_POS 10
+#define MMC_TISR_TXUNICASTFRAMES_GB_LEN 1
+#define MMC_TISR_TXMULTICASTFRAMES_GB_POS 11
+#define MMC_TISR_TXMULTICASTFRAMES_GB_LEN 1
+#define MMC_TISR_TXBROADCASTFRAMES_GB_POS 12
+#define MMC_TISR_TXBROADCASTFRAMES_GB_LEN 1
+#define MMC_TISR_TXUNDERFLOWERROR_POS 13
+#define MMC_TISR_TXUNDERFLOWERROR_LEN 1
+#define MMC_TISR_TXOCTETCOUNT_G_POS 14
+#define MMC_TISR_TXOCTETCOUNT_G_LEN 1
+#define MMC_TISR_TXFRAMECOUNT_G_POS 15
+#define MMC_TISR_TXFRAMECOUNT_G_LEN 1
+#define MMC_TISR_TXPAUSEFRAMES_POS 16
+#define MMC_TISR_TXPAUSEFRAMES_LEN 1
+#define MMC_TISR_TXVLANFRAMES_G_POS 17
+#define MMC_TISR_TXVLANFRAMES_G_LEN 1
+
+/* MTL register offsets */
+#define MTL_OMR 0x1000
+#define MTL_FDDR 0x1010
+#define MTL_RQDCM0R 0x1030
+
+#define MTL_RQDCM_INC 4
+#define MTL_RQDCM_Q_PER_REG 4
+
+/* MTL register entry bit positions and sizes */
+#define MTL_OMR_ETSALG_POS 5
+#define MTL_OMR_ETSALG_LEN 2
+#define MTL_OMR_RAA_POS 2
+#define MTL_OMR_RAA_LEN 1
+
+/* MTL queue register offsets
+ * Multiple queues can be active. The first queue has registers
+ * that begin at 0x1100. Each subsequent queue has registers that
+ * are accessed using an offset of 0x80 from the previous queue.
+ */
+#define MTL_Q_BASE 0x1100
+#define MTL_Q_INC 0x80
+
+#define MTL_Q_TQOMR 0x00
+#define MTL_Q_RQOMR 0x40
+#define MTL_Q_RQDR 0x48
+#define MTL_Q_RQFCR 0x50
+#define MTL_Q_IER 0x70
+#define MTL_Q_ISR 0x74
+
+/* MTL queue register entry bit positions and sizes */
+#define MTL_Q_RQDR_PRXQ_POS 16
+#define MTL_Q_RQDR_PRXQ_LEN 14
+#define MTL_Q_RQDR_RXQSTS_POS 4
+#define MTL_Q_RQDR_RXQSTS_LEN 2
+#define MTL_Q_RQFCR_RFA_POS 1
+#define MTL_Q_RQFCR_RFA_LEN 6
+#define MTL_Q_RQFCR_RFD_POS 17
+#define MTL_Q_RQFCR_RFD_LEN 6
+#define MTL_Q_RQOMR_EHFC_POS 7
+#define MTL_Q_RQOMR_EHFC_LEN 1
+#define MTL_Q_RQOMR_RQS_POS 16
+#define MTL_Q_RQOMR_RQS_LEN 9
+#define MTL_Q_RQOMR_RSF_POS 5
+#define MTL_Q_RQOMR_RSF_LEN 1
+#define MTL_Q_RQOMR_FEP_POS 4
+#define MTL_Q_RQOMR_FEP_LEN 1
+#define MTL_Q_RQOMR_FUP_POS 3
+#define MTL_Q_RQOMR_FUP_LEN 1
+#define MTL_Q_RQOMR_RTC_POS 0
+#define MTL_Q_RQOMR_RTC_LEN 2
+#define MTL_Q_TQOMR_FTQ_POS 0
+#define MTL_Q_TQOMR_FTQ_LEN 1
+#define MTL_Q_TQOMR_Q2TCMAP_POS 8
+#define MTL_Q_TQOMR_Q2TCMAP_LEN 3
+#define MTL_Q_TQOMR_TQS_POS 16
+#define MTL_Q_TQOMR_TQS_LEN 10
+#define MTL_Q_TQOMR_TSF_POS 1
+#define MTL_Q_TQOMR_TSF_LEN 1
+#define MTL_Q_TQOMR_TTC_POS 4
+#define MTL_Q_TQOMR_TTC_LEN 3
+#define MTL_Q_TQOMR_TXQEN_POS 2
+#define MTL_Q_TQOMR_TXQEN_LEN 2
+
+/* MTL queue register value */
+#define MTL_RSF_DISABLE 0x00
+#define MTL_RSF_ENABLE 0x01
+#define MTL_TSF_DISABLE 0x00
+#define MTL_TSF_ENABLE 0x01
+
+#define MTL_RX_THRESHOLD_64 0x00
+#define MTL_RX_THRESHOLD_96 0x02
+#define MTL_RX_THRESHOLD_128 0x03
+#define MTL_TX_THRESHOLD_64 0x00
+#define MTL_TX_THRESHOLD_96 0x02
+#define MTL_TX_THRESHOLD_128 0x03
+#define MTL_TX_THRESHOLD_192 0x04
+#define MTL_TX_THRESHOLD_256 0x05
+#define MTL_TX_THRESHOLD_384 0x06
+#define MTL_TX_THRESHOLD_512 0x07
+
+#define MTL_ETSALG_WRR 0x00
+#define MTL_ETSALG_WFQ 0x01
+#define MTL_ETSALG_DWRR 0x02
+#define MTL_RAA_SP 0x00
+#define MTL_RAA_WSP 0x01
+
+#define MTL_Q_DISABLED 0x00
+#define MTL_Q_ENABLED 0x02
+
+#define MTL_RQDCM0R_Q0MDMACH 0x0
+#define MTL_RQDCM0R_Q1MDMACH 0x00000100
+#define MTL_RQDCM0R_Q2MDMACH 0x00020000
+#define MTL_RQDCM0R_Q3MDMACH 0x03000000
+#define MTL_RQDCM1R_Q4MDMACH 0x00000004
+#define MTL_RQDCM1R_Q5MDMACH 0x00000500
+#define MTL_RQDCM1R_Q6MDMACH 0x00060000
+#define MTL_RQDCM1R_Q7MDMACH 0x07000000
+#define MTL_RQDCM2R_Q8MDMACH 0x00000008
+#define MTL_RQDCM2R_Q9MDMACH 0x00000900
+#define MTL_RQDCM2R_Q10MDMACH 0x000A0000
+#define MTL_RQDCM2R_Q11MDMACH 0x0B000000
+
+/* MTL traffic class register offsets
+ * Multiple traffic classes can be active. The first class has registers
+ * that begin at 0x1100. Each subsequent queue has registers that
+ * are accessed using an offset of 0x80 from the previous queue.
+ */
+#define MTL_TC_BASE MTL_Q_BASE
+#define MTL_TC_INC MTL_Q_INC
+
+#define MTL_TC_ETSCR 0x10
+#define MTL_TC_ETSSR 0x14
+#define MTL_TC_QWR 0x18
+
+/* MTL traffic class register entry bit positions and sizes */
+#define MTL_TC_ETSCR_TSA_POS 0
+#define MTL_TC_ETSCR_TSA_LEN 2
+#define MTL_TC_QWR_QW_POS 0
+#define MTL_TC_QWR_QW_LEN 21
+
+/* MTL traffic class register value */
+#define MTL_TSA_SP 0x00
+#define MTL_TSA_ETS 0x02
+
+/* DMA register offsets */
+#define DMA_MR 0x3000
+#define DMA_SBMR 0x3004
+#define DMA_ISR 0x3008
+#define DMA_DSR0 0x3020
+#define DMA_DSR1 0x3024
+
+/* DMA register entry bit positions and sizes */
+#define DMA_ISR_MACIS_POS 17
+#define DMA_ISR_MACIS_LEN 1
+#define DMA_ISR_MTLIS_POS 16
+#define DMA_ISR_MTLIS_LEN 1
+#define DMA_MR_SWR_POS 0
+#define DMA_MR_SWR_LEN 1
+#define DMA_SBMR_EAME_POS 11
+#define DMA_SBMR_EAME_LEN 1
+#define DMA_SBMR_BLEN_64_POS 5
+#define DMA_SBMR_BLEN_64_LEN 1
+#define DMA_SBMR_BLEN_128_POS 6
+#define DMA_SBMR_BLEN_128_LEN 1
+#define DMA_SBMR_BLEN_256_POS 7
+#define DMA_SBMR_BLEN_256_LEN 1
+#define DMA_SBMR_UNDEF_POS 0
+#define DMA_SBMR_UNDEF_LEN 1
+
+/* DMA register values */
+#define DMA_DSR_RPS_LEN 4
+#define DMA_DSR_TPS_LEN 4
+#define DMA_DSR_Q_LEN (DMA_DSR_RPS_LEN + DMA_DSR_TPS_LEN)
+#define DMA_DSR0_TPS_START 12
+#define DMA_DSRX_FIRST_QUEUE 3
+#define DMA_DSRX_INC 4
+#define DMA_DSRX_QPR 4
+#define DMA_DSRX_TPS_START 4
+#define DMA_TPS_STOPPED 0x00
+#define DMA_TPS_SUSPENDED 0x06
+
+/* DMA channel register offsets
+ * Multiple channels can be active. The first channel has registers
+ * that begin at 0x3100. Each subsequent channel has registers that
+ * are accessed using an offset of 0x80 from the previous channel.
+ */
+#define DMA_CH_BASE 0x3100
+#define DMA_CH_INC 0x80
+
+#define DMA_CH_CR 0x00
+#define DMA_CH_TCR 0x04
+#define DMA_CH_RCR 0x08
+#define DMA_CH_TDLR_HI 0x10
+#define DMA_CH_TDLR_LO 0x14
+#define DMA_CH_RDLR_HI 0x18
+#define DMA_CH_RDLR_LO 0x1c
+#define DMA_CH_TDTR_LO 0x24
+#define DMA_CH_RDTR_LO 0x2c
+#define DMA_CH_TDRLR 0x30
+#define DMA_CH_RDRLR 0x34
+#define DMA_CH_IER 0x38
+#define DMA_CH_RIWT 0x3c
+#define DMA_CH_SR 0x60
+
+/* DMA channel register entry bit positions and sizes */
+#define DMA_CH_CR_PBLX8_POS 16
+#define DMA_CH_CR_PBLX8_LEN 1
+#define DMA_CH_CR_SPH_POS 24
+#define DMA_CH_CR_SPH_LEN 1
+#define DMA_CH_IER_AIE_POS 15
+#define DMA_CH_IER_AIE_LEN 1
+#define DMA_CH_IER_FBEE_POS 12
+#define DMA_CH_IER_FBEE_LEN 1
+#define DMA_CH_IER_NIE_POS 16
+#define DMA_CH_IER_NIE_LEN 1
+#define DMA_CH_IER_RBUE_POS 7
+#define DMA_CH_IER_RBUE_LEN 1
+#define DMA_CH_IER_RIE_POS 6
+#define DMA_CH_IER_RIE_LEN 1
+#define DMA_CH_IER_RSE_POS 8
+#define DMA_CH_IER_RSE_LEN 1
+#define DMA_CH_IER_TBUE_POS 2
+#define DMA_CH_IER_TBUE_LEN 1
+#define DMA_CH_IER_TIE_POS 0
+#define DMA_CH_IER_TIE_LEN 1
+#define DMA_CH_IER_TXSE_POS 1
+#define DMA_CH_IER_TXSE_LEN 1
+#define DMA_CH_RCR_PBL_POS 16
+#define DMA_CH_RCR_PBL_LEN 6
+#define DMA_CH_RCR_RBSZ_POS 1
+#define DMA_CH_RCR_RBSZ_LEN 14
+#define DMA_CH_RCR_SR_POS 0
+#define DMA_CH_RCR_SR_LEN 1
+#define DMA_CH_RIWT_RWT_POS 0
+#define DMA_CH_RIWT_RWT_LEN 8
+#define DMA_CH_SR_FBE_POS 12
+#define DMA_CH_SR_FBE_LEN 1
+#define DMA_CH_SR_RBU_POS 7
+#define DMA_CH_SR_RBU_LEN 1
+#define DMA_CH_SR_RI_POS 6
+#define DMA_CH_SR_RI_LEN 1
+#define DMA_CH_SR_RPS_POS 8
+#define DMA_CH_SR_RPS_LEN 1
+#define DMA_CH_SR_TBU_POS 2
+#define DMA_CH_SR_TBU_LEN 1
+#define DMA_CH_SR_TI_POS 0
+#define DMA_CH_SR_TI_LEN 1
+#define DMA_CH_SR_TPS_POS 1
+#define DMA_CH_SR_TPS_LEN 1
+#define DMA_CH_TCR_OSP_POS 4
+#define DMA_CH_TCR_OSP_LEN 1
+#define DMA_CH_TCR_PBL_POS 16
+#define DMA_CH_TCR_PBL_LEN 6
+#define DMA_CH_TCR_ST_POS 0
+#define DMA_CH_TCR_ST_LEN 1
+#define DMA_CH_TCR_TSE_POS 12
+#define DMA_CH_TCR_TSE_LEN 1
+
+/* DMA channel register values */
+#define DMA_OSP_DISABLE 0x00
+#define DMA_OSP_ENABLE 0x01
+#define DMA_PBL_1 1
+#define DMA_PBL_2 2
+#define DMA_PBL_4 4
+#define DMA_PBL_8 8
+#define DMA_PBL_16 16
+#define DMA_PBL_32 32
+#define DMA_PBL_64 64
+#define DMA_PBL_128 128
+#define DMA_PBL_256 256
+#define DMA_PBL_X8_DISABLE 0x00
+#define DMA_PBL_X8_ENABLE 0x01
+
+/* Descriptor/Packet entry bit positions and sizes */
+#define RX_PACKET_ERRORS_CRC_POS 2
+#define RX_PACKET_ERRORS_CRC_LEN 1
+#define RX_PACKET_ERRORS_FRAME_POS 3
+#define RX_PACKET_ERRORS_FRAME_LEN 1
+#define RX_PACKET_ERRORS_LENGTH_POS 0
+#define RX_PACKET_ERRORS_LENGTH_LEN 1
+#define RX_PACKET_ERRORS_OVERRUN_POS 1
+#define RX_PACKET_ERRORS_OVERRUN_LEN 1
+
+#define RX_PACKET_ATTRIBUTES_CSUM_DONE_POS 0
+#define RX_PACKET_ATTRIBUTES_CSUM_DONE_LEN 1
+#define RX_PACKET_ATTRIBUTES_VLAN_CTAG_POS 1
+#define RX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN 1
+#define RX_PACKET_ATTRIBUTES_INCOMPLETE_POS 2
+#define RX_PACKET_ATTRIBUTES_INCOMPLETE_LEN 1
+#define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_POS 3
+#define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_LEN 1
+#define RX_PACKET_ATTRIBUTES_CONTEXT_POS 4
+#define RX_PACKET_ATTRIBUTES_CONTEXT_LEN 1
+#define RX_PACKET_ATTRIBUTES_RX_TSTAMP_POS 5
+#define RX_PACKET_ATTRIBUTES_RX_TSTAMP_LEN 1
+#define RX_PACKET_ATTRIBUTES_RSS_HASH_POS 6
+#define RX_PACKET_ATTRIBUTES_RSS_HASH_LEN 1
+
+#define RX_NORMAL_DESC0_OVT_POS 0
+#define RX_NORMAL_DESC0_OVT_LEN 16
+#define RX_NORMAL_DESC2_HL_POS 0
+#define RX_NORMAL_DESC2_HL_LEN 10
+#define RX_NORMAL_DESC3_CDA_POS 27
+#define RX_NORMAL_DESC3_CDA_LEN 1
+#define RX_NORMAL_DESC3_CTXT_POS 30
+#define RX_NORMAL_DESC3_CTXT_LEN 1
+#define RX_NORMAL_DESC3_ES_POS 15
+#define RX_NORMAL_DESC3_ES_LEN 1
+#define RX_NORMAL_DESC3_ETLT_POS 16
+#define RX_NORMAL_DESC3_ETLT_LEN 4
+#define RX_NORMAL_DESC3_FD_POS 29
+#define RX_NORMAL_DESC3_FD_LEN 1
+#define RX_NORMAL_DESC3_INTE_POS 30
+#define RX_NORMAL_DESC3_INTE_LEN 1
+#define RX_NORMAL_DESC3_L34T_POS 20
+#define RX_NORMAL_DESC3_L34T_LEN 4
+#define RX_NORMAL_DESC3_LD_POS 28
+#define RX_NORMAL_DESC3_LD_LEN 1
+#define RX_NORMAL_DESC3_OWN_POS 31
+#define RX_NORMAL_DESC3_OWN_LEN 1
+#define RX_NORMAL_DESC3_PL_POS 0
+#define RX_NORMAL_DESC3_PL_LEN 14
+#define RX_NORMAL_DESC3_RSV_POS 26
+#define RX_NORMAL_DESC3_RSV_LEN 1
+
+#define RX_DESC3_L34T_IPV4_TCP 1
+#define RX_DESC3_L34T_IPV4_UDP 2
+#define RX_DESC3_L34T_IPV4_ICMP 3
+#define RX_DESC3_L34T_IPV6_TCP 9
+#define RX_DESC3_L34T_IPV6_UDP 10
+#define RX_DESC3_L34T_IPV6_ICMP 11
+
+#define RX_CONTEXT_DESC3_TSA_POS 4
+#define RX_CONTEXT_DESC3_TSA_LEN 1
+#define RX_CONTEXT_DESC3_TSD_POS 6
+#define RX_CONTEXT_DESC3_TSD_LEN 1
+
+#define TX_PACKET_ATTRIBUTES_CSUM_ENABLE_POS 0
+#define TX_PACKET_ATTRIBUTES_CSUM_ENABLE_LEN 1
+#define TX_PACKET_ATTRIBUTES_TSO_ENABLE_POS 1
+#define TX_PACKET_ATTRIBUTES_TSO_ENABLE_LEN 1
+#define TX_PACKET_ATTRIBUTES_VLAN_CTAG_POS 2
+#define TX_PACKET_ATTRIBUTES_VLAN_CTAG_LEN 1
+#define TX_PACKET_ATTRIBUTES_PTP_POS 3
+#define TX_PACKET_ATTRIBUTES_PTP_LEN 1
+
+#define TX_CONTEXT_DESC2_MSS_POS 0
+#define TX_CONTEXT_DESC2_MSS_LEN 15
+#define TX_CONTEXT_DESC3_CTXT_POS 30
+#define TX_CONTEXT_DESC3_CTXT_LEN 1
+#define TX_CONTEXT_DESC3_TCMSSV_POS 26
+#define TX_CONTEXT_DESC3_TCMSSV_LEN 1
+#define TX_CONTEXT_DESC3_VLTV_POS 16
+#define TX_CONTEXT_DESC3_VLTV_LEN 1
+#define TX_CONTEXT_DESC3_VT_POS 0
+#define TX_CONTEXT_DESC3_VT_LEN 16
+
+#define TX_NORMAL_DESC2_HL_B1L_POS 0
+#define TX_NORMAL_DESC2_HL_B1L_LEN 14
+#define TX_NORMAL_DESC2_IC_POS 31
+#define TX_NORMAL_DESC2_IC_LEN 1
+#define TX_NORMAL_DESC2_TTSE_POS 30
+#define TX_NORMAL_DESC2_TTSE_LEN 1
+#define TX_NORMAL_DESC2_VTIR_POS 14
+#define TX_NORMAL_DESC2_VTIR_LEN 2
+#define TX_NORMAL_DESC3_CIC_POS 16
+#define TX_NORMAL_DESC3_CIC_LEN 2
+#define TX_NORMAL_DESC3_CPC_POS 26
+#define TX_NORMAL_DESC3_CPC_LEN 2
+#define TX_NORMAL_DESC3_CTXT_POS 30
+#define TX_NORMAL_DESC3_CTXT_LEN 1
+#define TX_NORMAL_DESC3_FD_POS 29
+#define TX_NORMAL_DESC3_FD_LEN 1
+#define TX_NORMAL_DESC3_FL_POS 0
+#define TX_NORMAL_DESC3_FL_LEN 15
+#define TX_NORMAL_DESC3_LD_POS 28
+#define TX_NORMAL_DESC3_LD_LEN 1
+#define TX_NORMAL_DESC3_OWN_POS 31
+#define TX_NORMAL_DESC3_OWN_LEN 1
+#define TX_NORMAL_DESC3_TCPHDRLEN_POS 19
+#define TX_NORMAL_DESC3_TCPHDRLEN_LEN 4
+#define TX_NORMAL_DESC3_TCPPL_POS 0
+#define TX_NORMAL_DESC3_TCPPL_LEN 18
+#define TX_NORMAL_DESC3_TSE_POS 18
+#define TX_NORMAL_DESC3_TSE_LEN 1
+
+#define TX_NORMAL_DESC2_VLAN_INSERT 0x2
+
+#define XLGMAC_MTL_REG(pdata, n, reg) \
+ ((pdata)->mac_regs + MTL_Q_BASE + ((n) * MTL_Q_INC) + (reg))
+
+#define XLGMAC_DMA_REG(channel, reg) ((channel)->dma_regs + (reg))
+
+#endif /* __DWC_XLGMAC_REG_H__ */
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac.h b/drivers/net/ethernet/synopsys/dwc-xlgmac.h
new file mode 100644
index 0000000..676b2fb8
--- /dev/null
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac.h
@@ -0,0 +1,649 @@
+/* Synopsys DesignWare Core Enterprise Ethernet (XLGMAC) Driver
+ *
+ * Copyright (c) 2017 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is dual-licensed; you may select either version 2 of
+ * the GNU General Public License ("GPL") or BSD license ("BSD").
+ *
+ * This Synopsys DWC XLGMAC software driver and associated documentation
+ * (hereinafter the "Software") is an unsupported proprietary work of
+ * Synopsys, Inc. unless otherwise expressly agreed to in writing between
+ * Synopsys and you. The Software IS NOT an item of Licensed Software or a
+ * Licensed Product under any End User Software License Agreement or
+ * Agreement for Licensed Products with Synopsys or any supplement thereto.
+ * Synopsys is a registered trademark of Synopsys, Inc. Other names included
+ * in the SOFTWARE may be the trademarks of their respective owners.
+ */
+
+#ifndef __DWC_XLGMAC_H__
+#define __DWC_XLGMAC_H__
+
+#include <linux/dma-mapping.h>
+#include <linux/netdevice.h>
+#include <linux/workqueue.h>
+#include <linux/phy.h>
+#include <linux/if_vlan.h>
+#include <linux/bitops.h>
+#include <linux/timecounter.h>
+
+#define XLGMAC_DRV_NAME "dwc-xlgmac"
+#define XLGMAC_DRV_VERSION "1.0.0"
+#define XLGMAC_DRV_DESC "Synopsys DWC XLGMAC Driver"
+
+/* Descriptor related parameters */
+#define XLGMAC_TX_DESC_CNT 1024
+#define XLGMAC_TX_DESC_MIN_FREE (XLGMAC_TX_DESC_CNT >> 3)
+#define XLGMAC_TX_DESC_MAX_PROC (XLGMAC_TX_DESC_CNT >> 1)
+#define XLGMAC_RX_DESC_CNT 1024
+#define XLGMAC_RX_DESC_MAX_DIRTY (XLGMAC_RX_DESC_CNT >> 3)
+
+/* Descriptors required for maximum contiguous TSO/GSO packet */
+#define XLGMAC_TX_MAX_SPLIT ((GSO_MAX_SIZE / XLGMAC_TX_MAX_BUF_SIZE) + 1)
+
+/* Maximum possible descriptors needed for a SKB */
+#define XLGMAC_TX_MAX_DESC_NR (MAX_SKB_FRAGS + XLGMAC_TX_MAX_SPLIT + 2)
+
+#define XLGMAC_TX_MAX_BUF_SIZE (0x3fff & ~(64 - 1))
+#define XLGMAC_RX_MIN_BUF_SIZE (ETH_FRAME_LEN + ETH_FCS_LEN + VLAN_HLEN)
+#define XLGMAC_RX_BUF_ALIGN 64
+
+/* Maximum Size for Splitting the Header Data
+ * Keep in sync with SKB_ALLOC_SIZE
+ * 3'b000: 64 bytes, 3'b001: 128 bytes
+ * 3'b010: 256 bytes, 3'b011: 512 bytes
+ * 3'b100: 1023 bytes , 3'b101'3'b111: Reserved
+ */
+#define XLGMAC_SPH_HDSMS_SIZE 3
+#define XLGMAC_SKB_ALLOC_SIZE 512
+
+#define XLGMAC_MAX_FIFO 81920
+
+#define XLGMAC_MAX_DMA_CHANNELS 16
+#define XLGMAC_DMA_STOP_TIMEOUT 5
+#define XLGMAC_DMA_INTERRUPT_MASK 0x31c7
+
+/* Default coalescing parameters */
+#define XLGMAC_INIT_DMA_TX_USECS 1000
+#define XLGMAC_INIT_DMA_TX_FRAMES 25
+#define XLGMAC_INIT_DMA_RX_USECS 30
+#define XLGMAC_INIT_DMA_RX_FRAMES 25
+
+/* Flow control queue count */
+#define XLGMAC_MAX_FLOW_CONTROL_QUEUES 8
+
+/* System clock is 125 MHz */
+#define XLGMAC_SYSCLOCK 125000000
+
+/* Maximum MAC address hash table size (256 bits = 8 bytes) */
+#define XLGMAC_MAC_HASH_TABLE_SIZE 8
+
+/* Receive Side Scaling */
+#define XLGMAC_RSS_HASH_KEY_SIZE 40
+#define XLGMAC_RSS_MAX_TABLE_SIZE 256
+#define XLGMAC_RSS_LOOKUP_TABLE_TYPE 0
+#define XLGMAC_RSS_HASH_KEY_TYPE 1
+
+#define XLGMAC_STD_PACKET_MTU 1500
+#define XLGMAC_JUMBO_PACKET_MTU 9000
+
+/* Helper macro for descriptor handling
+ * Always use XLGMAC_GET_DESC_DATA to access the descriptor data
+ */
+#define XLGMAC_GET_DESC_DATA(ring, idx) ({ \
+ typeof(ring) _ring = (ring); \
+ ((_ring)->desc_data_head + \
+ ((idx) & ((_ring)->dma_desc_count - 1))); \
+})
+
+#define XLGMAC_GET_REG_BITS(var, pos, len) ({ \
+ typeof(pos) _pos = (pos); \
+ typeof(len) _len = (len); \
+ ((var) & GENMASK(_pos + _len - 1, _pos)) >> (_pos); \
+})
+
+#define XLGMAC_GET_REG_BITS_LE(var, pos, len) ({ \
+ typeof(pos) _pos = (pos); \
+ typeof(len) _len = (len); \
+ typeof(var) _var = le32_to_cpu((var)); \
+ ((_var) & GENMASK(_pos + _len - 1, _pos)) >> (_pos); \
+})
+
+#define XLGMAC_SET_REG_BITS(var, pos, len, val) ({ \
+ typeof(var) _var = (var); \
+ typeof(pos) _pos = (pos); \
+ typeof(len) _len = (len); \
+ typeof(val) _val = (val); \
+ _val = (_val << _pos) & GENMASK(_pos + _len - 1, _pos); \
+ _var = (_var & ~GENMASK(_pos + _len - 1, _pos)) | _val; \
+})
+
+#define XLGMAC_SET_REG_BITS_LE(var, pos, len, val) ({ \
+ typeof(var) _var = (var); \
+ typeof(pos) _pos = (pos); \
+ typeof(len) _len = (len); \
+ typeof(val) _val = (val); \
+ _val = (_val << _pos) & GENMASK(_pos + _len - 1, _pos); \
+ _var = (_var & ~GENMASK(_pos + _len - 1, _pos)) | _val; \
+ cpu_to_le32(_var); \
+})
+
+struct xlgmac_pdata;
+
+enum xlgmac_int {
+ XLGMAC_INT_DMA_CH_SR_TI,
+ XLGMAC_INT_DMA_CH_SR_TPS,
+ XLGMAC_INT_DMA_CH_SR_TBU,
+ XLGMAC_INT_DMA_CH_SR_RI,
+ XLGMAC_INT_DMA_CH_SR_RBU,
+ XLGMAC_INT_DMA_CH_SR_RPS,
+ XLGMAC_INT_DMA_CH_SR_TI_RI,
+ XLGMAC_INT_DMA_CH_SR_FBE,
+ XLGMAC_INT_DMA_ALL,
+};
+
+struct xlgmac_stats {
+ /* MMC TX counters */
+ u64 txoctetcount_gb;
+ u64 txframecount_gb;
+ u64 txbroadcastframes_g;
+ u64 txmulticastframes_g;
+ u64 tx64octets_gb;
+ u64 tx65to127octets_gb;
+ u64 tx128to255octets_gb;
+ u64 tx256to511octets_gb;
+ u64 tx512to1023octets_gb;
+ u64 tx1024tomaxoctets_gb;
+ u64 txunicastframes_gb;
+ u64 txmulticastframes_gb;
+ u64 txbroadcastframes_gb;
+ u64 txunderflowerror;
+ u64 txoctetcount_g;
+ u64 txframecount_g;
+ u64 txpauseframes;
+ u64 txvlanframes_g;
+
+ /* MMC RX counters */
+ u64 rxframecount_gb;
+ u64 rxoctetcount_gb;
+ u64 rxoctetcount_g;
+ u64 rxbroadcastframes_g;
+ u64 rxmulticastframes_g;
+ u64 rxcrcerror;
+ u64 rxrunterror;
+ u64 rxjabbererror;
+ u64 rxundersize_g;
+ u64 rxoversize_g;
+ u64 rx64octets_gb;
+ u64 rx65to127octets_gb;
+ u64 rx128to255octets_gb;
+ u64 rx256to511octets_gb;
+ u64 rx512to1023octets_gb;
+ u64 rx1024tomaxoctets_gb;
+ u64 rxunicastframes_g;
+ u64 rxlengtherror;
+ u64 rxoutofrangetype;
+ u64 rxpauseframes;
+ u64 rxfifooverflow;
+ u64 rxvlanframes_gb;
+ u64 rxwatchdogerror;
+
+ /* Extra counters */
+ u64 tx_tso_packets;
+ u64 rx_split_header_packets;
+ u64 rx_buffer_unavailable;
+};
+
+struct xlgmac_ring_buf {
+ struct sk_buff *skb;
+ dma_addr_t skb_dma;
+ unsigned int skb_len;
+};
+
+/* Common Tx and Rx DMA hardware descriptor */
+struct xlgmac_dma_desc {
+ __le32 desc0;
+ __le32 desc1;
+ __le32 desc2;
+ __le32 desc3;
+};
+
+/* Page allocation related values */
+struct xlgmac_page_alloc {
+ struct page *pages;
+ unsigned int pages_len;
+ unsigned int pages_offset;
+
+ dma_addr_t pages_dma;
+};
+
+/* Ring entry buffer data */
+struct xlgmac_buffer_data {
+ struct xlgmac_page_alloc pa;
+ struct xlgmac_page_alloc pa_unmap;
+
+ dma_addr_t dma_base;
+ unsigned long dma_off;
+ unsigned int dma_len;
+};
+
+/* Tx-related desc data */
+struct xlgmac_tx_desc_data {
+ unsigned int packets; /* BQL packet count */
+ unsigned int bytes; /* BQL byte count */
+};
+
+/* Rx-related desc data */
+struct xlgmac_rx_desc_data {
+ struct xlgmac_buffer_data hdr; /* Header locations */
+ struct xlgmac_buffer_data buf; /* Payload locations */
+
+ unsigned short hdr_len; /* Length of received header */
+ unsigned short len; /* Length of received packet */
+};
+
+struct xlgmac_pkt_info {
+ struct sk_buff *skb;
+
+ unsigned int attributes;
+
+ unsigned int errors;
+
+ /* descriptors needed for this packet */
+ unsigned int desc_count;
+ unsigned int length;
+
+ unsigned int tx_packets;
+ unsigned int tx_bytes;
+
+ unsigned int header_len;
+ unsigned int tcp_header_len;
+ unsigned int tcp_payload_len;
+ unsigned short mss;
+
+ unsigned short vlan_ctag;
+
+ u64 rx_tstamp;
+
+ u32 rss_hash;
+ enum pkt_hash_types rss_hash_type;
+};
+
+struct xlgmac_desc_data {
+ /* dma_desc: Virtual address of descriptor
+ * dma_desc_addr: DMA address of descriptor
+ */
+ struct xlgmac_dma_desc *dma_desc;
+ dma_addr_t dma_desc_addr;
+
+ /* skb: Virtual address of SKB
+ * skb_dma: DMA address of SKB data
+ * skb_dma_len: Length of SKB DMA area
+ */
+ struct sk_buff *skb;
+ dma_addr_t skb_dma;
+ unsigned int skb_dma_len;
+
+ /* Tx/Rx -related data */
+ struct xlgmac_tx_desc_data tx;
+ struct xlgmac_rx_desc_data rx;
+
+ unsigned int mapped_as_page;
+
+ /* Incomplete receive save location. If the budget is exhausted
+ * or the last descriptor (last normal descriptor or a following
+ * context descriptor) has not been DMA'd yet the current state
+ * of the receive processing needs to be saved.
+ */
+ unsigned int state_saved;
+ struct {
+ struct sk_buff *skb;
+ unsigned int len;
+ unsigned int error;
+ } state;
+};
+
+struct xlgmac_ring {
+ /* Per packet related information */
+ struct xlgmac_pkt_info pkt_info;
+
+ /* Virtual/DMA addresses of DMA descriptor list and the total count */
+ struct xlgmac_dma_desc *dma_desc_head;
+ dma_addr_t dma_desc_head_addr;
+ unsigned int dma_desc_count;
+
+ /* Array of descriptor data corresponding the DMA descriptor
+ * (always use the XLGMAC_GET_DESC_DATA macro to access this data)
+ */
+ struct xlgmac_desc_data *desc_data_head;
+
+ /* Page allocation for RX buffers */
+ struct xlgmac_page_alloc rx_hdr_pa;
+ struct xlgmac_page_alloc rx_buf_pa;
+
+ /* Ring index values
+ * cur - Tx: index of descriptor to be used for current transfer
+ * Rx: index of descriptor to check for packet availability
+ * dirty - Tx: index of descriptor to check for transfer complete
+ * Rx: index of descriptor to check for buffer reallocation
+ */
+ unsigned int cur;
+ unsigned int dirty;
+
+ /* Coalesce frame count used for interrupt bit setting */
+ unsigned int coalesce_count;
+
+ union {
+ struct {
+ unsigned int xmit_more;
+ unsigned int queue_stopped;
+ unsigned short cur_mss;
+ unsigned short cur_vlan_ctag;
+ } tx;
+ };
+} ____cacheline_aligned;
+
+struct xlgmac_channel {
+ char name[16];
+
+ /* Address of private data area for device */
+ struct xlgmac_pdata *pdata;
+
+ /* Queue index and base address of queue's DMA registers */
+ unsigned int queue_index;
+ void __iomem *dma_regs;
+
+ /* Per channel interrupt irq number */
+ int dma_irq;
+ char dma_irq_name[IFNAMSIZ + 32];
+
+ /* Netdev related settings */
+ struct napi_struct napi;
+
+ unsigned int saved_ier;
+
+ unsigned int tx_timer_active;
+ struct timer_list tx_timer;
+
+ struct xlgmac_ring *tx_ring;
+ struct xlgmac_ring *rx_ring;
+} ____cacheline_aligned;
+
+struct xlgmac_desc_ops {
+ int (*alloc_channles_and_rings)(struct xlgmac_pdata *pdata);
+ void (*free_channels_and_rings)(struct xlgmac_pdata *pdata);
+ int (*map_tx_skb)(struct xlgmac_channel *channel,
+ struct sk_buff *skb);
+ int (*map_rx_buffer)(struct xlgmac_pdata *pdata,
+ struct xlgmac_ring *ring,
+ struct xlgmac_desc_data *desc_data);
+ void (*unmap_desc_data)(struct xlgmac_pdata *pdata,
+ struct xlgmac_desc_data *desc_data);
+ void (*tx_desc_init)(struct xlgmac_pdata *pdata);
+ void (*rx_desc_init)(struct xlgmac_pdata *pdata);
+};
+
+struct xlgmac_hw_ops {
+ int (*init)(struct xlgmac_pdata *pdata);
+ int (*exit)(struct xlgmac_pdata *pdata);
+
+ int (*tx_complete)(struct xlgmac_dma_desc *dma_desc);
+
+ void (*enable_tx)(struct xlgmac_pdata *pdata);
+ void (*disable_tx)(struct xlgmac_pdata *pdata);
+ void (*enable_rx)(struct xlgmac_pdata *pdata);
+ void (*disable_rx)(struct xlgmac_pdata *pdata);
+
+ int (*enable_int)(struct xlgmac_channel *channel,
+ enum xlgmac_int int_id);
+ int (*disable_int)(struct xlgmac_channel *channel,
+ enum xlgmac_int int_id);
+ void (*dev_xmit)(struct xlgmac_channel *channel);
+ int (*dev_read)(struct xlgmac_channel *channel);
+
+ int (*set_mac_address)(struct xlgmac_pdata *pdata, u8 *addr);
+ int (*config_rx_mode)(struct xlgmac_pdata *pdata);
+ int (*enable_rx_csum)(struct xlgmac_pdata *pdata);
+ int (*disable_rx_csum)(struct xlgmac_pdata *pdata);
+
+ /* For MII speed configuration */
+ int (*set_xlgmii_25000_speed)(struct xlgmac_pdata *pdata);
+ int (*set_xlgmii_40000_speed)(struct xlgmac_pdata *pdata);
+ int (*set_xlgmii_50000_speed)(struct xlgmac_pdata *pdata);
+ int (*set_xlgmii_100000_speed)(struct xlgmac_pdata *pdata);
+
+ /* For descriptor related operation */
+ void (*tx_desc_init)(struct xlgmac_channel *channel);
+ void (*rx_desc_init)(struct xlgmac_channel *channel);
+ void (*tx_desc_reset)(struct xlgmac_desc_data *desc_data);
+ void (*rx_desc_reset)(struct xlgmac_pdata *pdata,
+ struct xlgmac_desc_data *desc_data,
+ unsigned int index);
+ int (*is_last_desc)(struct xlgmac_dma_desc *dma_desc);
+ int (*is_context_desc)(struct xlgmac_dma_desc *dma_desc);
+ void (*tx_start_xmit)(struct xlgmac_channel *channel,
+ struct xlgmac_ring *ring);
+
+ /* For Flow Control */
+ int (*config_tx_flow_control)(struct xlgmac_pdata *pdata);
+ int (*config_rx_flow_control)(struct xlgmac_pdata *pdata);
+
+ /* For Vlan related config */
+ int (*enable_rx_vlan_stripping)(struct xlgmac_pdata *pdata);
+ int (*disable_rx_vlan_stripping)(struct xlgmac_pdata *pdata);
+ int (*enable_rx_vlan_filtering)(struct xlgmac_pdata *pdata);
+ int (*disable_rx_vlan_filtering)(struct xlgmac_pdata *pdata);
+ int (*update_vlan_hash_table)(struct xlgmac_pdata *pdata);
+
+ /* For RX coalescing */
+ int (*config_rx_coalesce)(struct xlgmac_pdata *pdata);
+ int (*config_tx_coalesce)(struct xlgmac_pdata *pdata);
+ unsigned int (*usec_to_riwt)(struct xlgmac_pdata *pdata,
+ unsigned int usec);
+ unsigned int (*riwt_to_usec)(struct xlgmac_pdata *pdata,
+ unsigned int riwt);
+
+ /* For RX and TX threshold config */
+ int (*config_rx_threshold)(struct xlgmac_pdata *pdata,
+ unsigned int val);
+ int (*config_tx_threshold)(struct xlgmac_pdata *pdata,
+ unsigned int val);
+
+ /* For RX and TX Store and Forward Mode config */
+ int (*config_rsf_mode)(struct xlgmac_pdata *pdata,
+ unsigned int val);
+ int (*config_tsf_mode)(struct xlgmac_pdata *pdata,
+ unsigned int val);
+
+ /* For TX DMA Operate on Second Frame config */
+ int (*config_osp_mode)(struct xlgmac_pdata *pdata);
+
+ /* For RX and TX PBL config */
+ int (*config_rx_pbl_val)(struct xlgmac_pdata *pdata);
+ int (*get_rx_pbl_val)(struct xlgmac_pdata *pdata);
+ int (*config_tx_pbl_val)(struct xlgmac_pdata *pdata);
+ int (*get_tx_pbl_val)(struct xlgmac_pdata *pdata);
+ int (*config_pblx8)(struct xlgmac_pdata *pdata);
+
+ /* For MMC statistics */
+ void (*rx_mmc_int)(struct xlgmac_pdata *pdata);
+ void (*tx_mmc_int)(struct xlgmac_pdata *pdata);
+ void (*read_mmc_stats)(struct xlgmac_pdata *pdata);
+
+ /* For Receive Side Scaling */
+ int (*enable_rss)(struct xlgmac_pdata *pdata);
+ int (*disable_rss)(struct xlgmac_pdata *pdata);
+ int (*set_rss_hash_key)(struct xlgmac_pdata *pdata,
+ const u8 *key);
+ int (*set_rss_lookup_table)(struct xlgmac_pdata *pdata,
+ const u32 *table);
+};
+
+/* This structure contains flags that indicate what hardware features
+ * or configurations are present in the device.
+ */
+struct xlgmac_hw_features {
+ /* HW Version */
+ unsigned int version;
+
+ /* HW Feature Register0 */
+ unsigned int phyifsel; /* PHY interface support */
+ unsigned int vlhash; /* VLAN Hash Filter */
+ unsigned int sma; /* SMA(MDIO) Interface */
+ unsigned int rwk; /* PMT remote wake-up packet */
+ unsigned int mgk; /* PMT magic packet */
+ unsigned int mmc; /* RMON module */
+ unsigned int aoe; /* ARP Offload */
+ unsigned int ts; /* IEEE 1588-2008 Advanced Timestamp */
+ unsigned int eee; /* Energy Efficient Ethernet */
+ unsigned int tx_coe; /* Tx Checksum Offload */
+ unsigned int rx_coe; /* Rx Checksum Offload */
+ unsigned int addn_mac; /* Additional MAC Addresses */
+ unsigned int ts_src; /* Timestamp Source */
+ unsigned int sa_vlan_ins; /* Source Address or VLAN Insertion */
+
+ /* HW Feature Register1 */
+ unsigned int rx_fifo_size; /* MTL Receive FIFO Size */
+ unsigned int tx_fifo_size; /* MTL Transmit FIFO Size */
+ unsigned int adv_ts_hi; /* Advance Timestamping High Word */
+ unsigned int dma_width; /* DMA width */
+ unsigned int dcb; /* DCB Feature */
+ unsigned int sph; /* Split Header Feature */
+ unsigned int tso; /* TCP Segmentation Offload */
+ unsigned int dma_debug; /* DMA Debug Registers */
+ unsigned int rss; /* Receive Side Scaling */
+ unsigned int tc_cnt; /* Number of Traffic Classes */
+ unsigned int hash_table_size; /* Hash Table Size */
+ unsigned int l3l4_filter_num; /* Number of L3-L4 Filters */
+
+ /* HW Feature Register2 */
+ unsigned int rx_q_cnt; /* Number of MTL Receive Queues */
+ unsigned int tx_q_cnt; /* Number of MTL Transmit Queues */
+ unsigned int rx_ch_cnt; /* Number of DMA Receive Channels */
+ unsigned int tx_ch_cnt; /* Number of DMA Transmit Channels */
+ unsigned int pps_out_num; /* Number of PPS outputs */
+ unsigned int aux_snap_num; /* Number of Aux snapshot inputs */
+};
+
+struct xlgmac_resources {
+ void __iomem *addr;
+ int irq;
+};
+
+struct xlgmac_pdata {
+ struct net_device *netdev;
+ struct device *dev;
+
+ struct xlgmac_hw_ops hw_ops;
+ struct xlgmac_desc_ops desc_ops;
+
+ /* Device statistics */
+ struct xlgmac_stats stats;
+
+ u32 msg_enable;
+
+ /* MAC registers base */
+ void __iomem *mac_regs;
+
+ /* Hardware features of the device */
+ struct xlgmac_hw_features hw_feat;
+
+ struct work_struct restart_work;
+
+ /* Rings for Tx/Rx on a DMA channel */
+ struct xlgmac_channel *channel_head;
+ unsigned int channel_count;
+ unsigned int tx_ring_count;
+ unsigned int rx_ring_count;
+ unsigned int tx_desc_count;
+ unsigned int rx_desc_count;
+ unsigned int tx_q_count;
+ unsigned int rx_q_count;
+
+ /* Tx/Rx common settings */
+ unsigned int pblx8;
+
+ /* Tx settings */
+ unsigned int tx_sf_mode;
+ unsigned int tx_threshold;
+ unsigned int tx_pbl;
+ unsigned int tx_osp_mode;
+
+ /* Rx settings */
+ unsigned int rx_sf_mode;
+ unsigned int rx_threshold;
+ unsigned int rx_pbl;
+
+ /* Tx coalescing settings */
+ unsigned int tx_usecs;
+ unsigned int tx_frames;
+
+ /* Rx coalescing settings */
+ unsigned int rx_riwt;
+ unsigned int rx_usecs;
+ unsigned int rx_frames;
+
+ /* Current Rx buffer size */
+ unsigned int rx_buf_size;
+
+ /* Flow control settings */
+ unsigned int tx_pause;
+ unsigned int rx_pause;
+
+ /* Device interrupt number */
+ int dev_irq;
+ unsigned int per_channel_irq;
+ int channel_irq[XLGMAC_MAX_DMA_CHANNELS];
+
+ /* Netdev related settings */
+ unsigned char mac_addr[ETH_ALEN];
+ netdev_features_t netdev_features;
+ struct napi_struct napi;
+
+ /* Filtering support */
+ unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
+
+ /* Device clocks */
+ unsigned long sysclk_rate;
+
+ /* RSS addressing mutex */
+ struct mutex rss_mutex;
+
+ /* Receive Side Scaling settings */
+ u8 rss_key[XLGMAC_RSS_HASH_KEY_SIZE];
+ u32 rss_table[XLGMAC_RSS_MAX_TABLE_SIZE];
+ u32 rss_options;
+
+ int phy_speed;
+
+ char drv_name[32];
+ char drv_ver[32];
+};
+
+void xlgmac_init_desc_ops(struct xlgmac_desc_ops *desc_ops);
+void xlgmac_init_hw_ops(struct xlgmac_hw_ops *hw_ops);
+const struct net_device_ops *xlgmac_get_netdev_ops(void);
+void xlgmac_dump_tx_desc(struct xlgmac_pdata *pdata,
+ struct xlgmac_ring *ring,
+ unsigned int idx,
+ unsigned int count,
+ unsigned int flag);
+void xlgmac_dump_rx_desc(struct xlgmac_pdata *pdata,
+ struct xlgmac_ring *ring,
+ unsigned int idx);
+void xlgmac_print_pkt(struct net_device *netdev,
+ struct sk_buff *skb, bool tx_rx);
+void xlgmac_get_all_hw_features(struct xlgmac_pdata *pdata);
+void xlgmac_print_all_hw_features(struct xlgmac_pdata *pdata);
+int xlgmac_drv_probe(struct device *dev,
+ struct xlgmac_resources *res);
+int xlgmac_drv_remove(struct device *dev);
+
+/* For debug prints */
+#ifdef XLGMAC_DEBUG
+#define XLGMAC_PR(fmt, args...) \
+ pr_alert("[%s,%d]:" fmt, __func__, __LINE__, ## args)
+#else
+#define XLGMAC_PR(x...) do { } while (0)
+#endif
+
+#endif /* __DWC_XLGMAC_H__ */
diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
index f864fd0..711fbbb 100644
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -2124,33 +2124,26 @@ static const char
};
/*
- * bdx_get_settings - get device-specific settings
+ * bdx_get_link_ksettings - get device-specific settings
* @netdev
* @ecmd
*/
-static int bdx_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+static int bdx_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *ecmd)
{
- u32 rdintcm;
- u32 tdintcm;
- struct bdx_priv *priv = netdev_priv(netdev);
+ ethtool_link_ksettings_zero_link_mode(ecmd, supported);
+ ethtool_link_ksettings_add_link_mode(ecmd, supported,
+ 10000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(ecmd, supported, FIBRE);
+ ethtool_link_ksettings_zero_link_mode(ecmd, advertising);
+ ethtool_link_ksettings_add_link_mode(ecmd, advertising,
+ 10000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(ecmd, advertising, FIBRE);
- rdintcm = priv->rdintcm;
- tdintcm = priv->tdintcm;
-
- ecmd->supported = (SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE);
- ecmd->advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_FIBRE);
- ethtool_cmd_speed_set(ecmd, SPEED_10000);
- ecmd->duplex = DUPLEX_FULL;
- ecmd->port = PORT_FIBRE;
- ecmd->transceiver = XCVR_EXTERNAL; /* what does it mean? */
- ecmd->autoneg = AUTONEG_DISABLE;
-
- /* PCK_TH measures in multiples of FIFO bytes
- We translate to packets */
- ecmd->maxtxpkt =
- ((GET_PCK_TH(tdintcm) * PCK_TH_MULT) / BDX_TXF_DESC_SZ);
- ecmd->maxrxpkt =
- ((GET_PCK_TH(rdintcm) * PCK_TH_MULT) / sizeof(struct rxf_desc));
+ ecmd->base.speed = SPEED_10000;
+ ecmd->base.duplex = DUPLEX_FULL;
+ ecmd->base.port = PORT_FIBRE;
+ ecmd->base.autoneg = AUTONEG_DISABLE;
return 0;
}
@@ -2384,7 +2377,6 @@ static void bdx_get_ethtool_stats(struct net_device *netdev,
static void bdx_set_ethtool_ops(struct net_device *netdev)
{
static const struct ethtool_ops bdx_ethtool_ops = {
- .get_settings = bdx_get_settings,
.get_drvinfo = bdx_get_drvinfo,
.get_link = ethtool_op_get_link,
.get_coalesce = bdx_get_coalesce,
@@ -2394,6 +2386,7 @@ static void bdx_set_ethtool_ops(struct net_device *netdev)
.get_strings = bdx_get_strings,
.get_sset_count = bdx_get_sset_count,
.get_ethtool_stats = bdx_get_ethtool_stats,
+ .get_link_ksettings = bdx_get_link_ksettings,
};
netdev->ethtool_ops = &bdx_ethtool_ops;
diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index 296c8ef..9e63195 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -74,15 +74,21 @@
will be called cpsw.
config TI_CPTS
- tristate "TI Common Platform Time Sync (CPTS) Support"
+ bool "TI Common Platform Time Sync (CPTS) Support"
depends on TI_CPSW || TI_KEYSTONE_NETCP
- imply PTP_1588_CLOCK
+ depends on PTP_1588_CLOCK
---help---
This driver supports the Common Platform Time Sync unit of
the CPSW Ethernet Switch and Keystone 2 1g/10g Switch Subsystem.
The unit can time stamp PTP UDP/IPv4 and Layer 2 packets, and the
driver offers a PTP Hardware Clock.
+config TI_CPTS_MOD
+ tristate
+ depends on TI_CPTS
+ default y if TI_CPSW=y || TI_KEYSTONE_NETCP=y
+ default m
+
config TI_KEYSTONE_NETCP
tristate "TI Keystone NETCP Core Support"
select TI_CPSW_ALE
diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile
index 1e7c10b..10e6b0c 100644
--- a/drivers/net/ethernet/ti/Makefile
+++ b/drivers/net/ethernet/ti/Makefile
@@ -12,7 +12,7 @@
obj-$(CONFIG_TI_DAVINCI_CPDMA) += davinci_cpdma.o
obj-$(CONFIG_TI_CPSW_PHY_SEL) += cpsw-phy-sel.o
obj-$(CONFIG_TI_CPSW_ALE) += cpsw_ale.o
-obj-$(CONFIG_TI_CPTS) += cpts.o
+obj-$(CONFIG_TI_CPTS_MOD) += cpts.o
obj-$(CONFIG_TI_CPSW) += ti_cpsw.o
ti_cpsw-y := cpsw.o
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 9f3d9c6..fa674a8 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1267,6 +1267,7 @@ static void soft_reset_slave(struct cpsw_slave *slave)
static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
{
u32 slave_port;
+ struct phy_device *phy;
struct cpsw_common *cpsw = priv->cpsw;
soft_reset_slave(slave);
@@ -1300,27 +1301,28 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
1 << slave_port, 0, 0, ALE_MCAST_FWD_2);
if (slave->data->phy_node) {
- slave->phy = of_phy_connect(priv->ndev, slave->data->phy_node,
+ phy = of_phy_connect(priv->ndev, slave->data->phy_node,
&cpsw_adjust_link, 0, slave->data->phy_if);
- if (!slave->phy) {
+ if (!phy) {
dev_err(priv->dev, "phy \"%s\" not found on slave %d\n",
slave->data->phy_node->full_name,
slave->slave_num);
return;
}
} else {
- slave->phy = phy_connect(priv->ndev, slave->data->phy_id,
+ phy = phy_connect(priv->ndev, slave->data->phy_id,
&cpsw_adjust_link, slave->data->phy_if);
- if (IS_ERR(slave->phy)) {
+ if (IS_ERR(phy)) {
dev_err(priv->dev,
"phy \"%s\" not found on slave %d, err %ld\n",
slave->data->phy_id, slave->slave_num,
- PTR_ERR(slave->phy));
- slave->phy = NULL;
+ PTR_ERR(phy));
return;
}
}
+ slave->phy = phy;
+
phy_attached_info(slave->phy);
phy_start(slave->phy);
@@ -1817,6 +1819,8 @@ static void cpsw_ndo_tx_timeout(struct net_device *ndev)
}
cpsw_intr_enable(cpsw);
+ netif_trans_update(ndev);
+ netif_tx_wake_all_queues(ndev);
}
static int cpsw_ndo_set_mac_address(struct net_device *ndev, void *p)
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index 7c7ae08..9027c9c 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -1882,6 +1882,7 @@ static u16 netcp_select_queue(struct net_device *dev, struct sk_buff *skb,
static int netcp_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
struct tc_to_netdev *tc)
{
+ u8 num_tc;
int i;
/* setup tc must be called under rtnl lock */
@@ -1890,15 +1891,18 @@ static int netcp_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
if (tc->type != TC_SETUP_MQPRIO)
return -EINVAL;
+ tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+ num_tc = tc->mqprio->num_tc;
+
/* Sanity-check the number of traffic classes requested */
if ((dev->real_num_tx_queues <= 1) ||
- (dev->real_num_tx_queues < tc->tc))
+ (dev->real_num_tx_queues < num_tc))
return -EINVAL;
/* Configure traffic class to queue mappings */
- if (tc->tc) {
- netdev_set_num_tc(dev, tc->tc);
- for (i = 0; i < tc->tc; i++)
+ if (num_tc) {
+ netdev_set_num_tc(dev, num_tc);
+ for (i = 0; i < num_tc; i++)
netdev_set_tc_queue(dev, i, 1, i);
} else {
netdev_reset_tc(dev);
diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.c b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
index 7201331..fa6a065 100644
--- a/drivers/net/ethernet/toshiba/ps3_gelic_net.c
+++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
@@ -1206,61 +1206,68 @@ void gelic_net_get_drvinfo(struct net_device *netdev,
strlcpy(info->version, DRV_VERSION, sizeof(info->version));
}
-static int gelic_ether_get_settings(struct net_device *netdev,
- struct ethtool_cmd *cmd)
+static int gelic_ether_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *cmd)
{
struct gelic_card *card = netdev_card(netdev);
+ u32 supported, advertising;
gelic_card_get_ether_port_status(card, 0);
if (card->ether_port_status & GELIC_LV1_ETHER_FULL_DUPLEX)
- cmd->duplex = DUPLEX_FULL;
+ cmd->base.duplex = DUPLEX_FULL;
else
- cmd->duplex = DUPLEX_HALF;
+ cmd->base.duplex = DUPLEX_HALF;
switch (card->ether_port_status & GELIC_LV1_ETHER_SPEED_MASK) {
case GELIC_LV1_ETHER_SPEED_10:
- ethtool_cmd_speed_set(cmd, SPEED_10);
+ cmd->base.speed = SPEED_10;
break;
case GELIC_LV1_ETHER_SPEED_100:
- ethtool_cmd_speed_set(cmd, SPEED_100);
+ cmd->base.speed = SPEED_100;
break;
case GELIC_LV1_ETHER_SPEED_1000:
- ethtool_cmd_speed_set(cmd, SPEED_1000);
+ cmd->base.speed = SPEED_1000;
break;
default:
pr_info("%s: speed unknown\n", __func__);
- ethtool_cmd_speed_set(cmd, SPEED_10);
+ cmd->base.speed = SPEED_10;
break;
}
- cmd->supported = SUPPORTED_TP | SUPPORTED_Autoneg |
+ supported = SUPPORTED_TP | SUPPORTED_Autoneg |
SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full |
SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full |
SUPPORTED_1000baseT_Full;
- cmd->advertising = cmd->supported;
+ advertising = supported;
if (card->link_mode & GELIC_LV1_ETHER_AUTO_NEG) {
- cmd->autoneg = AUTONEG_ENABLE;
+ cmd->base.autoneg = AUTONEG_ENABLE;
} else {
- cmd->autoneg = AUTONEG_DISABLE;
- cmd->advertising &= ~ADVERTISED_Autoneg;
+ cmd->base.autoneg = AUTONEG_DISABLE;
+ advertising &= ~ADVERTISED_Autoneg;
}
- cmd->port = PORT_TP;
+ cmd->base.port = PORT_TP;
+
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ supported);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+ advertising);
return 0;
}
-static int gelic_ether_set_settings(struct net_device *netdev,
- struct ethtool_cmd *cmd)
+static int
+gelic_ether_set_link_ksettings(struct net_device *netdev,
+ const struct ethtool_link_ksettings *cmd)
{
struct gelic_card *card = netdev_card(netdev);
u64 mode;
int ret;
- if (cmd->autoneg == AUTONEG_ENABLE) {
+ if (cmd->base.autoneg == AUTONEG_ENABLE) {
mode = GELIC_LV1_ETHER_AUTO_NEG;
} else {
- switch (cmd->speed) {
+ switch (cmd->base.speed) {
case SPEED_10:
mode = GELIC_LV1_ETHER_SPEED_10;
break;
@@ -1273,9 +1280,9 @@ static int gelic_ether_set_settings(struct net_device *netdev,
default:
return -EINVAL;
}
- if (cmd->duplex == DUPLEX_FULL)
+ if (cmd->base.duplex == DUPLEX_FULL) {
mode |= GELIC_LV1_ETHER_FULL_DUPLEX;
- else if (cmd->speed == SPEED_1000) {
+ } else if (cmd->base.speed == SPEED_1000) {
pr_info("1000 half duplex is not supported.\n");
return -EINVAL;
}
@@ -1370,11 +1377,11 @@ static int gelic_net_set_wol(struct net_device *netdev,
static const struct ethtool_ops gelic_ether_ethtool_ops = {
.get_drvinfo = gelic_net_get_drvinfo,
- .get_settings = gelic_ether_get_settings,
- .set_settings = gelic_ether_set_settings,
.get_link = ethtool_op_get_link,
.get_wol = gelic_net_get_wol,
.set_wol = gelic_net_set_wol,
+ .get_link_ksettings = gelic_ether_get_link_ksettings,
+ .set_link_ksettings = gelic_ether_set_link_ksettings,
};
/**
diff --git a/drivers/net/ethernet/toshiba/spider_net_ethtool.c b/drivers/net/ethernet/toshiba/spider_net_ethtool.c
index ffe5193..16bd036 100644
--- a/drivers/net/ethernet/toshiba/spider_net_ethtool.c
+++ b/drivers/net/ethernet/toshiba/spider_net_ethtool.c
@@ -47,19 +47,23 @@ static struct {
};
static int
-spider_net_ethtool_get_settings(struct net_device *netdev,
- struct ethtool_cmd *cmd)
+spider_net_ethtool_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *cmd)
{
struct spider_net_card *card;
card = netdev_priv(netdev);
- cmd->supported = (SUPPORTED_1000baseT_Full |
- SUPPORTED_FIBRE);
- cmd->advertising = (ADVERTISED_1000baseT_Full |
- ADVERTISED_FIBRE);
- cmd->port = PORT_FIBRE;
- ethtool_cmd_speed_set(cmd, card->phy.speed);
- cmd->duplex = DUPLEX_FULL;
+ ethtool_link_ksettings_zero_link_mode(cmd, supported);
+ ethtool_link_ksettings_add_link_mode(cmd, supported, 1000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
+
+ ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising, 1000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE);
+
+ cmd->base.port = PORT_FIBRE;
+ cmd->base.speed = card->phy.speed;
+ cmd->base.duplex = DUPLEX_FULL;
return 0;
}
@@ -166,7 +170,6 @@ static void spider_net_get_strings(struct net_device *netdev, u32 stringset,
}
const struct ethtool_ops spider_net_ethtool_ops = {
- .get_settings = spider_net_ethtool_get_settings,
.get_drvinfo = spider_net_ethtool_get_drvinfo,
.get_wol = spider_net_ethtool_get_wol,
.get_msglevel = spider_net_ethtool_get_msglevel,
@@ -177,5 +180,6 @@ const struct ethtool_ops spider_net_ethtool_ops = {
.get_strings = spider_net_get_strings,
.get_sset_count = spider_net_get_sset_count,
.get_ethtool_stats = spider_net_get_ethtool_stats,
+ .get_link_ksettings = spider_net_ethtool_get_link_ksettings,
};
diff --git a/drivers/net/ethernet/tundra/tsi108_eth.c b/drivers/net/ethernet/tundra/tsi108_eth.c
index c558399..5ac6eaa 100644
--- a/drivers/net/ethernet/tundra/tsi108_eth.c
+++ b/drivers/net/ethernet/tundra/tsi108_eth.c
@@ -1499,27 +1499,29 @@ static void tsi108_init_mac(struct net_device *dev)
TSI_WRITE(TSI108_EC_INTMASK, ~0);
}
-static int tsi108_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int tsi108_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
struct tsi108_prv_data *data = netdev_priv(dev);
unsigned long flags;
int rc;
spin_lock_irqsave(&data->txlock, flags);
- rc = mii_ethtool_gset(&data->mii_if, cmd);
+ rc = mii_ethtool_get_link_ksettings(&data->mii_if, cmd);
spin_unlock_irqrestore(&data->txlock, flags);
return rc;
}
-static int tsi108_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int tsi108_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
{
struct tsi108_prv_data *data = netdev_priv(dev);
unsigned long flags;
int rc;
spin_lock_irqsave(&data->txlock, flags);
- rc = mii_ethtool_sset(&data->mii_if, cmd);
+ rc = mii_ethtool_set_link_ksettings(&data->mii_if, cmd);
spin_unlock_irqrestore(&data->txlock, flags);
return rc;
@@ -1535,8 +1537,8 @@ static int tsi108_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
static const struct ethtool_ops tsi108_ethtool_ops = {
.get_link = ethtool_op_get_link,
- .get_settings = tsi108_get_settings,
- .set_settings = tsi108_set_settings,
+ .get_link_ksettings = tsi108_get_link_ksettings,
+ .set_link_ksettings = tsi108_set_link_ksettings,
};
static const struct net_device_ops tsi108_netdev_ops = {
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index c068c58..4cf41f7 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -2303,25 +2303,27 @@ static void netdev_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *i
strlcpy(info->bus_info, dev_name(hwdev), sizeof(info->bus_info));
}
-static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int netdev_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
struct rhine_private *rp = netdev_priv(dev);
int rc;
mutex_lock(&rp->task_lock);
- rc = mii_ethtool_gset(&rp->mii_if, cmd);
+ rc = mii_ethtool_get_link_ksettings(&rp->mii_if, cmd);
mutex_unlock(&rp->task_lock);
return rc;
}
-static int netdev_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int netdev_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
{
struct rhine_private *rp = netdev_priv(dev);
int rc;
mutex_lock(&rp->task_lock);
- rc = mii_ethtool_sset(&rp->mii_if, cmd);
+ rc = mii_ethtool_set_link_ksettings(&rp->mii_if, cmd);
rhine_set_carrier(&rp->mii_if);
mutex_unlock(&rp->task_lock);
@@ -2391,14 +2393,14 @@ static int rhine_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
static const struct ethtool_ops netdev_ethtool_ops = {
.get_drvinfo = netdev_get_drvinfo,
- .get_settings = netdev_get_settings,
- .set_settings = netdev_set_settings,
.nway_reset = netdev_nway_reset,
.get_link = netdev_get_link,
.get_msglevel = netdev_get_msglevel,
.set_msglevel = netdev_set_msglevel,
.get_wol = rhine_get_wol,
.set_wol = rhine_set_wol,
+ .get_link_ksettings = netdev_get_link_ksettings,
+ .set_link_ksettings = netdev_set_link_ksettings,
};
static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c
index d088788..ef9538e 100644
--- a/drivers/net/ethernet/via/via-velocity.c
+++ b/drivers/net/ethernet/via/via-velocity.c
@@ -3291,15 +3291,17 @@ static void velocity_ethtool_down(struct net_device *dev)
velocity_set_power_state(vptr, PCI_D3hot);
}
-static int velocity_get_settings(struct net_device *dev,
- struct ethtool_cmd *cmd)
+static int velocity_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
struct velocity_info *vptr = netdev_priv(dev);
struct mac_regs __iomem *regs = vptr->mac_regs;
u32 status;
+ u32 supported, advertising;
+
status = check_connection_type(vptr->mac_regs);
- cmd->supported = SUPPORTED_TP |
+ supported = SUPPORTED_TP |
SUPPORTED_Autoneg |
SUPPORTED_10baseT_Half |
SUPPORTED_10baseT_Full |
@@ -3308,9 +3310,9 @@ static int velocity_get_settings(struct net_device *dev,
SUPPORTED_1000baseT_Half |
SUPPORTED_1000baseT_Full;
- cmd->advertising = ADVERTISED_TP | ADVERTISED_Autoneg;
+ advertising = ADVERTISED_TP | ADVERTISED_Autoneg;
if (vptr->options.spd_dpx == SPD_DPX_AUTO) {
- cmd->advertising |=
+ advertising |=
ADVERTISED_10baseT_Half |
ADVERTISED_10baseT_Full |
ADVERTISED_100baseT_Half |
@@ -3320,19 +3322,19 @@ static int velocity_get_settings(struct net_device *dev,
} else {
switch (vptr->options.spd_dpx) {
case SPD_DPX_1000_FULL:
- cmd->advertising |= ADVERTISED_1000baseT_Full;
+ advertising |= ADVERTISED_1000baseT_Full;
break;
case SPD_DPX_100_HALF:
- cmd->advertising |= ADVERTISED_100baseT_Half;
+ advertising |= ADVERTISED_100baseT_Half;
break;
case SPD_DPX_100_FULL:
- cmd->advertising |= ADVERTISED_100baseT_Full;
+ advertising |= ADVERTISED_100baseT_Full;
break;
case SPD_DPX_10_HALF:
- cmd->advertising |= ADVERTISED_10baseT_Half;
+ advertising |= ADVERTISED_10baseT_Half;
break;
case SPD_DPX_10_FULL:
- cmd->advertising |= ADVERTISED_10baseT_Full;
+ advertising |= ADVERTISED_10baseT_Full;
break;
default:
break;
@@ -3340,30 +3342,35 @@ static int velocity_get_settings(struct net_device *dev,
}
if (status & VELOCITY_SPEED_1000)
- ethtool_cmd_speed_set(cmd, SPEED_1000);
+ cmd->base.speed = SPEED_1000;
else if (status & VELOCITY_SPEED_100)
- ethtool_cmd_speed_set(cmd, SPEED_100);
+ cmd->base.speed = SPEED_100;
else
- ethtool_cmd_speed_set(cmd, SPEED_10);
+ cmd->base.speed = SPEED_10;
- cmd->autoneg = (status & VELOCITY_AUTONEG_ENABLE) ? AUTONEG_ENABLE : AUTONEG_DISABLE;
- cmd->port = PORT_TP;
- cmd->transceiver = XCVR_INTERNAL;
- cmd->phy_address = readb(®s->MIIADR) & 0x1F;
+ cmd->base.autoneg = (status & VELOCITY_AUTONEG_ENABLE) ?
+ AUTONEG_ENABLE : AUTONEG_DISABLE;
+ cmd->base.port = PORT_TP;
+ cmd->base.phy_address = readb(®s->MIIADR) & 0x1F;
if (status & VELOCITY_DUPLEX_FULL)
- cmd->duplex = DUPLEX_FULL;
+ cmd->base.duplex = DUPLEX_FULL;
else
- cmd->duplex = DUPLEX_HALF;
+ cmd->base.duplex = DUPLEX_HALF;
+
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ supported);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+ advertising);
return 0;
}
-static int velocity_set_settings(struct net_device *dev,
- struct ethtool_cmd *cmd)
+static int velocity_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
{
struct velocity_info *vptr = netdev_priv(dev);
- u32 speed = ethtool_cmd_speed(cmd);
+ u32 speed = cmd->base.speed;
u32 curr_status;
u32 new_status = 0;
int ret = 0;
@@ -3371,11 +3378,12 @@ static int velocity_set_settings(struct net_device *dev,
curr_status = check_connection_type(vptr->mac_regs);
curr_status &= (~VELOCITY_LINK_FAIL);
- new_status |= ((cmd->autoneg) ? VELOCITY_AUTONEG_ENABLE : 0);
+ new_status |= ((cmd->base.autoneg) ? VELOCITY_AUTONEG_ENABLE : 0);
new_status |= ((speed == SPEED_1000) ? VELOCITY_SPEED_1000 : 0);
new_status |= ((speed == SPEED_100) ? VELOCITY_SPEED_100 : 0);
new_status |= ((speed == SPEED_10) ? VELOCITY_SPEED_10 : 0);
- new_status |= ((cmd->duplex == DUPLEX_FULL) ? VELOCITY_DUPLEX_FULL : 0);
+ new_status |= ((cmd->base.duplex == DUPLEX_FULL) ?
+ VELOCITY_DUPLEX_FULL : 0);
if ((new_status & VELOCITY_AUTONEG_ENABLE) &&
(new_status != (curr_status | VELOCITY_AUTONEG_ENABLE))) {
@@ -3644,8 +3652,6 @@ static void velocity_get_ethtool_stats(struct net_device *dev,
}
static const struct ethtool_ops velocity_ethtool_ops = {
- .get_settings = velocity_get_settings,
- .set_settings = velocity_set_settings,
.get_drvinfo = velocity_get_drvinfo,
.get_wol = velocity_ethtool_get_wol,
.set_wol = velocity_ethtool_set_wol,
@@ -3658,7 +3664,9 @@ static const struct ethtool_ops velocity_ethtool_ops = {
.get_coalesce = velocity_get_coalesce,
.set_coalesce = velocity_set_coalesce,
.begin = velocity_ethtool_up,
- .complete = velocity_ethtool_down
+ .complete = velocity_ethtool_down,
+ .get_link_ksettings = velocity_get_link_ksettings,
+ .set_link_ksettings = velocity_set_link_ksettings,
};
#if defined(CONFIG_PM) && defined(CONFIG_INET)
diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c
index f90267f..2bdfb39 100644
--- a/drivers/net/ethernet/wiznet/w5100.c
+++ b/drivers/net/ethernet/wiznet/w5100.c
@@ -1152,7 +1152,8 @@ int w5100_probe(struct device *dev, const struct w5100_ops *ops,
if (err < 0)
goto err_register;
- priv->xfer_wq = alloc_workqueue(netdev_name(ndev), WQ_MEM_RECLAIM, 0);
+ priv->xfer_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0,
+ netdev_name(ndev));
if (!priv->xfer_wq) {
err = -ENOMEM;
goto err_wq;
diff --git a/drivers/net/fjes/fjes_ethtool.c b/drivers/net/fjes/fjes_ethtool.c
index 6575f88..7d10171 100644
--- a/drivers/net/fjes/fjes_ethtool.c
+++ b/drivers/net/fjes/fjes_ethtool.c
@@ -175,16 +175,15 @@ static void fjes_get_drvinfo(struct net_device *netdev,
"platform:%s", plat_dev->name);
}
-static int fjes_get_settings(struct net_device *netdev,
- struct ethtool_cmd *ecmd)
+static int fjes_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *ecmd)
{
- ecmd->supported = 0;
- ecmd->advertising = 0;
- ecmd->duplex = DUPLEX_FULL;
- ecmd->autoneg = AUTONEG_DISABLE;
- ecmd->transceiver = XCVR_DUMMY1;
- ecmd->port = PORT_NONE;
- ethtool_cmd_speed_set(ecmd, 20000); /* 20Gb/s */
+ ethtool_link_ksettings_zero_link_mode(ecmd, supported);
+ ethtool_link_ksettings_zero_link_mode(ecmd, advertising);
+ ecmd->base.duplex = DUPLEX_FULL;
+ ecmd->base.autoneg = AUTONEG_DISABLE;
+ ecmd->base.port = PORT_NONE;
+ ecmd->base.speed = 20000; /* 20Gb/s */
return 0;
}
@@ -296,7 +295,6 @@ static int fjes_get_dump_data(struct net_device *netdev,
}
static const struct ethtool_ops fjes_ethtool_ops = {
- .get_settings = fjes_get_settings,
.get_drvinfo = fjes_get_drvinfo,
.get_ethtool_stats = fjes_get_ethtool_stats,
.get_strings = fjes_get_strings,
@@ -306,6 +304,7 @@ static const struct ethtool_ops fjes_ethtool_ops = {
.set_dump = fjes_set_dump,
.get_dump_flag = fjes_get_dump_flag,
.get_dump_data = fjes_get_dump_data,
+ .get_link_ksettings = fjes_get_link_ksettings,
};
void fjes_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c
index b75d9cd..ae48c80 100644
--- a/drivers/net/fjes/fjes_main.c
+++ b/drivers/net/fjes/fjes_main.c
@@ -45,6 +45,8 @@ MODULE_DESCRIPTION("FUJITSU Extended Socket Network Device Driver");
MODULE_LICENSE("GPL");
MODULE_VERSION(DRV_VERSION);
+#define ACPI_MOTHERBOARD_RESOURCE_HID "PNP0C02"
+
static int fjes_request_irq(struct fjes_adapter *);
static void fjes_free_irq(struct fjes_adapter *);
@@ -78,7 +80,7 @@ static void fjes_rx_irq(struct fjes_adapter *, int);
static int fjes_poll(struct napi_struct *, int);
static const struct acpi_device_id fjes_acpi_ids[] = {
- {"PNP0C02", 0},
+ {ACPI_MOTHERBOARD_RESOURCE_HID, 0},
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, fjes_acpi_ids);
@@ -115,18 +117,17 @@ static struct resource fjes_resource[] = {
},
};
-static int fjes_acpi_add(struct acpi_device *device)
+static bool is_extended_socket_device(struct acpi_device *device)
{
struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL};
char str_buf[sizeof(FJES_ACPI_SYMBOL) + 1];
- struct platform_device *plat_dev;
union acpi_object *str;
acpi_status status;
int result;
status = acpi_evaluate_object(device->handle, "_STR", NULL, &buffer);
if (ACPI_FAILURE(status))
- return -ENODEV;
+ return false;
str = buffer.pointer;
result = utf16s_to_utf8s((wchar_t *)str->string.pointer,
@@ -136,10 +137,42 @@ static int fjes_acpi_add(struct acpi_device *device)
if (strncmp(FJES_ACPI_SYMBOL, str_buf, strlen(FJES_ACPI_SYMBOL)) != 0) {
kfree(buffer.pointer);
- return -ENODEV;
+ return false;
}
kfree(buffer.pointer);
+ return true;
+}
+
+static int acpi_check_extended_socket_status(struct acpi_device *device)
+{
+ unsigned long long sta;
+ acpi_status status;
+
+ status = acpi_evaluate_integer(device->handle, "_STA", NULL, &sta);
+ if (ACPI_FAILURE(status))
+ return -ENODEV;
+
+ if (!((sta & ACPI_STA_DEVICE_PRESENT) &&
+ (sta & ACPI_STA_DEVICE_ENABLED) &&
+ (sta & ACPI_STA_DEVICE_UI) &&
+ (sta & ACPI_STA_DEVICE_FUNCTIONING)))
+ return -ENODEV;
+
+ return 0;
+}
+
+static int fjes_acpi_add(struct acpi_device *device)
+{
+ struct platform_device *plat_dev;
+ acpi_status status;
+
+ if (!is_extended_socket_device(device))
+ return -ENODEV;
+
+ if (acpi_check_extended_socket_status(device))
+ return -ENODEV;
+
status = acpi_walk_resources(device->handle, METHOD_NAME__CRS,
fjes_get_acpi_resource, fjes_resource);
if (ACPI_FAILURE(status))
@@ -1316,7 +1349,7 @@ static void fjes_netdev_setup(struct net_device *netdev)
netdev->min_mtu = fjes_support_mtu[0];
netdev->max_mtu = fjes_support_mtu[3];
netdev->flags |= IFF_BROADCAST;
- netdev->features |= NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_FILTER;
+ netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
}
static void fjes_irq_watch_task(struct work_struct *work)
@@ -1473,11 +1506,44 @@ static void fjes_watch_unshare_task(struct work_struct *work)
}
}
+static acpi_status
+acpi_find_extended_socket_device(acpi_handle obj_handle, u32 level,
+ void *context, void **return_value)
+{
+ struct acpi_device *device;
+ bool *found = context;
+ int result;
+
+ result = acpi_bus_get_device(obj_handle, &device);
+ if (result)
+ return AE_OK;
+
+ if (strcmp(acpi_device_hid(device), ACPI_MOTHERBOARD_RESOURCE_HID))
+ return AE_OK;
+
+ if (!is_extended_socket_device(device))
+ return AE_OK;
+
+ if (acpi_check_extended_socket_status(device))
+ return AE_OK;
+
+ *found = true;
+ return AE_CTRL_TERMINATE;
+}
+
/* fjes_init_module - Driver Registration Routine */
static int __init fjes_init_module(void)
{
+ bool found = false;
int result;
+ acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT, ACPI_UINT32_MAX,
+ acpi_find_extended_socket_device, NULL, &found,
+ NULL);
+
+ if (!found)
+ return -ENODEV;
+
pr_info("%s - version %s - %s\n",
fjes_driver_string, fjes_driver_version, fjes_copyright);
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 8969874..4fea1b3 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -56,7 +56,10 @@ struct pdp_ctx {
u16 af;
struct in_addr ms_addr_ip4;
- struct in_addr sgsn_addr_ip4;
+ struct in_addr peer_addr_ip4;
+
+ struct sock *sk;
+ struct net_device *dev;
atomic_t tx_seq;
struct rcu_head rcu_head;
@@ -66,11 +69,12 @@ struct pdp_ctx {
struct gtp_dev {
struct list_head list;
- struct socket *sock0;
- struct socket *sock1u;
+ struct sock *sk0;
+ struct sock *sk1u;
struct net_device *dev;
+ unsigned int role;
unsigned int hash_size;
struct hlist_head *tid_hash;
struct hlist_head *addr_hash;
@@ -84,6 +88,8 @@ struct gtp_net {
static u32 gtp_h_initval;
+static void pdp_context_delete(struct pdp_ctx *pctx);
+
static inline u32 gtp0_hashfn(u64 tid)
{
u32 *tid32 = (u32 *) &tid;
@@ -149,8 +155,8 @@ static struct pdp_ctx *ipv4_pdp_find(struct gtp_dev *gtp, __be32 ms_addr)
return NULL;
}
-static bool gtp_check_src_ms_ipv4(struct sk_buff *skb, struct pdp_ctx *pctx,
- unsigned int hdrlen)
+static bool gtp_check_ms_ipv4(struct sk_buff *skb, struct pdp_ctx *pctx,
+ unsigned int hdrlen, unsigned int role)
{
struct iphdr *iph;
@@ -159,25 +165,62 @@ static bool gtp_check_src_ms_ipv4(struct sk_buff *skb, struct pdp_ctx *pctx,
iph = (struct iphdr *)(skb->data + hdrlen);
- return iph->saddr == pctx->ms_addr_ip4.s_addr;
+ if (role == GTP_ROLE_SGSN)
+ return iph->daddr == pctx->ms_addr_ip4.s_addr;
+ else
+ return iph->saddr == pctx->ms_addr_ip4.s_addr;
}
-/* Check if the inner IP source address in this packet is assigned to any
+/* Check if the inner IP address in this packet is assigned to any
* existing mobile subscriber.
*/
-static bool gtp_check_src_ms(struct sk_buff *skb, struct pdp_ctx *pctx,
- unsigned int hdrlen)
+static bool gtp_check_ms(struct sk_buff *skb, struct pdp_ctx *pctx,
+ unsigned int hdrlen, unsigned int role)
{
switch (ntohs(skb->protocol)) {
case ETH_P_IP:
- return gtp_check_src_ms_ipv4(skb, pctx, hdrlen);
+ return gtp_check_ms_ipv4(skb, pctx, hdrlen, role);
}
return false;
}
+static int gtp_rx(struct pdp_ctx *pctx, struct sk_buff *skb,
+ unsigned int hdrlen, unsigned int role)
+{
+ struct pcpu_sw_netstats *stats;
+
+ if (!gtp_check_ms(skb, pctx, hdrlen, role)) {
+ netdev_dbg(pctx->dev, "No PDP ctx for this MS\n");
+ return 1;
+ }
+
+ /* Get rid of the GTP + UDP headers. */
+ if (iptunnel_pull_header(skb, hdrlen, skb->protocol,
+ !net_eq(sock_net(pctx->sk), dev_net(pctx->dev))))
+ return -1;
+
+ netdev_dbg(pctx->dev, "forwarding packet from GGSN to uplink\n");
+
+ /* Now that the UDP and the GTP header have been removed, set up the
+ * new network header. This is required by the upper layer to
+ * calculate the transport header.
+ */
+ skb_reset_network_header(skb);
+
+ skb->dev = pctx->dev;
+
+ stats = this_cpu_ptr(pctx->dev->tstats);
+ u64_stats_update_begin(&stats->syncp);
+ stats->rx_packets++;
+ stats->rx_bytes += skb->len;
+ u64_stats_update_end(&stats->syncp);
+
+ netif_rx(skb);
+ return 0;
+}
+
/* 1 means pass up to the stack, -1 means drop and 0 means decapsulated. */
-static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb,
- bool xnet)
+static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb)
{
unsigned int hdrlen = sizeof(struct udphdr) +
sizeof(struct gtp0_header);
@@ -201,17 +244,10 @@ static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb,
return 1;
}
- if (!gtp_check_src_ms(skb, pctx, hdrlen)) {
- netdev_dbg(gtp->dev, "No PDP ctx for this MS\n");
- return 1;
- }
-
- /* Get rid of the GTP + UDP headers. */
- return iptunnel_pull_header(skb, hdrlen, skb->protocol, xnet);
+ return gtp_rx(pctx, skb, hdrlen, gtp->role);
}
-static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb,
- bool xnet)
+static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb)
{
unsigned int hdrlen = sizeof(struct udphdr) +
sizeof(struct gtp1_header);
@@ -250,28 +286,7 @@ static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb,
return 1;
}
- if (!gtp_check_src_ms(skb, pctx, hdrlen)) {
- netdev_dbg(gtp->dev, "No PDP ctx for this MS\n");
- return 1;
- }
-
- /* Get rid of the GTP + UDP headers. */
- return iptunnel_pull_header(skb, hdrlen, skb->protocol, xnet);
-}
-
-static void gtp_encap_disable(struct gtp_dev *gtp)
-{
- if (gtp->sock0 && gtp->sock0->sk) {
- udp_sk(gtp->sock0->sk)->encap_type = 0;
- rcu_assign_sk_user_data(gtp->sock0->sk, NULL);
- }
- if (gtp->sock1u && gtp->sock1u->sk) {
- udp_sk(gtp->sock1u->sk)->encap_type = 0;
- rcu_assign_sk_user_data(gtp->sock1u->sk, NULL);
- }
-
- gtp->sock0 = NULL;
- gtp->sock1u = NULL;
+ return gtp_rx(pctx, skb, hdrlen, gtp->role);
}
static void gtp_encap_destroy(struct sock *sk)
@@ -279,8 +294,25 @@ static void gtp_encap_destroy(struct sock *sk)
struct gtp_dev *gtp;
gtp = rcu_dereference_sk_user_data(sk);
- if (gtp)
- gtp_encap_disable(gtp);
+ if (gtp) {
+ udp_sk(sk)->encap_type = 0;
+ rcu_assign_sk_user_data(sk, NULL);
+ sock_put(sk);
+ }
+}
+
+static void gtp_encap_disable_sock(struct sock *sk)
+{
+ if (!sk)
+ return;
+
+ gtp_encap_destroy(sk);
+}
+
+static void gtp_encap_disable(struct gtp_dev *gtp)
+{
+ gtp_encap_disable_sock(gtp->sk0);
+ gtp_encap_disable_sock(gtp->sk1u);
}
/* UDP encapsulation receive handler. See net/ipv4/udp.c.
@@ -288,10 +320,8 @@ static void gtp_encap_destroy(struct sock *sk)
*/
static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb)
{
- struct pcpu_sw_netstats *stats;
struct gtp_dev *gtp;
- bool xnet;
- int ret;
+ int ret = 0;
gtp = rcu_dereference_sk_user_data(sk);
if (!gtp)
@@ -299,16 +329,14 @@ static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb)
netdev_dbg(gtp->dev, "encap_recv sk=%p\n", sk);
- xnet = !net_eq(sock_net(sk), dev_net(gtp->dev));
-
switch (udp_sk(sk)->encap_type) {
case UDP_ENCAP_GTP0:
netdev_dbg(gtp->dev, "received GTP0 packet\n");
- ret = gtp0_udp_encap_recv(gtp, skb, xnet);
+ ret = gtp0_udp_encap_recv(gtp, skb);
break;
case UDP_ENCAP_GTP1U:
netdev_dbg(gtp->dev, "received GTP1U packet\n");
- ret = gtp1u_udp_encap_recv(gtp, skb, xnet);
+ ret = gtp1u_udp_encap_recv(gtp, skb);
break;
default:
ret = -1; /* Shouldn't happen. */
@@ -317,33 +345,17 @@ static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb)
switch (ret) {
case 1:
netdev_dbg(gtp->dev, "pass up to the process\n");
- return 1;
+ break;
case 0:
- netdev_dbg(gtp->dev, "forwarding packet from GGSN to uplink\n");
break;
case -1:
netdev_dbg(gtp->dev, "GTP packet has been dropped\n");
kfree_skb(skb);
- return 0;
+ ret = 0;
+ break;
}
- /* Now that the UDP and the GTP header have been removed, set up the
- * new network header. This is required by the upper layer to
- * calculate the transport header.
- */
- skb_reset_network_header(skb);
-
- skb->dev = gtp->dev;
-
- stats = this_cpu_ptr(gtp->dev->tstats);
- u64_stats_update_begin(&stats->syncp);
- stats->rx_packets++;
- stats->rx_bytes += skb->len;
- u64_stats_update_end(&stats->syncp);
-
- netif_rx(skb);
-
- return 0;
+ return ret;
}
static int gtp_dev_init(struct net_device *dev)
@@ -367,8 +379,9 @@ static void gtp_dev_uninit(struct net_device *dev)
free_percpu(dev->tstats);
}
-static struct rtable *ip4_route_output_gtp(struct net *net, struct flowi4 *fl4,
- const struct sock *sk, __be32 daddr)
+static struct rtable *ip4_route_output_gtp(struct flowi4 *fl4,
+ const struct sock *sk,
+ __be32 daddr)
{
memset(fl4, 0, sizeof(*fl4));
fl4->flowi4_oif = sk->sk_bound_dev_if;
@@ -377,7 +390,7 @@ static struct rtable *ip4_route_output_gtp(struct net *net, struct flowi4 *fl4,
fl4->flowi4_tos = RT_CONN_FLAGS(sk);
fl4->flowi4_proto = sk->sk_protocol;
- return ip_route_output_key(net, fl4);
+ return ip_route_output_key(sock_net(sk), fl4);
}
static inline void gtp0_push_header(struct sk_buff *skb, struct pdp_ctx *pctx)
@@ -466,7 +479,6 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
struct rtable *rt;
struct flowi4 fl4;
struct iphdr *iph;
- struct sock *sk;
__be16 df;
int mtu;
@@ -474,7 +486,11 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
* Prepend PDP header with TEI/TID from PDP ctx.
*/
iph = ip_hdr(skb);
- pctx = ipv4_pdp_find(gtp, iph->daddr);
+ if (gtp->role == GTP_ROLE_SGSN)
+ pctx = ipv4_pdp_find(gtp, iph->saddr);
+ else
+ pctx = ipv4_pdp_find(gtp, iph->daddr);
+
if (!pctx) {
netdev_dbg(dev, "no PDP ctx found for %pI4, skip\n",
&iph->daddr);
@@ -482,40 +498,17 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
}
netdev_dbg(dev, "found PDP context %p\n", pctx);
- switch (pctx->gtp_version) {
- case GTP_V0:
- if (gtp->sock0)
- sk = gtp->sock0->sk;
- else
- sk = NULL;
- break;
- case GTP_V1:
- if (gtp->sock1u)
- sk = gtp->sock1u->sk;
- else
- sk = NULL;
- break;
- default:
- return -ENOENT;
- }
-
- if (!sk) {
- netdev_dbg(dev, "no userspace socket is available, skip\n");
- return -ENOENT;
- }
-
- rt = ip4_route_output_gtp(sock_net(sk), &fl4, gtp->sock0->sk,
- pctx->sgsn_addr_ip4.s_addr);
+ rt = ip4_route_output_gtp(&fl4, pctx->sk, pctx->peer_addr_ip4.s_addr);
if (IS_ERR(rt)) {
netdev_dbg(dev, "no route to SSGN %pI4\n",
- &pctx->sgsn_addr_ip4.s_addr);
+ &pctx->peer_addr_ip4.s_addr);
dev->stats.tx_carrier_errors++;
goto err;
}
if (rt->dst.dev == dev) {
netdev_dbg(dev, "circular route to SSGN %pI4\n",
- &pctx->sgsn_addr_ip4.s_addr);
+ &pctx->peer_addr_ip4.s_addr);
dev->stats.collisions++;
goto err_rt;
}
@@ -550,7 +543,7 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
goto err_rt;
}
- gtp_set_pktinfo_ipv4(pktinfo, sk, iph, pctx, rt, &fl4, dev);
+ gtp_set_pktinfo_ipv4(pktinfo, pctx->sk, iph, pctx, rt, &fl4, dev);
gtp_push_header(skb, pktinfo);
return 0;
@@ -640,27 +633,23 @@ static void gtp_link_setup(struct net_device *dev)
static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize);
static void gtp_hashtable_free(struct gtp_dev *gtp);
-static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp,
- int fd_gtp0, int fd_gtp1);
+static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]);
static int gtp_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
- int hashsize, err, fd0, fd1;
struct gtp_dev *gtp;
struct gtp_net *gn;
+ int hashsize, err;
- if (!data[IFLA_GTP_FD0] || !data[IFLA_GTP_FD1])
+ if (!data[IFLA_GTP_FD0] && !data[IFLA_GTP_FD1])
return -EINVAL;
gtp = netdev_priv(dev);
- fd0 = nla_get_u32(data[IFLA_GTP_FD0]);
- fd1 = nla_get_u32(data[IFLA_GTP_FD1]);
-
- err = gtp_encap_enable(dev, gtp, fd0, fd1);
+ err = gtp_encap_enable(gtp, data);
if (err < 0)
- goto out_err;
+ return err;
if (!data[IFLA_GTP_PDP_HASHSIZE])
hashsize = 1024;
@@ -688,7 +677,6 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev,
gtp_hashtable_free(gtp);
out_encap:
gtp_encap_disable(gtp);
-out_err:
return err;
}
@@ -706,6 +694,7 @@ static const struct nla_policy gtp_policy[IFLA_GTP_MAX + 1] = {
[IFLA_GTP_FD0] = { .type = NLA_U32 },
[IFLA_GTP_FD1] = { .type = NLA_U32 },
[IFLA_GTP_PDP_HASHSIZE] = { .type = NLA_U32 },
+ [IFLA_GTP_ROLE] = { .type = NLA_U32 },
};
static int gtp_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -747,21 +736,6 @@ static struct rtnl_link_ops gtp_link_ops __read_mostly = {
.fill_info = gtp_fill_info,
};
-static struct net *gtp_genl_get_net(struct net *src_net, struct nlattr *tb[])
-{
- struct net *net;
-
- /* Examine the link attributes and figure out which network namespace
- * we are talking about.
- */
- if (tb[GTPA_NET_NS_FD])
- net = get_net_ns_by_fd(nla_get_u32(tb[GTPA_NET_NS_FD]));
- else
- net = get_net(src_net);
-
- return net;
-}
-
static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize)
{
int i;
@@ -791,93 +765,127 @@ static void gtp_hashtable_free(struct gtp_dev *gtp)
struct pdp_ctx *pctx;
int i;
- for (i = 0; i < gtp->hash_size; i++) {
- hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) {
- hlist_del_rcu(&pctx->hlist_tid);
- hlist_del_rcu(&pctx->hlist_addr);
- kfree_rcu(pctx, rcu_head);
- }
- }
+ for (i = 0; i < gtp->hash_size; i++)
+ hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid)
+ pdp_context_delete(pctx);
+
synchronize_rcu();
kfree(gtp->addr_hash);
kfree(gtp->tid_hash);
}
-static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp,
- int fd_gtp0, int fd_gtp1)
+static struct sock *gtp_encap_enable_socket(int fd, int type,
+ struct gtp_dev *gtp)
{
struct udp_tunnel_sock_cfg tuncfg = {NULL};
- struct socket *sock0, *sock1u;
+ struct socket *sock;
+ struct sock *sk;
int err;
- netdev_dbg(dev, "enable gtp on %d, %d\n", fd_gtp0, fd_gtp1);
+ pr_debug("enable gtp on %d, %d\n", fd, type);
- sock0 = sockfd_lookup(fd_gtp0, &err);
- if (sock0 == NULL) {
- netdev_dbg(dev, "socket fd=%d not found (gtp0)\n", fd_gtp0);
- return -ENOENT;
+ sock = sockfd_lookup(fd, &err);
+ if (!sock) {
+ pr_debug("gtp socket fd=%d not found\n", fd);
+ return NULL;
}
- if (sock0->sk->sk_protocol != IPPROTO_UDP) {
- netdev_dbg(dev, "socket fd=%d not UDP\n", fd_gtp0);
- err = -EINVAL;
- goto err1;
+ if (sock->sk->sk_protocol != IPPROTO_UDP) {
+ pr_debug("socket fd=%d not UDP\n", fd);
+ sk = ERR_PTR(-EINVAL);
+ goto out_sock;
}
- sock1u = sockfd_lookup(fd_gtp1, &err);
- if (sock1u == NULL) {
- netdev_dbg(dev, "socket fd=%d not found (gtp1u)\n", fd_gtp1);
- err = -ENOENT;
- goto err1;
+ if (rcu_dereference_sk_user_data(sock->sk)) {
+ sk = ERR_PTR(-EBUSY);
+ goto out_sock;
}
- if (sock1u->sk->sk_protocol != IPPROTO_UDP) {
- netdev_dbg(dev, "socket fd=%d not UDP\n", fd_gtp1);
- err = -EINVAL;
- goto err2;
- }
-
- netdev_dbg(dev, "enable gtp on %p, %p\n", sock0, sock1u);
-
- gtp->sock0 = sock0;
- gtp->sock1u = sock1u;
+ sk = sock->sk;
+ sock_hold(sk);
tuncfg.sk_user_data = gtp;
+ tuncfg.encap_type = type;
tuncfg.encap_rcv = gtp_encap_recv;
tuncfg.encap_destroy = gtp_encap_destroy;
- tuncfg.encap_type = UDP_ENCAP_GTP0;
- setup_udp_tunnel_sock(sock_net(gtp->sock0->sk), gtp->sock0, &tuncfg);
+ setup_udp_tunnel_sock(sock_net(sock->sk), sock, &tuncfg);
- tuncfg.encap_type = UDP_ENCAP_GTP1U;
- setup_udp_tunnel_sock(sock_net(gtp->sock1u->sk), gtp->sock1u, &tuncfg);
-
- err = 0;
-err2:
- sockfd_put(sock1u);
-err1:
- sockfd_put(sock0);
- return err;
+out_sock:
+ sockfd_put(sock);
+ return sk;
}
-static struct net_device *gtp_find_dev(struct net *net, int ifindex)
+static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[])
{
- struct gtp_net *gn = net_generic(net, gtp_net_id);
- struct gtp_dev *gtp;
+ struct sock *sk1u = NULL;
+ struct sock *sk0 = NULL;
+ unsigned int role = GTP_ROLE_GGSN;
- list_for_each_entry_rcu(gtp, &gn->gtp_dev_list, list) {
- if (ifindex == gtp->dev->ifindex)
- return gtp->dev;
+ if (data[IFLA_GTP_FD0]) {
+ u32 fd0 = nla_get_u32(data[IFLA_GTP_FD0]);
+
+ sk0 = gtp_encap_enable_socket(fd0, UDP_ENCAP_GTP0, gtp);
+ if (IS_ERR(sk0))
+ return PTR_ERR(sk0);
}
- return NULL;
+
+ if (data[IFLA_GTP_FD1]) {
+ u32 fd1 = nla_get_u32(data[IFLA_GTP_FD1]);
+
+ sk1u = gtp_encap_enable_socket(fd1, UDP_ENCAP_GTP1U, gtp);
+ if (IS_ERR(sk1u)) {
+ if (sk0)
+ gtp_encap_disable_sock(sk0);
+ return PTR_ERR(sk1u);
+ }
+ }
+
+ if (data[IFLA_GTP_ROLE]) {
+ role = nla_get_u32(data[IFLA_GTP_ROLE]);
+ if (role > GTP_ROLE_SGSN)
+ return -EINVAL;
+ }
+
+ gtp->sk0 = sk0;
+ gtp->sk1u = sk1u;
+ gtp->role = role;
+
+ return 0;
+}
+
+static struct gtp_dev *gtp_find_dev(struct net *src_net, struct nlattr *nla[])
+{
+ struct gtp_dev *gtp = NULL;
+ struct net_device *dev;
+ struct net *net;
+
+ /* Examine the link attributes and figure out which network namespace
+ * we are talking about.
+ */
+ if (nla[GTPA_NET_NS_FD])
+ net = get_net_ns_by_fd(nla_get_u32(nla[GTPA_NET_NS_FD]));
+ else
+ net = get_net(src_net);
+
+ if (IS_ERR(net))
+ return NULL;
+
+ /* Check if there's an existing gtpX device to configure */
+ dev = dev_get_by_index_rcu(net, nla_get_u32(nla[GTPA_LINK]));
+ if (dev->netdev_ops == >p_netdev_ops)
+ gtp = netdev_priv(dev);
+
+ put_net(net);
+ return gtp;
}
static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info)
{
pctx->gtp_version = nla_get_u32(info->attrs[GTPA_VERSION]);
pctx->af = AF_INET;
- pctx->sgsn_addr_ip4.s_addr =
- nla_get_be32(info->attrs[GTPA_SGSN_ADDRESS]);
+ pctx->peer_addr_ip4.s_addr =
+ nla_get_be32(info->attrs[GTPA_PEER_ADDRESS]);
pctx->ms_addr_ip4.s_addr =
nla_get_be32(info->attrs[GTPA_MS_ADDRESS]);
@@ -899,9 +907,10 @@ static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info)
}
}
-static int ipv4_pdp_add(struct net_device *dev, struct genl_info *info)
+static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk,
+ struct genl_info *info)
{
- struct gtp_dev *gtp = netdev_priv(dev);
+ struct net_device *dev = gtp->dev;
u32 hash_ms, hash_tid = 0;
struct pdp_ctx *pctx;
bool found = false;
@@ -940,6 +949,9 @@ static int ipv4_pdp_add(struct net_device *dev, struct genl_info *info)
if (pctx == NULL)
return -ENOMEM;
+ sock_hold(sk);
+ pctx->sk = sk;
+ pctx->dev = gtp->dev;
ipv4_pdp_fill(pctx, info);
atomic_set(&pctx->tx_seq, 0);
@@ -963,31 +975,50 @@ static int ipv4_pdp_add(struct net_device *dev, struct genl_info *info)
switch (pctx->gtp_version) {
case GTP_V0:
netdev_dbg(dev, "GTPv0-U: new PDP ctx id=%llx ssgn=%pI4 ms=%pI4 (pdp=%p)\n",
- pctx->u.v0.tid, &pctx->sgsn_addr_ip4,
+ pctx->u.v0.tid, &pctx->peer_addr_ip4,
&pctx->ms_addr_ip4, pctx);
break;
case GTP_V1:
netdev_dbg(dev, "GTPv1-U: new PDP ctx id=%x/%x ssgn=%pI4 ms=%pI4 (pdp=%p)\n",
pctx->u.v1.i_tei, pctx->u.v1.o_tei,
- &pctx->sgsn_addr_ip4, &pctx->ms_addr_ip4, pctx);
+ &pctx->peer_addr_ip4, &pctx->ms_addr_ip4, pctx);
break;
}
return 0;
}
+static void pdp_context_free(struct rcu_head *head)
+{
+ struct pdp_ctx *pctx = container_of(head, struct pdp_ctx, rcu_head);
+
+ sock_put(pctx->sk);
+ kfree(pctx);
+}
+
+static void pdp_context_delete(struct pdp_ctx *pctx)
+{
+ hlist_del_rcu(&pctx->hlist_tid);
+ hlist_del_rcu(&pctx->hlist_addr);
+ call_rcu(&pctx->rcu_head, pdp_context_free);
+}
+
static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info)
{
- struct net_device *dev;
- struct net *net;
+ unsigned int version;
+ struct gtp_dev *gtp;
+ struct sock *sk;
+ int err;
if (!info->attrs[GTPA_VERSION] ||
!info->attrs[GTPA_LINK] ||
- !info->attrs[GTPA_SGSN_ADDRESS] ||
+ !info->attrs[GTPA_PEER_ADDRESS] ||
!info->attrs[GTPA_MS_ADDRESS])
return -EINVAL;
- switch (nla_get_u32(info->attrs[GTPA_VERSION])) {
+ version = nla_get_u32(info->attrs[GTPA_VERSION]);
+
+ switch (version) {
case GTP_V0:
if (!info->attrs[GTPA_TID] ||
!info->attrs[GTPA_FLOW])
@@ -1003,77 +1034,101 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info)
return -EINVAL;
}
- net = gtp_genl_get_net(sock_net(skb->sk), info->attrs);
- if (IS_ERR(net))
- return PTR_ERR(net);
+ rcu_read_lock();
- /* Check if there's an existing gtpX device to configure */
- dev = gtp_find_dev(net, nla_get_u32(info->attrs[GTPA_LINK]));
- if (dev == NULL) {
- put_net(net);
- return -ENODEV;
+ gtp = gtp_find_dev(sock_net(skb->sk), info->attrs);
+ if (!gtp) {
+ err = -ENODEV;
+ goto out_unlock;
}
- put_net(net);
- return ipv4_pdp_add(dev, info);
+ if (version == GTP_V0)
+ sk = gtp->sk0;
+ else if (version == GTP_V1)
+ sk = gtp->sk1u;
+ else
+ sk = NULL;
+
+ if (!sk) {
+ err = -ENODEV;
+ goto out_unlock;
+ }
+
+ err = ipv4_pdp_add(gtp, sk, info);
+
+out_unlock:
+ rcu_read_unlock();
+ return err;
+}
+
+static struct pdp_ctx *gtp_find_pdp_by_link(struct net *net,
+ struct nlattr *nla[])
+{
+ struct gtp_dev *gtp;
+
+ gtp = gtp_find_dev(net, nla);
+ if (!gtp)
+ return ERR_PTR(-ENODEV);
+
+ if (nla[GTPA_MS_ADDRESS]) {
+ __be32 ip = nla_get_be32(nla[GTPA_MS_ADDRESS]);
+
+ return ipv4_pdp_find(gtp, ip);
+ } else if (nla[GTPA_VERSION]) {
+ u32 gtp_version = nla_get_u32(nla[GTPA_VERSION]);
+
+ if (gtp_version == GTP_V0 && nla[GTPA_TID])
+ return gtp0_pdp_find(gtp, nla_get_u64(nla[GTPA_TID]));
+ else if (gtp_version == GTP_V1 && nla[GTPA_I_TEI])
+ return gtp1_pdp_find(gtp, nla_get_u32(nla[GTPA_I_TEI]));
+ }
+
+ return ERR_PTR(-EINVAL);
+}
+
+static struct pdp_ctx *gtp_find_pdp(struct net *net, struct nlattr *nla[])
+{
+ struct pdp_ctx *pctx;
+
+ if (nla[GTPA_LINK])
+ pctx = gtp_find_pdp_by_link(net, nla);
+ else
+ pctx = ERR_PTR(-EINVAL);
+
+ if (!pctx)
+ pctx = ERR_PTR(-ENOENT);
+
+ return pctx;
}
static int gtp_genl_del_pdp(struct sk_buff *skb, struct genl_info *info)
{
- struct net_device *dev;
struct pdp_ctx *pctx;
- struct gtp_dev *gtp;
- struct net *net;
+ int err = 0;
- if (!info->attrs[GTPA_VERSION] ||
- !info->attrs[GTPA_LINK])
+ if (!info->attrs[GTPA_VERSION])
return -EINVAL;
- net = gtp_genl_get_net(sock_net(skb->sk), info->attrs);
- if (IS_ERR(net))
- return PTR_ERR(net);
+ rcu_read_lock();
- /* Check if there's an existing gtpX device to configure */
- dev = gtp_find_dev(net, nla_get_u32(info->attrs[GTPA_LINK]));
- if (dev == NULL) {
- put_net(net);
- return -ENODEV;
+ pctx = gtp_find_pdp(sock_net(skb->sk), info->attrs);
+ if (IS_ERR(pctx)) {
+ err = PTR_ERR(pctx);
+ goto out_unlock;
}
- put_net(net);
-
- gtp = netdev_priv(dev);
-
- switch (nla_get_u32(info->attrs[GTPA_VERSION])) {
- case GTP_V0:
- if (!info->attrs[GTPA_TID])
- return -EINVAL;
- pctx = gtp0_pdp_find(gtp, nla_get_u64(info->attrs[GTPA_TID]));
- break;
- case GTP_V1:
- if (!info->attrs[GTPA_I_TEI])
- return -EINVAL;
- pctx = gtp1_pdp_find(gtp, nla_get_u64(info->attrs[GTPA_I_TEI]));
- break;
-
- default:
- return -EINVAL;
- }
-
- if (pctx == NULL)
- return -ENOENT;
if (pctx->gtp_version == GTP_V0)
- netdev_dbg(dev, "GTPv0-U: deleting tunnel id = %llx (pdp %p)\n",
+ netdev_dbg(pctx->dev, "GTPv0-U: deleting tunnel id = %llx (pdp %p)\n",
pctx->u.v0.tid, pctx);
else if (pctx->gtp_version == GTP_V1)
- netdev_dbg(dev, "GTPv1-U: deleting tunnel id = %x/%x (pdp %p)\n",
+ netdev_dbg(pctx->dev, "GTPv1-U: deleting tunnel id = %x/%x (pdp %p)\n",
pctx->u.v1.i_tei, pctx->u.v1.o_tei, pctx);
- hlist_del_rcu(&pctx->hlist_tid);
- hlist_del_rcu(&pctx->hlist_addr);
- kfree_rcu(pctx, rcu_head);
+ pdp_context_delete(pctx);
- return 0;
+out_unlock:
+ rcu_read_unlock();
+ return err;
}
static struct genl_family gtp_genl_family;
@@ -1089,7 +1144,7 @@ static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq,
goto nlmsg_failure;
if (nla_put_u32(skb, GTPA_VERSION, pctx->gtp_version) ||
- nla_put_be32(skb, GTPA_SGSN_ADDRESS, pctx->sgsn_addr_ip4.s_addr) ||
+ nla_put_be32(skb, GTPA_PEER_ADDRESS, pctx->peer_addr_ip4.s_addr) ||
nla_put_be32(skb, GTPA_MS_ADDRESS, pctx->ms_addr_ip4.s_addr))
goto nla_put_failure;
@@ -1117,59 +1172,17 @@ static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq,
static int gtp_genl_get_pdp(struct sk_buff *skb, struct genl_info *info)
{
struct pdp_ctx *pctx = NULL;
- struct net_device *dev;
struct sk_buff *skb2;
- struct gtp_dev *gtp;
- u32 gtp_version;
- struct net *net;
int err;
- if (!info->attrs[GTPA_VERSION] ||
- !info->attrs[GTPA_LINK])
+ if (!info->attrs[GTPA_VERSION])
return -EINVAL;
- gtp_version = nla_get_u32(info->attrs[GTPA_VERSION]);
- switch (gtp_version) {
- case GTP_V0:
- case GTP_V1:
- break;
- default:
- return -EINVAL;
- }
-
- net = gtp_genl_get_net(sock_net(skb->sk), info->attrs);
- if (IS_ERR(net))
- return PTR_ERR(net);
-
- /* Check if there's an existing gtpX device to configure */
- dev = gtp_find_dev(net, nla_get_u32(info->attrs[GTPA_LINK]));
- if (dev == NULL) {
- put_net(net);
- return -ENODEV;
- }
- put_net(net);
-
- gtp = netdev_priv(dev);
-
rcu_read_lock();
- if (gtp_version == GTP_V0 &&
- info->attrs[GTPA_TID]) {
- u64 tid = nla_get_u64(info->attrs[GTPA_TID]);
- pctx = gtp0_pdp_find(gtp, tid);
- } else if (gtp_version == GTP_V1 &&
- info->attrs[GTPA_I_TEI]) {
- u32 tid = nla_get_u32(info->attrs[GTPA_I_TEI]);
-
- pctx = gtp1_pdp_find(gtp, tid);
- } else if (info->attrs[GTPA_MS_ADDRESS]) {
- __be32 ip = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]);
-
- pctx = ipv4_pdp_find(gtp, ip);
- }
-
- if (pctx == NULL) {
- err = -ENOENT;
+ pctx = gtp_find_pdp(sock_net(skb->sk), info->attrs);
+ if (IS_ERR(pctx)) {
+ err = PTR_ERR(pctx);
goto err_unlock;
}
@@ -1242,7 +1255,7 @@ static struct nla_policy gtp_genl_policy[GTPA_MAX + 1] = {
[GTPA_LINK] = { .type = NLA_U32, },
[GTPA_VERSION] = { .type = NLA_U32, },
[GTPA_TID] = { .type = NLA_U64, },
- [GTPA_SGSN_ADDRESS] = { .type = NLA_U32, },
+ [GTPA_PEER_ADDRESS] = { .type = NLA_U32, },
[GTPA_MS_ADDRESS] = { .type = NLA_U32, },
[GTPA_FLOW] = { .type = NLA_U16, },
[GTPA_NET_NS_FD] = { .type = NLA_U32, },
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 7433b16..4747ad4 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -686,7 +686,7 @@ struct net_device_context {
/* point back to our device context */
struct hv_device *device_ctx;
/* netvsc_device */
- struct netvsc_device *nvdev;
+ struct netvsc_device __rcu *nvdev;
/* reconfigure work */
struct delayed_work dwork;
/* last reconfig time */
@@ -701,14 +701,13 @@ struct net_device_context {
u32 tx_checksum_mask;
+ u32 tx_send_table[VRSS_SEND_TAB_SIZE];
+
/* Ethtool settings */
u8 duplex;
u32 speed;
struct netvsc_ethtool_stats eth_stats;
- /* the device is going away */
- bool start_remove;
-
/* State to manage the associated VF interface. */
struct net_device __rcu *vf_netdev;
@@ -721,6 +720,7 @@ struct net_device_context {
/* Per channel data */
struct netvsc_channel {
struct vmbus_channel *channel;
+ const struct vmpacket_descriptor *desc;
struct napi_struct napi;
struct multi_send_data msd;
struct multi_recv_comp mrc;
@@ -759,11 +759,10 @@ struct netvsc_device {
struct nvsp_message revoke_packet;
- u32 send_table[VRSS_SEND_TAB_SIZE];
u32 max_chn;
u32 num_chn;
- spinlock_t sc_lock; /* Protects num_sc_offered variable */
- u32 num_sc_offered;
+
+ refcount_t sc_offered;
/* Holds rndis device info */
void *extension;
@@ -778,6 +777,8 @@ struct netvsc_device {
atomic_t open_cnt;
struct netvsc_channel chan_table[VRSS_CHANNEL_MAX];
+
+ struct rcu_head rcu;
};
static inline struct netvsc_device *
@@ -1426,9 +1427,6 @@ struct rndis_message {
((void *) rndis_msg)
-#define __struct_bcount(x)
-
-
#define RNDIS_HEADER_SIZE (sizeof(struct rndis_message) - \
sizeof(union rndis_message_container))
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index b1328ce..7ab06b3 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -80,8 +80,10 @@ static struct netvsc_device *alloc_net_device(void)
return net_device;
}
-static void free_netvsc_device(struct netvsc_device *nvdev)
+static void free_netvsc_device(struct rcu_head *head)
{
+ struct netvsc_device *nvdev
+ = container_of(head, struct netvsc_device, rcu);
int i;
for (i = 0; i < VRSS_CHANNEL_MAX; i++)
@@ -90,14 +92,9 @@ static void free_netvsc_device(struct netvsc_device *nvdev)
kfree(nvdev);
}
-
-static inline bool netvsc_channel_idle(const struct netvsc_device *net_device,
- u16 q_idx)
+static void free_netvsc_device_rcu(struct netvsc_device *nvdev)
{
- const struct netvsc_channel *nvchan = &net_device->chan_table[q_idx];
-
- return atomic_read(&net_device->num_outstanding_recvs) == 0 &&
- atomic_read(&nvchan->queue_sends) == 0;
+ call_rcu(&nvdev->rcu, free_netvsc_device);
}
static struct netvsc_device *get_outbound_net_device(struct hv_device *device)
@@ -560,7 +557,7 @@ void netvsc_device_remove(struct hv_device *device)
netvsc_disconnect_vsp(device);
- net_device_ctx->nvdev = NULL;
+ RCU_INIT_POINTER(net_device_ctx->nvdev, NULL);
/*
* At this point, no one should be accessing net_device
@@ -571,11 +568,11 @@ void netvsc_device_remove(struct hv_device *device)
/* Now, we can close the channel safely */
vmbus_close(device->channel);
- for (i = 0; i < VRSS_CHANNEL_MAX; i++)
- napi_disable(&net_device->chan_table[0].napi);
+ for (i = 0; i < net_device->num_chn; i++)
+ napi_disable(&net_device->chan_table[i].napi);
/* Release all resources */
- free_netvsc_device(net_device);
+ free_netvsc_device_rcu(net_device);
}
#define RING_AVAIL_PERCENT_HIWATER 20
@@ -608,7 +605,6 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device,
{
struct sk_buff *skb = (struct sk_buff *)(unsigned long)desc->trans_id;
struct net_device *ndev = hv_get_drvdata(device);
- struct net_device_context *net_device_ctx = netdev_priv(ndev);
struct vmbus_channel *channel = device->channel;
u16 q_idx = 0;
int queue_sends;
@@ -642,7 +638,6 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device,
wake_up(&net_device->wait_drain);
if (netif_tx_queue_stopped(netdev_get_tx_queue(ndev, q_idx)) &&
- !net_device_ctx->start_remove &&
(hv_ringbuf_avail_percent(&channel->outbound) > RING_AVAIL_PERCENT_HIWATER ||
queue_sends < 1))
netif_tx_wake_queue(netdev_get_tx_queue(ndev, q_idx));
@@ -711,8 +706,7 @@ static u32 netvsc_copy_to_send_buf(struct netvsc_device *net_device,
packet->page_buf_cnt;
/* Add padding */
- if (skb && skb->xmit_more && remain &&
- !packet->cp_partial) {
+ if (skb->xmit_more && remain && !packet->cp_partial) {
padding = net_device->pkt_align - remain;
rndis_msg->msg_len += padding;
packet->total_data_buflen += padding;
@@ -870,9 +864,7 @@ int netvsc_send(struct hv_device *device,
if (msdp->pkt)
msd_len = msdp->pkt->total_data_buflen;
- try_batch = (skb != NULL) && msd_len > 0 && msdp->count <
- net_device->max_pkt;
-
+ try_batch = msd_len > 0 && msdp->count < net_device->max_pkt;
if (try_batch && msd_len + pktlen + net_device->pkt_align <
net_device->send_section_size) {
section_index = msdp->pkt->send_buf_index;
@@ -882,7 +874,7 @@ int netvsc_send(struct hv_device *device,
section_index = msdp->pkt->send_buf_index;
packet->cp_partial = true;
- } else if ((skb != NULL) && pktlen + net_device->pkt_align <
+ } else if (pktlen + net_device->pkt_align <
net_device->send_section_size) {
section_index = netvsc_get_next_send_section(net_device);
if (section_index != NETVSC_INVALID_INDEX) {
@@ -1138,15 +1130,11 @@ static int netvsc_receive(struct net_device *ndev,
static void netvsc_send_table(struct hv_device *hdev,
struct nvsp_message *nvmsg)
{
- struct netvsc_device *nvscdev;
struct net_device *ndev = hv_get_drvdata(hdev);
+ struct net_device_context *net_device_ctx = netdev_priv(ndev);
int i;
u32 count, *tab;
- nvscdev = get_outbound_net_device(hdev);
- if (!nvscdev)
- return;
-
count = nvmsg->msg.v5_msg.send_table.count;
if (count != VRSS_SEND_TAB_SIZE) {
netdev_err(ndev, "Received wrong send-table size:%u\n", count);
@@ -1157,7 +1145,7 @@ static void netvsc_send_table(struct hv_device *hdev,
nvmsg->msg.v5_msg.send_table.offset);
for (i = 0; i < count; i++)
- nvscdev->send_table[i] = tab[i];
+ net_device_ctx->tx_send_table[i] = tab[i];
}
static void netvsc_send_vf(struct net_device_context *net_device_ctx,
@@ -1186,7 +1174,6 @@ static int netvsc_process_raw_pkt(struct hv_device *device,
struct vmbus_channel *channel,
struct netvsc_device *net_device,
struct net_device *ndev,
- u64 request_id,
const struct vmpacket_descriptor *desc)
{
struct net_device_context *net_device_ctx = netdev_priv(ndev);
@@ -1208,7 +1195,7 @@ static int netvsc_process_raw_pkt(struct hv_device *device,
default:
netdev_err(ndev, "unhandled packet type %d, tid %llx\n",
- desc->type, request_id);
+ desc->type, desc->trans_id);
break;
}
@@ -1222,6 +1209,10 @@ static struct hv_device *netvsc_channel_to_device(struct vmbus_channel *channel)
return primary ? primary->device_obj : channel->device_obj;
}
+/* Network processing softirq
+ * Process data in incoming ring buffer from host
+ * Stops when ring is empty or budget is met or exceeded.
+ */
int netvsc_poll(struct napi_struct *napi, int budget)
{
struct netvsc_channel *nvchan
@@ -1231,56 +1222,47 @@ int netvsc_poll(struct napi_struct *napi, int budget)
u16 q_idx = channel->offermsg.offer.sub_channel_index;
struct net_device *ndev = hv_get_drvdata(device);
struct netvsc_device *net_device = net_device_to_netvsc_device(ndev);
- const struct vmpacket_descriptor *desc;
int work_done = 0;
- desc = hv_pkt_iter_first(channel);
- while (desc) {
- int count;
+ /* If starting a new interval */
+ if (!nvchan->desc)
+ nvchan->desc = hv_pkt_iter_first(channel);
- count = netvsc_process_raw_pkt(device, channel, net_device,
- ndev, desc->trans_id, desc);
- work_done += count;
- desc = __hv_pkt_iter_next(channel, desc);
-
- /* If receive packet budget is exhausted, reschedule */
- if (work_done >= budget) {
- work_done = budget;
- break;
- }
+ while (nvchan->desc && work_done < budget) {
+ work_done += netvsc_process_raw_pkt(device, channel, net_device,
+ ndev, nvchan->desc);
+ nvchan->desc = hv_pkt_iter_next(channel, nvchan->desc);
}
- hv_pkt_iter_close(channel);
- /* If ring is empty and NAPI is not doing polling */
+ /* If receive ring was exhausted
+ * and not doing busy poll
+ * then re-enable host interrupts
+ * and reschedule if ring is not empty.
+ */
if (work_done < budget &&
napi_complete_done(napi, work_done) &&
hv_end_read(&channel->inbound) != 0)
napi_reschedule(napi);
netvsc_chk_recv_comp(net_device, channel, q_idx);
- return work_done;
+
+ /* Driver may overshoot since multiple packets per descriptor */
+ return min(work_done, budget);
}
+/* Call back when data is available in host ring buffer.
+ * Processing is deferred until network softirq (NAPI)
+ */
void netvsc_channel_cb(void *context)
{
- struct vmbus_channel *channel = context;
- struct hv_device *device = netvsc_channel_to_device(channel);
- u16 q_idx = channel->offermsg.offer.sub_channel_index;
- struct netvsc_device *net_device;
- struct net_device *ndev;
+ struct netvsc_channel *nvchan = context;
- ndev = hv_get_drvdata(device);
- if (unlikely(!ndev))
- return;
+ if (napi_schedule_prep(&nvchan->napi)) {
+ /* disable interupts from host */
+ hv_begin_read(&nvchan->channel->inbound);
- net_device = net_device_to_netvsc_device(ndev);
- if (unlikely(net_device->destroy) &&
- netvsc_channel_idle(net_device, q_idx))
- return;
-
- /* disable interupts from host */
- hv_begin_read(&channel->inbound);
- napi_schedule(&net_device->chan_table[q_idx].napi);
+ __napi_schedule(&nvchan->napi);
+ }
}
/*
@@ -1307,10 +1289,26 @@ int netvsc_device_add(struct hv_device *device,
*/
set_channel_read_mode(device->channel, HV_CALL_ISR);
+ /* If we're reopening the device we may have multiple queues, fill the
+ * chn_table with the default channel to use it before subchannels are
+ * opened.
+ * Initialize the channel state before we open;
+ * we can be interrupted as soon as we open the channel.
+ */
+
+ for (i = 0; i < VRSS_CHANNEL_MAX; i++) {
+ struct netvsc_channel *nvchan = &net_device->chan_table[i];
+
+ nvchan->channel = device->channel;
+ netif_napi_add(ndev, &nvchan->napi,
+ netvsc_poll, NAPI_POLL_WEIGHT);
+ }
+
/* Open the channel */
ret = vmbus_open(device->channel, ring_size * PAGE_SIZE,
ring_size * PAGE_SIZE, NULL, 0,
- netvsc_channel_cb, device->channel);
+ netvsc_channel_cb,
+ net_device->chan_table);
if (ret != 0) {
netdev_err(ndev, "unable to open channel: %d\n", ret);
@@ -1320,27 +1318,13 @@ int netvsc_device_add(struct hv_device *device,
/* Channel is opened */
netdev_dbg(ndev, "hv_netvsc channel opened successfully\n");
- /* If we're reopening the device we may have multiple queues, fill the
- * chn_table with the default channel to use it before subchannels are
- * opened.
- */
- for (i = 0; i < VRSS_CHANNEL_MAX; i++) {
- struct netvsc_channel *nvchan = &net_device->chan_table[i];
-
- nvchan->channel = device->channel;
- netif_napi_add(ndev, &nvchan->napi,
- netvsc_poll, NAPI_POLL_WEIGHT);
- }
-
/* Enable NAPI handler for init callbacks */
napi_enable(&net_device->chan_table[0].napi);
/* Writing nvdev pointer unlocks netvsc_send(), make sure chn_table is
* populated.
*/
- wmb();
-
- net_device_ctx->nvdev = net_device;
+ rcu_assign_pointer(net_device_ctx->nvdev, net_device);
/* Connect with the NetVsp */
ret = netvsc_connect_vsp(device);
@@ -1359,7 +1343,7 @@ int netvsc_device_add(struct hv_device *device,
vmbus_close(device->channel);
cleanup:
- free_netvsc_device(net_device);
+ free_netvsc_device(&net_device->rcu);
return ret;
}
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 617dd90..f24c289 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -62,7 +62,7 @@ static void do_set_multicast(struct work_struct *w)
container_of(w, struct net_device_context, work);
struct hv_device *device_obj = ndevctx->device_ctx;
struct net_device *ndev = hv_get_drvdata(device_obj);
- struct netvsc_device *nvdev = ndevctx->nvdev;
+ struct netvsc_device *nvdev = rcu_dereference(ndevctx->nvdev);
struct rndis_device *rdev;
if (!nvdev)
@@ -116,7 +116,7 @@ static int netvsc_open(struct net_device *net)
static int netvsc_close(struct net_device *net)
{
struct net_device_context *net_device_ctx = netdev_priv(net);
- struct netvsc_device *nvdev = net_device_ctx->nvdev;
+ struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);
int ret;
u32 aread, awrite, i, msec = 10, retry = 0, retry_max = 20;
struct vmbus_channel *chn;
@@ -206,17 +206,15 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
void *accel_priv, select_queue_fallback_t fallback)
{
struct net_device_context *net_device_ctx = netdev_priv(ndev);
- struct netvsc_device *nvsc_dev = net_device_ctx->nvdev;
+ unsigned int num_tx_queues = ndev->real_num_tx_queues;
struct sock *sk = skb->sk;
int q_idx = sk_tx_queue_get(sk);
- if (q_idx < 0 || skb->ooo_okay ||
- q_idx >= ndev->real_num_tx_queues) {
+ if (q_idx < 0 || skb->ooo_okay || q_idx >= num_tx_queues) {
u16 hash = __skb_tx_hash(ndev, skb, VRSS_SEND_TAB_SIZE);
int new_idx;
- new_idx = nvsc_dev->send_table[hash]
- % nvsc_dev->num_chn;
+ new_idx = net_device_ctx->tx_send_table[hash] % num_tx_queues;
if (q_idx != new_idx && sk &&
sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache))
@@ -225,9 +223,6 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
q_idx = new_idx;
}
- if (unlikely(!nvsc_dev->chan_table[q_idx].channel))
- q_idx = 0;
-
return q_idx;
}
@@ -642,9 +637,9 @@ int netvsc_recv_callback(struct net_device *net,
const struct ndis_pkt_8021q_info *vlan)
{
struct net_device_context *net_device_ctx = netdev_priv(net);
- struct netvsc_device *net_device = net_device_ctx->nvdev;
+ struct netvsc_device *net_device;
u16 q_idx = channel->offermsg.offer.sub_channel_index;
- struct netvsc_channel *nvchan = &net_device->chan_table[q_idx];
+ struct netvsc_channel *nvchan;
struct net_device *vf_netdev;
struct sk_buff *skb;
struct netvsc_stats *rx_stats;
@@ -660,6 +655,11 @@ int netvsc_recv_callback(struct net_device *net,
* interface in the guest.
*/
rcu_read_lock();
+ net_device = rcu_dereference(net_device_ctx->nvdev);
+ if (unlikely(!net_device))
+ goto drop;
+
+ nvchan = &net_device->chan_table[q_idx];
vf_netdev = rcu_dereference(net_device_ctx->vf_netdev);
if (vf_netdev && (vf_netdev->flags & IFF_UP))
net = vf_netdev;
@@ -668,6 +668,7 @@ int netvsc_recv_callback(struct net_device *net,
skb = netvsc_alloc_recv_skb(net, &nvchan->napi,
csum_info, vlan, data, len);
if (unlikely(!skb)) {
+drop:
++net->stats.rx_dropped;
rcu_read_unlock();
return NVSP_STAT_FAIL;
@@ -709,7 +710,7 @@ static void netvsc_get_channels(struct net_device *net,
struct ethtool_channels *channel)
{
struct net_device_context *net_device_ctx = netdev_priv(net);
- struct netvsc_device *nvdev = net_device_ctx->nvdev;
+ struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);
if (nvdev) {
channel->max_combined = nvdev->max_chn;
@@ -746,8 +747,9 @@ static int netvsc_set_channels(struct net_device *net,
{
struct net_device_context *net_device_ctx = netdev_priv(net);
struct hv_device *dev = net_device_ctx->device_ctx;
- struct netvsc_device *nvdev = net_device_ctx->nvdev;
+ struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);
unsigned int count = channels->combined_count;
+ bool was_running;
int ret;
/* We do not support separate count for rx, tx, or other */
@@ -758,7 +760,7 @@ static int netvsc_set_channels(struct net_device *net,
if (count > net->num_tx_queues || count > net->num_rx_queues)
return -EINVAL;
- if (net_device_ctx->start_remove || !nvdev || nvdev->destroy)
+ if (!nvdev || nvdev->destroy)
return -ENODEV;
if (nvdev->nvsp_version < NVSP_PROTOCOL_VERSION_5)
@@ -767,11 +769,13 @@ static int netvsc_set_channels(struct net_device *net,
if (count > nvdev->max_chn)
return -EINVAL;
- ret = netvsc_close(net);
- if (ret)
- return ret;
+ was_running = netif_running(net);
+ if (was_running) {
+ ret = netvsc_close(net);
+ if (ret)
+ return ret;
+ }
- net_device_ctx->start_remove = true;
rndis_filter_device_remove(dev, nvdev);
ret = netvsc_set_queues(net, dev, count);
@@ -780,8 +784,8 @@ static int netvsc_set_channels(struct net_device *net,
else
netvsc_set_queues(net, dev, nvdev->num_chn);
- netvsc_open(net);
- net_device_ctx->start_remove = false;
+ if (was_running)
+ ret = netvsc_open(net);
/* We may have missed link change notifications */
schedule_delayed_work(&net_device_ctx->dwork, 0);
@@ -789,18 +793,19 @@ static int netvsc_set_channels(struct net_device *net,
return ret;
}
-static bool netvsc_validate_ethtool_ss_cmd(const struct ethtool_cmd *cmd)
+static bool
+netvsc_validate_ethtool_ss_cmd(const struct ethtool_link_ksettings *cmd)
{
- struct ethtool_cmd diff1 = *cmd;
- struct ethtool_cmd diff2 = {};
+ struct ethtool_link_ksettings diff1 = *cmd;
+ struct ethtool_link_ksettings diff2 = {};
- ethtool_cmd_speed_set(&diff1, 0);
- diff1.duplex = 0;
+ diff1.base.speed = 0;
+ diff1.base.duplex = 0;
/* advertising and cmd are usually set */
- diff1.advertising = 0;
- diff1.cmd = 0;
+ ethtool_link_ksettings_zero_link_mode(&diff1, advertising);
+ diff1.base.cmd = 0;
/* We set port to PORT_OTHER */
- diff2.port = PORT_OTHER;
+ diff2.base.port = PORT_OTHER;
return !memcmp(&diff1, &diff2, sizeof(diff1));
}
@@ -813,30 +818,32 @@ static void netvsc_init_settings(struct net_device *dev)
ndc->duplex = DUPLEX_UNKNOWN;
}
-static int netvsc_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int netvsc_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
struct net_device_context *ndc = netdev_priv(dev);
- ethtool_cmd_speed_set(cmd, ndc->speed);
- cmd->duplex = ndc->duplex;
- cmd->port = PORT_OTHER;
+ cmd->base.speed = ndc->speed;
+ cmd->base.duplex = ndc->duplex;
+ cmd->base.port = PORT_OTHER;
return 0;
}
-static int netvsc_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int netvsc_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
{
struct net_device_context *ndc = netdev_priv(dev);
u32 speed;
- speed = ethtool_cmd_speed(cmd);
+ speed = cmd->base.speed;
if (!ethtool_validate_speed(speed) ||
- !ethtool_validate_duplex(cmd->duplex) ||
+ !ethtool_validate_duplex(cmd->base.duplex) ||
!netvsc_validate_ethtool_ss_cmd(cmd))
return -EINVAL;
ndc->speed = speed;
- ndc->duplex = cmd->duplex;
+ ndc->duplex = cmd->base.duplex;
return 0;
}
@@ -844,24 +851,27 @@ static int netvsc_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
static int netvsc_change_mtu(struct net_device *ndev, int mtu)
{
struct net_device_context *ndevctx = netdev_priv(ndev);
- struct netvsc_device *nvdev = ndevctx->nvdev;
+ struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev);
struct hv_device *hdev = ndevctx->device_ctx;
struct netvsc_device_info device_info;
- int ret;
+ bool was_running;
+ int ret = 0;
- if (ndevctx->start_remove || !nvdev || nvdev->destroy)
+ if (!nvdev || nvdev->destroy)
return -ENODEV;
- ret = netvsc_close(ndev);
- if (ret)
- goto out;
+ was_running = netif_running(ndev);
+ if (was_running) {
+ ret = netvsc_close(ndev);
+ if (ret)
+ return ret;
+ }
memset(&device_info, 0, sizeof(device_info));
device_info.ring_size = ring_size;
device_info.num_chn = nvdev->num_chn;
device_info.max_num_vrss_chns = nvdev->num_chn;
- ndevctx->start_remove = true;
rndis_filter_device_remove(hdev, nvdev);
/* 'nvdev' has been freed in rndis_filter_device_remove() ->
@@ -874,9 +884,8 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
rndis_filter_device_add(hdev, &device_info);
-out:
- netvsc_open(ndev);
- ndevctx->start_remove = false;
+ if (was_running)
+ ret = netvsc_open(ndev);
/* We may have missed link change notifications */
schedule_delayed_work(&ndevctx->dwork, 0);
@@ -888,7 +897,7 @@ static void netvsc_get_stats64(struct net_device *net,
struct rtnl_link_stats64 *t)
{
struct net_device_context *ndev_ctx = netdev_priv(net);
- struct netvsc_device *nvdev = ndev_ctx->nvdev;
+ struct netvsc_device *nvdev = rcu_dereference(ndev_ctx->nvdev);
int i;
if (!nvdev)
@@ -973,7 +982,10 @@ static const struct {
static int netvsc_get_sset_count(struct net_device *dev, int string_set)
{
struct net_device_context *ndc = netdev_priv(dev);
- struct netvsc_device *nvdev = ndc->nvdev;
+ struct netvsc_device *nvdev = rcu_dereference(ndc->nvdev);
+
+ if (!nvdev)
+ return -ENODEV;
switch (string_set) {
case ETH_SS_STATS:
@@ -987,13 +999,16 @@ static void netvsc_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 *data)
{
struct net_device_context *ndc = netdev_priv(dev);
- struct netvsc_device *nvdev = ndc->nvdev;
+ struct netvsc_device *nvdev = rcu_dereference(ndc->nvdev);
const void *nds = &ndc->eth_stats;
const struct netvsc_stats *qstats;
unsigned int start;
u64 packets, bytes;
int i, j;
+ if (!nvdev)
+ return;
+
for (i = 0; i < NETVSC_GLOBAL_STATS_LEN; i++)
data[i] = *(unsigned long *)(nds + netvsc_stats[i].offset);
@@ -1022,10 +1037,13 @@ static void netvsc_get_ethtool_stats(struct net_device *dev,
static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
{
struct net_device_context *ndc = netdev_priv(dev);
- struct netvsc_device *nvdev = ndc->nvdev;
+ struct netvsc_device *nvdev = rcu_dereference(ndc->nvdev);
u8 *p = data;
int i;
+ if (!nvdev)
+ return;
+
switch (stringset) {
case ETH_SS_STATS:
for (i = 0; i < ARRAY_SIZE(netvsc_stats); i++)
@@ -1077,7 +1095,10 @@ netvsc_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
u32 *rules)
{
struct net_device_context *ndc = netdev_priv(dev);
- struct netvsc_device *nvdev = ndc->nvdev;
+ struct netvsc_device *nvdev = rcu_dereference(ndc->nvdev);
+
+ if (!nvdev)
+ return -ENODEV;
switch (info->cmd) {
case ETHTOOL_GRXRINGS:
@@ -1113,13 +1134,17 @@ static int netvsc_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
u8 *hfunc)
{
struct net_device_context *ndc = netdev_priv(dev);
- struct netvsc_device *ndev = ndc->nvdev;
- struct rndis_device *rndis_dev = ndev->extension;
+ struct netvsc_device *ndev = rcu_dereference(ndc->nvdev);
+ struct rndis_device *rndis_dev;
int i;
+ if (!ndev)
+ return -ENODEV;
+
if (hfunc)
*hfunc = ETH_RSS_HASH_TOP; /* Toeplitz */
+ rndis_dev = ndev->extension;
if (indir) {
for (i = 0; i < ITAB_NUM; i++)
indir[i] = rndis_dev->ind_table[i];
@@ -1135,13 +1160,17 @@ static int netvsc_set_rxfh(struct net_device *dev, const u32 *indir,
const u8 *key, const u8 hfunc)
{
struct net_device_context *ndc = netdev_priv(dev);
- struct netvsc_device *ndev = ndc->nvdev;
- struct rndis_device *rndis_dev = ndev->extension;
+ struct netvsc_device *ndev = rtnl_dereference(ndc->nvdev);
+ struct rndis_device *rndis_dev;
int i;
+ if (!ndev)
+ return -ENODEV;
+
if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
return -EOPNOTSUPP;
+ rndis_dev = ndev->extension;
if (indir) {
for (i = 0; i < ITAB_NUM; i++)
if (indir[i] >= dev->num_rx_queues)
@@ -1170,13 +1199,13 @@ static const struct ethtool_ops ethtool_ops = {
.get_channels = netvsc_get_channels,
.set_channels = netvsc_set_channels,
.get_ts_info = ethtool_op_get_ts_info,
- .get_settings = netvsc_get_settings,
- .set_settings = netvsc_set_settings,
.get_rxnfc = netvsc_get_rxnfc,
.get_rxfh_key_size = netvsc_get_rxfh_key_size,
.get_rxfh_indir_size = netvsc_rss_indir_size,
.get_rxfh = netvsc_get_rxfh,
.set_rxfh = netvsc_set_rxfh,
+ .get_link_ksettings = netvsc_get_link_ksettings,
+ .set_link_ksettings = netvsc_set_link_ksettings,
};
static const struct net_device_ops device_ops = {
@@ -1212,10 +1241,10 @@ static void netvsc_link_change(struct work_struct *w)
unsigned long flags, next_reconfig, delay;
rtnl_lock();
- if (ndev_ctx->start_remove)
+ net_device = rtnl_dereference(ndev_ctx->nvdev);
+ if (!net_device)
goto out_unlock;
- net_device = ndev_ctx->nvdev;
rdev = net_device->extension;
next_reconfig = ndev_ctx->last_reconfig + LINKCHANGE_INT;
@@ -1356,7 +1385,7 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
return NOTIFY_DONE;
net_device_ctx = netdev_priv(ndev);
- netvsc_dev = net_device_ctx->nvdev;
+ netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
if (!netvsc_dev || rtnl_dereference(net_device_ctx->vf_netdev))
return NOTIFY_DONE;
@@ -1382,7 +1411,7 @@ static int netvsc_vf_up(struct net_device *vf_netdev)
return NOTIFY_DONE;
net_device_ctx = netdev_priv(ndev);
- netvsc_dev = net_device_ctx->nvdev;
+ netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
netdev_info(ndev, "VF up: %s\n", vf_netdev->name);
@@ -1416,7 +1445,7 @@ static int netvsc_vf_down(struct net_device *vf_netdev)
return NOTIFY_DONE;
net_device_ctx = netdev_priv(ndev);
- netvsc_dev = net_device_ctx->nvdev;
+ netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
netdev_info(ndev, "VF down: %s\n", vf_netdev->name);
netvsc_switch_datapath(ndev, false);
@@ -1476,8 +1505,6 @@ static int netvsc_probe(struct hv_device *dev,
hv_set_drvdata(dev, net);
- net_device_ctx->start_remove = false;
-
INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change);
INIT_WORK(&net_device_ctx->work, do_set_multicast);
@@ -1494,8 +1521,7 @@ static int netvsc_probe(struct hv_device *dev,
/* Notify the netvsc driver of the new device */
memset(&device_info, 0, sizeof(device_info));
device_info.ring_size = ring_size;
- device_info.max_num_vrss_chns = min_t(u32, VRSS_CHANNEL_DEFAULT,
- num_online_cpus());
+ device_info.num_chn = VRSS_CHANNEL_DEFAULT;
ret = rndis_filter_device_add(dev, &device_info);
if (ret != 0) {
netdev_err(net, "unable to add netvsc device (ret %d)\n", ret);
@@ -1511,6 +1537,7 @@ static int netvsc_probe(struct hv_device *dev,
NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
net->vlan_features = net->features;
+ /* RCU not necessary here, device not registered */
nvdev = net_device_ctx->nvdev;
netif_set_real_num_tx_queues(net, nvdev->num_chn);
netif_set_real_num_rx_queues(net, nvdev->num_chn);
@@ -1546,26 +1573,20 @@ static int netvsc_remove(struct hv_device *dev)
ndev_ctx = netdev_priv(net);
- /* Avoid racing with netvsc_change_mtu()/netvsc_set_channels()
- * removing the device.
- */
- rtnl_lock();
- ndev_ctx->start_remove = true;
- rtnl_unlock();
+ netif_device_detach(net);
cancel_delayed_work_sync(&ndev_ctx->dwork);
cancel_work_sync(&ndev_ctx->work);
- /* Stop outbound asap */
- netif_tx_disable(net);
-
- unregister_netdev(net);
-
/*
* Call to the vsc driver to let it know that the device is being
- * removed
+ * removed. Also blocks mtu and channel changes.
*/
+ rtnl_lock();
rndis_filter_device_remove(dev, ndev_ctx->nvdev);
+ rtnl_unlock();
+
+ unregister_netdev(net);
hv_set_drvdata(dev, NULL);
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index d7b6311..1e9445b 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -819,16 +819,14 @@ int rndis_filter_set_packet_filter(struct rndis_device *dev, u32 new_filter)
{
struct rndis_request *request;
struct rndis_set_request *set;
- struct rndis_set_complete *set_complete;
int ret;
request = get_rndis_request(dev, RNDIS_MSG_SET,
RNDIS_MESSAGE_SIZE(struct rndis_set_request) +
sizeof(u32));
- if (!request) {
- ret = -ENOMEM;
- goto cleanup;
- }
+ if (!request)
+ return -ENOMEM;
+
/* Setup the rndis set */
set = &request->request_msg.msg.set_req;
@@ -840,15 +838,11 @@ int rndis_filter_set_packet_filter(struct rndis_device *dev, u32 new_filter)
&new_filter, sizeof(u32));
ret = rndis_filter_send_request(dev, request);
- if (ret != 0)
- goto cleanup;
+ if (ret == 0)
+ wait_for_completion(&request->wait_event);
- wait_for_completion(&request->wait_event);
+ put_rndis_request(dev, request);
- set_complete = &request->response_msg.msg.set_complete;
-cleanup:
- if (request)
- put_rndis_request(dev, request);
return ret;
}
@@ -926,8 +920,6 @@ static void rndis_filter_halt_device(struct rndis_device *dev)
struct rndis_halt_request *halt;
struct net_device_context *net_device_ctx = netdev_priv(dev->ndev);
struct netvsc_device *nvdev = net_device_ctx->nvdev;
- struct hv_device *hdev = net_device_ctx->device_ctx;
- ulong flags;
/* Attempt to do a rndis device halt */
request = get_rndis_request(dev, RNDIS_MSG_HALT,
@@ -945,9 +937,10 @@ static void rndis_filter_halt_device(struct rndis_device *dev)
dev->state = RNDIS_DEV_UNINITIALIZED;
cleanup:
- spin_lock_irqsave(&hdev->channel->inbound_lock, flags);
nvdev->destroy = true;
- spin_unlock_irqrestore(&hdev->channel->inbound_lock, flags);
+
+ /* Force flag to be ordered before waiting */
+ wmb();
/* Wait for all send completions */
wait_event(nvdev->wait_drain, netvsc_device_idle(nvdev));
@@ -996,28 +989,35 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc)
hv_get_drvdata(new_sc->primary_channel->device_obj);
struct netvsc_device *nvscdev = net_device_to_netvsc_device(ndev);
u16 chn_index = new_sc->offermsg.offer.sub_channel_index;
+ struct netvsc_channel *nvchan;
int ret;
- unsigned long flags;
if (chn_index >= nvscdev->num_chn)
return;
- nvscdev->chan_table[chn_index].mrc.buf
+ nvchan = nvscdev->chan_table + chn_index;
+ nvchan->mrc.buf
= vzalloc(NETVSC_RECVSLOT_MAX * sizeof(struct recv_comp_data));
+ if (!nvchan->mrc.buf)
+ return;
+
+ /* Because the device uses NAPI, all the interrupt batching and
+ * control is done via Net softirq, not the channel handling
+ */
+ set_channel_read_mode(new_sc, HV_CALL_ISR);
+
+ /* Set the channel before opening.*/
+ nvchan->channel = new_sc;
+
ret = vmbus_open(new_sc, nvscdev->ring_size * PAGE_SIZE,
nvscdev->ring_size * PAGE_SIZE, NULL, 0,
- netvsc_channel_cb, new_sc);
+ netvsc_channel_cb, nvchan);
- if (ret == 0)
- nvscdev->chan_table[chn_index].channel = new_sc;
- napi_enable(&nvscdev->chan_table[chn_index].napi);
+ napi_enable(&nvchan->napi);
- spin_lock_irqsave(&nvscdev->sc_lock, flags);
- nvscdev->num_sc_offered--;
- spin_unlock_irqrestore(&nvscdev->sc_lock, flags);
- if (nvscdev->num_sc_offered == 0)
+ if (refcount_dec_and_test(&nvscdev->sc_offered))
complete(&nvscdev->channel_init_wait);
}
@@ -1034,12 +1034,9 @@ int rndis_filter_device_add(struct hv_device *dev,
struct ndis_recv_scale_cap rsscap;
u32 rsscap_size = sizeof(struct ndis_recv_scale_cap);
unsigned int gso_max_size = GSO_MAX_SIZE;
- u32 mtu, size;
- u32 num_rss_qs;
- u32 sc_delta;
+ u32 mtu, size, num_rss_qs;
const struct cpumask *node_cpu_mask;
u32 num_possible_rss_qs;
- unsigned long flags;
int i, ret;
rndis_device = get_rndis_device();
@@ -1062,7 +1059,7 @@ int rndis_filter_device_add(struct hv_device *dev,
net_device->max_chn = 1;
net_device->num_chn = 1;
- spin_lock_init(&net_device->sc_lock);
+ refcount_set(&net_device->sc_offered, 0);
net_device->extension = rndis_device;
rndis_device->ndev = net;
@@ -1176,34 +1173,30 @@ int rndis_filter_device_add(struct hv_device *dev,
if (ret || rsscap.num_recv_que < 2)
goto out;
- net_device->max_chn = min_t(u32, VRSS_CHANNEL_MAX, rsscap.num_recv_que);
-
- num_rss_qs = min(device_info->max_num_vrss_chns, net_device->max_chn);
-
/*
* We will limit the VRSS channels to the number CPUs in the NUMA node
* the primary channel is currently bound to.
+ *
+ * This also guarantees that num_possible_rss_qs <= num_online_cpus
*/
node_cpu_mask = cpumask_of_node(cpu_to_node(dev->channel->target_cpu));
- num_possible_rss_qs = cpumask_weight(node_cpu_mask);
+ num_possible_rss_qs = min_t(u32, cpumask_weight(node_cpu_mask),
+ rsscap.num_recv_que);
+
+ net_device->max_chn = min_t(u32, VRSS_CHANNEL_MAX, num_possible_rss_qs);
/* We will use the given number of channels if available. */
- if (device_info->num_chn && device_info->num_chn < net_device->max_chn)
- net_device->num_chn = device_info->num_chn;
- else
- net_device->num_chn = min(num_possible_rss_qs, num_rss_qs);
-
- num_rss_qs = net_device->num_chn - 1;
+ net_device->num_chn = min(net_device->max_chn, device_info->num_chn);
for (i = 0; i < ITAB_NUM; i++)
rndis_device->ind_table[i] = ethtool_rxfh_indir_default(i,
net_device->num_chn);
- net_device->num_sc_offered = num_rss_qs;
+ num_rss_qs = net_device->num_chn - 1;
+ if (num_rss_qs == 0)
+ return 0;
- if (net_device->num_chn == 1)
- goto out;
-
+ refcount_set(&net_device->sc_offered, num_rss_qs);
vmbus_set_sc_create_callback(dev->channel, netvsc_sc_open);
init_packet = &net_device->channel_init_pkt;
@@ -1219,32 +1212,23 @@ int rndis_filter_device_add(struct hv_device *dev,
VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
if (ret)
goto out;
- wait_for_completion(&net_device->channel_init_wait);
- if (init_packet->msg.v5_msg.subchn_comp.status !=
- NVSP_STAT_SUCCESS) {
+ if (init_packet->msg.v5_msg.subchn_comp.status != NVSP_STAT_SUCCESS) {
ret = -ENODEV;
goto out;
}
+ wait_for_completion(&net_device->channel_init_wait);
+
net_device->num_chn = 1 +
init_packet->msg.v5_msg.subchn_comp.num_subchannels;
- ret = rndis_filter_set_rss_param(rndis_device, netvsc_hash_key,
- net_device->num_chn);
-
- /*
- * Set the number of sub-channels to be received.
- */
- spin_lock_irqsave(&net_device->sc_lock, flags);
- sc_delta = num_rss_qs - (net_device->num_chn - 1);
- net_device->num_sc_offered -= sc_delta;
- spin_unlock_irqrestore(&net_device->sc_lock, flags);
-
+ /* ignore failues from setting rss parameters, still have channels */
+ rndis_filter_set_rss_param(rndis_device, netvsc_hash_key,
+ net_device->num_chn);
out:
if (ret) {
net_device->max_chn = 1;
net_device->num_chn = 1;
- net_device->num_sc_offered = 0;
}
return 0; /* return 0 because primary channel can be used alone */
@@ -1259,12 +1243,6 @@ void rndis_filter_device_remove(struct hv_device *dev,
{
struct rndis_device *rndis_dev = net_dev->extension;
- /* If not all subchannel offers are complete, wait for them until
- * completion to avoid race.
- */
- if (net_dev->num_sc_offered > 0)
- wait_for_completion(&net_dev->channel_init_wait);
-
/* Halt and release the rndis device */
rndis_filter_halt_device(rndis_dev);
diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c
index 7b131f8..bd63289 100644
--- a/drivers/net/ieee802154/mrf24j40.c
+++ b/drivers/net/ieee802154/mrf24j40.c
@@ -18,6 +18,7 @@
#include <linux/spi/spi.h>
#include <linux/interrupt.h>
#include <linux/module.h>
+#include <linux/of.h>
#include <linux/regmap.h>
#include <linux/ieee802154.h>
#include <linux/irq.h>
diff --git a/drivers/net/irda/vlsi_ir.c b/drivers/net/irda/vlsi_ir.c
index ffedad2..15b9200 100644
--- a/drivers/net/irda/vlsi_ir.c
+++ b/drivers/net/irda/vlsi_ir.c
@@ -418,8 +418,9 @@ static struct vlsi_ring *vlsi_alloc_ring(struct pci_dev *pdev, struct ring_descr
memset(rd, 0, sizeof(*rd));
rd->hw = hwmap + i;
rd->buf = kmalloc(len, GFP_KERNEL|GFP_DMA);
- if (rd->buf == NULL ||
- !(busaddr = pci_map_single(pdev, rd->buf, len, dir))) {
+ if (rd->buf)
+ busaddr = pci_map_single(pdev, rd->buf, len, dir);
+ if (rd->buf == NULL || pci_dma_mapping_error(pdev, busaddr)) {
if (rd->buf) {
net_err_ratelimited("%s: failed to create PCI-MAP for %p\n",
__func__, rd->buf);
@@ -430,8 +431,7 @@ static struct vlsi_ring *vlsi_alloc_ring(struct pci_dev *pdev, struct ring_descr
rd = r->rd + j;
busaddr = rd_get_addr(rd);
rd_set_addr_status(rd, 0, 0);
- if (busaddr)
- pci_unmap_single(pdev, busaddr, len, dir);
+ pci_unmap_single(pdev, busaddr, len, dir);
kfree(rd->buf);
rd->buf = NULL;
}
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index b23b719..224f65c 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -13,7 +13,7 @@
*
* Alan Cox : Fixed oddments for NET3.014
* Alan Cox : Rejig for NET3.029 snap #3
- * Alan Cox : Fixed NET3.029 bugs and sped up
+ * Alan Cox : Fixed NET3.029 bugs and sped up
* Larry McVoy : Tiny tweak to double performance
* Alan Cox : Backed out LMV's tweak - the linux mm
* can't take it...
@@ -41,7 +41,7 @@
#include <linux/in.h>
#include <linux/uaccess.h>
-#include <asm/io.h>
+#include <linux/io.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
@@ -55,6 +55,7 @@
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/percpu.h>
+#include <linux/net_tstamp.h>
#include <net/net_namespace.h>
#include <linux/u64_stats_sync.h>
@@ -64,8 +65,7 @@ struct pcpu_lstats {
struct u64_stats_sync syncp;
};
-/*
- * The higher levels take care of making this non-reentrant (it's
+/* The higher levels take care of making this non-reentrant (it's
* called with bh's disabled).
*/
static netdev_tx_t loopback_xmit(struct sk_buff *skb,
@@ -74,6 +74,7 @@ static netdev_tx_t loopback_xmit(struct sk_buff *skb,
struct pcpu_lstats *lb_stats;
int len;
+ skb_tx_timestamp(skb);
skb_orphan(skb);
/* Before queueing this packet to netif_rx(),
@@ -129,8 +130,21 @@ static u32 always_on(struct net_device *dev)
return 1;
}
+static int loopback_get_ts_info(struct net_device *netdev,
+ struct ethtool_ts_info *ts_info)
+{
+ ts_info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+ SOF_TIMESTAMPING_RX_SOFTWARE |
+ SOF_TIMESTAMPING_SOFTWARE;
+
+ ts_info->phc_index = -1;
+
+ return 0;
+};
+
static const struct ethtool_ops loopback_ethtool_ops = {
.get_link = always_on,
+ .get_ts_info = loopback_get_ts_info,
};
static int loopback_dev_init(struct net_device *dev)
@@ -149,14 +163,13 @@ static void loopback_dev_free(struct net_device *dev)
}
static const struct net_device_ops loopback_ops = {
- .ndo_init = loopback_dev_init,
- .ndo_start_xmit= loopback_xmit,
+ .ndo_init = loopback_dev_init,
+ .ndo_start_xmit = loopback_xmit,
.ndo_get_stats64 = loopback_get_stats64,
.ndo_set_mac_address = eth_mac_addr,
};
-/*
- * The loopback device is special. There is only one instance
+/* The loopback device is special. There is only one instance
* per network namespace.
*/
static void loopback_setup(struct net_device *dev)
@@ -170,7 +183,7 @@ static void loopback_setup(struct net_device *dev)
dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
netif_keep_dst(dev);
dev->hw_features = NETIF_F_GSO_SOFTWARE;
- dev->features = NETIF_F_SG | NETIF_F_FRAGLIST
+ dev->features = NETIF_F_SG | NETIF_F_FRAGLIST
| NETIF_F_GSO_SOFTWARE
| NETIF_F_HW_CSUM
| NETIF_F_RXCSUM
@@ -206,7 +219,6 @@ static __net_init int loopback_net_init(struct net *net)
net->loopback_dev = dev;
return 0;
-
out_free_netdev:
free_netdev(dev);
out:
@@ -217,5 +229,5 @@ static __net_init int loopback_net_init(struct net *net)
/* Registered in net/core/dev.c */
struct pernet_operations __net_initdata loopback_net_ops = {
- .init = loopback_net_init,
+ .init = loopback_net_init,
};
diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c
index 36877ba..4daf3d0 100644
--- a/drivers/net/ntb_netdev.c
+++ b/drivers/net/ntb_netdev.c
@@ -372,18 +372,19 @@ static void ntb_get_drvinfo(struct net_device *ndev,
strlcpy(info->bus_info, pci_name(dev->pdev), sizeof(info->bus_info));
}
-static int ntb_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int ntb_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
- cmd->supported = SUPPORTED_Backplane;
- cmd->advertising = ADVERTISED_Backplane;
- ethtool_cmd_speed_set(cmd, SPEED_UNKNOWN);
- cmd->duplex = DUPLEX_FULL;
- cmd->port = PORT_OTHER;
- cmd->phy_address = 0;
- cmd->transceiver = XCVR_DUMMY1;
- cmd->autoneg = AUTONEG_ENABLE;
- cmd->maxtxpkt = 0;
- cmd->maxrxpkt = 0;
+ ethtool_link_ksettings_zero_link_mode(cmd, supported);
+ ethtool_link_ksettings_add_link_mode(cmd, supported, Backplane);
+ ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising, Backplane);
+
+ cmd->base.speed = SPEED_UNKNOWN;
+ cmd->base.duplex = DUPLEX_FULL;
+ cmd->base.port = PORT_OTHER;
+ cmd->base.phy_address = 0;
+ cmd->base.autoneg = AUTONEG_ENABLE;
return 0;
}
@@ -391,7 +392,7 @@ static int ntb_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
static const struct ethtool_ops ntb_ethtool_ops = {
.get_drvinfo = ntb_get_drvinfo,
.get_link = ethtool_op_get_link,
- .get_settings = ntb_get_settings,
+ .get_link_ksettings = ntb_get_link_ksettings,
};
static const struct ntb_queue_handlers ntb_netdev_handlers = {
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 8dbd59b..60ffc9d 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -2,33 +2,12 @@
# PHY Layer Configuration
#
-menuconfig PHYLIB
- tristate "PHY Device support and infrastructure"
- depends on NETDEVICES
+menuconfig MDIO_DEVICE
+ tristate "MDIO bus device drivers"
help
- Ethernet controllers are usually attached to PHY
- devices. This option provides infrastructure for
- managing PHY devices.
+ MDIO devices and driver infrastructure code.
-if PHYLIB
-
-config SWPHY
- bool
-
-config LED_TRIGGER_PHY
- bool "Support LED triggers for tracking link state"
- depends on LEDS_TRIGGERS
- ---help---
- Adds support for a set of LED trigger events per-PHY. Link
- state change will trigger the events, for consumption by an
- LED class driver. There are triggers for each link speed currently
- supported by the phy, and are of the form:
- <mii bus id>:<phy>:<speed>
-
- Where speed is in the form:
- <Speed in megabits>Mbps or <Speed in gigabits>Gbps
-
-comment "MDIO bus device drivers"
+if MDIO_DEVICE
config MDIO_BCM_IPROC
tristate "Broadcom iProc MDIO bus controller"
@@ -40,7 +19,7 @@
config MDIO_BCM_UNIMAC
tristate "Broadcom UniMAC MDIO bus controller"
- depends on HAS_IOMEM
+ depends on HAS_IOMEM && OF_MDIO
help
This module provides a driver for the Broadcom UniMAC MDIO busses.
This hardware can be found in the Broadcom GENET Ethernet MAC
@@ -49,6 +28,7 @@
config MDIO_BITBANG
tristate "Bitbanged MDIO buses"
+ depends on !(MDIO_DEVICE=y && PHYLIB=m)
help
This module implements the MDIO bus protocol in software,
for use by low level drivers that export the ability to
@@ -160,6 +140,36 @@
This module provides a driver for the MDIO busses found in the
APM X-Gene SoC's.
+endif
+
+menuconfig PHYLIB
+ tristate "PHY Device support and infrastructure"
+ depends on NETDEVICES
+ select MDIO_DEVICE
+ help
+ Ethernet controllers are usually attached to PHY
+ devices. This option provides infrastructure for
+ managing PHY devices.
+
+if PHYLIB
+
+config SWPHY
+ bool
+
+config LED_TRIGGER_PHY
+ bool "Support LED triggers for tracking link state"
+ depends on LEDS_TRIGGERS
+ ---help---
+ Adds support for a set of LED trigger events per-PHY. Link
+ state change will trigger the events, for consumption by an
+ LED class driver. There are triggers for each link speed currently
+ supported by the phy, and are of the form:
+ <mii bus id>:<phy>:<speed>
+
+ Where speed is in the form:
+ <Speed in megabits>Mbps or <Speed in gigabits>Gbps
+
+
comment "MII PHY device drivers"
config AMD_PHY
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index 407b0b6..e36db9a 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -1,7 +1,20 @@
# Makefile for Linux PHY drivers and MDIO bus drivers
-libphy-y := phy.o phy_device.o mdio_bus.o mdio_device.o \
- mdio-boardinfo.o
+libphy-y := phy.o phy-core.o phy_device.o
+mdio-bus-y += mdio_bus.o mdio_device.o
+
+ifdef CONFIG_MDIO_DEVICE
+obj-y += mdio-boardinfo.o
+endif
+
+# PHYLIB implies MDIO_DEVICE, in that case, we have a bunch of circular
+# dependencies that does not make it possible to split mdio-bus objects into a
+# dedicated loadable module, so we bundle them all together into libphy.ko
+ifdef CONFIG_PHYLIB
+libphy-y += $(mdio-bus-y)
+else
+obj-$(CONFIG_MDIO_DEVICE) += mdio-bus.o
+endif
libphy-$(CONFIG_SWPHY) += swphy.o
libphy-$(CONFIG_LED_TRIGGER_PHY) += phy_led_triggers.o
diff --git a/drivers/net/phy/bcm-phy-lib.c b/drivers/net/phy/bcm-phy-lib.c
index ab9ad68..171010e 100644
--- a/drivers/net/phy/bcm-phy-lib.c
+++ b/drivers/net/phy/bcm-phy-lib.c
@@ -1,5 +1,5 @@
/*
- * Copyright (C) 2015 Broadcom Corporation
+ * Copyright (C) 2015-2017 Broadcom
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
@@ -201,8 +201,7 @@ int bcm_phy_set_eee(struct phy_device *phydev, bool enable)
int val;
/* Enable EEE at PHY level */
- val = phy_read_mmd_indirect(phydev, BRCM_CL45VEN_EEE_CONTROL,
- MDIO_MMD_AN);
+ val = phy_read_mmd(phydev, MDIO_MMD_AN, BRCM_CL45VEN_EEE_CONTROL);
if (val < 0)
return val;
@@ -211,22 +210,19 @@ int bcm_phy_set_eee(struct phy_device *phydev, bool enable)
else
val &= ~(LPI_FEATURE_EN | LPI_FEATURE_EN_DIG1000X);
- phy_write_mmd_indirect(phydev, BRCM_CL45VEN_EEE_CONTROL,
- MDIO_MMD_AN, (u32)val);
+ phy_write_mmd(phydev, MDIO_MMD_AN, BRCM_CL45VEN_EEE_CONTROL, (u32)val);
/* Advertise EEE */
- val = phy_read_mmd_indirect(phydev, BCM_CL45VEN_EEE_ADV,
- MDIO_MMD_AN);
+ val = phy_read_mmd(phydev, MDIO_MMD_AN, BCM_CL45VEN_EEE_ADV);
if (val < 0)
return val;
if (enable)
- val |= (MDIO_AN_EEE_ADV_100TX | MDIO_AN_EEE_ADV_1000T);
+ val |= (MDIO_EEE_100TX | MDIO_EEE_1000T);
else
- val &= ~(MDIO_AN_EEE_ADV_100TX | MDIO_AN_EEE_ADV_1000T);
+ val &= ~(MDIO_EEE_100TX | MDIO_EEE_1000T);
- phy_write_mmd_indirect(phydev, BCM_CL45VEN_EEE_ADV,
- MDIO_MMD_AN, (u32)val);
+ phy_write_mmd(phydev, MDIO_MMD_AN, BCM_CL45VEN_EEE_ADV, (u32)val);
return 0;
}
diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index d1c2614..caa9f6e 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -1,7 +1,7 @@
/*
* Broadcom BCM7xxx internal transceivers support.
*
- * Copyright (C) 2014, Broadcom Corporation
+ * Copyright (C) 2014-2017 Broadcom
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
@@ -19,7 +19,7 @@
/* Broadcom BCM7xxx internal PHY registers */
-/* 40nm only register definitions */
+/* EPHY only register definitions */
#define MII_BCM7XXX_100TX_AUX_CTL 0x10
#define MII_BCM7XXX_100TX_FALSE_CAR 0x13
#define MII_BCM7XXX_100TX_DISC 0x14
@@ -27,6 +27,19 @@
#define MII_BCM7XXX_64CLK_MDIO BIT(12)
#define MII_BCM7XXX_TEST 0x1f
#define MII_BCM7XXX_SHD_MODE_2 BIT(2)
+#define MII_BCM7XXX_SHD_2_ADDR_CTRL 0xe
+#define MII_BCM7XXX_SHD_2_CTRL_STAT 0xf
+#define MII_BCM7XXX_SHD_2_BIAS_TRIM 0x1a
+#define MII_BCM7XXX_SHD_3_AN_EEE_ADV 0x3
+#define MII_BCM7XXX_SHD_3_PCS_CTRL_2 0x6
+#define MII_BCM7XXX_PCS_CTRL_2_DEF 0x4400
+#define MII_BCM7XXX_SHD_3_AN_STAT 0xb
+#define MII_BCM7XXX_AN_NULL_MSG_EN BIT(0)
+#define MII_BCM7XXX_AN_EEE_EN BIT(1)
+#define MII_BCM7XXX_SHD_3_EEE_THRESH 0xe
+#define MII_BCM7XXX_EEE_THRESH_DEF 0x50
+#define MII_BCM7XXX_SHD_3_TL4 0x23
+#define MII_BCM7XXX_TL4_RST_MSK (BIT(2) | BIT(1))
/* 28nm only register definitions */
#define MISC_ADDR(base, channel) base, channel
@@ -286,6 +299,181 @@ static int phy_set_clr_bits(struct phy_device *dev, int location,
return v;
}
+static int bcm7xxx_28nm_ephy_01_afe_config_init(struct phy_device *phydev)
+{
+ int ret;
+
+ /* set shadow mode 2 */
+ ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST,
+ MII_BCM7XXX_SHD_MODE_2, 0);
+ if (ret < 0)
+ return ret;
+
+ /* Set current trim values INT_trim = -1, Ext_trim =0 */
+ ret = phy_write(phydev, MII_BCM7XXX_SHD_2_BIAS_TRIM, 0x3BE0);
+ if (ret < 0)
+ goto reset_shadow_mode;
+
+ /* Cal reset */
+ ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL,
+ MII_BCM7XXX_SHD_3_TL4);
+ if (ret < 0)
+ goto reset_shadow_mode;
+ ret = phy_set_clr_bits(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT,
+ MII_BCM7XXX_TL4_RST_MSK, 0);
+ if (ret < 0)
+ goto reset_shadow_mode;
+
+ /* Cal reset disable */
+ ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL,
+ MII_BCM7XXX_SHD_3_TL4);
+ if (ret < 0)
+ goto reset_shadow_mode;
+ ret = phy_set_clr_bits(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT,
+ 0, MII_BCM7XXX_TL4_RST_MSK);
+ if (ret < 0)
+ goto reset_shadow_mode;
+
+reset_shadow_mode:
+ /* reset shadow mode 2 */
+ ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, 0,
+ MII_BCM7XXX_SHD_MODE_2);
+ if (ret < 0)
+ return ret;
+
+ return 0;
+}
+
+/* The 28nm EPHY does not support Clause 45 (MMD) used by bcm-phy-lib */
+static int bcm7xxx_28nm_ephy_apd_enable(struct phy_device *phydev)
+{
+ int ret;
+
+ /* set shadow mode 1 */
+ ret = phy_set_clr_bits(phydev, MII_BRCM_FET_BRCMTEST,
+ MII_BRCM_FET_BT_SRE, 0);
+ if (ret < 0)
+ return ret;
+
+ /* Enable auto-power down */
+ ret = phy_set_clr_bits(phydev, MII_BRCM_FET_SHDW_AUXSTAT2,
+ MII_BRCM_FET_SHDW_AS2_APDE, 0);
+ if (ret < 0)
+ return ret;
+
+ /* reset shadow mode 1 */
+ ret = phy_set_clr_bits(phydev, MII_BRCM_FET_BRCMTEST, 0,
+ MII_BRCM_FET_BT_SRE);
+ if (ret < 0)
+ return ret;
+
+ return 0;
+}
+
+static int bcm7xxx_28nm_ephy_eee_enable(struct phy_device *phydev)
+{
+ int ret;
+
+ /* set shadow mode 2 */
+ ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST,
+ MII_BCM7XXX_SHD_MODE_2, 0);
+ if (ret < 0)
+ return ret;
+
+ /* Advertise supported modes */
+ ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL,
+ MII_BCM7XXX_SHD_3_AN_EEE_ADV);
+ if (ret < 0)
+ goto reset_shadow_mode;
+ ret = phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT,
+ MDIO_EEE_100TX);
+ if (ret < 0)
+ goto reset_shadow_mode;
+
+ /* Restore Defaults */
+ ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL,
+ MII_BCM7XXX_SHD_3_PCS_CTRL_2);
+ if (ret < 0)
+ goto reset_shadow_mode;
+ ret = phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT,
+ MII_BCM7XXX_PCS_CTRL_2_DEF);
+ if (ret < 0)
+ goto reset_shadow_mode;
+
+ ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL,
+ MII_BCM7XXX_SHD_3_EEE_THRESH);
+ if (ret < 0)
+ goto reset_shadow_mode;
+ ret = phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT,
+ MII_BCM7XXX_EEE_THRESH_DEF);
+ if (ret < 0)
+ goto reset_shadow_mode;
+
+ /* Enable EEE autonegotiation */
+ ret = phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL,
+ MII_BCM7XXX_SHD_3_AN_STAT);
+ if (ret < 0)
+ goto reset_shadow_mode;
+ ret = phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT,
+ (MII_BCM7XXX_AN_NULL_MSG_EN | MII_BCM7XXX_AN_EEE_EN));
+ if (ret < 0)
+ goto reset_shadow_mode;
+
+reset_shadow_mode:
+ /* reset shadow mode 2 */
+ ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, 0,
+ MII_BCM7XXX_SHD_MODE_2);
+ if (ret < 0)
+ return ret;
+
+ /* Restart autoneg */
+ phy_write(phydev, MII_BMCR,
+ (BMCR_SPEED100 | BMCR_ANENABLE | BMCR_ANRESTART));
+
+ return 0;
+}
+
+static int bcm7xxx_28nm_ephy_config_init(struct phy_device *phydev)
+{
+ u8 rev = phydev->phy_id & ~phydev->drv->phy_id_mask;
+ int ret = 0;
+
+ pr_info_once("%s: %s PHY revision: 0x%02x\n",
+ phydev_name(phydev), phydev->drv->name, rev);
+
+ /* Dummy read to a register to workaround a possible issue upon reset
+ * where the internal inverter may not allow the first MDIO transaction
+ * to pass the MDIO management controller and make us return 0xffff for
+ * such reads.
+ */
+ phy_read(phydev, MII_BMSR);
+
+ /* Apply AFE software work-around if necessary */
+ if (rev == 0x01) {
+ ret = bcm7xxx_28nm_ephy_01_afe_config_init(phydev);
+ if (ret)
+ return ret;
+ }
+
+ ret = bcm7xxx_28nm_ephy_eee_enable(phydev);
+ if (ret)
+ return ret;
+
+ return bcm7xxx_28nm_ephy_apd_enable(phydev);
+}
+
+static int bcm7xxx_28nm_ephy_resume(struct phy_device *phydev)
+{
+ int ret;
+
+ /* Re-apply workarounds coming out suspend/resume */
+ ret = bcm7xxx_28nm_ephy_config_init(phydev);
+ if (ret)
+ return ret;
+
+ return genphy_config_aneg(phydev);
+}
+
static int bcm7xxx_config_init(struct phy_device *phydev)
{
int ret;
@@ -434,6 +622,23 @@ static int bcm7xxx_28nm_probe(struct phy_device *phydev)
.probe = bcm7xxx_28nm_probe, \
}
+#define BCM7XXX_28NM_EPHY(_oui, _name) \
+{ \
+ .phy_id = (_oui), \
+ .phy_id_mask = 0xfffffff0, \
+ .name = _name, \
+ .features = PHY_BASIC_FEATURES, \
+ .flags = PHY_IS_INTERNAL, \
+ .config_init = bcm7xxx_28nm_ephy_config_init, \
+ .config_aneg = genphy_config_aneg, \
+ .read_status = genphy_read_status, \
+ .resume = bcm7xxx_28nm_ephy_resume, \
+ .get_sset_count = bcm_phy_get_sset_count, \
+ .get_strings = bcm_phy_get_strings, \
+ .get_stats = bcm7xxx_28nm_get_phy_stats, \
+ .probe = bcm7xxx_28nm_probe, \
+}
+
#define BCM7XXX_40NM_EPHY(_oui, _name) \
{ \
.phy_id = (_oui), \
@@ -450,6 +655,9 @@ static int bcm7xxx_28nm_probe(struct phy_device *phydev)
static struct phy_driver bcm7xxx_driver[] = {
BCM7XXX_28NM_GPHY(PHY_ID_BCM7250, "Broadcom BCM7250"),
+ BCM7XXX_28NM_EPHY(PHY_ID_BCM7260, "Broadcom BCM7260"),
+ BCM7XXX_28NM_EPHY(PHY_ID_BCM7268, "Broadcom BCM7268"),
+ BCM7XXX_28NM_EPHY(PHY_ID_BCM7271, "Broadcom BCM7271"),
BCM7XXX_28NM_GPHY(PHY_ID_BCM7278, "Broadcom BCM7278"),
BCM7XXX_28NM_GPHY(PHY_ID_BCM7364, "Broadcom BCM7364"),
BCM7XXX_28NM_GPHY(PHY_ID_BCM7366, "Broadcom BCM7366"),
@@ -466,6 +674,9 @@ static struct phy_driver bcm7xxx_driver[] = {
static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = {
{ PHY_ID_BCM7250, 0xfffffff0, },
+ { PHY_ID_BCM7260, 0xfffffff0, },
+ { PHY_ID_BCM7268, 0xfffffff0, },
+ { PHY_ID_BCM7271, 0xfffffff0, },
{ PHY_ID_BCM7278, 0xfffffff0, },
{ PHY_ID_BCM7364, 0xfffffff0, },
{ PHY_ID_BCM7366, 0xfffffff0, },
diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c
index 1986553..b57f20e 100644
--- a/drivers/net/phy/dp83867.c
+++ b/drivers/net/phy/dp83867.c
@@ -133,14 +133,14 @@ static int dp83867_config_port_mirroring(struct phy_device *phydev)
(struct dp83867_private *)phydev->priv;
u16 val;
- val = phy_read_mmd_indirect(phydev, DP83867_CFG4, DP83867_DEVADDR);
+ val = phy_read_mmd(phydev, DP83867_DEVADDR, DP83867_CFG4);
if (dp83867->port_mirroring == DP83867_PORT_MIRROING_EN)
val |= DP83867_CFG4_PORT_MIRROR_EN;
else
val &= ~DP83867_CFG4_PORT_MIRROR_EN;
- phy_write_mmd_indirect(phydev, DP83867_CFG4, DP83867_DEVADDR, val);
+ phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_CFG4, val);
return 0;
}
@@ -231,8 +231,7 @@ static int dp83867_config_init(struct phy_device *phydev)
* register's bit 11 (marked as RESERVED).
*/
- bs = phy_read_mmd_indirect(phydev, DP83867_STRAP_STS1,
- DP83867_DEVADDR);
+ bs = phy_read_mmd(phydev, DP83867_DEVADDR, DP83867_STRAP_STS1);
if (bs & DP83867_STRAP_STS1_RESERVED)
val &= ~DP83867_PHYCR_RESERVED_MASK;
@@ -243,8 +242,7 @@ static int dp83867_config_init(struct phy_device *phydev)
if ((phydev->interface >= PHY_INTERFACE_MODE_RGMII_ID) &&
(phydev->interface <= PHY_INTERFACE_MODE_RGMII_RXID)) {
- val = phy_read_mmd_indirect(phydev, DP83867_RGMIICTL,
- DP83867_DEVADDR);
+ val = phy_read_mmd(phydev, DP83867_DEVADDR, DP83867_RGMIICTL);
if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID)
val |= (DP83867_RGMII_TX_CLK_DELAY_EN | DP83867_RGMII_RX_CLK_DELAY_EN);
@@ -255,25 +253,24 @@ static int dp83867_config_init(struct phy_device *phydev)
if (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID)
val |= DP83867_RGMII_RX_CLK_DELAY_EN;
- phy_write_mmd_indirect(phydev, DP83867_RGMIICTL,
- DP83867_DEVADDR, val);
+ phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RGMIICTL, val);
delay = (dp83867->rx_id_delay |
(dp83867->tx_id_delay << DP83867_RGMII_TX_CLK_DELAY_SHIFT));
- phy_write_mmd_indirect(phydev, DP83867_RGMIIDCTL,
- DP83867_DEVADDR, delay);
+ phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RGMIIDCTL,
+ delay);
if (dp83867->io_impedance >= 0) {
- val = phy_read_mmd_indirect(phydev, DP83867_IO_MUX_CFG,
- DP83867_DEVADDR);
+ val = phy_read_mmd(phydev, DP83867_DEVADDR,
+ DP83867_IO_MUX_CFG);
val &= ~DP83867_IO_MUX_CFG_IO_IMPEDANCE_CTRL;
val |= dp83867->io_impedance &
DP83867_IO_MUX_CFG_IO_IMPEDANCE_CTRL;
- phy_write_mmd_indirect(phydev, DP83867_IO_MUX_CFG,
- DP83867_DEVADDR, val);
+ phy_write_mmd(phydev, DP83867_DEVADDR,
+ DP83867_IO_MUX_CFG, val);
}
}
diff --git a/drivers/net/phy/intel-xway.c b/drivers/net/phy/intel-xway.c
index b1fd7bb..55f8c52 100644
--- a/drivers/net/phy/intel-xway.c
+++ b/drivers/net/phy/intel-xway.c
@@ -166,13 +166,13 @@ static int xway_gphy_config_init(struct phy_device *phydev)
/* Clear all pending interrupts */
phy_read(phydev, XWAY_MDIO_ISTAT);
- phy_write_mmd_indirect(phydev, XWAY_MMD_LEDCH, MDIO_MMD_VEND2,
- XWAY_MMD_LEDCH_NACS_NONE |
- XWAY_MMD_LEDCH_SBF_F02HZ |
- XWAY_MMD_LEDCH_FBF_F16HZ);
- phy_write_mmd_indirect(phydev, XWAY_MMD_LEDCL, MDIO_MMD_VEND2,
- XWAY_MMD_LEDCH_CBLINK_NONE |
- XWAY_MMD_LEDCH_SCAN_NONE);
+ phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LEDCH,
+ XWAY_MMD_LEDCH_NACS_NONE |
+ XWAY_MMD_LEDCH_SBF_F02HZ |
+ XWAY_MMD_LEDCH_FBF_F16HZ);
+ phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LEDCL,
+ XWAY_MMD_LEDCH_CBLINK_NONE |
+ XWAY_MMD_LEDCH_SCAN_NONE);
/**
* In most cases only one LED is connected to this phy, so
@@ -183,12 +183,12 @@ static int xway_gphy_config_init(struct phy_device *phydev)
ledxh = XWAY_MMD_LEDxH_BLINKF_NONE | XWAY_MMD_LEDxH_CON_LINK10XX;
ledxl = XWAY_MMD_LEDxL_PULSE_TXACT | XWAY_MMD_LEDxL_PULSE_RXACT |
XWAY_MMD_LEDxL_BLINKS_NONE;
- phy_write_mmd_indirect(phydev, XWAY_MMD_LED0H, MDIO_MMD_VEND2, ledxh);
- phy_write_mmd_indirect(phydev, XWAY_MMD_LED0L, MDIO_MMD_VEND2, ledxl);
- phy_write_mmd_indirect(phydev, XWAY_MMD_LED1H, MDIO_MMD_VEND2, ledxh);
- phy_write_mmd_indirect(phydev, XWAY_MMD_LED1L, MDIO_MMD_VEND2, ledxl);
- phy_write_mmd_indirect(phydev, XWAY_MMD_LED2H, MDIO_MMD_VEND2, ledxh);
- phy_write_mmd_indirect(phydev, XWAY_MMD_LED2L, MDIO_MMD_VEND2, ledxl);
+ phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LED0H, ledxh);
+ phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LED0L, ledxl);
+ phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LED1H, ledxh);
+ phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LED1L, ledxl);
+ phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LED2H, ledxh);
+ phy_write_mmd(phydev, MDIO_MMD_VEND2, XWAY_MMD_LED2L, ledxl);
return 0;
}
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index f9d0fa3..272b051 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -1883,17 +1883,6 @@ static int m88e1510_probe(struct phy_device *phydev)
return m88e1510_hwmon_probe(phydev);
}
-static void marvell_remove(struct phy_device *phydev)
-{
-#ifdef CONFIG_HWMON
-
- struct marvell_priv *priv = phydev->priv;
-
- if (priv && priv->hwmon_dev)
- hwmon_device_unregister(priv->hwmon_dev);
-#endif
-}
-
static struct phy_driver marvell_drivers[] = {
{
.phy_id = MARVELL_PHY_ID_88E1101,
@@ -1974,7 +1963,6 @@ static struct phy_driver marvell_drivers[] = {
.features = PHY_GBIT_FEATURES,
.flags = PHY_HAS_INTERRUPT,
.probe = &m88e1121_probe,
- .remove = &marvell_remove,
.config_init = &m88e1121_config_init,
.config_aneg = &m88e1121_config_aneg,
.read_status = &marvell_read_status,
@@ -2087,7 +2075,6 @@ static struct phy_driver marvell_drivers[] = {
.features = PHY_GBIT_FEATURES | SUPPORTED_FIBRE,
.flags = PHY_HAS_INTERRUPT,
.probe = &m88e1510_probe,
- .remove = &marvell_remove,
.config_init = &m88e1510_config_init,
.config_aneg = &m88e1510_config_aneg,
.read_status = &marvell_read_status,
@@ -2109,7 +2096,6 @@ static struct phy_driver marvell_drivers[] = {
.features = PHY_GBIT_FEATURES,
.flags = PHY_HAS_INTERRUPT,
.probe = m88e1510_probe,
- .remove = &marvell_remove,
.config_init = &marvell_config_init,
.config_aneg = &m88e1510_config_aneg,
.read_status = &marvell_read_status,
@@ -2127,7 +2113,6 @@ static struct phy_driver marvell_drivers[] = {
.phy_id_mask = MARVELL_PHY_ID_MASK,
.name = "Marvell 88E1545",
.probe = m88e1510_probe,
- .remove = &marvell_remove,
.features = PHY_GBIT_FEATURES,
.flags = PHY_HAS_INTERRUPT,
.config_init = &marvell_config_init,
diff --git a/drivers/net/phy/mdio-bcm-unimac.c b/drivers/net/phy/mdio-bcm-unimac.c
index 8c73b2e..3439523 100644
--- a/drivers/net/phy/mdio-bcm-unimac.c
+++ b/drivers/net/phy/mdio-bcm-unimac.c
@@ -1,7 +1,7 @@
/*
* Broadcom UniMAC MDIO bus controller driver
*
- * Copyright (C) 2014, Broadcom Corporation
+ * Copyright (C) 2014-2017 Broadcom
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -228,6 +228,7 @@ static int unimac_mdio_remove(struct platform_device *pdev)
}
static const struct of_device_id unimac_mdio_ids[] = {
+ { .compatible = "brcm,genet-mdio-v5", },
{ .compatible = "brcm,genet-mdio-v4", },
{ .compatible = "brcm,genet-mdio-v3", },
{ .compatible = "brcm,genet-mdio-v2", },
diff --git a/drivers/net/phy/mdio-boardinfo.c b/drivers/net/phy/mdio-boardinfo.c
index 6b988f7..1861f38 100644
--- a/drivers/net/phy/mdio-boardinfo.c
+++ b/drivers/net/phy/mdio-boardinfo.c
@@ -24,10 +24,12 @@ static DEFINE_MUTEX(mdio_board_lock);
* @mdiodev: MDIO device pointer
* Context: can sleep
*/
-void mdiobus_setup_mdiodev_from_board_info(struct mii_bus *bus)
+void mdiobus_setup_mdiodev_from_board_info(struct mii_bus *bus,
+ int (*cb)
+ (struct mii_bus *bus,
+ struct mdio_board_info *bi))
{
struct mdio_board_entry *be;
- struct mdio_device *mdiodev;
struct mdio_board_info *bi;
int ret;
@@ -38,23 +40,14 @@ void mdiobus_setup_mdiodev_from_board_info(struct mii_bus *bus)
if (strcmp(bus->id, bi->bus_id))
continue;
- mdiodev = mdio_device_create(bus, bi->mdio_addr);
- if (IS_ERR(mdiodev))
+ ret = cb(bus, bi);
+ if (ret)
continue;
- strncpy(mdiodev->modalias, bi->modalias,
- sizeof(mdiodev->modalias));
- mdiodev->bus_match = mdio_device_bus_match;
- mdiodev->dev.platform_data = (void *)bi->platform_data;
-
- ret = mdio_device_register(mdiodev);
- if (ret) {
- mdio_device_free(mdiodev);
- continue;
- }
}
mutex_unlock(&mdio_board_lock);
}
+EXPORT_SYMBOL(mdiobus_setup_mdiodev_from_board_info);
/**
* mdio_register_board_info - register MDIO devices for a given board
@@ -84,3 +77,4 @@ int mdiobus_register_board_info(const struct mdio_board_info *info,
return 0;
}
+EXPORT_SYMBOL(mdiobus_register_board_info);
diff --git a/drivers/net/phy/mdio-boardinfo.h b/drivers/net/phy/mdio-boardinfo.h
index 00f9816..3a7f1439 100644
--- a/drivers/net/phy/mdio-boardinfo.h
+++ b/drivers/net/phy/mdio-boardinfo.h
@@ -14,6 +14,9 @@ struct mdio_board_entry {
struct mdio_board_info board_info;
};
-void mdiobus_setup_mdiodev_from_board_info(struct mii_bus *bus);
+void mdiobus_setup_mdiodev_from_board_info(struct mii_bus *bus,
+ int (*cb)
+ (struct mii_bus *bus,
+ struct mdio_board_info *bi));
#endif /* __MDIO_BOARD_INFO_H */
diff --git a/drivers/net/phy/mdio-xgene.c b/drivers/net/phy/mdio-xgene.c
index f095051..3e2ac07 100644
--- a/drivers/net/phy/mdio-xgene.c
+++ b/drivers/net/phy/mdio-xgene.c
@@ -229,7 +229,7 @@ static int xgene_xfi_mdio_write(struct mii_bus *bus, int phy_id,
val = SET_VAL(HSTPHYADX, phy_id) | SET_VAL(HSTREGADX, reg) |
SET_VAL(HSTMIIMWRDAT, data);
- xgene_enet_wr_mdio_csr(addr, MIIM_FIELD_ADDR, data);
+ xgene_enet_wr_mdio_csr(addr, MIIM_FIELD_ADDR, val);
val = HSTLDCMD | SET_VAL(HSTMIIMCMD, MIIM_CMD_LEGACY_WRITE);
xgene_enet_wr_mdio_csr(addr, MIIM_COMMAND_ADDR, val);
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index fa7d51f..5a214f3 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -290,6 +290,36 @@ static inline void of_mdiobus_link_mdiodev(struct mii_bus *mdio,
#endif
/**
+ * mdiobus_create_device_from_board_info - create a full MDIO device given
+ * a mdio_board_info structure
+ * @bus: MDIO bus to create the devices on
+ * @bi: mdio_board_info structure describing the devices
+ *
+ * Returns 0 on success or < 0 on error.
+ */
+static int mdiobus_create_device(struct mii_bus *bus,
+ struct mdio_board_info *bi)
+{
+ struct mdio_device *mdiodev;
+ int ret = 0;
+
+ mdiodev = mdio_device_create(bus, bi->mdio_addr);
+ if (IS_ERR(mdiodev))
+ return -ENODEV;
+
+ strncpy(mdiodev->modalias, bi->modalias,
+ sizeof(mdiodev->modalias));
+ mdiodev->bus_match = mdio_device_bus_match;
+ mdiodev->dev.platform_data = (void *)bi->platform_data;
+
+ ret = mdio_device_register(mdiodev);
+ if (ret)
+ mdio_device_free(mdiodev);
+
+ return ret;
+}
+
+/**
* __mdiobus_register - bring up all the PHYs on a given bus and attach them to bus
* @bus: target mii_bus
* @owner: module containing bus accessor functions
@@ -345,7 +375,7 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner)
}
}
- mdiobus_setup_mdiodev_from_board_info(bus);
+ mdiobus_setup_mdiodev_from_board_info(bus, mdiobus_create_device);
bus->state = MDIOBUS_REGISTERED;
pr_info("%s: probed\n", bus->name);
@@ -648,9 +678,18 @@ int __init mdio_bus_init(void)
return ret;
}
+EXPORT_SYMBOL_GPL(mdio_bus_init);
+#if IS_ENABLED(CONFIG_PHYLIB)
void mdio_bus_exit(void)
{
class_unregister(&mdio_bus_class);
bus_unregister(&mdio_bus_type);
}
+EXPORT_SYMBOL_GPL(mdio_bus_exit);
+#else
+module_init(mdio_bus_init);
+/* no module_exit, intentional */
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("MDIO bus/device layer");
+#endif
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 6742070..b847184 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -637,8 +637,7 @@ static int ksz8873mll_config_aneg(struct phy_device *phydev)
* MMD extended PHY registers.
*/
static int
-ksz9021_rd_mmd_phyreg(struct phy_device *phydev, int ptrad, int devnum,
- int regnum)
+ksz9021_rd_mmd_phyreg(struct phy_device *phydev, int devad, u16 regnum)
{
return -1;
}
@@ -646,10 +645,10 @@ ksz9021_rd_mmd_phyreg(struct phy_device *phydev, int ptrad, int devnum,
/* This routine does nothing since the Micrel ksz9021 does not support
* standard IEEE MMD extended PHY registers.
*/
-static void
-ksz9021_wr_mmd_phyreg(struct phy_device *phydev, int ptrad, int devnum,
- int regnum, u32 val)
+static int
+ksz9021_wr_mmd_phyreg(struct phy_device *phydev, int devad, u16 regnum, u16 val)
{
+ return -1;
}
static int kszphy_get_sset_count(struct phy_device *phydev)
@@ -962,8 +961,8 @@ static struct phy_driver ksphy_driver[] = {
.get_stats = kszphy_get_stats,
.suspend = genphy_suspend,
.resume = genphy_resume,
- .read_mmd_indirect = ksz9021_rd_mmd_phyreg,
- .write_mmd_indirect = ksz9021_wr_mmd_phyreg,
+ .read_mmd = ksz9021_rd_mmd_phyreg,
+ .write_mmd = ksz9021_wr_mmd_phyreg,
}, {
.phy_id = PHY_ID_KSZ9031,
.phy_id_mask = MICREL_PHY_ID_MASK,
diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c
index 324fbf6..2b2f543 100644
--- a/drivers/net/phy/microchip.c
+++ b/drivers/net/phy/microchip.c
@@ -78,9 +78,8 @@ static int lan88xx_probe(struct phy_device *phydev)
priv->wolopts = 0;
/* these values can be used to identify internal PHY */
- priv->chip_id = phy_read_mmd_indirect(phydev, LAN88XX_MMD3_CHIP_ID, 3);
- priv->chip_rev = phy_read_mmd_indirect(phydev, LAN88XX_MMD3_CHIP_REV,
- 3);
+ priv->chip_id = phy_read_mmd(phydev, 3, LAN88XX_MMD3_CHIP_ID);
+ priv->chip_rev = phy_read_mmd(phydev, 3, LAN88XX_MMD3_CHIP_REV);
phydev->priv = priv;
diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
new file mode 100644
index 0000000..357a4d0
--- /dev/null
+++ b/drivers/net/phy/phy-core.c
@@ -0,0 +1,101 @@
+/*
+ * Core PHY library, taken from phy.c
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+#include <linux/export.h>
+#include <linux/phy.h>
+
+static void mmd_phy_indirect(struct mii_bus *bus, int phy_addr, int devad,
+ u16 regnum)
+{
+ /* Write the desired MMD Devad */
+ bus->write(bus, phy_addr, MII_MMD_CTRL, devad);
+
+ /* Write the desired MMD register address */
+ bus->write(bus, phy_addr, MII_MMD_DATA, regnum);
+
+ /* Select the Function : DATA with no post increment */
+ bus->write(bus, phy_addr, MII_MMD_CTRL, devad | MII_MMD_CTRL_NOINCR);
+}
+
+/**
+ * phy_read_mmd - Convenience function for reading a register
+ * from an MMD on a given PHY.
+ * @phydev: The phy_device struct
+ * @devad: The MMD to read from (0..31)
+ * @regnum: The register on the MMD to read (0..65535)
+ *
+ * Same rules as for phy_read();
+ */
+int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum)
+{
+ int val;
+
+ if (regnum > (u16)~0 || devad > 32)
+ return -EINVAL;
+
+ if (phydev->drv->read_mmd) {
+ val = phydev->drv->read_mmd(phydev, devad, regnum);
+ } else if (phydev->is_c45) {
+ u32 addr = MII_ADDR_C45 | (devad << 16) | (regnum & 0xffff);
+
+ val = mdiobus_read(phydev->mdio.bus, phydev->mdio.addr, addr);
+ } else {
+ struct mii_bus *bus = phydev->mdio.bus;
+ int phy_addr = phydev->mdio.addr;
+
+ mutex_lock(&bus->mdio_lock);
+ mmd_phy_indirect(bus, phy_addr, devad, regnum);
+
+ /* Read the content of the MMD's selected register */
+ val = bus->read(bus, phy_addr, MII_MMD_DATA);
+ mutex_unlock(&bus->mdio_lock);
+ }
+ return val;
+}
+EXPORT_SYMBOL(phy_read_mmd);
+
+/**
+ * phy_write_mmd - Convenience function for writing a register
+ * on an MMD on a given PHY.
+ * @phydev: The phy_device struct
+ * @devad: The MMD to read from
+ * @regnum: The register on the MMD to read
+ * @val: value to write to @regnum
+ *
+ * Same rules as for phy_write();
+ */
+int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val)
+{
+ int ret;
+
+ if (regnum > (u16)~0 || devad > 32)
+ return -EINVAL;
+
+ if (phydev->drv->read_mmd) {
+ ret = phydev->drv->write_mmd(phydev, devad, regnum, val);
+ } else if (phydev->is_c45) {
+ u32 addr = MII_ADDR_C45 | (devad << 16) | (regnum & 0xffff);
+
+ ret = mdiobus_write(phydev->mdio.bus, phydev->mdio.addr,
+ addr, val);
+ } else {
+ struct mii_bus *bus = phydev->mdio.bus;
+ int phy_addr = phydev->mdio.addr;
+
+ mutex_lock(&bus->mdio_lock);
+ mmd_phy_indirect(bus, phy_addr, devad, regnum);
+
+ /* Write the data into MMD's selected register */
+ bus->write(bus, phy_addr, MII_MMD_DATA, val);
+ mutex_unlock(&bus->mdio_lock);
+
+ ret = 0;
+ }
+ return ret;
+}
+EXPORT_SYMBOL(phy_write_mmd);
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 1be69d8..bf7d614 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -50,8 +50,22 @@ static const char *phy_speed_to_str(int speed)
return "1Gbps";
case SPEED_2500:
return "2.5Gbps";
+ case SPEED_5000:
+ return "5Gbps";
case SPEED_10000:
return "10Gbps";
+ case SPEED_20000:
+ return "20Gbps";
+ case SPEED_25000:
+ return "25Gbps";
+ case SPEED_40000:
+ return "40Gbps";
+ case SPEED_50000:
+ return "50Gbps";
+ case SPEED_56000:
+ return "56Gbps";
+ case SPEED_100000:
+ return "100Gbps";
case SPEED_UNKNOWN:
return "Unknown";
default:
@@ -681,7 +695,7 @@ void phy_stop_machine(struct phy_device *phydev)
cancel_delayed_work_sync(&phydev->state_queue);
mutex_lock(&phydev->lock);
- if (phydev->state > PHY_UP)
+ if (phydev->state > PHY_UP && phydev->state != PHY_HALTED)
phydev->state = PHY_UP;
mutex_unlock(&phydev->lock);
}
@@ -1192,91 +1206,6 @@ void phy_mac_interrupt(struct phy_device *phydev, int new_link)
}
EXPORT_SYMBOL(phy_mac_interrupt);
-static inline void mmd_phy_indirect(struct mii_bus *bus, int prtad, int devad,
- int addr)
-{
- /* Write the desired MMD Devad */
- bus->write(bus, addr, MII_MMD_CTRL, devad);
-
- /* Write the desired MMD register address */
- bus->write(bus, addr, MII_MMD_DATA, prtad);
-
- /* Select the Function : DATA with no post increment */
- bus->write(bus, addr, MII_MMD_CTRL, (devad | MII_MMD_CTRL_NOINCR));
-}
-
-/**
- * phy_read_mmd_indirect - reads data from the MMD registers
- * @phydev: The PHY device bus
- * @prtad: MMD Address
- * @devad: MMD DEVAD
- *
- * Description: it reads data from the MMD registers (clause 22 to access to
- * clause 45) of the specified phy address.
- * To read these register we have:
- * 1) Write reg 13 // DEVAD
- * 2) Write reg 14 // MMD Address
- * 3) Write reg 13 // MMD Data Command for MMD DEVAD
- * 3) Read reg 14 // Read MMD data
- */
-int phy_read_mmd_indirect(struct phy_device *phydev, int prtad, int devad)
-{
- struct phy_driver *phydrv = phydev->drv;
- int addr = phydev->mdio.addr;
- int value = -1;
-
- if (!phydrv->read_mmd_indirect) {
- struct mii_bus *bus = phydev->mdio.bus;
-
- mutex_lock(&bus->mdio_lock);
- mmd_phy_indirect(bus, prtad, devad, addr);
-
- /* Read the content of the MMD's selected register */
- value = bus->read(bus, addr, MII_MMD_DATA);
- mutex_unlock(&bus->mdio_lock);
- } else {
- value = phydrv->read_mmd_indirect(phydev, prtad, devad, addr);
- }
- return value;
-}
-EXPORT_SYMBOL(phy_read_mmd_indirect);
-
-/**
- * phy_write_mmd_indirect - writes data to the MMD registers
- * @phydev: The PHY device
- * @prtad: MMD Address
- * @devad: MMD DEVAD
- * @data: data to write in the MMD register
- *
- * Description: Write data from the MMD registers of the specified
- * phy address.
- * To write these register we have:
- * 1) Write reg 13 // DEVAD
- * 2) Write reg 14 // MMD Address
- * 3) Write reg 13 // MMD Data Command for MMD DEVAD
- * 3) Write reg 14 // Write MMD data
- */
-void phy_write_mmd_indirect(struct phy_device *phydev, int prtad,
- int devad, u32 data)
-{
- struct phy_driver *phydrv = phydev->drv;
- int addr = phydev->mdio.addr;
-
- if (!phydrv->write_mmd_indirect) {
- struct mii_bus *bus = phydev->mdio.bus;
-
- mutex_lock(&bus->mdio_lock);
- mmd_phy_indirect(bus, prtad, devad, addr);
-
- /* Write the data into MMD's selected register */
- bus->write(bus, addr, MII_MMD_DATA, data);
- mutex_unlock(&bus->mdio_lock);
- } else {
- phydrv->write_mmd_indirect(phydev, prtad, devad, addr, data);
- }
-}
-EXPORT_SYMBOL(phy_write_mmd_indirect);
-
/**
* phy_init_eee - init and check the EEE feature
* @phydev: target phy_device struct
@@ -1293,15 +1222,8 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable)
return -EIO;
/* According to 802.3az,the EEE is supported only in full duplex-mode.
- * Also EEE feature is active when core is operating with MII, GMII
- * or RGMII (all kinds). Internal PHYs are also allowed to proceed and
- * should return an error if they do not support EEE.
*/
- if ((phydev->duplex == DUPLEX_FULL) &&
- ((phydev->interface == PHY_INTERFACE_MODE_MII) ||
- (phydev->interface == PHY_INTERFACE_MODE_GMII) ||
- phy_interface_is_rgmii(phydev) ||
- phy_is_internal(phydev))) {
+ if (phydev->duplex == DUPLEX_FULL) {
int eee_lp, eee_cap, eee_adv;
u32 lp, cap, adv;
int status;
@@ -1312,8 +1234,7 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable)
return status;
/* First check if the EEE ability is supported */
- eee_cap = phy_read_mmd_indirect(phydev, MDIO_PCS_EEE_ABLE,
- MDIO_MMD_PCS);
+ eee_cap = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_EEE_ABLE);
if (eee_cap <= 0)
goto eee_exit_err;
@@ -1324,13 +1245,11 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable)
/* Check which link settings negotiated and verify it in
* the EEE advertising registers.
*/
- eee_lp = phy_read_mmd_indirect(phydev, MDIO_AN_EEE_LPABLE,
- MDIO_MMD_AN);
+ eee_lp = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_LPABLE);
if (eee_lp <= 0)
goto eee_exit_err;
- eee_adv = phy_read_mmd_indirect(phydev, MDIO_AN_EEE_ADV,
- MDIO_MMD_AN);
+ eee_adv = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV);
if (eee_adv <= 0)
goto eee_exit_err;
@@ -1343,14 +1262,12 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable)
/* Configure the PHY to stop receiving xMII
* clock while it is signaling LPI.
*/
- int val = phy_read_mmd_indirect(phydev, MDIO_CTRL1,
- MDIO_MMD_PCS);
+ int val = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1);
if (val < 0)
return val;
val |= MDIO_PCS_CTRL1_CLKSTOP_EN;
- phy_write_mmd_indirect(phydev, MDIO_CTRL1,
- MDIO_MMD_PCS, val);
+ phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, val);
}
return 0; /* EEE supported */
@@ -1372,7 +1289,7 @@ int phy_get_eee_err(struct phy_device *phydev)
if (!phydev->drv)
return -EIO;
- return phy_read_mmd_indirect(phydev, MDIO_PCS_EEE_WK_ERR, MDIO_MMD_PCS);
+ return phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_EEE_WK_ERR);
}
EXPORT_SYMBOL(phy_get_eee_err);
@@ -1392,19 +1309,19 @@ int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_eee *data)
return -EIO;
/* Get Supported EEE */
- val = phy_read_mmd_indirect(phydev, MDIO_PCS_EEE_ABLE, MDIO_MMD_PCS);
+ val = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_EEE_ABLE);
if (val < 0)
return val;
data->supported = mmd_eee_cap_to_ethtool_sup_t(val);
/* Get advertisement EEE */
- val = phy_read_mmd_indirect(phydev, MDIO_AN_EEE_ADV, MDIO_MMD_AN);
+ val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV);
if (val < 0)
return val;
data->advertised = mmd_eee_adv_to_ethtool_adv_t(val);
/* Get LP advertisement EEE */
- val = phy_read_mmd_indirect(phydev, MDIO_AN_EEE_LPABLE, MDIO_MMD_AN);
+ val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_LPABLE);
if (val < 0)
return val;
data->lp_advertised = mmd_eee_adv_to_ethtool_adv_t(val);
@@ -1422,15 +1339,37 @@ EXPORT_SYMBOL(phy_ethtool_get_eee);
*/
int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data)
{
- int val = ethtool_adv_to_mmd_eee_adv_t(data->advertised);
+ int cap, old_adv, adv, ret;
if (!phydev->drv)
return -EIO;
- /* Mask prohibited EEE modes */
- val &= ~phydev->eee_broken_modes;
+ /* Get Supported EEE */
+ cap = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_EEE_ABLE);
+ if (cap < 0)
+ return cap;
- phy_write_mmd_indirect(phydev, MDIO_AN_EEE_ADV, MDIO_MMD_AN, val);
+ old_adv = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV);
+ if (old_adv < 0)
+ return old_adv;
+
+ adv = ethtool_adv_to_mmd_eee_adv_t(data->advertised) & cap;
+
+ /* Mask prohibited EEE modes */
+ adv &= ~phydev->eee_broken_modes;
+
+ if (old_adv != adv) {
+ ret = phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, adv);
+ if (ret < 0)
+ return ret;
+
+ /* Restart autonegotiation so the new modes get sent to the
+ * link partner.
+ */
+ ret = genphy_restart_aneg(phydev);
+ if (ret < 0)
+ return ret;
+ }
return 0;
}
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 5198ccf..1219eea 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1217,7 +1217,7 @@ static int genphy_config_eee_advert(struct phy_device *phydev)
* supported by the phy. If we read 0, EEE is not advertised
* In both case, we don't need to continue
*/
- adv = phy_read_mmd_indirect(phydev, MDIO_AN_EEE_ADV, MDIO_MMD_AN);
+ adv = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV);
if (adv <= 0)
return 0;
@@ -1228,7 +1228,7 @@ static int genphy_config_eee_advert(struct phy_device *phydev)
if (old_adv == adv)
return 0;
- phy_write_mmd_indirect(phydev, MDIO_AN_EEE_ADV, MDIO_MMD_AN, adv);
+ phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, adv);
return 1;
}
diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index fb32eaf..cef6967 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -20,6 +20,7 @@
#include <linux/module.h>
#include <linux/mii.h>
#include <linux/ethtool.h>
+#include <linux/of.h>
#include <linux/phy.h>
#include <linux/netdevice.h>
#include <linux/smscphy.h>
diff --git a/drivers/net/phy/spi_ks8995.c b/drivers/net/phy/spi_ks8995.c
index 93ffedf..1e2d4f1 100644
--- a/drivers/net/phy/spi_ks8995.c
+++ b/drivers/net/phy/spi_ks8995.c
@@ -491,13 +491,14 @@ static int ks8995_probe(struct spi_device *spi)
if (err)
return err;
- ks->regs_attr.size = ks->chip->regs_size;
memcpy(&ks->regs_attr, &ks8995_registers_attr, sizeof(ks->regs_attr));
+ ks->regs_attr.size = ks->chip->regs_size;
err = ks8995_reset(ks);
if (err)
return err;
+ sysfs_attr_init(&ks->regs_attr.attr);
err = sysfs_create_bin_file(&spi->dev.kobj, &ks->regs_attr);
if (err) {
dev_err(&spi->dev, "unable to create sysfs file, err=%d\n",
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 4a24b5d..1b52520 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2072,6 +2072,7 @@ static int team_dev_type_check_change(struct net_device *dev,
static void team_setup(struct net_device *dev)
{
ether_setup(dev);
+ dev->max_mtu = ETH_MAX_MTU;
dev->netdev_ops = &team_netdev_ops;
dev->ethtool_ops = &team_ethtool_ops;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index dc1b1dd..bbd707b 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -822,7 +822,18 @@ static void tun_net_uninit(struct net_device *dev)
/* Net device open. */
static int tun_net_open(struct net_device *dev)
{
+ struct tun_struct *tun = netdev_priv(dev);
+ int i;
+
netif_tx_start_all_queues(dev);
+
+ for (i = 0; i < tun->numqueues; i++) {
+ struct tun_file *tfile;
+
+ tfile = rtnl_dereference(tun->tfiles[i]);
+ tfile->socket.sk->sk_write_space(tfile->socket.sk);
+ }
+
return 0;
}
@@ -1103,9 +1114,10 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait)
if (!skb_array_empty(&tfile->tx_array))
mask |= POLLIN | POLLRDNORM;
- if (sock_writeable(sk) ||
- (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
- sock_writeable(sk)))
+ if (tun->dev->flags & IFF_UP &&
+ (sock_writeable(sk) ||
+ (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
+ sock_writeable(sk))))
mask |= POLLOUT | POLLWRNORM;
if (tun->dev->reg_state != NETREG_REGISTERED)
@@ -1919,6 +1931,8 @@ static int set_offload(struct tun_struct *tun, unsigned long arg)
return -EINVAL;
tun->set_features = features;
+ tun->dev->wanted_features &= ~TUN_USER_FEATURES;
+ tun->dev->wanted_features |= features;
netdev_update_features(tun->dev);
return 0;
@@ -2430,18 +2444,16 @@ static struct miscdevice tun_miscdev = {
/* ethtool interface */
-static int tun_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int tun_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
- cmd->supported = 0;
- cmd->advertising = 0;
- ethtool_cmd_speed_set(cmd, SPEED_10);
- cmd->duplex = DUPLEX_FULL;
- cmd->port = PORT_TP;
- cmd->phy_address = 0;
- cmd->transceiver = XCVR_INTERNAL;
- cmd->autoneg = AUTONEG_DISABLE;
- cmd->maxtxpkt = 0;
- cmd->maxrxpkt = 0;
+ ethtool_link_ksettings_zero_link_mode(cmd, supported);
+ ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+ cmd->base.speed = SPEED_10;
+ cmd->base.duplex = DUPLEX_FULL;
+ cmd->base.port = PORT_TP;
+ cmd->base.phy_address = 0;
+ cmd->base.autoneg = AUTONEG_DISABLE;
return 0;
}
@@ -2504,7 +2516,6 @@ static int tun_set_coalesce(struct net_device *dev,
}
static const struct ethtool_ops tun_ethtool_ops = {
- .get_settings = tun_get_settings,
.get_drvinfo = tun_get_drvinfo,
.get_msglevel = tun_get_msglevel,
.set_msglevel = tun_set_msglevel,
@@ -2512,6 +2523,7 @@ static const struct ethtool_ops tun_ethtool_ops = {
.get_ts_info = ethtool_op_get_ts_info,
.get_coalesce = tun_get_coalesce,
.set_coalesce = tun_set_coalesce,
+ .get_link_ksettings = tun_get_link_ksettings,
};
static int tun_queue_resize(struct tun_struct *tun)
@@ -2570,7 +2582,6 @@ static int __init tun_init(void)
int ret = 0;
pr_info("%s, %s\n", DRV_DESCRIPTION, DRV_VERSION);
- pr_info("%s\n", DRV_COPYRIGHT);
ret = rtnl_link_register(&tun_link_ops);
if (ret) {
diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 0dd5106..a3aa0a2 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -136,9 +136,9 @@ static const struct ethtool_ops ax88172_ethtool_ops = {
.get_eeprom_len = asix_get_eeprom_len,
.get_eeprom = asix_get_eeprom,
.set_eeprom = asix_set_eeprom,
- .get_settings = usbnet_get_settings,
- .set_settings = usbnet_set_settings,
.nway_reset = usbnet_nway_reset,
+ .get_link_ksettings = usbnet_get_link_ksettings,
+ .set_link_ksettings = usbnet_set_link_ksettings,
};
static void ax88172_set_multicast(struct net_device *net)
@@ -206,6 +206,7 @@ static const struct net_device_ops ax88172_netdev_ops = {
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_change_mtu = usbnet_change_mtu,
+ .ndo_get_stats64 = usbnet_get_stats64,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_do_ioctl = asix_ioctl,
@@ -301,9 +302,9 @@ static const struct ethtool_ops ax88772_ethtool_ops = {
.get_eeprom_len = asix_get_eeprom_len,
.get_eeprom = asix_get_eeprom,
.set_eeprom = asix_set_eeprom,
- .get_settings = usbnet_get_settings,
- .set_settings = usbnet_set_settings,
.nway_reset = usbnet_nway_reset,
+ .get_link_ksettings = usbnet_get_link_ksettings,
+ .set_link_ksettings = usbnet_set_link_ksettings,
};
static int ax88772_link_reset(struct usbnet *dev)
@@ -591,6 +592,7 @@ static const struct net_device_ops ax88772_netdev_ops = {
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_change_mtu = usbnet_change_mtu,
+ .ndo_get_stats64 = usbnet_get_stats64,
.ndo_set_mac_address = asix_set_mac_address,
.ndo_validate_addr = eth_validate_addr,
.ndo_do_ioctl = asix_ioctl,
@@ -775,9 +777,9 @@ static const struct ethtool_ops ax88178_ethtool_ops = {
.get_eeprom_len = asix_get_eeprom_len,
.get_eeprom = asix_get_eeprom,
.set_eeprom = asix_set_eeprom,
- .get_settings = usbnet_get_settings,
- .set_settings = usbnet_set_settings,
.nway_reset = usbnet_nway_reset,
+ .get_link_ksettings = usbnet_get_link_ksettings,
+ .set_link_ksettings = usbnet_set_link_ksettings,
};
static int marvell_phy_init(struct usbnet *dev)
@@ -1044,6 +1046,7 @@ static const struct net_device_ops ax88178_netdev_ops = {
.ndo_stop = usbnet_stop,
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
+ .ndo_get_stats64 = usbnet_get_stats64,
.ndo_set_mac_address = asix_set_mac_address,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_rx_mode = asix_set_multicast,
diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c
index 6308386..501576f 100644
--- a/drivers/net/usb/ax88172a.c
+++ b/drivers/net/usb/ax88172a.c
@@ -143,6 +143,7 @@ static const struct net_device_ops ax88172a_netdev_ops = {
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_change_mtu = usbnet_change_mtu,
+ .ndo_get_stats64 = usbnet_get_stats64,
.ndo_set_mac_address = asix_set_mac_address,
.ndo_validate_addr = eth_validate_addr,
.ndo_do_ioctl = ax88172a_ioctl,
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index a3a7db0..51cf600 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -620,16 +620,18 @@ ax88179_get_eeprom(struct net_device *net, struct ethtool_eeprom *eeprom,
return 0;
}
-static int ax88179_get_settings(struct net_device *net, struct ethtool_cmd *cmd)
+static int ax88179_get_link_ksettings(struct net_device *net,
+ struct ethtool_link_ksettings *cmd)
{
struct usbnet *dev = netdev_priv(net);
- return mii_ethtool_gset(&dev->mii, cmd);
+ return mii_ethtool_get_link_ksettings(&dev->mii, cmd);
}
-static int ax88179_set_settings(struct net_device *net, struct ethtool_cmd *cmd)
+static int ax88179_set_link_ksettings(struct net_device *net,
+ const struct ethtool_link_ksettings *cmd)
{
struct usbnet *dev = netdev_priv(net);
- return mii_ethtool_sset(&dev->mii, cmd);
+ return mii_ethtool_set_link_ksettings(&dev->mii, cmd);
}
static int
@@ -826,11 +828,11 @@ static const struct ethtool_ops ax88179_ethtool_ops = {
.set_wol = ax88179_set_wol,
.get_eeprom_len = ax88179_get_eeprom_len,
.get_eeprom = ax88179_get_eeprom,
- .get_settings = ax88179_get_settings,
- .set_settings = ax88179_set_settings,
.get_eee = ax88179_get_eee,
.set_eee = ax88179_set_eee,
.nway_reset = usbnet_nway_reset,
+ .get_link_ksettings = ax88179_get_link_ksettings,
+ .set_link_ksettings = ax88179_set_link_ksettings,
};
static void ax88179_set_multicast(struct net_device *net)
@@ -957,6 +959,7 @@ static const struct net_device_ops ax88179_netdev_ops = {
.ndo_stop = usbnet_stop,
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
+ .ndo_get_stats64 = usbnet_get_stats64,
.ndo_change_mtu = ax88179_change_mtu,
.ndo_set_mac_address = ax88179_set_mac_addr,
.ndo_validate_addr = eth_validate_addr,
diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c
index 0acc9b64..fce92f0 100644
--- a/drivers/net/usb/catc.c
+++ b/drivers/net/usb/catc.c
@@ -688,29 +688,34 @@ static void catc_get_drvinfo(struct net_device *dev,
usb_make_path(catc->usbdev, info->bus_info, sizeof(info->bus_info));
}
-static int catc_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int catc_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
struct catc *catc = netdev_priv(dev);
if (!catc->is_f5u011)
return -EOPNOTSUPP;
- cmd->supported = SUPPORTED_10baseT_Half | SUPPORTED_TP;
- cmd->advertising = ADVERTISED_10baseT_Half | ADVERTISED_TP;
- ethtool_cmd_speed_set(cmd, SPEED_10);
- cmd->duplex = DUPLEX_HALF;
- cmd->port = PORT_TP;
- cmd->phy_address = 0;
- cmd->transceiver = XCVR_INTERNAL;
- cmd->autoneg = AUTONEG_DISABLE;
- cmd->maxtxpkt = 1;
- cmd->maxrxpkt = 1;
+ ethtool_link_ksettings_zero_link_mode(cmd, supported);
+ ethtool_link_ksettings_add_link_mode(cmd, supported, 10baseT_Half);
+ ethtool_link_ksettings_add_link_mode(cmd, supported, TP);
+
+ ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Half);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising, TP);
+
+ cmd->base.speed = SPEED_10;
+ cmd->base.duplex = DUPLEX_HALF;
+ cmd->base.port = PORT_TP;
+ cmd->base.phy_address = 0;
+ cmd->base.autoneg = AUTONEG_DISABLE;
+
return 0;
}
static const struct ethtool_ops ops = {
.get_drvinfo = catc_get_drvinfo,
- .get_settings = catc_get_settings,
- .get_link = ethtool_op_get_link
+ .get_link = ethtool_op_get_link,
+ .get_link_ksettings = catc_get_link_ksettings,
};
/*
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index f5552aa..f3ae88f 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -532,6 +532,7 @@ static const struct driver_info wwan_info = {
#define LENOVO_VENDOR_ID 0x17ef
#define NVIDIA_VENDOR_ID 0x0955
#define HP_VENDOR_ID 0x03f0
+#define MICROSOFT_VENDOR_ID 0x045e
static const struct usb_device_id products[] = {
/* BLACKLIST !!
@@ -761,6 +762,20 @@ static const struct usb_device_id products[] = {
.driver_info = 0,
},
+/* Microsoft Surface 2 dock (based on Realtek RTL8152) */
+{
+ USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x07ab, USB_CLASS_COMM,
+ USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+ .driver_info = 0,
+},
+
+/* Microsoft Surface 3 dock (based on Realtek RTL8153) */
+{
+ USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x07c6, USB_CLASS_COMM,
+ USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+ .driver_info = 0,
+},
+
/* WHITELIST!!!
*
* CDC Ether uses two interfaces, not necessarily consecutive.
diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index 3a98f37..a6b997c 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -100,6 +100,7 @@ static const struct net_device_ops cdc_mbim_netdev_ops = {
.ndo_stop = usbnet_stop,
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
+ .ndo_get_stats64 = usbnet_get_stats64,
.ndo_change_mtu = cdc_ncm_change_mtu,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index f317984..bb3f71f 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -131,8 +131,6 @@ static void cdc_ncm_get_strings(struct net_device __always_unused *netdev, u32 s
static void cdc_ncm_update_rxtx_max(struct usbnet *dev, u32 new_rx, u32 new_tx);
static const struct ethtool_ops cdc_ncm_ethtool_ops = {
- .get_settings = usbnet_get_settings,
- .set_settings = usbnet_set_settings,
.get_link = usbnet_get_link,
.nway_reset = usbnet_nway_reset,
.get_drvinfo = usbnet_get_drvinfo,
@@ -142,6 +140,8 @@ static const struct ethtool_ops cdc_ncm_ethtool_ops = {
.get_sset_count = cdc_ncm_get_sset_count,
.get_strings = cdc_ncm_get_strings,
.get_ethtool_stats = cdc_ncm_get_ethtool_stats,
+ .get_link_ksettings = usbnet_get_link_ksettings,
+ .set_link_ksettings = usbnet_set_link_ksettings,
};
static u32 cdc_ncm_check_rx_max(struct usbnet *dev, u32 new_rx)
@@ -753,6 +753,7 @@ static const struct net_device_ops cdc_ncm_netdev_ops = {
.ndo_stop = usbnet_stop,
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
+ .ndo_get_stats64 = usbnet_get_stats64,
.ndo_change_mtu = cdc_ncm_change_mtu,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c
index 0b4bdd3..b91f92e 100644
--- a/drivers/net/usb/dm9601.c
+++ b/drivers/net/usb/dm9601.c
@@ -281,9 +281,9 @@ static const struct ethtool_ops dm9601_ethtool_ops = {
.set_msglevel = usbnet_set_msglevel,
.get_eeprom_len = dm9601_get_eeprom_len,
.get_eeprom = dm9601_get_eeprom,
- .get_settings = usbnet_get_settings,
- .set_settings = usbnet_set_settings,
.nway_reset = usbnet_nway_reset,
+ .get_link_ksettings = usbnet_get_link_ksettings,
+ .set_link_ksettings = usbnet_set_link_ksettings,
};
static void dm9601_set_multicast(struct net_device *net)
@@ -343,6 +343,7 @@ static const struct net_device_ops dm9601_netdev_ops = {
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_change_mtu = usbnet_change_mtu,
+ .ndo_get_stats64 = usbnet_get_stats64,
.ndo_validate_addr = eth_validate_addr,
.ndo_do_ioctl = dm9601_ioctl,
.ndo_set_rx_mode = dm9601_set_multicast,
diff --git a/drivers/net/usb/int51x1.c b/drivers/net/usb/int51x1.c
index 4ff70b2..5a43b77 100644
--- a/drivers/net/usb/int51x1.c
+++ b/drivers/net/usb/int51x1.c
@@ -144,6 +144,7 @@ static const struct net_device_ops int51x1_netdev_ops = {
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_change_mtu = usbnet_change_mtu,
+ .ndo_get_stats64 = usbnet_get_stats64,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_rx_mode = int51x1_set_multicast,
diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c
index 876f02f..3d8ea18 100644
--- a/drivers/net/usb/kaweth.c
+++ b/drivers/net/usb/kaweth.c
@@ -245,8 +245,6 @@ struct kaweth_device
__u16 packet_filter_bitmap;
struct kaweth_ethernet_configuration configuration;
-
- struct net_device_stats stats;
};
/****************************************************************
@@ -598,7 +596,7 @@ static void kaweth_usb_receive(struct urb *urb)
struct sk_buff *skb;
if (unlikely(status == -EPIPE)) {
- kaweth->stats.rx_errors++;
+ net->stats.rx_errors++;
kaweth->end = 1;
wake_up(&kaweth->term_wait);
dev_dbg(dev, "Status was -EPIPE.\n");
@@ -613,12 +611,12 @@ static void kaweth_usb_receive(struct urb *urb)
}
if (unlikely(status == -EPROTO || status == -ETIME ||
status == -EILSEQ)) {
- kaweth->stats.rx_errors++;
+ net->stats.rx_errors++;
dev_dbg(dev, "Status was -EPROTO, -ETIME, or -EILSEQ.\n");
return;
}
if (unlikely(status == -EOVERFLOW)) {
- kaweth->stats.rx_errors++;
+ net->stats.rx_errors++;
dev_dbg(dev, "Status was -EOVERFLOW.\n");
}
spin_lock(&kaweth->device_lock);
@@ -663,8 +661,8 @@ static void kaweth_usb_receive(struct urb *urb)
netif_rx(skb);
- kaweth->stats.rx_packets++;
- kaweth->stats.rx_bytes += pkt_len;
+ net->stats.rx_packets++;
+ net->stats.rx_bytes += pkt_len;
}
kaweth_resubmit_rx_urb(kaweth, GFP_ATOMIC);
@@ -810,7 +808,7 @@ static netdev_tx_t kaweth_start_xmit(struct sk_buff *skb,
dev_kfree_skb_irq(skb);
skb = copied_skb;
if (!copied_skb) {
- kaweth->stats.tx_errors++;
+ net->stats.tx_errors++;
netif_start_queue(net);
spin_unlock_irq(&kaweth->device_lock);
return NETDEV_TX_OK;
@@ -834,15 +832,15 @@ static netdev_tx_t kaweth_start_xmit(struct sk_buff *skb,
{
dev_warn(&net->dev, "kaweth failed tx_urb %d\n", res);
skip:
- kaweth->stats.tx_errors++;
+ net->stats.tx_errors++;
netif_start_queue(net);
dev_kfree_skb_irq(skb);
}
else
{
- kaweth->stats.tx_packets++;
- kaweth->stats.tx_bytes += skb->len;
+ net->stats.tx_packets++;
+ net->stats.tx_bytes += skb->len;
}
spin_unlock_irq(&kaweth->device_lock);
@@ -912,15 +910,6 @@ static void kaweth_async_set_rx_mode(struct kaweth_device *kaweth)
}
/****************************************************************
- * kaweth_netdev_stats
- ****************************************************************/
-static struct net_device_stats *kaweth_netdev_stats(struct net_device *dev)
-{
- struct kaweth_device *kaweth = netdev_priv(dev);
- return &kaweth->stats;
-}
-
-/****************************************************************
* kaweth_tx_timeout
****************************************************************/
static void kaweth_tx_timeout(struct net_device *net)
@@ -928,7 +917,7 @@ static void kaweth_tx_timeout(struct net_device *net)
struct kaweth_device *kaweth = netdev_priv(net);
dev_warn(&net->dev, "%s: Tx timed out. Resetting.\n", net->name);
- kaweth->stats.tx_errors++;
+ net->stats.tx_errors++;
netif_trans_update(net);
usb_unlink_urb(kaweth->tx_urb);
@@ -981,7 +970,6 @@ static const struct net_device_ops kaweth_netdev_ops = {
.ndo_start_xmit = kaweth_start_xmit,
.ndo_tx_timeout = kaweth_tx_timeout,
.ndo_set_rx_mode = kaweth_set_rx_mode,
- .ndo_get_stats = kaweth_netdev_stats,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
};
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 9889a70..a17e32b 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -29,6 +29,7 @@
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/mdio.h>
+#include <linux/phy.h>
#include <net/ip6_checksum.h>
#include <linux/interrupt.h>
#include <linux/irqdomain.h>
@@ -1952,10 +1953,10 @@ static int lan8835_fixup(struct phy_device *phydev)
struct lan78xx_net *dev = netdev_priv(phydev->attached_dev);
/* LED2/PME_N/IRQ_N/RGMII_ID pin to IRQ_N mode */
- buf = phy_read_mmd_indirect(phydev, 0x8010, 3);
+ buf = phy_read_mmd(phydev, MDIO_MMD_PCS, 0x8010);
buf &= ~0x1800;
buf |= 0x0800;
- phy_write_mmd_indirect(phydev, 0x8010, 3, buf);
+ phy_write_mmd(phydev, MDIO_MMD_PCS, 0x8010, buf);
/* RGMII MAC TXC Delay Enable */
ret = lan78xx_write_reg(dev, MAC_RGMII_ID,
@@ -1975,11 +1976,11 @@ static int ksz9031rnx_fixup(struct phy_device *phydev)
/* Micrel9301RNX PHY configuration */
/* RGMII Control Signal Pad Skew */
- phy_write_mmd_indirect(phydev, 4, 2, 0x0077);
+ phy_write_mmd(phydev, MDIO_MMD_WIS, 4, 0x0077);
/* RGMII RX Data Pad Skew */
- phy_write_mmd_indirect(phydev, 5, 2, 0x7777);
+ phy_write_mmd(phydev, MDIO_MMD_WIS, 5, 0x7777);
/* RGMII RX Clock Pad Skew */
- phy_write_mmd_indirect(phydev, 8, 2, 0x1FF);
+ phy_write_mmd(phydev, MDIO_MMD_WIS, 8, 0x1FF);
dev->interface = PHY_INTERFACE_MODE_RGMII_RXID;
diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c
index 4f345bd..5a47e55 100644
--- a/drivers/net/usb/mcs7830.c
+++ b/drivers/net/usb/mcs7830.c
@@ -464,9 +464,9 @@ static const struct ethtool_ops mcs7830_ethtool_ops = {
.get_link = usbnet_get_link,
.get_msglevel = usbnet_get_msglevel,
.set_msglevel = usbnet_set_msglevel,
- .get_settings = usbnet_get_settings,
- .set_settings = usbnet_set_settings,
.nway_reset = usbnet_nway_reset,
+ .get_link_ksettings = usbnet_get_link_ksettings,
+ .set_link_ksettings = usbnet_set_link_ksettings,
};
static const struct net_device_ops mcs7830_netdev_ops = {
@@ -475,6 +475,7 @@ static const struct net_device_ops mcs7830_netdev_ops = {
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_change_mtu = usbnet_change_mtu,
+ .ndo_get_stats64 = usbnet_get_stats64,
.ndo_validate_addr = eth_validate_addr,
.ndo_do_ioctl = mcs7830_ioctl,
.ndo_set_rx_mode = mcs7830_set_multicast,
diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index 3667448..6514c86 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -501,13 +501,13 @@ static void read_bulk_callback(struct urb *urb)
if (rx_status & 0x1e) {
netif_dbg(pegasus, rx_err, net,
"RX packet error %x\n", rx_status);
- pegasus->stats.rx_errors++;
+ net->stats.rx_errors++;
if (rx_status & 0x06) /* long or runt */
- pegasus->stats.rx_length_errors++;
+ net->stats.rx_length_errors++;
if (rx_status & 0x08)
- pegasus->stats.rx_crc_errors++;
+ net->stats.rx_crc_errors++;
if (rx_status & 0x10) /* extra bits */
- pegasus->stats.rx_frame_errors++;
+ net->stats.rx_frame_errors++;
goto goon;
}
if (pegasus->chip == 0x8513) {
@@ -535,8 +535,8 @@ static void read_bulk_callback(struct urb *urb)
skb_put(pegasus->rx_skb, pkt_len);
pegasus->rx_skb->protocol = eth_type_trans(pegasus->rx_skb, net);
netif_rx(pegasus->rx_skb);
- pegasus->stats.rx_packets++;
- pegasus->stats.rx_bytes += pkt_len;
+ net->stats.rx_packets++;
+ net->stats.rx_bytes += pkt_len;
if (pegasus->flags & PEGASUS_UNPLUG)
return;
@@ -670,13 +670,13 @@ static void intr_callback(struct urb *urb)
/* byte 0 == tx_status1, reg 2B */
if (d[0] & (TX_UNDERRUN|EXCESSIVE_COL
|LATE_COL|JABBER_TIMEOUT)) {
- pegasus->stats.tx_errors++;
+ net->stats.tx_errors++;
if (d[0] & TX_UNDERRUN)
- pegasus->stats.tx_fifo_errors++;
+ net->stats.tx_fifo_errors++;
if (d[0] & (EXCESSIVE_COL | JABBER_TIMEOUT))
- pegasus->stats.tx_aborted_errors++;
+ net->stats.tx_aborted_errors++;
if (d[0] & LATE_COL)
- pegasus->stats.tx_window_errors++;
+ net->stats.tx_window_errors++;
}
/* d[5].LINK_STATUS lies on some adapters.
@@ -685,7 +685,7 @@ static void intr_callback(struct urb *urb)
*/
/* bytes 3-4 == rx_lostpkt, reg 2E/2F */
- pegasus->stats.rx_missed_errors += ((d[3] & 0x7f) << 8) | d[4];
+ net->stats.rx_missed_errors += ((d[3] & 0x7f) << 8) | d[4];
}
res = usb_submit_urb(urb, GFP_ATOMIC);
@@ -701,7 +701,7 @@ static void pegasus_tx_timeout(struct net_device *net)
pegasus_t *pegasus = netdev_priv(net);
netif_warn(pegasus, timer, net, "tx timeout\n");
usb_unlink_urb(pegasus->tx_urb);
- pegasus->stats.tx_errors++;
+ net->stats.tx_errors++;
}
static netdev_tx_t pegasus_start_xmit(struct sk_buff *skb,
@@ -731,23 +731,18 @@ static netdev_tx_t pegasus_start_xmit(struct sk_buff *skb,
netif_device_detach(pegasus->net);
break;
default:
- pegasus->stats.tx_errors++;
+ net->stats.tx_errors++;
netif_start_queue(net);
}
} else {
- pegasus->stats.tx_packets++;
- pegasus->stats.tx_bytes += skb->len;
+ net->stats.tx_packets++;
+ net->stats.tx_bytes += skb->len;
}
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
-static struct net_device_stats *pegasus_netdev_stats(struct net_device *dev)
-{
- return &((pegasus_t *) netdev_priv(dev))->stats;
-}
-
static inline void disable_net_traffic(pegasus_t *pegasus)
{
__le16 tmp = cpu_to_le16(0);
@@ -953,20 +948,22 @@ static inline void pegasus_reset_wol(struct net_device *dev)
}
static int
-pegasus_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
+pegasus_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *ecmd)
{
pegasus_t *pegasus;
pegasus = netdev_priv(dev);
- mii_ethtool_gset(&pegasus->mii, ecmd);
+ mii_ethtool_get_link_ksettings(&pegasus->mii, ecmd);
return 0;
}
static int
-pegasus_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
+pegasus_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *ecmd)
{
pegasus_t *pegasus = netdev_priv(dev);
- return mii_ethtool_sset(&pegasus->mii, ecmd);
+ return mii_ethtool_set_link_ksettings(&pegasus->mii, ecmd);
}
static int pegasus_nway_reset(struct net_device *dev)
@@ -995,14 +992,14 @@ static void pegasus_set_msglevel(struct net_device *dev, u32 v)
static const struct ethtool_ops ops = {
.get_drvinfo = pegasus_get_drvinfo,
- .get_settings = pegasus_get_settings,
- .set_settings = pegasus_set_settings,
.nway_reset = pegasus_nway_reset,
.get_link = pegasus_get_link,
.get_msglevel = pegasus_get_msglevel,
.set_msglevel = pegasus_set_msglevel,
.get_wol = pegasus_get_wol,
.set_wol = pegasus_set_wol,
+ .get_link_ksettings = pegasus_get_link_ksettings,
+ .set_link_ksettings = pegasus_set_link_ksettings,
};
static int pegasus_ioctl(struct net_device *net, struct ifreq *rq, int cmd)
@@ -1292,7 +1289,6 @@ static const struct net_device_ops pegasus_netdev_ops = {
.ndo_do_ioctl = pegasus_ioctl,
.ndo_start_xmit = pegasus_start_xmit,
.ndo_set_rx_mode = pegasus_set_multicast,
- .ndo_get_stats = pegasus_netdev_stats,
.ndo_tx_timeout = pegasus_tx_timeout,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
diff --git a/drivers/net/usb/pegasus.h b/drivers/net/usb/pegasus.h
index d156462..9b7ea9c 100644
--- a/drivers/net/usb/pegasus.h
+++ b/drivers/net/usb/pegasus.h
@@ -83,7 +83,6 @@ typedef struct pegasus {
struct usb_device *usb;
struct usb_interface *intf;
struct net_device *net;
- struct net_device_stats stats;
struct mii_if_info mii;
unsigned flags;
unsigned features;
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 8056745..adbed26 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -58,12 +58,198 @@ struct qmi_wwan_state {
enum qmi_wwan_flags {
QMI_WWAN_FLAG_RAWIP = 1 << 0,
+ QMI_WWAN_FLAG_MUX = 1 << 1,
};
enum qmi_wwan_quirks {
QMI_WWAN_QUIRK_DTR = 1 << 0, /* needs "set DTR" request */
};
+struct qmimux_hdr {
+ u8 pad;
+ u8 mux_id;
+ __be16 pkt_len;
+};
+
+struct qmimux_priv {
+ struct net_device *real_dev;
+ u8 mux_id;
+};
+
+static int qmimux_open(struct net_device *dev)
+{
+ struct qmimux_priv *priv = netdev_priv(dev);
+ struct net_device *real_dev = priv->real_dev;
+
+ if (!(priv->real_dev->flags & IFF_UP))
+ return -ENETDOWN;
+
+ if (netif_carrier_ok(real_dev))
+ netif_carrier_on(dev);
+ return 0;
+}
+
+static int qmimux_stop(struct net_device *dev)
+{
+ netif_carrier_off(dev);
+ return 0;
+}
+
+static netdev_tx_t qmimux_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct qmimux_priv *priv = netdev_priv(dev);
+ unsigned int len = skb->len;
+ struct qmimux_hdr *hdr;
+
+ hdr = (struct qmimux_hdr *)skb_push(skb, sizeof(struct qmimux_hdr));
+ hdr->pad = 0;
+ hdr->mux_id = priv->mux_id;
+ hdr->pkt_len = cpu_to_be16(len);
+ skb->dev = priv->real_dev;
+ return dev_queue_xmit(skb);
+}
+
+static const struct net_device_ops qmimux_netdev_ops = {
+ .ndo_open = qmimux_open,
+ .ndo_stop = qmimux_stop,
+ .ndo_start_xmit = qmimux_start_xmit,
+};
+
+static void qmimux_setup(struct net_device *dev)
+{
+ dev->header_ops = NULL; /* No header */
+ dev->type = ARPHRD_NONE;
+ dev->hard_header_len = 0;
+ dev->addr_len = 0;
+ dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
+ dev->netdev_ops = &qmimux_netdev_ops;
+ dev->destructor = free_netdev;
+}
+
+static struct net_device *qmimux_find_dev(struct usbnet *dev, u8 mux_id)
+{
+ struct qmimux_priv *priv;
+ struct list_head *iter;
+ struct net_device *ldev;
+
+ rcu_read_lock();
+ netdev_for_each_upper_dev_rcu(dev->net, ldev, iter) {
+ priv = netdev_priv(ldev);
+ if (priv->mux_id == mux_id) {
+ rcu_read_unlock();
+ return ldev;
+ }
+ }
+ rcu_read_unlock();
+ return NULL;
+}
+
+static bool qmimux_has_slaves(struct usbnet *dev)
+{
+ return !list_empty(&dev->net->adj_list.upper);
+}
+
+static int qmimux_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
+{
+ unsigned int len, offset = sizeof(struct qmimux_hdr);
+ struct qmimux_hdr *hdr;
+ struct net_device *net;
+ struct sk_buff *skbn;
+
+ while (offset < skb->len) {
+ hdr = (struct qmimux_hdr *)skb->data;
+ len = be16_to_cpu(hdr->pkt_len);
+
+ /* drop the packet, bogus length */
+ if (offset + len > skb->len)
+ return 0;
+
+ /* control packet, we do not know what to do */
+ if (hdr->pad & 0x80)
+ goto skip;
+
+ net = qmimux_find_dev(dev, hdr->mux_id);
+ if (!net)
+ goto skip;
+ skbn = netdev_alloc_skb(net, len);
+ if (!skbn)
+ return 0;
+ skbn->dev = net;
+
+ switch (skb->data[offset] & 0xf0) {
+ case 0x40:
+ skbn->protocol = htons(ETH_P_IP);
+ break;
+ case 0x60:
+ skbn->protocol = htons(ETH_P_IPV6);
+ break;
+ default:
+ /* not ip - do not know what to do */
+ goto skip;
+ }
+
+ memcpy(skb_put(skbn, len), skb->data + offset, len);
+ if (netif_rx(skbn) != NET_RX_SUCCESS)
+ return 0;
+
+skip:
+ offset += len + sizeof(struct qmimux_hdr);
+ }
+ return 1;
+}
+
+static int qmimux_register_device(struct net_device *real_dev, u8 mux_id)
+{
+ struct net_device *new_dev;
+ struct qmimux_priv *priv;
+ int err;
+
+ new_dev = alloc_netdev(sizeof(struct qmimux_priv),
+ "qmimux%d", NET_NAME_UNKNOWN, qmimux_setup);
+ if (!new_dev)
+ return -ENOBUFS;
+
+ dev_net_set(new_dev, dev_net(real_dev));
+ priv = netdev_priv(new_dev);
+ priv->mux_id = mux_id;
+ priv->real_dev = real_dev;
+
+ err = register_netdevice(new_dev);
+ if (err < 0)
+ goto out_free_newdev;
+
+ /* Account for reference in struct qmimux_priv_priv */
+ dev_hold(real_dev);
+
+ err = netdev_upper_dev_link(real_dev, new_dev);
+ if (err)
+ goto out_unregister_netdev;
+
+ netif_stacked_transfer_operstate(real_dev, new_dev);
+
+ return 0;
+
+out_unregister_netdev:
+ unregister_netdevice(new_dev);
+ dev_put(real_dev);
+
+out_free_newdev:
+ free_netdev(new_dev);
+ return err;
+}
+
+static void qmimux_unregister_device(struct net_device *dev)
+{
+ struct qmimux_priv *priv = netdev_priv(dev);
+ struct net_device *real_dev = priv->real_dev;
+
+ netdev_upper_dev_unlink(real_dev, dev);
+ unregister_netdevice(dev);
+
+ /* Get rid of the reference to real_dev */
+ dev_put(real_dev);
+}
+
static void qmi_wwan_netdev_setup(struct net_device *net)
{
struct usbnet *dev = netdev_priv(net);
@@ -137,10 +323,114 @@ static ssize_t raw_ip_store(struct device *d, struct device_attribute *attr, co
return ret;
}
+static ssize_t add_mux_show(struct device *d, struct device_attribute *attr, char *buf)
+{
+ struct net_device *dev = to_net_dev(d);
+ struct qmimux_priv *priv;
+ struct list_head *iter;
+ struct net_device *ldev;
+ ssize_t count = 0;
+
+ rcu_read_lock();
+ netdev_for_each_upper_dev_rcu(dev, ldev, iter) {
+ priv = netdev_priv(ldev);
+ count += scnprintf(&buf[count], PAGE_SIZE - count,
+ "0x%02x\n", priv->mux_id);
+ }
+ rcu_read_unlock();
+ return count;
+}
+
+static ssize_t add_mux_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len)
+{
+ struct usbnet *dev = netdev_priv(to_net_dev(d));
+ struct qmi_wwan_state *info = (void *)&dev->data;
+ u8 mux_id;
+ int ret;
+
+ if (kstrtou8(buf, 0, &mux_id))
+ return -EINVAL;
+
+ /* mux_id [1 - 0x7f] range empirically found */
+ if (mux_id < 1 || mux_id > 0x7f)
+ return -EINVAL;
+
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+ if (qmimux_find_dev(dev, mux_id)) {
+ netdev_err(dev->net, "mux_id already present\n");
+ ret = -EINVAL;
+ goto err;
+ }
+
+ /* we don't want to modify a running netdev */
+ if (netif_running(dev->net)) {
+ netdev_err(dev->net, "Cannot change a running device\n");
+ ret = -EBUSY;
+ goto err;
+ }
+
+ ret = qmimux_register_device(dev->net, mux_id);
+ if (!ret) {
+ info->flags |= QMI_WWAN_FLAG_MUX;
+ ret = len;
+ }
+err:
+ rtnl_unlock();
+ return ret;
+}
+
+static ssize_t del_mux_show(struct device *d, struct device_attribute *attr, char *buf)
+{
+ return add_mux_show(d, attr, buf);
+}
+
+static ssize_t del_mux_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len)
+{
+ struct usbnet *dev = netdev_priv(to_net_dev(d));
+ struct qmi_wwan_state *info = (void *)&dev->data;
+ struct net_device *del_dev;
+ u8 mux_id;
+ int ret = 0;
+
+ if (kstrtou8(buf, 0, &mux_id))
+ return -EINVAL;
+
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+ /* we don't want to modify a running netdev */
+ if (netif_running(dev->net)) {
+ netdev_err(dev->net, "Cannot change a running device\n");
+ ret = -EBUSY;
+ goto err;
+ }
+
+ del_dev = qmimux_find_dev(dev, mux_id);
+ if (!del_dev) {
+ netdev_err(dev->net, "mux_id not present\n");
+ ret = -EINVAL;
+ goto err;
+ }
+ qmimux_unregister_device(del_dev);
+
+ if (!qmimux_has_slaves(dev))
+ info->flags &= ~QMI_WWAN_FLAG_MUX;
+ ret = len;
+err:
+ rtnl_unlock();
+ return ret;
+}
+
static DEVICE_ATTR_RW(raw_ip);
+static DEVICE_ATTR_RW(add_mux);
+static DEVICE_ATTR_RW(del_mux);
static struct attribute *qmi_wwan_sysfs_attrs[] = {
&dev_attr_raw_ip.attr,
+ &dev_attr_add_mux.attr,
+ &dev_attr_del_mux.attr,
NULL,
};
@@ -184,6 +474,9 @@ static int qmi_wwan_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
if (skb->len < dev->net->hard_header_len)
return 0;
+ if (info->flags & QMI_WWAN_FLAG_MUX)
+ return qmimux_rx_fixup(dev, skb);
+
switch (skb->data[0] & 0xf0) {
case 0x40:
proto = htons(ETH_P_IP);
@@ -249,6 +542,7 @@ static const struct net_device_ops qmi_wwan_netdev_ops = {
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_change_mtu = usbnet_change_mtu,
+ .ndo_get_stats64 = usbnet_get_stats64,
.ndo_set_mac_address = qmi_wwan_mac_addr,
.ndo_validate_addr = eth_validate_addr,
};
@@ -580,6 +874,10 @@ static const struct usb_device_id products[] = {
USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, USB_CLASS_VENDOR_SPEC, 0x01, 0x69),
.driver_info = (unsigned long)&qmi_wwan_info,
},
+ { /* Motorola Mapphone devices with MDM6600 */
+ USB_VENDOR_AND_INTERFACE_INFO(0x22b8, USB_CLASS_VENDOR_SPEC, 0xfb, 0xff),
+ .driver_info = (unsigned long)&qmi_wwan_info,
+ },
/* 2. Combined interface devices matching on class+protocol */
{ /* Huawei E367 and possibly others in "Windows mode" */
@@ -925,6 +1223,8 @@ static const struct usb_device_id products[] = {
{QMI_FIXED_INTF(0x413c, 0x81a9, 8)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */
{QMI_FIXED_INTF(0x413c, 0x81b1, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */
{QMI_FIXED_INTF(0x413c, 0x81b3, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
+ {QMI_FIXED_INTF(0x413c, 0x81b6, 8)}, /* Dell Wireless 5811e */
+ {QMI_FIXED_INTF(0x413c, 0x81b6, 10)}, /* Dell Wireless 5811e */
{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
{QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */
{QMI_FIXED_INTF(0x1e0e, 0x9001, 5)}, /* SIMCom 7230E */
@@ -1030,11 +1330,33 @@ static int qmi_wwan_probe(struct usb_interface *intf,
return usbnet_probe(intf, id);
}
+static void qmi_wwan_disconnect(struct usb_interface *intf)
+{
+ struct usbnet *dev = usb_get_intfdata(intf);
+ struct qmi_wwan_state *info = (void *)&dev->data;
+ struct list_head *iter;
+ struct net_device *ldev;
+
+ if (info->flags & QMI_WWAN_FLAG_MUX) {
+ if (!rtnl_trylock()) {
+ restart_syscall();
+ return;
+ }
+ rcu_read_lock();
+ netdev_for_each_upper_dev_rcu(dev->net, ldev, iter)
+ qmimux_unregister_device(ldev);
+ rcu_read_unlock();
+ rtnl_unlock();
+ info->flags &= ~QMI_WWAN_FLAG_MUX;
+ }
+ usbnet_disconnect(intf);
+}
+
static struct usb_driver qmi_wwan_driver = {
.name = "qmi_wwan",
.id_table = products,
.probe = qmi_wwan_probe,
- .disconnect = usbnet_disconnect,
+ .disconnect = qmi_wwan_disconnect,
.suspend = qmi_wwan_suspend,
.resume = qmi_wwan_resume,
.reset_resume = qmi_wwan_resume,
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 986243c..ddc62cb 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -32,7 +32,7 @@
#define NETNEXT_VERSION "08"
/* Information for net */
-#define NET_VERSION "8"
+#define NET_VERSION "9"
#define DRIVER_VERSION "v1." NETNEXT_VERSION "." NET_VERSION
#define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>"
@@ -501,6 +501,8 @@ enum rtl_register_content {
#define RTL8153_RMS RTL8153_MAX_PACKET
#define RTL8152_TX_TIMEOUT (5 * HZ)
#define RTL8152_NAPI_WEIGHT 64
+#define rx_reserved_size(x) ((x) + VLAN_ETH_HLEN + CRC_SIZE + \
+ sizeof(struct rx_desc) + RX_ALIGN)
/* rtl8152 flags */
enum rtl8152_flags {
@@ -515,6 +517,7 @@ enum rtl8152_flags {
/* Define these values to match your device */
#define VENDOR_ID_REALTEK 0x0bda
+#define VENDOR_ID_MICROSOFT 0x045e
#define VENDOR_ID_SAMSUNG 0x04e8
#define VENDOR_ID_LENOVO 0x17ef
#define VENDOR_ID_NVIDIA 0x0955
@@ -1292,6 +1295,7 @@ static void intr_callback(struct urb *urb)
}
} else {
if (netif_carrier_ok(tp->netdev)) {
+ netif_stop_queue(tp->netdev);
set_bit(RTL8152_LINK_CHG, &tp->flags);
schedule_delayed_work(&tp->schedule, 0);
}
@@ -1362,6 +1366,7 @@ static int alloc_all_mem(struct r8152 *tp)
spin_lock_init(&tp->rx_lock);
spin_lock_init(&tp->tx_lock);
INIT_LIST_HEAD(&tp->tx_free);
+ INIT_LIST_HEAD(&tp->rx_done);
skb_queue_head_init(&tp->tx_queue);
skb_queue_head_init(&tp->rx_queue);
@@ -1761,6 +1766,7 @@ static int rx_bottom(struct r8152 *tp, int budget)
unsigned long flags;
struct list_head *cursor, *next, rx_queue;
int ret = 0, work_done = 0;
+ struct napi_struct *napi = &tp->napi;
if (!skb_queue_empty(&tp->rx_queue)) {
while (work_done < budget) {
@@ -1773,7 +1779,7 @@ static int rx_bottom(struct r8152 *tp, int budget)
break;
pkt_len = skb->len;
- napi_gro_receive(&tp->napi, skb);
+ napi_gro_receive(napi, skb);
work_done++;
stats->rx_packets++;
stats->rx_bytes += pkt_len;
@@ -1823,7 +1829,7 @@ static int rx_bottom(struct r8152 *tp, int budget)
pkt_len -= CRC_SIZE;
rx_data += sizeof(struct rx_desc);
- skb = napi_alloc_skb(&tp->napi, pkt_len);
+ skb = napi_alloc_skb(napi, pkt_len);
if (!skb) {
stats->rx_dropped++;
goto find_next_rx;
@@ -1835,7 +1841,7 @@ static int rx_bottom(struct r8152 *tp, int budget)
skb->protocol = eth_type_trans(skb, netdev);
rtl_rx_vlan_tag(rx_desc, skb);
if (work_done < budget) {
- napi_gro_receive(&tp->napi, skb);
+ napi_gro_receive(napi, skb);
work_done++;
stats->rx_packets++;
stats->rx_bytes += pkt_len;
@@ -2252,8 +2258,7 @@ static void r8153_set_rx_early_timeout(struct r8152 *tp)
static void r8153_set_rx_early_size(struct r8152 *tp)
{
- u32 mtu = tp->netdev->mtu;
- u32 ocp_data = (agg_buf_sz - mtu - VLAN_ETH_HLEN - VLAN_HLEN) / 8;
+ u32 ocp_data = (agg_buf_sz - rx_reserved_size(tp->netdev->mtu)) / 4;
ocp_write_word(tp, MCU_TYPE_USB, USB_RX_EARLY_SIZE, ocp_data);
}
@@ -2898,7 +2903,8 @@ static void r8153_first_init(struct r8152 *tp)
rtl_rx_vlan_en(tp, tp->netdev->features & NETIF_F_HW_VLAN_CTAG_RX);
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_RMS, RTL8153_RMS);
+ ocp_data = tp->netdev->mtu + VLAN_ETH_HLEN + CRC_SIZE;
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_RMS, ocp_data);
ocp_write_byte(tp, MCU_TYPE_PLA, PLA_MTPS, MTPS_JUMBO);
ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_TCR0);
@@ -2950,7 +2956,8 @@ static void r8153_enter_oob(struct r8152 *tp)
usleep_range(1000, 2000);
}
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_RMS, RTL8153_RMS);
+ ocp_data = tp->netdev->mtu + VLAN_ETH_HLEN + CRC_SIZE;
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_RMS, ocp_data);
ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_TEREDO_CFG);
ocp_data &= ~TEREDO_WAKE_MASK;
@@ -3150,6 +3157,7 @@ static bool rtl8153_in_nway(struct r8152 *tp)
static void set_carrier(struct r8152 *tp)
{
struct net_device *netdev = tp->netdev;
+ struct napi_struct *napi = &tp->napi;
u8 speed;
speed = rtl8152_get_speed(tp);
@@ -3159,19 +3167,22 @@ static void set_carrier(struct r8152 *tp)
tp->rtl_ops.enable(tp);
set_bit(RTL8152_SET_RX_MODE, &tp->flags);
netif_stop_queue(netdev);
- napi_disable(&tp->napi);
+ napi_disable(napi);
netif_carrier_on(netdev);
rtl_start_rx(tp);
napi_enable(&tp->napi);
netif_wake_queue(netdev);
netif_info(tp, link, netdev, "carrier on\n");
+ } else if (netif_queue_stopped(netdev) &&
+ skb_queue_len(&tp->tx_queue) < tp->tx_qlen) {
+ netif_wake_queue(netdev);
}
} else {
if (netif_carrier_ok(netdev)) {
netif_carrier_off(netdev);
- napi_disable(&tp->napi);
+ napi_disable(napi);
tp->rtl_ops.disable(tp);
- napi_enable(&tp->napi);
+ napi_enable(napi);
netif_info(tp, link, netdev, "carrier off\n");
}
}
@@ -3633,11 +3644,13 @@ static int rtl8152_runtime_suspend(struct r8152 *tp)
tp->rtl_ops.autosuspend_en(tp, true);
if (netif_carrier_ok(netdev)) {
- napi_disable(&tp->napi);
+ struct napi_struct *napi = &tp->napi;
+
+ napi_disable(napi);
rtl_stop_rx(tp);
rxdy_gated_en(tp, false);
ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, rcr);
- napi_enable(&tp->napi);
+ napi_enable(napi);
}
}
@@ -3653,12 +3666,14 @@ static int rtl8152_system_suspend(struct r8152 *tp)
netif_device_detach(netdev);
if (netif_running(netdev) && test_bit(WORK_ENABLE, &tp->flags)) {
+ struct napi_struct *napi = &tp->napi;
+
clear_bit(WORK_ENABLE, &tp->flags);
usb_kill_urb(tp->intr_urb);
- napi_disable(&tp->napi);
+ napi_disable(napi);
cancel_delayed_work_sync(&tp->schedule);
tp->rtl_ops.down(tp);
- napi_enable(&tp->napi);
+ napi_enable(napi);
}
return ret;
@@ -3684,35 +3699,46 @@ static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message)
static int rtl8152_resume(struct usb_interface *intf)
{
struct r8152 *tp = usb_get_intfdata(intf);
+ struct net_device *netdev = tp->netdev;
mutex_lock(&tp->control);
if (!test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
tp->rtl_ops.init(tp);
queue_delayed_work(system_long_wq, &tp->hw_phy_work, 0);
- netif_device_attach(tp->netdev);
+ netif_device_attach(netdev);
}
- if (netif_running(tp->netdev) && tp->netdev->flags & IFF_UP) {
+ if (netif_running(netdev) && netdev->flags & IFF_UP) {
if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
+ struct napi_struct *napi = &tp->napi;
+
tp->rtl_ops.autosuspend_en(tp, false);
- napi_disable(&tp->napi);
+ napi_disable(napi);
set_bit(WORK_ENABLE, &tp->flags);
- if (netif_carrier_ok(tp->netdev))
- rtl_start_rx(tp);
- napi_enable(&tp->napi);
+ if (netif_carrier_ok(netdev)) {
+ if (rtl8152_get_speed(tp) & LINK_STATUS) {
+ rtl_start_rx(tp);
+ } else {
+ netif_carrier_off(netdev);
+ tp->rtl_ops.disable(tp);
+ netif_info(tp, link, netdev,
+ "linking down\n");
+ }
+ }
+ napi_enable(napi);
clear_bit(SELECTIVE_SUSPEND, &tp->flags);
smp_mb__after_atomic();
if (!list_empty(&tp->rx_done))
napi_schedule(&tp->napi);
} else {
tp->rtl_ops.up(tp);
- netif_carrier_off(tp->netdev);
+ netif_carrier_off(netdev);
set_bit(WORK_ENABLE, &tp->flags);
}
usb_submit_urb(tp->intr_urb, GFP_KERNEL);
} else if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
- if (tp->netdev->flags & IFF_UP)
+ if (netdev->flags & IFF_UP)
tp->rtl_ops.autosuspend_en(tp, false);
clear_bit(SELECTIVE_SUSPEND, &tp->flags);
}
@@ -3800,7 +3826,8 @@ static void rtl8152_get_drvinfo(struct net_device *netdev,
}
static
-int rtl8152_get_settings(struct net_device *netdev, struct ethtool_cmd *cmd)
+int rtl8152_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *cmd)
{
struct r8152 *tp = netdev_priv(netdev);
int ret;
@@ -3814,7 +3841,7 @@ int rtl8152_get_settings(struct net_device *netdev, struct ethtool_cmd *cmd)
mutex_lock(&tp->control);
- ret = mii_ethtool_gset(&tp->mii, cmd);
+ ret = mii_ethtool_get_link_ksettings(&tp->mii, cmd);
mutex_unlock(&tp->control);
@@ -3824,7 +3851,8 @@ int rtl8152_get_settings(struct net_device *netdev, struct ethtool_cmd *cmd)
return ret;
}
-static int rtl8152_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int rtl8152_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
{
struct r8152 *tp = netdev_priv(dev);
int ret;
@@ -3835,11 +3863,12 @@ static int rtl8152_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
mutex_lock(&tp->control);
- ret = rtl8152_set_speed(tp, cmd->autoneg, cmd->speed, cmd->duplex);
+ ret = rtl8152_set_speed(tp, cmd->base.autoneg, cmd->base.speed,
+ cmd->base.duplex);
if (!ret) {
- tp->autoneg = cmd->autoneg;
- tp->speed = cmd->speed;
- tp->duplex = cmd->duplex;
+ tp->autoneg = cmd->base.autoneg;
+ tp->speed = cmd->base.speed;
+ tp->duplex = cmd->base.duplex;
}
mutex_unlock(&tp->control);
@@ -4117,8 +4146,6 @@ static int rtl8152_set_coalesce(struct net_device *netdev,
static const struct ethtool_ops ops = {
.get_drvinfo = rtl8152_get_drvinfo,
- .get_settings = rtl8152_get_settings,
- .set_settings = rtl8152_set_settings,
.get_link = ethtool_op_get_link,
.nway_reset = rtl8152_nway_reset,
.get_msglevel = rtl8152_get_msglevel,
@@ -4132,6 +4159,8 @@ static const struct ethtool_ops ops = {
.set_coalesce = rtl8152_set_coalesce,
.get_eee = rtl_ethtool_get_eee,
.set_eee = rtl_ethtool_set_eee,
+ .get_link_ksettings = rtl8152_get_link_ksettings,
+ .set_link_ksettings = rtl8152_set_link_ksettings,
};
static int rtl8152_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd)
@@ -4200,8 +4229,14 @@ static int rtl8152_change_mtu(struct net_device *dev, int new_mtu)
dev->mtu = new_mtu;
- if (netif_running(dev) && netif_carrier_ok(dev))
- r8153_set_rx_early_size(tp);
+ if (netif_running(dev)) {
+ u32 rms = new_mtu + VLAN_ETH_HLEN + CRC_SIZE;
+
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_RMS, rms);
+
+ if (netif_carrier_ok(dev))
+ r8153_set_rx_early_size(tp);
+ }
mutex_unlock(&tp->control);
@@ -4224,44 +4259,6 @@ static const struct net_device_ops rtl8152_netdev_ops = {
.ndo_features_check = rtl8152_features_check,
};
-static void r8152b_get_version(struct r8152 *tp)
-{
- u32 ocp_data;
- u16 version;
-
- ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_TCR1);
- version = (u16)(ocp_data & VERSION_MASK);
-
- switch (version) {
- case 0x4c00:
- tp->version = RTL_VER_01;
- break;
- case 0x4c10:
- tp->version = RTL_VER_02;
- break;
- case 0x5c00:
- tp->version = RTL_VER_03;
- tp->mii.supports_gmii = 1;
- break;
- case 0x5c10:
- tp->version = RTL_VER_04;
- tp->mii.supports_gmii = 1;
- break;
- case 0x5c20:
- tp->version = RTL_VER_05;
- tp->mii.supports_gmii = 1;
- break;
- case 0x5c30:
- tp->version = RTL_VER_06;
- tp->mii.supports_gmii = 1;
- break;
- default:
- netif_info(tp, probe, tp->netdev,
- "Unknown version 0x%04x\n", version);
- break;
- }
-}
-
static void rtl8152_unload(struct r8152 *tp)
{
if (test_bit(RTL8152_UNPLUG, &tp->flags))
@@ -4326,14 +4323,66 @@ static int rtl_ops_init(struct r8152 *tp)
return ret;
}
+static u8 rtl_get_version(struct usb_interface *intf)
+{
+ struct usb_device *udev = interface_to_usbdev(intf);
+ u32 ocp_data = 0;
+ __le32 *tmp;
+ u8 version;
+ int ret;
+
+ tmp = kmalloc(sizeof(*tmp), GFP_KERNEL);
+ if (!tmp)
+ return 0;
+
+ ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0),
+ RTL8152_REQ_GET_REGS, RTL8152_REQT_READ,
+ PLA_TCR0, MCU_TYPE_PLA, tmp, sizeof(*tmp), 500);
+ if (ret > 0)
+ ocp_data = (__le32_to_cpu(*tmp) >> 16) & VERSION_MASK;
+
+ kfree(tmp);
+
+ switch (ocp_data) {
+ case 0x4c00:
+ version = RTL_VER_01;
+ break;
+ case 0x4c10:
+ version = RTL_VER_02;
+ break;
+ case 0x5c00:
+ version = RTL_VER_03;
+ break;
+ case 0x5c10:
+ version = RTL_VER_04;
+ break;
+ case 0x5c20:
+ version = RTL_VER_05;
+ break;
+ case 0x5c30:
+ version = RTL_VER_06;
+ break;
+ default:
+ version = RTL_VER_UNKNOWN;
+ dev_info(&intf->dev, "Unknown version 0x%04x\n", ocp_data);
+ break;
+ }
+
+ return version;
+}
+
static int rtl8152_probe(struct usb_interface *intf,
const struct usb_device_id *id)
{
struct usb_device *udev = interface_to_usbdev(intf);
+ u8 version = rtl_get_version(intf);
struct r8152 *tp;
struct net_device *netdev;
int ret;
+ if (version == RTL_VER_UNKNOWN)
+ return -ENODEV;
+
if (udev->actconfig->desc.bConfigurationValue != 1) {
usb_driver_set_configuration(udev, 1);
return -ENODEV;
@@ -4353,8 +4402,18 @@ static int rtl8152_probe(struct usb_interface *intf,
tp->udev = udev;
tp->netdev = netdev;
tp->intf = intf;
+ tp->version = version;
- r8152b_get_version(tp);
+ switch (version) {
+ case RTL_VER_01:
+ case RTL_VER_02:
+ tp->mii.supports_gmii = 0;
+ break;
+ default:
+ tp->mii.supports_gmii = 1;
+ break;
+ }
+
ret = rtl_ops_init(tp);
if (ret)
goto out;
@@ -4497,6 +4556,8 @@ static void rtl8152_disconnect(struct usb_interface *intf)
static struct usb_device_id rtl8152_table[] = {
{REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8152)},
{REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8153)},
+ {REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07ab)},
+ {REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07c6)},
{REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101)},
{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x304f)},
{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x3062)},
diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c
index c5b2113..e96e2e5 100644
--- a/drivers/net/usb/rndis_host.c
+++ b/drivers/net/usb/rndis_host.c
@@ -291,6 +291,7 @@ static const struct net_device_ops rndis_netdev_ops = {
.ndo_stop = usbnet_stop,
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
+ .ndo_get_stats64 = usbnet_get_stats64,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
};
diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c
index c81c791..daaa88a 100644
--- a/drivers/net/usb/rtl8150.c
+++ b/drivers/net/usb/rtl8150.c
@@ -791,47 +791,52 @@ static void rtl8150_get_drvinfo(struct net_device *netdev, struct ethtool_drvinf
usb_make_path(dev->udev, info->bus_info, sizeof(info->bus_info));
}
-static int rtl8150_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+static int rtl8150_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *ecmd)
{
rtl8150_t *dev = netdev_priv(netdev);
short lpa, bmcr;
+ u32 supported;
- ecmd->supported = (SUPPORTED_10baseT_Half |
+ supported = (SUPPORTED_10baseT_Half |
SUPPORTED_10baseT_Full |
SUPPORTED_100baseT_Half |
SUPPORTED_100baseT_Full |
SUPPORTED_Autoneg |
SUPPORTED_TP | SUPPORTED_MII);
- ecmd->port = PORT_TP;
- ecmd->transceiver = XCVR_INTERNAL;
- ecmd->phy_address = dev->phy;
+ ecmd->base.port = PORT_TP;
+ ecmd->base.phy_address = dev->phy;
get_registers(dev, BMCR, 2, &bmcr);
get_registers(dev, ANLP, 2, &lpa);
if (bmcr & BMCR_ANENABLE) {
u32 speed = ((lpa & (LPA_100HALF | LPA_100FULL)) ?
SPEED_100 : SPEED_10);
- ethtool_cmd_speed_set(ecmd, speed);
- ecmd->autoneg = AUTONEG_ENABLE;
+ ecmd->base.speed = speed;
+ ecmd->base.autoneg = AUTONEG_ENABLE;
if (speed == SPEED_100)
- ecmd->duplex = (lpa & LPA_100FULL) ?
+ ecmd->base.duplex = (lpa & LPA_100FULL) ?
DUPLEX_FULL : DUPLEX_HALF;
else
- ecmd->duplex = (lpa & LPA_10FULL) ?
+ ecmd->base.duplex = (lpa & LPA_10FULL) ?
DUPLEX_FULL : DUPLEX_HALF;
} else {
- ecmd->autoneg = AUTONEG_DISABLE;
- ethtool_cmd_speed_set(ecmd, ((bmcr & BMCR_SPEED100) ?
- SPEED_100 : SPEED_10));
- ecmd->duplex = (bmcr & BMCR_FULLDPLX) ?
+ ecmd->base.autoneg = AUTONEG_DISABLE;
+ ecmd->base.speed = ((bmcr & BMCR_SPEED100) ?
+ SPEED_100 : SPEED_10);
+ ecmd->base.duplex = (bmcr & BMCR_FULLDPLX) ?
DUPLEX_FULL : DUPLEX_HALF;
}
+
+ ethtool_convert_legacy_u32_to_link_mode(ecmd->link_modes.supported,
+ supported);
+
return 0;
}
static const struct ethtool_ops ops = {
.get_drvinfo = rtl8150_get_drvinfo,
- .get_settings = rtl8150_get_settings,
- .get_link = ethtool_op_get_link
+ .get_link = ethtool_op_get_link,
+ .get_link_ksettings = rtl8150_get_link_ksettings,
};
static int rtl8150_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd)
diff --git a/drivers/net/usb/sierra_net.c b/drivers/net/usb/sierra_net.c
index ac69f28..2110ab3 100644
--- a/drivers/net/usb/sierra_net.c
+++ b/drivers/net/usb/sierra_net.c
@@ -199,6 +199,7 @@ static const struct net_device_ops sierra_net_device_ops = {
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_change_mtu = usbnet_change_mtu,
+ .ndo_get_stats64 = usbnet_get_stats64,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
};
@@ -648,9 +649,9 @@ static const struct ethtool_ops sierra_net_ethtool_ops = {
.get_link = sierra_net_get_link,
.get_msglevel = usbnet_get_msglevel,
.set_msglevel = usbnet_set_msglevel,
- .get_settings = usbnet_get_settings,
- .set_settings = usbnet_set_settings,
.nway_reset = usbnet_nway_reset,
+ .get_link_ksettings = usbnet_get_link_ksettings,
+ .set_link_ksettings = usbnet_set_link_ksettings,
};
static int sierra_net_get_fw_attr(struct usbnet *dev, u16 *datap)
diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c
index 0b17b40..1ce01db 100644
--- a/drivers/net/usb/smsc75xx.c
+++ b/drivers/net/usb/smsc75xx.c
@@ -743,13 +743,13 @@ static const struct ethtool_ops smsc75xx_ethtool_ops = {
.get_drvinfo = usbnet_get_drvinfo,
.get_msglevel = usbnet_get_msglevel,
.set_msglevel = usbnet_set_msglevel,
- .get_settings = usbnet_get_settings,
- .set_settings = usbnet_set_settings,
.get_eeprom_len = smsc75xx_ethtool_get_eeprom_len,
.get_eeprom = smsc75xx_ethtool_get_eeprom,
.set_eeprom = smsc75xx_ethtool_set_eeprom,
.get_wol = smsc75xx_ethtool_get_wol,
.set_wol = smsc75xx_ethtool_set_wol,
+ .get_link_ksettings = usbnet_get_link_ksettings,
+ .set_link_ksettings = usbnet_set_link_ksettings,
};
static int smsc75xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd)
@@ -1381,6 +1381,7 @@ static const struct net_device_ops smsc75xx_netdev_ops = {
.ndo_stop = usbnet_stop,
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
+ .ndo_get_stats64 = usbnet_get_stats64,
.ndo_change_mtu = smsc75xx_change_mtu,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 831aa33..c2f67ce 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -853,32 +853,32 @@ static void set_mdix_status(struct net_device *net, __u8 mdix_ctrl)
pdata->mdix_ctrl = mdix_ctrl;
}
-static int smsc95xx_get_settings(struct net_device *net,
- struct ethtool_cmd *cmd)
+static int smsc95xx_get_link_ksettings(struct net_device *net,
+ struct ethtool_link_ksettings *cmd)
{
struct usbnet *dev = netdev_priv(net);
struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]);
int retval;
- retval = usbnet_get_settings(net, cmd);
+ retval = usbnet_get_link_ksettings(net, cmd);
- cmd->eth_tp_mdix = pdata->mdix_ctrl;
- cmd->eth_tp_mdix_ctrl = pdata->mdix_ctrl;
+ cmd->base.eth_tp_mdix = pdata->mdix_ctrl;
+ cmd->base.eth_tp_mdix_ctrl = pdata->mdix_ctrl;
return retval;
}
-static int smsc95xx_set_settings(struct net_device *net,
- struct ethtool_cmd *cmd)
+static int smsc95xx_set_link_ksettings(struct net_device *net,
+ const struct ethtool_link_ksettings *cmd)
{
struct usbnet *dev = netdev_priv(net);
struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]);
int retval;
- if (pdata->mdix_ctrl != cmd->eth_tp_mdix_ctrl)
- set_mdix_status(net, cmd->eth_tp_mdix_ctrl);
+ if (pdata->mdix_ctrl != cmd->base.eth_tp_mdix_ctrl)
+ set_mdix_status(net, cmd->base.eth_tp_mdix_ctrl);
- retval = usbnet_set_settings(net, cmd);
+ retval = usbnet_set_link_ksettings(net, cmd);
return retval;
}
@@ -889,8 +889,6 @@ static const struct ethtool_ops smsc95xx_ethtool_ops = {
.get_drvinfo = usbnet_get_drvinfo,
.get_msglevel = usbnet_get_msglevel,
.set_msglevel = usbnet_set_msglevel,
- .get_settings = smsc95xx_get_settings,
- .set_settings = smsc95xx_set_settings,
.get_eeprom_len = smsc95xx_ethtool_get_eeprom_len,
.get_eeprom = smsc95xx_ethtool_get_eeprom,
.set_eeprom = smsc95xx_ethtool_set_eeprom,
@@ -898,6 +896,8 @@ static const struct ethtool_ops smsc95xx_ethtool_ops = {
.get_regs = smsc95xx_ethtool_getregs,
.get_wol = smsc95xx_ethtool_get_wol,
.set_wol = smsc95xx_ethtool_set_wol,
+ .get_link_ksettings = smsc95xx_get_link_ksettings,
+ .set_link_ksettings = smsc95xx_set_link_ksettings,
};
static int smsc95xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd)
@@ -1248,6 +1248,7 @@ static const struct net_device_ops smsc95xx_netdev_ops = {
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_change_mtu = usbnet_change_mtu,
+ .ndo_get_stats64 = usbnet_get_stats64,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_do_ioctl = smsc95xx_ioctl,
diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c
index 4a1e9c4..317287f 100644
--- a/drivers/net/usb/sr9700.c
+++ b/drivers/net/usb/sr9700.c
@@ -249,9 +249,9 @@ static const struct ethtool_ops sr9700_ethtool_ops = {
.set_msglevel = usbnet_set_msglevel,
.get_eeprom_len = sr9700_get_eeprom_len,
.get_eeprom = sr9700_get_eeprom,
- .get_settings = usbnet_get_settings,
- .set_settings = usbnet_set_settings,
.nway_reset = usbnet_nway_reset,
+ .get_link_ksettings = usbnet_get_link_ksettings,
+ .set_link_ksettings = usbnet_set_link_ksettings,
};
static void sr9700_set_multicast(struct net_device *netdev)
@@ -308,6 +308,7 @@ static const struct net_device_ops sr9700_netdev_ops = {
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_change_mtu = usbnet_change_mtu,
+ .ndo_get_stats64 = usbnet_get_stats64,
.ndo_validate_addr = eth_validate_addr,
.ndo_do_ioctl = sr9700_ioctl,
.ndo_set_rx_mode = sr9700_set_multicast,
diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c
index a50df0d..9277a0f 100644
--- a/drivers/net/usb/sr9800.c
+++ b/drivers/net/usb/sr9800.c
@@ -524,9 +524,9 @@ static const struct ethtool_ops sr9800_ethtool_ops = {
.set_wol = sr_set_wol,
.get_eeprom_len = sr_get_eeprom_len,
.get_eeprom = sr_get_eeprom,
- .get_settings = usbnet_get_settings,
- .set_settings = usbnet_set_settings,
.nway_reset = usbnet_nway_reset,
+ .get_link_ksettings = usbnet_get_link_ksettings,
+ .set_link_ksettings = usbnet_set_link_ksettings,
};
static int sr9800_link_reset(struct usbnet *dev)
@@ -679,6 +679,7 @@ static const struct net_device_ops sr9800_netdev_ops = {
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_change_mtu = usbnet_change_mtu,
+ .ndo_get_stats64 = usbnet_get_stats64,
.ndo_set_mac_address = sr_set_mac_address,
.ndo_validate_addr = eth_validate_addr,
.ndo_do_ioctl = sr_ioctl,
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 3de65ea..1cc945c 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -82,8 +82,6 @@
// randomly generated ethernet address
static u8 node_id [ETH_ALEN];
-static const char driver_name [] = "usbnet";
-
/* use ethtool to change the level for any given device */
static int msg_level = -1;
module_param (msg_level, int, 0);
@@ -316,6 +314,7 @@ static void __usbnet_status_stop_force(struct usbnet *dev)
*/
void usbnet_skb_return (struct usbnet *dev, struct sk_buff *skb)
{
+ struct pcpu_sw_netstats *stats64 = this_cpu_ptr(dev->stats64);
int status;
if (test_bit(EVENT_RX_PAUSED, &dev->flags)) {
@@ -327,8 +326,10 @@ void usbnet_skb_return (struct usbnet *dev, struct sk_buff *skb)
if (skb->protocol == 0)
skb->protocol = eth_type_trans (skb, dev->net);
- dev->net->stats.rx_packets++;
- dev->net->stats.rx_bytes += skb->len;
+ u64_stats_update_begin(&stats64->syncp);
+ stats64->rx_packets++;
+ stats64->rx_bytes += skb->len;
+ u64_stats_update_end(&stats64->syncp);
netif_dbg(dev, rx_status, dev->net, "< rx, len %zu, type 0x%x\n",
skb->len + sizeof (struct ethhdr), skb->protocol);
@@ -947,18 +948,20 @@ EXPORT_SYMBOL_GPL(usbnet_open);
* they'll probably want to use this base set.
*/
-int usbnet_get_settings (struct net_device *net, struct ethtool_cmd *cmd)
+int usbnet_get_link_ksettings(struct net_device *net,
+ struct ethtool_link_ksettings *cmd)
{
struct usbnet *dev = netdev_priv(net);
if (!dev->mii.mdio_read)
return -EOPNOTSUPP;
- return mii_ethtool_gset(&dev->mii, cmd);
+ return mii_ethtool_get_link_ksettings(&dev->mii, cmd);
}
-EXPORT_SYMBOL_GPL(usbnet_get_settings);
+EXPORT_SYMBOL_GPL(usbnet_get_link_ksettings);
-int usbnet_set_settings (struct net_device *net, struct ethtool_cmd *cmd)
+int usbnet_set_link_ksettings(struct net_device *net,
+ const struct ethtool_link_ksettings *cmd)
{
struct usbnet *dev = netdev_priv(net);
int retval;
@@ -966,7 +969,7 @@ int usbnet_set_settings (struct net_device *net, struct ethtool_cmd *cmd)
if (!dev->mii.mdio_write)
return -EOPNOTSUPP;
- retval = mii_ethtool_sset(&dev->mii, cmd);
+ retval = mii_ethtool_set_link_ksettings(&dev->mii, cmd);
/* link speed/duplex might have changed */
if (dev->driver_info->link_reset)
@@ -976,9 +979,39 @@ int usbnet_set_settings (struct net_device *net, struct ethtool_cmd *cmd)
usbnet_update_max_qlen(dev);
return retval;
-
}
-EXPORT_SYMBOL_GPL(usbnet_set_settings);
+EXPORT_SYMBOL_GPL(usbnet_set_link_ksettings);
+
+void usbnet_get_stats64(struct net_device *net, struct rtnl_link_stats64 *stats)
+{
+ struct usbnet *dev = netdev_priv(net);
+ unsigned int start;
+ int cpu;
+
+ netdev_stats_to_stats64(stats, &net->stats);
+
+ for_each_possible_cpu(cpu) {
+ struct pcpu_sw_netstats *stats64;
+ u64 rx_packets, rx_bytes;
+ u64 tx_packets, tx_bytes;
+
+ stats64 = per_cpu_ptr(dev->stats64, cpu);
+
+ do {
+ start = u64_stats_fetch_begin_irq(&stats64->syncp);
+ rx_packets = stats64->rx_packets;
+ rx_bytes = stats64->rx_bytes;
+ tx_packets = stats64->tx_packets;
+ tx_bytes = stats64->tx_bytes;
+ } while (u64_stats_fetch_retry_irq(&stats64->syncp, start));
+
+ stats->rx_packets += rx_packets;
+ stats->rx_bytes += rx_bytes;
+ stats->tx_packets += tx_packets;
+ stats->tx_bytes += tx_bytes;
+ }
+}
+EXPORT_SYMBOL_GPL(usbnet_get_stats64);
u32 usbnet_get_link (struct net_device *net)
{
@@ -1038,14 +1071,14 @@ EXPORT_SYMBOL_GPL(usbnet_set_msglevel);
/* drivers may override default ethtool_ops in their bind() routine */
static const struct ethtool_ops usbnet_ethtool_ops = {
- .get_settings = usbnet_get_settings,
- .set_settings = usbnet_set_settings,
.get_link = usbnet_get_link,
.nway_reset = usbnet_nway_reset,
.get_drvinfo = usbnet_get_drvinfo,
.get_msglevel = usbnet_get_msglevel,
.set_msglevel = usbnet_set_msglevel,
.get_ts_info = ethtool_op_get_ts_info,
+ .get_link_ksettings = usbnet_get_link_ksettings,
+ .set_link_ksettings = usbnet_set_link_ksettings,
};
/*-------------------------------------------------------------------------*/
@@ -1211,8 +1244,12 @@ static void tx_complete (struct urb *urb)
struct usbnet *dev = entry->dev;
if (urb->status == 0) {
- dev->net->stats.tx_packets += entry->packets;
- dev->net->stats.tx_bytes += entry->length;
+ struct pcpu_sw_netstats *stats64 = this_cpu_ptr(dev->stats64);
+
+ u64_stats_update_begin(&stats64->syncp);
+ stats64->tx_packets += entry->packets;
+ stats64->tx_bytes += entry->length;
+ u64_stats_update_end(&stats64->syncp);
} else {
dev->net->stats.tx_errors++;
@@ -1569,6 +1606,7 @@ void usbnet_disconnect (struct usb_interface *intf)
usb_free_urb(dev->interrupt);
kfree(dev->padding_pkt);
+ free_percpu(dev->stats64);
free_netdev(net);
}
EXPORT_SYMBOL_GPL(usbnet_disconnect);
@@ -1580,6 +1618,7 @@ static const struct net_device_ops usbnet_netdev_ops = {
.ndo_tx_timeout = usbnet_tx_timeout,
.ndo_set_rx_mode = usbnet_set_rx_mode,
.ndo_change_mtu = usbnet_change_mtu,
+ .ndo_get_stats64 = usbnet_get_stats64,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
};
@@ -1641,6 +1680,11 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
dev->intf = udev;
dev->driver_info = info;
dev->driver_name = name;
+
+ dev->stats64 = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+ if (!dev->stats64)
+ goto out0;
+
dev->msg_enable = netif_msg_init (msg_level, NETIF_MSG_DRV
| NETIF_MSG_PROBE | NETIF_MSG_LINK);
init_waitqueue_head(&dev->wait);
@@ -1780,6 +1824,8 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
*/
cancel_work_sync(&dev->kevent);
del_timer_sync(&dev->delay);
+ free_percpu(dev->stats64);
+out0:
free_netdev(net);
out:
return status;
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 8c39d6d..3171036 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -45,18 +45,13 @@ static struct {
{ "peer_ifindex" },
};
-static int veth_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int veth_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
- cmd->supported = 0;
- cmd->advertising = 0;
- ethtool_cmd_speed_set(cmd, SPEED_10000);
- cmd->duplex = DUPLEX_FULL;
- cmd->port = PORT_TP;
- cmd->phy_address = 0;
- cmd->transceiver = XCVR_INTERNAL;
- cmd->autoneg = AUTONEG_DISABLE;
- cmd->maxtxpkt = 0;
- cmd->maxrxpkt = 0;
+ cmd->base.speed = SPEED_10000;
+ cmd->base.duplex = DUPLEX_FULL;
+ cmd->base.port = PORT_TP;
+ cmd->base.autoneg = AUTONEG_DISABLE;
return 0;
}
@@ -95,12 +90,12 @@ static void veth_get_ethtool_stats(struct net_device *dev,
}
static const struct ethtool_ops veth_ethtool_ops = {
- .get_settings = veth_get_settings,
.get_drvinfo = veth_get_drvinfo,
.get_link = ethtool_op_get_link,
.get_strings = veth_get_strings,
.get_sset_count = veth_get_sset_count,
.get_ethtool_stats = veth_get_ethtool_stats,
+ .get_link_ksettings = veth_get_link_ksettings,
};
static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index ea9890d..b0d241d 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1636,47 +1636,57 @@ static void virtnet_get_channels(struct net_device *dev,
}
/* Check if the user is trying to change anything besides speed/duplex */
-static bool virtnet_validate_ethtool_cmd(const struct ethtool_cmd *cmd)
+static bool
+virtnet_validate_ethtool_cmd(const struct ethtool_link_ksettings *cmd)
{
- struct ethtool_cmd diff1 = *cmd;
- struct ethtool_cmd diff2 = {};
+ struct ethtool_link_ksettings diff1 = *cmd;
+ struct ethtool_link_ksettings diff2 = {};
/* cmd is always set so we need to clear it, validate the port type
* and also without autonegotiation we can ignore advertising
*/
- ethtool_cmd_speed_set(&diff1, 0);
- diff2.port = PORT_OTHER;
- diff1.advertising = 0;
- diff1.duplex = 0;
- diff1.cmd = 0;
+ diff1.base.speed = 0;
+ diff2.base.port = PORT_OTHER;
+ ethtool_link_ksettings_zero_link_mode(&diff1, advertising);
+ diff1.base.duplex = 0;
+ diff1.base.cmd = 0;
+ diff1.base.link_mode_masks_nwords = 0;
- return !memcmp(&diff1, &diff2, sizeof(diff1));
+ return !memcmp(&diff1.base, &diff2.base, sizeof(diff1.base)) &&
+ bitmap_empty(diff1.link_modes.supported,
+ __ETHTOOL_LINK_MODE_MASK_NBITS) &&
+ bitmap_empty(diff1.link_modes.advertising,
+ __ETHTOOL_LINK_MODE_MASK_NBITS) &&
+ bitmap_empty(diff1.link_modes.lp_advertising,
+ __ETHTOOL_LINK_MODE_MASK_NBITS);
}
-static int virtnet_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int virtnet_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
{
struct virtnet_info *vi = netdev_priv(dev);
u32 speed;
- speed = ethtool_cmd_speed(cmd);
+ speed = cmd->base.speed;
/* don't allow custom speed and duplex */
if (!ethtool_validate_speed(speed) ||
- !ethtool_validate_duplex(cmd->duplex) ||
+ !ethtool_validate_duplex(cmd->base.duplex) ||
!virtnet_validate_ethtool_cmd(cmd))
return -EINVAL;
vi->speed = speed;
- vi->duplex = cmd->duplex;
+ vi->duplex = cmd->base.duplex;
return 0;
}
-static int virtnet_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int virtnet_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
struct virtnet_info *vi = netdev_priv(dev);
- ethtool_cmd_speed_set(cmd, vi->speed);
- cmd->duplex = vi->duplex;
- cmd->port = PORT_OTHER;
+ cmd->base.speed = vi->speed;
+ cmd->base.duplex = vi->duplex;
+ cmd->base.port = PORT_OTHER;
return 0;
}
@@ -1696,8 +1706,8 @@ static const struct ethtool_ops virtnet_ethtool_ops = {
.set_channels = virtnet_set_channels,
.get_channels = virtnet_get_channels,
.get_ts_info = ethtool_op_get_ts_info,
- .get_settings = virtnet_get_settings,
- .set_settings = virtnet_set_settings,
+ .get_link_ksettings = virtnet_get_link_ksettings,
+ .set_link_ksettings = virtnet_set_link_ksettings,
};
static void virtnet_freeze_down(struct virtio_device *vdev)
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index f88ffaf..2ff2731 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -471,22 +471,25 @@ vmxnet3_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
static int
-vmxnet3_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+vmxnet3_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *ecmd)
{
struct vmxnet3_adapter *adapter = netdev_priv(netdev);
- ecmd->supported = SUPPORTED_10000baseT_Full | SUPPORTED_1000baseT_Full |
- SUPPORTED_TP;
- ecmd->advertising = ADVERTISED_TP;
- ecmd->port = PORT_TP;
- ecmd->transceiver = XCVR_INTERNAL;
+ ethtool_link_ksettings_zero_link_mode(ecmd, supported);
+ ethtool_link_ksettings_add_link_mode(ecmd, supported, 10000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(ecmd, supported, 1000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(ecmd, supported, TP);
+ ethtool_link_ksettings_zero_link_mode(ecmd, advertising);
+ ethtool_link_ksettings_add_link_mode(ecmd, advertising, TP);
+ ecmd->base.port = PORT_TP;
if (adapter->link_speed) {
- ethtool_cmd_speed_set(ecmd, adapter->link_speed);
- ecmd->duplex = DUPLEX_FULL;
+ ecmd->base.speed = adapter->link_speed;
+ ecmd->base.duplex = DUPLEX_FULL;
} else {
- ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
- ecmd->duplex = DUPLEX_UNKNOWN;
+ ecmd->base.speed = SPEED_UNKNOWN;
+ ecmd->base.duplex = DUPLEX_UNKNOWN;
}
return 0;
}
@@ -880,7 +883,6 @@ vmxnet3_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec)
}
static const struct ethtool_ops vmxnet3_ethtool_ops = {
- .get_settings = vmxnet3_get_settings,
.get_drvinfo = vmxnet3_get_drvinfo,
.get_regs_len = vmxnet3_get_regs_len,
.get_regs = vmxnet3_get_regs,
@@ -900,6 +902,7 @@ static const struct ethtool_ops vmxnet3_ethtool_ops = {
.get_rxfh = vmxnet3_get_rss,
.set_rxfh = vmxnet3_set_rss,
#endif
+ .get_link_ksettings = vmxnet3_get_link_ksettings,
};
void vmxnet3_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 22379da..eb5493e 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -104,6 +104,23 @@ static void vrf_get_stats64(struct net_device *dev,
}
}
+/* by default VRF devices do not have a qdisc and are expected
+ * to be created with only a single queue.
+ */
+static bool qdisc_tx_is_default(const struct net_device *dev)
+{
+ struct netdev_queue *txq;
+ struct Qdisc *qdisc;
+
+ if (dev->num_tx_queues > 1)
+ return false;
+
+ txq = netdev_get_tx_queue(dev, 0);
+ qdisc = rcu_access_pointer(txq->qdisc);
+
+ return !qdisc->enqueue;
+}
+
/* Local traffic destined to local address. Reinsert the packet to rx
* path, similar to loopback handling.
*/
@@ -340,6 +357,7 @@ static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev)
static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
{
+ int len = skb->len;
netdev_tx_t ret = is_ip_tx_frame(skb, dev);
if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
@@ -347,7 +365,7 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
u64_stats_update_begin(&dstats->syncp);
dstats->tx_pkts++;
- dstats->tx_bytes += skb->len;
+ dstats->tx_bytes += len;
u64_stats_update_end(&dstats->syncp);
} else {
this_cpu_inc(dev->dstats->tx_drps);
@@ -356,6 +374,29 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
return ret;
}
+static int vrf_finish_direct(struct net *net, struct sock *sk,
+ struct sk_buff *skb)
+{
+ struct net_device *vrf_dev = skb->dev;
+
+ if (!list_empty(&vrf_dev->ptype_all) &&
+ likely(skb_headroom(skb) >= ETH_HLEN)) {
+ struct ethhdr *eth = (struct ethhdr *)skb_push(skb, ETH_HLEN);
+
+ ether_addr_copy(eth->h_source, vrf_dev->dev_addr);
+ eth_zero_addr(eth->h_dest);
+ eth->h_proto = skb->protocol;
+
+ rcu_read_lock_bh();
+ dev_queue_xmit_nit(skb, vrf_dev);
+ rcu_read_unlock_bh();
+
+ skb_pull(skb, ETH_HLEN);
+ }
+
+ return 1;
+}
+
#if IS_ENABLED(CONFIG_IPV6)
/* modelled after ip6_finish_output2 */
static int vrf_finish_output6(struct net *net, struct sock *sk,
@@ -404,18 +445,13 @@ static int vrf_output6(struct net *net, struct sock *sk, struct sk_buff *skb)
* packet to go through device based features such as qdisc, netfilter
* hooks and packet sockets with skb->dev set to vrf device.
*/
-static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
- struct sock *sk,
- struct sk_buff *skb)
+static struct sk_buff *vrf_ip6_out_redirect(struct net_device *vrf_dev,
+ struct sk_buff *skb)
{
struct net_vrf *vrf = netdev_priv(vrf_dev);
struct dst_entry *dst = NULL;
struct rt6_info *rt6;
- /* don't divert link scope packets */
- if (rt6_need_strict(&ipv6_hdr(skb)->daddr))
- return skb;
-
rcu_read_lock();
rt6 = rcu_dereference(vrf->rt6);
@@ -437,6 +473,55 @@ static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
return skb;
}
+static int vrf_output6_direct(struct net *net, struct sock *sk,
+ struct sk_buff *skb)
+{
+ skb->protocol = htons(ETH_P_IPV6);
+
+ return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING,
+ net, sk, skb, NULL, skb->dev,
+ vrf_finish_direct,
+ !(IPCB(skb)->flags & IPSKB_REROUTED));
+}
+
+static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev,
+ struct sock *sk,
+ struct sk_buff *skb)
+{
+ struct net *net = dev_net(vrf_dev);
+ int err;
+
+ skb->dev = vrf_dev;
+
+ err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk,
+ skb, NULL, vrf_dev, vrf_output6_direct);
+
+ if (likely(err == 1))
+ err = vrf_output6_direct(net, sk, skb);
+
+ /* reset skb device */
+ if (likely(err == 1))
+ nf_reset(skb);
+ else
+ skb = NULL;
+
+ return skb;
+}
+
+static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
+ struct sock *sk,
+ struct sk_buff *skb)
+{
+ /* don't divert link scope packets */
+ if (rt6_need_strict(&ipv6_hdr(skb)->daddr))
+ return skb;
+
+ if (qdisc_tx_is_default(vrf_dev))
+ return vrf_ip6_out_direct(vrf_dev, sk, skb);
+
+ return vrf_ip6_out_redirect(vrf_dev, skb);
+}
+
/* holding rtnl */
static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf)
{
@@ -461,8 +546,10 @@ static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf)
}
if (rt6_local) {
- if (rt6_local->rt6i_idev)
+ if (rt6_local->rt6i_idev) {
in6_dev_put(rt6_local->rt6i_idev);
+ rt6_local->rt6i_idev = NULL;
+ }
dst = &rt6_local->dst;
dev_put(dst->dev);
@@ -606,18 +693,13 @@ static int vrf_output(struct net *net, struct sock *sk, struct sk_buff *skb)
* packet to go through device based features such as qdisc, netfilter
* hooks and packet sockets with skb->dev set to vrf device.
*/
-static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
- struct sock *sk,
- struct sk_buff *skb)
+static struct sk_buff *vrf_ip_out_redirect(struct net_device *vrf_dev,
+ struct sk_buff *skb)
{
struct net_vrf *vrf = netdev_priv(vrf_dev);
struct dst_entry *dst = NULL;
struct rtable *rth;
- /* don't divert multicast */
- if (ipv4_is_multicast(ip_hdr(skb)->daddr))
- return skb;
-
rcu_read_lock();
rth = rcu_dereference(vrf->rth);
@@ -639,6 +721,55 @@ static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
return skb;
}
+static int vrf_output_direct(struct net *net, struct sock *sk,
+ struct sk_buff *skb)
+{
+ skb->protocol = htons(ETH_P_IP);
+
+ return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
+ net, sk, skb, NULL, skb->dev,
+ vrf_finish_direct,
+ !(IPCB(skb)->flags & IPSKB_REROUTED));
+}
+
+static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev,
+ struct sock *sk,
+ struct sk_buff *skb)
+{
+ struct net *net = dev_net(vrf_dev);
+ int err;
+
+ skb->dev = vrf_dev;
+
+ err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk,
+ skb, NULL, vrf_dev, vrf_output_direct);
+
+ if (likely(err == 1))
+ err = vrf_output_direct(net, sk, skb);
+
+ /* reset skb device */
+ if (likely(err == 1))
+ nf_reset(skb);
+ else
+ skb = NULL;
+
+ return skb;
+}
+
+static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
+ struct sock *sk,
+ struct sk_buff *skb)
+{
+ /* don't divert multicast */
+ if (ipv4_is_multicast(ip_hdr(skb)->daddr))
+ return skb;
+
+ if (qdisc_tx_is_default(vrf_dev))
+ return vrf_ip_out_direct(vrf_dev, sk, skb);
+
+ return vrf_ip_out_redirect(vrf_dev, skb);
+}
+
/* called with rcu lock held */
static struct sk_buff *vrf_l3_out(struct net_device *vrf_dev,
struct sock *sk,
@@ -746,14 +877,18 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
{
int ret;
+ port_dev->priv_flags |= IFF_L3MDEV_SLAVE;
ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL);
if (ret < 0)
- return ret;
+ goto err;
- port_dev->priv_flags |= IFF_L3MDEV_SLAVE;
cycle_netdev(port_dev);
return 0;
+
+err:
+ port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE;
+ return ret;
}
static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
@@ -975,9 +1110,11 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
skb->dev = vrf_dev;
skb->skb_iif = vrf_dev->ifindex;
- skb_push(skb, skb->mac_len);
- dev_queue_xmit_nit(skb, vrf_dev);
- skb_pull(skb, skb->mac_len);
+ if (!list_empty(&vrf_dev->ptype_all)) {
+ skb_push(skb, skb->mac_len);
+ dev_queue_xmit_nit(skb, vrf_dev);
+ skb_pull(skb, skb->mac_len);
+ }
IP6CB(skb)->flags |= IP6SKB_L3SLAVE;
}
@@ -1018,9 +1155,11 @@ static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev,
vrf_rx_stats(vrf_dev, skb->len);
- skb_push(skb, skb->mac_len);
- dev_queue_xmit_nit(skb, vrf_dev);
- skb_pull(skb, skb->mac_len);
+ if (!list_empty(&vrf_dev->ptype_all)) {
+ skb_push(skb, skb->mac_len);
+ dev_queue_xmit_nit(skb, vrf_dev);
+ skb_pull(skb, skb->mac_len);
+ }
skb = vrf_rcv_nfhook(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, vrf_dev);
out:
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index e375560..ebc98bb 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -276,9 +276,9 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
send_eth = send_ip = true;
if (type == RTM_GETNEIGH) {
- ndm->ndm_family = AF_INET;
send_ip = !vxlan_addr_any(&rdst->remote_ip);
send_eth = !is_zero_ether_addr(fdb->eth_addr);
+ ndm->ndm_family = send_ip ? rdst->remote_ip.sa.sa_family : AF_INET;
} else
ndm->ndm_family = AF_BRIDGE;
ndm->ndm_state = fdb->state;
@@ -1515,7 +1515,7 @@ static struct sk_buff *vxlan_na_create(struct sk_buff *request,
int ns_olen;
int i, len;
- if (dev == NULL)
+ if (dev == NULL || !pskb_may_pull(request, request->len))
return NULL;
len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) +
@@ -1530,10 +1530,11 @@ static struct sk_buff *vxlan_na_create(struct sk_buff *request,
skb_push(reply, sizeof(struct ethhdr));
skb_reset_mac_header(reply);
- ns = (struct nd_msg *)skb_transport_header(request);
+ ns = (struct nd_msg *)(ipv6_hdr(request) + 1);
daddr = eth_hdr(request)->h_source;
- ns_olen = request->len - skb_transport_offset(request) - sizeof(*ns);
+ ns_olen = request->len - skb_network_offset(request) -
+ sizeof(struct ipv6hdr) - sizeof(*ns);
for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) {
if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
@@ -1604,10 +1605,13 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni)
if (!in6_dev)
goto out;
+ if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg)))
+ goto out;
+
iphdr = ipv6_hdr(skb);
daddr = &iphdr->daddr;
- msg = (struct nd_msg *)skb_transport_header(skb);
+ msg = (struct nd_msg *)(iphdr + 1);
if (msg->icmph.icmp6_code != 0 ||
msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
goto out;
@@ -2242,16 +2246,13 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
if (ntohs(eth->h_proto) == ETH_P_ARP)
return arp_reduce(dev, skb, vni);
#if IS_ENABLED(CONFIG_IPV6)
- else if (ntohs(eth->h_proto) == ETH_P_IPV6 &&
- pskb_may_pull(skb, sizeof(struct ipv6hdr)
- + sizeof(struct nd_msg)) &&
- ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) {
- struct nd_msg *msg;
-
- msg = (struct nd_msg *)skb_transport_header(skb);
- if (msg->icmph.icmp6_code == 0 &&
- msg->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION)
- return neigh_reduce(dev, skb, vni);
+ else if (ntohs(eth->h_proto) == ETH_P_IPV6) {
+ struct ipv6hdr *hdr, _hdr;
+ if ((hdr = skb_header_pointer(skb,
+ skb_network_offset(skb),
+ sizeof(_hdr), &_hdr)) &&
+ hdr->nexthdr == IPPROTO_ICMPV6)
+ return neigh_reduce(dev, skb, vni);
}
#endif
}
@@ -2322,6 +2323,9 @@ static void vxlan_cleanup(unsigned long arg)
if (f->state & (NUD_PERMANENT | NUD_NOARP))
continue;
+ if (f->flags & NTF_EXT_LEARNED)
+ continue;
+
timeout = f->used + vxlan->cfg.age_interval * HZ;
if (time_before_eq(timeout, jiffies)) {
netdev_dbg(vxlan->dev,
@@ -2923,6 +2927,11 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
return -EINVAL;
}
+ if (lowerdev) {
+ dev->gso_max_size = lowerdev->gso_max_size;
+ dev->gso_max_segs = lowerdev->gso_max_segs;
+ }
+
if (conf->mtu) {
int max_mtu = ETH_MAX_MTU;
@@ -2976,6 +2985,44 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
return 0;
}
+static int __vxlan_dev_create(struct net *net, struct net_device *dev,
+ struct vxlan_config *conf)
+{
+ struct vxlan_net *vn = net_generic(net, vxlan_net_id);
+ struct vxlan_dev *vxlan = netdev_priv(dev);
+ int err;
+
+ err = vxlan_dev_configure(net, dev, conf, false);
+ if (err)
+ return err;
+
+ dev->ethtool_ops = &vxlan_ethtool_ops;
+
+ /* create an fdb entry for a valid default destination */
+ if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) {
+ err = vxlan_fdb_create(vxlan, all_zeros_mac,
+ &vxlan->default_dst.remote_ip,
+ NUD_REACHABLE | NUD_PERMANENT,
+ NLM_F_EXCL | NLM_F_CREATE,
+ vxlan->cfg.dst_port,
+ vxlan->default_dst.remote_vni,
+ vxlan->default_dst.remote_vni,
+ vxlan->default_dst.remote_ifindex,
+ NTF_SELF);
+ if (err)
+ return err;
+ }
+
+ err = register_netdevice(dev);
+ if (err) {
+ vxlan_fdb_delete_default(vxlan, vxlan->default_dst.remote_vni);
+ return err;
+ }
+
+ list_add(&vxlan->next, &vn->vxlan_list);
+ return 0;
+}
+
static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
struct net_device *dev, struct vxlan_config *conf,
bool changelink)
@@ -3172,8 +3219,6 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
static int vxlan_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
- struct vxlan_net *vn = net_generic(src_net, vxlan_net_id);
- struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_config conf;
int err;
@@ -3181,36 +3226,7 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev,
if (err)
return err;
- err = vxlan_dev_configure(src_net, dev, &conf, false);
- if (err)
- return err;
-
- dev->ethtool_ops = &vxlan_ethtool_ops;
-
- /* create an fdb entry for a valid default destination */
- if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) {
- err = vxlan_fdb_create(vxlan, all_zeros_mac,
- &vxlan->default_dst.remote_ip,
- NUD_REACHABLE | NUD_PERMANENT,
- NLM_F_EXCL | NLM_F_CREATE,
- vxlan->cfg.dst_port,
- vxlan->default_dst.remote_vni,
- vxlan->default_dst.remote_vni,
- vxlan->default_dst.remote_ifindex,
- NTF_SELF);
- if (err)
- return err;
- }
-
- err = register_netdevice(dev);
- if (err) {
- vxlan_fdb_delete_default(vxlan, vxlan->default_dst.remote_vni);
- return err;
- }
-
- list_add(&vxlan->next, &vn->vxlan_list);
-
- return 0;
+ return __vxlan_dev_create(src_net, dev, &conf);
}
static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
@@ -3440,7 +3456,7 @@ struct net_device *vxlan_dev_create(struct net *net, const char *name,
if (IS_ERR(dev))
return dev;
- err = vxlan_dev_configure(net, dev, conf, false);
+ err = __vxlan_dev_create(net, dev, conf);
if (err < 0) {
free_netdev(dev);
return ERR_PTR(err);
diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c
index a5045b5..6742ae6 100644
--- a/drivers/net/wan/fsl_ucc_hdlc.c
+++ b/drivers/net/wan/fsl_ucc_hdlc.c
@@ -381,8 +381,8 @@ static netdev_tx_t ucc_hdlc_tx(struct sk_buff *skb, struct net_device *dev)
/* set bd status and length */
bd_status = (bd_status & T_W_S) | T_R_S | T_I_S | T_L_S | T_TC_S;
- iowrite16be(bd_status, &bd->status);
iowrite16be(skb->len, &bd->length);
+ iowrite16be(bd_status, &bd->status);
/* Move to next BD in the ring */
if (!(bd_status & T_W_S))
@@ -457,7 +457,7 @@ static int hdlc_rx_done(struct ucc_hdlc_private *priv, int rx_work_limit)
struct sk_buff *skb;
hdlc_device *hdlc = dev_to_hdlc(dev);
struct qe_bd *bd;
- u32 bd_status;
+ u16 bd_status;
u16 length, howmany = 0;
u8 *bdbuffer;
int i;
diff --git a/drivers/net/wimax/i2400m/usb.c b/drivers/net/wimax/i2400m/usb.c
index e7f5910..f8eb66e 100644
--- a/drivers/net/wimax/i2400m/usb.c
+++ b/drivers/net/wimax/i2400m/usb.c
@@ -467,6 +467,9 @@ int i2400mu_probe(struct usb_interface *iface,
struct i2400mu *i2400mu;
struct usb_device *usb_dev = interface_to_usbdev(iface);
+ if (iface->cur_altsetting->desc.bNumEndpoints < 4)
+ return -ENODEV;
+
if (usb_dev->speed != USB_SPEED_HIGH)
dev_err(dev, "device not connected as high speed\n");
diff --git a/drivers/net/wireless/ath/ath10k/hw.c b/drivers/net/wireless/ath/ath10k/hw.c
index 85582bd..c866ab5 100644
--- a/drivers/net/wireless/ath/ath10k/hw.c
+++ b/drivers/net/wireless/ath/ath10k/hw.c
@@ -52,7 +52,7 @@ const struct ath10k_hw_regs qca6174_regs = {
.rtc_soc_base_address = 0x00000800,
.rtc_wmac_base_address = 0x00001000,
.soc_core_base_address = 0x0003a000,
- .wlan_mac_base_address = 0x00020000,
+ .wlan_mac_base_address = 0x00010000,
.ce_wrapper_base_address = 0x00034000,
.ce0_base_address = 0x00034400,
.ce1_base_address = 0x00034800,
diff --git a/drivers/net/wireless/ath/wcn36xx/Kconfig b/drivers/net/wireless/ath/wcn36xx/Kconfig
index 4b83e87..20bf967 100644
--- a/drivers/net/wireless/ath/wcn36xx/Kconfig
+++ b/drivers/net/wireless/ath/wcn36xx/Kconfig
@@ -2,7 +2,7 @@
tristate "Qualcomm Atheros WCN3660/3680 support"
depends on MAC80211 && HAS_DMA
depends on QCOM_WCNSS_CTRL || QCOM_WCNSS_CTRL=n
- depends on QCOM_SMD || QCOM_SMD=n
+ depends on RPMSG || RPMSG=n
---help---
This module adds support for wireless adapters based on
Qualcomm Atheros WCN3660 and WCN3680 mobile chipsets.
diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c
index 2b05154..ac919e4 100644
--- a/drivers/net/wireless/ath/wcn36xx/main.c
+++ b/drivers/net/wireless/ath/wcn36xx/main.c
@@ -22,7 +22,7 @@
#include <linux/of_address.h>
#include <linux/of_device.h>
#include <linux/of_irq.h>
-#include <linux/soc/qcom/smd.h>
+#include <linux/rpmsg.h>
#include <linux/soc/qcom/smem_state.h>
#include <linux/soc/qcom/wcnss_ctrl.h>
#include "wcn36xx.h"
@@ -1218,15 +1218,13 @@ static int wcn36xx_probe(struct platform_device *pdev)
INIT_WORK(&wcn->scan_work, wcn36xx_hw_scan_worker);
- wcn->smd_channel = qcom_wcnss_open_channel(wcnss, "WLAN_CTRL", wcn36xx_smd_rsp_process);
+ wcn->smd_channel = qcom_wcnss_open_channel(wcnss, "WLAN_CTRL", wcn36xx_smd_rsp_process, hw);
if (IS_ERR(wcn->smd_channel)) {
wcn36xx_err("failed to open WLAN_CTRL channel\n");
ret = PTR_ERR(wcn->smd_channel);
goto out_wq;
}
- qcom_smd_set_drvdata(wcn->smd_channel, hw);
-
addr = of_get_property(pdev->dev.of_node, "local-mac-address", &ret);
if (addr && ret != ETH_ALEN) {
wcn36xx_err("invalid local-mac-address\n");
diff --git a/drivers/net/wireless/ath/wcn36xx/smd.c b/drivers/net/wireless/ath/wcn36xx/smd.c
index 1c2966f..9c6590d 100644
--- a/drivers/net/wireless/ath/wcn36xx/smd.c
+++ b/drivers/net/wireless/ath/wcn36xx/smd.c
@@ -19,7 +19,7 @@
#include <linux/etherdevice.h>
#include <linux/firmware.h>
#include <linux/bitops.h>
-#include <linux/soc/qcom/smd.h>
+#include <linux/rpmsg.h>
#include "smd.h"
struct wcn36xx_cfg_val {
@@ -254,7 +254,7 @@ static int wcn36xx_smd_send_and_wait(struct wcn36xx *wcn, size_t len)
init_completion(&wcn->hal_rsp_compl);
start = jiffies;
- ret = qcom_smd_send(wcn->smd_channel, wcn->hal_buf, len);
+ ret = rpmsg_send(wcn->smd_channel, wcn->hal_buf, len);
if (ret) {
wcn36xx_err("HAL TX failed\n");
goto out;
@@ -2205,11 +2205,11 @@ int wcn36xx_smd_set_mc_list(struct wcn36xx *wcn,
return ret;
}
-int wcn36xx_smd_rsp_process(struct qcom_smd_channel *channel,
- const void *buf, size_t len)
+int wcn36xx_smd_rsp_process(struct rpmsg_device *rpdev,
+ void *buf, int len, void *priv, u32 addr)
{
const struct wcn36xx_hal_msg_header *msg_header = buf;
- struct ieee80211_hw *hw = qcom_smd_get_drvdata(channel);
+ struct ieee80211_hw *hw = priv;
struct wcn36xx *wcn = hw->priv;
struct wcn36xx_hal_ind_msg *msg_ind;
wcn36xx_dbg_dump(WCN36XX_DBG_SMD_DUMP, "SMD <<< ", buf, len);
diff --git a/drivers/net/wireless/ath/wcn36xx/smd.h b/drivers/net/wireless/ath/wcn36xx/smd.h
index 8892ccd..013fc95 100644
--- a/drivers/net/wireless/ath/wcn36xx/smd.h
+++ b/drivers/net/wireless/ath/wcn36xx/smd.h
@@ -51,7 +51,7 @@ struct wcn36xx_hal_ind_msg {
};
struct wcn36xx;
-struct qcom_smd_channel;
+struct rpmsg_device;
int wcn36xx_smd_open(struct wcn36xx *wcn);
void wcn36xx_smd_close(struct wcn36xx *wcn);
@@ -129,8 +129,8 @@ int wcn36xx_smd_trigger_ba(struct wcn36xx *wcn, u8 sta_index);
int wcn36xx_smd_update_cfg(struct wcn36xx *wcn, u32 cfg_id, u32 value);
-int wcn36xx_smd_rsp_process(struct qcom_smd_channel *channel,
- const void *buf, size_t len);
+int wcn36xx_smd_rsp_process(struct rpmsg_device *rpdev,
+ void *buf, int len, void *priv, u32 addr);
int wcn36xx_smd_set_mc_list(struct wcn36xx *wcn,
struct ieee80211_vif *vif,
diff --git a/drivers/net/wireless/ath/wcn36xx/wcn36xx.h b/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
index 7423998..b52b4da9 100644
--- a/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
+++ b/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
@@ -195,7 +195,7 @@ struct wcn36xx {
void __iomem *ccu_base;
void __iomem *dxe_base;
- struct qcom_smd_channel *smd_channel;
+ struct rpmsg_endpoint *smd_channel;
struct qcom_smem_state *tx_enable_state;
unsigned tx_enable_state_bit;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
index 5bc2ba2..9b970dc 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
@@ -21,6 +21,7 @@
#include <linux/pci_ids.h>
#include <linux/sched.h>
#include <linux/completion.h>
+#include <linux/interrupt.h>
#include <linux/scatterlist.h>
#include <linux/mmc/sdio.h>
#include <linux/mmc/core.h>
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
index de19c7c..85d949e 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
@@ -2238,14 +2238,16 @@ int brcmf_p2p_del_vif(struct wiphy *wiphy, struct wireless_dev *wdev)
struct brcmf_cfg80211_info *cfg = wiphy_priv(wiphy);
struct brcmf_p2p_info *p2p = &cfg->p2p;
struct brcmf_cfg80211_vif *vif;
+ enum nl80211_iftype iftype;
bool wait_for_disable = false;
int err;
brcmf_dbg(TRACE, "delete P2P vif\n");
vif = container_of(wdev, struct brcmf_cfg80211_vif, wdev);
+ iftype = vif->wdev.iftype;
brcmf_cfg80211_arm_vif_event(cfg, vif);
- switch (vif->wdev.iftype) {
+ switch (iftype) {
case NL80211_IFTYPE_P2P_CLIENT:
if (test_bit(BRCMF_VIF_STATUS_DISCONNECTING, &vif->sme_state))
wait_for_disable = true;
@@ -2275,7 +2277,7 @@ int brcmf_p2p_del_vif(struct wiphy *wiphy, struct wireless_dev *wdev)
BRCMF_P2P_DISABLE_TIMEOUT);
err = 0;
- if (vif->wdev.iftype != NL80211_IFTYPE_P2P_DEVICE) {
+ if (iftype != NL80211_IFTYPE_P2P_DEVICE) {
brcmf_vif_clear_mgmt_ies(vif);
err = brcmf_p2p_release_p2p_if(vif);
}
@@ -2291,7 +2293,7 @@ int brcmf_p2p_del_vif(struct wiphy *wiphy, struct wireless_dev *wdev)
brcmf_remove_interface(vif->ifp, true);
brcmf_cfg80211_arm_vif_event(cfg, NULL);
- if (vif->wdev.iftype != NL80211_IFTYPE_P2P_DEVICE)
+ if (iftype != NL80211_IFTYPE_P2P_DEVICE)
p2p->bss_idx[P2PAPI_BSSCFG_CONNECTION].vif = NULL;
return err;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
index a260cd5..077bfd8 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
@@ -1056,6 +1056,8 @@ static ssize_t iwl_dbgfs_fw_dbg_collect_write(struct iwl_mvm *mvm,
if (ret)
return ret;
+ if (count == 0)
+ return 0;
iwl_mvm_fw_dbg_collect(mvm, FW_DBG_TRIGGER_USER, buf,
(count - 1), NULL);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index 99132ea..c5734e1 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -216,7 +216,8 @@ u32 iwl_mvm_mac_get_queues_mask(struct ieee80211_vif *vif)
qmask |= BIT(vif->hw_queue[ac]);
}
- if (vif->type == NL80211_IFTYPE_AP)
+ if (vif->type == NL80211_IFTYPE_AP ||
+ vif->type == NL80211_IFTYPE_ADHOC)
qmask |= BIT(vif->cab_queue);
return qmask;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index d37b169..486dcce 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -2319,7 +2319,7 @@ iwl_mvm_mac_release_buffered_frames(struct ieee80211_hw *hw,
{
struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
- /* Called when we need to transmit (a) frame(s) from agg queue */
+ /* Called when we need to transmit (a) frame(s) from agg or dqa queue */
iwl_mvm_sta_modify_sleep_tx_count(mvm, sta, reason, num_frames,
tids, more_data, true);
@@ -2338,7 +2338,8 @@ static void __iwl_mvm_mac_sta_notify(struct ieee80211_hw *hw,
for (tid = 0; tid < IWL_MAX_TID_COUNT; tid++) {
struct iwl_mvm_tid_data *tid_data = &mvmsta->tid_data[tid];
- if (tid_data->state != IWL_AGG_ON &&
+ if (!iwl_mvm_is_dqa_supported(mvm) &&
+ tid_data->state != IWL_AGG_ON &&
tid_data->state != IWL_EMPTYING_HW_QUEUE_DELBA)
continue;
@@ -2400,7 +2401,7 @@ void iwl_mvm_sta_pm_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb)
return;
rcu_read_lock();
- sta = mvm->fw_id_to_mac_id[notif->sta_id];
+ sta = rcu_dereference(mvm->fw_id_to_mac_id[notif->sta_id]);
if (WARN_ON(IS_ERR_OR_NULL(sta))) {
rcu_read_unlock();
return;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index bd1dcc8..9d28db7 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -1806,7 +1806,8 @@ int iwl_mvm_send_add_bcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
iwl_mvm_get_wd_timeout(mvm, vif, false, false);
int queue;
- if (vif->type == NL80211_IFTYPE_AP)
+ if (vif->type == NL80211_IFTYPE_AP ||
+ vif->type == NL80211_IFTYPE_ADHOC)
queue = IWL_MVM_DQA_AP_PROBE_RESP_QUEUE;
else if (vif->type == NL80211_IFTYPE_P2P_DEVICE)
queue = IWL_MVM_DQA_P2P_DEVICE_QUEUE;
@@ -1837,7 +1838,8 @@ int iwl_mvm_send_add_bcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
* enabled-cab_queue to the mask)
*/
if (iwl_mvm_is_dqa_supported(mvm) &&
- vif->type == NL80211_IFTYPE_AP) {
+ (vif->type == NL80211_IFTYPE_AP ||
+ vif->type == NL80211_IFTYPE_ADHOC)) {
struct iwl_trans_txq_scd_cfg cfg = {
.fifo = IWL_MVM_TX_FIFO_MCAST,
.sta_id = mvmvif->bcast_sta.sta_id,
@@ -1862,7 +1864,8 @@ static void iwl_mvm_free_bcast_sta_queues(struct iwl_mvm *mvm,
lockdep_assert_held(&mvm->mutex);
- if (vif->type == NL80211_IFTYPE_AP)
+ if (vif->type == NL80211_IFTYPE_AP ||
+ vif->type == NL80211_IFTYPE_ADHOC)
iwl_mvm_disable_txq(mvm, vif->cab_queue, vif->cab_queue,
IWL_MAX_TID_COUNT, 0);
@@ -3135,7 +3138,7 @@ void iwl_mvm_sta_modify_sleep_tx_count(struct iwl_mvm *mvm,
struct ieee80211_sta *sta,
enum ieee80211_frame_release_type reason,
u16 cnt, u16 tids, bool more_data,
- bool agg)
+ bool single_sta_queue)
{
struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
struct iwl_mvm_add_sta_cmd cmd = {
@@ -3155,14 +3158,14 @@ void iwl_mvm_sta_modify_sleep_tx_count(struct iwl_mvm *mvm,
for_each_set_bit(tid, &_tids, IWL_MAX_TID_COUNT)
cmd.awake_acs |= BIT(tid_to_ucode_ac[tid]);
- /* If we're releasing frames from aggregation queues then check if the
- * all queues combined that we're releasing frames from have
+ /* If we're releasing frames from aggregation or dqa queues then check
+ * if all the queues that we're releasing frames from, combined, have:
* - more frames than the service period, in which case more_data
* needs to be set
* - fewer than 'cnt' frames, in which case we need to adjust the
* firmware command (but do that unconditionally)
*/
- if (agg) {
+ if (single_sta_queue) {
int remaining = cnt;
int sleep_tx_count;
@@ -3172,7 +3175,8 @@ void iwl_mvm_sta_modify_sleep_tx_count(struct iwl_mvm *mvm,
u16 n_queued;
tid_data = &mvmsta->tid_data[tid];
- if (WARN(tid_data->state != IWL_AGG_ON &&
+ if (WARN(!iwl_mvm_is_dqa_supported(mvm) &&
+ tid_data->state != IWL_AGG_ON &&
tid_data->state != IWL_EMPTYING_HW_QUEUE_DELBA,
"TID %d state is %d\n",
tid, tid_data->state)) {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
index 4be34f9..1927ce6 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
@@ -547,7 +547,7 @@ void iwl_mvm_sta_modify_sleep_tx_count(struct iwl_mvm *mvm,
struct ieee80211_sta *sta,
enum ieee80211_frame_release_type reason,
u16 cnt, u16 tids, bool more_data,
- bool agg);
+ bool single_sta_queue);
int iwl_mvm_drain_sta(struct iwl_mvm *mvm, struct iwl_mvm_sta *mvmsta,
bool drain);
void iwl_mvm_sta_modify_disable_tx(struct iwl_mvm *mvm,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index dd2b4a3..1ba0a6f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -7,7 +7,7 @@
*
* Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
- * Copyright(c) 2016 Intel Deutschland GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
@@ -34,6 +34,7 @@
*
* Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
@@ -505,6 +506,7 @@ static int iwl_mvm_get_ctrl_vif_queue(struct iwl_mvm *mvm,
switch (info->control.vif->type) {
case NL80211_IFTYPE_AP:
+ case NL80211_IFTYPE_ADHOC:
/*
* Handle legacy hostapd as well, where station may be added
* only after assoc. Take care of the case where we send a
@@ -516,7 +518,8 @@ static int iwl_mvm_get_ctrl_vif_queue(struct iwl_mvm *mvm,
if (info->hw_queue == info->control.vif->cab_queue)
return info->hw_queue;
- WARN_ONCE(1, "fc=0x%02x", le16_to_cpu(fc));
+ WARN_ONCE(info->control.vif->type != NL80211_IFTYPE_ADHOC,
+ "fc=0x%02x", le16_to_cpu(fc));
return IWL_MVM_DQA_AP_PROBE_RESP_QUEUE;
case NL80211_IFTYPE_P2P_DEVICE:
if (ieee80211_is_mgmt(fc))
@@ -583,7 +586,8 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb)
iwl_mvm_vif_from_mac80211(info.control.vif);
if (info.control.vif->type == NL80211_IFTYPE_P2P_DEVICE ||
- info.control.vif->type == NL80211_IFTYPE_AP) {
+ info.control.vif->type == NL80211_IFTYPE_AP ||
+ info.control.vif->type == NL80211_IFTYPE_ADHOC) {
sta_id = mvmvif->bcast_sta.sta_id;
queue = iwl_mvm_get_ctrl_vif_queue(mvm, &info,
hdr->frame_control);
@@ -628,8 +632,10 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb)
* values.
* Note that we don't need to make sure it isn't agg'd, since we're
* TXing non-sta
+ * For DQA mode - we shouldn't increase it though
*/
- atomic_inc(&mvm->pending_frames[sta_id]);
+ if (!iwl_mvm_is_dqa_supported(mvm))
+ atomic_inc(&mvm->pending_frames[sta_id]);
return 0;
}
@@ -1005,11 +1011,8 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
spin_unlock(&mvmsta->lock);
- /* Increase pending frames count if this isn't AMPDU */
- if ((iwl_mvm_is_dqa_supported(mvm) &&
- mvmsta->tid_data[tx_cmd->tid_tspec].state != IWL_AGG_ON &&
- mvmsta->tid_data[tx_cmd->tid_tspec].state != IWL_AGG_STARTING) ||
- (!iwl_mvm_is_dqa_supported(mvm) && !is_ampdu))
+ /* Increase pending frames count if this isn't AMPDU or DQA queue */
+ if (!iwl_mvm_is_dqa_supported(mvm) && !is_ampdu)
atomic_inc(&mvm->pending_frames[mvmsta->sta_id]);
return 0;
@@ -1079,12 +1082,13 @@ static void iwl_mvm_check_ratid_empty(struct iwl_mvm *mvm,
lockdep_assert_held(&mvmsta->lock);
if ((tid_data->state == IWL_AGG_ON ||
- tid_data->state == IWL_EMPTYING_HW_QUEUE_DELBA) &&
+ tid_data->state == IWL_EMPTYING_HW_QUEUE_DELBA ||
+ iwl_mvm_is_dqa_supported(mvm)) &&
iwl_mvm_tid_queued(tid_data) == 0) {
/*
- * Now that this aggregation queue is empty tell mac80211 so it
- * knows we no longer have frames buffered for the station on
- * this TID (for the TIM bitmap calculation.)
+ * Now that this aggregation or DQA queue is empty tell
+ * mac80211 so it knows we no longer have frames buffered for
+ * the station on this TID (for the TIM bitmap calculation.)
*/
ieee80211_sta_set_buffered(sta, tid, false);
}
@@ -1257,7 +1261,6 @@ static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm,
u8 skb_freed = 0;
u16 next_reclaimed, seq_ctl;
bool is_ndp = false;
- bool txq_agg = false; /* Is this TXQ aggregated */
__skb_queue_head_init(&skbs);
@@ -1283,6 +1286,10 @@ static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm,
info->flags |= IEEE80211_TX_STAT_ACK;
break;
case TX_STATUS_FAIL_DEST_PS:
+ /* In DQA, the FW should have stopped the queue and not
+ * return this status
+ */
+ WARN_ON(iwl_mvm_is_dqa_supported(mvm));
info->flags |= IEEE80211_TX_STAT_TX_FILTERED;
break;
default:
@@ -1387,15 +1394,6 @@ static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm,
bool send_eosp_ndp = false;
spin_lock_bh(&mvmsta->lock);
- if (iwl_mvm_is_dqa_supported(mvm)) {
- enum iwl_mvm_agg_state state;
-
- state = mvmsta->tid_data[tid].state;
- txq_agg = (state == IWL_AGG_ON ||
- state == IWL_EMPTYING_HW_QUEUE_DELBA);
- } else {
- txq_agg = txq_id >= mvm->first_agg_queue;
- }
if (!is_ndp) {
tid_data->next_reclaimed = next_reclaimed;
@@ -1452,11 +1450,11 @@ static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm,
* If the txq is not an AMPDU queue, there is no chance we freed
* several skbs. Check that out...
*/
- if (txq_agg)
+ if (iwl_mvm_is_dqa_supported(mvm) || txq_id >= mvm->first_agg_queue)
goto out;
/* We can't free more than one frame at once on a shared queue */
- WARN_ON(!iwl_mvm_is_dqa_supported(mvm) && (skb_freed > 1));
+ WARN_ON(skb_freed > 1);
/* If we have still frames for this STA nothing to do here */
if (!atomic_sub_and_test(skb_freed, &mvm->pending_frames[sta_id]))
diff --git a/drivers/net/wireless/marvell/mwifiex/main.c b/drivers/net/wireless/marvell/mwifiex/main.c
index 0dfbac8..912b687 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.c
+++ b/drivers/net/wireless/marvell/mwifiex/main.c
@@ -59,8 +59,8 @@ MODULE_PARM_DESC(mfg_mode, "manufacturing mode enable:1, disable:0");
* In case of any errors during inittialization, this function also ensures
* proper cleanup before exiting.
*/
-static int mwifiex_register(void *card, struct mwifiex_if_ops *if_ops,
- void **padapter)
+static int mwifiex_register(void *card, struct device *dev,
+ struct mwifiex_if_ops *if_ops, void **padapter)
{
struct mwifiex_adapter *adapter;
int i;
@@ -70,6 +70,7 @@ static int mwifiex_register(void *card, struct mwifiex_if_ops *if_ops,
return -ENOMEM;
*padapter = adapter;
+ adapter->dev = dev;
adapter->card = card;
/* Save interface specific operations in adapter */
@@ -1581,12 +1582,11 @@ mwifiex_add_card(void *card, struct completion *fw_done,
{
struct mwifiex_adapter *adapter;
- if (mwifiex_register(card, if_ops, (void **)&adapter)) {
+ if (mwifiex_register(card, dev, if_ops, (void **)&adapter)) {
pr_err("%s: software init failed\n", __func__);
goto err_init_sw;
}
- adapter->dev = dev;
mwifiex_probe_of(adapter);
adapter->iface_type = iface_type;
@@ -1731,6 +1731,9 @@ int mwifiex_remove_card(struct mwifiex_adapter *adapter)
wiphy_unregister(adapter->wiphy);
wiphy_free(adapter->wiphy);
+ if (adapter->irq_wakeup >= 0)
+ device_init_wakeup(adapter->dev, false);
+
/* Unregister device */
mwifiex_dbg(adapter, INFO,
"info: unregister device\n");
diff --git a/drivers/net/wireless/marvell/mwifiex/pcie.c b/drivers/net/wireless/marvell/mwifiex/pcie.c
index f45ab12..92ffb1b 100644
--- a/drivers/net/wireless/marvell/mwifiex/pcie.c
+++ b/drivers/net/wireless/marvell/mwifiex/pcie.c
@@ -2730,6 +2730,21 @@ static void mwifiex_pcie_device_dump(struct mwifiex_adapter *adapter)
schedule_work(&card->work);
}
+static void mwifiex_pcie_free_buffers(struct mwifiex_adapter *adapter)
+{
+ struct pcie_service_card *card = adapter->card;
+ const struct mwifiex_pcie_card_reg *reg = card->pcie.reg;
+
+ if (reg->sleep_cookie)
+ mwifiex_pcie_delete_sleep_cookie_buf(adapter);
+
+ mwifiex_pcie_delete_cmdrsp_buf(adapter);
+ mwifiex_pcie_delete_evtbd_ring(adapter);
+ mwifiex_pcie_delete_rxbd_ring(adapter);
+ mwifiex_pcie_delete_txbd_ring(adapter);
+ card->cmdrsp_buf = NULL;
+}
+
/*
* This function initializes the PCI-E host memory space, WCB rings, etc.
*
@@ -2841,13 +2856,6 @@ static int mwifiex_init_pcie(struct mwifiex_adapter *adapter)
/*
* This function cleans up the allocated card buffers.
- *
- * The following are freed by this function -
- * - TXBD ring buffers
- * - RXBD ring buffers
- * - Event BD ring buffers
- * - Command response ring buffer
- * - Sleep cookie buffer
*/
static void mwifiex_cleanup_pcie(struct mwifiex_adapter *adapter)
{
@@ -2868,6 +2876,8 @@ static void mwifiex_cleanup_pcie(struct mwifiex_adapter *adapter)
"Failed to write driver not-ready signature\n");
}
+ mwifiex_pcie_free_buffers(adapter);
+
if (pdev) {
pci_iounmap(pdev, card->pci_mmap);
pci_iounmap(pdev, card->pci_mmap1);
@@ -3119,10 +3129,7 @@ static void mwifiex_pcie_up_dev(struct mwifiex_adapter *adapter)
pci_iounmap(pdev, card->pci_mmap1);
}
-/* This function cleans up the PCI-E host memory space.
- * Some code is extracted from mwifiex_unregister_dev()
- *
- */
+/* This function cleans up the PCI-E host memory space. */
static void mwifiex_pcie_down_dev(struct mwifiex_adapter *adapter)
{
struct pcie_service_card *card = adapter->card;
@@ -3133,14 +3140,7 @@ static void mwifiex_pcie_down_dev(struct mwifiex_adapter *adapter)
adapter->seq_num = 0;
- if (reg->sleep_cookie)
- mwifiex_pcie_delete_sleep_cookie_buf(adapter);
-
- mwifiex_pcie_delete_cmdrsp_buf(adapter);
- mwifiex_pcie_delete_evtbd_ring(adapter);
- mwifiex_pcie_delete_rxbd_ring(adapter);
- mwifiex_pcie_delete_txbd_ring(adapter);
- card->cmdrsp_buf = NULL;
+ mwifiex_pcie_free_buffers(adapter);
}
static struct mwifiex_if_ops pcie_ops = {
diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c
index caea350..bdc3791 100644
--- a/drivers/net/wireless/realtek/rtlwifi/base.c
+++ b/drivers/net/wireless/realtek/rtlwifi/base.c
@@ -1742,12 +1742,14 @@ void rtl_c2hcmd_enqueue(struct ieee80211_hw *hw, u8 tag, u8 len, u8 *val)
unsigned long flags;
struct rtl_c2hcmd *c2hcmd;
- c2hcmd = kmalloc(sizeof(*c2hcmd), GFP_KERNEL);
+ c2hcmd = kmalloc(sizeof(*c2hcmd),
+ in_interrupt() ? GFP_ATOMIC : GFP_KERNEL);
if (!c2hcmd)
goto label_err;
- c2hcmd->val = kmalloc(len, GFP_KERNEL);
+ c2hcmd->val = kmalloc(len,
+ in_interrupt() ? GFP_ATOMIC : GFP_KERNEL);
if (!c2hcmd->val)
goto label_err2;
diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c
index 785334f..3b68eaff 100644
--- a/drivers/net/wireless/rndis_wlan.c
+++ b/drivers/net/wireless/rndis_wlan.c
@@ -3392,6 +3392,7 @@ static const struct net_device_ops rndis_wlan_netdev_ops = {
.ndo_stop = usbnet_stop,
.ndo_start_xmit = usbnet_start_xmit,
.ndo_tx_timeout = usbnet_tx_timeout,
+ .ndo_get_stats64 = usbnet_get_stats64,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_rx_mode = rndis_wlan_set_multicast_list,
diff --git a/drivers/net/wireless/st/cw1200/cw1200_sdio.c b/drivers/net/wireless/st/cw1200/cw1200_sdio.c
index d3acc85..709f56e 100644
--- a/drivers/net/wireless/st/cw1200/cw1200_sdio.c
+++ b/drivers/net/wireless/st/cw1200/cw1200_sdio.c
@@ -10,6 +10,7 @@
*/
#include <linux/module.h>
+#include <linux/interrupt.h>
#include <linux/gpio.h>
#include <linux/delay.h>
#include <linux/mmc/host.h>
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 829b26c..8397f6c 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -165,13 +165,17 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct xenvif *vif = netdev_priv(dev);
struct xenvif_queue *queue = NULL;
- unsigned int num_queues = vif->num_queues;
+ unsigned int num_queues;
u16 index;
struct xenvif_rx_cb *cb;
BUG_ON(skb->dev != dev);
- /* Drop the packet if queues are not set up */
+ /* Drop the packet if queues are not set up.
+ * This handler should be called inside an RCU read section
+ * so we don't need to enter it here explicitly.
+ */
+ num_queues = READ_ONCE(vif->num_queues);
if (num_queues < 1)
goto drop;
@@ -222,18 +226,18 @@ static struct net_device_stats *xenvif_get_stats(struct net_device *dev)
{
struct xenvif *vif = netdev_priv(dev);
struct xenvif_queue *queue = NULL;
+ unsigned int num_queues;
u64 rx_bytes = 0;
u64 rx_packets = 0;
u64 tx_bytes = 0;
u64 tx_packets = 0;
unsigned int index;
- spin_lock(&vif->lock);
- if (vif->queues == NULL)
- goto out;
+ rcu_read_lock();
+ num_queues = READ_ONCE(vif->num_queues);
/* Aggregate tx and rx stats from each queue */
- for (index = 0; index < vif->num_queues; ++index) {
+ for (index = 0; index < num_queues; ++index) {
queue = &vif->queues[index];
rx_bytes += queue->stats.rx_bytes;
rx_packets += queue->stats.rx_packets;
@@ -241,8 +245,7 @@ static struct net_device_stats *xenvif_get_stats(struct net_device *dev)
tx_packets += queue->stats.tx_packets;
}
-out:
- spin_unlock(&vif->lock);
+ rcu_read_unlock();
vif->dev->stats.rx_bytes = rx_bytes;
vif->dev->stats.rx_packets = rx_packets;
@@ -378,10 +381,13 @@ static void xenvif_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 * data)
{
struct xenvif *vif = netdev_priv(dev);
- unsigned int num_queues = vif->num_queues;
+ unsigned int num_queues;
int i;
unsigned int queue_index;
+ rcu_read_lock();
+ num_queues = READ_ONCE(vif->num_queues);
+
for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++) {
unsigned long accum = 0;
for (queue_index = 0; queue_index < num_queues; ++queue_index) {
@@ -390,6 +396,8 @@ static void xenvif_get_ethtool_stats(struct net_device *dev,
}
data[i] = accum;
}
+
+ rcu_read_unlock();
}
static void xenvif_get_strings(struct net_device *dev, u32 stringset, u8 * data)
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index f9bcf4a..602d408 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -214,7 +214,7 @@ static void xenvif_fatal_tx_err(struct xenvif *vif)
netdev_err(vif->dev, "fatal error; disabling device\n");
vif->disabled = true;
/* Disable the vif from queue 0's kthread */
- if (vif->queues)
+ if (vif->num_queues)
xenvif_kick_thread(&vif->queues[0]);
}
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index d2d7cd9..a56d3ea 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -495,26 +495,26 @@ static void backend_disconnect(struct backend_info *be)
struct xenvif *vif = be->vif;
if (vif) {
+ unsigned int num_queues = vif->num_queues;
unsigned int queue_index;
- struct xenvif_queue *queues;
xen_unregister_watchers(vif);
#ifdef CONFIG_DEBUG_FS
xenvif_debugfs_delif(vif);
#endif /* CONFIG_DEBUG_FS */
xenvif_disconnect_data(vif);
- for (queue_index = 0;
- queue_index < vif->num_queues;
- ++queue_index)
+
+ /* At this point some of the handlers may still be active
+ * so we need to have additional synchronization here.
+ */
+ vif->num_queues = 0;
+ synchronize_net();
+
+ for (queue_index = 0; queue_index < num_queues; ++queue_index)
xenvif_deinit_queue(&vif->queues[queue_index]);
- spin_lock(&vif->lock);
- queues = vif->queues;
- vif->num_queues = 0;
+ vfree(vif->queues);
vif->queues = NULL;
- spin_unlock(&vif->lock);
-
- vfree(queues);
xenvif_disconnect_ctrl(vif);
}
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 779f516..47a479f 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -343,8 +343,6 @@ static int __nvme_rdma_init_request(struct nvme_rdma_ctrl *ctrl,
struct ib_device *ibdev = dev->dev;
int ret;
- BUG_ON(queue_idx >= ctrl->queue_count);
-
ret = nvme_rdma_alloc_qe(ibdev, &req->sqe, sizeof(struct nvme_command),
DMA_TO_DEVICE);
if (ret)
@@ -652,8 +650,22 @@ static int nvme_rdma_connect_io_queues(struct nvme_rdma_ctrl *ctrl)
static int nvme_rdma_init_io_queues(struct nvme_rdma_ctrl *ctrl)
{
+ struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
+ unsigned int nr_io_queues;
int i, ret;
+ nr_io_queues = min(opts->nr_io_queues, num_online_cpus());
+ ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues);
+ if (ret)
+ return ret;
+
+ ctrl->queue_count = nr_io_queues + 1;
+ if (ctrl->queue_count < 2)
+ return 0;
+
+ dev_info(ctrl->ctrl.device,
+ "creating %d I/O queues.\n", nr_io_queues);
+
for (i = 1; i < ctrl->queue_count; i++) {
ret = nvme_rdma_init_queue(ctrl, i,
ctrl->ctrl.opts->queue_size);
@@ -1791,20 +1803,8 @@ static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = {
static int nvme_rdma_create_io_queues(struct nvme_rdma_ctrl *ctrl)
{
- struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
int ret;
- ret = nvme_set_queue_count(&ctrl->ctrl, &opts->nr_io_queues);
- if (ret)
- return ret;
-
- ctrl->queue_count = opts->nr_io_queues + 1;
- if (ctrl->queue_count < 2)
- return 0;
-
- dev_info(ctrl->ctrl.device,
- "creating %d I/O queues.\n", opts->nr_io_queues);
-
ret = nvme_rdma_init_io_queues(ctrl);
if (ret)
return ret;
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 11b0a0a..798653b 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -425,6 +425,13 @@ void nvmet_sq_setup(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq,
ctrl->sqs[qid] = sq;
}
+static void nvmet_confirm_sq(struct percpu_ref *ref)
+{
+ struct nvmet_sq *sq = container_of(ref, struct nvmet_sq, ref);
+
+ complete(&sq->confirm_done);
+}
+
void nvmet_sq_destroy(struct nvmet_sq *sq)
{
/*
@@ -433,7 +440,8 @@ void nvmet_sq_destroy(struct nvmet_sq *sq)
*/
if (sq->ctrl && sq->ctrl->sqs && sq->ctrl->sqs[0] == sq)
nvmet_async_events_free(sq->ctrl);
- percpu_ref_kill(&sq->ref);
+ percpu_ref_kill_and_confirm(&sq->ref, nvmet_confirm_sq);
+ wait_for_completion(&sq->confirm_done);
wait_for_completion(&sq->free_done);
percpu_ref_exit(&sq->ref);
@@ -461,6 +469,7 @@ int nvmet_sq_init(struct nvmet_sq *sq)
return ret;
}
init_completion(&sq->free_done);
+ init_completion(&sq->confirm_done);
return 0;
}
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index d1f06e7..22f7bc6 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -223,8 +223,6 @@ static void nvme_loop_submit_async_event(struct nvme_ctrl *arg, int aer_idx)
static int nvme_loop_init_iod(struct nvme_loop_ctrl *ctrl,
struct nvme_loop_iod *iod, unsigned int queue_idx)
{
- BUG_ON(queue_idx >= ctrl->queue_count);
-
iod->req.cmd = &iod->cmd;
iod->req.rsp = &iod->rsp;
iod->queue = &ctrl->queues[queue_idx];
@@ -288,9 +286,9 @@ static struct blk_mq_ops nvme_loop_admin_mq_ops = {
static void nvme_loop_destroy_admin_queue(struct nvme_loop_ctrl *ctrl)
{
+ nvmet_sq_destroy(&ctrl->queues[0].nvme_sq);
blk_cleanup_queue(ctrl->ctrl.admin_q);
blk_mq_free_tag_set(&ctrl->admin_tag_set);
- nvmet_sq_destroy(&ctrl->queues[0].nvme_sq);
}
static void nvme_loop_free_ctrl(struct nvme_ctrl *nctrl)
@@ -314,6 +312,43 @@ static void nvme_loop_free_ctrl(struct nvme_ctrl *nctrl)
kfree(ctrl);
}
+static void nvme_loop_destroy_io_queues(struct nvme_loop_ctrl *ctrl)
+{
+ int i;
+
+ for (i = 1; i < ctrl->queue_count; i++)
+ nvmet_sq_destroy(&ctrl->queues[i].nvme_sq);
+}
+
+static int nvme_loop_init_io_queues(struct nvme_loop_ctrl *ctrl)
+{
+ struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
+ unsigned int nr_io_queues;
+ int ret, i;
+
+ nr_io_queues = min(opts->nr_io_queues, num_online_cpus());
+ ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues);
+ if (ret || !nr_io_queues)
+ return ret;
+
+ dev_info(ctrl->ctrl.device, "creating %d I/O queues.\n", nr_io_queues);
+
+ for (i = 1; i <= nr_io_queues; i++) {
+ ctrl->queues[i].ctrl = ctrl;
+ ret = nvmet_sq_init(&ctrl->queues[i].nvme_sq);
+ if (ret)
+ goto out_destroy_queues;
+
+ ctrl->queue_count++;
+ }
+
+ return 0;
+
+out_destroy_queues:
+ nvme_loop_destroy_io_queues(ctrl);
+ return ret;
+}
+
static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
{
int error;
@@ -385,17 +420,13 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
static void nvme_loop_shutdown_ctrl(struct nvme_loop_ctrl *ctrl)
{
- int i;
-
nvme_stop_keep_alive(&ctrl->ctrl);
if (ctrl->queue_count > 1) {
nvme_stop_queues(&ctrl->ctrl);
blk_mq_tagset_busy_iter(&ctrl->tag_set,
nvme_cancel_request, &ctrl->ctrl);
-
- for (i = 1; i < ctrl->queue_count; i++)
- nvmet_sq_destroy(&ctrl->queues[i].nvme_sq);
+ nvme_loop_destroy_io_queues(ctrl);
}
if (ctrl->ctrl.state == NVME_CTRL_LIVE)
@@ -467,19 +498,14 @@ static void nvme_loop_reset_ctrl_work(struct work_struct *work)
if (ret)
goto out_disable;
- for (i = 1; i <= ctrl->ctrl.opts->nr_io_queues; i++) {
- ctrl->queues[i].ctrl = ctrl;
- ret = nvmet_sq_init(&ctrl->queues[i].nvme_sq);
- if (ret)
- goto out_free_queues;
+ ret = nvme_loop_init_io_queues(ctrl);
+ if (ret)
+ goto out_destroy_admin;
- ctrl->queue_count++;
- }
-
- for (i = 1; i <= ctrl->ctrl.opts->nr_io_queues; i++) {
+ for (i = 1; i < ctrl->queue_count; i++) {
ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
if (ret)
- goto out_free_queues;
+ goto out_destroy_io;
}
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
@@ -492,9 +518,9 @@ static void nvme_loop_reset_ctrl_work(struct work_struct *work)
return;
-out_free_queues:
- for (i = 1; i < ctrl->queue_count; i++)
- nvmet_sq_destroy(&ctrl->queues[i].nvme_sq);
+out_destroy_io:
+ nvme_loop_destroy_io_queues(ctrl);
+out_destroy_admin:
nvme_loop_destroy_admin_queue(ctrl);
out_disable:
dev_warn(ctrl->ctrl.device, "Removing after reset failure\n");
@@ -533,25 +559,12 @@ static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = {
static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
{
- struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
int ret, i;
- ret = nvme_set_queue_count(&ctrl->ctrl, &opts->nr_io_queues);
- if (ret || !opts->nr_io_queues)
+ ret = nvme_loop_init_io_queues(ctrl);
+ if (ret)
return ret;
- dev_info(ctrl->ctrl.device, "creating %d I/O queues.\n",
- opts->nr_io_queues);
-
- for (i = 1; i <= opts->nr_io_queues; i++) {
- ctrl->queues[i].ctrl = ctrl;
- ret = nvmet_sq_init(&ctrl->queues[i].nvme_sq);
- if (ret)
- goto out_destroy_queues;
-
- ctrl->queue_count++;
- }
-
memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
ctrl->tag_set.ops = &nvme_loop_mq_ops;
ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size;
@@ -575,7 +588,7 @@ static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
goto out_free_tagset;
}
- for (i = 1; i <= opts->nr_io_queues; i++) {
+ for (i = 1; i < ctrl->queue_count; i++) {
ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
if (ret)
goto out_cleanup_connect_q;
@@ -588,8 +601,7 @@ static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
out_free_tagset:
blk_mq_free_tag_set(&ctrl->tag_set);
out_destroy_queues:
- for (i = 1; i < ctrl->queue_count; i++)
- nvmet_sq_destroy(&ctrl->queues[i].nvme_sq);
+ nvme_loop_destroy_io_queues(ctrl);
return ret;
}
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 1370eee..f7ff15f 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -73,6 +73,7 @@ struct nvmet_sq {
u16 qid;
u16 size;
struct completion free_done;
+ struct completion confirm_done;
};
/**
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 9aa1da3..ecc4fe8 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -703,11 +703,6 @@ static void nvmet_rdma_handle_command(struct nvmet_rdma_queue *queue,
{
u16 status;
- cmd->queue = queue;
- cmd->n_rdma = 0;
- cmd->req.port = queue->port;
-
-
ib_dma_sync_single_for_cpu(queue->dev->device,
cmd->cmd->sge[0].addr, cmd->cmd->sge[0].length,
DMA_FROM_DEVICE);
@@ -760,9 +755,12 @@ static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
cmd->queue = queue;
rsp = nvmet_rdma_get_rsp(queue);
+ rsp->queue = queue;
rsp->cmd = cmd;
rsp->flags = 0;
rsp->req.cmd = cmd->nvme_cmd;
+ rsp->req.port = queue->port;
+ rsp->n_rdma = 0;
if (unlikely(queue->state != NVMET_RDMA_Q_LIVE)) {
unsigned long flags;
diff --git a/drivers/parport/share.c b/drivers/parport/share.c
index bc090da..5dc53d4 100644
--- a/drivers/parport/share.c
+++ b/drivers/parport/share.c
@@ -939,8 +939,10 @@ parport_register_dev_model(struct parport *port, const char *name,
* pardevice fields. -arca
*/
port->ops->init_state(par_dev, par_dev->state);
- port->proc_device = par_dev;
- parport_device_proc_register(par_dev);
+ if (!test_and_set_bit(PARPORT_DEVPROC_REGISTERED, &port->devflags)) {
+ port->proc_device = par_dev;
+ parport_device_proc_register(par_dev);
+ }
return par_dev;
diff --git a/drivers/pci/dwc/pci-exynos.c b/drivers/pci/dwc/pci-exynos.c
index 993b650..44f774c 100644
--- a/drivers/pci/dwc/pci-exynos.c
+++ b/drivers/pci/dwc/pci-exynos.c
@@ -132,10 +132,6 @@ static int exynos5440_pcie_get_mem_resources(struct platform_device *pdev,
struct device *dev = pci->dev;
struct resource *res;
- /* If using the PHY framework, doesn't need to get other resource */
- if (ep->using_phy)
- return 0;
-
ep->mem_res = devm_kzalloc(dev, sizeof(*ep->mem_res), GFP_KERNEL);
if (!ep->mem_res)
return -ENOMEM;
@@ -145,6 +141,10 @@ static int exynos5440_pcie_get_mem_resources(struct platform_device *pdev,
if (IS_ERR(ep->mem_res->elbi_base))
return PTR_ERR(ep->mem_res->elbi_base);
+ /* If using the PHY framework, doesn't need to get other resource */
+ if (ep->using_phy)
+ return 0;
+
res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
ep->mem_res->phy_base = devm_ioremap_resource(dev, res);
if (IS_ERR(ep->mem_res->phy_base))
diff --git a/drivers/pci/host/pci-thunder-pem.c b/drivers/pci/host/pci-thunder-pem.c
index 52b5bdc..b89c373 100644
--- a/drivers/pci/host/pci-thunder-pem.c
+++ b/drivers/pci/host/pci-thunder-pem.c
@@ -14,6 +14,7 @@
* Copyright (C) 2015 - 2016 Cavium, Inc.
*/
+#include <linux/bitfield.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/of_address.h>
@@ -334,6 +335,50 @@ static int thunder_pem_init(struct device *dev, struct pci_config_window *cfg,
#if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS)
+#define PEM_RES_BASE 0x87e0c0000000UL
+#define PEM_NODE_MASK GENMASK(45, 44)
+#define PEM_INDX_MASK GENMASK(26, 24)
+#define PEM_MIN_DOM_IN_NODE 4
+#define PEM_MAX_DOM_IN_NODE 10
+
+static void thunder_pem_reserve_range(struct device *dev, int seg,
+ struct resource *r)
+{
+ resource_size_t start = r->start, end = r->end;
+ struct resource *res;
+ const char *regionid;
+
+ regionid = kasprintf(GFP_KERNEL, "PEM RC:%d", seg);
+ if (!regionid)
+ return;
+
+ res = request_mem_region(start, end - start + 1, regionid);
+ if (res)
+ res->flags &= ~IORESOURCE_BUSY;
+ else
+ kfree(regionid);
+
+ dev_info(dev, "%pR %s reserved\n", r,
+ res ? "has been" : "could not be");
+}
+
+static void thunder_pem_legacy_fw(struct acpi_pci_root *root,
+ struct resource *res_pem)
+{
+ int node = acpi_get_node(root->device->handle);
+ int index;
+
+ if (node == NUMA_NO_NODE)
+ node = 0;
+
+ index = root->segment - PEM_MIN_DOM_IN_NODE;
+ index -= node * PEM_MAX_DOM_IN_NODE;
+ res_pem->start = PEM_RES_BASE | FIELD_PREP(PEM_NODE_MASK, node) |
+ FIELD_PREP(PEM_INDX_MASK, index);
+ res_pem->end = res_pem->start + SZ_16M - 1;
+ res_pem->flags = IORESOURCE_MEM;
+}
+
static int thunder_pem_acpi_init(struct pci_config_window *cfg)
{
struct device *dev = cfg->parent;
@@ -346,10 +391,17 @@ static int thunder_pem_acpi_init(struct pci_config_window *cfg)
if (!res_pem)
return -ENOMEM;
- ret = acpi_get_rc_resources(dev, "THRX0002", root->segment, res_pem);
+ ret = acpi_get_rc_resources(dev, "CAVA02B", root->segment, res_pem);
+
+ /*
+ * If we fail to gather resources it means that we run with old
+ * FW where we need to calculate PEM-specific resources manually.
+ */
if (ret) {
- dev_err(dev, "can't get rc base address\n");
- return ret;
+ thunder_pem_legacy_fw(root, res_pem);
+ /* Reserve PEM-specific resources and PCI configuration space */
+ thunder_pem_reserve_range(dev, root->segment, res_pem);
+ thunder_pem_reserve_range(dev, root->segment, &cfg->res);
}
return thunder_pem_init(dev, cfg, res_pem);
diff --git a/drivers/pci/host/pcie-iproc-bcma.c b/drivers/pci/host/pcie-iproc-bcma.c
index bd4c9ec..384c27e 100644
--- a/drivers/pci/host/pcie-iproc-bcma.c
+++ b/drivers/pci/host/pcie-iproc-bcma.c
@@ -44,8 +44,7 @@ static int iproc_pcie_bcma_probe(struct bcma_device *bdev)
{
struct device *dev = &bdev->dev;
struct iproc_pcie *pcie;
- LIST_HEAD(res);
- struct resource res_mem;
+ LIST_HEAD(resources);
int ret;
pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL);
@@ -63,22 +62,23 @@ static int iproc_pcie_bcma_probe(struct bcma_device *bdev)
pcie->base_addr = bdev->addr;
- res_mem.start = bdev->addr_s[0];
- res_mem.end = bdev->addr_s[0] + SZ_128M - 1;
- res_mem.name = "PCIe MEM space";
- res_mem.flags = IORESOURCE_MEM;
- pci_add_resource(&res, &res_mem);
+ pcie->mem.start = bdev->addr_s[0];
+ pcie->mem.end = bdev->addr_s[0] + SZ_128M - 1;
+ pcie->mem.name = "PCIe MEM space";
+ pcie->mem.flags = IORESOURCE_MEM;
+ pci_add_resource(&resources, &pcie->mem);
pcie->map_irq = iproc_pcie_bcma_map_irq;
- ret = iproc_pcie_setup(pcie, &res);
- if (ret)
+ ret = iproc_pcie_setup(pcie, &resources);
+ if (ret) {
dev_err(dev, "PCIe controller setup failed\n");
-
- pci_free_resource_list(&res);
+ pci_free_resource_list(&resources);
+ return ret;
+ }
bcma_set_drvdata(bdev, pcie);
- return ret;
+ return 0;
}
static void iproc_pcie_bcma_remove(struct bcma_device *bdev)
diff --git a/drivers/pci/host/pcie-iproc-platform.c b/drivers/pci/host/pcie-iproc-platform.c
index f4909bb..8c6a327 100644
--- a/drivers/pci/host/pcie-iproc-platform.c
+++ b/drivers/pci/host/pcie-iproc-platform.c
@@ -51,7 +51,7 @@ static int iproc_pcie_pltfm_probe(struct platform_device *pdev)
struct device_node *np = dev->of_node;
struct resource reg;
resource_size_t iobase = 0;
- LIST_HEAD(res);
+ LIST_HEAD(resources);
int ret;
pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL);
@@ -96,10 +96,10 @@ static int iproc_pcie_pltfm_probe(struct platform_device *pdev)
pcie->phy = NULL;
}
- ret = of_pci_get_host_bridge_resources(np, 0, 0xff, &res, &iobase);
+ ret = of_pci_get_host_bridge_resources(np, 0, 0xff, &resources,
+ &iobase);
if (ret) {
- dev_err(dev,
- "unable to get PCI host bridge resources\n");
+ dev_err(dev, "unable to get PCI host bridge resources\n");
return ret;
}
@@ -112,14 +112,15 @@ static int iproc_pcie_pltfm_probe(struct platform_device *pdev)
pcie->map_irq = of_irq_parse_and_map_pci;
}
- ret = iproc_pcie_setup(pcie, &res);
- if (ret)
+ ret = iproc_pcie_setup(pcie, &resources);
+ if (ret) {
dev_err(dev, "PCIe controller setup failed\n");
-
- pci_free_resource_list(&res);
+ pci_free_resource_list(&resources);
+ return ret;
+ }
platform_set_drvdata(pdev, pcie);
- return ret;
+ return 0;
}
static int iproc_pcie_pltfm_remove(struct platform_device *pdev)
diff --git a/drivers/pci/host/pcie-iproc.h b/drivers/pci/host/pcie-iproc.h
index 04fed8e..0bbe2ea 100644
--- a/drivers/pci/host/pcie-iproc.h
+++ b/drivers/pci/host/pcie-iproc.h
@@ -90,6 +90,7 @@ struct iproc_pcie {
#ifdef CONFIG_ARM
struct pci_sys_data sysdata;
#endif
+ struct resource mem;
struct pci_bus *root_bus;
struct phy *phy;
int (*map_irq)(const struct pci_dev *, u8, u8);
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 973472c..1dfa10c 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -478,7 +478,7 @@ static void aspm_calc_l1ss_info(struct pcie_link_state *link,
static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
{
- struct pci_dev *child, *parent = link->pdev;
+ struct pci_dev *child = link->downstream, *parent = link->pdev;
struct pci_bus *linkbus = parent->subordinate;
struct aspm_register_info upreg, dwreg;
@@ -491,9 +491,7 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
/* Get upstream/downstream components' register state */
pcie_get_aspm_reg(parent, &upreg);
- child = pci_function_0(linkbus);
pcie_get_aspm_reg(child, &dwreg);
- link->downstream = child;
/*
* If ASPM not supported, don't mess with the clocks and link,
@@ -800,6 +798,7 @@ static struct pcie_link_state *alloc_pcie_link_state(struct pci_dev *pdev)
INIT_LIST_HEAD(&link->children);
INIT_LIST_HEAD(&link->link);
link->pdev = pdev;
+ link->downstream = pci_function_0(pdev->subordinate);
/*
* Root Ports and PCI/PCI-X to PCIe Bridges are roots of PCIe
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index f754453..6736836 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -2174,6 +2174,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LSI_LOGIC, 0x005d, quirk_blacklist_vpd);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LSI_LOGIC, 0x005f, quirk_blacklist_vpd);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATTANSIC, PCI_ANY_ID,
quirk_blacklist_vpd);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_QLOGIC, 0x2261, quirk_blacklist_vpd);
/*
* For Broadcom 5706, 5708, 5709 rev. A nics, any read beyond the
diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index dc5277a..005cadb 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -449,6 +449,7 @@
config PHY_QCOM_USB_HS
tristate "Qualcomm USB HS PHY module"
depends on USB_ULPI_BUS
+ depends on EXTCON || !EXTCON # if EXTCON=m, this cannot be built-in
select GENERIC_PHY
help
Support for the USB high-speed ULPI compliant phy on Qualcomm
@@ -510,12 +511,4 @@
and GXBB SoCs.
If unsure, say N.
-config PHY_NSP_USB3
- tristate "Broadcom NorthStar plus USB3 PHY driver"
- depends on OF && (ARCH_BCM_NSP || COMPILE_TEST)
- select GENERIC_PHY
- default ARCH_BCM_NSP
- help
- Enable this to support the Broadcom Northstar plus USB3 PHY.
- If unsure, say N.
endmenu
diff --git a/drivers/phy/Makefile b/drivers/phy/Makefile
index e7b0feb..dd8f3b5 100644
--- a/drivers/phy/Makefile
+++ b/drivers/phy/Makefile
@@ -62,4 +62,3 @@
obj-$(CONFIG_ARCH_TEGRA) += tegra/
obj-$(CONFIG_PHY_NS2_PCIE) += phy-bcm-ns2-pcie.o
obj-$(CONFIG_PHY_MESON8B_USB2) += phy-meson8b-usb2.o
-obj-$(CONFIG_PHY_NSP_USB3) += phy-bcm-nsp-usb3.o
diff --git a/drivers/phy/phy-bcm-nsp-usb3.c b/drivers/phy/phy-bcm-nsp-usb3.c
deleted file mode 100644
index 49024ea..0000000
--- a/drivers/phy/phy-bcm-nsp-usb3.c
+++ /dev/null
@@ -1,177 +0,0 @@
-/*
- * Copyright (C) 2016 Broadcom
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- */
-
-#include <linux/delay.h>
-#include <linux/io.h>
-#include <linux/kernel.h>
-#include <linux/mfd/syscon.h>
-#include <linux/mdio.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/phy/phy.h>
-#include <linux/regmap.h>
-
-#define NSP_USB3_RST_CTRL_OFFSET 0x3f8
-
-/* mdio reg access */
-#define NSP_USB3_PHY_BASE_ADDR_REG 0x1f
-
-#define NSP_USB3_PHY_PLL30_BLOCK 0x8000
-#define NSP_USB3_PLL_CONTROL 0x01
-#define NSP_USB3_PLLA_CONTROL0 0x0a
-#define NSP_USB3_PLLA_CONTROL1 0x0b
-
-#define NSP_USB3_PHY_TX_PMD_BLOCK 0x8040
-#define NSP_USB3_TX_PMD_CONTROL1 0x01
-
-#define NSP_USB3_PHY_PIPE_BLOCK 0x8060
-#define NSP_USB3_LFPS_CMP 0x02
-#define NSP_USB3_LFPS_DEGLITCH 0x03
-
-struct nsp_usb3_phy {
- struct regmap *usb3_ctrl;
- struct phy *phy;
- struct mdio_device *mdiodev;
-};
-
-static int nsp_usb3_phy_init(struct phy *phy)
-{
- struct nsp_usb3_phy *iphy = phy_get_drvdata(phy);
- struct mii_bus *bus = iphy->mdiodev->bus;
- int addr = iphy->mdiodev->addr;
- u32 data;
- int rc;
-
- rc = regmap_read(iphy->usb3_ctrl, 0, &data);
- if (rc)
- return rc;
- data |= 1;
- rc = regmap_write(iphy->usb3_ctrl, 0, data);
- if (rc)
- return rc;
-
- rc = regmap_write(iphy->usb3_ctrl, NSP_USB3_RST_CTRL_OFFSET, 1);
- if (rc)
- return rc;
-
- rc = mdiobus_write(bus, addr, NSP_USB3_PHY_BASE_ADDR_REG,
- NSP_USB3_PHY_PLL30_BLOCK);
- if (rc)
- return rc;
-
- rc = mdiobus_write(bus, addr, NSP_USB3_PLL_CONTROL, 0x1000);
- if (rc)
- return rc;
-
- rc = mdiobus_write(bus, addr, NSP_USB3_PLLA_CONTROL0, 0x6400);
- if (rc)
- return rc;
-
- rc = mdiobus_write(bus, addr, NSP_USB3_PLLA_CONTROL1, 0xc000);
- if (rc)
- return rc;
-
- rc = mdiobus_write(bus, addr, NSP_USB3_PLLA_CONTROL1, 0x8000);
- if (rc)
- return rc;
-
- rc = regmap_write(iphy->usb3_ctrl, NSP_USB3_RST_CTRL_OFFSET, 0);
- if (rc)
- return rc;
-
- rc = mdiobus_write(bus, addr, NSP_USB3_PLL_CONTROL, 0x9000);
- if (rc)
- return rc;
-
- rc = mdiobus_write(bus, addr, NSP_USB3_PHY_BASE_ADDR_REG,
- NSP_USB3_PHY_PIPE_BLOCK);
- if (rc)
- return rc;
-
- rc = mdiobus_write(bus, addr, NSP_USB3_LFPS_CMP, 0xf30d);
- if (rc)
- return rc;
-
- rc = mdiobus_write(bus, addr, NSP_USB3_LFPS_DEGLITCH, 0x6302);
- if (rc)
- return rc;
-
- rc = mdiobus_write(bus, addr, NSP_USB3_PHY_BASE_ADDR_REG,
- NSP_USB3_PHY_TX_PMD_BLOCK);
- if (rc)
- return rc;
-
- rc = mdiobus_write(bus, addr, NSP_USB3_TX_PMD_CONTROL1, 0x1003);
-
- return rc;
-}
-
-static struct phy_ops nsp_usb3_phy_ops = {
- .init = nsp_usb3_phy_init,
- .owner = THIS_MODULE,
-};
-
-static int nsp_usb3_phy_probe(struct mdio_device *mdiodev)
-{
- struct device *dev = &mdiodev->dev;
- struct phy_provider *provider;
- struct nsp_usb3_phy *iphy;
-
- iphy = devm_kzalloc(dev, sizeof(*iphy), GFP_KERNEL);
- if (!iphy)
- return -ENOMEM;
- iphy->mdiodev = mdiodev;
-
- iphy->usb3_ctrl = syscon_regmap_lookup_by_phandle(dev->of_node,
- "usb3-ctrl-syscon");
- if (IS_ERR(iphy->usb3_ctrl))
- return PTR_ERR(iphy->usb3_ctrl);
-
- iphy->phy = devm_phy_create(dev, dev->of_node, &nsp_usb3_phy_ops);
- if (IS_ERR(iphy->phy)) {
- dev_err(dev, "failed to create PHY\n");
- return PTR_ERR(iphy->phy);
- }
-
- phy_set_drvdata(iphy->phy, iphy);
-
- provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate);
- if (IS_ERR(provider)) {
- dev_err(dev, "could not register PHY provider\n");
- return PTR_ERR(provider);
- }
-
- return 0;
-}
-
-static const struct of_device_id nsp_usb3_phy_of_match[] = {
- {.compatible = "brcm,nsp-usb3-phy",},
- { /* sentinel */ }
-};
-
-static struct mdio_driver nsp_usb3_phy_driver = {
- .mdiodrv = {
- .driver = {
- .name = "nsp-usb3-phy",
- .of_match_table = nsp_usb3_phy_of_match,
- },
- },
- .probe = nsp_usb3_phy_probe,
-};
-
-mdio_module_driver(nsp_usb3_phy_driver);
-
-MODULE_DESCRIPTION("Broadcom NSP USB3 PHY driver");
-MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR("Yendapally Reddy Dhananjaya Reddy <yendapally.reddy@broadcom.com");
diff --git a/drivers/phy/phy-exynos-pcie.c b/drivers/phy/phy-exynos-pcie.c
index 4f60b83..60baf25 100644
--- a/drivers/phy/phy-exynos-pcie.c
+++ b/drivers/phy/phy-exynos-pcie.c
@@ -254,8 +254,8 @@ static int exynos_pcie_phy_probe(struct platform_device *pdev)
res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
exynos_phy->blk_base = devm_ioremap_resource(dev, res);
- if (IS_ERR(exynos_phy->phy_base))
- return PTR_ERR(exynos_phy->phy_base);
+ if (IS_ERR(exynos_phy->blk_base))
+ return PTR_ERR(exynos_phy->blk_base);
exynos_phy->drv_data = drv_data;
diff --git a/drivers/pinctrl/meson/pinctrl-meson-gxbb.c b/drivers/pinctrl/meson/pinctrl-meson-gxbb.c
index 7671424..31a3a98 100644
--- a/drivers/pinctrl/meson/pinctrl-meson-gxbb.c
+++ b/drivers/pinctrl/meson/pinctrl-meson-gxbb.c
@@ -667,11 +667,11 @@ static const char * const uart_ao_b_groups[] = {
};
static const char * const i2c_ao_groups[] = {
- "i2c_sdk_ao", "i2c_sda_ao",
+ "i2c_sck_ao", "i2c_sda_ao",
};
static const char * const i2c_slave_ao_groups[] = {
- "i2c_slave_sdk_ao", "i2c_slave_sda_ao",
+ "i2c_slave_sck_ao", "i2c_slave_sda_ao",
};
static const char * const remote_input_ao_groups[] = {
diff --git a/drivers/pinctrl/pinctrl-st.c b/drivers/pinctrl/pinctrl-st.c
index 676efcc..3ae8066 100644
--- a/drivers/pinctrl/pinctrl-st.c
+++ b/drivers/pinctrl/pinctrl-st.c
@@ -1285,6 +1285,22 @@ static void st_gpio_irq_unmask(struct irq_data *d)
writel(BIT(d->hwirq), bank->base + REG_PIO_SET_PMASK);
}
+static int st_gpio_irq_request_resources(struct irq_data *d)
+{
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+
+ st_gpio_direction_input(gc, d->hwirq);
+
+ return gpiochip_lock_as_irq(gc, d->hwirq);
+}
+
+static void st_gpio_irq_release_resources(struct irq_data *d)
+{
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+
+ gpiochip_unlock_as_irq(gc, d->hwirq);
+}
+
static int st_gpio_irq_set_type(struct irq_data *d, unsigned type)
{
struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
@@ -1438,12 +1454,14 @@ static struct gpio_chip st_gpio_template = {
};
static struct irq_chip st_gpio_irqchip = {
- .name = "GPIO",
- .irq_disable = st_gpio_irq_mask,
- .irq_mask = st_gpio_irq_mask,
- .irq_unmask = st_gpio_irq_unmask,
- .irq_set_type = st_gpio_irq_set_type,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+ .name = "GPIO",
+ .irq_request_resources = st_gpio_irq_request_resources,
+ .irq_release_resources = st_gpio_irq_release_resources,
+ .irq_disable = st_gpio_irq_mask,
+ .irq_mask = st_gpio_irq_mask,
+ .irq_unmask = st_gpio_irq_unmask,
+ .irq_set_type = st_gpio_irq_set_type,
+ .flags = IRQCHIP_SKIP_SET_WAKE,
};
static int st_gpiolib_register_bank(struct st_pinctrl *info,
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq4019.c b/drivers/pinctrl/qcom/pinctrl-ipq4019.c
index b68ae42..743d1f4 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq4019.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq4019.c
@@ -405,6 +405,36 @@ static const struct msm_pingroup ipq4019_groups[] = {
PINGROUP(67, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
PINGROUP(68, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
PINGROUP(69, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(70, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(71, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(72, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(73, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(74, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(75, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(76, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(77, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(78, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(79, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(80, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(81, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(82, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(83, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(84, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(85, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(86, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(87, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(88, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(89, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(90, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(91, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(92, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(93, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(94, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(95, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(96, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(97, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(98, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+ PINGROUP(99, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
};
static const struct msm_pinctrl_soc_data ipq4019_pinctrl = {
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index f8e9e1c..273badd 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -422,6 +422,20 @@ static int msm_gpio_direction_output(struct gpio_chip *chip, unsigned offset, in
return 0;
}
+static int msm_gpio_get_direction(struct gpio_chip *chip, unsigned int offset)
+{
+ struct msm_pinctrl *pctrl = gpiochip_get_data(chip);
+ const struct msm_pingroup *g;
+ u32 val;
+
+ g = &pctrl->soc->groups[offset];
+
+ val = readl(pctrl->regs + g->ctl_reg);
+
+ /* 0 = output, 1 = input */
+ return val & BIT(g->oe_bit) ? 0 : 1;
+}
+
static int msm_gpio_get(struct gpio_chip *chip, unsigned offset)
{
const struct msm_pingroup *g;
@@ -510,6 +524,7 @@ static void msm_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip)
static struct gpio_chip msm_gpio_template = {
.direction_input = msm_gpio_direction_input,
.direction_output = msm_gpio_direction_output,
+ .get_direction = msm_gpio_get_direction,
.get = msm_gpio_get,
.set = msm_gpio_set,
.request = gpiochip_generic_request,
@@ -594,10 +609,6 @@ static void msm_gpio_irq_unmask(struct irq_data *d)
raw_spin_lock_irqsave(&pctrl->lock, flags);
- val = readl(pctrl->regs + g->intr_status_reg);
- val &= ~BIT(g->intr_status_bit);
- writel(val, pctrl->regs + g->intr_status_reg);
-
val = readl(pctrl->regs + g->intr_cfg_reg);
val |= BIT(g->intr_enable_bit);
writel(val, pctrl->regs + g->intr_cfg_reg);
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c
index f9ddba7..d7aa22c 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.c
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.c
@@ -988,9 +988,16 @@ samsung_pinctrl_get_soc_data(struct samsung_pinctrl_drv_data *d,
for (i = 0; i < ctrl->nr_ext_resources + 1; i++) {
res = platform_get_resource(pdev, IORESOURCE_MEM, i);
- virt_base[i] = devm_ioremap_resource(&pdev->dev, res);
- if (IS_ERR(virt_base[i]))
- return ERR_CAST(virt_base[i]);
+ if (!res) {
+ dev_err(&pdev->dev, "failed to get mem%d resource\n", i);
+ return ERR_PTR(-EINVAL);
+ }
+ virt_base[i] = devm_ioremap(&pdev->dev, res->start,
+ resource_size(res));
+ if (!virt_base[i]) {
+ dev_err(&pdev->dev, "failed to ioremap %pR\n", res);
+ return ERR_PTR(-EIO);
+ }
}
bank = d->pin_banks;
diff --git a/drivers/pinctrl/ti/Kconfig b/drivers/pinctrl/ti/Kconfig
index 815a886..5420770 100644
--- a/drivers/pinctrl/ti/Kconfig
+++ b/drivers/pinctrl/ti/Kconfig
@@ -1,6 +1,6 @@
config PINCTRL_TI_IODELAY
tristate "TI IODelay Module pinconf driver"
- depends on OF
+ depends on OF && (SOC_DRA7XX || COMPILE_TEST)
select GENERIC_PINCTRL_GROUPS
select GENERIC_PINMUX_FUNCTIONS
select GENERIC_PINCONF
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c
index 77a0236..83f8864 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c
@@ -390,22 +390,22 @@ static const struct pinctrl_pin_desc uniphier_ld11_pins[] = {
UNIPHIER_PINCTRL_PIN(140, "AO1D0", 140,
140, UNIPHIER_PIN_DRV_1BIT,
140, UNIPHIER_PIN_PULL_DOWN),
- UNIPHIER_PINCTRL_PIN(141, "TCON0", 141,
+ UNIPHIER_PINCTRL_PIN(141, "AO1D1", 141,
141, UNIPHIER_PIN_DRV_1BIT,
141, UNIPHIER_PIN_PULL_DOWN),
- UNIPHIER_PINCTRL_PIN(142, "TCON1", 142,
+ UNIPHIER_PINCTRL_PIN(142, "AO1D2", 142,
142, UNIPHIER_PIN_DRV_1BIT,
142, UNIPHIER_PIN_PULL_DOWN),
- UNIPHIER_PINCTRL_PIN(143, "TCON2", 143,
+ UNIPHIER_PINCTRL_PIN(143, "XIRQ9", 143,
143, UNIPHIER_PIN_DRV_1BIT,
143, UNIPHIER_PIN_PULL_DOWN),
- UNIPHIER_PINCTRL_PIN(144, "TCON3", 144,
+ UNIPHIER_PINCTRL_PIN(144, "XIRQ10", 144,
144, UNIPHIER_PIN_DRV_1BIT,
144, UNIPHIER_PIN_PULL_DOWN),
- UNIPHIER_PINCTRL_PIN(145, "TCON4", 145,
+ UNIPHIER_PINCTRL_PIN(145, "XIRQ11", 145,
145, UNIPHIER_PIN_DRV_1BIT,
145, UNIPHIER_PIN_PULL_DOWN),
- UNIPHIER_PINCTRL_PIN(146, "TCON5", 146,
+ UNIPHIER_PINCTRL_PIN(146, "XIRQ13", 146,
146, UNIPHIER_PIN_DRV_1BIT,
146, UNIPHIER_PIN_PULL_DOWN),
UNIPHIER_PINCTRL_PIN(147, "PWMA", 147,
diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index 5be4783..dea98ff 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -103,15 +103,6 @@ static struct quirk_entry quirk_asus_x200ca = {
.wapf = 2,
};
-static struct quirk_entry quirk_no_rfkill = {
- .no_rfkill = true,
-};
-
-static struct quirk_entry quirk_no_rfkill_wapf4 = {
- .wapf = 4,
- .no_rfkill = true,
-};
-
static struct quirk_entry quirk_asus_ux303ub = {
.wmi_backlight_native = true,
};
@@ -194,7 +185,7 @@ static const struct dmi_system_id asus_quirks[] = {
DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
DMI_MATCH(DMI_PRODUCT_NAME, "X456UA"),
},
- .driver_data = &quirk_no_rfkill_wapf4,
+ .driver_data = &quirk_asus_wapf4,
},
{
.callback = dmi_matched,
@@ -203,7 +194,7 @@ static const struct dmi_system_id asus_quirks[] = {
DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
DMI_MATCH(DMI_PRODUCT_NAME, "X456UF"),
},
- .driver_data = &quirk_no_rfkill_wapf4,
+ .driver_data = &quirk_asus_wapf4,
},
{
.callback = dmi_matched,
@@ -369,42 +360,6 @@ static const struct dmi_system_id asus_quirks[] = {
},
{
.callback = dmi_matched,
- .ident = "ASUSTeK COMPUTER INC. X555UB",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
- DMI_MATCH(DMI_PRODUCT_NAME, "X555UB"),
- },
- .driver_data = &quirk_no_rfkill,
- },
- {
- .callback = dmi_matched,
- .ident = "ASUSTeK COMPUTER INC. N552VW",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
- DMI_MATCH(DMI_PRODUCT_NAME, "N552VW"),
- },
- .driver_data = &quirk_no_rfkill,
- },
- {
- .callback = dmi_matched,
- .ident = "ASUSTeK COMPUTER INC. U303LB",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
- DMI_MATCH(DMI_PRODUCT_NAME, "U303LB"),
- },
- .driver_data = &quirk_no_rfkill,
- },
- {
- .callback = dmi_matched,
- .ident = "ASUSTeK COMPUTER INC. Z550MA",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
- DMI_MATCH(DMI_PRODUCT_NAME, "Z550MA"),
- },
- .driver_data = &quirk_no_rfkill,
- },
- {
- .callback = dmi_matched,
.ident = "ASUSTeK COMPUTER INC. UX303UB",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 43cb680..8fe5890 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -159,6 +159,8 @@ MODULE_LICENSE("GPL");
#define USB_INTEL_XUSB2PR 0xD0
#define PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI 0x9c31
+static const char * const ashs_ids[] = { "ATK4001", "ATK4002", NULL };
+
struct bios_args {
u32 arg0;
u32 arg1;
@@ -2051,6 +2053,16 @@ static int asus_wmi_fan_init(struct asus_wmi *asus)
return 0;
}
+static bool ashs_present(void)
+{
+ int i = 0;
+ while (ashs_ids[i]) {
+ if (acpi_dev_found(ashs_ids[i++]))
+ return true;
+ }
+ return false;
+}
+
/*
* WMI Driver
*/
@@ -2095,7 +2107,11 @@ static int asus_wmi_add(struct platform_device *pdev)
if (err)
goto fail_leds;
- if (!asus->driver->quirks->no_rfkill) {
+ asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_WLAN, &result);
+ if (result & (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT))
+ asus->driver->wlan_ctrl_by_user = 1;
+
+ if (!(asus->driver->wlan_ctrl_by_user && ashs_present())) {
err = asus_wmi_rfkill_init(asus);
if (err)
goto fail_rfkill;
@@ -2134,10 +2150,6 @@ static int asus_wmi_add(struct platform_device *pdev)
if (err)
goto fail_debugfs;
- asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_WLAN, &result);
- if (result & (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT))
- asus->driver->wlan_ctrl_by_user = 1;
-
return 0;
fail_debugfs:
diff --git a/drivers/platform/x86/asus-wmi.h b/drivers/platform/x86/asus-wmi.h
index fdff626..c9589d9 100644
--- a/drivers/platform/x86/asus-wmi.h
+++ b/drivers/platform/x86/asus-wmi.h
@@ -39,7 +39,6 @@ struct key_entry;
struct asus_wmi;
struct quirk_entry {
- bool no_rfkill;
bool hotplug_wireless;
bool scalar_panel_brightness;
bool store_backlight_power;
diff --git a/drivers/platform/x86/fujitsu-laptop.c b/drivers/platform/x86/fujitsu-laptop.c
index 2b218b1..e12cc35 100644
--- a/drivers/platform/x86/fujitsu-laptop.c
+++ b/drivers/platform/x86/fujitsu-laptop.c
@@ -78,18 +78,18 @@
#define FUJITSU_LCD_N_LEVELS 8
-#define ACPI_FUJITSU_CLASS "fujitsu"
-#define ACPI_FUJITSU_HID "FUJ02B1"
-#define ACPI_FUJITSU_DRIVER_NAME "Fujitsu laptop FUJ02B1 ACPI brightness driver"
-#define ACPI_FUJITSU_DEVICE_NAME "Fujitsu FUJ02B1"
-#define ACPI_FUJITSU_HOTKEY_HID "FUJ02E3"
-#define ACPI_FUJITSU_HOTKEY_DRIVER_NAME "Fujitsu laptop FUJ02E3 ACPI hotkeys driver"
-#define ACPI_FUJITSU_HOTKEY_DEVICE_NAME "Fujitsu FUJ02E3"
+#define ACPI_FUJITSU_CLASS "fujitsu"
+#define ACPI_FUJITSU_BL_HID "FUJ02B1"
+#define ACPI_FUJITSU_BL_DRIVER_NAME "Fujitsu laptop FUJ02B1 ACPI brightness driver"
+#define ACPI_FUJITSU_BL_DEVICE_NAME "Fujitsu FUJ02B1"
+#define ACPI_FUJITSU_LAPTOP_HID "FUJ02E3"
+#define ACPI_FUJITSU_LAPTOP_DRIVER_NAME "Fujitsu laptop FUJ02E3 ACPI hotkeys driver"
+#define ACPI_FUJITSU_LAPTOP_DEVICE_NAME "Fujitsu FUJ02E3"
#define ACPI_FUJITSU_NOTIFY_CODE1 0x80
/* FUNC interface - command values */
-#define FUNC_RFKILL 0x1000
+#define FUNC_FLAGS 0x1000
#define FUNC_LEDS 0x1001
#define FUNC_BUTTONS 0x1002
#define FUNC_BACKLIGHT 0x1004
@@ -97,6 +97,11 @@
/* FUNC interface - responses */
#define UNSUPPORTED_CMD 0x80000000
+/* FUNC interface - status flags */
+#define FLAG_RFKILL 0x020
+#define FLAG_LID 0x100
+#define FLAG_DOCK 0x200
+
#if IS_ENABLED(CONFIG_LEDS_CLASS)
/* FUNC interface - LED control */
#define FUNC_LED_OFF 0x1
@@ -136,7 +141,7 @@
#endif
/* Device controlling the backlight and associated keys */
-struct fujitsu_t {
+struct fujitsu_bl {
acpi_handle acpi_handle;
struct acpi_device *dev;
struct input_dev *input;
@@ -150,12 +155,12 @@ struct fujitsu_t {
unsigned int brightness_level;
};
-static struct fujitsu_t *fujitsu;
+static struct fujitsu_bl *fujitsu_bl;
static int use_alt_lcd_levels = -1;
static int disable_brightness_adjust = -1;
-/* Device used to access other hotkeys on the laptop */
-struct fujitsu_hotkey_t {
+/* Device used to access hotkeys and other features on the laptop */
+struct fujitsu_laptop {
acpi_handle acpi_handle;
struct acpi_device *dev;
struct input_dev *input;
@@ -163,17 +168,15 @@ struct fujitsu_hotkey_t {
struct platform_device *pf_device;
struct kfifo fifo;
spinlock_t fifo_lock;
- int rfkill_supported;
- int rfkill_state;
+ int flags_supported;
+ int flags_state;
int logolamp_registered;
int kblamps_registered;
int radio_led_registered;
int eco_led_registered;
};
-static struct fujitsu_hotkey_t *fujitsu_hotkey;
-
-static void acpi_fujitsu_hotkey_notify(struct acpi_device *device, u32 event);
+static struct fujitsu_laptop *fujitsu_laptop;
#if IS_ENABLED(CONFIG_LEDS_CLASS)
static enum led_brightness logolamp_get(struct led_classdev *cdev);
@@ -222,8 +225,6 @@ static struct led_classdev eco_led = {
static u32 dbg_level = 0x03;
#endif
-static void acpi_fujitsu_notify(struct acpi_device *device, u32 event);
-
/* Fujitsu ACPI interface function */
static int call_fext_func(int cmd, int arg0, int arg1, int arg2)
@@ -239,7 +240,7 @@ static int call_fext_func(int cmd, int arg0, int arg1, int arg2)
unsigned long long value;
acpi_handle handle = NULL;
- status = acpi_get_handle(fujitsu_hotkey->acpi_handle, "FUNC", &handle);
+ status = acpi_get_handle(fujitsu_laptop->acpi_handle, "FUNC", &handle);
if (ACPI_FAILURE(status)) {
vdbg_printk(FUJLAPTOP_DBG_ERROR,
"FUNC interface is not present\n");
@@ -300,9 +301,9 @@ static int radio_led_set(struct led_classdev *cdev,
enum led_brightness brightness)
{
if (brightness >= LED_FULL)
- return call_fext_func(FUNC_RFKILL, 0x5, RADIO_LED_ON, RADIO_LED_ON);
+ return call_fext_func(FUNC_FLAGS, 0x5, RADIO_LED_ON, RADIO_LED_ON);
else
- return call_fext_func(FUNC_RFKILL, 0x5, RADIO_LED_ON, 0x0);
+ return call_fext_func(FUNC_FLAGS, 0x5, RADIO_LED_ON, 0x0);
}
static int eco_led_set(struct led_classdev *cdev,
@@ -346,7 +347,7 @@ static enum led_brightness radio_led_get(struct led_classdev *cdev)
{
enum led_brightness brightness = LED_OFF;
- if (call_fext_func(FUNC_RFKILL, 0x4, 0x0, 0x0) & RADIO_LED_ON)
+ if (call_fext_func(FUNC_FLAGS, 0x4, 0x0, 0x0) & RADIO_LED_ON)
brightness = LED_FULL;
return brightness;
@@ -373,10 +374,10 @@ static int set_lcd_level(int level)
vdbg_printk(FUJLAPTOP_DBG_TRACE, "set lcd level via SBLL [%d]\n",
level);
- if (level < 0 || level >= fujitsu->max_brightness)
+ if (level < 0 || level >= fujitsu_bl->max_brightness)
return -EINVAL;
- status = acpi_get_handle(fujitsu->acpi_handle, "SBLL", &handle);
+ status = acpi_get_handle(fujitsu_bl->acpi_handle, "SBLL", &handle);
if (ACPI_FAILURE(status)) {
vdbg_printk(FUJLAPTOP_DBG_ERROR, "SBLL not present\n");
return -ENODEV;
@@ -398,10 +399,10 @@ static int set_lcd_level_alt(int level)
vdbg_printk(FUJLAPTOP_DBG_TRACE, "set lcd level via SBL2 [%d]\n",
level);
- if (level < 0 || level >= fujitsu->max_brightness)
+ if (level < 0 || level >= fujitsu_bl->max_brightness)
return -EINVAL;
- status = acpi_get_handle(fujitsu->acpi_handle, "SBL2", &handle);
+ status = acpi_get_handle(fujitsu_bl->acpi_handle, "SBL2", &handle);
if (ACPI_FAILURE(status)) {
vdbg_printk(FUJLAPTOP_DBG_ERROR, "SBL2 not present\n");
return -ENODEV;
@@ -421,19 +422,19 @@ static int get_lcd_level(void)
vdbg_printk(FUJLAPTOP_DBG_TRACE, "get lcd level via GBLL\n");
- status =
- acpi_evaluate_integer(fujitsu->acpi_handle, "GBLL", NULL, &state);
+ status = acpi_evaluate_integer(fujitsu_bl->acpi_handle, "GBLL", NULL,
+ &state);
if (ACPI_FAILURE(status))
return 0;
- fujitsu->brightness_level = state & 0x0fffffff;
+ fujitsu_bl->brightness_level = state & 0x0fffffff;
if (state & 0x80000000)
- fujitsu->brightness_changed = 1;
+ fujitsu_bl->brightness_changed = 1;
else
- fujitsu->brightness_changed = 0;
+ fujitsu_bl->brightness_changed = 0;
- return fujitsu->brightness_level;
+ return fujitsu_bl->brightness_level;
}
static int get_max_brightness(void)
@@ -443,14 +444,14 @@ static int get_max_brightness(void)
vdbg_printk(FUJLAPTOP_DBG_TRACE, "get max lcd level via RBLL\n");
- status =
- acpi_evaluate_integer(fujitsu->acpi_handle, "RBLL", NULL, &state);
+ status = acpi_evaluate_integer(fujitsu_bl->acpi_handle, "RBLL", NULL,
+ &state);
if (ACPI_FAILURE(status))
return -1;
- fujitsu->max_brightness = state;
+ fujitsu_bl->max_brightness = state;
- return fujitsu->max_brightness;
+ return fujitsu_bl->max_brightness;
}
/* Backlight device stuff */
@@ -483,7 +484,7 @@ static int bl_update_status(struct backlight_device *b)
return ret;
}
-static const struct backlight_ops fujitsubl_ops = {
+static const struct backlight_ops fujitsu_bl_ops = {
.get_brightness = bl_get_brightness,
.update_status = bl_update_status,
};
@@ -511,7 +512,7 @@ show_brightness_changed(struct device *dev,
int ret;
- ret = fujitsu->brightness_changed;
+ ret = fujitsu_bl->brightness_changed;
if (ret < 0)
return ret;
@@ -539,7 +540,7 @@ static ssize_t store_lcd_level(struct device *dev,
int level, ret;
if (sscanf(buf, "%i", &level) != 1
- || (level < 0 || level >= fujitsu->max_brightness))
+ || (level < 0 || level >= fujitsu_bl->max_brightness))
return -EINVAL;
if (use_alt_lcd_levels)
@@ -567,9 +568,9 @@ static ssize_t
show_lid_state(struct device *dev,
struct device_attribute *attr, char *buf)
{
- if (!(fujitsu_hotkey->rfkill_supported & 0x100))
+ if (!(fujitsu_laptop->flags_supported & FLAG_LID))
return sprintf(buf, "unknown\n");
- if (fujitsu_hotkey->rfkill_state & 0x100)
+ if (fujitsu_laptop->flags_state & FLAG_LID)
return sprintf(buf, "open\n");
else
return sprintf(buf, "closed\n");
@@ -579,9 +580,9 @@ static ssize_t
show_dock_state(struct device *dev,
struct device_attribute *attr, char *buf)
{
- if (!(fujitsu_hotkey->rfkill_supported & 0x200))
+ if (!(fujitsu_laptop->flags_supported & FLAG_DOCK))
return sprintf(buf, "unknown\n");
- if (fujitsu_hotkey->rfkill_state & 0x200)
+ if (fujitsu_laptop->flags_state & FLAG_DOCK)
return sprintf(buf, "docked\n");
else
return sprintf(buf, "undocked\n");
@@ -591,9 +592,9 @@ static ssize_t
show_radios_state(struct device *dev,
struct device_attribute *attr, char *buf)
{
- if (!(fujitsu_hotkey->rfkill_supported & 0x20))
+ if (!(fujitsu_laptop->flags_supported & FLAG_RFKILL))
return sprintf(buf, "unknown\n");
- if (fujitsu_hotkey->rfkill_state & 0x20)
+ if (fujitsu_laptop->flags_state & FLAG_RFKILL)
return sprintf(buf, "on\n");
else
return sprintf(buf, "killed\n");
@@ -607,7 +608,7 @@ static DEVICE_ATTR(lid, 0444, show_lid_state, ignore_store);
static DEVICE_ATTR(dock, 0444, show_dock_state, ignore_store);
static DEVICE_ATTR(radios, 0444, show_radios_state, ignore_store);
-static struct attribute *fujitsupf_attributes[] = {
+static struct attribute *fujitsu_pf_attributes[] = {
&dev_attr_brightness_changed.attr,
&dev_attr_max_brightness.attr,
&dev_attr_lcd_level.attr,
@@ -617,11 +618,11 @@ static struct attribute *fujitsupf_attributes[] = {
NULL
};
-static struct attribute_group fujitsupf_attribute_group = {
- .attrs = fujitsupf_attributes
+static struct attribute_group fujitsu_pf_attribute_group = {
+ .attrs = fujitsu_pf_attributes
};
-static struct platform_driver fujitsupf_driver = {
+static struct platform_driver fujitsu_pf_driver = {
.driver = {
.name = "fujitsu-laptop",
}
@@ -630,39 +631,30 @@ static struct platform_driver fujitsupf_driver = {
static void __init dmi_check_cb_common(const struct dmi_system_id *id)
{
pr_info("Identified laptop model '%s'\n", id->ident);
- if (use_alt_lcd_levels == -1) {
- if (acpi_has_method(NULL,
- "\\_SB.PCI0.LPCB.FJEX.SBL2"))
- use_alt_lcd_levels = 1;
- else
- use_alt_lcd_levels = 0;
- vdbg_printk(FUJLAPTOP_DBG_TRACE, "auto-detected usealt as "
- "%i\n", use_alt_lcd_levels);
- }
}
static int __init dmi_check_cb_s6410(const struct dmi_system_id *id)
{
dmi_check_cb_common(id);
- fujitsu->keycode1 = KEY_SCREENLOCK; /* "Lock" */
- fujitsu->keycode2 = KEY_HELP; /* "Mobility Center" */
+ fujitsu_bl->keycode1 = KEY_SCREENLOCK; /* "Lock" */
+ fujitsu_bl->keycode2 = KEY_HELP; /* "Mobility Center" */
return 1;
}
static int __init dmi_check_cb_s6420(const struct dmi_system_id *id)
{
dmi_check_cb_common(id);
- fujitsu->keycode1 = KEY_SCREENLOCK; /* "Lock" */
- fujitsu->keycode2 = KEY_HELP; /* "Mobility Center" */
+ fujitsu_bl->keycode1 = KEY_SCREENLOCK; /* "Lock" */
+ fujitsu_bl->keycode2 = KEY_HELP; /* "Mobility Center" */
return 1;
}
static int __init dmi_check_cb_p8010(const struct dmi_system_id *id)
{
dmi_check_cb_common(id);
- fujitsu->keycode1 = KEY_HELP; /* "Support" */
- fujitsu->keycode3 = KEY_SWITCHVIDEOMODE; /* "Presentation" */
- fujitsu->keycode4 = KEY_WWW; /* "Internet" */
+ fujitsu_bl->keycode1 = KEY_HELP; /* "Support" */
+ fujitsu_bl->keycode3 = KEY_SWITCHVIDEOMODE; /* "Presentation" */
+ fujitsu_bl->keycode4 = KEY_WWW; /* "Internet" */
return 1;
}
@@ -693,7 +685,7 @@ static const struct dmi_system_id fujitsu_dmi_table[] __initconst = {
/* ACPI device for LCD brightness control */
-static int acpi_fujitsu_add(struct acpi_device *device)
+static int acpi_fujitsu_bl_add(struct acpi_device *device)
{
int state = 0;
struct input_dev *input;
@@ -702,22 +694,22 @@ static int acpi_fujitsu_add(struct acpi_device *device)
if (!device)
return -EINVAL;
- fujitsu->acpi_handle = device->handle;
- sprintf(acpi_device_name(device), "%s", ACPI_FUJITSU_DEVICE_NAME);
+ fujitsu_bl->acpi_handle = device->handle;
+ sprintf(acpi_device_name(device), "%s", ACPI_FUJITSU_BL_DEVICE_NAME);
sprintf(acpi_device_class(device), "%s", ACPI_FUJITSU_CLASS);
- device->driver_data = fujitsu;
+ device->driver_data = fujitsu_bl;
- fujitsu->input = input = input_allocate_device();
+ fujitsu_bl->input = input = input_allocate_device();
if (!input) {
error = -ENOMEM;
goto err_stop;
}
- snprintf(fujitsu->phys, sizeof(fujitsu->phys),
+ snprintf(fujitsu_bl->phys, sizeof(fujitsu_bl->phys),
"%s/video/input0", acpi_device_hid(device));
input->name = acpi_device_name(device);
- input->phys = fujitsu->phys;
+ input->phys = fujitsu_bl->phys;
input->id.bustype = BUS_HOST;
input->id.product = 0x06;
input->dev.parent = &device->dev;
@@ -730,7 +722,7 @@ static int acpi_fujitsu_add(struct acpi_device *device)
if (error)
goto err_free_input_dev;
- error = acpi_bus_update_power(fujitsu->acpi_handle, &state);
+ error = acpi_bus_update_power(fujitsu_bl->acpi_handle, &state);
if (error) {
pr_err("Error reading power state\n");
goto err_unregister_input_dev;
@@ -740,7 +732,7 @@ static int acpi_fujitsu_add(struct acpi_device *device)
acpi_device_name(device), acpi_device_bid(device),
!device->power.state ? "on" : "off");
- fujitsu->dev = device;
+ fujitsu_bl->dev = device;
if (acpi_has_method(device->handle, METHOD_NAME__INI)) {
vdbg_printk(FUJLAPTOP_DBG_INFO, "Invoking _INI\n");
@@ -750,6 +742,15 @@ static int acpi_fujitsu_add(struct acpi_device *device)
pr_err("_INI Method failed\n");
}
+ if (use_alt_lcd_levels == -1) {
+ if (acpi_has_method(NULL, "\\_SB.PCI0.LPCB.FJEX.SBL2"))
+ use_alt_lcd_levels = 1;
+ else
+ use_alt_lcd_levels = 0;
+ vdbg_printk(FUJLAPTOP_DBG_TRACE, "auto-detected usealt as %i\n",
+ use_alt_lcd_levels);
+ }
+
/* do config (detect defaults) */
use_alt_lcd_levels = use_alt_lcd_levels == 1 ? 1 : 0;
disable_brightness_adjust = disable_brightness_adjust == 1 ? 1 : 0;
@@ -758,7 +759,7 @@ static int acpi_fujitsu_add(struct acpi_device *device)
use_alt_lcd_levels, disable_brightness_adjust);
if (get_max_brightness() <= 0)
- fujitsu->max_brightness = FUJITSU_LCD_N_LEVELS;
+ fujitsu_bl->max_brightness = FUJITSU_LCD_N_LEVELS;
get_lcd_level();
return 0;
@@ -772,38 +773,38 @@ static int acpi_fujitsu_add(struct acpi_device *device)
return error;
}
-static int acpi_fujitsu_remove(struct acpi_device *device)
+static int acpi_fujitsu_bl_remove(struct acpi_device *device)
{
- struct fujitsu_t *fujitsu = acpi_driver_data(device);
- struct input_dev *input = fujitsu->input;
+ struct fujitsu_bl *fujitsu_bl = acpi_driver_data(device);
+ struct input_dev *input = fujitsu_bl->input;
input_unregister_device(input);
- fujitsu->acpi_handle = NULL;
+ fujitsu_bl->acpi_handle = NULL;
return 0;
}
/* Brightness notify */
-static void acpi_fujitsu_notify(struct acpi_device *device, u32 event)
+static void acpi_fujitsu_bl_notify(struct acpi_device *device, u32 event)
{
struct input_dev *input;
int keycode;
int oldb, newb;
- input = fujitsu->input;
+ input = fujitsu_bl->input;
switch (event) {
case ACPI_FUJITSU_NOTIFY_CODE1:
keycode = 0;
- oldb = fujitsu->brightness_level;
+ oldb = fujitsu_bl->brightness_level;
get_lcd_level();
- newb = fujitsu->brightness_level;
+ newb = fujitsu_bl->brightness_level;
vdbg_printk(FUJLAPTOP_DBG_TRACE,
"brightness button event [%i -> %i (%i)]\n",
- oldb, newb, fujitsu->brightness_changed);
+ oldb, newb, fujitsu_bl->brightness_changed);
if (oldb < newb) {
if (disable_brightness_adjust != 1) {
@@ -840,7 +841,7 @@ static void acpi_fujitsu_notify(struct acpi_device *device, u32 event)
/* ACPI device for hotkey handling */
-static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
+static int acpi_fujitsu_laptop_add(struct acpi_device *device)
{
int result = 0;
int state = 0;
@@ -851,42 +852,42 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
if (!device)
return -EINVAL;
- fujitsu_hotkey->acpi_handle = device->handle;
+ fujitsu_laptop->acpi_handle = device->handle;
sprintf(acpi_device_name(device), "%s",
- ACPI_FUJITSU_HOTKEY_DEVICE_NAME);
+ ACPI_FUJITSU_LAPTOP_DEVICE_NAME);
sprintf(acpi_device_class(device), "%s", ACPI_FUJITSU_CLASS);
- device->driver_data = fujitsu_hotkey;
+ device->driver_data = fujitsu_laptop;
/* kfifo */
- spin_lock_init(&fujitsu_hotkey->fifo_lock);
- error = kfifo_alloc(&fujitsu_hotkey->fifo, RINGBUFFERSIZE * sizeof(int),
+ spin_lock_init(&fujitsu_laptop->fifo_lock);
+ error = kfifo_alloc(&fujitsu_laptop->fifo, RINGBUFFERSIZE * sizeof(int),
GFP_KERNEL);
if (error) {
pr_err("kfifo_alloc failed\n");
goto err_stop;
}
- fujitsu_hotkey->input = input = input_allocate_device();
+ fujitsu_laptop->input = input = input_allocate_device();
if (!input) {
error = -ENOMEM;
goto err_free_fifo;
}
- snprintf(fujitsu_hotkey->phys, sizeof(fujitsu_hotkey->phys),
+ snprintf(fujitsu_laptop->phys, sizeof(fujitsu_laptop->phys),
"%s/video/input0", acpi_device_hid(device));
input->name = acpi_device_name(device);
- input->phys = fujitsu_hotkey->phys;
+ input->phys = fujitsu_laptop->phys;
input->id.bustype = BUS_HOST;
input->id.product = 0x06;
input->dev.parent = &device->dev;
set_bit(EV_KEY, input->evbit);
- set_bit(fujitsu->keycode1, input->keybit);
- set_bit(fujitsu->keycode2, input->keybit);
- set_bit(fujitsu->keycode3, input->keybit);
- set_bit(fujitsu->keycode4, input->keybit);
- set_bit(fujitsu->keycode5, input->keybit);
+ set_bit(fujitsu_bl->keycode1, input->keybit);
+ set_bit(fujitsu_bl->keycode2, input->keybit);
+ set_bit(fujitsu_bl->keycode3, input->keybit);
+ set_bit(fujitsu_bl->keycode4, input->keybit);
+ set_bit(fujitsu_bl->keycode5, input->keybit);
set_bit(KEY_TOUCHPAD_TOGGLE, input->keybit);
set_bit(KEY_UNKNOWN, input->keybit);
@@ -894,7 +895,7 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
if (error)
goto err_free_input_dev;
- error = acpi_bus_update_power(fujitsu_hotkey->acpi_handle, &state);
+ error = acpi_bus_update_power(fujitsu_laptop->acpi_handle, &state);
if (error) {
pr_err("Error reading power state\n");
goto err_unregister_input_dev;
@@ -904,7 +905,7 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
acpi_device_name(device), acpi_device_bid(device),
!device->power.state ? "on" : "off");
- fujitsu_hotkey->dev = device;
+ fujitsu_laptop->dev = device;
if (acpi_has_method(device->handle, METHOD_NAME__INI)) {
vdbg_printk(FUJLAPTOP_DBG_INFO, "Invoking _INI\n");
@@ -920,27 +921,27 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
; /* No action, result is discarded */
vdbg_printk(FUJLAPTOP_DBG_INFO, "Discarded %i ringbuffer entries\n", i);
- fujitsu_hotkey->rfkill_supported =
- call_fext_func(FUNC_RFKILL, 0x0, 0x0, 0x0);
+ fujitsu_laptop->flags_supported =
+ call_fext_func(FUNC_FLAGS, 0x0, 0x0, 0x0);
/* Make sure our bitmask of supported functions is cleared if the
RFKILL function block is not implemented, like on the S7020. */
- if (fujitsu_hotkey->rfkill_supported == UNSUPPORTED_CMD)
- fujitsu_hotkey->rfkill_supported = 0;
+ if (fujitsu_laptop->flags_supported == UNSUPPORTED_CMD)
+ fujitsu_laptop->flags_supported = 0;
- if (fujitsu_hotkey->rfkill_supported)
- fujitsu_hotkey->rfkill_state =
- call_fext_func(FUNC_RFKILL, 0x4, 0x0, 0x0);
+ if (fujitsu_laptop->flags_supported)
+ fujitsu_laptop->flags_state =
+ call_fext_func(FUNC_FLAGS, 0x4, 0x0, 0x0);
/* Suspect this is a keymap of the application panel, print it */
pr_info("BTNI: [0x%x]\n", call_fext_func(FUNC_BUTTONS, 0x0, 0x0, 0x0));
#if IS_ENABLED(CONFIG_LEDS_CLASS)
if (call_fext_func(FUNC_LEDS, 0x0, 0x0, 0x0) & LOGOLAMP_POWERON) {
- result = led_classdev_register(&fujitsu->pf_device->dev,
+ result = led_classdev_register(&fujitsu_bl->pf_device->dev,
&logolamp_led);
if (result == 0) {
- fujitsu_hotkey->logolamp_registered = 1;
+ fujitsu_laptop->logolamp_registered = 1;
} else {
pr_err("Could not register LED handler for logo lamp, error %i\n",
result);
@@ -949,10 +950,10 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
if ((call_fext_func(FUNC_LEDS, 0x0, 0x0, 0x0) & KEYBOARD_LAMPS) &&
(call_fext_func(FUNC_BUTTONS, 0x0, 0x0, 0x0) == 0x0)) {
- result = led_classdev_register(&fujitsu->pf_device->dev,
+ result = led_classdev_register(&fujitsu_bl->pf_device->dev,
&kblamps_led);
if (result == 0) {
- fujitsu_hotkey->kblamps_registered = 1;
+ fujitsu_laptop->kblamps_registered = 1;
} else {
pr_err("Could not register LED handler for keyboard lamps, error %i\n",
result);
@@ -966,10 +967,10 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
* that an RF LED is present.
*/
if (call_fext_func(FUNC_BUTTONS, 0x0, 0x0, 0x0) & BIT(24)) {
- result = led_classdev_register(&fujitsu->pf_device->dev,
+ result = led_classdev_register(&fujitsu_bl->pf_device->dev,
&radio_led);
if (result == 0) {
- fujitsu_hotkey->radio_led_registered = 1;
+ fujitsu_laptop->radio_led_registered = 1;
} else {
pr_err("Could not register LED handler for radio LED, error %i\n",
result);
@@ -983,10 +984,10 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
*/
if ((call_fext_func(FUNC_LEDS, 0x0, 0x0, 0x0) & BIT(14)) &&
(call_fext_func(FUNC_LEDS, 0x2, ECO_LED, 0x0) != UNSUPPORTED_CMD)) {
- result = led_classdev_register(&fujitsu->pf_device->dev,
+ result = led_classdev_register(&fujitsu_bl->pf_device->dev,
&eco_led);
if (result == 0) {
- fujitsu_hotkey->eco_led_registered = 1;
+ fujitsu_laptop->eco_led_registered = 1;
} else {
pr_err("Could not register LED handler for eco LED, error %i\n",
result);
@@ -1002,47 +1003,47 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
err_free_input_dev:
input_free_device(input);
err_free_fifo:
- kfifo_free(&fujitsu_hotkey->fifo);
+ kfifo_free(&fujitsu_laptop->fifo);
err_stop:
return error;
}
-static int acpi_fujitsu_hotkey_remove(struct acpi_device *device)
+static int acpi_fujitsu_laptop_remove(struct acpi_device *device)
{
- struct fujitsu_hotkey_t *fujitsu_hotkey = acpi_driver_data(device);
- struct input_dev *input = fujitsu_hotkey->input;
+ struct fujitsu_laptop *fujitsu_laptop = acpi_driver_data(device);
+ struct input_dev *input = fujitsu_laptop->input;
#if IS_ENABLED(CONFIG_LEDS_CLASS)
- if (fujitsu_hotkey->logolamp_registered)
+ if (fujitsu_laptop->logolamp_registered)
led_classdev_unregister(&logolamp_led);
- if (fujitsu_hotkey->kblamps_registered)
+ if (fujitsu_laptop->kblamps_registered)
led_classdev_unregister(&kblamps_led);
- if (fujitsu_hotkey->radio_led_registered)
+ if (fujitsu_laptop->radio_led_registered)
led_classdev_unregister(&radio_led);
- if (fujitsu_hotkey->eco_led_registered)
+ if (fujitsu_laptop->eco_led_registered)
led_classdev_unregister(&eco_led);
#endif
input_unregister_device(input);
- kfifo_free(&fujitsu_hotkey->fifo);
+ kfifo_free(&fujitsu_laptop->fifo);
- fujitsu_hotkey->acpi_handle = NULL;
+ fujitsu_laptop->acpi_handle = NULL;
return 0;
}
-static void acpi_fujitsu_hotkey_press(int keycode)
+static void acpi_fujitsu_laptop_press(int keycode)
{
- struct input_dev *input = fujitsu_hotkey->input;
+ struct input_dev *input = fujitsu_laptop->input;
int status;
- status = kfifo_in_locked(&fujitsu_hotkey->fifo,
+ status = kfifo_in_locked(&fujitsu_laptop->fifo,
(unsigned char *)&keycode, sizeof(keycode),
- &fujitsu_hotkey->fifo_lock);
+ &fujitsu_laptop->fifo_lock);
if (status != sizeof(keycode)) {
vdbg_printk(FUJLAPTOP_DBG_WARN,
"Could not push keycode [0x%x]\n", keycode);
@@ -1054,16 +1055,16 @@ static void acpi_fujitsu_hotkey_press(int keycode)
"Push keycode into ringbuffer [%d]\n", keycode);
}
-static void acpi_fujitsu_hotkey_release(void)
+static void acpi_fujitsu_laptop_release(void)
{
- struct input_dev *input = fujitsu_hotkey->input;
+ struct input_dev *input = fujitsu_laptop->input;
int keycode, status;
while (true) {
- status = kfifo_out_locked(&fujitsu_hotkey->fifo,
+ status = kfifo_out_locked(&fujitsu_laptop->fifo,
(unsigned char *)&keycode,
sizeof(keycode),
- &fujitsu_hotkey->fifo_lock);
+ &fujitsu_laptop->fifo_lock);
if (status != sizeof(keycode))
return;
input_report_key(input, keycode, 0);
@@ -1073,14 +1074,14 @@ static void acpi_fujitsu_hotkey_release(void)
}
}
-static void acpi_fujitsu_hotkey_notify(struct acpi_device *device, u32 event)
+static void acpi_fujitsu_laptop_notify(struct acpi_device *device, u32 event)
{
struct input_dev *input;
int keycode;
unsigned int irb = 1;
int i;
- input = fujitsu_hotkey->input;
+ input = fujitsu_laptop->input;
if (event != ACPI_FUJITSU_NOTIFY_CODE1) {
keycode = KEY_UNKNOWN;
@@ -1093,9 +1094,9 @@ static void acpi_fujitsu_hotkey_notify(struct acpi_device *device, u32 event)
return;
}
- if (fujitsu_hotkey->rfkill_supported)
- fujitsu_hotkey->rfkill_state =
- call_fext_func(FUNC_RFKILL, 0x4, 0x0, 0x0);
+ if (fujitsu_laptop->flags_supported)
+ fujitsu_laptop->flags_state =
+ call_fext_func(FUNC_FLAGS, 0x4, 0x0, 0x0);
i = 0;
while ((irb =
@@ -1103,19 +1104,19 @@ static void acpi_fujitsu_hotkey_notify(struct acpi_device *device, u32 event)
&& (i++) < MAX_HOTKEY_RINGBUFFER_SIZE) {
switch (irb & 0x4ff) {
case KEY1_CODE:
- keycode = fujitsu->keycode1;
+ keycode = fujitsu_bl->keycode1;
break;
case KEY2_CODE:
- keycode = fujitsu->keycode2;
+ keycode = fujitsu_bl->keycode2;
break;
case KEY3_CODE:
- keycode = fujitsu->keycode3;
+ keycode = fujitsu_bl->keycode3;
break;
case KEY4_CODE:
- keycode = fujitsu->keycode4;
+ keycode = fujitsu_bl->keycode4;
break;
case KEY5_CODE:
- keycode = fujitsu->keycode5;
+ keycode = fujitsu_bl->keycode5;
break;
case 0:
keycode = 0;
@@ -1128,17 +1129,17 @@ static void acpi_fujitsu_hotkey_notify(struct acpi_device *device, u32 event)
}
if (keycode > 0)
- acpi_fujitsu_hotkey_press(keycode);
+ acpi_fujitsu_laptop_press(keycode);
else if (keycode == 0)
- acpi_fujitsu_hotkey_release();
+ acpi_fujitsu_laptop_release();
}
/* On some models (first seen on the Skylake-based Lifebook
* E736/E746/E756), the touchpad toggle hotkey (Fn+F4) is
- * handled in software; its state is queried using FUNC_RFKILL
+ * handled in software; its state is queried using FUNC_FLAGS
*/
- if ((fujitsu_hotkey->rfkill_supported & BIT(26)) &&
- (call_fext_func(FUNC_RFKILL, 0x1, 0x0, 0x0) & BIT(26))) {
+ if ((fujitsu_laptop->flags_supported & BIT(26)) &&
+ (call_fext_func(FUNC_FLAGS, 0x1, 0x0, 0x0) & BIT(26))) {
keycode = KEY_TOUCHPAD_TOGGLE;
input_report_key(input, keycode, 1);
input_sync(input);
@@ -1150,83 +1151,81 @@ static void acpi_fujitsu_hotkey_notify(struct acpi_device *device, u32 event)
/* Initialization */
-static const struct acpi_device_id fujitsu_device_ids[] = {
- {ACPI_FUJITSU_HID, 0},
+static const struct acpi_device_id fujitsu_bl_device_ids[] = {
+ {ACPI_FUJITSU_BL_HID, 0},
{"", 0},
};
-static struct acpi_driver acpi_fujitsu_driver = {
- .name = ACPI_FUJITSU_DRIVER_NAME,
+static struct acpi_driver acpi_fujitsu_bl_driver = {
+ .name = ACPI_FUJITSU_BL_DRIVER_NAME,
.class = ACPI_FUJITSU_CLASS,
- .ids = fujitsu_device_ids,
+ .ids = fujitsu_bl_device_ids,
.ops = {
- .add = acpi_fujitsu_add,
- .remove = acpi_fujitsu_remove,
- .notify = acpi_fujitsu_notify,
+ .add = acpi_fujitsu_bl_add,
+ .remove = acpi_fujitsu_bl_remove,
+ .notify = acpi_fujitsu_bl_notify,
},
};
-static const struct acpi_device_id fujitsu_hotkey_device_ids[] = {
- {ACPI_FUJITSU_HOTKEY_HID, 0},
+static const struct acpi_device_id fujitsu_laptop_device_ids[] = {
+ {ACPI_FUJITSU_LAPTOP_HID, 0},
{"", 0},
};
-static struct acpi_driver acpi_fujitsu_hotkey_driver = {
- .name = ACPI_FUJITSU_HOTKEY_DRIVER_NAME,
+static struct acpi_driver acpi_fujitsu_laptop_driver = {
+ .name = ACPI_FUJITSU_LAPTOP_DRIVER_NAME,
.class = ACPI_FUJITSU_CLASS,
- .ids = fujitsu_hotkey_device_ids,
+ .ids = fujitsu_laptop_device_ids,
.ops = {
- .add = acpi_fujitsu_hotkey_add,
- .remove = acpi_fujitsu_hotkey_remove,
- .notify = acpi_fujitsu_hotkey_notify,
+ .add = acpi_fujitsu_laptop_add,
+ .remove = acpi_fujitsu_laptop_remove,
+ .notify = acpi_fujitsu_laptop_notify,
},
};
static const struct acpi_device_id fujitsu_ids[] __used = {
- {ACPI_FUJITSU_HID, 0},
- {ACPI_FUJITSU_HOTKEY_HID, 0},
+ {ACPI_FUJITSU_BL_HID, 0},
+ {ACPI_FUJITSU_LAPTOP_HID, 0},
{"", 0}
};
MODULE_DEVICE_TABLE(acpi, fujitsu_ids);
static int __init fujitsu_init(void)
{
- int ret, result, max_brightness;
+ int ret, max_brightness;
if (acpi_disabled)
return -ENODEV;
- fujitsu = kzalloc(sizeof(struct fujitsu_t), GFP_KERNEL);
- if (!fujitsu)
+ fujitsu_bl = kzalloc(sizeof(struct fujitsu_bl), GFP_KERNEL);
+ if (!fujitsu_bl)
return -ENOMEM;
- fujitsu->keycode1 = KEY_PROG1;
- fujitsu->keycode2 = KEY_PROG2;
- fujitsu->keycode3 = KEY_PROG3;
- fujitsu->keycode4 = KEY_PROG4;
- fujitsu->keycode5 = KEY_RFKILL;
+ fujitsu_bl->keycode1 = KEY_PROG1;
+ fujitsu_bl->keycode2 = KEY_PROG2;
+ fujitsu_bl->keycode3 = KEY_PROG3;
+ fujitsu_bl->keycode4 = KEY_PROG4;
+ fujitsu_bl->keycode5 = KEY_RFKILL;
dmi_check_system(fujitsu_dmi_table);
- result = acpi_bus_register_driver(&acpi_fujitsu_driver);
- if (result < 0) {
- ret = -ENODEV;
+ ret = acpi_bus_register_driver(&acpi_fujitsu_bl_driver);
+ if (ret)
goto fail_acpi;
- }
/* Register platform stuff */
- fujitsu->pf_device = platform_device_alloc("fujitsu-laptop", -1);
- if (!fujitsu->pf_device) {
+ fujitsu_bl->pf_device = platform_device_alloc("fujitsu-laptop", -1);
+ if (!fujitsu_bl->pf_device) {
ret = -ENOMEM;
goto fail_platform_driver;
}
- ret = platform_device_add(fujitsu->pf_device);
+ ret = platform_device_add(fujitsu_bl->pf_device);
if (ret)
goto fail_platform_device1;
ret =
- sysfs_create_group(&fujitsu->pf_device->dev.kobj,
- &fujitsupf_attribute_group);
+ sysfs_create_group(&fujitsu_bl->pf_device->dev.kobj,
+ &fujitsu_pf_attribute_group);
if (ret)
goto fail_platform_device2;
@@ -1236,90 +1235,88 @@ static int __init fujitsu_init(void)
struct backlight_properties props;
memset(&props, 0, sizeof(struct backlight_properties));
- max_brightness = fujitsu->max_brightness;
+ max_brightness = fujitsu_bl->max_brightness;
props.type = BACKLIGHT_PLATFORM;
props.max_brightness = max_brightness - 1;
- fujitsu->bl_device = backlight_device_register("fujitsu-laptop",
- NULL, NULL,
- &fujitsubl_ops,
- &props);
- if (IS_ERR(fujitsu->bl_device)) {
- ret = PTR_ERR(fujitsu->bl_device);
- fujitsu->bl_device = NULL;
+ fujitsu_bl->bl_device = backlight_device_register("fujitsu-laptop",
+ NULL, NULL,
+ &fujitsu_bl_ops,
+ &props);
+ if (IS_ERR(fujitsu_bl->bl_device)) {
+ ret = PTR_ERR(fujitsu_bl->bl_device);
+ fujitsu_bl->bl_device = NULL;
goto fail_sysfs_group;
}
- fujitsu->bl_device->props.brightness = fujitsu->brightness_level;
+ fujitsu_bl->bl_device->props.brightness = fujitsu_bl->brightness_level;
}
- ret = platform_driver_register(&fujitsupf_driver);
+ ret = platform_driver_register(&fujitsu_pf_driver);
if (ret)
goto fail_backlight;
- /* Register hotkey driver */
+ /* Register laptop driver */
- fujitsu_hotkey = kzalloc(sizeof(struct fujitsu_hotkey_t), GFP_KERNEL);
- if (!fujitsu_hotkey) {
+ fujitsu_laptop = kzalloc(sizeof(struct fujitsu_laptop), GFP_KERNEL);
+ if (!fujitsu_laptop) {
ret = -ENOMEM;
- goto fail_hotkey;
+ goto fail_laptop;
}
- result = acpi_bus_register_driver(&acpi_fujitsu_hotkey_driver);
- if (result < 0) {
- ret = -ENODEV;
- goto fail_hotkey1;
- }
+ ret = acpi_bus_register_driver(&acpi_fujitsu_laptop_driver);
+ if (ret)
+ goto fail_laptop1;
/* Sync backlight power status (needs FUJ02E3 device, hence deferred) */
if (acpi_video_get_backlight_type() == acpi_backlight_vendor) {
if (call_fext_func(FUNC_BACKLIGHT, 0x2, 0x4, 0x0) == 3)
- fujitsu->bl_device->props.power = FB_BLANK_POWERDOWN;
+ fujitsu_bl->bl_device->props.power = FB_BLANK_POWERDOWN;
else
- fujitsu->bl_device->props.power = FB_BLANK_UNBLANK;
+ fujitsu_bl->bl_device->props.power = FB_BLANK_UNBLANK;
}
pr_info("driver " FUJITSU_DRIVER_VERSION " successfully loaded\n");
return 0;
-fail_hotkey1:
- kfree(fujitsu_hotkey);
-fail_hotkey:
- platform_driver_unregister(&fujitsupf_driver);
+fail_laptop1:
+ kfree(fujitsu_laptop);
+fail_laptop:
+ platform_driver_unregister(&fujitsu_pf_driver);
fail_backlight:
- backlight_device_unregister(fujitsu->bl_device);
+ backlight_device_unregister(fujitsu_bl->bl_device);
fail_sysfs_group:
- sysfs_remove_group(&fujitsu->pf_device->dev.kobj,
- &fujitsupf_attribute_group);
+ sysfs_remove_group(&fujitsu_bl->pf_device->dev.kobj,
+ &fujitsu_pf_attribute_group);
fail_platform_device2:
- platform_device_del(fujitsu->pf_device);
+ platform_device_del(fujitsu_bl->pf_device);
fail_platform_device1:
- platform_device_put(fujitsu->pf_device);
+ platform_device_put(fujitsu_bl->pf_device);
fail_platform_driver:
- acpi_bus_unregister_driver(&acpi_fujitsu_driver);
+ acpi_bus_unregister_driver(&acpi_fujitsu_bl_driver);
fail_acpi:
- kfree(fujitsu);
+ kfree(fujitsu_bl);
return ret;
}
static void __exit fujitsu_cleanup(void)
{
- acpi_bus_unregister_driver(&acpi_fujitsu_hotkey_driver);
+ acpi_bus_unregister_driver(&acpi_fujitsu_laptop_driver);
- kfree(fujitsu_hotkey);
+ kfree(fujitsu_laptop);
- platform_driver_unregister(&fujitsupf_driver);
+ platform_driver_unregister(&fujitsu_pf_driver);
- backlight_device_unregister(fujitsu->bl_device);
+ backlight_device_unregister(fujitsu_bl->bl_device);
- sysfs_remove_group(&fujitsu->pf_device->dev.kobj,
- &fujitsupf_attribute_group);
+ sysfs_remove_group(&fujitsu_bl->pf_device->dev.kobj,
+ &fujitsu_pf_attribute_group);
- platform_device_unregister(fujitsu->pf_device);
+ platform_device_unregister(fujitsu_bl->pf_device);
- acpi_bus_unregister_driver(&acpi_fujitsu_driver);
+ acpi_bus_unregister_driver(&acpi_fujitsu_bl_driver);
- kfree(fujitsu);
+ kfree(fujitsu_bl);
pr_info("driver unloaded\n");
}
@@ -1341,7 +1338,3 @@ MODULE_AUTHOR("Jonathan Woithe, Peter Gruber, Tony Vroon");
MODULE_DESCRIPTION("Fujitsu laptop extras support");
MODULE_VERSION(FUJITSU_DRIVER_VERSION);
MODULE_LICENSE("GPL");
-
-MODULE_ALIAS("dmi:*:svnFUJITSUSIEMENS:*:pvr:rvnFUJITSU:rnFJNB1D3:*:cvrS6410:*");
-MODULE_ALIAS("dmi:*:svnFUJITSUSIEMENS:*:pvr:rvnFUJITSU:rnFJNB1E6:*:cvrS6420:*");
-MODULE_ALIAS("dmi:*:svnFUJITSU:*:pvr:rvnFUJITSU:rnFJNB19C:*:cvrS7020:*");
diff --git a/drivers/ptp/ptp_kvm.c b/drivers/ptp/ptp_kvm.c
index 09b4df7..bb86569 100644
--- a/drivers/ptp/ptp_kvm.c
+++ b/drivers/ptp/ptp_kvm.c
@@ -193,10 +193,7 @@ static int __init ptp_kvm_init(void)
kvm_ptp_clock.ptp_clock = ptp_clock_register(&kvm_ptp_clock.caps, NULL);
- if (IS_ERR(kvm_ptp_clock.ptp_clock))
- return PTR_ERR(kvm_ptp_clock.ptp_clock);
-
- return 0;
+ return PTR_ERR_OR_ZERO(kvm_ptp_clock.ptp_clock);
}
module_init(ptp_kvm_init);
diff --git a/drivers/rapidio/devices/tsi721.c b/drivers/rapidio/devices/tsi721.c
index 9d19b9a..315a4be 100644
--- a/drivers/rapidio/devices/tsi721.c
+++ b/drivers/rapidio/devices/tsi721.c
@@ -37,8 +37,8 @@
#include "tsi721.h"
#ifdef DEBUG
-u32 dbg_level;
-module_param(dbg_level, uint, S_IWUSR | S_IRUGO);
+u32 tsi_dbg_level;
+module_param_named(dbg_level, tsi_dbg_level, uint, S_IWUSR | S_IRUGO);
MODULE_PARM_DESC(dbg_level, "Debugging output level (default 0 = none)");
#endif
diff --git a/drivers/rapidio/devices/tsi721.h b/drivers/rapidio/devices/tsi721.h
index 5941437..957eadc 100644
--- a/drivers/rapidio/devices/tsi721.h
+++ b/drivers/rapidio/devices/tsi721.h
@@ -40,11 +40,11 @@ enum {
};
#ifdef DEBUG
-extern u32 dbg_level;
+extern u32 tsi_dbg_level;
#define tsi_debug(level, dev, fmt, arg...) \
do { \
- if (DBG_##level & dbg_level) \
+ if (DBG_##level & tsi_dbg_level) \
dev_dbg(dev, "%s: " fmt "\n", __func__, ##arg); \
} while (0)
#else
diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig
index 65f86bc..faad69a 100644
--- a/drivers/remoteproc/Kconfig
+++ b/drivers/remoteproc/Kconfig
@@ -76,7 +76,7 @@
depends on OF && ARCH_QCOM
depends on REMOTEPROC
depends on QCOM_SMEM
- depends on QCOM_SMD || (COMPILE_TEST && QCOM_SMD=n)
+ depends on RPMSG_QCOM_SMD || (COMPILE_TEST && RPMSG_QCOM_SMD=n)
select MFD_SYSCON
select QCOM_MDT_LOADER
select QCOM_RPROC_COMMON
@@ -93,7 +93,7 @@
depends on OF && ARCH_QCOM
depends on QCOM_SMEM
depends on REMOTEPROC
- depends on QCOM_SMD || (COMPILE_TEST && QCOM_SMD=n)
+ depends on RPMSG_QCOM_SMD || (COMPILE_TEST && RPMSG_QCOM_SMD=n)
select MFD_SYSCON
select QCOM_RPROC_COMMON
select QCOM_SCM
@@ -104,7 +104,7 @@
config QCOM_WCNSS_PIL
tristate "Qualcomm WCNSS Peripheral Image Loader"
depends on OF && ARCH_QCOM
- depends on QCOM_SMD || (COMPILE_TEST && QCOM_SMD=n)
+ depends on RPMSG_QCOM_SMD || (COMPILE_TEST && RPMSG_QCOM_SMD=n)
depends on QCOM_SMEM
depends on REMOTEPROC
select QCOM_MDT_LOADER
diff --git a/drivers/rpmsg/Kconfig b/drivers/rpmsg/Kconfig
index f12ac0b..edc008f 100644
--- a/drivers/rpmsg/Kconfig
+++ b/drivers/rpmsg/Kconfig
@@ -16,7 +16,6 @@
config RPMSG_QCOM_SMD
tristate "Qualcomm Shared Memory Driver (SMD)"
depends on QCOM_SMEM
- depends on QCOM_SMD=n
select RPMSG
help
Say y here to enable support for the Qualcomm Shared Memory Driver
diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c
index 40f1136..058db72 100644
--- a/drivers/s390/crypto/pkey_api.c
+++ b/drivers/s390/crypto/pkey_api.c
@@ -572,6 +572,12 @@ int pkey_sec2protkey(u16 cardnr, u16 domain,
rc = -EIO;
goto out;
}
+ if (prepcblk->ccp_rscode != 0) {
+ DEBUG_WARN(
+ "pkey_sec2protkey unwrap secure key warning, card response %d/%d\n",
+ (int) prepcblk->ccp_rtcode,
+ (int) prepcblk->ccp_rscode);
+ }
/* process response cprb param block */
prepcblk->rpl_parmb = ((u8 *) prepcblk) + sizeof(struct CPRBX);
@@ -761,9 +767,10 @@ static int query_crypto_facility(u16 cardnr, u16 domain,
}
/*
- * Fetch just the mkvp value via query_crypto_facility from adapter.
+ * Fetch the current and old mkvp values via
+ * query_crypto_facility from adapter.
*/
-static int fetch_mkvp(u16 cardnr, u16 domain, u64 *mkvp)
+static int fetch_mkvp(u16 cardnr, u16 domain, u64 mkvp[2])
{
int rc, found = 0;
size_t rlen, vlen;
@@ -779,9 +786,10 @@ static int fetch_mkvp(u16 cardnr, u16 domain, u64 *mkvp)
rc = query_crypto_facility(cardnr, domain, "STATICSA",
rarray, &rlen, varray, &vlen);
if (rc == 0 && rlen > 8*8 && vlen > 184+8) {
- if (rarray[64] == '2') {
+ if (rarray[8*8] == '2') {
/* current master key state is valid */
- *mkvp = *((u64 *)(varray + 184));
+ mkvp[0] = *((u64 *)(varray + 184));
+ mkvp[1] = *((u64 *)(varray + 172));
found = 1;
}
}
@@ -796,14 +804,14 @@ struct mkvp_info {
struct list_head list;
u16 cardnr;
u16 domain;
- u64 mkvp;
+ u64 mkvp[2];
};
/* a list with mkvp_info entries */
static LIST_HEAD(mkvp_list);
static DEFINE_SPINLOCK(mkvp_list_lock);
-static int mkvp_cache_fetch(u16 cardnr, u16 domain, u64 *mkvp)
+static int mkvp_cache_fetch(u16 cardnr, u16 domain, u64 mkvp[2])
{
int rc = -ENOENT;
struct mkvp_info *ptr;
@@ -812,7 +820,7 @@ static int mkvp_cache_fetch(u16 cardnr, u16 domain, u64 *mkvp)
list_for_each_entry(ptr, &mkvp_list, list) {
if (ptr->cardnr == cardnr &&
ptr->domain == domain) {
- *mkvp = ptr->mkvp;
+ memcpy(mkvp, ptr->mkvp, 2 * sizeof(u64));
rc = 0;
break;
}
@@ -822,7 +830,7 @@ static int mkvp_cache_fetch(u16 cardnr, u16 domain, u64 *mkvp)
return rc;
}
-static void mkvp_cache_update(u16 cardnr, u16 domain, u64 mkvp)
+static void mkvp_cache_update(u16 cardnr, u16 domain, u64 mkvp[2])
{
int found = 0;
struct mkvp_info *ptr;
@@ -831,7 +839,7 @@ static void mkvp_cache_update(u16 cardnr, u16 domain, u64 mkvp)
list_for_each_entry(ptr, &mkvp_list, list) {
if (ptr->cardnr == cardnr &&
ptr->domain == domain) {
- ptr->mkvp = mkvp;
+ memcpy(ptr->mkvp, mkvp, 2 * sizeof(u64));
found = 1;
break;
}
@@ -844,7 +852,7 @@ static void mkvp_cache_update(u16 cardnr, u16 domain, u64 mkvp)
}
ptr->cardnr = cardnr;
ptr->domain = domain;
- ptr->mkvp = mkvp;
+ memcpy(ptr->mkvp, mkvp, 2 * sizeof(u64));
list_add(&ptr->list, &mkvp_list);
}
spin_unlock_bh(&mkvp_list_lock);
@@ -888,8 +896,8 @@ int pkey_findcard(const struct pkey_seckey *seckey,
struct secaeskeytoken *t = (struct secaeskeytoken *) seckey;
struct zcrypt_device_matrix *device_matrix;
u16 card, dom;
- u64 mkvp;
- int i, rc;
+ u64 mkvp[2];
+ int i, rc, oi = -1;
/* mkvp must not be zero */
if (t->mkvp == 0)
@@ -910,14 +918,14 @@ int pkey_findcard(const struct pkey_seckey *seckey,
device_matrix->device[i].functions & 0x04) {
/* an enabled CCA Coprocessor card */
/* try cached mkvp */
- if (mkvp_cache_fetch(card, dom, &mkvp) == 0 &&
- t->mkvp == mkvp) {
+ if (mkvp_cache_fetch(card, dom, mkvp) == 0 &&
+ t->mkvp == mkvp[0]) {
if (!verify)
break;
/* verify: fetch mkvp from adapter */
- if (fetch_mkvp(card, dom, &mkvp) == 0) {
+ if (fetch_mkvp(card, dom, mkvp) == 0) {
mkvp_cache_update(card, dom, mkvp);
- if (t->mkvp == mkvp)
+ if (t->mkvp == mkvp[0])
break;
}
}
@@ -936,14 +944,21 @@ int pkey_findcard(const struct pkey_seckey *seckey,
card = AP_QID_CARD(device_matrix->device[i].qid);
dom = AP_QID_QUEUE(device_matrix->device[i].qid);
/* fresh fetch mkvp from adapter */
- if (fetch_mkvp(card, dom, &mkvp) == 0) {
+ if (fetch_mkvp(card, dom, mkvp) == 0) {
mkvp_cache_update(card, dom, mkvp);
- if (t->mkvp == mkvp)
+ if (t->mkvp == mkvp[0])
break;
+ if (t->mkvp == mkvp[1] && oi < 0)
+ oi = i;
}
}
+ if (i >= MAX_ZDEV_ENTRIES && oi >= 0) {
+ /* old mkvp matched, use this card then */
+ card = AP_QID_CARD(device_matrix->device[oi].qid);
+ dom = AP_QID_QUEUE(device_matrix->device[oi].qid);
+ }
}
- if (i < MAX_ZDEV_ENTRIES) {
+ if (i < MAX_ZDEV_ENTRIES || oi >= 0) {
if (pcardnr)
*pcardnr = card;
if (pdomain)
diff --git a/drivers/s390/net/ctcm_fsms.c b/drivers/s390/net/ctcm_fsms.c
index fd5944b..730d961 100644
--- a/drivers/s390/net/ctcm_fsms.c
+++ b/drivers/s390/net/ctcm_fsms.c
@@ -1283,7 +1283,7 @@ static void ctcmpc_chx_txdone(fsm_instance *fi, int event, void *arg)
p_header = (struct pdu *)
(skb_tail_pointer(ch->trans_skb) - skb->len);
p_header->pdu_flag = 0x00;
- if (skb->protocol == ntohs(ETH_P_SNAP))
+ if (be16_to_cpu(skb->protocol) == ETH_P_SNAP)
p_header->pdu_flag |= 0x60;
else
p_header->pdu_flag |= 0x20;
diff --git a/drivers/s390/net/ctcm_main.c b/drivers/s390/net/ctcm_main.c
index ac65f12..198842c 100644
--- a/drivers/s390/net/ctcm_main.c
+++ b/drivers/s390/net/ctcm_main.c
@@ -106,7 +106,7 @@ void ctcm_unpack_skb(struct channel *ch, struct sk_buff *pskb)
priv->stats.rx_frame_errors++;
return;
}
- pskb->protocol = ntohs(header->type);
+ pskb->protocol = cpu_to_be16(header->type);
if ((header->length <= LL_HEADER_LENGTH) ||
(len <= LL_HEADER_LENGTH)) {
if (!(ch->logflags & LOG_FLAG_ILLEGALSIZE)) {
@@ -125,7 +125,7 @@ void ctcm_unpack_skb(struct channel *ch, struct sk_buff *pskb)
header->length -= LL_HEADER_LENGTH;
len -= LL_HEADER_LENGTH;
if ((header->length > skb_tailroom(pskb)) ||
- (header->length > len)) {
+ (header->length > len)) {
if (!(ch->logflags & LOG_FLAG_OVERRUN)) {
CTCM_DBF_TEXT_(ERROR, CTC_DBF_ERROR,
"%s(%s): Packet size %d (overrun)"
@@ -485,7 +485,7 @@ static int ctcm_transmit_skb(struct channel *ch, struct sk_buff *skb)
} else {
atomic_inc(&skb->users);
header.length = l;
- header.type = skb->protocol;
+ header.type = be16_to_cpu(skb->protocol);
header.unused = 0;
memcpy(skb_push(skb, LL_HEADER_LENGTH), &header,
LL_HEADER_LENGTH);
@@ -503,7 +503,7 @@ static int ctcm_transmit_skb(struct channel *ch, struct sk_buff *skb)
atomic_inc(&skb->users);
ch->prof.txlen += skb->len;
header.length = skb->len + LL_HEADER_LENGTH;
- header.type = skb->protocol;
+ header.type = be16_to_cpu(skb->protocol);
header.unused = 0;
memcpy(skb_push(skb, LL_HEADER_LENGTH), &header, LL_HEADER_LENGTH);
block_len = skb->len + 2;
@@ -690,7 +690,7 @@ static int ctcmpc_transmit_skb(struct channel *ch, struct sk_buff *skb)
p_header->pdu_offset = skb->len;
p_header->pdu_proto = 0x01;
p_header->pdu_flag = 0x00;
- if (skb->protocol == ntohs(ETH_P_SNAP)) {
+ if (be16_to_cpu(skb->protocol) == ETH_P_SNAP) {
p_header->pdu_flag |= PDU_FIRST | PDU_CNTL;
} else {
p_header->pdu_flag |= PDU_FIRST;
@@ -745,7 +745,7 @@ static int ctcmpc_transmit_skb(struct channel *ch, struct sk_buff *skb)
p_header->pdu_proto = 0x01;
p_header->pdu_flag = 0x00;
p_header->pdu_seq = 0;
- if (skb->protocol == ntohs(ETH_P_SNAP)) {
+ if (be16_to_cpu(skb->protocol) == ETH_P_SNAP) {
p_header->pdu_flag |= PDU_FIRST | PDU_CNTL;
} else {
p_header->pdu_flag |= PDU_FIRST;
diff --git a/drivers/s390/net/netiucv.c b/drivers/s390/net/netiucv.c
index 3f85b97..dba94b4 100644
--- a/drivers/s390/net/netiucv.c
+++ b/drivers/s390/net/netiucv.c
@@ -635,7 +635,7 @@ static void netiucv_unpack_skb(struct iucv_connection *conn,
skb_put(pskb, NETIUCV_HDRLEN);
pskb->dev = dev;
pskb->ip_summed = CHECKSUM_NONE;
- pskb->protocol = ntohs(ETH_P_IP);
+ pskb->protocol = cpu_to_be16(ETH_P_IP);
while (1) {
struct sk_buff *skb;
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index e7addea..ed5b358 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -503,22 +503,12 @@ struct qeth_qdio_info {
int default_out_queue;
};
-enum qeth_send_errors {
- QETH_SEND_ERROR_NONE,
- QETH_SEND_ERROR_LINK_FAILURE,
- QETH_SEND_ERROR_RETRY,
- QETH_SEND_ERROR_KICK_IT,
-};
-
#define QETH_ETH_MAC_V4 0x0100 /* like v4 */
#define QETH_ETH_MAC_V6 0x3333 /* like v6 */
/* tr mc mac is longer, but that will be enough to detect mc frames */
#define QETH_TR_MAC_NC 0xc000 /* non-canonical */
#define QETH_TR_MAC_C 0x0300 /* canonical */
-#define DEFAULT_ADD_HHLEN 0
-#define MAX_ADD_HHLEN 1024
-
/**
* buffer stuff for read channel
*/
@@ -644,7 +634,6 @@ struct qeth_reply {
atomic_t refcnt;
};
-
struct qeth_card_blkt {
int time_total;
int inter_packet;
@@ -685,7 +674,6 @@ struct qeth_card_options {
struct qeth_ipa_info ipa6;
struct qeth_sbp_info sbp; /* SETBRIDGEPORT options */
int fake_broadcast;
- int add_hhlen;
int layer2;
int performance_stats;
int rx_sg_cb;
@@ -856,9 +844,9 @@ static inline int qeth_get_ip_version(struct sk_buff *skb)
{
__be16 *p = &((struct ethhdr *)skb->data)->h_proto;
- if (*p == ETH_P_8021Q)
+ if (be16_to_cpu(*p) == ETH_P_8021Q)
p += 2;
- switch (*p) {
+ switch (be16_to_cpu(*p)) {
case ETH_P_IPV6:
return 6;
case ETH_P_IP:
@@ -961,7 +949,8 @@ int qeth_bridgeport_query_ports(struct qeth_card *card,
int qeth_bridgeport_setrole(struct qeth_card *card, enum qeth_sbp_roles role);
int qeth_bridgeport_an_set(struct qeth_card *card, int enable);
int qeth_get_priority_queue(struct qeth_card *, struct sk_buff *, int, int);
-int qeth_get_elements_no(struct qeth_card *, struct sk_buff *, int);
+int qeth_get_elements_no(struct qeth_card *card, struct sk_buff *skb,
+ int extra_elems, int data_offset);
int qeth_get_elements_for_frags(struct sk_buff *);
int qeth_do_send_packet_fast(struct qeth_card *, struct qeth_qdio_out_q *,
struct sk_buff *, struct qeth_hdr *, int, int, int);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 315d8a2..6b22b05 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -55,7 +55,6 @@ static struct mutex qeth_mod_mutex;
static void qeth_send_control_data_cb(struct qeth_channel *,
struct qeth_cmd_buffer *);
-static int qeth_issue_next_read(struct qeth_card *);
static struct qeth_cmd_buffer *qeth_get_buffer(struct qeth_channel *);
static void qeth_setup_ccw(struct qeth_channel *, unsigned char *, __u32);
static void qeth_free_buffer_pool(struct qeth_card *);
@@ -1202,7 +1201,7 @@ static void qeth_notify_skbs(struct qeth_qdio_out_q *q,
while (skb) {
QETH_CARD_TEXT_(q->card, 5, "skbn%d", notification);
QETH_CARD_TEXT_(q->card, 5, "%lx", (long) skb);
- if (skb->protocol == ETH_P_AF_IUCV) {
+ if (be16_to_cpu(skb->protocol) == ETH_P_AF_IUCV) {
if (skb->sk) {
struct iucv_sock *iucv = iucv_sk(skb->sk);
iucv->sk_txnotify(skb, notification);
@@ -1233,7 +1232,8 @@ static void qeth_release_skbs(struct qeth_qdio_out_buffer *buf)
while (skb) {
QETH_CARD_TEXT(buf->q->card, 5, "skbr");
QETH_CARD_TEXT_(buf->q->card, 5, "%lx", (long) skb);
- if (notify_general_error && skb->protocol == ETH_P_AF_IUCV) {
+ if (notify_general_error &&
+ be16_to_cpu(skb->protocol) == ETH_P_AF_IUCV) {
if (skb->sk) {
iucv = iucv_sk(skb->sk);
iucv->sk_txnotify(skb, TX_NOTIFY_GENERALERROR);
@@ -1396,7 +1396,6 @@ static void qeth_set_intial_options(struct qeth_card *card)
card->options.route4.type = NO_ROUTER;
card->options.route6.type = NO_ROUTER;
card->options.fake_broadcast = 0;
- card->options.add_hhlen = DEFAULT_ADD_HHLEN;
card->options.performance_stats = 0;
card->options.rx_sg_cb = QETH_RX_SG_CB;
card->options.isolation = ISOLATION_MODE_NONE;
@@ -3322,7 +3321,7 @@ void qeth_queue_input_buffer(struct qeth_card *card, int index)
}
EXPORT_SYMBOL_GPL(qeth_queue_input_buffer);
-static int qeth_handle_send_error(struct qeth_card *card,
+static void qeth_handle_send_error(struct qeth_card *card,
struct qeth_qdio_out_buffer *buffer, unsigned int qdio_err)
{
int sbalf15 = buffer->buffer->element[15].sflags;
@@ -3338,15 +3337,14 @@ static int qeth_handle_send_error(struct qeth_card *card,
qeth_check_qdio_errors(card, buffer->buffer, qdio_err, "qouterr");
if (!qdio_err)
- return QETH_SEND_ERROR_NONE;
+ return;
if ((sbalf15 >= 15) && (sbalf15 <= 31))
- return QETH_SEND_ERROR_RETRY;
+ return;
QETH_CARD_TEXT(card, 1, "lnkfail");
QETH_CARD_TEXT_(card, 1, "%04x %02x",
(u16)qdio_err, (u8)sbalf15);
- return QETH_SEND_ERROR_LINK_FAILURE;
}
/*
@@ -3799,9 +3797,9 @@ int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb,
return qeth_cut_iqd_prio(card, ~skb->priority >> 1 & 3);
case QETH_PRIO_Q_ING_VLAN:
tci = &((struct ethhdr *)skb->data)->h_proto;
- if (*tci == ETH_P_8021Q)
- return qeth_cut_iqd_prio(card, ~*(tci + 1) >>
- (VLAN_PRIO_SHIFT + 1) & 3);
+ if (be16_to_cpu(*tci) == ETH_P_8021Q)
+ return qeth_cut_iqd_prio(card,
+ ~be16_to_cpu(*(tci + 1)) >> (VLAN_PRIO_SHIFT + 1) & 3);
break;
default:
break;
@@ -3837,6 +3835,7 @@ EXPORT_SYMBOL_GPL(qeth_get_elements_for_frags);
* @card: qeth card structure, to check max. elems.
* @skb: SKB address
* @extra_elems: extra elems needed, to check against max.
+ * @data_offset: range starts at skb->data + data_offset
*
* Returns the number of pages, and thus QDIO buffer elements, needed to cover
* skb data, including linear part and fragments. Checks if the result plus
@@ -3844,10 +3843,10 @@ EXPORT_SYMBOL_GPL(qeth_get_elements_for_frags);
* Note: extra_elems is not included in the returned result.
*/
int qeth_get_elements_no(struct qeth_card *card,
- struct sk_buff *skb, int extra_elems)
+ struct sk_buff *skb, int extra_elems, int data_offset)
{
int elements = qeth_get_elements_for_range(
- (addr_t)skb->data,
+ (addr_t)skb->data + data_offset,
(addr_t)skb->data + skb_headlen(skb)) +
qeth_get_elements_for_frags(skb);
@@ -4774,12 +4773,10 @@ static int qeth_query_card_info(struct qeth_card *card,
static inline int qeth_get_qdio_q_format(struct qeth_card *card)
{
- switch (card->info.type) {
- case QETH_CARD_TYPE_IQD:
- return 2;
- default:
- return 0;
- }
+ if (card->info.type == QETH_CARD_TYPE_IQD)
+ return QDIO_IQDIO_QFMT;
+ else
+ return QDIO_QETH_QFMT;
}
static void qeth_determine_capabilities(struct qeth_card *card)
@@ -4818,8 +4815,9 @@ static void qeth_determine_capabilities(struct qeth_card *card)
QETH_DBF_TEXT_(SETUP, 2, "6err%d", rc);
QETH_DBF_TEXT_(SETUP, 2, "qfmt%d", card->ssqd.qfmt);
- QETH_DBF_TEXT_(SETUP, 2, "%d", card->ssqd.qdioac1);
- QETH_DBF_TEXT_(SETUP, 2, "%d", card->ssqd.qdioac3);
+ QETH_DBF_TEXT_(SETUP, 2, "ac1:%02x", card->ssqd.qdioac1);
+ QETH_DBF_TEXT_(SETUP, 2, "ac2:%04x", card->ssqd.qdioac2);
+ QETH_DBF_TEXT_(SETUP, 2, "ac3:%04x", card->ssqd.qdioac3);
QETH_DBF_TEXT_(SETUP, 2, "icnt%d", card->ssqd.icnt);
if (!((card->ssqd.qfmt != QDIO_IQDIO_QFMT) ||
((card->ssqd.qdioac1 & CHSC_AC1_INITIATE_INPUTQ) == 0) ||
diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h
index bc69d0a..4accb0a 100644
--- a/drivers/s390/net/qeth_core_mpc.h
+++ b/drivers/s390/net/qeth_core_mpc.h
@@ -29,7 +29,6 @@ extern unsigned char IPA_PDU_HEADER[];
#define QETH_TIMEOUT (10 * HZ)
#define QETH_IPA_TIMEOUT (45 * HZ)
#define QETH_IDX_COMMAND_SEQNO 0xffff0000
-#define SR_INFO_LEN 16
#define QETH_CLEAR_CHANNEL_PARM -10
#define QETH_HALT_CHANNEL_PARM -11
@@ -65,7 +64,6 @@ enum qeth_link_types {
QETH_LINK_TYPE_LANE_TR = 0x82,
QETH_LINK_TYPE_LANE_ETH1000 = 0x83,
QETH_LINK_TYPE_LANE = 0x88,
- QETH_LINK_TYPE_ATM_NATIVE = 0x90,
};
/*
@@ -185,8 +183,6 @@ enum qeth_ipa_return_codes {
IPA_RC_ENOMEM = 0xfffe,
IPA_RC_FFFF = 0xffff
};
-/* for DELIP */
-#define IPA_RC_IP_ADDRESS_NOT_DEFINED IPA_RC_PRIMARY_ALREADY_DEFINED
/* for SET_DIAGNOSTIC_ASSIST */
#define IPA_RC_INVALID_SUBCMD IPA_RC_IP_TABLE_FULL
#define IPA_RC_HARDWARE_AUTH_ERROR IPA_RC_UNKNOWN_ERROR
@@ -631,14 +627,6 @@ enum qeth_ipa_addr_change_code {
IPA_ADDR_CHANGE_CODE_MACADDR = 0x02,
IPA_ADDR_CHANGE_CODE_REMOVAL = 0x80, /* else addition */
};
-enum qeth_ipa_addr_change_retcode {
- IPA_ADDR_CHANGE_RETCODE_OK = 0x0000,
- IPA_ADDR_CHANGE_RETCODE_LOSTEVENTS = 0x0010,
-};
-enum qeth_ipa_addr_change_lostmask {
- IPA_ADDR_CHANGE_MASK_OVERFLOW = 0x01,
- IPA_ADDR_CHANGE_MASK_STATECHANGE = 0x02,
-};
struct qeth_ipacmd_addr_change_entry {
struct net_if_token token;
@@ -817,9 +805,4 @@ extern unsigned char IDX_ACTIVATE_WRITE[];
((buffer) && \
(*(buffer + ((*(buffer + 0x0b)) + 4)) == 0xc1))
-#define ADDR_FRAME_TYPE_DIX 1
-#define ADDR_FRAME_TYPE_802_3 2
-#define ADDR_FRAME_TYPE_TR_WITHOUT_SR 0x10
-#define ADDR_FRAME_TYPE_TR_WITH_SR 0x20
-
#endif
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index bea4833..cd0ba9e 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -28,7 +28,6 @@
static int qeth_l2_set_offline(struct ccwgroup_device *);
static int qeth_l2_stop(struct net_device *);
static void qeth_l2_set_rx_mode(struct net_device *);
-static int qeth_l2_recover(void *);
static void qeth_bridgeport_query_support(struct qeth_card *card);
static void qeth_bridge_state_change(struct qeth_card *card,
struct qeth_ipa_cmd *cmd);
@@ -849,7 +848,7 @@ static int qeth_l2_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
* chaining we can not send long frag lists
*/
if ((card->info.type != QETH_CARD_TYPE_IQD) &&
- !qeth_get_elements_no(card, new_skb, 0)) {
+ !qeth_get_elements_no(card, new_skb, 0, 0)) {
int lin_rc = skb_linearize(new_skb);
if (card->options.performance_stats) {
@@ -894,7 +893,8 @@ static int qeth_l2_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
}
}
- elements = qeth_get_elements_no(card, new_skb, elements_needed);
+ elements = qeth_get_elements_no(card, new_skb, elements_needed,
+ (data_offset > 0) ? data_offset : 0);
if (!elements) {
if (data_offset >= 0)
kmem_cache_free(qeth_core_header_cache, hdr);
diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c
index 692db49..6879723 100644
--- a/drivers/s390/net/qeth_l2_sys.c
+++ b/drivers/s390/net/qeth_l2_sys.c
@@ -8,9 +8,6 @@
#include "qeth_core.h"
#include "qeth_l2.h"
-#define QETH_DEVICE_ATTR(_id, _name, _mode, _show, _store) \
-struct device_attribute dev_attr_##_id = __ATTR(_name, _mode, _show, _store)
-
static ssize_t qeth_bridge_port_role_state_show(struct device *dev,
struct device_attribute *attr, char *buf,
int show_state)
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 06d0add..c295258 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -36,16 +36,12 @@
static int qeth_l3_set_offline(struct ccwgroup_device *);
-static int qeth_l3_recover(void *);
static int qeth_l3_stop(struct net_device *);
static void qeth_l3_set_multicast_list(struct net_device *);
-static int qeth_l3_neigh_setup(struct net_device *, struct neigh_parms *);
static int qeth_l3_register_addr_entry(struct qeth_card *,
struct qeth_ipaddr *);
static int qeth_l3_deregister_addr_entry(struct qeth_card *,
struct qeth_ipaddr *);
-static int __qeth_l3_set_online(struct ccwgroup_device *, int);
-static int __qeth_l3_set_offline(struct ccwgroup_device *, int);
static int qeth_l3_isxdigit(char *buf)
{
@@ -1341,7 +1337,7 @@ qeth_diags_trace(struct qeth_card *card, enum qeth_diags_trace_cmds diags_cmd)
return qeth_send_ipa_cmd(card, iob, qeth_diags_trace_cb, NULL);
}
-static void qeth_l3_get_mac_for_ipm(__u32 ipm, char *mac)
+static void qeth_l3_get_mac_for_ipm(__be32 ipm, char *mac)
{
ip_eth_mc_map(ipm, mac);
}
@@ -1414,7 +1410,7 @@ qeth_l3_add_mc_to_hash(struct qeth_card *card, struct in_device *in4_dev)
im4 = rcu_dereference(im4->next_rcu)) {
qeth_l3_get_mac_for_ipm(im4->multiaddr, buf);
- tmp->u.a4.addr = im4->multiaddr;
+ tmp->u.a4.addr = be32_to_cpu(im4->multiaddr);
memcpy(tmp->mac, buf, sizeof(tmp->mac));
ipm = qeth_l3_ip_from_hash(card, tmp);
@@ -1425,7 +1421,7 @@ qeth_l3_add_mc_to_hash(struct qeth_card *card, struct in_device *in4_dev)
if (!ipm)
continue;
memcpy(ipm->mac, buf, sizeof(tmp->mac));
- ipm->u.a4.addr = im4->multiaddr;
+ ipm->u.a4.addr = be32_to_cpu(im4->multiaddr);
ipm->is_multicast = 1;
ipm->disp_flag = QETH_DISP_ADDR_ADD;
hash_add(card->ip_mc_htable,
@@ -1598,8 +1594,8 @@ static void qeth_l3_free_vlan_addresses4(struct qeth_card *card,
spin_lock_bh(&card->ip_lock);
for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
- addr->u.a4.addr = ifa->ifa_address;
- addr->u.a4.mask = ifa->ifa_mask;
+ addr->u.a4.addr = be32_to_cpu(ifa->ifa_address);
+ addr->u.a4.mask = be32_to_cpu(ifa->ifa_mask);
addr->type = QETH_IP_TYPE_NORMAL;
qeth_l3_delete_ip(card, addr);
}
@@ -1690,25 +1686,25 @@ static inline int qeth_l3_rebuild_skb(struct qeth_card *card,
struct sk_buff *skb, struct qeth_hdr *hdr,
unsigned short *vlan_id)
{
- __be16 prot;
+ __u16 prot;
struct iphdr *ip_hdr;
unsigned char tg_addr[MAX_ADDR_LEN];
int is_vlan = 0;
if (!(hdr->hdr.l3.flags & QETH_HDR_PASSTHRU)) {
- prot = htons((hdr->hdr.l3.flags & QETH_HDR_IPV6)? ETH_P_IPV6 :
- ETH_P_IP);
+ prot = (hdr->hdr.l3.flags & QETH_HDR_IPV6) ? ETH_P_IPV6 :
+ ETH_P_IP;
switch (hdr->hdr.l3.flags & QETH_HDR_CAST_MASK) {
case QETH_CAST_MULTICAST:
switch (prot) {
#ifdef CONFIG_QETH_IPV6
- case __constant_htons(ETH_P_IPV6):
+ case ETH_P_IPV6:
ndisc_mc_map((struct in6_addr *)
skb->data + 24,
tg_addr, card->dev, 0);
break;
#endif
- case __constant_htons(ETH_P_IP):
+ case ETH_P_IP:
ip_hdr = (struct iphdr *)skb->data;
ip_eth_mc_map(ip_hdr->daddr, tg_addr);
break;
@@ -1795,7 +1791,7 @@ static int qeth_l3_process_inbound_buffer(struct qeth_card *card,
magic = *(__u16 *)skb->data;
if ((card->info.type == QETH_CARD_TYPE_IQD) &&
(magic == ETH_P_AF_IUCV)) {
- skb->protocol = ETH_P_AF_IUCV;
+ skb->protocol = cpu_to_be16(ETH_P_AF_IUCV);
skb->pkt_type = PACKET_HOST;
skb->mac_header = NET_SKB_PAD;
skb->dev = card->dev;
@@ -2572,10 +2568,10 @@ int inline qeth_l3_get_cast_type(struct qeth_card *card, struct sk_buff *skb)
rcu_read_unlock();
/* try something else */
- if (skb->protocol == ETH_P_IPV6)
+ if (be16_to_cpu(skb->protocol) == ETH_P_IPV6)
return (skb_network_header(skb)[24] == 0xff) ?
RTN_MULTICAST : 0;
- else if (skb->protocol == ETH_P_IP)
+ else if (be16_to_cpu(skb->protocol) == ETH_P_IP)
return ((skb_network_header(skb)[16] & 0xf0) == 0xe0) ?
RTN_MULTICAST : 0;
/* ... */
@@ -2609,17 +2605,13 @@ static void qeth_l3_fill_af_iucv_hdr(struct qeth_card *card,
char daddr[16];
struct af_iucv_trans_hdr *iucv_hdr;
- skb_pull(skb, 14);
- card->dev->header_ops->create(skb, card->dev, 0,
- card->dev->dev_addr, card->dev->dev_addr,
- card->dev->addr_len);
- skb_pull(skb, 14);
- iucv_hdr = (struct af_iucv_trans_hdr *)skb->data;
memset(hdr, 0, sizeof(struct qeth_hdr));
hdr->hdr.l3.id = QETH_HEADER_TYPE_LAYER3;
hdr->hdr.l3.ext_flags = 0;
- hdr->hdr.l3.length = skb->len;
+ hdr->hdr.l3.length = skb->len - ETH_HLEN;
hdr->hdr.l3.flags = QETH_HDR_IPV6 | QETH_CAST_UNICAST;
+
+ iucv_hdr = (struct af_iucv_trans_hdr *) (skb->data + ETH_HLEN);
memset(daddr, 0, sizeof(daddr));
daddr[0] = 0xfe;
daddr[1] = 0x80;
@@ -2730,7 +2722,7 @@ static void qeth_tso_fill_header(struct qeth_card *card,
hdr->ext.payload_len = (__u16)(skb->len - hdr->ext.dg_hdr_len -
sizeof(struct qeth_hdr_tso));
tcph->check = 0;
- if (skb->protocol == ETH_P_IPV6) {
+ if (be16_to_cpu(skb->protocol) == ETH_P_IPV6) {
ip6h->payload_len = 0;
tcph->check = ~csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
0, IPPROTO_TCP, 0);
@@ -2777,7 +2769,7 @@ static int qeth_l3_get_elements_no_tso(struct qeth_card *card,
static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
int rc;
- u16 *tag;
+ __be16 *tag;
struct qeth_hdr *hdr = NULL;
int hdr_elements = 0;
int elements;
@@ -2798,7 +2790,7 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
if (((card->info.type == QETH_CARD_TYPE_IQD) &&
(((card->options.cq != QETH_CQ_ENABLED) && !ipv) ||
((card->options.cq == QETH_CQ_ENABLED) &&
- (skb->protocol != ETH_P_AF_IUCV)))) ||
+ (be16_to_cpu(skb->protocol) != ETH_P_AF_IUCV)))) ||
card->options.sniffer)
goto tx_drop;
@@ -2823,10 +2815,7 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
if ((card->info.type == QETH_CARD_TYPE_IQD) &&
!skb_is_nonlinear(skb)) {
new_skb = skb;
- if (new_skb->protocol == ETH_P_AF_IUCV)
- data_offset = 0;
- else
- data_offset = ETH_HLEN;
+ data_offset = ETH_HLEN;
hdr = kmem_cache_alloc(qeth_core_header_cache, GFP_ATOMIC);
if (!hdr)
goto tx_drop;
@@ -2854,9 +2843,9 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
new_skb->data + 8, 4);
skb_copy_to_linear_data_offset(new_skb, 8,
new_skb->data + 12, 4);
- tag = (u16 *)(new_skb->data + 12);
- *tag = __constant_htons(ETH_P_8021Q);
- *(tag + 1) = htons(skb_vlan_tag_get(new_skb));
+ tag = (__be16 *)(new_skb->data + 12);
+ *tag = cpu_to_be16(ETH_P_8021Q);
+ *(tag + 1) = cpu_to_be16(skb_vlan_tag_get(new_skb));
}
}
@@ -2867,7 +2856,7 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
*/
if ((card->info.type != QETH_CARD_TYPE_IQD) &&
((use_tso && !qeth_l3_get_elements_no_tso(card, new_skb, 1)) ||
- (!use_tso && !qeth_get_elements_no(card, new_skb, 0)))) {
+ (!use_tso && !qeth_get_elements_no(card, new_skb, 0, 0)))) {
int lin_rc = skb_linearize(new_skb);
if (card->options.performance_stats) {
@@ -2894,7 +2883,7 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
qeth_l3_fill_header(card, hdr, new_skb, ipv,
cast_type);
} else {
- if (new_skb->protocol == ETH_P_AF_IUCV)
+ if (be16_to_cpu(new_skb->protocol) == ETH_P_AF_IUCV)
qeth_l3_fill_af_iucv_hdr(card, hdr, new_skb);
else {
qeth_l3_fill_header(card, hdr, new_skb, ipv,
@@ -2909,7 +2898,8 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
elements = use_tso ?
qeth_l3_get_elements_no_tso(card, new_skb, hdr_elements) :
- qeth_get_elements_no(card, new_skb, hdr_elements);
+ qeth_get_elements_no(card, new_skb, hdr_elements,
+ (data_offset > 0) ? data_offset : 0);
if (!elements) {
if (data_offset >= 0)
kmem_cache_free(qeth_core_header_cache, hdr);
@@ -3472,8 +3462,8 @@ static int qeth_l3_ip_event(struct notifier_block *this,
addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
if (addr) {
- addr->u.a4.addr = ifa->ifa_address;
- addr->u.a4.mask = ifa->ifa_mask;
+ addr->u.a4.addr = be32_to_cpu(ifa->ifa_address);
+ addr->u.a4.mask = be32_to_cpu(ifa->ifa_mask);
addr->type = QETH_IP_TYPE_NORMAL;
} else
return NOTIFY_DONE;
diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c
index 05e9471..ff29a4b 100644
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -286,7 +286,7 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev,
if (!addr)
return -ENOMEM;
- addr->u.a6.addr.s6_addr32[0] = 0xfe800000;
+ addr->u.a6.addr.s6_addr32[0] = cpu_to_be32(0xfe800000);
addr->u.a6.addr.s6_addr32[1] = 0x00000000;
for (i = 8; i < 16; i++)
addr->u.a6.addr.s6_addr[i] =
@@ -320,7 +320,7 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev,
addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV6);
if (addr != NULL) {
- addr->u.a6.addr.s6_addr32[0] = 0xfe800000;
+ addr->u.a6.addr.s6_addr32[0] = cpu_to_be32(0xfe800000);
addr->u.a6.addr.s6_addr32[1] = 0x00000000;
for (i = 8; i < 16; i++)
addr->u.a6.addr.s6_addr[i] = card->options.hsuid[i - 8];
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index 230043c..3c52867 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -1241,16 +1241,15 @@
tristate "Emulex LightPulse Fibre Channel Support"
depends on PCI && SCSI
depends on SCSI_FC_ATTRS
- depends on NVME_FC && NVME_TARGET_FC
select CRC_T10DIF
- help
+ ---help---
This lpfc driver supports the Emulex LightPulse
Family of Fibre Channel PCI host adapters.
config SCSI_LPFC_DEBUG_FS
bool "Emulex LightPulse Fibre Channel debugfs Support"
depends on SCSI_LPFC && DEBUG_FS
- help
+ ---help---
This makes debugging information from the lpfc driver
available via the debugfs filesystem.
diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index a3ad042..c8172f1 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -2056,7 +2056,6 @@ static int fillup_pools(struct aac_dev *dev, struct hw_fib **hw_fib_pool,
{
struct hw_fib **hw_fib_p;
struct fib **fib_p;
- int rcode = 1;
hw_fib_p = hw_fib_pool;
fib_p = fib_pool;
@@ -2074,11 +2073,11 @@ static int fillup_pools(struct aac_dev *dev, struct hw_fib **hw_fib_pool,
}
}
+ /*
+ * Get the actual number of allocated fibs
+ */
num = hw_fib_p - hw_fib_pool;
- if (!num)
- rcode = 0;
-
- return rcode;
+ return num;
}
static void wakeup_fibctx_threads(struct aac_dev *dev,
@@ -2186,7 +2185,6 @@ static void aac_process_events(struct aac_dev *dev)
struct fib *fib;
unsigned long flags;
spinlock_t *t_lock;
- unsigned int rcode;
t_lock = dev->queues->queue[HostNormCmdQueue].lock;
spin_lock_irqsave(t_lock, flags);
@@ -2269,8 +2267,8 @@ static void aac_process_events(struct aac_dev *dev)
* Fill up fib pointer pools with actual fibs
* and hw_fibs
*/
- rcode = fillup_pools(dev, hw_fib_pool, fib_pool, num);
- if (!rcode)
+ num = fillup_pools(dev, hw_fib_pool, fib_pool, num);
+ if (!num)
goto free_mem;
/*
diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c
index 2e5338d..7b0410e 100644
--- a/drivers/scsi/aacraid/src.c
+++ b/drivers/scsi/aacraid/src.c
@@ -468,7 +468,7 @@ static int aac_src_check_health(struct aac_dev *dev)
return -1;
err_blink:
- return (status > 16) & 0xFF;
+ return (status >> 16) & 0xFF;
}
static inline u32 aac_get_vector(struct aac_dev *dev)
diff --git a/drivers/scsi/aic7xxx/aic79xx_core.c b/drivers/scsi/aic7xxx/aic79xx_core.c
index 109e2c9..95d8f25 100644
--- a/drivers/scsi/aic7xxx/aic79xx_core.c
+++ b/drivers/scsi/aic7xxx/aic79xx_core.c
@@ -6278,7 +6278,7 @@ ahd_reset(struct ahd_softc *ahd, int reinit)
* does not disable its parity logic prior to
* the start of the reset. This may cause a
* parity error to be detected and thus a
- * spurious SERR or PERR assertion. Disble
+ * spurious SERR or PERR assertion. Disable
* PERR and SERR responses during the CHIPRST.
*/
mod_cmd = cmd & ~(PCIM_CMD_PERRESPEN|PCIM_CMD_SERRESPEN);
diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c
index 48e2001..c01b47e 100644
--- a/drivers/scsi/device_handler/scsi_dh_alua.c
+++ b/drivers/scsi/device_handler/scsi_dh_alua.c
@@ -113,7 +113,7 @@ struct alua_queue_data {
#define ALUA_POLICY_SWITCH_ALL 1
static void alua_rtpg_work(struct work_struct *work);
-static void alua_rtpg_queue(struct alua_port_group *pg,
+static bool alua_rtpg_queue(struct alua_port_group *pg,
struct scsi_device *sdev,
struct alua_queue_data *qdata, bool force);
static void alua_check(struct scsi_device *sdev, bool force);
@@ -862,7 +862,13 @@ static void alua_rtpg_work(struct work_struct *work)
kref_put(&pg->kref, release_port_group);
}
-static void alua_rtpg_queue(struct alua_port_group *pg,
+/**
+ * alua_rtpg_queue() - cause RTPG to be submitted asynchronously
+ *
+ * Returns true if and only if alua_rtpg_work() will be called asynchronously.
+ * That function is responsible for calling @qdata->fn().
+ */
+static bool alua_rtpg_queue(struct alua_port_group *pg,
struct scsi_device *sdev,
struct alua_queue_data *qdata, bool force)
{
@@ -870,8 +876,8 @@ static void alua_rtpg_queue(struct alua_port_group *pg,
unsigned long flags;
struct workqueue_struct *alua_wq = kaluad_wq;
- if (!pg)
- return;
+ if (WARN_ON_ONCE(!pg) || scsi_device_get(sdev))
+ return false;
spin_lock_irqsave(&pg->lock, flags);
if (qdata) {
@@ -884,14 +890,12 @@ static void alua_rtpg_queue(struct alua_port_group *pg,
pg->flags |= ALUA_PG_RUN_RTPG;
kref_get(&pg->kref);
pg->rtpg_sdev = sdev;
- scsi_device_get(sdev);
start_queue = 1;
} else if (!(pg->flags & ALUA_PG_RUN_RTPG) && force) {
pg->flags |= ALUA_PG_RUN_RTPG;
/* Do not queue if the worker is already running */
if (!(pg->flags & ALUA_PG_RUNNING)) {
kref_get(&pg->kref);
- sdev = NULL;
start_queue = 1;
}
}
@@ -900,13 +904,17 @@ static void alua_rtpg_queue(struct alua_port_group *pg,
alua_wq = kaluad_sync_wq;
spin_unlock_irqrestore(&pg->lock, flags);
- if (start_queue &&
- !queue_delayed_work(alua_wq, &pg->rtpg_work,
- msecs_to_jiffies(ALUA_RTPG_DELAY_MSECS))) {
- if (sdev)
- scsi_device_put(sdev);
- kref_put(&pg->kref, release_port_group);
+ if (start_queue) {
+ if (queue_delayed_work(alua_wq, &pg->rtpg_work,
+ msecs_to_jiffies(ALUA_RTPG_DELAY_MSECS)))
+ sdev = NULL;
+ else
+ kref_put(&pg->kref, release_port_group);
}
+ if (sdev)
+ scsi_device_put(sdev);
+
+ return true;
}
/*
@@ -1007,11 +1015,13 @@ static int alua_activate(struct scsi_device *sdev,
mutex_unlock(&h->init_mutex);
goto out;
}
- fn = NULL;
rcu_read_unlock();
mutex_unlock(&h->init_mutex);
- alua_rtpg_queue(pg, sdev, qdata, true);
+ if (alua_rtpg_queue(pg, sdev, qdata, true))
+ fn = NULL;
+ else
+ err = SCSI_DH_DEV_OFFLINED;
kref_put(&pg->kref, release_port_group);
out:
if (fn)
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 524a0c7..9d659aa 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -2956,7 +2956,7 @@ static int hpsa_send_reset(struct ctlr_info *h, unsigned char *scsi3addr,
/* fill_cmd can't fail here, no data buffer to map. */
(void) fill_cmd(c, reset_type, h, NULL, 0, 0,
scsi3addr, TYPE_MSG);
- rc = hpsa_scsi_do_simple_cmd(h, c, reply_queue, DEFAULT_TIMEOUT);
+ rc = hpsa_scsi_do_simple_cmd(h, c, reply_queue, NO_TIMEOUT);
if (rc) {
dev_warn(&h->pdev->dev, "Failed to send reset command\n");
goto out;
@@ -3714,7 +3714,7 @@ static int hpsa_get_volume_status(struct ctlr_info *h,
* # (integer code indicating one of several NOT READY states
* describing why a volume is to be kept offline)
*/
-static int hpsa_volume_offline(struct ctlr_info *h,
+static unsigned char hpsa_volume_offline(struct ctlr_info *h,
unsigned char scsi3addr[])
{
struct CommandList *c;
@@ -3735,7 +3735,7 @@ static int hpsa_volume_offline(struct ctlr_info *h,
DEFAULT_TIMEOUT);
if (rc) {
cmd_free(h, c);
- return 0;
+ return HPSA_VPD_LV_STATUS_UNSUPPORTED;
}
sense = c->err_info->SenseInfo;
if (c->err_info->SenseLen > sizeof(c->err_info->SenseInfo))
@@ -3746,19 +3746,13 @@ static int hpsa_volume_offline(struct ctlr_info *h,
cmd_status = c->err_info->CommandStatus;
scsi_status = c->err_info->ScsiStatus;
cmd_free(h, c);
- /* Is the volume 'not ready'? */
- if (cmd_status != CMD_TARGET_STATUS ||
- scsi_status != SAM_STAT_CHECK_CONDITION ||
- sense_key != NOT_READY ||
- asc != ASC_LUN_NOT_READY) {
- return 0;
- }
/* Determine the reason for not ready state */
ldstat = hpsa_get_volume_status(h, scsi3addr);
/* Keep volume offline in certain cases: */
switch (ldstat) {
+ case HPSA_LV_FAILED:
case HPSA_LV_UNDERGOING_ERASE:
case HPSA_LV_NOT_AVAILABLE:
case HPSA_LV_UNDERGOING_RPI:
@@ -3780,7 +3774,7 @@ static int hpsa_volume_offline(struct ctlr_info *h,
default:
break;
}
- return 0;
+ return HPSA_LV_OK;
}
/*
@@ -3853,10 +3847,10 @@ static int hpsa_update_device_info(struct ctlr_info *h,
/* Do an inquiry to the device to see what it is. */
if (hpsa_scsi_do_inquiry(h, scsi3addr, 0, inq_buff,
(unsigned char) OBDR_TAPE_INQ_SIZE) != 0) {
- /* Inquiry failed (msg printed already) */
dev_err(&h->pdev->dev,
- "hpsa_update_device_info: inquiry failed\n");
- rc = -EIO;
+ "%s: inquiry failed, device will be skipped.\n",
+ __func__);
+ rc = HPSA_INQUIRY_FAILED;
goto bail_out;
}
@@ -3885,15 +3879,20 @@ static int hpsa_update_device_info(struct ctlr_info *h,
if ((this_device->devtype == TYPE_DISK ||
this_device->devtype == TYPE_ZBC) &&
is_logical_dev_addr_mode(scsi3addr)) {
- int volume_offline;
+ unsigned char volume_offline;
hpsa_get_raid_level(h, scsi3addr, &this_device->raid_level);
if (h->fw_support & MISC_FW_RAID_OFFLOAD_BASIC)
hpsa_get_ioaccel_status(h, scsi3addr, this_device);
volume_offline = hpsa_volume_offline(h, scsi3addr);
- if (volume_offline < 0 || volume_offline > 0xff)
- volume_offline = HPSA_VPD_LV_STATUS_UNSUPPORTED;
- this_device->volume_offline = volume_offline & 0xff;
+ this_device->volume_offline = volume_offline;
+ if (volume_offline == HPSA_LV_FAILED) {
+ rc = HPSA_LV_FAILED;
+ dev_err(&h->pdev->dev,
+ "%s: LV failed, device will be skipped.\n",
+ __func__);
+ goto bail_out;
+ }
} else {
this_device->raid_level = RAID_UNKNOWN;
this_device->offload_config = 0;
@@ -4379,8 +4378,7 @@ static void hpsa_update_scsi_devices(struct ctlr_info *h)
goto out;
}
if (rc) {
- dev_warn(&h->pdev->dev,
- "Inquiry failed, skipping device.\n");
+ h->drv_req_rescan = 1;
continue;
}
@@ -5558,7 +5556,7 @@ static void hpsa_scan_complete(struct ctlr_info *h)
spin_lock_irqsave(&h->scan_lock, flags);
h->scan_finished = 1;
- wake_up_all(&h->scan_wait_queue);
+ wake_up(&h->scan_wait_queue);
spin_unlock_irqrestore(&h->scan_lock, flags);
}
@@ -5576,11 +5574,23 @@ static void hpsa_scan_start(struct Scsi_Host *sh)
if (unlikely(lockup_detected(h)))
return hpsa_scan_complete(h);
+ /*
+ * If a scan is already waiting to run, no need to add another
+ */
+ spin_lock_irqsave(&h->scan_lock, flags);
+ if (h->scan_waiting) {
+ spin_unlock_irqrestore(&h->scan_lock, flags);
+ return;
+ }
+
+ spin_unlock_irqrestore(&h->scan_lock, flags);
+
/* wait until any scan already in progress is finished. */
while (1) {
spin_lock_irqsave(&h->scan_lock, flags);
if (h->scan_finished)
break;
+ h->scan_waiting = 1;
spin_unlock_irqrestore(&h->scan_lock, flags);
wait_event(h->scan_wait_queue, h->scan_finished);
/* Note: We don't need to worry about a race between this
@@ -5590,6 +5600,7 @@ static void hpsa_scan_start(struct Scsi_Host *sh)
*/
}
h->scan_finished = 0; /* mark scan as in progress */
+ h->scan_waiting = 0;
spin_unlock_irqrestore(&h->scan_lock, flags);
if (unlikely(lockup_detected(h)))
@@ -8792,6 +8803,7 @@ static int hpsa_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
init_waitqueue_head(&h->event_sync_wait_queue);
mutex_init(&h->reset_mutex);
h->scan_finished = 1; /* no scan currently in progress */
+ h->scan_waiting = 0;
pci_set_drvdata(pdev, h);
h->ndevices = 0;
diff --git a/drivers/scsi/hpsa.h b/drivers/scsi/hpsa.h
index bf6cdc1..6f04f2a 100644
--- a/drivers/scsi/hpsa.h
+++ b/drivers/scsi/hpsa.h
@@ -201,6 +201,7 @@ struct ctlr_info {
dma_addr_t errinfo_pool_dhandle;
unsigned long *cmd_pool_bits;
int scan_finished;
+ u8 scan_waiting : 1;
spinlock_t scan_lock;
wait_queue_head_t scan_wait_queue;
diff --git a/drivers/scsi/hpsa_cmd.h b/drivers/scsi/hpsa_cmd.h
index a584cdf..5961705 100644
--- a/drivers/scsi/hpsa_cmd.h
+++ b/drivers/scsi/hpsa_cmd.h
@@ -156,6 +156,7 @@
#define CFGTBL_BusType_Fibre2G 0x00000200l
/* VPD Inquiry types */
+#define HPSA_INQUIRY_FAILED 0x02
#define HPSA_VPD_SUPPORTED_PAGES 0x00
#define HPSA_VPD_LV_DEVICE_ID 0x83
#define HPSA_VPD_LV_DEVICE_GEOMETRY 0xC1
@@ -166,6 +167,7 @@
/* Logical volume states */
#define HPSA_VPD_LV_STATUS_UNSUPPORTED 0xff
#define HPSA_LV_OK 0x0
+#define HPSA_LV_FAILED 0x01
#define HPSA_LV_NOT_AVAILABLE 0x0b
#define HPSA_LV_UNDERGOING_ERASE 0x0F
#define HPSA_LV_UNDERGOING_RPI 0x12
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 07c08ce..894b1e3 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -561,8 +561,12 @@ static void iscsi_complete_task(struct iscsi_task *task, int state)
WARN_ON_ONCE(task->state == ISCSI_TASK_FREE);
task->state = state;
- if (!list_empty(&task->running))
+ spin_lock_bh(&conn->taskqueuelock);
+ if (!list_empty(&task->running)) {
+ pr_debug_once("%s while task on list", __func__);
list_del_init(&task->running);
+ }
+ spin_unlock_bh(&conn->taskqueuelock);
if (conn->task == task)
conn->task = NULL;
@@ -784,7 +788,9 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr,
if (session->tt->xmit_task(task))
goto free_task;
} else {
+ spin_lock_bh(&conn->taskqueuelock);
list_add_tail(&task->running, &conn->mgmtqueue);
+ spin_unlock_bh(&conn->taskqueuelock);
iscsi_conn_queue_work(conn);
}
@@ -1475,8 +1481,10 @@ void iscsi_requeue_task(struct iscsi_task *task)
* this may be on the requeue list already if the xmit_task callout
* is handling the r2ts while we are adding new ones
*/
+ spin_lock_bh(&conn->taskqueuelock);
if (list_empty(&task->running))
list_add_tail(&task->running, &conn->requeue);
+ spin_unlock_bh(&conn->taskqueuelock);
iscsi_conn_queue_work(conn);
}
EXPORT_SYMBOL_GPL(iscsi_requeue_task);
@@ -1513,22 +1521,26 @@ static int iscsi_data_xmit(struct iscsi_conn *conn)
* only have one nop-out as a ping from us and targets should not
* overflow us with nop-ins
*/
+ spin_lock_bh(&conn->taskqueuelock);
check_mgmt:
while (!list_empty(&conn->mgmtqueue)) {
conn->task = list_entry(conn->mgmtqueue.next,
struct iscsi_task, running);
list_del_init(&conn->task->running);
+ spin_unlock_bh(&conn->taskqueuelock);
if (iscsi_prep_mgmt_task(conn, conn->task)) {
/* regular RX path uses back_lock */
spin_lock_bh(&conn->session->back_lock);
__iscsi_put_task(conn->task);
spin_unlock_bh(&conn->session->back_lock);
conn->task = NULL;
+ spin_lock_bh(&conn->taskqueuelock);
continue;
}
rc = iscsi_xmit_task(conn);
if (rc)
goto done;
+ spin_lock_bh(&conn->taskqueuelock);
}
/* process pending command queue */
@@ -1536,19 +1548,24 @@ static int iscsi_data_xmit(struct iscsi_conn *conn)
conn->task = list_entry(conn->cmdqueue.next, struct iscsi_task,
running);
list_del_init(&conn->task->running);
+ spin_unlock_bh(&conn->taskqueuelock);
if (conn->session->state == ISCSI_STATE_LOGGING_OUT) {
fail_scsi_task(conn->task, DID_IMM_RETRY);
+ spin_lock_bh(&conn->taskqueuelock);
continue;
}
rc = iscsi_prep_scsi_cmd_pdu(conn->task);
if (rc) {
if (rc == -ENOMEM || rc == -EACCES) {
+ spin_lock_bh(&conn->taskqueuelock);
list_add_tail(&conn->task->running,
&conn->cmdqueue);
conn->task = NULL;
+ spin_unlock_bh(&conn->taskqueuelock);
goto done;
} else
fail_scsi_task(conn->task, DID_ABORT);
+ spin_lock_bh(&conn->taskqueuelock);
continue;
}
rc = iscsi_xmit_task(conn);
@@ -1559,6 +1576,7 @@ static int iscsi_data_xmit(struct iscsi_conn *conn)
* we need to check the mgmt queue for nops that need to
* be sent to aviod starvation
*/
+ spin_lock_bh(&conn->taskqueuelock);
if (!list_empty(&conn->mgmtqueue))
goto check_mgmt;
}
@@ -1578,12 +1596,15 @@ static int iscsi_data_xmit(struct iscsi_conn *conn)
conn->task = task;
list_del_init(&conn->task->running);
conn->task->state = ISCSI_TASK_RUNNING;
+ spin_unlock_bh(&conn->taskqueuelock);
rc = iscsi_xmit_task(conn);
if (rc)
goto done;
+ spin_lock_bh(&conn->taskqueuelock);
if (!list_empty(&conn->mgmtqueue))
goto check_mgmt;
}
+ spin_unlock_bh(&conn->taskqueuelock);
spin_unlock_bh(&conn->session->frwd_lock);
return -ENODATA;
@@ -1739,7 +1760,9 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc)
goto prepd_reject;
}
} else {
+ spin_lock_bh(&conn->taskqueuelock);
list_add_tail(&task->running, &conn->cmdqueue);
+ spin_unlock_bh(&conn->taskqueuelock);
iscsi_conn_queue_work(conn);
}
@@ -2897,6 +2920,7 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size,
INIT_LIST_HEAD(&conn->mgmtqueue);
INIT_LIST_HEAD(&conn->cmdqueue);
INIT_LIST_HEAD(&conn->requeue);
+ spin_lock_init(&conn->taskqueuelock);
INIT_WORK(&conn->xmitwork, iscsi_xmitworker);
/* allocate login_task used for the login/text sequences */
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 763f012..87f5e694 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -221,7 +221,7 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
task->num_scatter = qc->n_elem;
} else {
for_each_sg(qc->sg, sg, qc->n_elem, si)
- xfer += sg->length;
+ xfer += sg_dma_len(sg);
task->total_xfer_len = xfer;
task->num_scatter = si;
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 0bba2e3..257bbdd 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -99,12 +99,13 @@ struct lpfc_sli2_slim;
#define FC_MAX_ADPTMSG 64
#define MAX_HBAEVT 32
+#define MAX_HBAS_NO_RESET 16
/* Number of MSI-X vectors the driver uses */
#define LPFC_MSIX_VECTORS 2
/* lpfc wait event data ready flag */
-#define LPFC_DATA_READY (1<<0)
+#define LPFC_DATA_READY 0 /* bit 0 */
/* queue dump line buffer size */
#define LPFC_LBUF_SZ 128
@@ -692,6 +693,7 @@ struct lpfc_hba {
* capability
*/
#define HBA_NVME_IOQ_FLUSH 0x80000 /* NVME IO queues flushed. */
+#define NVME_XRI_ABORT_EVENT 0x100000
uint32_t fcp_ring_in_use; /* When polling test if intr-hndlr active*/
struct lpfc_dmabuf slim2p;
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index 5c783ef..22819af 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -3010,6 +3010,12 @@ MODULE_PARM_DESC(lpfc_poll, "FCP ring polling mode control:"
static DEVICE_ATTR(lpfc_poll, S_IRUGO | S_IWUSR,
lpfc_poll_show, lpfc_poll_store);
+int lpfc_no_hba_reset_cnt;
+unsigned long lpfc_no_hba_reset[MAX_HBAS_NO_RESET] = {
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
+module_param_array(lpfc_no_hba_reset, ulong, &lpfc_no_hba_reset_cnt, 0444);
+MODULE_PARM_DESC(lpfc_no_hba_reset, "WWPN of HBAs that should not be reset");
+
LPFC_ATTR(sli_mode, 0, 0, 3,
"SLI mode selector:"
" 0 - auto (SLI-3 if supported),"
@@ -3309,9 +3315,9 @@ LPFC_ATTR_R(nvmet_mrq_post, LPFC_DEF_MRQ_POST,
* lpfc_enable_fc4_type: Defines what FC4 types are supported.
* Supported Values: 1 - register just FCP
* 3 - register both FCP and NVME
- * Supported values are [1,3]. Default value is 3
+ * Supported values are [1,3]. Default value is 1
*/
-LPFC_ATTR_R(enable_fc4_type, LPFC_ENABLE_BOTH,
+LPFC_ATTR_R(enable_fc4_type, LPFC_ENABLE_FCP,
LPFC_ENABLE_FCP, LPFC_ENABLE_BOTH,
"Define fc4 type to register with fabric.");
@@ -4451,7 +4457,8 @@ lpfc_fcp_imax_store(struct device *dev, struct device_attribute *attr,
return -EINVAL;
phba->cfg_fcp_imax = (uint32_t)val;
- for (i = 0; i < phba->io_channel_irqs; i++)
+
+ for (i = 0; i < phba->io_channel_irqs; i += LPFC_MAX_EQ_DELAY_EQID_CNT)
lpfc_modify_hba_eq_delay(phba, i);
return strlen(buf);
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index 843dd73..54e6ac4 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -384,7 +384,7 @@ void lpfc_free_sysfs_attr(struct lpfc_vport *);
extern struct device_attribute *lpfc_hba_attrs[];
extern struct device_attribute *lpfc_vport_attrs[];
extern struct scsi_host_template lpfc_template;
-extern struct scsi_host_template lpfc_template_s3;
+extern struct scsi_host_template lpfc_template_no_hr;
extern struct scsi_host_template lpfc_template_nvme;
extern struct scsi_host_template lpfc_vport_template;
extern struct fc_function_template lpfc_transport_functions;
@@ -554,3 +554,5 @@ void lpfc_nvme_abort_fcreq_cmpl(struct lpfc_hba *phba,
struct lpfc_wcqe_complete *abts_cmpl);
extern int lpfc_enable_nvmet_cnt;
extern unsigned long long lpfc_enable_nvmet[];
+extern int lpfc_no_hba_reset_cnt;
+extern unsigned long lpfc_no_hba_reset[];
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index c22bb3f..d3e9af9 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -939,8 +939,8 @@ lpfc_cmpl_ct_cmd_gft_id(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
"FC4 x%08x, Data: x%08x x%08x\n",
ndlp, did, ndlp->nlp_fc4_type,
FC_TYPE_FCP, FC_TYPE_NVME);
+ ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE;
}
- ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE;
lpfc_nlp_set_state(vport, ndlp, NLP_STE_PRLI_ISSUE);
lpfc_issue_els_prli(vport, ndlp, 0);
} else
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index 9f4798e..913eed82 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -3653,17 +3653,6 @@ lpfc_idiag_queacc_write(struct file *file, const char __user *buf,
idiag.ptr_private = phba->sli4_hba.nvmels_cq;
goto pass_check;
}
- /* NVME LS complete queue */
- if (phba->sli4_hba.nvmels_cq &&
- phba->sli4_hba.nvmels_cq->queue_id == queid) {
- /* Sanity check */
- rc = lpfc_idiag_que_param_check(
- phba->sli4_hba.nvmels_cq, index, count);
- if (rc)
- goto error_out;
- idiag.ptr_private = phba->sli4_hba.nvmels_cq;
- goto pass_check;
- }
/* FCP complete queue */
if (phba->sli4_hba.fcp_cq) {
for (qidx = 0; qidx < phba->cfg_fcp_io_channel;
@@ -3738,17 +3727,6 @@ lpfc_idiag_queacc_write(struct file *file, const char __user *buf,
idiag.ptr_private = phba->sli4_hba.nvmels_wq;
goto pass_check;
}
- /* NVME LS work queue */
- if (phba->sli4_hba.nvmels_wq &&
- phba->sli4_hba.nvmels_wq->queue_id == queid) {
- /* Sanity check */
- rc = lpfc_idiag_que_param_check(
- phba->sli4_hba.nvmels_wq, index, count);
- if (rc)
- goto error_out;
- idiag.ptr_private = phba->sli4_hba.nvmels_wq;
- goto pass_check;
- }
/* FCP work queue */
if (phba->sli4_hba.fcp_wq) {
for (qidx = 0; qidx < phba->cfg_fcp_io_channel;
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.h b/drivers/scsi/lpfc/lpfc_debugfs.h
index c05f56c..7b7d314 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.h
+++ b/drivers/scsi/lpfc/lpfc_debugfs.h
@@ -44,14 +44,6 @@
/* hbqinfo output buffer size */
#define LPFC_HBQINFO_SIZE 8192
-enum {
- DUMP_FCP,
- DUMP_NVME,
- DUMP_MBX,
- DUMP_ELS,
- DUMP_NVMELS,
-};
-
/* nvmestat output buffer size */
#define LPFC_NVMESTAT_SIZE 8192
#define LPFC_NVMEKTIME_SIZE 8192
@@ -283,8 +275,22 @@ struct lpfc_idiag {
struct lpfc_idiag_offset offset;
void *ptr_private;
};
+
+#else
+
+#define lpfc_nvmeio_data(phba, fmt, arg...) \
+ no_printk(fmt, ##arg)
+
#endif
+enum {
+ DUMP_FCP,
+ DUMP_NVME,
+ DUMP_MBX,
+ DUMP_ELS,
+ DUMP_NVMELS,
+};
+
/* Mask for discovery_trace */
#define LPFC_DISC_TRC_ELS_CMD 0x1 /* Trace ELS commands */
#define LPFC_DISC_TRC_ELS_RSP 0x2 /* Trace ELS response */
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 2d26440..a5ca37e 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -5177,15 +5177,15 @@ lpfc_rdp_res_speed(struct fc_rdp_port_speed_desc *desc, struct lpfc_hba *phba)
static uint32_t
lpfc_rdp_res_diag_port_names(struct fc_rdp_port_name_desc *desc,
- struct lpfc_hba *phba)
+ struct lpfc_vport *vport)
{
desc->tag = cpu_to_be32(RDP_PORT_NAMES_DESC_TAG);
- memcpy(desc->port_names.wwnn, phba->wwnn,
+ memcpy(desc->port_names.wwnn, &vport->fc_nodename,
sizeof(desc->port_names.wwnn));
- memcpy(desc->port_names.wwpn, phba->wwpn,
+ memcpy(desc->port_names.wwpn, &vport->fc_portname,
sizeof(desc->port_names.wwpn));
desc->length = cpu_to_be32(sizeof(desc->port_names));
@@ -5279,7 +5279,7 @@ lpfc_els_rdp_cmpl(struct lpfc_hba *phba, struct lpfc_rdp_context *rdp_context,
len += lpfc_rdp_res_link_error((struct fc_rdp_link_error_status_desc *)
(len + pcmd), &rdp_context->link_stat);
len += lpfc_rdp_res_diag_port_names((struct fc_rdp_port_name_desc *)
- (len + pcmd), phba);
+ (len + pcmd), vport);
len += lpfc_rdp_res_attach_port_names((struct fc_rdp_port_name_desc *)
(len + pcmd), vport, ndlp);
len += lpfc_rdp_res_fec_desc((struct fc_fec_rdp_desc *)(len + pcmd),
@@ -7968,7 +7968,8 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
did, vport->port_state, ndlp->nlp_flag);
phba->fc_stat.elsRcvPRLI++;
- if (vport->port_state < LPFC_DISC_AUTH) {
+ if ((vport->port_state < LPFC_DISC_AUTH) &&
+ (vport->fc_flag & FC_FABRIC)) {
rjt_err = LSRJT_UNABLE_TPC;
rjt_exp = LSEXP_NOTHING_MORE;
break;
@@ -8371,11 +8372,17 @@ lpfc_cmpl_reg_new_vport(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
spin_lock_irq(shost->host_lock);
vport->fc_flag |= FC_VPORT_NEEDS_REG_VPI;
spin_unlock_irq(shost->host_lock);
- if (vport->port_type == LPFC_PHYSICAL_PORT
- && !(vport->fc_flag & FC_LOGO_RCVD_DID_CHNG))
- lpfc_issue_init_vfi(vport);
- else
+ if (mb->mbxStatus == MBX_NOT_FINISHED)
+ break;
+ if ((vport->port_type == LPFC_PHYSICAL_PORT) &&
+ !(vport->fc_flag & FC_LOGO_RCVD_DID_CHNG)) {
+ if (phba->sli_rev == LPFC_SLI_REV4)
+ lpfc_issue_init_vfi(vport);
+ else
+ lpfc_initial_flogi(vport);
+ } else {
lpfc_initial_fdisc(vport);
+ }
break;
}
} else {
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 194a14d..180b072b 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -313,8 +313,7 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp)
ndlp->nlp_state, ndlp->nlp_rpi);
}
- if (!(vport->load_flag & FC_UNLOADING) &&
- !(ndlp->nlp_flag & NLP_DELAY_TMO) &&
+ if (!(ndlp->nlp_flag & NLP_DELAY_TMO) &&
!(ndlp->nlp_flag & NLP_NPR_2B_DISC) &&
(ndlp->nlp_state != NLP_STE_UNMAPPED_NODE) &&
(ndlp->nlp_state != NLP_STE_REG_LOGIN_ISSUE) &&
@@ -641,6 +640,8 @@ lpfc_work_done(struct lpfc_hba *phba)
lpfc_handle_rrq_active(phba);
if (phba->hba_flag & FCP_XRI_ABORT_EVENT)
lpfc_sli4_fcp_xri_abort_event_proc(phba);
+ if (phba->hba_flag & NVME_XRI_ABORT_EVENT)
+ lpfc_sli4_nvme_xri_abort_event_proc(phba);
if (phba->hba_flag & ELS_XRI_ABORT_EVENT)
lpfc_sli4_els_xri_abort_event_proc(phba);
if (phba->hba_flag & ASYNC_EVENT)
@@ -2173,7 +2174,7 @@ lpfc_mbx_cmpl_fcf_scan_read_fcf_rec(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
uint32_t boot_flag, addr_mode;
uint16_t fcf_index, next_fcf_index;
struct lpfc_fcf_rec *fcf_rec = NULL;
- uint16_t vlan_id;
+ uint16_t vlan_id = LPFC_FCOE_NULL_VID;
bool select_new_fcf;
int rc;
@@ -4020,9 +4021,11 @@ lpfc_register_remote_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
rdata = rport->dd_data;
/* break the link before dropping the ref */
ndlp->rport = NULL;
- if (rdata && rdata->pnode == ndlp)
- lpfc_nlp_put(ndlp);
- rdata->pnode = NULL;
+ if (rdata) {
+ if (rdata->pnode == ndlp)
+ lpfc_nlp_put(ndlp);
+ rdata->pnode = NULL;
+ }
/* drop reference for earlier registeration */
put_device(&rport->dev);
}
@@ -4344,9 +4347,8 @@ lpfc_initialize_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
{
INIT_LIST_HEAD(&ndlp->els_retry_evt.evt_listp);
INIT_LIST_HEAD(&ndlp->dev_loss_evt.evt_listp);
- init_timer(&ndlp->nlp_delayfunc);
- ndlp->nlp_delayfunc.function = lpfc_els_retry_delay;
- ndlp->nlp_delayfunc.data = (unsigned long)ndlp;
+ setup_timer(&ndlp->nlp_delayfunc, lpfc_els_retry_delay,
+ (unsigned long)ndlp);
ndlp->nlp_DID = did;
ndlp->vport = vport;
ndlp->phba = vport->phba;
@@ -4606,9 +4608,9 @@ lpfc_sli4_dequeue_nport_iocbs(struct lpfc_hba *phba,
pring = qp->pring;
if (!pring)
continue;
- spin_lock_irq(&pring->ring_lock);
+ spin_lock(&pring->ring_lock);
__lpfc_dequeue_nport_iocbs(phba, ndlp, pring, dequeue_list);
- spin_unlock_irq(&pring->ring_lock);
+ spin_unlock(&pring->ring_lock);
}
spin_unlock_irq(&phba->hbalock);
}
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index cfdb068..1527770 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -1001,7 +1001,7 @@ struct eq_delay_info {
uint32_t phase;
uint32_t delay_multi;
};
-#define LPFC_MAX_EQ_DELAY 8
+#define LPFC_MAX_EQ_DELAY_EQID_CNT 8
struct sgl_page_pairs {
uint32_t sgl_pg0_addr_lo;
@@ -1070,7 +1070,7 @@ struct lpfc_mbx_modify_eq_delay {
union {
struct {
uint32_t num_eq;
- struct eq_delay_info eq[LPFC_MAX_EQ_DELAY];
+ struct eq_delay_info eq[LPFC_MAX_EQ_DELAY_EQID_CNT];
} request;
struct {
uint32_t word0;
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 0ee429d..6cc561b 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -3555,6 +3555,44 @@ lpfc_sli4_scsi_sgl_update(struct lpfc_hba *phba)
return rc;
}
+static uint64_t
+lpfc_get_wwpn(struct lpfc_hba *phba)
+{
+ uint64_t wwn;
+ int rc;
+ LPFC_MBOXQ_t *mboxq;
+ MAILBOX_t *mb;
+
+
+ mboxq = (LPFC_MBOXQ_t *) mempool_alloc(phba->mbox_mem_pool,
+ GFP_KERNEL);
+ if (!mboxq)
+ return (uint64_t)-1;
+
+ /* First get WWN of HBA instance */
+ lpfc_read_nv(phba, mboxq);
+ rc = lpfc_sli_issue_mbox(phba, mboxq, MBX_POLL);
+ if (rc != MBX_SUCCESS) {
+ lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
+ "6019 Mailbox failed , mbxCmd x%x "
+ "READ_NV, mbxStatus x%x\n",
+ bf_get(lpfc_mqe_command, &mboxq->u.mqe),
+ bf_get(lpfc_mqe_status, &mboxq->u.mqe));
+ mempool_free(mboxq, phba->mbox_mem_pool);
+ return (uint64_t) -1;
+ }
+ mb = &mboxq->u.mb;
+ memcpy(&wwn, (char *)mb->un.varRDnvp.portname, sizeof(uint64_t));
+ /* wwn is WWPN of HBA instance */
+ mempool_free(mboxq, phba->mbox_mem_pool);
+ if (phba->sli_rev == LPFC_SLI_REV4)
+ return be64_to_cpu(wwn);
+ else
+ return (((wwn & 0xffffffff00000000) >> 32) |
+ ((wwn & 0x00000000ffffffff) << 32));
+
+}
+
/**
* lpfc_sli4_nvme_sgl_update - update xri-sgl sizing and mapping
* @phba: pointer to lpfc hba data structure.
@@ -3676,17 +3714,32 @@ lpfc_create_port(struct lpfc_hba *phba, int instance, struct device *dev)
struct lpfc_vport *vport;
struct Scsi_Host *shost = NULL;
int error = 0;
+ int i;
+ uint64_t wwn;
+ bool use_no_reset_hba = false;
+
+ wwn = lpfc_get_wwpn(phba);
+
+ for (i = 0; i < lpfc_no_hba_reset_cnt; i++) {
+ if (wwn == lpfc_no_hba_reset[i]) {
+ lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
+ "6020 Setting use_no_reset port=%llx\n",
+ wwn);
+ use_no_reset_hba = true;
+ break;
+ }
+ }
if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP) {
if (dev != &phba->pcidev->dev) {
shost = scsi_host_alloc(&lpfc_vport_template,
sizeof(struct lpfc_vport));
} else {
- if (phba->sli_rev == LPFC_SLI_REV4)
+ if (!use_no_reset_hba)
shost = scsi_host_alloc(&lpfc_template,
sizeof(struct lpfc_vport));
else
- shost = scsi_host_alloc(&lpfc_template_s3,
+ shost = scsi_host_alloc(&lpfc_template_no_hr,
sizeof(struct lpfc_vport));
}
} else if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) {
@@ -3734,17 +3787,14 @@ lpfc_create_port(struct lpfc_hba *phba, int instance, struct device *dev)
INIT_LIST_HEAD(&vport->rcv_buffer_list);
spin_lock_init(&vport->work_port_lock);
- init_timer(&vport->fc_disctmo);
- vport->fc_disctmo.function = lpfc_disc_timeout;
- vport->fc_disctmo.data = (unsigned long)vport;
+ setup_timer(&vport->fc_disctmo, lpfc_disc_timeout,
+ (unsigned long)vport);
- init_timer(&vport->els_tmofunc);
- vport->els_tmofunc.function = lpfc_els_timeout;
- vport->els_tmofunc.data = (unsigned long)vport;
+ setup_timer(&vport->els_tmofunc, lpfc_els_timeout,
+ (unsigned long)vport);
- init_timer(&vport->delayed_disc_tmo);
- vport->delayed_disc_tmo.function = lpfc_delayed_disc_tmo;
- vport->delayed_disc_tmo.data = (unsigned long)vport;
+ setup_timer(&vport->delayed_disc_tmo, lpfc_delayed_disc_tmo,
+ (unsigned long)vport);
error = scsi_add_host_with_dma(shost, dev, &phba->pcidev->dev);
if (error)
@@ -5406,21 +5456,15 @@ lpfc_setup_driver_resource_phase1(struct lpfc_hba *phba)
INIT_LIST_HEAD(&phba->luns);
/* MBOX heartbeat timer */
- init_timer(&psli->mbox_tmo);
- psli->mbox_tmo.function = lpfc_mbox_timeout;
- psli->mbox_tmo.data = (unsigned long) phba;
+ setup_timer(&psli->mbox_tmo, lpfc_mbox_timeout, (unsigned long)phba);
/* Fabric block timer */
- init_timer(&phba->fabric_block_timer);
- phba->fabric_block_timer.function = lpfc_fabric_block_timeout;
- phba->fabric_block_timer.data = (unsigned long) phba;
+ setup_timer(&phba->fabric_block_timer, lpfc_fabric_block_timeout,
+ (unsigned long)phba);
/* EA polling mode timer */
- init_timer(&phba->eratt_poll);
- phba->eratt_poll.function = lpfc_poll_eratt;
- phba->eratt_poll.data = (unsigned long) phba;
+ setup_timer(&phba->eratt_poll, lpfc_poll_eratt,
+ (unsigned long)phba);
/* Heartbeat timer */
- init_timer(&phba->hb_tmofunc);
- phba->hb_tmofunc.function = lpfc_hb_timeout;
- phba->hb_tmofunc.data = (unsigned long)phba;
+ setup_timer(&phba->hb_tmofunc, lpfc_hb_timeout, (unsigned long)phba);
return 0;
}
@@ -5446,9 +5490,8 @@ lpfc_sli_driver_resource_setup(struct lpfc_hba *phba)
*/
/* FCP polling mode timer */
- init_timer(&phba->fcp_poll_timer);
- phba->fcp_poll_timer.function = lpfc_poll_timeout;
- phba->fcp_poll_timer.data = (unsigned long) phba;
+ setup_timer(&phba->fcp_poll_timer, lpfc_poll_timeout,
+ (unsigned long)phba);
/* Host attention work mask setup */
phba->work_ha_mask = (HA_ERATT | HA_MBATT | HA_LATT);
@@ -5482,7 +5525,8 @@ lpfc_sli_driver_resource_setup(struct lpfc_hba *phba)
/* Initialize the host templates the configured values. */
lpfc_vport_template.sg_tablesize = phba->cfg_sg_seg_cnt;
- lpfc_template_s3.sg_tablesize = phba->cfg_sg_seg_cnt;
+ lpfc_template_no_hr.sg_tablesize = phba->cfg_sg_seg_cnt;
+ lpfc_template.sg_tablesize = phba->cfg_sg_seg_cnt;
/* There are going to be 2 reserved BDEs: 1 FCP cmnd + 1 FCP rsp */
if (phba->cfg_enable_bg) {
@@ -5617,14 +5661,11 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
* Initialize timers used by driver
*/
- init_timer(&phba->rrq_tmr);
- phba->rrq_tmr.function = lpfc_rrq_timeout;
- phba->rrq_tmr.data = (unsigned long)phba;
+ setup_timer(&phba->rrq_tmr, lpfc_rrq_timeout, (unsigned long)phba);
/* FCF rediscover timer */
- init_timer(&phba->fcf.redisc_wait);
- phba->fcf.redisc_wait.function = lpfc_sli4_fcf_redisc_wait_tmo;
- phba->fcf.redisc_wait.data = (unsigned long)phba;
+ setup_timer(&phba->fcf.redisc_wait, lpfc_sli4_fcf_redisc_wait_tmo,
+ (unsigned long)phba);
/*
* Control structure for handling external multi-buffer mailbox
@@ -5706,6 +5747,7 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
/* Initialize the host templates with the updated values. */
lpfc_vport_template.sg_tablesize = phba->cfg_sg_seg_cnt;
lpfc_template.sg_tablesize = phba->cfg_sg_seg_cnt;
+ lpfc_template_no_hr.sg_tablesize = phba->cfg_sg_seg_cnt;
if (phba->cfg_sg_dma_buf_size <= LPFC_MIN_SG_SLI4_BUF_SZ)
phba->cfg_sg_dma_buf_size = LPFC_MIN_SG_SLI4_BUF_SZ;
@@ -5736,6 +5778,8 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
/* Initialize the Abort nvme buffer list used by driver */
spin_lock_init(&phba->sli4_hba.abts_nvme_buf_list_lock);
INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_nvme_buf_list);
+ /* Fast-path XRI aborted CQ Event work queue list */
+ INIT_LIST_HEAD(&phba->sli4_hba.sp_nvme_xri_aborted_work_queue);
}
/* This abort list used by worker thread */
@@ -5847,10 +5891,17 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
/* Check to see if it matches any module parameter */
for (i = 0; i < lpfc_enable_nvmet_cnt; i++) {
if (wwn == lpfc_enable_nvmet[i]) {
+#if (IS_ENABLED(CONFIG_NVME_TARGET_FC))
lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
"6017 NVME Target %016llx\n",
wwn);
phba->nvmet_support = 1; /* a match */
+#else
+ lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+ "6021 Can't enable NVME Target."
+ " NVME_TARGET_FC infrastructure"
+ " is not in kernel\n");
+#endif
}
}
}
@@ -8712,12 +8763,9 @@ lpfc_sli4_queue_setup(struct lpfc_hba *phba)
}
}
- /*
- * Configure EQ delay multipier for interrupt coalescing using
- * MODIFY_EQ_DELAY for all EQs created, LPFC_MAX_EQ_DELAY at a time.
- */
- for (qidx = 0; qidx < io_channel; qidx += LPFC_MAX_EQ_DELAY)
+ for (qidx = 0; qidx < io_channel; qidx += LPFC_MAX_EQ_DELAY_EQID_CNT)
lpfc_modify_hba_eq_delay(phba, qidx);
+
return 0;
out_destroy:
@@ -8973,6 +9021,11 @@ lpfc_sli4_cq_event_release_all(struct lpfc_hba *phba)
/* Pending ELS XRI abort events */
list_splice_init(&phba->sli4_hba.sp_els_xri_aborted_work_queue,
&cqelist);
+ if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) {
+ /* Pending NVME XRI abort events */
+ list_splice_init(&phba->sli4_hba.sp_nvme_xri_aborted_work_queue,
+ &cqelist);
+ }
/* Pending asynnc events */
list_splice_init(&phba->sli4_hba.sp_asynce_work_queue,
&cqelist);
@@ -10400,12 +10453,7 @@ lpfc_pci_remove_one_s3(struct pci_dev *pdev)
fc_remove_host(shost);
scsi_remove_host(shost);
- /* Perform ndlp cleanup on the physical port. The nvme and nvmet
- * localports are destroyed after to cleanup all transport memory.
- */
lpfc_cleanup(vport);
- lpfc_nvmet_destroy_targetport(phba);
- lpfc_nvme_destroy_localport(vport);
/*
* Bring down the SLI Layer. This step disable all interrupts,
@@ -12018,6 +12066,7 @@ static struct pci_driver lpfc_driver = {
.id_table = lpfc_id_table,
.probe = lpfc_pci_probe_one,
.remove = lpfc_pci_remove_one,
+ .shutdown = lpfc_pci_remove_one,
.suspend = lpfc_pci_suspend_one,
.resume = lpfc_pci_resume_one,
.err_handler = &lpfc_err_handler,
diff --git a/drivers/scsi/lpfc/lpfc_mem.c b/drivers/scsi/lpfc/lpfc_mem.c
index c61d8d6..5986c79 100644
--- a/drivers/scsi/lpfc/lpfc_mem.c
+++ b/drivers/scsi/lpfc/lpfc_mem.c
@@ -646,7 +646,6 @@ lpfc_sli4_nvmet_alloc(struct lpfc_hba *phba)
}
dma_buf->iocbq = lpfc_sli_get_iocbq(phba);
- dma_buf->iocbq->iocb_flag = LPFC_IO_NVMET;
if (!dma_buf->iocbq) {
kfree(dma_buf->context);
pci_pool_free(phba->lpfc_drb_pool, dma_buf->dbuf.virt,
@@ -658,6 +657,7 @@ lpfc_sli4_nvmet_alloc(struct lpfc_hba *phba)
"2621 Ran out of nvmet iocb/WQEs\n");
return NULL;
}
+ dma_buf->iocbq->iocb_flag = LPFC_IO_NVMET;
nvmewqe = dma_buf->iocbq;
wqe = (union lpfc_wqe128 *)&nvmewqe->wqe;
/* Initialize WQE */
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index 609a908..0024de1 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -316,7 +316,7 @@ lpfc_nvme_gen_req(struct lpfc_vport *vport, struct lpfc_dmabuf *bmp,
bf_set(wqe_dfctl, &wqe->gen_req.wge_ctl, 0);
bf_set(wqe_si, &wqe->gen_req.wge_ctl, 1);
bf_set(wqe_la, &wqe->gen_req.wge_ctl, 1);
- bf_set(wqe_rctl, &wqe->gen_req.wge_ctl, FC_RCTL_DD_UNSOL_CTL);
+ bf_set(wqe_rctl, &wqe->gen_req.wge_ctl, FC_RCTL_ELS4_REQ);
bf_set(wqe_type, &wqe->gen_req.wge_ctl, FC_TYPE_NVME);
/* Word 6 */
@@ -620,15 +620,15 @@ lpfc_nvme_adj_fcp_sgls(struct lpfc_vport *vport,
* Embed the payload in the last half of the WQE
* WQE words 16-30 get the NVME CMD IU payload
*
- * WQE Word 16 is already setup with flags
- * WQE words 17-19 get payload Words 2-4
+ * WQE words 16-19 get payload Words 1-4
* WQE words 20-21 get payload Words 6-7
* WQE words 22-29 get payload Words 16-23
*/
- wptr = &wqe->words[17]; /* WQE ptr */
+ wptr = &wqe->words[16]; /* WQE ptr */
dptr = (uint32_t *)nCmd->cmdaddr; /* payload ptr */
- dptr += 2; /* Skip Words 0-1 in payload */
+ dptr++; /* Skip Word 0 in payload */
+ *wptr++ = *dptr++; /* Word 1 */
*wptr++ = *dptr++; /* Word 2 */
*wptr++ = *dptr++; /* Word 3 */
*wptr++ = *dptr++; /* Word 4 */
@@ -978,9 +978,6 @@ lpfc_nvme_prep_io_cmd(struct lpfc_vport *vport,
bf_set(wqe_cmd_type, &wqe->generic.wqe_com,
NVME_WRITE_CMD);
- /* Word 16 */
- wqe->words[16] = LPFC_NVME_EMBED_WRITE;
-
phba->fc4NvmeOutputRequests++;
} else {
/* Word 7 */
@@ -1002,9 +999,6 @@ lpfc_nvme_prep_io_cmd(struct lpfc_vport *vport,
bf_set(wqe_cmd_type, &wqe->generic.wqe_com,
NVME_READ_CMD);
- /* Word 16 */
- wqe->words[16] = LPFC_NVME_EMBED_READ;
-
phba->fc4NvmeInputRequests++;
}
} else {
@@ -1026,9 +1020,6 @@ lpfc_nvme_prep_io_cmd(struct lpfc_vport *vport,
/* Word 11 */
bf_set(wqe_cmd_type, &wqe->generic.wqe_com, NVME_READ_CMD);
- /* Word 16 */
- wqe->words[16] = LPFC_NVME_EMBED_CMD;
-
phba->fc4NvmeControlRequests++;
}
/*
@@ -1286,6 +1277,7 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport,
pnvme_fcreq->private = (void *)lpfc_ncmd;
lpfc_ncmd->nvmeCmd = pnvme_fcreq;
lpfc_ncmd->nrport = rport;
+ lpfc_ncmd->ndlp = ndlp;
lpfc_ncmd->start_time = jiffies;
lpfc_nvme_prep_io_cmd(vport, lpfc_ncmd, ndlp);
@@ -1319,7 +1311,7 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport,
"sid: x%x did: x%x oxid: x%x\n",
ret, vport->fc_myDID, ndlp->nlp_DID,
lpfc_ncmd->cur_iocbq.sli4_xritag);
- ret = -EINVAL;
+ ret = -EBUSY;
goto out_free_nvme_buf;
}
@@ -1821,10 +1813,10 @@ lpfc_post_nvme_sgl_list(struct lpfc_hba *phba,
pdma_phys_sgl1, cur_xritag);
if (status) {
/* failure, put on abort nvme list */
- lpfc_ncmd->exch_busy = 1;
+ lpfc_ncmd->flags |= LPFC_SBUF_XBUSY;
} else {
/* success, put on NVME buffer list */
- lpfc_ncmd->exch_busy = 0;
+ lpfc_ncmd->flags &= ~LPFC_SBUF_XBUSY;
lpfc_ncmd->status = IOSTAT_SUCCESS;
num_posted++;
}
@@ -1854,10 +1846,10 @@ lpfc_post_nvme_sgl_list(struct lpfc_hba *phba,
struct lpfc_nvme_buf, list);
if (status) {
/* failure, put on abort nvme list */
- lpfc_ncmd->exch_busy = 1;
+ lpfc_ncmd->flags |= LPFC_SBUF_XBUSY;
} else {
/* success, put on NVME buffer list */
- lpfc_ncmd->exch_busy = 0;
+ lpfc_ncmd->flags &= ~LPFC_SBUF_XBUSY;
lpfc_ncmd->status = IOSTAT_SUCCESS;
num_posted++;
}
@@ -2099,7 +2091,7 @@ lpfc_release_nvme_buf(struct lpfc_hba *phba, struct lpfc_nvme_buf *lpfc_ncmd)
unsigned long iflag = 0;
lpfc_ncmd->nonsg_phys = 0;
- if (lpfc_ncmd->exch_busy) {
+ if (lpfc_ncmd->flags & LPFC_SBUF_XBUSY) {
spin_lock_irqsave(&phba->sli4_hba.abts_nvme_buf_list_lock,
iflag);
lpfc_ncmd->nvmeCmd = NULL;
@@ -2135,11 +2127,12 @@ lpfc_release_nvme_buf(struct lpfc_hba *phba, struct lpfc_nvme_buf *lpfc_ncmd)
int
lpfc_nvme_create_localport(struct lpfc_vport *vport)
{
+ int ret = 0;
struct lpfc_hba *phba = vport->phba;
struct nvme_fc_port_info nfcp_info;
struct nvme_fc_local_port *localport;
struct lpfc_nvme_lport *lport;
- int len, ret = 0;
+ int len;
/* Initialize this localport instance. The vport wwn usage ensures
* that NPIV is accounted for.
@@ -2156,8 +2149,12 @@ lpfc_nvme_create_localport(struct lpfc_vport *vport)
/* localport is allocated from the stack, but the registration
* call allocates heap memory as well as the private area.
*/
+#if (IS_ENABLED(CONFIG_NVME_FC))
ret = nvme_fc_register_localport(&nfcp_info, &lpfc_nvme_template,
&vport->phba->pcidev->dev, &localport);
+#else
+ ret = -ENOMEM;
+#endif
if (!ret) {
lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME | LOG_NVME_DISC,
"6005 Successfully registered local "
@@ -2173,10 +2170,10 @@ lpfc_nvme_create_localport(struct lpfc_vport *vport)
lport->vport = vport;
INIT_LIST_HEAD(&lport->rport_list);
vport->nvmei_support = 1;
+ len = lpfc_new_nvme_buf(vport, phba->sli4_hba.nvme_xri_max);
+ vport->phba->total_nvme_bufs += len;
}
- len = lpfc_new_nvme_buf(vport, phba->sli4_hba.nvme_xri_max);
- vport->phba->total_nvme_bufs += len;
return ret;
}
@@ -2193,6 +2190,7 @@ lpfc_nvme_create_localport(struct lpfc_vport *vport)
void
lpfc_nvme_destroy_localport(struct lpfc_vport *vport)
{
+#if (IS_ENABLED(CONFIG_NVME_FC))
struct nvme_fc_local_port *localport;
struct lpfc_nvme_lport *lport;
struct lpfc_nvme_rport *rport = NULL, *rport_next = NULL;
@@ -2208,7 +2206,6 @@ lpfc_nvme_destroy_localport(struct lpfc_vport *vport)
lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME,
"6011 Destroying NVME localport %p\n",
localport);
-
list_for_each_entry_safe(rport, rport_next, &lport->rport_list, list) {
/* The last node ref has to get released now before the rport
* private memory area is released by the transport.
@@ -2222,6 +2219,7 @@ lpfc_nvme_destroy_localport(struct lpfc_vport *vport)
"6008 rport fail destroy %x\n", ret);
wait_for_completion_timeout(&rport->rport_unreg_done, 5);
}
+
/* lport's rport list is clear. Unregister
* lport and release resources.
*/
@@ -2245,6 +2243,7 @@ lpfc_nvme_destroy_localport(struct lpfc_vport *vport)
"Failed, status x%x\n",
ret);
}
+#endif
}
void
@@ -2275,6 +2274,7 @@ lpfc_nvme_update_localport(struct lpfc_vport *vport)
int
lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
{
+#if (IS_ENABLED(CONFIG_NVME_FC))
int ret = 0;
struct nvme_fc_local_port *localport;
struct lpfc_nvme_lport *lport;
@@ -2348,7 +2348,6 @@ lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
rpinfo.port_role |= FC_PORT_ROLE_NVME_INITIATOR;
rpinfo.port_name = wwn_to_u64(ndlp->nlp_portname.u.wwn);
rpinfo.node_name = wwn_to_u64(ndlp->nlp_nodename.u.wwn);
-
ret = nvme_fc_register_remoteport(localport, &rpinfo,
&remote_port);
if (!ret) {
@@ -2384,6 +2383,9 @@ lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
ndlp->nlp_type, ndlp->nlp_DID, ndlp);
}
return ret;
+#else
+ return 0;
+#endif
}
/* lpfc_nvme_unregister_port - unbind the DID and port_role from this rport.
@@ -2401,6 +2403,7 @@ lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
void
lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
{
+#if (IS_ENABLED(CONFIG_NVME_FC))
int ret;
struct nvme_fc_local_port *localport;
struct lpfc_nvme_lport *lport;
@@ -2458,7 +2461,61 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
return;
input_err:
+#endif
lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC,
"6168: State error: lport %p, rport%p FCID x%06x\n",
vport->localport, ndlp->rport, ndlp->nlp_DID);
}
+
+/**
+ * lpfc_sli4_nvme_xri_aborted - Fast-path process of NVME xri abort
+ * @phba: pointer to lpfc hba data structure.
+ * @axri: pointer to the fcp xri abort wcqe structure.
+ *
+ * This routine is invoked by the worker thread to process a SLI4 fast-path
+ * FCP aborted xri.
+ **/
+void
+lpfc_sli4_nvme_xri_aborted(struct lpfc_hba *phba,
+ struct sli4_wcqe_xri_aborted *axri)
+{
+ uint16_t xri = bf_get(lpfc_wcqe_xa_xri, axri);
+ uint16_t rxid = bf_get(lpfc_wcqe_xa_remote_xid, axri);
+ struct lpfc_nvme_buf *lpfc_ncmd, *next_lpfc_ncmd;
+ struct lpfc_nodelist *ndlp;
+ unsigned long iflag = 0;
+ int rrq_empty = 0;
+
+ if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME))
+ return;
+ spin_lock_irqsave(&phba->hbalock, iflag);
+ spin_lock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+ list_for_each_entry_safe(lpfc_ncmd, next_lpfc_ncmd,
+ &phba->sli4_hba.lpfc_abts_nvme_buf_list,
+ list) {
+ if (lpfc_ncmd->cur_iocbq.sli4_xritag == xri) {
+ list_del(&lpfc_ncmd->list);
+ lpfc_ncmd->flags &= ~LPFC_SBUF_XBUSY;
+ lpfc_ncmd->status = IOSTAT_SUCCESS;
+ spin_unlock(
+ &phba->sli4_hba.abts_nvme_buf_list_lock);
+
+ rrq_empty = list_empty(&phba->active_rrq_list);
+ spin_unlock_irqrestore(&phba->hbalock, iflag);
+ ndlp = lpfc_ncmd->ndlp;
+ if (ndlp) {
+ lpfc_set_rrq_active(
+ phba, ndlp,
+ lpfc_ncmd->cur_iocbq.sli4_lxritag,
+ rxid, 1);
+ lpfc_sli4_abts_err_handler(phba, ndlp, axri);
+ }
+ lpfc_release_nvme_buf(phba, lpfc_ncmd);
+ if (rrq_empty)
+ lpfc_worker_wake_up(phba);
+ return;
+ }
+ }
+ spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+ spin_unlock_irqrestore(&phba->hbalock, iflag);
+}
diff --git a/drivers/scsi/lpfc/lpfc_nvme.h b/drivers/scsi/lpfc/lpfc_nvme.h
index b2fae5e..1347deb 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.h
+++ b/drivers/scsi/lpfc/lpfc_nvme.h
@@ -57,6 +57,7 @@ struct lpfc_nvme_buf {
struct list_head list;
struct nvmefc_fcp_req *nvmeCmd;
struct lpfc_nvme_rport *nrport;
+ struct lpfc_nodelist *ndlp;
uint32_t timeout;
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index c421e17..acba1b6 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -520,7 +520,7 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport,
struct lpfc_hba *phba = ctxp->phba;
struct lpfc_iocbq *nvmewqeq;
unsigned long iflags;
- int rc, id;
+ int rc;
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
if (phba->ktime_on) {
@@ -530,7 +530,7 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport,
ctxp->ts_nvme_data = ktime_get_ns();
}
if (phba->cpucheck_on & LPFC_CHECK_NVMET_IO) {
- id = smp_processor_id();
+ int id = smp_processor_id();
ctxp->cpu = id;
if (id < LPFC_CHECK_CPU_CNT)
phba->cpucheck_xmt_io[id]++;
@@ -571,6 +571,7 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport,
lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
"6102 Bad state IO x%x aborted\n",
ctxp->oxid);
+ rc = -ENXIO;
goto aerr;
}
@@ -580,6 +581,7 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport,
lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
"6152 FCP Drop IO x%x: Prep\n",
ctxp->oxid);
+ rc = -ENXIO;
goto aerr;
}
@@ -618,8 +620,9 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport,
ctxp->wqeq->hba_wqidx = 0;
nvmewqeq->context2 = NULL;
nvmewqeq->context3 = NULL;
+ rc = -EBUSY;
aerr:
- return -ENXIO;
+ return rc;
}
static void
@@ -668,9 +671,13 @@ lpfc_nvmet_create_targetport(struct lpfc_hba *phba)
lpfc_tgttemplate.target_features = NVMET_FCTGTFEAT_READDATA_RSP |
NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED;
+#if (IS_ENABLED(CONFIG_NVME_TARGET_FC))
error = nvmet_fc_register_targetport(&pinfo, &lpfc_tgttemplate,
&phba->pcidev->dev,
&phba->targetport);
+#else
+ error = -ENOMEM;
+#endif
if (error) {
lpfc_printf_log(phba, KERN_ERR, LOG_NVME_DISC,
"6025 Cannot register NVME targetport "
@@ -731,9 +738,25 @@ lpfc_nvmet_update_targetport(struct lpfc_hba *phba)
return 0;
}
+/**
+ * lpfc_sli4_nvmet_xri_aborted - Fast-path process of nvmet xri abort
+ * @phba: pointer to lpfc hba data structure.
+ * @axri: pointer to the nvmet xri abort wcqe structure.
+ *
+ * This routine is invoked by the worker thread to process a SLI4 fast-path
+ * NVMET aborted xri.
+ **/
+void
+lpfc_sli4_nvmet_xri_aborted(struct lpfc_hba *phba,
+ struct sli4_wcqe_xri_aborted *axri)
+{
+ /* TODO: work in progress */
+}
+
void
lpfc_nvmet_destroy_targetport(struct lpfc_hba *phba)
{
+#if (IS_ENABLED(CONFIG_NVME_TARGET_FC))
struct lpfc_nvmet_tgtport *tgtp;
if (phba->nvmet_support == 0)
@@ -745,6 +768,7 @@ lpfc_nvmet_destroy_targetport(struct lpfc_hba *phba)
wait_for_completion_timeout(&tgtp->tport_unreg_done, 5);
}
phba->targetport = NULL;
+#endif
}
/**
@@ -764,6 +788,7 @@ static void
lpfc_nvmet_unsol_ls_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
struct hbq_dmabuf *nvmebuf)
{
+#if (IS_ENABLED(CONFIG_NVME_TARGET_FC))
struct lpfc_nvmet_tgtport *tgtp;
struct fc_frame_header *fc_hdr;
struct lpfc_nvmet_rcv_ctx *ctxp;
@@ -844,6 +869,7 @@ lpfc_nvmet_unsol_ls_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
atomic_inc(&tgtp->xmt_ls_abort);
lpfc_nvmet_unsol_ls_issue_abort(phba, ctxp, sid, oxid);
+#endif
}
/**
@@ -865,6 +891,7 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba,
struct rqb_dmabuf *nvmebuf,
uint64_t isr_timestamp)
{
+#if (IS_ENABLED(CONFIG_NVME_TARGET_FC))
struct lpfc_nvmet_rcv_ctx *ctxp;
struct lpfc_nvmet_tgtport *tgtp;
struct fc_frame_header *fc_hdr;
@@ -955,7 +982,7 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba,
atomic_inc(&tgtp->rcv_fcp_cmd_drop);
lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
- "6159 FCP Drop IO x%x: nvmet_fc_rcv_fcp_req x%x\n",
+ "6159 FCP Drop IO x%x: err x%x\n",
ctxp->oxid, rc);
dropit:
lpfc_nvmeio_data(phba, "NVMET FCP DROP: xri x%x sz %d from %06x\n",
@@ -970,6 +997,7 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba,
/* We assume a rcv'ed cmd ALWAYs fits into 1 buffer */
lpfc_nvmet_rq_post(phba, NULL, &nvmebuf->hbuf);
}
+#endif
}
/**
@@ -1114,7 +1142,7 @@ lpfc_nvmet_prep_ls_wqe(struct lpfc_hba *phba,
bf_set(wqe_dfctl, &wqe->xmit_sequence.wge_ctl, 0);
bf_set(wqe_ls, &wqe->xmit_sequence.wge_ctl, 1);
bf_set(wqe_la, &wqe->xmit_sequence.wge_ctl, 0);
- bf_set(wqe_rctl, &wqe->xmit_sequence.wge_ctl, FC_RCTL_DD_SOL_CTL);
+ bf_set(wqe_rctl, &wqe->xmit_sequence.wge_ctl, FC_RCTL_ELS4_REP);
bf_set(wqe_type, &wqe->xmit_sequence.wge_ctl, FC_TYPE_NVME);
/* Word 6 */
@@ -1445,7 +1473,6 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
case NVMET_FCOP_RSP:
/* Words 0 - 2 */
- sgel = &rsp->sg[0];
physaddr = rsp->rspdma;
wqe->fcp_trsp.bde.tus.f.bdeFlags = BUFF_TYPE_BDE_64;
wqe->fcp_trsp.bde.tus.f.bdeSize = rsp->rsplen;
@@ -1681,8 +1708,8 @@ lpfc_nvmet_unsol_issue_abort(struct lpfc_hba *phba,
struct lpfc_nodelist *ndlp;
lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
- "6067 %s: Entrypoint: sid %x xri %x\n", __func__,
- sid, xri);
+ "6067 Abort: sid %x xri x%x/x%x\n",
+ sid, xri, ctxp->wqeq->sli4_xritag);
tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
@@ -1693,7 +1720,7 @@ lpfc_nvmet_unsol_issue_abort(struct lpfc_hba *phba,
atomic_inc(&tgtp->xmt_abort_rsp_error);
lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
"6134 Drop ABTS - wrong NDLP state x%x.\n",
- ndlp->nlp_state);
+ (ndlp) ? ndlp->nlp_state : NLP_STE_MAX_STATE);
/* No failure to an ABTS request. */
return 0;
@@ -1791,7 +1818,7 @@ lpfc_nvmet_sol_fcp_issue_abort(struct lpfc_hba *phba,
atomic_inc(&tgtp->xmt_abort_rsp_error);
lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
"6160 Drop ABTS - wrong NDLP state x%x.\n",
- ndlp->nlp_state);
+ (ndlp) ? ndlp->nlp_state : NLP_STE_MAX_STATE);
/* No failure to an ABTS request. */
return 0;
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 9d6384a..54fd0c8 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -5953,12 +5953,13 @@ struct scsi_host_template lpfc_template_nvme = {
.track_queue_depth = 0,
};
-struct scsi_host_template lpfc_template_s3 = {
+struct scsi_host_template lpfc_template_no_hr = {
.module = THIS_MODULE,
.name = LPFC_DRIVER_NAME,
.proc_name = LPFC_DRIVER_NAME,
.info = lpfc_info,
.queuecommand = lpfc_queuecommand,
+ .eh_timed_out = fc_eh_timed_out,
.eh_abort_handler = lpfc_abort_handler,
.eh_device_reset_handler = lpfc_device_reset_handler,
.eh_target_reset_handler = lpfc_target_reset_handler,
@@ -6015,7 +6016,6 @@ struct scsi_host_template lpfc_vport_template = {
.eh_abort_handler = lpfc_abort_handler,
.eh_device_reset_handler = lpfc_device_reset_handler,
.eh_target_reset_handler = lpfc_target_reset_handler,
- .eh_bus_reset_handler = lpfc_bus_reset_handler,
.slave_alloc = lpfc_slave_alloc,
.slave_configure = lpfc_slave_configure,
.slave_destroy = lpfc_slave_destroy,
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index e43e5e2..1c9fa45 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -1,3 +1,4 @@
+
/*******************************************************************
* This file is part of the Emulex Linux Device Driver for *
* Fibre Channel Host Bus Adapters. *
@@ -952,7 +953,7 @@ __lpfc_sli_get_els_sglq(struct lpfc_hba *phba, struct lpfc_iocbq *piocbq)
start_sglq = sglq;
while (!found) {
if (!sglq)
- return NULL;
+ break;
if (ndlp && ndlp->active_rrqs_xri_bitmap &&
test_bit(sglq->sli4_lxritag,
ndlp->active_rrqs_xri_bitmap)) {
@@ -12213,6 +12214,41 @@ void lpfc_sli4_fcp_xri_abort_event_proc(struct lpfc_hba *phba)
}
/**
+ * lpfc_sli4_nvme_xri_abort_event_proc - Process nvme xri abort event
+ * @phba: pointer to lpfc hba data structure.
+ *
+ * This routine is invoked by the worker thread to process all the pending
+ * SLI4 NVME abort XRI events.
+ **/
+void lpfc_sli4_nvme_xri_abort_event_proc(struct lpfc_hba *phba)
+{
+ struct lpfc_cq_event *cq_event;
+
+ /* First, declare the fcp xri abort event has been handled */
+ spin_lock_irq(&phba->hbalock);
+ phba->hba_flag &= ~NVME_XRI_ABORT_EVENT;
+ spin_unlock_irq(&phba->hbalock);
+ /* Now, handle all the fcp xri abort events */
+ while (!list_empty(&phba->sli4_hba.sp_nvme_xri_aborted_work_queue)) {
+ /* Get the first event from the head of the event queue */
+ spin_lock_irq(&phba->hbalock);
+ list_remove_head(&phba->sli4_hba.sp_nvme_xri_aborted_work_queue,
+ cq_event, struct lpfc_cq_event, list);
+ spin_unlock_irq(&phba->hbalock);
+ /* Notify aborted XRI for NVME work queue */
+ if (phba->nvmet_support) {
+ lpfc_sli4_nvmet_xri_aborted(phba,
+ &cq_event->cqe.wcqe_axri);
+ } else {
+ lpfc_sli4_nvme_xri_aborted(phba,
+ &cq_event->cqe.wcqe_axri);
+ }
+ /* Free the event processed back to the free pool */
+ lpfc_sli4_cq_event_release(phba, cq_event);
+ }
+}
+
+/**
* lpfc_sli4_els_xri_abort_event_proc - Process els xri abort event
* @phba: pointer to lpfc hba data structure.
*
@@ -12709,10 +12745,22 @@ lpfc_sli4_sp_handle_abort_xri_wcqe(struct lpfc_hba *phba,
spin_unlock_irqrestore(&phba->hbalock, iflags);
workposted = true;
break;
+ case LPFC_NVME:
+ spin_lock_irqsave(&phba->hbalock, iflags);
+ list_add_tail(&cq_event->list,
+ &phba->sli4_hba.sp_nvme_xri_aborted_work_queue);
+ /* Set the nvme xri abort event flag */
+ phba->hba_flag |= NVME_XRI_ABORT_EVENT;
+ spin_unlock_irqrestore(&phba->hbalock, iflags);
+ workposted = true;
+ break;
default:
lpfc_printf_log(phba, KERN_ERR, LOG_SLI,
- "0603 Invalid work queue CQE subtype (x%x)\n",
- cq->subtype);
+ "0603 Invalid CQ subtype %d: "
+ "%08x %08x %08x %08x\n",
+ cq->subtype, wcqe->word0, wcqe->parameter,
+ wcqe->word2, wcqe->word3);
+ lpfc_sli4_cq_event_release(phba, cq_event);
workposted = false;
break;
}
@@ -13827,6 +13875,8 @@ lpfc_dual_chute_pci_bar_map(struct lpfc_hba *phba, uint16_t pci_barset)
* @startq: The starting FCP EQ to modify
*
* This function sends an MODIFY_EQ_DELAY mailbox command to the HBA.
+ * The command allows up to LPFC_MAX_EQ_DELAY_EQID_CNT EQ ID's to be
+ * updated in one mailbox command.
*
* The @phba struct is used to send mailbox command to HBA. The @startq
* is used to get the starting FCP EQ to change.
@@ -13879,7 +13929,7 @@ lpfc_modify_hba_eq_delay(struct lpfc_hba *phba, uint32_t startq)
eq_delay->u.request.eq[cnt].phase = 0;
eq_delay->u.request.eq[cnt].delay_multi = dmult;
cnt++;
- if (cnt >= LPFC_MAX_EQ_DELAY)
+ if (cnt >= LPFC_MAX_EQ_DELAY_EQID_CNT)
break;
}
eq_delay->u.request.num_eq = cnt;
@@ -15185,17 +15235,17 @@ lpfc_mrq_create(struct lpfc_hba *phba, struct lpfc_queue **hrqp,
drq = drqp[idx];
cq = cqp[idx];
- if (hrq->entry_count != drq->entry_count) {
- status = -EINVAL;
- goto out;
- }
-
/* sanity check on queue memory */
if (!hrq || !drq || !cq) {
status = -ENODEV;
goto out;
}
+ if (hrq->entry_count != drq->entry_count) {
+ status = -EINVAL;
+ goto out;
+ }
+
if (idx == 0) {
bf_set(lpfc_mbx_rq_create_num_pages,
&rq_create->u.request,
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index 91153c9..710458c 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -642,6 +642,7 @@ struct lpfc_sli4_hba {
struct list_head sp_asynce_work_queue;
struct list_head sp_fcp_xri_aborted_work_queue;
struct list_head sp_els_xri_aborted_work_queue;
+ struct list_head sp_nvme_xri_aborted_work_queue;
struct list_head sp_unsol_work_queue;
struct lpfc_sli4_link link_state;
struct lpfc_sli4_lnk_info lnk_info;
@@ -794,9 +795,14 @@ void lpfc_sli4_fcf_redisc_event_proc(struct lpfc_hba *);
int lpfc_sli4_resume_rpi(struct lpfc_nodelist *,
void (*)(struct lpfc_hba *, LPFC_MBOXQ_t *), void *);
void lpfc_sli4_fcp_xri_abort_event_proc(struct lpfc_hba *);
+void lpfc_sli4_nvme_xri_abort_event_proc(struct lpfc_hba *phba);
void lpfc_sli4_els_xri_abort_event_proc(struct lpfc_hba *);
void lpfc_sli4_fcp_xri_aborted(struct lpfc_hba *,
struct sli4_wcqe_xri_aborted *);
+void lpfc_sli4_nvme_xri_aborted(struct lpfc_hba *phba,
+ struct sli4_wcqe_xri_aborted *axri);
+void lpfc_sli4_nvmet_xri_aborted(struct lpfc_hba *phba,
+ struct sli4_wcqe_xri_aborted *axri);
void lpfc_sli4_els_xri_aborted(struct lpfc_hba *,
struct sli4_wcqe_xri_aborted *);
void lpfc_sli4_vport_delete_els_xri_aborted(struct lpfc_vport *);
diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index 86c6c9b..d4e95e2 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -20,7 +20,7 @@
* included with this package. *
*******************************************************************/
-#define LPFC_DRIVER_VERSION "11.2.0.7"
+#define LPFC_DRIVER_VERSION "11.2.0.10"
#define LPFC_DRIVER_NAME "lpfc"
/* Used for SLI 2/3 */
diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index e7e5974..2b209bb 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -35,8 +35,8 @@
/*
* MegaRAID SAS Driver meta data
*/
-#define MEGASAS_VERSION "07.701.16.00-rc1"
-#define MEGASAS_RELDATE "February 2, 2017"
+#define MEGASAS_VERSION "07.701.17.00-rc1"
+#define MEGASAS_RELDATE "March 2, 2017"
/*
* Device IDs
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 7ac9a9e..0016f12c 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -1963,6 +1963,9 @@ static int megasas_slave_alloc(struct scsi_device *sdev)
if (!mr_device_priv_data)
return -ENOMEM;
sdev->hostdata = mr_device_priv_data;
+
+ atomic_set(&mr_device_priv_data->r1_ldio_hint,
+ instance->r1_ldio_hint_default);
return 0;
}
@@ -5034,10 +5037,12 @@ megasas_setup_irqs_msix(struct megasas_instance *instance, u8 is_probe)
&instance->irq_context[j]);
/* Retry irq register for IO_APIC*/
instance->msix_vectors = 0;
- if (is_probe)
+ if (is_probe) {
+ pci_free_irq_vectors(instance->pdev);
return megasas_setup_irqs_ioapic(instance);
- else
+ } else {
return -1;
+ }
}
}
return 0;
@@ -5277,9 +5282,11 @@ static int megasas_init_fw(struct megasas_instance *instance)
MPI2_REPLY_POST_HOST_INDEX_OFFSET);
}
- i = pci_alloc_irq_vectors(instance->pdev, 1, 1, PCI_IRQ_LEGACY);
- if (i < 0)
- goto fail_setup_irqs;
+ if (!instance->msix_vectors) {
+ i = pci_alloc_irq_vectors(instance->pdev, 1, 1, PCI_IRQ_LEGACY);
+ if (i < 0)
+ goto fail_setup_irqs;
+ }
dev_info(&instance->pdev->dev,
"firmware supports msix\t: (%d)", fw_msix_count);
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 29650ba..f990ab4d 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -2159,7 +2159,7 @@ megasas_set_raidflag_cpu_affinity(union RAID_CONTEXT_UNION *praid_context,
cpu_sel = MR_RAID_CTX_CPUSEL_1;
if (is_stream_detected(rctx_g35) &&
- (raid->level == 5) &&
+ ((raid->level == 5) || (raid->level == 6)) &&
(raid->writeMode == MR_RL_WRITE_THROUGH_MODE) &&
(cpu_sel == MR_RAID_CTX_CPUSEL_FCFS))
cpu_sel = MR_RAID_CTX_CPUSEL_0;
@@ -2338,7 +2338,7 @@ megasas_build_ldio_fusion(struct megasas_instance *instance,
fp_possible = false;
atomic_dec(&instance->fw_outstanding);
} else if ((scsi_buff_len > MR_LARGE_IO_MIN_SIZE) ||
- atomic_dec_if_positive(&mrdev_priv->r1_ldio_hint)) {
+ (atomic_dec_if_positive(&mrdev_priv->r1_ldio_hint) > 0)) {
fp_possible = false;
atomic_dec(&instance->fw_outstanding);
if (scsi_buff_len > MR_LARGE_IO_MIN_SIZE)
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index 7fe7e6e..8981806f 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -1442,9 +1442,6 @@ void mpt3sas_transport_update_links(struct MPT3SAS_ADAPTER *ioc,
u64 sas_address, u16 handle, u8 phy_number, u8 link_rate);
extern struct sas_function_template mpt3sas_transport_functions;
extern struct scsi_transport_template *mpt3sas_transport_template;
-extern int scsi_internal_device_block(struct scsi_device *sdev);
-extern int scsi_internal_device_unblock(struct scsi_device *sdev,
- enum scsi_device_state new_state);
/* trigger data externs */
void mpt3sas_send_trigger_data_event(struct MPT3SAS_ADAPTER *ioc,
struct SL_WH_TRIGGERS_EVENT_DATA_T *event_data);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 46e866c..919ba2b 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -2859,7 +2859,7 @@ _scsih_internal_device_block(struct scsi_device *sdev,
sas_device_priv_data->sas_target->handle);
sas_device_priv_data->block = 1;
- r = scsi_internal_device_block(sdev);
+ r = scsi_internal_device_block(sdev, false);
if (r == -EINVAL)
sdev_printk(KERN_WARNING, sdev,
"device_block failed with return(%d) for handle(0x%04x)\n",
@@ -2895,7 +2895,7 @@ _scsih_internal_device_unblock(struct scsi_device *sdev,
"performing a block followed by an unblock\n",
r, sas_device_priv_data->sas_target->handle);
sas_device_priv_data->block = 1;
- r = scsi_internal_device_block(sdev);
+ r = scsi_internal_device_block(sdev, false);
if (r)
sdev_printk(KERN_WARNING, sdev, "retried device_block "
"failed with return(%d) for handle(0x%04x)\n",
@@ -4677,7 +4677,6 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
struct MPT3SAS_DEVICE *sas_device_priv_data;
u32 response_code = 0;
unsigned long flags;
- unsigned int sector_sz;
mpi_reply = mpt3sas_base_get_reply_virt_addr(ioc, reply);
@@ -4742,20 +4741,6 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
}
xfer_cnt = le32_to_cpu(mpi_reply->TransferCount);
-
- /* In case of bogus fw or device, we could end up having
- * unaligned partial completion. We can force alignment here,
- * then scsi-ml does not need to handle this misbehavior.
- */
- sector_sz = scmd->device->sector_size;
- if (unlikely(!blk_rq_is_passthrough(scmd->request) && sector_sz &&
- xfer_cnt % sector_sz)) {
- sdev_printk(KERN_INFO, scmd->device,
- "unaligned partial completion avoided (xfer_cnt=%u, sector_sz=%u)\n",
- xfer_cnt, sector_sz);
- xfer_cnt = round_down(xfer_cnt, sector_sz);
- }
-
scsi_set_resid(scmd, scsi_bufflen(scmd) - xfer_cnt);
if (ioc_status & MPI2_IOCSTATUS_FLAG_LOG_INFO_AVAILABLE)
log_info = le32_to_cpu(mpi_reply->IOCLogInfo);
diff --git a/drivers/scsi/qedf/Makefile b/drivers/scsi/qedf/Makefile
index 64e9f50..414f2a7 100644
--- a/drivers/scsi/qedf/Makefile
+++ b/drivers/scsi/qedf/Makefile
@@ -1,5 +1,5 @@
obj-$(CONFIG_QEDF) := qedf.o
qedf-y = qedf_dbg.o qedf_main.o qedf_io.o qedf_fip.o \
- qedf_attr.o qedf_els.o
+ qedf_attr.o qedf_els.o drv_scsi_fw_funcs.o drv_fcoe_fw_funcs.o
qedf-$(CONFIG_DEBUG_FS) += qedf_debugfs.o
diff --git a/drivers/scsi/qedf/drv_fcoe_fw_funcs.c b/drivers/scsi/qedf/drv_fcoe_fw_funcs.c
new file mode 100644
index 0000000..8c65e3b
--- /dev/null
+++ b/drivers/scsi/qedf/drv_fcoe_fw_funcs.c
@@ -0,0 +1,190 @@
+/* QLogic FCoE Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+#include "drv_fcoe_fw_funcs.h"
+#include "drv_scsi_fw_funcs.h"
+
+#define FCOE_RX_ID (0xFFFFu)
+
+static inline void init_common_sqe(struct fcoe_task_params *task_params,
+ enum fcoe_sqe_request_type request_type)
+{
+ memset(task_params->sqe, 0, sizeof(*(task_params->sqe)));
+ SET_FIELD(task_params->sqe->flags, FCOE_WQE_REQ_TYPE,
+ request_type);
+ task_params->sqe->task_id = task_params->itid;
+}
+
+int init_initiator_rw_fcoe_task(struct fcoe_task_params *task_params,
+ struct scsi_sgl_task_params *sgl_task_params,
+ struct regpair sense_data_buffer_phys_addr,
+ u32 task_retry_id,
+ u8 fcp_cmd_payload[32])
+{
+ struct fcoe_task_context *ctx = task_params->context;
+ struct ystorm_fcoe_task_st_ctx *y_st_ctx;
+ struct tstorm_fcoe_task_st_ctx *t_st_ctx;
+ struct ustorm_fcoe_task_ag_ctx *u_ag_ctx;
+ struct mstorm_fcoe_task_st_ctx *m_st_ctx;
+ u32 io_size, val;
+ bool slow_sgl;
+
+ memset(ctx, 0, sizeof(*(ctx)));
+ slow_sgl = scsi_is_slow_sgl(sgl_task_params->num_sges,
+ sgl_task_params->small_mid_sge);
+ io_size = (task_params->task_type == FCOE_TASK_TYPE_WRITE_INITIATOR ?
+ task_params->tx_io_size : task_params->rx_io_size);
+
+ /* Ystorm ctx */
+ y_st_ctx = &ctx->ystorm_st_context;
+ y_st_ctx->data_2_trns_rem = cpu_to_le32(io_size);
+ y_st_ctx->task_rety_identifier = cpu_to_le32(task_retry_id);
+ y_st_ctx->task_type = task_params->task_type;
+ memcpy(&y_st_ctx->tx_info_union.fcp_cmd_payload,
+ fcp_cmd_payload, sizeof(struct fcoe_fcp_cmd_payload));
+
+ /* Tstorm ctx */
+ t_st_ctx = &ctx->tstorm_st_context;
+ t_st_ctx->read_only.dev_type = (task_params->is_tape_device == 1 ?
+ FCOE_TASK_DEV_TYPE_TAPE :
+ FCOE_TASK_DEV_TYPE_DISK);
+ t_st_ctx->read_only.cid = cpu_to_le32(task_params->conn_cid);
+ val = cpu_to_le32(task_params->cq_rss_number);
+ t_st_ctx->read_only.glbl_q_num = val;
+ t_st_ctx->read_only.fcp_cmd_trns_size = cpu_to_le32(io_size);
+ t_st_ctx->read_only.task_type = task_params->task_type;
+ SET_FIELD(t_st_ctx->read_write.flags,
+ FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME, 1);
+ t_st_ctx->read_write.rx_id = cpu_to_le16(FCOE_RX_ID);
+
+ /* Ustorm ctx */
+ u_ag_ctx = &ctx->ustorm_ag_context;
+ u_ag_ctx->global_cq_num = cpu_to_le32(task_params->cq_rss_number);
+
+ /* Mstorm buffer for sense/rsp data placement */
+ m_st_ctx = &ctx->mstorm_st_context;
+ val = cpu_to_le32(sense_data_buffer_phys_addr.hi);
+ m_st_ctx->rsp_buf_addr.hi = val;
+ val = cpu_to_le32(sense_data_buffer_phys_addr.lo);
+ m_st_ctx->rsp_buf_addr.lo = val;
+
+ if (task_params->task_type == FCOE_TASK_TYPE_WRITE_INITIATOR) {
+ /* Ystorm ctx */
+ y_st_ctx->expect_first_xfer = 1;
+
+ /* Set the amount of super SGEs. Can be up to 4. */
+ SET_FIELD(y_st_ctx->sgl_mode,
+ YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE,
+ (slow_sgl ? SCSI_TX_SLOW_SGL : SCSI_FAST_SGL));
+ init_scsi_sgl_context(&y_st_ctx->sgl_params,
+ &y_st_ctx->data_desc,
+ sgl_task_params);
+
+ /* Mstorm ctx */
+ SET_FIELD(m_st_ctx->flags,
+ MSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE,
+ (slow_sgl ? SCSI_TX_SLOW_SGL : SCSI_FAST_SGL));
+ } else {
+ /* Tstorm ctx */
+ SET_FIELD(t_st_ctx->read_write.flags,
+ FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE,
+ (slow_sgl ? SCSI_TX_SLOW_SGL : SCSI_FAST_SGL));
+
+ /* Mstorm ctx */
+ m_st_ctx->data_2_trns_rem = cpu_to_le32(io_size);
+ init_scsi_sgl_context(&m_st_ctx->sgl_params,
+ &m_st_ctx->data_desc,
+ sgl_task_params);
+ }
+
+ init_common_sqe(task_params, SEND_FCOE_CMD);
+ return 0;
+}
+
+int init_initiator_midpath_unsolicited_fcoe_task(
+ struct fcoe_task_params *task_params,
+ struct fcoe_tx_mid_path_params *mid_path_fc_header,
+ struct scsi_sgl_task_params *tx_sgl_task_params,
+ struct scsi_sgl_task_params *rx_sgl_task_params,
+ u8 fw_to_place_fc_header)
+{
+ struct fcoe_task_context *ctx = task_params->context;
+ struct ystorm_fcoe_task_st_ctx *y_st_ctx;
+ struct tstorm_fcoe_task_st_ctx *t_st_ctx;
+ struct ustorm_fcoe_task_ag_ctx *u_ag_ctx;
+ struct mstorm_fcoe_task_st_ctx *m_st_ctx;
+ u32 val;
+
+ memset(ctx, 0, sizeof(*(ctx)));
+
+ /* Init Ystorm */
+ y_st_ctx = &ctx->ystorm_st_context;
+ init_scsi_sgl_context(&y_st_ctx->sgl_params,
+ &y_st_ctx->data_desc,
+ tx_sgl_task_params);
+ SET_FIELD(y_st_ctx->sgl_mode,
+ YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE, SCSI_FAST_SGL);
+ y_st_ctx->data_2_trns_rem = cpu_to_le32(task_params->tx_io_size);
+ y_st_ctx->task_type = task_params->task_type;
+ memcpy(&y_st_ctx->tx_info_union.tx_params.mid_path,
+ mid_path_fc_header, sizeof(struct fcoe_tx_mid_path_params));
+
+ /* Init Mstorm */
+ m_st_ctx = &ctx->mstorm_st_context;
+ init_scsi_sgl_context(&m_st_ctx->sgl_params,
+ &m_st_ctx->data_desc,
+ rx_sgl_task_params);
+ SET_FIELD(m_st_ctx->flags,
+ MSTORM_FCOE_TASK_ST_CTX_MP_INCLUDE_FC_HEADER,
+ fw_to_place_fc_header);
+ m_st_ctx->data_2_trns_rem = cpu_to_le32(task_params->rx_io_size);
+
+ /* Init Tstorm */
+ t_st_ctx = &ctx->tstorm_st_context;
+ t_st_ctx->read_only.cid = cpu_to_le32(task_params->conn_cid);
+ val = cpu_to_le32(task_params->cq_rss_number);
+ t_st_ctx->read_only.glbl_q_num = val;
+ t_st_ctx->read_only.task_type = task_params->task_type;
+ SET_FIELD(t_st_ctx->read_write.flags,
+ FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME, 1);
+ t_st_ctx->read_write.rx_id = cpu_to_le16(FCOE_RX_ID);
+
+ /* Init Ustorm */
+ u_ag_ctx = &ctx->ustorm_ag_context;
+ u_ag_ctx->global_cq_num = cpu_to_le32(task_params->cq_rss_number);
+
+ /* Init SQE */
+ init_common_sqe(task_params, SEND_FCOE_MIDPATH);
+ task_params->sqe->additional_info_union.burst_length =
+ tx_sgl_task_params->total_buffer_size;
+ SET_FIELD(task_params->sqe->flags,
+ FCOE_WQE_NUM_SGES, tx_sgl_task_params->num_sges);
+ SET_FIELD(task_params->sqe->flags, FCOE_WQE_SGL_MODE,
+ SCSI_FAST_SGL);
+
+ return 0;
+}
+
+int init_initiator_abort_fcoe_task(struct fcoe_task_params *task_params)
+{
+ init_common_sqe(task_params, SEND_FCOE_ABTS_REQUEST);
+ return 0;
+}
+
+int init_initiator_cleanup_fcoe_task(struct fcoe_task_params *task_params)
+{
+ init_common_sqe(task_params, FCOE_EXCHANGE_CLEANUP);
+ return 0;
+}
+
+int init_initiator_sequence_recovery_fcoe_task(
+ struct fcoe_task_params *task_params, u32 off)
+{
+ init_common_sqe(task_params, FCOE_SEQUENCE_RECOVERY);
+ task_params->sqe->additional_info_union.seq_rec_updated_offset = off;
+ return 0;
+}
diff --git a/drivers/scsi/qedf/drv_fcoe_fw_funcs.h b/drivers/scsi/qedf/drv_fcoe_fw_funcs.h
new file mode 100644
index 0000000..617529b
--- /dev/null
+++ b/drivers/scsi/qedf/drv_fcoe_fw_funcs.h
@@ -0,0 +1,93 @@
+/* QLogic FCoE Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+#ifndef _FCOE_FW_FUNCS_H
+#define _FCOE_FW_FUNCS_H
+#include "drv_scsi_fw_funcs.h"
+#include "qedf_hsi.h"
+#include <linux/qed/qed_if.h>
+
+struct fcoe_task_params {
+ /* Output parameter [set/filled by the HSI function] */
+ struct fcoe_task_context *context;
+
+ /* Output parameter [set/filled by the HSI function] */
+ struct fcoe_wqe *sqe;
+ enum fcoe_task_type task_type;
+ u32 tx_io_size; /* in bytes */
+ u32 rx_io_size; /* in bytes */
+ u32 conn_cid;
+ u16 itid;
+ u8 cq_rss_number;
+
+ /* Whether it's Tape device or not (0=Disk, 1=Tape) */
+ u8 is_tape_device;
+};
+
+/**
+ * @brief init_initiator_rw_fcoe_task - Initializes FCoE task context for
+ * read/write task types and init fcoe_sqe
+ *
+ * @param task_params - Pointer to task parameters struct
+ * @param sgl_task_params - Pointer to SGL task params
+ * @param sense_data_buffer_phys_addr - Pointer to sense data buffer
+ * @param task_retry_id - retry identification - Used only for Tape device
+ * @param fcp_cmnd_payload - FCP CMD Payload
+ */
+int init_initiator_rw_fcoe_task(struct fcoe_task_params *task_params,
+ struct scsi_sgl_task_params *sgl_task_params,
+ struct regpair sense_data_buffer_phys_addr,
+ u32 task_retry_id,
+ u8 fcp_cmd_payload[32]);
+
+/**
+ * @brief init_initiator_midpath_fcoe_task - Initializes FCoE task context for
+ * midpath/unsolicited task types and init fcoe_sqe
+ *
+ * @param task_params - Pointer to task parameters struct
+ * @param mid_path_fc_header - FC header
+ * @param tx_sgl_task_params - Pointer to Tx SGL task params
+ * @param rx_sgl_task_params - Pointer to Rx SGL task params
+ * @param fw_to_place_fc_header - Indication if the FW will place the FC header
+ * in addition to the data arrives.
+ */
+int init_initiator_midpath_unsolicited_fcoe_task(
+ struct fcoe_task_params *task_params,
+ struct fcoe_tx_mid_path_params *mid_path_fc_header,
+ struct scsi_sgl_task_params *tx_sgl_task_params,
+ struct scsi_sgl_task_params *rx_sgl_task_params,
+ u8 fw_to_place_fc_header);
+
+/**
+ * @brief init_initiator_abort_fcoe_task - Initializes FCoE task context for
+ * abort task types and init fcoe_sqe
+ *
+ * @param task_params - Pointer to task parameters struct
+ */
+int init_initiator_abort_fcoe_task(struct fcoe_task_params *task_params);
+
+/**
+ * @brief init_initiator_cleanup_fcoe_task - Initializes FCoE task context for
+ * cleanup task types and init fcoe_sqe
+ *
+ *
+ * @param task_params - Pointer to task parameters struct
+ */
+int init_initiator_cleanup_fcoe_task(struct fcoe_task_params *task_params);
+
+/**
+ * @brief init_initiator_cleanup_fcoe_task - Initializes FCoE task context for
+ * sequence recovery task types and init fcoe_sqe
+ *
+ *
+ * @param task_params - Pointer to task parameters struct
+ * @param desired_offset - The desired offest the task will be re-sent from
+ */
+int init_initiator_sequence_recovery_fcoe_task(
+ struct fcoe_task_params *task_params,
+ u32 desired_offset);
+#endif
diff --git a/drivers/scsi/qedf/drv_scsi_fw_funcs.c b/drivers/scsi/qedf/drv_scsi_fw_funcs.c
new file mode 100644
index 0000000..11e0cc0
--- /dev/null
+++ b/drivers/scsi/qedf/drv_scsi_fw_funcs.c
@@ -0,0 +1,44 @@
+/* QLogic FCoE Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+#include "drv_scsi_fw_funcs.h"
+
+#define SCSI_NUM_SGES_IN_CACHE 0x4
+
+bool scsi_is_slow_sgl(u16 num_sges, bool small_mid_sge)
+{
+ return (num_sges > SCSI_NUM_SGES_SLOW_SGL_THR && small_mid_sge);
+}
+
+void init_scsi_sgl_context(struct scsi_sgl_params *ctx_sgl_params,
+ struct scsi_cached_sges *ctx_data_desc,
+ struct scsi_sgl_task_params *sgl_task_params)
+{
+ /* no need to check for sgl_task_params->sgl validity */
+ u8 num_sges_to_init = sgl_task_params->num_sges >
+ SCSI_NUM_SGES_IN_CACHE ? SCSI_NUM_SGES_IN_CACHE :
+ sgl_task_params->num_sges;
+ u8 sge_index;
+ u32 val;
+
+ val = cpu_to_le32(sgl_task_params->sgl_phys_addr.lo);
+ ctx_sgl_params->sgl_addr.lo = val;
+ val = cpu_to_le32(sgl_task_params->sgl_phys_addr.hi);
+ ctx_sgl_params->sgl_addr.hi = val;
+ val = cpu_to_le32(sgl_task_params->total_buffer_size);
+ ctx_sgl_params->sgl_total_length = val;
+ ctx_sgl_params->sgl_num_sges = cpu_to_le16(sgl_task_params->num_sges);
+
+ for (sge_index = 0; sge_index < num_sges_to_init; sge_index++) {
+ val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_addr.lo);
+ ctx_data_desc->sge[sge_index].sge_addr.lo = val;
+ val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_addr.hi);
+ ctx_data_desc->sge[sge_index].sge_addr.hi = val;
+ val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_len);
+ ctx_data_desc->sge[sge_index].sge_len = val;
+ }
+}
diff --git a/drivers/scsi/qedf/drv_scsi_fw_funcs.h b/drivers/scsi/qedf/drv_scsi_fw_funcs.h
new file mode 100644
index 0000000..9cb4541
--- /dev/null
+++ b/drivers/scsi/qedf/drv_scsi_fw_funcs.h
@@ -0,0 +1,85 @@
+/* QLogic FCoE Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+#ifndef _SCSI_FW_FUNCS_H
+#define _SCSI_FW_FUNCS_H
+#include <linux/qed/common_hsi.h>
+#include <linux/qed/storage_common.h>
+#include <linux/qed/fcoe_common.h>
+
+struct scsi_sgl_task_params {
+ struct scsi_sge *sgl;
+ struct regpair sgl_phys_addr;
+ u32 total_buffer_size;
+ u16 num_sges;
+
+ /* true if SGL contains a small (< 4KB) SGE in middle(not 1st or last)
+ * -> relevant for tx only
+ */
+ bool small_mid_sge;
+};
+
+struct scsi_dif_task_params {
+ u32 initial_ref_tag;
+ bool initial_ref_tag_is_valid;
+ u16 application_tag;
+ u16 application_tag_mask;
+ u16 dif_block_size_log;
+ bool dif_on_network;
+ bool dif_on_host;
+ u8 host_guard_type;
+ u8 protection_type;
+ u8 ref_tag_mask;
+ bool crc_seed;
+
+ /* Enable Connection error upon DIF error (segments with DIF errors are
+ * dropped)
+ */
+ bool tx_dif_conn_err_en;
+ bool ignore_app_tag;
+ bool keep_ref_tag_const;
+ bool validate_guard;
+ bool validate_app_tag;
+ bool validate_ref_tag;
+ bool forward_guard;
+ bool forward_app_tag;
+ bool forward_ref_tag;
+ bool forward_app_tag_with_mask;
+ bool forward_ref_tag_with_mask;
+};
+
+struct scsi_initiator_cmd_params {
+ /* for cdb_size > default CDB size (extended CDB > 16 bytes) ->
+ * pointer to the CDB buffer SGE
+ */
+ struct scsi_sge extended_cdb_sge;
+
+ /* Physical address of sense data buffer for sense data - 256B buffer */
+ struct regpair sense_data_buffer_phys_addr;
+};
+
+/**
+ * @brief scsi_is_slow_sgl - checks for slow SGL
+ *
+ * @param num_sges - number of sges in SGL
+ * @param small_mid_sge - True is the SGL contains an SGE which is smaller than
+ * 4KB and its not the 1st or last SGE in the SGL
+ */
+bool scsi_is_slow_sgl(u16 num_sges, bool small_mid_sge);
+
+/**
+ * @brief init_scsi_sgl_context - initializes SGL task context
+ *
+ * @param sgl_params - SGL context parameters to initialize (output parameter)
+ * @param data_desc - context struct containing SGEs array to set (output
+ * parameter)
+ * @param sgl_task_params - SGL parameters (input)
+ */
+void init_scsi_sgl_context(struct scsi_sgl_params *sgl_params,
+ struct scsi_cached_sges *ctx_data_desc,
+ struct scsi_sgl_task_params *sgl_task_params);
+#endif
diff --git a/drivers/scsi/qedf/qedf.h b/drivers/scsi/qedf/qedf.h
index 96346a1..40aeb6b 100644
--- a/drivers/scsi/qedf/qedf.h
+++ b/drivers/scsi/qedf/qedf.h
@@ -26,6 +26,7 @@
#include <linux/qed/qed_ll2_if.h>
#include "qedf_version.h"
#include "qedf_dbg.h"
+#include "drv_fcoe_fw_funcs.h"
/* Helpers to extract upper and lower 32-bits of pointer */
#define U64_HI(val) ((u32)(((u64)(val)) >> 32))
@@ -59,19 +60,17 @@
#define UPSTREAM_KEEP 1
struct qedf_mp_req {
- uint8_t tm_flags;
-
uint32_t req_len;
void *req_buf;
dma_addr_t req_buf_dma;
- struct fcoe_sge *mp_req_bd;
+ struct scsi_sge *mp_req_bd;
dma_addr_t mp_req_bd_dma;
struct fc_frame_header req_fc_hdr;
uint32_t resp_len;
void *resp_buf;
dma_addr_t resp_buf_dma;
- struct fcoe_sge *mp_resp_bd;
+ struct scsi_sge *mp_resp_bd;
dma_addr_t mp_resp_bd_dma;
struct fc_frame_header resp_fc_hdr;
};
@@ -119,6 +118,7 @@ struct qedf_ioreq {
#define QEDF_CMD_IN_CLEANUP 0x2
#define QEDF_CMD_SRR_SENT 0x3
u8 io_req_flags;
+ uint8_t tm_flags;
struct qedf_rport *fcport;
unsigned long flags;
enum qedf_ioreq_event event;
@@ -130,6 +130,8 @@ struct qedf_ioreq {
struct completion tm_done;
struct completion abts_done;
struct fcoe_task_context *task;
+ struct fcoe_task_params *task_params;
+ struct scsi_sgl_task_params *sgl_task_params;
int idx;
/*
* Need to allocate enough room for both sense data and FCP response data
@@ -199,8 +201,8 @@ struct qedf_rport {
dma_addr_t sq_pbl_dma;
u32 sq_pbl_size;
u32 sid;
-#define QEDF_RPORT_TYPE_DISK 1
-#define QEDF_RPORT_TYPE_TAPE 2
+#define QEDF_RPORT_TYPE_DISK 0
+#define QEDF_RPORT_TYPE_TAPE 1
uint dev_type; /* Disk or tape */
struct list_head peers;
};
@@ -391,7 +393,7 @@ struct qedf_ctx {
struct io_bdt {
struct qedf_ioreq *io_req;
- struct fcoe_sge *bd_tbl;
+ struct scsi_sge *bd_tbl;
dma_addr_t bd_tbl_dma;
u16 bd_valid;
};
@@ -400,7 +402,7 @@ struct qedf_cmd_mgr {
struct qedf_ctx *qedf;
u16 idx;
struct io_bdt **io_bdt_pool;
-#define FCOE_PARAMS_NUM_TASKS 4096
+#define FCOE_PARAMS_NUM_TASKS 2048
struct qedf_ioreq cmds[FCOE_PARAMS_NUM_TASKS];
spinlock_t lock;
atomic_t free_list_cnt;
@@ -465,9 +467,8 @@ extern void qedf_cmd_timer_set(struct qedf_ctx *qedf, struct qedf_ioreq *io_req,
unsigned int timer_msec);
extern int qedf_init_mp_req(struct qedf_ioreq *io_req);
extern void qedf_init_mp_task(struct qedf_ioreq *io_req,
- struct fcoe_task_context *task_ctx);
-extern void qedf_add_to_sq(struct qedf_rport *fcport, u16 xid,
- u32 ptu_invalidate, enum fcoe_task_type req_type, u32 offset);
+ struct fcoe_task_context *task_ctx, struct fcoe_wqe *wqe);
+extern u16 qedf_get_sqe_idx(struct qedf_rport *fcport);
extern void qedf_ring_doorbell(struct qedf_rport *fcport);
extern void qedf_process_els_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
struct qedf_ioreq *els_req);
diff --git a/drivers/scsi/qedf/qedf_dbg.h b/drivers/scsi/qedf/qedf_dbg.h
index 23bd706..7d173f48 100644
--- a/drivers/scsi/qedf/qedf_dbg.h
+++ b/drivers/scsi/qedf/qedf_dbg.h
@@ -81,14 +81,17 @@ struct qedf_dbg_ctx {
#define QEDF_INFO(pdev, level, fmt, ...) \
qedf_dbg_info(pdev, __func__, __LINE__, level, fmt, \
## __VA_ARGS__)
-
-extern void qedf_dbg_err(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
+__printf(4, 5)
+void qedf_dbg_err(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
const char *fmt, ...);
-extern void qedf_dbg_warn(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
+__printf(4, 5)
+void qedf_dbg_warn(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
const char *, ...);
-extern void qedf_dbg_notice(struct qedf_dbg_ctx *qedf, const char *func,
+__printf(4, 5)
+void qedf_dbg_notice(struct qedf_dbg_ctx *qedf, const char *func,
u32 line, const char *, ...);
-extern void qedf_dbg_info(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
+__printf(5, 6)
+void qedf_dbg_info(struct qedf_dbg_ctx *qedf, const char *func, u32 line,
u32 info, const char *fmt, ...);
/* GRC Dump related defines */
diff --git a/drivers/scsi/qedf/qedf_els.c b/drivers/scsi/qedf/qedf_els.c
index 59f3e5c..c505d41 100644
--- a/drivers/scsi/qedf/qedf_els.c
+++ b/drivers/scsi/qedf/qedf_els.c
@@ -25,6 +25,9 @@ static int qedf_initiate_els(struct qedf_rport *fcport, unsigned int op,
uint16_t xid;
uint32_t start_time = jiffies / HZ;
uint32_t current_time;
+ struct fcoe_wqe *sqe;
+ unsigned long flags;
+ u16 sqe_idx;
QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "Sending ELS\n");
@@ -113,20 +116,25 @@ static int qedf_initiate_els(struct qedf_rport *fcport, unsigned int op,
/* Obtain exchange id */
xid = els_req->xid;
+ spin_lock_irqsave(&fcport->rport_lock, flags);
+
+ sqe_idx = qedf_get_sqe_idx(fcport);
+ sqe = &fcport->sq[sqe_idx];
+ memset(sqe, 0, sizeof(struct fcoe_wqe));
+
/* Initialize task context for this IO request */
task = qedf_get_task_mem(&qedf->tasks, xid);
- qedf_init_mp_task(els_req, task);
+ qedf_init_mp_task(els_req, task, sqe);
/* Put timer on original I/O request */
if (timer_msec)
qedf_cmd_timer_set(qedf, els_req, timer_msec);
- qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_MIDPATH, 0);
-
/* Ring doorbell */
QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_ELS, "Ringing doorbell for ELS "
"req\n");
qedf_ring_doorbell(fcport);
+ spin_unlock_irqrestore(&fcport->rport_lock, flags);
els_err:
return rc;
}
@@ -604,6 +612,8 @@ static void qedf_initiate_seq_cleanup(struct qedf_ioreq *orig_io_req,
struct qedf_rport *fcport;
unsigned long flags;
struct qedf_els_cb_arg *cb_arg;
+ struct fcoe_wqe *sqe;
+ u16 sqe_idx;
fcport = orig_io_req->fcport;
@@ -631,8 +641,13 @@ static void qedf_initiate_seq_cleanup(struct qedf_ioreq *orig_io_req,
spin_lock_irqsave(&fcport->rport_lock, flags);
- qedf_add_to_sq(fcport, orig_io_req->xid, 0,
- FCOE_TASK_TYPE_SEQUENCE_CLEANUP, offset);
+ sqe_idx = qedf_get_sqe_idx(fcport);
+ sqe = &fcport->sq[sqe_idx];
+ memset(sqe, 0, sizeof(struct fcoe_wqe));
+ orig_io_req->task_params->sqe = sqe;
+
+ init_initiator_sequence_recovery_fcoe_task(orig_io_req->task_params,
+ offset);
qedf_ring_doorbell(fcport);
spin_unlock_irqrestore(&fcport->rport_lock, flags);
diff --git a/drivers/scsi/qedf/qedf_fip.c b/drivers/scsi/qedf/qedf_fip.c
index 868d423..ed58b91 100644
--- a/drivers/scsi/qedf/qedf_fip.c
+++ b/drivers/scsi/qedf/qedf_fip.c
@@ -203,7 +203,7 @@ void qedf_fip_recv(struct qedf_ctx *qedf, struct sk_buff *skb)
case FIP_DT_MAC:
mp = (struct fip_mac_desc *)desc;
QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_LL2,
- "fd_mac=%pM.\n", __func__, mp->fd_mac);
+ "fd_mac=%pM\n", mp->fd_mac);
ether_addr_copy(cvl_mac, mp->fd_mac);
break;
case FIP_DT_NAME:
diff --git a/drivers/scsi/qedf/qedf_io.c b/drivers/scsi/qedf/qedf_io.c
index ee0dcf9..1d7f90d 100644
--- a/drivers/scsi/qedf/qedf_io.c
+++ b/drivers/scsi/qedf/qedf_io.c
@@ -96,7 +96,7 @@ void qedf_cmd_mgr_free(struct qedf_cmd_mgr *cmgr)
if (!cmgr->io_bdt_pool)
goto free_cmd_pool;
- bd_tbl_sz = QEDF_MAX_BDS_PER_CMD * sizeof(struct fcoe_sge);
+ bd_tbl_sz = QEDF_MAX_BDS_PER_CMD * sizeof(struct scsi_sge);
for (i = 0; i < num_ios; i++) {
bdt_info = cmgr->io_bdt_pool[i];
if (bdt_info->bd_tbl) {
@@ -119,6 +119,8 @@ void qedf_cmd_mgr_free(struct qedf_cmd_mgr *cmgr)
for (i = 0; i < num_ios; i++) {
io_req = &cmgr->cmds[i];
+ kfree(io_req->sgl_task_params);
+ kfree(io_req->task_params);
/* Make sure we free per command sense buffer */
if (io_req->sense_buffer)
dma_free_coherent(&qedf->pdev->dev,
@@ -178,7 +180,7 @@ struct qedf_cmd_mgr *qedf_cmd_mgr_alloc(struct qedf_ctx *qedf)
spin_lock_init(&cmgr->lock);
/*
- * Initialize list of qedf_ioreq.
+ * Initialize I/O request fields.
*/
xid = QEDF_MIN_XID;
@@ -196,6 +198,29 @@ struct qedf_cmd_mgr *qedf_cmd_mgr_alloc(struct qedf_ctx *qedf)
GFP_KERNEL);
if (!io_req->sense_buffer)
goto mem_err;
+
+ /* Allocate task parameters to pass to f/w init funcions */
+ io_req->task_params = kzalloc(sizeof(*io_req->task_params),
+ GFP_KERNEL);
+ if (!io_req->task_params) {
+ QEDF_ERR(&(qedf->dbg_ctx),
+ "Failed to allocate task_params for xid=0x%x\n",
+ i);
+ goto mem_err;
+ }
+
+ /*
+ * Allocate scatter/gather list info to pass to f/w init
+ * functions.
+ */
+ io_req->sgl_task_params = kzalloc(
+ sizeof(struct scsi_sgl_task_params), GFP_KERNEL);
+ if (!io_req->sgl_task_params) {
+ QEDF_ERR(&(qedf->dbg_ctx),
+ "Failed to allocate sgl_task_params for xid=0x%x\n",
+ i);
+ goto mem_err;
+ }
}
/* Allocate pool of io_bdts - one for each qedf_ioreq */
@@ -211,8 +236,8 @@ struct qedf_cmd_mgr *qedf_cmd_mgr_alloc(struct qedf_ctx *qedf)
cmgr->io_bdt_pool[i] = kmalloc(sizeof(struct io_bdt),
GFP_KERNEL);
if (!cmgr->io_bdt_pool[i]) {
- QEDF_WARN(&(qedf->dbg_ctx), "Failed to alloc "
- "io_bdt_pool[%d].\n", i);
+ QEDF_WARN(&(qedf->dbg_ctx),
+ "Failed to alloc io_bdt_pool[%d].\n", i);
goto mem_err;
}
}
@@ -220,11 +245,11 @@ struct qedf_cmd_mgr *qedf_cmd_mgr_alloc(struct qedf_ctx *qedf)
for (i = 0; i < num_ios; i++) {
bdt_info = cmgr->io_bdt_pool[i];
bdt_info->bd_tbl = dma_alloc_coherent(&qedf->pdev->dev,
- QEDF_MAX_BDS_PER_CMD * sizeof(struct fcoe_sge),
+ QEDF_MAX_BDS_PER_CMD * sizeof(struct scsi_sge),
&bdt_info->bd_tbl_dma, GFP_KERNEL);
if (!bdt_info->bd_tbl) {
- QEDF_WARN(&(qedf->dbg_ctx), "Failed to alloc "
- "bdt_tbl[%d].\n", i);
+ QEDF_WARN(&(qedf->dbg_ctx),
+ "Failed to alloc bdt_tbl[%d].\n", i);
goto mem_err;
}
}
@@ -318,6 +343,7 @@ struct qedf_ioreq *qedf_alloc_cmd(struct qedf_rport *fcport, u8 cmd_type)
}
bd_tbl->io_req = io_req;
io_req->cmd_type = cmd_type;
+ io_req->tm_flags = 0;
/* Reset sequence offset data */
io_req->rx_buf_off = 0;
@@ -336,10 +362,9 @@ static void qedf_free_mp_resc(struct qedf_ioreq *io_req)
{
struct qedf_mp_req *mp_req = &(io_req->mp_req);
struct qedf_ctx *qedf = io_req->fcport->qedf;
- uint64_t sz = sizeof(struct fcoe_sge);
+ uint64_t sz = sizeof(struct scsi_sge);
/* clear tm flags */
- mp_req->tm_flags = 0;
if (mp_req->mp_req_bd) {
dma_free_coherent(&qedf->pdev->dev, sz,
mp_req->mp_req_bd, mp_req->mp_req_bd_dma);
@@ -387,7 +412,7 @@ void qedf_release_cmd(struct kref *ref)
static int qedf_split_bd(struct qedf_ioreq *io_req, u64 addr, int sg_len,
int bd_index)
{
- struct fcoe_sge *bd = io_req->bd_tbl->bd_tbl;
+ struct scsi_sge *bd = io_req->bd_tbl->bd_tbl;
int frag_size, sg_frags;
sg_frags = 0;
@@ -398,7 +423,7 @@ static int qedf_split_bd(struct qedf_ioreq *io_req, u64 addr, int sg_len,
frag_size = sg_len;
bd[bd_index + sg_frags].sge_addr.lo = U64_LO(addr);
bd[bd_index + sg_frags].sge_addr.hi = U64_HI(addr);
- bd[bd_index + sg_frags].size = (uint16_t)frag_size;
+ bd[bd_index + sg_frags].sge_len = (uint16_t)frag_size;
addr += (u64)frag_size;
sg_frags++;
@@ -413,7 +438,7 @@ static int qedf_map_sg(struct qedf_ioreq *io_req)
struct Scsi_Host *host = sc->device->host;
struct fc_lport *lport = shost_priv(host);
struct qedf_ctx *qedf = lport_priv(lport);
- struct fcoe_sge *bd = io_req->bd_tbl->bd_tbl;
+ struct scsi_sge *bd = io_req->bd_tbl->bd_tbl;
struct scatterlist *sg;
int byte_count = 0;
int sg_count = 0;
@@ -439,7 +464,7 @@ static int qedf_map_sg(struct qedf_ioreq *io_req)
bd[bd_count].sge_addr.lo = (addr & 0xffffffff);
bd[bd_count].sge_addr.hi = (addr >> 32);
- bd[bd_count].size = (u16)sg_len;
+ bd[bd_count].sge_len = (u16)sg_len;
return ++bd_count;
}
@@ -480,7 +505,7 @@ static int qedf_map_sg(struct qedf_ioreq *io_req)
sg_frags = 1;
bd[bd_count].sge_addr.lo = U64_LO(addr);
bd[bd_count].sge_addr.hi = U64_HI(addr);
- bd[bd_count].size = (uint16_t)sg_len;
+ bd[bd_count].sge_len = (uint16_t)sg_len;
}
bd_count += sg_frags;
@@ -498,7 +523,7 @@ static int qedf_map_sg(struct qedf_ioreq *io_req)
static int qedf_build_bd_list_from_sg(struct qedf_ioreq *io_req)
{
struct scsi_cmnd *sc = io_req->sc_cmd;
- struct fcoe_sge *bd = io_req->bd_tbl->bd_tbl;
+ struct scsi_sge *bd = io_req->bd_tbl->bd_tbl;
int bd_count;
if (scsi_sg_count(sc)) {
@@ -508,7 +533,7 @@ static int qedf_build_bd_list_from_sg(struct qedf_ioreq *io_req)
} else {
bd_count = 0;
bd[0].sge_addr.lo = bd[0].sge_addr.hi = 0;
- bd[0].size = 0;
+ bd[0].sge_len = 0;
}
io_req->bd_tbl->bd_valid = bd_count;
@@ -529,430 +554,223 @@ static void qedf_build_fcp_cmnd(struct qedf_ioreq *io_req,
/* 4 bytes: flag info */
fcp_cmnd->fc_pri_ta = 0;
- fcp_cmnd->fc_tm_flags = io_req->mp_req.tm_flags;
+ fcp_cmnd->fc_tm_flags = io_req->tm_flags;
fcp_cmnd->fc_flags = io_req->io_req_flags;
fcp_cmnd->fc_cmdref = 0;
/* Populate data direction */
- if (sc_cmd->sc_data_direction == DMA_TO_DEVICE)
- fcp_cmnd->fc_flags |= FCP_CFL_WRDATA;
- else if (sc_cmd->sc_data_direction == DMA_FROM_DEVICE)
+ if (io_req->cmd_type == QEDF_TASK_MGMT_CMD) {
fcp_cmnd->fc_flags |= FCP_CFL_RDDATA;
+ } else {
+ if (sc_cmd->sc_data_direction == DMA_TO_DEVICE)
+ fcp_cmnd->fc_flags |= FCP_CFL_WRDATA;
+ else if (sc_cmd->sc_data_direction == DMA_FROM_DEVICE)
+ fcp_cmnd->fc_flags |= FCP_CFL_RDDATA;
+ }
fcp_cmnd->fc_pri_ta = FCP_PTA_SIMPLE;
/* 16 bytes: CDB information */
- memcpy(fcp_cmnd->fc_cdb, sc_cmd->cmnd, sc_cmd->cmd_len);
+ if (io_req->cmd_type != QEDF_TASK_MGMT_CMD)
+ memcpy(fcp_cmnd->fc_cdb, sc_cmd->cmnd, sc_cmd->cmd_len);
/* 4 bytes: FCP data length */
fcp_cmnd->fc_dl = htonl(io_req->data_xfer_len);
-
}
static void qedf_init_task(struct qedf_rport *fcport, struct fc_lport *lport,
- struct qedf_ioreq *io_req, u32 *ptu_invalidate,
- struct fcoe_task_context *task_ctx)
+ struct qedf_ioreq *io_req, struct fcoe_task_context *task_ctx,
+ struct fcoe_wqe *sqe)
{
enum fcoe_task_type task_type;
struct scsi_cmnd *sc_cmd = io_req->sc_cmd;
struct io_bdt *bd_tbl = io_req->bd_tbl;
- union fcoe_data_desc_ctx *data_desc;
- u32 *fcp_cmnd;
+ u8 fcp_cmnd[32];
u32 tmp_fcp_cmnd[8];
- int cnt, i;
- int bd_count;
+ int bd_count = 0;
struct qedf_ctx *qedf = fcport->qedf;
uint16_t cq_idx = smp_processor_id() % qedf->num_queues;
- u8 tmp_sgl_mode = 0;
- u8 mst_sgl_mode = 0;
+ struct regpair sense_data_buffer_phys_addr;
+ u32 tx_io_size = 0;
+ u32 rx_io_size = 0;
+ int i, cnt;
- memset(task_ctx, 0, sizeof(struct fcoe_task_context));
+ /* Note init_initiator_rw_fcoe_task memsets the task context */
io_req->task = task_ctx;
+ memset(task_ctx, 0, sizeof(struct fcoe_task_context));
+ memset(io_req->task_params, 0, sizeof(struct fcoe_task_params));
+ memset(io_req->sgl_task_params, 0, sizeof(struct scsi_sgl_task_params));
- if (sc_cmd->sc_data_direction == DMA_TO_DEVICE)
- task_type = FCOE_TASK_TYPE_WRITE_INITIATOR;
- else
+ /* Set task type bassed on DMA directio of command */
+ if (io_req->cmd_type == QEDF_TASK_MGMT_CMD) {
task_type = FCOE_TASK_TYPE_READ_INITIATOR;
-
- /* Y Storm context */
- task_ctx->ystorm_st_context.expect_first_xfer = 1;
- task_ctx->ystorm_st_context.data_2_trns_rem = io_req->data_xfer_len;
- /* Check if this is required */
- task_ctx->ystorm_st_context.ox_id = io_req->xid;
- task_ctx->ystorm_st_context.task_rety_identifier =
- io_req->task_retry_identifier;
-
- /* T Storm ag context */
- SET_FIELD(task_ctx->tstorm_ag_context.flags0,
- TSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE, PROTOCOLID_FCOE);
- task_ctx->tstorm_ag_context.icid = (u16)fcport->fw_cid;
-
- /* T Storm st context */
- SET_FIELD(task_ctx->tstorm_st_context.read_write.flags,
- FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME,
- 1);
- task_ctx->tstorm_st_context.read_write.rx_id = 0xffff;
-
- task_ctx->tstorm_st_context.read_only.dev_type =
- FCOE_TASK_DEV_TYPE_DISK;
- task_ctx->tstorm_st_context.read_only.conf_supported = 0;
- task_ctx->tstorm_st_context.read_only.cid = fcport->fw_cid;
-
- /* Completion queue for response. */
- task_ctx->tstorm_st_context.read_only.glbl_q_num = cq_idx;
- task_ctx->tstorm_st_context.read_only.fcp_cmd_trns_size =
- io_req->data_xfer_len;
- task_ctx->tstorm_st_context.read_write.e_d_tov_exp_timeout_val =
- lport->e_d_tov;
-
- task_ctx->ustorm_ag_context.global_cq_num = cq_idx;
- io_req->fp_idx = cq_idx;
-
- bd_count = bd_tbl->bd_valid;
- if (task_type == FCOE_TASK_TYPE_WRITE_INITIATOR) {
- /* Setup WRITE task */
- struct fcoe_sge *fcoe_bd_tbl = bd_tbl->bd_tbl;
-
- task_ctx->ystorm_st_context.task_type =
- FCOE_TASK_TYPE_WRITE_INITIATOR;
- data_desc = &task_ctx->ystorm_st_context.data_desc;
-
- if (io_req->use_slowpath) {
- SET_FIELD(task_ctx->ystorm_st_context.sgl_mode,
- YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE,
- FCOE_SLOW_SGL);
- data_desc->slow.base_sgl_addr.lo =
- U64_LO(bd_tbl->bd_tbl_dma);
- data_desc->slow.base_sgl_addr.hi =
- U64_HI(bd_tbl->bd_tbl_dma);
- data_desc->slow.remainder_num_sges = bd_count;
- data_desc->slow.curr_sge_off = 0;
- data_desc->slow.curr_sgl_index = 0;
- qedf->slow_sge_ios++;
- io_req->sge_type = QEDF_IOREQ_SLOW_SGE;
- } else {
- SET_FIELD(task_ctx->ystorm_st_context.sgl_mode,
- YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE,
- (bd_count <= 4) ? (enum fcoe_sgl_mode)bd_count :
- FCOE_MUL_FAST_SGES);
-
- if (bd_count == 1) {
- data_desc->single_sge.sge_addr.lo =
- fcoe_bd_tbl->sge_addr.lo;
- data_desc->single_sge.sge_addr.hi =
- fcoe_bd_tbl->sge_addr.hi;
- data_desc->single_sge.size =
- fcoe_bd_tbl->size;
- data_desc->single_sge.is_valid_sge = 0;
- qedf->single_sge_ios++;
- io_req->sge_type = QEDF_IOREQ_SINGLE_SGE;
- } else {
- data_desc->fast.sgl_start_addr.lo =
- U64_LO(bd_tbl->bd_tbl_dma);
- data_desc->fast.sgl_start_addr.hi =
- U64_HI(bd_tbl->bd_tbl_dma);
- data_desc->fast.sgl_byte_offset =
- data_desc->fast.sgl_start_addr.lo &
- (QEDF_PAGE_SIZE - 1);
- if (data_desc->fast.sgl_byte_offset > 0)
- QEDF_ERR(&(qedf->dbg_ctx),
- "byte_offset=%u for xid=0x%x.\n",
- io_req->xid,
- data_desc->fast.sgl_byte_offset);
- data_desc->fast.task_reuse_cnt =
- io_req->reuse_count;
- io_req->reuse_count++;
- if (io_req->reuse_count == QEDF_MAX_REUSE) {
- *ptu_invalidate = 1;
- io_req->reuse_count = 0;
- }
- qedf->fast_sge_ios++;
- io_req->sge_type = QEDF_IOREQ_FAST_SGE;
- }
- }
-
- /* T Storm context */
- task_ctx->tstorm_st_context.read_only.task_type =
- FCOE_TASK_TYPE_WRITE_INITIATOR;
-
- /* M Storm context */
- tmp_sgl_mode = GET_FIELD(task_ctx->ystorm_st_context.sgl_mode,
- YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE);
- SET_FIELD(task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode,
- FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_TX_SGL_MODE,
- tmp_sgl_mode);
-
} else {
- /* Setup READ task */
-
- /* M Storm context */
- struct fcoe_sge *fcoe_bd_tbl = bd_tbl->bd_tbl;
-
- data_desc = &task_ctx->mstorm_st_context.fp.data_desc;
- task_ctx->mstorm_st_context.fp.data_2_trns_rem =
- io_req->data_xfer_len;
-
- if (io_req->use_slowpath) {
- SET_FIELD(
- task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode,
- FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE,
- FCOE_SLOW_SGL);
- data_desc->slow.base_sgl_addr.lo =
- U64_LO(bd_tbl->bd_tbl_dma);
- data_desc->slow.base_sgl_addr.hi =
- U64_HI(bd_tbl->bd_tbl_dma);
- data_desc->slow.remainder_num_sges =
- bd_count;
- data_desc->slow.curr_sge_off = 0;
- data_desc->slow.curr_sgl_index = 0;
- qedf->slow_sge_ios++;
- io_req->sge_type = QEDF_IOREQ_SLOW_SGE;
+ if (sc_cmd->sc_data_direction == DMA_TO_DEVICE) {
+ task_type = FCOE_TASK_TYPE_WRITE_INITIATOR;
+ tx_io_size = io_req->data_xfer_len;
} else {
- SET_FIELD(
- task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode,
- FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE,
- (bd_count <= 4) ? (enum fcoe_sgl_mode)bd_count :
- FCOE_MUL_FAST_SGES);
-
- if (bd_count == 1) {
- data_desc->single_sge.sge_addr.lo =
- fcoe_bd_tbl->sge_addr.lo;
- data_desc->single_sge.sge_addr.hi =
- fcoe_bd_tbl->sge_addr.hi;
- data_desc->single_sge.size =
- fcoe_bd_tbl->size;
- data_desc->single_sge.is_valid_sge = 0;
- qedf->single_sge_ios++;
- io_req->sge_type = QEDF_IOREQ_SINGLE_SGE;
- } else {
- data_desc->fast.sgl_start_addr.lo =
- U64_LO(bd_tbl->bd_tbl_dma);
- data_desc->fast.sgl_start_addr.hi =
- U64_HI(bd_tbl->bd_tbl_dma);
- data_desc->fast.sgl_byte_offset = 0;
- data_desc->fast.task_reuse_cnt =
- io_req->reuse_count;
- io_req->reuse_count++;
- if (io_req->reuse_count == QEDF_MAX_REUSE) {
- *ptu_invalidate = 1;
- io_req->reuse_count = 0;
- }
- qedf->fast_sge_ios++;
- io_req->sge_type = QEDF_IOREQ_FAST_SGE;
- }
+ task_type = FCOE_TASK_TYPE_READ_INITIATOR;
+ rx_io_size = io_req->data_xfer_len;
}
-
- /* Y Storm context */
- task_ctx->ystorm_st_context.expect_first_xfer = 0;
- task_ctx->ystorm_st_context.task_type =
- FCOE_TASK_TYPE_READ_INITIATOR;
-
- /* T Storm context */
- task_ctx->tstorm_st_context.read_only.task_type =
- FCOE_TASK_TYPE_READ_INITIATOR;
- mst_sgl_mode = GET_FIELD(
- task_ctx->mstorm_st_context.non_fp.tx_rx_sgl_mode,
- FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE);
- SET_FIELD(task_ctx->tstorm_st_context.read_write.flags,
- FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE,
- mst_sgl_mode);
}
+ /* Setup the fields for fcoe_task_params */
+ io_req->task_params->context = task_ctx;
+ io_req->task_params->sqe = sqe;
+ io_req->task_params->task_type = task_type;
+ io_req->task_params->tx_io_size = tx_io_size;
+ io_req->task_params->rx_io_size = rx_io_size;
+ io_req->task_params->conn_cid = fcport->fw_cid;
+ io_req->task_params->itid = io_req->xid;
+ io_req->task_params->cq_rss_number = cq_idx;
+ io_req->task_params->is_tape_device = fcport->dev_type;
+
+ /* Fill in information for scatter/gather list */
+ if (io_req->cmd_type != QEDF_TASK_MGMT_CMD) {
+ bd_count = bd_tbl->bd_valid;
+ io_req->sgl_task_params->sgl = bd_tbl->bd_tbl;
+ io_req->sgl_task_params->sgl_phys_addr.lo =
+ U64_LO(bd_tbl->bd_tbl_dma);
+ io_req->sgl_task_params->sgl_phys_addr.hi =
+ U64_HI(bd_tbl->bd_tbl_dma);
+ io_req->sgl_task_params->num_sges = bd_count;
+ io_req->sgl_task_params->total_buffer_size =
+ scsi_bufflen(io_req->sc_cmd);
+ io_req->sgl_task_params->small_mid_sge =
+ io_req->use_slowpath;
+ }
+
+ /* Fill in physical address of sense buffer */
+ sense_data_buffer_phys_addr.lo = U64_LO(io_req->sense_buffer_dma);
+ sense_data_buffer_phys_addr.hi = U64_HI(io_req->sense_buffer_dma);
+
/* fill FCP_CMND IU */
- fcp_cmnd = (u32 *)task_ctx->ystorm_st_context.tx_info_union.fcp_cmd_payload.opaque;
- qedf_build_fcp_cmnd(io_req, (struct fcp_cmnd *)&tmp_fcp_cmnd);
+ qedf_build_fcp_cmnd(io_req, (struct fcp_cmnd *)tmp_fcp_cmnd);
/* Swap fcp_cmnd since FC is big endian */
cnt = sizeof(struct fcp_cmnd) / sizeof(u32);
-
for (i = 0; i < cnt; i++) {
- *fcp_cmnd = cpu_to_be32(tmp_fcp_cmnd[i]);
- fcp_cmnd++;
+ tmp_fcp_cmnd[i] = cpu_to_be32(tmp_fcp_cmnd[i]);
}
+ memcpy(fcp_cmnd, tmp_fcp_cmnd, sizeof(struct fcp_cmnd));
- /* M Storm context - Sense buffer */
- task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.lo =
- U64_LO(io_req->sense_buffer_dma);
- task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.hi =
- U64_HI(io_req->sense_buffer_dma);
+ init_initiator_rw_fcoe_task(io_req->task_params,
+ io_req->sgl_task_params,
+ sense_data_buffer_phys_addr,
+ io_req->task_retry_identifier, fcp_cmnd);
+
+ /* Increment SGL type counters */
+ if (bd_count == 1) {
+ qedf->single_sge_ios++;
+ io_req->sge_type = QEDF_IOREQ_SINGLE_SGE;
+ } else if (io_req->use_slowpath) {
+ qedf->slow_sge_ios++;
+ io_req->sge_type = QEDF_IOREQ_SLOW_SGE;
+ } else {
+ qedf->fast_sge_ios++;
+ io_req->sge_type = QEDF_IOREQ_FAST_SGE;
+ }
}
void qedf_init_mp_task(struct qedf_ioreq *io_req,
- struct fcoe_task_context *task_ctx)
+ struct fcoe_task_context *task_ctx, struct fcoe_wqe *sqe)
{
struct qedf_mp_req *mp_req = &(io_req->mp_req);
struct qedf_rport *fcport = io_req->fcport;
struct qedf_ctx *qedf = io_req->fcport->qedf;
struct fc_frame_header *fc_hdr;
- enum fcoe_task_type task_type = 0;
- union fcoe_data_desc_ctx *data_desc;
+ struct fcoe_tx_mid_path_params task_fc_hdr;
+ struct scsi_sgl_task_params tx_sgl_task_params;
+ struct scsi_sgl_task_params rx_sgl_task_params;
- QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "Initializing MP task "
- "for cmd_type = %d\n", io_req->cmd_type);
+ QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
+ "Initializing MP task for cmd_type=%d\n",
+ io_req->cmd_type);
qedf->control_requests++;
- /* Obtain task_type */
- if ((io_req->cmd_type == QEDF_TASK_MGMT_CMD) ||
- (io_req->cmd_type == QEDF_ELS)) {
- task_type = FCOE_TASK_TYPE_MIDPATH;
- } else if (io_req->cmd_type == QEDF_ABTS) {
- task_type = FCOE_TASK_TYPE_ABTS;
- }
-
+ memset(&tx_sgl_task_params, 0, sizeof(struct scsi_sgl_task_params));
+ memset(&rx_sgl_task_params, 0, sizeof(struct scsi_sgl_task_params));
memset(task_ctx, 0, sizeof(struct fcoe_task_context));
+ memset(&task_fc_hdr, 0, sizeof(struct fcoe_tx_mid_path_params));
/* Setup the task from io_req for easy reference */
io_req->task = task_ctx;
- QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "task type = %d\n",
- task_type);
+ /* Setup the fields for fcoe_task_params */
+ io_req->task_params->context = task_ctx;
+ io_req->task_params->sqe = sqe;
+ io_req->task_params->task_type = FCOE_TASK_TYPE_MIDPATH;
+ io_req->task_params->tx_io_size = io_req->data_xfer_len;
+ /* rx_io_size tells the f/w how large a response buffer we have */
+ io_req->task_params->rx_io_size = PAGE_SIZE;
+ io_req->task_params->conn_cid = fcport->fw_cid;
+ io_req->task_params->itid = io_req->xid;
+ /* Return middle path commands on CQ 0 */
+ io_req->task_params->cq_rss_number = 0;
+ io_req->task_params->is_tape_device = fcport->dev_type;
- /* YSTORM only */
- {
- /* Initialize YSTORM task context */
- struct fcoe_tx_mid_path_params *task_fc_hdr =
- &task_ctx->ystorm_st_context.tx_info_union.tx_params.mid_path;
- memset(task_fc_hdr, 0, sizeof(struct fcoe_tx_mid_path_params));
- task_ctx->ystorm_st_context.task_rety_identifier =
- io_req->task_retry_identifier;
+ fc_hdr = &(mp_req->req_fc_hdr);
+ /* Set OX_ID and RX_ID based on driver task id */
+ fc_hdr->fh_ox_id = io_req->xid;
+ fc_hdr->fh_rx_id = htons(0xffff);
- /* Init SGL parameters */
- if ((task_type == FCOE_TASK_TYPE_MIDPATH) ||
- (task_type == FCOE_TASK_TYPE_UNSOLICITED)) {
- data_desc = &task_ctx->ystorm_st_context.data_desc;
- data_desc->slow.base_sgl_addr.lo =
- U64_LO(mp_req->mp_req_bd_dma);
- data_desc->slow.base_sgl_addr.hi =
- U64_HI(mp_req->mp_req_bd_dma);
- data_desc->slow.remainder_num_sges = 1;
- data_desc->slow.curr_sge_off = 0;
- data_desc->slow.curr_sgl_index = 0;
- }
+ /* Set up FC header information */
+ task_fc_hdr.parameter = fc_hdr->fh_parm_offset;
+ task_fc_hdr.r_ctl = fc_hdr->fh_r_ctl;
+ task_fc_hdr.type = fc_hdr->fh_type;
+ task_fc_hdr.cs_ctl = fc_hdr->fh_cs_ctl;
+ task_fc_hdr.df_ctl = fc_hdr->fh_df_ctl;
+ task_fc_hdr.rx_id = fc_hdr->fh_rx_id;
+ task_fc_hdr.ox_id = fc_hdr->fh_ox_id;
- fc_hdr = &(mp_req->req_fc_hdr);
- if (task_type == FCOE_TASK_TYPE_MIDPATH) {
- fc_hdr->fh_ox_id = io_req->xid;
- fc_hdr->fh_rx_id = htons(0xffff);
- } else if (task_type == FCOE_TASK_TYPE_UNSOLICITED) {
- fc_hdr->fh_rx_id = io_req->xid;
- }
+ /* Set up s/g list parameters for request buffer */
+ tx_sgl_task_params.sgl = mp_req->mp_req_bd;
+ tx_sgl_task_params.sgl_phys_addr.lo = U64_LO(mp_req->mp_req_bd_dma);
+ tx_sgl_task_params.sgl_phys_addr.hi = U64_HI(mp_req->mp_req_bd_dma);
+ tx_sgl_task_params.num_sges = 1;
+ /* Set PAGE_SIZE for now since sg element is that size ??? */
+ tx_sgl_task_params.total_buffer_size = io_req->data_xfer_len;
+ tx_sgl_task_params.small_mid_sge = 0;
- /* Fill FC Header into middle path buffer */
- task_fc_hdr->parameter = fc_hdr->fh_parm_offset;
- task_fc_hdr->r_ctl = fc_hdr->fh_r_ctl;
- task_fc_hdr->type = fc_hdr->fh_type;
- task_fc_hdr->cs_ctl = fc_hdr->fh_cs_ctl;
- task_fc_hdr->df_ctl = fc_hdr->fh_df_ctl;
- task_fc_hdr->rx_id = fc_hdr->fh_rx_id;
- task_fc_hdr->ox_id = fc_hdr->fh_ox_id;
+ /* Set up s/g list parameters for request buffer */
+ rx_sgl_task_params.sgl = mp_req->mp_resp_bd;
+ rx_sgl_task_params.sgl_phys_addr.lo = U64_LO(mp_req->mp_resp_bd_dma);
+ rx_sgl_task_params.sgl_phys_addr.hi = U64_HI(mp_req->mp_resp_bd_dma);
+ rx_sgl_task_params.num_sges = 1;
+ /* Set PAGE_SIZE for now since sg element is that size ??? */
+ rx_sgl_task_params.total_buffer_size = PAGE_SIZE;
+ rx_sgl_task_params.small_mid_sge = 0;
- task_ctx->ystorm_st_context.data_2_trns_rem =
- io_req->data_xfer_len;
- task_ctx->ystorm_st_context.task_type = task_type;
- }
- /* TSTORM ONLY */
- {
- task_ctx->tstorm_ag_context.icid = (u16)fcport->fw_cid;
- task_ctx->tstorm_st_context.read_only.cid = fcport->fw_cid;
- /* Always send middle-path repsonses on CQ #0 */
- task_ctx->tstorm_st_context.read_only.glbl_q_num = 0;
- io_req->fp_idx = 0;
- SET_FIELD(task_ctx->tstorm_ag_context.flags0,
- TSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE,
- PROTOCOLID_FCOE);
- task_ctx->tstorm_st_context.read_only.task_type = task_type;
- SET_FIELD(task_ctx->tstorm_st_context.read_write.flags,
- FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME,
- 1);
- task_ctx->tstorm_st_context.read_write.rx_id = 0xffff;
- }
+ /*
+ * Last arg is 0 as previous code did not set that we wanted the
+ * fc header information.
+ */
+ init_initiator_midpath_unsolicited_fcoe_task(io_req->task_params,
+ &task_fc_hdr,
+ &tx_sgl_task_params,
+ &rx_sgl_task_params, 0);
- /* MSTORM only */
- {
- if (task_type == FCOE_TASK_TYPE_MIDPATH) {
- /* Initialize task context */
- data_desc = &task_ctx->mstorm_st_context.fp.data_desc;
-
- /* Set cache sges address and length */
- data_desc->slow.base_sgl_addr.lo =
- U64_LO(mp_req->mp_resp_bd_dma);
- data_desc->slow.base_sgl_addr.hi =
- U64_HI(mp_req->mp_resp_bd_dma);
- data_desc->slow.remainder_num_sges = 1;
- data_desc->slow.curr_sge_off = 0;
- data_desc->slow.curr_sgl_index = 0;
-
- /*
- * Also need to fil in non-fastpath response address
- * for middle path commands.
- */
- task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.lo =
- U64_LO(mp_req->mp_resp_bd_dma);
- task_ctx->mstorm_st_context.non_fp.rsp_buf_addr.hi =
- U64_HI(mp_req->mp_resp_bd_dma);
- }
- }
-
- /* USTORM ONLY */
- {
- task_ctx->ustorm_ag_context.global_cq_num = 0;
- }
-
- /* I/O stats. Middle path commands always use slow SGEs */
- qedf->slow_sge_ios++;
- io_req->sge_type = QEDF_IOREQ_SLOW_SGE;
+ /* Midpath requests always consume 1 SGE */
+ qedf->single_sge_ios++;
}
-void qedf_add_to_sq(struct qedf_rport *fcport, u16 xid, u32 ptu_invalidate,
- enum fcoe_task_type req_type, u32 offset)
+/* Presumed that fcport->rport_lock is held */
+u16 qedf_get_sqe_idx(struct qedf_rport *fcport)
{
- struct fcoe_wqe *sqe;
uint16_t total_sqe = (fcport->sq_mem_size)/(sizeof(struct fcoe_wqe));
+ u16 rval;
- sqe = &fcport->sq[fcport->sq_prod_idx];
+ rval = fcport->sq_prod_idx;
+ /* Adjust ring index */
fcport->sq_prod_idx++;
fcport->fw_sq_prod_idx++;
if (fcport->sq_prod_idx == total_sqe)
fcport->sq_prod_idx = 0;
- switch (req_type) {
- case FCOE_TASK_TYPE_WRITE_INITIATOR:
- case FCOE_TASK_TYPE_READ_INITIATOR:
- SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE, SEND_FCOE_CMD);
- if (ptu_invalidate)
- SET_FIELD(sqe->flags, FCOE_WQE_INVALIDATE_PTU, 1);
- break;
- case FCOE_TASK_TYPE_MIDPATH:
- SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE, SEND_FCOE_MIDPATH);
- break;
- case FCOE_TASK_TYPE_ABTS:
- SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE,
- SEND_FCOE_ABTS_REQUEST);
- break;
- case FCOE_TASK_TYPE_EXCHANGE_CLEANUP:
- SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE,
- FCOE_EXCHANGE_CLEANUP);
- break;
- case FCOE_TASK_TYPE_SEQUENCE_CLEANUP:
- SET_FIELD(sqe->flags, FCOE_WQE_REQ_TYPE,
- FCOE_SEQUENCE_RECOVERY);
- /* NOTE: offset param only used for sequence recovery */
- sqe->additional_info_union.seq_rec_updated_offset = offset;
- break;
- case FCOE_TASK_TYPE_UNSOLICITED:
- break;
- default:
- break;
- }
-
- sqe->task_id = xid;
-
- /* Make sure SQ data is coherent */
- wmb();
-
+ return rval;
}
void qedf_ring_doorbell(struct qedf_rport *fcport)
@@ -1029,7 +847,8 @@ int qedf_post_io_req(struct qedf_rport *fcport, struct qedf_ioreq *io_req)
struct fcoe_task_context *task_ctx;
u16 xid;
enum fcoe_task_type req_type = 0;
- u32 ptu_invalidate = 0;
+ struct fcoe_wqe *sqe;
+ u16 sqe_idx;
/* Initialize rest of io_req fileds */
io_req->data_xfer_len = scsi_bufflen(sc_cmd);
@@ -1061,6 +880,16 @@ int qedf_post_io_req(struct qedf_rport *fcport, struct qedf_ioreq *io_req)
return -EAGAIN;
}
+ if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
+ QEDF_ERR(&(qedf->dbg_ctx), "Session not offloaded yet.\n");
+ kref_put(&io_req->refcount, qedf_release_cmd);
+ }
+
+ /* Obtain free SQE */
+ sqe_idx = qedf_get_sqe_idx(fcport);
+ sqe = &fcport->sq[sqe_idx];
+ memset(sqe, 0, sizeof(struct fcoe_wqe));
+
/* Get the task context */
task_ctx = qedf_get_task_mem(&qedf->tasks, xid);
if (!task_ctx) {
@@ -1070,15 +899,7 @@ int qedf_post_io_req(struct qedf_rport *fcport, struct qedf_ioreq *io_req)
return -EINVAL;
}
- qedf_init_task(fcport, lport, io_req, &ptu_invalidate, task_ctx);
-
- if (!test_bit(QEDF_RPORT_SESSION_READY, &fcport->flags)) {
- QEDF_ERR(&(qedf->dbg_ctx), "Session not offloaded yet.\n");
- kref_put(&io_req->refcount, qedf_release_cmd);
- }
-
- /* Obtain free SQ entry */
- qedf_add_to_sq(fcport, xid, ptu_invalidate, req_type, 0);
+ qedf_init_task(fcport, lport, io_req, task_ctx, sqe);
/* Ring doorbell */
qedf_ring_doorbell(fcport);
@@ -1342,7 +1163,7 @@ void qedf_scsi_completion(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
} else {
refcount = kref_read(&io_req->refcount);
QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO,
- "%d:0:%d:%d xid=0x%0x op=0x%02x "
+ "%d:0:%d:%lld xid=0x%0x op=0x%02x "
"lba=%02x%02x%02x%02x cdb_status=%d "
"fcp_resid=0x%x refcount=%d.\n",
qedf->lport->host->host_no, sc_cmd->device->id,
@@ -1426,7 +1247,7 @@ void qedf_scsi_done(struct qedf_ctx *qedf, struct qedf_ioreq *io_req,
sc_cmd->result = result << 16;
refcount = kref_read(&io_req->refcount);
- QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO, "%d:0:%d:%d: Completing "
+ QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO, "%d:0:%d:%lld: Completing "
"sc_cmd=%p result=0x%08x op=0x%02x lba=0x%02x%02x%02x%02x, "
"allowed=%d retries=%d refcount=%d.\n",
qedf->lport->host->host_no, sc_cmd->device->id,
@@ -1661,6 +1482,8 @@ int qedf_initiate_abts(struct qedf_ioreq *io_req, bool return_scsi_cmd_on_abts)
u32 r_a_tov = 0;
int rc = 0;
unsigned long flags;
+ struct fcoe_wqe *sqe;
+ u16 sqe_idx;
r_a_tov = rdata->r_a_tov;
lport = qedf->lport;
@@ -1712,10 +1535,12 @@ int qedf_initiate_abts(struct qedf_ioreq *io_req, bool return_scsi_cmd_on_abts)
spin_lock_irqsave(&fcport->rport_lock, flags);
- /* Add ABTS to send queue */
- qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_ABTS, 0);
+ sqe_idx = qedf_get_sqe_idx(fcport);
+ sqe = &fcport->sq[sqe_idx];
+ memset(sqe, 0, sizeof(struct fcoe_wqe));
+ io_req->task_params->sqe = sqe;
- /* Ring doorbell */
+ init_initiator_abort_fcoe_task(io_req->task_params);
qedf_ring_doorbell(fcport);
spin_unlock_irqrestore(&fcport->rport_lock, flags);
@@ -1784,8 +1609,8 @@ void qedf_process_abts_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
int qedf_init_mp_req(struct qedf_ioreq *io_req)
{
struct qedf_mp_req *mp_req;
- struct fcoe_sge *mp_req_bd;
- struct fcoe_sge *mp_resp_bd;
+ struct scsi_sge *mp_req_bd;
+ struct scsi_sge *mp_resp_bd;
struct qedf_ctx *qedf = io_req->fcport->qedf;
dma_addr_t addr;
uint64_t sz;
@@ -1819,7 +1644,7 @@ int qedf_init_mp_req(struct qedf_ioreq *io_req)
}
/* Allocate and map mp_req_bd and mp_resp_bd */
- sz = sizeof(struct fcoe_sge);
+ sz = sizeof(struct scsi_sge);
mp_req->mp_req_bd = dma_alloc_coherent(&qedf->pdev->dev, sz,
&mp_req->mp_req_bd_dma, GFP_KERNEL);
if (!mp_req->mp_req_bd) {
@@ -1841,7 +1666,7 @@ int qedf_init_mp_req(struct qedf_ioreq *io_req)
mp_req_bd = mp_req->mp_req_bd;
mp_req_bd->sge_addr.lo = U64_LO(addr);
mp_req_bd->sge_addr.hi = U64_HI(addr);
- mp_req_bd->size = QEDF_PAGE_SIZE;
+ mp_req_bd->sge_len = QEDF_PAGE_SIZE;
/*
* MP buffer is either a task mgmt command or an ELS.
@@ -1852,7 +1677,7 @@ int qedf_init_mp_req(struct qedf_ioreq *io_req)
addr = mp_req->resp_buf_dma;
mp_resp_bd->sge_addr.lo = U64_LO(addr);
mp_resp_bd->sge_addr.hi = U64_HI(addr);
- mp_resp_bd->size = QEDF_PAGE_SIZE;
+ mp_resp_bd->sge_len = QEDF_PAGE_SIZE;
return 0;
}
@@ -1895,6 +1720,8 @@ int qedf_initiate_cleanup(struct qedf_ioreq *io_req,
int tmo = 0;
int rc = SUCCESS;
unsigned long flags;
+ struct fcoe_wqe *sqe;
+ u16 sqe_idx;
fcport = io_req->fcport;
if (!fcport) {
@@ -1940,12 +1767,16 @@ int qedf_initiate_cleanup(struct qedf_ioreq *io_req,
init_completion(&io_req->tm_done);
- /* Obtain free SQ entry */
spin_lock_irqsave(&fcport->rport_lock, flags);
- qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_EXCHANGE_CLEANUP, 0);
- /* Ring doorbell */
+ sqe_idx = qedf_get_sqe_idx(fcport);
+ sqe = &fcport->sq[sqe_idx];
+ memset(sqe, 0, sizeof(struct fcoe_wqe));
+ io_req->task_params->sqe = sqe;
+
+ init_initiator_cleanup_fcoe_task(io_req->task_params);
qedf_ring_doorbell(fcport);
+
spin_unlock_irqrestore(&fcport->rport_lock, flags);
tmo = wait_for_completion_timeout(&io_req->tm_done,
@@ -1991,16 +1822,15 @@ static int qedf_execute_tmf(struct qedf_rport *fcport, struct scsi_cmnd *sc_cmd,
uint8_t tm_flags)
{
struct qedf_ioreq *io_req;
- struct qedf_mp_req *tm_req;
struct fcoe_task_context *task;
- struct fc_frame_header *fc_hdr;
- struct fcp_cmnd *fcp_cmnd;
struct qedf_ctx *qedf = fcport->qedf;
+ struct fc_lport *lport = qedf->lport;
int rc = 0;
uint16_t xid;
- uint32_t sid, did;
int tmo = 0;
unsigned long flags;
+ struct fcoe_wqe *sqe;
+ u16 sqe_idx;
if (!sc_cmd) {
QEDF_ERR(&(qedf->dbg_ctx), "invalid arg\n");
@@ -2031,36 +1861,14 @@ static int qedf_execute_tmf(struct qedf_rport *fcport, struct scsi_cmnd *sc_cmd,
/* Set the return CPU to be the same as the request one */
io_req->cpu = smp_processor_id();
- tm_req = (struct qedf_mp_req *)&(io_req->mp_req);
-
- rc = qedf_init_mp_req(io_req);
- if (rc == FAILED) {
- QEDF_ERR(&(qedf->dbg_ctx), "Task mgmt MP request init "
- "failed\n");
- kref_put(&io_req->refcount, qedf_release_cmd);
- goto reset_tmf_err;
- }
-
/* Set TM flags */
- io_req->io_req_flags = 0;
- tm_req->tm_flags = tm_flags;
+ io_req->io_req_flags = QEDF_READ;
+ io_req->data_xfer_len = 0;
+ io_req->tm_flags = tm_flags;
/* Default is to return a SCSI command when an error occurs */
io_req->return_scsi_cmd_on_abts = true;
- /* Fill FCP_CMND */
- qedf_build_fcp_cmnd(io_req, (struct fcp_cmnd *)tm_req->req_buf);
- fcp_cmnd = (struct fcp_cmnd *)tm_req->req_buf;
- memset(fcp_cmnd->fc_cdb, 0, FCP_CMND_LEN);
- fcp_cmnd->fc_dl = 0;
-
- /* Fill FC header */
- fc_hdr = &(tm_req->req_fc_hdr);
- sid = fcport->sid;
- did = fcport->rdata->ids.port_id;
- __fc_fill_fc_hdr(fc_hdr, FC_RCTL_DD_UNSOL_CMD, sid, did,
- FC_TYPE_FCP, FC_FC_FIRST_SEQ | FC_FC_END_SEQ |
- FC_FC_SEQ_INIT, 0);
/* Obtain exchange id */
xid = io_req->xid;
@@ -2069,16 +1877,18 @@ static int qedf_execute_tmf(struct qedf_rport *fcport, struct scsi_cmnd *sc_cmd,
/* Initialize task context for this IO request */
task = qedf_get_task_mem(&qedf->tasks, xid);
- qedf_init_mp_task(io_req, task);
init_completion(&io_req->tm_done);
- /* Obtain free SQ entry */
spin_lock_irqsave(&fcport->rport_lock, flags);
- qedf_add_to_sq(fcport, xid, 0, FCOE_TASK_TYPE_MIDPATH, 0);
- /* Ring doorbell */
+ sqe_idx = qedf_get_sqe_idx(fcport);
+ sqe = &fcport->sq[sqe_idx];
+ memset(sqe, 0, sizeof(struct fcoe_wqe));
+
+ qedf_init_task(fcport, lport, io_req, task, sqe);
qedf_ring_doorbell(fcport);
+
spin_unlock_irqrestore(&fcport->rport_lock, flags);
tmo = wait_for_completion_timeout(&io_req->tm_done,
@@ -2162,14 +1972,6 @@ void qedf_process_tmf_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe,
struct qedf_ioreq *io_req)
{
struct fcoe_cqe_rsp_info *fcp_rsp;
- struct fcoe_cqe_midpath_info *mp_info;
-
-
- /* Get TMF response length from CQE */
- mp_info = &cqe->cqe_info.midpath_info;
- io_req->mp_req.resp_len = mp_info->data_placement_size;
- QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_SCSI_TM,
- "Response len is %d.\n", io_req->mp_req.resp_len);
fcp_rsp = &cqe->cqe_info.rsp_info;
qedf_parse_fcp_rsp(io_req, fcp_rsp);
diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c
index d9d7a86..8e2a160 100644
--- a/drivers/scsi/qedf/qedf_main.c
+++ b/drivers/scsi/qedf/qedf_main.c
@@ -2456,8 +2456,8 @@ static int qedf_alloc_bdq(struct qedf_ctx *qedf)
}
QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
- "BDQ PBL addr=0x%p dma=0x%llx.\n", qedf->bdq_pbl,
- qedf->bdq_pbl_dma);
+ "BDQ PBL addr=0x%p dma=%pad\n",
+ qedf->bdq_pbl, &qedf->bdq_pbl_dma);
/*
* Populate BDQ PBL with physical and virtual address of individual
diff --git a/drivers/scsi/qedi/Makefile b/drivers/scsi/qedi/Makefile
index 2b3e16b..90a6925 100644
--- a/drivers/scsi/qedi/Makefile
+++ b/drivers/scsi/qedi/Makefile
@@ -1,5 +1,5 @@
obj-$(CONFIG_QEDI) := qedi.o
qedi-y := qedi_main.o qedi_iscsi.o qedi_fw.o qedi_sysfs.o \
- qedi_dbg.o
+ qedi_dbg.o qedi_fw_api.o
qedi-$(CONFIG_DEBUG_FS) += qedi_debugfs.o
diff --git a/drivers/scsi/qedi/qedi_debugfs.c b/drivers/scsi/qedi/qedi_debugfs.c
index 9559362..5941719 100644
--- a/drivers/scsi/qedi/qedi_debugfs.c
+++ b/drivers/scsi/qedi/qedi_debugfs.c
@@ -14,7 +14,7 @@
#include <linux/debugfs.h>
#include <linux/module.h>
-int do_not_recover;
+int qedi_do_not_recover;
static struct dentry *qedi_dbg_root;
void
@@ -74,22 +74,22 @@ qedi_dbg_exit(void)
static ssize_t
qedi_dbg_do_not_recover_enable(struct qedi_dbg_ctx *qedi_dbg)
{
- if (!do_not_recover)
- do_not_recover = 1;
+ if (!qedi_do_not_recover)
+ qedi_do_not_recover = 1;
QEDI_INFO(qedi_dbg, QEDI_LOG_DEBUGFS, "do_not_recover=%d\n",
- do_not_recover);
+ qedi_do_not_recover);
return 0;
}
static ssize_t
qedi_dbg_do_not_recover_disable(struct qedi_dbg_ctx *qedi_dbg)
{
- if (do_not_recover)
- do_not_recover = 0;
+ if (qedi_do_not_recover)
+ qedi_do_not_recover = 0;
QEDI_INFO(qedi_dbg, QEDI_LOG_DEBUGFS, "do_not_recover=%d\n",
- do_not_recover);
+ qedi_do_not_recover);
return 0;
}
@@ -141,7 +141,7 @@ qedi_dbg_do_not_recover_cmd_read(struct file *filp, char __user *buffer,
if (*ppos)
return 0;
- cnt = sprintf(buffer, "do_not_recover=%d\n", do_not_recover);
+ cnt = sprintf(buffer, "do_not_recover=%d\n", qedi_do_not_recover);
cnt = min_t(int, count, cnt - *ppos);
*ppos += cnt;
return cnt;
diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c
index c9f0ef4..d6978cb 100644
--- a/drivers/scsi/qedi/qedi_fw.c
+++ b/drivers/scsi/qedi/qedi_fw.c
@@ -14,6 +14,8 @@
#include "qedi.h"
#include "qedi_iscsi.h"
#include "qedi_gbl.h"
+#include "qedi_fw_iscsi.h"
+#include "qedi_fw_scsi.h"
static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn,
struct iscsi_task *mtask);
@@ -53,8 +55,8 @@ static void qedi_process_logout_resp(struct qedi_ctx *qedi,
resp_hdr->exp_cmdsn = cpu_to_be32(cqe_logout_response->exp_cmd_sn);
resp_hdr->max_cmdsn = cpu_to_be32(cqe_logout_response->max_cmd_sn);
- resp_hdr->t2wait = cpu_to_be32(cqe_logout_response->time2wait);
- resp_hdr->t2retain = cpu_to_be32(cqe_logout_response->time2retain);
+ resp_hdr->t2wait = cpu_to_be32(cqe_logout_response->time_2_wait);
+ resp_hdr->t2retain = cpu_to_be32(cqe_logout_response->time_2_retain);
QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_TID,
"Freeing tid=0x%x for cid=0x%x\n",
@@ -975,81 +977,6 @@ void qedi_fp_process_cqes(struct qedi_work *work)
return;
}
-static void qedi_add_to_sq(struct qedi_conn *qedi_conn, struct iscsi_task *task,
- u16 tid, uint16_t ptu_invalidate, int is_cleanup)
-{
- struct iscsi_wqe *wqe;
- struct iscsi_wqe_field *cont_field;
- struct qedi_endpoint *ep;
- struct scsi_cmnd *sc = task->sc;
- struct iscsi_login_req *login_hdr;
- struct qedi_cmd *cmd = task->dd_data;
-
- login_hdr = (struct iscsi_login_req *)task->hdr;
- ep = qedi_conn->ep;
- wqe = &ep->sq[ep->sq_prod_idx];
-
- memset(wqe, 0, sizeof(*wqe));
-
- ep->sq_prod_idx++;
- ep->fw_sq_prod_idx++;
- if (ep->sq_prod_idx == QEDI_SQ_SIZE)
- ep->sq_prod_idx = 0;
-
- if (is_cleanup) {
- SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE,
- ISCSI_WQE_TYPE_TASK_CLEANUP);
- wqe->task_id = tid;
- return;
- }
-
- if (ptu_invalidate) {
- SET_FIELD(wqe->flags, ISCSI_WQE_PTU_INVALIDATE,
- ISCSI_WQE_SET_PTU_INVALIDATE);
- }
-
- cont_field = &wqe->cont_prevtid_union.cont_field;
-
- switch (task->hdr->opcode & ISCSI_OPCODE_MASK) {
- case ISCSI_OP_LOGIN:
- case ISCSI_OP_TEXT:
- SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE,
- ISCSI_WQE_TYPE_MIDDLE_PATH);
- SET_FIELD(wqe->flags, ISCSI_WQE_NUM_FAST_SGES,
- 1);
- cont_field->contlen_cdbsize_field = ntoh24(login_hdr->dlength);
- break;
- case ISCSI_OP_LOGOUT:
- case ISCSI_OP_NOOP_OUT:
- case ISCSI_OP_SCSI_TMFUNC:
- SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE,
- ISCSI_WQE_TYPE_NORMAL);
- break;
- default:
- if (!sc)
- break;
-
- SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE,
- ISCSI_WQE_TYPE_NORMAL);
- cont_field->contlen_cdbsize_field =
- (sc->sc_data_direction == DMA_TO_DEVICE) ?
- scsi_bufflen(sc) : 0;
- if (cmd->use_slowpath)
- SET_FIELD(wqe->flags, ISCSI_WQE_NUM_FAST_SGES, 0);
- else
- SET_FIELD(wqe->flags, ISCSI_WQE_NUM_FAST_SGES,
- (sc->sc_data_direction ==
- DMA_TO_DEVICE) ?
- min((u16)QEDI_FAST_SGE_COUNT,
- (u16)cmd->io_tbl.sge_valid) : 0);
- break;
- }
-
- wqe->task_id = tid;
- /* Make sure SQ data is coherent */
- wmb();
-}
-
static void qedi_ring_doorbell(struct qedi_conn *qedi_conn)
{
struct iscsi_db_data dbell = { 0 };
@@ -1076,96 +1003,116 @@ static void qedi_ring_doorbell(struct qedi_conn *qedi_conn)
qedi_conn->iscsi_conn_id);
}
+static u16 qedi_get_wqe_idx(struct qedi_conn *qedi_conn)
+{
+ struct qedi_endpoint *ep;
+ u16 rval;
+
+ ep = qedi_conn->ep;
+ rval = ep->sq_prod_idx;
+
+ /* Increament SQ index */
+ ep->sq_prod_idx++;
+ ep->fw_sq_prod_idx++;
+ if (ep->sq_prod_idx == QEDI_SQ_SIZE)
+ ep->sq_prod_idx = 0;
+
+ return rval;
+}
+
int qedi_send_iscsi_login(struct qedi_conn *qedi_conn,
struct iscsi_task *task)
{
- struct qedi_ctx *qedi = qedi_conn->qedi;
+ struct iscsi_login_req_hdr login_req_pdu_header;
+ struct scsi_sgl_task_params tx_sgl_task_params;
+ struct scsi_sgl_task_params rx_sgl_task_params;
+ struct iscsi_task_params task_params;
struct iscsi_task_context *fw_task_ctx;
+ struct qedi_ctx *qedi = qedi_conn->qedi;
struct iscsi_login_req *login_hdr;
- struct iscsi_login_req_hdr *fw_login_req = NULL;
- struct iscsi_cached_sge_ctx *cached_sge = NULL;
- struct iscsi_sge *single_sge = NULL;
- struct iscsi_sge *req_sge = NULL;
- struct iscsi_sge *resp_sge = NULL;
+ struct scsi_sge *req_sge = NULL;
+ struct scsi_sge *resp_sge = NULL;
struct qedi_cmd *qedi_cmd;
- s16 ptu_invalidate = 0;
+ struct qedi_endpoint *ep;
s16 tid = 0;
+ u16 sq_idx = 0;
+ int rval = 0;
- req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
- resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+ req_sge = (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+ resp_sge = (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
qedi_cmd = (struct qedi_cmd *)task->dd_data;
+ ep = qedi_conn->ep;
login_hdr = (struct iscsi_login_req *)task->hdr;
tid = qedi_get_task_idx(qedi);
if (tid == -1)
return -ENOMEM;
- fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+ fw_task_ctx =
+ (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid);
memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
qedi_cmd->task_id = tid;
- /* Ystorm context */
- fw_login_req = &fw_task_ctx->ystorm_st_context.pdu_hdr.login_req;
- fw_login_req->opcode = login_hdr->opcode;
- fw_login_req->version_min = login_hdr->min_version;
- fw_login_req->version_max = login_hdr->max_version;
- fw_login_req->flags_attr = login_hdr->flags;
- fw_login_req->isid_tabc = *((u16 *)login_hdr->isid + 2);
- fw_login_req->isid_d = *((u32 *)login_hdr->isid);
- fw_login_req->tsih = login_hdr->tsih;
+ memset(&task_params, 0, sizeof(task_params));
+ memset(&login_req_pdu_header, 0, sizeof(login_req_pdu_header));
+ memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params));
+ memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params));
+ /* Update header info */
+ login_req_pdu_header.opcode = login_hdr->opcode;
+ login_req_pdu_header.version_min = login_hdr->min_version;
+ login_req_pdu_header.version_max = login_hdr->max_version;
+ login_req_pdu_header.flags_attr = login_hdr->flags;
+ login_req_pdu_header.isid_tabc = swab32p((u32 *)login_hdr->isid);
+ login_req_pdu_header.isid_d = swab16p((u16 *)&login_hdr->isid[4]);
+
+ login_req_pdu_header.tsih = login_hdr->tsih;
+ login_req_pdu_header.hdr_second_dword = ntoh24(login_hdr->dlength);
+
qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
- fw_login_req->itt = qedi_set_itt(tid, get_itt(task->itt));
- fw_login_req->cid = qedi_conn->iscsi_conn_id;
- fw_login_req->cmd_sn = be32_to_cpu(login_hdr->cmdsn);
- fw_login_req->exp_stat_sn = be32_to_cpu(login_hdr->exp_statsn);
- fw_login_req->exp_stat_sn = 0;
+ login_req_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt));
+ login_req_pdu_header.cid = qedi_conn->iscsi_conn_id;
+ login_req_pdu_header.cmd_sn = be32_to_cpu(login_hdr->cmdsn);
+ login_req_pdu_header.exp_stat_sn = be32_to_cpu(login_hdr->exp_statsn);
+ login_req_pdu_header.exp_stat_sn = 0;
- if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
- ptu_invalidate = 1;
- qedi->tid_reuse_count[tid] = 0;
- }
+ /* Fill tx AHS and rx buffer */
+ tx_sgl_task_params.sgl =
+ (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+ tx_sgl_task_params.sgl_phys_addr.lo =
+ (u32)(qedi_conn->gen_pdu.req_dma_addr);
+ tx_sgl_task_params.sgl_phys_addr.hi =
+ (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
+ tx_sgl_task_params.total_buffer_size = ntoh24(login_hdr->dlength);
+ tx_sgl_task_params.num_sges = 1;
- fw_task_ctx->ystorm_st_context.state.reuse_count =
- qedi->tid_reuse_count[tid];
- fw_task_ctx->mstorm_st_context.reuse_count =
- qedi->tid_reuse_count[tid]++;
- cached_sge =
- &fw_task_ctx->ystorm_st_context.state.sgl_ctx_union.cached_sge;
- cached_sge->sge.sge_len = req_sge->sge_len;
- cached_sge->sge.sge_addr.lo = (u32)(qedi_conn->gen_pdu.req_dma_addr);
- cached_sge->sge.sge_addr.hi =
- (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
+ rx_sgl_task_params.sgl =
+ (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+ rx_sgl_task_params.sgl_phys_addr.lo =
+ (u32)(qedi_conn->gen_pdu.resp_dma_addr);
+ rx_sgl_task_params.sgl_phys_addr.hi =
+ (u32)((u64)qedi_conn->gen_pdu.resp_dma_addr >> 32);
+ rx_sgl_task_params.total_buffer_size = resp_sge->sge_len;
+ rx_sgl_task_params.num_sges = 1;
- /* Mstorm context */
- single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge;
- fw_task_ctx->mstorm_st_context.task_type = 0x2;
- fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
- single_sge->sge_addr.lo = resp_sge->sge_addr.lo;
- single_sge->sge_addr.hi = resp_sge->sge_addr.hi;
- single_sge->sge_len = resp_sge->sge_len;
+ /* Fill fw input params */
+ task_params.context = fw_task_ctx;
+ task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id;
+ task_params.itid = tid;
+ task_params.cq_rss_number = 0;
+ task_params.tx_io_size = ntoh24(login_hdr->dlength);
+ task_params.rx_io_size = resp_sge->sge_len;
- SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
- ISCSI_MFLAGS_SINGLE_SGE, 1);
- SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
- ISCSI_MFLAGS_SLOW_IO, 0);
- fw_task_ctx->mstorm_st_context.sgl_size = 1;
- fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len;
+ sq_idx = qedi_get_wqe_idx(qedi_conn);
+ task_params.sqe = &ep->sq[sq_idx];
- /* Ustorm context */
- fw_task_ctx->ustorm_st_context.rem_rcv_len = resp_sge->sge_len;
- fw_task_ctx->ustorm_st_context.exp_data_transfer_len =
- ntoh24(login_hdr->dlength);
- fw_task_ctx->ustorm_st_context.exp_data_sn = 0;
- fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
- fw_task_ctx->ustorm_st_context.task_type = 0x2;
- fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
- fw_task_ctx->ustorm_ag_context.exp_data_acked =
- ntoh24(login_hdr->dlength);
- SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
- USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
- SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
- USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0);
+ memset(task_params.sqe, 0, sizeof(struct iscsi_wqe));
+ rval = init_initiator_login_request_task(&task_params,
+ &login_req_pdu_header,
+ &tx_sgl_task_params,
+ &rx_sgl_task_params);
+ if (rval)
+ return -1;
spin_lock(&qedi_conn->list_lock);
list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
@@ -1173,7 +1120,6 @@ int qedi_send_iscsi_login(struct qedi_conn *qedi_conn,
qedi_conn->active_cmd_count++;
spin_unlock(&qedi_conn->list_lock);
- qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
qedi_ring_doorbell(qedi_conn);
return 0;
}
@@ -1181,65 +1127,64 @@ int qedi_send_iscsi_login(struct qedi_conn *qedi_conn,
int qedi_send_iscsi_logout(struct qedi_conn *qedi_conn,
struct iscsi_task *task)
{
- struct qedi_ctx *qedi = qedi_conn->qedi;
- struct iscsi_logout_req_hdr *fw_logout_req = NULL;
- struct iscsi_task_context *fw_task_ctx = NULL;
+ struct iscsi_logout_req_hdr logout_pdu_header;
+ struct scsi_sgl_task_params tx_sgl_task_params;
+ struct scsi_sgl_task_params rx_sgl_task_params;
+ struct iscsi_task_params task_params;
+ struct iscsi_task_context *fw_task_ctx;
struct iscsi_logout *logout_hdr = NULL;
- struct qedi_cmd *qedi_cmd = NULL;
- s16 tid = 0;
- s16 ptu_invalidate = 0;
+ struct qedi_ctx *qedi = qedi_conn->qedi;
+ struct qedi_cmd *qedi_cmd;
+ struct qedi_endpoint *ep;
+ s16 tid = 0;
+ u16 sq_idx = 0;
+ int rval = 0;
qedi_cmd = (struct qedi_cmd *)task->dd_data;
logout_hdr = (struct iscsi_logout *)task->hdr;
+ ep = qedi_conn->ep;
tid = qedi_get_task_idx(qedi);
if (tid == -1)
return -ENOMEM;
- fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
-
+ fw_task_ctx =
+ (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid);
memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
+
qedi_cmd->task_id = tid;
- /* Ystorm context */
- fw_logout_req = &fw_task_ctx->ystorm_st_context.pdu_hdr.logout_req;
- fw_logout_req->opcode = ISCSI_OPCODE_LOGOUT_REQUEST;
- fw_logout_req->reason_code = 0x80 | logout_hdr->flags;
+ memset(&task_params, 0, sizeof(task_params));
+ memset(&logout_pdu_header, 0, sizeof(logout_pdu_header));
+ memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params));
+ memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params));
+
+ /* Update header info */
+ logout_pdu_header.opcode = logout_hdr->opcode;
+ logout_pdu_header.reason_code = 0x80 | logout_hdr->flags;
qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
- fw_logout_req->itt = qedi_set_itt(tid, get_itt(task->itt));
- fw_logout_req->exp_stat_sn = be32_to_cpu(logout_hdr->exp_statsn);
- fw_logout_req->cmd_sn = be32_to_cpu(logout_hdr->cmdsn);
+ logout_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt));
+ logout_pdu_header.exp_stat_sn = be32_to_cpu(logout_hdr->exp_statsn);
+ logout_pdu_header.cmd_sn = be32_to_cpu(logout_hdr->cmdsn);
+ logout_pdu_header.cid = qedi_conn->iscsi_conn_id;
- if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
- ptu_invalidate = 1;
- qedi->tid_reuse_count[tid] = 0;
- }
- fw_task_ctx->ystorm_st_context.state.reuse_count =
- qedi->tid_reuse_count[tid];
- fw_task_ctx->mstorm_st_context.reuse_count =
- qedi->tid_reuse_count[tid]++;
- fw_logout_req->cid = qedi_conn->iscsi_conn_id;
- fw_task_ctx->ystorm_st_context.state.buffer_offset[0] = 0;
+ /* Fill fw input params */
+ task_params.context = fw_task_ctx;
+ task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id;
+ task_params.itid = tid;
+ task_params.cq_rss_number = 0;
+ task_params.tx_io_size = 0;
+ task_params.rx_io_size = 0;
- /* Mstorm context */
- fw_task_ctx->mstorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH;
- fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
+ sq_idx = qedi_get_wqe_idx(qedi_conn);
+ task_params.sqe = &ep->sq[sq_idx];
+ memset(task_params.sqe, 0, sizeof(struct iscsi_wqe));
- /* Ustorm context */
- fw_task_ctx->ustorm_st_context.rem_rcv_len = 0;
- fw_task_ctx->ustorm_st_context.exp_data_transfer_len = 0;
- fw_task_ctx->ustorm_st_context.exp_data_sn = 0;
- fw_task_ctx->ustorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH;
- fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
-
- SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
- USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0);
- SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
- ISCSI_REG1_NUM_FAST_SGES, 0);
-
- fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
- SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
- USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
+ rval = init_initiator_logout_request_task(&task_params,
+ &logout_pdu_header,
+ NULL, NULL);
+ if (rval)
+ return -1;
spin_lock(&qedi_conn->list_lock);
list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
@@ -1247,9 +1192,7 @@ int qedi_send_iscsi_logout(struct qedi_conn *qedi_conn,
qedi_conn->active_cmd_count++;
spin_unlock(&qedi_conn->list_lock);
- qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
qedi_ring_doorbell(qedi_conn);
-
return 0;
}
@@ -1461,9 +1404,9 @@ static void qedi_tmf_work(struct work_struct *work)
get_itt(tmf_hdr->rtt), get_itt(ctask->itt), cmd->task_id,
qedi_conn->iscsi_conn_id);
- if (do_not_recover) {
+ if (qedi_do_not_recover) {
QEDI_ERR(&qedi->dbg_ctx, "DONT SEND CLEANUP/ABORT %d\n",
- do_not_recover);
+ qedi_do_not_recover);
goto abort_ret;
}
@@ -1533,47 +1476,46 @@ static void qedi_tmf_work(struct work_struct *work)
static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn,
struct iscsi_task *mtask)
{
- struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+ struct iscsi_tmf_request_hdr tmf_pdu_header;
+ struct iscsi_task_params task_params;
struct qedi_ctx *qedi = qedi_conn->qedi;
struct iscsi_task_context *fw_task_ctx;
- struct iscsi_tmf_request_hdr *fw_tmf_request;
- struct iscsi_sge *single_sge;
- struct qedi_cmd *qedi_cmd;
- struct qedi_cmd *cmd;
+ struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
struct iscsi_task *ctask;
struct iscsi_tm *tmf_hdr;
- struct iscsi_sge *req_sge;
- struct iscsi_sge *resp_sge;
- u32 lun[2];
- s16 tid = 0, ptu_invalidate = 0;
+ struct qedi_cmd *qedi_cmd;
+ struct qedi_cmd *cmd;
+ struct qedi_endpoint *ep;
+ u32 scsi_lun[2];
+ s16 tid = 0;
+ u16 sq_idx = 0;
+ int rval = 0;
- req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
- resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
- qedi_cmd = (struct qedi_cmd *)mtask->dd_data;
tmf_hdr = (struct iscsi_tm *)mtask->hdr;
+ qedi_cmd = (struct qedi_cmd *)mtask->dd_data;
+ ep = qedi_conn->ep;
- tid = qedi_cmd->task_id;
- qedi_update_itt_map(qedi, tid, mtask->itt, qedi_cmd);
+ tid = qedi_get_task_idx(qedi);
+ if (tid == -1)
+ return -ENOMEM;
- fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+ fw_task_ctx =
+ (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid);
memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
- fw_tmf_request = &fw_task_ctx->ystorm_st_context.pdu_hdr.tmf_request;
- fw_tmf_request->itt = qedi_set_itt(tid, get_itt(mtask->itt));
- fw_tmf_request->cmd_sn = be32_to_cpu(tmf_hdr->cmdsn);
+ qedi_cmd->task_id = tid;
- memcpy(lun, &tmf_hdr->lun, sizeof(struct scsi_lun));
- fw_tmf_request->lun.lo = be32_to_cpu(lun[0]);
- fw_tmf_request->lun.hi = be32_to_cpu(lun[1]);
+ memset(&task_params, 0, sizeof(task_params));
+ memset(&tmf_pdu_header, 0, sizeof(tmf_pdu_header));
- if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
- ptu_invalidate = 1;
- qedi->tid_reuse_count[tid] = 0;
- }
- fw_task_ctx->ystorm_st_context.state.reuse_count =
- qedi->tid_reuse_count[tid];
- fw_task_ctx->mstorm_st_context.reuse_count =
- qedi->tid_reuse_count[tid]++;
+ /* Update header info */
+ qedi_update_itt_map(qedi, tid, mtask->itt, qedi_cmd);
+ tmf_pdu_header.itt = qedi_set_itt(tid, get_itt(mtask->itt));
+ tmf_pdu_header.cmd_sn = be32_to_cpu(tmf_hdr->cmdsn);
+
+ memcpy(scsi_lun, &tmf_hdr->lun, sizeof(struct scsi_lun));
+ tmf_pdu_header.lun.lo = be32_to_cpu(scsi_lun[0]);
+ tmf_pdu_header.lun.hi = be32_to_cpu(scsi_lun[1]);
if ((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
ISCSI_TM_FUNC_ABORT_TASK) {
@@ -1584,53 +1526,34 @@ static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn,
return 0;
}
cmd = (struct qedi_cmd *)ctask->dd_data;
- fw_tmf_request->rtt =
+ tmf_pdu_header.rtt =
qedi_set_itt(cmd->task_id,
get_itt(tmf_hdr->rtt));
} else {
- fw_tmf_request->rtt = ISCSI_RESERVED_TAG;
+ tmf_pdu_header.rtt = ISCSI_RESERVED_TAG;
}
- fw_tmf_request->opcode = tmf_hdr->opcode;
- fw_tmf_request->function = tmf_hdr->flags;
- fw_tmf_request->hdr_second_dword = ntoh24(tmf_hdr->dlength);
- fw_tmf_request->ref_cmd_sn = be32_to_cpu(tmf_hdr->refcmdsn);
+ tmf_pdu_header.opcode = tmf_hdr->opcode;
+ tmf_pdu_header.function = tmf_hdr->flags;
+ tmf_pdu_header.hdr_second_dword = ntoh24(tmf_hdr->dlength);
+ tmf_pdu_header.ref_cmd_sn = be32_to_cpu(tmf_hdr->refcmdsn);
- single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge;
- fw_task_ctx->mstorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH;
- fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
- single_sge->sge_addr.lo = resp_sge->sge_addr.lo;
- single_sge->sge_addr.hi = resp_sge->sge_addr.hi;
- single_sge->sge_len = resp_sge->sge_len;
+ /* Fill fw input params */
+ task_params.context = fw_task_ctx;
+ task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id;
+ task_params.itid = tid;
+ task_params.cq_rss_number = 0;
+ task_params.tx_io_size = 0;
+ task_params.rx_io_size = 0;
- SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
- ISCSI_MFLAGS_SINGLE_SGE, 1);
- SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
- ISCSI_MFLAGS_SLOW_IO, 0);
- fw_task_ctx->mstorm_st_context.sgl_size = 1;
- fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len;
+ sq_idx = qedi_get_wqe_idx(qedi_conn);
+ task_params.sqe = &ep->sq[sq_idx];
- /* Ustorm context */
- fw_task_ctx->ustorm_st_context.rem_rcv_len = 0;
- fw_task_ctx->ustorm_st_context.exp_data_transfer_len = 0;
- fw_task_ctx->ustorm_st_context.exp_data_sn = 0;
- fw_task_ctx->ustorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH;
- fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
-
- SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
- USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0);
- SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
- ISCSI_REG1_NUM_FAST_SGES, 0);
-
- fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
- SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
- USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
- fw_task_ctx->ustorm_st_context.lun.lo = be32_to_cpu(lun[0]);
- fw_task_ctx->ustorm_st_context.lun.hi = be32_to_cpu(lun[1]);
-
- QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
- "Add TMF to SQ, tmf tid=0x%x, itt=0x%x, cid=0x%x\n",
- tid, mtask->itt, qedi_conn->iscsi_conn_id);
+ memset(task_params.sqe, 0, sizeof(struct iscsi_wqe));
+ rval = init_initiator_tmf_request_task(&task_params,
+ &tmf_pdu_header);
+ if (rval)
+ return -1;
spin_lock(&qedi_conn->list_lock);
list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
@@ -1638,7 +1561,6 @@ static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn,
qedi_conn->active_cmd_count++;
spin_unlock(&qedi_conn->list_lock);
- qedi_add_to_sq(qedi_conn, mtask, tid, ptu_invalidate, false);
qedi_ring_doorbell(qedi_conn);
return 0;
}
@@ -1689,101 +1611,98 @@ int qedi_iscsi_abort_work(struct qedi_conn *qedi_conn,
int qedi_send_iscsi_text(struct qedi_conn *qedi_conn,
struct iscsi_task *task)
{
- struct qedi_ctx *qedi = qedi_conn->qedi;
+ struct iscsi_text_request_hdr text_request_pdu_header;
+ struct scsi_sgl_task_params tx_sgl_task_params;
+ struct scsi_sgl_task_params rx_sgl_task_params;
+ struct iscsi_task_params task_params;
struct iscsi_task_context *fw_task_ctx;
- struct iscsi_text_request_hdr *fw_text_request;
- struct iscsi_cached_sge_ctx *cached_sge;
- struct iscsi_sge *single_sge;
- struct qedi_cmd *qedi_cmd;
- /* For 6.5 hdr iscsi_hdr */
+ struct qedi_ctx *qedi = qedi_conn->qedi;
struct iscsi_text *text_hdr;
- struct iscsi_sge *req_sge;
- struct iscsi_sge *resp_sge;
- s16 ptu_invalidate = 0;
+ struct scsi_sge *req_sge = NULL;
+ struct scsi_sge *resp_sge = NULL;
+ struct qedi_cmd *qedi_cmd;
+ struct qedi_endpoint *ep;
s16 tid = 0;
+ u16 sq_idx = 0;
+ int rval = 0;
- req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
- resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+ req_sge = (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+ resp_sge = (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
qedi_cmd = (struct qedi_cmd *)task->dd_data;
text_hdr = (struct iscsi_text *)task->hdr;
+ ep = qedi_conn->ep;
tid = qedi_get_task_idx(qedi);
if (tid == -1)
return -ENOMEM;
- fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+ fw_task_ctx =
+ (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid);
memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
qedi_cmd->task_id = tid;
- /* Ystorm context */
- fw_text_request =
- &fw_task_ctx->ystorm_st_context.pdu_hdr.text_request;
- fw_text_request->opcode = text_hdr->opcode;
- fw_text_request->flags_attr = text_hdr->flags;
+ memset(&task_params, 0, sizeof(task_params));
+ memset(&text_request_pdu_header, 0, sizeof(text_request_pdu_header));
+ memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params));
+ memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params));
+
+ /* Update header info */
+ text_request_pdu_header.opcode = text_hdr->opcode;
+ text_request_pdu_header.flags_attr = text_hdr->flags;
qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
- fw_text_request->itt = qedi_set_itt(tid, get_itt(task->itt));
- fw_text_request->ttt = text_hdr->ttt;
- fw_text_request->cmd_sn = be32_to_cpu(text_hdr->cmdsn);
- fw_text_request->exp_stat_sn = be32_to_cpu(text_hdr->exp_statsn);
- fw_text_request->hdr_second_dword = ntoh24(text_hdr->dlength);
+ text_request_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt));
+ text_request_pdu_header.ttt = text_hdr->ttt;
+ text_request_pdu_header.cmd_sn = be32_to_cpu(text_hdr->cmdsn);
+ text_request_pdu_header.exp_stat_sn = be32_to_cpu(text_hdr->exp_statsn);
+ text_request_pdu_header.hdr_second_dword = ntoh24(text_hdr->dlength);
- if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
- ptu_invalidate = 1;
- qedi->tid_reuse_count[tid] = 0;
- }
- fw_task_ctx->ystorm_st_context.state.reuse_count =
- qedi->tid_reuse_count[tid];
- fw_task_ctx->mstorm_st_context.reuse_count =
- qedi->tid_reuse_count[tid]++;
-
- cached_sge =
- &fw_task_ctx->ystorm_st_context.state.sgl_ctx_union.cached_sge;
- cached_sge->sge.sge_len = req_sge->sge_len;
- cached_sge->sge.sge_addr.lo = (u32)(qedi_conn->gen_pdu.req_dma_addr);
- cached_sge->sge.sge_addr.hi =
+ /* Fill tx AHS and rx buffer */
+ tx_sgl_task_params.sgl =
+ (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+ tx_sgl_task_params.sgl_phys_addr.lo =
+ (u32)(qedi_conn->gen_pdu.req_dma_addr);
+ tx_sgl_task_params.sgl_phys_addr.hi =
(u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
+ tx_sgl_task_params.total_buffer_size = req_sge->sge_len;
+ tx_sgl_task_params.num_sges = 1;
- /* Mstorm context */
- single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge;
- fw_task_ctx->mstorm_st_context.task_type = 0x2;
- fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
- single_sge->sge_addr.lo = resp_sge->sge_addr.lo;
- single_sge->sge_addr.hi = resp_sge->sge_addr.hi;
- single_sge->sge_len = resp_sge->sge_len;
+ rx_sgl_task_params.sgl =
+ (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+ rx_sgl_task_params.sgl_phys_addr.lo =
+ (u32)(qedi_conn->gen_pdu.resp_dma_addr);
+ rx_sgl_task_params.sgl_phys_addr.hi =
+ (u32)((u64)qedi_conn->gen_pdu.resp_dma_addr >> 32);
+ rx_sgl_task_params.total_buffer_size = resp_sge->sge_len;
+ rx_sgl_task_params.num_sges = 1;
- SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
- ISCSI_MFLAGS_SINGLE_SGE, 1);
- SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
- ISCSI_MFLAGS_SLOW_IO, 0);
- fw_task_ctx->mstorm_st_context.sgl_size = 1;
- fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len;
+ /* Fill fw input params */
+ task_params.context = fw_task_ctx;
+ task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id;
+ task_params.itid = tid;
+ task_params.cq_rss_number = 0;
+ task_params.tx_io_size = ntoh24(text_hdr->dlength);
+ task_params.rx_io_size = resp_sge->sge_len;
- /* Ustorm context */
- fw_task_ctx->ustorm_ag_context.exp_data_acked =
- ntoh24(text_hdr->dlength);
- fw_task_ctx->ustorm_st_context.rem_rcv_len = resp_sge->sge_len;
- fw_task_ctx->ustorm_st_context.exp_data_transfer_len =
- ntoh24(text_hdr->dlength);
- fw_task_ctx->ustorm_st_context.exp_data_sn =
- be32_to_cpu(text_hdr->exp_statsn);
- fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
- fw_task_ctx->ustorm_st_context.task_type = 0x2;
- fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
- SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
- USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
+ sq_idx = qedi_get_wqe_idx(qedi_conn);
+ task_params.sqe = &ep->sq[sq_idx];
- /* Add command in active command list */
+ memset(task_params.sqe, 0, sizeof(struct iscsi_wqe));
+ rval = init_initiator_text_request_task(&task_params,
+ &text_request_pdu_header,
+ &tx_sgl_task_params,
+ &rx_sgl_task_params);
+ if (rval)
+ return -1;
+
spin_lock(&qedi_conn->list_lock);
list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
qedi_cmd->io_cmd_in_list = true;
qedi_conn->active_cmd_count++;
spin_unlock(&qedi_conn->list_lock);
- qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
qedi_ring_doorbell(qedi_conn);
-
return 0;
}
@@ -1791,58 +1710,62 @@ int qedi_send_iscsi_nopout(struct qedi_conn *qedi_conn,
struct iscsi_task *task,
char *datap, int data_len, int unsol)
{
+ struct iscsi_nop_out_hdr nop_out_pdu_header;
+ struct scsi_sgl_task_params tx_sgl_task_params;
+ struct scsi_sgl_task_params rx_sgl_task_params;
+ struct iscsi_task_params task_params;
struct qedi_ctx *qedi = qedi_conn->qedi;
struct iscsi_task_context *fw_task_ctx;
- struct iscsi_nop_out_hdr *fw_nop_out;
- struct qedi_cmd *qedi_cmd;
- /* For 6.5 hdr iscsi_hdr */
struct iscsi_nopout *nopout_hdr;
- struct iscsi_cached_sge_ctx *cached_sge;
- struct iscsi_sge *single_sge;
- struct iscsi_sge *req_sge;
- struct iscsi_sge *resp_sge;
- u32 lun[2];
- s16 ptu_invalidate = 0;
+ struct scsi_sge *req_sge = NULL;
+ struct scsi_sge *resp_sge = NULL;
+ struct qedi_cmd *qedi_cmd;
+ struct qedi_endpoint *ep;
+ u32 scsi_lun[2];
s16 tid = 0;
+ u16 sq_idx = 0;
+ int rval = 0;
- req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
- resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+ req_sge = (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+ resp_sge = (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
qedi_cmd = (struct qedi_cmd *)task->dd_data;
nopout_hdr = (struct iscsi_nopout *)task->hdr;
+ ep = qedi_conn->ep;
tid = qedi_get_task_idx(qedi);
- if (tid == -1) {
- QEDI_WARN(&qedi->dbg_ctx, "Invalid tid\n");
+ if (tid == -1)
return -ENOMEM;
- }
- fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
-
+ fw_task_ctx =
+ (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid);
memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
+
qedi_cmd->task_id = tid;
- /* Ystorm context */
- fw_nop_out = &fw_task_ctx->ystorm_st_context.pdu_hdr.nop_out;
- SET_FIELD(fw_nop_out->flags_attr, ISCSI_NOP_OUT_HDR_CONST1, 1);
- SET_FIELD(fw_nop_out->flags_attr, ISCSI_NOP_OUT_HDR_RSRV, 0);
+ memset(&task_params, 0, sizeof(task_params));
+ memset(&nop_out_pdu_header, 0, sizeof(nop_out_pdu_header));
+ memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params));
+ memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params));
- memcpy(lun, &nopout_hdr->lun, sizeof(struct scsi_lun));
- fw_nop_out->lun.lo = be32_to_cpu(lun[0]);
- fw_nop_out->lun.hi = be32_to_cpu(lun[1]);
+ /* Update header info */
+ nop_out_pdu_header.opcode = nopout_hdr->opcode;
+ SET_FIELD(nop_out_pdu_header.flags_attr, ISCSI_NOP_OUT_HDR_CONST1, 1);
+ SET_FIELD(nop_out_pdu_header.flags_attr, ISCSI_NOP_OUT_HDR_RSRV, 0);
+
+ memcpy(scsi_lun, &nopout_hdr->lun, sizeof(struct scsi_lun));
+ nop_out_pdu_header.lun.lo = be32_to_cpu(scsi_lun[0]);
+ nop_out_pdu_header.lun.hi = be32_to_cpu(scsi_lun[1]);
+ nop_out_pdu_header.cmd_sn = be32_to_cpu(nopout_hdr->cmdsn);
+ nop_out_pdu_header.exp_stat_sn = be32_to_cpu(nopout_hdr->exp_statsn);
qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
if (nopout_hdr->ttt != ISCSI_TTT_ALL_ONES) {
- fw_nop_out->itt = be32_to_cpu(nopout_hdr->itt);
- fw_nop_out->ttt = be32_to_cpu(nopout_hdr->ttt);
- fw_task_ctx->ystorm_st_context.state.buffer_offset[0] = 0;
- fw_task_ctx->ystorm_st_context.state.local_comp = 1;
- SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
- USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 1);
+ nop_out_pdu_header.itt = be32_to_cpu(nopout_hdr->itt);
+ nop_out_pdu_header.ttt = be32_to_cpu(nopout_hdr->ttt);
} else {
- fw_nop_out->itt = qedi_set_itt(tid, get_itt(task->itt));
- fw_nop_out->ttt = ISCSI_TTT_ALL_ONES;
- fw_task_ctx->ystorm_st_context.state.buffer_offset[0] = 0;
+ nop_out_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt));
+ nop_out_pdu_header.ttt = ISCSI_TTT_ALL_ONES;
spin_lock(&qedi_conn->list_lock);
list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
@@ -1851,53 +1774,46 @@ int qedi_send_iscsi_nopout(struct qedi_conn *qedi_conn,
spin_unlock(&qedi_conn->list_lock);
}
- fw_nop_out->opcode = ISCSI_OPCODE_NOP_OUT;
- fw_nop_out->cmd_sn = be32_to_cpu(nopout_hdr->cmdsn);
- fw_nop_out->exp_stat_sn = be32_to_cpu(nopout_hdr->exp_statsn);
+ /* Fill tx AHS and rx buffer */
+ if (data_len) {
+ tx_sgl_task_params.sgl =
+ (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+ tx_sgl_task_params.sgl_phys_addr.lo =
+ (u32)(qedi_conn->gen_pdu.req_dma_addr);
+ tx_sgl_task_params.sgl_phys_addr.hi =
+ (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
+ tx_sgl_task_params.total_buffer_size = data_len;
+ tx_sgl_task_params.num_sges = 1;
- cached_sge =
- &fw_task_ctx->ystorm_st_context.state.sgl_ctx_union.cached_sge;
- cached_sge->sge.sge_len = req_sge->sge_len;
- cached_sge->sge.sge_addr.lo = (u32)(qedi_conn->gen_pdu.req_dma_addr);
- cached_sge->sge.sge_addr.hi =
- (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
-
- /* Mstorm context */
- fw_task_ctx->mstorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH;
- fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
-
- single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge;
- single_sge->sge_addr.lo = resp_sge->sge_addr.lo;
- single_sge->sge_addr.hi = resp_sge->sge_addr.hi;
- single_sge->sge_len = resp_sge->sge_len;
- fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len;
-
- if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
- ptu_invalidate = 1;
- qedi->tid_reuse_count[tid] = 0;
+ rx_sgl_task_params.sgl =
+ (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+ rx_sgl_task_params.sgl_phys_addr.lo =
+ (u32)(qedi_conn->gen_pdu.resp_dma_addr);
+ rx_sgl_task_params.sgl_phys_addr.hi =
+ (u32)((u64)qedi_conn->gen_pdu.resp_dma_addr >> 32);
+ rx_sgl_task_params.total_buffer_size = resp_sge->sge_len;
+ rx_sgl_task_params.num_sges = 1;
}
- fw_task_ctx->ystorm_st_context.state.reuse_count =
- qedi->tid_reuse_count[tid];
- fw_task_ctx->mstorm_st_context.reuse_count =
- qedi->tid_reuse_count[tid]++;
- /* Ustorm context */
- fw_task_ctx->ustorm_st_context.rem_rcv_len = resp_sge->sge_len;
- fw_task_ctx->ustorm_st_context.exp_data_transfer_len = data_len;
- fw_task_ctx->ustorm_st_context.exp_data_sn = 0;
- fw_task_ctx->ustorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH;
- fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
- SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
- ISCSI_REG1_NUM_FAST_SGES, 0);
+ /* Fill fw input params */
+ task_params.context = fw_task_ctx;
+ task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id;
+ task_params.itid = tid;
+ task_params.cq_rss_number = 0;
+ task_params.tx_io_size = data_len;
+ task_params.rx_io_size = resp_sge->sge_len;
- fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
- SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
- USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
+ sq_idx = qedi_get_wqe_idx(qedi_conn);
+ task_params.sqe = &ep->sq[sq_idx];
- fw_task_ctx->ustorm_st_context.lun.lo = be32_to_cpu(lun[0]);
- fw_task_ctx->ustorm_st_context.lun.hi = be32_to_cpu(lun[1]);
+ memset(task_params.sqe, 0, sizeof(struct iscsi_wqe));
+ rval = init_initiator_nop_out_task(&task_params,
+ &nop_out_pdu_header,
+ &tx_sgl_task_params,
+ &rx_sgl_task_params);
+ if (rval)
+ return -1;
- qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
qedi_ring_doorbell(qedi_conn);
return 0;
}
@@ -1905,7 +1821,7 @@ int qedi_send_iscsi_nopout(struct qedi_conn *qedi_conn,
static int qedi_split_bd(struct qedi_cmd *cmd, u64 addr, int sg_len,
int bd_index)
{
- struct iscsi_sge *bd = cmd->io_tbl.sge_tbl;
+ struct scsi_sge *bd = cmd->io_tbl.sge_tbl;
int frag_size, sg_frags;
sg_frags = 0;
@@ -1938,7 +1854,7 @@ static int qedi_split_bd(struct qedi_cmd *cmd, u64 addr, int sg_len,
static int qedi_map_scsi_sg(struct qedi_ctx *qedi, struct qedi_cmd *cmd)
{
struct scsi_cmnd *sc = cmd->scsi_cmd;
- struct iscsi_sge *bd = cmd->io_tbl.sge_tbl;
+ struct scsi_sge *bd = cmd->io_tbl.sge_tbl;
struct scatterlist *sg;
int byte_count = 0;
int bd_count = 0;
@@ -2040,7 +1956,7 @@ static void qedi_iscsi_map_sg_list(struct qedi_cmd *cmd)
if (bd_count == 0)
return;
} else {
- struct iscsi_sge *bd = cmd->io_tbl.sge_tbl;
+ struct scsi_sge *bd = cmd->io_tbl.sge_tbl;
bd[0].sge_addr.lo = 0;
bd[0].sge_addr.hi = 0;
@@ -2136,244 +2052,182 @@ int qedi_iscsi_send_ioreq(struct iscsi_task *task)
struct qedi_conn *qedi_conn = conn->dd_data;
struct qedi_cmd *cmd = task->dd_data;
struct scsi_cmnd *sc = task->sc;
+ struct iscsi_cmd_hdr cmd_pdu_header;
+ struct scsi_sgl_task_params tx_sgl_task_params;
+ struct scsi_sgl_task_params rx_sgl_task_params;
+ struct scsi_sgl_task_params *prx_sgl = NULL;
+ struct scsi_sgl_task_params *ptx_sgl = NULL;
+ struct iscsi_task_params task_params;
+ struct iscsi_conn_params conn_params;
+ struct scsi_initiator_cmd_params cmd_params;
struct iscsi_task_context *fw_task_ctx;
- struct iscsi_cached_sge_ctx *cached_sge;
- struct iscsi_phys_sgl_ctx *phys_sgl;
- struct iscsi_virt_sgl_ctx *virt_sgl;
- struct ystorm_iscsi_task_st_ctx *yst_cxt;
- struct mstorm_iscsi_task_st_ctx *mst_cxt;
- struct iscsi_sgl *sgl_struct;
- struct iscsi_sge *single_sge;
+ struct iscsi_cls_conn *cls_conn;
struct iscsi_scsi_req *hdr = (struct iscsi_scsi_req *)task->hdr;
- struct iscsi_sge *bd = cmd->io_tbl.sge_tbl;
- enum iscsi_task_type task_type;
- struct iscsi_cmd_hdr *fw_cmd;
- u32 lun[2];
- u32 exp_data;
- u16 cq_idx = smp_processor_id() % qedi->num_queues;
- s16 ptu_invalidate = 0;
+ enum iscsi_task_type task_type = MAX_ISCSI_TASK_TYPE;
+ struct qedi_endpoint *ep;
+ u32 scsi_lun[2];
s16 tid = 0;
- u8 num_fast_sgs;
+ u16 sq_idx = 0;
+ u16 cq_idx;
+ int rval = 0;
+
+ ep = qedi_conn->ep;
+ cls_conn = qedi_conn->cls_conn;
+ conn = cls_conn->dd_data;
+
+ qedi_iscsi_map_sg_list(cmd);
+ int_to_scsilun(sc->device->lun, (struct scsi_lun *)scsi_lun);
tid = qedi_get_task_idx(qedi);
if (tid == -1)
return -ENOMEM;
- qedi_iscsi_map_sg_list(cmd);
-
- int_to_scsilun(sc->device->lun, (struct scsi_lun *)lun);
- fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
-
+ fw_task_ctx =
+ (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid);
memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
+
cmd->task_id = tid;
- /* Ystorm context */
- fw_cmd = &fw_task_ctx->ystorm_st_context.pdu_hdr.cmd;
- SET_FIELD(fw_cmd->flags_attr, ISCSI_CMD_HDR_ATTR, ISCSI_ATTR_SIMPLE);
+ memset(&task_params, 0, sizeof(task_params));
+ memset(&cmd_pdu_header, 0, sizeof(cmd_pdu_header));
+ memset(&tx_sgl_task_params, 0, sizeof(tx_sgl_task_params));
+ memset(&rx_sgl_task_params, 0, sizeof(rx_sgl_task_params));
+ memset(&conn_params, 0, sizeof(conn_params));
+ memset(&cmd_params, 0, sizeof(cmd_params));
+ cq_idx = smp_processor_id() % qedi->num_queues;
+ /* Update header info */
+ SET_FIELD(cmd_pdu_header.flags_attr, ISCSI_CMD_HDR_ATTR,
+ ISCSI_ATTR_SIMPLE);
if (sc->sc_data_direction == DMA_TO_DEVICE) {
- if (conn->session->initial_r2t_en) {
- exp_data = min((conn->session->imm_data_en *
- conn->max_xmit_dlength),
- conn->session->first_burst);
- exp_data = min(exp_data, scsi_bufflen(sc));
- fw_task_ctx->ustorm_ag_context.exp_data_acked =
- cpu_to_le32(exp_data);
- } else {
- fw_task_ctx->ustorm_ag_context.exp_data_acked =
- min(conn->session->first_burst, scsi_bufflen(sc));
- }
-
- SET_FIELD(fw_cmd->flags_attr, ISCSI_CMD_HDR_WRITE, 1);
+ SET_FIELD(cmd_pdu_header.flags_attr,
+ ISCSI_CMD_HDR_WRITE, 1);
task_type = ISCSI_TASK_TYPE_INITIATOR_WRITE;
} else {
- if (scsi_bufflen(sc))
- SET_FIELD(fw_cmd->flags_attr, ISCSI_CMD_HDR_READ, 1);
+ SET_FIELD(cmd_pdu_header.flags_attr,
+ ISCSI_CMD_HDR_READ, 1);
task_type = ISCSI_TASK_TYPE_INITIATOR_READ;
}
- fw_cmd->lun.lo = be32_to_cpu(lun[0]);
- fw_cmd->lun.hi = be32_to_cpu(lun[1]);
+ cmd_pdu_header.lun.lo = be32_to_cpu(scsi_lun[0]);
+ cmd_pdu_header.lun.hi = be32_to_cpu(scsi_lun[1]);
qedi_update_itt_map(qedi, tid, task->itt, cmd);
- fw_cmd->itt = qedi_set_itt(tid, get_itt(task->itt));
- fw_cmd->expected_transfer_length = scsi_bufflen(sc);
- fw_cmd->cmd_sn = be32_to_cpu(hdr->cmdsn);
- fw_cmd->opcode = hdr->opcode;
- qedi_cpy_scsi_cdb(sc, (u32 *)fw_cmd->cdb);
+ cmd_pdu_header.itt = qedi_set_itt(tid, get_itt(task->itt));
+ cmd_pdu_header.expected_transfer_length = cpu_to_be32(hdr->data_length);
+ cmd_pdu_header.hdr_second_dword = ntoh24(hdr->dlength);
+ cmd_pdu_header.cmd_sn = be32_to_cpu(hdr->cmdsn);
+ cmd_pdu_header.opcode = hdr->opcode;
+ qedi_cpy_scsi_cdb(sc, (u32 *)cmd_pdu_header.cdb);
- /* Mstorm context */
- fw_task_ctx->mstorm_st_context.sense_db.lo = (u32)cmd->sense_buffer_dma;
- fw_task_ctx->mstorm_st_context.sense_db.hi =
- (u32)((u64)cmd->sense_buffer_dma >> 32);
- fw_task_ctx->mstorm_ag_context.task_cid = qedi_conn->iscsi_conn_id;
- fw_task_ctx->mstorm_st_context.task_type = task_type;
-
- if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
- ptu_invalidate = 1;
- qedi->tid_reuse_count[tid] = 0;
- }
- fw_task_ctx->ystorm_st_context.state.reuse_count =
- qedi->tid_reuse_count[tid];
- fw_task_ctx->mstorm_st_context.reuse_count =
- qedi->tid_reuse_count[tid]++;
-
- /* Ustorm context */
- fw_task_ctx->ustorm_st_context.rem_rcv_len = scsi_bufflen(sc);
- fw_task_ctx->ustorm_st_context.exp_data_transfer_len = scsi_bufflen(sc);
- fw_task_ctx->ustorm_st_context.exp_data_sn =
- be32_to_cpu(hdr->exp_statsn);
- fw_task_ctx->ustorm_st_context.task_type = task_type;
- fw_task_ctx->ustorm_st_context.cq_rss_number = cq_idx;
- fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
-
- SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
- USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
- SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
- USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0);
-
- num_fast_sgs = (cmd->io_tbl.sge_valid ?
- min((u16)QEDI_FAST_SGE_COUNT,
- (u16)cmd->io_tbl.sge_valid) : 0);
- SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
- ISCSI_REG1_NUM_FAST_SGES, num_fast_sgs);
-
- fw_task_ctx->ustorm_st_context.lun.lo = be32_to_cpu(lun[0]);
- fw_task_ctx->ustorm_st_context.lun.hi = be32_to_cpu(lun[1]);
-
- QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO, "Total sge count [%d]\n",
- cmd->io_tbl.sge_valid);
-
- yst_cxt = &fw_task_ctx->ystorm_st_context;
- mst_cxt = &fw_task_ctx->mstorm_st_context;
- /* Tx path */
+ /* Fill tx AHS and rx buffer */
if (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE) {
- /* not considering superIO or FastIO */
- if (cmd->io_tbl.sge_valid == 1) {
- cached_sge = &yst_cxt->state.sgl_ctx_union.cached_sge;
- cached_sge->sge.sge_addr.lo = bd[0].sge_addr.lo;
- cached_sge->sge.sge_addr.hi = bd[0].sge_addr.hi;
- cached_sge->sge.sge_len = bd[0].sge_len;
- qedi->cached_sgls++;
- } else if ((cmd->io_tbl.sge_valid != 1) && cmd->use_slowpath) {
- SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
- ISCSI_MFLAGS_SLOW_IO, 1);
- SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
- ISCSI_REG1_NUM_FAST_SGES, 0);
- phys_sgl = &yst_cxt->state.sgl_ctx_union.phys_sgl;
- phys_sgl->sgl_base.lo = (u32)(cmd->io_tbl.sge_tbl_dma);
- phys_sgl->sgl_base.hi =
- (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
- phys_sgl->sgl_size = cmd->io_tbl.sge_valid;
- qedi->slow_sgls++;
- } else if ((cmd->io_tbl.sge_valid != 1) && !cmd->use_slowpath) {
- SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
- ISCSI_MFLAGS_SLOW_IO, 0);
- SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
- ISCSI_REG1_NUM_FAST_SGES,
- min((u16)QEDI_FAST_SGE_COUNT,
- (u16)cmd->io_tbl.sge_valid));
- virt_sgl = &yst_cxt->state.sgl_ctx_union.virt_sgl;
- virt_sgl->sgl_base.lo = (u32)(cmd->io_tbl.sge_tbl_dma);
- virt_sgl->sgl_base.hi =
+ tx_sgl_task_params.sgl = cmd->io_tbl.sge_tbl;
+ tx_sgl_task_params.sgl_phys_addr.lo =
+ (u32)(cmd->io_tbl.sge_tbl_dma);
+ tx_sgl_task_params.sgl_phys_addr.hi =
(u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
- virt_sgl->sgl_initial_offset =
- (u32)bd[0].sge_addr.lo & (QEDI_PAGE_SIZE - 1);
- qedi->fast_sgls++;
- }
- fw_task_ctx->mstorm_st_context.sgl_size = cmd->io_tbl.sge_valid;
- fw_task_ctx->mstorm_st_context.rem_task_size = scsi_bufflen(sc);
- } else {
- /* Rx path */
- if (cmd->io_tbl.sge_valid == 1) {
- SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
- ISCSI_MFLAGS_SLOW_IO, 0);
- SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
- ISCSI_MFLAGS_SINGLE_SGE, 1);
- single_sge = &mst_cxt->sgl_union.single_sge;
- single_sge->sge_addr.lo = bd[0].sge_addr.lo;
- single_sge->sge_addr.hi = bd[0].sge_addr.hi;
- single_sge->sge_len = bd[0].sge_len;
- qedi->cached_sgls++;
- } else if ((cmd->io_tbl.sge_valid != 1) && cmd->use_slowpath) {
- sgl_struct = &mst_cxt->sgl_union.sgl_struct;
- sgl_struct->sgl_addr.lo =
- (u32)(cmd->io_tbl.sge_tbl_dma);
- sgl_struct->sgl_addr.hi =
- (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
- SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
- ISCSI_MFLAGS_SLOW_IO, 1);
- SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
- ISCSI_REG1_NUM_FAST_SGES, 0);
- sgl_struct->updated_sge_size = 0;
- sgl_struct->updated_sge_offset = 0;
- qedi->slow_sgls++;
- } else if ((cmd->io_tbl.sge_valid != 1) && !cmd->use_slowpath) {
- sgl_struct = &mst_cxt->sgl_union.sgl_struct;
- sgl_struct->sgl_addr.lo =
- (u32)(cmd->io_tbl.sge_tbl_dma);
- sgl_struct->sgl_addr.hi =
- (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
- sgl_struct->byte_offset =
- (u32)bd[0].sge_addr.lo & (QEDI_PAGE_SIZE - 1);
- SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
- ISCSI_MFLAGS_SLOW_IO, 0);
- SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
- ISCSI_REG1_NUM_FAST_SGES, 0);
- sgl_struct->updated_sge_size = 0;
- sgl_struct->updated_sge_offset = 0;
- qedi->fast_sgls++;
- }
- fw_task_ctx->mstorm_st_context.sgl_size = cmd->io_tbl.sge_valid;
- fw_task_ctx->mstorm_st_context.rem_task_size = scsi_bufflen(sc);
+ tx_sgl_task_params.total_buffer_size = scsi_bufflen(sc);
+ tx_sgl_task_params.num_sges = cmd->io_tbl.sge_valid;
+ if (cmd->use_slowpath)
+ tx_sgl_task_params.small_mid_sge = true;
+ } else if (task_type == ISCSI_TASK_TYPE_INITIATOR_READ) {
+ rx_sgl_task_params.sgl = cmd->io_tbl.sge_tbl;
+ rx_sgl_task_params.sgl_phys_addr.lo =
+ (u32)(cmd->io_tbl.sge_tbl_dma);
+ rx_sgl_task_params.sgl_phys_addr.hi =
+ (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
+ rx_sgl_task_params.total_buffer_size = scsi_bufflen(sc);
+ rx_sgl_task_params.num_sges = cmd->io_tbl.sge_valid;
}
- if (cmd->io_tbl.sge_valid == 1)
- /* Singel-SGL */
- qedi->use_cached_sge = true;
- else {
- if (cmd->use_slowpath)
- qedi->use_slow_sge = true;
- else
- qedi->use_fast_sge = true;
- }
+ /* Add conn param */
+ conn_params.first_burst_length = conn->session->first_burst;
+ conn_params.max_send_pdu_length = conn->max_xmit_dlength;
+ conn_params.max_burst_length = conn->session->max_burst;
+ if (conn->session->initial_r2t_en)
+ conn_params.initial_r2t = true;
+ if (conn->session->imm_data_en)
+ conn_params.immediate_data = true;
+
+ /* Add cmd params */
+ cmd_params.sense_data_buffer_phys_addr.lo = (u32)cmd->sense_buffer_dma;
+ cmd_params.sense_data_buffer_phys_addr.hi =
+ (u32)((u64)cmd->sense_buffer_dma >> 32);
+ /* Fill fw input params */
+ task_params.context = fw_task_ctx;
+ task_params.conn_icid = (u16)qedi_conn->iscsi_conn_id;
+ task_params.itid = tid;
+ task_params.cq_rss_number = cq_idx;
+ if (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE)
+ task_params.tx_io_size = scsi_bufflen(sc);
+ else if (task_type == ISCSI_TASK_TYPE_INITIATOR_READ)
+ task_params.rx_io_size = scsi_bufflen(sc);
+
+ sq_idx = qedi_get_wqe_idx(qedi_conn);
+ task_params.sqe = &ep->sq[sq_idx];
+
QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO,
- "%s: %s-SGL: num_sges=0x%x first-sge-lo=0x%x first-sge-hi=0x%x",
+ "%s: %s-SGL: sg_len=0x%x num_sges=0x%x first-sge-lo=0x%x first-sge-hi=0x%x\n",
(task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE) ?
"Write " : "Read ", (cmd->io_tbl.sge_valid == 1) ?
"Single" : (cmd->use_slowpath ? "SLOW" : "FAST"),
- (u16)cmd->io_tbl.sge_valid, (u32)(cmd->io_tbl.sge_tbl_dma),
+ (u16)cmd->io_tbl.sge_valid, scsi_bufflen(sc),
+ (u32)(cmd->io_tbl.sge_tbl_dma),
(u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32));
- /* Add command in active command list */
+ memset(task_params.sqe, 0, sizeof(struct iscsi_wqe));
+
+ if (task_params.tx_io_size != 0)
+ ptx_sgl = &tx_sgl_task_params;
+ if (task_params.rx_io_size != 0)
+ prx_sgl = &rx_sgl_task_params;
+
+ rval = init_initiator_rw_iscsi_task(&task_params, &conn_params,
+ &cmd_params, &cmd_pdu_header,
+ ptx_sgl, prx_sgl,
+ NULL);
+ if (rval)
+ return -1;
+
spin_lock(&qedi_conn->list_lock);
list_add_tail(&cmd->io_cmd, &qedi_conn->active_cmd_list);
cmd->io_cmd_in_list = true;
qedi_conn->active_cmd_count++;
spin_unlock(&qedi_conn->list_lock);
- qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
qedi_ring_doorbell(qedi_conn);
- if (qedi_io_tracing)
- qedi_trace_io(qedi, task, tid, QEDI_IO_TRACE_REQ);
-
return 0;
}
int qedi_iscsi_cleanup_task(struct iscsi_task *task, bool mark_cmd_node_deleted)
{
+ struct iscsi_task_params task_params;
+ struct qedi_endpoint *ep;
struct iscsi_conn *conn = task->conn;
struct qedi_conn *qedi_conn = conn->dd_data;
struct qedi_cmd *cmd = task->dd_data;
- s16 ptu_invalidate = 0;
+ u16 sq_idx = 0;
+ int rval = 0;
QEDI_INFO(&qedi_conn->qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
"issue cleanup tid=0x%x itt=0x%x task_state=%d cmd_state=0%x cid=0x%x\n",
cmd->task_id, get_itt(task->itt), task->state,
cmd->state, qedi_conn->iscsi_conn_id);
- qedi_add_to_sq(qedi_conn, task, cmd->task_id, ptu_invalidate, true);
- qedi_ring_doorbell(qedi_conn);
+ memset(&task_params, 0, sizeof(task_params));
+ ep = qedi_conn->ep;
+ sq_idx = qedi_get_wqe_idx(qedi_conn);
+
+ task_params.sqe = &ep->sq[sq_idx];
+ memset(task_params.sqe, 0, sizeof(struct iscsi_wqe));
+ task_params.itid = cmd->task_id;
+
+ rval = init_cleanup_task(&task_params);
+ if (rval)
+ return rval;
+
+ qedi_ring_doorbell(qedi_conn);
return 0;
}
diff --git a/drivers/scsi/qedi/qedi_fw_api.c b/drivers/scsi/qedi/qedi_fw_api.c
new file mode 100644
index 0000000..fd354d4
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_fw_api.c
@@ -0,0 +1,781 @@
+/* QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+#include "qedi_hsi.h"
+#include <linux/qed/qed_if.h>
+
+#include "qedi_fw_iscsi.h"
+#include "qedi_fw_scsi.h"
+
+#define SCSI_NUM_SGES_IN_CACHE 0x4
+
+static bool scsi_is_slow_sgl(u16 num_sges, bool small_mid_sge)
+{
+ return (num_sges > SCSI_NUM_SGES_SLOW_SGL_THR && small_mid_sge);
+}
+
+static
+void init_scsi_sgl_context(struct scsi_sgl_params *ctx_sgl_params,
+ struct scsi_cached_sges *ctx_data_desc,
+ struct scsi_sgl_task_params *sgl_task_params)
+{
+ u8 sge_index;
+ u8 num_sges;
+ u32 val;
+
+ num_sges = (sgl_task_params->num_sges > SCSI_NUM_SGES_IN_CACHE) ?
+ SCSI_NUM_SGES_IN_CACHE : sgl_task_params->num_sges;
+
+ /* sgl params */
+ val = cpu_to_le32(sgl_task_params->sgl_phys_addr.lo);
+ ctx_sgl_params->sgl_addr.lo = val;
+ val = cpu_to_le32(sgl_task_params->sgl_phys_addr.hi);
+ ctx_sgl_params->sgl_addr.hi = val;
+ val = cpu_to_le32(sgl_task_params->total_buffer_size);
+ ctx_sgl_params->sgl_total_length = val;
+ ctx_sgl_params->sgl_num_sges = cpu_to_le16(sgl_task_params->num_sges);
+
+ for (sge_index = 0; sge_index < num_sges; sge_index++) {
+ val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_addr.lo);
+ ctx_data_desc->sge[sge_index].sge_addr.lo = val;
+ val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_addr.hi);
+ ctx_data_desc->sge[sge_index].sge_addr.hi = val;
+ val = cpu_to_le32(sgl_task_params->sgl[sge_index].sge_len);
+ ctx_data_desc->sge[sge_index].sge_len = val;
+ }
+}
+
+static u32 calc_rw_task_size(struct iscsi_task_params *task_params,
+ enum iscsi_task_type task_type,
+ struct scsi_sgl_task_params *sgl_task_params,
+ struct scsi_dif_task_params *dif_task_params)
+{
+ u32 io_size;
+
+ if (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE ||
+ task_type == ISCSI_TASK_TYPE_TARGET_READ)
+ io_size = task_params->tx_io_size;
+ else
+ io_size = task_params->rx_io_size;
+
+ if (!io_size)
+ return 0;
+
+ if (!dif_task_params)
+ return io_size;
+
+ return !dif_task_params->dif_on_network ?
+ io_size : sgl_task_params->total_buffer_size;
+}
+
+static void
+init_dif_context_flags(struct iscsi_dif_flags *ctx_dif_flags,
+ struct scsi_dif_task_params *dif_task_params)
+{
+ if (!dif_task_params)
+ return;
+
+ SET_FIELD(ctx_dif_flags->flags, ISCSI_DIF_FLAGS_PROT_INTERVAL_SIZE_LOG,
+ dif_task_params->dif_block_size_log);
+ SET_FIELD(ctx_dif_flags->flags, ISCSI_DIF_FLAGS_DIF_TO_PEER,
+ dif_task_params->dif_on_network ? 1 : 0);
+ SET_FIELD(ctx_dif_flags->flags, ISCSI_DIF_FLAGS_HOST_INTERFACE,
+ dif_task_params->dif_on_host ? 1 : 0);
+}
+
+static void init_sqe(struct iscsi_task_params *task_params,
+ struct scsi_sgl_task_params *sgl_task_params,
+ struct scsi_dif_task_params *dif_task_params,
+ struct iscsi_common_hdr *pdu_header,
+ struct scsi_initiator_cmd_params *cmd_params,
+ enum iscsi_task_type task_type,
+ bool is_cleanup)
+{
+ if (!task_params->sqe)
+ return;
+
+ memset(task_params->sqe, 0, sizeof(*task_params->sqe));
+ task_params->sqe->task_id = cpu_to_le16(task_params->itid);
+ if (is_cleanup) {
+ SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE,
+ ISCSI_WQE_TYPE_TASK_CLEANUP);
+ return;
+ }
+
+ switch (task_type) {
+ case ISCSI_TASK_TYPE_INITIATOR_WRITE:
+ {
+ u32 buf_size = 0;
+ u32 num_sges = 0;
+
+ init_dif_context_flags(&task_params->sqe->prot_flags,
+ dif_task_params);
+
+ SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE,
+ ISCSI_WQE_TYPE_NORMAL);
+
+ if (task_params->tx_io_size) {
+ buf_size = calc_rw_task_size(task_params, task_type,
+ sgl_task_params,
+ dif_task_params);
+
+ if (scsi_is_slow_sgl(sgl_task_params->num_sges,
+ sgl_task_params->small_mid_sge))
+ num_sges = ISCSI_WQE_NUM_SGES_SLOWIO;
+ else
+ num_sges = min(sgl_task_params->num_sges,
+ (u16)SCSI_NUM_SGES_SLOW_SGL_THR);
+ }
+
+ SET_FIELD(task_params->sqe->flags, ISCSI_WQE_NUM_SGES, num_sges);
+ SET_FIELD(task_params->sqe->contlen_cdbsize, ISCSI_WQE_CONT_LEN,
+ buf_size);
+
+ if (GET_FIELD(pdu_header->hdr_second_dword,
+ ISCSI_CMD_HDR_TOTAL_AHS_LEN))
+ SET_FIELD(task_params->sqe->contlen_cdbsize, ISCSI_WQE_CDB_SIZE,
+ cmd_params->extended_cdb_sge.sge_len);
+ }
+ break;
+ case ISCSI_TASK_TYPE_INITIATOR_READ:
+ SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE,
+ ISCSI_WQE_TYPE_NORMAL);
+
+ if (GET_FIELD(pdu_header->hdr_second_dword,
+ ISCSI_CMD_HDR_TOTAL_AHS_LEN))
+ SET_FIELD(task_params->sqe->contlen_cdbsize,
+ ISCSI_WQE_CDB_SIZE,
+ cmd_params->extended_cdb_sge.sge_len);
+ break;
+ case ISCSI_TASK_TYPE_LOGIN_RESPONSE:
+ case ISCSI_TASK_TYPE_MIDPATH:
+ {
+ bool advance_statsn = true;
+
+ if (task_type == ISCSI_TASK_TYPE_LOGIN_RESPONSE)
+ SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE,
+ ISCSI_WQE_TYPE_LOGIN);
+ else
+ SET_FIELD(task_params->sqe->flags, ISCSI_WQE_WQE_TYPE,
+ ISCSI_WQE_TYPE_MIDDLE_PATH);
+
+ if (task_type == ISCSI_TASK_TYPE_MIDPATH) {
+ u8 opcode = GET_FIELD(pdu_header->hdr_first_byte,
+ ISCSI_COMMON_HDR_OPCODE);
+
+ if (opcode != ISCSI_OPCODE_TEXT_RESPONSE &&
+ (opcode != ISCSI_OPCODE_NOP_IN ||
+ pdu_header->itt == ISCSI_TTT_ALL_ONES))
+ advance_statsn = false;
+ }
+
+ SET_FIELD(task_params->sqe->flags, ISCSI_WQE_RESPONSE,
+ advance_statsn ? 1 : 0);
+
+ if (task_params->tx_io_size) {
+ SET_FIELD(task_params->sqe->contlen_cdbsize,
+ ISCSI_WQE_CONT_LEN, task_params->tx_io_size);
+
+ if (scsi_is_slow_sgl(sgl_task_params->num_sges,
+ sgl_task_params->small_mid_sge))
+ SET_FIELD(task_params->sqe->flags, ISCSI_WQE_NUM_SGES,
+ ISCSI_WQE_NUM_SGES_SLOWIO);
+ else
+ SET_FIELD(task_params->sqe->flags, ISCSI_WQE_NUM_SGES,
+ min(sgl_task_params->num_sges,
+ (u16)SCSI_NUM_SGES_SLOW_SGL_THR));
+ }
+ }
+ break;
+ default:
+ break;
+ }
+}
+
+static void init_default_iscsi_task(struct iscsi_task_params *task_params,
+ struct data_hdr *pdu_header,
+ enum iscsi_task_type task_type)
+{
+ struct iscsi_task_context *context;
+ u16 index;
+ u32 val;
+
+ context = task_params->context;
+ memset(context, 0, sizeof(*context));
+
+ for (index = 0; index <
+ ARRAY_SIZE(context->ystorm_st_context.pdu_hdr.data.data);
+ index++) {
+ val = cpu_to_le32(pdu_header->data[index]);
+ context->ystorm_st_context.pdu_hdr.data.data[index] = val;
+ }
+
+ context->mstorm_st_context.task_type = task_type;
+ context->mstorm_ag_context.task_cid =
+ cpu_to_le16(task_params->conn_icid);
+
+ SET_FIELD(context->ustorm_ag_context.flags1,
+ USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
+
+ context->ustorm_st_context.task_type = task_type;
+ context->ustorm_st_context.cq_rss_number = task_params->cq_rss_number;
+ context->ustorm_ag_context.icid = cpu_to_le16(task_params->conn_icid);
+}
+
+static
+void init_initiator_rw_cdb_ystorm_context(struct ystorm_iscsi_task_st_ctx *ystc,
+ struct scsi_initiator_cmd_params *cmd)
+{
+ union iscsi_task_hdr *ctx_pdu_hdr = &ystc->pdu_hdr;
+ u32 val;
+
+ if (!cmd->extended_cdb_sge.sge_len)
+ return;
+
+ SET_FIELD(ctx_pdu_hdr->ext_cdb_cmd.hdr_second_dword,
+ ISCSI_EXT_CDB_CMD_HDR_CDB_SIZE,
+ cmd->extended_cdb_sge.sge_len);
+ val = cpu_to_le32(cmd->extended_cdb_sge.sge_addr.lo);
+ ctx_pdu_hdr->ext_cdb_cmd.cdb_sge.sge_addr.lo = val;
+ val = cpu_to_le32(cmd->extended_cdb_sge.sge_addr.hi);
+ ctx_pdu_hdr->ext_cdb_cmd.cdb_sge.sge_addr.hi = val;
+ val = cpu_to_le32(cmd->extended_cdb_sge.sge_len);
+ ctx_pdu_hdr->ext_cdb_cmd.cdb_sge.sge_len = val;
+}
+
+static
+void init_ustorm_task_contexts(struct ustorm_iscsi_task_st_ctx *ustorm_st_cxt,
+ struct ustorm_iscsi_task_ag_ctx *ustorm_ag_cxt,
+ u32 remaining_recv_len,
+ u32 expected_data_transfer_len,
+ u8 num_sges, bool tx_dif_conn_err_en)
+{
+ u32 val;
+
+ ustorm_st_cxt->rem_rcv_len = cpu_to_le32(remaining_recv_len);
+ ustorm_ag_cxt->exp_data_acked = cpu_to_le32(expected_data_transfer_len);
+ val = cpu_to_le32(expected_data_transfer_len);
+ ustorm_st_cxt->exp_data_transfer_len = val;
+ SET_FIELD(ustorm_st_cxt->reg1.reg1_map, ISCSI_REG1_NUM_SGES, num_sges);
+ SET_FIELD(ustorm_ag_cxt->flags2,
+ USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_CF_EN,
+ tx_dif_conn_err_en ? 1 : 0);
+}
+
+static
+void set_rw_exp_data_acked_and_cont_len(struct iscsi_task_context *context,
+ struct iscsi_conn_params *conn_params,
+ enum iscsi_task_type task_type,
+ u32 task_size,
+ u32 exp_data_transfer_len,
+ u8 total_ahs_length)
+{
+ u32 max_unsolicited_data = 0, val;
+
+ if (total_ahs_length &&
+ (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE ||
+ task_type == ISCSI_TASK_TYPE_INITIATOR_READ))
+ SET_FIELD(context->ustorm_st_context.flags2,
+ USTORM_ISCSI_TASK_ST_CTX_AHS_EXIST, 1);
+
+ switch (task_type) {
+ case ISCSI_TASK_TYPE_INITIATOR_WRITE:
+ if (!conn_params->initial_r2t)
+ max_unsolicited_data = conn_params->first_burst_length;
+ else if (conn_params->immediate_data)
+ max_unsolicited_data =
+ min(conn_params->first_burst_length,
+ conn_params->max_send_pdu_length);
+
+ context->ustorm_ag_context.exp_data_acked =
+ cpu_to_le32(total_ahs_length == 0 ?
+ min(exp_data_transfer_len,
+ max_unsolicited_data) :
+ ((u32)(total_ahs_length +
+ ISCSI_AHS_CNTL_SIZE)));
+ break;
+ case ISCSI_TASK_TYPE_TARGET_READ:
+ val = cpu_to_le32(exp_data_transfer_len);
+ context->ustorm_ag_context.exp_data_acked = val;
+ break;
+ case ISCSI_TASK_TYPE_INITIATOR_READ:
+ context->ustorm_ag_context.exp_data_acked =
+ cpu_to_le32((total_ahs_length == 0 ? 0 :
+ total_ahs_length +
+ ISCSI_AHS_CNTL_SIZE));
+ break;
+ case ISCSI_TASK_TYPE_TARGET_WRITE:
+ val = cpu_to_le32(task_size);
+ context->ustorm_ag_context.exp_cont_len = val;
+ break;
+ default:
+ break;
+ }
+}
+
+static
+void init_rtdif_task_context(struct rdif_task_context *rdif_context,
+ struct tdif_task_context *tdif_context,
+ struct scsi_dif_task_params *dif_task_params,
+ enum iscsi_task_type task_type)
+{
+ u32 val;
+
+ if (!dif_task_params->dif_on_network || !dif_task_params->dif_on_host)
+ return;
+
+ if (task_type == ISCSI_TASK_TYPE_TARGET_WRITE ||
+ task_type == ISCSI_TASK_TYPE_INITIATOR_READ) {
+ rdif_context->app_tag_value =
+ cpu_to_le16(dif_task_params->application_tag);
+ rdif_context->partial_crc_value = cpu_to_le16(0xffff);
+ val = cpu_to_le32(dif_task_params->initial_ref_tag);
+ rdif_context->initial_ref_tag = val;
+ rdif_context->app_tag_mask =
+ cpu_to_le16(dif_task_params->application_tag_mask);
+ SET_FIELD(rdif_context->flags0, RDIF_TASK_CONTEXT_CRC_SEED,
+ dif_task_params->crc_seed ? 1 : 0);
+ SET_FIELD(rdif_context->flags0, RDIF_TASK_CONTEXT_HOSTGUARDTYPE,
+ dif_task_params->host_guard_type);
+ SET_FIELD(rdif_context->flags0,
+ RDIF_TASK_CONTEXT_PROTECTIONTYPE,
+ dif_task_params->protection_type);
+ SET_FIELD(rdif_context->flags0,
+ RDIF_TASK_CONTEXT_INITIALREFTAGVALID, 1);
+ SET_FIELD(rdif_context->flags0,
+ RDIF_TASK_CONTEXT_KEEPREFTAGCONST,
+ dif_task_params->keep_ref_tag_const ? 1 : 0);
+ SET_FIELD(rdif_context->flags1,
+ RDIF_TASK_CONTEXT_VALIDATEAPPTAG,
+ (dif_task_params->validate_app_tag &&
+ dif_task_params->dif_on_network) ? 1 : 0);
+ SET_FIELD(rdif_context->flags1,
+ RDIF_TASK_CONTEXT_VALIDATEGUARD,
+ (dif_task_params->validate_guard &&
+ dif_task_params->dif_on_network) ? 1 : 0);
+ SET_FIELD(rdif_context->flags1,
+ RDIF_TASK_CONTEXT_VALIDATEREFTAG,
+ (dif_task_params->validate_ref_tag &&
+ dif_task_params->dif_on_network) ? 1 : 0);
+ SET_FIELD(rdif_context->flags1,
+ RDIF_TASK_CONTEXT_HOSTINTERFACE,
+ dif_task_params->dif_on_host ? 1 : 0);
+ SET_FIELD(rdif_context->flags1,
+ RDIF_TASK_CONTEXT_NETWORKINTERFACE,
+ dif_task_params->dif_on_network ? 1 : 0);
+ SET_FIELD(rdif_context->flags1,
+ RDIF_TASK_CONTEXT_FORWARDGUARD,
+ dif_task_params->forward_guard ? 1 : 0);
+ SET_FIELD(rdif_context->flags1,
+ RDIF_TASK_CONTEXT_FORWARDAPPTAG,
+ dif_task_params->forward_app_tag ? 1 : 0);
+ SET_FIELD(rdif_context->flags1,
+ RDIF_TASK_CONTEXT_FORWARDREFTAG,
+ dif_task_params->forward_ref_tag ? 1 : 0);
+ SET_FIELD(rdif_context->flags1,
+ RDIF_TASK_CONTEXT_FORWARDAPPTAGWITHMASK,
+ dif_task_params->forward_app_tag_with_mask ? 1 : 0);
+ SET_FIELD(rdif_context->flags1,
+ RDIF_TASK_CONTEXT_FORWARDREFTAGWITHMASK,
+ dif_task_params->forward_ref_tag_with_mask ? 1 : 0);
+ SET_FIELD(rdif_context->flags1,
+ RDIF_TASK_CONTEXT_INTERVALSIZE,
+ dif_task_params->dif_block_size_log - 9);
+ SET_FIELD(rdif_context->state,
+ RDIF_TASK_CONTEXT_REFTAGMASK,
+ dif_task_params->ref_tag_mask);
+ SET_FIELD(rdif_context->state, RDIF_TASK_CONTEXT_IGNOREAPPTAG,
+ dif_task_params->ignore_app_tag);
+ }
+
+ if (task_type == ISCSI_TASK_TYPE_TARGET_READ ||
+ task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE) {
+ tdif_context->app_tag_value =
+ cpu_to_le16(dif_task_params->application_tag);
+ tdif_context->partial_crc_valueB =
+ cpu_to_le16(dif_task_params->crc_seed ? 0xffff : 0x0000);
+ tdif_context->partial_crc_value_a =
+ cpu_to_le16(dif_task_params->crc_seed ? 0xffff : 0x0000);
+ SET_FIELD(tdif_context->flags0, TDIF_TASK_CONTEXT_CRC_SEED,
+ dif_task_params->crc_seed ? 1 : 0);
+
+ SET_FIELD(tdif_context->flags0,
+ TDIF_TASK_CONTEXT_SETERRORWITHEOP,
+ dif_task_params->tx_dif_conn_err_en ? 1 : 0);
+ SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_FORWARDGUARD,
+ dif_task_params->forward_guard ? 1 : 0);
+ SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_FORWARDAPPTAG,
+ dif_task_params->forward_app_tag ? 1 : 0);
+ SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_FORWARDREFTAG,
+ dif_task_params->forward_ref_tag ? 1 : 0);
+ SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_INTERVALSIZE,
+ dif_task_params->dif_block_size_log - 9);
+ SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_HOSTINTERFACE,
+ dif_task_params->dif_on_host ? 1 : 0);
+ SET_FIELD(tdif_context->flags1,
+ TDIF_TASK_CONTEXT_NETWORKINTERFACE,
+ dif_task_params->dif_on_network ? 1 : 0);
+ val = cpu_to_le32(dif_task_params->initial_ref_tag);
+ tdif_context->initial_ref_tag = val;
+ tdif_context->app_tag_mask =
+ cpu_to_le16(dif_task_params->application_tag_mask);
+ SET_FIELD(tdif_context->flags0,
+ TDIF_TASK_CONTEXT_HOSTGUARDTYPE,
+ dif_task_params->host_guard_type);
+ SET_FIELD(tdif_context->flags0,
+ TDIF_TASK_CONTEXT_PROTECTIONTYPE,
+ dif_task_params->protection_type);
+ SET_FIELD(tdif_context->flags0,
+ TDIF_TASK_CONTEXT_INITIALREFTAGVALID,
+ dif_task_params->initial_ref_tag_is_valid ? 1 : 0);
+ SET_FIELD(tdif_context->flags0,
+ TDIF_TASK_CONTEXT_KEEPREFTAGCONST,
+ dif_task_params->keep_ref_tag_const ? 1 : 0);
+ SET_FIELD(tdif_context->flags1, TDIF_TASK_CONTEXT_VALIDATEGUARD,
+ (dif_task_params->validate_guard &&
+ dif_task_params->dif_on_host) ? 1 : 0);
+ SET_FIELD(tdif_context->flags1,
+ TDIF_TASK_CONTEXT_VALIDATEAPPTAG,
+ (dif_task_params->validate_app_tag &&
+ dif_task_params->dif_on_host) ? 1 : 0);
+ SET_FIELD(tdif_context->flags1,
+ TDIF_TASK_CONTEXT_VALIDATEREFTAG,
+ (dif_task_params->validate_ref_tag &&
+ dif_task_params->dif_on_host) ? 1 : 0);
+ SET_FIELD(tdif_context->flags1,
+ TDIF_TASK_CONTEXT_FORWARDAPPTAGWITHMASK,
+ dif_task_params->forward_app_tag_with_mask ? 1 : 0);
+ SET_FIELD(tdif_context->flags1,
+ TDIF_TASK_CONTEXT_FORWARDREFTAGWITHMASK,
+ dif_task_params->forward_ref_tag_with_mask ? 1 : 0);
+ SET_FIELD(tdif_context->flags1,
+ TDIF_TASK_CONTEXT_REFTAGMASK,
+ dif_task_params->ref_tag_mask);
+ SET_FIELD(tdif_context->flags0,
+ TDIF_TASK_CONTEXT_IGNOREAPPTAG,
+ dif_task_params->ignore_app_tag ? 1 : 0);
+ }
+}
+
+static void set_local_completion_context(struct iscsi_task_context *context)
+{
+ SET_FIELD(context->ystorm_st_context.state.flags,
+ YSTORM_ISCSI_TASK_STATE_LOCAL_COMP, 1);
+ SET_FIELD(context->ustorm_st_context.flags,
+ USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 1);
+}
+
+static int init_rw_iscsi_task(struct iscsi_task_params *task_params,
+ enum iscsi_task_type task_type,
+ struct iscsi_conn_params *conn_params,
+ struct iscsi_common_hdr *pdu_header,
+ struct scsi_sgl_task_params *sgl_task_params,
+ struct scsi_initiator_cmd_params *cmd_params,
+ struct scsi_dif_task_params *dif_task_params)
+{
+ u32 exp_data_transfer_len = conn_params->max_burst_length;
+ struct iscsi_task_context *cxt;
+ bool slow_io = false;
+ u32 task_size, val;
+ u8 num_sges = 0;
+
+ task_size = calc_rw_task_size(task_params, task_type, sgl_task_params,
+ dif_task_params);
+
+ init_default_iscsi_task(task_params, (struct data_hdr *)pdu_header,
+ task_type);
+
+ cxt = task_params->context;
+
+ val = cpu_to_le32(task_size);
+ cxt->ystorm_st_context.pdu_hdr.cmd.expected_transfer_length = val;
+ init_initiator_rw_cdb_ystorm_context(&cxt->ystorm_st_context,
+ cmd_params);
+ val = cpu_to_le32(cmd_params->sense_data_buffer_phys_addr.lo);
+ cxt->mstorm_st_context.sense_db.lo = val;
+
+ val = cpu_to_le32(cmd_params->sense_data_buffer_phys_addr.hi);
+ cxt->mstorm_st_context.sense_db.hi = val;
+
+ if (task_params->tx_io_size) {
+ init_dif_context_flags(&cxt->ystorm_st_context.state.dif_flags,
+ dif_task_params);
+ init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params,
+ &cxt->ystorm_st_context.state.data_desc,
+ sgl_task_params);
+
+ slow_io = scsi_is_slow_sgl(sgl_task_params->num_sges,
+ sgl_task_params->small_mid_sge);
+
+ num_sges = !slow_io ? min_t(u16, sgl_task_params->num_sges,
+ (u16)SCSI_NUM_SGES_SLOW_SGL_THR) :
+ ISCSI_WQE_NUM_SGES_SLOWIO;
+
+ if (slow_io) {
+ SET_FIELD(cxt->ystorm_st_context.state.flags,
+ YSTORM_ISCSI_TASK_STATE_SLOW_IO, 1);
+ }
+ } else if (task_params->rx_io_size) {
+ init_dif_context_flags(&cxt->mstorm_st_context.dif_flags,
+ dif_task_params);
+ init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params,
+ &cxt->mstorm_st_context.data_desc,
+ sgl_task_params);
+ num_sges = !scsi_is_slow_sgl(sgl_task_params->num_sges,
+ sgl_task_params->small_mid_sge) ?
+ min_t(u16, sgl_task_params->num_sges,
+ (u16)SCSI_NUM_SGES_SLOW_SGL_THR) :
+ ISCSI_WQE_NUM_SGES_SLOWIO;
+ cxt->mstorm_st_context.rem_task_size = cpu_to_le32(task_size);
+ }
+
+ if (exp_data_transfer_len > task_size ||
+ task_type != ISCSI_TASK_TYPE_TARGET_WRITE)
+ exp_data_transfer_len = task_size;
+
+ init_ustorm_task_contexts(&task_params->context->ustorm_st_context,
+ &task_params->context->ustorm_ag_context,
+ task_size, exp_data_transfer_len, num_sges,
+ dif_task_params ?
+ dif_task_params->tx_dif_conn_err_en : false);
+
+ set_rw_exp_data_acked_and_cont_len(task_params->context, conn_params,
+ task_type, task_size,
+ exp_data_transfer_len,
+ GET_FIELD(pdu_header->hdr_second_dword,
+ ISCSI_CMD_HDR_TOTAL_AHS_LEN));
+
+ if (dif_task_params)
+ init_rtdif_task_context(&task_params->context->rdif_context,
+ &task_params->context->tdif_context,
+ dif_task_params, task_type);
+
+ init_sqe(task_params, sgl_task_params, dif_task_params, pdu_header,
+ cmd_params, task_type, false);
+
+ return 0;
+}
+
+int init_initiator_rw_iscsi_task(struct iscsi_task_params *task_params,
+ struct iscsi_conn_params *conn_params,
+ struct scsi_initiator_cmd_params *cmd_params,
+ struct iscsi_cmd_hdr *cmd_header,
+ struct scsi_sgl_task_params *tx_sgl_params,
+ struct scsi_sgl_task_params *rx_sgl_params,
+ struct scsi_dif_task_params *dif_task_params)
+{
+ if (GET_FIELD(cmd_header->flags_attr, ISCSI_CMD_HDR_WRITE))
+ return init_rw_iscsi_task(task_params,
+ ISCSI_TASK_TYPE_INITIATOR_WRITE,
+ conn_params,
+ (struct iscsi_common_hdr *)cmd_header,
+ tx_sgl_params, cmd_params,
+ dif_task_params);
+ else if (GET_FIELD(cmd_header->flags_attr, ISCSI_CMD_HDR_READ))
+ return init_rw_iscsi_task(task_params,
+ ISCSI_TASK_TYPE_INITIATOR_READ,
+ conn_params,
+ (struct iscsi_common_hdr *)cmd_header,
+ rx_sgl_params, cmd_params,
+ dif_task_params);
+ else
+ return -1;
+}
+
+int init_initiator_login_request_task(struct iscsi_task_params *task_params,
+ struct iscsi_login_req_hdr *login_header,
+ struct scsi_sgl_task_params *tx_params,
+ struct scsi_sgl_task_params *rx_params)
+{
+ struct iscsi_task_context *cxt;
+
+ cxt = task_params->context;
+
+ init_default_iscsi_task(task_params,
+ (struct data_hdr *)login_header,
+ ISCSI_TASK_TYPE_MIDPATH);
+
+ init_ustorm_task_contexts(&cxt->ustorm_st_context,
+ &cxt->ustorm_ag_context,
+ task_params->rx_io_size ?
+ rx_params->total_buffer_size : 0,
+ task_params->tx_io_size ?
+ tx_params->total_buffer_size : 0, 0,
+ 0);
+
+ if (task_params->tx_io_size)
+ init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params,
+ &cxt->ystorm_st_context.state.data_desc,
+ tx_params);
+
+ if (task_params->rx_io_size)
+ init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params,
+ &cxt->mstorm_st_context.data_desc,
+ rx_params);
+
+ cxt->mstorm_st_context.rem_task_size =
+ cpu_to_le32(task_params->rx_io_size ?
+ rx_params->total_buffer_size : 0);
+
+ init_sqe(task_params, tx_params, NULL,
+ (struct iscsi_common_hdr *)login_header, NULL,
+ ISCSI_TASK_TYPE_MIDPATH, false);
+
+ return 0;
+}
+
+int init_initiator_nop_out_task(struct iscsi_task_params *task_params,
+ struct iscsi_nop_out_hdr *nop_out_pdu_header,
+ struct scsi_sgl_task_params *tx_sgl_task_params,
+ struct scsi_sgl_task_params *rx_sgl_task_params)
+{
+ struct iscsi_task_context *cxt;
+
+ cxt = task_params->context;
+
+ init_default_iscsi_task(task_params,
+ (struct data_hdr *)nop_out_pdu_header,
+ ISCSI_TASK_TYPE_MIDPATH);
+
+ if (nop_out_pdu_header->itt == ISCSI_ITT_ALL_ONES)
+ set_local_completion_context(task_params->context);
+
+ if (task_params->tx_io_size)
+ init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params,
+ &cxt->ystorm_st_context.state.data_desc,
+ tx_sgl_task_params);
+
+ if (task_params->rx_io_size)
+ init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params,
+ &cxt->mstorm_st_context.data_desc,
+ rx_sgl_task_params);
+
+ init_ustorm_task_contexts(&cxt->ustorm_st_context,
+ &cxt->ustorm_ag_context,
+ task_params->rx_io_size ?
+ rx_sgl_task_params->total_buffer_size : 0,
+ task_params->tx_io_size ?
+ tx_sgl_task_params->total_buffer_size : 0,
+ 0, 0);
+
+ cxt->mstorm_st_context.rem_task_size =
+ cpu_to_le32(task_params->rx_io_size ?
+ rx_sgl_task_params->total_buffer_size :
+ 0);
+
+ init_sqe(task_params, tx_sgl_task_params, NULL,
+ (struct iscsi_common_hdr *)nop_out_pdu_header, NULL,
+ ISCSI_TASK_TYPE_MIDPATH, false);
+
+ return 0;
+}
+
+int init_initiator_logout_request_task(struct iscsi_task_params *task_params,
+ struct iscsi_logout_req_hdr *logout_hdr,
+ struct scsi_sgl_task_params *tx_params,
+ struct scsi_sgl_task_params *rx_params)
+{
+ struct iscsi_task_context *cxt;
+
+ cxt = task_params->context;
+
+ init_default_iscsi_task(task_params,
+ (struct data_hdr *)logout_hdr,
+ ISCSI_TASK_TYPE_MIDPATH);
+
+ if (task_params->tx_io_size)
+ init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params,
+ &cxt->ystorm_st_context.state.data_desc,
+ tx_params);
+
+ if (task_params->rx_io_size)
+ init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params,
+ &cxt->mstorm_st_context.data_desc,
+ rx_params);
+
+ init_ustorm_task_contexts(&cxt->ustorm_st_context,
+ &cxt->ustorm_ag_context,
+ task_params->rx_io_size ?
+ rx_params->total_buffer_size : 0,
+ task_params->tx_io_size ?
+ tx_params->total_buffer_size : 0,
+ 0, 0);
+
+ cxt->mstorm_st_context.rem_task_size =
+ cpu_to_le32(task_params->rx_io_size ?
+ rx_params->total_buffer_size : 0);
+
+ init_sqe(task_params, tx_params, NULL,
+ (struct iscsi_common_hdr *)logout_hdr, NULL,
+ ISCSI_TASK_TYPE_MIDPATH, false);
+
+ return 0;
+}
+
+int init_initiator_tmf_request_task(struct iscsi_task_params *task_params,
+ struct iscsi_tmf_request_hdr *tmf_header)
+{
+ init_default_iscsi_task(task_params, (struct data_hdr *)tmf_header,
+ ISCSI_TASK_TYPE_MIDPATH);
+
+ init_sqe(task_params, NULL, NULL,
+ (struct iscsi_common_hdr *)tmf_header, NULL,
+ ISCSI_TASK_TYPE_MIDPATH, false);
+
+ return 0;
+}
+
+int init_initiator_text_request_task(struct iscsi_task_params *task_params,
+ struct iscsi_text_request_hdr *text_header,
+ struct scsi_sgl_task_params *tx_params,
+ struct scsi_sgl_task_params *rx_params)
+{
+ struct iscsi_task_context *cxt;
+
+ cxt = task_params->context;
+
+ init_default_iscsi_task(task_params,
+ (struct data_hdr *)text_header,
+ ISCSI_TASK_TYPE_MIDPATH);
+
+ if (task_params->tx_io_size)
+ init_scsi_sgl_context(&cxt->ystorm_st_context.state.sgl_params,
+ &cxt->ystorm_st_context.state.data_desc,
+ tx_params);
+
+ if (task_params->rx_io_size)
+ init_scsi_sgl_context(&cxt->mstorm_st_context.sgl_params,
+ &cxt->mstorm_st_context.data_desc,
+ rx_params);
+
+ cxt->mstorm_st_context.rem_task_size =
+ cpu_to_le32(task_params->rx_io_size ?
+ rx_params->total_buffer_size : 0);
+
+ init_ustorm_task_contexts(&cxt->ustorm_st_context,
+ &cxt->ustorm_ag_context,
+ task_params->rx_io_size ?
+ rx_params->total_buffer_size : 0,
+ task_params->tx_io_size ?
+ tx_params->total_buffer_size : 0, 0, 0);
+
+ init_sqe(task_params, tx_params, NULL,
+ (struct iscsi_common_hdr *)text_header, NULL,
+ ISCSI_TASK_TYPE_MIDPATH, false);
+
+ return 0;
+}
+
+int init_cleanup_task(struct iscsi_task_params *task_params)
+{
+ init_sqe(task_params, NULL, NULL, NULL, NULL, ISCSI_TASK_TYPE_MIDPATH,
+ true);
+ return 0;
+}
diff --git a/drivers/scsi/qedi/qedi_fw_iscsi.h b/drivers/scsi/qedi/qedi_fw_iscsi.h
new file mode 100644
index 0000000..b6f24f9
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_fw_iscsi.h
@@ -0,0 +1,117 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#ifndef _QEDI_FW_ISCSI_H_
+#define _QEDI_FW_ISCSI_H_
+
+#include "qedi_fw_scsi.h"
+
+struct iscsi_task_params {
+ struct iscsi_task_context *context;
+ struct iscsi_wqe *sqe;
+ u32 tx_io_size;
+ u32 rx_io_size;
+ u16 conn_icid;
+ u16 itid;
+ u8 cq_rss_number;
+};
+
+struct iscsi_conn_params {
+ u32 first_burst_length;
+ u32 max_send_pdu_length;
+ u32 max_burst_length;
+ bool initial_r2t;
+ bool immediate_data;
+};
+
+/* @brief init_initiator_read_iscsi_task - initializes iSCSI Initiator Read
+ * task context.
+ *
+ * @param task_params - Pointer to task parameters struct
+ * @param conn_params - Connection Parameters
+ * @param cmd_params - command specific parameters
+ * @param cmd_pdu_header - PDU Header Parameters
+ * @param sgl_task_params - Pointer to SGL task params
+ * @param dif_task_params - Pointer to DIF parameters struct
+ */
+int init_initiator_rw_iscsi_task(struct iscsi_task_params *task_params,
+ struct iscsi_conn_params *conn_params,
+ struct scsi_initiator_cmd_params *cmd_params,
+ struct iscsi_cmd_hdr *cmd_pdu_header,
+ struct scsi_sgl_task_params *tx_sgl_params,
+ struct scsi_sgl_task_params *rx_sgl_params,
+ struct scsi_dif_task_params *dif_task_params);
+
+/* @brief init_initiator_login_request_task - initializes iSCSI Initiator Login
+ * Request task context.
+ *
+ * @param task_params - Pointer to task parameters struct
+ * @param login_req_pdu_header - PDU Header Parameters
+ * @param tx_sgl_task_params - Pointer to SGL task params
+ * @param rx_sgl_task_params - Pointer to SGL task params
+ */
+int init_initiator_login_request_task(struct iscsi_task_params *task_params,
+ struct iscsi_login_req_hdr *login_header,
+ struct scsi_sgl_task_params *tx_params,
+ struct scsi_sgl_task_params *rx_params);
+
+/* @brief init_initiator_nop_out_task - initializes iSCSI Initiator NOP Out
+ * task context.
+ *
+ * @param task_params - Pointer to task parameters struct
+ * @param nop_out_pdu_header - PDU Header Parameters
+ * @param tx_sgl_task_params - Pointer to SGL task params
+ * @param rx_sgl_task_params - Pointer to SGL task params
+ */
+int init_initiator_nop_out_task(struct iscsi_task_params *task_params,
+ struct iscsi_nop_out_hdr *nop_out_pdu_header,
+ struct scsi_sgl_task_params *tx_sgl_params,
+ struct scsi_sgl_task_params *rx_sgl_params);
+
+/* @brief init_initiator_logout_request_task - initializes iSCSI Initiator
+ * Logout Request task context.
+ *
+ * @param task_params - Pointer to task parameters struct
+ * @param logout_pdu_header - PDU Header Parameters
+ * @param tx_sgl_task_params - Pointer to SGL task params
+ * @param rx_sgl_task_params - Pointer to SGL task params
+ */
+int init_initiator_logout_request_task(struct iscsi_task_params *task_params,
+ struct iscsi_logout_req_hdr *logout_hdr,
+ struct scsi_sgl_task_params *tx_params,
+ struct scsi_sgl_task_params *rx_params);
+
+/* @brief init_initiator_tmf_request_task - initializes iSCSI Initiator TMF
+ * task context.
+ *
+ * @param task_params - Pointer to task parameters struct
+ * @param tmf_pdu_header - PDU Header Parameters
+ */
+int init_initiator_tmf_request_task(struct iscsi_task_params *task_params,
+ struct iscsi_tmf_request_hdr *tmf_header);
+
+/* @brief init_initiator_text_request_task - initializes iSCSI Initiator Text
+ * Request task context.
+ *
+ * @param task_params - Pointer to task parameters struct
+ * @param text_request_pdu_header - PDU Header Parameters
+ * @param tx_sgl_task_params - Pointer to Tx SGL task params
+ * @param rx_sgl_task_params - Pointer to Rx SGL task params
+ */
+int init_initiator_text_request_task(struct iscsi_task_params *task_params,
+ struct iscsi_text_request_hdr *text_header,
+ struct scsi_sgl_task_params *tx_params,
+ struct scsi_sgl_task_params *rx_params);
+
+/* @brief init_cleanup_task - initializes Clean task (SQE)
+ *
+ * @param task_params - Pointer to task parameters struct
+ */
+int init_cleanup_task(struct iscsi_task_params *task_params);
+#endif
diff --git a/drivers/scsi/qedi/qedi_fw_scsi.h b/drivers/scsi/qedi/qedi_fw_scsi.h
new file mode 100644
index 0000000..cdaf918
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_fw_scsi.h
@@ -0,0 +1,55 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#ifndef _QEDI_FW_SCSI_H_
+#define _QEDI_FW_SCSI_H_
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+#include "qedi_hsi.h"
+#include <linux/qed/qed_if.h>
+
+struct scsi_sgl_task_params {
+ struct scsi_sge *sgl;
+ struct regpair sgl_phys_addr;
+ u32 total_buffer_size;
+ u16 num_sges;
+ bool small_mid_sge;
+};
+
+struct scsi_dif_task_params {
+ u32 initial_ref_tag;
+ bool initial_ref_tag_is_valid;
+ u16 application_tag;
+ u16 application_tag_mask;
+ u16 dif_block_size_log;
+ bool dif_on_network;
+ bool dif_on_host;
+ u8 host_guard_type;
+ u8 protection_type;
+ u8 ref_tag_mask;
+ bool crc_seed;
+ bool tx_dif_conn_err_en;
+ bool ignore_app_tag;
+ bool keep_ref_tag_const;
+ bool validate_guard;
+ bool validate_app_tag;
+ bool validate_ref_tag;
+ bool forward_guard;
+ bool forward_app_tag;
+ bool forward_ref_tag;
+ bool forward_app_tag_with_mask;
+ bool forward_ref_tag_with_mask;
+};
+
+struct scsi_initiator_cmd_params {
+ struct scsi_sge extended_cdb_sge;
+ struct regpair sense_data_buffer_phys_addr;
+};
+#endif
diff --git a/drivers/scsi/qedi/qedi_gbl.h b/drivers/scsi/qedi/qedi_gbl.h
index 8e488de..63d793f 100644
--- a/drivers/scsi/qedi/qedi_gbl.h
+++ b/drivers/scsi/qedi/qedi_gbl.h
@@ -12,8 +12,14 @@
#include "qedi_iscsi.h"
+#ifdef CONFIG_DEBUG_FS
+extern int qedi_do_not_recover;
+#else
+#define qedi_do_not_recover (0)
+#endif
+
extern uint qedi_io_tracing;
-extern int do_not_recover;
+
extern struct scsi_host_template qedi_host_template;
extern struct iscsi_transport qedi_iscsi_transport;
extern const struct qed_iscsi_ops *qedi_ops;
diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c
index b9f79d3..d1de172 100644
--- a/drivers/scsi/qedi/qedi_iscsi.c
+++ b/drivers/scsi/qedi/qedi_iscsi.c
@@ -175,7 +175,7 @@ static void qedi_destroy_cmd_pool(struct qedi_ctx *qedi,
if (cmd->io_tbl.sge_tbl)
dma_free_coherent(&qedi->pdev->dev,
QEDI_ISCSI_MAX_BDS_PER_CMD *
- sizeof(struct iscsi_sge),
+ sizeof(struct scsi_sge),
cmd->io_tbl.sge_tbl,
cmd->io_tbl.sge_tbl_dma);
@@ -191,7 +191,7 @@ static int qedi_alloc_sget(struct qedi_ctx *qedi, struct iscsi_session *session,
struct qedi_cmd *cmd)
{
struct qedi_io_bdt *io = &cmd->io_tbl;
- struct iscsi_sge *sge;
+ struct scsi_sge *sge;
io->sge_tbl = dma_alloc_coherent(&qedi->pdev->dev,
QEDI_ISCSI_MAX_BDS_PER_CMD *
@@ -708,22 +708,20 @@ static void qedi_conn_get_stats(struct iscsi_cls_conn *cls_conn,
static void qedi_iscsi_prep_generic_pdu_bd(struct qedi_conn *qedi_conn)
{
- struct iscsi_sge *bd_tbl;
+ struct scsi_sge *bd_tbl;
- bd_tbl = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+ bd_tbl = (struct scsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
bd_tbl->sge_addr.hi =
(u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
bd_tbl->sge_addr.lo = (u32)qedi_conn->gen_pdu.req_dma_addr;
bd_tbl->sge_len = qedi_conn->gen_pdu.req_wr_ptr -
qedi_conn->gen_pdu.req_buf;
- bd_tbl->reserved0 = 0;
- bd_tbl = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+ bd_tbl = (struct scsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
bd_tbl->sge_addr.hi =
(u32)((u64)qedi_conn->gen_pdu.resp_dma_addr >> 32);
bd_tbl->sge_addr.lo = (u32)qedi_conn->gen_pdu.resp_dma_addr;
bd_tbl->sge_len = ISCSI_DEF_MAX_RECV_SEG_LEN;
- bd_tbl->reserved0 = 0;
}
static int qedi_iscsi_send_generic_request(struct iscsi_task *task)
@@ -833,7 +831,7 @@ qedi_ep_connect(struct Scsi_Host *shost, struct sockaddr *dst_addr,
return ERR_PTR(ret);
}
- if (do_not_recover) {
+ if (qedi_do_not_recover) {
ret = -ENOMEM;
return ERR_PTR(ret);
}
@@ -957,7 +955,7 @@ static int qedi_ep_poll(struct iscsi_endpoint *ep, int timeout_ms)
struct qedi_endpoint *qedi_ep;
int ret = 0;
- if (do_not_recover)
+ if (qedi_do_not_recover)
return 1;
qedi_ep = ep->dd_data;
@@ -1025,7 +1023,7 @@ static void qedi_ep_disconnect(struct iscsi_endpoint *ep)
}
if (test_bit(QEDI_IN_RECOVERY, &qedi->flags)) {
- if (do_not_recover) {
+ if (qedi_do_not_recover) {
QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
"Do not recover cid=0x%x\n",
qedi_ep->iscsi_cid);
@@ -1039,7 +1037,7 @@ static void qedi_ep_disconnect(struct iscsi_endpoint *ep)
}
}
- if (do_not_recover)
+ if (qedi_do_not_recover)
goto ep_exit_recover;
switch (qedi_ep->state) {
diff --git a/drivers/scsi/qedi/qedi_iscsi.h b/drivers/scsi/qedi/qedi_iscsi.h
index d3c06bb..3247287 100644
--- a/drivers/scsi/qedi/qedi_iscsi.h
+++ b/drivers/scsi/qedi/qedi_iscsi.h
@@ -102,7 +102,7 @@ struct qedi_endpoint {
#define QEDI_SQ_WQES_MIN 16
struct qedi_io_bdt {
- struct iscsi_sge *sge_tbl;
+ struct scsi_sge *sge_tbl;
dma_addr_t sge_tbl_dma;
u16 sge_valid;
};
diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
index 5eda21d..92775a8 100644
--- a/drivers/scsi/qedi/qedi_main.c
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -1805,7 +1805,7 @@ static int __qedi_probe(struct pci_dev *pdev, int mode)
*/
qedi_ops->common->update_pf_params(qedi->cdev, &qedi->pf_params);
- qedi_setup_int(qedi);
+ rc = qedi_setup_int(qedi);
if (rc)
goto stop_iscsi_func;
@@ -2007,6 +2007,7 @@ static void qedi_remove(struct pci_dev *pdev)
static struct pci_device_id qedi_pci_tbl[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, 0x165E) },
+ { PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, 0x8084) },
{ 0 },
};
MODULE_DEVICE_TABLE(pci, qedi_pci_tbl);
diff --git a/drivers/scsi/qedi/qedi_version.h b/drivers/scsi/qedi/qedi_version.h
index 9543a1b..d61e3ac 100644
--- a/drivers/scsi/qedi/qedi_version.h
+++ b/drivers/scsi/qedi/qedi_version.h
@@ -7,8 +7,8 @@
* this source tree.
*/
-#define QEDI_MODULE_VERSION "8.10.3.0"
+#define QEDI_MODULE_VERSION "8.10.4.0"
#define QEDI_DRIVER_MAJOR_VER 8
#define QEDI_DRIVER_MINOR_VER 10
-#define QEDI_DRIVER_REV_VER 3
+#define QEDI_DRIVER_REV_VER 4
#define QEDI_DRIVER_ENG_VER 0
diff --git a/drivers/scsi/qla2xxx/Kconfig b/drivers/scsi/qla2xxx/Kconfig
index 67c0d5a..de95293 100644
--- a/drivers/scsi/qla2xxx/Kconfig
+++ b/drivers/scsi/qla2xxx/Kconfig
@@ -3,6 +3,7 @@
depends on PCI && SCSI
depends on SCSI_FC_ATTRS
select FW_LOADER
+ select BTREE
---help---
This qla2xxx driver supports all QLogic Fibre Channel
PCI and PCIe host adapters.
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index f610103..435ff7f 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -2154,8 +2154,6 @@ qla24xx_vport_delete(struct fc_vport *fc_vport)
"Timer for the VP[%d] has stopped\n", vha->vp_idx);
}
- BUG_ON(atomic_read(&vha->vref_count));
-
qla2x00_free_fcports(vha);
mutex_lock(&ha->vport_lock);
@@ -2166,7 +2164,7 @@ qla24xx_vport_delete(struct fc_vport *fc_vport)
dma_free_coherent(&ha->pdev->dev, vha->gnl.size, vha->gnl.l,
vha->gnl.ldma);
- if (vha->qpair->vp_idx == vha->vp_idx) {
+ if (vha->qpair && vha->qpair->vp_idx == vha->vp_idx) {
if (qla2xxx_delete_qpair(vha, vha->qpair) != QLA_SUCCESS)
ql_log(ql_log_warn, vha, 0x7087,
"Queue Pair delete failed.\n");
diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c
index 21d9fb7..51b4179 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/drivers/scsi/qla2xxx/qla_dbg.c
@@ -2707,13 +2707,9 @@ ql_dump_buffer(uint32_t level, scsi_qla_host_t *vha, int32_t id,
"%-+5d 0 1 2 3 4 5 6 7 8 9 A B C D E F\n", size);
ql_dbg(level, vha, id,
"----- -----------------------------------------------\n");
- for (cnt = 0; cnt < size; cnt++, buf++) {
- if (cnt % 16 == 0)
- ql_dbg(level, vha, id, "%04x:", cnt & ~0xFU);
- printk(" %02x", *buf);
- if (cnt % 16 == 15)
- printk("\n");
+ for (cnt = 0; cnt < size; cnt += 16) {
+ ql_dbg(level, vha, id, "%04x: ", cnt);
+ print_hex_dump(KERN_CONT, "", DUMP_PREFIX_NONE, 16, 1,
+ buf + cnt, min(16U, size - cnt), false);
}
- if (cnt % 16 != 0)
- printk("\n");
}
diff --git a/drivers/scsi/qla2xxx/qla_dbg.h b/drivers/scsi/qla2xxx/qla_dbg.h
index e1fc4e6..c6bffe9 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.h
+++ b/drivers/scsi/qla2xxx/qla_dbg.h
@@ -348,6 +348,7 @@ ql_log_pci(uint32_t, struct pci_dev *pdev, int32_t, const char *fmt, ...);
#define ql_dbg_tgt 0x00004000 /* Target mode */
#define ql_dbg_tgt_mgt 0x00002000 /* Target mode management */
#define ql_dbg_tgt_tmr 0x00001000 /* Target mode task management */
+#define ql_dbg_tgt_dif 0x00000800 /* Target mode dif */
extern int qla27xx_dump_mpi_ram(struct qla_hw_data *, uint32_t, uint32_t *,
uint32_t, void **);
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 625d438..ae11901 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -25,6 +25,7 @@
#include <linux/firmware.h>
#include <linux/aer.h>
#include <linux/mutex.h>
+#include <linux/btree.h>
#include <scsi/scsi.h>
#include <scsi/scsi_host.h>
@@ -395,11 +396,15 @@ struct srb_iocb {
struct completion comp;
} abt;
struct ct_arg ctarg;
+#define MAX_IOCB_MB_REG 28
+#define SIZEOF_IOCB_MB_REG (MAX_IOCB_MB_REG * sizeof(uint16_t))
struct {
- __le16 in_mb[28]; /* fr fw */
- __le16 out_mb[28]; /* to fw */
+ __le16 in_mb[MAX_IOCB_MB_REG]; /* from FW */
+ __le16 out_mb[MAX_IOCB_MB_REG]; /* to FW */
void *out, *in;
dma_addr_t out_dma, in_dma;
+ struct completion comp;
+ int rc;
} mbx;
struct {
struct imm_ntfy_from_isp *ntfy;
@@ -437,7 +442,7 @@ typedef struct srb {
uint32_t handle;
uint16_t flags;
uint16_t type;
- char *name;
+ const char *name;
int iocbs;
struct qla_qpair *qpair;
u32 gen1; /* scratch */
@@ -2300,6 +2305,8 @@ typedef struct fc_port {
struct ct_sns_desc ct_desc;
enum discovery_state disc_state;
enum login_state fw_login_state;
+ unsigned long plogi_nack_done_deadline;
+
u32 login_gen, last_login_gen;
u32 rscn_gen, last_rscn_gen;
u32 chip_reset;
@@ -3106,6 +3113,16 @@ struct qla_chip_state_84xx {
uint32_t gold_fw_version;
};
+struct qla_dif_statistics {
+ uint64_t dif_input_bytes;
+ uint64_t dif_output_bytes;
+ uint64_t dif_input_requests;
+ uint64_t dif_output_requests;
+ uint32_t dif_guard_err;
+ uint32_t dif_ref_tag_err;
+ uint32_t dif_app_tag_err;
+};
+
struct qla_statistics {
uint32_t total_isp_aborts;
uint64_t input_bytes;
@@ -3118,6 +3135,8 @@ struct qla_statistics {
uint32_t stat_max_pend_cmds;
uint32_t stat_max_qfull_cmds_alloc;
uint32_t stat_max_qfull_cmds_dropped;
+
+ struct qla_dif_statistics qla_dif_stats;
};
struct bidi_statistics {
@@ -3125,6 +3144,16 @@ struct bidi_statistics {
unsigned long long transfer_bytes;
};
+struct qla_tc_param {
+ struct scsi_qla_host *vha;
+ uint32_t blk_sz;
+ uint32_t bufflen;
+ struct scatterlist *sg;
+ struct scatterlist *prot_sg;
+ struct crc_context *ctx;
+ uint8_t *ctx_dsd_alloced;
+};
+
/* Multi queue support */
#define MBC_INITIALIZE_MULTIQ 0x1f
#define QLA_QUE_PAGE 0X1000
@@ -3272,6 +3301,8 @@ struct qlt_hw_data {
uint8_t tgt_node_name[WWN_SIZE];
struct dentry *dfs_tgt_sess;
+ struct dentry *dfs_tgt_port_database;
+
struct list_head q_full_list;
uint32_t num_pend_cmds;
uint32_t num_qfull_cmds_alloc;
@@ -3281,6 +3312,7 @@ struct qlt_hw_data {
spinlock_t sess_lock;
int rspq_vector_cpuid;
spinlock_t atio_lock ____cacheline_aligned;
+ struct btree_head32 host_map;
};
#define MAX_QFULL_CMDS_ALLOC 8192
@@ -3290,6 +3322,10 @@ struct qlt_hw_data {
#define LEAK_EXCHG_THRESH_HOLD_PERCENT 75 /* 75 percent */
+#define QLA_EARLY_LINKUP(_ha) \
+ ((_ha->flags.n2n_ae || _ha->flags.lip_ae) && \
+ _ha->flags.fw_started && !_ha->flags.fw_init_done)
+
/*
* Qlogic host adapter specific data structure.
*/
@@ -3339,7 +3375,11 @@ struct qla_hw_data {
uint32_t fawwpn_enabled:1;
uint32_t exlogins_enabled:1;
uint32_t exchoffld_enabled:1;
- /* 35 bits */
+
+ uint32_t lip_ae:1;
+ uint32_t n2n_ae:1;
+ uint32_t fw_started:1;
+ uint32_t fw_init_done:1;
} flags;
/* This spinlock is used to protect "io transactions", you must
@@ -3432,7 +3472,6 @@ struct qla_hw_data {
#define P2P_LOOP 3
uint8_t interrupts_on;
uint32_t isp_abort_cnt;
-
#define PCI_DEVICE_ID_QLOGIC_ISP2532 0x2532
#define PCI_DEVICE_ID_QLOGIC_ISP8432 0x8432
#define PCI_DEVICE_ID_QLOGIC_ISP8001 0x8001
@@ -3913,6 +3952,7 @@ typedef struct scsi_qla_host {
struct list_head vp_fcports; /* list of fcports */
struct list_head work_list;
spinlock_t work_lock;
+ struct work_struct iocb_work;
/* Commonly used flags and state information. */
struct Scsi_Host *host;
@@ -4076,6 +4116,7 @@ typedef struct scsi_qla_host {
/* Count of active session/fcport */
int fcport_count;
wait_queue_head_t fcport_waitQ;
+ wait_queue_head_t vref_waitq;
} scsi_qla_host_t;
struct qla27xx_image_status {
@@ -4131,14 +4172,17 @@ struct qla2_sgx {
mb(); \
if (__vha->flags.delete_progress) { \
atomic_dec(&__vha->vref_count); \
+ wake_up(&__vha->vref_waitq); \
__bail = 1; \
} else { \
__bail = 0; \
} \
} while (0)
-#define QLA_VHA_MARK_NOT_BUSY(__vha) \
+#define QLA_VHA_MARK_NOT_BUSY(__vha) do { \
atomic_dec(&__vha->vref_count); \
+ wake_up(&__vha->vref_waitq); \
+} while (0) \
#define QLA_QPAIR_MARK_BUSY(__qpair, __bail) do { \
atomic_inc(&__qpair->ref_count); \
diff --git a/drivers/scsi/qla2xxx/qla_dfs.c b/drivers/scsi/qla2xxx/qla_dfs.c
index b48cce6..989e17b 100644
--- a/drivers/scsi/qla2xxx/qla_dfs.c
+++ b/drivers/scsi/qla2xxx/qla_dfs.c
@@ -19,11 +19,11 @@ qla2x00_dfs_tgt_sess_show(struct seq_file *s, void *unused)
struct qla_hw_data *ha = vha->hw;
unsigned long flags;
struct fc_port *sess = NULL;
- struct qla_tgt *tgt= vha->vha_tgt.qla_tgt;
+ struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
- seq_printf(s, "%s\n",vha->host_str);
+ seq_printf(s, "%s\n", vha->host_str);
if (tgt) {
- seq_printf(s, "Port ID Port Name Handle\n");
+ seq_puts(s, "Port ID Port Name Handle\n");
spin_lock_irqsave(&ha->tgt.sess_lock, flags);
list_for_each_entry(sess, &vha->vp_fcports, list)
@@ -44,7 +44,6 @@ qla2x00_dfs_tgt_sess_open(struct inode *inode, struct file *file)
return single_open(file, qla2x00_dfs_tgt_sess_show, vha);
}
-
static const struct file_operations dfs_tgt_sess_ops = {
.open = qla2x00_dfs_tgt_sess_open,
.read = seq_read,
@@ -53,6 +52,78 @@ static const struct file_operations dfs_tgt_sess_ops = {
};
static int
+qla2x00_dfs_tgt_port_database_show(struct seq_file *s, void *unused)
+{
+ scsi_qla_host_t *vha = s->private;
+ struct qla_hw_data *ha = vha->hw;
+ struct gid_list_info *gid_list;
+ dma_addr_t gid_list_dma;
+ fc_port_t fc_port;
+ char *id_iter;
+ int rc, i;
+ uint16_t entries, loop_id;
+ struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
+
+ seq_printf(s, "%s\n", vha->host_str);
+ if (tgt) {
+ gid_list = dma_alloc_coherent(&ha->pdev->dev,
+ qla2x00_gid_list_size(ha),
+ &gid_list_dma, GFP_KERNEL);
+ if (!gid_list) {
+ ql_dbg(ql_dbg_user, vha, 0x705c,
+ "DMA allocation failed for %u\n",
+ qla2x00_gid_list_size(ha));
+ return 0;
+ }
+
+ rc = qla24xx_gidlist_wait(vha, gid_list, gid_list_dma,
+ &entries);
+ if (rc != QLA_SUCCESS)
+ goto out_free_id_list;
+
+ id_iter = (char *)gid_list;
+
+ seq_puts(s, "Port Name Port ID Loop ID\n");
+
+ for (i = 0; i < entries; i++) {
+ struct gid_list_info *gid =
+ (struct gid_list_info *)id_iter;
+ loop_id = le16_to_cpu(gid->loop_id);
+ memset(&fc_port, 0, sizeof(fc_port_t));
+
+ fc_port.loop_id = loop_id;
+
+ rc = qla24xx_gpdb_wait(vha, &fc_port, 0);
+ seq_printf(s, "%8phC %02x%02x%02x %d\n",
+ fc_port.port_name, fc_port.d_id.b.domain,
+ fc_port.d_id.b.area, fc_port.d_id.b.al_pa,
+ fc_port.loop_id);
+ id_iter += ha->gid_list_info_size;
+ }
+out_free_id_list:
+ dma_free_coherent(&ha->pdev->dev, qla2x00_gid_list_size(ha),
+ gid_list, gid_list_dma);
+ }
+
+ return 0;
+}
+
+static int
+qla2x00_dfs_tgt_port_database_open(struct inode *inode, struct file *file)
+{
+ scsi_qla_host_t *vha = inode->i_private;
+
+ return single_open(file, qla2x00_dfs_tgt_port_database_show, vha);
+}
+
+static const struct file_operations dfs_tgt_port_database_ops = {
+ .open = qla2x00_dfs_tgt_port_database_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static int
qla_dfs_fw_resource_cnt_show(struct seq_file *s, void *unused)
{
struct scsi_qla_host *vha = s->private;
@@ -114,6 +185,21 @@ qla_dfs_tgt_counters_show(struct seq_file *s, void *unused)
seq_printf(s, "num Q full sent = %lld\n",
vha->tgt_counters.num_q_full_sent);
+ /* DIF stats */
+ seq_printf(s, "DIF Inp Bytes = %lld\n",
+ vha->qla_stats.qla_dif_stats.dif_input_bytes);
+ seq_printf(s, "DIF Outp Bytes = %lld\n",
+ vha->qla_stats.qla_dif_stats.dif_output_bytes);
+ seq_printf(s, "DIF Inp Req = %lld\n",
+ vha->qla_stats.qla_dif_stats.dif_input_requests);
+ seq_printf(s, "DIF Outp Req = %lld\n",
+ vha->qla_stats.qla_dif_stats.dif_output_requests);
+ seq_printf(s, "DIF Guard err = %d\n",
+ vha->qla_stats.qla_dif_stats.dif_guard_err);
+ seq_printf(s, "DIF Ref tag err = %d\n",
+ vha->qla_stats.qla_dif_stats.dif_ref_tag_err);
+ seq_printf(s, "DIF App tag err = %d\n",
+ vha->qla_stats.qla_dif_stats.dif_app_tag_err);
return 0;
}
@@ -281,6 +367,14 @@ qla2x00_dfs_setup(scsi_qla_host_t *vha)
goto out;
}
+ ha->tgt.dfs_tgt_port_database = debugfs_create_file("tgt_port_database",
+ S_IRUSR, ha->dfs_dir, vha, &dfs_tgt_port_database_ops);
+ if (!ha->tgt.dfs_tgt_port_database) {
+ ql_log(ql_log_warn, vha, 0xffff,
+ "Unable to create debugFS tgt_port_database node.\n");
+ goto out;
+ }
+
ha->dfs_fce = debugfs_create_file("fce", S_IRUSR, ha->dfs_dir, vha,
&dfs_fce_ops);
if (!ha->dfs_fce) {
@@ -311,6 +405,11 @@ qla2x00_dfs_remove(scsi_qla_host_t *vha)
ha->tgt.dfs_tgt_sess = NULL;
}
+ if (ha->tgt.dfs_tgt_port_database) {
+ debugfs_remove(ha->tgt.dfs_tgt_port_database);
+ ha->tgt.dfs_tgt_port_database = NULL;
+ }
+
if (ha->dfs_fw_resource_cnt) {
debugfs_remove(ha->dfs_fw_resource_cnt);
ha->dfs_fw_resource_cnt = NULL;
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index b3d6441..5b24517 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -193,6 +193,7 @@ extern int qla24xx_post_upd_fcport_work(struct scsi_qla_host *, fc_port_t *);
void qla2x00_handle_login_done_event(struct scsi_qla_host *, fc_port_t *,
uint16_t *);
int qla24xx_post_gnl_work(struct scsi_qla_host *, fc_port_t *);
+int qla24xx_async_abort_cmd(srb_t *);
/*
* Global Functions in qla_mid.c source file.
@@ -256,11 +257,11 @@ extern unsigned long qla2x00_get_async_timeout(struct scsi_qla_host *);
extern void *qla2x00_alloc_iocbs(scsi_qla_host_t *, srb_t *);
extern int qla2x00_issue_marker(scsi_qla_host_t *, int);
extern int qla24xx_walk_and_build_sglist_no_difb(struct qla_hw_data *, srb_t *,
- uint32_t *, uint16_t, struct qla_tgt_cmd *);
+ uint32_t *, uint16_t, struct qla_tc_param *);
extern int qla24xx_walk_and_build_sglist(struct qla_hw_data *, srb_t *,
- uint32_t *, uint16_t, struct qla_tgt_cmd *);
+ uint32_t *, uint16_t, struct qla_tc_param *);
extern int qla24xx_walk_and_build_prot_sglist(struct qla_hw_data *, srb_t *,
- uint32_t *, uint16_t, struct qla_tgt_cmd *);
+ uint32_t *, uint16_t, struct qla_tc_param *);
extern int qla24xx_get_one_block_sg(uint32_t, struct qla2_sgx *, uint32_t *);
extern int qla24xx_configure_prot_mode(srb_t *, uint16_t *);
extern int qla24xx_build_scsi_crc_2_iocbs(srb_t *,
@@ -368,7 +369,7 @@ qla2x00_get_link_status(scsi_qla_host_t *, uint16_t, struct link_statistics *,
extern int
qla24xx_get_isp_stats(scsi_qla_host_t *, struct link_statistics *,
- dma_addr_t, uint);
+ dma_addr_t, uint16_t);
extern int qla24xx_abort_command(srb_t *);
extern int qla24xx_async_abort_command(srb_t *);
@@ -472,6 +473,13 @@ qla2x00_dump_mctp_data(scsi_qla_host_t *, dma_addr_t, uint32_t, uint32_t);
extern int
qla26xx_dport_diagnostics(scsi_qla_host_t *, void *, uint, uint);
+int qla24xx_send_mb_cmd(struct scsi_qla_host *, mbx_cmd_t *);
+int qla24xx_gpdb_wait(struct scsi_qla_host *, fc_port_t *, u8);
+int qla24xx_gidlist_wait(struct scsi_qla_host *, void *, dma_addr_t,
+ uint16_t *);
+int __qla24xx_parse_gpdb(struct scsi_qla_host *, fc_port_t *,
+ struct port_database_24xx *);
+
/*
* Global Function Prototypes in qla_isr.c source file.
*/
@@ -846,5 +854,7 @@ extern struct fc_port *qlt_find_sess_invalidate_other(scsi_qla_host_t *,
uint64_t wwn, port_id_t port_id, uint16_t loop_id, struct fc_port **);
void qla24xx_delete_sess_fn(struct work_struct *);
void qlt_unknown_atio_work_fn(struct work_struct *);
+void qlt_update_host_map(struct scsi_qla_host *, port_id_t);
+void qlt_remove_target_resources(struct qla_hw_data *);
#endif /* _QLA_GBL_H */
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 32fb900..f9d2fe7 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -629,7 +629,6 @@ void qla24xx_async_gpdb_sp_done(void *s, int res)
struct srb *sp = s;
struct scsi_qla_host *vha = sp->vha;
struct qla_hw_data *ha = vha->hw;
- uint64_t zero = 0;
struct port_database_24xx *pd;
fc_port_t *fcport = sp->fcport;
u16 *mb = sp->u.iocb_cmd.u.mbx.in_mb;
@@ -649,48 +648,7 @@ void qla24xx_async_gpdb_sp_done(void *s, int res)
pd = (struct port_database_24xx *)sp->u.iocb_cmd.u.mbx.in;
- /* Check for logged in state. */
- if (pd->current_login_state != PDS_PRLI_COMPLETE &&
- pd->last_login_state != PDS_PRLI_COMPLETE) {
- ql_dbg(ql_dbg_mbx, vha, 0xffff,
- "Unable to verify login-state (%x/%x) for "
- "loop_id %x.\n", pd->current_login_state,
- pd->last_login_state, fcport->loop_id);
- rval = QLA_FUNCTION_FAILED;
- goto gpd_error_out;
- }
-
- if (fcport->loop_id == FC_NO_LOOP_ID ||
- (memcmp(fcport->port_name, (uint8_t *)&zero, 8) &&
- memcmp(fcport->port_name, pd->port_name, 8))) {
- /* We lost the device mid way. */
- rval = QLA_NOT_LOGGED_IN;
- goto gpd_error_out;
- }
-
- /* Names are little-endian. */
- memcpy(fcport->node_name, pd->node_name, WWN_SIZE);
-
- /* Get port_id of device. */
- fcport->d_id.b.domain = pd->port_id[0];
- fcport->d_id.b.area = pd->port_id[1];
- fcport->d_id.b.al_pa = pd->port_id[2];
- fcport->d_id.b.rsvd_1 = 0;
-
- /* If not target must be initiator or unknown type. */
- if ((pd->prli_svc_param_word_3[0] & BIT_4) == 0)
- fcport->port_type = FCT_INITIATOR;
- else
- fcport->port_type = FCT_TARGET;
-
- /* Passback COS information. */
- fcport->supported_classes = (pd->flags & PDF_CLASS_2) ?
- FC_COS_CLASS2 : FC_COS_CLASS3;
-
- if (pd->prli_svc_param_word_3[0] & BIT_7) {
- fcport->flags |= FCF_CONF_COMP_SUPPORTED;
- fcport->conf_compl_supported = 1;
- }
+ rval = __qla24xx_parse_gpdb(vha, fcport, pd);
gpd_error_out:
memset(&ea, 0, sizeof(ea));
@@ -876,10 +834,14 @@ int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport)
fcport->login_retry--;
if ((fcport->fw_login_state == DSC_LS_PLOGI_PEND) ||
- (fcport->fw_login_state == DSC_LS_PLOGI_COMP) ||
(fcport->fw_login_state == DSC_LS_PRLI_PEND))
return 0;
+ if (fcport->fw_login_state == DSC_LS_PLOGI_COMP) {
+ if (time_before_eq(jiffies, fcport->plogi_nack_done_deadline))
+ return 0;
+ }
+
/* for pure Target Mode. Login will not be initiated */
if (vha->host->active_mode == MODE_TARGET)
return 0;
@@ -1041,10 +1003,14 @@ void qla24xx_handle_relogin_event(scsi_qla_host_t *vha,
fcport->flags);
if ((fcport->fw_login_state == DSC_LS_PLOGI_PEND) ||
- (fcport->fw_login_state == DSC_LS_PLOGI_COMP) ||
(fcport->fw_login_state == DSC_LS_PRLI_PEND))
return;
+ if (fcport->fw_login_state == DSC_LS_PLOGI_COMP) {
+ if (time_before_eq(jiffies, fcport->plogi_nack_done_deadline))
+ return;
+ }
+
if (fcport->flags & FCF_ASYNC_SENT) {
fcport->login_retry++;
set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
@@ -1258,7 +1224,7 @@ qla24xx_abort_sp_done(void *ptr, int res)
complete(&abt->u.abt.comp);
}
-static int
+int
qla24xx_async_abort_cmd(srb_t *cmd_sp)
{
scsi_qla_host_t *vha = cmd_sp->vha;
@@ -3212,6 +3178,7 @@ qla2x00_init_rings(scsi_qla_host_t *vha)
} else {
ql_dbg(ql_dbg_init, vha, 0x00d3,
"Init Firmware -- success.\n");
+ ha->flags.fw_started = 1;
}
return (rval);
@@ -3374,8 +3341,8 @@ qla2x00_configure_hba(scsi_qla_host_t *vha)
uint8_t domain;
char connect_type[22];
struct qla_hw_data *ha = vha->hw;
- unsigned long flags;
scsi_qla_host_t *base_vha = pci_get_drvdata(ha->pdev);
+ port_id_t id;
/* Get host addresses. */
rval = qla2x00_get_adapter_id(vha,
@@ -3453,13 +3420,11 @@ qla2x00_configure_hba(scsi_qla_host_t *vha)
/* Save Host port and loop ID. */
/* byte order - Big Endian */
- vha->d_id.b.domain = domain;
- vha->d_id.b.area = area;
- vha->d_id.b.al_pa = al_pa;
-
- spin_lock_irqsave(&ha->vport_slock, flags);
- qlt_update_vp_map(vha, SET_AL_PA);
- spin_unlock_irqrestore(&ha->vport_slock, flags);
+ id.b.domain = domain;
+ id.b.area = area;
+ id.b.al_pa = al_pa;
+ id.b.rsvd_1 = 0;
+ qlt_update_host_map(vha, id);
if (!vha->flags.init_done)
ql_log(ql_log_info, vha, 0x2010,
@@ -4036,6 +4001,7 @@ qla2x00_configure_loop(scsi_qla_host_t *vha)
atomic_set(&vha->loop_state, LOOP_READY);
ql_dbg(ql_dbg_disc, vha, 0x2069,
"LOOP READY.\n");
+ ha->flags.fw_init_done = 1;
/*
* Process any ATIO queue entries that came in
@@ -5148,6 +5114,7 @@ qla2x00_update_fcports(scsi_qla_host_t *base_vha)
}
}
atomic_dec(&vha->vref_count);
+ wake_up(&vha->vref_waitq);
}
spin_unlock_irqrestore(&ha->vport_slock, flags);
}
@@ -5526,6 +5493,11 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha)
if (!(IS_P3P_TYPE(ha)))
ha->isp_ops->reset_chip(vha);
+ ha->flags.n2n_ae = 0;
+ ha->flags.lip_ae = 0;
+ ha->current_topology = 0;
+ ha->flags.fw_started = 0;
+ ha->flags.fw_init_done = 0;
ha->chip_reset++;
atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME);
@@ -6802,6 +6774,8 @@ qla2x00_try_to_stop_firmware(scsi_qla_host_t *vha)
return;
if (!ha->fw_major_version)
return;
+ if (!ha->flags.fw_started)
+ return;
ret = qla2x00_stop_firmware(vha);
for (retries = 5; ret != QLA_SUCCESS && ret != QLA_FUNCTION_TIMEOUT &&
@@ -6815,6 +6789,9 @@ qla2x00_try_to_stop_firmware(scsi_qla_host_t *vha)
"Attempting retry of stop-firmware command.\n");
ret = qla2x00_stop_firmware(vha);
}
+
+ ha->flags.fw_started = 0;
+ ha->flags.fw_init_done = 0;
}
int
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 5350792..ea027f6 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -889,7 +889,7 @@ qla24xx_get_one_block_sg(uint32_t blk_sz, struct qla2_sgx *sgx,
int
qla24xx_walk_and_build_sglist_no_difb(struct qla_hw_data *ha, srb_t *sp,
- uint32_t *dsd, uint16_t tot_dsds, struct qla_tgt_cmd *tc)
+ uint32_t *dsd, uint16_t tot_dsds, struct qla_tc_param *tc)
{
void *next_dsd;
uint8_t avail_dsds = 0;
@@ -898,7 +898,6 @@ qla24xx_walk_and_build_sglist_no_difb(struct qla_hw_data *ha, srb_t *sp,
struct scatterlist *sg_prot;
uint32_t *cur_dsd = dsd;
uint16_t used_dsds = tot_dsds;
-
uint32_t prot_int; /* protection interval */
uint32_t partial;
struct qla2_sgx sgx;
@@ -966,7 +965,7 @@ qla24xx_walk_and_build_sglist_no_difb(struct qla_hw_data *ha, srb_t *sp,
} else {
list_add_tail(&dsd_ptr->list,
&(tc->ctx->dsd_list));
- tc->ctx_dsd_alloced = 1;
+ *tc->ctx_dsd_alloced = 1;
}
@@ -1005,7 +1004,7 @@ qla24xx_walk_and_build_sglist_no_difb(struct qla_hw_data *ha, srb_t *sp,
int
qla24xx_walk_and_build_sglist(struct qla_hw_data *ha, srb_t *sp, uint32_t *dsd,
- uint16_t tot_dsds, struct qla_tgt_cmd *tc)
+ uint16_t tot_dsds, struct qla_tc_param *tc)
{
void *next_dsd;
uint8_t avail_dsds = 0;
@@ -1066,7 +1065,7 @@ qla24xx_walk_and_build_sglist(struct qla_hw_data *ha, srb_t *sp, uint32_t *dsd,
} else {
list_add_tail(&dsd_ptr->list,
&(tc->ctx->dsd_list));
- tc->ctx_dsd_alloced = 1;
+ *tc->ctx_dsd_alloced = 1;
}
/* add new list to cmd iocb or last list */
@@ -1092,7 +1091,7 @@ qla24xx_walk_and_build_sglist(struct qla_hw_data *ha, srb_t *sp, uint32_t *dsd,
int
qla24xx_walk_and_build_prot_sglist(struct qla_hw_data *ha, srb_t *sp,
- uint32_t *dsd, uint16_t tot_dsds, struct qla_tgt_cmd *tc)
+ uint32_t *dsd, uint16_t tot_dsds, struct qla_tc_param *tc)
{
void *next_dsd;
uint8_t avail_dsds = 0;
@@ -1158,7 +1157,7 @@ qla24xx_walk_and_build_prot_sglist(struct qla_hw_data *ha, srb_t *sp,
} else {
list_add_tail(&dsd_ptr->list,
&(tc->ctx->dsd_list));
- tc->ctx_dsd_alloced = 1;
+ *tc->ctx_dsd_alloced = 1;
}
/* add new list to cmd iocb or last list */
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 3c66ea2..3203367 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -708,6 +708,8 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb)
"mbx7=%xh.\n", mb[1], mb[2], mb[3], mbx);
ha->isp_ops->fw_dump(vha, 1);
+ ha->flags.fw_init_done = 0;
+ ha->flags.fw_started = 0;
if (IS_FWI2_CAPABLE(ha)) {
if (mb[1] == 0 && mb[2] == 0) {
@@ -761,6 +763,9 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb)
break;
case MBA_LIP_OCCURRED: /* Loop Initialization Procedure */
+ ha->flags.lip_ae = 1;
+ ha->flags.n2n_ae = 0;
+
ql_dbg(ql_dbg_async, vha, 0x5009,
"LIP occurred (%x).\n", mb[1]);
@@ -797,6 +802,10 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb)
break;
case MBA_LOOP_DOWN: /* Loop Down Event */
+ ha->flags.n2n_ae = 0;
+ ha->flags.lip_ae = 0;
+ ha->current_topology = 0;
+
mbx = (IS_QLA81XX(ha) || IS_QLA8031(ha))
? RD_REG_WORD(®24->mailbox4) : 0;
mbx = (IS_P3P_TYPE(ha)) ? RD_REG_WORD(®82->mailbox_out[4])
@@ -866,6 +875,9 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb)
/* case MBA_DCBX_COMPLETE: */
case MBA_POINT_TO_POINT: /* Point-to-Point */
+ ha->flags.lip_ae = 0;
+ ha->flags.n2n_ae = 1;
+
if (IS_QLA2100(ha))
break;
@@ -1620,9 +1632,9 @@ qla24xx_logio_entry(scsi_qla_host_t *vha, struct req_que *req,
QLA_LOGIO_LOGIN_RETRIED : 0;
if (logio->entry_status) {
ql_log(ql_log_warn, fcport->vha, 0x5034,
- "Async-%s error entry - hdl=%x"
+ "Async-%s error entry - %8phC hdl=%x"
"portid=%02x%02x%02x entry-status=%x.\n",
- type, sp->handle, fcport->d_id.b.domain,
+ type, fcport->port_name, sp->handle, fcport->d_id.b.domain,
fcport->d_id.b.area, fcport->d_id.b.al_pa,
logio->entry_status);
ql_dump_buffer(ql_dbg_async + ql_dbg_buffer, vha, 0x504d,
@@ -1633,8 +1645,9 @@ qla24xx_logio_entry(scsi_qla_host_t *vha, struct req_que *req,
if (le16_to_cpu(logio->comp_status) == CS_COMPLETE) {
ql_dbg(ql_dbg_async, fcport->vha, 0x5036,
- "Async-%s complete - hdl=%x portid=%02x%02x%02x "
- "iop0=%x.\n", type, sp->handle, fcport->d_id.b.domain,
+ "Async-%s complete - %8phC hdl=%x portid=%02x%02x%02x "
+ "iop0=%x.\n", type, fcport->port_name, sp->handle,
+ fcport->d_id.b.domain,
fcport->d_id.b.area, fcport->d_id.b.al_pa,
le32_to_cpu(logio->io_parameter[0]));
@@ -1674,6 +1687,17 @@ qla24xx_logio_entry(scsi_qla_host_t *vha, struct req_que *req,
case LSC_SCODE_NPORT_USED:
data[0] = MBS_LOOP_ID_USED;
break;
+ case LSC_SCODE_CMD_FAILED:
+ if (iop[1] == 0x0606) {
+ /*
+ * PLOGI/PRLI Completed. We must have Recv PLOGI/PRLI,
+ * Target side acked.
+ */
+ data[0] = MBS_COMMAND_COMPLETE;
+ goto logio_done;
+ }
+ data[0] = MBS_COMMAND_ERROR;
+ break;
case LSC_SCODE_NOXCB:
vha->hw->exch_starvation++;
if (vha->hw->exch_starvation > 5) {
@@ -1695,8 +1719,9 @@ qla24xx_logio_entry(scsi_qla_host_t *vha, struct req_que *req,
}
ql_dbg(ql_dbg_async, fcport->vha, 0x5037,
- "Async-%s failed - hdl=%x portid=%02x%02x%02x comp=%x "
- "iop0=%x iop1=%x.\n", type, sp->handle, fcport->d_id.b.domain,
+ "Async-%s failed - %8phC hdl=%x portid=%02x%02x%02x comp=%x "
+ "iop0=%x iop1=%x.\n", type, fcport->port_name,
+ sp->handle, fcport->d_id.b.domain,
fcport->d_id.b.area, fcport->d_id.b.al_pa,
le16_to_cpu(logio->comp_status),
le32_to_cpu(logio->io_parameter[0]),
@@ -2679,7 +2704,7 @@ qla24xx_abort_iocb_entry(scsi_qla_host_t *vha, struct req_que *req,
return;
abt = &sp->u.iocb_cmd;
- abt->u.abt.comp_status = le32_to_cpu(pkt->nport_handle);
+ abt->u.abt.comp_status = le16_to_cpu(pkt->nport_handle);
sp->done(sp, 0);
}
@@ -2693,7 +2718,7 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha,
struct sts_entry_24xx *pkt;
struct qla_hw_data *ha = vha->hw;
- if (!vha->flags.online)
+ if (!ha->flags.fw_started)
return;
while (rsp->ring_ptr->signature != RESPONSE_PROCESSED) {
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 35079f4..a113ab3 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -10,6 +10,28 @@
#include <linux/delay.h>
#include <linux/gfp.h>
+static struct mb_cmd_name {
+ uint16_t cmd;
+ const char *str;
+} mb_str[] = {
+ {MBC_GET_PORT_DATABASE, "GPDB"},
+ {MBC_GET_ID_LIST, "GIDList"},
+ {MBC_GET_LINK_PRIV_STATS, "Stats"},
+};
+
+static const char *mb_to_str(uint16_t cmd)
+{
+ int i;
+ struct mb_cmd_name *e;
+
+ for (i = 0; i < ARRAY_SIZE(mb_str); i++) {
+ e = mb_str + i;
+ if (cmd == e->cmd)
+ return e->str;
+ }
+ return "unknown";
+}
+
static struct rom_cmd {
uint16_t cmd;
} rom_cmds[] = {
@@ -2818,7 +2840,7 @@ qla2x00_get_link_status(scsi_qla_host_t *vha, uint16_t loop_id,
int
qla24xx_get_isp_stats(scsi_qla_host_t *vha, struct link_statistics *stats,
- dma_addr_t stats_dma, uint options)
+ dma_addr_t stats_dma, uint16_t options)
{
int rval;
mbx_cmd_t mc;
@@ -2828,19 +2850,17 @@ qla24xx_get_isp_stats(scsi_qla_host_t *vha, struct link_statistics *stats,
ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x1088,
"Entered %s.\n", __func__);
- mcp->mb[0] = MBC_GET_LINK_PRIV_STATS;
- mcp->mb[2] = MSW(stats_dma);
- mcp->mb[3] = LSW(stats_dma);
- mcp->mb[6] = MSW(MSD(stats_dma));
- mcp->mb[7] = LSW(MSD(stats_dma));
- mcp->mb[8] = sizeof(struct link_statistics) / 4;
- mcp->mb[9] = vha->vp_idx;
- mcp->mb[10] = options;
- mcp->out_mb = MBX_10|MBX_9|MBX_8|MBX_7|MBX_6|MBX_3|MBX_2|MBX_0;
- mcp->in_mb = MBX_2|MBX_1|MBX_0;
- mcp->tov = MBX_TOV_SECONDS;
- mcp->flags = IOCTL_CMD;
- rval = qla2x00_mailbox_command(vha, mcp);
+ memset(&mc, 0, sizeof(mc));
+ mc.mb[0] = MBC_GET_LINK_PRIV_STATS;
+ mc.mb[2] = MSW(stats_dma);
+ mc.mb[3] = LSW(stats_dma);
+ mc.mb[6] = MSW(MSD(stats_dma));
+ mc.mb[7] = LSW(MSD(stats_dma));
+ mc.mb[8] = sizeof(struct link_statistics) / 4;
+ mc.mb[9] = cpu_to_le16(vha->vp_idx);
+ mc.mb[10] = cpu_to_le16(options);
+
+ rval = qla24xx_send_mb_cmd(vha, &mc);
if (rval == QLA_SUCCESS) {
if (mcp->mb[0] != MBS_COMMAND_COMPLETE) {
@@ -3603,6 +3623,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
scsi_qla_host_t *vp = NULL;
unsigned long flags;
int found;
+ port_id_t id;
ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10b6,
"Entered %s.\n", __func__);
@@ -3610,28 +3631,27 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
if (rptid_entry->entry_status != 0)
return;
+ id.b.domain = rptid_entry->port_id[2];
+ id.b.area = rptid_entry->port_id[1];
+ id.b.al_pa = rptid_entry->port_id[0];
+ id.b.rsvd_1 = 0;
+
if (rptid_entry->format == 0) {
/* loop */
- ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10b7,
+ ql_dbg(ql_dbg_async, vha, 0x10b7,
"Format 0 : Number of VPs setup %d, number of "
"VPs acquired %d.\n", rptid_entry->vp_setup,
rptid_entry->vp_acquired);
- ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10b8,
+ ql_dbg(ql_dbg_async, vha, 0x10b8,
"Primary port id %02x%02x%02x.\n",
rptid_entry->port_id[2], rptid_entry->port_id[1],
rptid_entry->port_id[0]);
- vha->d_id.b.domain = rptid_entry->port_id[2];
- vha->d_id.b.area = rptid_entry->port_id[1];
- vha->d_id.b.al_pa = rptid_entry->port_id[0];
-
- spin_lock_irqsave(&ha->vport_slock, flags);
- qlt_update_vp_map(vha, SET_AL_PA);
- spin_unlock_irqrestore(&ha->vport_slock, flags);
+ qlt_update_host_map(vha, id);
} else if (rptid_entry->format == 1) {
/* fabric */
- ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10b9,
+ ql_dbg(ql_dbg_async, vha, 0x10b9,
"Format 1: VP[%d] enabled - status %d - with "
"port id %02x%02x%02x.\n", rptid_entry->vp_idx,
rptid_entry->vp_status,
@@ -3653,12 +3673,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
WWN_SIZE);
}
- vha->d_id.b.domain = rptid_entry->port_id[2];
- vha->d_id.b.area = rptid_entry->port_id[1];
- vha->d_id.b.al_pa = rptid_entry->port_id[0];
- spin_lock_irqsave(&ha->vport_slock, flags);
- qlt_update_vp_map(vha, SET_AL_PA);
- spin_unlock_irqrestore(&ha->vport_slock, flags);
+ qlt_update_host_map(vha, id);
}
fc_host_port_name(vha->host) =
@@ -3694,12 +3709,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
if (!found)
return;
- vp->d_id.b.domain = rptid_entry->port_id[2];
- vp->d_id.b.area = rptid_entry->port_id[1];
- vp->d_id.b.al_pa = rptid_entry->port_id[0];
- spin_lock_irqsave(&ha->vport_slock, flags);
- qlt_update_vp_map(vp, SET_AL_PA);
- spin_unlock_irqrestore(&ha->vport_slock, flags);
+ qlt_update_host_map(vp, id);
/*
* Cannot configure here as we are still sitting on the
@@ -5827,3 +5837,225 @@ qla26xx_dport_diagnostics(scsi_qla_host_t *vha,
return rval;
}
+
+static void qla2x00_async_mb_sp_done(void *s, int res)
+{
+ struct srb *sp = s;
+
+ sp->u.iocb_cmd.u.mbx.rc = res;
+
+ complete(&sp->u.iocb_cmd.u.mbx.comp);
+ /* don't free sp here. Let the caller do the free */
+}
+
+/*
+ * This mailbox uses the iocb interface to send MB command.
+ * This allows non-critial (non chip setup) command to go
+ * out in parrallel.
+ */
+int qla24xx_send_mb_cmd(struct scsi_qla_host *vha, mbx_cmd_t *mcp)
+{
+ int rval = QLA_FUNCTION_FAILED;
+ srb_t *sp;
+ struct srb_iocb *c;
+
+ if (!vha->hw->flags.fw_started)
+ goto done;
+
+ sp = qla2x00_get_sp(vha, NULL, GFP_KERNEL);
+ if (!sp)
+ goto done;
+
+ sp->type = SRB_MB_IOCB;
+ sp->name = mb_to_str(mcp->mb[0]);
+
+ qla2x00_init_timer(sp, qla2x00_get_async_timeout(vha) + 2);
+
+ memcpy(sp->u.iocb_cmd.u.mbx.out_mb, mcp->mb, SIZEOF_IOCB_MB_REG);
+
+ c = &sp->u.iocb_cmd;
+ c->timeout = qla2x00_async_iocb_timeout;
+ init_completion(&c->u.mbx.comp);
+
+ sp->done = qla2x00_async_mb_sp_done;
+
+ rval = qla2x00_start_sp(sp);
+ if (rval != QLA_SUCCESS) {
+ ql_dbg(ql_dbg_mbx, vha, 0xffff,
+ "%s: %s Failed submission. %x.\n",
+ __func__, sp->name, rval);
+ goto done_free_sp;
+ }
+
+ ql_dbg(ql_dbg_mbx, vha, 0xffff, "MB:%s hndl %x submitted\n",
+ sp->name, sp->handle);
+
+ wait_for_completion(&c->u.mbx.comp);
+ memcpy(mcp->mb, sp->u.iocb_cmd.u.mbx.in_mb, SIZEOF_IOCB_MB_REG);
+
+ rval = c->u.mbx.rc;
+ switch (rval) {
+ case QLA_FUNCTION_TIMEOUT:
+ ql_dbg(ql_dbg_mbx, vha, 0xffff, "%s: %s Timeout. %x.\n",
+ __func__, sp->name, rval);
+ break;
+ case QLA_SUCCESS:
+ ql_dbg(ql_dbg_mbx, vha, 0xffff, "%s: %s done.\n",
+ __func__, sp->name);
+ sp->free(sp);
+ break;
+ default:
+ ql_dbg(ql_dbg_mbx, vha, 0xffff, "%s: %s Failed. %x.\n",
+ __func__, sp->name, rval);
+ sp->free(sp);
+ break;
+ }
+
+ return rval;
+
+done_free_sp:
+ sp->free(sp);
+done:
+ return rval;
+}
+
+/*
+ * qla24xx_gpdb_wait
+ * NOTE: Do not call this routine from DPC thread
+ */
+int qla24xx_gpdb_wait(struct scsi_qla_host *vha, fc_port_t *fcport, u8 opt)
+{
+ int rval = QLA_FUNCTION_FAILED;
+ dma_addr_t pd_dma;
+ struct port_database_24xx *pd;
+ struct qla_hw_data *ha = vha->hw;
+ mbx_cmd_t mc;
+
+ if (!vha->hw->flags.fw_started)
+ goto done;
+
+ pd = dma_pool_alloc(ha->s_dma_pool, GFP_KERNEL, &pd_dma);
+ if (pd == NULL) {
+ ql_log(ql_log_warn, vha, 0xffff,
+ "Failed to allocate port database structure.\n");
+ goto done_free_sp;
+ }
+ memset(pd, 0, max(PORT_DATABASE_SIZE, PORT_DATABASE_24XX_SIZE));
+
+ memset(&mc, 0, sizeof(mc));
+ mc.mb[0] = MBC_GET_PORT_DATABASE;
+ mc.mb[1] = cpu_to_le16(fcport->loop_id);
+ mc.mb[2] = MSW(pd_dma);
+ mc.mb[3] = LSW(pd_dma);
+ mc.mb[6] = MSW(MSD(pd_dma));
+ mc.mb[7] = LSW(MSD(pd_dma));
+ mc.mb[9] = cpu_to_le16(vha->vp_idx);
+ mc.mb[10] = cpu_to_le16((uint16_t)opt);
+
+ rval = qla24xx_send_mb_cmd(vha, &mc);
+ if (rval != QLA_SUCCESS) {
+ ql_dbg(ql_dbg_mbx, vha, 0xffff,
+ "%s: %8phC fail\n", __func__, fcport->port_name);
+ goto done_free_sp;
+ }
+
+ rval = __qla24xx_parse_gpdb(vha, fcport, pd);
+
+ ql_dbg(ql_dbg_mbx, vha, 0xffff, "%s: %8phC done\n",
+ __func__, fcport->port_name);
+
+done_free_sp:
+ if (pd)
+ dma_pool_free(ha->s_dma_pool, pd, pd_dma);
+done:
+ return rval;
+}
+
+int __qla24xx_parse_gpdb(struct scsi_qla_host *vha, fc_port_t *fcport,
+ struct port_database_24xx *pd)
+{
+ int rval = QLA_SUCCESS;
+ uint64_t zero = 0;
+
+ /* Check for logged in state. */
+ if (pd->current_login_state != PDS_PRLI_COMPLETE &&
+ pd->last_login_state != PDS_PRLI_COMPLETE) {
+ ql_dbg(ql_dbg_mbx, vha, 0xffff,
+ "Unable to verify login-state (%x/%x) for "
+ "loop_id %x.\n", pd->current_login_state,
+ pd->last_login_state, fcport->loop_id);
+ rval = QLA_FUNCTION_FAILED;
+ goto gpd_error_out;
+ }
+
+ if (fcport->loop_id == FC_NO_LOOP_ID ||
+ (memcmp(fcport->port_name, (uint8_t *)&zero, 8) &&
+ memcmp(fcport->port_name, pd->port_name, 8))) {
+ /* We lost the device mid way. */
+ rval = QLA_NOT_LOGGED_IN;
+ goto gpd_error_out;
+ }
+
+ /* Names are little-endian. */
+ memcpy(fcport->node_name, pd->node_name, WWN_SIZE);
+ memcpy(fcport->port_name, pd->port_name, WWN_SIZE);
+
+ /* Get port_id of device. */
+ fcport->d_id.b.domain = pd->port_id[0];
+ fcport->d_id.b.area = pd->port_id[1];
+ fcport->d_id.b.al_pa = pd->port_id[2];
+ fcport->d_id.b.rsvd_1 = 0;
+
+ /* If not target must be initiator or unknown type. */
+ if ((pd->prli_svc_param_word_3[0] & BIT_4) == 0)
+ fcport->port_type = FCT_INITIATOR;
+ else
+ fcport->port_type = FCT_TARGET;
+
+ /* Passback COS information. */
+ fcport->supported_classes = (pd->flags & PDF_CLASS_2) ?
+ FC_COS_CLASS2 : FC_COS_CLASS3;
+
+ if (pd->prli_svc_param_word_3[0] & BIT_7) {
+ fcport->flags |= FCF_CONF_COMP_SUPPORTED;
+ fcport->conf_compl_supported = 1;
+ }
+
+gpd_error_out:
+ return rval;
+}
+
+/*
+ * qla24xx_gidlist__wait
+ * NOTE: don't call this routine from DPC thread.
+ */
+int qla24xx_gidlist_wait(struct scsi_qla_host *vha,
+ void *id_list, dma_addr_t id_list_dma, uint16_t *entries)
+{
+ int rval = QLA_FUNCTION_FAILED;
+ mbx_cmd_t mc;
+
+ if (!vha->hw->flags.fw_started)
+ goto done;
+
+ memset(&mc, 0, sizeof(mc));
+ mc.mb[0] = MBC_GET_ID_LIST;
+ mc.mb[2] = MSW(id_list_dma);
+ mc.mb[3] = LSW(id_list_dma);
+ mc.mb[6] = MSW(MSD(id_list_dma));
+ mc.mb[7] = LSW(MSD(id_list_dma));
+ mc.mb[8] = 0;
+ mc.mb[9] = cpu_to_le16(vha->vp_idx);
+
+ rval = qla24xx_send_mb_cmd(vha, &mc);
+ if (rval != QLA_SUCCESS) {
+ ql_dbg(ql_dbg_mbx, vha, 0xffff,
+ "%s: fail\n", __func__);
+ } else {
+ *entries = mc.mb[1];
+ ql_dbg(ql_dbg_mbx, vha, 0xffff,
+ "%s: done\n", __func__);
+ }
+done:
+ return rval;
+}
diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c
index c6d6f0d..09a490c 100644
--- a/drivers/scsi/qla2xxx/qla_mid.c
+++ b/drivers/scsi/qla2xxx/qla_mid.c
@@ -74,13 +74,14 @@ qla24xx_deallocate_vp_id(scsi_qla_host_t *vha)
* ensures no active vp_list traversal while the vport is removed
* from the queue)
*/
+ wait_event_timeout(vha->vref_waitq, atomic_read(&vha->vref_count),
+ 10*HZ);
+
spin_lock_irqsave(&ha->vport_slock, flags);
- while (atomic_read(&vha->vref_count)) {
- spin_unlock_irqrestore(&ha->vport_slock, flags);
-
- msleep(500);
-
- spin_lock_irqsave(&ha->vport_slock, flags);
+ if (atomic_read(&vha->vref_count)) {
+ ql_dbg(ql_dbg_vport, vha, 0xfffa,
+ "vha->vref_count=%u timeout\n", vha->vref_count.counter);
+ vha->vref_count = (atomic_t)ATOMIC_INIT(0);
}
list_del(&vha->list);
qlt_update_vp_map(vha, RESET_VP_IDX);
@@ -269,6 +270,7 @@ qla2x00_alert_all_vps(struct rsp_que *rsp, uint16_t *mb)
spin_lock_irqsave(&ha->vport_slock, flags);
atomic_dec(&vha->vref_count);
+ wake_up(&vha->vref_waitq);
}
i++;
}
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 1fed235..3e70117 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1651,7 +1651,8 @@ qla2x00_abort_all_cmds(scsi_qla_host_t *vha, int res)
/* Don't abort commands in adapter during EEH
* recovery as it's not accessible/responding.
*/
- if (GET_CMD_SP(sp) && !ha->flags.eeh_busy) {
+ if (GET_CMD_SP(sp) && !ha->flags.eeh_busy &&
+ (sp->type == SRB_SCSI_CMD)) {
/* Get a reference to the sp and drop the lock.
* The reference ensures this sp->done() call
* - and not the call in qla2xxx_eh_abort() -
@@ -2560,6 +2561,20 @@ qla2xxx_scan_finished(struct Scsi_Host *shost, unsigned long time)
return atomic_read(&vha->loop_state) == LOOP_READY;
}
+static void qla2x00_iocb_work_fn(struct work_struct *work)
+{
+ struct scsi_qla_host *vha = container_of(work,
+ struct scsi_qla_host, iocb_work);
+ int cnt = 0;
+
+ while (!list_empty(&vha->work_list)) {
+ qla2x00_do_work(vha);
+ cnt++;
+ if (cnt > 10)
+ break;
+ }
+}
+
/*
* PCI driver interface
*/
@@ -3078,6 +3093,7 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
*/
qla2xxx_wake_dpc(base_vha);
+ INIT_WORK(&base_vha->iocb_work, qla2x00_iocb_work_fn);
INIT_WORK(&ha->board_disable, qla2x00_disable_board_on_pci_error);
if (IS_QLA8031(ha) || IS_MCTP_CAPABLE(ha)) {
@@ -3469,6 +3485,7 @@ qla2x00_remove_one(struct pci_dev *pdev)
qla2x00_free_sysfs_attr(base_vha, true);
fc_remove_host(base_vha->host);
+ qlt_remove_target_resources(ha);
scsi_remove_host(base_vha->host);
@@ -4268,6 +4285,7 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht,
spin_lock_init(&vha->work_lock);
spin_lock_init(&vha->cmd_list_lock);
init_waitqueue_head(&vha->fcport_waitQ);
+ init_waitqueue_head(&vha->vref_waitq);
vha->gnl.size = sizeof(struct get_name_list_extended) *
(ha->max_loop_id + 1);
@@ -4319,7 +4337,11 @@ qla2x00_post_work(struct scsi_qla_host *vha, struct qla_work_evt *e)
spin_lock_irqsave(&vha->work_lock, flags);
list_add_tail(&e->list, &vha->work_list);
spin_unlock_irqrestore(&vha->work_lock, flags);
- qla2xxx_wake_dpc(vha);
+
+ if (QLA_EARLY_LINKUP(vha->hw))
+ schedule_work(&vha->iocb_work);
+ else
+ qla2xxx_wake_dpc(vha);
return QLA_SUCCESS;
}
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 45f5077..0e03ca2 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -130,6 +130,9 @@ static void qlt_send_term_imm_notif(struct scsi_qla_host *vha,
static struct fc_port *qlt_create_sess(struct scsi_qla_host *vha,
fc_port_t *fcport, bool local);
void qlt_unreg_sess(struct fc_port *sess);
+static void qlt_24xx_handle_abts(struct scsi_qla_host *,
+ struct abts_recv_from_24xx *);
+
/*
* Global Variables
*/
@@ -140,6 +143,20 @@ static struct workqueue_struct *qla_tgt_wq;
static DEFINE_MUTEX(qla_tgt_mutex);
static LIST_HEAD(qla_tgt_glist);
+static const char *prot_op_str(u32 prot_op)
+{
+ switch (prot_op) {
+ case TARGET_PROT_NORMAL: return "NORMAL";
+ case TARGET_PROT_DIN_INSERT: return "DIN_INSERT";
+ case TARGET_PROT_DOUT_INSERT: return "DOUT_INSERT";
+ case TARGET_PROT_DIN_STRIP: return "DIN_STRIP";
+ case TARGET_PROT_DOUT_STRIP: return "DOUT_STRIP";
+ case TARGET_PROT_DIN_PASS: return "DIN_PASS";
+ case TARGET_PROT_DOUT_PASS: return "DOUT_PASS";
+ default: return "UNKNOWN";
+ }
+}
+
/* This API intentionally takes dest as a parameter, rather than returning
* int value to avoid caller forgetting to issue wmb() after the store */
void qlt_do_generation_tick(struct scsi_qla_host *vha, int *dest)
@@ -170,21 +187,23 @@ static inline
struct scsi_qla_host *qlt_find_host_by_d_id(struct scsi_qla_host *vha,
uint8_t *d_id)
{
- struct qla_hw_data *ha = vha->hw;
- uint8_t vp_idx;
+ struct scsi_qla_host *host;
+ uint32_t key = 0;
- if ((vha->d_id.b.area != d_id[1]) || (vha->d_id.b.domain != d_id[0]))
- return NULL;
-
- if (vha->d_id.b.al_pa == d_id[2])
+ if ((vha->d_id.b.area == d_id[1]) && (vha->d_id.b.domain == d_id[0]) &&
+ (vha->d_id.b.al_pa == d_id[2]))
return vha;
- BUG_ON(ha->tgt.tgt_vp_map == NULL);
- vp_idx = ha->tgt.tgt_vp_map[d_id[2]].idx;
- if (likely(test_bit(vp_idx, ha->vp_idx_map)))
- return ha->tgt.tgt_vp_map[vp_idx].vha;
+ key = (uint32_t)d_id[0] << 16;
+ key |= (uint32_t)d_id[1] << 8;
+ key |= (uint32_t)d_id[2];
- return NULL;
+ host = btree_lookup32(&vha->hw->tgt.host_map, key);
+ if (!host)
+ ql_dbg(ql_dbg_tgt_mgt, vha, 0xffff,
+ "Unable to find host %06x\n", key);
+
+ return host;
}
static inline
@@ -389,6 +408,8 @@ static bool qlt_24xx_atio_pkt_all_vps(struct scsi_qla_host *vha,
(struct abts_recv_from_24xx *)atio;
struct scsi_qla_host *host = qlt_find_host_by_vp_idx(vha,
entry->vp_index);
+ unsigned long flags;
+
if (unlikely(!host)) {
ql_dbg(ql_dbg_tgt, vha, 0xffff,
"qla_target(%d): Response pkt (ABTS_RECV_24XX) "
@@ -396,9 +417,12 @@ static bool qlt_24xx_atio_pkt_all_vps(struct scsi_qla_host *vha,
vha->vp_idx, entry->vp_index);
break;
}
- qlt_response_pkt(host, (response_t *)atio);
+ if (!ha_locked)
+ spin_lock_irqsave(&host->hw->hardware_lock, flags);
+ qlt_24xx_handle_abts(host, (struct abts_recv_from_24xx *)atio);
+ if (!ha_locked)
+ spin_unlock_irqrestore(&host->hw->hardware_lock, flags);
break;
-
}
/* case PUREX_IOCB_TYPE: ql2xmvasynctoatio */
@@ -554,6 +578,7 @@ void qla2x00_async_nack_sp_done(void *s, int res)
sp->fcport->login_gen++;
sp->fcport->fw_login_state = DSC_LS_PLOGI_COMP;
sp->fcport->logout_on_delete = 1;
+ sp->fcport->plogi_nack_done_deadline = jiffies + HZ;
break;
case SRB_NACK_PRLI:
@@ -613,6 +638,7 @@ int qla24xx_async_notify_ack(scsi_qla_host_t *vha, fc_port_t *fcport,
break;
case SRB_NACK_PRLI:
fcport->fw_login_state = DSC_LS_PRLI_PEND;
+ fcport->deleted = 0;
c = "PRLI";
break;
case SRB_NACK_LOGO:
@@ -1215,7 +1241,7 @@ static int qla24xx_get_loop_id(struct scsi_qla_host *vha, const uint8_t *s_id,
}
/* Get list of logged in devices */
- rc = qla2x00_get_id_list(vha, gid_list, gid_list_dma, &entries);
+ rc = qla24xx_gidlist_wait(vha, gid_list, gid_list_dma, &entries);
if (rc != QLA_SUCCESS) {
ql_dbg(ql_dbg_tgt_mgt, vha, 0xf045,
"qla_target(%d): get_id_list() failed: %x\n",
@@ -1551,6 +1577,9 @@ static void qlt_send_notify_ack(struct scsi_qla_host *vha,
request_t *pkt;
struct nack_to_isp *nack;
+ if (!ha->flags.fw_started)
+ return;
+
ql_dbg(ql_dbg_tgt, vha, 0xe004, "Sending NOTIFY_ACK (ha=%p)\n", ha);
/* Send marker if required */
@@ -2013,6 +2042,70 @@ void qlt_free_mcmd(struct qla_tgt_mgmt_cmd *mcmd)
}
EXPORT_SYMBOL(qlt_free_mcmd);
+/*
+ * ha->hardware_lock supposed to be held on entry. Might drop it, then
+ * reacquire
+ */
+void qlt_send_resp_ctio(scsi_qla_host_t *vha, struct qla_tgt_cmd *cmd,
+ uint8_t scsi_status, uint8_t sense_key, uint8_t asc, uint8_t ascq)
+{
+ struct atio_from_isp *atio = &cmd->atio;
+ struct ctio7_to_24xx *ctio;
+ uint16_t temp;
+
+ ql_dbg(ql_dbg_tgt_dif, vha, 0x3066,
+ "Sending response CTIO7 (vha=%p, atio=%p, scsi_status=%02x, "
+ "sense_key=%02x, asc=%02x, ascq=%02x",
+ vha, atio, scsi_status, sense_key, asc, ascq);
+
+ ctio = (struct ctio7_to_24xx *)qla2x00_alloc_iocbs(vha, NULL);
+ if (!ctio) {
+ ql_dbg(ql_dbg_async, vha, 0x3067,
+ "qla2x00t(%ld): %s failed: unable to allocate request packet",
+ vha->host_no, __func__);
+ goto out;
+ }
+
+ ctio->entry_type = CTIO_TYPE7;
+ ctio->entry_count = 1;
+ ctio->handle = QLA_TGT_SKIP_HANDLE;
+ ctio->nport_handle = cmd->sess->loop_id;
+ ctio->timeout = cpu_to_le16(QLA_TGT_TIMEOUT);
+ ctio->vp_index = vha->vp_idx;
+ ctio->initiator_id[0] = atio->u.isp24.fcp_hdr.s_id[2];
+ ctio->initiator_id[1] = atio->u.isp24.fcp_hdr.s_id[1];
+ ctio->initiator_id[2] = atio->u.isp24.fcp_hdr.s_id[0];
+ ctio->exchange_addr = atio->u.isp24.exchange_addr;
+ ctio->u.status1.flags = (atio->u.isp24.attr << 9) |
+ cpu_to_le16(CTIO7_FLAGS_STATUS_MODE_1 | CTIO7_FLAGS_SEND_STATUS);
+ temp = be16_to_cpu(atio->u.isp24.fcp_hdr.ox_id);
+ ctio->u.status1.ox_id = cpu_to_le16(temp);
+ ctio->u.status1.scsi_status =
+ cpu_to_le16(SS_RESPONSE_INFO_LEN_VALID | scsi_status);
+ ctio->u.status1.response_len = cpu_to_le16(18);
+ ctio->u.status1.residual = cpu_to_le32(get_datalen_for_atio(atio));
+
+ if (ctio->u.status1.residual != 0)
+ ctio->u.status1.scsi_status |=
+ cpu_to_le16(SS_RESIDUAL_UNDER);
+
+ /* Response code and sense key */
+ put_unaligned_le32(((0x70 << 24) | (sense_key << 8)),
+ (&ctio->u.status1.sense_data)[0]);
+ /* Additional sense length */
+ put_unaligned_le32(0x0a, (&ctio->u.status1.sense_data)[1]);
+ /* ASC and ASCQ */
+ put_unaligned_le32(((asc << 24) | (ascq << 16)),
+ (&ctio->u.status1.sense_data)[3]);
+
+ /* Memory Barrier */
+ wmb();
+
+ qla2x00_start_iocbs(vha, vha->req);
+out:
+ return;
+}
+
/* callback from target fabric module code */
void qlt_xmit_tm_rsp(struct qla_tgt_mgmt_cmd *mcmd)
{
@@ -2261,7 +2354,7 @@ static int qlt_24xx_build_ctio_pkt(struct qla_tgt_prm *prm,
*/
return -EAGAIN;
} else
- ha->tgt.cmds[h-1] = prm->cmd;
+ ha->tgt.cmds[h - 1] = prm->cmd;
pkt->handle = h | CTIO_COMPLETION_HANDLE_MARK;
pkt->nport_handle = prm->cmd->loop_id;
@@ -2391,6 +2484,50 @@ static inline int qlt_has_data(struct qla_tgt_cmd *cmd)
return cmd->bufflen > 0;
}
+static void qlt_print_dif_err(struct qla_tgt_prm *prm)
+{
+ struct qla_tgt_cmd *cmd;
+ struct scsi_qla_host *vha;
+
+ /* asc 0x10=dif error */
+ if (prm->sense_buffer && (prm->sense_buffer[12] == 0x10)) {
+ cmd = prm->cmd;
+ vha = cmd->vha;
+ /* ASCQ */
+ switch (prm->sense_buffer[13]) {
+ case 1:
+ ql_dbg(ql_dbg_tgt_dif, vha, 0xffff,
+ "BE detected Guard TAG ERR: lba[0x%llx|%lld] len[0x%x] "
+ "se_cmd=%p tag[%x]",
+ cmd->lba, cmd->lba, cmd->num_blks, &cmd->se_cmd,
+ cmd->atio.u.isp24.exchange_addr);
+ break;
+ case 2:
+ ql_dbg(ql_dbg_tgt_dif, vha, 0xffff,
+ "BE detected APP TAG ERR: lba[0x%llx|%lld] len[0x%x] "
+ "se_cmd=%p tag[%x]",
+ cmd->lba, cmd->lba, cmd->num_blks, &cmd->se_cmd,
+ cmd->atio.u.isp24.exchange_addr);
+ break;
+ case 3:
+ ql_dbg(ql_dbg_tgt_dif, vha, 0xffff,
+ "BE detected REF TAG ERR: lba[0x%llx|%lld] len[0x%x] "
+ "se_cmd=%p tag[%x]",
+ cmd->lba, cmd->lba, cmd->num_blks, &cmd->se_cmd,
+ cmd->atio.u.isp24.exchange_addr);
+ break;
+ default:
+ ql_dbg(ql_dbg_tgt_dif, vha, 0xffff,
+ "BE detected Dif ERR: lba[%llx|%lld] len[%x] "
+ "se_cmd=%p tag[%x]",
+ cmd->lba, cmd->lba, cmd->num_blks, &cmd->se_cmd,
+ cmd->atio.u.isp24.exchange_addr);
+ break;
+ }
+ ql_dump_buffer(ql_dbg_tgt_dif, vha, 0xffff, cmd->cdb, 16);
+ }
+}
+
/*
* Called without ha->hardware_lock held
*/
@@ -2512,18 +2649,9 @@ static void qlt_24xx_init_ctio_to_isp(struct ctio7_to_24xx *ctio,
for (i = 0; i < prm->sense_buffer_len/4; i++)
((uint32_t *)ctio->u.status1.sense_data)[i] =
cpu_to_be32(((uint32_t *)prm->sense_buffer)[i]);
-#if 0
- if (unlikely((prm->sense_buffer_len % 4) != 0)) {
- static int q;
- if (q < 10) {
- ql_dbg(ql_dbg_tgt, vha, 0xe04f,
- "qla_target(%d): %d bytes of sense "
- "lost", prm->tgt->ha->vp_idx,
- prm->sense_buffer_len % 4);
- q++;
- }
- }
-#endif
+
+ qlt_print_dif_err(prm);
+
} else {
ctio->u.status1.flags &=
~cpu_to_le16(CTIO7_FLAGS_STATUS_MODE_0);
@@ -2537,19 +2665,9 @@ static void qlt_24xx_init_ctio_to_isp(struct ctio7_to_24xx *ctio,
/* Sense with len > 24, is it possible ??? */
}
-
-
-/* diff */
static inline int
qlt_hba_err_chk_enabled(struct se_cmd *se_cmd)
{
- /*
- * Uncomment when corresponding SCSI changes are done.
- *
- if (!sp->cmd->prot_chk)
- return 0;
- *
- */
switch (se_cmd->prot_op) {
case TARGET_PROT_DOUT_INSERT:
case TARGET_PROT_DIN_STRIP:
@@ -2570,16 +2688,38 @@ qlt_hba_err_chk_enabled(struct se_cmd *se_cmd)
return 0;
}
-/*
- * qla24xx_set_t10dif_tags_from_cmd - Extract Ref and App tags from SCSI command
- *
- */
-static inline void
-qlt_set_t10dif_tags(struct se_cmd *se_cmd, struct crc_context *ctx)
+static inline int
+qla_tgt_ref_mask_check(struct se_cmd *se_cmd)
{
- uint32_t lba = 0xffffffff & se_cmd->t_task_lba;
+ switch (se_cmd->prot_op) {
+ case TARGET_PROT_DIN_INSERT:
+ case TARGET_PROT_DOUT_INSERT:
+ case TARGET_PROT_DIN_STRIP:
+ case TARGET_PROT_DOUT_STRIP:
+ case TARGET_PROT_DIN_PASS:
+ case TARGET_PROT_DOUT_PASS:
+ return 1;
+ default:
+ return 0;
+ }
+ return 0;
+}
- /* wait til Mode Sense/Select cmd, modepage Ah, subpage 2
+/*
+ * qla_tgt_set_dif_tags - Extract Ref and App tags from SCSI command
+ */
+static void
+qla_tgt_set_dif_tags(struct qla_tgt_cmd *cmd, struct crc_context *ctx,
+ uint16_t *pfw_prot_opts)
+{
+ struct se_cmd *se_cmd = &cmd->se_cmd;
+ uint32_t lba = 0xffffffff & se_cmd->t_task_lba;
+ scsi_qla_host_t *vha = cmd->tgt->vha;
+ struct qla_hw_data *ha = vha->hw;
+ uint32_t t32 = 0;
+
+ /*
+ * wait till Mode Sense/Select cmd, modepage Ah, subpage 2
* have been immplemented by TCM, before AppTag is avail.
* Look for modesense_handlers[]
*/
@@ -2587,65 +2727,73 @@ qlt_set_t10dif_tags(struct se_cmd *se_cmd, struct crc_context *ctx)
ctx->app_tag_mask[0] = 0x0;
ctx->app_tag_mask[1] = 0x0;
+ if (IS_PI_UNINIT_CAPABLE(ha)) {
+ if ((se_cmd->prot_type == TARGET_DIF_TYPE1_PROT) ||
+ (se_cmd->prot_type == TARGET_DIF_TYPE2_PROT))
+ *pfw_prot_opts |= PO_DIS_VALD_APP_ESC;
+ else if (se_cmd->prot_type == TARGET_DIF_TYPE3_PROT)
+ *pfw_prot_opts |= PO_DIS_VALD_APP_REF_ESC;
+ }
+
+ t32 = ha->tgt.tgt_ops->get_dif_tags(cmd, pfw_prot_opts);
+
switch (se_cmd->prot_type) {
case TARGET_DIF_TYPE0_PROT:
/*
- * No check for ql2xenablehba_err_chk, as it would be an
- * I/O error if hba tag generation is not done.
+ * No check for ql2xenablehba_err_chk, as it
+ * would be an I/O error if hba tag generation
+ * is not done.
*/
ctx->ref_tag = cpu_to_le32(lba);
-
- if (!qlt_hba_err_chk_enabled(se_cmd))
- break;
-
/* enable ALL bytes of the ref tag */
ctx->ref_tag_mask[0] = 0xff;
ctx->ref_tag_mask[1] = 0xff;
ctx->ref_tag_mask[2] = 0xff;
ctx->ref_tag_mask[3] = 0xff;
break;
- /*
- * For TYpe 1 protection: 16 bit GUARD tag, 32 bit REF tag, and
- * 16 bit app tag.
- */
case TARGET_DIF_TYPE1_PROT:
- ctx->ref_tag = cpu_to_le32(lba);
-
- if (!qlt_hba_err_chk_enabled(se_cmd))
- break;
-
- /* enable ALL bytes of the ref tag */
- ctx->ref_tag_mask[0] = 0xff;
- ctx->ref_tag_mask[1] = 0xff;
- ctx->ref_tag_mask[2] = 0xff;
- ctx->ref_tag_mask[3] = 0xff;
- break;
- /*
- * For TYPE 2 protection: 16 bit GUARD + 32 bit REF tag has to
- * match LBA in CDB + N
- */
+ /*
+ * For TYPE 1 protection: 16 bit GUARD tag, 32 bit
+ * REF tag, and 16 bit app tag.
+ */
+ ctx->ref_tag = cpu_to_le32(lba);
+ if (!qla_tgt_ref_mask_check(se_cmd) ||
+ !(ha->tgt.tgt_ops->chk_dif_tags(t32))) {
+ *pfw_prot_opts |= PO_DIS_REF_TAG_VALD;
+ break;
+ }
+ /* enable ALL bytes of the ref tag */
+ ctx->ref_tag_mask[0] = 0xff;
+ ctx->ref_tag_mask[1] = 0xff;
+ ctx->ref_tag_mask[2] = 0xff;
+ ctx->ref_tag_mask[3] = 0xff;
+ break;
case TARGET_DIF_TYPE2_PROT:
- ctx->ref_tag = cpu_to_le32(lba);
-
- if (!qlt_hba_err_chk_enabled(se_cmd))
- break;
-
- /* enable ALL bytes of the ref tag */
- ctx->ref_tag_mask[0] = 0xff;
- ctx->ref_tag_mask[1] = 0xff;
- ctx->ref_tag_mask[2] = 0xff;
- ctx->ref_tag_mask[3] = 0xff;
- break;
-
- /* For Type 3 protection: 16 bit GUARD only */
+ /*
+ * For TYPE 2 protection: 16 bit GUARD + 32 bit REF
+ * tag has to match LBA in CDB + N
+ */
+ ctx->ref_tag = cpu_to_le32(lba);
+ if (!qla_tgt_ref_mask_check(se_cmd) ||
+ !(ha->tgt.tgt_ops->chk_dif_tags(t32))) {
+ *pfw_prot_opts |= PO_DIS_REF_TAG_VALD;
+ break;
+ }
+ /* enable ALL bytes of the ref tag */
+ ctx->ref_tag_mask[0] = 0xff;
+ ctx->ref_tag_mask[1] = 0xff;
+ ctx->ref_tag_mask[2] = 0xff;
+ ctx->ref_tag_mask[3] = 0xff;
+ break;
case TARGET_DIF_TYPE3_PROT:
- ctx->ref_tag_mask[0] = ctx->ref_tag_mask[1] =
- ctx->ref_tag_mask[2] = ctx->ref_tag_mask[3] = 0x00;
- break;
+ /* For TYPE 3 protection: 16 bit GUARD only */
+ *pfw_prot_opts |= PO_DIS_REF_TAG_VALD;
+ ctx->ref_tag_mask[0] = ctx->ref_tag_mask[1] =
+ ctx->ref_tag_mask[2] = ctx->ref_tag_mask[3] = 0x00;
+ break;
}
}
-
static inline int
qlt_build_ctio_crc2_pkt(struct qla_tgt_prm *prm, scsi_qla_host_t *vha)
{
@@ -2664,6 +2812,7 @@ qlt_build_ctio_crc2_pkt(struct qla_tgt_prm *prm, scsi_qla_host_t *vha)
struct se_cmd *se_cmd = &cmd->se_cmd;
uint32_t h;
struct atio_from_isp *atio = &prm->cmd->atio;
+ struct qla_tc_param tc;
uint16_t t16;
ha = vha->hw;
@@ -2689,16 +2838,15 @@ qlt_build_ctio_crc2_pkt(struct qla_tgt_prm *prm, scsi_qla_host_t *vha)
case TARGET_PROT_DIN_INSERT:
case TARGET_PROT_DOUT_STRIP:
transfer_length = data_bytes;
- data_bytes += dif_bytes;
+ if (cmd->prot_sg_cnt)
+ data_bytes += dif_bytes;
break;
-
case TARGET_PROT_DIN_STRIP:
case TARGET_PROT_DOUT_INSERT:
case TARGET_PROT_DIN_PASS:
case TARGET_PROT_DOUT_PASS:
transfer_length = data_bytes + dif_bytes;
break;
-
default:
BUG();
break;
@@ -2734,7 +2882,6 @@ qlt_build_ctio_crc2_pkt(struct qla_tgt_prm *prm, scsi_qla_host_t *vha)
break;
}
-
/* ---- PKT ---- */
/* Update entry type to indicate Command Type CRC_2 IOCB */
pkt->entry_type = CTIO_CRC2;
@@ -2752,9 +2899,8 @@ qlt_build_ctio_crc2_pkt(struct qla_tgt_prm *prm, scsi_qla_host_t *vha)
} else
ha->tgt.cmds[h-1] = prm->cmd;
-
pkt->handle = h | CTIO_COMPLETION_HANDLE_MARK;
- pkt->nport_handle = prm->cmd->loop_id;
+ pkt->nport_handle = cpu_to_le16(prm->cmd->loop_id);
pkt->timeout = cpu_to_le16(QLA_TGT_TIMEOUT);
pkt->initiator_id[0] = atio->u.isp24.fcp_hdr.s_id[2];
pkt->initiator_id[1] = atio->u.isp24.fcp_hdr.s_id[1];
@@ -2775,12 +2921,10 @@ qlt_build_ctio_crc2_pkt(struct qla_tgt_prm *prm, scsi_qla_host_t *vha)
else if (cmd->dma_data_direction == DMA_FROM_DEVICE)
pkt->flags = cpu_to_le16(CTIO7_FLAGS_DATA_OUT);
-
pkt->dseg_count = prm->tot_dsds;
/* Fibre channel byte count */
pkt->transfer_length = cpu_to_le32(transfer_length);
-
/* ----- CRC context -------- */
/* Allocate CRC context from global pool */
@@ -2800,13 +2944,12 @@ qlt_build_ctio_crc2_pkt(struct qla_tgt_prm *prm, scsi_qla_host_t *vha)
/* Set handle */
crc_ctx_pkt->handle = pkt->handle;
- qlt_set_t10dif_tags(se_cmd, crc_ctx_pkt);
+ qla_tgt_set_dif_tags(cmd, crc_ctx_pkt, &fw_prot_opts);
pkt->crc_context_address[0] = cpu_to_le32(LSD(crc_ctx_dma));
pkt->crc_context_address[1] = cpu_to_le32(MSD(crc_ctx_dma));
pkt->crc_context_len = CRC_CONTEXT_LEN_FW;
-
if (!bundling) {
cur_dsd = (uint32_t *) &crc_ctx_pkt->u.nobundling.data_address;
} else {
@@ -2827,16 +2970,24 @@ qlt_build_ctio_crc2_pkt(struct qla_tgt_prm *prm, scsi_qla_host_t *vha)
crc_ctx_pkt->byte_count = cpu_to_le32(data_bytes);
crc_ctx_pkt->guard_seed = cpu_to_le16(0);
+ memset((uint8_t *)&tc, 0 , sizeof(tc));
+ tc.vha = vha;
+ tc.blk_sz = cmd->blk_sz;
+ tc.bufflen = cmd->bufflen;
+ tc.sg = cmd->sg;
+ tc.prot_sg = cmd->prot_sg;
+ tc.ctx = crc_ctx_pkt;
+ tc.ctx_dsd_alloced = &cmd->ctx_dsd_alloced;
/* Walks data segments */
pkt->flags |= cpu_to_le16(CTIO7_FLAGS_DSD_PTR);
if (!bundling && prm->prot_seg_cnt) {
if (qla24xx_walk_and_build_sglist_no_difb(ha, NULL, cur_dsd,
- prm->tot_dsds, cmd))
+ prm->tot_dsds, &tc))
goto crc_queuing_error;
} else if (qla24xx_walk_and_build_sglist(ha, NULL, cur_dsd,
- (prm->tot_dsds - prm->prot_seg_cnt), cmd))
+ (prm->tot_dsds - prm->prot_seg_cnt), &tc))
goto crc_queuing_error;
if (bundling && prm->prot_seg_cnt) {
@@ -2845,18 +2996,18 @@ qlt_build_ctio_crc2_pkt(struct qla_tgt_prm *prm, scsi_qla_host_t *vha)
cur_dsd = (uint32_t *) &crc_ctx_pkt->u.bundling.dif_address;
if (qla24xx_walk_and_build_prot_sglist(ha, NULL, cur_dsd,
- prm->prot_seg_cnt, cmd))
+ prm->prot_seg_cnt, &tc))
goto crc_queuing_error;
}
return QLA_SUCCESS;
crc_queuing_error:
/* Cleanup will be performed by the caller */
+ vha->hw->tgt.cmds[h - 1] = NULL;
return QLA_FUNCTION_FAILED;
}
-
/*
* Callback to setup response of xmit_type of QLA_TGT_XMIT_DATA and *
* QLA_TGT_XMIT_STATUS for >= 24xx silicon
@@ -2906,7 +3057,7 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
else
vha->tgt_counters.core_qla_que_buf++;
- if (!vha->flags.online || cmd->reset_count != ha->chip_reset) {
+ if (!ha->flags.fw_started || cmd->reset_count != ha->chip_reset) {
/*
* Either the port is not online or this request was from
* previous life, just abort the processing.
@@ -3047,7 +3198,7 @@ int qlt_rdy_to_xfer(struct qla_tgt_cmd *cmd)
spin_lock_irqsave(&ha->hardware_lock, flags);
- if (!vha->flags.online || (cmd->reset_count != ha->chip_reset) ||
+ if (!ha->flags.fw_started || (cmd->reset_count != ha->chip_reset) ||
(cmd->sess && cmd->sess->deleted)) {
/*
* Either the port is not online or this request was from
@@ -3104,139 +3255,113 @@ EXPORT_SYMBOL(qlt_rdy_to_xfer);
/*
- * Checks the guard or meta-data for the type of error
- * detected by the HBA.
+ * it is assumed either hardware_lock or qpair lock is held.
*/
-static inline int
+static void
qlt_handle_dif_error(struct scsi_qla_host *vha, struct qla_tgt_cmd *cmd,
- struct ctio_crc_from_fw *sts)
+ struct ctio_crc_from_fw *sts)
{
uint8_t *ap = &sts->actual_dif[0];
uint8_t *ep = &sts->expected_dif[0];
- uint32_t e_ref_tag, a_ref_tag;
- uint16_t e_app_tag, a_app_tag;
- uint16_t e_guard, a_guard;
uint64_t lba = cmd->se_cmd.t_task_lba;
+ uint8_t scsi_status, sense_key, asc, ascq;
+ unsigned long flags;
- a_guard = be16_to_cpu(*(uint16_t *)(ap + 0));
- a_app_tag = be16_to_cpu(*(uint16_t *)(ap + 2));
- a_ref_tag = be32_to_cpu(*(uint32_t *)(ap + 4));
+ cmd->trc_flags |= TRC_DIF_ERR;
- e_guard = be16_to_cpu(*(uint16_t *)(ep + 0));
- e_app_tag = be16_to_cpu(*(uint16_t *)(ep + 2));
- e_ref_tag = be32_to_cpu(*(uint32_t *)(ep + 4));
+ cmd->a_guard = be16_to_cpu(*(uint16_t *)(ap + 0));
+ cmd->a_app_tag = be16_to_cpu(*(uint16_t *)(ap + 2));
+ cmd->a_ref_tag = be32_to_cpu(*(uint32_t *)(ap + 4));
- ql_dbg(ql_dbg_tgt, vha, 0xe075,
- "iocb(s) %p Returned STATUS.\n", sts);
+ cmd->e_guard = be16_to_cpu(*(uint16_t *)(ep + 0));
+ cmd->e_app_tag = be16_to_cpu(*(uint16_t *)(ep + 2));
+ cmd->e_ref_tag = be32_to_cpu(*(uint32_t *)(ep + 4));
- ql_dbg(ql_dbg_tgt, vha, 0xf075,
- "dif check TGT cdb 0x%x lba 0x%llx: [Actual|Expected] Ref Tag[0x%x|0x%x], App Tag [0x%x|0x%x], Guard [0x%x|0x%x]\n",
- cmd->atio.u.isp24.fcp_cmnd.cdb[0], lba,
- a_ref_tag, e_ref_tag, a_app_tag, e_app_tag, a_guard, e_guard);
+ ql_dbg(ql_dbg_tgt_dif, vha, 0xf075,
+ "%s: aborted %d state %d\n", __func__, cmd->aborted, cmd->state);
- /*
- * Ignore sector if:
- * For type 3: ref & app tag is all 'f's
- * For type 0,1,2: app tag is all 'f's
- */
- if ((a_app_tag == 0xffff) &&
- ((cmd->se_cmd.prot_type != TARGET_DIF_TYPE3_PROT) ||
- (a_ref_tag == 0xffffffff))) {
- uint32_t blocks_done;
+ scsi_status = sense_key = asc = ascq = 0;
- /* 2TB boundary case covered automatically with this */
- blocks_done = e_ref_tag - (uint32_t)lba + 1;
- cmd->se_cmd.bad_sector = e_ref_tag;
- cmd->se_cmd.pi_err = 0;
- ql_dbg(ql_dbg_tgt, vha, 0xf074,
- "need to return scsi good\n");
+ /* check appl tag */
+ if (cmd->e_app_tag != cmd->a_app_tag) {
+ ql_dbg(ql_dbg_tgt_dif, vha, 0xffff,
+ "App Tag ERR: cdb[%x] lba[%llx %llx] blks[%x] [Actual|Expected] "
+ "Ref[%x|%x], App[%x|%x], "
+ "Guard [%x|%x] cmd=%p ox_id[%04x]",
+ cmd->cdb[0], lba, (lba+cmd->num_blks), cmd->num_blks,
+ cmd->a_ref_tag, cmd->e_ref_tag,
+ cmd->a_app_tag, cmd->e_app_tag,
+ cmd->a_guard, cmd->e_guard,
+ cmd, cmd->atio.u.isp24.fcp_hdr.ox_id);
- /* Update protection tag */
- if (cmd->prot_sg_cnt) {
- uint32_t i, k = 0, num_ent;
- struct scatterlist *sg, *sgl;
-
-
- sgl = cmd->prot_sg;
-
- /* Patch the corresponding protection tags */
- for_each_sg(sgl, sg, cmd->prot_sg_cnt, i) {
- num_ent = sg_dma_len(sg) / 8;
- if (k + num_ent < blocks_done) {
- k += num_ent;
- continue;
- }
- k = blocks_done;
- break;
- }
-
- if (k != blocks_done) {
- ql_log(ql_log_warn, vha, 0xf076,
- "unexpected tag values tag:lba=%u:%llu)\n",
- e_ref_tag, (unsigned long long)lba);
- goto out;
- }
-
-#if 0
- struct sd_dif_tuple *spt;
- /* TODO:
- * This section came from initiator. Is it valid here?
- * should ulp be override with actual val???
- */
- spt = page_address(sg_page(sg)) + sg->offset;
- spt += j;
-
- spt->app_tag = 0xffff;
- if (cmd->se_cmd.prot_type == SCSI_PROT_DIF_TYPE3)
- spt->ref_tag = 0xffffffff;
-#endif
- }
-
- return 0;
- }
-
- /* check guard */
- if (e_guard != a_guard) {
- cmd->se_cmd.pi_err = TCM_LOGICAL_BLOCK_GUARD_CHECK_FAILED;
- cmd->se_cmd.bad_sector = cmd->se_cmd.t_task_lba;
-
- ql_log(ql_log_warn, vha, 0xe076,
- "Guard ERR: cdb 0x%x lba 0x%llx: [Actual|Expected] Ref Tag[0x%x|0x%x], App Tag [0x%x|0x%x], Guard [0x%x|0x%x] cmd=%p\n",
- cmd->atio.u.isp24.fcp_cmnd.cdb[0], lba,
- a_ref_tag, e_ref_tag, a_app_tag, e_app_tag,
- a_guard, e_guard, cmd);
- goto out;
+ cmd->dif_err_code = DIF_ERR_APP;
+ scsi_status = SAM_STAT_CHECK_CONDITION;
+ sense_key = ABORTED_COMMAND;
+ asc = 0x10;
+ ascq = 0x2;
}
/* check ref tag */
- if (e_ref_tag != a_ref_tag) {
- cmd->se_cmd.pi_err = TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED;
- cmd->se_cmd.bad_sector = e_ref_tag;
+ if (cmd->e_ref_tag != cmd->a_ref_tag) {
+ ql_dbg(ql_dbg_tgt_dif, vha, 0xffff,
+ "Ref Tag ERR: cdb[%x] lba[%llx %llx] blks[%x] [Actual|Expected] "
+ "Ref[%x|%x], App[%x|%x], "
+ "Guard[%x|%x] cmd=%p ox_id[%04x] ",
+ cmd->cdb[0], lba, (lba+cmd->num_blks), cmd->num_blks,
+ cmd->a_ref_tag, cmd->e_ref_tag,
+ cmd->a_app_tag, cmd->e_app_tag,
+ cmd->a_guard, cmd->e_guard,
+ cmd, cmd->atio.u.isp24.fcp_hdr.ox_id);
- ql_log(ql_log_warn, vha, 0xe077,
- "Ref Tag ERR: cdb 0x%x lba 0x%llx: [Actual|Expected] Ref Tag[0x%x|0x%x], App Tag [0x%x|0x%x], Guard [0x%x|0x%x] cmd=%p\n",
- cmd->atio.u.isp24.fcp_cmnd.cdb[0], lba,
- a_ref_tag, e_ref_tag, a_app_tag, e_app_tag,
- a_guard, e_guard, cmd);
+ cmd->dif_err_code = DIF_ERR_REF;
+ scsi_status = SAM_STAT_CHECK_CONDITION;
+ sense_key = ABORTED_COMMAND;
+ asc = 0x10;
+ ascq = 0x3;
goto out;
}
- /* check appl tag */
- if (e_app_tag != a_app_tag) {
- cmd->se_cmd.pi_err = TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED;
- cmd->se_cmd.bad_sector = cmd->se_cmd.t_task_lba;
-
- ql_log(ql_log_warn, vha, 0xe078,
- "App Tag ERR: cdb 0x%x lba 0x%llx: [Actual|Expected] Ref Tag[0x%x|0x%x], App Tag [0x%x|0x%x], Guard [0x%x|0x%x] cmd=%p\n",
- cmd->atio.u.isp24.fcp_cmnd.cdb[0], lba,
- a_ref_tag, e_ref_tag, a_app_tag, e_app_tag,
- a_guard, e_guard, cmd);
- goto out;
+ /* check guard */
+ if (cmd->e_guard != cmd->a_guard) {
+ ql_dbg(ql_dbg_tgt_dif, vha, 0xffff,
+ "Guard ERR: cdb[%x] lba[%llx %llx] blks[%x] [Actual|Expected] "
+ "Ref[%x|%x], App[%x|%x], "
+ "Guard [%x|%x] cmd=%p ox_id[%04x]",
+ cmd->cdb[0], lba, (lba+cmd->num_blks), cmd->num_blks,
+ cmd->a_ref_tag, cmd->e_ref_tag,
+ cmd->a_app_tag, cmd->e_app_tag,
+ cmd->a_guard, cmd->e_guard,
+ cmd, cmd->atio.u.isp24.fcp_hdr.ox_id);
+ cmd->dif_err_code = DIF_ERR_GRD;
+ scsi_status = SAM_STAT_CHECK_CONDITION;
+ sense_key = ABORTED_COMMAND;
+ asc = 0x10;
+ ascq = 0x1;
}
out:
- return 1;
-}
+ switch (cmd->state) {
+ case QLA_TGT_STATE_NEED_DATA:
+ /* handle_data will load DIF error code */
+ cmd->state = QLA_TGT_STATE_DATA_IN;
+ vha->hw->tgt.tgt_ops->handle_data(cmd);
+ break;
+ default:
+ spin_lock_irqsave(&cmd->cmd_lock, flags);
+ if (cmd->aborted) {
+ spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+ vha->hw->tgt.tgt_ops->free_cmd(cmd);
+ break;
+ }
+ spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+ qlt_send_resp_ctio(vha, cmd, scsi_status, sense_key, asc, ascq);
+ /* assume scsi status gets out on the wire.
+ * Will not wait for completion.
+ */
+ vha->hw->tgt.tgt_ops->free_cmd(cmd);
+ break;
+ }
+}
/* If hardware_lock held on entry, might drop it, then reaquire */
/* This function sends the appropriate CTIO to ISP 2xxx or 24xx */
@@ -3251,7 +3376,7 @@ static int __qlt_send_term_imm_notif(struct scsi_qla_host *vha,
ql_dbg(ql_dbg_tgt_tmr, vha, 0xe01c,
"Sending TERM ELS CTIO (ha=%p)\n", ha);
- pkt = (request_t *)qla2x00_alloc_iocbs_ready(vha, NULL);
+ pkt = (request_t *)qla2x00_alloc_iocbs(vha, NULL);
if (pkt == NULL) {
ql_dbg(ql_dbg_tgt, vha, 0xe080,
"qla_target(%d): %s failed: unable to allocate "
@@ -3543,6 +3668,16 @@ static int qlt_term_ctio_exchange(struct scsi_qla_host *vha, void *ctio,
{
int term = 0;
+ if (cmd->se_cmd.prot_op)
+ ql_dbg(ql_dbg_tgt_dif, vha, 0xffff,
+ "Term DIF cmd: lba[0x%llx|%lld] len[0x%x] "
+ "se_cmd=%p tag[%x] op %#x/%s",
+ cmd->lba, cmd->lba,
+ cmd->num_blks, &cmd->se_cmd,
+ cmd->atio.u.isp24.exchange_addr,
+ cmd->se_cmd.prot_op,
+ prot_op_str(cmd->se_cmd.prot_op));
+
if (ctio != NULL) {
struct ctio7_from_24xx *c = (struct ctio7_from_24xx *)ctio;
term = !(c->flags &
@@ -3760,32 +3895,15 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, uint32_t handle,
struct ctio_crc_from_fw *crc =
(struct ctio_crc_from_fw *)ctio;
ql_dbg(ql_dbg_tgt_mgt, vha, 0xf073,
- "qla_target(%d): CTIO with DIF_ERROR status %x received (state %x, se_cmd %p) actual_dif[0x%llx] expect_dif[0x%llx]\n",
+ "qla_target(%d): CTIO with DIF_ERROR status %x "
+ "received (state %x, ulp_cmd %p) actual_dif[0x%llx] "
+ "expect_dif[0x%llx]\n",
vha->vp_idx, status, cmd->state, se_cmd,
*((u64 *)&crc->actual_dif[0]),
*((u64 *)&crc->expected_dif[0]));
- if (qlt_handle_dif_error(vha, cmd, ctio)) {
- if (cmd->state == QLA_TGT_STATE_NEED_DATA) {
- /* scsi Write/xfer rdy complete */
- goto skip_term;
- } else {
- /* scsi read/xmit respond complete
- * call handle dif to send scsi status
- * rather than terminate exchange.
- */
- cmd->state = QLA_TGT_STATE_PROCESSED;
- ha->tgt.tgt_ops->handle_dif_err(cmd);
- return;
- }
- } else {
- /* Need to generate a SCSI good completion.
- * because FW did not send scsi status.
- */
- status = 0;
- goto skip_term;
- }
- break;
+ qlt_handle_dif_error(vha, cmd, ctio);
+ return;
}
default:
ql_dbg(ql_dbg_tgt_mgt, vha, 0xf05b,
@@ -3808,7 +3926,6 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, uint32_t handle,
return;
}
}
-skip_term:
if (cmd->state == QLA_TGT_STATE_PROCESSED) {
cmd->trc_flags |= TRC_CTIO_DONE;
@@ -4584,7 +4701,8 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
}
if (sess != NULL) {
- if (sess->fw_login_state == DSC_LS_PLOGI_PEND) {
+ if (sess->fw_login_state != DSC_LS_PLOGI_PEND &&
+ sess->fw_login_state != DSC_LS_PLOGI_COMP) {
/*
* Impatient initiator sent PRLI before last
* PLOGI could finish. Will force him to re-try,
@@ -4623,15 +4741,23 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
/* Make session global (not used in fabric mode) */
if (ha->current_topology != ISP_CFG_F) {
- set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
- set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags);
- qla2xxx_wake_dpc(vha);
+ if (sess) {
+ ql_dbg(ql_dbg_disc, vha, 0xffff,
+ "%s %d %8phC post nack\n",
+ __func__, __LINE__, sess->port_name);
+ qla24xx_post_nack_work(vha, sess, iocb,
+ SRB_NACK_PRLI);
+ res = 0;
+ } else {
+ set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
+ set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags);
+ qla2xxx_wake_dpc(vha);
+ }
} else {
if (sess) {
ql_dbg(ql_dbg_disc, vha, 0xffff,
- "%s %d %8phC post nack\n",
- __func__, __LINE__, sess->port_name);
-
+ "%s %d %8phC post nack\n",
+ __func__, __LINE__, sess->port_name);
qla24xx_post_nack_work(vha, sess, iocb,
SRB_NACK_PRLI);
res = 0;
@@ -4639,7 +4765,6 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
}
break;
-
case ELS_TPRLO:
if (le16_to_cpu(iocb->u.isp24.flags) &
NOTIFY24XX_FLAGS_GLOBAL_TPRLO) {
@@ -5079,16 +5204,22 @@ qlt_send_busy(struct scsi_qla_host *vha,
static int
qlt_chk_qfull_thresh_hold(struct scsi_qla_host *vha,
- struct atio_from_isp *atio)
+ struct atio_from_isp *atio, bool ha_locked)
{
struct qla_hw_data *ha = vha->hw;
uint16_t status;
+ unsigned long flags;
if (ha->tgt.num_pend_cmds < Q_FULL_THRESH_HOLD(ha))
return 0;
+ if (!ha_locked)
+ spin_lock_irqsave(&ha->hardware_lock, flags);
status = temp_sam_status;
qlt_send_busy(vha, atio, status);
+ if (!ha_locked)
+ spin_unlock_irqrestore(&ha->hardware_lock, flags);
+
return 1;
}
@@ -5103,7 +5234,7 @@ static void qlt_24xx_atio_pkt(struct scsi_qla_host *vha,
unsigned long flags;
if (unlikely(tgt == NULL)) {
- ql_dbg(ql_dbg_io, vha, 0x3064,
+ ql_dbg(ql_dbg_tgt, vha, 0x3064,
"ATIO pkt, but no tgt (ha %p)", ha);
return;
}
@@ -5133,7 +5264,7 @@ static void qlt_24xx_atio_pkt(struct scsi_qla_host *vha,
if (likely(atio->u.isp24.fcp_cmnd.task_mgmt_flags == 0)) {
- rc = qlt_chk_qfull_thresh_hold(vha, atio);
+ rc = qlt_chk_qfull_thresh_hold(vha, atio, ha_locked);
if (rc != 0) {
tgt->atio_irq_cmd_count--;
return;
@@ -5256,7 +5387,7 @@ static void qlt_response_pkt(struct scsi_qla_host *vha, response_t *pkt)
break;
}
- rc = qlt_chk_qfull_thresh_hold(vha, atio);
+ rc = qlt_chk_qfull_thresh_hold(vha, atio, true);
if (rc != 0) {
tgt->irq_cmd_count--;
return;
@@ -5531,7 +5662,7 @@ static fc_port_t *qlt_get_port_database(struct scsi_qla_host *vha,
fcport->loop_id = loop_id;
- rc = qla2x00_get_port_database(vha, fcport, 0);
+ rc = qla24xx_gpdb_wait(vha, fcport, 0);
if (rc != QLA_SUCCESS) {
ql_dbg(ql_dbg_tgt_mgt, vha, 0xf070,
"qla_target(%d): Failed to retrieve fcport "
@@ -5713,30 +5844,23 @@ static void qlt_abort_work(struct qla_tgt *tgt,
}
}
- spin_lock_irqsave(&ha->hardware_lock, flags);
-
- if (tgt->tgt_stop)
- goto out_term;
-
rc = __qlt_24xx_handle_abts(vha, &prm->abts, sess);
+ ha->tgt.tgt_ops->put_sess(sess);
+ spin_unlock_irqrestore(&ha->tgt.sess_lock, flags2);
+
if (rc != 0)
goto out_term;
- spin_unlock_irqrestore(&ha->hardware_lock, flags);
- if (sess)
- ha->tgt.tgt_ops->put_sess(sess);
- spin_unlock_irqrestore(&ha->tgt.sess_lock, flags2);
return;
out_term2:
- spin_lock_irqsave(&ha->hardware_lock, flags);
-
-out_term:
- qlt_24xx_send_abts_resp(vha, &prm->abts, FCP_TMF_REJECTED, false);
- spin_unlock_irqrestore(&ha->hardware_lock, flags);
-
if (sess)
ha->tgt.tgt_ops->put_sess(sess);
spin_unlock_irqrestore(&ha->tgt.sess_lock, flags2);
+
+out_term:
+ spin_lock_irqsave(&ha->hardware_lock, flags);
+ qlt_24xx_send_abts_resp(vha, &prm->abts, FCP_TMF_REJECTED, false);
+ spin_unlock_irqrestore(&ha->hardware_lock, flags);
}
static void qlt_tmr_work(struct qla_tgt *tgt,
@@ -5756,7 +5880,7 @@ static void qlt_tmr_work(struct qla_tgt *tgt,
spin_lock_irqsave(&ha->tgt.sess_lock, flags);
if (tgt->tgt_stop)
- goto out_term;
+ goto out_term2;
s_id = prm->tm_iocb2.u.isp24.fcp_hdr.s_id;
sess = ha->tgt.tgt_ops->find_sess_by_s_id(vha, s_id);
@@ -5768,11 +5892,11 @@ static void qlt_tmr_work(struct qla_tgt *tgt,
spin_lock_irqsave(&ha->tgt.sess_lock, flags);
if (!sess)
- goto out_term;
+ goto out_term2;
} else {
if (sess->deleted) {
sess = NULL;
- goto out_term;
+ goto out_term2;
}
if (!kref_get_unless_zero(&sess->sess_kref)) {
@@ -5780,7 +5904,7 @@ static void qlt_tmr_work(struct qla_tgt *tgt,
"%s: kref_get fail %8phC\n",
__func__, sess->port_name);
sess = NULL;
- goto out_term;
+ goto out_term2;
}
}
@@ -5790,17 +5914,19 @@ static void qlt_tmr_work(struct qla_tgt *tgt,
unpacked_lun = scsilun_to_int((struct scsi_lun *)&lun);
rc = qlt_issue_task_mgmt(sess, unpacked_lun, fn, iocb, 0);
+ ha->tgt.tgt_ops->put_sess(sess);
+ spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+
if (rc != 0)
goto out_term;
-
- ha->tgt.tgt_ops->put_sess(sess);
- spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
return;
+out_term2:
+ if (sess)
+ ha->tgt.tgt_ops->put_sess(sess);
+ spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
out_term:
qlt_send_term_exchange(vha, NULL, &prm->tm_iocb2, 1, 0);
- ha->tgt.tgt_ops->put_sess(sess);
- spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
}
static void qlt_sess_work_fn(struct work_struct *work)
@@ -5893,13 +6019,13 @@ int qlt_add_target(struct qla_hw_data *ha, struct scsi_qla_host *base_vha)
tgt->datasegs_per_cmd = QLA_TGT_DATASEGS_PER_CMD_24XX;
tgt->datasegs_per_cont = QLA_TGT_DATASEGS_PER_CONT_24XX;
- if (base_vha->fc_vport)
- return 0;
-
mutex_lock(&qla_tgt_mutex);
list_add_tail(&tgt->tgt_list_entry, &qla_tgt_glist);
mutex_unlock(&qla_tgt_mutex);
+ if (ha->tgt.tgt_ops && ha->tgt.tgt_ops->add_target)
+ ha->tgt.tgt_ops->add_target(base_vha);
+
return 0;
}
@@ -5928,6 +6054,17 @@ int qlt_remove_target(struct qla_hw_data *ha, struct scsi_qla_host *vha)
return 0;
}
+void qlt_remove_target_resources(struct qla_hw_data *ha)
+{
+ struct scsi_qla_host *node;
+ u32 key = 0;
+
+ btree_for_each_safe32(&ha->tgt.host_map, key, node)
+ btree_remove32(&ha->tgt.host_map, key);
+
+ btree_destroy32(&ha->tgt.host_map);
+}
+
static void qlt_lport_dump(struct scsi_qla_host *vha, u64 wwpn,
unsigned char *b)
{
@@ -6234,7 +6371,7 @@ qlt_24xx_process_atio_queue(struct scsi_qla_host *vha, uint8_t ha_locked)
struct atio_from_isp *pkt;
int cnt, i;
- if (!vha->flags.online)
+ if (!ha->flags.fw_started)
return;
while ((ha->tgt.atio_ring_ptr->signature != ATIO_PROCESSED) ||
@@ -6581,6 +6718,8 @@ qlt_modify_vp_config(struct scsi_qla_host *vha,
void
qlt_probe_one_stage1(struct scsi_qla_host *base_vha, struct qla_hw_data *ha)
{
+ int rc;
+
if (!QLA_TGT_MODE_ENABLED())
return;
@@ -6600,6 +6739,13 @@ qlt_probe_one_stage1(struct scsi_qla_host *base_vha, struct qla_hw_data *ha)
qlt_unknown_atio_work_fn);
qlt_clear_mode(base_vha);
+
+ rc = btree_init32(&ha->tgt.host_map);
+ if (rc)
+ ql_log(ql_log_info, base_vha, 0xffff,
+ "Unable to initialize ha->host_map btree\n");
+
+ qlt_update_vp_map(base_vha, SET_VP_IDX);
}
irqreturn_t
@@ -6642,6 +6788,8 @@ qlt_handle_abts_recv_work(struct work_struct *work)
spin_lock_irqsave(&ha->hardware_lock, flags);
qlt_response_pkt_all_vps(vha, (response_t *)&op->atio);
spin_unlock_irqrestore(&ha->hardware_lock, flags);
+
+ kfree(op);
}
void
@@ -6706,25 +6854,69 @@ qlt_mem_free(struct qla_hw_data *ha)
void
qlt_update_vp_map(struct scsi_qla_host *vha, int cmd)
{
+ void *slot;
+ u32 key;
+ int rc;
+
if (!QLA_TGT_MODE_ENABLED())
return;
+ key = vha->d_id.b24;
+
switch (cmd) {
case SET_VP_IDX:
vha->hw->tgt.tgt_vp_map[vha->vp_idx].vha = vha;
break;
case SET_AL_PA:
- vha->hw->tgt.tgt_vp_map[vha->d_id.b.al_pa].idx = vha->vp_idx;
+ slot = btree_lookup32(&vha->hw->tgt.host_map, key);
+ if (!slot) {
+ ql_dbg(ql_dbg_tgt_mgt, vha, 0xffff,
+ "Save vha in host_map %p %06x\n", vha, key);
+ rc = btree_insert32(&vha->hw->tgt.host_map,
+ key, vha, GFP_ATOMIC);
+ if (rc)
+ ql_log(ql_log_info, vha, 0xffff,
+ "Unable to insert s_id into host_map: %06x\n",
+ key);
+ return;
+ }
+ ql_dbg(ql_dbg_tgt_mgt, vha, 0xffff,
+ "replace existing vha in host_map %p %06x\n", vha, key);
+ btree_update32(&vha->hw->tgt.host_map, key, vha);
break;
case RESET_VP_IDX:
vha->hw->tgt.tgt_vp_map[vha->vp_idx].vha = NULL;
break;
case RESET_AL_PA:
- vha->hw->tgt.tgt_vp_map[vha->d_id.b.al_pa].idx = 0;
+ ql_dbg(ql_dbg_tgt_mgt, vha, 0xffff,
+ "clear vha in host_map %p %06x\n", vha, key);
+ slot = btree_lookup32(&vha->hw->tgt.host_map, key);
+ if (slot)
+ btree_remove32(&vha->hw->tgt.host_map, key);
+ vha->d_id.b24 = 0;
break;
}
}
+void qlt_update_host_map(struct scsi_qla_host *vha, port_id_t id)
+{
+ unsigned long flags;
+ struct qla_hw_data *ha = vha->hw;
+
+ if (!vha->d_id.b24) {
+ spin_lock_irqsave(&ha->vport_slock, flags);
+ vha->d_id = id;
+ qlt_update_vp_map(vha, SET_AL_PA);
+ spin_unlock_irqrestore(&ha->vport_slock, flags);
+ } else if (vha->d_id.b24 != id.b24) {
+ spin_lock_irqsave(&ha->vport_slock, flags);
+ qlt_update_vp_map(vha, RESET_AL_PA);
+ vha->d_id = id;
+ qlt_update_vp_map(vha, SET_AL_PA);
+ spin_unlock_irqrestore(&ha->vport_slock, flags);
+ }
+}
+
static int __init qlt_parse_ini_mode(void)
{
if (strcasecmp(qlini_mode, QLA2XXX_INI_MODE_STR_EXCLUSIVE) == 0)
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index a7f90dc..d644202 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -378,6 +378,14 @@ static inline void adjust_corrupted_atio(struct atio_from_isp *atio)
atio->u.isp24.fcp_cmnd.add_cdb_len = 0;
}
+static inline int get_datalen_for_atio(struct atio_from_isp *atio)
+{
+ int len = atio->u.isp24.fcp_cmnd.add_cdb_len;
+
+ return (be32_to_cpu(get_unaligned((uint32_t *)
+ &atio->u.isp24.fcp_cmnd.add_cdb[len * 4])));
+}
+
#define CTIO_TYPE7 0x12 /* Continue target I/O entry (for 24xx) */
/*
@@ -667,7 +675,6 @@ struct qla_tgt_func_tmpl {
int (*handle_cmd)(struct scsi_qla_host *, struct qla_tgt_cmd *,
unsigned char *, uint32_t, int, int, int);
void (*handle_data)(struct qla_tgt_cmd *);
- void (*handle_dif_err)(struct qla_tgt_cmd *);
int (*handle_tmr)(struct qla_tgt_mgmt_cmd *, uint32_t, uint16_t,
uint32_t);
void (*free_cmd)(struct qla_tgt_cmd *);
@@ -684,6 +691,9 @@ struct qla_tgt_func_tmpl {
void (*clear_nacl_from_fcport_map)(struct fc_port *);
void (*put_sess)(struct fc_port *);
void (*shutdown_sess)(struct fc_port *);
+ int (*get_dif_tags)(struct qla_tgt_cmd *cmd, uint16_t *pfw_prot_opts);
+ int (*chk_dif_tags)(uint32_t tag);
+ void (*add_target)(struct scsi_qla_host *);
};
int qla2x00_wait_for_hba_online(struct scsi_qla_host *);
@@ -720,8 +730,8 @@ int qla2x00_wait_for_hba_online(struct scsi_qla_host *);
#define QLA_TGT_ABORT_ALL 0xFFFE
#define QLA_TGT_NEXUS_LOSS_SESS 0xFFFD
#define QLA_TGT_NEXUS_LOSS 0xFFFC
-#define QLA_TGT_ABTS 0xFFFB
-#define QLA_TGT_2G_ABORT_TASK 0xFFFA
+#define QLA_TGT_ABTS 0xFFFB
+#define QLA_TGT_2G_ABORT_TASK 0xFFFA
/* Notify Acknowledge flags */
#define NOTIFY_ACK_RES_COUNT BIT_8
@@ -845,6 +855,7 @@ enum trace_flags {
TRC_CMD_FREE = BIT_17,
TRC_DATA_IN = BIT_18,
TRC_ABORT = BIT_19,
+ TRC_DIF_ERR = BIT_20,
};
struct qla_tgt_cmd {
@@ -862,7 +873,6 @@ struct qla_tgt_cmd {
unsigned int sg_mapped:1;
unsigned int free_sg:1;
unsigned int write_data_transferred:1;
- unsigned int ctx_dsd_alloced:1;
unsigned int q_full:1;
unsigned int term_exchg:1;
unsigned int cmd_sent_to_fw:1;
@@ -885,11 +895,25 @@ struct qla_tgt_cmd {
struct list_head cmd_list;
struct atio_from_isp atio;
- /* t10dif */
+
+ uint8_t ctx_dsd_alloced;
+
+ /* T10-DIF */
+#define DIF_ERR_NONE 0
+#define DIF_ERR_GRD 1
+#define DIF_ERR_REF 2
+#define DIF_ERR_APP 3
+ int8_t dif_err_code;
struct scatterlist *prot_sg;
uint32_t prot_sg_cnt;
- uint32_t blk_sz;
+ uint32_t blk_sz, num_blks;
+ uint8_t scsi_status, sense_key, asc, ascq;
+
struct crc_context *ctx;
+ uint8_t *cdb;
+ uint64_t lba;
+ uint16_t a_guard, e_guard, a_app_tag, e_app_tag;
+ uint32_t a_ref_tag, e_ref_tag;
uint64_t jiffies_at_alloc;
uint64_t jiffies_at_free;
@@ -1053,4 +1077,7 @@ extern int qlt_free_qfull_cmds(struct scsi_qla_host *);
extern void qlt_logo_completion_handler(fc_port_t *, int);
extern void qlt_do_generation_tick(struct scsi_qla_host *, int *);
+void qlt_send_resp_ctio(scsi_qla_host_t *, struct qla_tgt_cmd *, uint8_t,
+ uint8_t, uint8_t, uint8_t);
+
#endif /* __QLA_TARGET_H */
diff --git a/drivers/scsi/qla2xxx/qla_version.h b/drivers/scsi/qla2xxx/qla_version.h
index 3cb1964..45bc84e 100644
--- a/drivers/scsi/qla2xxx/qla_version.h
+++ b/drivers/scsi/qla2xxx/qla_version.h
@@ -7,9 +7,9 @@
/*
* Driver version
*/
-#define QLA2XXX_VERSION "8.07.00.38-k"
+#define QLA2XXX_VERSION "9.00.00.00-k"
-#define QLA_DRIVER_MAJOR_VER 8
-#define QLA_DRIVER_MINOR_VER 7
+#define QLA_DRIVER_MAJOR_VER 9
+#define QLA_DRIVER_MINOR_VER 0
#define QLA_DRIVER_PATCH_VER 0
#define QLA_DRIVER_BETA_VER 0
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 8e8ab0f..7443e4e 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -531,6 +531,24 @@ static void tcm_qla2xxx_handle_data_work(struct work_struct *work)
return;
}
+ switch (cmd->dif_err_code) {
+ case DIF_ERR_GRD:
+ cmd->se_cmd.pi_err =
+ TCM_LOGICAL_BLOCK_GUARD_CHECK_FAILED;
+ break;
+ case DIF_ERR_REF:
+ cmd->se_cmd.pi_err =
+ TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED;
+ break;
+ case DIF_ERR_APP:
+ cmd->se_cmd.pi_err =
+ TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED;
+ break;
+ case DIF_ERR_NONE:
+ default:
+ break;
+ }
+
if (cmd->se_cmd.pi_err)
transport_generic_request_failure(&cmd->se_cmd,
cmd->se_cmd.pi_err);
@@ -555,25 +573,23 @@ static void tcm_qla2xxx_handle_data(struct qla_tgt_cmd *cmd)
queue_work_on(smp_processor_id(), tcm_qla2xxx_free_wq, &cmd->work);
}
-static void tcm_qla2xxx_handle_dif_work(struct work_struct *work)
+static int tcm_qla2xxx_chk_dif_tags(uint32_t tag)
{
- struct qla_tgt_cmd *cmd = container_of(work, struct qla_tgt_cmd, work);
-
- /* take an extra kref to prevent cmd free too early.
- * need to wait for SCSI status/check condition to
- * finish responding generate by transport_generic_request_failure.
- */
- kref_get(&cmd->se_cmd.cmd_kref);
- transport_generic_request_failure(&cmd->se_cmd, cmd->se_cmd.pi_err);
+ return 0;
}
-/*
- * Called from qla_target.c:qlt_do_ctio_completion()
- */
-static void tcm_qla2xxx_handle_dif_err(struct qla_tgt_cmd *cmd)
+static int tcm_qla2xxx_dif_tags(struct qla_tgt_cmd *cmd,
+ uint16_t *pfw_prot_opts)
{
- INIT_WORK(&cmd->work, tcm_qla2xxx_handle_dif_work);
- queue_work(tcm_qla2xxx_free_wq, &cmd->work);
+ struct se_cmd *se_cmd = &cmd->se_cmd;
+
+ if (!(se_cmd->prot_checks & TARGET_DIF_CHECK_GUARD))
+ *pfw_prot_opts |= PO_DISABLE_GUARD_CHECK;
+
+ if (!(se_cmd->prot_checks & TARGET_DIF_CHECK_APPTAG))
+ *pfw_prot_opts |= PO_DIS_APP_TAG_VALD;
+
+ return 0;
}
/*
@@ -1610,7 +1626,6 @@ static void tcm_qla2xxx_update_sess(struct fc_port *sess, port_id_t s_id,
static struct qla_tgt_func_tmpl tcm_qla2xxx_template = {
.handle_cmd = tcm_qla2xxx_handle_cmd,
.handle_data = tcm_qla2xxx_handle_data,
- .handle_dif_err = tcm_qla2xxx_handle_dif_err,
.handle_tmr = tcm_qla2xxx_handle_tmr,
.free_cmd = tcm_qla2xxx_free_cmd,
.free_mcmd = tcm_qla2xxx_free_mcmd,
@@ -1622,6 +1637,8 @@ static struct qla_tgt_func_tmpl tcm_qla2xxx_template = {
.clear_nacl_from_fcport_map = tcm_qla2xxx_clear_nacl_from_fcport_map,
.put_sess = tcm_qla2xxx_put_sess,
.shutdown_sess = tcm_qla2xxx_shutdown_sess,
+ .get_dif_tags = tcm_qla2xxx_dif_tags,
+ .chk_dif_tags = tcm_qla2xxx_chk_dif_tags,
};
static int tcm_qla2xxx_init_lport(struct tcm_qla2xxx_lport *lport)
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index ba22866..19125d7 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -2932,6 +2932,8 @@ EXPORT_SYMBOL(scsi_target_resume);
/**
* scsi_internal_device_block - internal function to put a device temporarily into the SDEV_BLOCK state
* @sdev: device to block
+ * @wait: Whether or not to wait until ongoing .queuecommand() /
+ * .queue_rq() calls have finished.
*
* Block request made by scsi lld's to temporarily stop all
* scsi commands on the specified device. May sleep.
@@ -2949,7 +2951,7 @@ EXPORT_SYMBOL(scsi_target_resume);
* remove the rport mutex lock and unlock calls from srp_queuecommand().
*/
int
-scsi_internal_device_block(struct scsi_device *sdev)
+scsi_internal_device_block(struct scsi_device *sdev, bool wait)
{
struct request_queue *q = sdev->request_queue;
unsigned long flags;
@@ -2969,12 +2971,16 @@ scsi_internal_device_block(struct scsi_device *sdev)
* request queue.
*/
if (q->mq_ops) {
- blk_mq_quiesce_queue(q);
+ if (wait)
+ blk_mq_quiesce_queue(q);
+ else
+ blk_mq_stop_hw_queues(q);
} else {
spin_lock_irqsave(q->queue_lock, flags);
blk_stop_queue(q);
spin_unlock_irqrestore(q->queue_lock, flags);
- scsi_wait_for_queuecommand(sdev);
+ if (wait)
+ scsi_wait_for_queuecommand(sdev);
}
return 0;
@@ -3036,7 +3042,7 @@ EXPORT_SYMBOL_GPL(scsi_internal_device_unblock);
static void
device_block(struct scsi_device *sdev, void *data)
{
- scsi_internal_device_block(sdev);
+ scsi_internal_device_block(sdev, true);
}
static int
diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h
index 99bfc98..f11bd10 100644
--- a/drivers/scsi/scsi_priv.h
+++ b/drivers/scsi/scsi_priv.h
@@ -188,8 +188,5 @@ static inline void scsi_dh_remove_device(struct scsi_device *sdev) { }
*/
#define SCSI_DEVICE_BLOCK_MAX_TIMEOUT 600 /* units in seconds */
-extern int scsi_internal_device_block(struct scsi_device *sdev);
-extern int scsi_internal_device_unblock(struct scsi_device *sdev,
- enum scsi_device_state new_state);
#endif /* _SCSI_PRIV_H */
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index c7839f6..fcfeddc 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1783,6 +1783,8 @@ static int sd_done(struct scsi_cmnd *SCpnt)
{
int result = SCpnt->result;
unsigned int good_bytes = result ? 0 : scsi_bufflen(SCpnt);
+ unsigned int sector_size = SCpnt->device->sector_size;
+ unsigned int resid;
struct scsi_sense_hdr sshdr;
struct scsi_disk *sdkp = scsi_disk(SCpnt->request->rq_disk);
struct request *req = SCpnt->request;
@@ -1813,6 +1815,21 @@ static int sd_done(struct scsi_cmnd *SCpnt)
scsi_set_resid(SCpnt, blk_rq_bytes(req));
}
break;
+ default:
+ /*
+ * In case of bogus fw or device, we could end up having
+ * an unaligned partial completion. Check this here and force
+ * alignment.
+ */
+ resid = scsi_get_resid(SCpnt);
+ if (resid & (sector_size - 1)) {
+ sd_printk(KERN_INFO, sdkp,
+ "Unaligned partial completion (resid=%u, sector_sz=%u)\n",
+ resid, sector_size);
+ resid = min(scsi_bufflen(SCpnt),
+ round_up(resid, sector_size));
+ scsi_set_resid(SCpnt, resid);
+ }
}
if (result) {
@@ -3075,23 +3092,6 @@ static void sd_probe_async(void *data, async_cookie_t cookie)
put_device(&sdkp->dev);
}
-struct sd_devt {
- int idx;
- struct disk_devt disk_devt;
-};
-
-static void sd_devt_release(struct disk_devt *disk_devt)
-{
- struct sd_devt *sd_devt = container_of(disk_devt, struct sd_devt,
- disk_devt);
-
- spin_lock(&sd_index_lock);
- ida_remove(&sd_index_ida, sd_devt->idx);
- spin_unlock(&sd_index_lock);
-
- kfree(sd_devt);
-}
-
/**
* sd_probe - called during driver initialization and whenever a
* new scsi device is attached to the system. It is called once
@@ -3113,7 +3113,6 @@ static void sd_devt_release(struct disk_devt *disk_devt)
static int sd_probe(struct device *dev)
{
struct scsi_device *sdp = to_scsi_device(dev);
- struct sd_devt *sd_devt;
struct scsi_disk *sdkp;
struct gendisk *gd;
int index;
@@ -3139,13 +3138,9 @@ static int sd_probe(struct device *dev)
if (!sdkp)
goto out;
- sd_devt = kzalloc(sizeof(*sd_devt), GFP_KERNEL);
- if (!sd_devt)
- goto out_free;
-
gd = alloc_disk(SD_MINORS);
if (!gd)
- goto out_free_devt;
+ goto out_free;
do {
if (!ida_pre_get(&sd_index_ida, GFP_KERNEL))
@@ -3161,11 +3156,6 @@ static int sd_probe(struct device *dev)
goto out_put;
}
- atomic_set(&sd_devt->disk_devt.count, 1);
- sd_devt->disk_devt.release = sd_devt_release;
- sd_devt->idx = index;
- gd->disk_devt = &sd_devt->disk_devt;
-
error = sd_format_disk_name("sd", index, gd->disk_name, DISK_NAME_LEN);
if (error) {
sdev_printk(KERN_WARNING, sdp, "SCSI disk (sd) name length exceeded.\n");
@@ -3205,12 +3195,11 @@ static int sd_probe(struct device *dev)
return 0;
out_free_index:
- put_disk_devt(&sd_devt->disk_devt);
- sd_devt = NULL;
+ spin_lock(&sd_index_lock);
+ ida_remove(&sd_index_ida, index);
+ spin_unlock(&sd_index_lock);
out_put:
put_disk(gd);
- out_free_devt:
- kfree(sd_devt);
out_free:
kfree(sdkp);
out:
@@ -3271,7 +3260,10 @@ static void scsi_disk_release(struct device *dev)
struct scsi_disk *sdkp = to_scsi_disk(dev);
struct gendisk *disk = sdkp->disk;
- put_disk_devt(disk->disk_devt);
+ spin_lock(&sd_index_lock);
+ ida_remove(&sd_index_ida, sdkp->index);
+ spin_unlock(&sd_index_lock);
+
disk->private_data = NULL;
put_disk(disk);
put_device(&sdkp->device->sdev_gendev);
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 29b8650..225abaa 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -996,6 +996,8 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
result = get_user(val, ip);
if (result)
return result;
+ if (val > SG_MAX_CDB_SIZE)
+ return -ENOMEM;
sfp->next_cmd_len = (val > 0) ? val : 0;
return 0;
case SG_GET_VERSION_NUM:
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 638e5f4..016639d 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -400,8 +400,6 @@ MODULE_PARM_DESC(storvsc_vcpus_per_sub_channel, "Ratio of VCPUs to subchannels")
*/
static int storvsc_timeout = 180;
-static int msft_blist_flags = BLIST_TRY_VPD_PAGES;
-
#if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
static struct scsi_transport_template *fc_transport_template;
#endif
@@ -1383,6 +1381,22 @@ static int storvsc_do_io(struct hv_device *device,
return ret;
}
+static int storvsc_device_alloc(struct scsi_device *sdevice)
+{
+ /*
+ * Set blist flag to permit the reading of the VPD pages even when
+ * the target may claim SPC-2 compliance. MSFT targets currently
+ * claim SPC-2 compliance while they implement post SPC-2 features.
+ * With this flag we can correctly handle WRITE_SAME_16 issues.
+ *
+ * Hypervisor reports SCSI_UNKNOWN type for DVD ROM device but
+ * still supports REPORT LUN.
+ */
+ sdevice->sdev_bflags = BLIST_REPORTLUN2 | BLIST_TRY_VPD_PAGES;
+
+ return 0;
+}
+
static int storvsc_device_configure(struct scsi_device *sdevice)
{
@@ -1396,14 +1410,6 @@ static int storvsc_device_configure(struct scsi_device *sdevice)
sdevice->no_write_same = 1;
/*
- * Add blist flags to permit the reading of the VPD pages even when
- * the target may claim SPC-2 compliance. MSFT targets currently
- * claim SPC-2 compliance while they implement post SPC-2 features.
- * With this patch we can correctly handle WRITE_SAME_16 issues.
- */
- sdevice->sdev_bflags |= msft_blist_flags;
-
- /*
* If the host is WIN8 or WIN8 R2, claim conformance to SPC-3
* if the device is a MSFT virtual device. If the host is
* WIN10 or newer, allow write_same.
@@ -1661,6 +1667,7 @@ static struct scsi_host_template scsi_driver = {
.eh_host_reset_handler = storvsc_host_reset_handler,
.proc_name = "storvsc_host",
.eh_timed_out = storvsc_eh_timed_out,
+ .slave_alloc = storvsc_device_alloc,
.slave_configure = storvsc_device_configure,
.cmd_per_lun = 255,
.this_id = -1,
diff --git a/drivers/scsi/ufs/ufs.h b/drivers/scsi/ufs/ufs.h
index 318e4a1..54deeb7 100644
--- a/drivers/scsi/ufs/ufs.h
+++ b/drivers/scsi/ufs/ufs.h
@@ -146,7 +146,7 @@ enum attr_idn {
/* Descriptor idn for Query requests */
enum desc_idn {
QUERY_DESC_IDN_DEVICE = 0x0,
- QUERY_DESC_IDN_CONFIGURAION = 0x1,
+ QUERY_DESC_IDN_CONFIGURATION = 0x1,
QUERY_DESC_IDN_UNIT = 0x2,
QUERY_DESC_IDN_RFU_0 = 0x3,
QUERY_DESC_IDN_INTERCONNECT = 0x4,
@@ -162,19 +162,13 @@ enum desc_header_offset {
QUERY_DESC_DESC_TYPE_OFFSET = 0x01,
};
-enum ufs_desc_max_size {
- QUERY_DESC_DEVICE_MAX_SIZE = 0x40,
- QUERY_DESC_CONFIGURAION_MAX_SIZE = 0x90,
- QUERY_DESC_UNIT_MAX_SIZE = 0x23,
- QUERY_DESC_INTERCONNECT_MAX_SIZE = 0x06,
- /*
- * Max. 126 UNICODE characters (2 bytes per character) plus 2 bytes
- * of descriptor header.
- */
- QUERY_DESC_STRING_MAX_SIZE = 0xFE,
- QUERY_DESC_GEOMETRY_MAX_SIZE = 0x44,
- QUERY_DESC_POWER_MAX_SIZE = 0x62,
- QUERY_DESC_RFU_MAX_SIZE = 0x00,
+enum ufs_desc_def_size {
+ QUERY_DESC_DEVICE_DEF_SIZE = 0x40,
+ QUERY_DESC_CONFIGURATION_DEF_SIZE = 0x90,
+ QUERY_DESC_UNIT_DEF_SIZE = 0x23,
+ QUERY_DESC_INTERCONNECT_DEF_SIZE = 0x06,
+ QUERY_DESC_GEOMETRY_DEF_SIZE = 0x44,
+ QUERY_DESC_POWER_DEF_SIZE = 0x62,
};
/* Unit descriptor parameters offsets in bytes*/
diff --git a/drivers/scsi/ufs/ufshcd-pltfrm.c b/drivers/scsi/ufs/ufshcd-pltfrm.c
index a72a4ba..8e5e6c0 100644
--- a/drivers/scsi/ufs/ufshcd-pltfrm.c
+++ b/drivers/scsi/ufs/ufshcd-pltfrm.c
@@ -309,8 +309,8 @@ int ufshcd_pltfrm_init(struct platform_device *pdev,
mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
mmio_base = devm_ioremap_resource(dev, mem_res);
- if (IS_ERR(*(void **)&mmio_base)) {
- err = PTR_ERR(*(void **)&mmio_base);
+ if (IS_ERR(mmio_base)) {
+ err = PTR_ERR(mmio_base);
goto out;
}
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index dc6efbd..096e95b 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -100,19 +100,6 @@
#define ufshcd_hex_dump(prefix_str, buf, len) \
print_hex_dump(KERN_ERR, prefix_str, DUMP_PREFIX_OFFSET, 16, 4, buf, len, false)
-static u32 ufs_query_desc_max_size[] = {
- QUERY_DESC_DEVICE_MAX_SIZE,
- QUERY_DESC_CONFIGURAION_MAX_SIZE,
- QUERY_DESC_UNIT_MAX_SIZE,
- QUERY_DESC_RFU_MAX_SIZE,
- QUERY_DESC_INTERCONNECT_MAX_SIZE,
- QUERY_DESC_STRING_MAX_SIZE,
- QUERY_DESC_RFU_MAX_SIZE,
- QUERY_DESC_GEOMETRY_MAX_SIZE,
- QUERY_DESC_POWER_MAX_SIZE,
- QUERY_DESC_RFU_MAX_SIZE,
-};
-
enum {
UFSHCD_MAX_CHANNEL = 0,
UFSHCD_MAX_ID = 1,
@@ -2857,7 +2844,7 @@ static int __ufshcd_query_descriptor(struct ufs_hba *hba,
goto out;
}
- if (*buf_len <= QUERY_DESC_MIN_SIZE || *buf_len > QUERY_DESC_MAX_SIZE) {
+ if (*buf_len < QUERY_DESC_MIN_SIZE || *buf_len > QUERY_DESC_MAX_SIZE) {
dev_err(hba->dev, "%s: descriptor buffer size (%d) is out of range\n",
__func__, *buf_len);
err = -EINVAL;
@@ -2938,6 +2925,92 @@ static int ufshcd_query_descriptor_retry(struct ufs_hba *hba,
}
/**
+ * ufshcd_read_desc_length - read the specified descriptor length from header
+ * @hba: Pointer to adapter instance
+ * @desc_id: descriptor idn value
+ * @desc_index: descriptor index
+ * @desc_length: pointer to variable to read the length of descriptor
+ *
+ * Return 0 in case of success, non-zero otherwise
+ */
+static int ufshcd_read_desc_length(struct ufs_hba *hba,
+ enum desc_idn desc_id,
+ int desc_index,
+ int *desc_length)
+{
+ int ret;
+ u8 header[QUERY_DESC_HDR_SIZE];
+ int header_len = QUERY_DESC_HDR_SIZE;
+
+ if (desc_id >= QUERY_DESC_IDN_MAX)
+ return -EINVAL;
+
+ ret = ufshcd_query_descriptor_retry(hba, UPIU_QUERY_OPCODE_READ_DESC,
+ desc_id, desc_index, 0, header,
+ &header_len);
+
+ if (ret) {
+ dev_err(hba->dev, "%s: Failed to get descriptor header id %d",
+ __func__, desc_id);
+ return ret;
+ } else if (desc_id != header[QUERY_DESC_DESC_TYPE_OFFSET]) {
+ dev_warn(hba->dev, "%s: descriptor header id %d and desc_id %d mismatch",
+ __func__, header[QUERY_DESC_DESC_TYPE_OFFSET],
+ desc_id);
+ ret = -EINVAL;
+ }
+
+ *desc_length = header[QUERY_DESC_LENGTH_OFFSET];
+ return ret;
+
+}
+
+/**
+ * ufshcd_map_desc_id_to_length - map descriptor IDN to its length
+ * @hba: Pointer to adapter instance
+ * @desc_id: descriptor idn value
+ * @desc_len: mapped desc length (out)
+ *
+ * Return 0 in case of success, non-zero otherwise
+ */
+int ufshcd_map_desc_id_to_length(struct ufs_hba *hba,
+ enum desc_idn desc_id, int *desc_len)
+{
+ switch (desc_id) {
+ case QUERY_DESC_IDN_DEVICE:
+ *desc_len = hba->desc_size.dev_desc;
+ break;
+ case QUERY_DESC_IDN_POWER:
+ *desc_len = hba->desc_size.pwr_desc;
+ break;
+ case QUERY_DESC_IDN_GEOMETRY:
+ *desc_len = hba->desc_size.geom_desc;
+ break;
+ case QUERY_DESC_IDN_CONFIGURATION:
+ *desc_len = hba->desc_size.conf_desc;
+ break;
+ case QUERY_DESC_IDN_UNIT:
+ *desc_len = hba->desc_size.unit_desc;
+ break;
+ case QUERY_DESC_IDN_INTERCONNECT:
+ *desc_len = hba->desc_size.interc_desc;
+ break;
+ case QUERY_DESC_IDN_STRING:
+ *desc_len = QUERY_DESC_MAX_SIZE;
+ break;
+ case QUERY_DESC_IDN_RFU_0:
+ case QUERY_DESC_IDN_RFU_1:
+ *desc_len = 0;
+ break;
+ default:
+ *desc_len = 0;
+ return -EINVAL;
+ }
+ return 0;
+}
+EXPORT_SYMBOL(ufshcd_map_desc_id_to_length);
+
+/**
* ufshcd_read_desc_param - read the specified descriptor parameter
* @hba: Pointer to adapter instance
* @desc_id: descriptor idn value
@@ -2951,42 +3024,49 @@ static int ufshcd_query_descriptor_retry(struct ufs_hba *hba,
static int ufshcd_read_desc_param(struct ufs_hba *hba,
enum desc_idn desc_id,
int desc_index,
- u32 param_offset,
+ u8 param_offset,
u8 *param_read_buf,
- u32 param_size)
+ u8 param_size)
{
int ret;
u8 *desc_buf;
- u32 buff_len;
+ int buff_len;
bool is_kmalloc = true;
- /* safety checks */
- if (desc_id >= QUERY_DESC_IDN_MAX)
+ /* Safety check */
+ if (desc_id >= QUERY_DESC_IDN_MAX || !param_size)
return -EINVAL;
- buff_len = ufs_query_desc_max_size[desc_id];
- if ((param_offset + param_size) > buff_len)
- return -EINVAL;
+ /* Get the max length of descriptor from structure filled up at probe
+ * time.
+ */
+ ret = ufshcd_map_desc_id_to_length(hba, desc_id, &buff_len);
- if (!param_offset && (param_size == buff_len)) {
- /* memory space already available to hold full descriptor */
- desc_buf = param_read_buf;
- is_kmalloc = false;
- } else {
- /* allocate memory to hold full descriptor */
+ /* Sanity checks */
+ if (ret || !buff_len) {
+ dev_err(hba->dev, "%s: Failed to get full descriptor length",
+ __func__);
+ return ret;
+ }
+
+ /* Check whether we need temp memory */
+ if (param_offset != 0 || param_size < buff_len) {
desc_buf = kmalloc(buff_len, GFP_KERNEL);
if (!desc_buf)
return -ENOMEM;
+ } else {
+ desc_buf = param_read_buf;
+ is_kmalloc = false;
}
+ /* Request for full descriptor */
ret = ufshcd_query_descriptor_retry(hba, UPIU_QUERY_OPCODE_READ_DESC,
- desc_id, desc_index, 0, desc_buf,
- &buff_len);
+ desc_id, desc_index, 0,
+ desc_buf, &buff_len);
if (ret) {
dev_err(hba->dev, "%s: Failed reading descriptor. desc_id %d, desc_index %d, param_offset %d, ret %d",
__func__, desc_id, desc_index, param_offset, ret);
-
goto out;
}
@@ -2998,25 +3078,9 @@ static int ufshcd_read_desc_param(struct ufs_hba *hba,
goto out;
}
- /*
- * While reading variable size descriptors (like string descriptor),
- * some UFS devices may report the "LENGTH" (field in "Transaction
- * Specific fields" of Query Response UPIU) same as what was requested
- * in Query Request UPIU instead of reporting the actual size of the
- * variable size descriptor.
- * Although it's safe to ignore the "LENGTH" field for variable size
- * descriptors as we can always derive the length of the descriptor from
- * the descriptor header fields. Hence this change impose the length
- * match check only for fixed size descriptors (for which we always
- * request the correct size as part of Query Request UPIU).
- */
- if ((desc_id != QUERY_DESC_IDN_STRING) &&
- (buff_len != desc_buf[QUERY_DESC_LENGTH_OFFSET])) {
- dev_err(hba->dev, "%s: desc_buf length mismatch: buff_len %d, buff_len(desc_header) %d",
- __func__, buff_len, desc_buf[QUERY_DESC_LENGTH_OFFSET]);
- ret = -EINVAL;
- goto out;
- }
+ /* Check wherher we will not copy more data, than available */
+ if (is_kmalloc && param_size > buff_len)
+ param_size = buff_len;
if (is_kmalloc)
memcpy(param_read_buf, &desc_buf[param_offset], param_size);
@@ -4598,8 +4662,6 @@ static void __ufshcd_transfer_req_compl(struct ufs_hba *hba,
}
if (ufshcd_is_clkscaling_supported(hba))
hba->clk_scaling.active_reqs--;
- if (ufshcd_is_clkscaling_supported(hba))
- hba->clk_scaling.active_reqs--;
}
/* clear corresponding bits of completed commands */
@@ -5919,8 +5981,8 @@ static int ufshcd_set_icc_levels_attr(struct ufs_hba *hba, u32 icc_level)
static void ufshcd_init_icc_levels(struct ufs_hba *hba)
{
int ret;
- int buff_len = QUERY_DESC_POWER_MAX_SIZE;
- u8 desc_buf[QUERY_DESC_POWER_MAX_SIZE];
+ int buff_len = hba->desc_size.pwr_desc;
+ u8 desc_buf[hba->desc_size.pwr_desc];
ret = ufshcd_read_power_desc(hba, desc_buf, buff_len);
if (ret) {
@@ -6017,11 +6079,10 @@ static int ufs_get_device_desc(struct ufs_hba *hba,
{
int err;
u8 model_index;
- u8 str_desc_buf[QUERY_DESC_STRING_MAX_SIZE + 1] = {0};
- u8 desc_buf[QUERY_DESC_DEVICE_MAX_SIZE];
+ u8 str_desc_buf[QUERY_DESC_MAX_SIZE + 1] = {0};
+ u8 desc_buf[hba->desc_size.dev_desc];
- err = ufshcd_read_device_desc(hba, desc_buf,
- QUERY_DESC_DEVICE_MAX_SIZE);
+ err = ufshcd_read_device_desc(hba, desc_buf, hba->desc_size.dev_desc);
if (err) {
dev_err(hba->dev, "%s: Failed reading Device Desc. err = %d\n",
__func__, err);
@@ -6038,14 +6099,14 @@ static int ufs_get_device_desc(struct ufs_hba *hba,
model_index = desc_buf[DEVICE_DESC_PARAM_PRDCT_NAME];
err = ufshcd_read_string_desc(hba, model_index, str_desc_buf,
- QUERY_DESC_STRING_MAX_SIZE, ASCII_STD);
+ QUERY_DESC_MAX_SIZE, ASCII_STD);
if (err) {
dev_err(hba->dev, "%s: Failed reading Product Name. err = %d\n",
__func__, err);
goto out;
}
- str_desc_buf[QUERY_DESC_STRING_MAX_SIZE] = '\0';
+ str_desc_buf[QUERY_DESC_MAX_SIZE] = '\0';
strlcpy(dev_desc->model, (str_desc_buf + QUERY_DESC_HDR_SIZE),
min_t(u8, str_desc_buf[QUERY_DESC_LENGTH_OFFSET],
MAX_MODEL_LEN));
@@ -6251,6 +6312,51 @@ static void ufshcd_clear_dbg_ufs_stats(struct ufs_hba *hba)
hba->req_abort_count = 0;
}
+static void ufshcd_init_desc_sizes(struct ufs_hba *hba)
+{
+ int err;
+
+ err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_DEVICE, 0,
+ &hba->desc_size.dev_desc);
+ if (err)
+ hba->desc_size.dev_desc = QUERY_DESC_DEVICE_DEF_SIZE;
+
+ err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_POWER, 0,
+ &hba->desc_size.pwr_desc);
+ if (err)
+ hba->desc_size.pwr_desc = QUERY_DESC_POWER_DEF_SIZE;
+
+ err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_INTERCONNECT, 0,
+ &hba->desc_size.interc_desc);
+ if (err)
+ hba->desc_size.interc_desc = QUERY_DESC_INTERCONNECT_DEF_SIZE;
+
+ err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_CONFIGURATION, 0,
+ &hba->desc_size.conf_desc);
+ if (err)
+ hba->desc_size.conf_desc = QUERY_DESC_CONFIGURATION_DEF_SIZE;
+
+ err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_UNIT, 0,
+ &hba->desc_size.unit_desc);
+ if (err)
+ hba->desc_size.unit_desc = QUERY_DESC_UNIT_DEF_SIZE;
+
+ err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_GEOMETRY, 0,
+ &hba->desc_size.geom_desc);
+ if (err)
+ hba->desc_size.geom_desc = QUERY_DESC_GEOMETRY_DEF_SIZE;
+}
+
+static void ufshcd_def_desc_sizes(struct ufs_hba *hba)
+{
+ hba->desc_size.dev_desc = QUERY_DESC_DEVICE_DEF_SIZE;
+ hba->desc_size.pwr_desc = QUERY_DESC_POWER_DEF_SIZE;
+ hba->desc_size.interc_desc = QUERY_DESC_INTERCONNECT_DEF_SIZE;
+ hba->desc_size.conf_desc = QUERY_DESC_CONFIGURATION_DEF_SIZE;
+ hba->desc_size.unit_desc = QUERY_DESC_UNIT_DEF_SIZE;
+ hba->desc_size.geom_desc = QUERY_DESC_GEOMETRY_DEF_SIZE;
+}
+
/**
* ufshcd_probe_hba - probe hba to detect device and initialize
* @hba: per-adapter instance
@@ -6285,6 +6391,9 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
if (ret)
goto out;
+ /* Init check for device descriptor sizes */
+ ufshcd_init_desc_sizes(hba);
+
ret = ufs_get_device_desc(hba, &card);
if (ret) {
dev_err(hba->dev, "%s: Failed getting device info. err = %d\n",
@@ -6320,6 +6429,7 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
/* set the state as operational after switching to desired gear */
hba->ufshcd_state = UFSHCD_STATE_OPERATIONAL;
+
/*
* If we are in error handling context or in power management callbacks
* context, no need to scan the host
@@ -7530,7 +7640,7 @@ static inline ssize_t ufshcd_pm_lvl_store(struct device *dev,
if (kstrtoul(buf, 0, &value))
return -EINVAL;
- if ((value < UFS_PM_LVL_0) || (value >= UFS_PM_LVL_MAX))
+ if (value >= UFS_PM_LVL_MAX)
return -EINVAL;
spin_lock_irqsave(hba->host->host_lock, flags);
@@ -7774,6 +7884,9 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
hba->mmio_base = mmio_base;
hba->irq = irq;
+ /* Set descriptor lengths to specification defaults */
+ ufshcd_def_desc_sizes(hba);
+
err = ufshcd_hba_init(hba);
if (err)
goto out_error;
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index 7630600..cdc8bd0 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -220,6 +220,15 @@ struct ufs_dev_cmd {
struct ufs_query query;
};
+struct ufs_desc_size {
+ int dev_desc;
+ int pwr_desc;
+ int geom_desc;
+ int interc_desc;
+ int unit_desc;
+ int conf_desc;
+};
+
/**
* struct ufs_clk_info - UFS clock related info
* @list: list headed by hba->clk_list_head
@@ -483,6 +492,7 @@ struct ufs_stats {
* @clk_list_head: UFS host controller clocks list node head
* @pwr_info: holds current power mode
* @max_pwr_info: keeps the device max valid pwm
+ * @desc_size: descriptor sizes reported by device
* @urgent_bkops_lvl: keeps track of urgent bkops level for device
* @is_urgent_bkops_lvl_checked: keeps track if the urgent bkops level for
* device is known or not.
@@ -666,6 +676,7 @@ struct ufs_hba {
bool is_urgent_bkops_lvl_checked;
struct rw_semaphore clk_scaling_lock;
+ struct ufs_desc_size desc_size;
};
/* Returns true if clocks can be gated. Otherwise false */
@@ -832,6 +843,10 @@ int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode,
enum flag_idn idn, bool *flag_res);
int ufshcd_hold(struct ufs_hba *hba, bool async);
void ufshcd_release(struct ufs_hba *hba);
+
+int ufshcd_map_desc_id_to_length(struct ufs_hba *hba, enum desc_idn desc_id,
+ int *desc_length);
+
u32 ufshcd_get_local_unipro_ver(struct ufs_hba *hba);
/* Wrapper functions for safely calling variant operations */
diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c
index ef474a7..c374e3b 100644
--- a/drivers/scsi/vmw_pvscsi.c
+++ b/drivers/scsi/vmw_pvscsi.c
@@ -1487,7 +1487,7 @@ static int pvscsi_probe(struct pci_dev *pdev, const struct pci_device_id *id)
irq_flag &= ~PCI_IRQ_MSI;
error = pci_alloc_irq_vectors(adapter->dev, 1, 1, irq_flag);
- if (error)
+ if (error < 0)
goto out_reset_adapter;
adapter->use_req_threshold = pvscsi_setup_req_threshold(adapter, true);
diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig
index 78b1bb7..9fca977 100644
--- a/drivers/soc/qcom/Kconfig
+++ b/drivers/soc/qcom/Kconfig
@@ -33,17 +33,10 @@
The driver provides an interface to items in a heap shared among all
processors in a Qualcomm platform.
-config QCOM_SMD
- tristate "Qualcomm Shared Memory Driver (SMD)"
- depends on QCOM_SMEM
- help
- Say y here to enable support for the Qualcomm Shared Memory Driver
- providing communication channels to remote processors in Qualcomm
- platforms.
-
config QCOM_SMD_RPM
tristate "Qualcomm Resource Power Manager (RPM) over SMD"
- depends on QCOM_SMD && OF
+ depends on ARCH_QCOM
+ depends on RPMSG && OF
help
If you say yes to this option, support will be included for the
Resource Power Manager system found in the Qualcomm 8974 based
@@ -76,7 +69,8 @@
config QCOM_WCNSS_CTRL
tristate "Qualcomm WCNSS control driver"
- depends on QCOM_SMD
+ depends on ARCH_QCOM
+ depends on RPMSG
help
Client driver for the WCNSS_CTRL SMD channel, used to download nv
firmware to a newly booted WCNSS chip.
diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile
index 1f30260..414f0de 100644
--- a/drivers/soc/qcom/Makefile
+++ b/drivers/soc/qcom/Makefile
@@ -1,7 +1,6 @@
obj-$(CONFIG_QCOM_GSBI) += qcom_gsbi.o
obj-$(CONFIG_QCOM_MDT_LOADER) += mdt_loader.o
obj-$(CONFIG_QCOM_PM) += spm.o
-obj-$(CONFIG_QCOM_SMD) += smd.o
obj-$(CONFIG_QCOM_SMD_RPM) += smd-rpm.o
obj-$(CONFIG_QCOM_SMEM) += smem.o
obj-$(CONFIG_QCOM_SMEM_STATE) += smem_state.o
diff --git a/drivers/soc/qcom/smd-rpm.c b/drivers/soc/qcom/smd-rpm.c
index 6609d7e..c234675 100644
--- a/drivers/soc/qcom/smd-rpm.c
+++ b/drivers/soc/qcom/smd-rpm.c
@@ -19,7 +19,7 @@
#include <linux/interrupt.h>
#include <linux/slab.h>
-#include <linux/soc/qcom/smd.h>
+#include <linux/rpmsg.h>
#include <linux/soc/qcom/smd-rpm.h>
#define RPM_REQUEST_TIMEOUT (5 * HZ)
@@ -32,7 +32,7 @@
* @ack_status: result of the rpm request
*/
struct qcom_smd_rpm {
- struct qcom_smd_channel *rpm_channel;
+ struct rpmsg_endpoint *rpm_channel;
struct device *dev;
struct completion ack;
@@ -133,7 +133,7 @@ int qcom_rpm_smd_write(struct qcom_smd_rpm *rpm,
pkt->req.data_len = cpu_to_le32(count);
memcpy(pkt->payload, buf, count);
- ret = qcom_smd_send(rpm->rpm_channel, pkt, size);
+ ret = rpmsg_send(rpm->rpm_channel, pkt, size);
if (ret)
goto out;
@@ -150,14 +150,16 @@ int qcom_rpm_smd_write(struct qcom_smd_rpm *rpm,
}
EXPORT_SYMBOL(qcom_rpm_smd_write);
-static int qcom_smd_rpm_callback(struct qcom_smd_channel *channel,
- const void *data,
- size_t count)
+static int qcom_smd_rpm_callback(struct rpmsg_device *rpdev,
+ void *data,
+ int count,
+ void *priv,
+ u32 addr)
{
const struct qcom_rpm_header *hdr = data;
size_t hdr_length = le32_to_cpu(hdr->length);
const struct qcom_rpm_message *msg;
- struct qcom_smd_rpm *rpm = qcom_smd_get_drvdata(channel);
+ struct qcom_smd_rpm *rpm = dev_get_drvdata(&rpdev->dev);
const u8 *buf = data + sizeof(struct qcom_rpm_header);
const u8 *end = buf + hdr_length;
char msgbuf[32];
@@ -196,59 +198,57 @@ static int qcom_smd_rpm_callback(struct qcom_smd_channel *channel,
return 0;
}
-static int qcom_smd_rpm_probe(struct qcom_smd_device *sdev)
+static int qcom_smd_rpm_probe(struct rpmsg_device *rpdev)
{
struct qcom_smd_rpm *rpm;
- rpm = devm_kzalloc(&sdev->dev, sizeof(*rpm), GFP_KERNEL);
+ rpm = devm_kzalloc(&rpdev->dev, sizeof(*rpm), GFP_KERNEL);
if (!rpm)
return -ENOMEM;
mutex_init(&rpm->lock);
init_completion(&rpm->ack);
- rpm->dev = &sdev->dev;
- rpm->rpm_channel = sdev->channel;
- qcom_smd_set_drvdata(sdev->channel, rpm);
+ rpm->dev = &rpdev->dev;
+ rpm->rpm_channel = rpdev->ept;
+ dev_set_drvdata(&rpdev->dev, rpm);
- dev_set_drvdata(&sdev->dev, rpm);
-
- return of_platform_populate(sdev->dev.of_node, NULL, NULL, &sdev->dev);
+ return of_platform_populate(rpdev->dev.of_node, NULL, NULL, &rpdev->dev);
}
-static void qcom_smd_rpm_remove(struct qcom_smd_device *sdev)
+static void qcom_smd_rpm_remove(struct rpmsg_device *rpdev)
{
- of_platform_depopulate(&sdev->dev);
+ of_platform_depopulate(&rpdev->dev);
}
static const struct of_device_id qcom_smd_rpm_of_match[] = {
{ .compatible = "qcom,rpm-apq8084" },
{ .compatible = "qcom,rpm-msm8916" },
{ .compatible = "qcom,rpm-msm8974" },
+ { .compatible = "qcom,rpm-msm8996" },
{}
};
MODULE_DEVICE_TABLE(of, qcom_smd_rpm_of_match);
-static struct qcom_smd_driver qcom_smd_rpm_driver = {
+static struct rpmsg_driver qcom_smd_rpm_driver = {
.probe = qcom_smd_rpm_probe,
.remove = qcom_smd_rpm_remove,
.callback = qcom_smd_rpm_callback,
- .driver = {
+ .drv = {
.name = "qcom_smd_rpm",
- .owner = THIS_MODULE,
.of_match_table = qcom_smd_rpm_of_match,
},
};
static int __init qcom_smd_rpm_init(void)
{
- return qcom_smd_driver_register(&qcom_smd_rpm_driver);
+ return register_rpmsg_driver(&qcom_smd_rpm_driver);
}
arch_initcall(qcom_smd_rpm_init);
static void __exit qcom_smd_rpm_exit(void)
{
- qcom_smd_driver_unregister(&qcom_smd_rpm_driver);
+ unregister_rpmsg_driver(&qcom_smd_rpm_driver);
}
module_exit(qcom_smd_rpm_exit);
diff --git a/drivers/soc/qcom/smd.c b/drivers/soc/qcom/smd.c
deleted file mode 100644
index 322034a..0000000
--- a/drivers/soc/qcom/smd.c
+++ /dev/null
@@ -1,1560 +0,0 @@
-/*
- * Copyright (c) 2015, Sony Mobile Communications AB.
- * Copyright (c) 2012-2013, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- */
-
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/mfd/syscon.h>
-#include <linux/module.h>
-#include <linux/of_irq.h>
-#include <linux/of_platform.h>
-#include <linux/platform_device.h>
-#include <linux/regmap.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/soc/qcom/smd.h>
-#include <linux/soc/qcom/smem.h>
-#include <linux/wait.h>
-
-/*
- * The Qualcomm Shared Memory communication solution provides point-to-point
- * channels for clients to send and receive streaming or packet based data.
- *
- * Each channel consists of a control item (channel info) and a ring buffer
- * pair. The channel info carry information related to channel state, flow
- * control and the offsets within the ring buffer.
- *
- * All allocated channels are listed in an allocation table, identifying the
- * pair of items by name, type and remote processor.
- *
- * Upon creating a new channel the remote processor allocates channel info and
- * ring buffer items from the smem heap and populate the allocation table. An
- * interrupt is sent to the other end of the channel and a scan for new
- * channels should be done. A channel never goes away, it will only change
- * state.
- *
- * The remote processor signals it intent for bring up the communication
- * channel by setting the state of its end of the channel to "opening" and
- * sends out an interrupt. We detect this change and register a smd device to
- * consume the channel. Upon finding a consumer we finish the handshake and the
- * channel is up.
- *
- * Upon closing a channel, the remote processor will update the state of its
- * end of the channel and signal us, we will then unregister any attached
- * device and close our end of the channel.
- *
- * Devices attached to a channel can use the qcom_smd_send function to push
- * data to the channel, this is done by copying the data into the tx ring
- * buffer, updating the pointers in the channel info and signaling the remote
- * processor.
- *
- * The remote processor does the equivalent when it transfer data and upon
- * receiving the interrupt we check the channel info for new data and delivers
- * this to the attached device. If the device is not ready to receive the data
- * we leave it in the ring buffer for now.
- */
-
-struct smd_channel_info;
-struct smd_channel_info_pair;
-struct smd_channel_info_word;
-struct smd_channel_info_word_pair;
-
-#define SMD_ALLOC_TBL_COUNT 2
-#define SMD_ALLOC_TBL_SIZE 64
-
-/*
- * This lists the various smem heap items relevant for the allocation table and
- * smd channel entries.
- */
-static const struct {
- unsigned alloc_tbl_id;
- unsigned info_base_id;
- unsigned fifo_base_id;
-} smem_items[SMD_ALLOC_TBL_COUNT] = {
- {
- .alloc_tbl_id = 13,
- .info_base_id = 14,
- .fifo_base_id = 338
- },
- {
- .alloc_tbl_id = 266,
- .info_base_id = 138,
- .fifo_base_id = 202,
- },
-};
-
-/**
- * struct qcom_smd_edge - representing a remote processor
- * @dev: device for this edge
- * @of_node: of_node handle for information related to this edge
- * @edge_id: identifier of this edge
- * @remote_pid: identifier of remote processor
- * @irq: interrupt for signals on this edge
- * @ipc_regmap: regmap handle holding the outgoing ipc register
- * @ipc_offset: offset within @ipc_regmap of the register for ipc
- * @ipc_bit: bit in the register at @ipc_offset of @ipc_regmap
- * @channels: list of all channels detected on this edge
- * @channels_lock: guard for modifications of @channels
- * @allocated: array of bitmaps representing already allocated channels
- * @smem_available: last available amount of smem triggering a channel scan
- * @scan_work: work item for discovering new channels
- * @state_work: work item for edge state changes
- */
-struct qcom_smd_edge {
- struct device dev;
-
- struct device_node *of_node;
- unsigned edge_id;
- unsigned remote_pid;
-
- int irq;
-
- struct regmap *ipc_regmap;
- int ipc_offset;
- int ipc_bit;
-
- struct list_head channels;
- spinlock_t channels_lock;
-
- DECLARE_BITMAP(allocated[SMD_ALLOC_TBL_COUNT], SMD_ALLOC_TBL_SIZE);
-
- unsigned smem_available;
-
- wait_queue_head_t new_channel_event;
-
- struct work_struct scan_work;
- struct work_struct state_work;
-};
-
-#define to_smd_edge(d) container_of(d, struct qcom_smd_edge, dev)
-
-/*
- * SMD channel states.
- */
-enum smd_channel_state {
- SMD_CHANNEL_CLOSED,
- SMD_CHANNEL_OPENING,
- SMD_CHANNEL_OPENED,
- SMD_CHANNEL_FLUSHING,
- SMD_CHANNEL_CLOSING,
- SMD_CHANNEL_RESET,
- SMD_CHANNEL_RESET_OPENING
-};
-
-/**
- * struct qcom_smd_channel - smd channel struct
- * @edge: qcom_smd_edge this channel is living on
- * @qsdev: reference to a associated smd client device
- * @name: name of the channel
- * @state: local state of the channel
- * @remote_state: remote state of the channel
- * @info: byte aligned outgoing/incoming channel info
- * @info_word: word aligned outgoing/incoming channel info
- * @tx_lock: lock to make writes to the channel mutually exclusive
- * @fblockread_event: wakeup event tied to tx fBLOCKREADINTR
- * @tx_fifo: pointer to the outgoing ring buffer
- * @rx_fifo: pointer to the incoming ring buffer
- * @fifo_size: size of each ring buffer
- * @bounce_buffer: bounce buffer for reading wrapped packets
- * @cb: callback function registered for this channel
- * @recv_lock: guard for rx info modifications and cb pointer
- * @pkt_size: size of the currently handled packet
- * @list: lite entry for @channels in qcom_smd_edge
- */
-struct qcom_smd_channel {
- struct qcom_smd_edge *edge;
-
- struct qcom_smd_device *qsdev;
-
- char *name;
- enum smd_channel_state state;
- enum smd_channel_state remote_state;
-
- struct smd_channel_info_pair *info;
- struct smd_channel_info_word_pair *info_word;
-
- struct mutex tx_lock;
- wait_queue_head_t fblockread_event;
-
- void *tx_fifo;
- void *rx_fifo;
- int fifo_size;
-
- void *bounce_buffer;
- qcom_smd_cb_t cb;
-
- spinlock_t recv_lock;
-
- int pkt_size;
-
- void *drvdata;
-
- struct list_head list;
-};
-
-/*
- * Format of the smd_info smem items, for byte aligned channels.
- */
-struct smd_channel_info {
- __le32 state;
- u8 fDSR;
- u8 fCTS;
- u8 fCD;
- u8 fRI;
- u8 fHEAD;
- u8 fTAIL;
- u8 fSTATE;
- u8 fBLOCKREADINTR;
- __le32 tail;
- __le32 head;
-};
-
-struct smd_channel_info_pair {
- struct smd_channel_info tx;
- struct smd_channel_info rx;
-};
-
-/*
- * Format of the smd_info smem items, for word aligned channels.
- */
-struct smd_channel_info_word {
- __le32 state;
- __le32 fDSR;
- __le32 fCTS;
- __le32 fCD;
- __le32 fRI;
- __le32 fHEAD;
- __le32 fTAIL;
- __le32 fSTATE;
- __le32 fBLOCKREADINTR;
- __le32 tail;
- __le32 head;
-};
-
-struct smd_channel_info_word_pair {
- struct smd_channel_info_word tx;
- struct smd_channel_info_word rx;
-};
-
-#define GET_RX_CHANNEL_FLAG(channel, param) \
- ({ \
- BUILD_BUG_ON(sizeof(channel->info->rx.param) != sizeof(u8)); \
- channel->info_word ? \
- le32_to_cpu(channel->info_word->rx.param) : \
- channel->info->rx.param; \
- })
-
-#define GET_RX_CHANNEL_INFO(channel, param) \
- ({ \
- BUILD_BUG_ON(sizeof(channel->info->rx.param) != sizeof(u32)); \
- le32_to_cpu(channel->info_word ? \
- channel->info_word->rx.param : \
- channel->info->rx.param); \
- })
-
-#define SET_RX_CHANNEL_FLAG(channel, param, value) \
- ({ \
- BUILD_BUG_ON(sizeof(channel->info->rx.param) != sizeof(u8)); \
- if (channel->info_word) \
- channel->info_word->rx.param = cpu_to_le32(value); \
- else \
- channel->info->rx.param = value; \
- })
-
-#define SET_RX_CHANNEL_INFO(channel, param, value) \
- ({ \
- BUILD_BUG_ON(sizeof(channel->info->rx.param) != sizeof(u32)); \
- if (channel->info_word) \
- channel->info_word->rx.param = cpu_to_le32(value); \
- else \
- channel->info->rx.param = cpu_to_le32(value); \
- })
-
-#define GET_TX_CHANNEL_FLAG(channel, param) \
- ({ \
- BUILD_BUG_ON(sizeof(channel->info->tx.param) != sizeof(u8)); \
- channel->info_word ? \
- le32_to_cpu(channel->info_word->tx.param) : \
- channel->info->tx.param; \
- })
-
-#define GET_TX_CHANNEL_INFO(channel, param) \
- ({ \
- BUILD_BUG_ON(sizeof(channel->info->tx.param) != sizeof(u32)); \
- le32_to_cpu(channel->info_word ? \
- channel->info_word->tx.param : \
- channel->info->tx.param); \
- })
-
-#define SET_TX_CHANNEL_FLAG(channel, param, value) \
- ({ \
- BUILD_BUG_ON(sizeof(channel->info->tx.param) != sizeof(u8)); \
- if (channel->info_word) \
- channel->info_word->tx.param = cpu_to_le32(value); \
- else \
- channel->info->tx.param = value; \
- })
-
-#define SET_TX_CHANNEL_INFO(channel, param, value) \
- ({ \
- BUILD_BUG_ON(sizeof(channel->info->tx.param) != sizeof(u32)); \
- if (channel->info_word) \
- channel->info_word->tx.param = cpu_to_le32(value); \
- else \
- channel->info->tx.param = cpu_to_le32(value); \
- })
-
-/**
- * struct qcom_smd_alloc_entry - channel allocation entry
- * @name: channel name
- * @cid: channel index
- * @flags: channel flags and edge id
- * @ref_count: reference count of the channel
- */
-struct qcom_smd_alloc_entry {
- u8 name[20];
- __le32 cid;
- __le32 flags;
- __le32 ref_count;
-} __packed;
-
-#define SMD_CHANNEL_FLAGS_EDGE_MASK 0xff
-#define SMD_CHANNEL_FLAGS_STREAM BIT(8)
-#define SMD_CHANNEL_FLAGS_PACKET BIT(9)
-
-/*
- * Each smd packet contains a 20 byte header, with the first 4 being the length
- * of the packet.
- */
-#define SMD_PACKET_HEADER_LEN 20
-
-/*
- * Signal the remote processor associated with 'channel'.
- */
-static void qcom_smd_signal_channel(struct qcom_smd_channel *channel)
-{
- struct qcom_smd_edge *edge = channel->edge;
-
- regmap_write(edge->ipc_regmap, edge->ipc_offset, BIT(edge->ipc_bit));
-}
-
-/*
- * Initialize the tx channel info
- */
-static void qcom_smd_channel_reset(struct qcom_smd_channel *channel)
-{
- SET_TX_CHANNEL_INFO(channel, state, SMD_CHANNEL_CLOSED);
- SET_TX_CHANNEL_FLAG(channel, fDSR, 0);
- SET_TX_CHANNEL_FLAG(channel, fCTS, 0);
- SET_TX_CHANNEL_FLAG(channel, fCD, 0);
- SET_TX_CHANNEL_FLAG(channel, fRI, 0);
- SET_TX_CHANNEL_FLAG(channel, fHEAD, 0);
- SET_TX_CHANNEL_FLAG(channel, fTAIL, 0);
- SET_TX_CHANNEL_FLAG(channel, fSTATE, 1);
- SET_TX_CHANNEL_FLAG(channel, fBLOCKREADINTR, 1);
- SET_TX_CHANNEL_INFO(channel, head, 0);
- SET_RX_CHANNEL_INFO(channel, tail, 0);
-
- qcom_smd_signal_channel(channel);
-
- channel->state = SMD_CHANNEL_CLOSED;
- channel->pkt_size = 0;
-}
-
-/*
- * Set the callback for a channel, with appropriate locking
- */
-static void qcom_smd_channel_set_callback(struct qcom_smd_channel *channel,
- qcom_smd_cb_t cb)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&channel->recv_lock, flags);
- channel->cb = cb;
- spin_unlock_irqrestore(&channel->recv_lock, flags);
-};
-
-/*
- * Calculate the amount of data available in the rx fifo
- */
-static size_t qcom_smd_channel_get_rx_avail(struct qcom_smd_channel *channel)
-{
- unsigned head;
- unsigned tail;
-
- head = GET_RX_CHANNEL_INFO(channel, head);
- tail = GET_RX_CHANNEL_INFO(channel, tail);
-
- return (head - tail) & (channel->fifo_size - 1);
-}
-
-/*
- * Set tx channel state and inform the remote processor
- */
-static void qcom_smd_channel_set_state(struct qcom_smd_channel *channel,
- int state)
-{
- struct qcom_smd_edge *edge = channel->edge;
- bool is_open = state == SMD_CHANNEL_OPENED;
-
- if (channel->state == state)
- return;
-
- dev_dbg(&edge->dev, "set_state(%s, %d)\n", channel->name, state);
-
- SET_TX_CHANNEL_FLAG(channel, fDSR, is_open);
- SET_TX_CHANNEL_FLAG(channel, fCTS, is_open);
- SET_TX_CHANNEL_FLAG(channel, fCD, is_open);
-
- SET_TX_CHANNEL_INFO(channel, state, state);
- SET_TX_CHANNEL_FLAG(channel, fSTATE, 1);
-
- channel->state = state;
- qcom_smd_signal_channel(channel);
-}
-
-/*
- * Copy count bytes of data using 32bit accesses, if that's required.
- */
-static void smd_copy_to_fifo(void __iomem *dst,
- const void *src,
- size_t count,
- bool word_aligned)
-{
- if (word_aligned) {
- __iowrite32_copy(dst, src, count / sizeof(u32));
- } else {
- memcpy_toio(dst, src, count);
- }
-}
-
-/*
- * Copy count bytes of data using 32bit accesses, if that is required.
- */
-static void smd_copy_from_fifo(void *dst,
- const void __iomem *src,
- size_t count,
- bool word_aligned)
-{
- if (word_aligned) {
- __ioread32_copy(dst, src, count / sizeof(u32));
- } else {
- memcpy_fromio(dst, src, count);
- }
-}
-
-/*
- * Read count bytes of data from the rx fifo into buf, but don't advance the
- * tail.
- */
-static size_t qcom_smd_channel_peek(struct qcom_smd_channel *channel,
- void *buf, size_t count)
-{
- bool word_aligned;
- unsigned tail;
- size_t len;
-
- word_aligned = channel->info_word;
- tail = GET_RX_CHANNEL_INFO(channel, tail);
-
- len = min_t(size_t, count, channel->fifo_size - tail);
- if (len) {
- smd_copy_from_fifo(buf,
- channel->rx_fifo + tail,
- len,
- word_aligned);
- }
-
- if (len != count) {
- smd_copy_from_fifo(buf + len,
- channel->rx_fifo,
- count - len,
- word_aligned);
- }
-
- return count;
-}
-
-/*
- * Advance the rx tail by count bytes.
- */
-static void qcom_smd_channel_advance(struct qcom_smd_channel *channel,
- size_t count)
-{
- unsigned tail;
-
- tail = GET_RX_CHANNEL_INFO(channel, tail);
- tail += count;
- tail &= (channel->fifo_size - 1);
- SET_RX_CHANNEL_INFO(channel, tail, tail);
-}
-
-/*
- * Read out a single packet from the rx fifo and deliver it to the device
- */
-static int qcom_smd_channel_recv_single(struct qcom_smd_channel *channel)
-{
- unsigned tail;
- size_t len;
- void *ptr;
- int ret;
-
- if (!channel->cb)
- return 0;
-
- tail = GET_RX_CHANNEL_INFO(channel, tail);
-
- /* Use bounce buffer if the data wraps */
- if (tail + channel->pkt_size >= channel->fifo_size) {
- ptr = channel->bounce_buffer;
- len = qcom_smd_channel_peek(channel, ptr, channel->pkt_size);
- } else {
- ptr = channel->rx_fifo + tail;
- len = channel->pkt_size;
- }
-
- ret = channel->cb(channel, ptr, len);
- if (ret < 0)
- return ret;
-
- /* Only forward the tail if the client consumed the data */
- qcom_smd_channel_advance(channel, len);
-
- channel->pkt_size = 0;
-
- return 0;
-}
-
-/*
- * Per channel interrupt handling
- */
-static bool qcom_smd_channel_intr(struct qcom_smd_channel *channel)
-{
- bool need_state_scan = false;
- int remote_state;
- __le32 pktlen;
- int avail;
- int ret;
-
- /* Handle state changes */
- remote_state = GET_RX_CHANNEL_INFO(channel, state);
- if (remote_state != channel->remote_state) {
- channel->remote_state = remote_state;
- need_state_scan = true;
- }
- /* Indicate that we have seen any state change */
- SET_RX_CHANNEL_FLAG(channel, fSTATE, 0);
-
- /* Signal waiting qcom_smd_send() about the interrupt */
- if (!GET_TX_CHANNEL_FLAG(channel, fBLOCKREADINTR))
- wake_up_interruptible(&channel->fblockread_event);
-
- /* Don't consume any data until we've opened the channel */
- if (channel->state != SMD_CHANNEL_OPENED)
- goto out;
-
- /* Indicate that we've seen the new data */
- SET_RX_CHANNEL_FLAG(channel, fHEAD, 0);
-
- /* Consume data */
- for (;;) {
- avail = qcom_smd_channel_get_rx_avail(channel);
-
- if (!channel->pkt_size && avail >= SMD_PACKET_HEADER_LEN) {
- qcom_smd_channel_peek(channel, &pktlen, sizeof(pktlen));
- qcom_smd_channel_advance(channel, SMD_PACKET_HEADER_LEN);
- channel->pkt_size = le32_to_cpu(pktlen);
- } else if (channel->pkt_size && avail >= channel->pkt_size) {
- ret = qcom_smd_channel_recv_single(channel);
- if (ret)
- break;
- } else {
- break;
- }
- }
-
- /* Indicate that we have seen and updated tail */
- SET_RX_CHANNEL_FLAG(channel, fTAIL, 1);
-
- /* Signal the remote that we've consumed the data (if requested) */
- if (!GET_RX_CHANNEL_FLAG(channel, fBLOCKREADINTR)) {
- /* Ensure ordering of channel info updates */
- wmb();
-
- qcom_smd_signal_channel(channel);
- }
-
-out:
- return need_state_scan;
-}
-
-/*
- * The edge interrupts are triggered by the remote processor on state changes,
- * channel info updates or when new channels are created.
- */
-static irqreturn_t qcom_smd_edge_intr(int irq, void *data)
-{
- struct qcom_smd_edge *edge = data;
- struct qcom_smd_channel *channel;
- unsigned available;
- bool kick_scanner = false;
- bool kick_state = false;
-
- /*
- * Handle state changes or data on each of the channels on this edge
- */
- spin_lock(&edge->channels_lock);
- list_for_each_entry(channel, &edge->channels, list) {
- spin_lock(&channel->recv_lock);
- kick_state |= qcom_smd_channel_intr(channel);
- spin_unlock(&channel->recv_lock);
- }
- spin_unlock(&edge->channels_lock);
-
- /*
- * Creating a new channel requires allocating an smem entry, so we only
- * have to scan if the amount of available space in smem have changed
- * since last scan.
- */
- available = qcom_smem_get_free_space(edge->remote_pid);
- if (available != edge->smem_available) {
- edge->smem_available = available;
- kick_scanner = true;
- }
-
- if (kick_scanner)
- schedule_work(&edge->scan_work);
- if (kick_state)
- schedule_work(&edge->state_work);
-
- return IRQ_HANDLED;
-}
-
-/*
- * Delivers any outstanding packets in the rx fifo, can be used after probe of
- * the clients to deliver any packets that wasn't delivered before the client
- * was setup.
- */
-static void qcom_smd_channel_resume(struct qcom_smd_channel *channel)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&channel->recv_lock, flags);
- qcom_smd_channel_intr(channel);
- spin_unlock_irqrestore(&channel->recv_lock, flags);
-}
-
-/*
- * Calculate how much space is available in the tx fifo.
- */
-static size_t qcom_smd_get_tx_avail(struct qcom_smd_channel *channel)
-{
- unsigned head;
- unsigned tail;
- unsigned mask = channel->fifo_size - 1;
-
- head = GET_TX_CHANNEL_INFO(channel, head);
- tail = GET_TX_CHANNEL_INFO(channel, tail);
-
- return mask - ((head - tail) & mask);
-}
-
-/*
- * Write count bytes of data into channel, possibly wrapping in the ring buffer
- */
-static int qcom_smd_write_fifo(struct qcom_smd_channel *channel,
- const void *data,
- size_t count)
-{
- bool word_aligned;
- unsigned head;
- size_t len;
-
- word_aligned = channel->info_word;
- head = GET_TX_CHANNEL_INFO(channel, head);
-
- len = min_t(size_t, count, channel->fifo_size - head);
- if (len) {
- smd_copy_to_fifo(channel->tx_fifo + head,
- data,
- len,
- word_aligned);
- }
-
- if (len != count) {
- smd_copy_to_fifo(channel->tx_fifo,
- data + len,
- count - len,
- word_aligned);
- }
-
- head += count;
- head &= (channel->fifo_size - 1);
- SET_TX_CHANNEL_INFO(channel, head, head);
-
- return count;
-}
-
-/**
- * qcom_smd_send - write data to smd channel
- * @channel: channel handle
- * @data: buffer of data to write
- * @len: number of bytes to write
- *
- * This is a blocking write of len bytes into the channel's tx ring buffer and
- * signal the remote end. It will sleep until there is enough space available
- * in the tx buffer, utilizing the fBLOCKREADINTR signaling mechanism to avoid
- * polling.
- */
-int qcom_smd_send(struct qcom_smd_channel *channel, const void *data, int len)
-{
- __le32 hdr[5] = { cpu_to_le32(len), };
- int tlen = sizeof(hdr) + len;
- int ret;
-
- /* Word aligned channels only accept word size aligned data */
- if (channel->info_word && len % 4)
- return -EINVAL;
-
- /* Reject packets that are too big */
- if (tlen >= channel->fifo_size)
- return -EINVAL;
-
- ret = mutex_lock_interruptible(&channel->tx_lock);
- if (ret)
- return ret;
-
- while (qcom_smd_get_tx_avail(channel) < tlen) {
- if (channel->state != SMD_CHANNEL_OPENED) {
- ret = -EPIPE;
- goto out;
- }
-
- SET_TX_CHANNEL_FLAG(channel, fBLOCKREADINTR, 0);
-
- ret = wait_event_interruptible(channel->fblockread_event,
- qcom_smd_get_tx_avail(channel) >= tlen ||
- channel->state != SMD_CHANNEL_OPENED);
- if (ret)
- goto out;
-
- SET_TX_CHANNEL_FLAG(channel, fBLOCKREADINTR, 1);
- }
-
- SET_TX_CHANNEL_FLAG(channel, fTAIL, 0);
-
- qcom_smd_write_fifo(channel, hdr, sizeof(hdr));
- qcom_smd_write_fifo(channel, data, len);
-
- SET_TX_CHANNEL_FLAG(channel, fHEAD, 1);
-
- /* Ensure ordering of channel info updates */
- wmb();
-
- qcom_smd_signal_channel(channel);
-
-out:
- mutex_unlock(&channel->tx_lock);
-
- return ret;
-}
-EXPORT_SYMBOL(qcom_smd_send);
-
-static struct qcom_smd_device *to_smd_device(struct device *dev)
-{
- return container_of(dev, struct qcom_smd_device, dev);
-}
-
-static struct qcom_smd_driver *to_smd_driver(struct device *dev)
-{
- struct qcom_smd_device *qsdev = to_smd_device(dev);
-
- return container_of(qsdev->dev.driver, struct qcom_smd_driver, driver);
-}
-
-static int qcom_smd_dev_match(struct device *dev, struct device_driver *drv)
-{
- struct qcom_smd_device *qsdev = to_smd_device(dev);
- struct qcom_smd_driver *qsdrv = container_of(drv, struct qcom_smd_driver, driver);
- const struct qcom_smd_id *match = qsdrv->smd_match_table;
- const char *name = qsdev->channel->name;
-
- if (match) {
- while (match->name[0]) {
- if (!strcmp(match->name, name))
- return 1;
- match++;
- }
- }
-
- return of_driver_match_device(dev, drv);
-}
-
-/*
- * Helper for opening a channel
- */
-static int qcom_smd_channel_open(struct qcom_smd_channel *channel,
- qcom_smd_cb_t cb)
-{
- size_t bb_size;
-
- /*
- * Packets are maximum 4k, but reduce if the fifo is smaller
- */
- bb_size = min(channel->fifo_size, SZ_4K);
- channel->bounce_buffer = kmalloc(bb_size, GFP_KERNEL);
- if (!channel->bounce_buffer)
- return -ENOMEM;
-
- qcom_smd_channel_set_callback(channel, cb);
- qcom_smd_channel_set_state(channel, SMD_CHANNEL_OPENING);
- qcom_smd_channel_set_state(channel, SMD_CHANNEL_OPENED);
-
- return 0;
-}
-
-/*
- * Helper for closing and resetting a channel
- */
-static void qcom_smd_channel_close(struct qcom_smd_channel *channel)
-{
- qcom_smd_channel_set_callback(channel, NULL);
-
- kfree(channel->bounce_buffer);
- channel->bounce_buffer = NULL;
-
- qcom_smd_channel_set_state(channel, SMD_CHANNEL_CLOSED);
- qcom_smd_channel_reset(channel);
-}
-
-/*
- * Probe the smd client.
- *
- * The remote side have indicated that it want the channel to be opened, so
- * complete the state handshake and probe our client driver.
- */
-static int qcom_smd_dev_probe(struct device *dev)
-{
- struct qcom_smd_device *qsdev = to_smd_device(dev);
- struct qcom_smd_driver *qsdrv = to_smd_driver(dev);
- struct qcom_smd_channel *channel = qsdev->channel;
- int ret;
-
- ret = qcom_smd_channel_open(channel, qsdrv->callback);
- if (ret)
- return ret;
-
- ret = qsdrv->probe(qsdev);
- if (ret)
- goto err;
-
- qcom_smd_channel_resume(channel);
-
- return 0;
-
-err:
- dev_err(&qsdev->dev, "probe failed\n");
-
- qcom_smd_channel_close(channel);
- return ret;
-}
-
-/*
- * Remove the smd client.
- *
- * The channel is going away, for some reason, so remove the smd client and
- * reset the channel state.
- */
-static int qcom_smd_dev_remove(struct device *dev)
-{
- struct qcom_smd_device *qsdev = to_smd_device(dev);
- struct qcom_smd_driver *qsdrv = to_smd_driver(dev);
- struct qcom_smd_channel *channel = qsdev->channel;
-
- qcom_smd_channel_set_state(channel, SMD_CHANNEL_CLOSING);
-
- /*
- * Make sure we don't race with the code receiving data.
- */
- qcom_smd_channel_set_callback(channel, NULL);
-
- /* Wake up any sleepers in qcom_smd_send() */
- wake_up_interruptible(&channel->fblockread_event);
-
- /*
- * We expect that the client might block in remove() waiting for any
- * outstanding calls to qcom_smd_send() to wake up and finish.
- */
- if (qsdrv->remove)
- qsdrv->remove(qsdev);
-
- /* The client is now gone, close the primary channel */
- qcom_smd_channel_close(channel);
- channel->qsdev = NULL;
-
- return 0;
-}
-
-static struct bus_type qcom_smd_bus = {
- .name = "qcom_smd",
- .match = qcom_smd_dev_match,
- .probe = qcom_smd_dev_probe,
- .remove = qcom_smd_dev_remove,
-};
-
-/*
- * Release function for the qcom_smd_device object.
- */
-static void qcom_smd_release_device(struct device *dev)
-{
- struct qcom_smd_device *qsdev = to_smd_device(dev);
-
- kfree(qsdev);
-}
-
-/*
- * Finds the device_node for the smd child interested in this channel.
- */
-static struct device_node *qcom_smd_match_channel(struct device_node *edge_node,
- const char *channel)
-{
- struct device_node *child;
- const char *name;
- const char *key;
- int ret;
-
- for_each_available_child_of_node(edge_node, child) {
- key = "qcom,smd-channels";
- ret = of_property_read_string(child, key, &name);
- if (ret)
- continue;
-
- if (strcmp(name, channel) == 0)
- return child;
- }
-
- return NULL;
-}
-
-/*
- * Create a smd client device for channel that is being opened.
- */
-static int qcom_smd_create_device(struct qcom_smd_channel *channel)
-{
- struct qcom_smd_device *qsdev;
- struct qcom_smd_edge *edge = channel->edge;
- struct device_node *node;
- int ret;
-
- if (channel->qsdev)
- return -EEXIST;
-
- dev_dbg(&edge->dev, "registering '%s'\n", channel->name);
-
- qsdev = kzalloc(sizeof(*qsdev), GFP_KERNEL);
- if (!qsdev)
- return -ENOMEM;
-
- node = qcom_smd_match_channel(edge->of_node, channel->name);
- dev_set_name(&qsdev->dev, "%s.%s",
- edge->of_node->name,
- node ? node->name : channel->name);
-
- qsdev->dev.parent = &edge->dev;
- qsdev->dev.bus = &qcom_smd_bus;
- qsdev->dev.release = qcom_smd_release_device;
- qsdev->dev.of_node = node;
-
- qsdev->channel = channel;
-
- channel->qsdev = qsdev;
-
- ret = device_register(&qsdev->dev);
- if (ret) {
- dev_err(&edge->dev, "device_register failed: %d\n", ret);
- put_device(&qsdev->dev);
- }
-
- return ret;
-}
-
-/*
- * Destroy a smd client device for a channel that's going away.
- */
-static void qcom_smd_destroy_device(struct qcom_smd_channel *channel)
-{
- struct device *dev;
-
- BUG_ON(!channel->qsdev);
-
- dev = &channel->qsdev->dev;
-
- device_unregister(dev);
- of_node_put(dev->of_node);
- put_device(dev);
-}
-
-/**
- * qcom_smd_driver_register - register a smd driver
- * @qsdrv: qcom_smd_driver struct
- */
-int qcom_smd_driver_register(struct qcom_smd_driver *qsdrv)
-{
- qsdrv->driver.bus = &qcom_smd_bus;
- return driver_register(&qsdrv->driver);
-}
-EXPORT_SYMBOL(qcom_smd_driver_register);
-
-void *qcom_smd_get_drvdata(struct qcom_smd_channel *channel)
-{
- return channel->drvdata;
-}
-EXPORT_SYMBOL(qcom_smd_get_drvdata);
-
-void qcom_smd_set_drvdata(struct qcom_smd_channel *channel, void *data)
-{
- channel->drvdata = data;
-}
-EXPORT_SYMBOL(qcom_smd_set_drvdata);
-
-/**
- * qcom_smd_driver_unregister - unregister a smd driver
- * @qsdrv: qcom_smd_driver struct
- */
-void qcom_smd_driver_unregister(struct qcom_smd_driver *qsdrv)
-{
- driver_unregister(&qsdrv->driver);
-}
-EXPORT_SYMBOL(qcom_smd_driver_unregister);
-
-static struct qcom_smd_channel *
-qcom_smd_find_channel(struct qcom_smd_edge *edge, const char *name)
-{
- struct qcom_smd_channel *channel;
- struct qcom_smd_channel *ret = NULL;
- unsigned long flags;
- unsigned state;
-
- spin_lock_irqsave(&edge->channels_lock, flags);
- list_for_each_entry(channel, &edge->channels, list) {
- if (strcmp(channel->name, name))
- continue;
-
- state = GET_RX_CHANNEL_INFO(channel, state);
- if (state != SMD_CHANNEL_OPENING &&
- state != SMD_CHANNEL_OPENED)
- continue;
-
- ret = channel;
- break;
- }
- spin_unlock_irqrestore(&edge->channels_lock, flags);
-
- return ret;
-}
-
-/**
- * qcom_smd_open_channel() - claim additional channels on the same edge
- * @sdev: smd_device handle
- * @name: channel name
- * @cb: callback method to use for incoming data
- *
- * Returns a channel handle on success, or -EPROBE_DEFER if the channel isn't
- * ready.
- *
- * Any channels returned must be closed with a call to qcom_smd_close_channel()
- */
-struct qcom_smd_channel *qcom_smd_open_channel(struct qcom_smd_channel *parent,
- const char *name,
- qcom_smd_cb_t cb)
-{
- struct qcom_smd_channel *channel;
- struct qcom_smd_device *sdev = parent->qsdev;
- struct qcom_smd_edge *edge = parent->edge;
- int ret;
-
- /* Wait up to HZ for the channel to appear */
- ret = wait_event_interruptible_timeout(edge->new_channel_event,
- (channel = qcom_smd_find_channel(edge, name)) != NULL,
- HZ);
- if (!ret)
- return ERR_PTR(-ETIMEDOUT);
-
- if (channel->state != SMD_CHANNEL_CLOSED) {
- dev_err(&sdev->dev, "channel %s is busy\n", channel->name);
- return ERR_PTR(-EBUSY);
- }
-
- channel->qsdev = sdev;
- ret = qcom_smd_channel_open(channel, cb);
- if (ret) {
- channel->qsdev = NULL;
- return ERR_PTR(ret);
- }
-
- return channel;
-}
-EXPORT_SYMBOL(qcom_smd_open_channel);
-
-/**
- * qcom_smd_close_channel() - close an additionally opened channel
- * @channel: channel handle, returned by qcom_smd_open_channel()
- */
-void qcom_smd_close_channel(struct qcom_smd_channel *channel)
-{
- qcom_smd_channel_close(channel);
- channel->qsdev = NULL;
-}
-EXPORT_SYMBOL(qcom_smd_close_channel);
-
-/*
- * Allocate the qcom_smd_channel object for a newly found smd channel,
- * retrieving and validating the smem items involved.
- */
-static struct qcom_smd_channel *qcom_smd_create_channel(struct qcom_smd_edge *edge,
- unsigned smem_info_item,
- unsigned smem_fifo_item,
- char *name)
-{
- struct qcom_smd_channel *channel;
- size_t fifo_size;
- size_t info_size;
- void *fifo_base;
- void *info;
- int ret;
-
- channel = devm_kzalloc(&edge->dev, sizeof(*channel), GFP_KERNEL);
- if (!channel)
- return ERR_PTR(-ENOMEM);
-
- channel->edge = edge;
- channel->name = devm_kstrdup(&edge->dev, name, GFP_KERNEL);
- if (!channel->name)
- return ERR_PTR(-ENOMEM);
-
- mutex_init(&channel->tx_lock);
- spin_lock_init(&channel->recv_lock);
- init_waitqueue_head(&channel->fblockread_event);
-
- info = qcom_smem_get(edge->remote_pid, smem_info_item, &info_size);
- if (IS_ERR(info)) {
- ret = PTR_ERR(info);
- goto free_name_and_channel;
- }
-
- /*
- * Use the size of the item to figure out which channel info struct to
- * use.
- */
- if (info_size == 2 * sizeof(struct smd_channel_info_word)) {
- channel->info_word = info;
- } else if (info_size == 2 * sizeof(struct smd_channel_info)) {
- channel->info = info;
- } else {
- dev_err(&edge->dev,
- "channel info of size %zu not supported\n", info_size);
- ret = -EINVAL;
- goto free_name_and_channel;
- }
-
- fifo_base = qcom_smem_get(edge->remote_pid, smem_fifo_item, &fifo_size);
- if (IS_ERR(fifo_base)) {
- ret = PTR_ERR(fifo_base);
- goto free_name_and_channel;
- }
-
- /* The channel consist of a rx and tx fifo of equal size */
- fifo_size /= 2;
-
- dev_dbg(&edge->dev, "new channel '%s' info-size: %zu fifo-size: %zu\n",
- name, info_size, fifo_size);
-
- channel->tx_fifo = fifo_base;
- channel->rx_fifo = fifo_base + fifo_size;
- channel->fifo_size = fifo_size;
-
- qcom_smd_channel_reset(channel);
-
- return channel;
-
-free_name_and_channel:
- devm_kfree(&edge->dev, channel->name);
- devm_kfree(&edge->dev, channel);
-
- return ERR_PTR(ret);
-}
-
-/*
- * Scans the allocation table for any newly allocated channels, calls
- * qcom_smd_create_channel() to create representations of these and add
- * them to the edge's list of channels.
- */
-static void qcom_channel_scan_worker(struct work_struct *work)
-{
- struct qcom_smd_edge *edge = container_of(work, struct qcom_smd_edge, scan_work);
- struct qcom_smd_alloc_entry *alloc_tbl;
- struct qcom_smd_alloc_entry *entry;
- struct qcom_smd_channel *channel;
- unsigned long flags;
- unsigned fifo_id;
- unsigned info_id;
- int tbl;
- int i;
- u32 eflags, cid;
-
- for (tbl = 0; tbl < SMD_ALLOC_TBL_COUNT; tbl++) {
- alloc_tbl = qcom_smem_get(edge->remote_pid,
- smem_items[tbl].alloc_tbl_id, NULL);
- if (IS_ERR(alloc_tbl))
- continue;
-
- for (i = 0; i < SMD_ALLOC_TBL_SIZE; i++) {
- entry = &alloc_tbl[i];
- eflags = le32_to_cpu(entry->flags);
- if (test_bit(i, edge->allocated[tbl]))
- continue;
-
- if (entry->ref_count == 0)
- continue;
-
- if (!entry->name[0])
- continue;
-
- if (!(eflags & SMD_CHANNEL_FLAGS_PACKET))
- continue;
-
- if ((eflags & SMD_CHANNEL_FLAGS_EDGE_MASK) != edge->edge_id)
- continue;
-
- cid = le32_to_cpu(entry->cid);
- info_id = smem_items[tbl].info_base_id + cid;
- fifo_id = smem_items[tbl].fifo_base_id + cid;
-
- channel = qcom_smd_create_channel(edge, info_id, fifo_id, entry->name);
- if (IS_ERR(channel))
- continue;
-
- spin_lock_irqsave(&edge->channels_lock, flags);
- list_add(&channel->list, &edge->channels);
- spin_unlock_irqrestore(&edge->channels_lock, flags);
-
- dev_dbg(&edge->dev, "new channel found: '%s'\n", channel->name);
- set_bit(i, edge->allocated[tbl]);
-
- wake_up_interruptible(&edge->new_channel_event);
- }
- }
-
- schedule_work(&edge->state_work);
-}
-
-/*
- * This per edge worker scans smem for any new channels and register these. It
- * then scans all registered channels for state changes that should be handled
- * by creating or destroying smd client devices for the registered channels.
- *
- * LOCKING: edge->channels_lock only needs to cover the list operations, as the
- * worker is killed before any channels are deallocated
- */
-static void qcom_channel_state_worker(struct work_struct *work)
-{
- struct qcom_smd_channel *channel;
- struct qcom_smd_edge *edge = container_of(work,
- struct qcom_smd_edge,
- state_work);
- unsigned remote_state;
- unsigned long flags;
-
- /*
- * Register a device for any closed channel where the remote processor
- * is showing interest in opening the channel.
- */
- spin_lock_irqsave(&edge->channels_lock, flags);
- list_for_each_entry(channel, &edge->channels, list) {
- if (channel->state != SMD_CHANNEL_CLOSED)
- continue;
-
- remote_state = GET_RX_CHANNEL_INFO(channel, state);
- if (remote_state != SMD_CHANNEL_OPENING &&
- remote_state != SMD_CHANNEL_OPENED)
- continue;
-
- spin_unlock_irqrestore(&edge->channels_lock, flags);
- qcom_smd_create_device(channel);
- spin_lock_irqsave(&edge->channels_lock, flags);
- }
-
- /*
- * Unregister the device for any channel that is opened where the
- * remote processor is closing the channel.
- */
- list_for_each_entry(channel, &edge->channels, list) {
- if (channel->state != SMD_CHANNEL_OPENING &&
- channel->state != SMD_CHANNEL_OPENED)
- continue;
-
- remote_state = GET_RX_CHANNEL_INFO(channel, state);
- if (remote_state == SMD_CHANNEL_OPENING ||
- remote_state == SMD_CHANNEL_OPENED)
- continue;
-
- spin_unlock_irqrestore(&edge->channels_lock, flags);
- qcom_smd_destroy_device(channel);
- spin_lock_irqsave(&edge->channels_lock, flags);
- }
- spin_unlock_irqrestore(&edge->channels_lock, flags);
-}
-
-/*
- * Parses an of_node describing an edge.
- */
-static int qcom_smd_parse_edge(struct device *dev,
- struct device_node *node,
- struct qcom_smd_edge *edge)
-{
- struct device_node *syscon_np;
- const char *key;
- int irq;
- int ret;
-
- INIT_LIST_HEAD(&edge->channels);
- spin_lock_init(&edge->channels_lock);
-
- INIT_WORK(&edge->scan_work, qcom_channel_scan_worker);
- INIT_WORK(&edge->state_work, qcom_channel_state_worker);
-
- edge->of_node = of_node_get(node);
-
- key = "qcom,smd-edge";
- ret = of_property_read_u32(node, key, &edge->edge_id);
- if (ret) {
- dev_err(dev, "edge missing %s property\n", key);
- return -EINVAL;
- }
-
- edge->remote_pid = QCOM_SMEM_HOST_ANY;
- key = "qcom,remote-pid";
- of_property_read_u32(node, key, &edge->remote_pid);
-
- syscon_np = of_parse_phandle(node, "qcom,ipc", 0);
- if (!syscon_np) {
- dev_err(dev, "no qcom,ipc node\n");
- return -ENODEV;
- }
-
- edge->ipc_regmap = syscon_node_to_regmap(syscon_np);
- if (IS_ERR(edge->ipc_regmap))
- return PTR_ERR(edge->ipc_regmap);
-
- key = "qcom,ipc";
- ret = of_property_read_u32_index(node, key, 1, &edge->ipc_offset);
- if (ret < 0) {
- dev_err(dev, "no offset in %s\n", key);
- return -EINVAL;
- }
-
- ret = of_property_read_u32_index(node, key, 2, &edge->ipc_bit);
- if (ret < 0) {
- dev_err(dev, "no bit in %s\n", key);
- return -EINVAL;
- }
-
- irq = irq_of_parse_and_map(node, 0);
- if (irq < 0) {
- dev_err(dev, "required smd interrupt missing\n");
- return -EINVAL;
- }
-
- ret = devm_request_irq(dev, irq,
- qcom_smd_edge_intr, IRQF_TRIGGER_RISING,
- node->name, edge);
- if (ret) {
- dev_err(dev, "failed to request smd irq\n");
- return ret;
- }
-
- edge->irq = irq;
-
- return 0;
-}
-
-/*
- * Release function for an edge.
- * Reset the state of each associated channel and free the edge context.
- */
-static void qcom_smd_edge_release(struct device *dev)
-{
- struct qcom_smd_channel *channel;
- struct qcom_smd_edge *edge = to_smd_edge(dev);
-
- list_for_each_entry(channel, &edge->channels, list) {
- SET_RX_CHANNEL_INFO(channel, state, SMD_CHANNEL_CLOSED);
- SET_RX_CHANNEL_INFO(channel, head, 0);
- SET_RX_CHANNEL_INFO(channel, tail, 0);
- }
-
- kfree(edge);
-}
-
-/**
- * qcom_smd_register_edge() - register an edge based on an device_node
- * @parent: parent device for the edge
- * @node: device_node describing the edge
- *
- * Returns an edge reference, or negative ERR_PTR() on failure.
- */
-struct qcom_smd_edge *qcom_smd_register_edge(struct device *parent,
- struct device_node *node)
-{
- struct qcom_smd_edge *edge;
- int ret;
-
- edge = kzalloc(sizeof(*edge), GFP_KERNEL);
- if (!edge)
- return ERR_PTR(-ENOMEM);
-
- init_waitqueue_head(&edge->new_channel_event);
-
- edge->dev.parent = parent;
- edge->dev.release = qcom_smd_edge_release;
- dev_set_name(&edge->dev, "%s:%s", dev_name(parent), node->name);
- ret = device_register(&edge->dev);
- if (ret) {
- pr_err("failed to register smd edge\n");
- return ERR_PTR(ret);
- }
-
- ret = qcom_smd_parse_edge(&edge->dev, node, edge);
- if (ret) {
- dev_err(&edge->dev, "failed to parse smd edge\n");
- goto unregister_dev;
- }
-
- schedule_work(&edge->scan_work);
-
- return edge;
-
-unregister_dev:
- put_device(&edge->dev);
- return ERR_PTR(ret);
-}
-EXPORT_SYMBOL(qcom_smd_register_edge);
-
-static int qcom_smd_remove_device(struct device *dev, void *data)
-{
- device_unregister(dev);
- of_node_put(dev->of_node);
- put_device(dev);
-
- return 0;
-}
-
-/**
- * qcom_smd_unregister_edge() - release an edge and its children
- * @edge: edge reference acquired from qcom_smd_register_edge
- */
-int qcom_smd_unregister_edge(struct qcom_smd_edge *edge)
-{
- int ret;
-
- disable_irq(edge->irq);
- cancel_work_sync(&edge->scan_work);
- cancel_work_sync(&edge->state_work);
-
- ret = device_for_each_child(&edge->dev, NULL, qcom_smd_remove_device);
- if (ret)
- dev_warn(&edge->dev, "can't remove smd device: %d\n", ret);
-
- device_unregister(&edge->dev);
-
- return 0;
-}
-EXPORT_SYMBOL(qcom_smd_unregister_edge);
-
-static int qcom_smd_probe(struct platform_device *pdev)
-{
- struct device_node *node;
- void *p;
-
- /* Wait for smem */
- p = qcom_smem_get(QCOM_SMEM_HOST_ANY, smem_items[0].alloc_tbl_id, NULL);
- if (PTR_ERR(p) == -EPROBE_DEFER)
- return PTR_ERR(p);
-
- for_each_available_child_of_node(pdev->dev.of_node, node)
- qcom_smd_register_edge(&pdev->dev, node);
-
- return 0;
-}
-
-static int qcom_smd_remove_edge(struct device *dev, void *data)
-{
- struct qcom_smd_edge *edge = to_smd_edge(dev);
-
- return qcom_smd_unregister_edge(edge);
-}
-
-/*
- * Shut down all smd clients by making sure that each edge stops processing
- * events and scanning for new channels, then call destroy on the devices.
- */
-static int qcom_smd_remove(struct platform_device *pdev)
-{
- int ret;
-
- ret = device_for_each_child(&pdev->dev, NULL, qcom_smd_remove_edge);
- if (ret)
- dev_warn(&pdev->dev, "can't remove smd device: %d\n", ret);
-
- return ret;
-}
-
-static const struct of_device_id qcom_smd_of_match[] = {
- { .compatible = "qcom,smd" },
- {}
-};
-MODULE_DEVICE_TABLE(of, qcom_smd_of_match);
-
-static struct platform_driver qcom_smd_driver = {
- .probe = qcom_smd_probe,
- .remove = qcom_smd_remove,
- .driver = {
- .name = "qcom-smd",
- .of_match_table = qcom_smd_of_match,
- },
-};
-
-static int __init qcom_smd_init(void)
-{
- int ret;
-
- ret = bus_register(&qcom_smd_bus);
- if (ret) {
- pr_err("failed to register smd bus: %d\n", ret);
- return ret;
- }
-
- return platform_driver_register(&qcom_smd_driver);
-}
-postcore_initcall(qcom_smd_init);
-
-static void __exit qcom_smd_exit(void)
-{
- platform_driver_unregister(&qcom_smd_driver);
- bus_unregister(&qcom_smd_bus);
-}
-module_exit(qcom_smd_exit);
-
-MODULE_AUTHOR("Bjorn Andersson <bjorn.andersson@sonymobile.com>");
-MODULE_DESCRIPTION("Qualcomm Shared Memory Driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/soc/qcom/wcnss_ctrl.c b/drivers/soc/qcom/wcnss_ctrl.c
index 520aedd..b906918 100644
--- a/drivers/soc/qcom/wcnss_ctrl.c
+++ b/drivers/soc/qcom/wcnss_ctrl.c
@@ -14,10 +14,10 @@
#include <linux/firmware.h>
#include <linux/module.h>
#include <linux/slab.h>
-#include <linux/soc/qcom/smd.h>
#include <linux/io.h>
#include <linux/of_platform.h>
#include <linux/platform_device.h>
+#include <linux/rpmsg.h>
#include <linux/soc/qcom/wcnss_ctrl.h>
#define WCNSS_REQUEST_TIMEOUT (5 * HZ)
@@ -40,7 +40,7 @@
*/
struct wcnss_ctrl {
struct device *dev;
- struct qcom_smd_channel *channel;
+ struct rpmsg_endpoint *channel;
struct completion ack;
struct completion cbc;
@@ -122,11 +122,13 @@ struct wcnss_download_nv_resp {
*
* Handles any incoming packets from the remote WCNSS_CTRL service.
*/
-static int wcnss_ctrl_smd_callback(struct qcom_smd_channel *channel,
- const void *data,
- size_t count)
+static int wcnss_ctrl_smd_callback(struct rpmsg_device *rpdev,
+ void *data,
+ int count,
+ void *priv,
+ u32 addr)
{
- struct wcnss_ctrl *wcnss = qcom_smd_get_drvdata(channel);
+ struct wcnss_ctrl *wcnss = dev_get_drvdata(&rpdev->dev);
const struct wcnss_download_nv_resp *nvresp;
const struct wcnss_version_resp *version;
const struct wcnss_msg_hdr *hdr = data;
@@ -180,7 +182,7 @@ static int wcnss_request_version(struct wcnss_ctrl *wcnss)
msg.type = WCNSS_VERSION_REQ;
msg.len = sizeof(msg);
- ret = qcom_smd_send(wcnss->channel, &msg, sizeof(msg));
+ ret = rpmsg_send(wcnss->channel, &msg, sizeof(msg));
if (ret < 0)
return ret;
@@ -238,7 +240,7 @@ static int wcnss_download_nv(struct wcnss_ctrl *wcnss, bool *expect_cbc)
memcpy(req->fragment, data, req->frag_size);
- ret = qcom_smd_send(wcnss->channel, req, req->hdr.len);
+ ret = rpmsg_send(wcnss->channel, req, req->hdr.len);
if (ret < 0) {
dev_err(wcnss->dev, "failed to send smd packet\n");
goto release_fw;
@@ -274,11 +276,16 @@ static int wcnss_download_nv(struct wcnss_ctrl *wcnss, bool *expect_cbc)
* @name: SMD channel name
* @cb: callback to handle incoming data on the channel
*/
-struct qcom_smd_channel *qcom_wcnss_open_channel(void *wcnss, const char *name, qcom_smd_cb_t cb)
+struct rpmsg_endpoint *qcom_wcnss_open_channel(void *wcnss, const char *name, rpmsg_rx_cb_t cb, void *priv)
{
+ struct rpmsg_channel_info chinfo;
struct wcnss_ctrl *_wcnss = wcnss;
- return qcom_smd_open_channel(_wcnss->channel, name, cb);
+ strncpy(chinfo.name, name, sizeof(chinfo.name));
+ chinfo.src = RPMSG_ADDR_ANY;
+ chinfo.dst = RPMSG_ADDR_ANY;
+
+ return rpmsg_create_ept(_wcnss->channel->rpdev, cb, priv, chinfo);
}
EXPORT_SYMBOL(qcom_wcnss_open_channel);
@@ -306,35 +313,34 @@ static void wcnss_async_probe(struct work_struct *work)
of_platform_populate(wcnss->dev->of_node, NULL, NULL, wcnss->dev);
}
-static int wcnss_ctrl_probe(struct qcom_smd_device *sdev)
+static int wcnss_ctrl_probe(struct rpmsg_device *rpdev)
{
struct wcnss_ctrl *wcnss;
- wcnss = devm_kzalloc(&sdev->dev, sizeof(*wcnss), GFP_KERNEL);
+ wcnss = devm_kzalloc(&rpdev->dev, sizeof(*wcnss), GFP_KERNEL);
if (!wcnss)
return -ENOMEM;
- wcnss->dev = &sdev->dev;
- wcnss->channel = sdev->channel;
+ wcnss->dev = &rpdev->dev;
+ wcnss->channel = rpdev->ept;
init_completion(&wcnss->ack);
init_completion(&wcnss->cbc);
INIT_WORK(&wcnss->probe_work, wcnss_async_probe);
- qcom_smd_set_drvdata(sdev->channel, wcnss);
- dev_set_drvdata(&sdev->dev, wcnss);
+ dev_set_drvdata(&rpdev->dev, wcnss);
schedule_work(&wcnss->probe_work);
return 0;
}
-static void wcnss_ctrl_remove(struct qcom_smd_device *sdev)
+static void wcnss_ctrl_remove(struct rpmsg_device *rpdev)
{
- struct wcnss_ctrl *wcnss = qcom_smd_get_drvdata(sdev->channel);
+ struct wcnss_ctrl *wcnss = dev_get_drvdata(&rpdev->dev);
cancel_work_sync(&wcnss->probe_work);
- of_platform_depopulate(&sdev->dev);
+ of_platform_depopulate(&rpdev->dev);
}
static const struct of_device_id wcnss_ctrl_of_match[] = {
@@ -342,18 +348,18 @@ static const struct of_device_id wcnss_ctrl_of_match[] = {
{}
};
-static struct qcom_smd_driver wcnss_ctrl_driver = {
+static struct rpmsg_driver wcnss_ctrl_driver = {
.probe = wcnss_ctrl_probe,
.remove = wcnss_ctrl_remove,
.callback = wcnss_ctrl_smd_callback,
- .driver = {
+ .drv = {
.name = "qcom_wcnss_ctrl",
.owner = THIS_MODULE,
.of_match_table = wcnss_ctrl_of_match,
},
};
-module_qcom_smd_driver(wcnss_ctrl_driver);
+module_rpmsg_driver(wcnss_ctrl_driver);
MODULE_DESCRIPTION("Qualcomm WCNSS control driver");
MODULE_LICENSE("GPL v2");
diff --git a/drivers/staging/lustre/lnet/lnet/lib-socket.c b/drivers/staging/lustre/lnet/lnet/lib-socket.c
index b7b87ec..9fca8d2 100644
--- a/drivers/staging/lustre/lnet/lnet/lib-socket.c
+++ b/drivers/staging/lustre/lnet/lnet/lib-socket.c
@@ -532,7 +532,7 @@ lnet_sock_accept(struct socket **newsockp, struct socket *sock)
newsock->ops = sock->ops;
- rc = sock->ops->accept(sock, newsock, O_NONBLOCK);
+ rc = sock->ops->accept(sock, newsock, O_NONBLOCK, false);
if (rc == -EAGAIN) {
/* Nothing ready, so wait for activity */
init_waitqueue_entry(&wait, current);
@@ -540,7 +540,7 @@ lnet_sock_accept(struct socket **newsockp, struct socket *sock)
set_current_state(TASK_INTERRUPTIBLE);
schedule();
remove_wait_queue(sk_sleep(sock->sk), &wait);
- rc = sock->ops->accept(sock, newsock, O_NONBLOCK);
+ rc = sock->ops->accept(sock, newsock, O_NONBLOCK, false);
}
if (rc)
diff --git a/drivers/staging/octeon/ethernet-rx.c b/drivers/staging/octeon/ethernet-rx.c
index 7f8cf87..65a2856 100644
--- a/drivers/staging/octeon/ethernet-rx.c
+++ b/drivers/staging/octeon/ethernet-rx.c
@@ -336,7 +336,6 @@ static int cvm_oct_poll(struct oct_rx_group *rx_group, int budget)
if (likely((port < TOTAL_NUMBER_OF_PORTS) &&
cvm_oct_device[port])) {
struct net_device *dev = cvm_oct_device[port];
- struct octeon_ethernet *priv = netdev_priv(dev);
/*
* Only accept packets for devices that are
diff --git a/drivers/staging/vc04_services/Kconfig b/drivers/staging/vc04_services/Kconfig
index e61e4ca..74094ff 100644
--- a/drivers/staging/vc04_services/Kconfig
+++ b/drivers/staging/vc04_services/Kconfig
@@ -1,6 +1,7 @@
config BCM2835_VCHIQ
tristate "Videocore VCHIQ"
depends on HAS_DMA
+ depends on OF
depends on RASPBERRYPI_FIRMWARE || (COMPILE_TEST && !RASPBERRYPI_FIRMWARE)
default y
help
diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index f5e3300..fd7c16a 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -43,7 +43,7 @@
#include "target_core_ua.h"
static sense_reason_t core_alua_check_transition(int state, int valid,
- int *primary);
+ int *primary, int explicit);
static int core_alua_set_tg_pt_secondary_state(
struct se_lun *lun, int explicit, int offline);
@@ -335,8 +335,8 @@ target_emulate_set_target_port_groups(struct se_cmd *cmd)
* the state is a primary or secondary target port asymmetric
* access state.
*/
- rc = core_alua_check_transition(alua_access_state,
- valid_states, &primary);
+ rc = core_alua_check_transition(alua_access_state, valid_states,
+ &primary, 1);
if (rc) {
/*
* If the SET TARGET PORT GROUPS attempts to establish
@@ -691,7 +691,7 @@ target_alua_state_check(struct se_cmd *cmd)
if (dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)
return 0;
- if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH_ALUA)
return 0;
/*
@@ -762,7 +762,7 @@ target_alua_state_check(struct se_cmd *cmd)
* Check implicit and explicit ALUA state change request.
*/
static sense_reason_t
-core_alua_check_transition(int state, int valid, int *primary)
+core_alua_check_transition(int state, int valid, int *primary, int explicit)
{
/*
* OPTIMIZED, NON-OPTIMIZED, STANDBY and UNAVAILABLE are
@@ -804,11 +804,14 @@ core_alua_check_transition(int state, int valid, int *primary)
*primary = 0;
break;
case ALUA_ACCESS_STATE_TRANSITION:
- /*
- * Transitioning is set internally, and
- * cannot be selected manually.
- */
- goto not_supported;
+ if (!(valid & ALUA_T_SUP) || explicit)
+ /*
+ * Transitioning is set internally and by tcmu daemon,
+ * and cannot be selected through a STPG.
+ */
+ goto not_supported;
+ *primary = 0;
+ break;
default:
pr_err("Unknown ALUA access state: 0x%02x\n", state);
return TCM_INVALID_PARAMETER_LIST;
@@ -1013,7 +1016,7 @@ static void core_alua_queue_state_change_ua(struct t10_alua_tg_pt_gp *tg_pt_gp)
static void core_alua_do_transition_tg_pt_work(struct work_struct *work)
{
struct t10_alua_tg_pt_gp *tg_pt_gp = container_of(work,
- struct t10_alua_tg_pt_gp, tg_pt_gp_transition_work.work);
+ struct t10_alua_tg_pt_gp, tg_pt_gp_transition_work);
struct se_device *dev = tg_pt_gp->tg_pt_gp_dev;
bool explicit = (tg_pt_gp->tg_pt_gp_alua_access_status ==
ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG);
@@ -1070,32 +1073,19 @@ static int core_alua_do_transition_tg_pt(
if (atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state) == new_state)
return 0;
- if (new_state == ALUA_ACCESS_STATE_TRANSITION)
+ if (explicit && new_state == ALUA_ACCESS_STATE_TRANSITION)
return -EAGAIN;
/*
* Flush any pending transitions
*/
- if (!explicit && tg_pt_gp->tg_pt_gp_implicit_trans_secs &&
- atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state) ==
- ALUA_ACCESS_STATE_TRANSITION) {
- /* Just in case */
- tg_pt_gp->tg_pt_gp_alua_pending_state = new_state;
- tg_pt_gp->tg_pt_gp_transition_complete = &wait;
- flush_delayed_work(&tg_pt_gp->tg_pt_gp_transition_work);
- wait_for_completion(&wait);
- tg_pt_gp->tg_pt_gp_transition_complete = NULL;
- return 0;
- }
+ if (!explicit)
+ flush_work(&tg_pt_gp->tg_pt_gp_transition_work);
/*
* Save the old primary ALUA access state, and set the current state
* to ALUA_ACCESS_STATE_TRANSITION.
*/
- tg_pt_gp->tg_pt_gp_alua_previous_state =
- atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state);
- tg_pt_gp->tg_pt_gp_alua_pending_state = new_state;
-
atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state,
ALUA_ACCESS_STATE_TRANSITION);
tg_pt_gp->tg_pt_gp_alua_access_status = (explicit) ?
@@ -1104,6 +1094,13 @@ static int core_alua_do_transition_tg_pt(
core_alua_queue_state_change_ua(tg_pt_gp);
+ if (new_state == ALUA_ACCESS_STATE_TRANSITION)
+ return 0;
+
+ tg_pt_gp->tg_pt_gp_alua_previous_state =
+ atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state);
+ tg_pt_gp->tg_pt_gp_alua_pending_state = new_state;
+
/*
* Check for the optional ALUA primary state transition delay
*/
@@ -1117,17 +1114,9 @@ static int core_alua_do_transition_tg_pt(
atomic_inc(&tg_pt_gp->tg_pt_gp_ref_cnt);
spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
- if (!explicit && tg_pt_gp->tg_pt_gp_implicit_trans_secs) {
- unsigned long transition_tmo;
-
- transition_tmo = tg_pt_gp->tg_pt_gp_implicit_trans_secs * HZ;
- queue_delayed_work(tg_pt_gp->tg_pt_gp_dev->tmr_wq,
- &tg_pt_gp->tg_pt_gp_transition_work,
- transition_tmo);
- } else {
+ schedule_work(&tg_pt_gp->tg_pt_gp_transition_work);
+ if (explicit) {
tg_pt_gp->tg_pt_gp_transition_complete = &wait;
- queue_delayed_work(tg_pt_gp->tg_pt_gp_dev->tmr_wq,
- &tg_pt_gp->tg_pt_gp_transition_work, 0);
wait_for_completion(&wait);
tg_pt_gp->tg_pt_gp_transition_complete = NULL;
}
@@ -1149,8 +1138,12 @@ int core_alua_do_port_transition(
struct t10_alua_tg_pt_gp *tg_pt_gp;
int primary, valid_states, rc = 0;
+ if (l_dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH_ALUA)
+ return -ENODEV;
+
valid_states = l_tg_pt_gp->tg_pt_gp_alua_supported_states;
- if (core_alua_check_transition(new_state, valid_states, &primary) != 0)
+ if (core_alua_check_transition(new_state, valid_states, &primary,
+ explicit) != 0)
return -EINVAL;
local_lu_gp_mem = l_dev->dev_alua_lu_gp_mem;
@@ -1695,8 +1688,8 @@ struct t10_alua_tg_pt_gp *core_alua_allocate_tg_pt_gp(struct se_device *dev,
mutex_init(&tg_pt_gp->tg_pt_gp_md_mutex);
spin_lock_init(&tg_pt_gp->tg_pt_gp_lock);
atomic_set(&tg_pt_gp->tg_pt_gp_ref_cnt, 0);
- INIT_DELAYED_WORK(&tg_pt_gp->tg_pt_gp_transition_work,
- core_alua_do_transition_tg_pt_work);
+ INIT_WORK(&tg_pt_gp->tg_pt_gp_transition_work,
+ core_alua_do_transition_tg_pt_work);
tg_pt_gp->tg_pt_gp_dev = dev;
atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state,
ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED);
@@ -1804,7 +1797,7 @@ void core_alua_free_tg_pt_gp(
dev->t10_alua.alua_tg_pt_gps_counter--;
spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
- flush_delayed_work(&tg_pt_gp->tg_pt_gp_transition_work);
+ flush_work(&tg_pt_gp->tg_pt_gp_transition_work);
/*
* Allow a struct t10_alua_tg_pt_gp_member * referenced by
@@ -1973,7 +1966,7 @@ ssize_t core_alua_store_tg_pt_gp_info(
unsigned char buf[TG_PT_GROUP_NAME_BUF];
int move = 0;
- if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH ||
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH_ALUA ||
(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE))
return -ENODEV;
@@ -2230,7 +2223,7 @@ ssize_t core_alua_store_offline_bit(
unsigned long tmp;
int ret;
- if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH ||
+ if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH_ALUA ||
(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE))
return -ENODEV;
@@ -2316,7 +2309,8 @@ ssize_t core_alua_store_secondary_write_metadata(
int core_setup_alua(struct se_device *dev)
{
- if (!(dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) &&
+ if (!(dev->transport->transport_flags &
+ TRANSPORT_FLAG_PASSTHROUGH_ALUA) &&
!(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)) {
struct t10_alua_lu_gp_member *lu_gp_mem;
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 54b36c9..38b5025 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -421,6 +421,10 @@ static int target_fabric_tf_ops_check(const struct target_core_fabric_ops *tfo)
pr_err("Missing tfo->aborted_task()\n");
return -EINVAL;
}
+ if (!tfo->check_stop_free) {
+ pr_err("Missing tfo->check_stop_free()\n");
+ return -EINVAL;
+ }
/*
* We at least require tfo->fabric_make_wwn(), tfo->fabric_drop_wwn()
* tfo->fabric_make_tpg() and tfo->fabric_drop_tpg() in
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index a8f8e53..94cda79 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -154,7 +154,7 @@ static void pscsi_tape_read_blocksize(struct se_device *dev,
buf = kzalloc(12, GFP_KERNEL);
if (!buf)
- return;
+ goto out_free;
memset(cdb, 0, MAX_COMMAND_SIZE);
cdb[0] = MODE_SENSE;
@@ -169,9 +169,10 @@ static void pscsi_tape_read_blocksize(struct se_device *dev,
* If MODE_SENSE still returns zero, set the default value to 1024.
*/
sdev->sector_size = (buf[9] << 16) | (buf[10] << 8) | (buf[11]);
+out_free:
if (!sdev->sector_size)
sdev->sector_size = 1024;
-out_free:
+
kfree(buf);
}
@@ -314,9 +315,10 @@ static int pscsi_add_device_to_list(struct se_device *dev,
sd->lun, sd->queue_depth);
}
- dev->dev_attrib.hw_block_size = sd->sector_size;
+ dev->dev_attrib.hw_block_size =
+ min_not_zero((int)sd->sector_size, 512);
dev->dev_attrib.hw_max_sectors =
- min_t(int, sd->host->max_sectors, queue_max_hw_sectors(q));
+ min_not_zero(sd->host->max_sectors, queue_max_hw_sectors(q));
dev->dev_attrib.hw_queue_depth = sd->queue_depth;
/*
@@ -339,8 +341,10 @@ static int pscsi_add_device_to_list(struct se_device *dev,
/*
* For TYPE_TAPE, attempt to determine blocksize with MODE_SENSE.
*/
- if (sd->type == TYPE_TAPE)
+ if (sd->type == TYPE_TAPE) {
pscsi_tape_read_blocksize(dev, sd);
+ dev->dev_attrib.hw_block_size = sd->sector_size;
+ }
return 0;
}
@@ -406,7 +410,7 @@ static int pscsi_create_type_disk(struct se_device *dev, struct scsi_device *sd)
/*
* Called with struct Scsi_Host->host_lock called.
*/
-static int pscsi_create_type_rom(struct se_device *dev, struct scsi_device *sd)
+static int pscsi_create_type_nondisk(struct se_device *dev, struct scsi_device *sd)
__releases(sh->host_lock)
{
struct pscsi_hba_virt *phv = dev->se_hba->hba_ptr;
@@ -433,28 +437,6 @@ static int pscsi_create_type_rom(struct se_device *dev, struct scsi_device *sd)
return 0;
}
-/*
- * Called with struct Scsi_Host->host_lock called.
- */
-static int pscsi_create_type_other(struct se_device *dev,
- struct scsi_device *sd)
- __releases(sh->host_lock)
-{
- struct pscsi_hba_virt *phv = dev->se_hba->hba_ptr;
- struct Scsi_Host *sh = sd->host;
- int ret;
-
- spin_unlock_irq(sh->host_lock);
- ret = pscsi_add_device_to_list(dev, sd);
- if (ret)
- return ret;
-
- pr_debug("CORE_PSCSI[%d] - Added Type: %s for %d:%d:%d:%llu\n",
- phv->phv_host_id, scsi_device_type(sd->type), sh->host_no,
- sd->channel, sd->id, sd->lun);
- return 0;
-}
-
static int pscsi_configure_device(struct se_device *dev)
{
struct se_hba *hba = dev->se_hba;
@@ -542,11 +524,8 @@ static int pscsi_configure_device(struct se_device *dev)
case TYPE_DISK:
ret = pscsi_create_type_disk(dev, sd);
break;
- case TYPE_ROM:
- ret = pscsi_create_type_rom(dev, sd);
- break;
default:
- ret = pscsi_create_type_other(dev, sd);
+ ret = pscsi_create_type_nondisk(dev, sd);
break;
}
@@ -611,8 +590,7 @@ static void pscsi_free_device(struct se_device *dev)
else if (pdv->pdv_lld_host)
scsi_host_put(pdv->pdv_lld_host);
- if ((sd->type == TYPE_DISK) || (sd->type == TYPE_ROM))
- scsi_device_put(sd);
+ scsi_device_put(sd);
pdv->pdv_sd = NULL;
}
@@ -1064,7 +1042,6 @@ static sector_t pscsi_get_blocks(struct se_device *dev)
if (pdv->pdv_bd && pdv->pdv_bd->bd_part)
return pdv->pdv_bd->bd_part->nr_sects;
- dump_stack();
return 0;
}
@@ -1103,7 +1080,8 @@ static void pscsi_req_done(struct request *req, int uptodate)
static const struct target_backend_ops pscsi_ops = {
.name = "pscsi",
.owner = THIS_MODULE,
- .transport_flags = TRANSPORT_FLAG_PASSTHROUGH,
+ .transport_flags = TRANSPORT_FLAG_PASSTHROUGH |
+ TRANSPORT_FLAG_PASSTHROUGH_ALUA,
.attach_hba = pscsi_attach_hba,
.detach_hba = pscsi_detach_hba,
.pmode_enable_hba = pscsi_pmode_enable_hba,
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 68d8aef..c194063 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -1105,9 +1105,15 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
return ret;
break;
case VERIFY:
+ case VERIFY_16:
size = 0;
- sectors = transport_get_sectors_10(cdb);
- cmd->t_task_lba = transport_lba_32(cdb);
+ if (cdb[0] == VERIFY) {
+ sectors = transport_get_sectors_10(cdb);
+ cmd->t_task_lba = transport_lba_32(cdb);
+ } else {
+ sectors = transport_get_sectors_16(cdb);
+ cmd->t_task_lba = transport_lba_64(cdb);
+ }
cmd->execute_cmd = sbc_emulate_noop;
goto check_lba;
case REZERO_UNIT:
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index c0dbfa0..6fb1919 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -602,7 +602,8 @@ int core_tpg_add_lun(
if (ret)
goto out_kill_ref;
- if (!(dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) &&
+ if (!(dev->transport->transport_flags &
+ TRANSPORT_FLAG_PASSTHROUGH_ALUA) &&
!(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE))
target_attach_tg_pt_gp(lun, dev->t10_alua.default_tg_pt_gp);
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 434d9d6..b1a3cdb 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -636,8 +636,7 @@ static int transport_cmd_check_stop_to_fabric(struct se_cmd *cmd)
* Fabric modules are expected to return '1' here if the se_cmd being
* passed is released at this point, or zero if not being released.
*/
- return cmd->se_tfo->check_stop_free ? cmd->se_tfo->check_stop_free(cmd)
- : 0;
+ return cmd->se_tfo->check_stop_free(cmd);
}
static void transport_lun_remove_cmd(struct se_cmd *cmd)
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index c3adefe..c6874c3 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -28,6 +28,7 @@
#include <linux/stringify.h>
#include <linux/bitops.h>
#include <linux/highmem.h>
+#include <linux/configfs.h>
#include <net/genetlink.h>
#include <scsi/scsi_common.h>
#include <scsi/scsi_proto.h>
@@ -112,6 +113,7 @@ struct tcmu_dev {
spinlock_t commands_lock;
struct timer_list timeout;
+ unsigned int cmd_time_out;
char dev_config[TCMU_CONFIG_LEN];
};
@@ -172,7 +174,9 @@ static struct tcmu_cmd *tcmu_alloc_cmd(struct se_cmd *se_cmd)
tcmu_cmd->se_cmd = se_cmd;
tcmu_cmd->tcmu_dev = udev;
- tcmu_cmd->deadline = jiffies + msecs_to_jiffies(TCMU_TIME_OUT);
+ if (udev->cmd_time_out)
+ tcmu_cmd->deadline = jiffies +
+ msecs_to_jiffies(udev->cmd_time_out);
idr_preload(GFP_KERNEL);
spin_lock_irq(&udev->commands_lock);
@@ -451,7 +455,11 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
pr_debug("sleeping for ring space\n");
spin_unlock_irq(&udev->cmdr_lock);
- ret = schedule_timeout(msecs_to_jiffies(TCMU_TIME_OUT));
+ if (udev->cmd_time_out)
+ ret = schedule_timeout(
+ msecs_to_jiffies(udev->cmd_time_out));
+ else
+ ret = schedule_timeout(msecs_to_jiffies(TCMU_TIME_OUT));
finish_wait(&udev->wait_cmdr, &__wait);
if (!ret) {
pr_warn("tcmu: command timed out\n");
@@ -526,8 +534,9 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
/* TODO: only if FLUSH and FUA? */
uio_event_notify(&udev->uio_info);
- mod_timer(&udev->timeout,
- round_jiffies_up(jiffies + msecs_to_jiffies(TCMU_TIME_OUT)));
+ if (udev->cmd_time_out)
+ mod_timer(&udev->timeout, round_jiffies_up(jiffies +
+ msecs_to_jiffies(udev->cmd_time_out)));
return TCM_NO_SENSE;
}
@@ -742,6 +751,7 @@ static struct se_device *tcmu_alloc_device(struct se_hba *hba, const char *name)
}
udev->hba = hba;
+ udev->cmd_time_out = TCMU_TIME_OUT;
init_waitqueue_head(&udev->wait_cmdr);
spin_lock_init(&udev->cmdr_lock);
@@ -960,7 +970,8 @@ static int tcmu_configure_device(struct se_device *dev)
if (dev->dev_attrib.hw_block_size == 0)
dev->dev_attrib.hw_block_size = 512;
/* Other attributes can be configured in userspace */
- dev->dev_attrib.hw_max_sectors = 128;
+ if (!dev->dev_attrib.hw_max_sectors)
+ dev->dev_attrib.hw_max_sectors = 128;
dev->dev_attrib.hw_queue_depth = 128;
ret = tcmu_netlink_event(TCMU_CMD_ADDED_DEVICE, udev->uio_info.name,
@@ -997,6 +1008,11 @@ static void tcmu_dev_call_rcu(struct rcu_head *p)
kfree(udev);
}
+static bool tcmu_dev_configured(struct tcmu_dev *udev)
+{
+ return udev->uio_info.uio_dev ? true : false;
+}
+
static void tcmu_free_device(struct se_device *dev)
{
struct tcmu_dev *udev = TCMU_DEV(dev);
@@ -1018,8 +1034,7 @@ static void tcmu_free_device(struct se_device *dev)
spin_unlock_irq(&udev->commands_lock);
WARN_ON(!all_expired);
- /* Device was configured */
- if (udev->uio_info.uio_dev) {
+ if (tcmu_dev_configured(udev)) {
tcmu_netlink_event(TCMU_CMD_REMOVED_DEVICE, udev->uio_info.name,
udev->uio_info.uio_dev->minor);
@@ -1031,16 +1046,42 @@ static void tcmu_free_device(struct se_device *dev)
}
enum {
- Opt_dev_config, Opt_dev_size, Opt_hw_block_size, Opt_err,
+ Opt_dev_config, Opt_dev_size, Opt_hw_block_size, Opt_hw_max_sectors,
+ Opt_err,
};
static match_table_t tokens = {
{Opt_dev_config, "dev_config=%s"},
{Opt_dev_size, "dev_size=%u"},
{Opt_hw_block_size, "hw_block_size=%u"},
+ {Opt_hw_max_sectors, "hw_max_sectors=%u"},
{Opt_err, NULL}
};
+static int tcmu_set_dev_attrib(substring_t *arg, u32 *dev_attrib)
+{
+ unsigned long tmp_ul;
+ char *arg_p;
+ int ret;
+
+ arg_p = match_strdup(arg);
+ if (!arg_p)
+ return -ENOMEM;
+
+ ret = kstrtoul(arg_p, 0, &tmp_ul);
+ kfree(arg_p);
+ if (ret < 0) {
+ pr_err("kstrtoul() failed for dev attrib\n");
+ return ret;
+ }
+ if (!tmp_ul) {
+ pr_err("dev attrib must be nonzero\n");
+ return -EINVAL;
+ }
+ *dev_attrib = tmp_ul;
+ return 0;
+}
+
static ssize_t tcmu_set_configfs_dev_params(struct se_device *dev,
const char *page, ssize_t count)
{
@@ -1048,7 +1089,6 @@ static ssize_t tcmu_set_configfs_dev_params(struct se_device *dev,
char *orig, *ptr, *opts, *arg_p;
substring_t args[MAX_OPT_ARGS];
int ret = 0, token;
- unsigned long tmp_ul;
opts = kstrdup(page, GFP_KERNEL);
if (!opts)
@@ -1082,26 +1122,19 @@ static ssize_t tcmu_set_configfs_dev_params(struct se_device *dev,
pr_err("kstrtoul() failed for dev_size=\n");
break;
case Opt_hw_block_size:
- arg_p = match_strdup(&args[0]);
- if (!arg_p) {
- ret = -ENOMEM;
- break;
- }
- ret = kstrtoul(arg_p, 0, &tmp_ul);
- kfree(arg_p);
- if (ret < 0) {
- pr_err("kstrtoul() failed for hw_block_size=\n");
- break;
- }
- if (!tmp_ul) {
- pr_err("hw_block_size must be nonzero\n");
- break;
- }
- dev->dev_attrib.hw_block_size = tmp_ul;
+ ret = tcmu_set_dev_attrib(&args[0],
+ &(dev->dev_attrib.hw_block_size));
+ break;
+ case Opt_hw_max_sectors:
+ ret = tcmu_set_dev_attrib(&args[0],
+ &(dev->dev_attrib.hw_max_sectors));
break;
default:
break;
}
+
+ if (ret)
+ break;
}
kfree(orig);
@@ -1134,7 +1167,48 @@ tcmu_parse_cdb(struct se_cmd *cmd)
return passthrough_parse_cdb(cmd, tcmu_queue_cmd);
}
-static const struct target_backend_ops tcmu_ops = {
+static ssize_t tcmu_cmd_time_out_show(struct config_item *item, char *page)
+{
+ struct se_dev_attrib *da = container_of(to_config_group(item),
+ struct se_dev_attrib, da_group);
+ struct tcmu_dev *udev = container_of(da->da_dev,
+ struct tcmu_dev, se_dev);
+
+ return snprintf(page, PAGE_SIZE, "%lu\n", udev->cmd_time_out / MSEC_PER_SEC);
+}
+
+static ssize_t tcmu_cmd_time_out_store(struct config_item *item, const char *page,
+ size_t count)
+{
+ struct se_dev_attrib *da = container_of(to_config_group(item),
+ struct se_dev_attrib, da_group);
+ struct tcmu_dev *udev = container_of(da->da_dev,
+ struct tcmu_dev, se_dev);
+ u32 val;
+ int ret;
+
+ if (da->da_dev->export_count) {
+ pr_err("Unable to set tcmu cmd_time_out while exports exist\n");
+ return -EINVAL;
+ }
+
+ ret = kstrtou32(page, 0, &val);
+ if (ret < 0)
+ return ret;
+
+ if (!val) {
+ pr_err("Illegal value for cmd_time_out\n");
+ return -EINVAL;
+ }
+
+ udev->cmd_time_out = val * MSEC_PER_SEC;
+ return count;
+}
+CONFIGFS_ATTR(tcmu_, cmd_time_out);
+
+static struct configfs_attribute **tcmu_attrs;
+
+static struct target_backend_ops tcmu_ops = {
.name = "user",
.owner = THIS_MODULE,
.transport_flags = TRANSPORT_FLAG_PASSTHROUGH,
@@ -1148,12 +1222,12 @@ static const struct target_backend_ops tcmu_ops = {
.show_configfs_dev_params = tcmu_show_configfs_dev_params,
.get_device_type = sbc_get_device_type,
.get_blocks = tcmu_get_blocks,
- .tb_dev_attrib_attrs = passthrough_attrib_attrs,
+ .tb_dev_attrib_attrs = NULL,
};
static int __init tcmu_module_init(void)
{
- int ret;
+ int ret, i, len = 0;
BUILD_BUG_ON((sizeof(struct tcmu_cmd_entry) % TCMU_OP_ALIGN_SIZE) != 0);
@@ -1175,12 +1249,31 @@ static int __init tcmu_module_init(void)
goto out_unreg_device;
}
+ for (i = 0; passthrough_attrib_attrs[i] != NULL; i++) {
+ len += sizeof(struct configfs_attribute *);
+ }
+ len += sizeof(struct configfs_attribute *) * 2;
+
+ tcmu_attrs = kzalloc(len, GFP_KERNEL);
+ if (!tcmu_attrs) {
+ ret = -ENOMEM;
+ goto out_unreg_genl;
+ }
+
+ for (i = 0; passthrough_attrib_attrs[i] != NULL; i++) {
+ tcmu_attrs[i] = passthrough_attrib_attrs[i];
+ }
+ tcmu_attrs[i] = &tcmu_attr_cmd_time_out;
+ tcmu_ops.tb_dev_attrib_attrs = tcmu_attrs;
+
ret = transport_backend_register(&tcmu_ops);
if (ret)
- goto out_unreg_genl;
+ goto out_attrs;
return 0;
+out_attrs:
+ kfree(tcmu_attrs);
out_unreg_genl:
genl_unregister_family(&tcmu_genl_family);
out_unreg_device:
@@ -1194,6 +1287,7 @@ static int __init tcmu_module_init(void)
static void __exit tcmu_module_exit(void)
{
target_backend_unregister(&tcmu_ops);
+ kfree(tcmu_attrs);
genl_unregister_family(&tcmu_genl_family);
root_device_unregister(tcmu_root_device);
kmem_cache_destroy(tcmu_cmd_cache);
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 91048ee..69d0f43 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -107,8 +107,6 @@ struct cpufreq_cooling_device {
};
static DEFINE_IDA(cpufreq_ida);
-static unsigned int cpufreq_dev_count;
-
static DEFINE_MUTEX(cooling_list_lock);
static LIST_HEAD(cpufreq_dev_list);
@@ -395,13 +393,20 @@ static int get_static_power(struct cpufreq_cooling_device *cpufreq_device,
opp = dev_pm_opp_find_freq_exact(cpufreq_device->cpu_dev, freq_hz,
true);
+ if (IS_ERR(opp)) {
+ dev_warn_ratelimited(cpufreq_device->cpu_dev,
+ "Failed to find OPP for frequency %lu: %ld\n",
+ freq_hz, PTR_ERR(opp));
+ return -EINVAL;
+ }
+
voltage = dev_pm_opp_get_voltage(opp);
dev_pm_opp_put(opp);
if (voltage == 0) {
- dev_warn_ratelimited(cpufreq_device->cpu_dev,
- "Failed to get voltage for frequency %lu: %ld\n",
- freq_hz, IS_ERR(opp) ? PTR_ERR(opp) : 0);
+ dev_err_ratelimited(cpufreq_device->cpu_dev,
+ "Failed to get voltage for frequency %lu\n",
+ freq_hz);
return -EINVAL;
}
@@ -693,9 +698,9 @@ static int cpufreq_power2state(struct thermal_cooling_device *cdev,
*state = cpufreq_cooling_get_level(cpu, target_freq);
if (*state == THERMAL_CSTATE_INVALID) {
- dev_warn_ratelimited(&cdev->device,
- "Failed to convert %dKHz for cpu %d into a cdev state\n",
- target_freq, cpu);
+ dev_err_ratelimited(&cdev->device,
+ "Failed to convert %dKHz for cpu %d into a cdev state\n",
+ target_freq, cpu);
return -EINVAL;
}
@@ -771,6 +776,7 @@ __cpufreq_cooling_register(struct device_node *np,
unsigned int freq, i, num_cpus;
int ret;
struct thermal_cooling_device_ops *cooling_ops;
+ bool first;
if (!alloc_cpumask_var(&temp_mask, GFP_KERNEL))
return ERR_PTR(-ENOMEM);
@@ -874,13 +880,14 @@ __cpufreq_cooling_register(struct device_node *np,
cpufreq_dev->cool_dev = cool_dev;
mutex_lock(&cooling_list_lock);
- list_add(&cpufreq_dev->node, &cpufreq_dev_list);
-
/* Register the notifier for first cpufreq cooling device */
- if (!cpufreq_dev_count++)
+ first = list_empty(&cpufreq_dev_list);
+ list_add(&cpufreq_dev->node, &cpufreq_dev_list);
+ mutex_unlock(&cooling_list_lock);
+
+ if (first)
cpufreq_register_notifier(&thermal_cpufreq_notifier_block,
CPUFREQ_POLICY_NOTIFIER);
- mutex_unlock(&cooling_list_lock);
goto put_policy;
@@ -1021,6 +1028,7 @@ EXPORT_SYMBOL(of_cpufreq_power_cooling_register);
void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
{
struct cpufreq_cooling_device *cpufreq_dev;
+ bool last;
if (!cdev)
return;
@@ -1028,14 +1036,15 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
cpufreq_dev = cdev->devdata;
mutex_lock(&cooling_list_lock);
+ list_del(&cpufreq_dev->node);
/* Unregister the notifier for the last cpufreq cooling device */
- if (!--cpufreq_dev_count)
+ last = list_empty(&cpufreq_dev_list);
+ mutex_unlock(&cooling_list_lock);
+
+ if (last)
cpufreq_unregister_notifier(&thermal_cpufreq_notifier_block,
CPUFREQ_POLICY_NOTIFIER);
- list_del(&cpufreq_dev->node);
- mutex_unlock(&cooling_list_lock);
-
thermal_cooling_device_unregister(cpufreq_dev->cool_dev);
ida_simple_remove(&cpufreq_ida, cpufreq_dev->id);
kfree(cpufreq_dev->dyn_power_table);
diff --git a/drivers/thermal/devfreq_cooling.c b/drivers/thermal/devfreq_cooling.c
index 7743a78..4bf4ad5 100644
--- a/drivers/thermal/devfreq_cooling.c
+++ b/drivers/thermal/devfreq_cooling.c
@@ -186,16 +186,22 @@ get_static_power(struct devfreq_cooling_device *dfc, unsigned long freq)
return 0;
opp = dev_pm_opp_find_freq_exact(dev, freq, true);
- if (IS_ERR(opp) && (PTR_ERR(opp) == -ERANGE))
+ if (PTR_ERR(opp) == -ERANGE)
opp = dev_pm_opp_find_freq_exact(dev, freq, false);
+ if (IS_ERR(opp)) {
+ dev_err_ratelimited(dev, "Failed to find OPP for frequency %lu: %ld\n",
+ freq, PTR_ERR(opp));
+ return 0;
+ }
+
voltage = dev_pm_opp_get_voltage(opp) / 1000; /* mV */
dev_pm_opp_put(opp);
if (voltage == 0) {
- dev_warn_ratelimited(dev,
- "Failed to get voltage for frequency %lu: %ld\n",
- freq, IS_ERR(opp) ? PTR_ERR(opp) : 0);
+ dev_err_ratelimited(dev,
+ "Failed to get voltage for frequency %lu\n",
+ freq);
return 0;
}
diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c
index 1bacbc3..e94aea8 100644
--- a/drivers/tty/n_hdlc.c
+++ b/drivers/tty/n_hdlc.c
@@ -114,7 +114,7 @@
#define DEFAULT_TX_BUF_COUNT 3
struct n_hdlc_buf {
- struct n_hdlc_buf *link;
+ struct list_head list_item;
int count;
char buf[1];
};
@@ -122,8 +122,7 @@ struct n_hdlc_buf {
#define N_HDLC_BUF_SIZE (sizeof(struct n_hdlc_buf) + maxframe)
struct n_hdlc_buf_list {
- struct n_hdlc_buf *head;
- struct n_hdlc_buf *tail;
+ struct list_head list;
int count;
spinlock_t spinlock;
};
@@ -136,7 +135,6 @@ struct n_hdlc_buf_list {
* @backup_tty - TTY to use if tty gets closed
* @tbusy - reentrancy flag for tx wakeup code
* @woke_up - FIXME: describe this field
- * @tbuf - currently transmitting tx buffer
* @tx_buf_list - list of pending transmit frame buffers
* @rx_buf_list - list of received frame buffers
* @tx_free_buf_list - list unused transmit frame buffers
@@ -149,7 +147,6 @@ struct n_hdlc {
struct tty_struct *backup_tty;
int tbusy;
int woke_up;
- struct n_hdlc_buf *tbuf;
struct n_hdlc_buf_list tx_buf_list;
struct n_hdlc_buf_list rx_buf_list;
struct n_hdlc_buf_list tx_free_buf_list;
@@ -159,6 +156,8 @@ struct n_hdlc {
/*
* HDLC buffer list manipulation functions
*/
+static void n_hdlc_buf_return(struct n_hdlc_buf_list *buf_list,
+ struct n_hdlc_buf *buf);
static void n_hdlc_buf_put(struct n_hdlc_buf_list *list,
struct n_hdlc_buf *buf);
static struct n_hdlc_buf *n_hdlc_buf_get(struct n_hdlc_buf_list *list);
@@ -208,16 +207,9 @@ static void flush_tx_queue(struct tty_struct *tty)
{
struct n_hdlc *n_hdlc = tty2n_hdlc(tty);
struct n_hdlc_buf *buf;
- unsigned long flags;
while ((buf = n_hdlc_buf_get(&n_hdlc->tx_buf_list)))
n_hdlc_buf_put(&n_hdlc->tx_free_buf_list, buf);
- spin_lock_irqsave(&n_hdlc->tx_buf_list.spinlock, flags);
- if (n_hdlc->tbuf) {
- n_hdlc_buf_put(&n_hdlc->tx_free_buf_list, n_hdlc->tbuf);
- n_hdlc->tbuf = NULL;
- }
- spin_unlock_irqrestore(&n_hdlc->tx_buf_list.spinlock, flags);
}
static struct tty_ldisc_ops n_hdlc_ldisc = {
@@ -283,7 +275,6 @@ static void n_hdlc_release(struct n_hdlc *n_hdlc)
} else
break;
}
- kfree(n_hdlc->tbuf);
kfree(n_hdlc);
} /* end of n_hdlc_release() */
@@ -402,13 +393,7 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty)
n_hdlc->woke_up = 0;
spin_unlock_irqrestore(&n_hdlc->tx_buf_list.spinlock, flags);
- /* get current transmit buffer or get new transmit */
- /* buffer from list of pending transmit buffers */
-
- tbuf = n_hdlc->tbuf;
- if (!tbuf)
- tbuf = n_hdlc_buf_get(&n_hdlc->tx_buf_list);
-
+ tbuf = n_hdlc_buf_get(&n_hdlc->tx_buf_list);
while (tbuf) {
if (debuglevel >= DEBUG_LEVEL_INFO)
printk("%s(%d)sending frame %p, count=%d\n",
@@ -420,7 +405,7 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty)
/* rollback was possible and has been done */
if (actual == -ERESTARTSYS) {
- n_hdlc->tbuf = tbuf;
+ n_hdlc_buf_return(&n_hdlc->tx_buf_list, tbuf);
break;
}
/* if transmit error, throw frame away by */
@@ -435,10 +420,7 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty)
/* free current transmit buffer */
n_hdlc_buf_put(&n_hdlc->tx_free_buf_list, tbuf);
-
- /* this tx buffer is done */
- n_hdlc->tbuf = NULL;
-
+
/* wait up sleeping writers */
wake_up_interruptible(&tty->write_wait);
@@ -448,10 +430,12 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty)
if (debuglevel >= DEBUG_LEVEL_INFO)
printk("%s(%d)frame %p pending\n",
__FILE__,__LINE__,tbuf);
-
- /* buffer not accepted by driver */
- /* set this buffer as pending buffer */
- n_hdlc->tbuf = tbuf;
+
+ /*
+ * the buffer was not accepted by driver,
+ * return it back into tx queue
+ */
+ n_hdlc_buf_return(&n_hdlc->tx_buf_list, tbuf);
break;
}
}
@@ -749,7 +733,8 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file,
int error = 0;
int count;
unsigned long flags;
-
+ struct n_hdlc_buf *buf = NULL;
+
if (debuglevel >= DEBUG_LEVEL_INFO)
printk("%s(%d)n_hdlc_tty_ioctl() called %d\n",
__FILE__,__LINE__,cmd);
@@ -763,8 +748,10 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file,
/* report count of read data available */
/* in next available frame (if any) */
spin_lock_irqsave(&n_hdlc->rx_buf_list.spinlock,flags);
- if (n_hdlc->rx_buf_list.head)
- count = n_hdlc->rx_buf_list.head->count;
+ buf = list_first_entry_or_null(&n_hdlc->rx_buf_list.list,
+ struct n_hdlc_buf, list_item);
+ if (buf)
+ count = buf->count;
else
count = 0;
spin_unlock_irqrestore(&n_hdlc->rx_buf_list.spinlock,flags);
@@ -776,8 +763,10 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file,
count = tty_chars_in_buffer(tty);
/* add size of next output frame in queue */
spin_lock_irqsave(&n_hdlc->tx_buf_list.spinlock,flags);
- if (n_hdlc->tx_buf_list.head)
- count += n_hdlc->tx_buf_list.head->count;
+ buf = list_first_entry_or_null(&n_hdlc->tx_buf_list.list,
+ struct n_hdlc_buf, list_item);
+ if (buf)
+ count += buf->count;
spin_unlock_irqrestore(&n_hdlc->tx_buf_list.spinlock,flags);
error = put_user(count, (int __user *)arg);
break;
@@ -825,14 +814,14 @@ static unsigned int n_hdlc_tty_poll(struct tty_struct *tty, struct file *filp,
poll_wait(filp, &tty->write_wait, wait);
/* set bits for operations that won't block */
- if (n_hdlc->rx_buf_list.head)
+ if (!list_empty(&n_hdlc->rx_buf_list.list))
mask |= POLLIN | POLLRDNORM; /* readable */
if (test_bit(TTY_OTHER_CLOSED, &tty->flags))
mask |= POLLHUP;
if (tty_hung_up_p(filp))
mask |= POLLHUP;
if (!tty_is_writelocked(tty) &&
- n_hdlc->tx_free_buf_list.head)
+ !list_empty(&n_hdlc->tx_free_buf_list.list))
mask |= POLLOUT | POLLWRNORM; /* writable */
}
return mask;
@@ -856,7 +845,12 @@ static struct n_hdlc *n_hdlc_alloc(void)
spin_lock_init(&n_hdlc->tx_free_buf_list.spinlock);
spin_lock_init(&n_hdlc->rx_buf_list.spinlock);
spin_lock_init(&n_hdlc->tx_buf_list.spinlock);
-
+
+ INIT_LIST_HEAD(&n_hdlc->rx_free_buf_list.list);
+ INIT_LIST_HEAD(&n_hdlc->tx_free_buf_list.list);
+ INIT_LIST_HEAD(&n_hdlc->rx_buf_list.list);
+ INIT_LIST_HEAD(&n_hdlc->tx_buf_list.list);
+
/* allocate free rx buffer list */
for(i=0;i<DEFAULT_RX_BUF_COUNT;i++) {
buf = kmalloc(N_HDLC_BUF_SIZE, GFP_KERNEL);
@@ -884,53 +878,65 @@ static struct n_hdlc *n_hdlc_alloc(void)
} /* end of n_hdlc_alloc() */
/**
+ * n_hdlc_buf_return - put the HDLC buffer after the head of the specified list
+ * @buf_list - pointer to the buffer list
+ * @buf - pointer to the buffer
+ */
+static void n_hdlc_buf_return(struct n_hdlc_buf_list *buf_list,
+ struct n_hdlc_buf *buf)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&buf_list->spinlock, flags);
+
+ list_add(&buf->list_item, &buf_list->list);
+ buf_list->count++;
+
+ spin_unlock_irqrestore(&buf_list->spinlock, flags);
+}
+
+/**
* n_hdlc_buf_put - add specified HDLC buffer to tail of specified list
- * @list - pointer to buffer list
+ * @buf_list - pointer to buffer list
* @buf - pointer to buffer
*/
-static void n_hdlc_buf_put(struct n_hdlc_buf_list *list,
+static void n_hdlc_buf_put(struct n_hdlc_buf_list *buf_list,
struct n_hdlc_buf *buf)
{
unsigned long flags;
- spin_lock_irqsave(&list->spinlock,flags);
-
- buf->link=NULL;
- if (list->tail)
- list->tail->link = buf;
- else
- list->head = buf;
- list->tail = buf;
- (list->count)++;
-
- spin_unlock_irqrestore(&list->spinlock,flags);
-
+
+ spin_lock_irqsave(&buf_list->spinlock, flags);
+
+ list_add_tail(&buf->list_item, &buf_list->list);
+ buf_list->count++;
+
+ spin_unlock_irqrestore(&buf_list->spinlock, flags);
} /* end of n_hdlc_buf_put() */
/**
* n_hdlc_buf_get - remove and return an HDLC buffer from list
- * @list - pointer to HDLC buffer list
+ * @buf_list - pointer to HDLC buffer list
*
* Remove and return an HDLC buffer from the head of the specified HDLC buffer
* list.
* Returns a pointer to HDLC buffer if available, otherwise %NULL.
*/
-static struct n_hdlc_buf* n_hdlc_buf_get(struct n_hdlc_buf_list *list)
+static struct n_hdlc_buf *n_hdlc_buf_get(struct n_hdlc_buf_list *buf_list)
{
unsigned long flags;
struct n_hdlc_buf *buf;
- spin_lock_irqsave(&list->spinlock,flags);
-
- buf = list->head;
+
+ spin_lock_irqsave(&buf_list->spinlock, flags);
+
+ buf = list_first_entry_or_null(&buf_list->list,
+ struct n_hdlc_buf, list_item);
if (buf) {
- list->head = buf->link;
- (list->count)--;
+ list_del(&buf->list_item);
+ buf_list->count--;
}
- if (!list->head)
- list->tail = NULL;
-
- spin_unlock_irqrestore(&list->spinlock,flags);
+
+ spin_unlock_irqrestore(&buf_list->spinlock, flags);
return buf;
-
} /* end of n_hdlc_buf_get() */
static char hdlc_banner[] __initdata =
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index 6ee55a2..e65808c 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -257,7 +257,7 @@ static void dw8250_set_termios(struct uart_port *p, struct ktermios *termios,
{
unsigned int baud = tty_termios_baud_rate(termios);
struct dw8250_data *d = p->private_data;
- unsigned int rate;
+ long rate;
int ret;
if (IS_ERR(d->clk) || !old)
@@ -265,7 +265,12 @@ static void dw8250_set_termios(struct uart_port *p, struct ktermios *termios,
clk_disable_unprepare(d->clk);
rate = clk_round_rate(d->clk, baud * 16);
- ret = clk_set_rate(d->clk, rate);
+ if (rate < 0)
+ ret = rate;
+ else if (rate == 0)
+ ret = -ENOENT;
+ else
+ ret = clk_set_rate(d->clk, rate);
clk_prepare_enable(d->clk);
if (!ret)
diff --git a/drivers/tty/serial/8250/Kconfig b/drivers/tty/serial/8250/Kconfig
index a65fb81..0e3f529 100644
--- a/drivers/tty/serial/8250/Kconfig
+++ b/drivers/tty/serial/8250/Kconfig
@@ -128,9 +128,13 @@
by the parport_serial driver, enabled with CONFIG_PARPORT_SERIAL.
config SERIAL_8250_EXAR
- tristate "8250/16550 PCI device support"
- depends on SERIAL_8250_PCI
+ tristate "8250/16550 Exar/Commtech PCI/PCIe device support"
+ depends on SERIAL_8250_PCI
default SERIAL_8250
+ help
+ This builds support for XR17C1xx, XR17V3xx and some Commtech
+ 422x PCIe serial cards that are not covered by the more generic
+ SERIAL_8250_PCI option.
config SERIAL_8250_HP300
tristate
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 8789ea4..b0a3777 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -2373,7 +2373,7 @@ static int __init pl011_console_match(struct console *co, char *name, int idx,
if (strcmp(name, "qdf2400_e44") == 0) {
pr_info_once("UART: Working around QDF2400 SoC erratum 44");
qdf2400_e44_present = true;
- } else if (strcmp(name, "pl011") != 0 || strcmp(name, "ttyAMA") != 0) {
+ } else if (strcmp(name, "pl011") != 0) {
return -ENODEV;
}
@@ -2452,18 +2452,37 @@ static void pl011_early_write(struct console *con, const char *s, unsigned n)
uart_console_write(&dev->port, s, n, pl011_putc);
}
+/*
+ * On non-ACPI systems, earlycon is enabled by specifying
+ * "earlycon=pl011,<address>" on the kernel command line.
+ *
+ * On ACPI ARM64 systems, an "early" console is enabled via the SPCR table,
+ * by specifying only "earlycon" on the command line. Because it requires
+ * SPCR, the console starts after ACPI is parsed, which is later than a
+ * traditional early console.
+ *
+ * To get the traditional early console that starts before ACPI is parsed,
+ * specify the full "earlycon=pl011,<address>" option.
+ */
static int __init pl011_early_console_setup(struct earlycon_device *device,
const char *opt)
{
if (!device->port.membase)
return -ENODEV;
- device->con->write = qdf2400_e44_present ?
- qdf2400_e44_early_write : pl011_early_write;
+ /* On QDF2400 SOCs affected by Erratum 44, the "qdf2400_e44" must
+ * also be specified, e.g. "earlycon=pl011,<address>,qdf2400_e44".
+ */
+ if (!strcmp(device->options, "qdf2400_e44"))
+ device->con->write = qdf2400_e44_early_write;
+ else
+ device->con->write = pl011_early_write;
+
return 0;
}
OF_EARLYCON_DECLARE(pl011, "arm,pl011", pl011_early_console_setup);
OF_EARLYCON_DECLARE(pl011, "arm,sbsa-uart", pl011_early_console_setup);
+EARLYCON_DECLARE(qdf2400_e44, pl011_early_console_setup);
#else
#define AMBA_CONSOLE NULL
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index dcebb28..1f50a83 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -1951,6 +1951,11 @@ static void atmel_flush_buffer(struct uart_port *port)
atmel_uart_writel(port, ATMEL_PDC_TCR, 0);
atmel_port->pdc_tx.ofs = 0;
}
+ /*
+ * in uart_flush_buffer(), the xmit circular buffer has just
+ * been cleared, so we have to reset tx_len accordingly.
+ */
+ atmel_port->tx_len = 0;
}
/*
@@ -2483,6 +2488,9 @@ static void atmel_console_write(struct console *co, const char *s, u_int count)
pdc_tx = atmel_uart_readl(port, ATMEL_PDC_PTSR) & ATMEL_PDC_TXTEN;
atmel_uart_writel(port, ATMEL_PDC_PTCR, ATMEL_PDC_TXTDIS);
+ /* Make sure that tx path is actually able to send characters */
+ atmel_uart_writel(port, ATMEL_US_CR, ATMEL_US_TXEN);
+
uart_console_write(port, s, count, atmel_console_putchar);
/*
diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c
index 6989b227d..be94246 100644
--- a/drivers/tty/serial/mxs-auart.c
+++ b/drivers/tty/serial/mxs-auart.c
@@ -1088,7 +1088,7 @@ static void mxs_auart_settermios(struct uart_port *u,
AUART_LINECTRL_BAUD_DIV_MAX);
baud_max = u->uartclk * 32 / AUART_LINECTRL_BAUD_DIV_MIN;
baud = uart_get_baud_rate(u, termios, old, baud_min, baud_max);
- div = u->uartclk * 32 / baud;
+ div = DIV_ROUND_CLOSEST(u->uartclk * 32, baud);
}
ctrl |= AUART_LINECTRL_BAUD_DIVFRAC(div & 0x3F);
diff --git a/drivers/tty/serial/samsung.c b/drivers/tty/serial/samsung.c
index b4f86c2..7a17aed 100644
--- a/drivers/tty/serial/samsung.c
+++ b/drivers/tty/serial/samsung.c
@@ -1031,8 +1031,10 @@ static int s3c64xx_serial_startup(struct uart_port *port)
if (ourport->dma) {
ret = s3c24xx_serial_request_dma(ourport);
if (ret < 0) {
- dev_warn(port->dev, "DMA request failed\n");
- return ret;
+ dev_warn(port->dev,
+ "DMA request failed, DMA will not be used\n");
+ devm_kfree(port->dev, ourport->dma);
+ ourport->dma = NULL;
}
}
diff --git a/drivers/tty/serial/st-asc.c b/drivers/tty/serial/st-asc.c
index bcf1d33..c334bcc 100644
--- a/drivers/tty/serial/st-asc.c
+++ b/drivers/tty/serial/st-asc.c
@@ -575,12 +575,13 @@ static void asc_set_termios(struct uart_port *port, struct ktermios *termios,
pinctrl_select_state(ascport->pinctrl,
ascport->states[NO_HW_FLOWCTRL]);
- gpiod = devm_get_gpiod_from_child(port->dev, "rts",
- &np->fwnode);
- if (!IS_ERR(gpiod)) {
- gpiod_direction_output(gpiod, 0);
+ gpiod = devm_fwnode_get_gpiod_from_child(port->dev,
+ "rts",
+ &np->fwnode,
+ GPIOD_OUT_LOW,
+ np->name);
+ if (!IS_ERR(gpiod))
ascport->rts = gpiod;
- }
}
}
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index c6fc714..677f0dd 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -446,7 +446,7 @@ static struct sysrq_key_op *sysrq_key_table[36] = {
*/
NULL, /* a */
&sysrq_reboot_op, /* b */
- &sysrq_crash_op, /* c & ibm_emac driver debug */
+ &sysrq_crash_op, /* c */
&sysrq_showlocks_op, /* d */
&sysrq_term_op, /* e */
&sysrq_moom_op, /* f */
diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c
index 68947f6..b0500a0 100644
--- a/drivers/tty/tty_ldisc.c
+++ b/drivers/tty/tty_ldisc.c
@@ -271,10 +271,13 @@ const struct file_operations tty_ldiscs_proc_fops = {
struct tty_ldisc *tty_ldisc_ref_wait(struct tty_struct *tty)
{
+ struct tty_ldisc *ld;
+
ldsem_down_read(&tty->ldisc_sem, MAX_SCHEDULE_TIMEOUT);
- if (!tty->ldisc)
+ ld = tty->ldisc;
+ if (!ld)
ldsem_up_read(&tty->ldisc_sem);
- return tty->ldisc;
+ return ld;
}
EXPORT_SYMBOL_GPL(tty_ldisc_ref_wait);
@@ -489,41 +492,6 @@ static void tty_ldisc_close(struct tty_struct *tty, struct tty_ldisc *ld)
}
/**
- * tty_ldisc_restore - helper for tty ldisc change
- * @tty: tty to recover
- * @old: previous ldisc
- *
- * Restore the previous line discipline or N_TTY when a line discipline
- * change fails due to an open error
- */
-
-static void tty_ldisc_restore(struct tty_struct *tty, struct tty_ldisc *old)
-{
- struct tty_ldisc *new_ldisc;
- int r;
-
- /* There is an outstanding reference here so this is safe */
- old = tty_ldisc_get(tty, old->ops->num);
- WARN_ON(IS_ERR(old));
- tty->ldisc = old;
- tty_set_termios_ldisc(tty, old->ops->num);
- if (tty_ldisc_open(tty, old) < 0) {
- tty_ldisc_put(old);
- /* This driver is always present */
- new_ldisc = tty_ldisc_get(tty, N_TTY);
- if (IS_ERR(new_ldisc))
- panic("n_tty: get");
- tty->ldisc = new_ldisc;
- tty_set_termios_ldisc(tty, N_TTY);
- r = tty_ldisc_open(tty, new_ldisc);
- if (r < 0)
- panic("Couldn't open N_TTY ldisc for "
- "%s --- error %d.",
- tty_name(tty), r);
- }
-}
-
-/**
* tty_set_ldisc - set line discipline
* @tty: the terminal to set
* @ldisc: the line discipline
@@ -536,12 +504,7 @@ static void tty_ldisc_restore(struct tty_struct *tty, struct tty_ldisc *old)
int tty_set_ldisc(struct tty_struct *tty, int disc)
{
- int retval;
- struct tty_ldisc *old_ldisc, *new_ldisc;
-
- new_ldisc = tty_ldisc_get(tty, disc);
- if (IS_ERR(new_ldisc))
- return PTR_ERR(new_ldisc);
+ int retval, old_disc;
tty_lock(tty);
retval = tty_ldisc_lock(tty, 5 * HZ);
@@ -554,7 +517,8 @@ int tty_set_ldisc(struct tty_struct *tty, int disc)
}
/* Check the no-op case */
- if (tty->ldisc->ops->num == disc)
+ old_disc = tty->ldisc->ops->num;
+ if (old_disc == disc)
goto out;
if (test_bit(TTY_HUPPED, &tty->flags)) {
@@ -563,34 +527,25 @@ int tty_set_ldisc(struct tty_struct *tty, int disc)
goto out;
}
- old_ldisc = tty->ldisc;
-
- /* Shutdown the old discipline. */
- tty_ldisc_close(tty, old_ldisc);
-
- /* Now set up the new line discipline. */
- tty->ldisc = new_ldisc;
- tty_set_termios_ldisc(tty, disc);
-
- retval = tty_ldisc_open(tty, new_ldisc);
+ retval = tty_ldisc_reinit(tty, disc);
if (retval < 0) {
/* Back to the old one or N_TTY if we can't */
- tty_ldisc_put(new_ldisc);
- tty_ldisc_restore(tty, old_ldisc);
+ if (tty_ldisc_reinit(tty, old_disc) < 0) {
+ pr_err("tty: TIOCSETD failed, reinitializing N_TTY\n");
+ if (tty_ldisc_reinit(tty, N_TTY) < 0) {
+ /* At this point we have tty->ldisc == NULL. */
+ pr_err("tty: reinitializing N_TTY failed\n");
+ }
+ }
}
- if (tty->ldisc->ops->num != old_ldisc->ops->num && tty->ops->set_ldisc) {
+ if (tty->ldisc && tty->ldisc->ops->num != old_disc &&
+ tty->ops->set_ldisc) {
down_read(&tty->termios_rwsem);
tty->ops->set_ldisc(tty);
up_read(&tty->termios_rwsem);
}
- /* At this point we hold a reference to the new ldisc and a
- reference to the old ldisc, or we hold two references to
- the old ldisc (if it was restored as part of error cleanup
- above). In either case, releasing a single reference from
- the old ldisc is correct. */
- new_ldisc = old_ldisc;
out:
tty_ldisc_unlock(tty);
@@ -598,7 +553,6 @@ int tty_set_ldisc(struct tty_struct *tty, int disc)
already running */
tty_buffer_restart_work(tty->port);
err:
- tty_ldisc_put(new_ldisc); /* drop the extra reference */
tty_unlock(tty);
return retval;
}
@@ -659,10 +613,8 @@ int tty_ldisc_reinit(struct tty_struct *tty, int disc)
int retval;
ld = tty_ldisc_get(tty, disc);
- if (IS_ERR(ld)) {
- BUG_ON(disc == N_TTY);
+ if (IS_ERR(ld))
return PTR_ERR(ld);
- }
if (tty->ldisc) {
tty_ldisc_close(tty, tty->ldisc);
@@ -674,10 +626,8 @@ int tty_ldisc_reinit(struct tty_struct *tty, int disc)
tty_set_termios_ldisc(tty, disc);
retval = tty_ldisc_open(tty, tty->ldisc);
if (retval) {
- if (!WARN_ON(disc == N_TTY)) {
- tty_ldisc_put(tty->ldisc);
- tty->ldisc = NULL;
- }
+ tty_ldisc_put(tty->ldisc);
+ tty->ldisc = NULL;
}
return retval;
}
diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index c5f0fc9..8af8d95 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -28,7 +28,6 @@
#include <linux/module.h>
#include <linux/sched/signal.h>
#include <linux/sched/debug.h>
-#include <linux/sched/debug.h>
#include <linux/tty.h>
#include <linux/tty_flip.h>
#include <linux/mm.h>
diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c
index f03692e..8fb309a 100644
--- a/drivers/usb/class/usbtmc.c
+++ b/drivers/usb/class/usbtmc.c
@@ -1381,7 +1381,7 @@ static int usbtmc_probe(struct usb_interface *intf,
dev_dbg(&intf->dev, "%s called\n", __func__);
- data = kmalloc(sizeof(*data), GFP_KERNEL);
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
if (!data)
return -ENOMEM;
@@ -1444,6 +1444,13 @@ static int usbtmc_probe(struct usb_interface *intf,
break;
}
}
+
+ if (!data->bulk_out || !data->bulk_in) {
+ dev_err(&intf->dev, "bulk endpoints not found\n");
+ retcode = -ENODEV;
+ goto err_put;
+ }
+
/* Find int endpoint */
for (n = 0; n < iface_desc->desc.bNumEndpoints; n++) {
endpoint = &iface_desc->endpoint[n].desc;
@@ -1469,8 +1476,10 @@ static int usbtmc_probe(struct usb_interface *intf,
if (data->iin_ep_present) {
/* allocate int urb */
data->iin_urb = usb_alloc_urb(0, GFP_KERNEL);
- if (!data->iin_urb)
+ if (!data->iin_urb) {
+ retcode = -ENOMEM;
goto error_register;
+ }
/* Protect interrupt in endpoint data until iin_urb is freed */
kref_get(&data->kref);
@@ -1478,8 +1487,10 @@ static int usbtmc_probe(struct usb_interface *intf,
/* allocate buffer for interrupt in */
data->iin_buffer = kmalloc(data->iin_wMaxPacketSize,
GFP_KERNEL);
- if (!data->iin_buffer)
+ if (!data->iin_buffer) {
+ retcode = -ENOMEM;
goto error_register;
+ }
/* fill interrupt urb */
usb_fill_int_urb(data->iin_urb, data->usb_dev,
@@ -1512,6 +1523,7 @@ static int usbtmc_probe(struct usb_interface *intf,
sysfs_remove_group(&intf->dev.kobj, &capability_attr_grp);
sysfs_remove_group(&intf->dev.kobj, &data_attr_grp);
usbtmc_free_int(data);
+err_put:
kref_put(&data->kref, usbtmc_delete);
return retcode;
}
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index 25dbd8c..4be52c6 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -280,6 +280,16 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum,
/*
* Adjust bInterval for quirked devices.
+ */
+ /*
+ * This quirk fixes bIntervals reported in ms.
+ */
+ if (to_usb_device(ddev)->quirks &
+ USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL) {
+ n = clamp(fls(d->bInterval) + 3, i, j);
+ i = j = n;
+ }
+ /*
* This quirk fixes bIntervals reported in
* linear microframes.
*/
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 612fab6..79bdca5 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -520,8 +520,10 @@ static int rh_call_control (struct usb_hcd *hcd, struct urb *urb)
*/
tbuf_size = max_t(u16, sizeof(struct usb_hub_descriptor), wLength);
tbuf = kzalloc(tbuf_size, GFP_KERNEL);
- if (!tbuf)
- return -ENOMEM;
+ if (!tbuf) {
+ status = -ENOMEM;
+ goto err_alloc;
+ }
bufp = tbuf;
@@ -734,6 +736,7 @@ static int rh_call_control (struct usb_hcd *hcd, struct urb *urb)
}
kfree(tbuf);
+ err_alloc:
/* any errors get returned through the urb completion */
spin_lock_irq(&hcd_root_hub_lock);
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index f0dd081..5286bf6 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -4275,7 +4275,7 @@ static void hub_set_initial_usb2_lpm_policy(struct usb_device *udev)
struct usb_hub *hub = usb_hub_to_struct_hub(udev->parent);
int connect_type = USB_PORT_CONNECT_TYPE_UNKNOWN;
- if (!udev->usb2_hw_lpm_capable)
+ if (!udev->usb2_hw_lpm_capable || !udev->bos)
return;
if (hub)
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 24f9f98..96b21b0 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -170,6 +170,14 @@ static const struct usb_device_id usb_quirk_list[] = {
/* M-Systems Flash Disk Pioneers */
{ USB_DEVICE(0x08ec, 0x1000), .driver_info = USB_QUIRK_RESET_RESUME },
+ /* Baum Vario Ultra */
+ { USB_DEVICE(0x0904, 0x6101), .driver_info =
+ USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL },
+ { USB_DEVICE(0x0904, 0x6102), .driver_info =
+ USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL },
+ { USB_DEVICE(0x0904, 0x6103), .driver_info =
+ USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL },
+
/* Keytouch QWERTY Panel keyboard */
{ USB_DEVICE(0x0926, 0x3333), .driver_info =
USB_QUIRK_CONFIG_INTF_STRINGS },
diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c
index 2092e46..f8d0747 100644
--- a/drivers/usb/dwc3/dwc3-omap.c
+++ b/drivers/usb/dwc3/dwc3-omap.c
@@ -250,6 +250,7 @@ static void dwc3_omap_set_mailbox(struct dwc3_omap *omap,
val = dwc3_omap_read_utmi_ctrl(omap);
val |= USBOTGSS_UTMI_OTG_CTRL_IDDIG;
dwc3_omap_write_utmi_ctrl(omap, val);
+ break;
case OMAP_DWC3_VBUS_OFF:
val = dwc3_omap_read_utmi_ctrl(omap);
@@ -392,7 +393,7 @@ static void dwc3_omap_set_utmi_mode(struct dwc3_omap *omap)
{
u32 reg;
struct device_node *node = omap->dev->of_node;
- int utmi_mode = 0;
+ u32 utmi_mode = 0;
reg = dwc3_omap_read_utmi_ctrl(omap);
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 4db97ec..79e7a34 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -171,6 +171,7 @@ void dwc3_gadget_giveback(struct dwc3_ep *dep, struct dwc3_request *req,
int status)
{
struct dwc3 *dwc = dep->dwc;
+ unsigned int unmap_after_complete = false;
req->started = false;
list_del(&req->list);
@@ -180,11 +181,19 @@ void dwc3_gadget_giveback(struct dwc3_ep *dep, struct dwc3_request *req,
if (req->request.status == -EINPROGRESS)
req->request.status = status;
- if (dwc->ep0_bounced && dep->number <= 1)
+ /*
+ * NOTICE we don't want to unmap before calling ->complete() if we're
+ * dealing with a bounced ep0 request. If we unmap it here, we would end
+ * up overwritting the contents of req->buf and this could confuse the
+ * gadget driver.
+ */
+ if (dwc->ep0_bounced && dep->number <= 1) {
dwc->ep0_bounced = false;
-
- usb_gadget_unmap_request_by_dev(dwc->sysdev,
- &req->request, req->direction);
+ unmap_after_complete = true;
+ } else {
+ usb_gadget_unmap_request_by_dev(dwc->sysdev,
+ &req->request, req->direction);
+ }
trace_dwc3_gadget_giveback(req);
@@ -192,6 +201,10 @@ void dwc3_gadget_giveback(struct dwc3_ep *dep, struct dwc3_request *req,
usb_gadget_giveback_request(&dep->endpoint, &req->request);
spin_lock(&dwc->lock);
+ if (unmap_after_complete)
+ usb_gadget_unmap_request_by_dev(dwc->sysdev,
+ &req->request, req->direction);
+
if (dep->number > 1)
pm_runtime_put(dwc->dev);
}
@@ -1342,6 +1355,68 @@ static int dwc3_gadget_ep_dequeue(struct usb_ep *ep,
if (r == req) {
/* wait until it is processed */
dwc3_stop_active_transfer(dwc, dep->number, true);
+
+ /*
+ * If request was already started, this means we had to
+ * stop the transfer. With that we also need to ignore
+ * all TRBs used by the request, however TRBs can only
+ * be modified after completion of END_TRANSFER
+ * command. So what we do here is that we wait for
+ * END_TRANSFER completion and only after that, we jump
+ * over TRBs by clearing HWO and incrementing dequeue
+ * pointer.
+ *
+ * Note that we have 2 possible types of transfers here:
+ *
+ * i) Linear buffer request
+ * ii) SG-list based request
+ *
+ * SG-list based requests will have r->num_pending_sgs
+ * set to a valid number (> 0). Linear requests,
+ * normally use a single TRB.
+ *
+ * For each of these two cases, if r->unaligned flag is
+ * set, one extra TRB has been used to align transfer
+ * size to wMaxPacketSize.
+ *
+ * All of these cases need to be taken into
+ * consideration so we don't mess up our TRB ring
+ * pointers.
+ */
+ wait_event_lock_irq(dep->wait_end_transfer,
+ !(dep->flags & DWC3_EP_END_TRANSFER_PENDING),
+ dwc->lock);
+
+ if (!r->trb)
+ goto out1;
+
+ if (r->num_pending_sgs) {
+ struct dwc3_trb *trb;
+ int i = 0;
+
+ for (i = 0; i < r->num_pending_sgs; i++) {
+ trb = r->trb + i;
+ trb->ctrl &= ~DWC3_TRB_CTRL_HWO;
+ dwc3_ep_inc_deq(dep);
+ }
+
+ if (r->unaligned) {
+ trb = r->trb + r->num_pending_sgs + 1;
+ trb->ctrl &= ~DWC3_TRB_CTRL_HWO;
+ dwc3_ep_inc_deq(dep);
+ }
+ } else {
+ struct dwc3_trb *trb = r->trb;
+
+ trb->ctrl &= ~DWC3_TRB_CTRL_HWO;
+ dwc3_ep_inc_deq(dep);
+
+ if (r->unaligned) {
+ trb = r->trb + 1;
+ trb->ctrl &= ~DWC3_TRB_CTRL_HWO;
+ dwc3_ep_inc_deq(dep);
+ }
+ }
goto out1;
}
dev_err(dwc->dev, "request %p was not queued to %s\n",
@@ -1352,6 +1427,7 @@ static int dwc3_gadget_ep_dequeue(struct usb_ep *ep,
out1:
/* giveback the request */
+ dep->queued_requests--;
dwc3_gadget_giveback(dep, req, -ECONNRESET);
out0:
@@ -2126,12 +2202,12 @@ static int __dwc3_cleanup_done_trbs(struct dwc3 *dwc, struct dwc3_ep *dep,
return 1;
}
- if ((trb->ctrl & DWC3_TRB_CTRL_HWO) && status != -ESHUTDOWN)
- return 1;
-
count = trb->size & DWC3_TRB_SIZE_MASK;
req->remaining += count;
+ if ((trb->ctrl & DWC3_TRB_CTRL_HWO) && status != -ESHUTDOWN)
+ return 1;
+
if (dep->direction) {
if (count) {
trb_status = DWC3_TRB_SIZE_TRBSTS(trb->size);
@@ -3228,15 +3304,10 @@ void dwc3_gadget_exit(struct dwc3 *dwc)
int dwc3_gadget_suspend(struct dwc3 *dwc)
{
- int ret;
-
if (!dwc->gadget_driver)
return 0;
- ret = dwc3_gadget_run_stop(dwc, false, false);
- if (ret < 0)
- return ret;
-
+ dwc3_gadget_run_stop(dwc, false, false);
dwc3_disconnect_gadget(dwc);
__dwc3_gadget_stop(dwc);
diff --git a/drivers/usb/dwc3/gadget.h b/drivers/usb/dwc3/gadget.h
index 3129bcf..265e223 100644
--- a/drivers/usb/dwc3/gadget.h
+++ b/drivers/usb/dwc3/gadget.h
@@ -28,23 +28,23 @@ struct dwc3;
#define gadget_to_dwc(g) (container_of(g, struct dwc3, gadget))
/* DEPCFG parameter 1 */
-#define DWC3_DEPCFG_INT_NUM(n) ((n) << 0)
+#define DWC3_DEPCFG_INT_NUM(n) (((n) & 0x1f) << 0)
#define DWC3_DEPCFG_XFER_COMPLETE_EN (1 << 8)
#define DWC3_DEPCFG_XFER_IN_PROGRESS_EN (1 << 9)
#define DWC3_DEPCFG_XFER_NOT_READY_EN (1 << 10)
#define DWC3_DEPCFG_FIFO_ERROR_EN (1 << 11)
#define DWC3_DEPCFG_STREAM_EVENT_EN (1 << 13)
-#define DWC3_DEPCFG_BINTERVAL_M1(n) ((n) << 16)
+#define DWC3_DEPCFG_BINTERVAL_M1(n) (((n) & 0xff) << 16)
#define DWC3_DEPCFG_STREAM_CAPABLE (1 << 24)
-#define DWC3_DEPCFG_EP_NUMBER(n) ((n) << 25)
+#define DWC3_DEPCFG_EP_NUMBER(n) (((n) & 0x1f) << 25)
#define DWC3_DEPCFG_BULK_BASED (1 << 30)
#define DWC3_DEPCFG_FIFO_BASED (1 << 31)
/* DEPCFG parameter 0 */
-#define DWC3_DEPCFG_EP_TYPE(n) ((n) << 1)
-#define DWC3_DEPCFG_MAX_PACKET_SIZE(n) ((n) << 3)
-#define DWC3_DEPCFG_FIFO_NUMBER(n) ((n) << 17)
-#define DWC3_DEPCFG_BURST_SIZE(n) ((n) << 22)
+#define DWC3_DEPCFG_EP_TYPE(n) (((n) & 0x3) << 1)
+#define DWC3_DEPCFG_MAX_PACKET_SIZE(n) (((n) & 0x7ff) << 3)
+#define DWC3_DEPCFG_FIFO_NUMBER(n) (((n) & 0x1f) << 17)
+#define DWC3_DEPCFG_BURST_SIZE(n) (((n) & 0xf) << 22)
#define DWC3_DEPCFG_DATA_SEQ_NUM(n) ((n) << 26)
/* This applies for core versions earlier than 1.94a */
#define DWC3_DEPCFG_IGN_SEQ_NUM (1 << 31)
diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index 78c4497..cbff3b0 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -269,6 +269,7 @@ static ssize_t gadget_dev_desc_UDC_store(struct config_item *item,
ret = unregister_gadget(gi);
if (ret)
goto err;
+ kfree(name);
} else {
if (gi->composite.gadget_driver.udc_name) {
ret = -EBUSY;
diff --git a/drivers/usb/gadget/function/f_acm.c b/drivers/usb/gadget/function/f_acm.c
index a30766c..5e3828d 100644
--- a/drivers/usb/gadget/function/f_acm.c
+++ b/drivers/usb/gadget/function/f_acm.c
@@ -535,13 +535,15 @@ static int acm_notify_serial_state(struct f_acm *acm)
{
struct usb_composite_dev *cdev = acm->port.func.config->cdev;
int status;
+ __le16 serial_state;
spin_lock(&acm->lock);
if (acm->notify_req) {
dev_dbg(&cdev->gadget->dev, "acm ttyGS%d serial state %04x\n",
acm->port_num, acm->serial_state);
+ serial_state = cpu_to_le16(acm->serial_state);
status = acm_cdc_notify(acm, USB_CDC_NOTIFY_SERIAL_STATE,
- 0, &acm->serial_state, sizeof(acm->serial_state));
+ 0, &serial_state, sizeof(acm->serial_state));
} else {
acm->pending = true;
status = 0;
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index a5b7cd6..a008557 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -1834,11 +1834,14 @@ static int ffs_func_eps_enable(struct ffs_function *func)
spin_lock_irqsave(&func->ffs->eps_lock, flags);
while(count--) {
struct usb_endpoint_descriptor *ds;
+ struct usb_ss_ep_comp_descriptor *comp_desc = NULL;
+ int needs_comp_desc = false;
int desc_idx;
- if (ffs->gadget->speed == USB_SPEED_SUPER)
+ if (ffs->gadget->speed == USB_SPEED_SUPER) {
desc_idx = 2;
- else if (ffs->gadget->speed == USB_SPEED_HIGH)
+ needs_comp_desc = true;
+ } else if (ffs->gadget->speed == USB_SPEED_HIGH)
desc_idx = 1;
else
desc_idx = 0;
@@ -1855,6 +1858,14 @@ static int ffs_func_eps_enable(struct ffs_function *func)
ep->ep->driver_data = ep;
ep->ep->desc = ds;
+
+ comp_desc = (struct usb_ss_ep_comp_descriptor *)(ds +
+ USB_DT_ENDPOINT_SIZE);
+ ep->ep->maxburst = comp_desc->bMaxBurst + 1;
+
+ if (needs_comp_desc)
+ ep->ep->comp_desc = comp_desc;
+
ret = usb_ep_enable(ep->ep);
if (likely(!ret)) {
epfile->ep = ep;
@@ -2253,7 +2264,7 @@ static int __ffs_data_do_os_desc(enum ffs_os_desc_type type,
if (len < sizeof(*d) ||
d->bFirstInterfaceNumber >= ffs->interfaces_count ||
- d->Reserved1)
+ !d->Reserved1)
return -EINVAL;
for (i = 0; i < ARRAY_SIZE(d->Reserved2); ++i)
if (d->Reserved2[i])
diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c
index 89b48bc..5eea448 100644
--- a/drivers/usb/gadget/function/f_hid.c
+++ b/drivers/usb/gadget/function/f_hid.c
@@ -367,7 +367,7 @@ static ssize_t f_hidg_write(struct file *file, const char __user *buffer,
count = min_t(unsigned, count, hidg->report_length);
spin_unlock_irqrestore(&hidg->write_spinlock, flags);
- status = copy_from_user(hidg->req->buf, buffer, count);
+ status = copy_from_user(req->buf, buffer, count);
if (status != 0) {
ERROR(hidg->func.config->cdev,
@@ -378,9 +378,9 @@ static ssize_t f_hidg_write(struct file *file, const char __user *buffer,
spin_lock_irqsave(&hidg->write_spinlock, flags);
- /* we our function has been disabled by host */
+ /* when our function has been disabled by host */
if (!hidg->req) {
- free_ep_req(hidg->in_ep, hidg->req);
+ free_ep_req(hidg->in_ep, req);
/*
* TODO
* Should we fail with error here?
@@ -394,7 +394,7 @@ static ssize_t f_hidg_write(struct file *file, const char __user *buffer,
req->complete = f_hidg_req_complete;
req->context = hidg;
- status = usb_ep_queue(hidg->in_ep, hidg->req, GFP_ATOMIC);
+ status = usb_ep_queue(hidg->in_ep, req, GFP_ATOMIC);
if (status < 0) {
ERROR(hidg->func.config->cdev,
"usb_ep_queue error on int endpoint %zd\n", status);
diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index 224717e6..864819f 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -16,6 +16,7 @@
*/
#include <linux/kernel.h>
+#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/device.h>
#include <linux/etherdevice.h>
diff --git a/drivers/usb/gadget/function/f_uvc.c b/drivers/usb/gadget/function/f_uvc.c
index 27ed51b..f8a1881 100644
--- a/drivers/usb/gadget/function/f_uvc.c
+++ b/drivers/usb/gadget/function/f_uvc.c
@@ -258,13 +258,6 @@ uvc_function_setup(struct usb_function *f, const struct usb_ctrlrequest *ctrl)
memcpy(&uvc_event->req, ctrl, sizeof(uvc_event->req));
v4l2_event_queue(&uvc->vdev, &v4l2_event);
- /* Pass additional setup data to userspace */
- if (uvc->event_setup_out && uvc->event_length) {
- uvc->control_req->length = uvc->event_length;
- return usb_ep_queue(uvc->func.config->cdev->gadget->ep0,
- uvc->control_req, GFP_ATOMIC);
- }
-
return 0;
}
@@ -601,6 +594,14 @@ uvc_function_bind(struct usb_configuration *c, struct usb_function *f)
opts->streaming_maxpacket = clamp(opts->streaming_maxpacket, 1U, 3072U);
opts->streaming_maxburst = min(opts->streaming_maxburst, 15U);
+ /* For SS, wMaxPacketSize has to be 1024 if bMaxBurst is not 0 */
+ if (opts->streaming_maxburst &&
+ (opts->streaming_maxpacket % 1024) != 0) {
+ opts->streaming_maxpacket = roundup(opts->streaming_maxpacket, 1024);
+ INFO(cdev, "overriding streaming_maxpacket to %d\n",
+ opts->streaming_maxpacket);
+ }
+
/* Fill in the FS/HS/SS Video Streaming specific descriptors from the
* module parameters.
*
@@ -632,7 +633,7 @@ uvc_function_bind(struct usb_configuration *c, struct usb_function *f)
uvc_ss_streaming_comp.bMaxBurst = opts->streaming_maxburst;
uvc_ss_streaming_comp.wBytesPerInterval =
cpu_to_le16(max_packet_size * max_packet_mult *
- opts->streaming_maxburst);
+ (opts->streaming_maxburst + 1));
/* Allocate endpoints. */
ep = usb_ep_autoconfig(cdev->gadget, &uvc_control_ep);
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index a2615d6..a2c9168 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -84,8 +84,7 @@ static int ep_open(struct inode *, struct file *);
/* /dev/gadget/$CHIP represents ep0 and the whole device */
enum ep0_state {
- /* DISBLED is the initial state.
- */
+ /* DISABLED is the initial state. */
STATE_DEV_DISABLED = 0,
/* Only one open() of /dev/gadget/$CHIP; only one file tracks
@@ -1782,8 +1781,10 @@ dev_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr)
spin_lock_irq (&dev->lock);
value = -EINVAL;
- if (dev->buf)
+ if (dev->buf) {
+ kfree(kbuf);
goto fail;
+ }
dev->buf = kbuf;
/* full or low speed config */
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index 11bbce2..2035906 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -610,7 +610,7 @@ usba_ep_enable(struct usb_ep *_ep, const struct usb_endpoint_descriptor *desc)
{
struct usba_ep *ep = to_usba_ep(_ep);
struct usba_udc *udc = ep->udc;
- unsigned long flags, ept_cfg, maxpacket;
+ unsigned long flags, maxpacket;
unsigned int nr_trans;
DBG(DBG_GADGET, "%s: ep_enable: desc=%p\n", ep->ep.name, desc);
@@ -630,7 +630,7 @@ usba_ep_enable(struct usb_ep *_ep, const struct usb_endpoint_descriptor *desc)
ep->is_in = 0;
DBG(DBG_ERR, "%s: EPT_CFG = 0x%lx (maxpacket = %lu)\n",
- ep->ep.name, ept_cfg, maxpacket);
+ ep->ep.name, ep->ept_cfg, maxpacket);
if (usb_endpoint_dir_in(desc)) {
ep->is_in = 1;
diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
index c60abe3..8cabc59 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -1031,6 +1031,8 @@ static int dummy_udc_probe(struct platform_device *pdev)
int rc;
dum = *((void **)dev_get_platdata(&pdev->dev));
+ /* Clear usb_gadget region for new registration to udc-core */
+ memzero_explicit(&dum->gadget, sizeof(struct usb_gadget));
dum->gadget.name = gadget_name;
dum->gadget.ops = &dummy_ops;
dum->gadget.max_speed = USB_SPEED_SUPER;
diff --git a/drivers/usb/gadget/udc/net2280.c b/drivers/usb/gadget/udc/net2280.c
index 8550441..3828c2e 100644
--- a/drivers/usb/gadget/udc/net2280.c
+++ b/drivers/usb/gadget/udc/net2280.c
@@ -1146,15 +1146,15 @@ static int scan_dma_completions(struct net2280_ep *ep)
*/
while (!list_empty(&ep->queue)) {
struct net2280_request *req;
- u32 tmp;
+ u32 req_dma_count;
req = list_entry(ep->queue.next,
struct net2280_request, queue);
if (!req->valid)
break;
rmb();
- tmp = le32_to_cpup(&req->td->dmacount);
- if ((tmp & BIT(VALID_BIT)) != 0)
+ req_dma_count = le32_to_cpup(&req->td->dmacount);
+ if ((req_dma_count & BIT(VALID_BIT)) != 0)
break;
/* SHORT_PACKET_TRANSFERRED_INTERRUPT handles "usb-short"
@@ -1163,40 +1163,41 @@ static int scan_dma_completions(struct net2280_ep *ep)
*/
if (unlikely(req->td->dmadesc == 0)) {
/* paranoia */
- tmp = readl(&ep->dma->dmacount);
- if (tmp & DMA_BYTE_COUNT_MASK)
+ u32 const ep_dmacount = readl(&ep->dma->dmacount);
+
+ if (ep_dmacount & DMA_BYTE_COUNT_MASK)
break;
/* single transfer mode */
- dma_done(ep, req, tmp, 0);
+ dma_done(ep, req, req_dma_count, 0);
num_completed++;
break;
} else if (!ep->is_in &&
(req->req.length % ep->ep.maxpacket) &&
!(ep->dev->quirks & PLX_PCIE)) {
- tmp = readl(&ep->regs->ep_stat);
+ u32 const ep_stat = readl(&ep->regs->ep_stat);
/* AVOID TROUBLE HERE by not issuing short reads from
* your gadget driver. That helps avoids errata 0121,
* 0122, and 0124; not all cases trigger the warning.
*/
- if ((tmp & BIT(NAK_OUT_PACKETS)) == 0) {
+ if ((ep_stat & BIT(NAK_OUT_PACKETS)) == 0) {
ep_warn(ep->dev, "%s lost packet sync!\n",
ep->ep.name);
req->req.status = -EOVERFLOW;
} else {
- tmp = readl(&ep->regs->ep_avail);
- if (tmp) {
+ u32 const ep_avail = readl(&ep->regs->ep_avail);
+ if (ep_avail) {
/* fifo gets flushed later */
ep->out_overflow = 1;
ep_dbg(ep->dev,
"%s dma, discard %d len %d\n",
- ep->ep.name, tmp,
+ ep->ep.name, ep_avail,
req->req.length);
req->req.status = -EOVERFLOW;
}
}
}
- dma_done(ep, req, tmp, 0);
+ dma_done(ep, req, req_dma_count, 0);
num_completed++;
}
diff --git a/drivers/usb/gadget/udc/pch_udc.c b/drivers/usb/gadget/udc/pch_udc.c
index a97da64..8a365aa 100644
--- a/drivers/usb/gadget/udc/pch_udc.c
+++ b/drivers/usb/gadget/udc/pch_udc.c
@@ -1523,7 +1523,6 @@ static void pch_udc_free_dma_chain(struct pch_udc_dev *dev,
td = phys_to_virt(addr);
addr2 = (dma_addr_t)td->next;
pci_pool_free(dev->data_requests, td, addr);
- td->next = 0x00;
addr = addr2;
}
req->chain_len = 1;
diff --git a/drivers/usb/gadget/udc/pxa27x_udc.c b/drivers/usb/gadget/udc/pxa27x_udc.c
index e1335ad..832c4fd 100644
--- a/drivers/usb/gadget/udc/pxa27x_udc.c
+++ b/drivers/usb/gadget/udc/pxa27x_udc.c
@@ -2534,9 +2534,10 @@ static int pxa_udc_remove(struct platform_device *_dev)
usb_del_gadget_udc(&udc->gadget);
pxa_cleanup_debugfs(udc);
- if (!IS_ERR_OR_NULL(udc->transceiver))
+ if (!IS_ERR_OR_NULL(udc->transceiver)) {
usb_unregister_notifier(udc->transceiver, &pxa27x_udc_phy);
- usb_put_phy(udc->transceiver);
+ usb_put_phy(udc->transceiver);
+ }
udc->transceiver = NULL;
the_controller = NULL;
diff --git a/drivers/usb/host/ohci-at91.c b/drivers/usb/host/ohci-at91.c
index 414e3c3..5302f98 100644
--- a/drivers/usb/host/ohci-at91.c
+++ b/drivers/usb/host/ohci-at91.c
@@ -350,7 +350,7 @@ static int ohci_at91_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
case USB_PORT_FEAT_SUSPEND:
dev_dbg(hcd->self.controller, "SetPortFeat: SUSPEND\n");
- if (valid_port(wIndex)) {
+ if (valid_port(wIndex) && ohci_at91->sfr_regmap) {
ohci_at91_port_suspend(ohci_at91->sfr_regmap,
1);
return 0;
@@ -393,7 +393,7 @@ static int ohci_at91_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
case USB_PORT_FEAT_SUSPEND:
dev_dbg(hcd->self.controller, "ClearPortFeature: SUSPEND\n");
- if (valid_port(wIndex)) {
+ if (valid_port(wIndex) && ohci_at91->sfr_regmap) {
ohci_at91_port_suspend(ohci_at91->sfr_regmap,
0);
return 0;
diff --git a/drivers/usb/host/xhci-dbg.c b/drivers/usb/host/xhci-dbg.c
index 363d125..2b4a00f 100644
--- a/drivers/usb/host/xhci-dbg.c
+++ b/drivers/usb/host/xhci-dbg.c
@@ -109,7 +109,7 @@ static void xhci_print_cap_regs(struct xhci_hcd *xhci)
xhci_dbg(xhci, "RTSOFF 0x%x:\n", temp & RTSOFF_MASK);
/* xhci 1.1 controllers have the HCCPARAMS2 register */
- if (hci_version > 100) {
+ if (hci_version > 0x100) {
temp = readl(&xhci->cap_regs->hcc_params2);
xhci_dbg(xhci, "HCC PARAMS2 0x%x:\n", (unsigned int) temp);
xhci_dbg(xhci, " HC %s Force save context capability",
diff --git a/drivers/usb/host/xhci-mtk.c b/drivers/usb/host/xhci-mtk.c
index 9066ec9..67d5dc7 100644
--- a/drivers/usb/host/xhci-mtk.c
+++ b/drivers/usb/host/xhci-mtk.c
@@ -382,7 +382,6 @@ static int usb_wakeup_of_property_parse(struct xhci_hcd_mtk *mtk,
static int xhci_mtk_setup(struct usb_hcd *hcd);
static const struct xhci_driver_overrides xhci_mtk_overrides __initconst = {
- .extra_priv_size = sizeof(struct xhci_hcd),
.reset = xhci_mtk_setup,
};
@@ -678,13 +677,13 @@ static int xhci_mtk_probe(struct platform_device *pdev)
goto power_off_phys;
}
- if (HCC_MAX_PSA(xhci->hcc_params) >= 4)
- xhci->shared_hcd->can_do_streams = 1;
-
ret = usb_add_hcd(hcd, irq, IRQF_SHARED);
if (ret)
goto put_usb3_hcd;
+ if (HCC_MAX_PSA(xhci->hcc_params) >= 4)
+ xhci->shared_hcd->can_do_streams = 1;
+
ret = usb_add_hcd(xhci->shared_hcd, irq, IRQF_SHARED);
if (ret)
goto dealloc_usb2_hcd;
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index 6d33b42..6ed468f 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -286,6 +286,8 @@ static int xhci_plat_remove(struct platform_device *dev)
struct xhci_hcd *xhci = hcd_to_xhci(hcd);
struct clk *clk = xhci->clk;
+ xhci->xhc_state |= XHCI_STATE_REMOVING;
+
usb_remove_hcd(xhci->shared_hcd);
usb_phy_shutdown(hcd->usb_phy);
@@ -342,6 +344,7 @@ MODULE_DEVICE_TABLE(acpi, usb_xhci_acpi_match);
static struct platform_driver usb_xhci_driver = {
.probe = xhci_plat_probe,
.remove = xhci_plat_remove,
+ .shutdown = usb_hcd_platform_shutdown,
.driver = {
.name = "xhci-hcd",
.pm = DEV_PM_OPS,
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index d9936c7..a3309aa 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -1989,6 +1989,9 @@ static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td,
case TRB_NORMAL:
td->urb->actual_length = requested - remaining;
goto finish_td;
+ case TRB_STATUS:
+ td->urb->actual_length = requested;
+ goto finish_td;
default:
xhci_warn(xhci, "WARN: unexpected TRB Type %d\n",
trb_type);
diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c
index a59fafb..74436f8 100644
--- a/drivers/usb/host/xhci-tegra.c
+++ b/drivers/usb/host/xhci-tegra.c
@@ -1308,7 +1308,6 @@ static int tegra_xhci_setup(struct usb_hcd *hcd)
}
static const struct xhci_driver_overrides tegra_xhci_overrides __initconst = {
- .extra_priv_size = sizeof(struct xhci_hcd),
.reset = tegra_xhci_setup,
};
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 6d6c460..953fd8f 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -868,7 +868,7 @@ static void xhci_disable_port_wake_on_bits(struct xhci_hcd *xhci)
spin_lock_irqsave(&xhci->lock, flags);
- /* disble usb3 ports Wake bits*/
+ /* disable usb3 ports Wake bits */
port_index = xhci->num_usb3_ports;
port_array = xhci->usb3_ports;
while (port_index--) {
@@ -879,7 +879,7 @@ static void xhci_disable_port_wake_on_bits(struct xhci_hcd *xhci)
writel(t2, port_array[port_index]);
}
- /* disble usb2 ports Wake bits*/
+ /* disable usb2 ports Wake bits */
port_index = xhci->num_usb2_ports;
port_array = xhci->usb2_ports;
while (port_index--) {
@@ -1477,6 +1477,7 @@ int xhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
struct xhci_ring *ep_ring;
struct xhci_virt_ep *ep;
struct xhci_command *command;
+ struct xhci_virt_device *vdev;
xhci = hcd_to_xhci(hcd);
spin_lock_irqsave(&xhci->lock, flags);
@@ -1485,15 +1486,27 @@ int xhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
/* Make sure the URB hasn't completed or been unlinked already */
ret = usb_hcd_check_unlink_urb(hcd, urb, status);
- if (ret || !urb->hcpriv)
+ if (ret)
goto done;
+
+ /* give back URB now if we can't queue it for cancel */
+ vdev = xhci->devs[urb->dev->slot_id];
+ urb_priv = urb->hcpriv;
+ if (!vdev || !urb_priv)
+ goto err_giveback;
+
+ ep_index = xhci_get_endpoint_index(&urb->ep->desc);
+ ep = &vdev->eps[ep_index];
+ ep_ring = xhci_urb_to_transfer_ring(xhci, urb);
+ if (!ep || !ep_ring)
+ goto err_giveback;
+
temp = readl(&xhci->op_regs->status);
if (temp == 0xffffffff || (xhci->xhc_state & XHCI_STATE_HALTED)) {
xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
"HW died, freeing TD.");
- urb_priv = urb->hcpriv;
for (i = urb_priv->num_tds_done;
- i < urb_priv->num_tds && xhci->devs[urb->dev->slot_id];
+ i < urb_priv->num_tds;
i++) {
td = &urb_priv->td[i];
if (!list_empty(&td->td_list))
@@ -1501,23 +1514,9 @@ int xhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
if (!list_empty(&td->cancelled_td_list))
list_del_init(&td->cancelled_td_list);
}
-
- usb_hcd_unlink_urb_from_ep(hcd, urb);
- spin_unlock_irqrestore(&xhci->lock, flags);
- usb_hcd_giveback_urb(hcd, urb, -ESHUTDOWN);
- xhci_urb_free_priv(urb_priv);
- return ret;
+ goto err_giveback;
}
- ep_index = xhci_get_endpoint_index(&urb->ep->desc);
- ep = &xhci->devs[urb->dev->slot_id]->eps[ep_index];
- ep_ring = xhci_urb_to_transfer_ring(xhci, urb);
- if (!ep_ring) {
- ret = -EINVAL;
- goto done;
- }
-
- urb_priv = urb->hcpriv;
i = urb_priv->num_tds_done;
if (i < urb_priv->num_tds)
xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
@@ -1554,6 +1553,14 @@ int xhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
done:
spin_unlock_irqrestore(&xhci->lock, flags);
return ret;
+
+err_giveback:
+ if (urb_priv)
+ xhci_urb_free_priv(urb_priv);
+ usb_hcd_unlink_urb_from_ep(hcd, urb);
+ spin_unlock_irqrestore(&xhci->lock, flags);
+ usb_hcd_giveback_urb(hcd, urb, -ESHUTDOWN);
+ return ret;
}
/* Drop an endpoint from a new bandwidth configuration for this device.
diff --git a/drivers/usb/misc/idmouse.c b/drivers/usb/misc/idmouse.c
index 8b9fd75..502bfe3 100644
--- a/drivers/usb/misc/idmouse.c
+++ b/drivers/usb/misc/idmouse.c
@@ -347,6 +347,9 @@ static int idmouse_probe(struct usb_interface *interface,
if (iface_desc->desc.bInterfaceClass != 0x0A)
return -ENODEV;
+ if (iface_desc->desc.bNumEndpoints < 1)
+ return -ENODEV;
+
/* allocate memory for our device state and initialize it */
dev = kzalloc(sizeof(*dev), GFP_KERNEL);
if (dev == NULL)
diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c
index 095778f..37c63cb 100644
--- a/drivers/usb/misc/iowarrior.c
+++ b/drivers/usb/misc/iowarrior.c
@@ -781,12 +781,6 @@ static int iowarrior_probe(struct usb_interface *interface,
iface_desc = interface->cur_altsetting;
dev->product_id = le16_to_cpu(udev->descriptor.idProduct);
- if (iface_desc->desc.bNumEndpoints < 1) {
- dev_err(&interface->dev, "Invalid number of endpoints\n");
- retval = -EINVAL;
- goto error;
- }
-
/* set up the endpoint information */
for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) {
endpoint = &iface_desc->endpoint[i].desc;
@@ -797,6 +791,21 @@ static int iowarrior_probe(struct usb_interface *interface,
/* this one will match for the IOWarrior56 only */
dev->int_out_endpoint = endpoint;
}
+
+ if (!dev->int_in_endpoint) {
+ dev_err(&interface->dev, "no interrupt-in endpoint found\n");
+ retval = -ENODEV;
+ goto error;
+ }
+
+ if (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) {
+ if (!dev->int_out_endpoint) {
+ dev_err(&interface->dev, "no interrupt-out endpoint found\n");
+ retval = -ENODEV;
+ goto error;
+ }
+ }
+
/* we have to check the report_size often, so remember it in the endianness suitable for our machine */
dev->report_size = usb_endpoint_maxp(dev->int_in_endpoint);
if ((dev->interface->cur_altsetting->desc.bInterfaceNumber == 0) &&
diff --git a/drivers/usb/misc/lvstest.c b/drivers/usb/misc/lvstest.c
index 7717651..d3d1247 100644
--- a/drivers/usb/misc/lvstest.c
+++ b/drivers/usb/misc/lvstest.c
@@ -366,6 +366,10 @@ static int lvs_rh_probe(struct usb_interface *intf,
hdev = interface_to_usbdev(intf);
desc = intf->cur_altsetting;
+
+ if (desc->desc.bNumEndpoints < 1)
+ return -ENODEV;
+
endpoint = &desc->endpoint[0].desc;
/* valid only for SS root hub */
diff --git a/drivers/usb/misc/usb251xb.c b/drivers/usb/misc/usb251xb.c
index 4e18600..91f66d68 100644
--- a/drivers/usb/misc/usb251xb.c
+++ b/drivers/usb/misc/usb251xb.c
@@ -375,18 +375,24 @@ static int usb251xb_get_ofdata(struct usb251xb *hub,
if (of_get_property(np, "dynamic-power-switching", NULL))
hub->conf_data2 |= BIT(7);
- if (of_get_property(np, "oc-delay-100us", NULL)) {
- hub->conf_data2 &= ~BIT(5);
- hub->conf_data2 &= ~BIT(4);
- } else if (of_get_property(np, "oc-delay-4ms", NULL)) {
- hub->conf_data2 &= ~BIT(5);
- hub->conf_data2 |= BIT(4);
- } else if (of_get_property(np, "oc-delay-8ms", NULL)) {
- hub->conf_data2 |= BIT(5);
- hub->conf_data2 &= ~BIT(4);
- } else if (of_get_property(np, "oc-delay-16ms", NULL)) {
- hub->conf_data2 |= BIT(5);
- hub->conf_data2 |= BIT(4);
+ if (!of_property_read_u32(np, "oc-delay-us", property_u32)) {
+ if (*property_u32 == 100) {
+ /* 100 us*/
+ hub->conf_data2 &= ~BIT(5);
+ hub->conf_data2 &= ~BIT(4);
+ } else if (*property_u32 == 4000) {
+ /* 4 ms */
+ hub->conf_data2 &= ~BIT(5);
+ hub->conf_data2 |= BIT(4);
+ } else if (*property_u32 == 16000) {
+ /* 16 ms */
+ hub->conf_data2 |= BIT(5);
+ hub->conf_data2 |= BIT(4);
+ } else {
+ /* 8 ms (DEFAULT) */
+ hub->conf_data2 |= BIT(5);
+ hub->conf_data2 &= ~BIT(4);
+ }
}
if (of_get_property(np, "compound-device", NULL))
@@ -432,30 +438,9 @@ static int usb251xb_get_ofdata(struct usb251xb *hub,
}
}
- hub->max_power_sp = USB251XB_DEF_MAX_POWER_SELF;
- if (!of_property_read_u32(np, "max-sp-power", property_u32))
- hub->max_power_sp = min_t(u8, be32_to_cpu(*property_u32) / 2,
- 250);
-
- hub->max_power_bp = USB251XB_DEF_MAX_POWER_BUS;
- if (!of_property_read_u32(np, "max-bp-power", property_u32))
- hub->max_power_bp = min_t(u8, be32_to_cpu(*property_u32) / 2,
- 250);
-
- hub->max_current_sp = USB251XB_DEF_MAX_CURRENT_SELF;
- if (!of_property_read_u32(np, "max-sp-current", property_u32))
- hub->max_current_sp = min_t(u8, be32_to_cpu(*property_u32) / 2,
- 250);
-
- hub->max_current_bp = USB251XB_DEF_MAX_CURRENT_BUS;
- if (!of_property_read_u32(np, "max-bp-current", property_u32))
- hub->max_current_bp = min_t(u8, be32_to_cpu(*property_u32) / 2,
- 250);
-
hub->power_on_time = USB251XB_DEF_POWER_ON_TIME;
- if (!of_property_read_u32(np, "power-on-time", property_u32))
- hub->power_on_time = min_t(u8, be32_to_cpu(*property_u32) / 2,
- 255);
+ if (!of_property_read_u32(np, "power-on-time-ms", property_u32))
+ hub->power_on_time = min_t(u8, *property_u32 / 2, 255);
if (of_property_read_u16_array(np, "language-id", &hub->lang_id, 1))
hub->lang_id = USB251XB_DEF_LANGUAGE_ID;
@@ -492,6 +477,10 @@ static int usb251xb_get_ofdata(struct usb251xb *hub,
/* The following parameters are currently not exposed to devicetree, but
* may be as soon as needed.
*/
+ hub->max_power_sp = USB251XB_DEF_MAX_POWER_SELF;
+ hub->max_power_bp = USB251XB_DEF_MAX_POWER_BUS;
+ hub->max_current_sp = USB251XB_DEF_MAX_CURRENT_SELF;
+ hub->max_current_bp = USB251XB_DEF_MAX_CURRENT_BUS;
hub->bat_charge_en = USB251XB_DEF_BATTERY_CHARGING_ENABLE;
hub->boost_up = USB251XB_DEF_BOOST_UP;
hub->boost_x = USB251XB_DEF_BOOST_X;
diff --git a/drivers/usb/misc/uss720.c b/drivers/usb/misc/uss720.c
index e45a3a6..07014ca 100644
--- a/drivers/usb/misc/uss720.c
+++ b/drivers/usb/misc/uss720.c
@@ -709,6 +709,11 @@ static int uss720_probe(struct usb_interface *intf,
interface = intf->cur_altsetting;
+ if (interface->desc.bNumEndpoints < 3) {
+ usb_put_dev(usbdev);
+ return -ENODEV;
+ }
+
/*
* Allocate parport interface
*/
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index d8bae6c..0c3664ab 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -2490,8 +2490,8 @@ static int musb_remove(struct platform_device *pdev)
musb_host_cleanup(musb);
musb_gadget_cleanup(musb);
- spin_lock_irqsave(&musb->lock, flags);
musb_platform_disable(musb);
+ spin_lock_irqsave(&musb->lock, flags);
musb_disable_interrupts(musb);
musb_writeb(musb->mregs, MUSB_DEVCTL, 0);
spin_unlock_irqrestore(&musb->lock, flags);
diff --git a/drivers/usb/musb/musb_cppi41.c b/drivers/usb/musb/musb_cppi41.c
index 00e272b..355655f 100644
--- a/drivers/usb/musb/musb_cppi41.c
+++ b/drivers/usb/musb/musb_cppi41.c
@@ -238,8 +238,27 @@ static void cppi41_dma_callback(void *private_data,
transferred < cppi41_channel->packet_sz)
cppi41_channel->prog_len = 0;
- if (cppi41_channel->is_tx)
- empty = musb_is_tx_fifo_empty(hw_ep);
+ if (cppi41_channel->is_tx) {
+ u8 type;
+
+ if (is_host_active(musb))
+ type = hw_ep->out_qh->type;
+ else
+ type = hw_ep->ep_in.type;
+
+ if (type == USB_ENDPOINT_XFER_ISOC)
+ /*
+ * Don't use the early-TX-interrupt workaround below
+ * for Isoch transfter. Since Isoch are periodic
+ * transfer, by the time the next transfer is
+ * scheduled, the current one should be done already.
+ *
+ * This avoids audio playback underrun issue.
+ */
+ empty = true;
+ else
+ empty = musb_is_tx_fifo_empty(hw_ep);
+ }
if (!cppi41_channel->is_tx || empty) {
cppi41_trans_done(cppi41_channel);
diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c
index 7c047c4..9c7ee26 100644
--- a/drivers/usb/musb/musb_dsps.c
+++ b/drivers/usb/musb/musb_dsps.c
@@ -933,7 +933,7 @@ static int dsps_probe(struct platform_device *pdev)
if (usb_get_dr_mode(&pdev->dev) == USB_DR_MODE_PERIPHERAL) {
ret = dsps_setup_optional_vbus_irq(pdev, glue);
if (ret)
- return ret;
+ goto err_iounmap;
}
platform_set_drvdata(pdev, glue);
@@ -946,6 +946,8 @@ static int dsps_probe(struct platform_device *pdev)
err:
pm_runtime_disable(&pdev->dev);
+err_iounmap:
+ iounmap(glue->usbss_base);
return ret;
}
@@ -956,6 +958,7 @@ static int dsps_remove(struct platform_device *pdev)
platform_device_unregister(glue->musb);
pm_runtime_disable(&pdev->dev);
+ iounmap(glue->usbss_base);
return 0;
}
diff --git a/drivers/usb/phy/phy-isp1301.c b/drivers/usb/phy/phy-isp1301.c
index db68156..f333024 100644
--- a/drivers/usb/phy/phy-isp1301.c
+++ b/drivers/usb/phy/phy-isp1301.c
@@ -33,6 +33,12 @@ static const struct i2c_device_id isp1301_id[] = {
};
MODULE_DEVICE_TABLE(i2c, isp1301_id);
+static const struct of_device_id isp1301_of_match[] = {
+ {.compatible = "nxp,isp1301" },
+ { },
+};
+MODULE_DEVICE_TABLE(of, isp1301_of_match);
+
static struct i2c_client *isp1301_i2c_client;
static int __isp1301_write(struct isp1301 *isp, u8 reg, u8 value, u8 clear)
@@ -130,6 +136,7 @@ static int isp1301_remove(struct i2c_client *client)
static struct i2c_driver isp1301_driver = {
.driver = {
.name = DRV_NAME,
+ .of_match_table = isp1301_of_match,
},
.probe = isp1301_probe,
.remove = isp1301_remove,
diff --git a/drivers/usb/serial/digi_acceleport.c b/drivers/usb/serial/digi_acceleport.c
index ab78111..6537d3c 100644
--- a/drivers/usb/serial/digi_acceleport.c
+++ b/drivers/usb/serial/digi_acceleport.c
@@ -1500,7 +1500,7 @@ static int digi_read_oob_callback(struct urb *urb)
return -1;
/* handle each oob command */
- for (i = 0; i < urb->actual_length - 4; i += 4) {
+ for (i = 0; i < urb->actual_length - 3; i += 4) {
opcode = buf[i];
line = buf[i + 1];
status = buf[i + 2];
diff --git a/drivers/usb/serial/io_ti.c b/drivers/usb/serial/io_ti.c
index ceaeeba..a76b95d 100644
--- a/drivers/usb/serial/io_ti.c
+++ b/drivers/usb/serial/io_ti.c
@@ -1674,6 +1674,12 @@ static void edge_interrupt_callback(struct urb *urb)
function = TIUMP_GET_FUNC_FROM_CODE(data[0]);
dev_dbg(dev, "%s - port_number %d, function %d, info 0x%x\n", __func__,
port_number, function, data[1]);
+
+ if (port_number >= edge_serial->serial->num_ports) {
+ dev_err(dev, "bad port number %d\n", port_number);
+ goto exit;
+ }
+
port = edge_serial->serial->port[port_number];
edge_port = usb_get_serial_port_data(port);
if (!edge_port) {
@@ -1755,7 +1761,7 @@ static void edge_bulk_in_callback(struct urb *urb)
port_number = edge_port->port->port_number;
- if (edge_port->lsr_event) {
+ if (urb->actual_length > 0 && edge_port->lsr_event) {
edge_port->lsr_event = 0;
dev_dbg(dev, "%s ===== Port %u LSR Status = %02x, Data = %02x ======\n",
__func__, port_number, edge_port->lsr_mask, *data);
diff --git a/drivers/usb/serial/omninet.c b/drivers/usb/serial/omninet.c
index a180b17..dd70695 100644
--- a/drivers/usb/serial/omninet.c
+++ b/drivers/usb/serial/omninet.c
@@ -31,7 +31,6 @@
#define BT_IGNITIONPRO_ID 0x2000
/* function prototypes */
-static int omninet_open(struct tty_struct *tty, struct usb_serial_port *port);
static void omninet_process_read_urb(struct urb *urb);
static void omninet_write_bulk_callback(struct urb *urb);
static int omninet_write(struct tty_struct *tty, struct usb_serial_port *port,
@@ -60,7 +59,6 @@ static struct usb_serial_driver zyxel_omninet_device = {
.attach = omninet_attach,
.port_probe = omninet_port_probe,
.port_remove = omninet_port_remove,
- .open = omninet_open,
.write = omninet_write,
.write_room = omninet_write_room,
.write_bulk_callback = omninet_write_bulk_callback,
@@ -140,17 +138,6 @@ static int omninet_port_remove(struct usb_serial_port *port)
return 0;
}
-static int omninet_open(struct tty_struct *tty, struct usb_serial_port *port)
-{
- struct usb_serial *serial = port->serial;
- struct usb_serial_port *wport;
-
- wport = serial->port[1];
- tty_port_tty_set(&wport->port, tty);
-
- return usb_serial_generic_open(tty, port);
-}
-
#define OMNINET_HEADERLEN 4
#define OMNINET_BULKOUTSIZE 64
#define OMNINET_PAYLOADSIZE (OMNINET_BULKOUTSIZE - OMNINET_HEADERLEN)
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 42cc72e..af67a0d 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -233,6 +233,14 @@ static void option_instat_callback(struct urb *urb);
#define BANDRICH_PRODUCT_1012 0x1012
#define QUALCOMM_VENDOR_ID 0x05C6
+/* These Quectel products use Qualcomm's vendor ID */
+#define QUECTEL_PRODUCT_UC20 0x9003
+#define QUECTEL_PRODUCT_UC15 0x9090
+
+#define QUECTEL_VENDOR_ID 0x2c7c
+/* These Quectel products use Quectel's vendor ID */
+#define QUECTEL_PRODUCT_EC21 0x0121
+#define QUECTEL_PRODUCT_EC25 0x0125
#define CMOTECH_VENDOR_ID 0x16d8
#define CMOTECH_PRODUCT_6001 0x6001
@@ -1161,7 +1169,14 @@ static const struct usb_device_id option_ids[] = {
{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */
{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x0023)}, /* ONYX 3G device */
{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */
- { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9003), /* Quectel UC20 */
+ /* Quectel products using Qualcomm vendor ID */
+ { USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC15)},
+ { USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC20),
+ .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+ /* Quectel products using Quectel vendor ID */
+ { USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21),
+ .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+ { USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC25),
.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) },
{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) },
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index 696458d..38b3f0d 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -169,6 +169,8 @@ static const struct usb_device_id id_table[] = {
{DEVICE_SWI(0x413c, 0x81a9)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */
{DEVICE_SWI(0x413c, 0x81b1)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */
{DEVICE_SWI(0x413c, 0x81b3)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
+ {DEVICE_SWI(0x413c, 0x81b5)}, /* Dell Wireless 5811e QDL */
+ {DEVICE_SWI(0x413c, 0x81b6)}, /* Dell Wireless 5811e QDL */
/* Huawei devices */
{DEVICE_HWI(0x03f0, 0x581d)}, /* HP lt4112 LTE/HSPA+ Gobi 4G Modem (Huawei me906e) */
diff --git a/drivers/usb/serial/safe_serial.c b/drivers/usb/serial/safe_serial.c
index 93c6c9b..8a069aa 100644
--- a/drivers/usb/serial/safe_serial.c
+++ b/drivers/usb/serial/safe_serial.c
@@ -200,6 +200,11 @@ static void safe_process_read_urb(struct urb *urb)
if (!safe)
goto out;
+ if (length < 2) {
+ dev_err(&port->dev, "malformed packet\n");
+ return;
+ }
+
fcs = fcs_compute10(data, length, CRC10_INITFCS);
if (fcs) {
dev_err(&port->dev, "%s - bad CRC %x\n", __func__, fcs);
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 16cc183..9129f6c 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -2071,6 +2071,20 @@ UNUSUAL_DEV( 0x1370, 0x6828, 0x0110, 0x0110,
USB_SC_DEVICE, USB_PR_DEVICE, NULL,
US_FL_IGNORE_RESIDUE ),
+/*
+ * Reported by Tobias Jakobi <tjakobi@math.uni-bielefeld.de>
+ * The INIC-3619 bridge is used in the StarTech SLSODDU33B
+ * SATA-USB enclosure for slimline optical drives.
+ *
+ * The quirk enables MakeMKV to properly exchange keys with
+ * an installed BD drive.
+ */
+UNUSUAL_DEV( 0x13fd, 0x3609, 0x0209, 0x0209,
+ "Initio Corporation",
+ "INIC-3619",
+ USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+ US_FL_IGNORE_RESIDUE ),
+
/* Reported by Qinglin Ye <yestyle@gmail.com> */
UNUSUAL_DEV( 0x13fe, 0x3600, 0x0100, 0x0100,
"Kingston",
diff --git a/drivers/usb/wusbcore/wa-hc.c b/drivers/usb/wusbcore/wa-hc.c
index 252c7bd..d01496f 100644
--- a/drivers/usb/wusbcore/wa-hc.c
+++ b/drivers/usb/wusbcore/wa-hc.c
@@ -39,6 +39,9 @@ int wa_create(struct wahc *wa, struct usb_interface *iface,
int result;
struct device *dev = &iface->dev;
+ if (iface->cur_altsetting->desc.bNumEndpoints < 3)
+ return -ENODEV;
+
result = wa_rpipes_create(wa);
if (result < 0)
goto error_rpipes_create;
diff --git a/drivers/uwb/hwa-rc.c b/drivers/uwb/hwa-rc.c
index 0aa6c3c..35a1e77 100644
--- a/drivers/uwb/hwa-rc.c
+++ b/drivers/uwb/hwa-rc.c
@@ -823,6 +823,9 @@ static int hwarc_probe(struct usb_interface *iface,
struct hwarc *hwarc;
struct device *dev = &iface->dev;
+ if (iface->cur_altsetting->desc.bNumEndpoints < 1)
+ return -ENODEV;
+
result = -ENOMEM;
uwb_rc = uwb_rc_alloc();
if (uwb_rc == NULL) {
diff --git a/drivers/uwb/i1480/dfu/usb.c b/drivers/uwb/i1480/dfu/usb.c
index 2bfc846..6345e85 100644
--- a/drivers/uwb/i1480/dfu/usb.c
+++ b/drivers/uwb/i1480/dfu/usb.c
@@ -362,6 +362,9 @@ int i1480_usb_probe(struct usb_interface *iface, const struct usb_device_id *id)
result);
}
+ if (iface->cur_altsetting->desc.bNumEndpoints < 1)
+ return -ENODEV;
+
result = -ENOMEM;
i1480_usb = kzalloc(sizeof(*i1480_usb), GFP_KERNEL);
if (i1480_usb == NULL) {
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 609f4f9..561084a 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -403,6 +403,7 @@ static void vfio_group_release(struct kref *kref)
struct iommu_group *iommu_group = group->iommu_group;
WARN_ON(!list_empty(&group->device_list));
+ WARN_ON(group->notifier.head);
list_for_each_entry_safe(unbound, tmp,
&group->unbound_list, unbound_next) {
@@ -1573,6 +1574,10 @@ static int vfio_group_fops_open(struct inode *inode, struct file *filep)
return -EBUSY;
}
+ /* Warn if previous user didn't cleanup and re-init to drop them */
+ if (WARN_ON(group->notifier.head))
+ BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier);
+
filep->private_data = group;
return 0;
@@ -1584,9 +1589,6 @@ static int vfio_group_fops_release(struct inode *inode, struct file *filep)
filep->private_data = NULL;
- /* Any user didn't unregister? */
- WARN_ON(group->notifier.head);
-
vfio_group_try_dissolve_container(group);
atomic_dec(&group->opened);
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index c26fa1f..32d2633 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -1182,8 +1182,7 @@ static struct vfio_group *find_iommu_group(struct vfio_domain *domain,
return NULL;
}
-static bool vfio_iommu_has_resv_msi(struct iommu_group *group,
- phys_addr_t *base)
+static bool vfio_iommu_has_sw_msi(struct iommu_group *group, phys_addr_t *base)
{
struct list_head group_resv_regions;
struct iommu_resv_region *region, *next;
@@ -1192,7 +1191,7 @@ static bool vfio_iommu_has_resv_msi(struct iommu_group *group,
INIT_LIST_HEAD(&group_resv_regions);
iommu_get_group_resv_regions(group, &group_resv_regions);
list_for_each_entry(region, &group_resv_regions, list) {
- if (region->type & IOMMU_RESV_MSI) {
+ if (region->type == IOMMU_RESV_SW_MSI) {
*base = region->start;
ret = true;
goto out;
@@ -1283,7 +1282,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
if (ret)
goto out_domain;
- resv_msi = vfio_iommu_has_resv_msi(iommu_group, &resv_msi_base);
+ resv_msi = vfio_iommu_has_sw_msi(iommu_group, &resv_msi_base);
INIT_LIST_HEAD(&domain->group_list);
list_add(&group->next, &domain->group_list);
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index ce5e63d..44eed8e 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -223,6 +223,46 @@ vhost_transport_send_pkt(struct virtio_vsock_pkt *pkt)
return len;
}
+static int
+vhost_transport_cancel_pkt(struct vsock_sock *vsk)
+{
+ struct vhost_vsock *vsock;
+ struct virtio_vsock_pkt *pkt, *n;
+ int cnt = 0;
+ LIST_HEAD(freeme);
+
+ /* Find the vhost_vsock according to guest context id */
+ vsock = vhost_vsock_get(vsk->remote_addr.svm_cid);
+ if (!vsock)
+ return -ENODEV;
+
+ spin_lock_bh(&vsock->send_pkt_list_lock);
+ list_for_each_entry_safe(pkt, n, &vsock->send_pkt_list, list) {
+ if (pkt->vsk != vsk)
+ continue;
+ list_move(&pkt->list, &freeme);
+ }
+ spin_unlock_bh(&vsock->send_pkt_list_lock);
+
+ list_for_each_entry_safe(pkt, n, &freeme, list) {
+ if (pkt->reply)
+ cnt++;
+ list_del(&pkt->list);
+ virtio_transport_free_pkt(pkt);
+ }
+
+ if (cnt) {
+ struct vhost_virtqueue *tx_vq = &vsock->vqs[VSOCK_VQ_TX];
+ int new_cnt;
+
+ new_cnt = atomic_sub_return(cnt, &vsock->queued_replies);
+ if (new_cnt + cnt >= tx_vq->num && new_cnt < tx_vq->num)
+ vhost_poll_queue(&tx_vq->poll);
+ }
+
+ return 0;
+}
+
static struct virtio_vsock_pkt *
vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq,
unsigned int out, unsigned int in)
@@ -675,6 +715,7 @@ static struct virtio_transport vhost_transport = {
.release = virtio_transport_release,
.connect = virtio_transport_connect,
.shutdown = virtio_transport_shutdown,
+ .cancel_pkt = vhost_transport_cancel_pkt,
.dgram_enqueue = virtio_transport_dgram_enqueue,
.dgram_dequeue = virtio_transport_dgram_dequeue,
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 4e119150..34adf9b 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -242,11 +242,11 @@ static inline void update_stat(struct virtio_balloon *vb, int idx,
#define pages_to_bytes(x) ((u64)(x) << PAGE_SHIFT)
-static void update_balloon_stats(struct virtio_balloon *vb)
+static unsigned int update_balloon_stats(struct virtio_balloon *vb)
{
unsigned long events[NR_VM_EVENT_ITEMS];
struct sysinfo i;
- int idx = 0;
+ unsigned int idx = 0;
long available;
all_vm_events(events);
@@ -254,18 +254,22 @@ static void update_balloon_stats(struct virtio_balloon *vb)
available = si_mem_available();
+#ifdef CONFIG_VM_EVENT_COUNTERS
update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_IN,
pages_to_bytes(events[PSWPIN]));
update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_OUT,
pages_to_bytes(events[PSWPOUT]));
update_stat(vb, idx++, VIRTIO_BALLOON_S_MAJFLT, events[PGMAJFAULT]);
update_stat(vb, idx++, VIRTIO_BALLOON_S_MINFLT, events[PGFAULT]);
+#endif
update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMFREE,
pages_to_bytes(i.freeram));
update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMTOT,
pages_to_bytes(i.totalram));
update_stat(vb, idx++, VIRTIO_BALLOON_S_AVAIL,
pages_to_bytes(available));
+
+ return idx;
}
/*
@@ -291,14 +295,14 @@ static void stats_handle_request(struct virtio_balloon *vb)
{
struct virtqueue *vq;
struct scatterlist sg;
- unsigned int len;
+ unsigned int len, num_stats;
- update_balloon_stats(vb);
+ num_stats = update_balloon_stats(vb);
vq = vb->stats_vq;
if (!virtqueue_get_buf(vq, &len))
return;
- sg_init_one(&sg, vb->stats, sizeof(vb->stats));
+ sg_init_one(&sg, vb->stats, sizeof(vb->stats[0]) * num_stats);
virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL);
virtqueue_kick(vq);
}
@@ -423,13 +427,16 @@ static int init_vqs(struct virtio_balloon *vb)
vb->deflate_vq = vqs[1];
if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
struct scatterlist sg;
+ unsigned int num_stats;
vb->stats_vq = vqs[2];
/*
* Prime this virtqueue with one buffer so the hypervisor can
* use it to signal us later (it can't be broken yet!).
*/
- sg_init_one(&sg, vb->stats, sizeof vb->stats);
+ num_stats = update_balloon_stats(vb);
+
+ sg_init_one(&sg, vb->stats, sizeof(vb->stats[0]) * num_stats);
if (virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb, GFP_KERNEL)
< 0)
BUG();
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index df548a6..5905349 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -147,7 +147,7 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
const char *name = dev_name(&vp_dev->vdev.dev);
- int i, err = -ENOMEM, allocated_vectors, nvectors;
+ int i, j, err = -ENOMEM, allocated_vectors, nvectors;
unsigned flags = PCI_IRQ_MSIX;
bool shared = false;
u16 msix_vec;
@@ -212,7 +212,7 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
if (!vp_dev->msix_vector_map)
goto out_disable_config_irq;
- allocated_vectors = 1; /* vector 0 is the config interrupt */
+ allocated_vectors = j = 1; /* vector 0 is the config interrupt */
for (i = 0; i < nvqs; ++i) {
if (!names[i]) {
vqs[i] = NULL;
@@ -236,18 +236,19 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
continue;
}
- snprintf(vp_dev->msix_names[i + 1],
+ snprintf(vp_dev->msix_names[j],
sizeof(*vp_dev->msix_names), "%s-%s",
dev_name(&vp_dev->vdev.dev), names[i]);
err = request_irq(pci_irq_vector(vp_dev->pci_dev, msix_vec),
vring_interrupt, IRQF_SHARED,
- vp_dev->msix_names[i + 1], vqs[i]);
+ vp_dev->msix_names[j], vqs[i]);
if (err) {
/* don't free this irq on error */
vp_dev->msix_vector_map[i] = VIRTIO_MSI_NO_VECTOR;
goto out_remove_vqs;
}
vp_dev->msix_vector_map[i] = msix_vec;
+ j++;
/*
* Use a different vector for each queue if they are available,
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index c77a075..f3bf8f4 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -36,6 +36,7 @@
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/highmem.h>
+#include <linux/refcount.h>
#include <xen/xen.h>
#include <xen/grant_table.h>
@@ -86,7 +87,7 @@ struct grant_map {
int index;
int count;
int flags;
- atomic_t users;
+ refcount_t users;
struct unmap_notify notify;
struct ioctl_gntdev_grant_ref *grants;
struct gnttab_map_grant_ref *map_ops;
@@ -166,7 +167,7 @@ static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count)
add->index = 0;
add->count = count;
- atomic_set(&add->users, 1);
+ refcount_set(&add->users, 1);
return add;
@@ -212,7 +213,7 @@ static void gntdev_put_map(struct gntdev_priv *priv, struct grant_map *map)
if (!map)
return;
- if (!atomic_dec_and_test(&map->users))
+ if (!refcount_dec_and_test(&map->users))
return;
atomic_sub(map->count, &pages_mapped);
@@ -400,7 +401,7 @@ static void gntdev_vma_open(struct vm_area_struct *vma)
struct grant_map *map = vma->vm_private_data;
pr_debug("gntdev_vma_open %p\n", vma);
- atomic_inc(&map->users);
+ refcount_inc(&map->users);
}
static void gntdev_vma_close(struct vm_area_struct *vma)
@@ -1004,7 +1005,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
goto unlock_out;
}
- atomic_inc(&map->users);
+ refcount_inc(&map->users);
vma->vm_ops = &gntdev_vmops;
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index f8afc6d..e8cef1a 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -681,3 +681,50 @@ xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask)
return 0;
}
EXPORT_SYMBOL_GPL(xen_swiotlb_set_dma_mask);
+
+/*
+ * Create userspace mapping for the DMA-coherent memory.
+ * This function should be called with the pages from the current domain only,
+ * passing pages mapped from other domains would lead to memory corruption.
+ */
+int
+xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ unsigned long attrs)
+{
+#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
+ if (__generic_dma_ops(dev)->mmap)
+ return __generic_dma_ops(dev)->mmap(dev, vma, cpu_addr,
+ dma_addr, size, attrs);
+#endif
+ return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_dma_mmap);
+
+/*
+ * This function should be called with the pages from the current domain only,
+ * passing pages mapped from other domains would lead to memory corruption.
+ */
+int
+xen_swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
+ void *cpu_addr, dma_addr_t handle, size_t size,
+ unsigned long attrs)
+{
+#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
+ if (__generic_dma_ops(dev)->get_sgtable) {
+#if 0
+ /*
+ * This check verifies that the page belongs to the current domain and
+ * is not one mapped from another domain.
+ * This check is for debug only, and should not go to production build
+ */
+ unsigned long bfn = PHYS_PFN(dma_to_phys(dev, handle));
+ BUG_ON (!page_is_ram(bfn));
+#endif
+ return __generic_dma_ops(dev)->get_sgtable(dev, sgt, cpu_addr,
+ handle, size, attrs);
+ }
+#endif
+ return dma_common_get_sgtable(dev, sgt, cpu_addr, handle, size);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_get_sgtable);
diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c
index 4ce10bc..23e391d 100644
--- a/drivers/xen/xen-acpi-processor.c
+++ b/drivers/xen/xen-acpi-processor.c
@@ -27,10 +27,10 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/types.h>
+#include <linux/syscore_ops.h>
#include <linux/acpi.h>
#include <acpi/processor.h>
#include <xen/xen.h>
-#include <xen/xen-ops.h>
#include <xen/interface/platform.h>
#include <asm/xen/hypercall.h>
@@ -408,7 +408,7 @@ static int check_acpi_ids(struct acpi_processor *pr_backup)
acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT,
ACPI_UINT32_MAX,
read_acpi_id, NULL, NULL, NULL);
- acpi_get_devices("ACPI0007", read_acpi_id, NULL, NULL);
+ acpi_get_devices(ACPI_PROCESSOR_DEVICE_HID, read_acpi_id, NULL, NULL);
upload:
if (!bitmap_equal(acpi_id_present, acpi_ids_done, nr_acpi_bits)) {
@@ -466,15 +466,33 @@ static int xen_upload_processor_pm_data(void)
return rc;
}
-static int xen_acpi_processor_resume(struct notifier_block *nb,
- unsigned long action, void *data)
+static void xen_acpi_processor_resume_worker(struct work_struct *dummy)
{
+ int rc;
+
bitmap_zero(acpi_ids_done, nr_acpi_bits);
- return xen_upload_processor_pm_data();
+
+ rc = xen_upload_processor_pm_data();
+ if (rc != 0)
+ pr_info("ACPI data upload failed, error = %d\n", rc);
}
-struct notifier_block xen_acpi_processor_resume_nb = {
- .notifier_call = xen_acpi_processor_resume,
+static void xen_acpi_processor_resume(void)
+{
+ static DECLARE_WORK(wq, xen_acpi_processor_resume_worker);
+
+ /*
+ * xen_upload_processor_pm_data() calls non-atomic code.
+ * However, the context for xen_acpi_processor_resume is syscore
+ * with only the boot CPU online and in an atomic context.
+ *
+ * So defer the upload for some point safer.
+ */
+ schedule_work(&wq);
+}
+
+static struct syscore_ops xap_syscore_ops = {
+ .resume = xen_acpi_processor_resume,
};
static int __init xen_acpi_processor_init(void)
@@ -527,7 +545,7 @@ static int __init xen_acpi_processor_init(void)
if (rc)
goto err_unregister;
- xen_resume_notifier_register(&xen_acpi_processor_resume_nb);
+ register_syscore_ops(&xap_syscore_ops);
return 0;
err_unregister:
@@ -544,7 +562,7 @@ static void __exit xen_acpi_processor_exit(void)
{
int i;
- xen_resume_notifier_unregister(&xen_acpi_processor_resume_nb);
+ unregister_syscore_ops(&xap_syscore_ops);
kfree(acpi_ids_done);
kfree(acpi_id_present);
kfree(acpi_id_cst_present);
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 4d343ee..1f4733b 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -55,7 +55,6 @@
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/miscdevice.h>
-#include <linux/init.h>
#include <xen/xenbus.h>
#include <xen/xen.h>
diff --git a/fs/afs/callback.c b/fs/afs/callback.c
index b29447e..25d404d 100644
--- a/fs/afs/callback.c
+++ b/fs/afs/callback.c
@@ -362,7 +362,7 @@ static void afs_callback_updater(struct work_struct *work)
{
struct afs_server *server;
struct afs_vnode *vnode, *xvnode;
- time_t now;
+ time64_t now;
long timeout;
int ret;
@@ -370,7 +370,7 @@ static void afs_callback_updater(struct work_struct *work)
_enter("");
- now = get_seconds();
+ now = ktime_get_real_seconds();
/* find the first vnode to update */
spin_lock(&server->cb_lock);
@@ -424,7 +424,8 @@ static void afs_callback_updater(struct work_struct *work)
/* and then reschedule */
_debug("reschedule");
- vnode->update_at = get_seconds() + afs_vnode_update_timeout;
+ vnode->update_at = ktime_get_real_seconds() +
+ afs_vnode_update_timeout;
spin_lock(&server->cb_lock);
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index 2edbdcb..3062cce 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -187,7 +187,6 @@ static int afs_deliver_cb_callback(struct afs_call *call)
struct afs_callback *cb;
struct afs_server *server;
__be32 *bp;
- u32 tmp;
int ret, loop;
_enter("{%u}", call->unmarshall);
@@ -249,9 +248,9 @@ static int afs_deliver_cb_callback(struct afs_call *call)
if (ret < 0)
return ret;
- tmp = ntohl(call->tmp);
- _debug("CB count: %u", tmp);
- if (tmp != call->count && tmp != 0)
+ call->count2 = ntohl(call->tmp);
+ _debug("CB count: %u", call->count2);
+ if (call->count2 != call->count && call->count2 != 0)
return -EBADMSG;
call->offset = 0;
call->unmarshall++;
@@ -259,14 +258,14 @@ static int afs_deliver_cb_callback(struct afs_call *call)
case 4:
_debug("extract CB array");
ret = afs_extract_data(call, call->buffer,
- call->count * 3 * 4, false);
+ call->count2 * 3 * 4, false);
if (ret < 0)
return ret;
_debug("unmarshall CB array");
cb = call->request;
bp = call->buffer;
- for (loop = call->count; loop > 0; loop--, cb++) {
+ for (loop = call->count2; loop > 0; loop--, cb++) {
cb->version = ntohl(*bp++);
cb->expiry = ntohl(*bp++);
cb->type = ntohl(*bp++);
diff --git a/fs/afs/file.c b/fs/afs/file.c
index ba7b71f..0d5b850 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -30,6 +30,7 @@ static int afs_readpages(struct file *filp, struct address_space *mapping,
const struct file_operations afs_file_operations = {
.open = afs_open,
+ .flush = afs_flush,
.release = afs_release,
.llseek = generic_file_llseek,
.read_iter = generic_file_read_iter,
@@ -184,10 +185,13 @@ int afs_page_filler(void *data, struct page *page)
if (!req)
goto enomem;
+ /* We request a full page. If the page is a partial one at the
+ * end of the file, the server will return a short read and the
+ * unmarshalling code will clear the unfilled space.
+ */
atomic_set(&req->usage, 1);
req->pos = (loff_t)page->index << PAGE_SHIFT;
- req->len = min_t(size_t, i_size_read(inode) - req->pos,
- PAGE_SIZE);
+ req->len = PAGE_SIZE;
req->nr_pages = 1;
req->pages[0] = page;
get_page(page);
@@ -208,7 +212,13 @@ int afs_page_filler(void *data, struct page *page)
fscache_uncache_page(vnode->cache, page);
#endif
BUG_ON(PageFsCache(page));
- goto error;
+
+ if (ret == -EINTR ||
+ ret == -ENOMEM ||
+ ret == -ERESTARTSYS ||
+ ret == -EAGAIN)
+ goto error;
+ goto io_error;
}
SetPageUptodate(page);
@@ -227,10 +237,12 @@ int afs_page_filler(void *data, struct page *page)
_leave(" = 0");
return 0;
+io_error:
+ SetPageError(page);
+ goto error;
enomem:
ret = -ENOMEM;
error:
- SetPageError(page);
unlock_page(page);
_leave(" = %d", ret);
return ret;
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index ac8e766..19f76ae 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -17,6 +17,12 @@
#include "afs_fs.h"
/*
+ * We need somewhere to discard into in case the server helpfully returns more
+ * than we asked for in FS.FetchData{,64}.
+ */
+static u8 afs_discard_buffer[64];
+
+/*
* decode an AFSFid block
*/
static void xdr_decode_AFSFid(const __be32 **_bp, struct afs_fid *fid)
@@ -105,7 +111,7 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp,
vnode->vfs_inode.i_mode = mode;
}
- vnode->vfs_inode.i_ctime.tv_sec = status->mtime_server;
+ vnode->vfs_inode.i_ctime.tv_sec = status->mtime_client;
vnode->vfs_inode.i_mtime = vnode->vfs_inode.i_ctime;
vnode->vfs_inode.i_atime = vnode->vfs_inode.i_ctime;
vnode->vfs_inode.i_version = data_version;
@@ -139,7 +145,7 @@ static void xdr_decode_AFSCallBack(const __be32 **_bp, struct afs_vnode *vnode)
vnode->cb_version = ntohl(*bp++);
vnode->cb_expiry = ntohl(*bp++);
vnode->cb_type = ntohl(*bp++);
- vnode->cb_expires = vnode->cb_expiry + get_seconds();
+ vnode->cb_expires = vnode->cb_expiry + ktime_get_real_seconds();
*_bp = bp;
}
@@ -315,7 +321,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
void *buffer;
int ret;
- _enter("{%u,%zu/%u;%u/%llu}",
+ _enter("{%u,%zu/%u;%llu/%llu}",
call->unmarshall, call->offset, call->count,
req->remain, req->actual_len);
@@ -353,12 +359,6 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
req->actual_len |= ntohl(call->tmp);
_debug("DATA length: %llu", req->actual_len);
- /* Check that the server didn't want to send us extra. We
- * might want to just discard instead, but that requires
- * cooperation from AF_RXRPC.
- */
- if (req->actual_len > req->len)
- return -EBADMSG;
req->remain = req->actual_len;
call->offset = req->pos & (PAGE_SIZE - 1);
@@ -368,6 +368,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
call->unmarshall++;
begin_page:
+ ASSERTCMP(req->index, <, req->nr_pages);
if (req->remain > PAGE_SIZE - call->offset)
size = PAGE_SIZE - call->offset;
else
@@ -378,7 +379,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
/* extract the returned data */
case 3:
- _debug("extract data %u/%llu %zu/%u",
+ _debug("extract data %llu/%llu %zu/%u",
req->remain, req->actual_len, call->offset, call->count);
buffer = kmap(req->pages[req->index]);
@@ -389,19 +390,40 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
if (call->offset == PAGE_SIZE) {
if (req->page_done)
req->page_done(call, req);
+ req->index++;
if (req->remain > 0) {
- req->index++;
call->offset = 0;
+ if (req->index >= req->nr_pages) {
+ call->unmarshall = 4;
+ goto begin_discard;
+ }
goto begin_page;
}
}
+ goto no_more_data;
+
+ /* Discard any excess data the server gave us */
+ begin_discard:
+ case 4:
+ size = min_t(loff_t, sizeof(afs_discard_buffer), req->remain);
+ call->count = size;
+ _debug("extract discard %llu/%llu %zu/%u",
+ req->remain, req->actual_len, call->offset, call->count);
+
+ call->offset = 0;
+ ret = afs_extract_data(call, afs_discard_buffer, call->count, true);
+ req->remain -= call->offset;
+ if (ret < 0)
+ return ret;
+ if (req->remain > 0)
+ goto begin_discard;
no_more_data:
call->offset = 0;
- call->unmarshall++;
+ call->unmarshall = 5;
/* extract the metadata */
- case 4:
+ case 5:
ret = afs_extract_data(call, call->buffer,
(21 + 3 + 6) * 4, false);
if (ret < 0)
@@ -416,16 +438,17 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
call->offset = 0;
call->unmarshall++;
- case 5:
+ case 6:
break;
}
- if (call->count < PAGE_SIZE) {
- buffer = kmap(req->pages[req->index]);
- memset(buffer + call->count, 0, PAGE_SIZE - call->count);
- kunmap(req->pages[req->index]);
+ for (; req->index < req->nr_pages; req->index++) {
+ if (call->count < PAGE_SIZE)
+ zero_user_segment(req->pages[req->index],
+ call->count, PAGE_SIZE);
if (req->page_done)
req->page_done(call, req);
+ call->count = 0;
}
_leave(" = 0 [done]");
@@ -711,8 +734,8 @@ int afs_fs_create(struct afs_server *server,
memset(bp, 0, padsz);
bp = (void *) bp + padsz;
}
- *bp++ = htonl(AFS_SET_MODE);
- *bp++ = 0; /* mtime */
+ *bp++ = htonl(AFS_SET_MODE | AFS_SET_MTIME);
+ *bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */
*bp++ = 0; /* owner */
*bp++ = 0; /* group */
*bp++ = htonl(mode & S_IALLUGO); /* unix mode */
@@ -980,8 +1003,8 @@ int afs_fs_symlink(struct afs_server *server,
memset(bp, 0, c_padsz);
bp = (void *) bp + c_padsz;
}
- *bp++ = htonl(AFS_SET_MODE);
- *bp++ = 0; /* mtime */
+ *bp++ = htonl(AFS_SET_MODE | AFS_SET_MTIME);
+ *bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */
*bp++ = 0; /* owner */
*bp++ = 0; /* group */
*bp++ = htonl(S_IRWXUGO); /* unix mode */
@@ -1180,8 +1203,8 @@ static int afs_fs_store_data64(struct afs_server *server,
*bp++ = htonl(vnode->fid.vnode);
*bp++ = htonl(vnode->fid.unique);
- *bp++ = 0; /* mask */
- *bp++ = 0; /* mtime */
+ *bp++ = htonl(AFS_SET_MTIME); /* mask */
+ *bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */
*bp++ = 0; /* owner */
*bp++ = 0; /* group */
*bp++ = 0; /* unix mode */
@@ -1213,7 +1236,7 @@ int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb,
_enter(",%x,{%x:%u},,",
key_serial(wb->key), vnode->fid.vid, vnode->fid.vnode);
- size = to - offset;
+ size = (loff_t)to - (loff_t)offset;
if (first != last)
size += (loff_t)(last - first) << PAGE_SHIFT;
pos = (loff_t)first << PAGE_SHIFT;
@@ -1257,8 +1280,8 @@ int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb,
*bp++ = htonl(vnode->fid.vnode);
*bp++ = htonl(vnode->fid.unique);
- *bp++ = 0; /* mask */
- *bp++ = 0; /* mtime */
+ *bp++ = htonl(AFS_SET_MTIME); /* mask */
+ *bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */
*bp++ = 0; /* owner */
*bp++ = 0; /* group */
*bp++ = 0; /* unix mode */
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 1e4897a..aae55dd 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -54,8 +54,21 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key)
inode->i_fop = &afs_dir_file_operations;
break;
case AFS_FTYPE_SYMLINK:
- inode->i_mode = S_IFLNK | vnode->status.mode;
- inode->i_op = &page_symlink_inode_operations;
+ /* Symlinks with a mode of 0644 are actually mountpoints. */
+ if ((vnode->status.mode & 0777) == 0644) {
+ inode->i_flags |= S_AUTOMOUNT;
+
+ spin_lock(&vnode->lock);
+ set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags);
+ spin_unlock(&vnode->lock);
+
+ inode->i_mode = S_IFDIR | 0555;
+ inode->i_op = &afs_mntpt_inode_operations;
+ inode->i_fop = &afs_mntpt_file_operations;
+ } else {
+ inode->i_mode = S_IFLNK | vnode->status.mode;
+ inode->i_op = &page_symlink_inode_operations;
+ }
inode_nohighmem(inode);
break;
default:
@@ -70,27 +83,15 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key)
set_nlink(inode, vnode->status.nlink);
inode->i_uid = vnode->status.owner;
- inode->i_gid = GLOBAL_ROOT_GID;
+ inode->i_gid = vnode->status.group;
inode->i_size = vnode->status.size;
- inode->i_ctime.tv_sec = vnode->status.mtime_server;
+ inode->i_ctime.tv_sec = vnode->status.mtime_client;
inode->i_ctime.tv_nsec = 0;
inode->i_atime = inode->i_mtime = inode->i_ctime;
inode->i_blocks = 0;
inode->i_generation = vnode->fid.unique;
inode->i_version = vnode->status.data_version;
inode->i_mapping->a_ops = &afs_fs_aops;
-
- /* check to see whether a symbolic link is really a mountpoint */
- if (vnode->status.type == AFS_FTYPE_SYMLINK) {
- afs_mntpt_check_symlink(vnode, key);
-
- if (test_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags)) {
- inode->i_mode = S_IFDIR | vnode->status.mode;
- inode->i_op = &afs_mntpt_inode_operations;
- inode->i_fop = &afs_mntpt_file_operations;
- }
- }
-
return 0;
}
@@ -245,12 +246,13 @@ struct inode *afs_iget(struct super_block *sb, struct key *key,
vnode->cb_version = 0;
vnode->cb_expiry = 0;
vnode->cb_type = 0;
- vnode->cb_expires = get_seconds();
+ vnode->cb_expires = ktime_get_real_seconds();
} else {
vnode->cb_version = cb->version;
vnode->cb_expiry = cb->expiry;
vnode->cb_type = cb->type;
- vnode->cb_expires = vnode->cb_expiry + get_seconds();
+ vnode->cb_expires = vnode->cb_expiry +
+ ktime_get_real_seconds();
}
}
@@ -323,7 +325,7 @@ int afs_validate(struct afs_vnode *vnode, struct key *key)
!test_bit(AFS_VNODE_CB_BROKEN, &vnode->flags) &&
!test_bit(AFS_VNODE_MODIFIED, &vnode->flags) &&
!test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags)) {
- if (vnode->cb_expires < get_seconds() + 10) {
+ if (vnode->cb_expires < ktime_get_real_seconds() + 10) {
_debug("callback expired");
set_bit(AFS_VNODE_CB_BROKEN, &vnode->flags);
} else {
@@ -444,7 +446,7 @@ void afs_evict_inode(struct inode *inode)
mutex_lock(&vnode->permits_lock);
permits = vnode->permits;
- rcu_assign_pointer(vnode->permits, NULL);
+ RCU_INIT_POINTER(vnode->permits, NULL);
mutex_unlock(&vnode->permits_lock);
if (permits)
call_rcu(&permits->rcu, afs_zap_permits);
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 5dfa569..a690136 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -11,6 +11,7 @@
#include <linux/compiler.h>
#include <linux/kernel.h>
+#include <linux/ktime.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/rxrpc.h>
@@ -90,7 +91,10 @@ struct afs_call {
unsigned request_size; /* size of request data */
unsigned reply_max; /* maximum size of reply */
unsigned first_offset; /* offset into mapping[first] */
- unsigned last_to; /* amount of mapping[last] */
+ union {
+ unsigned last_to; /* amount of mapping[last] */
+ unsigned count2; /* count used in unmarshalling */
+ };
unsigned char unmarshall; /* unmarshalling phase */
bool incoming; /* T if incoming call */
bool send_pages; /* T if data from mapping should be sent */
@@ -127,12 +131,11 @@ struct afs_call_type {
*/
struct afs_read {
loff_t pos; /* Where to start reading */
- loff_t len; /* How much to read */
+ loff_t len; /* How much we're asking for */
loff_t actual_len; /* How much we're actually getting */
+ loff_t remain; /* Amount remaining */
atomic_t usage;
- unsigned int remain; /* Amount remaining */
unsigned int index; /* Which page we're reading into */
- unsigned int pg_offset; /* Offset in page we're at */
unsigned int nr_pages;
void (*page_done)(struct afs_call *, struct afs_read *);
struct page *pages[];
@@ -247,7 +250,7 @@ struct afs_cache_vhash {
*/
struct afs_vlocation {
atomic_t usage;
- time_t time_of_death; /* time at which put reduced usage to 0 */
+ time64_t time_of_death; /* time at which put reduced usage to 0 */
struct list_head link; /* link in cell volume location list */
struct list_head grave; /* link in master graveyard list */
struct list_head update; /* link in master update list */
@@ -258,7 +261,7 @@ struct afs_vlocation {
struct afs_cache_vlocation vldb; /* volume information DB record */
struct afs_volume *vols[3]; /* volume access record pointer (index by type) */
wait_queue_head_t waitq; /* status change waitqueue */
- time_t update_at; /* time at which record should be updated */
+ time64_t update_at; /* time at which record should be updated */
spinlock_t lock; /* access lock */
afs_vlocation_state_t state; /* volume location state */
unsigned short upd_rej_cnt; /* ENOMEDIUM count during update */
@@ -271,7 +274,7 @@ struct afs_vlocation {
*/
struct afs_server {
atomic_t usage;
- time_t time_of_death; /* time at which put reduced usage to 0 */
+ time64_t time_of_death; /* time at which put reduced usage to 0 */
struct in_addr addr; /* server address */
struct afs_cell *cell; /* cell in which server resides */
struct list_head link; /* link in cell's server list */
@@ -374,8 +377,8 @@ struct afs_vnode {
struct rb_node server_rb; /* link in server->fs_vnodes */
struct rb_node cb_promise; /* link in server->cb_promises */
struct work_struct cb_broken_work; /* work to be done on callback break */
- time_t cb_expires; /* time at which callback expires */
- time_t cb_expires_at; /* time used to order cb_promise */
+ time64_t cb_expires; /* time at which callback expires */
+ time64_t cb_expires_at; /* time used to order cb_promise */
unsigned cb_version; /* callback version */
unsigned cb_expiry; /* callback expiry time */
afs_callback_type_t cb_type; /* type of callback */
@@ -557,7 +560,6 @@ extern const struct inode_operations afs_autocell_inode_operations;
extern const struct file_operations afs_mntpt_file_operations;
extern struct vfsmount *afs_d_automount(struct path *);
-extern int afs_mntpt_check_symlink(struct afs_vnode *, struct key *);
extern void afs_mntpt_kill_timer(void);
/*
@@ -718,6 +720,7 @@ extern int afs_writepages(struct address_space *, struct writeback_control *);
extern void afs_pages_written_back(struct afs_vnode *, struct afs_call *);
extern ssize_t afs_file_write(struct kiocb *, struct iov_iter *);
extern int afs_writeback_all(struct afs_vnode *);
+extern int afs_flush(struct file *, fl_owner_t);
extern int afs_fsync(struct file *, loff_t, loff_t, int);
diff --git a/fs/afs/misc.c b/fs/afs/misc.c
index 91ea1aa..100b207 100644
--- a/fs/afs/misc.c
+++ b/fs/afs/misc.c
@@ -84,6 +84,8 @@ int afs_abort_to_error(u32 abort_code)
case RXKADDATALEN: return -EKEYREJECTED;
case RXKADILLEGALLEVEL: return -EKEYREJECTED;
+ case RXGEN_OPCODE: return -ENOTSUPP;
+
default: return -EREMOTEIO;
}
}
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index d4fb0af..bd3b65c 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -47,59 +47,6 @@ static DECLARE_DELAYED_WORK(afs_mntpt_expiry_timer, afs_mntpt_expiry_timed_out);
static unsigned long afs_mntpt_expiry_timeout = 10 * 60;
/*
- * check a symbolic link to see whether it actually encodes a mountpoint
- * - sets the AFS_VNODE_MOUNTPOINT flag on the vnode appropriately
- */
-int afs_mntpt_check_symlink(struct afs_vnode *vnode, struct key *key)
-{
- struct page *page;
- size_t size;
- char *buf;
- int ret;
-
- _enter("{%x:%u,%u}",
- vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique);
-
- /* read the contents of the symlink into the pagecache */
- page = read_cache_page(AFS_VNODE_TO_I(vnode)->i_mapping, 0,
- afs_page_filler, key);
- if (IS_ERR(page)) {
- ret = PTR_ERR(page);
- goto out;
- }
-
- ret = -EIO;
- if (PageError(page))
- goto out_free;
-
- buf = kmap(page);
-
- /* examine the symlink's contents */
- size = vnode->status.size;
- _debug("symlink to %*.*s", (int) size, (int) size, buf);
-
- if (size > 2 &&
- (buf[0] == '%' || buf[0] == '#') &&
- buf[size - 1] == '.'
- ) {
- _debug("symlink is a mountpoint");
- spin_lock(&vnode->lock);
- set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags);
- vnode->vfs_inode.i_flags |= S_AUTOMOUNT;
- spin_unlock(&vnode->lock);
- }
-
- ret = 0;
-
- kunmap(page);
-out_free:
- put_page(page);
-out:
- _leave(" = %d", ret);
- return ret;
-}
-
-/*
* no valid lookup procedure on this sort of dir
*/
static struct dentry *afs_mntpt_lookup(struct inode *dir,
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 419ef05..d5990eb 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -259,67 +259,74 @@ void afs_flat_call_destructor(struct afs_call *call)
call->buffer = NULL;
}
+#define AFS_BVEC_MAX 8
+
+/*
+ * Load the given bvec with the next few pages.
+ */
+static void afs_load_bvec(struct afs_call *call, struct msghdr *msg,
+ struct bio_vec *bv, pgoff_t first, pgoff_t last,
+ unsigned offset)
+{
+ struct page *pages[AFS_BVEC_MAX];
+ unsigned int nr, n, i, to, bytes = 0;
+
+ nr = min_t(pgoff_t, last - first + 1, AFS_BVEC_MAX);
+ n = find_get_pages_contig(call->mapping, first, nr, pages);
+ ASSERTCMP(n, ==, nr);
+
+ msg->msg_flags |= MSG_MORE;
+ for (i = 0; i < nr; i++) {
+ to = PAGE_SIZE;
+ if (first + i >= last) {
+ to = call->last_to;
+ msg->msg_flags &= ~MSG_MORE;
+ }
+ bv[i].bv_page = pages[i];
+ bv[i].bv_len = to - offset;
+ bv[i].bv_offset = offset;
+ bytes += to - offset;
+ offset = 0;
+ }
+
+ iov_iter_bvec(&msg->msg_iter, WRITE | ITER_BVEC, bv, nr, bytes);
+}
+
/*
* attach the data from a bunch of pages on an inode to a call
*/
static int afs_send_pages(struct afs_call *call, struct msghdr *msg)
{
- struct page *pages[8];
- unsigned count, n, loop, offset, to;
+ struct bio_vec bv[AFS_BVEC_MAX];
+ unsigned int bytes, nr, loop, offset;
pgoff_t first = call->first, last = call->last;
int ret;
- _enter("");
-
offset = call->first_offset;
call->first_offset = 0;
do {
- _debug("attach %lx-%lx", first, last);
+ afs_load_bvec(call, msg, bv, first, last, offset);
+ offset = 0;
+ bytes = msg->msg_iter.count;
+ nr = msg->msg_iter.nr_segs;
- count = last - first + 1;
- if (count > ARRAY_SIZE(pages))
- count = ARRAY_SIZE(pages);
- n = find_get_pages_contig(call->mapping, first, count, pages);
- ASSERTCMP(n, ==, count);
-
- loop = 0;
- do {
- struct bio_vec bvec = {.bv_page = pages[loop],
- .bv_offset = offset};
- msg->msg_flags = 0;
- to = PAGE_SIZE;
- if (first + loop >= last)
- to = call->last_to;
- else
- msg->msg_flags = MSG_MORE;
- bvec.bv_len = to - offset;
- offset = 0;
-
- _debug("- range %u-%u%s",
- offset, to, msg->msg_flags ? " [more]" : "");
- iov_iter_bvec(&msg->msg_iter, WRITE | ITER_BVEC,
- &bvec, 1, to - offset);
-
- /* have to change the state *before* sending the last
- * packet as RxRPC might give us the reply before it
- * returns from sending the request */
- if (first + loop >= last)
- call->state = AFS_CALL_AWAIT_REPLY;
- ret = rxrpc_kernel_send_data(afs_socket, call->rxcall,
- msg, to - offset);
- if (ret < 0)
- break;
- } while (++loop < count);
- first += count;
-
- for (loop = 0; loop < count; loop++)
- put_page(pages[loop]);
+ /* Have to change the state *before* sending the last
+ * packet as RxRPC might give us the reply before it
+ * returns from sending the request.
+ */
+ if (first + nr - 1 >= last)
+ call->state = AFS_CALL_AWAIT_REPLY;
+ ret = rxrpc_kernel_send_data(afs_socket, call->rxcall,
+ msg, bytes);
+ for (loop = 0; loop < nr; loop++)
+ put_page(bv[loop].bv_page);
if (ret < 0)
break;
+
+ first += nr;
} while (first <= last);
- _leave(" = %d", ret);
return ret;
}
@@ -333,6 +340,8 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
struct rxrpc_call *rxcall;
struct msghdr msg;
struct kvec iov[1];
+ size_t offset;
+ u32 abort_code;
int ret;
_enter("%x,{%d},", addr->s_addr, ntohs(call->port));
@@ -381,9 +390,11 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
msg.msg_controllen = 0;
msg.msg_flags = (call->send_pages ? MSG_MORE : 0);
- /* have to change the state *before* sending the last packet as RxRPC
- * might give us the reply before it returns from sending the
- * request */
+ /* We have to change the state *before* sending the last packet as
+ * rxrpc might give us the reply before it returns from sending the
+ * request. Further, if the send fails, we may already have been given
+ * a notification and may have collected it.
+ */
if (!call->send_pages)
call->state = AFS_CALL_AWAIT_REPLY;
ret = rxrpc_kernel_send_data(afs_socket, rxcall,
@@ -405,7 +416,17 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
return afs_wait_for_call_to_complete(call);
error_do_abort:
- rxrpc_kernel_abort_call(afs_socket, rxcall, RX_USER_ABORT, -ret, "KSD");
+ call->state = AFS_CALL_COMPLETE;
+ if (ret != -ECONNABORTED) {
+ rxrpc_kernel_abort_call(afs_socket, rxcall, RX_USER_ABORT,
+ ret, "KSD");
+ } else {
+ abort_code = 0;
+ offset = 0;
+ rxrpc_kernel_recv_data(afs_socket, rxcall, NULL, 0, &offset,
+ false, &abort_code);
+ ret = call->type->abort_to_error(abort_code);
+ }
error_kill_call:
afs_put_call(call);
_leave(" = %d", ret);
@@ -452,16 +473,18 @@ static void afs_deliver_to_call(struct afs_call *call)
case -EINPROGRESS:
case -EAGAIN:
goto out;
+ case -ECONNABORTED:
+ goto call_complete;
case -ENOTCONN:
abort_code = RX_CALL_DEAD;
rxrpc_kernel_abort_call(afs_socket, call->rxcall,
- abort_code, -ret, "KNC");
- goto do_abort;
+ abort_code, ret, "KNC");
+ goto save_error;
case -ENOTSUPP:
- abort_code = RX_INVALID_OPERATION;
+ abort_code = RXGEN_OPCODE;
rxrpc_kernel_abort_call(afs_socket, call->rxcall,
- abort_code, -ret, "KIV");
- goto do_abort;
+ abort_code, ret, "KIV");
+ goto save_error;
case -ENODATA:
case -EBADMSG:
case -EMSGSIZE:
@@ -470,8 +493,8 @@ static void afs_deliver_to_call(struct afs_call *call)
if (call->state != AFS_CALL_AWAIT_REPLY)
abort_code = RXGEN_SS_UNMARSHAL;
rxrpc_kernel_abort_call(afs_socket, call->rxcall,
- abort_code, EBADMSG, "KUM");
- goto do_abort;
+ abort_code, -EBADMSG, "KUM");
+ goto save_error;
}
}
@@ -482,8 +505,9 @@ static void afs_deliver_to_call(struct afs_call *call)
_leave("");
return;
-do_abort:
+save_error:
call->error = ret;
+call_complete:
call->state = AFS_CALL_COMPLETE;
goto done;
}
@@ -493,7 +517,6 @@ static void afs_deliver_to_call(struct afs_call *call)
*/
static int afs_wait_for_call_to_complete(struct afs_call *call)
{
- const char *abort_why;
int ret;
DECLARE_WAITQUEUE(myself, current);
@@ -512,13 +535,8 @@ static int afs_wait_for_call_to_complete(struct afs_call *call)
continue;
}
- abort_why = "KWC";
- ret = call->error;
- if (call->state == AFS_CALL_COMPLETE)
- break;
- abort_why = "KWI";
- ret = -EINTR;
- if (signal_pending(current))
+ if (call->state == AFS_CALL_COMPLETE ||
+ signal_pending(current))
break;
schedule();
}
@@ -526,13 +544,14 @@ static int afs_wait_for_call_to_complete(struct afs_call *call)
remove_wait_queue(&call->waitq, &myself);
__set_current_state(TASK_RUNNING);
- /* kill the call */
+ /* Kill off the call if it's still live. */
if (call->state < AFS_CALL_COMPLETE) {
- _debug("call incomplete");
+ _debug("call interrupted");
rxrpc_kernel_abort_call(afs_socket, call->rxcall,
- RX_CALL_DEAD, -ret, abort_why);
+ RX_USER_ABORT, -EINTR, "KWI");
}
+ ret = call->error;
_debug("call complete");
afs_put_call(call);
_leave(" = %d", ret);
@@ -735,7 +754,7 @@ void afs_send_empty_reply(struct afs_call *call)
case -ENOMEM:
_debug("oom");
rxrpc_kernel_abort_call(afs_socket, call->rxcall,
- RX_USER_ABORT, ENOMEM, "KOO");
+ RX_USER_ABORT, -ENOMEM, "KOO");
default:
_leave(" [error]");
return;
@@ -773,7 +792,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len)
if (n == -ENOMEM) {
_debug("oom");
rxrpc_kernel_abort_call(afs_socket, call->rxcall,
- RX_USER_ABORT, ENOMEM, "KOO");
+ RX_USER_ABORT, -ENOMEM, "KOO");
}
_leave(" [error]");
}
diff --git a/fs/afs/security.c b/fs/afs/security.c
index 8d01042..ecb86a6 100644
--- a/fs/afs/security.c
+++ b/fs/afs/security.c
@@ -114,7 +114,7 @@ void afs_clear_permits(struct afs_vnode *vnode)
mutex_lock(&vnode->permits_lock);
permits = vnode->permits;
- rcu_assign_pointer(vnode->permits, NULL);
+ RCU_INIT_POINTER(vnode->permits, NULL);
mutex_unlock(&vnode->permits_lock);
if (permits)
@@ -340,17 +340,22 @@ int afs_permission(struct inode *inode, int mask)
} else {
if (!(access & AFS_ACE_LOOKUP))
goto permission_denied;
+ if ((mask & MAY_EXEC) && !(inode->i_mode & S_IXUSR))
+ goto permission_denied;
if (mask & (MAY_EXEC | MAY_READ)) {
if (!(access & AFS_ACE_READ))
goto permission_denied;
+ if (!(inode->i_mode & S_IRUSR))
+ goto permission_denied;
} else if (mask & MAY_WRITE) {
if (!(access & AFS_ACE_WRITE))
goto permission_denied;
+ if (!(inode->i_mode & S_IWUSR))
+ goto permission_denied;
}
}
key_put(key);
- ret = generic_permission(inode, mask);
_leave(" = %d", ret);
return ret;
diff --git a/fs/afs/server.c b/fs/afs/server.c
index d4066ab..c001b1f 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -242,7 +242,7 @@ void afs_put_server(struct afs_server *server)
spin_lock(&afs_server_graveyard_lock);
if (atomic_read(&server->usage) == 0) {
list_move_tail(&server->grave, &afs_server_graveyard);
- server->time_of_death = get_seconds();
+ server->time_of_death = ktime_get_real_seconds();
queue_delayed_work(afs_wq, &afs_server_reaper,
afs_server_timeout * HZ);
}
@@ -277,9 +277,9 @@ static void afs_reap_server(struct work_struct *work)
LIST_HEAD(corpses);
struct afs_server *server;
unsigned long delay, expiry;
- time_t now;
+ time64_t now;
- now = get_seconds();
+ now = ktime_get_real_seconds();
spin_lock(&afs_server_graveyard_lock);
while (!list_empty(&afs_server_graveyard)) {
diff --git a/fs/afs/vlocation.c b/fs/afs/vlocation.c
index d7d8dd8..37b7c3b 100644
--- a/fs/afs/vlocation.c
+++ b/fs/afs/vlocation.c
@@ -340,7 +340,8 @@ static void afs_vlocation_queue_for_updates(struct afs_vlocation *vl)
struct afs_vlocation *xvl;
/* wait at least 10 minutes before updating... */
- vl->update_at = get_seconds() + afs_vlocation_update_timeout;
+ vl->update_at = ktime_get_real_seconds() +
+ afs_vlocation_update_timeout;
spin_lock(&afs_vlocation_updates_lock);
@@ -506,7 +507,7 @@ void afs_put_vlocation(struct afs_vlocation *vl)
if (atomic_read(&vl->usage) == 0) {
_debug("buried");
list_move_tail(&vl->grave, &afs_vlocation_graveyard);
- vl->time_of_death = get_seconds();
+ vl->time_of_death = ktime_get_real_seconds();
queue_delayed_work(afs_wq, &afs_vlocation_reap,
afs_vlocation_timeout * HZ);
@@ -543,11 +544,11 @@ static void afs_vlocation_reaper(struct work_struct *work)
LIST_HEAD(corpses);
struct afs_vlocation *vl;
unsigned long delay, expiry;
- time_t now;
+ time64_t now;
_enter("");
- now = get_seconds();
+ now = ktime_get_real_seconds();
spin_lock(&afs_vlocation_graveyard_lock);
while (!list_empty(&afs_vlocation_graveyard)) {
@@ -622,13 +623,13 @@ static void afs_vlocation_updater(struct work_struct *work)
{
struct afs_cache_vlocation vldb;
struct afs_vlocation *vl, *xvl;
- time_t now;
+ time64_t now;
long timeout;
int ret;
_enter("");
- now = get_seconds();
+ now = ktime_get_real_seconds();
/* find a record to update */
spin_lock(&afs_vlocation_updates_lock);
@@ -684,7 +685,8 @@ static void afs_vlocation_updater(struct work_struct *work)
/* and then reschedule */
_debug("reschedule");
- vl->update_at = get_seconds() + afs_vlocation_update_timeout;
+ vl->update_at = ktime_get_real_seconds() +
+ afs_vlocation_update_timeout;
spin_lock(&afs_vlocation_updates_lock);
diff --git a/fs/afs/write.c b/fs/afs/write.c
index c83c1a0..2d2fccd 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -84,10 +84,9 @@ void afs_put_writeback(struct afs_writeback *wb)
* partly or wholly fill a page that's under preparation for writing
*/
static int afs_fill_page(struct afs_vnode *vnode, struct key *key,
- loff_t pos, struct page *page)
+ loff_t pos, unsigned int len, struct page *page)
{
struct afs_read *req;
- loff_t i_size;
int ret;
_enter(",,%llu", (unsigned long long)pos);
@@ -99,14 +98,10 @@ static int afs_fill_page(struct afs_vnode *vnode, struct key *key,
atomic_set(&req->usage, 1);
req->pos = pos;
+ req->len = len;
req->nr_pages = 1;
req->pages[0] = page;
-
- i_size = i_size_read(&vnode->vfs_inode);
- if (pos + PAGE_SIZE > i_size)
- req->len = i_size - pos;
- else
- req->len = PAGE_SIZE;
+ get_page(page);
ret = afs_vnode_fetch_data(vnode, key, req);
afs_put_read(req);
@@ -159,12 +154,12 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
kfree(candidate);
return -ENOMEM;
}
- *pagep = page;
- /* page won't leak in error case: it eventually gets cleaned off LRU */
if (!PageUptodate(page) && len != PAGE_SIZE) {
- ret = afs_fill_page(vnode, key, index << PAGE_SHIFT, page);
+ ret = afs_fill_page(vnode, key, pos & PAGE_MASK, PAGE_SIZE, page);
if (ret < 0) {
+ unlock_page(page);
+ put_page(page);
kfree(candidate);
_leave(" = %d [prep]", ret);
return ret;
@@ -172,6 +167,9 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
SetPageUptodate(page);
}
+ /* page won't leak in error case: it eventually gets cleaned off LRU */
+ *pagep = page;
+
try_again:
spin_lock(&vnode->writeback_lock);
@@ -233,7 +231,7 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
if (wb->state == AFS_WBACK_PENDING)
wb->state = AFS_WBACK_CONFLICTING;
spin_unlock(&vnode->writeback_lock);
- if (PageDirty(page)) {
+ if (clear_page_dirty_for_io(page)) {
ret = afs_write_back_from_locked_page(wb, page);
if (ret < 0) {
afs_put_writeback(candidate);
@@ -257,7 +255,9 @@ int afs_write_end(struct file *file, struct address_space *mapping,
struct page *page, void *fsdata)
{
struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
+ struct key *key = file->private_data;
loff_t i_size, maybe_i_size;
+ int ret;
_enter("{%x:%u},{%lx}",
vnode->fid.vid, vnode->fid.vnode, page->index);
@@ -273,6 +273,20 @@ int afs_write_end(struct file *file, struct address_space *mapping,
spin_unlock(&vnode->writeback_lock);
}
+ if (!PageUptodate(page)) {
+ if (copied < len) {
+ /* Try and load any missing data from the server. The
+ * unmarshalling routine will take care of clearing any
+ * bits that are beyond the EOF.
+ */
+ ret = afs_fill_page(vnode, key, pos + copied,
+ len - copied, page);
+ if (ret < 0)
+ return ret;
+ }
+ SetPageUptodate(page);
+ }
+
set_page_dirty(page);
if (PageDirty(page))
_debug("dirtied");
@@ -307,10 +321,14 @@ static void afs_kill_pages(struct afs_vnode *vnode, bool error,
ASSERTCMP(pv.nr, ==, count);
for (loop = 0; loop < count; loop++) {
- ClearPageUptodate(pv.pages[loop]);
+ struct page *page = pv.pages[loop];
+ ClearPageUptodate(page);
if (error)
- SetPageError(pv.pages[loop]);
- end_page_writeback(pv.pages[loop]);
+ SetPageError(page);
+ if (PageWriteback(page))
+ end_page_writeback(page);
+ if (page->index >= first)
+ first = page->index + 1;
}
__pagevec_release(&pv);
@@ -335,8 +353,6 @@ static int afs_write_back_from_locked_page(struct afs_writeback *wb,
_enter(",%lx", primary_page->index);
count = 1;
- if (!clear_page_dirty_for_io(primary_page))
- BUG();
if (test_set_page_writeback(primary_page))
BUG();
@@ -502,17 +518,17 @@ static int afs_writepages_region(struct address_space *mapping,
*/
lock_page(page);
- if (page->mapping != mapping) {
+ if (page->mapping != mapping || !PageDirty(page)) {
unlock_page(page);
put_page(page);
continue;
}
- if (wbc->sync_mode != WB_SYNC_NONE)
- wait_on_page_writeback(page);
-
- if (PageWriteback(page) || !PageDirty(page)) {
+ if (PageWriteback(page)) {
unlock_page(page);
+ if (wbc->sync_mode != WB_SYNC_NONE)
+ wait_on_page_writeback(page);
+ put_page(page);
continue;
}
@@ -523,6 +539,8 @@ static int afs_writepages_region(struct address_space *mapping,
wb->state = AFS_WBACK_WRITING;
spin_unlock(&wb->vnode->writeback_lock);
+ if (!clear_page_dirty_for_io(page))
+ BUG();
ret = afs_write_back_from_locked_page(wb, page);
unlock_page(page);
put_page(page);
@@ -746,6 +764,20 @@ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
}
/*
+ * Flush out all outstanding writes on a file opened for writing when it is
+ * closed.
+ */
+int afs_flush(struct file *file, fl_owner_t id)
+{
+ _enter("");
+
+ if ((file->f_mode & FMODE_WRITE) == 0)
+ return 0;
+
+ return vfs_fsync(file, 0);
+}
+
+/*
* notification that a previously read-only page is about to become writable
* - if it returns an error, the caller will deliver a bus error signal
*/
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 29b7fc2..c411590 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1259,7 +1259,7 @@ struct btrfs_root {
atomic_t will_be_snapshoted;
/* For qgroup metadata space reserve */
- atomic_t qgroup_meta_rsv;
+ atomic64_t qgroup_meta_rsv;
};
static inline u32 btrfs_inode_sectorsize(const struct inode *inode)
{
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 08b74da..eb1ee7b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1342,7 +1342,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
atomic_set(&root->orphan_inodes, 0);
atomic_set(&root->refs, 1);
atomic_set(&root->will_be_snapshoted, 0);
- atomic_set(&root->qgroup_meta_rsv, 0);
+ atomic64_set(&root->qgroup_meta_rsv, 0);
root->log_transid = 0;
root->log_transid_committed = -1;
root->last_log_commit = 0;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 28e8192..27fdb25 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1714,7 +1714,8 @@ static int __process_pages_contig(struct address_space *mapping,
* can we find nothing at @index.
*/
ASSERT(page_ops & PAGE_LOCK);
- return ret;
+ err = -EAGAIN;
+ goto out;
}
for (i = 0; i < ret; i++) {
@@ -2583,26 +2584,36 @@ static void end_bio_extent_readpage(struct bio *bio)
if (tree->ops) {
ret = tree->ops->readpage_io_failed_hook(page, mirror);
- if (!ret && !bio->bi_error)
- uptodate = 1;
- } else {
- /*
- * The generic bio_readpage_error handles errors the
- * following way: If possible, new read requests are
- * created and submitted and will end up in
- * end_bio_extent_readpage as well (if we're lucky, not
- * in the !uptodate case). In that case it returns 0 and
- * we just go on with the next page in our bio. If it
- * can't handle the error it will return -EIO and we
- * remain responsible for that page.
- */
- ret = bio_readpage_error(bio, offset, page, start, end,
- mirror);
- if (ret == 0) {
- uptodate = !bio->bi_error;
- offset += len;
- continue;
+ if (ret == -EAGAIN) {
+ /*
+ * Data inode's readpage_io_failed_hook() always
+ * returns -EAGAIN.
+ *
+ * The generic bio_readpage_error handles errors
+ * the following way: If possible, new read
+ * requests are created and submitted and will
+ * end up in end_bio_extent_readpage as well (if
+ * we're lucky, not in the !uptodate case). In
+ * that case it returns 0 and we just go on with
+ * the next page in our bio. If it can't handle
+ * the error it will return -EIO and we remain
+ * responsible for that page.
+ */
+ ret = bio_readpage_error(bio, offset, page,
+ start, end, mirror);
+ if (ret == 0) {
+ uptodate = !bio->bi_error;
+ offset += len;
+ continue;
+ }
}
+
+ /*
+ * metadata's readpage_io_failed_hook() always returns
+ * -EIO and fixes nothing. -EIO is also returned if
+ * data inode error could not be fixed.
+ */
+ ASSERT(ret == -EIO);
}
readpage_ok:
if (likely(uptodate)) {
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index c40060c..a18510b 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6709,6 +6709,20 @@ static noinline int uncompress_inline(struct btrfs_path *path,
max_size = min_t(unsigned long, PAGE_SIZE, max_size);
ret = btrfs_decompress(compress_type, tmp, page,
extent_offset, inline_size, max_size);
+
+ /*
+ * decompression code contains a memset to fill in any space between the end
+ * of the uncompressed data and the end of max_size in case the decompressed
+ * data ends up shorter than ram_bytes. That doesn't cover the hole between
+ * the end of an inline extent and the beginning of the next block, so we
+ * cover that region here.
+ */
+
+ if (max_size + pg_offset < PAGE_SIZE) {
+ char *map = kmap(page);
+ memset(map + pg_offset + max_size, 0, PAGE_SIZE - max_size - pg_offset);
+ kunmap(page);
+ }
kfree(tmp);
return ret;
}
@@ -10509,9 +10523,9 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
}
__attribute__((const))
-static int dummy_readpage_io_failed_hook(struct page *page, int failed_mirror)
+static int btrfs_readpage_io_failed_hook(struct page *page, int failed_mirror)
{
- return 0;
+ return -EAGAIN;
}
static const struct inode_operations btrfs_dir_inode_operations = {
@@ -10556,7 +10570,7 @@ static const struct extent_io_ops btrfs_extent_io_ops = {
.submit_bio_hook = btrfs_submit_bio_hook,
.readpage_end_io_hook = btrfs_readpage_end_io_hook,
.merge_bio_hook = btrfs_merge_bio_hook,
- .readpage_io_failed_hook = dummy_readpage_io_failed_hook,
+ .readpage_io_failed_hook = btrfs_readpage_io_failed_hook,
/* optional callbacks */
.fill_delalloc = run_delalloc_range,
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index a5da750..a59801d 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2948,20 +2948,20 @@ int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
ret = qgroup_reserve(root, num_bytes, enforce);
if (ret < 0)
return ret;
- atomic_add(num_bytes, &root->qgroup_meta_rsv);
+ atomic64_add(num_bytes, &root->qgroup_meta_rsv);
return ret;
}
void btrfs_qgroup_free_meta_all(struct btrfs_root *root)
{
struct btrfs_fs_info *fs_info = root->fs_info;
- int reserved;
+ u64 reserved;
if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) ||
!is_fstree(root->objectid))
return;
- reserved = atomic_xchg(&root->qgroup_meta_rsv, 0);
+ reserved = atomic64_xchg(&root->qgroup_meta_rsv, 0);
if (reserved == 0)
return;
btrfs_qgroup_free_refroot(fs_info, root->objectid, reserved);
@@ -2976,8 +2976,8 @@ void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes)
return;
BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize));
- WARN_ON(atomic_read(&root->qgroup_meta_rsv) < num_bytes);
- atomic_sub(num_bytes, &root->qgroup_meta_rsv);
+ WARN_ON(atomic64_read(&root->qgroup_meta_rsv) < num_bytes);
+ atomic64_sub(num_bytes, &root->qgroup_meta_rsv);
btrfs_qgroup_free_refroot(fs_info, root->objectid, num_bytes);
}
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 456c890..a60d5bf 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -6305,8 +6305,13 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
goto out;
}
+ /*
+ * Check that we don't overflow at later allocations, we request
+ * clone_sources_count + 1 items, and compare to unsigned long inside
+ * access_ok.
+ */
if (arg->clone_sources_count >
- ULLONG_MAX / sizeof(*arg->clone_sources)) {
+ ULONG_MAX / sizeof(struct clone_root) - 1) {
ret = -EINVAL;
goto out;
}
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 15e1db8..8c91f37 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -37,6 +37,7 @@
#include <linux/freezer.h>
#include <linux/namei.h>
#include <linux/random.h>
+#include <linux/uuid.h>
#include <linux/xattr.h>
#include <net/ipv6.h>
#include "cifsfs.h"
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 9ae695a..858698d 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -35,6 +35,7 @@
#include <linux/pagevec.h>
#include <linux/freezer.h>
#include <linux/namei.h>
+#include <linux/uuid.h>
#include <linux/uaccess.h>
#include <asm/processor.h>
#include <linux/inet.h>
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 7446496..fb75fe9 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -33,6 +33,7 @@
#include <linux/vfs.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/uaccess.h>
+#include <linux/uuid.h>
#include <linux/pagemap.h>
#include <linux/xattr.h>
#include "smb2pdu.h"
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
index 02a7a92..6d6eca3 100644
--- a/fs/crypto/crypto.c
+++ b/fs/crypto/crypto.c
@@ -327,7 +327,6 @@ EXPORT_SYMBOL(fscrypt_decrypt_page);
static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
{
struct dentry *dir;
- struct fscrypt_info *ci;
int dir_has_key, cached_with_key;
if (flags & LOOKUP_RCU)
@@ -339,18 +338,11 @@ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
return 0;
}
- ci = d_inode(dir)->i_crypt_info;
- if (ci && ci->ci_keyring_key &&
- (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
- (1 << KEY_FLAG_REVOKED) |
- (1 << KEY_FLAG_DEAD))))
- ci = NULL;
-
/* this should eventually be an flag in d_flags */
spin_lock(&dentry->d_lock);
cached_with_key = dentry->d_flags & DCACHE_ENCRYPTED_WITH_KEY;
spin_unlock(&dentry->d_lock);
- dir_has_key = (ci != NULL);
+ dir_has_key = (d_inode(dir)->i_crypt_info != NULL);
dput(dir);
/*
diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index 13052b8..37b4989 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -350,7 +350,7 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
fname->disk_name.len = iname->len;
return 0;
}
- ret = fscrypt_get_crypt_info(dir);
+ ret = fscrypt_get_encryption_info(dir);
if (ret && ret != -EOPNOTSUPP)
return ret;
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index fdbb8af..e39696e 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -67,7 +67,6 @@ struct fscrypt_info {
u8 ci_filename_mode;
u8 ci_flags;
struct crypto_skcipher *ci_ctfm;
- struct key *ci_keyring_key;
u8 ci_master_key[FS_KEY_DESCRIPTOR_SIZE];
};
@@ -101,7 +100,4 @@ extern int fscrypt_do_page_crypto(const struct inode *inode,
extern struct page *fscrypt_alloc_bounce_page(struct fscrypt_ctx *ctx,
gfp_t gfp_flags);
-/* keyinfo.c */
-extern int fscrypt_get_crypt_info(struct inode *);
-
#endif /* _FSCRYPT_PRIVATE_H */
diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c
index d5d896f..8cdfddc 100644
--- a/fs/crypto/keyinfo.c
+++ b/fs/crypto/keyinfo.c
@@ -95,6 +95,7 @@ static int validate_user_key(struct fscrypt_info *crypt_info,
kfree(description);
if (IS_ERR(keyring_key))
return PTR_ERR(keyring_key);
+ down_read(&keyring_key->sem);
if (keyring_key->type != &key_type_logon) {
printk_once(KERN_WARNING
@@ -102,11 +103,9 @@ static int validate_user_key(struct fscrypt_info *crypt_info,
res = -ENOKEY;
goto out;
}
- down_read(&keyring_key->sem);
ukp = user_key_payload_locked(keyring_key);
if (ukp->datalen != sizeof(struct fscrypt_key)) {
res = -EINVAL;
- up_read(&keyring_key->sem);
goto out;
}
master_key = (struct fscrypt_key *)ukp->data;
@@ -117,17 +116,11 @@ static int validate_user_key(struct fscrypt_info *crypt_info,
"%s: key size incorrect: %d\n",
__func__, master_key->size);
res = -ENOKEY;
- up_read(&keyring_key->sem);
goto out;
}
res = derive_key_aes(ctx->nonce, master_key->raw, raw_key);
- up_read(&keyring_key->sem);
- if (res)
- goto out;
-
- crypt_info->ci_keyring_key = keyring_key;
- return 0;
out:
+ up_read(&keyring_key->sem);
key_put(keyring_key);
return res;
}
@@ -169,12 +162,11 @@ static void put_crypt_info(struct fscrypt_info *ci)
if (!ci)
return;
- key_put(ci->ci_keyring_key);
crypto_free_skcipher(ci->ci_ctfm);
kmem_cache_free(fscrypt_info_cachep, ci);
}
-int fscrypt_get_crypt_info(struct inode *inode)
+int fscrypt_get_encryption_info(struct inode *inode)
{
struct fscrypt_info *crypt_info;
struct fscrypt_context ctx;
@@ -184,21 +176,15 @@ int fscrypt_get_crypt_info(struct inode *inode)
u8 *raw_key = NULL;
int res;
+ if (inode->i_crypt_info)
+ return 0;
+
res = fscrypt_initialize(inode->i_sb->s_cop->flags);
if (res)
return res;
if (!inode->i_sb->s_cop->get_context)
return -EOPNOTSUPP;
-retry:
- crypt_info = ACCESS_ONCE(inode->i_crypt_info);
- if (crypt_info) {
- if (!crypt_info->ci_keyring_key ||
- key_validate(crypt_info->ci_keyring_key) == 0)
- return 0;
- fscrypt_put_encryption_info(inode, crypt_info);
- goto retry;
- }
res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
if (res < 0) {
@@ -229,7 +215,6 @@ int fscrypt_get_crypt_info(struct inode *inode)
crypt_info->ci_data_mode = ctx.contents_encryption_mode;
crypt_info->ci_filename_mode = ctx.filenames_encryption_mode;
crypt_info->ci_ctfm = NULL;
- crypt_info->ci_keyring_key = NULL;
memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor,
sizeof(crypt_info->ci_master_key));
@@ -273,14 +258,8 @@ int fscrypt_get_crypt_info(struct inode *inode)
if (res)
goto out;
- kzfree(raw_key);
- raw_key = NULL;
- if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) != NULL) {
- put_crypt_info(crypt_info);
- goto retry;
- }
- return 0;
-
+ if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) == NULL)
+ crypt_info = NULL;
out:
if (res == -ENOKEY)
res = 0;
@@ -288,6 +267,7 @@ int fscrypt_get_crypt_info(struct inode *inode)
kzfree(raw_key);
return res;
}
+EXPORT_SYMBOL(fscrypt_get_encryption_info);
void fscrypt_put_encryption_info(struct inode *inode, struct fscrypt_info *ci)
{
@@ -305,17 +285,3 @@ void fscrypt_put_encryption_info(struct inode *inode, struct fscrypt_info *ci)
put_crypt_info(ci);
}
EXPORT_SYMBOL(fscrypt_put_encryption_info);
-
-int fscrypt_get_encryption_info(struct inode *inode)
-{
- struct fscrypt_info *ci = inode->i_crypt_info;
-
- if (!ci ||
- (ci->ci_keyring_key &&
- (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
- (1 << KEY_FLAG_REVOKED) |
- (1 << KEY_FLAG_DEAD)))))
- return fscrypt_get_crypt_info(inode);
- return 0;
-}
-EXPORT_SYMBOL(fscrypt_get_encryption_info);
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 14b76da..4908906 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -33,17 +33,10 @@ static int create_encryption_context_from_policy(struct inode *inode,
const struct fscrypt_policy *policy)
{
struct fscrypt_context ctx;
- int res;
if (!inode->i_sb->s_cop->set_context)
return -EOPNOTSUPP;
- if (inode->i_sb->s_cop->prepare_context) {
- res = inode->i_sb->s_cop->prepare_context(inode);
- if (res)
- return res;
- }
-
ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
memcpy(ctx.master_key_descriptor, policy->master_key_descriptor,
FS_KEY_DESCRIPTOR_SIZE);
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 7d398d3..9382db9 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -743,7 +743,7 @@ static int tcp_accept_from_sock(struct connection *con)
newsock->type = con->sock->type;
newsock->ops = con->sock->ops;
- result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK);
+ result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK, true);
if (result < 0)
goto accept_err;
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 3412514..5420767 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -42,6 +42,7 @@
#include <linux/seq_file.h>
#include <linux/compat.h>
#include <linux/rculist.h>
+#include <net/busy_poll.h>
/*
* LOCKING:
@@ -224,6 +225,11 @@ struct eventpoll {
/* used to optimize loop detection check */
int visited;
struct list_head visited_list_link;
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+ /* used to track busy poll napi_id */
+ unsigned int napi_id;
+#endif
};
/* Wait structure used by the poll hooks */
@@ -384,6 +390,77 @@ static inline int ep_events_available(struct eventpoll *ep)
return !list_empty(&ep->rdllist) || ep->ovflist != EP_UNACTIVE_PTR;
}
+#ifdef CONFIG_NET_RX_BUSY_POLL
+static bool ep_busy_loop_end(void *p, unsigned long start_time)
+{
+ struct eventpoll *ep = p;
+
+ return ep_events_available(ep) || busy_loop_timeout(start_time);
+}
+#endif /* CONFIG_NET_RX_BUSY_POLL */
+
+/*
+ * Busy poll if globally on and supporting sockets found && no events,
+ * busy loop will return if need_resched or ep_events_available.
+ *
+ * we must do our busy polling with irqs enabled
+ */
+static void ep_busy_loop(struct eventpoll *ep, int nonblock)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+ unsigned int napi_id = READ_ONCE(ep->napi_id);
+
+ if ((napi_id >= MIN_NAPI_ID) && net_busy_loop_on())
+ napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep);
+#endif
+}
+
+static inline void ep_reset_busy_poll_napi_id(struct eventpoll *ep)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+ if (ep->napi_id)
+ ep->napi_id = 0;
+#endif
+}
+
+/*
+ * Set epoll busy poll NAPI ID from sk.
+ */
+static inline void ep_set_busy_poll_napi_id(struct epitem *epi)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+ struct eventpoll *ep;
+ unsigned int napi_id;
+ struct socket *sock;
+ struct sock *sk;
+ int err;
+
+ if (!net_busy_loop_on())
+ return;
+
+ sock = sock_from_file(epi->ffd.file, &err);
+ if (!sock)
+ return;
+
+ sk = sock->sk;
+ if (!sk)
+ return;
+
+ napi_id = READ_ONCE(sk->sk_napi_id);
+ ep = epi->ep;
+
+ /* Non-NAPI IDs can be rejected
+ * or
+ * Nothing to do if we already have this ID
+ */
+ if (napi_id < MIN_NAPI_ID || napi_id == ep->napi_id)
+ return;
+
+ /* record NAPI ID for use in next busy poll */
+ ep->napi_id = napi_id;
+#endif
+}
+
/**
* ep_call_nested - Perform a bound (possibly) nested call, by checking
* that the recursion limit is not exceeded, and that
@@ -1022,6 +1099,8 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
spin_lock_irqsave(&ep->lock, flags);
+ ep_set_busy_poll_napi_id(epi);
+
/*
* If the event mask does not contain any poll(2) event, we consider the
* descriptor to be disabled. This condition is likely the effect of the
@@ -1363,6 +1442,9 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
/* We have to drop the new item inside our item list to keep track of it */
spin_lock_irqsave(&ep->lock, flags);
+ /* record NAPI ID of new item if present */
+ ep_set_busy_poll_napi_id(epi);
+
/* If the file is already "ready" we drop it inside the ready list */
if ((revents & event->events) && !ep_is_linked(&epi->rdllink)) {
list_add_tail(&epi->rdllink, &ep->rdllist);
@@ -1637,10 +1719,21 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
}
fetch_events:
+
+ if (!ep_events_available(ep))
+ ep_busy_loop(ep, timed_out);
+
spin_lock_irqsave(&ep->lock, flags);
if (!ep_events_available(ep)) {
/*
+ * Busy poll timed out. Drop NAPI ID for now, we can add
+ * it back in when we have moved a socket with a valid NAPI
+ * ID onto the ready list.
+ */
+ ep_reset_busy_poll_napi_id(ep);
+
+ /*
* We don't have any available event to return to the caller.
* We need to sleep here, and we will be wake up by
* ep_poll_callback() when events will become available.
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 30a9f21..375fb1c 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -1169,10 +1169,9 @@ static int ext4_finish_convert_inline_dir(handle_t *handle,
set_buffer_uptodate(dir_block);
err = ext4_handle_dirty_dirent_node(handle, inode, dir_block);
if (err)
- goto out;
+ return err;
set_buffer_verified(dir_block);
-out:
- return err;
+ return ext4_mark_inode_dirty(handle, inode);
}
static int ext4_convert_inline_data_nolock(handle_t *handle,
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 7385e6a..4247d8d 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5400,7 +5400,7 @@ int ext4_getattr(const struct path *path, struct kstat *stat,
* If there is inline data in the inode, the inode will normally not
* have data blocks allocated (it may have an external xattr block).
* Report at least one sector for such files, so tools like tar, rsync,
- * others doen't incorrectly think the file is completely sparse.
+ * others don't incorrectly think the file is completely sparse.
*/
if (unlikely(ext4_has_inline_data(inode)))
stat->blocks += (stat->size + 511) >> 9;
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 578f8c3..c992ef2 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -511,7 +511,7 @@ mext_check_arguments(struct inode *orig_inode,
if ((orig_start & ~(PAGE_MASK >> orig_inode->i_blkbits)) !=
(donor_start & ~(PAGE_MASK >> orig_inode->i_blkbits))) {
ext4_debug("ext4 move extent: orig and donor's start "
- "offset are not alligned [ino:orig %lu, donor %lu]\n",
+ "offsets are not aligned [ino:orig %lu, donor %lu]\n",
orig_inode->i_ino, donor_inode->i_ino);
return -EINVAL;
}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 2e03a0a..a9448db 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1120,17 +1120,16 @@ static int ext4_get_context(struct inode *inode, void *ctx, size_t len)
EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len);
}
-static int ext4_prepare_context(struct inode *inode)
-{
- return ext4_convert_inline_data(inode);
-}
-
static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
void *fs_data)
{
handle_t *handle = fs_data;
int res, res2, retries = 0;
+ res = ext4_convert_inline_data(inode);
+ if (res)
+ return res;
+
/*
* If a journal handle was specified, then the encryption context is
* being set on a new inode via inheritance and is part of a larger
@@ -1196,7 +1195,6 @@ static unsigned ext4_max_namelen(struct inode *inode)
static const struct fscrypt_operations ext4_cryptops = {
.key_prefix = "ext4:",
.get_context = ext4_get_context,
- .prepare_context = ext4_prepare_context,
.set_context = ext4_set_context,
.dummy_context = ext4_dummy_context,
.is_encrypted = ext4_encrypted_inode,
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 67636ac..996e790 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -131,31 +131,26 @@ static __le32 ext4_xattr_block_csum(struct inode *inode,
}
static int ext4_xattr_block_csum_verify(struct inode *inode,
- sector_t block_nr,
- struct ext4_xattr_header *hdr)
+ struct buffer_head *bh)
{
- if (ext4_has_metadata_csum(inode->i_sb) &&
- (hdr->h_checksum != ext4_xattr_block_csum(inode, block_nr, hdr)))
- return 0;
- return 1;
+ struct ext4_xattr_header *hdr = BHDR(bh);
+ int ret = 1;
+
+ if (ext4_has_metadata_csum(inode->i_sb)) {
+ lock_buffer(bh);
+ ret = (hdr->h_checksum == ext4_xattr_block_csum(inode,
+ bh->b_blocknr, hdr));
+ unlock_buffer(bh);
+ }
+ return ret;
}
static void ext4_xattr_block_csum_set(struct inode *inode,
- sector_t block_nr,
- struct ext4_xattr_header *hdr)
+ struct buffer_head *bh)
{
- if (!ext4_has_metadata_csum(inode->i_sb))
- return;
-
- hdr->h_checksum = ext4_xattr_block_csum(inode, block_nr, hdr);
-}
-
-static inline int ext4_handle_dirty_xattr_block(handle_t *handle,
- struct inode *inode,
- struct buffer_head *bh)
-{
- ext4_xattr_block_csum_set(inode, bh->b_blocknr, BHDR(bh));
- return ext4_handle_dirty_metadata(handle, inode, bh);
+ if (ext4_has_metadata_csum(inode->i_sb))
+ BHDR(bh)->h_checksum = ext4_xattr_block_csum(inode,
+ bh->b_blocknr, BHDR(bh));
}
static inline const struct xattr_handler *
@@ -233,7 +228,7 @@ ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh)
if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
BHDR(bh)->h_blocks != cpu_to_le32(1))
return -EFSCORRUPTED;
- if (!ext4_xattr_block_csum_verify(inode, bh->b_blocknr, BHDR(bh)))
+ if (!ext4_xattr_block_csum_verify(inode, bh))
return -EFSBADCRC;
error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size,
bh->b_data);
@@ -618,23 +613,22 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
}
}
+ ext4_xattr_block_csum_set(inode, bh);
/*
* Beware of this ugliness: Releasing of xattr block references
* from different inodes can race and so we have to protect
* from a race where someone else frees the block (and releases
* its journal_head) before we are done dirtying the buffer. In
* nojournal mode this race is harmless and we actually cannot
- * call ext4_handle_dirty_xattr_block() with locked buffer as
+ * call ext4_handle_dirty_metadata() with locked buffer as
* that function can call sync_dirty_buffer() so for that case
* we handle the dirtying after unlocking the buffer.
*/
if (ext4_handle_valid(handle))
- error = ext4_handle_dirty_xattr_block(handle, inode,
- bh);
+ error = ext4_handle_dirty_metadata(handle, inode, bh);
unlock_buffer(bh);
if (!ext4_handle_valid(handle))
- error = ext4_handle_dirty_xattr_block(handle, inode,
- bh);
+ error = ext4_handle_dirty_metadata(handle, inode, bh);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
dquot_free_block(inode, EXT4_C2B(EXT4_SB(inode->i_sb), 1));
@@ -863,13 +857,14 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
ext4_xattr_cache_insert(ext4_mb_cache,
bs->bh);
}
+ ext4_xattr_block_csum_set(inode, bs->bh);
unlock_buffer(bs->bh);
if (error == -EFSCORRUPTED)
goto bad_block;
if (!error)
- error = ext4_handle_dirty_xattr_block(handle,
- inode,
- bs->bh);
+ error = ext4_handle_dirty_metadata(handle,
+ inode,
+ bs->bh);
if (error)
goto cleanup;
goto inserted;
@@ -967,10 +962,11 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
ce->e_reusable = 0;
ea_bdebug(new_bh, "reusing; refcount now=%d",
ref);
+ ext4_xattr_block_csum_set(inode, new_bh);
unlock_buffer(new_bh);
- error = ext4_handle_dirty_xattr_block(handle,
- inode,
- new_bh);
+ error = ext4_handle_dirty_metadata(handle,
+ inode,
+ new_bh);
if (error)
goto cleanup_dquot;
}
@@ -1020,11 +1016,12 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
goto getblk_failed;
}
memcpy(new_bh->b_data, s->base, new_bh->b_size);
+ ext4_xattr_block_csum_set(inode, new_bh);
set_buffer_uptodate(new_bh);
unlock_buffer(new_bh);
ext4_xattr_cache_insert(ext4_mb_cache, new_bh);
- error = ext4_handle_dirty_xattr_block(handle,
- inode, new_bh);
+ error = ext4_handle_dirty_metadata(handle, inode,
+ new_bh);
if (error)
goto cleanup;
}
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index a77df37..ee2d0a48 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -196,6 +196,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
si->base_mem += (NM_I(sbi)->nat_bits_blocks << F2FS_BLKSIZE_BITS);
si->base_mem += NM_I(sbi)->nat_blocks * NAT_ENTRY_BITMAP_SIZE;
si->base_mem += NM_I(sbi)->nat_blocks / 8;
+ si->base_mem += NM_I(sbi)->nat_blocks * sizeof(unsigned short);
get_cache:
si->cache_mem = 0;
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 4650c9b..8d5c62b 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -750,7 +750,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
dentry_blk = page_address(page);
bit_pos = dentry - dentry_blk->dentry;
for (i = 0; i < slots; i++)
- clear_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap);
+ __clear_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap);
/* Let's check and deallocate this dentry page */
bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index e849f83..0a6e115 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -561,6 +561,8 @@ struct f2fs_nm_info {
struct mutex build_lock; /* lock for build free nids */
unsigned char (*free_nid_bitmap)[NAT_ENTRY_BITMAP_SIZE];
unsigned char *nat_block_bitmap;
+ unsigned short *free_nid_count; /* free nid count of NAT block */
+ spinlock_t free_nid_lock; /* protect updating of nid count */
/* for checkpoint */
char *nat_bitmap; /* NAT bitmap pointer */
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 9496717..481aa8d 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -338,9 +338,6 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
set_nat_flag(e, IS_CHECKPOINTED, false);
__set_nat_cache_dirty(nm_i, e);
- if (enabled_nat_bits(sbi, NULL) && new_blkaddr == NEW_ADDR)
- clear_bit_le(NAT_BLOCK_OFFSET(ni->nid), nm_i->empty_nat_bits);
-
/* update fsync_mark if its inode nat entry is still alive */
if (ni->nid != ni->ino)
e = __lookup_nat_cache(nm_i, ni->ino);
@@ -1823,7 +1820,8 @@ static void remove_free_nid(struct f2fs_sb_info *sbi, nid_t nid)
kmem_cache_free(free_nid_slab, i);
}
-void update_free_nid_bitmap(struct f2fs_sb_info *sbi, nid_t nid, bool set)
+static void update_free_nid_bitmap(struct f2fs_sb_info *sbi, nid_t nid,
+ bool set, bool build, bool locked)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
unsigned int nat_ofs = NAT_BLOCK_OFFSET(nid);
@@ -1833,9 +1831,18 @@ void update_free_nid_bitmap(struct f2fs_sb_info *sbi, nid_t nid, bool set)
return;
if (set)
- set_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]);
+ __set_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]);
else
- clear_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]);
+ __clear_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]);
+
+ if (!locked)
+ spin_lock(&nm_i->free_nid_lock);
+ if (set)
+ nm_i->free_nid_count[nat_ofs]++;
+ else if (!build)
+ nm_i->free_nid_count[nat_ofs]--;
+ if (!locked)
+ spin_unlock(&nm_i->free_nid_lock);
}
static void scan_nat_page(struct f2fs_sb_info *sbi,
@@ -1847,7 +1854,10 @@ static void scan_nat_page(struct f2fs_sb_info *sbi,
unsigned int nat_ofs = NAT_BLOCK_OFFSET(start_nid);
int i;
- set_bit_le(nat_ofs, nm_i->nat_block_bitmap);
+ if (test_bit_le(nat_ofs, nm_i->nat_block_bitmap))
+ return;
+
+ __set_bit_le(nat_ofs, nm_i->nat_block_bitmap);
i = start_nid % NAT_ENTRY_PER_BLOCK;
@@ -1861,7 +1871,7 @@ static void scan_nat_page(struct f2fs_sb_info *sbi,
f2fs_bug_on(sbi, blk_addr == NEW_ADDR);
if (blk_addr == NULL_ADDR)
freed = add_free_nid(sbi, start_nid, true);
- update_free_nid_bitmap(sbi, start_nid, freed);
+ update_free_nid_bitmap(sbi, start_nid, freed, true, false);
}
}
@@ -1877,6 +1887,8 @@ static void scan_free_nid_bits(struct f2fs_sb_info *sbi)
for (i = 0; i < nm_i->nat_blocks; i++) {
if (!test_bit_le(i, nm_i->nat_block_bitmap))
continue;
+ if (!nm_i->free_nid_count[i])
+ continue;
for (idx = 0; idx < NAT_ENTRY_PER_BLOCK; idx++) {
nid_t nid;
@@ -1907,58 +1919,6 @@ static void scan_free_nid_bits(struct f2fs_sb_info *sbi)
up_read(&nm_i->nat_tree_lock);
}
-static int scan_nat_bits(struct f2fs_sb_info *sbi)
-{
- struct f2fs_nm_info *nm_i = NM_I(sbi);
- struct page *page;
- unsigned int i = 0;
- nid_t nid;
-
- if (!enabled_nat_bits(sbi, NULL))
- return -EAGAIN;
-
- down_read(&nm_i->nat_tree_lock);
-check_empty:
- i = find_next_bit_le(nm_i->empty_nat_bits, nm_i->nat_blocks, i);
- if (i >= nm_i->nat_blocks) {
- i = 0;
- goto check_partial;
- }
-
- for (nid = i * NAT_ENTRY_PER_BLOCK; nid < (i + 1) * NAT_ENTRY_PER_BLOCK;
- nid++) {
- if (unlikely(nid >= nm_i->max_nid))
- break;
- add_free_nid(sbi, nid, true);
- }
-
- if (nm_i->nid_cnt[FREE_NID_LIST] >= MAX_FREE_NIDS)
- goto out;
- i++;
- goto check_empty;
-
-check_partial:
- i = find_next_zero_bit_le(nm_i->full_nat_bits, nm_i->nat_blocks, i);
- if (i >= nm_i->nat_blocks) {
- disable_nat_bits(sbi, true);
- up_read(&nm_i->nat_tree_lock);
- return -EINVAL;
- }
-
- nid = i * NAT_ENTRY_PER_BLOCK;
- page = get_current_nat_page(sbi, nid);
- scan_nat_page(sbi, page, nid);
- f2fs_put_page(page, 1);
-
- if (nm_i->nid_cnt[FREE_NID_LIST] < MAX_FREE_NIDS) {
- i++;
- goto check_partial;
- }
-out:
- up_read(&nm_i->nat_tree_lock);
- return 0;
-}
-
static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
@@ -1980,21 +1940,6 @@ static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
if (nm_i->nid_cnt[FREE_NID_LIST])
return;
-
- /* try to find free nids with nat_bits */
- if (!scan_nat_bits(sbi) && nm_i->nid_cnt[FREE_NID_LIST])
- return;
- }
-
- /* find next valid candidate */
- if (enabled_nat_bits(sbi, NULL)) {
- int idx = find_next_zero_bit_le(nm_i->full_nat_bits,
- nm_i->nat_blocks, 0);
-
- if (idx >= nm_i->nat_blocks)
- set_sbi_flag(sbi, SBI_NEED_FSCK);
- else
- nid = idx * NAT_ENTRY_PER_BLOCK;
}
/* readahead nat pages to be scanned */
@@ -2081,7 +2026,7 @@ bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid)
__insert_nid_to_list(sbi, i, ALLOC_NID_LIST, false);
nm_i->available_nids--;
- update_free_nid_bitmap(sbi, *nid, false);
+ update_free_nid_bitmap(sbi, *nid, false, false, false);
spin_unlock(&nm_i->nid_list_lock);
return true;
@@ -2137,7 +2082,7 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid)
nm_i->available_nids++;
- update_free_nid_bitmap(sbi, nid, true);
+ update_free_nid_bitmap(sbi, nid, true, false, false);
spin_unlock(&nm_i->nid_list_lock);
@@ -2383,7 +2328,7 @@ static void __adjust_nat_entry_set(struct nat_entry_set *nes,
list_add_tail(&nes->set_list, head);
}
-void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid,
+static void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid,
struct page *page)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
@@ -2402,16 +2347,16 @@ void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid,
valid++;
}
if (valid == 0) {
- set_bit_le(nat_index, nm_i->empty_nat_bits);
- clear_bit_le(nat_index, nm_i->full_nat_bits);
+ __set_bit_le(nat_index, nm_i->empty_nat_bits);
+ __clear_bit_le(nat_index, nm_i->full_nat_bits);
return;
}
- clear_bit_le(nat_index, nm_i->empty_nat_bits);
+ __clear_bit_le(nat_index, nm_i->empty_nat_bits);
if (valid == NAT_ENTRY_PER_BLOCK)
- set_bit_le(nat_index, nm_i->full_nat_bits);
+ __set_bit_le(nat_index, nm_i->full_nat_bits);
else
- clear_bit_le(nat_index, nm_i->full_nat_bits);
+ __clear_bit_le(nat_index, nm_i->full_nat_bits);
}
static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
@@ -2467,11 +2412,11 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
add_free_nid(sbi, nid, false);
spin_lock(&NM_I(sbi)->nid_list_lock);
NM_I(sbi)->available_nids++;
- update_free_nid_bitmap(sbi, nid, true);
+ update_free_nid_bitmap(sbi, nid, true, false, false);
spin_unlock(&NM_I(sbi)->nid_list_lock);
} else {
spin_lock(&NM_I(sbi)->nid_list_lock);
- update_free_nid_bitmap(sbi, nid, false);
+ update_free_nid_bitmap(sbi, nid, false, false, false);
spin_unlock(&NM_I(sbi)->nid_list_lock);
}
}
@@ -2577,6 +2522,40 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi)
return 0;
}
+inline void load_free_nid_bitmap(struct f2fs_sb_info *sbi)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ unsigned int i = 0;
+ nid_t nid, last_nid;
+
+ if (!enabled_nat_bits(sbi, NULL))
+ return;
+
+ for (i = 0; i < nm_i->nat_blocks; i++) {
+ i = find_next_bit_le(nm_i->empty_nat_bits, nm_i->nat_blocks, i);
+ if (i >= nm_i->nat_blocks)
+ break;
+
+ __set_bit_le(i, nm_i->nat_block_bitmap);
+
+ nid = i * NAT_ENTRY_PER_BLOCK;
+ last_nid = (i + 1) * NAT_ENTRY_PER_BLOCK;
+
+ spin_lock(&nm_i->free_nid_lock);
+ for (; nid < last_nid; nid++)
+ update_free_nid_bitmap(sbi, nid, true, true, true);
+ spin_unlock(&nm_i->free_nid_lock);
+ }
+
+ for (i = 0; i < nm_i->nat_blocks; i++) {
+ i = find_next_bit_le(nm_i->full_nat_bits, nm_i->nat_blocks, i);
+ if (i >= nm_i->nat_blocks)
+ break;
+
+ __set_bit_le(i, nm_i->nat_block_bitmap);
+ }
+}
+
static int init_node_manager(struct f2fs_sb_info *sbi)
{
struct f2fs_super_block *sb_raw = F2FS_RAW_SUPER(sbi);
@@ -2638,7 +2617,7 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
return 0;
}
-int init_free_nid_cache(struct f2fs_sb_info *sbi)
+static int init_free_nid_cache(struct f2fs_sb_info *sbi)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
@@ -2651,6 +2630,14 @@ int init_free_nid_cache(struct f2fs_sb_info *sbi)
GFP_KERNEL);
if (!nm_i->nat_block_bitmap)
return -ENOMEM;
+
+ nm_i->free_nid_count = f2fs_kvzalloc(nm_i->nat_blocks *
+ sizeof(unsigned short), GFP_KERNEL);
+ if (!nm_i->free_nid_count)
+ return -ENOMEM;
+
+ spin_lock_init(&nm_i->free_nid_lock);
+
return 0;
}
@@ -2670,6 +2657,9 @@ int build_node_manager(struct f2fs_sb_info *sbi)
if (err)
return err;
+ /* load free nid status from nat_bits table */
+ load_free_nid_bitmap(sbi);
+
build_free_nids(sbi, true, true);
return 0;
}
@@ -2730,6 +2720,7 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
kvfree(nm_i->nat_block_bitmap);
kvfree(nm_i->free_nid_bitmap);
+ kvfree(nm_i->free_nid_count);
kfree(nm_i->nat_bitmap);
kfree(nm_i->nat_bits);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 4bd7a8b..29ef708 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -1163,6 +1163,12 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
if (f2fs_discard_en(sbi) &&
!f2fs_test_and_set_bit(offset, se->discard_map))
sbi->discard_blks--;
+
+ /* don't overwrite by SSR to keep node chain */
+ if (se->type == CURSEG_WARM_NODE) {
+ if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map))
+ se->ckpt_valid_blocks++;
+ }
} else {
if (!f2fs_test_and_clear_bit(offset, se->cur_valid_map)) {
#ifdef CONFIG_F2FS_CHECK_FS
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 338d2f7..a2c05f2 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -1359,6 +1359,16 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
return 0;
}
+static void fat_dummy_inode_init(struct inode *inode)
+{
+ /* Initialize this dummy inode to work as no-op. */
+ MSDOS_I(inode)->mmu_private = 0;
+ MSDOS_I(inode)->i_start = 0;
+ MSDOS_I(inode)->i_logstart = 0;
+ MSDOS_I(inode)->i_attrs = 0;
+ MSDOS_I(inode)->i_pos = 0;
+}
+
static int fat_read_root(struct inode *inode)
{
struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
@@ -1803,12 +1813,13 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
fat_inode = new_inode(sb);
if (!fat_inode)
goto out_fail;
- MSDOS_I(fat_inode)->i_pos = 0;
+ fat_dummy_inode_init(fat_inode);
sbi->fat_inode = fat_inode;
fsinfo_inode = new_inode(sb);
if (!fsinfo_inode)
goto out_fail;
+ fat_dummy_inode_init(fsinfo_inode);
fsinfo_inode->i_ino = MSDOS_FSINFO_INO;
sbi->fsinfo_inode = fsinfo_inode;
insert_inode_hash(fsinfo_inode);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index ef60059..63ee294 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -173,19 +173,33 @@ static void wb_wakeup(struct bdi_writeback *wb)
spin_unlock_bh(&wb->work_lock);
}
+static void finish_writeback_work(struct bdi_writeback *wb,
+ struct wb_writeback_work *work)
+{
+ struct wb_completion *done = work->done;
+
+ if (work->auto_free)
+ kfree(work);
+ if (done && atomic_dec_and_test(&done->cnt))
+ wake_up_all(&wb->bdi->wb_waitq);
+}
+
static void wb_queue_work(struct bdi_writeback *wb,
struct wb_writeback_work *work)
{
trace_writeback_queue(wb, work);
- spin_lock_bh(&wb->work_lock);
- if (!test_bit(WB_registered, &wb->state))
- goto out_unlock;
if (work->done)
atomic_inc(&work->done->cnt);
- list_add_tail(&work->list, &wb->work_list);
- mod_delayed_work(bdi_wq, &wb->dwork, 0);
-out_unlock:
+
+ spin_lock_bh(&wb->work_lock);
+
+ if (test_bit(WB_registered, &wb->state)) {
+ list_add_tail(&work->list, &wb->work_list);
+ mod_delayed_work(bdi_wq, &wb->dwork, 0);
+ } else
+ finish_writeback_work(wb, work);
+
spin_unlock_bh(&wb->work_lock);
}
@@ -1873,16 +1887,9 @@ static long wb_do_writeback(struct bdi_writeback *wb)
set_bit(WB_writeback_running, &wb->state);
while ((work = get_next_work_item(wb)) != NULL) {
- struct wb_completion *done = work->done;
-
trace_writeback_exec(wb, work);
-
wrote += wb_writeback(wb, work);
-
- if (work->auto_free)
- kfree(work);
- if (done && atomic_dec_and_test(&done->cnt))
- wake_up_all(&wb->bdi->wb_waitq);
+ finish_writeback_work(wb, work);
}
/*
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index c45084a..511e1ed 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -207,7 +207,7 @@ struct lm_lockname {
struct gfs2_sbd *ln_sbd;
u64 ln_number;
unsigned int ln_type;
-};
+} __packed __aligned(sizeof(int));
#define lm_name_equal(name1, name2) \
(((name1)->ln_number == (name2)->ln_number) && \
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 8f96461..7163fe0 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -695,14 +695,11 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb,
inode = new_inode(sb);
if (inode) {
- struct hugetlbfs_inode_info *info;
inode->i_ino = get_next_ino();
inode->i_mode = S_IFDIR | config->mode;
inode->i_uid = config->uid;
inode->i_gid = config->gid;
inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
- info = HUGETLBFS_I(inode);
- mpol_shared_policy_init(&info->policy, NULL);
inode->i_op = &hugetlbfs_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
/* directory inodes start off with i_nlink == 2 (for "." entry) */
@@ -733,7 +730,6 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
inode = new_inode(sb);
if (inode) {
- struct hugetlbfs_inode_info *info;
inode->i_ino = get_next_ino();
inode_init_owner(inode, dir, mode);
lockdep_set_class(&inode->i_mapping->i_mmap_rwsem,
@@ -741,15 +737,6 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
inode->i_mapping->a_ops = &hugetlbfs_aops;
inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
inode->i_mapping->private_data = resv_map;
- info = HUGETLBFS_I(inode);
- /*
- * The policy is initialized here even if we are creating a
- * private inode because initialization simply creates an
- * an empty rb tree and calls rwlock_init(), later when we
- * call mpol_free_shared_policy() it will just return because
- * the rb tree will still be empty.
- */
- mpol_shared_policy_init(&info->policy, NULL);
switch (mode & S_IFMT) {
default:
init_special_inode(inode, mode, dev);
@@ -937,6 +924,18 @@ static struct inode *hugetlbfs_alloc_inode(struct super_block *sb)
hugetlbfs_inc_free_inodes(sbinfo);
return NULL;
}
+
+ /*
+ * Any time after allocation, hugetlbfs_destroy_inode can be called
+ * for the inode. mpol_free_shared_policy is unconditionally called
+ * as part of hugetlbfs_destroy_inode. So, initialize policy here
+ * in case of a quick call to destroy.
+ *
+ * Note that the policy is initialized even if we are creating a
+ * private inode. This simplifies hugetlbfs_destroy_inode.
+ */
+ mpol_shared_policy_init(&p->policy, NULL);
+
return &p->vfs_inode;
}
diff --git a/fs/iomap.c b/fs/iomap.c
index 3ca1a8e..141c3cd 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -846,7 +846,8 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
struct address_space *mapping = iocb->ki_filp->f_mapping;
struct inode *inode = file_inode(iocb->ki_filp);
size_t count = iov_iter_count(iter);
- loff_t pos = iocb->ki_pos, end = iocb->ki_pos + count - 1, ret = 0;
+ loff_t pos = iocb->ki_pos, start = pos;
+ loff_t end = iocb->ki_pos + count - 1, ret = 0;
unsigned int flags = IOMAP_DIRECT;
struct blk_plug plug;
struct iomap_dio *dio;
@@ -887,12 +888,12 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
}
if (mapping->nrpages) {
- ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end);
+ ret = filemap_write_and_wait_range(mapping, start, end);
if (ret)
goto out_free_dio;
ret = invalidate_inode_pages2_range(mapping,
- iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
+ start >> PAGE_SHIFT, end >> PAGE_SHIFT);
WARN_ON_ONCE(ret);
ret = 0;
}
@@ -941,6 +942,8 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
__set_current_state(TASK_RUNNING);
}
+ ret = iomap_dio_complete(dio);
+
/*
* Try again to invalidate clean pages which might have been cached by
* non-direct readahead, or faulted in by get_user_pages() if the source
@@ -949,12 +952,12 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
* this invalidation fails, tough, the write still worked...
*/
if (iov_iter_rw(iter) == WRITE && mapping->nrpages) {
- ret = invalidate_inode_pages2_range(mapping,
- iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
- WARN_ON_ONCE(ret);
+ int err = invalidate_inode_pages2_range(mapping,
+ start >> PAGE_SHIFT, end >> PAGE_SHIFT);
+ WARN_ON_ONCE(err);
}
- return iomap_dio_complete(dio);
+ return ret;
out_free_dio:
kfree(dio);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index a1a359b..5adc2fb 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1125,10 +1125,8 @@ static journal_t *journal_init_common(struct block_device *bdev,
/* Set up a default-sized revoke table for the new mount. */
err = jbd2_journal_init_revoke(journal, JOURNAL_REVOKE_DEFAULT_HASH);
- if (err) {
- kfree(journal);
- return NULL;
- }
+ if (err)
+ goto err_cleanup;
spin_lock_init(&journal->j_history_lock);
@@ -1145,23 +1143,25 @@ static journal_t *journal_init_common(struct block_device *bdev,
journal->j_wbufsize = n;
journal->j_wbuf = kmalloc_array(n, sizeof(struct buffer_head *),
GFP_KERNEL);
- if (!journal->j_wbuf) {
- kfree(journal);
- return NULL;
- }
+ if (!journal->j_wbuf)
+ goto err_cleanup;
bh = getblk_unmovable(journal->j_dev, start, journal->j_blocksize);
if (!bh) {
pr_err("%s: Cannot get buffer for journal superblock\n",
__func__);
- kfree(journal->j_wbuf);
- kfree(journal);
- return NULL;
+ goto err_cleanup;
}
journal->j_sb_buffer = bh;
journal->j_superblock = (journal_superblock_t *)bh->b_data;
return journal;
+
+err_cleanup:
+ kfree(journal->j_wbuf);
+ jbd2_journal_destroy_revoke(journal);
+ kfree(journal);
+ return NULL;
}
/* jbd2_journal_init_dev and jbd2_journal_init_inode:
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index cfc38b5..f9aefcd 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -280,6 +280,7 @@ int jbd2_journal_init_revoke(journal_t *journal, int hash_size)
fail1:
jbd2_journal_destroy_revoke_table(journal->j_revoke_table[0]);
+ journal->j_revoke_table[0] = NULL;
fail0:
return -ENOMEM;
}
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 8e4dc7a..ac2dfe0 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -809,7 +809,8 @@ void kernfs_drain_open_files(struct kernfs_node *kn)
if (kn->flags & KERNFS_HAS_MMAP)
unmap_mapping_range(inode->i_mapping, 0, 0, 1);
- kernfs_release_file(kn, of);
+ if (kn->flags & KERNFS_HAS_RELEASE)
+ kernfs_release_file(kn, of);
}
mutex_unlock(&kernfs_open_file_mutex);
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index bb79972..7737745 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -232,12 +232,12 @@ static struct svc_serv_ops nfs41_cb_sv_ops = {
.svo_module = THIS_MODULE,
};
-struct svc_serv_ops *nfs4_cb_sv_ops[] = {
+static struct svc_serv_ops *nfs4_cb_sv_ops[] = {
[0] = &nfs40_cb_sv_ops,
[1] = &nfs41_cb_sv_ops,
};
#else
-struct svc_serv_ops *nfs4_cb_sv_ops[] = {
+static struct svc_serv_ops *nfs4_cb_sv_ops[] = {
[0] = &nfs40_cb_sv_ops,
[1] = NULL,
};
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 91a8d61..390ada8 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -325,10 +325,33 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
return NULL;
}
-static bool nfs_client_init_is_complete(const struct nfs_client *clp)
+/*
+ * Return true if @clp is done initializing, false if still working on it.
+ *
+ * Use nfs_client_init_status to check if it was successful.
+ */
+bool nfs_client_init_is_complete(const struct nfs_client *clp)
{
return clp->cl_cons_state <= NFS_CS_READY;
}
+EXPORT_SYMBOL_GPL(nfs_client_init_is_complete);
+
+/*
+ * Return 0 if @clp was successfully initialized, -errno otherwise.
+ *
+ * This must be called *after* nfs_client_init_is_complete() returns true,
+ * otherwise it will pop WARN_ON_ONCE and return -EINVAL
+ */
+int nfs_client_init_status(const struct nfs_client *clp)
+{
+ /* called without checking nfs_client_init_is_complete */
+ if (clp->cl_cons_state > NFS_CS_READY) {
+ WARN_ON_ONCE(1);
+ return -EINVAL;
+ }
+ return clp->cl_cons_state;
+}
+EXPORT_SYMBOL_GPL(nfs_client_init_status);
int nfs_wait_client_init_complete(const struct nfs_client *clp)
{
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index fb499a3..f92ba8d 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2055,7 +2055,7 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
{
struct inode *old_inode = d_inode(old_dentry);
struct inode *new_inode = d_inode(new_dentry);
- struct dentry *dentry = NULL, *rehash = NULL;
+ struct dentry *dentry = NULL;
struct rpc_task *task;
int error = -EBUSY;
@@ -2078,10 +2078,8 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
* To prevent any new references to the target during the
* rename, we unhash the dentry in advance.
*/
- if (!d_unhashed(new_dentry)) {
+ if (!d_unhashed(new_dentry))
d_drop(new_dentry);
- rehash = new_dentry;
- }
if (d_count(new_dentry) > 2) {
int err;
@@ -2098,7 +2096,6 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
goto out;
new_dentry = dentry;
- rehash = NULL;
new_inode = NULL;
}
}
@@ -2119,8 +2116,6 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
error = task->tk_status;
rpc_put_task(task);
out:
- if (rehash)
- d_rehash(rehash);
trace_nfs_rename_exit(old_dir, old_dentry,
new_dir, new_dentry, error);
/* new dentry created? */
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 44347f4..acd30ba 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -202,10 +202,10 @@ static int filelayout_async_handle_error(struct rpc_task *task,
task->tk_status);
nfs4_mark_deviceid_unavailable(devid);
pnfs_error_mark_layout_for_return(inode, lseg);
- pnfs_set_lo_fail(lseg);
rpc_wake_up(&tbl->slot_tbl_waitq);
/* fall through */
default:
+ pnfs_set_lo_fail(lseg);
reset:
dprintk("%s Retry through MDS. Error %d\n", __func__,
task->tk_status);
@@ -560,49 +560,17 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
return PNFS_ATTEMPTED;
}
-/*
- * filelayout_check_layout()
- *
- * Make sure layout segment parameters are sane WRT the device.
- * At this point no generic layer initialization of the lseg has occurred,
- * and nothing has been added to the layout_hdr cache.
- *
- */
static int
-filelayout_check_layout(struct pnfs_layout_hdr *lo,
- struct nfs4_filelayout_segment *fl,
- struct nfs4_layoutget_res *lgr,
- struct nfs4_deviceid *id,
- gfp_t gfp_flags)
+filelayout_check_deviceid(struct pnfs_layout_hdr *lo,
+ struct nfs4_filelayout_segment *fl,
+ gfp_t gfp_flags)
{
struct nfs4_deviceid_node *d;
struct nfs4_file_layout_dsaddr *dsaddr;
int status = -EINVAL;
- dprintk("--> %s\n", __func__);
-
- /* FIXME: remove this check when layout segment support is added */
- if (lgr->range.offset != 0 ||
- lgr->range.length != NFS4_MAX_UINT64) {
- dprintk("%s Only whole file layouts supported. Use MDS i/o\n",
- __func__);
- goto out;
- }
-
- if (fl->pattern_offset > lgr->range.offset) {
- dprintk("%s pattern_offset %lld too large\n",
- __func__, fl->pattern_offset);
- goto out;
- }
-
- if (!fl->stripe_unit) {
- dprintk("%s Invalid stripe unit (%u)\n",
- __func__, fl->stripe_unit);
- goto out;
- }
-
/* find and reference the deviceid */
- d = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode), id,
+ d = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode), &fl->deviceid,
lo->plh_lc_cred, gfp_flags);
if (d == NULL)
goto out;
@@ -628,14 +596,56 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
__func__, fl->num_fh);
goto out_put;
}
+ status = 0;
+out:
+ return status;
+out_put:
+ nfs4_fl_put_deviceid(dsaddr);
+ goto out;
+}
+
+/*
+ * filelayout_check_layout()
+ *
+ * Make sure layout segment parameters are sane WRT the device.
+ * At this point no generic layer initialization of the lseg has occurred,
+ * and nothing has been added to the layout_hdr cache.
+ *
+ */
+static int
+filelayout_check_layout(struct pnfs_layout_hdr *lo,
+ struct nfs4_filelayout_segment *fl,
+ struct nfs4_layoutget_res *lgr,
+ gfp_t gfp_flags)
+{
+ int status = -EINVAL;
+
+ dprintk("--> %s\n", __func__);
+
+ /* FIXME: remove this check when layout segment support is added */
+ if (lgr->range.offset != 0 ||
+ lgr->range.length != NFS4_MAX_UINT64) {
+ dprintk("%s Only whole file layouts supported. Use MDS i/o\n",
+ __func__);
+ goto out;
+ }
+
+ if (fl->pattern_offset > lgr->range.offset) {
+ dprintk("%s pattern_offset %lld too large\n",
+ __func__, fl->pattern_offset);
+ goto out;
+ }
+
+ if (!fl->stripe_unit) {
+ dprintk("%s Invalid stripe unit (%u)\n",
+ __func__, fl->stripe_unit);
+ goto out;
+ }
status = 0;
out:
dprintk("--> %s returns %d\n", __func__, status);
return status;
-out_put:
- nfs4_fl_put_deviceid(dsaddr);
- goto out;
}
static void _filelayout_free_lseg(struct nfs4_filelayout_segment *fl)
@@ -657,7 +667,6 @@ static int
filelayout_decode_layout(struct pnfs_layout_hdr *flo,
struct nfs4_filelayout_segment *fl,
struct nfs4_layoutget_res *lgr,
- struct nfs4_deviceid *id,
gfp_t gfp_flags)
{
struct xdr_stream stream;
@@ -682,9 +691,9 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
if (unlikely(!p))
goto out_err;
- memcpy(id, p, sizeof(*id));
+ memcpy(&fl->deviceid, p, sizeof(fl->deviceid));
p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);
- nfs4_print_deviceid(id);
+ nfs4_print_deviceid(&fl->deviceid);
nfl_util = be32_to_cpup(p++);
if (nfl_util & NFL4_UFLG_COMMIT_THRU_MDS)
@@ -831,15 +840,14 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
{
struct nfs4_filelayout_segment *fl;
int rc;
- struct nfs4_deviceid id;
dprintk("--> %s\n", __func__);
fl = kzalloc(sizeof(*fl), gfp_flags);
if (!fl)
return NULL;
- rc = filelayout_decode_layout(layoutid, fl, lgr, &id, gfp_flags);
- if (rc != 0 || filelayout_check_layout(layoutid, fl, lgr, &id, gfp_flags)) {
+ rc = filelayout_decode_layout(layoutid, fl, lgr, gfp_flags);
+ if (rc != 0 || filelayout_check_layout(layoutid, fl, lgr, gfp_flags)) {
_filelayout_free_lseg(fl);
return NULL;
}
@@ -888,18 +896,51 @@ filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
return min(stripe_unit - (unsigned int)stripe_offset, size);
}
+static struct pnfs_layout_segment *
+fl_pnfs_update_layout(struct inode *ino,
+ struct nfs_open_context *ctx,
+ loff_t pos,
+ u64 count,
+ enum pnfs_iomode iomode,
+ bool strict_iomode,
+ gfp_t gfp_flags)
+{
+ struct pnfs_layout_segment *lseg = NULL;
+ struct pnfs_layout_hdr *lo;
+ struct nfs4_filelayout_segment *fl;
+ int status;
+
+ lseg = pnfs_update_layout(ino, ctx, pos, count, iomode, strict_iomode,
+ gfp_flags);
+ if (!lseg)
+ lseg = ERR_PTR(-ENOMEM);
+ if (IS_ERR(lseg))
+ goto out;
+
+ lo = NFS_I(ino)->layout;
+ fl = FILELAYOUT_LSEG(lseg);
+
+ status = filelayout_check_deviceid(lo, fl, gfp_flags);
+ if (status)
+ lseg = ERR_PTR(status);
+out:
+ if (IS_ERR(lseg))
+ pnfs_put_lseg(lseg);
+ return lseg;
+}
+
static void
filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
struct nfs_page *req)
{
if (!pgio->pg_lseg) {
- pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
- req->wb_context,
- 0,
- NFS4_MAX_UINT64,
- IOMODE_READ,
- false,
- GFP_KERNEL);
+ pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode,
+ req->wb_context,
+ 0,
+ NFS4_MAX_UINT64,
+ IOMODE_READ,
+ false,
+ GFP_KERNEL);
if (IS_ERR(pgio->pg_lseg)) {
pgio->pg_error = PTR_ERR(pgio->pg_lseg);
pgio->pg_lseg = NULL;
@@ -919,13 +960,13 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
int status;
if (!pgio->pg_lseg) {
- pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
- req->wb_context,
- 0,
- NFS4_MAX_UINT64,
- IOMODE_RW,
- false,
- GFP_NOFS);
+ pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode,
+ req->wb_context,
+ 0,
+ NFS4_MAX_UINT64,
+ IOMODE_RW,
+ false,
+ GFP_NOFS);
if (IS_ERR(pgio->pg_lseg)) {
pgio->pg_error = PTR_ERR(pgio->pg_lseg);
pgio->pg_lseg = NULL;
diff --git a/fs/nfs/filelayout/filelayout.h b/fs/nfs/filelayout/filelayout.h
index 2896cb8..79323b5 100644
--- a/fs/nfs/filelayout/filelayout.h
+++ b/fs/nfs/filelayout/filelayout.h
@@ -55,15 +55,16 @@ struct nfs4_file_layout_dsaddr {
};
struct nfs4_filelayout_segment {
- struct pnfs_layout_segment generic_hdr;
- u32 stripe_type;
- u32 commit_through_mds;
- u32 stripe_unit;
- u32 first_stripe_index;
- u64 pattern_offset;
- struct nfs4_file_layout_dsaddr *dsaddr; /* Point to GETDEVINFO data */
- unsigned int num_fh;
- struct nfs_fh **fh_array;
+ struct pnfs_layout_segment generic_hdr;
+ u32 stripe_type;
+ u32 commit_through_mds;
+ u32 stripe_unit;
+ u32 first_stripe_index;
+ u64 pattern_offset;
+ struct nfs4_deviceid deviceid;
+ struct nfs4_file_layout_dsaddr *dsaddr; /* Point to GETDEVINFO data */
+ unsigned int num_fh;
+ struct nfs_fh **fh_array;
};
struct nfs4_filelayout {
diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c
index f956ca2..d913e81 100644
--- a/fs/nfs/filelayout/filelayoutdev.c
+++ b/fs/nfs/filelayout/filelayoutdev.c
@@ -266,6 +266,7 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
struct nfs4_pnfs_ds *ret = ds;
struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode);
+ int status;
if (ds == NULL) {
printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
@@ -277,9 +278,14 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
if (ds->ds_clp)
goto out_test_devid;
- nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
+ status = nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
dataserver_retrans, 4,
s->nfs_client->cl_minorversion);
+ if (status) {
+ nfs4_mark_deviceid_unavailable(devid);
+ ret = NULL;
+ goto out;
+ }
out_test_devid:
if (ret->ds_clp == NULL ||
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h
index f4f39b0..98b34c9 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.h
+++ b/fs/nfs/flexfilelayout/flexfilelayout.h
@@ -175,7 +175,19 @@ ff_layout_no_read_on_rw(struct pnfs_layout_segment *lseg)
static inline bool
ff_layout_test_devid_unavailable(struct nfs4_deviceid_node *node)
{
- return nfs4_test_deviceid_unavailable(node);
+ /*
+ * Flexfiles should never mark a DS unavailable, but if it does
+ * print a (ratelimited) warning as this can affect performance.
+ */
+ if (nfs4_test_deviceid_unavailable(node)) {
+ u32 *p = (u32 *)node->deviceid.data;
+
+ pr_warn_ratelimited("NFS: flexfiles layout referencing an "
+ "unavailable device [%x%x%x%x]\n",
+ p[0], p[1], p[2], p[3]);
+ return true;
+ }
+ return false;
}
static inline int
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index e5a6f24..457cfeb 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -208,6 +208,10 @@ static bool ff_layout_mirror_valid(struct pnfs_layout_segment *lseg,
} else
goto outerr;
}
+
+ if (IS_ERR(mirror->mirror_ds))
+ goto outerr;
+
if (mirror->mirror_ds->ds == NULL) {
struct nfs4_deviceid_node *devid;
devid = &mirror->mirror_ds->id_node;
@@ -384,6 +388,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
struct inode *ino = lseg->pls_layout->plh_inode;
struct nfs_server *s = NFS_SERVER(ino);
unsigned int max_payload;
+ int status;
if (!ff_layout_mirror_valid(lseg, mirror, true)) {
pr_err_ratelimited("NFS: %s: No data server for offset index %d\n",
@@ -404,7 +409,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
/* FIXME: For now we assume the server sent only one version of NFS
* to use for the DS.
*/
- nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
+ status = nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
dataserver_retrans,
mirror->mirror_ds->ds_versions[0].version,
mirror->mirror_ds->ds_versions[0].minor_version);
@@ -420,11 +425,11 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
mirror->mirror_ds->ds_versions[0].wsize = max_payload;
goto out;
}
+out_fail:
ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout),
mirror, lseg->pls_range.offset,
lseg->pls_range.length, NFS4ERR_NXIO,
OP_ILLEGAL, GFP_NOIO);
-out_fail:
if (fail_return || !ff_layout_has_available_ds(lseg))
pnfs_error_mark_layout_for_return(ino, lseg);
ds = NULL;
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 09ca5095..7b38fed 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -186,6 +186,8 @@ extern struct nfs_server *nfs_clone_server(struct nfs_server *,
struct nfs_fh *,
struct nfs_fattr *,
rpc_authflavor_t);
+extern bool nfs_client_init_is_complete(const struct nfs_client *clp);
+extern int nfs_client_init_status(const struct nfs_client *clp);
extern int nfs_wait_client_init_complete(const struct nfs_client *clp);
extern void nfs_mark_client_ready(struct nfs_client *clp, int state);
extern struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 5ae9d64..8346ccb 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -1023,9 +1023,9 @@ static void nfs4_session_set_rwsize(struct nfs_server *server)
server_resp_sz = sess->fc_attrs.max_resp_sz - nfs41_maxread_overhead;
server_rqst_sz = sess->fc_attrs.max_rqst_sz - nfs41_maxwrite_overhead;
- if (server->rsize > server_resp_sz)
+ if (!server->rsize || server->rsize > server_resp_sz)
server->rsize = server_resp_sz;
- if (server->wsize > server_rqst_sz)
+ if (!server->wsize || server->wsize > server_rqst_sz)
server->wsize = server_rqst_sz;
#endif /* CONFIG_NFS_V4_1 */
}
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 1b18368..201ca3f 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2258,8 +2258,6 @@ static int nfs4_opendata_access(struct rpc_cred *cred,
if ((mask & ~cache.mask & (MAY_READ | MAY_EXEC)) == 0)
return 0;
- /* even though OPEN succeeded, access is denied. Close the file */
- nfs4_close_state(state, fmode);
return -EACCES;
}
@@ -2444,17 +2442,14 @@ static void nfs41_check_delegation_stateid(struct nfs4_state *state)
}
nfs4_stateid_copy(&stateid, &delegation->stateid);
- if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) {
+ if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags) ||
+ !test_and_clear_bit(NFS_DELEGATION_TEST_EXPIRED,
+ &delegation->flags)) {
rcu_read_unlock();
nfs_finish_clear_delegation_stateid(state, &stateid);
return;
}
- if (!test_and_clear_bit(NFS_DELEGATION_TEST_EXPIRED, &delegation->flags)) {
- rcu_read_unlock();
- return;
- }
-
cred = get_rpccred(delegation->cred);
rcu_read_unlock();
status = nfs41_test_and_free_expired_stateid(server, &stateid, cred);
@@ -7427,11 +7422,11 @@ static void nfs4_exchange_id_release(void *data)
struct nfs41_exchange_id_data *cdata =
(struct nfs41_exchange_id_data *)data;
- nfs_put_client(cdata->args.client);
if (cdata->xprt) {
xprt_put(cdata->xprt);
rpc_clnt_xprt_switch_put(cdata->args.client->cl_rpcclient);
}
+ nfs_put_client(cdata->args.client);
kfree(cdata->res.impl_id);
kfree(cdata->res.server_scope);
kfree(cdata->res.server_owner);
@@ -7538,10 +7533,8 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred,
task_setup_data.callback_data = calldata;
task = rpc_run_task(&task_setup_data);
- if (IS_ERR(task)) {
- status = PTR_ERR(task);
- goto out_impl_id;
- }
+ if (IS_ERR(task))
+ return PTR_ERR(task);
if (!xprt) {
status = rpc_wait_for_completion_task(task);
@@ -7569,6 +7562,7 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred,
kfree(calldata->res.server_owner);
out_calldata:
kfree(calldata);
+ nfs_put_client(clp);
goto out;
}
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index f0369e3..80ce289 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -3942,7 +3942,7 @@ static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap,
if (len <= 0)
goto out;
dprintk("%s: name=%s\n", __func__, group_name->data);
- return NFS_ATTR_FATTR_OWNER_NAME;
+ return NFS_ATTR_FATTR_GROUP_NAME;
} else {
len = xdr_stream_decode_opaque_inline(xdr, (void **)&p,
XDR_MAX_NETOBJ);
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 63f77b4..590e1e3 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -367,7 +367,7 @@ void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds);
struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs,
gfp_t gfp_flags);
void nfs4_pnfs_v3_ds_connect_unload(void);
-void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
+int nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
struct nfs4_deviceid_node *devid, unsigned int timeo,
unsigned int retrans, u32 version, u32 minor_version);
struct nfs4_pnfs_ds_addr *nfs4_decode_mp_ds_addr(struct net *net,
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 9414b49..7250b95 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -745,15 +745,17 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv,
/*
* Create an rpc connection to the nfs4_pnfs_ds data server.
* Currently only supports IPv4 and IPv6 addresses.
- * If connection fails, make devid unavailable.
+ * If connection fails, make devid unavailable and return a -errno.
*/
-void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
+int nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
struct nfs4_deviceid_node *devid, unsigned int timeo,
unsigned int retrans, u32 version, u32 minor_version)
{
- if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) {
- int err = 0;
+ int err;
+again:
+ err = 0;
+ if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) {
if (version == 3) {
err = _nfs4_pnfs_v3_ds_connect(mds_srv, ds, timeo,
retrans);
@@ -766,12 +768,29 @@ void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
err = -EPROTONOSUPPORT;
}
- if (err)
- nfs4_mark_deviceid_unavailable(devid);
nfs4_clear_ds_conn_bit(ds);
} else {
nfs4_wait_ds_connect(ds);
+
+ /* what was waited on didn't connect AND didn't mark unavail */
+ if (!ds->ds_clp && !nfs4_test_deviceid_unavailable(devid))
+ goto again;
}
+
+ /*
+ * At this point the ds->ds_clp should be ready, but it might have
+ * hit an error.
+ */
+ if (!err) {
+ if (!ds->ds_clp || !nfs_client_init_is_complete(ds->ds_clp)) {
+ WARN_ON_ONCE(ds->ds_clp ||
+ !nfs4_test_deviceid_unavailable(devid));
+ return -EINVAL;
+ }
+ err = nfs_client_init_status(ds->ds_clp);
+ }
+
+ return err;
}
EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_connect);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index e75b056..abb2c8a 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1784,7 +1784,8 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
(long long)req_offset(req));
if (status < 0) {
nfs_context_set_write_error(req->wb_context, status);
- nfs_inode_remove_request(req);
+ if (req->wb_page)
+ nfs_inode_remove_request(req);
dprintk_cont(", error = %d\n", status);
goto next;
}
@@ -1793,7 +1794,8 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
* returned by the server against all stored verfs. */
if (!nfs_write_verifier_cmp(&req->wb_verf, &data->verf.verifier)) {
/* We have a match */
- nfs_inode_remove_request(req);
+ if (req->wb_page)
+ nfs_inode_remove_request(req);
dprintk_cont(" OK\n");
goto next;
}
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 73e75ac..8bf8f66 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -538,13 +538,21 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size)
static ssize_t
nfsd_print_version_support(char *buf, int remaining, const char *sep,
- unsigned vers, unsigned minor)
+ unsigned vers, int minor)
{
- const char *format = (minor == 0) ? "%s%c%u" : "%s%c%u.%u";
+ const char *format = minor < 0 ? "%s%c%u" : "%s%c%u.%u";
bool supported = !!nfsd_vers(vers, NFSD_TEST);
- if (vers == 4 && !nfsd_minorversion(minor, NFSD_TEST))
+ if (vers == 4 && minor >= 0 &&
+ !nfsd_minorversion(minor, NFSD_TEST))
supported = false;
+ if (minor == 0 && supported)
+ /*
+ * special case for backward compatability.
+ * +4.0 is never reported, it is implied by
+ * +4, unless -4.0 is present.
+ */
+ return 0;
return snprintf(buf, remaining, format, sep,
supported ? '+' : '-', vers, minor);
}
@@ -554,7 +562,6 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
char *mesg = buf;
char *vers, *minorp, sign;
int len, num, remaining;
- unsigned minor;
ssize_t tlen = 0;
char *sep;
struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id);
@@ -575,6 +582,7 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
if (len <= 0) return -EINVAL;
do {
enum vers_op cmd;
+ unsigned minor;
sign = *vers;
if (sign == '+' || sign == '-')
num = simple_strtol((vers+1), &minorp, 0);
@@ -585,8 +593,8 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
return -EINVAL;
if (kstrtouint(minorp+1, 0, &minor) < 0)
return -EINVAL;
- } else
- minor = 0;
+ }
+
cmd = sign == '-' ? NFSD_CLEAR : NFSD_SET;
switch(num) {
case 2:
@@ -594,8 +602,20 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
nfsd_vers(num, cmd);
break;
case 4:
- if (nfsd_minorversion(minor, cmd) >= 0)
- break;
+ if (*minorp == '.') {
+ if (nfsd_minorversion(minor, cmd) < 0)
+ return -EINVAL;
+ } else if ((cmd == NFSD_SET) != nfsd_vers(num, NFSD_TEST)) {
+ /*
+ * Either we have +4 and no minors are enabled,
+ * or we have -4 and at least one minor is enabled.
+ * In either case, propagate 'cmd' to all minors.
+ */
+ minor = 0;
+ while (nfsd_minorversion(minor, cmd) >= 0)
+ minor++;
+ }
+ break;
default:
return -EINVAL;
}
@@ -612,9 +632,11 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
sep = "";
remaining = SIMPLE_TRANSACTION_LIMIT;
for (num=2 ; num <= 4 ; num++) {
+ int minor;
if (!nfsd_vers(num, NFSD_AVAIL))
continue;
- minor = 0;
+
+ minor = -1;
do {
len = nfsd_print_version_support(buf, remaining,
sep, num, minor);
@@ -624,7 +646,8 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
buf += len;
tlen += len;
minor++;
- sep = " ";
+ if (len)
+ sep = " ";
} while (num == 4 && minor <= NFSD_SUPPORTED_MINOR_VERSION);
}
out:
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index fa82b77..03a7e9d 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -786,6 +786,7 @@ nfserrno (int errno)
{ nfserr_serverfault, -ESERVERFAULT },
{ nfserr_serverfault, -ENFILE },
{ nfserr_io, -EUCLEAN },
+ { nfserr_perm, -ENOKEY },
};
int i;
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 786a4a2..31e1f95 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -167,7 +167,8 @@ nfsd_adjust_nfsd_versions4(void)
int nfsd_minorversion(u32 minorversion, enum vers_op change)
{
- if (minorversion > NFSD_SUPPORTED_MINOR_VERSION)
+ if (minorversion > NFSD_SUPPORTED_MINOR_VERSION &&
+ change != NFSD_AVAIL)
return -1;
switch(change) {
case NFSD_SET:
@@ -415,23 +416,20 @@ static void nfsd_last_thread(struct svc_serv *serv, struct net *net)
void nfsd_reset_versions(void)
{
- int found_one = 0;
int i;
- for (i = NFSD_MINVERS; i < NFSD_NRVERS; i++) {
- if (nfsd_program.pg_vers[i])
- found_one = 1;
- }
+ for (i = 0; i < NFSD_NRVERS; i++)
+ if (nfsd_vers(i, NFSD_TEST))
+ return;
- if (!found_one) {
- for (i = NFSD_MINVERS; i < NFSD_NRVERS; i++)
- nfsd_program.pg_vers[i] = nfsd_version[i];
-#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
- for (i = NFSD_ACL_MINVERS; i < NFSD_ACL_NRVERS; i++)
- nfsd_acl_program.pg_vers[i] =
- nfsd_acl_version[i];
-#endif
- }
+ for (i = 0; i < NFSD_NRVERS; i++)
+ if (i != 4)
+ nfsd_vers(i, NFSD_SET);
+ else {
+ int minor = 0;
+ while (nfsd_minorversion(minor, NFSD_SET) >= 0)
+ minor++;
+ }
}
/*
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 4348027..d0ab7e5 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -1863,7 +1863,7 @@ static int o2net_accept_one(struct socket *sock, int *more)
new_sock->type = sock->type;
new_sock->ops = sock->ops;
- ret = sock->ops->accept(sock, new_sock, O_NONBLOCK);
+ ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, false);
if (ret < 0)
goto out;
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 1953986..6e610a2 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -12,7 +12,6 @@
#include <linux/slab.h>
#include <linux/cred.h>
#include <linux/xattr.h>
-#include <linux/sched/signal.h>
#include "overlayfs.h"
#include "ovl_entry.h"
diff --git a/fs/select.c b/fs/select.c
index e211227..9287d3a 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -409,7 +409,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
int retval, i, timed_out = 0;
u64 slack = 0;
unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
- unsigned long busy_end = 0;
+ unsigned long busy_start = 0;
rcu_read_lock();
retval = max_select_fd(n, fds);
@@ -512,11 +512,11 @@ int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
/* only if found POLL_BUSY_LOOP sockets && not out of time */
if (can_busy_loop && !need_resched()) {
- if (!busy_end) {
- busy_end = busy_loop_end_time();
+ if (!busy_start) {
+ busy_start = busy_loop_current_time();
continue;
}
- if (!busy_loop_timeout(busy_end))
+ if (!busy_loop_timeout(busy_start))
continue;
}
busy_flag = 0;
@@ -800,7 +800,7 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
int timed_out = 0, count = 0;
u64 slack = 0;
unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
- unsigned long busy_end = 0;
+ unsigned long busy_start = 0;
/* Optimise the no-wait case */
if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
@@ -853,11 +853,11 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
/* only if found POLL_BUSY_LOOP sockets && not out of time */
if (can_busy_loop && !need_resched()) {
- if (!busy_end) {
- busy_end = busy_loop_end_time();
+ if (!busy_start) {
+ busy_start = busy_loop_current_time();
continue;
}
- if (!busy_loop_timeout(busy_end))
+ if (!busy_loop_timeout(busy_start))
continue;
}
busy_flag = 0;
diff --git a/fs/timerfd.c b/fs/timerfd.c
index 384fa75..c543cdb 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -400,9 +400,9 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags)
clockid != CLOCK_BOOTTIME_ALARM))
return -EINVAL;
- if (!capable(CAP_WAKE_ALARM) &&
- (clockid == CLOCK_REALTIME_ALARM ||
- clockid == CLOCK_BOOTTIME_ALARM))
+ if ((clockid == CLOCK_REALTIME_ALARM ||
+ clockid == CLOCK_BOOTTIME_ALARM) &&
+ !capable(CAP_WAKE_ALARM))
return -EPERM;
ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
@@ -449,7 +449,7 @@ static int do_timerfd_settime(int ufd, int flags,
return ret;
ctx = f.file->private_data;
- if (!capable(CAP_WAKE_ALARM) && isalarm(ctx)) {
+ if (isalarm(ctx) && !capable(CAP_WAKE_ALARM)) {
fdput(f);
return -EPERM;
}
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 973607d..1d227b0 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -138,8 +138,6 @@ static int userfaultfd_wake_function(wait_queue_t *wq, unsigned mode,
* userfaultfd_ctx_get - Acquires a reference to the internal userfaultfd
* context.
* @ctx: [in] Pointer to the userfaultfd context.
- *
- * Returns: In case of success, returns not zero.
*/
static void userfaultfd_ctx_get(struct userfaultfd_ctx *ctx)
{
@@ -267,6 +265,7 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
{
struct mm_struct *mm = ctx->mm;
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
pmd_t *pmd, _pmd;
pte_t *pte;
@@ -277,7 +276,10 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
pgd = pgd_offset(mm, address);
if (!pgd_present(*pgd))
goto out;
- pud = pud_offset(pgd, address);
+ p4d = p4d_offset(pgd, address);
+ if (!p4d_present(*p4d))
+ goto out;
+ pud = pud_offset(p4d, address);
if (!pud_present(*pud))
goto out;
pmd = pmd_offset(pud, address);
@@ -490,7 +492,7 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
* in such case.
*/
down_read(&mm->mmap_sem);
- ret = 0;
+ ret = VM_FAULT_NOPAGE;
}
}
@@ -527,10 +529,11 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
return ret;
}
-static int userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
- struct userfaultfd_wait_queue *ewq)
+static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
+ struct userfaultfd_wait_queue *ewq)
{
- int ret = 0;
+ if (WARN_ON_ONCE(current->flags & PF_EXITING))
+ goto out;
ewq->ctx = ctx;
init_waitqueue_entry(&ewq->wq, current);
@@ -547,8 +550,16 @@ static int userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
break;
if (ACCESS_ONCE(ctx->released) ||
fatal_signal_pending(current)) {
- ret = -1;
__remove_wait_queue(&ctx->event_wqh, &ewq->wq);
+ if (ewq->msg.event == UFFD_EVENT_FORK) {
+ struct userfaultfd_ctx *new;
+
+ new = (struct userfaultfd_ctx *)
+ (unsigned long)
+ ewq->msg.arg.reserved.reserved1;
+
+ userfaultfd_ctx_put(new);
+ }
break;
}
@@ -566,9 +577,8 @@ static int userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
* ctx may go away after this if the userfault pseudo fd is
* already released.
*/
-
+out:
userfaultfd_ctx_put(ctx);
- return ret;
}
static void userfaultfd_event_complete(struct userfaultfd_ctx *ctx,
@@ -626,7 +636,7 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
return 0;
}
-static int dup_fctx(struct userfaultfd_fork_ctx *fctx)
+static void dup_fctx(struct userfaultfd_fork_ctx *fctx)
{
struct userfaultfd_ctx *ctx = fctx->orig;
struct userfaultfd_wait_queue ewq;
@@ -636,17 +646,15 @@ static int dup_fctx(struct userfaultfd_fork_ctx *fctx)
ewq.msg.event = UFFD_EVENT_FORK;
ewq.msg.arg.reserved.reserved1 = (unsigned long)fctx->new;
- return userfaultfd_event_wait_completion(ctx, &ewq);
+ userfaultfd_event_wait_completion(ctx, &ewq);
}
void dup_userfaultfd_complete(struct list_head *fcs)
{
- int ret = 0;
struct userfaultfd_fork_ctx *fctx, *n;
list_for_each_entry_safe(fctx, n, fcs, list) {
- if (!ret)
- ret = dup_fctx(fctx);
+ dup_fctx(fctx);
list_del(&fctx->list);
kfree(fctx);
}
@@ -689,8 +697,7 @@ void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx,
userfaultfd_event_wait_completion(ctx, &ewq);
}
-void userfaultfd_remove(struct vm_area_struct *vma,
- struct vm_area_struct **prev,
+bool userfaultfd_remove(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
struct mm_struct *mm = vma->vm_mm;
@@ -699,13 +706,11 @@ void userfaultfd_remove(struct vm_area_struct *vma,
ctx = vma->vm_userfaultfd_ctx.ctx;
if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_REMOVE))
- return;
+ return true;
userfaultfd_ctx_get(ctx);
up_read(&mm->mmap_sem);
- *prev = NULL; /* We wait for ACK w/o the mmap semaphore */
-
msg_init(&ewq.msg);
ewq.msg.event = UFFD_EVENT_REMOVE;
@@ -714,7 +719,7 @@ void userfaultfd_remove(struct vm_area_struct *vma,
userfaultfd_event_wait_completion(ctx, &ewq);
- down_read(&mm->mmap_sem);
+ return false;
}
static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps,
@@ -775,34 +780,6 @@ void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf)
}
}
-void userfaultfd_exit(struct mm_struct *mm)
-{
- struct vm_area_struct *vma = mm->mmap;
-
- /*
- * We can do the vma walk without locking because the caller
- * (exit_mm) knows it now has exclusive access
- */
- while (vma) {
- struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;
-
- if (ctx && (ctx->features & UFFD_FEATURE_EVENT_EXIT)) {
- struct userfaultfd_wait_queue ewq;
-
- userfaultfd_ctx_get(ctx);
-
- msg_init(&ewq.msg);
- ewq.msg.event = UFFD_EVENT_EXIT;
-
- userfaultfd_event_wait_completion(ctx, &ewq);
-
- ctx->features &= ~UFFD_FEATURE_EVENT_EXIT;
- }
-
- vma = vma->vm_next;
- }
-}
-
static int userfaultfd_release(struct inode *inode, struct file *file)
{
struct userfaultfd_ctx *ctx = file->private_data;
diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c
index 2dfdc62..70a5b55 100644
--- a/fs/xfs/kmem.c
+++ b/fs/xfs/kmem.c
@@ -25,24 +25,6 @@
#include "kmem.h"
#include "xfs_message.h"
-/*
- * Greedy allocation. May fail and may return vmalloced memory.
- */
-void *
-kmem_zalloc_greedy(size_t *size, size_t minsize, size_t maxsize)
-{
- void *ptr;
- size_t kmsize = maxsize;
-
- while (!(ptr = vzalloc(kmsize))) {
- if ((kmsize >>= 1) <= minsize)
- kmsize = minsize;
- }
- if (ptr)
- *size = kmsize;
- return ptr;
-}
-
void *
kmem_alloc(size_t size, xfs_km_flags_t flags)
{
diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h
index 689f746..f0fc84f 100644
--- a/fs/xfs/kmem.h
+++ b/fs/xfs/kmem.h
@@ -69,8 +69,6 @@ static inline void kmem_free(const void *ptr)
}
-extern void *kmem_zalloc_greedy(size_t *, size_t, size_t);
-
static inline void *
kmem_zalloc(size_t size, xfs_km_flags_t flags)
{
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index a9c66d4..9bd104f 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -763,8 +763,8 @@ xfs_bmap_extents_to_btree(
args.type = XFS_ALLOCTYPE_START_BNO;
args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino);
} else if (dfops->dop_low) {
-try_another_ag:
args.type = XFS_ALLOCTYPE_START_BNO;
+try_another_ag:
args.fsbno = *firstblock;
} else {
args.type = XFS_ALLOCTYPE_NEAR_BNO;
@@ -790,13 +790,17 @@ xfs_bmap_extents_to_btree(
if (xfs_sb_version_hasreflink(&cur->bc_mp->m_sb) &&
args.fsbno == NULLFSBLOCK &&
args.type == XFS_ALLOCTYPE_NEAR_BNO) {
- dfops->dop_low = true;
+ args.type = XFS_ALLOCTYPE_FIRST_AG;
goto try_another_ag;
}
+ if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
+ xfs_iroot_realloc(ip, -1, whichfork);
+ xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+ return -ENOSPC;
+ }
/*
* Allocation can't fail, the space was reserved.
*/
- ASSERT(args.fsbno != NULLFSBLOCK);
ASSERT(*firstblock == NULLFSBLOCK ||
args.agno >= XFS_FSB_TO_AGNO(mp, *firstblock));
*firstblock = cur->bc_private.b.firstblock = args.fsbno;
@@ -4150,6 +4154,19 @@ xfs_bmapi_read(
return 0;
}
+/*
+ * Add a delayed allocation extent to an inode. Blocks are reserved from the
+ * global pool and the extent inserted into the inode in-core extent tree.
+ *
+ * On entry, got refers to the first extent beyond the offset of the extent to
+ * allocate or eof is specified if no such extent exists. On return, got refers
+ * to the extent record that was inserted to the inode fork.
+ *
+ * Note that the allocated extent may have been merged with contiguous extents
+ * during insertion into the inode fork. Thus, got does not reflect the current
+ * state of the inode fork on return. If necessary, the caller can use lastx to
+ * look up the updated record in the inode fork.
+ */
int
xfs_bmapi_reserve_delalloc(
struct xfs_inode *ip,
@@ -4236,13 +4253,8 @@ xfs_bmapi_reserve_delalloc(
got->br_startblock = nullstartblock(indlen);
got->br_blockcount = alen;
got->br_state = XFS_EXT_NORM;
- xfs_bmap_add_extent_hole_delay(ip, whichfork, lastx, got);
- /*
- * Update our extent pointer, given that xfs_bmap_add_extent_hole_delay
- * might have merged it into one of the neighbouring ones.
- */
- xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *lastx), got);
+ xfs_bmap_add_extent_hole_delay(ip, whichfork, lastx, got);
/*
* Tag the inode if blocks were preallocated. Note that COW fork
@@ -4254,10 +4266,6 @@ xfs_bmapi_reserve_delalloc(
if (whichfork == XFS_COW_FORK && (prealloc || aoff < off || alen > len))
xfs_inode_set_cowblocks_tag(ip);
- ASSERT(got->br_startoff <= aoff);
- ASSERT(got->br_startoff + got->br_blockcount >= aoff + alen);
- ASSERT(isnullstartblock(got->br_startblock));
- ASSERT(got->br_state == XFS_EXT_NORM);
return 0;
out_unreserve_blocks:
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index f93072b..fd55db4 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -447,8 +447,8 @@ xfs_bmbt_alloc_block(
if (args.fsbno == NULLFSBLOCK) {
args.fsbno = be64_to_cpu(start->l);
-try_another_ag:
args.type = XFS_ALLOCTYPE_START_BNO;
+try_another_ag:
/*
* Make sure there is sufficient room left in the AG to
* complete a full tree split for an extent insert. If
@@ -488,8 +488,8 @@ xfs_bmbt_alloc_block(
if (xfs_sb_version_hasreflink(&cur->bc_mp->m_sb) &&
args.fsbno == NULLFSBLOCK &&
args.type == XFS_ALLOCTYPE_NEAR_BNO) {
- cur->bc_private.b.dfops->dop_low = true;
args.fsbno = cur->bc_private.b.firstblock;
+ args.type = XFS_ALLOCTYPE_FIRST_AG;
goto try_another_ag;
}
@@ -506,7 +506,7 @@ xfs_bmbt_alloc_block(
goto error0;
cur->bc_private.b.dfops->dop_low = true;
}
- if (args.fsbno == NULLFSBLOCK) {
+ if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
*stat = 0;
return 0;
diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h
index d04547f..eb00bc1 100644
--- a/fs/xfs/libxfs/xfs_dir2_priv.h
+++ b/fs/xfs/libxfs/xfs_dir2_priv.h
@@ -125,6 +125,8 @@ extern int xfs_dir2_sf_create(struct xfs_da_args *args, xfs_ino_t pino);
extern int xfs_dir2_sf_lookup(struct xfs_da_args *args);
extern int xfs_dir2_sf_removename(struct xfs_da_args *args);
extern int xfs_dir2_sf_replace(struct xfs_da_args *args);
+extern int xfs_dir2_sf_verify(struct xfs_mount *mp, struct xfs_dir2_sf_hdr *sfp,
+ int size);
/* xfs_dir2_readdir.c */
extern int xfs_readdir(struct xfs_inode *dp, struct dir_context *ctx,
diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c
index c6809ff..96b45cd 100644
--- a/fs/xfs/libxfs/xfs_dir2_sf.c
+++ b/fs/xfs/libxfs/xfs_dir2_sf.c
@@ -629,6 +629,93 @@ xfs_dir2_sf_check(
}
#endif /* DEBUG */
+/* Verify the consistency of an inline directory. */
+int
+xfs_dir2_sf_verify(
+ struct xfs_mount *mp,
+ struct xfs_dir2_sf_hdr *sfp,
+ int size)
+{
+ struct xfs_dir2_sf_entry *sfep;
+ struct xfs_dir2_sf_entry *next_sfep;
+ char *endp;
+ const struct xfs_dir_ops *dops;
+ xfs_ino_t ino;
+ int i;
+ int i8count;
+ int offset;
+ __uint8_t filetype;
+
+ dops = xfs_dir_get_ops(mp, NULL);
+
+ /*
+ * Give up if the directory is way too short.
+ */
+ XFS_WANT_CORRUPTED_RETURN(mp, size >
+ offsetof(struct xfs_dir2_sf_hdr, parent));
+ XFS_WANT_CORRUPTED_RETURN(mp, size >=
+ xfs_dir2_sf_hdr_size(sfp->i8count));
+
+ endp = (char *)sfp + size;
+
+ /* Check .. entry */
+ ino = dops->sf_get_parent_ino(sfp);
+ i8count = ino > XFS_DIR2_MAX_SHORT_INUM;
+ XFS_WANT_CORRUPTED_RETURN(mp, !xfs_dir_ino_validate(mp, ino));
+ offset = dops->data_first_offset;
+
+ /* Check all reported entries */
+ sfep = xfs_dir2_sf_firstentry(sfp);
+ for (i = 0; i < sfp->count; i++) {
+ /*
+ * struct xfs_dir2_sf_entry has a variable length.
+ * Check the fixed-offset parts of the structure are
+ * within the data buffer.
+ */
+ XFS_WANT_CORRUPTED_RETURN(mp,
+ ((char *)sfep + sizeof(*sfep)) < endp);
+
+ /* Don't allow names with known bad length. */
+ XFS_WANT_CORRUPTED_RETURN(mp, sfep->namelen > 0);
+ XFS_WANT_CORRUPTED_RETURN(mp, sfep->namelen < MAXNAMELEN);
+
+ /*
+ * Check that the variable-length part of the structure is
+ * within the data buffer. The next entry starts after the
+ * name component, so nextentry is an acceptable test.
+ */
+ next_sfep = dops->sf_nextentry(sfp, sfep);
+ XFS_WANT_CORRUPTED_RETURN(mp, endp >= (char *)next_sfep);
+
+ /* Check that the offsets always increase. */
+ XFS_WANT_CORRUPTED_RETURN(mp,
+ xfs_dir2_sf_get_offset(sfep) >= offset);
+
+ /* Check the inode number. */
+ ino = dops->sf_get_ino(sfp, sfep);
+ i8count += ino > XFS_DIR2_MAX_SHORT_INUM;
+ XFS_WANT_CORRUPTED_RETURN(mp, !xfs_dir_ino_validate(mp, ino));
+
+ /* Check the file type. */
+ filetype = dops->sf_get_ftype(sfep);
+ XFS_WANT_CORRUPTED_RETURN(mp, filetype < XFS_DIR3_FT_MAX);
+
+ offset = xfs_dir2_sf_get_offset(sfep) +
+ dops->data_entsize(sfep->namelen);
+
+ sfep = next_sfep;
+ }
+ XFS_WANT_CORRUPTED_RETURN(mp, i8count == sfp->i8count);
+ XFS_WANT_CORRUPTED_RETURN(mp, (void *)sfep == (void *)endp);
+
+ /* Make sure this whole thing ought to be in local format. */
+ XFS_WANT_CORRUPTED_RETURN(mp, offset +
+ (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) +
+ (uint)sizeof(xfs_dir2_block_tail_t) <= mp->m_dir_geo->blksize);
+
+ return 0;
+}
+
/*
* Create a new (shortform) directory.
*/
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index 25c1e07..9653e96 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -33,6 +33,8 @@
#include "xfs_trace.h"
#include "xfs_attr_sf.h"
#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_dir2_priv.h"
kmem_zone_t *xfs_ifork_zone;
@@ -320,6 +322,7 @@ xfs_iformat_local(
int whichfork,
int size)
{
+ int error;
/*
* If the size is unreasonable, then something
@@ -336,6 +339,14 @@ xfs_iformat_local(
return -EFSCORRUPTED;
}
+ if (S_ISDIR(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK) {
+ error = xfs_dir2_sf_verify(ip->i_mount,
+ (struct xfs_dir2_sf_hdr *)XFS_DFORK_DPTR(dip),
+ size);
+ if (error)
+ return error;
+ }
+
xfs_init_local_fork(ip, whichfork, XFS_DFORK_PTR(dip, whichfork), size);
return 0;
}
@@ -856,7 +867,7 @@ xfs_iextents_copy(
* In these cases, the format always takes precedence, because the
* format indicates the current state of the fork.
*/
-void
+int
xfs_iflush_fork(
xfs_inode_t *ip,
xfs_dinode_t *dip,
@@ -866,6 +877,7 @@ xfs_iflush_fork(
char *cp;
xfs_ifork_t *ifp;
xfs_mount_t *mp;
+ int error;
static const short brootflag[2] =
{ XFS_ILOG_DBROOT, XFS_ILOG_ABROOT };
static const short dataflag[2] =
@@ -874,7 +886,7 @@ xfs_iflush_fork(
{ XFS_ILOG_DEXT, XFS_ILOG_AEXT };
if (!iip)
- return;
+ return 0;
ifp = XFS_IFORK_PTR(ip, whichfork);
/*
* This can happen if we gave up in iformat in an error path,
@@ -882,12 +894,19 @@ xfs_iflush_fork(
*/
if (!ifp) {
ASSERT(whichfork == XFS_ATTR_FORK);
- return;
+ return 0;
}
cp = XFS_DFORK_PTR(dip, whichfork);
mp = ip->i_mount;
switch (XFS_IFORK_FORMAT(ip, whichfork)) {
case XFS_DINODE_FMT_LOCAL:
+ if (S_ISDIR(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK) {
+ error = xfs_dir2_sf_verify(mp,
+ (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data,
+ ifp->if_bytes);
+ if (error)
+ return error;
+ }
if ((iip->ili_fields & dataflag[whichfork]) &&
(ifp->if_bytes > 0)) {
ASSERT(ifp->if_u1.if_data != NULL);
@@ -940,6 +959,7 @@ xfs_iflush_fork(
ASSERT(0);
break;
}
+ return 0;
}
/*
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index 7fb8365..132dc59 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -140,7 +140,7 @@ typedef struct xfs_ifork {
struct xfs_ifork *xfs_iext_state_to_fork(struct xfs_inode *ip, int state);
int xfs_iformat_fork(struct xfs_inode *, struct xfs_dinode *);
-void xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *,
+int xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *,
struct xfs_inode_log_item *, int);
void xfs_idestroy_fork(struct xfs_inode *, int);
void xfs_idata_realloc(struct xfs_inode *, int, int);
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index bf65a9e..6149429 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -274,54 +274,49 @@ xfs_end_io(
struct xfs_ioend *ioend =
container_of(work, struct xfs_ioend, io_work);
struct xfs_inode *ip = XFS_I(ioend->io_inode);
+ xfs_off_t offset = ioend->io_offset;
+ size_t size = ioend->io_size;
int error = ioend->io_bio->bi_error;
/*
- * Set an error if the mount has shut down and proceed with end I/O
- * processing so it can perform whatever cleanups are necessary.
+ * Just clean up the in-memory strutures if the fs has been shut down.
*/
- if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+ if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
error = -EIO;
-
- /*
- * For a CoW extent, we need to move the mapping from the CoW fork
- * to the data fork. If instead an error happened, just dump the
- * new blocks.
- */
- if (ioend->io_type == XFS_IO_COW) {
- if (error)
- goto done;
- if (ioend->io_bio->bi_error) {
- error = xfs_reflink_cancel_cow_range(ip,
- ioend->io_offset, ioend->io_size);
- goto done;
- }
- error = xfs_reflink_end_cow(ip, ioend->io_offset,
- ioend->io_size);
- if (error)
- goto done;
+ goto done;
}
/*
- * For unwritten extents we need to issue transactions to convert a
- * range to normal written extens after the data I/O has finished.
- * Detecting and handling completion IO errors is done individually
- * for each case as different cleanup operations need to be performed
- * on error.
+ * Clean up any COW blocks on an I/O error.
*/
- if (ioend->io_type == XFS_IO_UNWRITTEN) {
- if (error)
- goto done;
- error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
- ioend->io_size);
- } else if (ioend->io_append_trans) {
- error = xfs_setfilesize_ioend(ioend, error);
- } else {
- ASSERT(!xfs_ioend_is_append(ioend) ||
- ioend->io_type == XFS_IO_COW);
+ if (unlikely(error)) {
+ switch (ioend->io_type) {
+ case XFS_IO_COW:
+ xfs_reflink_cancel_cow_range(ip, offset, size, true);
+ break;
+ }
+
+ goto done;
+ }
+
+ /*
+ * Success: commit the COW or unwritten blocks if needed.
+ */
+ switch (ioend->io_type) {
+ case XFS_IO_COW:
+ error = xfs_reflink_end_cow(ip, offset, size);
+ break;
+ case XFS_IO_UNWRITTEN:
+ error = xfs_iomap_write_unwritten(ip, offset, size);
+ break;
+ default:
+ ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_append_trans);
+ break;
}
done:
+ if (ioend->io_append_trans)
+ error = xfs_setfilesize_ioend(ioend, error);
xfs_destroy_ioend(ioend, error);
}
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index 003a99b..ad9396e 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -71,22 +71,11 @@ xfs_dir2_sf_getdents(
struct xfs_da_geometry *geo = args->geo;
ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
- /*
- * Give up if the directory is way too short.
- */
- if (dp->i_d.di_size < offsetof(xfs_dir2_sf_hdr_t, parent)) {
- ASSERT(XFS_FORCED_SHUTDOWN(dp->i_mount));
- return -EIO;
- }
-
ASSERT(dp->i_df.if_bytes == dp->i_d.di_size);
ASSERT(dp->i_df.if_u1.if_data != NULL);
sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
- if (dp->i_d.di_size < xfs_dir2_sf_hdr_size(sfp->i8count))
- return -EFSCORRUPTED;
-
/*
* If the block number in the offset is out of range, we're done.
*/
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 7234b97..3531f8f 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1608,7 +1608,7 @@ xfs_inode_free_cowblocks(
xfs_ilock(ip, XFS_IOLOCK_EXCL);
xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
- ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF);
+ ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, false);
xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index edfa6a5..c7fe2c2 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1615,7 +1615,7 @@ xfs_itruncate_extents(
/* Remove all pending CoW reservations. */
error = xfs_reflink_cancel_cow_blocks(ip, &tp, first_unmap_block,
- last_block);
+ last_block, true);
if (error)
goto out;
@@ -3475,6 +3475,7 @@ xfs_iflush_int(
struct xfs_inode_log_item *iip = ip->i_itemp;
struct xfs_dinode *dip;
struct xfs_mount *mp = ip->i_mount;
+ int error;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
ASSERT(xfs_isiflocked(ip));
@@ -3557,9 +3558,14 @@ xfs_iflush_int(
if (ip->i_d.di_flushiter == DI_MAX_FLUSH)
ip->i_d.di_flushiter = 0;
- xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK);
- if (XFS_IFORK_Q(ip))
- xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK);
+ error = xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK);
+ if (error)
+ return error;
+ if (XFS_IFORK_Q(ip)) {
+ error = xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK);
+ if (error)
+ return error;
+ }
xfs_inobp_check(mp, bp);
/*
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 41662fb..288ee5b 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -630,6 +630,11 @@ xfs_file_iomap_begin_delay(
goto out_unlock;
}
+ /*
+ * Flag newly allocated delalloc blocks with IOMAP_F_NEW so we punch
+ * them out if the write happens to fail.
+ */
+ iomap->flags = IOMAP_F_NEW;
trace_xfs_iomap_alloc(ip, offset, count, 0, &got);
done:
if (isnullstartblock(got.br_startblock))
@@ -1071,16 +1076,22 @@ xfs_file_iomap_end_delalloc(
struct xfs_inode *ip,
loff_t offset,
loff_t length,
- ssize_t written)
+ ssize_t written,
+ struct iomap *iomap)
{
struct xfs_mount *mp = ip->i_mount;
xfs_fileoff_t start_fsb;
xfs_fileoff_t end_fsb;
int error = 0;
- /* behave as if the write failed if drop writes is enabled */
- if (xfs_mp_drop_writes(mp))
+ /*
+ * Behave as if the write failed if drop writes is enabled. Set the NEW
+ * flag to force delalloc cleanup.
+ */
+ if (xfs_mp_drop_writes(mp)) {
+ iomap->flags |= IOMAP_F_NEW;
written = 0;
+ }
/*
* start_fsb refers to the first unused block after a short write. If
@@ -1094,14 +1105,14 @@ xfs_file_iomap_end_delalloc(
end_fsb = XFS_B_TO_FSB(mp, offset + length);
/*
- * Trim back delalloc blocks if we didn't manage to write the whole
- * range reserved.
+ * Trim delalloc blocks if they were allocated by this write and we
+ * didn't manage to write the whole range.
*
* We don't need to care about racing delalloc as we hold i_mutex
* across the reserve/allocate/unreserve calls. If there are delalloc
* blocks in the range, they are ours.
*/
- if (start_fsb < end_fsb) {
+ if ((iomap->flags & IOMAP_F_NEW) && start_fsb < end_fsb) {
truncate_pagecache_range(VFS_I(ip), XFS_FSB_TO_B(mp, start_fsb),
XFS_FSB_TO_B(mp, end_fsb) - 1);
@@ -1131,7 +1142,7 @@ xfs_file_iomap_end(
{
if ((flags & IOMAP_WRITE) && iomap->type == IOMAP_DELALLOC)
return xfs_file_iomap_end_delalloc(XFS_I(inode), offset,
- length, written);
+ length, written, iomap);
return 0;
}
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 66e8817..2a6d9b1 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -361,7 +361,6 @@ xfs_bulkstat(
xfs_agino_t agino; /* inode # in allocation group */
xfs_agnumber_t agno; /* allocation group number */
xfs_btree_cur_t *cur; /* btree cursor for ialloc btree */
- size_t irbsize; /* size of irec buffer in bytes */
xfs_inobt_rec_incore_t *irbuf; /* start of irec buffer */
int nirbuf; /* size of irbuf */
int ubcount; /* size of user's buffer */
@@ -388,11 +387,10 @@ xfs_bulkstat(
*ubcountp = 0;
*done = 0;
- irbuf = kmem_zalloc_greedy(&irbsize, PAGE_SIZE, PAGE_SIZE * 4);
+ irbuf = kmem_zalloc_large(PAGE_SIZE * 4, KM_SLEEP);
if (!irbuf)
return -ENOMEM;
-
- nirbuf = irbsize / sizeof(*irbuf);
+ nirbuf = (PAGE_SIZE * 4) / sizeof(*irbuf);
/*
* Loop over the allocation groups, starting from the last
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 450bde6..688ebff 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -513,8 +513,7 @@ STATIC void
xfs_set_inoalignment(xfs_mount_t *mp)
{
if (xfs_sb_version_hasalign(&mp->m_sb) &&
- mp->m_sb.sb_inoalignmt >=
- XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size))
+ mp->m_sb.sb_inoalignmt >= xfs_icluster_size_fsb(mp))
mp->m_inoalign_mask = mp->m_sb.sb_inoalignmt - 1;
else
mp->m_inoalign_mask = 0;
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index da6d08f..4a84c5e 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -548,14 +548,18 @@ xfs_reflink_trim_irec_to_next_cow(
}
/*
- * Cancel all pending CoW reservations for some block range of an inode.
+ * Cancel CoW reservations for some block range of an inode.
+ *
+ * If cancel_real is true this function cancels all COW fork extents for the
+ * inode; if cancel_real is false, real extents are not cleared.
*/
int
xfs_reflink_cancel_cow_blocks(
struct xfs_inode *ip,
struct xfs_trans **tpp,
xfs_fileoff_t offset_fsb,
- xfs_fileoff_t end_fsb)
+ xfs_fileoff_t end_fsb,
+ bool cancel_real)
{
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
struct xfs_bmbt_irec got, del;
@@ -579,7 +583,7 @@ xfs_reflink_cancel_cow_blocks(
&idx, &got, &del);
if (error)
break;
- } else {
+ } else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
xfs_trans_ijoin(*tpp, ip, 0);
xfs_defer_init(&dfops, &firstfsb);
@@ -621,13 +625,17 @@ xfs_reflink_cancel_cow_blocks(
}
/*
- * Cancel all pending CoW reservations for some byte range of an inode.
+ * Cancel CoW reservations for some byte range of an inode.
+ *
+ * If cancel_real is true this function cancels all COW fork extents for the
+ * inode; if cancel_real is false, real extents are not cleared.
*/
int
xfs_reflink_cancel_cow_range(
struct xfs_inode *ip,
xfs_off_t offset,
- xfs_off_t count)
+ xfs_off_t count,
+ bool cancel_real)
{
struct xfs_trans *tp;
xfs_fileoff_t offset_fsb;
@@ -653,7 +661,8 @@ xfs_reflink_cancel_cow_range(
xfs_trans_ijoin(tp, ip, 0);
/* Scrape out the old CoW reservations */
- error = xfs_reflink_cancel_cow_blocks(ip, &tp, offset_fsb, end_fsb);
+ error = xfs_reflink_cancel_cow_blocks(ip, &tp, offset_fsb, end_fsb,
+ cancel_real);
if (error)
goto out_cancel;
@@ -1450,7 +1459,7 @@ xfs_reflink_clear_inode_flag(
* We didn't find any shared blocks so turn off the reflink flag.
* First, get rid of any leftover CoW mappings.
*/
- error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF);
+ error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF, true);
if (error)
return error;
diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h
index 33ac9b8..d29a796 100644
--- a/fs/xfs/xfs_reflink.h
+++ b/fs/xfs/xfs_reflink.h
@@ -39,9 +39,9 @@ extern void xfs_reflink_trim_irec_to_next_cow(struct xfs_inode *ip,
extern int xfs_reflink_cancel_cow_blocks(struct xfs_inode *ip,
struct xfs_trans **tpp, xfs_fileoff_t offset_fsb,
- xfs_fileoff_t end_fsb);
+ xfs_fileoff_t end_fsb, bool cancel_real);
extern int xfs_reflink_cancel_cow_range(struct xfs_inode *ip, xfs_off_t offset,
- xfs_off_t count);
+ xfs_off_t count, bool cancel_real);
extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset,
xfs_off_t count);
extern int xfs_reflink_recover_cow(struct xfs_mount *mp);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 890862f..685c042 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -953,7 +953,7 @@ xfs_fs_destroy_inode(
XFS_STATS_INC(ip->i_mount, vn_remove);
if (xfs_is_reflink_inode(ip)) {
- error = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF);
+ error = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, true);
if (error && !XFS_FORCED_SHUTDOWN(ip->i_mount))
xfs_warn(ip->i_mount,
"Error %d while evicting CoW blocks for inode %llu.",
diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h
index 5bdab6b..928fd66 100644
--- a/include/asm-generic/4level-fixup.h
+++ b/include/asm-generic/4level-fixup.h
@@ -15,7 +15,6 @@
((unlikely(pgd_none(*(pud))) && __pmd_alloc(mm, pud, address))? \
NULL: pmd_offset(pud, address))
-#define pud_alloc(mm, pgd, address) (pgd)
#define pud_offset(pgd, start) (pgd)
#define pud_none(pud) 0
#define pud_bad(pud) 0
@@ -35,4 +34,6 @@
#undef pud_addr_end
#define pud_addr_end(addr, end) (end)
+#include <asm-generic/5level-fixup.h>
+
#endif
diff --git a/include/asm-generic/5level-fixup.h b/include/asm-generic/5level-fixup.h
new file mode 100644
index 0000000..b5ca82d
--- /dev/null
+++ b/include/asm-generic/5level-fixup.h
@@ -0,0 +1,41 @@
+#ifndef _5LEVEL_FIXUP_H
+#define _5LEVEL_FIXUP_H
+
+#define __ARCH_HAS_5LEVEL_HACK
+#define __PAGETABLE_P4D_FOLDED
+
+#define P4D_SHIFT PGDIR_SHIFT
+#define P4D_SIZE PGDIR_SIZE
+#define P4D_MASK PGDIR_MASK
+#define PTRS_PER_P4D 1
+
+#define p4d_t pgd_t
+
+#define pud_alloc(mm, p4d, address) \
+ ((unlikely(pgd_none(*(p4d))) && __pud_alloc(mm, p4d, address)) ? \
+ NULL : pud_offset(p4d, address))
+
+#define p4d_alloc(mm, pgd, address) (pgd)
+#define p4d_offset(pgd, start) (pgd)
+#define p4d_none(p4d) 0
+#define p4d_bad(p4d) 0
+#define p4d_present(p4d) 1
+#define p4d_ERROR(p4d) do { } while (0)
+#define p4d_clear(p4d) pgd_clear(p4d)
+#define p4d_val(p4d) pgd_val(p4d)
+#define p4d_populate(mm, p4d, pud) pgd_populate(mm, p4d, pud)
+#define p4d_page(p4d) pgd_page(p4d)
+#define p4d_page_vaddr(p4d) pgd_page_vaddr(p4d)
+
+#define __p4d(x) __pgd(x)
+#define set_p4d(p4dp, p4d) set_pgd(p4dp, p4d)
+
+#undef p4d_free_tlb
+#define p4d_free_tlb(tlb, x, addr) do { } while (0)
+#define p4d_free(mm, x) do { } while (0)
+#define __p4d_free_tlb(tlb, x, addr) do { } while (0)
+
+#undef p4d_addr_end
+#define p4d_addr_end(addr, end) (end)
+
+#endif
diff --git a/include/asm-generic/pgtable-nop4d-hack.h b/include/asm-generic/pgtable-nop4d-hack.h
new file mode 100644
index 0000000..752fb75
--- /dev/null
+++ b/include/asm-generic/pgtable-nop4d-hack.h
@@ -0,0 +1,62 @@
+#ifndef _PGTABLE_NOP4D_HACK_H
+#define _PGTABLE_NOP4D_HACK_H
+
+#ifndef __ASSEMBLY__
+#include <asm-generic/5level-fixup.h>
+
+#define __PAGETABLE_PUD_FOLDED
+
+/*
+ * Having the pud type consist of a pgd gets the size right, and allows
+ * us to conceptually access the pgd entry that this pud is folded into
+ * without casting.
+ */
+typedef struct { pgd_t pgd; } pud_t;
+
+#define PUD_SHIFT PGDIR_SHIFT
+#define PTRS_PER_PUD 1
+#define PUD_SIZE (1UL << PUD_SHIFT)
+#define PUD_MASK (~(PUD_SIZE-1))
+
+/*
+ * The "pgd_xxx()" functions here are trivial for a folded two-level
+ * setup: the pud is never bad, and a pud always exists (as it's folded
+ * into the pgd entry)
+ */
+static inline int pgd_none(pgd_t pgd) { return 0; }
+static inline int pgd_bad(pgd_t pgd) { return 0; }
+static inline int pgd_present(pgd_t pgd) { return 1; }
+static inline void pgd_clear(pgd_t *pgd) { }
+#define pud_ERROR(pud) (pgd_ERROR((pud).pgd))
+
+#define pgd_populate(mm, pgd, pud) do { } while (0)
+/*
+ * (puds are folded into pgds so this doesn't get actually called,
+ * but the define is needed for a generic inline function.)
+ */
+#define set_pgd(pgdptr, pgdval) set_pud((pud_t *)(pgdptr), (pud_t) { pgdval })
+
+static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address)
+{
+ return (pud_t *)pgd;
+}
+
+#define pud_val(x) (pgd_val((x).pgd))
+#define __pud(x) ((pud_t) { __pgd(x) })
+
+#define pgd_page(pgd) (pud_page((pud_t){ pgd }))
+#define pgd_page_vaddr(pgd) (pud_page_vaddr((pud_t){ pgd }))
+
+/*
+ * allocating and freeing a pud is trivial: the 1-entry pud is
+ * inside the pgd, so has no extra memory associated with it.
+ */
+#define pud_alloc_one(mm, address) NULL
+#define pud_free(mm, x) do { } while (0)
+#define __pud_free_tlb(tlb, x, a) do { } while (0)
+
+#undef pud_addr_end
+#define pud_addr_end(addr, end) (end)
+
+#endif /* __ASSEMBLY__ */
+#endif /* _PGTABLE_NOP4D_HACK_H */
diff --git a/include/asm-generic/pgtable-nop4d.h b/include/asm-generic/pgtable-nop4d.h
new file mode 100644
index 0000000..de364ec
--- /dev/null
+++ b/include/asm-generic/pgtable-nop4d.h
@@ -0,0 +1,56 @@
+#ifndef _PGTABLE_NOP4D_H
+#define _PGTABLE_NOP4D_H
+
+#ifndef __ASSEMBLY__
+
+#define __PAGETABLE_P4D_FOLDED
+
+typedef struct { pgd_t pgd; } p4d_t;
+
+#define P4D_SHIFT PGDIR_SHIFT
+#define PTRS_PER_P4D 1
+#define P4D_SIZE (1UL << P4D_SHIFT)
+#define P4D_MASK (~(P4D_SIZE-1))
+
+/*
+ * The "pgd_xxx()" functions here are trivial for a folded two-level
+ * setup: the p4d is never bad, and a p4d always exists (as it's folded
+ * into the pgd entry)
+ */
+static inline int pgd_none(pgd_t pgd) { return 0; }
+static inline int pgd_bad(pgd_t pgd) { return 0; }
+static inline int pgd_present(pgd_t pgd) { return 1; }
+static inline void pgd_clear(pgd_t *pgd) { }
+#define p4d_ERROR(p4d) (pgd_ERROR((p4d).pgd))
+
+#define pgd_populate(mm, pgd, p4d) do { } while (0)
+/*
+ * (p4ds are folded into pgds so this doesn't get actually called,
+ * but the define is needed for a generic inline function.)
+ */
+#define set_pgd(pgdptr, pgdval) set_p4d((p4d_t *)(pgdptr), (p4d_t) { pgdval })
+
+static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+{
+ return (p4d_t *)pgd;
+}
+
+#define p4d_val(x) (pgd_val((x).pgd))
+#define __p4d(x) ((p4d_t) { __pgd(x) })
+
+#define pgd_page(pgd) (p4d_page((p4d_t){ pgd }))
+#define pgd_page_vaddr(pgd) (p4d_page_vaddr((p4d_t){ pgd }))
+
+/*
+ * allocating and freeing a p4d is trivial: the 1-entry p4d is
+ * inside the pgd, so has no extra memory associated with it.
+ */
+#define p4d_alloc_one(mm, address) NULL
+#define p4d_free(mm, x) do { } while (0)
+#define __p4d_free_tlb(tlb, x, a) do { } while (0)
+
+#undef p4d_addr_end
+#define p4d_addr_end(addr, end) (end)
+
+#endif /* __ASSEMBLY__ */
+#endif /* _PGTABLE_NOP4D_H */
diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h
index 810431d..c2b9b96 100644
--- a/include/asm-generic/pgtable-nopud.h
+++ b/include/asm-generic/pgtable-nopud.h
@@ -3,52 +3,57 @@
#ifndef __ASSEMBLY__
+#ifdef __ARCH_USE_5LEVEL_HACK
+#include <asm-generic/pgtable-nop4d-hack.h>
+#else
+#include <asm-generic/pgtable-nop4d.h>
+
#define __PAGETABLE_PUD_FOLDED
/*
- * Having the pud type consist of a pgd gets the size right, and allows
- * us to conceptually access the pgd entry that this pud is folded into
+ * Having the pud type consist of a p4d gets the size right, and allows
+ * us to conceptually access the p4d entry that this pud is folded into
* without casting.
*/
-typedef struct { pgd_t pgd; } pud_t;
+typedef struct { p4d_t p4d; } pud_t;
-#define PUD_SHIFT PGDIR_SHIFT
+#define PUD_SHIFT P4D_SHIFT
#define PTRS_PER_PUD 1
#define PUD_SIZE (1UL << PUD_SHIFT)
#define PUD_MASK (~(PUD_SIZE-1))
/*
- * The "pgd_xxx()" functions here are trivial for a folded two-level
+ * The "p4d_xxx()" functions here are trivial for a folded two-level
* setup: the pud is never bad, and a pud always exists (as it's folded
- * into the pgd entry)
+ * into the p4d entry)
*/
-static inline int pgd_none(pgd_t pgd) { return 0; }
-static inline int pgd_bad(pgd_t pgd) { return 0; }
-static inline int pgd_present(pgd_t pgd) { return 1; }
-static inline void pgd_clear(pgd_t *pgd) { }
-#define pud_ERROR(pud) (pgd_ERROR((pud).pgd))
+static inline int p4d_none(p4d_t p4d) { return 0; }
+static inline int p4d_bad(p4d_t p4d) { return 0; }
+static inline int p4d_present(p4d_t p4d) { return 1; }
+static inline void p4d_clear(p4d_t *p4d) { }
+#define pud_ERROR(pud) (p4d_ERROR((pud).p4d))
-#define pgd_populate(mm, pgd, pud) do { } while (0)
+#define p4d_populate(mm, p4d, pud) do { } while (0)
/*
- * (puds are folded into pgds so this doesn't get actually called,
+ * (puds are folded into p4ds so this doesn't get actually called,
* but the define is needed for a generic inline function.)
*/
-#define set_pgd(pgdptr, pgdval) set_pud((pud_t *)(pgdptr), (pud_t) { pgdval })
+#define set_p4d(p4dptr, p4dval) set_pud((pud_t *)(p4dptr), (pud_t) { p4dval })
-static inline pud_t * pud_offset(pgd_t * pgd, unsigned long address)
+static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
{
- return (pud_t *)pgd;
+ return (pud_t *)p4d;
}
-#define pud_val(x) (pgd_val((x).pgd))
-#define __pud(x) ((pud_t) { __pgd(x) } )
+#define pud_val(x) (p4d_val((x).p4d))
+#define __pud(x) ((pud_t) { __p4d(x) })
-#define pgd_page(pgd) (pud_page((pud_t){ pgd }))
-#define pgd_page_vaddr(pgd) (pud_page_vaddr((pud_t){ pgd }))
+#define p4d_page(p4d) (pud_page((pud_t){ p4d }))
+#define p4d_page_vaddr(p4d) (pud_page_vaddr((pud_t){ p4d }))
/*
* allocating and freeing a pud is trivial: the 1-entry pud is
- * inside the pgd, so has no extra memory associated with it.
+ * inside the p4d, so has no extra memory associated with it.
*/
#define pud_alloc_one(mm, address) NULL
#define pud_free(mm, x) do { } while (0)
@@ -58,4 +63,5 @@ static inline pud_t * pud_offset(pgd_t * pgd, unsigned long address)
#define pud_addr_end(addr, end) (end)
#endif /* __ASSEMBLY__ */
+#endif /* !__ARCH_USE_5LEVEL_HACK */
#endif /* _PGTABLE_NOPUD_H */
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index f4ca23b..1fad160 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -10,9 +10,9 @@
#include <linux/bug.h>
#include <linux/errno.h>
-#if 4 - defined(__PAGETABLE_PUD_FOLDED) - defined(__PAGETABLE_PMD_FOLDED) != \
- CONFIG_PGTABLE_LEVELS
-#error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{PUD,PMD}_FOLDED
+#if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \
+ defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS
+#error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{P4D,PUD,PMD}_FOLDED
#endif
/*
@@ -424,6 +424,13 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
(__boundary - 1 < (end) - 1)? __boundary: (end); \
})
+#ifndef p4d_addr_end
+#define p4d_addr_end(addr, end) \
+({ unsigned long __boundary = ((addr) + P4D_SIZE) & P4D_MASK; \
+ (__boundary - 1 < (end) - 1)? __boundary: (end); \
+})
+#endif
+
#ifndef pud_addr_end
#define pud_addr_end(addr, end) \
({ unsigned long __boundary = ((addr) + PUD_SIZE) & PUD_MASK; \
@@ -444,6 +451,7 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
* Do the tests inline, but report and clear the bad entry in mm/memory.c.
*/
void pgd_clear_bad(pgd_t *);
+void p4d_clear_bad(p4d_t *);
void pud_clear_bad(pud_t *);
void pmd_clear_bad(pmd_t *);
@@ -458,6 +466,17 @@ static inline int pgd_none_or_clear_bad(pgd_t *pgd)
return 0;
}
+static inline int p4d_none_or_clear_bad(p4d_t *p4d)
+{
+ if (p4d_none(*p4d))
+ return 1;
+ if (unlikely(p4d_bad(*p4d))) {
+ p4d_clear_bad(p4d);
+ return 1;
+ }
+ return 0;
+}
+
static inline int pud_none_or_clear_bad(pud_t *pud)
{
if (pud_none(*pud))
@@ -844,11 +863,30 @@ static inline int pmd_protnone(pmd_t pmd)
#endif /* CONFIG_MMU */
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+
+#ifndef __PAGETABLE_P4D_FOLDED
+int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot);
+int p4d_clear_huge(p4d_t *p4d);
+#else
+static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
+{
+ return 0;
+}
+static inline int p4d_clear_huge(p4d_t *p4d)
+{
+ return 0;
+}
+#endif /* !__PAGETABLE_P4D_FOLDED */
+
int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot);
int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot);
int pud_clear_huge(pud_t *pud);
int pmd_clear_huge(pmd_t *pmd);
#else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */
+static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
+{
+ return 0;
+}
static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
{
return 0;
@@ -857,6 +895,10 @@ static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
{
return 0;
}
+static inline int p4d_clear_huge(p4d_t *p4d)
+{
+ return 0;
+}
static inline int pud_clear_huge(pud_t *pud)
{
return 0;
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index 4df64a1..532372c 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -14,8 +14,8 @@
* [_sdata, _edata]: contains .data.* sections, may also contain .rodata.*
* and/or .init.* sections.
* [__start_rodata, __end_rodata]: contains .rodata.* sections
- * [__start_data_ro_after_init, __end_data_ro_after_init]:
- * contains data.ro_after_init section
+ * [__start_ro_after_init, __end_ro_after_init]:
+ * contains .data..ro_after_init section
* [__init_begin, __init_end]: contains .init.* sections, but .init.text.*
* may be out of this range on some architectures.
* [_sinittext, _einittext]: contains .init.text.* sections
@@ -33,7 +33,7 @@ extern char _data[], _sdata[], _edata[];
extern char __bss_start[], __bss_stop[];
extern char __init_begin[], __init_end[];
extern char _sinittext[], _einittext[];
-extern char __start_data_ro_after_init[], __end_data_ro_after_init[];
+extern char __start_ro_after_init[], __end_ro_after_init[];
extern char _end[];
extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
extern char __kprobes_text_start[], __kprobes_text_end[];
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 4329bc6..8afa433 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -270,6 +270,12 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
__pte_free_tlb(tlb, ptep, address); \
} while (0)
+#define pmd_free_tlb(tlb, pmdp, address) \
+ do { \
+ __tlb_adjust_range(tlb, address, PAGE_SIZE); \
+ __pmd_free_tlb(tlb, pmdp, address); \
+ } while (0)
+
#ifndef __ARCH_HAS_4LEVEL_HACK
#define pud_free_tlb(tlb, pudp, address) \
do { \
@@ -278,11 +284,13 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
} while (0)
#endif
-#define pmd_free_tlb(tlb, pmdp, address) \
+#ifndef __ARCH_HAS_5LEVEL_HACK
+#define p4d_free_tlb(tlb, pudp, address) \
do { \
- __tlb_adjust_range(tlb, address, PAGE_SIZE); \
- __pmd_free_tlb(tlb, pmdp, address); \
+ __tlb_adjust_range(tlb, address, PAGE_SIZE); \
+ __p4d_free_tlb(tlb, pudp, address); \
} while (0)
+#endif
#define tlb_migrate_finish(mm) do {} while (0)
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 0968d13..7cdfe16 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -173,6 +173,7 @@
KEEP(*(__##name##_of_table_end))
#define CLKSRC_OF_TABLES() OF_TABLE(CONFIG_CLKSRC_OF, clksrc)
+#define CLKEVT_OF_TABLES() OF_TABLE(CONFIG_CLKEVT_OF, clkevt)
#define IRQCHIP_OF_MATCH_TABLE() OF_TABLE(CONFIG_IRQCHIP, irqchip)
#define CLK_OF_TABLES() OF_TABLE(CONFIG_COMMON_CLK, clk)
#define IOMMU_OF_TABLES() OF_TABLE(CONFIG_OF_IOMMU, iommu)
@@ -260,9 +261,9 @@
*/
#ifndef RO_AFTER_INIT_DATA
#define RO_AFTER_INIT_DATA \
- __start_data_ro_after_init = .; \
+ __start_ro_after_init = .; \
*(.data..ro_after_init) \
- __end_data_ro_after_init = .;
+ __end_ro_after_init = .;
#endif
/*
@@ -559,6 +560,7 @@
CLK_OF_TABLES() \
RESERVEDMEM_OF_TABLES() \
CLKSRC_OF_TABLES() \
+ CLKEVT_OF_TABLES() \
IOMMU_OF_TABLES() \
CPU_METHOD_OF_TABLES() \
CPUIDLE_METHOD_OF_TABLES() \
diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h
index a2bfd78..e2b9c6f 100644
--- a/include/crypto/if_alg.h
+++ b/include/crypto/if_alg.h
@@ -73,7 +73,7 @@ int af_alg_unregister_type(const struct af_alg_type *type);
int af_alg_release(struct socket *sock);
void af_alg_release_parent(struct sock *sk);
-int af_alg_accept(struct sock *sk, struct socket *newsock);
+int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern);
int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len);
void af_alg_free_sg(struct af_alg_sgl *sgl);
diff --git a/include/drm/ttm/ttm_object.h b/include/drm/ttm/ttm_object.h
index ed953f9..1487011 100644
--- a/include/drm/ttm/ttm_object.h
+++ b/include/drm/ttm/ttm_object.h
@@ -229,6 +229,8 @@ extern void ttm_base_object_unref(struct ttm_base_object **p_base);
* @ref_type: The type of reference.
* @existed: Upon completion, indicates that an identical reference object
* already existed, and the refcount was upped on that object instead.
+ * @require_existed: Fail with -EPERM if an identical ref object didn't
+ * already exist.
*
* Checks that the base object is shareable and adds a ref object to it.
*
@@ -243,7 +245,8 @@ extern void ttm_base_object_unref(struct ttm_base_object **p_base);
*/
extern int ttm_ref_object_add(struct ttm_object_file *tfile,
struct ttm_base_object *base,
- enum ttm_ref_type ref_type, bool *existed);
+ enum ttm_ref_type ref_type, bool *existed,
+ bool require_existed);
extern bool ttm_ref_object_exists(struct ttm_object_file *tfile,
struct ttm_base_object *base);
diff --git a/include/dt-bindings/sound/cs42l42.h b/include/dt-bindings/sound/cs42l42.h
index 399a123..db69d84 100644
--- a/include/dt-bindings/sound/cs42l42.h
+++ b/include/dt-bindings/sound/cs42l42.h
@@ -20,7 +20,7 @@
#define CS42L42_HPOUT_LOAD_1NF 0
#define CS42L42_HPOUT_LOAD_10NF 1
-/* HPOUT Clamp to GND Overide */
+/* HPOUT Clamp to GND Override */
#define CS42L42_HPOUT_CLAMP_EN 0
#define CS42L42_HPOUT_CLAMP_DIS 1
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 673acda..9b05886 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -287,18 +287,15 @@ static inline bool invalid_phys_cpuid(phys_cpuid_t phys_id)
}
/* Validate the processor object's proc_id */
-bool acpi_processor_validate_proc_id(int proc_id);
+bool acpi_duplicate_processor_id(int proc_id);
#ifdef CONFIG_ACPI_HOTPLUG_CPU
/* Arch dependent functions for cpu hotplug support */
int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id,
int *pcpu);
int acpi_unmap_cpu(int cpu);
-int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid);
#endif /* CONFIG_ACPI_HOTPLUG_CPU */
-void acpi_set_processor_mapping(void);
-
#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr);
#endif
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 796016e..5a7da60 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -435,7 +435,6 @@ struct request_queue {
struct delayed_work delay_work;
struct backing_dev_info *backing_dev_info;
- struct disk_devt *disk_devt;
/*
* The queue owner gets to use this for whatever they like.
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 909fc03..bbb513d 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -35,6 +35,7 @@ struct bpf_map_ops {
void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file,
int fd);
void (*map_fd_put_ptr)(void *ptr);
+ u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf);
};
struct bpf_map {
@@ -49,6 +50,7 @@ struct bpf_map {
const struct bpf_map_ops *ops;
struct work_struct work;
atomic_t usercnt;
+ struct bpf_map *inner_map_meta;
};
struct bpf_map_type_list {
@@ -167,6 +169,8 @@ struct bpf_verifier_ops {
const struct bpf_insn *src,
struct bpf_insn *dst,
struct bpf_prog *prog);
+ int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr,
+ union bpf_attr __user *uattr);
};
struct bpf_prog_type_list {
@@ -231,6 +235,11 @@ typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src,
u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy);
+int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
+ union bpf_attr __user *uattr);
+int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
+ union bpf_attr __user *uattr);
+
#ifdef CONFIG_BPF_SYSCALL
DECLARE_PER_CPU(int, bpf_prog_active);
@@ -275,6 +284,8 @@ int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value);
int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
void *key, void *value, u64 map_flags);
void bpf_fd_array_map_clear(struct bpf_map *map);
+int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
+ void *key, void *value, u64 map_flags);
/* memcpy that is used with 8-byte aligned pointers, power-of-8 size and
* forced to use 'long' read/writes to try to atomically copy long counters.
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index a13b031..5efb4db 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -66,7 +66,10 @@ struct bpf_verifier_state_list {
};
struct bpf_insn_aux_data {
- enum bpf_reg_type ptr_type; /* pointer type for load/store insns */
+ union {
+ enum bpf_reg_type ptr_type; /* pointer type for load/store insns */
+ struct bpf_map *map_ptr; /* pointer for call insn into lookup_elem */
+ };
};
#define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 55e5171..abcda9b 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -25,6 +25,9 @@
#define PHY_ID_BCM57780 0x03625d90
#define PHY_ID_BCM7250 0xae025280
+#define PHY_ID_BCM7260 0xae025190
+#define PHY_ID_BCM7268 0xae025090
+#define PHY_ID_BCM7271 0xae0253b0
#define PHY_ID_BCM7278 0xae0251a0
#define PHY_ID_BCM7364 0xae025260
#define PHY_ID_BCM7366 0x600d8490
diff --git a/include/linux/can/core.h b/include/linux/can/core.h
index df08a41..319a0da 100644
--- a/include/linux/can/core.h
+++ b/include/linux/can/core.h
@@ -45,12 +45,13 @@ struct can_proto {
extern int can_proto_register(const struct can_proto *cp);
extern void can_proto_unregister(const struct can_proto *cp);
-int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
+int can_rx_register(struct net *net, struct net_device *dev,
+ canid_t can_id, canid_t mask,
void (*func)(struct sk_buff *, void *),
void *data, char *ident, struct sock *sk);
-extern void can_rx_unregister(struct net_device *dev, canid_t can_id,
- canid_t mask,
+extern void can_rx_unregister(struct net *net, struct net_device *dev,
+ canid_t can_id, canid_t mask,
void (*func)(struct sk_buff *, void *),
void *data);
diff --git a/include/linux/can/platform/ti_hecc.h b/include/linux/can/platform/ti_hecc.h
deleted file mode 100644
index a52f47c..0000000
--- a/include/linux/can/platform/ti_hecc.h
+++ /dev/null
@@ -1,44 +0,0 @@
-#ifndef _CAN_PLATFORM_TI_HECC_H
-#define _CAN_PLATFORM_TI_HECC_H
-
-/*
- * TI HECC (High End CAN Controller) driver platform header
- *
- * Copyright (C) 2009 Texas Instruments Incorporated - http://www.ti.com/
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed as is WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- */
-
-/**
- * struct hecc_platform_data - HECC Platform Data
- *
- * @scc_hecc_offset: mostly 0 - should really never change
- * @scc_ram_offset: SCC RAM offset
- * @hecc_ram_offset: HECC RAM offset
- * @mbx_offset: Mailbox RAM offset
- * @int_line: Interrupt line to use - 0 or 1
- * @version: version for future use
- * @transceiver_switch: platform specific callback fn for transceiver control
- *
- * Platform data structure to get all platform specific settings.
- * this structure also accounts the fact that the IP may have different
- * RAM and mailbox offsets for different SOC's
- */
-struct ti_hecc_platform_data {
- u32 scc_hecc_offset;
- u32 scc_ram_offset;
- u32 hecc_ram_offset;
- u32 mbx_offset;
- u32 int_line;
- u32 version;
- void (*transceiver_switch) (int);
-};
-#endif /* !_CAN_PLATFORM_TI_HECC_H */
diff --git a/include/linux/ccp.h b/include/linux/ccp.h
index c71dd8f..c41b8d99 100644
--- a/include/linux/ccp.h
+++ b/include/linux/ccp.h
@@ -556,7 +556,7 @@ enum ccp_engine {
* struct ccp_cmd - CCP operation request
* @entry: list element (ccp driver use only)
* @work: work element used for callbacks (ccp driver use only)
- * @ccp: CCP device to be run on (ccp driver use only)
+ * @ccp: CCP device to be run on
* @ret: operation return code (ccp driver use only)
* @flags: cmd processing flags
* @engine: CCP operation to perform
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 1816c5e..88cd5dc 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -48,6 +48,7 @@ struct ceph_options {
unsigned long mount_timeout; /* jiffies */
unsigned long osd_idle_ttl; /* jiffies */
unsigned long osd_keepalive_timeout; /* jiffies */
+ unsigned long osd_request_timeout; /* jiffies */
/*
* any type that can't be simply compared or doesn't need need
@@ -68,6 +69,7 @@ struct ceph_options {
#define CEPH_MOUNT_TIMEOUT_DEFAULT msecs_to_jiffies(60 * 1000)
#define CEPH_OSD_KEEPALIVE_DEFAULT msecs_to_jiffies(5 * 1000)
#define CEPH_OSD_IDLE_TTL_DEFAULT msecs_to_jiffies(60 * 1000)
+#define CEPH_OSD_REQUEST_TIMEOUT_DEFAULT 0 /* no timeout */
#define CEPH_MONC_HUNT_INTERVAL msecs_to_jiffies(3 * 1000)
#define CEPH_MONC_PING_INTERVAL msecs_to_jiffies(10 * 1000)
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 2ea0c28..c125b5d 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -189,6 +189,7 @@ struct ceph_osd_request {
/* internal */
unsigned long r_stamp; /* jiffies, send or check time */
+ unsigned long r_start_stamp; /* jiffies */
int r_attempts;
struct ceph_eversion r_replay_version; /* aka reassert_version */
u32 r_last_force_resend;
diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index 5d3053c..6d7edc3 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -229,7 +229,7 @@ static inline void tick_setup_hrtimer_broadcast(void) { }
#ifdef CONFIG_CLKEVT_PROBE
extern int clockevent_probe(void);
-#els
+#else
static inline int clockevent_probe(void) { return 0; }
#endif
diff --git a/include/linux/dccp.h b/include/linux/dccp.h
index 61d042b..6844929 100644
--- a/include/linux/dccp.h
+++ b/include/linux/dccp.h
@@ -163,6 +163,7 @@ struct dccp_request_sock {
__u64 dreq_isr;
__u64 dreq_gsr;
__be32 dreq_service;
+ spinlock_t dreq_lock;
struct list_head dreq_featneg;
__u32 dreq_timestamp_echo;
__u32 dreq_timestamp_time;
diff --git a/include/linux/device.h b/include/linux/device.h
index 30c4570e..9ef518a 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1140,7 +1140,6 @@ static inline bool device_supports_offline(struct device *dev)
extern void lock_device_hotplug(void);
extern void unlock_device_hotplug(void);
extern int lock_device_hotplug_sysfs(void);
-void assert_held_device_hotplug(void);
extern int device_offline(struct device *dev);
extern int device_online(struct device *dev);
extern void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode);
diff --git a/include/linux/errqueue.h b/include/linux/errqueue.h
index 9ca23fc..6fdfc88 100644
--- a/include/linux/errqueue.h
+++ b/include/linux/errqueue.h
@@ -20,6 +20,8 @@ struct sock_exterr_skb {
struct sock_extended_err ee;
u16 addr_offset;
__be16 port;
+ u8 opt_stats:1,
+ unused:7;
};
#endif
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index c62b709..2d9f808 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -447,21 +447,6 @@ static inline void eth_addr_dec(u8 *addr)
}
/**
- * ether_addr_greater - Compare two Ethernet addresses
- * @addr1: Pointer to a six-byte array containing the Ethernet address
- * @addr2: Pointer other six-byte array containing the Ethernet address
- *
- * Compare two Ethernet addresses, returns true addr1 is greater than addr2
- */
-static inline bool ether_addr_greater(const u8 *addr1, const u8 *addr2)
-{
- u64 u1 = ether_addr_to_u64(addr1);
- u64 u2 = ether_addr_to_u64(addr2);
-
- return u1 > u2;
-}
-
-/**
* is_etherdev_addr - Tell if given Ethernet address belongs to the device.
* @dev: Pointer to a device structure
* @addr: Pointer to a six-byte array containing the Ethernet address
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 9ded8c6..83cc986 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -60,6 +60,7 @@ enum ethtool_phys_id_state {
enum {
ETH_RSS_HASH_TOP_BIT, /* Configurable RSS hash function - Toeplitz */
ETH_RSS_HASH_XOR_BIT, /* Configurable RSS hash function - Xor */
+ ETH_RSS_HASH_CRC32_BIT, /* Configurable RSS hash function - Crc32 */
/*
* Add your fresh new hash function bits above and remember to update
@@ -73,6 +74,7 @@ enum {
#define ETH_RSS_HASH_TOP __ETH_RSS_HASH(TOP)
#define ETH_RSS_HASH_XOR __ETH_RSS_HASH(XOR)
+#define ETH_RSS_HASH_CRC32 __ETH_RSS_HASH(CRC32)
#define ETH_RSS_HASH_UNKNOWN 0
#define ETH_RSS_HASH_NO_CHANGE 0
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 0c167fd..511fe91 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -7,6 +7,7 @@
#include <stdarg.h>
#include <linux/atomic.h>
+#include <linux/refcount.h>
#include <linux/compat.h>
#include <linux/skbuff.h>
#include <linux/linkage.h>
@@ -409,6 +410,7 @@ struct bpf_prog {
u16 pages; /* Number of allocated pages */
kmemcheck_bitfield_begin(meta);
u16 jited:1, /* Is our filter JIT'ed? */
+ locked:1, /* Program image locked? */
gpl_compatible:1, /* Is filter GPL compatible? */
cb_access:1, /* Is control block accessed? */
dst_needed:1, /* Do we need dst entry? */
@@ -429,7 +431,7 @@ struct bpf_prog {
};
struct sk_filter {
- atomic_t refcnt;
+ refcount_t refcnt;
struct rcu_head rcu;
struct bpf_prog *prog;
};
@@ -554,22 +556,29 @@ static inline bool bpf_prog_was_classic(const struct bpf_prog *prog)
#ifdef CONFIG_ARCH_HAS_SET_MEMORY
static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
{
- set_memory_ro((unsigned long)fp, fp->pages);
+ fp->locked = 1;
+ WARN_ON_ONCE(set_memory_ro((unsigned long)fp, fp->pages));
}
static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
{
- set_memory_rw((unsigned long)fp, fp->pages);
+ if (fp->locked) {
+ WARN_ON_ONCE(set_memory_rw((unsigned long)fp, fp->pages));
+ /* In case set_memory_rw() fails, we want to be the first
+ * to crash here instead of some random place later on.
+ */
+ fp->locked = 0;
+ }
}
static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
{
- set_memory_ro((unsigned long)hdr, hdr->pages);
+ WARN_ON_ONCE(set_memory_ro((unsigned long)hdr, hdr->pages));
}
static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
{
- set_memory_rw((unsigned long)hdr, hdr->pages);
+ WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages));
}
#else
static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
@@ -685,6 +694,11 @@ static inline bool bpf_jit_is_ebpf(void)
# endif
}
+static inline bool ebpf_jit_enabled(void)
+{
+ return bpf_jit_enable && bpf_jit_is_ebpf();
+}
+
static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp)
{
return fp->jited && bpf_jit_is_ebpf();
@@ -745,6 +759,11 @@ void bpf_prog_kallsyms_del(struct bpf_prog *fp);
#else /* CONFIG_BPF_JIT */
+static inline bool ebpf_jit_enabled(void)
+{
+ return false;
+}
+
static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp)
{
return false;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index aad3fd0..7251f7b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2678,7 +2678,7 @@ static const char * const kernel_read_file_str[] = {
static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id)
{
- if (id < 0 || id >= READING_MAX_ID)
+ if ((unsigned)id >= READING_MAX_ID)
return kernel_read_file_str[READING_UNKNOWN];
return kernel_read_file_str[id];
diff --git a/include/linux/fscrypt_common.h b/include/linux/fscrypt_common.h
index 547f815..10c1abf 100644
--- a/include/linux/fscrypt_common.h
+++ b/include/linux/fscrypt_common.h
@@ -87,7 +87,6 @@ struct fscrypt_operations {
unsigned int flags;
const char *key_prefix;
int (*get_context)(struct inode *, void *, size_t);
- int (*prepare_context)(struct inode *);
int (*set_context)(struct inode *, const void *, size_t, void *);
int (*dummy_context)(struct inode *);
bool (*is_encrypted)(struct inode *);
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index a999d28..76f3975 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -167,13 +167,6 @@ struct blk_integrity {
};
#endif /* CONFIG_BLK_DEV_INTEGRITY */
-struct disk_devt {
- atomic_t count;
- void (*release)(struct disk_devt *disk_devt);
-};
-
-void put_disk_devt(struct disk_devt *disk_devt);
-void get_disk_devt(struct disk_devt *disk_devt);
struct gendisk {
/* major, first_minor and minors are input parameters only,
@@ -183,7 +176,6 @@ struct gendisk {
int first_minor;
int minors; /* maximum number of minors, =1 for
* disks that can't be partitioned. */
- struct disk_devt *disk_devt;
char disk_name[DISK_NAME_LEN]; /* name of major driver */
char *(*devnode)(struct gendisk *gd, umode_t *mode);
diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index 2484b2f..933d936 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -143,15 +143,6 @@ struct gpio_desc *devm_fwnode_get_index_gpiod_from_child(struct device *dev,
struct fwnode_handle *child,
enum gpiod_flags flags,
const char *label);
-/* FIXME: delete this helper when users are switched over */
-static inline struct gpio_desc *devm_get_gpiod_from_child(struct device *dev,
- const char *con_id, struct fwnode_handle *child)
-{
- return devm_fwnode_get_index_gpiod_from_child(dev, con_id,
- 0, child,
- GPIOD_ASIS,
- "?");
-}
#else /* CONFIG_GPIOLIB */
@@ -444,13 +435,6 @@ struct gpio_desc *devm_fwnode_get_index_gpiod_from_child(struct device *dev,
return ERR_PTR(-ENOSYS);
}
-/* FIXME: delete this when all users are switched over */
-static inline struct gpio_desc *devm_get_gpiod_from_child(struct device *dev,
- const char *con_id, struct fwnode_handle *child)
-{
- return ERR_PTR(-ENOSYS);
-}
-
#endif /* CONFIG_GPIOLIB */
static inline
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 503099d..b857fc8 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -122,7 +122,7 @@ struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
pud_t *pud, int flags);
int pmd_huge(pmd_t pmd);
-int pud_huge(pud_t pmd);
+int pud_huge(pud_t pud);
unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
unsigned long address, unsigned long end, pgprot_t newprot);
@@ -197,6 +197,9 @@ static inline void __unmap_hugepage_range(struct mmu_gather *tlb,
#ifndef pgd_huge
#define pgd_huge(x) 0
#endif
+#ifndef p4d_huge
+#define p4d_huge(x) 0
+#endif
#ifndef pgd_write
static inline int pgd_write(pgd_t pgd)
diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h
index 78d59db..88b6737 100644
--- a/include/linux/hwmon.h
+++ b/include/linux/hwmon.h
@@ -88,6 +88,7 @@ enum hwmon_temp_attributes {
#define HWMON_T_CRIT_HYST BIT(hwmon_temp_crit_hyst)
#define HWMON_T_EMERGENCY BIT(hwmon_temp_emergency)
#define HWMON_T_EMERGENCY_HYST BIT(hwmon_temp_emergency_hyst)
+#define HWMON_T_ALARM BIT(hwmon_temp_alarm)
#define HWMON_T_MIN_ALARM BIT(hwmon_temp_min_alarm)
#define HWMON_T_MAX_ALARM BIT(hwmon_temp_max_alarm)
#define HWMON_T_CRIT_ALARM BIT(hwmon_temp_crit_alarm)
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 3616248..0c170a3 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -845,6 +845,13 @@ struct vmbus_channel {
* link up channels based on their CPU affinity.
*/
struct list_head percpu_list;
+
+ /*
+ * Defer freeing channel until after all cpu's have
+ * gone through grace period.
+ */
+ struct rcu_head rcu;
+
/*
* For performance critical channels (storage, networking
* etc,), Hyper-V has a mechanism to enhance the throughput
@@ -1430,9 +1437,6 @@ extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf,
const int *srv_version, int srv_vercnt,
int *nego_fw_version, int *nego_srv_version);
-void hv_event_tasklet_disable(struct vmbus_channel *channel);
-void hv_event_tasklet_enable(struct vmbus_channel *channel);
-
void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid);
void vmbus_setevent(struct vmbus_channel *channel);
diff --git a/include/linux/iio/sw_device.h b/include/linux/iio/sw_device.h
index 23ca415..fa79319 100644
--- a/include/linux/iio/sw_device.h
+++ b/include/linux/iio/sw_device.h
@@ -62,7 +62,7 @@ void iio_swd_group_init_type_name(struct iio_sw_device *d,
const char *name,
struct config_item_type *type)
{
-#ifdef CONFIG_CONFIGFS_FS
+#if IS_ENABLED(CONFIG_CONFIGFS_FS)
config_group_init_type_name(&d->group, name, type);
#endif
}
diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index ee971f3..a2e9d6e 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -153,8 +153,8 @@ struct in_ifaddr {
int register_inetaddr_notifier(struct notifier_block *nb);
int unregister_inetaddr_notifier(struct notifier_block *nb);
-void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
- struct ipv4_devconf *devconf);
+void inet_netconf_notify_devconf(struct net *net, int event, int type,
+ int ifindex, struct ipv4_devconf *devconf);
struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref);
static inline struct net_device *ip_dev_find(struct net *net, __be32 addr)
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 6a6de18..2e4de0d 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -125,9 +125,16 @@ enum iommu_attr {
};
/* These are the possible reserved region types */
-#define IOMMU_RESV_DIRECT (1 << 0)
-#define IOMMU_RESV_RESERVED (1 << 1)
-#define IOMMU_RESV_MSI (1 << 2)
+enum iommu_resv_type {
+ /* Memory regions which must be mapped 1:1 at all times */
+ IOMMU_RESV_DIRECT,
+ /* Arbitrary "never map this or give it to a device" address ranges */
+ IOMMU_RESV_RESERVED,
+ /* Hardware MSI region (untranslated) */
+ IOMMU_RESV_MSI,
+ /* Software-managed MSI translation window */
+ IOMMU_RESV_SW_MSI,
+};
/**
* struct iommu_resv_region - descriptor for a reserved memory region
@@ -142,7 +149,7 @@ struct iommu_resv_region {
phys_addr_t start;
size_t length;
int prot;
- int type;
+ enum iommu_resv_type type;
};
#ifdef CONFIG_IOMMU_API
@@ -288,7 +295,8 @@ extern void iommu_get_resv_regions(struct device *dev, struct list_head *list);
extern void iommu_put_resv_regions(struct device *dev, struct list_head *list);
extern int iommu_request_dm_for_dev(struct device *dev);
extern struct iommu_resv_region *
-iommu_alloc_resv_region(phys_addr_t start, size_t length, int prot, int type);
+iommu_alloc_resv_region(phys_addr_t start, size_t length, int prot,
+ enum iommu_resv_type type);
extern int iommu_get_group_resv_regions(struct iommu_group *group,
struct list_head *head);
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index f0d79bd..e1b4429 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -37,6 +37,7 @@ struct ipv6_devconf {
__s32 accept_ra_rtr_pref;
__s32 rtr_probe_interval;
#ifdef CONFIG_IPV6_ROUTE_INFO
+ __s32 accept_ra_rt_info_min_plen;
__s32 accept_ra_rt_info_max_plen;
#endif
#endif
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 672cfef..97cbca1 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -373,6 +373,8 @@
#define ICC_IGRPEN0_EL1_MASK (1 << ICC_IGRPEN0_EL1_SHIFT)
#define ICC_IGRPEN1_EL1_SHIFT 0
#define ICC_IGRPEN1_EL1_MASK (1 << ICC_IGRPEN1_EL1_SHIFT)
+#define ICC_SRE_EL1_DIB (1U << 2)
+#define ICC_SRE_EL1_DFB (1U << 1)
#define ICC_SRE_EL1_SRE (1U << 0)
/*
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 188eced..9f36160 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -524,6 +524,10 @@ static inline struct irq_domain *irq_find_matching_fwnode(
{
return NULL;
}
+static inline bool irq_domain_check_msi_remap(void)
+{
+ return false;
+}
#endif /* !CONFIG_IRQ_DOMAIN */
#endif /* _LINUX_IRQDOMAIN_H */
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 8e06d75..2afd74b 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -90,6 +90,13 @@ extern bool static_key_initialized;
struct static_key {
atomic_t enabled;
/*
+ * Note:
+ * To make anonymous unions work with old compilers, the static
+ * initialization of them requires brackets. This creates a dependency
+ * on the order of the struct with the initializers. If any fields
+ * are added, STATIC_KEY_INIT_TRUE and STATIC_KEY_INIT_FALSE may need
+ * to be modified.
+ *
* bit 0 => 1 if key is initially true
* 0 if initially false
* bit 1 => 1 if points to struct static_key_mod
@@ -166,10 +173,10 @@ extern void static_key_disable(struct static_key *key);
*/
#define STATIC_KEY_INIT_TRUE \
{ .enabled = { 1 }, \
- .entries = (void *)JUMP_TYPE_TRUE }
+ { .entries = (void *)JUMP_TYPE_TRUE } }
#define STATIC_KEY_INIT_FALSE \
{ .enabled = { 0 }, \
- .entries = (void *)JUMP_TYPE_FALSE }
+ { .entries = (void *)JUMP_TYPE_FALSE } }
#else /* !HAVE_JUMP_LABEL */
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index ceb3fe7..a5c7046 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -6,6 +6,7 @@
struct kmem_cache;
struct page;
struct vm_struct;
+struct task_struct;
#ifdef CONFIG_KASAN
@@ -18,6 +19,7 @@ extern unsigned char kasan_zero_page[PAGE_SIZE];
extern pte_t kasan_zero_pte[PTRS_PER_PTE];
extern pmd_t kasan_zero_pmd[PTRS_PER_PMD];
extern pud_t kasan_zero_pud[PTRS_PER_PUD];
+extern p4d_t kasan_zero_p4d[PTRS_PER_P4D];
void kasan_populate_zero_shadow(const void *shadow_start,
const void *shadow_end);
@@ -74,6 +76,9 @@ size_t ksize(const void *);
static inline void kasan_unpoison_slab(const void *ptr) { ksize(ptr); }
size_t kasan_metadata_size(struct kmem_cache *cache);
+bool kasan_save_enable_multi_shot(void);
+void kasan_restore_multi_shot(bool enabled);
+
#else /* CONFIG_KASAN */
static inline void kasan_unpoison_shadow(const void *address, size_t size) {}
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 2c14ad9..d025074 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -162,8 +162,8 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
int len, void *val);
int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
int len, struct kvm_io_device *dev);
-int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
- struct kvm_io_device *dev);
+void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
+ struct kvm_io_device *dev);
struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
gpa_t addr);
diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h
index b01fe10..87ff4f5 100644
--- a/include/linux/list_nulls.h
+++ b/include/linux/list_nulls.h
@@ -29,6 +29,11 @@ struct hlist_nulls_node {
((ptr)->first = (struct hlist_nulls_node *) NULLS_MARKER(nulls))
#define hlist_nulls_entry(ptr, type, member) container_of(ptr,type,member)
+
+#define hlist_nulls_entry_safe(ptr, type, member) \
+ ({ typeof(ptr) ____ptr = (ptr); \
+ !is_a_nulls(____ptr) ? hlist_nulls_entry(____ptr, type, member) : NULL; \
+ })
/**
* ptr_is_a_nulls - Test if a ptr is a nulls
* @ptr: ptr to be tested
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 5af3773..bb7250c 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -740,6 +740,12 @@ static inline bool mem_cgroup_oom_synchronize(bool wait)
return false;
}
+static inline void mem_cgroup_update_page_stat(struct page *page,
+ enum mem_cgroup_stat_index idx,
+ int nr)
+{
+}
+
static inline void mem_cgroup_inc_page_stat(struct page *page,
enum mem_cgroup_stat_index idx)
{
diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h
index 7a01c94..3eef9fb 100644
--- a/include/linux/mfd/cros_ec.h
+++ b/include/linux/mfd/cros_ec.h
@@ -35,10 +35,11 @@
* Max bus-specific overhead incurred by request/responses.
* I2C requires 1 additional byte for requests.
* I2C requires 2 additional bytes for responses.
+ * SPI requires up to 32 additional bytes for responses.
* */
#define EC_PROTO_VERSION_UNKNOWN 0
#define EC_MAX_REQUEST_OVERHEAD 1
-#define EC_MAX_RESPONSE_OVERHEAD 2
+#define EC_MAX_RESPONSE_OVERHEAD 32
/*
* Command interface between EC and AP, for LPC, I2C and SPI interfaces.
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 7e66e4f..1beb1ec 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -476,6 +476,7 @@ enum {
enum {
MLX4_INTERFACE_STATE_UP = 1 << 0,
MLX4_INTERFACE_STATE_DELETION = 1 << 1,
+ MLX4_INTERFACE_STATE_NOWAIT = 1 << 2,
};
#define MSTR_SM_CHANGE_MASK (MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK | \
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 2fcff6b..f508646 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -728,6 +728,7 @@ struct mlx5e_resources {
u32 pdn;
struct mlx5_td td;
struct mlx5_core_mkey mkey;
+ struct mlx5_sq_bfreg bfreg;
};
struct mlx5_core_dev {
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 949b24b..ae91a4b 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -134,8 +134,13 @@ struct mlx5_flow_act {
u32 action;
u32 flow_tag;
u32 encap_id;
+ u32 modify_id;
};
+#define MLX5_DECLARE_FLOW_ACT(name) \
+ struct mlx5_flow_act name = {MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,\
+ MLX5_FS_DEFAULT_FLOW_TAG, 0, 0}
+
/* Single destination per rule.
* Group ID is implied by the match criteria.
*/
@@ -156,5 +161,4 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging);
void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter);
void mlx5_fc_query_cached(struct mlx5_fc *counter,
u64 *bytes, u64 *packets, u64 *lastuse);
-
#endif
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 8382426..1993adb 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -227,6 +227,8 @@ enum {
MLX5_CMD_OP_MODIFY_FLOW_TABLE = 0x93c,
MLX5_CMD_OP_ALLOC_ENCAP_HEADER = 0x93d,
MLX5_CMD_OP_DEALLOC_ENCAP_HEADER = 0x93e,
+ MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT = 0x940,
+ MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT = 0x941,
MLX5_CMD_OP_MAX
};
@@ -302,7 +304,8 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
u8 reserved_at_20[0x2];
u8 log_max_ft_size[0x6];
- u8 reserved_at_28[0x10];
+ u8 log_max_modify_header_context[0x8];
+ u8 max_modify_header_actions[0x8];
u8 max_ft_level[0x8];
u8 reserved_at_40[0x20];
@@ -2190,6 +2193,7 @@ enum {
MLX5_FLOW_CONTEXT_ACTION_COUNT = 0x8,
MLX5_FLOW_CONTEXT_ACTION_ENCAP = 0x10,
MLX5_FLOW_CONTEXT_ACTION_DECAP = 0x20,
+ MLX5_FLOW_CONTEXT_ACTION_MOD_HDR = 0x40,
};
struct mlx5_ifc_flow_context_bits {
@@ -2211,7 +2215,9 @@ struct mlx5_ifc_flow_context_bits {
u8 encap_id[0x20];
- u8 reserved_at_e0[0x120];
+ u8 modify_header_id[0x20];
+
+ u8 reserved_at_100[0x100];
struct mlx5_ifc_fte_match_param_bits match_value;
@@ -4534,6 +4540,109 @@ struct mlx5_ifc_dealloc_encap_header_in_bits {
u8 reserved_60[0x20];
};
+struct mlx5_ifc_set_action_in_bits {
+ u8 action_type[0x4];
+ u8 field[0xc];
+ u8 reserved_at_10[0x3];
+ u8 offset[0x5];
+ u8 reserved_at_18[0x3];
+ u8 length[0x5];
+
+ u8 data[0x20];
+};
+
+struct mlx5_ifc_add_action_in_bits {
+ u8 action_type[0x4];
+ u8 field[0xc];
+ u8 reserved_at_10[0x10];
+
+ u8 data[0x20];
+};
+
+union mlx5_ifc_set_action_in_add_action_in_auto_bits {
+ struct mlx5_ifc_set_action_in_bits set_action_in;
+ struct mlx5_ifc_add_action_in_bits add_action_in;
+ u8 reserved_at_0[0x40];
+};
+
+enum {
+ MLX5_ACTION_TYPE_SET = 0x1,
+ MLX5_ACTION_TYPE_ADD = 0x2,
+};
+
+enum {
+ MLX5_ACTION_IN_FIELD_OUT_SMAC_47_16 = 0x1,
+ MLX5_ACTION_IN_FIELD_OUT_SMAC_15_0 = 0x2,
+ MLX5_ACTION_IN_FIELD_OUT_ETHERTYPE = 0x3,
+ MLX5_ACTION_IN_FIELD_OUT_DMAC_47_16 = 0x4,
+ MLX5_ACTION_IN_FIELD_OUT_DMAC_15_0 = 0x5,
+ MLX5_ACTION_IN_FIELD_OUT_IP_DSCP = 0x6,
+ MLX5_ACTION_IN_FIELD_OUT_TCP_FLAGS = 0x7,
+ MLX5_ACTION_IN_FIELD_OUT_TCP_SPORT = 0x8,
+ MLX5_ACTION_IN_FIELD_OUT_TCP_DPORT = 0x9,
+ MLX5_ACTION_IN_FIELD_OUT_IP_TTL = 0xa,
+ MLX5_ACTION_IN_FIELD_OUT_UDP_SPORT = 0xb,
+ MLX5_ACTION_IN_FIELD_OUT_UDP_DPORT = 0xc,
+ MLX5_ACTION_IN_FIELD_OUT_SIPV6_127_96 = 0xd,
+ MLX5_ACTION_IN_FIELD_OUT_SIPV6_95_64 = 0xe,
+ MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32 = 0xf,
+ MLX5_ACTION_IN_FIELD_OUT_SIPV6_31_0 = 0x10,
+ MLX5_ACTION_IN_FIELD_OUT_DIPV6_127_96 = 0x11,
+ MLX5_ACTION_IN_FIELD_OUT_DIPV6_95_64 = 0x12,
+ MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32 = 0x13,
+ MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0 = 0x14,
+ MLX5_ACTION_IN_FIELD_OUT_SIPV4 = 0x15,
+ MLX5_ACTION_IN_FIELD_OUT_DIPV4 = 0x16,
+};
+
+struct mlx5_ifc_alloc_modify_header_context_out_bits {
+ u8 status[0x8];
+ u8 reserved_at_8[0x18];
+
+ u8 syndrome[0x20];
+
+ u8 modify_header_id[0x20];
+
+ u8 reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_alloc_modify_header_context_in_bits {
+ u8 opcode[0x10];
+ u8 reserved_at_10[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 op_mod[0x10];
+
+ u8 reserved_at_40[0x20];
+
+ u8 table_type[0x8];
+ u8 reserved_at_68[0x10];
+ u8 num_of_actions[0x8];
+
+ union mlx5_ifc_set_action_in_add_action_in_auto_bits actions[0];
+};
+
+struct mlx5_ifc_dealloc_modify_header_context_out_bits {
+ u8 status[0x8];
+ u8 reserved_at_8[0x18];
+
+ u8 syndrome[0x20];
+
+ u8 reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_dealloc_modify_header_context_in_bits {
+ u8 opcode[0x10];
+ u8 reserved_at_10[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 op_mod[0x10];
+
+ u8 modify_header_id[0x20];
+
+ u8 reserved_at_60[0x20];
+};
+
struct mlx5_ifc_query_dct_out_bits {
u8 status[0x8];
u8 reserved_at_8[0x18];
@@ -5013,6 +5122,7 @@ struct mlx5_ifc_modify_rq_out_bits {
enum {
MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_VSD = 1ULL << 1,
+ MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_SCATTER_FCS = 1ULL << 2,
MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_RQ_COUNTER_SET_ID = 1ULL << 3,
};
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0d65dd7..00a8fa7 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -32,6 +32,8 @@ struct user_struct;
struct writeback_control;
struct bdi_writeback;
+void init_mm_internals(void);
+
#ifndef CONFIG_NEED_MULTIPLE_NODES /* Don't use mapnrs, do it properly */
extern unsigned long max_mapnr;
@@ -1560,14 +1562,24 @@ static inline pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr,
return ptep;
}
-#ifdef __PAGETABLE_PUD_FOLDED
-static inline int __pud_alloc(struct mm_struct *mm, pgd_t *pgd,
+#ifdef __PAGETABLE_P4D_FOLDED
+static inline int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd,
unsigned long address)
{
return 0;
}
#else
-int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address);
+int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address);
+#endif
+
+#ifdef __PAGETABLE_PUD_FOLDED
+static inline int __pud_alloc(struct mm_struct *mm, p4d_t *p4d,
+ unsigned long address)
+{
+ return 0;
+}
+#else
+int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address);
#endif
#if defined(__PAGETABLE_PMD_FOLDED) || !defined(CONFIG_MMU)
@@ -1619,12 +1631,23 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address);
* Remove it when 4level-fixup.h has been removed.
*/
#if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK)
-static inline pud_t *pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+
+#ifndef __ARCH_HAS_5LEVEL_HACK
+static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd,
+ unsigned long address)
{
- return (unlikely(pgd_none(*pgd)) && __pud_alloc(mm, pgd, address))?
- NULL: pud_offset(pgd, address);
+ return (unlikely(pgd_none(*pgd)) && __p4d_alloc(mm, pgd, address)) ?
+ NULL : p4d_offset(pgd, address);
}
+static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d,
+ unsigned long address)
+{
+ return (unlikely(p4d_none(*p4d)) && __pud_alloc(mm, p4d, address)) ?
+ NULL : pud_offset(p4d, address);
+}
+#endif /* !__ARCH_HAS_5LEVEL_HACK */
+
static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
{
return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))?
@@ -2385,7 +2408,8 @@ void sparse_mem_maps_populate_node(struct page **map_map,
struct page *sparse_mem_map_populate(unsigned long pnum, int nid);
pgd_t *vmemmap_pgd_populate(unsigned long addr, int node);
-pud_t *vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node);
+p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node);
+pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node);
pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node);
pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node);
void *vmemmap_alloc_block(unsigned long size, int node);
diff --git a/include/linux/net.h b/include/linux/net.h
index cd0c8bd..a42fab2 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -146,7 +146,7 @@ struct proto_ops {
int (*socketpair)(struct socket *sock1,
struct socket *sock2);
int (*accept) (struct socket *sock,
- struct socket *newsock, int flags);
+ struct socket *newsock, int flags, bool kern);
int (*getname) (struct socket *sock,
struct sockaddr *addr,
int *sockaddr_len, int peer);
@@ -298,6 +298,9 @@ int kernel_sendpage(struct socket *sock, struct page *page, int offset,
int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg);
int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how);
+/* Following routine returns the IP overhead imposed by a socket. */
+u32 kernel_sock_ip_overhead(struct sock *sk);
+
#define MODULE_ALIAS_NETPROTO(proto) \
MODULE_ALIAS("net-pf-" __stringify(proto))
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 97456b25..cc07c3b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -41,7 +41,6 @@
#include <linux/ethtool.h>
#include <net/net_namespace.h>
-#include <net/dsa.h>
#ifdef CONFIG_DCB
#include <net/dcbnl.h>
#endif
@@ -57,6 +56,8 @@
struct netpoll_info;
struct device;
struct phy_device;
+struct dsa_switch_tree;
+
/* 802.11 specific */
struct wireless_dev;
/* 802.15.4 specific */
@@ -786,11 +787,11 @@ struct tc_cls_u32_offload;
struct tc_to_netdev {
unsigned int type;
union {
- u8 tc;
struct tc_cls_u32_offload *cls_u32;
struct tc_cls_flower_offload *cls_flower;
struct tc_cls_matchall_offload *cls_mall;
struct tc_cls_bpf_offload *cls_bpf;
+ struct tc_mqprio_qopt *mqprio;
};
bool egress_dev;
};
@@ -2004,15 +2005,6 @@ void dev_net_set(struct net_device *dev, struct net *net)
write_pnet(&dev->nd_net, net);
}
-static inline bool netdev_uses_dsa(struct net_device *dev)
-{
-#if IS_ENABLED(CONFIG_NET_DSA)
- if (dev->dsa_ptr != NULL)
- return dsa_uses_tagged_protocol(dev->dsa_ptr);
-#endif
- return false;
-}
-
/**
* netdev_priv - access network device private data
* @dev: network device
diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h
index a58cca8..ba35ba5 100644
--- a/include/linux/of_mdio.h
+++ b/include/linux/of_mdio.h
@@ -12,7 +12,7 @@
#include <linux/phy.h>
#include <linux/of.h>
-#ifdef CONFIG_OF
+#if IS_ENABLED(CONFIG_OF_MDIO)
extern int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np);
extern struct phy_device *of_phy_find_device(struct device_node *phy_np);
extern struct phy_device *of_phy_connect(struct net_device *dev,
@@ -32,7 +32,7 @@ extern int of_phy_register_fixed_link(struct device_node *np);
extern void of_phy_deregister_fixed_link(struct device_node *np);
extern bool of_phy_is_fixed_link(struct device_node *np);
-#else /* CONFIG_OF */
+#else /* CONFIG_OF_MDIO */
static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np)
{
/*
diff --git a/include/linux/omap-gpmc.h b/include/linux/omap-gpmc.h
index 35d0fd7..fd0de00 100644
--- a/include/linux/omap-gpmc.h
+++ b/include/linux/omap-gpmc.h
@@ -76,22 +76,12 @@ struct gpmc_timings;
struct omap_nand_platform_data;
struct omap_onenand_platform_data;
-#if IS_ENABLED(CONFIG_MTD_NAND_OMAP2)
-extern int gpmc_nand_init(struct omap_nand_platform_data *d,
- struct gpmc_timings *gpmc_t);
-#else
-static inline int gpmc_nand_init(struct omap_nand_platform_data *d,
- struct gpmc_timings *gpmc_t)
-{
- return 0;
-}
-#endif
-
#if IS_ENABLED(CONFIG_MTD_ONENAND_OMAP2)
-extern void gpmc_onenand_init(struct omap_onenand_platform_data *d);
+extern int gpmc_onenand_init(struct omap_onenand_platform_data *d);
#else
#define board_onenand_data NULL
-static inline void gpmc_onenand_init(struct omap_onenand_platform_data *d)
+static inline int gpmc_onenand_init(struct omap_onenand_platform_data *d)
{
+ return 0;
}
#endif
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 43a7748..624cecf 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -587,23 +587,29 @@ struct phy_driver {
*/
void (*link_change_notify)(struct phy_device *dev);
- /* A function provided by a phy specific driver to override the
- * the PHY driver framework support for reading a MMD register
- * from the PHY. If not supported, return -1. This function is
- * optional for PHY specific drivers, if not provided then the
- * default MMD read function is used by the PHY framework.
+ /*
+ * Phy specific driver override for reading a MMD register.
+ * This function is optional for PHY specific drivers. When
+ * not provided, the default MMD read function will be used
+ * by phy_read_mmd(), which will use either a direct read for
+ * Clause 45 PHYs or an indirect read for Clause 22 PHYs.
+ * devnum is the MMD device number within the PHY device,
+ * regnum is the register within the selected MMD device.
*/
- int (*read_mmd_indirect)(struct phy_device *dev, int ptrad,
- int devnum, int regnum);
+ int (*read_mmd)(struct phy_device *dev, int devnum, u16 regnum);
- /* A function provided by a phy specific driver to override the
- * the PHY driver framework support for writing a MMD register
- * from the PHY. This function is optional for PHY specific drivers,
- * if not provided then the default MMD read function is used by
- * the PHY framework.
+ /*
+ * Phy specific driver override for writing a MMD register.
+ * This function is optional for PHY specific drivers. When
+ * not provided, the default MMD write function will be used
+ * by phy_write_mmd(), which will use either a direct write for
+ * Clause 45 PHYs, or an indirect write for Clause 22 PHYs.
+ * devnum is the MMD device number within the PHY device,
+ * regnum is the register within the selected MMD device.
+ * val is the value to be written.
*/
- void (*write_mmd_indirect)(struct phy_device *dev, int ptrad,
- int devnum, int regnum, u32 val);
+ int (*write_mmd)(struct phy_device *dev, int devnum, u16 regnum,
+ u16 val);
/* Get the size and type of the eeprom contained within a plug-in
* module */
@@ -651,25 +657,7 @@ struct phy_fixup {
*
* Same rules as for phy_read();
*/
-static inline int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum)
-{
- if (!phydev->is_c45)
- return -EOPNOTSUPP;
-
- return mdiobus_read(phydev->mdio.bus, phydev->mdio.addr,
- MII_ADDR_C45 | (devad << 16) | (regnum & 0xffff));
-}
-
-/**
- * phy_read_mmd_indirect - reads data from the MMD registers
- * @phydev: The PHY device bus
- * @prtad: MMD Address
- * @addr: PHY address on the MII bus
- *
- * Description: it reads data from the MMD registers (clause 22 to access to
- * clause 45) of the specified phy address.
- */
-int phy_read_mmd_indirect(struct phy_device *phydev, int prtad, int devad);
+int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum);
/**
* phy_read - Convenience function for reading a given PHY register
@@ -752,35 +740,29 @@ static inline bool phy_is_pseudo_fixed_link(struct phy_device *phydev)
*
* Same rules as for phy_write();
*/
-static inline int phy_write_mmd(struct phy_device *phydev, int devad,
- u32 regnum, u16 val)
-{
- if (!phydev->is_c45)
- return -EOPNOTSUPP;
-
- regnum = MII_ADDR_C45 | ((devad & 0x1f) << 16) | (regnum & 0xffff);
-
- return mdiobus_write(phydev->mdio.bus, phydev->mdio.addr, regnum, val);
-}
-
-/**
- * phy_write_mmd_indirect - writes data to the MMD registers
- * @phydev: The PHY device
- * @prtad: MMD Address
- * @devad: MMD DEVAD
- * @data: data to write in the MMD register
- *
- * Description: Write data from the MMD registers of the specified
- * phy address.
- */
-void phy_write_mmd_indirect(struct phy_device *phydev, int prtad,
- int devad, u32 data);
+int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val);
struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id,
bool is_c45,
struct phy_c45_device_ids *c45_ids);
+#if IS_ENABLED(CONFIG_PHYLIB)
struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45);
int phy_device_register(struct phy_device *phy);
+void phy_device_free(struct phy_device *phydev);
+#else
+static inline
+struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45)
+{
+ return NULL;
+}
+
+static inline int phy_device_register(struct phy_device *phy)
+{
+ return 0;
+}
+
+static inline void phy_device_free(struct phy_device *phydev) { }
+#endif /* CONFIG_PHYLIB */
void phy_device_remove(struct phy_device *phydev);
int phy_init_hw(struct phy_device *phydev);
int phy_suspend(struct phy_device *phydev);
@@ -861,7 +843,6 @@ int phy_ethtool_ksettings_set(struct phy_device *phydev,
int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd);
int phy_start_interrupts(struct phy_device *phydev);
void phy_print_status(struct phy_device *phydev);
-void phy_device_free(struct phy_device *phydev);
int phy_set_max_speed(struct phy_device *phydev, u32 max_speed);
int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask,
@@ -888,8 +869,10 @@ int phy_ethtool_set_link_ksettings(struct net_device *ndev,
const struct ethtool_link_ksettings *cmd);
int phy_ethtool_nway_reset(struct net_device *ndev);
+#if IS_ENABLED(CONFIG_PHYLIB)
int __init mdio_bus_init(void);
void mdio_bus_exit(void);
+#endif
extern struct bus_type mdio_bus_type;
@@ -900,7 +883,7 @@ struct mdio_board_info {
const void *platform_data;
};
-#if IS_ENABLED(CONFIG_PHYLIB)
+#if IS_ENABLED(CONFIG_MDIO_DEVICE)
int mdiobus_register_board_info(const struct mdio_board_info *info,
unsigned int n);
#else
diff --git a/include/linux/purgatory.h b/include/linux/purgatory.h
new file mode 100644
index 0000000..d60d4e278
--- /dev/null
+++ b/include/linux/purgatory.h
@@ -0,0 +1,23 @@
+#ifndef _LINUX_PURGATORY_H
+#define _LINUX_PURGATORY_H
+
+#include <linux/types.h>
+#include <crypto/sha.h>
+#include <uapi/linux/kexec.h>
+
+struct kexec_sha_region {
+ unsigned long start;
+ unsigned long len;
+};
+
+/*
+ * These forward declarations serve two purposes:
+ *
+ * 1) Make sparse happy when checking arch/purgatory
+ * 2) Document that these are required to be global so the symbol
+ * lookup in kexec works
+ */
+extern struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX];
+extern u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE];
+
+#endif
diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h
index 52966b9..fbab6e0 100644
--- a/include/linux/qed/common_hsi.h
+++ b/include/linux/qed/common_hsi.h
@@ -100,8 +100,8 @@
#define MAX_NUM_LL2_TX_STATS_COUNTERS 32
#define FW_MAJOR_VERSION 8
-#define FW_MINOR_VERSION 10
-#define FW_REVISION_VERSION 10
+#define FW_MINOR_VERSION 15
+#define FW_REVISION_VERSION 3
#define FW_ENGINEERING_VERSION 0
/***********************/
@@ -187,6 +187,9 @@
/* DEMS */
#define DQ_DEMS_LEGACY 0
+#define DQ_DEMS_TOE_MORE_TO_SEND 3
+#define DQ_DEMS_TOE_LOCAL_ADV_WND 4
+#define DQ_DEMS_ROCE_CQ_CONS 7
/* XCM agg val selection */
#define DQ_XCM_AGG_VAL_SEL_WORD2 0
@@ -214,6 +217,9 @@
#define DQ_XCM_ISCSI_MORE_TO_SEND_SEQ_CMD DQ_XCM_AGG_VAL_SEL_REG3
#define DQ_XCM_ISCSI_EXP_STAT_SN_CMD DQ_XCM_AGG_VAL_SEL_REG6
#define DQ_XCM_ROCE_SQ_PROD_CMD DQ_XCM_AGG_VAL_SEL_WORD4
+#define DQ_XCM_TOE_TX_BD_PROD_CMD DQ_XCM_AGG_VAL_SEL_WORD4
+#define DQ_XCM_TOE_MORE_TO_SEND_SEQ_CMD DQ_XCM_AGG_VAL_SEL_REG3
+#define DQ_XCM_TOE_LOCAL_ADV_WND_SEQ_CMD DQ_XCM_AGG_VAL_SEL_REG4
/* UCM agg val selection (HW) */
#define DQ_UCM_AGG_VAL_SEL_WORD0 0
@@ -269,6 +275,8 @@
#define DQ_XCM_ISCSI_DQ_FLUSH_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF19)
#define DQ_XCM_ISCSI_SLOW_PATH_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF22)
#define DQ_XCM_ISCSI_PROC_ONLY_CLEANUP_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF23)
+#define DQ_XCM_TOE_DQ_FLUSH_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF19)
+#define DQ_XCM_TOE_SLOW_PATH_CMD BIT(DQ_XCM_AGG_FLG_SHIFT_CF22)
/* UCM agg counter flag selection (HW) */
#define DQ_UCM_AGG_FLG_SHIFT_CF0 0
@@ -285,6 +293,9 @@
#define DQ_UCM_ETH_PMD_RX_ARM_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF5)
#define DQ_UCM_ROCE_CQ_ARM_SE_CF_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF4)
#define DQ_UCM_ROCE_CQ_ARM_CF_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF5)
+#define DQ_UCM_TOE_TIMER_STOP_ALL_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF3)
+#define DQ_UCM_TOE_SLOW_PATH_CF_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF4)
+#define DQ_UCM_TOE_DQ_CF_CMD BIT(DQ_UCM_AGG_FLG_SHIFT_CF5)
/* TCM agg counter flag selection (HW) */
#define DQ_TCM_AGG_FLG_SHIFT_CF0 0
@@ -301,6 +312,9 @@
#define DQ_TCM_FCOE_TIMER_STOP_ALL_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF3)
#define DQ_TCM_ISCSI_FLUSH_Q0_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF1)
#define DQ_TCM_ISCSI_TIMER_STOP_ALL_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF3)
+#define DQ_TCM_TOE_FLUSH_Q0_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF1)
+#define DQ_TCM_TOE_TIMER_STOP_ALL_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF3)
+#define DQ_TCM_IWARP_POST_RQ_CF_CMD BIT(DQ_TCM_AGG_FLG_SHIFT_CF1)
/* PWM address mapping */
#define DQ_PWM_OFFSET_DPM_BASE 0x0
@@ -689,6 +703,16 @@ struct iscsi_eqe_data {
#define ISCSI_EQE_DATA_RESERVED0_SHIFT 7
};
+struct rdma_eqe_destroy_qp {
+ __le32 cid;
+ u8 reserved[4];
+};
+
+union rdma_eqe_data {
+ struct regpair async_handle;
+ struct rdma_eqe_destroy_qp rdma_destroy_qp_data;
+};
+
struct malicious_vf_eqe_data {
u8 vf_id;
u8 err_id;
@@ -705,9 +729,9 @@ union event_ring_data {
u8 bytes[8];
struct vf_pf_channel_eqe_data vf_pf_channel;
struct iscsi_eqe_data iscsi_info;
+ union rdma_eqe_data rdma_data;
struct malicious_vf_eqe_data malicious_vf;
struct initial_cleanup_eqe_data vf_init_cleanup;
- struct regpair roce_handle;
};
/* Event Ring Entry */
diff --git a/include/linux/qed/eth_common.h b/include/linux/qed/eth_common.h
index 4b402fb..34d93eb 100644
--- a/include/linux/qed/eth_common.h
+++ b/include/linux/qed/eth_common.h
@@ -49,6 +49,9 @@
#define ETH_RX_CQE_PAGE_SIZE_BYTES 4096
#define ETH_RX_NUM_NEXT_PAGE_BDS 2
+#define ETH_MAX_TUNN_LSO_INNER_IPV4_OFFSET 253
+#define ETH_MAX_TUNN_LSO_INNER_IPV6_OFFSET 251
+
#define ETH_TX_MIN_BDS_PER_NON_LSO_PKT 1
#define ETH_TX_MAX_BDS_PER_NON_LSO_PACKET 18
#define ETH_TX_MAX_BDS_PER_LSO_PACKET 255
diff --git a/include/linux/qed/fcoe_common.h b/include/linux/qed/fcoe_common.h
index 2e417a4..947a635 100644
--- a/include/linux/qed/fcoe_common.h
+++ b/include/linux/qed/fcoe_common.h
@@ -109,13 +109,6 @@ struct fcoe_conn_terminate_ramrod_data {
struct regpair terminate_params_addr;
};
-struct fcoe_fast_sgl_ctx {
- struct regpair sgl_start_addr;
- __le32 sgl_byte_offset;
- __le16 task_reuse_cnt;
- __le16 init_offset_in_first_sge;
-};
-
struct fcoe_slow_sgl_ctx {
struct regpair base_sgl_addr;
__le16 curr_sge_off;
@@ -124,23 +117,16 @@ struct fcoe_slow_sgl_ctx {
__le16 reserved;
};
-struct fcoe_sge {
- struct regpair sge_addr;
- __le16 size;
- __le16 reserved0;
- u8 reserved1[3];
- u8 is_valid_sge;
-};
-
-union fcoe_data_desc_ctx {
- struct fcoe_fast_sgl_ctx fast;
- struct fcoe_slow_sgl_ctx slow;
- struct fcoe_sge single_sge;
-};
-
union fcoe_dix_desc_ctx {
struct fcoe_slow_sgl_ctx dix_sgl;
- struct fcoe_sge cached_dix_sge;
+ struct scsi_sge cached_dix_sge;
+};
+
+struct fcoe_fast_sgl_ctx {
+ struct regpair sgl_start_addr;
+ __le32 sgl_byte_offset;
+ __le16 task_reuse_cnt;
+ __le16 init_offset_in_first_sge;
};
struct fcoe_fcp_cmd_payload {
@@ -172,57 +158,6 @@ enum fcoe_mode_type {
MAX_FCOE_MODE_TYPE
};
-struct fcoe_mstorm_fcoe_task_st_ctx_fp {
- __le16 flags;
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_FP_RSRV0_MASK 0x7FFF
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_FP_RSRV0_SHIFT 0
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_FP_MP_INCLUDE_FC_HEADER_MASK 0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_FP_MP_INCLUDE_FC_HEADER_SHIFT 15
- __le16 difDataResidue;
- __le16 parent_id;
- __le16 single_sge_saved_offset;
- __le32 data_2_trns_rem;
- __le32 offset_in_io;
- union fcoe_dix_desc_ctx dix_desc;
- union fcoe_data_desc_ctx data_desc;
-};
-
-struct fcoe_mstorm_fcoe_task_st_ctx_non_fp {
- __le16 flags;
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_HOST_INTERFACE_MASK 0x3
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_HOST_INTERFACE_SHIFT 0
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIF_TO_PEER_MASK 0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIF_TO_PEER_SHIFT 2
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_VALIDATE_DIX_APP_TAG_MASK 0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_VALIDATE_DIX_APP_TAG_SHIFT 3
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_INTERVAL_SIZE_LOG_MASK 0xF
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_INTERVAL_SIZE_LOG_SHIFT 4
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIX_BLOCK_SIZE_MASK 0x3
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIX_BLOCK_SIZE_SHIFT 8
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RESERVED_MASK 0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RESERVED_SHIFT 10
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_HAS_FIRST_PACKET_ARRIVED_MASK 0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_HAS_FIRST_PACKET_ARRIVED_SHIFT 11
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_VALIDATE_DIX_REF_TAG_MASK 0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_VALIDATE_DIX_REF_TAG_SHIFT 12
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIX_CACHED_SGE_FLG_MASK 0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIX_CACHED_SGE_FLG_SHIFT 13
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_OFFSET_IN_IO_VALID_MASK 0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_OFFSET_IN_IO_VALID_SHIFT 14
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIF_SUPPORTED_MASK 0x1
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_DIF_SUPPORTED_SHIFT 15
- u8 tx_rx_sgl_mode;
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_TX_SGL_MODE_MASK 0x7
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_TX_SGL_MODE_SHIFT 0
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE_MASK 0x7
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RX_SGL_MODE_SHIFT 3
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RSRV1_MASK 0x3
-#define FCOE_MSTORM_FCOE_TASK_ST_CTX_NON_FP_RSRV1_SHIFT 6
- u8 rsrv2;
- __le32 num_prm_zero_read;
- struct regpair rsp_buf_addr;
-};
-
struct fcoe_rx_stat {
struct regpair fcoe_rx_byte_cnt;
struct regpair fcoe_rx_data_pkt_cnt;
@@ -236,16 +171,6 @@ struct fcoe_rx_stat {
__le32 rsrv;
};
-enum fcoe_sgl_mode {
- FCOE_SLOW_SGL,
- FCOE_SINGLE_FAST_SGE,
- FCOE_2_FAST_SGE,
- FCOE_3_FAST_SGE,
- FCOE_4_FAST_SGE,
- FCOE_MUL_FAST_SGES,
- MAX_FCOE_SGL_MODE
-};
-
struct fcoe_stat_ramrod_data {
struct regpair stat_params_addr;
};
@@ -328,22 +253,24 @@ union fcoe_tx_info_union_ctx {
struct ystorm_fcoe_task_st_ctx {
u8 task_type;
u8 sgl_mode;
-#define YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_MASK 0x7
+#define YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_MASK 0x1
#define YSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_SHIFT 0
-#define YSTORM_FCOE_TASK_ST_CTX_RSRV_MASK 0x1F
-#define YSTORM_FCOE_TASK_ST_CTX_RSRV_SHIFT 3
+#define YSTORM_FCOE_TASK_ST_CTX_RSRV_MASK 0x7F
+#define YSTORM_FCOE_TASK_ST_CTX_RSRV_SHIFT 1
u8 cached_dix_sge;
u8 expect_first_xfer;
__le32 num_pbf_zero_write;
union protection_info_union_ctx protection_info_union;
__le32 data_2_trns_rem;
+ struct scsi_sgl_params sgl_params;
+ u8 reserved1[12];
union fcoe_tx_info_union_ctx tx_info_union;
union fcoe_dix_desc_ctx dix_desc;
- union fcoe_data_desc_ctx data_desc;
+ struct scsi_cached_sges data_desc;
__le16 ox_id;
__le16 rx_id;
__le32 task_rety_identifier;
- __le32 reserved1[2];
+ u8 reserved2[8];
};
struct ystorm_fcoe_task_ag_ctx {
@@ -484,22 +411,22 @@ struct tstorm_fcoe_task_ag_ctx {
struct fcoe_tstorm_fcoe_task_st_ctx_read_write {
union fcoe_cleanup_addr_exp_ro_union cleanup_addr_exp_ro_union;
__le16 flags;
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE_MASK 0x7
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE_MASK 0x1
#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RX_SGL_MODE_SHIFT 0
#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME_MASK 0x1
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME_SHIFT 3
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_EXP_FIRST_FRAME_SHIFT 1
#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_ACTIVE_MASK 0x1
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_ACTIVE_SHIFT 4
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_ACTIVE_SHIFT 2
#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_TIMEOUT_MASK 0x1
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_TIMEOUT_SHIFT 5
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SEQ_TIMEOUT_SHIFT 3
#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SINGLE_PKT_IN_EX_MASK 0x1
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SINGLE_PKT_IN_EX_SHIFT 6
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_SINGLE_PKT_IN_EX_SHIFT 4
#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_OOO_RX_SEQ_STAT_MASK 0x1
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_OOO_RX_SEQ_STAT_SHIFT 7
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_OOO_RX_SEQ_STAT_SHIFT 5
#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_CQ_ADD_ADV_MASK 0x3
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_CQ_ADD_ADV_SHIFT 8
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RSRV1_MASK 0x3F
-#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RSRV1_SHIFT 10
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_CQ_ADD_ADV_SHIFT 6
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RSRV1_MASK 0xFF
+#define FCOE_TSTORM_FCOE_TASK_ST_CTX_READ_WRITE_RSRV1_SHIFT 8
__le16 seq_cnt;
u8 seq_id;
u8 ooo_rx_seq_id;
@@ -582,8 +509,34 @@ struct mstorm_fcoe_task_ag_ctx {
};
struct mstorm_fcoe_task_st_ctx {
- struct fcoe_mstorm_fcoe_task_st_ctx_non_fp non_fp;
- struct fcoe_mstorm_fcoe_task_st_ctx_fp fp;
+ struct regpair rsp_buf_addr;
+ __le32 rsrv[2];
+ struct scsi_sgl_params sgl_params;
+ __le32 data_2_trns_rem;
+ __le32 data_buffer_offset;
+ __le16 parent_id;
+ __le16 flags;
+#define MSTORM_FCOE_TASK_ST_CTX_INTERVAL_SIZE_LOG_MASK 0xF
+#define MSTORM_FCOE_TASK_ST_CTX_INTERVAL_SIZE_LOG_SHIFT 0
+#define MSTORM_FCOE_TASK_ST_CTX_HOST_INTERFACE_MASK 0x3
+#define MSTORM_FCOE_TASK_ST_CTX_HOST_INTERFACE_SHIFT 4
+#define MSTORM_FCOE_TASK_ST_CTX_DIF_TO_PEER_MASK 0x1
+#define MSTORM_FCOE_TASK_ST_CTX_DIF_TO_PEER_SHIFT 6
+#define MSTORM_FCOE_TASK_ST_CTX_MP_INCLUDE_FC_HEADER_MASK 0x1
+#define MSTORM_FCOE_TASK_ST_CTX_MP_INCLUDE_FC_HEADER_SHIFT 7
+#define MSTORM_FCOE_TASK_ST_CTX_DIX_BLOCK_SIZE_MASK 0x3
+#define MSTORM_FCOE_TASK_ST_CTX_DIX_BLOCK_SIZE_SHIFT 8
+#define MSTORM_FCOE_TASK_ST_CTX_VALIDATE_DIX_REF_TAG_MASK 0x1
+#define MSTORM_FCOE_TASK_ST_CTX_VALIDATE_DIX_REF_TAG_SHIFT 10
+#define MSTORM_FCOE_TASK_ST_CTX_DIX_CACHED_SGE_FLG_MASK 0x1
+#define MSTORM_FCOE_TASK_ST_CTX_DIX_CACHED_SGE_FLG_SHIFT 11
+#define MSTORM_FCOE_TASK_ST_CTX_DIF_SUPPORTED_MASK 0x1
+#define MSTORM_FCOE_TASK_ST_CTX_DIF_SUPPORTED_SHIFT 12
+#define MSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_MASK 0x1
+#define MSTORM_FCOE_TASK_ST_CTX_TX_SGL_MODE_SHIFT 13
+#define MSTORM_FCOE_TASK_ST_CTX_RESERVED_MASK 0x3
+#define MSTORM_FCOE_TASK_ST_CTX_RESERVED_SHIFT 14
+ struct scsi_cached_sges data_desc;
};
struct ustorm_fcoe_task_ag_ctx {
@@ -646,6 +599,7 @@ struct ustorm_fcoe_task_ag_ctx {
struct fcoe_task_context {
struct ystorm_fcoe_task_st_ctx ystorm_st_context;
+ struct regpair ystorm_st_padding[2];
struct tdif_task_context tdif_context;
struct ystorm_fcoe_task_ag_ctx ystorm_ag_context;
struct tstorm_fcoe_task_ag_ctx tstorm_ag_context;
@@ -668,20 +622,20 @@ struct fcoe_tx_stat {
struct fcoe_wqe {
__le16 task_id;
__le16 flags;
-#define FCOE_WQE_REQ_TYPE_MASK 0xF
-#define FCOE_WQE_REQ_TYPE_SHIFT 0
-#define FCOE_WQE_SGL_MODE_MASK 0x7
-#define FCOE_WQE_SGL_MODE_SHIFT 4
-#define FCOE_WQE_CONTINUATION_MASK 0x1
-#define FCOE_WQE_CONTINUATION_SHIFT 7
-#define FCOE_WQE_INVALIDATE_PTU_MASK 0x1
-#define FCOE_WQE_INVALIDATE_PTU_SHIFT 8
-#define FCOE_WQE_SUPER_IO_MASK 0x1
-#define FCOE_WQE_SUPER_IO_SHIFT 9
-#define FCOE_WQE_SEND_AUTO_RSP_MASK 0x1
-#define FCOE_WQE_SEND_AUTO_RSP_SHIFT 10
-#define FCOE_WQE_RESERVED0_MASK 0x1F
-#define FCOE_WQE_RESERVED0_SHIFT 11
+#define FCOE_WQE_REQ_TYPE_MASK 0xF
+#define FCOE_WQE_REQ_TYPE_SHIFT 0
+#define FCOE_WQE_SGL_MODE_MASK 0x1
+#define FCOE_WQE_SGL_MODE_SHIFT 4
+#define FCOE_WQE_CONTINUATION_MASK 0x1
+#define FCOE_WQE_CONTINUATION_SHIFT 5
+#define FCOE_WQE_SEND_AUTO_RSP_MASK 0x1
+#define FCOE_WQE_SEND_AUTO_RSP_SHIFT 6
+#define FCOE_WQE_RESERVED_MASK 0x1
+#define FCOE_WQE_RESERVED_SHIFT 7
+#define FCOE_WQE_NUM_SGES_MASK 0xF
+#define FCOE_WQE_NUM_SGES_SHIFT 8
+#define FCOE_WQE_RESERVED1_MASK 0xF
+#define FCOE_WQE_RESERVED1_SHIFT 12
union fcoe_additional_info_union additional_info_union;
};
diff --git a/include/linux/qed/iscsi_common.h b/include/linux/qed/iscsi_common.h
index 4c5747b..69949f8 100644
--- a/include/linux/qed/iscsi_common.h
+++ b/include/linux/qed/iscsi_common.h
@@ -39,17 +39,9 @@
/* iSCSI HSI constants */
#define ISCSI_DEFAULT_MTU (1500)
-/* Current iSCSI HSI version number composed of two fields (16 bit) */
-#define ISCSI_HSI_MAJOR_VERSION (0)
-#define ISCSI_HSI_MINOR_VERSION (0)
-
/* KWQ (kernel work queue) layer codes */
#define ISCSI_SLOW_PATH_LAYER_CODE (6)
-/* CQE completion status */
-#define ISCSI_EQE_COMPLETION_SUCCESS (0x0)
-#define ISCSI_EQE_RST_CONN_RCVD (0x1)
-
/* iSCSI parameter defaults */
#define ISCSI_DEFAULT_HEADER_DIGEST (0)
#define ISCSI_DEFAULT_DATA_DIGEST (0)
@@ -68,6 +60,10 @@
#define ISCSI_MIN_VAL_MAX_OUTSTANDING_R2T (1)
#define ISCSI_MAX_VAL_MAX_OUTSTANDING_R2T (0xff)
+#define ISCSI_AHS_CNTL_SIZE 4
+
+#define ISCSI_WQE_NUM_SGES_SLOWIO (0xf)
+
/* iSCSI reserved params */
#define ISCSI_ITT_ALL_ONES (0xffffffff)
#define ISCSI_TTT_ALL_ONES (0xffffffff)
@@ -173,19 +169,6 @@ struct iscsi_async_msg_hdr {
__le32 reserved7;
};
-struct iscsi_sge {
- struct regpair sge_addr;
- __le16 sge_len;
- __le16 reserved0;
- __le32 reserved1;
-};
-
-struct iscsi_cached_sge_ctx {
- struct iscsi_sge sge;
- struct regpair reserved;
- __le32 dsgl_curr_offset[2];
-};
-
struct iscsi_cmd_hdr {
__le16 reserved1;
u8 flags_attr;
@@ -229,8 +212,13 @@ struct iscsi_common_hdr {
#define ISCSI_COMMON_HDR_DATA_SEG_LEN_SHIFT 0
#define ISCSI_COMMON_HDR_TOTAL_AHS_LEN_MASK 0xFF
#define ISCSI_COMMON_HDR_TOTAL_AHS_LEN_SHIFT 24
- __le32 lun_reserved[4];
- __le32 data[6];
+ struct regpair lun_reserved;
+ __le32 itt;
+ __le32 ttt;
+ __le32 cmdstat_sn;
+ __le32 exp_statcmd_sn;
+ __le32 max_cmd_sn;
+ __le32 data[3];
};
struct iscsi_conn_offload_params {
@@ -246,8 +234,10 @@ struct iscsi_conn_offload_params {
#define ISCSI_CONN_OFFLOAD_PARAMS_TCP_ON_CHIP_1B_SHIFT 0
#define ISCSI_CONN_OFFLOAD_PARAMS_TARGET_MODE_MASK 0x1
#define ISCSI_CONN_OFFLOAD_PARAMS_TARGET_MODE_SHIFT 1
-#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_MASK 0x3F
-#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_SHIFT 2
+#define ISCSI_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_MASK 0x1
+#define ISCSI_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_SHIFT 2
+#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_MASK 0x1F
+#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_SHIFT 3
u8 pbl_page_size_log;
u8 pbe_page_size_log;
u8 default_cq;
@@ -278,8 +268,12 @@ struct iscsi_conn_update_ramrod_params {
#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_INITIAL_R2T_SHIFT 2
#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_IMMEDIATE_DATA_MASK 0x1
#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_IMMEDIATE_DATA_SHIFT 3
-#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_MASK 0xF
-#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_SHIFT 4
+#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_BLOCK_SIZE_MASK 0x1
+#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_BLOCK_SIZE_SHIFT 4
+#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_ON_HOST_EN_MASK 0x1
+#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DIF_ON_HOST_EN_SHIFT 5
+#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_MASK 0x3
+#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_SHIFT 6
u8 reserved0[3];
__le32 max_seq_size;
__le32 max_send_pdu_length;
@@ -312,7 +306,7 @@ struct iscsi_ext_cdb_cmd_hdr {
__le32 expected_transfer_length;
__le32 cmd_sn;
__le32 exp_stat_sn;
- struct iscsi_sge cdb_sge;
+ struct scsi_sge cdb_sge;
};
struct iscsi_login_req_hdr {
@@ -519,8 +513,8 @@ struct iscsi_logout_response_hdr {
__le32 exp_cmd_sn;
__le32 max_cmd_sn;
__le32 reserved4;
- __le16 time2retain;
- __le16 time2wait;
+ __le16 time_2_retain;
+ __le16 time_2_wait;
__le32 reserved5[1];
};
@@ -602,7 +596,7 @@ struct iscsi_tmf_response_hdr {
#define ISCSI_TMF_RESPONSE_HDR_TOTAL_AHS_LEN_SHIFT 24
struct regpair reserved0;
__le32 itt;
- __le32 rtt;
+ __le32 reserved1;
__le32 stat_sn;
__le32 exp_cmd_sn;
__le32 max_cmd_sn;
@@ -641,7 +635,7 @@ struct iscsi_reject_hdr {
#define ISCSI_REJECT_HDR_TOTAL_AHS_LEN_MASK 0xFF
#define ISCSI_REJECT_HDR_TOTAL_AHS_LEN_SHIFT 24
struct regpair reserved0;
- __le32 reserved1;
+ __le32 all_ones;
__le32 reserved2;
__le32 stat_sn;
__le32 exp_cmd_sn;
@@ -688,7 +682,9 @@ struct iscsi_cqe_solicited {
__le16 itid;
u8 task_type;
u8 fw_dbg_field;
- __le32 reserved1[2];
+ u8 caused_conn_err;
+ u8 reserved0[3];
+ __le32 reserved1[1];
union iscsi_task_hdr iscsi_hdr;
};
@@ -727,35 +723,6 @@ enum iscsi_cqe_unsolicited_type {
MAX_ISCSI_CQE_UNSOLICITED_TYPE
};
-struct iscsi_virt_sgl_ctx {
- struct regpair sgl_base;
- struct regpair dsgl_base;
- __le32 sgl_initial_offset;
- __le32 dsgl_initial_offset;
- __le32 dsgl_curr_offset[2];
-};
-
-struct iscsi_sgl_var_params {
- u8 sgl_ptr;
- u8 dsgl_ptr;
- __le16 sge_offset;
- __le16 dsge_offset;
-};
-
-struct iscsi_phys_sgl_ctx {
- struct regpair sgl_base;
- struct regpair dsgl_base;
- u8 sgl_size;
- u8 dsgl_size;
- __le16 reserved;
- struct iscsi_sgl_var_params var_params[2];
-};
-
-union iscsi_data_desc_ctx {
- struct iscsi_virt_sgl_ctx virt_sgl;
- struct iscsi_phys_sgl_ctx phys_sgl;
- struct iscsi_cached_sge_ctx cached_sge;
-};
struct iscsi_debug_modes {
u8 flags;
@@ -771,8 +738,10 @@ struct iscsi_debug_modes {
#define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_REJECT_OR_ASYNC_SHIFT 4
#define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_NOP_MASK 0x1
#define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_NOP_SHIFT 5
-#define ISCSI_DEBUG_MODES_RESERVED0_MASK 0x3
-#define ISCSI_DEBUG_MODES_RESERVED0_SHIFT 6
+#define ISCSI_DEBUG_MODES_ASSERT_IF_DATA_DIGEST_ERROR_MASK 0x1
+#define ISCSI_DEBUG_MODES_ASSERT_IF_DATA_DIGEST_ERROR_SHIFT 6
+#define ISCSI_DEBUG_MODES_ASSERT_IF_DIF_ERROR_MASK 0x1
+#define ISCSI_DEBUG_MODES_ASSERT_IF_DIF_ERROR_SHIFT 7
};
struct iscsi_dif_flags {
@@ -806,7 +775,6 @@ enum iscsi_eqe_opcode {
ISCSI_EVENT_TYPE_ASYN_FIN_WAIT2,
ISCSI_EVENT_TYPE_ISCSI_CONN_ERROR,
ISCSI_EVENT_TYPE_TCP_CONN_ERROR,
- ISCSI_EVENT_TYPE_ASYN_DELETE_OOO_ISLES,
MAX_ISCSI_EQE_OPCODE
};
@@ -856,31 +824,11 @@ enum iscsi_error_types {
ISCSI_CONN_ERROR_PROTOCOL_ERR_DIF_TX,
ISCSI_CONN_ERROR_SENSE_DATA_LENGTH,
ISCSI_CONN_ERROR_DATA_PLACEMENT_ERROR,
+ ISCSI_CONN_ERROR_INVALID_ITT,
ISCSI_ERROR_UNKNOWN,
MAX_ISCSI_ERROR_TYPES
};
-struct iscsi_mflags {
- u8 mflags;
-#define ISCSI_MFLAGS_SLOW_IO_MASK 0x1
-#define ISCSI_MFLAGS_SLOW_IO_SHIFT 0
-#define ISCSI_MFLAGS_SINGLE_SGE_MASK 0x1
-#define ISCSI_MFLAGS_SINGLE_SGE_SHIFT 1
-#define ISCSI_MFLAGS_RESERVED_MASK 0x3F
-#define ISCSI_MFLAGS_RESERVED_SHIFT 2
-};
-
-struct iscsi_sgl {
- struct regpair sgl_addr;
- __le16 updated_sge_size;
- __le16 updated_sge_offset;
- __le32 byte_offset;
-};
-
-union iscsi_mstorm_sgl {
- struct iscsi_sgl sgl_struct;
- struct iscsi_sge single_sge;
-};
enum iscsi_ramrod_cmd_id {
ISCSI_RAMROD_CMD_ID_UNUSED = 0,
@@ -896,10 +844,10 @@ enum iscsi_ramrod_cmd_id {
struct iscsi_reg1 {
__le32 reg1_map;
-#define ISCSI_REG1_NUM_FAST_SGES_MASK 0x7
-#define ISCSI_REG1_NUM_FAST_SGES_SHIFT 0
-#define ISCSI_REG1_RESERVED1_MASK 0x1FFFFFFF
-#define ISCSI_REG1_RESERVED1_SHIFT 3
+#define ISCSI_REG1_NUM_SGES_MASK 0xF
+#define ISCSI_REG1_NUM_SGES_SHIFT 0
+#define ISCSI_REG1_RESERVED1_MASK 0xFFFFFFF
+#define ISCSI_REG1_RESERVED1_SHIFT 4
};
union iscsi_seq_num {
@@ -967,22 +915,33 @@ struct iscsi_spe_func_init {
};
struct ystorm_iscsi_task_state {
- union iscsi_data_desc_ctx sgl_ctx_union;
- __le32 buffer_offset[2];
- __le16 bytes_nxt_dif;
- __le16 rxmit_bytes_nxt_dif;
- union iscsi_seq_num seq_num_union;
- u8 dif_bytes_leftover;
- u8 rxmit_dif_bytes_leftover;
- __le16 reuse_count;
- struct iscsi_dif_flags dif_flags;
- u8 local_comp;
+ struct scsi_cached_sges data_desc;
+ struct scsi_sgl_params sgl_params;
__le32 exp_r2t_sn;
- __le32 sgl_offset[2];
+ __le32 buffer_offset;
+ union iscsi_seq_num seq_num;
+ struct iscsi_dif_flags dif_flags;
+ u8 flags;
+#define YSTORM_ISCSI_TASK_STATE_LOCAL_COMP_MASK 0x1
+#define YSTORM_ISCSI_TASK_STATE_LOCAL_COMP_SHIFT 0
+#define YSTORM_ISCSI_TASK_STATE_SLOW_IO_MASK 0x1
+#define YSTORM_ISCSI_TASK_STATE_SLOW_IO_SHIFT 1
+#define YSTORM_ISCSI_TASK_STATE_RESERVED0_MASK 0x3F
+#define YSTORM_ISCSI_TASK_STATE_RESERVED0_SHIFT 2
+};
+
+struct ystorm_iscsi_task_rxmit_opt {
+ __le32 fast_rxmit_sge_offset;
+ __le32 scan_start_buffer_offset;
+ __le32 fast_rxmit_buffer_offset;
+ u8 scan_start_sgl_index;
+ u8 fast_rxmit_sgl_index;
+ __le16 reserved;
};
struct ystorm_iscsi_task_st_ctx {
struct ystorm_iscsi_task_state state;
+ struct ystorm_iscsi_task_rxmit_opt rxmit_opt;
union iscsi_task_hdr pdu_hdr;
};
@@ -1152,25 +1111,16 @@ struct ustorm_iscsi_task_ag_ctx {
};
struct mstorm_iscsi_task_st_ctx {
- union iscsi_mstorm_sgl sgl_union;
- struct iscsi_dif_flags dif_flags;
- struct iscsi_mflags flags;
- u8 sgl_size;
- u8 host_sge_index;
- __le16 dix_cur_sge_offset;
- __le16 dix_cur_sge_size;
- __le32 data_offset_rtid;
- u8 dif_offset;
- u8 dix_sgl_size;
- u8 dix_sge_index;
- u8 task_type;
- struct regpair sense_db;
- struct regpair dix_sgl_cur_sge;
+ struct scsi_cached_sges data_desc;
+ struct scsi_sgl_params sgl_params;
__le32 rem_task_size;
- __le16 reuse_count;
- __le16 dif_data_residue;
- u8 reserved0[4];
- __le32 reserved1[1];
+ __le32 data_buffer_offset;
+ u8 task_type;
+ struct iscsi_dif_flags dif_flags;
+ u8 reserved0[2];
+ struct regpair sense_db;
+ __le32 expected_itt;
+ __le32 reserved1;
};
struct ustorm_iscsi_task_st_ctx {
@@ -1184,7 +1134,7 @@ struct ustorm_iscsi_task_st_ctx {
#define USTORM_ISCSI_TASK_ST_CTX_AHS_EXIST_SHIFT 0
#define USTORM_ISCSI_TASK_ST_CTX_RESERVED1_MASK 0x7F
#define USTORM_ISCSI_TASK_ST_CTX_RESERVED1_SHIFT 1
- u8 reserved2;
+ struct iscsi_dif_flags dif_flags;
__le16 reserved3;
__le32 reserved4;
__le32 reserved5;
@@ -1207,10 +1157,10 @@ struct ustorm_iscsi_task_st_ctx {
#define USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP_SHIFT 2
#define USTORM_ISCSI_TASK_ST_CTX_Q0_R2TQE_WRITE_MASK 0x1
#define USTORM_ISCSI_TASK_ST_CTX_Q0_R2TQE_WRITE_SHIFT 3
-#define USTORM_ISCSI_TASK_ST_CTX_TOTALDATAACKED_DONE_MASK 0x1
-#define USTORM_ISCSI_TASK_ST_CTX_TOTALDATAACKED_DONE_SHIFT 4
-#define USTORM_ISCSI_TASK_ST_CTX_HQSCANNED_DONE_MASK 0x1
-#define USTORM_ISCSI_TASK_ST_CTX_HQSCANNED_DONE_SHIFT 5
+#define USTORM_ISCSI_TASK_ST_CTX_TOTAL_DATA_ACKED_DONE_MASK 0x1
+#define USTORM_ISCSI_TASK_ST_CTX_TOTAL_DATA_ACKED_DONE_SHIFT 4
+#define USTORM_ISCSI_TASK_ST_CTX_HQ_SCANNED_DONE_MASK 0x1
+#define USTORM_ISCSI_TASK_ST_CTX_HQ_SCANNED_DONE_SHIFT 5
#define USTORM_ISCSI_TASK_ST_CTX_R2T2RECV_DONE_MASK 0x1
#define USTORM_ISCSI_TASK_ST_CTX_R2T2RECV_DONE_SHIFT 6
#define USTORM_ISCSI_TASK_ST_CTX_RESERVED0_MASK 0x1
@@ -1220,7 +1170,6 @@ struct ustorm_iscsi_task_st_ctx {
struct iscsi_task_context {
struct ystorm_iscsi_task_st_ctx ystorm_st_context;
- struct regpair ystorm_st_padding[2];
struct ystorm_iscsi_task_ag_ctx ystorm_ag_context;
struct regpair ystorm_ag_padding[2];
struct tdif_task_context tdif_context;
@@ -1272,32 +1221,22 @@ struct iscsi_uhqe {
#define ISCSI_UHQE_TASK_ID_LO_SHIFT 24
};
-struct iscsi_wqe_field {
- __le32 contlen_cdbsize_field;
-#define ISCSI_WQE_FIELD_CONT_LEN_MASK 0xFFFFFF
-#define ISCSI_WQE_FIELD_CONT_LEN_SHIFT 0
-#define ISCSI_WQE_FIELD_CDB_SIZE_MASK 0xFF
-#define ISCSI_WQE_FIELD_CDB_SIZE_SHIFT 24
-};
-
-union iscsi_wqe_field_union {
- struct iscsi_wqe_field cont_field;
- __le32 prev_tid;
-};
struct iscsi_wqe {
__le16 task_id;
u8 flags;
#define ISCSI_WQE_WQE_TYPE_MASK 0x7
#define ISCSI_WQE_WQE_TYPE_SHIFT 0
-#define ISCSI_WQE_NUM_FAST_SGES_MASK 0x7
-#define ISCSI_WQE_NUM_FAST_SGES_SHIFT 3
-#define ISCSI_WQE_PTU_INVALIDATE_MASK 0x1
-#define ISCSI_WQE_PTU_INVALIDATE_SHIFT 6
+#define ISCSI_WQE_NUM_SGES_MASK 0xF
+#define ISCSI_WQE_NUM_SGES_SHIFT 3
#define ISCSI_WQE_RESPONSE_MASK 0x1
#define ISCSI_WQE_RESPONSE_SHIFT 7
struct iscsi_dif_flags prot_flags;
- union iscsi_wqe_field_union cont_prevtid_union;
+ __le32 contlen_cdbsize;
+#define ISCSI_WQE_CONT_LEN_MASK 0xFFFFFF
+#define ISCSI_WQE_CONT_LEN_SHIFT 0
+#define ISCSI_WQE_CDB_SIZE_MASK 0xFF
+#define ISCSI_WQE_CDB_SIZE_SHIFT 24
};
enum iscsi_wqe_type {
@@ -1318,17 +1257,15 @@ struct iscsi_xhqe {
u8 total_ahs_length;
u8 opcode;
u8 flags;
-#define ISCSI_XHQE_NUM_FAST_SGES_MASK 0x7
-#define ISCSI_XHQE_NUM_FAST_SGES_SHIFT 0
-#define ISCSI_XHQE_FINAL_MASK 0x1
-#define ISCSI_XHQE_FINAL_SHIFT 3
-#define ISCSI_XHQE_SUPER_IO_MASK 0x1
-#define ISCSI_XHQE_SUPER_IO_SHIFT 4
-#define ISCSI_XHQE_STATUS_BIT_MASK 0x1
-#define ISCSI_XHQE_STATUS_BIT_SHIFT 5
-#define ISCSI_XHQE_RESERVED_MASK 0x3
-#define ISCSI_XHQE_RESERVED_SHIFT 6
- union iscsi_seq_num seq_num_union;
+#define ISCSI_XHQE_FINAL_MASK 0x1
+#define ISCSI_XHQE_FINAL_SHIFT 0
+#define ISCSI_XHQE_STATUS_BIT_MASK 0x1
+#define ISCSI_XHQE_STATUS_BIT_SHIFT 1
+#define ISCSI_XHQE_NUM_SGES_MASK 0xF
+#define ISCSI_XHQE_NUM_SGES_SHIFT 2
+#define ISCSI_XHQE_RESERVED0_MASK 0x3
+#define ISCSI_XHQE_RESERVED0_SHIFT 6
+ union iscsi_seq_num seq_num;
__le16 reserved1;
};
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index fde56c4..625f80f 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -263,7 +263,6 @@ struct qed_rdma_pf_params {
* the doorbell BAR).
*/
u32 min_dpis; /* number of requested DPIs */
- u32 num_mrs; /* number of requested memory regions */
u32 num_qps; /* number of requested Queue Pairs */
u32 num_srqs; /* number of requested SRQ */
u8 roce_edpm_mode; /* see QED_ROCE_EDPM_MODE_ENABLE */
@@ -300,6 +299,11 @@ struct qed_sb_info {
struct qed_dev *cdev;
};
+enum qed_dev_type {
+ QED_DEV_TYPE_BB,
+ QED_DEV_TYPE_AH,
+};
+
struct qed_dev_info {
unsigned long pci_mem_start;
unsigned long pci_mem_end;
@@ -325,6 +329,8 @@ struct qed_dev_info {
u16 mtu;
bool wol_support;
+
+ enum qed_dev_type dev_type;
};
enum qed_sb_type {
@@ -752,7 +758,7 @@ enum qed_mf_mode {
QED_MF_NPAR,
};
-struct qed_eth_stats {
+struct qed_eth_stats_common {
u64 no_buff_discards;
u64 packet_too_big_discard;
u64 ttl0_discard;
@@ -784,11 +790,6 @@ struct qed_eth_stats {
u64 rx_256_to_511_byte_packets;
u64 rx_512_to_1023_byte_packets;
u64 rx_1024_to_1518_byte_packets;
- u64 rx_1519_to_1522_byte_packets;
- u64 rx_1519_to_2047_byte_packets;
- u64 rx_2048_to_4095_byte_packets;
- u64 rx_4096_to_9216_byte_packets;
- u64 rx_9217_to_16383_byte_packets;
u64 rx_crc_errors;
u64 rx_mac_crtl_frames;
u64 rx_pause_frames;
@@ -805,14 +806,8 @@ struct qed_eth_stats {
u64 tx_256_to_511_byte_packets;
u64 tx_512_to_1023_byte_packets;
u64 tx_1024_to_1518_byte_packets;
- u64 tx_1519_to_2047_byte_packets;
- u64 tx_2048_to_4095_byte_packets;
- u64 tx_4096_to_9216_byte_packets;
- u64 tx_9217_to_16383_byte_packets;
u64 tx_pause_frames;
u64 tx_pfc_frames;
- u64 tx_lpi_entry_count;
- u64 tx_total_collisions;
u64 brb_truncates;
u64 brb_discards;
u64 rx_mac_bytes;
@@ -827,6 +822,34 @@ struct qed_eth_stats {
u64 tx_mac_ctrl_frames;
};
+struct qed_eth_stats_bb {
+ u64 rx_1519_to_1522_byte_packets;
+ u64 rx_1519_to_2047_byte_packets;
+ u64 rx_2048_to_4095_byte_packets;
+ u64 rx_4096_to_9216_byte_packets;
+ u64 rx_9217_to_16383_byte_packets;
+ u64 tx_1519_to_2047_byte_packets;
+ u64 tx_2048_to_4095_byte_packets;
+ u64 tx_4096_to_9216_byte_packets;
+ u64 tx_9217_to_16383_byte_packets;
+ u64 tx_lpi_entry_count;
+ u64 tx_total_collisions;
+};
+
+struct qed_eth_stats_ah {
+ u64 rx_1519_to_max_byte_packets;
+ u64 tx_1519_to_max_byte_packets;
+};
+
+struct qed_eth_stats {
+ struct qed_eth_stats_common common;
+
+ union {
+ struct qed_eth_stats_bb bb;
+ struct qed_eth_stats_ah ah;
+ };
+};
+
#define QED_SB_IDX 0x0002
#define RX_PI 0
diff --git a/include/linux/qed/qed_iscsi_if.h b/include/linux/qed/qed_iscsi_if.h
index f70bb81b..3414649 100644
--- a/include/linux/qed/qed_iscsi_if.h
+++ b/include/linux/qed/qed_iscsi_if.h
@@ -67,6 +67,8 @@ struct qed_dev_iscsi_info {
void __iomem *primary_dbq_rq_addr;
void __iomem *secondary_bdq_rq_addr;
+
+ u8 num_cqs;
};
struct qed_iscsi_id_params {
diff --git a/include/linux/qed/rdma_common.h b/include/linux/qed/rdma_common.h
index f773aa5..72c770f 100644
--- a/include/linux/qed/rdma_common.h
+++ b/include/linux/qed/rdma_common.h
@@ -52,7 +52,8 @@
#define RDMA_MAX_PDS (64 * 1024)
#define RDMA_NUM_STATISTIC_COUNTERS MAX_NUM_VPORTS
-#define RDMA_NUM_STATISTIC_COUNTERS_BB MAX_NUM_VPORTS_BB
+#define RDMA_NUM_STATISTIC_COUNTERS_K2 MAX_NUM_VPORTS_K2
+#define RDMA_NUM_STATISTIC_COUNTERS_BB MAX_NUM_VPORTS_BB
#define RDMA_TASK_TYPE (PROTOCOLID_ROCE)
diff --git a/include/linux/qed/roce_common.h b/include/linux/qed/roce_common.h
index bad02df..866f063 100644
--- a/include/linux/qed/roce_common.h
+++ b/include/linux/qed/roce_common.h
@@ -38,4 +38,21 @@
#define ROCE_MAX_QPS (32 * 1024)
+enum roce_async_events_type {
+ ROCE_ASYNC_EVENT_NONE = 0,
+ ROCE_ASYNC_EVENT_COMM_EST = 1,
+ ROCE_ASYNC_EVENT_SQ_DRAINED,
+ ROCE_ASYNC_EVENT_SRQ_LIMIT,
+ ROCE_ASYNC_EVENT_LAST_WQE_REACHED,
+ ROCE_ASYNC_EVENT_CQ_ERR,
+ ROCE_ASYNC_EVENT_LOCAL_INVALID_REQUEST_ERR,
+ ROCE_ASYNC_EVENT_LOCAL_CATASTROPHIC_ERR,
+ ROCE_ASYNC_EVENT_LOCAL_ACCESS_ERR,
+ ROCE_ASYNC_EVENT_QP_CATASTROPHIC_ERR,
+ ROCE_ASYNC_EVENT_CQ_OVERFLOW_ERR,
+ ROCE_ASYNC_EVENT_SRQ_EMPTY,
+ ROCE_ASYNC_EVENT_DESTROY_QP_DONE,
+ MAX_ROCE_ASYNC_EVENTS_TYPE
+};
+
#endif /* __ROCE_COMMON__ */
diff --git a/include/linux/qed/storage_common.h b/include/linux/qed/storage_common.h
index 03f3e37..08df82a 100644
--- a/include/linux/qed/storage_common.h
+++ b/include/linux/qed/storage_common.h
@@ -40,6 +40,8 @@
#define BDQ_ID_IMM_DATA (1)
#define BDQ_NUM_IDS (2)
+#define SCSI_NUM_SGES_SLOW_SGL_THR 8
+
#define BDQ_MAX_EXTERNAL_RING_SIZE (1 << 15)
struct scsi_bd {
@@ -52,6 +54,16 @@ struct scsi_bdq_ram_drv_data {
__le16 reserved0[3];
};
+struct scsi_sge {
+ struct regpair sge_addr;
+ __le32 sge_len;
+ __le32 reserved;
+};
+
+struct scsi_cached_sges {
+ struct scsi_sge sge[4];
+};
+
struct scsi_drv_cmdq {
__le16 cmdq_cons;
__le16 reserved0;
@@ -99,11 +111,19 @@ struct scsi_ram_per_bdq_resource_drv_data {
struct scsi_bdq_ram_drv_data drv_data_per_bdq_id[BDQ_NUM_IDS];
};
-struct scsi_sge {
- struct regpair sge_addr;
- __le16 sge_len;
- __le16 reserved0;
- __le32 reserved1;
+enum scsi_sgl_mode {
+ SCSI_TX_SLOW_SGL,
+ SCSI_FAST_SGL,
+ MAX_SCSI_SGL_MODE
+};
+
+struct scsi_sgl_params {
+ struct regpair sgl_addr;
+ __le32 sgl_total_length;
+ __le32 sge_offset;
+ __le16 sgl_num_sges;
+ u8 sgl_index;
+ u8 reserved;
};
struct scsi_terminate_extra_params {
diff --git a/include/linux/qed/tcp_common.h b/include/linux/qed/tcp_common.h
index 46fe785..a5e8432 100644
--- a/include/linux/qed/tcp_common.h
+++ b/include/linux/qed/tcp_common.h
@@ -173,6 +173,7 @@ enum tcp_seg_placement_event {
TCP_EVENT_ADD_ISLE_RIGHT,
TCP_EVENT_ADD_ISLE_LEFT,
TCP_EVENT_JOIN,
+ TCP_EVENT_DELETE_ISLES,
TCP_EVENT_NOP,
MAX_TCP_SEG_PLACEMENT_EVENT
};
diff --git a/include/linux/random.h b/include/linux/random.h
index 7bd2403..ed5c383 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -37,14 +37,26 @@ extern void get_random_bytes(void *buf, int nbytes);
extern int add_random_ready_callback(struct random_ready_callback *rdy);
extern void del_random_ready_callback(struct random_ready_callback *rdy);
extern void get_random_bytes_arch(void *buf, int nbytes);
-extern int random_int_secret_init(void);
#ifndef MODULE
extern const struct file_operations random_fops, urandom_fops;
#endif
-unsigned int get_random_int(void);
-unsigned long get_random_long(void);
+u32 get_random_u32(void);
+u64 get_random_u64(void);
+static inline unsigned int get_random_int(void)
+{
+ return get_random_u32();
+}
+static inline unsigned long get_random_long(void)
+{
+#if BITS_PER_LONG == 64
+ return get_random_u64();
+#else
+ return get_random_u32();
+#endif
+}
+
unsigned long randomize_page(unsigned long start, unsigned long range);
u32 prandom_u32(void);
diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index 4ae95f7..a23a331 100644
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -156,5 +156,19 @@ static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n,
({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1; }); \
pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)))
+/**
+ * hlist_nulls_for_each_entry_safe -
+ * iterate over list of given type safe against removal of list entry
+ * @tpos: the type * to use as a loop cursor.
+ * @pos: the &struct hlist_nulls_node to use as a loop cursor.
+ * @head: the head for your list.
+ * @member: the name of the hlist_nulls_node within the struct.
+ */
+#define hlist_nulls_for_each_entry_safe(tpos, pos, head, member) \
+ for (({barrier();}), \
+ pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \
+ (!is_a_nulls(pos)) && \
+ ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); \
+ pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)); 1; });)
#endif
#endif
diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h
index ad3e515..c9f795e 100644
--- a/include/linux/regulator/machine.h
+++ b/include/linux/regulator/machine.h
@@ -65,7 +65,7 @@ struct regulator_state {
int uV; /* suspend voltage */
unsigned int mode; /* suspend regulator operating mode */
int enabled; /* is regulator enabled in this suspend state */
- int disabled; /* is the regulator disbled in this suspend state */
+ int disabled; /* is the regulator disabled in this suspend state */
};
/**
diff --git a/include/linux/reset.h b/include/linux/reset.h
index 86b4ed7..96fb139 100644
--- a/include/linux/reset.h
+++ b/include/linux/reset.h
@@ -31,31 +31,26 @@ static inline int device_reset_optional(struct device *dev)
static inline int reset_control_reset(struct reset_control *rstc)
{
- WARN_ON(1);
return 0;
}
static inline int reset_control_assert(struct reset_control *rstc)
{
- WARN_ON(1);
return 0;
}
static inline int reset_control_deassert(struct reset_control *rstc)
{
- WARN_ON(1);
return 0;
}
static inline int reset_control_status(struct reset_control *rstc)
{
- WARN_ON(1);
return 0;
}
static inline void reset_control_put(struct reset_control *rstc)
{
- WARN_ON(1);
}
static inline int __must_check device_reset(struct device *dev)
@@ -74,14 +69,14 @@ static inline struct reset_control *__of_reset_control_get(
const char *id, int index, bool shared,
bool optional)
{
- return ERR_PTR(-ENOTSUPP);
+ return optional ? NULL : ERR_PTR(-ENOTSUPP);
}
static inline struct reset_control *__devm_reset_control_get(
struct device *dev, const char *id,
int index, bool shared, bool optional)
{
- return ERR_PTR(-ENOTSUPP);
+ return optional ? NULL : ERR_PTR(-ENOTSUPP);
}
#endif /* CONFIG_RESET_CONTROLLER */
diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 092292b..e507290 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -916,6 +916,28 @@ static inline int rhashtable_lookup_insert_fast(
}
/**
+ * rhashtable_lookup_get_insert_fast - lookup and insert object into hash table
+ * @ht: hash table
+ * @obj: pointer to hash head inside object
+ * @params: hash table parameters
+ *
+ * Just like rhashtable_lookup_insert_fast(), but this function returns the
+ * object if it exists, NULL if it did not and the insertion was successful,
+ * and an ERR_PTR otherwise.
+ */
+static inline void *rhashtable_lookup_get_insert_fast(
+ struct rhashtable *ht, struct rhash_head *obj,
+ const struct rhashtable_params params)
+{
+ const char *key = rht_obj(ht, obj);
+
+ BUG_ON(ht->p.obj_hashfn);
+
+ return __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj, params,
+ false);
+}
+
+/**
* rhashtable_lookup_insert_key - search and insert object to hash table
* with explicit key
* @ht: hash table
diff --git a/include/linux/rpmsg/qcom_smd.h b/include/linux/rpmsg/qcom_smd.h
index 8ec8b64..f27917e 100644
--- a/include/linux/rpmsg/qcom_smd.h
+++ b/include/linux/rpmsg/qcom_smd.h
@@ -6,7 +6,7 @@
struct qcom_smd_edge;
-#if IS_ENABLED(CONFIG_RPMSG_QCOM_SMD) || IS_ENABLED(CONFIG_QCOM_SMD)
+#if IS_ENABLED(CONFIG_RPMSG_QCOM_SMD)
struct qcom_smd_edge *qcom_smd_register_edge(struct device *parent,
struct device_node *node);
diff --git a/include/linux/sched/clock.h b/include/linux/sched/clock.h
index 4a68c67..34fe92c 100644
--- a/include/linux/sched/clock.h
+++ b/include/linux/sched/clock.h
@@ -54,15 +54,16 @@ static inline u64 local_clock(void)
}
#else
extern void sched_clock_init_late(void);
-/*
- * Architectures can set this to 1 if they have specified
- * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig,
- * but then during bootup it turns out that sched_clock()
- * is reliable after all:
- */
extern int sched_clock_stable(void);
extern void clear_sched_clock_stable(void);
+/*
+ * When sched_clock_stable(), __sched_clock_offset provides the offset
+ * between local_clock() and sched_clock().
+ */
+extern u64 __sched_clock_offset;
+
+
extern void sched_clock_tick(void);
extern void sched_clock_idle_sleep_event(void);
extern void sched_clock_idle_wakeup_event(u64 delta_ns);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index c776abd..741d75c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -413,14 +413,15 @@ struct ubuf_info {
* the end of the header data, ie. at skb->end.
*/
struct skb_shared_info {
+ unsigned short _unused;
unsigned char nr_frags;
__u8 tx_flags;
unsigned short gso_size;
/* Warning: this field is not always filled in (UFO)! */
unsigned short gso_segs;
- unsigned short gso_type;
struct sk_buff *frag_list;
struct skb_shared_hwtstamps hwtstamps;
+ unsigned int gso_type;
u32 tskey;
__be32 ip6_frag_id;
diff --git a/include/linux/soc/qcom/smd.h b/include/linux/soc/qcom/smd.h
deleted file mode 100644
index f148e0f..0000000
--- a/include/linux/soc/qcom/smd.h
+++ /dev/null
@@ -1,139 +0,0 @@
-#ifndef __QCOM_SMD_H__
-#define __QCOM_SMD_H__
-
-#include <linux/device.h>
-#include <linux/mod_devicetable.h>
-
-struct qcom_smd;
-struct qcom_smd_channel;
-struct qcom_smd_lookup;
-
-/**
- * struct qcom_smd_id - struct used for matching a smd device
- * @name: name of the channel
- */
-struct qcom_smd_id {
- char name[20];
-};
-
-/**
- * struct qcom_smd_device - smd device struct
- * @dev: the device struct
- * @channel: handle to the smd channel for this device
- */
-struct qcom_smd_device {
- struct device dev;
- struct qcom_smd_channel *channel;
-};
-
-typedef int (*qcom_smd_cb_t)(struct qcom_smd_channel *, const void *, size_t);
-
-/**
- * struct qcom_smd_driver - smd driver struct
- * @driver: underlying device driver
- * @smd_match_table: static channel match table
- * @probe: invoked when the smd channel is found
- * @remove: invoked when the smd channel is closed
- * @callback: invoked when an inbound message is received on the channel,
- * should return 0 on success or -EBUSY if the data cannot be
- * consumed at this time
- */
-struct qcom_smd_driver {
- struct device_driver driver;
- const struct qcom_smd_id *smd_match_table;
-
- int (*probe)(struct qcom_smd_device *dev);
- void (*remove)(struct qcom_smd_device *dev);
- qcom_smd_cb_t callback;
-};
-
-#if IS_ENABLED(CONFIG_QCOM_SMD)
-
-int qcom_smd_driver_register(struct qcom_smd_driver *drv);
-void qcom_smd_driver_unregister(struct qcom_smd_driver *drv);
-
-struct qcom_smd_channel *qcom_smd_open_channel(struct qcom_smd_channel *channel,
- const char *name,
- qcom_smd_cb_t cb);
-void qcom_smd_close_channel(struct qcom_smd_channel *channel);
-void *qcom_smd_get_drvdata(struct qcom_smd_channel *channel);
-void qcom_smd_set_drvdata(struct qcom_smd_channel *channel, void *data);
-int qcom_smd_send(struct qcom_smd_channel *channel, const void *data, int len);
-
-
-struct qcom_smd_edge *qcom_smd_register_edge(struct device *parent,
- struct device_node *node);
-int qcom_smd_unregister_edge(struct qcom_smd_edge *edge);
-
-#else
-
-static inline int qcom_smd_driver_register(struct qcom_smd_driver *drv)
-{
- return -ENXIO;
-}
-
-static inline void qcom_smd_driver_unregister(struct qcom_smd_driver *drv)
-{
- /* This shouldn't be possible */
- WARN_ON(1);
-}
-
-static inline struct qcom_smd_channel *
-qcom_smd_open_channel(struct qcom_smd_channel *channel,
- const char *name,
- qcom_smd_cb_t cb)
-{
- /* This shouldn't be possible */
- WARN_ON(1);
- return NULL;
-}
-
-static inline void qcom_smd_close_channel(struct qcom_smd_channel *channel)
-{
- /* This shouldn't be possible */
- WARN_ON(1);
-}
-
-static inline void *qcom_smd_get_drvdata(struct qcom_smd_channel *channel)
-{
- /* This shouldn't be possible */
- WARN_ON(1);
- return NULL;
-}
-
-static inline void qcom_smd_set_drvdata(struct qcom_smd_channel *channel, void *data)
-{
- /* This shouldn't be possible */
- WARN_ON(1);
-}
-
-static inline int qcom_smd_send(struct qcom_smd_channel *channel,
- const void *data, int len)
-{
- /* This shouldn't be possible */
- WARN_ON(1);
- return -ENXIO;
-}
-
-static inline struct qcom_smd_edge *
-qcom_smd_register_edge(struct device *parent,
- struct device_node *node)
-{
- return ERR_PTR(-ENXIO);
-}
-
-static inline int qcom_smd_unregister_edge(struct qcom_smd_edge *edge)
-{
- /* This shouldn't be possible */
- WARN_ON(1);
- return -ENXIO;
-}
-
-#endif
-
-#define module_qcom_smd_driver(__smd_driver) \
- module_driver(__smd_driver, qcom_smd_driver_register, \
- qcom_smd_driver_unregister)
-
-
-#endif
diff --git a/include/linux/soc/qcom/wcnss_ctrl.h b/include/linux/soc/qcom/wcnss_ctrl.h
index eab6497..a4dd4d7c 100644
--- a/include/linux/soc/qcom/wcnss_ctrl.h
+++ b/include/linux/soc/qcom/wcnss_ctrl.h
@@ -1,16 +1,19 @@
#ifndef __WCNSS_CTRL_H__
#define __WCNSS_CTRL_H__
-#include <linux/soc/qcom/smd.h>
+#include <linux/rpmsg.h>
#if IS_ENABLED(CONFIG_QCOM_WCNSS_CTRL)
-struct qcom_smd_channel *qcom_wcnss_open_channel(void *wcnss, const char *name, qcom_smd_cb_t cb);
+struct rpmsg_endpoint *qcom_wcnss_open_channel(void *wcnss, const char *name,
+ rpmsg_rx_cb_t cb, void *priv);
#else
-static inline struct qcom_smd_channel*
-qcom_wcnss_open_channel(void *wcnss, const char *name, qcom_smd_cb_t cb)
+static struct rpmsg_endpoint *qcom_wcnss_open_channel(void *wcnss,
+ const char *name,
+ rpmsg_rx_cb_t cb,
+ void *priv)
{
WARN_ON(1);
return ERR_PTR(-ENXIO);
diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h
index a0596ca0..a2f8109 100644
--- a/include/linux/sock_diag.h
+++ b/include/linux/sock_diag.h
@@ -24,6 +24,7 @@ void sock_diag_unregister(const struct sock_diag_handler *h);
void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh));
void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh));
+u64 sock_gen_cookie(struct sock *sk);
int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie);
void sock_diag_save_cookie(struct sock *sk, __u32 *cookie);
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index fc273e9..3921cb9 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -28,6 +28,9 @@
#include <linux/platform_device.h>
+#define MTL_MAX_RX_QUEUES 8
+#define MTL_MAX_TX_QUEUES 8
+
#define STMMAC_RX_COE_NONE 0
#define STMMAC_RX_COE_TYPE1 1
#define STMMAC_RX_COE_TYPE2 2
@@ -44,6 +47,18 @@
#define STMMAC_CSR_150_250M 0x4 /* MDC = clk_scr_i/102 */
#define STMMAC_CSR_250_300M 0x5 /* MDC = clk_scr_i/122 */
+/* MTL algorithms identifiers */
+#define MTL_TX_ALGORITHM_WRR 0x0
+#define MTL_TX_ALGORITHM_WFQ 0x1
+#define MTL_TX_ALGORITHM_DWRR 0x2
+#define MTL_TX_ALGORITHM_SP 0x3
+#define MTL_RX_ALGORITHM_SP 0x4
+#define MTL_RX_ALGORITHM_WSP 0x5
+
+/* RX/TX Queue Mode */
+#define MTL_QUEUE_AVB 0x0
+#define MTL_QUEUE_DCB 0x1
+
/* The MDC clock could be set higher than the IEEE 802.3
* specified frequency limit 0f 2.5 MHz, by programming a clock divider
* of value different than the above defined values. The resultant MDIO
@@ -109,6 +124,26 @@ struct stmmac_axi {
bool axi_rb;
};
+struct stmmac_rxq_cfg {
+ u8 mode_to_use;
+ u8 chan;
+ u8 pkt_route;
+ bool use_prio;
+ u32 prio;
+};
+
+struct stmmac_txq_cfg {
+ u8 weight;
+ u8 mode_to_use;
+ /* Credit Base Shaper parameters */
+ u32 send_slope;
+ u32 idle_slope;
+ u32 high_credit;
+ u32 low_credit;
+ bool use_prio;
+ u32 prio;
+};
+
struct plat_stmmacenet_data {
int bus_id;
int phy_addr;
@@ -133,6 +168,12 @@ struct plat_stmmacenet_data {
int unicast_filter_entries;
int tx_fifo_size;
int rx_fifo_size;
+ u8 rx_queues_to_use;
+ u8 tx_queues_to_use;
+ u8 rx_sched_algorithm;
+ u8 tx_sched_algorithm;
+ struct stmmac_rxq_cfg rx_queues_cfg[MTL_MAX_RX_QUEUES];
+ struct stmmac_txq_cfg tx_queues_cfg[MTL_MAX_TX_QUEUES];
void (*fix_mac_speed)(void *priv, unsigned int speed);
int (*init)(struct platform_device *pdev, void *priv);
void (*exit)(struct platform_device *pdev, void *priv);
diff --git a/include/linux/udp.h b/include/linux/udp.h
index c0f5308..6cb4061 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -115,6 +115,6 @@ static inline bool udp_get_no_check6_rx(struct sock *sk)
#define udp_portaddr_for_each_entry_rcu(__sk, list) \
hlist_for_each_entry_rcu(__sk, list, __sk_common.skc_portaddr_node)
-#define IS_UDPLITE(__sk) (udp_sk(__sk)->pcflag)
+#define IS_UDPLITE(__sk) (__sk->sk_protocol == IPPROTO_UDPLITE)
#endif /* _LINUX_UDP_H */
diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h
index 1d0043d..de2a722 100644
--- a/include/linux/usb/quirks.h
+++ b/include/linux/usb/quirks.h
@@ -50,4 +50,10 @@
/* device can't handle Link Power Management */
#define USB_QUIRK_NO_LPM BIT(10)
+/*
+ * Device reports its bInterval as linear frames instead of the
+ * USB 2.0 calculation.
+ */
+#define USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL BIT(11)
+
#endif /* __LINUX_USB_QUIRKS_H */
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 6e0ce8c..7dffa56 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -64,6 +64,8 @@ struct usbnet {
struct usb_anchor deferred;
struct tasklet_struct bh;
+ struct pcpu_sw_netstats __percpu *stats64;
+
struct work_struct kevent;
unsigned long flags;
# define EVENT_TX_HALT 0
@@ -261,10 +263,10 @@ extern void usbnet_pause_rx(struct usbnet *);
extern void usbnet_resume_rx(struct usbnet *);
extern void usbnet_purge_paused_rxq(struct usbnet *);
-extern int usbnet_get_settings(struct net_device *net,
- struct ethtool_cmd *cmd);
-extern int usbnet_set_settings(struct net_device *net,
- struct ethtool_cmd *cmd);
+extern int usbnet_get_link_ksettings(struct net_device *net,
+ struct ethtool_link_ksettings *cmd);
+extern int usbnet_set_link_ksettings(struct net_device *net,
+ const struct ethtool_link_ksettings *cmd);
extern u32 usbnet_get_link(struct net_device *net);
extern u32 usbnet_get_msglevel(struct net_device *);
extern void usbnet_set_msglevel(struct net_device *, u32);
@@ -278,5 +280,7 @@ extern int usbnet_status_start(struct usbnet *dev, gfp_t mem_flags);
extern void usbnet_status_stop(struct usbnet *dev);
extern void usbnet_update_max_qlen(struct usbnet *dev);
+extern void usbnet_get_stats64(struct net_device *dev,
+ struct rtnl_link_stats64 *stats);
#endif /* __LINUX_USB_USBNET_H */
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index be76523..32354b4 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -72,7 +72,7 @@ struct ucounts {
struct hlist_node node;
struct user_namespace *ns;
kuid_t uid;
- atomic_t count;
+ int count;
atomic_t ucount[UCOUNT_COUNTS];
};
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 0468548..48a3483 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -61,8 +61,7 @@ extern void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *,
unsigned long from, unsigned long to,
unsigned long len);
-extern void userfaultfd_remove(struct vm_area_struct *vma,
- struct vm_area_struct **prev,
+extern bool userfaultfd_remove(struct vm_area_struct *vma,
unsigned long start,
unsigned long end);
@@ -72,8 +71,6 @@ extern int userfaultfd_unmap_prep(struct vm_area_struct *vma,
extern void userfaultfd_unmap_complete(struct mm_struct *mm,
struct list_head *uf);
-extern void userfaultfd_exit(struct mm_struct *mm);
-
#else /* CONFIG_USERFAULTFD */
/* mm helpers */
@@ -120,11 +117,11 @@ static inline void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *ctx,
{
}
-static inline void userfaultfd_remove(struct vm_area_struct *vma,
- struct vm_area_struct **prev,
+static inline bool userfaultfd_remove(struct vm_area_struct *vma,
unsigned long start,
unsigned long end)
{
+ return true;
}
static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma,
@@ -139,10 +136,6 @@ static inline void userfaultfd_unmap_complete(struct mm_struct *mm,
{
}
-static inline void userfaultfd_exit(struct mm_struct *mm)
-{
-}
-
#endif /* CONFIG_USERFAULTFD */
#endif /* _LINUX_USERFAULTFD_K_H */
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 9638bfe..584f9a6 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -48,6 +48,8 @@ struct virtio_vsock_pkt {
struct virtio_vsock_hdr hdr;
struct work_struct work;
struct list_head list;
+ /* socket refcnt not held, only use for cancellation */
+ struct vsock_sock *vsk;
void *buf;
u32 len;
u32 off;
@@ -56,6 +58,7 @@ struct virtio_vsock_pkt {
struct virtio_vsock_pkt_info {
u32 remote_cid, remote_port;
+ struct vsock_sock *vsk;
struct msghdr *msg;
u32 pkt_len;
u16 type;
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 6aa1b6c..a80b7b5 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -79,6 +79,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
THP_SPLIT_PAGE_FAILED,
THP_DEFERRED_SPLIT_PAGE,
THP_SPLIT_PMD,
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+ THP_SPLIT_PUD,
+#endif
THP_ZERO_PAGE_ALLOC,
THP_ZERO_PAGE_ALLOC_FAILED,
#endif
diff --git a/include/linux/wait.h b/include/linux/wait.h
index aacb128..db076ca 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -620,30 +620,19 @@ do { \
__ret; \
})
+extern int do_wait_intr(wait_queue_head_t *, wait_queue_t *);
+extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *);
-#define __wait_event_interruptible_locked(wq, condition, exclusive, irq) \
+#define __wait_event_interruptible_locked(wq, condition, exclusive, fn) \
({ \
- int __ret = 0; \
+ int __ret; \
DEFINE_WAIT(__wait); \
if (exclusive) \
__wait.flags |= WQ_FLAG_EXCLUSIVE; \
do { \
- if (likely(list_empty(&__wait.task_list))) \
- __add_wait_queue_tail(&(wq), &__wait); \
- set_current_state(TASK_INTERRUPTIBLE); \
- if (signal_pending(current)) { \
- __ret = -ERESTARTSYS; \
+ __ret = fn(&(wq), &__wait); \
+ if (__ret) \
break; \
- } \
- if (irq) \
- spin_unlock_irq(&(wq).lock); \
- else \
- spin_unlock(&(wq).lock); \
- schedule(); \
- if (irq) \
- spin_lock_irq(&(wq).lock); \
- else \
- spin_lock(&(wq).lock); \
} while (!(condition)); \
__remove_wait_queue(&(wq), &__wait); \
__set_current_state(TASK_RUNNING); \
@@ -676,7 +665,7 @@ do { \
*/
#define wait_event_interruptible_locked(wq, condition) \
((condition) \
- ? 0 : __wait_event_interruptible_locked(wq, condition, 0, 0))
+ ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr))
/**
* wait_event_interruptible_locked_irq - sleep until a condition gets true
@@ -703,7 +692,7 @@ do { \
*/
#define wait_event_interruptible_locked_irq(wq, condition) \
((condition) \
- ? 0 : __wait_event_interruptible_locked(wq, condition, 0, 1))
+ ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr_irq))
/**
* wait_event_interruptible_exclusive_locked - sleep exclusively until a condition gets true
@@ -734,7 +723,7 @@ do { \
*/
#define wait_event_interruptible_exclusive_locked(wq, condition) \
((condition) \
- ? 0 : __wait_event_interruptible_locked(wq, condition, 1, 0))
+ ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr))
/**
* wait_event_interruptible_exclusive_locked_irq - sleep until a condition gets true
@@ -765,7 +754,7 @@ do { \
*/
#define wait_event_interruptible_exclusive_locked_irq(wq, condition) \
((condition) \
- ? 0 : __wait_event_interruptible_locked(wq, condition, 1, 1))
+ ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr_irq))
#define __wait_event_killable(wq, condition) \
diff --git a/include/media/vsp1.h b/include/media/vsp1.h
index 458b400..38aac55 100644
--- a/include/media/vsp1.h
+++ b/include/media/vsp1.h
@@ -20,8 +20,17 @@ struct device;
int vsp1_du_init(struct device *dev);
-int vsp1_du_setup_lif(struct device *dev, unsigned int width,
- unsigned int height);
+/**
+ * struct vsp1_du_lif_config - VSP LIF configuration
+ * @width: output frame width
+ * @height: output frame height
+ */
+struct vsp1_du_lif_config {
+ unsigned int width;
+ unsigned int height;
+};
+
+int vsp1_du_setup_lif(struct device *dev, const struct vsp1_du_lif_config *cfg);
struct vsp1_du_atomic_config {
u32 pixelformat;
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 17c6fd8..1aeb25d 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -262,8 +262,8 @@ int register_inet6addr_notifier(struct notifier_block *nb);
int unregister_inet6addr_notifier(struct notifier_block *nb);
int inet6addr_notifier_call_chain(unsigned long val, void *v);
-void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
- struct ipv6_devconf *devconf);
+void inet6_netconf_notify_devconf(struct net *net, int event, int type,
+ int ifindex, struct ipv6_devconf *devconf);
/**
* __in6_dev_get - get inet6_dev pointer from netdevice
diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
index 1061a47..b5f5187 100644
--- a/include/net/af_rxrpc.h
+++ b/include/net/af_rxrpc.h
@@ -39,7 +39,7 @@ int rxrpc_kernel_send_data(struct socket *, struct rxrpc_call *,
struct msghdr *, size_t);
int rxrpc_kernel_recv_data(struct socket *, struct rxrpc_call *,
void *, size_t, size_t *, bool, u32 *);
-void rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *,
+bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *,
u32, int, const char *);
void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *);
void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *,
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index f275896..f32ed9a 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -100,6 +100,9 @@ struct vsock_transport {
void (*destruct)(struct vsock_sock *);
void (*release)(struct vsock_sock *);
+ /* Cancel all pending packets sent on vsock. */
+ int (*cancel_pkt)(struct vsock_sock *vsk);
+
/* Connections. */
int (*connect)(struct vsock_sock *);
diff --git a/include/net/bonding.h b/include/net/bonding.h
index 3c85777..04a21e8 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -153,7 +153,8 @@ struct slave {
unsigned long last_link_up;
unsigned long last_rx;
unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS];
- s8 link; /* one of BOND_LINK_XXXX */
+ s8 link; /* one of BOND_LINK_XXXX */
+ s8 link_new_state; /* one of BOND_LINK_XXXX */
s8 new_link;
u8 backup:1, /* indicates backup slave. Value corresponds with
BOND_STATE_ACTIVE and BOND_STATE_BACKUP */
@@ -165,7 +166,7 @@ struct slave {
u32 link_failure_count;
u32 speed;
u16 queue_id;
- u8 perm_hwaddr[ETH_ALEN];
+ u8 perm_hwaddr[MAX_ADDR_LEN];
struct ad_slave_info *ad_info;
struct tlb_slave_info tlb_info;
#ifdef CONFIG_NET_POLL_CONTROLLER
@@ -401,6 +402,16 @@ static inline bool bond_slave_can_tx(struct slave *slave)
bond_is_active_slave(slave);
}
+static inline void bond_hw_addr_copy(u8 *dst, const u8 *src, unsigned int len)
+{
+ if (len == ETH_ALEN) {
+ ether_addr_copy(dst, src);
+ return;
+ }
+
+ memcpy(dst, src, len);
+}
+
#define BOND_PRI_RESELECT_ALWAYS 0
#define BOND_PRI_RESELECT_BETTER 1
#define BOND_PRI_RESELECT_FAILURE 2
@@ -504,13 +515,17 @@ static inline bool bond_is_slave_inactive(struct slave *slave)
return slave->inactive;
}
-static inline void bond_set_slave_link_state(struct slave *slave, int state,
- bool notify)
+static inline void bond_propose_link_state(struct slave *slave, int state)
{
- if (slave->link == state)
+ slave->link_new_state = state;
+}
+
+static inline void bond_commit_link_state(struct slave *slave, bool notify)
+{
+ if (slave->link == slave->link_new_state)
return;
- slave->link = state;
+ slave->link = slave->link_new_state;
if (notify) {
bond_queue_slave_event(slave);
bond_lower_state_changed(slave);
@@ -523,6 +538,13 @@ static inline void bond_set_slave_link_state(struct slave *slave, int state,
}
}
+static inline void bond_set_slave_link_state(struct slave *slave, int state,
+ bool notify)
+{
+ bond_propose_link_state(slave, state);
+ bond_commit_link_state(slave, notify);
+}
+
static inline void bond_slave_link_notify(struct bonding *bond)
{
struct list_head *iter;
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index c0452de..8ffd434 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -35,49 +35,27 @@ struct napi_struct;
extern unsigned int sysctl_net_busy_read __read_mostly;
extern unsigned int sysctl_net_busy_poll __read_mostly;
+/* 0 - Reserved to indicate value not set
+ * 1..NR_CPUS - Reserved for sender_cpu
+ * NR_CPUS+1..~0 - Region available for NAPI IDs
+ */
+#define MIN_NAPI_ID ((unsigned int)(NR_CPUS + 1))
+
static inline bool net_busy_loop_on(void)
{
return sysctl_net_busy_poll;
}
-static inline u64 busy_loop_us_clock(void)
-{
- return local_clock() >> 10;
-}
-
-static inline unsigned long sk_busy_loop_end_time(struct sock *sk)
-{
- return busy_loop_us_clock() + ACCESS_ONCE(sk->sk_ll_usec);
-}
-
-/* in poll/select we use the global sysctl_net_ll_poll value */
-static inline unsigned long busy_loop_end_time(void)
-{
- return busy_loop_us_clock() + ACCESS_ONCE(sysctl_net_busy_poll);
-}
-
static inline bool sk_can_busy_loop(const struct sock *sk)
{
- return sk->sk_ll_usec && sk->sk_napi_id && !signal_pending(current);
+ return sk->sk_ll_usec && !signal_pending(current);
}
+bool sk_busy_loop_end(void *p, unsigned long start_time);
-static inline bool busy_loop_timeout(unsigned long end_time)
-{
- unsigned long now = busy_loop_us_clock();
-
- return time_after(now, end_time);
-}
-
-bool sk_busy_loop(struct sock *sk, int nonblock);
-
-/* used in the NIC receive handler to mark the skb */
-static inline void skb_mark_napi_id(struct sk_buff *skb,
- struct napi_struct *napi)
-{
- skb->napi_id = napi->napi_id;
-}
-
+void napi_busy_loop(unsigned int napi_id,
+ bool (*loop_end)(void *, unsigned long),
+ void *loop_end_arg);
#else /* CONFIG_NET_RX_BUSY_POLL */
static inline unsigned long net_busy_loop_on(void)
@@ -85,32 +63,72 @@ static inline unsigned long net_busy_loop_on(void)
return 0;
}
-static inline unsigned long busy_loop_end_time(void)
-{
- return 0;
-}
-
static inline bool sk_can_busy_loop(struct sock *sk)
{
return false;
}
-static inline void skb_mark_napi_id(struct sk_buff *skb,
- struct napi_struct *napi)
+#endif /* CONFIG_NET_RX_BUSY_POLL */
+
+static inline unsigned long busy_loop_current_time(void)
{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+ return (unsigned long)(local_clock() >> 10);
+#else
+ return 0;
+#endif
}
-static inline bool busy_loop_timeout(unsigned long end_time)
+/* in poll/select we use the global sysctl_net_ll_poll value */
+static inline bool busy_loop_timeout(unsigned long start_time)
{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+ unsigned long bp_usec = READ_ONCE(sysctl_net_busy_poll);
+
+ if (bp_usec) {
+ unsigned long end_time = start_time + bp_usec;
+ unsigned long now = busy_loop_current_time();
+
+ return time_after(now, end_time);
+ }
+#endif
return true;
}
-static inline bool sk_busy_loop(struct sock *sk, int nonblock)
+static inline bool sk_busy_loop_timeout(struct sock *sk,
+ unsigned long start_time)
{
- return false;
+#ifdef CONFIG_NET_RX_BUSY_POLL
+ unsigned long bp_usec = READ_ONCE(sk->sk_ll_usec);
+
+ if (bp_usec) {
+ unsigned long end_time = start_time + bp_usec;
+ unsigned long now = busy_loop_current_time();
+
+ return time_after(now, end_time);
+ }
+#endif
+ return true;
}
-#endif /* CONFIG_NET_RX_BUSY_POLL */
+static inline void sk_busy_loop(struct sock *sk, int nonblock)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+ unsigned int napi_id = READ_ONCE(sk->sk_napi_id);
+
+ if (napi_id >= MIN_NAPI_ID)
+ napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk);
+#endif
+}
+
+/* used in the NIC receive handler to mark the skb */
+static inline void skb_mark_napi_id(struct sk_buff *skb,
+ struct napi_struct *napi)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+ skb->napi_id = napi->napi_id;
+#endif
+}
/* used in the protocol hanlder to propagate the napi_id to the socket */
static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb)
diff --git a/include/net/devlink.h b/include/net/devlink.h
index d29e5fc..24de13f 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -25,6 +25,8 @@ struct devlink {
struct list_head list;
struct list_head port_list;
struct list_head sb_list;
+ struct list_head dpipe_table_list;
+ struct devlink_dpipe_headers *dpipe_headers;
const struct devlink_ops *ops;
struct device *dev;
possible_net_t _net;
@@ -49,6 +51,178 @@ struct devlink_sb_pool_info {
enum devlink_sb_threshold_type threshold_type;
};
+/**
+ * struct devlink_dpipe_field - dpipe field object
+ * @name: field name
+ * @id: index inside the headers field array
+ * @bitwidth: bitwidth
+ * @mapping_type: mapping type
+ */
+struct devlink_dpipe_field {
+ const char *name;
+ unsigned int id;
+ unsigned int bitwidth;
+ enum devlink_dpipe_field_mapping_type mapping_type;
+};
+
+/**
+ * struct devlink_dpipe_header - dpipe header object
+ * @name: header name
+ * @id: index, global/local detrmined by global bit
+ * @fields: fields
+ * @fields_count: number of fields
+ * @global: indicates if header is shared like most protocol header
+ * or driver specific
+ */
+struct devlink_dpipe_header {
+ const char *name;
+ unsigned int id;
+ struct devlink_dpipe_field *fields;
+ unsigned int fields_count;
+ bool global;
+};
+
+/**
+ * struct devlink_dpipe_match - represents match operation
+ * @type: type of match
+ * @header_index: header index (packets can have several headers of same
+ * type like in case of tunnels)
+ * @header: header
+ * @fieled_id: field index
+ */
+struct devlink_dpipe_match {
+ enum devlink_dpipe_match_type type;
+ unsigned int header_index;
+ struct devlink_dpipe_header *header;
+ unsigned int field_id;
+};
+
+/**
+ * struct devlink_dpipe_action - represents action operation
+ * @type: type of action
+ * @header_index: header index (packets can have several headers of same
+ * type like in case of tunnels)
+ * @header: header
+ * @fieled_id: field index
+ */
+struct devlink_dpipe_action {
+ enum devlink_dpipe_action_type type;
+ unsigned int header_index;
+ struct devlink_dpipe_header *header;
+ unsigned int field_id;
+};
+
+/**
+ * struct devlink_dpipe_value - represents value of match/action
+ * @action: action
+ * @match: match
+ * @mapping_value: in case the field has some mapping this value
+ * specified the mapping value
+ * @mapping_valid: specify if mapping value is valid
+ * @value_size: value size
+ * @value: value
+ * @mask: bit mask
+ */
+struct devlink_dpipe_value {
+ union {
+ struct devlink_dpipe_action *action;
+ struct devlink_dpipe_match *match;
+ };
+ unsigned int mapping_value;
+ bool mapping_valid;
+ unsigned int value_size;
+ void *value;
+ void *mask;
+};
+
+/**
+ * struct devlink_dpipe_entry - table entry object
+ * @index: index of the entry in the table
+ * @match_values: match values
+ * @matche_values_count: count of matches tuples
+ * @action_values: actions values
+ * @action_values_count: count of actions values
+ * @counter: value of counter
+ * @counter_valid: Specify if value is valid from hardware
+ */
+struct devlink_dpipe_entry {
+ u64 index;
+ struct devlink_dpipe_value *match_values;
+ unsigned int match_values_count;
+ struct devlink_dpipe_value *action_values;
+ unsigned int action_values_count;
+ u64 counter;
+ bool counter_valid;
+};
+
+/**
+ * struct devlink_dpipe_dump_ctx - context provided to driver in order
+ * to dump
+ * @info: info
+ * @cmd: devlink command
+ * @skb: skb
+ * @nest: top attribute
+ * @hdr: hdr
+ */
+struct devlink_dpipe_dump_ctx {
+ struct genl_info *info;
+ enum devlink_command cmd;
+ struct sk_buff *skb;
+ struct nlattr *nest;
+ void *hdr;
+};
+
+struct devlink_dpipe_table_ops;
+
+/**
+ * struct devlink_dpipe_table - table object
+ * @priv: private
+ * @name: table name
+ * @size: maximum number of entries
+ * @counters_enabled: indicates if counters are active
+ * @counter_control_extern: indicates if counter control is in dpipe or
+ * external tool
+ * @table_ops: table operations
+ * @rcu: rcu
+ */
+struct devlink_dpipe_table {
+ void *priv;
+ struct list_head list;
+ const char *name;
+ u64 size;
+ bool counters_enabled;
+ bool counter_control_extern;
+ struct devlink_dpipe_table_ops *table_ops;
+ struct rcu_head rcu;
+};
+
+/**
+ * struct devlink_dpipe_table_ops - dpipe_table ops
+ * @actions_dump - dumps all tables actions
+ * @matches_dump - dumps all tables matches
+ * @entries_dump - dumps all active entries in the table
+ * @counters_set_update - when changing the counter status hardware sync
+ * maybe needed to allocate/free counter related
+ * resources
+ */
+struct devlink_dpipe_table_ops {
+ int (*actions_dump)(void *priv, struct sk_buff *skb);
+ int (*matches_dump)(void *priv, struct sk_buff *skb);
+ int (*entries_dump)(void *priv, bool counters_enabled,
+ struct devlink_dpipe_dump_ctx *dump_ctx);
+ int (*counters_set_update)(void *priv, bool enable);
+};
+
+/**
+ * struct devlink_dpipe_headers - dpipe headers
+ * @headers - header array can be shared (global bit) or driver specific
+ * @headers_count - count of headers
+ */
+struct devlink_dpipe_headers {
+ struct devlink_dpipe_header **headers;
+ unsigned int headers_count;
+};
+
struct devlink_ops {
int (*port_type_set)(struct devlink_port *devlink_port,
enum devlink_port_type port_type);
@@ -132,6 +306,26 @@ int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
u16 egress_pools_count, u16 ingress_tc_count,
u16 egress_tc_count);
void devlink_sb_unregister(struct devlink *devlink, unsigned int sb_index);
+int devlink_dpipe_table_register(struct devlink *devlink,
+ const char *table_name,
+ struct devlink_dpipe_table_ops *table_ops,
+ void *priv, u64 size,
+ bool counter_control_extern);
+void devlink_dpipe_table_unregister(struct devlink *devlink,
+ const char *table_name);
+int devlink_dpipe_headers_register(struct devlink *devlink,
+ struct devlink_dpipe_headers *dpipe_headers);
+void devlink_dpipe_headers_unregister(struct devlink *devlink);
+bool devlink_dpipe_table_counter_enabled(struct devlink *devlink,
+ const char *table_name);
+int devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx);
+int devlink_dpipe_entry_ctx_append(struct devlink_dpipe_dump_ctx *dump_ctx,
+ struct devlink_dpipe_entry *entry);
+int devlink_dpipe_entry_ctx_close(struct devlink_dpipe_dump_ctx *dump_ctx);
+int devlink_dpipe_action_put(struct sk_buff *skb,
+ struct devlink_dpipe_action *action);
+int devlink_dpipe_match_put(struct sk_buff *skb,
+ struct devlink_dpipe_match *match);
#else
@@ -200,6 +394,71 @@ static inline void devlink_sb_unregister(struct devlink *devlink,
{
}
+static inline int
+devlink_dpipe_table_register(struct devlink *devlink,
+ const char *table_name,
+ struct devlink_dpipe_table_ops *table_ops,
+ void *priv, u64 size,
+ bool counter_control_extern)
+{
+ return 0;
+}
+
+static inline void devlink_dpipe_table_unregister(struct devlink *devlink,
+ const char *table_name)
+{
+}
+
+static inline int devlink_dpipe_headers_register(struct devlink *devlink,
+ struct devlink_dpipe_headers *
+ dpipe_headers)
+{
+ return 0;
+}
+
+static inline void devlink_dpipe_headers_unregister(struct devlink *devlink)
+{
+}
+
+static inline bool devlink_dpipe_table_counter_enabled(struct devlink *devlink,
+ const char *table_name)
+{
+ return false;
+}
+
+static inline int
+devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+ return 0;
+}
+
+static inline int
+devlink_dpipe_entry_ctx_append(struct devlink_dpipe_dump_ctx *dump_ctx,
+ struct devlink_dpipe_entry *entry)
+{
+ return 0;
+}
+
+static inline int
+devlink_dpipe_entry_ctx_close(struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+ return 0;
+}
+
+static inline int
+devlink_dpipe_action_put(struct sk_buff *skb,
+ struct devlink_dpipe_action *action)
+{
+ return 0;
+}
+
+static inline int
+devlink_dpipe_match_put(struct sk_buff *skb,
+ struct devlink_dpipe_match *match)
+{
+ return 0;
+}
+
#endif
#endif /* _NET_DEVLINK_H_ */
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 4e13e69..9b1c1eb 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -19,6 +19,7 @@
#include <linux/workqueue.h>
#include <linux/of.h>
#include <linux/ethtool.h>
+#include <net/devlink.h>
struct tc_action;
struct phy_device;
@@ -31,6 +32,7 @@ enum dsa_tag_protocol {
DSA_TAG_PROTO_EDSA,
DSA_TAG_PROTO_BRCM,
DSA_TAG_PROTO_QCA,
+ DSA_TAG_PROTO_MTK,
DSA_TAG_LAST, /* MUST BE LAST */
};
@@ -122,7 +124,7 @@ struct dsa_switch_tree {
* protocol to use.
*/
struct net_device *master_netdev;
- int (*rcv)(struct sk_buff *skb,
+ struct sk_buff * (*rcv)(struct sk_buff *skb,
struct net_device *dev,
struct packet_type *pt,
struct net_device *orig_dev);
@@ -182,6 +184,7 @@ struct dsa_port {
unsigned int ageing_time;
u8 stp_state;
struct net_device *bridge_dev;
+ struct devlink_port devlink_port;
};
struct dsa_switch {
@@ -233,6 +236,13 @@ struct dsa_switch {
u32 phys_mii_mask;
struct mii_bus *slave_mii_bus;
+ /* Ageing Time limits in msecs */
+ unsigned int ageing_time_min;
+ unsigned int ageing_time_max;
+
+ /* devlink used to represent this switch device */
+ struct devlink *devlink;
+
/* Dynamically allocated ports, keep last */
size_t num_ports;
struct dsa_port ports[];
@@ -248,6 +258,11 @@ static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p)
return !!((ds->dsa_port_mask) & (1 << p));
}
+static inline bool dsa_is_normal_port(struct dsa_switch *ds, int p)
+{
+ return !dsa_is_cpu_port(ds, p) && !dsa_is_dsa_port(ds, p);
+}
+
static inline bool dsa_is_port_initialized(struct dsa_switch *ds, int p)
{
return ds->enabled_port_mask & (1 << p) && ds->ports[p].netdev;
@@ -442,6 +457,14 @@ struct dsa_switch_ops {
bool ingress);
void (*port_mirror_del)(struct dsa_switch *ds, int port,
struct dsa_mall_mirror_tc_entry *mirror);
+
+ /*
+ * Cross-chip operations
+ */
+ int (*crosschip_bridge_join)(struct dsa_switch *ds, int sw_index,
+ int port, struct net_device *br);
+ void (*crosschip_bridge_leave)(struct dsa_switch *ds, int sw_index,
+ int port, struct net_device *br);
};
struct dsa_switch_driver {
@@ -459,6 +482,15 @@ static inline bool dsa_uses_tagged_protocol(struct dsa_switch_tree *dst)
return dst->rcv != NULL;
}
+static inline bool netdev_uses_dsa(struct net_device *dev)
+{
+#if IS_ENABLED(CONFIG_NET_DSA)
+ if (dev->dsa_ptr != NULL)
+ return dsa_uses_tagged_protocol(dev->dsa_ptr);
+#endif
+ return false;
+}
+
struct dsa_switch *dsa_switch_alloc(struct device *dev, size_t n);
void dsa_unregister_switch(struct dsa_switch *ds);
int dsa_register_switch(struct dsa_switch *ds, struct device *dev);
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 8dbfdf7..1243b9c 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -141,6 +141,7 @@ int fib_rules_lookup(struct fib_rules_ops *, struct flowi *, int flags,
struct fib_lookup_arg *);
int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table,
u32 flags);
+bool fib_rule_matchall(const struct fib_rule *rule);
int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh);
int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh);
diff --git a/include/net/flow.h b/include/net/flow.h
index 6984f19..bae198b 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -202,7 +202,7 @@ static inline struct flowi *flowidn_to_flowi(struct flowidn *fldn)
typedef unsigned long flow_compare_t;
-static inline size_t flow_key_size(u16 family)
+static inline unsigned int flow_key_size(u16 family)
{
switch (family) {
case AF_INET:
diff --git a/include/net/flowcache.h b/include/net/flowcache.h
index 9caf3bf..51eb971 100644
--- a/include/net/flowcache.h
+++ b/include/net/flowcache.h
@@ -8,7 +8,7 @@
struct flow_cache_percpu {
struct hlist_head *hash_table;
- int hash_count;
+ unsigned int hash_count;
u32 hash_rnd;
int hash_rnd_recalc;
struct tasklet_struct flush_tasklet;
@@ -18,8 +18,8 @@ struct flow_cache {
u32 hash_shift;
struct flow_cache_percpu __percpu *percpu;
struct hlist_node node;
- int low_watermark;
- int high_watermark;
+ unsigned int low_watermark;
+ unsigned int high_watermark;
struct timer_list rnd_timer;
};
#endif /* _NET_FLOWCACHE_H */
diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index b7952d5..f39ae69 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -20,7 +20,8 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
int addr_len, int flags, int is_sendmsg);
int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr,
int addr_len, int flags);
-int inet_accept(struct socket *sock, struct socket *newsock, int flags);
+int inet_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern);
int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size);
ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
size_t size, int flags);
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 826f198..c7a5779 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -258,7 +258,7 @@ inet_csk_rto_backoff(const struct inet_connection_sock *icsk,
return (unsigned long)min_t(u64, when, max_when);
}
-struct sock *inet_csk_accept(struct sock *sk, int flags, int *err);
+struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern);
int inet_csk_get_port(struct sock *sk, unsigned short snum);
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 368bb40..6692c57 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -213,6 +213,11 @@ struct fib_entry_notifier_info {
u32 tb_id;
};
+struct fib_rule_notifier_info {
+ struct fib_notifier_info info; /* must be first */
+ struct fib_rule *rule;
+};
+
struct fib_nh_notifier_info {
struct fib_notifier_info info; /* must be first */
struct fib_nh *fib_nh;
@@ -232,9 +237,21 @@ enum fib_event_type {
int register_fib_notifier(struct notifier_block *nb,
void (*cb)(struct notifier_block *nb));
int unregister_fib_notifier(struct notifier_block *nb);
+int call_fib_notifier(struct notifier_block *nb, struct net *net,
+ enum fib_event_type event_type,
+ struct fib_notifier_info *info);
int call_fib_notifiers(struct net *net, enum fib_event_type event_type,
struct fib_notifier_info *info);
+void fib_notify(struct net *net, struct notifier_block *nb);
+#ifdef CONFIG_IP_MULTIPLE_TABLES
+void fib_rules_notify(struct net *net, struct notifier_block *nb);
+#else
+static inline void fib_rules_notify(struct net *net, struct notifier_block *nb)
+{
+}
+#endif
+
struct fib_table {
struct hlist_node tb_hlist;
u32 tb_id;
@@ -299,6 +316,11 @@ static inline int fib_lookup(struct net *net, const struct flowi4 *flp,
return err;
}
+static inline bool fib4_rule_default(const struct fib_rule *rule)
+{
+ return true;
+}
+
#else /* CONFIG_IP_MULTIPLE_TABLES */
int __net_init fib4_rules_init(struct net *net);
void __net_exit fib4_rules_exit(struct net *net);
@@ -343,6 +365,8 @@ static inline int fib_lookup(struct net *net, struct flowi4 *flp,
return err;
}
+bool fib4_rule_default(const struct fib_rule *rule);
+
#endif /* CONFIG_IP_MULTIPLE_TABLES */
/* Exported by fib_frontend.c */
@@ -371,17 +395,13 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force);
int fib_sync_down_addr(struct net_device *dev, __be32 local);
int fib_sync_up(struct net_device *dev, unsigned int nh_flags);
-extern u32 fib_multipath_secret __read_mostly;
-
-static inline int fib_multipath_hash(__be32 saddr, __be32 daddr)
-{
- return jhash_2words((__force u32)saddr, (__force u32)daddr,
- fib_multipath_secret) >> 1;
-}
-
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
+ const struct sk_buff *skb);
+#endif
void fib_select_multipath(struct fib_result *res, int hash);
void fib_select_path(struct net *net, struct fib_result *res,
- struct flowi4 *fl4, int mp_hash);
+ struct flowi4 *fl4, const struct sk_buff *skb);
/* Exported by fib_trie.c */
void fib_trie_init(void);
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 7bdfa7d..8a4a57b8 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -12,6 +12,8 @@
#include <linux/list.h> /* for struct list_head */
#include <linux/spinlock.h> /* for struct rwlock_t */
#include <linux/atomic.h> /* for struct atomic_t */
+#include <linux/refcount.h> /* for struct refcount_t */
+
#include <linux/compiler.h>
#include <linux/timer.h>
#include <linux/bug.h>
@@ -525,7 +527,7 @@ struct ip_vs_conn {
struct netns_ipvs *ipvs;
/* counter and timer */
- atomic_t refcnt; /* reference count */
+ refcount_t refcnt; /* reference count */
struct timer_list timer; /* Expiration timer */
volatile unsigned long timeout; /* timeout */
@@ -667,7 +669,7 @@ struct ip_vs_dest {
atomic_t conn_flags; /* flags to copy to conn */
atomic_t weight; /* server weight */
- atomic_t refcnt; /* reference counter */
+ refcount_t refcnt; /* reference counter */
struct ip_vs_stats stats; /* statistics */
unsigned long idle_start; /* start time, jiffies */
@@ -1211,14 +1213,14 @@ struct ip_vs_conn * ip_vs_conn_out_get_proto(struct netns_ipvs *ipvs, int af,
*/
static inline bool __ip_vs_conn_get(struct ip_vs_conn *cp)
{
- return atomic_inc_not_zero(&cp->refcnt);
+ return refcount_inc_not_zero(&cp->refcnt);
}
/* put back the conn without restarting its timer */
static inline void __ip_vs_conn_put(struct ip_vs_conn *cp)
{
smp_mb__before_atomic();
- atomic_dec(&cp->refcnt);
+ refcount_dec(&cp->refcnt);
}
void ip_vs_conn_put(struct ip_vs_conn *cp);
void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport);
@@ -1410,18 +1412,18 @@ void ip_vs_try_bind_dest(struct ip_vs_conn *cp);
static inline void ip_vs_dest_hold(struct ip_vs_dest *dest)
{
- atomic_inc(&dest->refcnt);
+ refcount_inc(&dest->refcnt);
}
static inline void ip_vs_dest_put(struct ip_vs_dest *dest)
{
smp_mb__before_atomic();
- atomic_dec(&dest->refcnt);
+ refcount_dec(&dest->refcnt);
}
static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest)
{
- if (atomic_dec_and_test(&dest->refcnt))
+ if (refcount_dec_and_test(&dest->refcnt))
kfree(dest);
}
diff --git a/include/net/irda/timer.h b/include/net/irda/timer.h
index cb2615c..d784f24 100644
--- a/include/net/irda/timer.h
+++ b/include/net/irda/timer.h
@@ -59,7 +59,7 @@ struct lap_cb;
* Slot timer must never exceed 85 ms, and must always be at least 25 ms,
* suggested to 75-85 msec by IrDA lite. This doesn't work with a lot of
* devices, and other stackes uses a lot more, so it's best we do it as well
- * (Note : this is the default value and sysctl overides it - Jean II)
+ * (Note : this is the default value and sysctl overrides it - Jean II)
*/
#define SLOT_TIMEOUT (90*HZ/1000)
diff --git a/include/net/mpls_iptunnel.h b/include/net/mpls_iptunnel.h
index 179253f..9d22bf6 100644
--- a/include/net/mpls_iptunnel.h
+++ b/include/net/mpls_iptunnel.h
@@ -14,11 +14,12 @@
#ifndef _NET_MPLS_IPTUNNEL_H
#define _NET_MPLS_IPTUNNEL_H 1
-#define MAX_NEW_LABELS 2
-
struct mpls_iptunnel_encap {
- u32 label[MAX_NEW_LABELS];
u8 labels;
+ u8 ttl_propagate;
+ u8 default_ttl;
+ u8 reserved1;
+ u32 label[0];
};
static inline struct mpls_iptunnel_encap *mpls_lwtunnel_encap(struct lwtunnel_state *lwtstate)
diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index 8a02146..1036c90 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -439,8 +439,10 @@ void ndisc_update(const struct net_device *dev, struct neighbour *neigh,
* IGMP
*/
int igmp6_init(void);
+int igmp6_late_init(void);
void igmp6_cleanup(void);
+void igmp6_late_cleanup(void);
int igmp6_event_query(struct sk_buff *skb);
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 5ebf694..9496179 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -314,7 +314,8 @@ static inline struct neighbour *neigh_create(struct neigh_table *tbl,
}
void neigh_destroy(struct neighbour *neigh);
int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb);
-int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags);
+int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags,
+ u32 nlmsg_pid);
void __neigh_set_probe_once(struct neighbour *neigh);
void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev);
int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index af8fe8a..fe80bb4 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -27,6 +27,7 @@
#include <net/netns/nftables.h>
#include <net/netns/xfrm.h>
#include <net/netns/mpls.h>
+#include <net/netns/can.h>
#include <linux/ns_common.h>
#include <linux/idr.h>
#include <linux/skbuff.h>
@@ -141,6 +142,9 @@ struct net {
#if IS_ENABLED(CONFIG_MPLS)
struct netns_mpls mpls;
#endif
+#if IS_ENABLED(CONFIG_CAN)
+ struct netns_can can;
+#endif
struct sock *diag_nlsk;
atomic_t fnhe_genid;
};
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index f540f9a..19605878 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -244,7 +244,7 @@ extern s32 (*nf_ct_nat_offset)(const struct nf_conn *ct,
u32 seq);
/* Fake conntrack entry for untracked connections */
-DECLARE_PER_CPU(struct nf_conn, nf_conntrack_untracked);
+DECLARE_PER_CPU_ALIGNED(struct nf_conn, nf_conntrack_untracked);
static inline struct nf_conn *nf_ct_untracked_get(void)
{
return raw_cpu_ptr(&nf_conntrack_untracked);
diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h
index 5ed33ea..65cc2cb 100644
--- a/include/net/netfilter/nf_conntrack_expect.h
+++ b/include/net/netfilter/nf_conntrack_expect.h
@@ -5,6 +5,8 @@
#ifndef _NF_CONNTRACK_EXPECT_H
#define _NF_CONNTRACK_EXPECT_H
+#include <linux/refcount.h>
+
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_zones.h>
@@ -37,7 +39,7 @@ struct nf_conntrack_expect {
struct timer_list timeout;
/* Usage count. */
- atomic_t use;
+ refcount_t use;
/* Flags */
unsigned int flags;
diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h
index 5cc5e9e..d40b893 100644
--- a/include/net/netfilter/nf_conntrack_timeout.h
+++ b/include/net/netfilter/nf_conntrack_timeout.h
@@ -4,6 +4,7 @@
#include <net/net_namespace.h>
#include <linux/netfilter/nf_conntrack_common.h>
#include <linux/netfilter/nf_conntrack_tuple_common.h>
+#include <linux/refcount.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_extend.h>
@@ -12,7 +13,7 @@
struct ctnl_timeout {
struct list_head head;
struct rcu_head rcu_head;
- atomic_t refcnt;
+ refcount_t refcnt;
char name[CTNL_TIMEOUT_NAME_MAX];
__u16 l3num;
struct nf_conntrack_l4proto *l4proto;
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 2aa8a9d..f713a05 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -103,6 +103,35 @@ struct nft_regs {
};
};
+/* Store/load an u16 or u8 integer to/from the u32 data register.
+ *
+ * Note, when using concatenations, register allocation happens at 32-bit
+ * level. So for store instruction, pad the rest part with zero to avoid
+ * garbage values.
+ */
+
+static inline void nft_reg_store16(u32 *dreg, u16 val)
+{
+ *dreg = 0;
+ *(u16 *)dreg = val;
+}
+
+static inline void nft_reg_store8(u32 *dreg, u8 val)
+{
+ *dreg = 0;
+ *(u8 *)dreg = val;
+}
+
+static inline u16 nft_reg_load16(u32 *sreg)
+{
+ return *(u16 *)sreg;
+}
+
+static inline u8 nft_reg_load8(u32 *sreg)
+{
+ return *(u8 *)sreg;
+}
+
static inline void nft_data_copy(u32 *dst, const struct nft_data *src,
unsigned int len)
{
@@ -203,7 +232,6 @@ struct nft_set_elem {
struct nft_set;
struct nft_set_iter {
u8 genmask;
- bool flush;
unsigned int count;
unsigned int skip;
int err;
@@ -385,10 +413,11 @@ static inline struct nft_set *nft_set_container_of(const void *priv)
return (void *)priv - offsetof(struct nft_set, data);
}
-struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
- const struct nlattr *nla, u8 genmask);
-struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
- const struct nlattr *nla, u8 genmask);
+struct nft_set *nft_set_lookup(const struct net *net,
+ const struct nft_table *table,
+ const struct nlattr *nla_set_name,
+ const struct nlattr *nla_set_id,
+ u8 genmask);
static inline unsigned long nft_set_gc_interval(const struct nft_set *set)
{
@@ -1016,7 +1045,8 @@ struct nft_object_type {
unsigned int maxattr;
struct module *owner;
const struct nla_policy *policy;
- int (*init)(const struct nlattr * const tb[],
+ int (*init)(const struct nft_ctx *ctx,
+ const struct nlattr *const tb[],
struct nft_object *obj);
void (*destroy)(struct nft_object *obj);
int (*dump)(struct sk_buff *skb,
diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h
index d150b50..97983d1 100644
--- a/include/net/netfilter/nf_tables_ipv6.h
+++ b/include/net/netfilter/nf_tables_ipv6.h
@@ -9,12 +9,13 @@ nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
+ unsigned int flags = IP6_FH_F_AUTH;
int protohdr, thoff = 0;
unsigned short frag_off;
nft_set_pktinfo(pkt, skb, state);
- protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, NULL);
+ protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags);
if (protohdr < 0) {
nft_set_pktinfo_proto_unspec(pkt, skb);
return;
@@ -32,6 +33,7 @@ __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt,
const struct nf_hook_state *state)
{
#if IS_ENABLED(CONFIG_IPV6)
+ unsigned int flags = IP6_FH_F_AUTH;
struct ipv6hdr *ip6h, _ip6h;
unsigned int thoff = 0;
unsigned short frag_off;
@@ -50,7 +52,7 @@ __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt,
if (pkt_len + sizeof(*ip6h) > skb->len)
return -1;
- protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, NULL);
+ protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags);
if (protohdr < 0)
return -1;
diff --git a/include/net/netfilter/nft_fib.h b/include/net/netfilter/nft_fib.h
index 5ceb220..381af94 100644
--- a/include/net/netfilter/nft_fib.h
+++ b/include/net/netfilter/nft_fib.h
@@ -32,6 +32,6 @@ void nft_fib6_eval_type(const struct nft_expr *expr, struct nft_regs *regs,
void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
const struct nft_pktinfo *pkt);
-void nft_fib_store_result(void *reg, enum nft_fib_result r,
+void nft_fib_store_result(void *reg, const struct nft_fib *priv,
const struct nft_pktinfo *pkt, int index);
#endif
diff --git a/include/net/netns/can.h b/include/net/netns/can.h
new file mode 100644
index 0000000..e8beba7
--- /dev/null
+++ b/include/net/netns/can.h
@@ -0,0 +1,31 @@
+/*
+ * can in net namespaces
+ */
+
+#ifndef __NETNS_CAN_H__
+#define __NETNS_CAN_H__
+
+#include <linux/spinlock.h>
+
+struct dev_rcv_lists;
+
+struct netns_can {
+#if IS_ENABLED(CONFIG_PROC_FS)
+ struct proc_dir_entry *proc_dir;
+ struct proc_dir_entry *pde_version;
+ struct proc_dir_entry *pde_stats;
+ struct proc_dir_entry *pde_reset_stats;
+ struct proc_dir_entry *pde_rcvlist_all;
+ struct proc_dir_entry *pde_rcvlist_fil;
+ struct proc_dir_entry *pde_rcvlist_inv;
+ struct proc_dir_entry *pde_rcvlist_sff;
+ struct proc_dir_entry *pde_rcvlist_eff;
+ struct proc_dir_entry *pde_rcvlist_err;
+#endif
+
+ /* receive filters subscribed for 'all' CAN devices */
+ struct dev_rcv_lists *can_rx_alldev_list;
+ spinlock_t can_rcvlists_lock;
+};
+
+#endif /* __NETNS_CAN_H__ */
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 622d2da..cd686c4 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -33,7 +33,6 @@ struct inet_timewait_death_row {
atomic_t tw_count;
struct inet_hashinfo *hashinfo ____cacheline_aligned_in_smp;
- int sysctl_tw_recycle;
int sysctl_max_tw_buckets;
};
@@ -96,6 +95,8 @@ struct netns_ipv4 {
/* Shall we try to damage output packets if routing dev changes? */
int sysctl_ip_dynaddr;
int sysctl_ip_early_demux;
+ int sysctl_tcp_early_demux;
+ int sysctl_udp_early_demux;
int sysctl_fwmark_reflect;
int sysctl_tcp_fwmark_accept;
@@ -152,6 +153,7 @@ struct netns_ipv4 {
#endif
#ifdef CONFIG_IP_ROUTE_MULTIPATH
int sysctl_fib_multipath_use_neigh;
+ int sysctl_fib_multipath_hash_policy;
#endif
unsigned int fib_seq; /* protected by rtnl_mutex */
diff --git a/include/net/netns/mpls.h b/include/net/netns/mpls.h
index d292036..6608b36 100644
--- a/include/net/netns/mpls.h
+++ b/include/net/netns/mpls.h
@@ -9,8 +9,11 @@ struct mpls_route;
struct ctl_table_header;
struct netns_mpls {
+ int ip_ttl_propagate;
+ int default_ttl;
size_t platform_labels;
struct mpls_route __rcu * __rcu *platform_label;
+
struct ctl_table_header *ctl;
};
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index f1b76b8..bec46f6 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -92,7 +92,7 @@ int unregister_qdisc(struct Qdisc_ops *qops);
void qdisc_get_default(char *id, size_t len);
int qdisc_set_default(const char *id);
-void qdisc_hash_add(struct Qdisc *q);
+void qdisc_hash_add(struct Qdisc *q, bool invisible);
void qdisc_hash_del(struct Qdisc *q);
struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle);
struct Qdisc *qdisc_lookup_class(struct net_device *dev, u32 handle);
diff --git a/include/net/protocol.h b/include/net/protocol.h
index bf36ca3..65ba335 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -40,6 +40,7 @@
/* This is used to register protocols. */
struct net_protocol {
void (*early_demux)(struct sk_buff *skb);
+ void (*early_demux_handler)(struct sk_buff *skb);
int (*handler)(struct sk_buff *skb);
void (*err_handler)(struct sk_buff *skb, u32 info);
unsigned int no_policy:1,
@@ -54,7 +55,7 @@ struct net_protocol {
#if IS_ENABLED(CONFIG_IPV6)
struct inet6_protocol {
void (*early_demux)(struct sk_buff *skb);
-
+ void (*early_demux_handler)(struct sk_buff *skb);
int (*handler)(struct sk_buff *skb);
void (*err_handler)(struct sk_buff *skb,
@@ -92,12 +93,12 @@ struct inet_protosw {
#define INET_PROTOSW_PERMANENT 0x02 /* Permanent protocols are unremovable. */
#define INET_PROTOSW_ICSK 0x04 /* Is this an inet_connection_sock? */
-extern const struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS];
+extern struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS];
extern const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS];
extern const struct net_offload __rcu *inet6_offloads[MAX_INET_PROTOS];
#if IS_ENABLED(CONFIG_IPV6)
-extern const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS];
+extern struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS];
#endif
int inet_add_protocol(const struct net_protocol *prot, unsigned char num);
diff --git a/include/net/route.h b/include/net/route.h
index c0874c8..2cc0e14 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -113,13 +113,13 @@ struct in_device;
int ip_rt_init(void);
void rt_cache_flush(struct net *net);
void rt_flush_dev(struct net_device *dev);
-struct rtable *__ip_route_output_key_hash(struct net *, struct flowi4 *flp,
- int mp_hash);
+struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *flp,
+ const struct sk_buff *skb);
static inline struct rtable *__ip_route_output_key(struct net *net,
struct flowi4 *flp)
{
- return __ip_route_output_key_hash(net, flp, -1);
+ return __ip_route_output_key_hash(net, flp, NULL);
}
struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp,
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index aeec408..65d5026 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -66,6 +66,7 @@ struct Qdisc {
#define TCQ_F_NOPARENT 0x40 /* root of its hierarchy :
* qdisc_tree_decrease_qlen() should stop.
*/
+#define TCQ_F_INVISIBLE 0x80 /* invisible by default in dump */
u32 limit;
const struct Qdisc_ops *ops;
struct qdisc_size_table __rcu *stab;
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 1f71ee5..069582e 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -448,10 +448,9 @@ static inline int sctp_frag_point(const struct sctp_association *asoc, int pmtu)
return frag;
}
-static inline void sctp_assoc_pending_pmtu(struct sock *sk, struct sctp_association *asoc)
+static inline void sctp_assoc_pending_pmtu(struct sctp_association *asoc)
{
-
- sctp_assoc_sync_pmtu(sk, asoc);
+ sctp_assoc_sync_pmtu(asoc);
asoc->pmtu_pending = 0;
}
@@ -596,12 +595,23 @@ static inline void sctp_v4_map_v6(union sctp_addr *addr)
*/
static inline struct dst_entry *sctp_transport_dst_check(struct sctp_transport *t)
{
- if (t->dst && (!dst_check(t->dst, t->dst_cookie) ||
- t->pathmtu != max_t(size_t, SCTP_TRUNC4(dst_mtu(t->dst)),
- SCTP_DEFAULT_MINSEGMENT)))
+ if (t->dst && !dst_check(t->dst, t->dst_cookie))
sctp_transport_dst_release(t);
return t->dst;
}
+static inline bool sctp_transport_pmtu_check(struct sctp_transport *t)
+{
+ __u32 pmtu = max_t(size_t, SCTP_TRUNC4(dst_mtu(t->dst)),
+ SCTP_DEFAULT_MINSEGMENT);
+
+ if (t->pathmtu == pmtu)
+ return true;
+
+ t->pathmtu = pmtu;
+
+ return false;
+}
+
#endif /* __net_sctp_h__ */
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index b6f682e..47113f2 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -293,6 +293,22 @@ struct sctp_chunk *sctp_process_strreset_inreq(
struct sctp_association *asoc,
union sctp_params param,
struct sctp_ulpevent **evp);
+struct sctp_chunk *sctp_process_strreset_tsnreq(
+ struct sctp_association *asoc,
+ union sctp_params param,
+ struct sctp_ulpevent **evp);
+struct sctp_chunk *sctp_process_strreset_addstrm_out(
+ struct sctp_association *asoc,
+ union sctp_params param,
+ struct sctp_ulpevent **evp);
+struct sctp_chunk *sctp_process_strreset_addstrm_in(
+ struct sctp_association *asoc,
+ union sctp_params param,
+ struct sctp_ulpevent **evp);
+struct sctp_chunk *sctp_process_strreset_resp(
+ struct sctp_association *asoc,
+ union sctp_params param,
+ struct sctp_ulpevent **evp);
/* Prototypes for statetable processing. */
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index a244db5..b751399 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -83,6 +83,7 @@ struct sctp_bind_addr;
struct sctp_ulpq;
struct sctp_ep_common;
struct crypto_shash;
+struct sctp_stream;
#include <net/sctp/tsnmap.h>
@@ -376,7 +377,8 @@ typedef struct sctp_sender_hb_info {
__u64 hb_nonce;
} sctp_sender_hb_info_t;
-struct sctp_stream *sctp_stream_new(__u16 incnt, __u16 outcnt, gfp_t gfp);
+int sctp_stream_new(struct sctp_association *asoc, gfp_t gfp);
+int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp);
void sctp_stream_free(struct sctp_stream *stream);
void sctp_stream_clear(struct sctp_stream *stream);
@@ -476,7 +478,8 @@ struct sctp_pf {
int (*send_verify) (struct sctp_sock *, union sctp_addr *);
int (*supported_addrs)(const struct sctp_sock *, __be16 *);
struct sock *(*create_accept_sk) (struct sock *sk,
- struct sctp_association *asoc);
+ struct sctp_association *asoc,
+ bool kern);
int (*addr_to_user)(struct sctp_sock *sk, union sctp_addr *addr);
void (*to_sk_saddr)(union sctp_addr *, struct sock *sk);
void (*to_sk_daddr)(union sctp_addr *, struct sock *sk);
@@ -497,7 +500,6 @@ struct sctp_datamsg {
/* Did the messenge fail to send? */
int send_error;
u8 send_failed:1,
- force_delay:1,
can_delay; /* should this message be Nagle delayed */
};
@@ -752,6 +754,8 @@ struct sctp_transport {
/* Is the Path MTU update pending on this tranport */
pmtu_pending:1,
+ dst_pending_confirm:1, /* need to confirm neighbour */
+
/* Has this transport moved the ctsn since we last sacked */
sack_generation:1;
u32 dst_cookie;
@@ -805,8 +809,6 @@ struct sctp_transport {
__u32 burst_limited; /* Holds old cwnd when max.burst is applied */
- __u32 dst_pending_confirm; /* need to confirm neighbour */
-
/* Destination */
struct dst_entry *dst;
/* Source address. */
@@ -950,8 +952,8 @@ void sctp_transport_lower_cwnd(struct sctp_transport *, sctp_lower_cwnd_t);
void sctp_transport_burst_limited(struct sctp_transport *);
void sctp_transport_burst_reset(struct sctp_transport *);
unsigned long sctp_transport_timeout(struct sctp_transport *);
-void sctp_transport_reset(struct sctp_transport *);
-void sctp_transport_update_pmtu(struct sock *, struct sctp_transport *, u32);
+void sctp_transport_reset(struct sctp_transport *t);
+void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu);
void sctp_transport_immediate_rtx(struct sctp_transport *);
void sctp_transport_dst_release(struct sctp_transport *t);
void sctp_transport_dst_confirm(struct sctp_transport *t);
@@ -1313,6 +1315,8 @@ struct sctp_inithdr_host {
struct sctp_stream_out {
__u16 ssn;
__u8 state;
+ __u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1];
+ __u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1];
};
struct sctp_stream_in {
@@ -1876,6 +1880,7 @@ struct sctp_association {
__u8 need_ecne:1, /* Need to send an ECNE Chunk? */
temp:1, /* Is it a temporary association? */
+ force_delay:1,
prsctp_enable:1,
reconf_enable:1;
@@ -1951,7 +1956,7 @@ void sctp_assoc_update(struct sctp_association *old,
__u32 sctp_association_get_next_tsn(struct sctp_association *);
-void sctp_assoc_sync_pmtu(struct sock *, struct sctp_association *);
+void sctp_assoc_sync_pmtu(struct sctp_association *asoc);
void sctp_assoc_rwnd_increase(struct sctp_association *, unsigned int);
void sctp_assoc_rwnd_decrease(struct sctp_association *, unsigned int);
void sctp_assoc_set_primary(struct sctp_association *,
diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h
index 324b596..1060494 100644
--- a/include/net/sctp/ulpevent.h
+++ b/include/net/sctp/ulpevent.h
@@ -132,6 +132,14 @@ struct sctp_ulpevent *sctp_ulpevent_make_stream_reset_event(
const struct sctp_association *asoc, __u16 flags,
__u16 stream_num, __u16 *stream_list, gfp_t gfp);
+struct sctp_ulpevent *sctp_ulpevent_make_assoc_reset_event(
+ const struct sctp_association *asoc, __u16 flags,
+ __u32 local_tsn, __u32 remote_tsn, gfp_t gfp);
+
+struct sctp_ulpevent *sctp_ulpevent_make_stream_change_event(
+ const struct sctp_association *asoc, __u16 flags,
+ __u32 strchange_instrms, __u32 strchange_outstrms, gfp_t gfp);
+
void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event,
struct msghdr *);
void sctp_ulpevent_read_rcvinfo(const struct sctp_ulpevent *event,
diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h
index 0caee63..fe236b3 100644
--- a/include/net/secure_seq.h
+++ b/include/net/secure_seq.h
@@ -6,10 +6,10 @@
u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport);
u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
__be16 dport);
-u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
+u32 secure_tcp_seq_and_tsoff(__be32 saddr, __be32 daddr,
+ __be16 sport, __be16 dport, u32 *tsoff);
+u32 secure_tcpv6_seq_and_tsoff(const __be32 *saddr, const __be32 *daddr,
__be16 sport, __be16 dport, u32 *tsoff);
-u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
- __be16 sport, __be16 dport, u32 *tsoff);
u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
__be16 sport, __be16 dport);
u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
diff --git a/include/net/sock.h b/include/net/sock.h
index 5e59976..66349e4 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -236,6 +236,7 @@ struct sock_common {
* @sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN
* @sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings
* @sk_lock: synchronizer
+ * @sk_kern_sock: True if sock is using kernel lock classes
* @sk_rcvbuf: size of receive buffer in bytes
* @sk_wq: sock wait queue and async head
* @sk_rx_dst: receive input route used by early demux
@@ -430,7 +431,8 @@ struct sock {
#endif
kmemcheck_bitfield_begin(flags);
- unsigned int sk_padding : 2,
+ unsigned int sk_padding : 1,
+ sk_kern_sock : 1,
sk_no_check_tx : 1,
sk_no_check_rx : 1,
sk_userlocks : 4,
@@ -1015,7 +1017,8 @@ struct proto {
int addr_len);
int (*disconnect)(struct sock *sk, int flags);
- struct sock * (*accept)(struct sock *sk, int flags, int *err);
+ struct sock * (*accept)(struct sock *sk, int flags, int *err,
+ bool kern);
int (*ioctl)(struct sock *sk, int cmd,
unsigned long arg);
@@ -1573,7 +1576,7 @@ int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
int sock_no_bind(struct socket *, struct sockaddr *, int);
int sock_no_connect(struct socket *, struct sockaddr *, int, int);
int sock_no_socketpair(struct socket *, struct socket *);
-int sock_no_accept(struct socket *, struct socket *, int);
+int sock_no_accept(struct socket *, struct socket *, int, bool);
int sock_no_getname(struct socket *, struct sockaddr *, int *, int);
unsigned int sock_no_poll(struct file *, struct socket *,
struct poll_table_struct *);
@@ -1780,11 +1783,8 @@ __sk_dst_set(struct sock *sk, struct dst_entry *dst)
sk_tx_queue_clear(sk);
sk->sk_dst_pending_confirm = 0;
- /*
- * This can be called while sk is owned by the caller only,
- * with no state that can be checked in a rcu_dereference_check() cond
- */
- old_dst = rcu_dereference_raw(sk->sk_dst_cache);
+ old_dst = rcu_dereference_protected(sk->sk_dst_cache,
+ lockdep_sock_is_held(sk));
rcu_assign_pointer(sk->sk_dst_cache, dst);
dst_release(old_dst);
}
@@ -2239,6 +2239,7 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
struct sk_buff *skb);
+#define SK_DEFAULT_STAMP (-1L * NSEC_PER_SEC)
static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
struct sk_buff *skb)
{
@@ -2249,8 +2250,10 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY)
__sock_recv_ts_and_drops(msg, sk, skb);
- else
+ else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP)))
sk->sk_stamp = skb->tstamp;
+ else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP))
+ sk->sk_stamp = 0;
}
void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags);
@@ -2362,6 +2365,8 @@ bool sk_ns_capable(const struct sock *sk,
bool sk_capable(const struct sock *sk, int cap);
bool sk_net_capable(const struct sock *sk, int cap);
+void sk_get_meminfo(const struct sock *sk, u32 *meminfo);
+
extern __u32 sysctl_wmem_max;
extern __u32 sysctl_rmem_max;
diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h
index dfbd6ee..a46c3f2 100644
--- a/include/net/tc_act/tc_pedit.h
+++ b/include/net/tc_act/tc_pedit.h
@@ -2,6 +2,7 @@
#define __NET_TC_PED_H
#include <net/act_api.h>
+#include <linux/tc_act/tc_pedit.h>
struct tcf_pedit_key_ex {
enum pedit_header_type htype;
@@ -17,4 +18,48 @@ struct tcf_pedit {
};
#define to_pedit(a) ((struct tcf_pedit *)a)
+static inline bool is_tcf_pedit(const struct tc_action *a)
+{
+#ifdef CONFIG_NET_CLS_ACT
+ if (a->ops && a->ops->type == TCA_ACT_PEDIT)
+ return true;
+#endif
+ return false;
+}
+
+static inline int tcf_pedit_nkeys(const struct tc_action *a)
+{
+ return to_pedit(a)->tcfp_nkeys;
+}
+
+static inline u32 tcf_pedit_htype(const struct tc_action *a, int index)
+{
+ if (to_pedit(a)->tcfp_keys_ex)
+ return to_pedit(a)->tcfp_keys_ex[index].htype;
+
+ return TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK;
+}
+
+static inline u32 tcf_pedit_cmd(const struct tc_action *a, int index)
+{
+ if (to_pedit(a)->tcfp_keys_ex)
+ return to_pedit(a)->tcfp_keys_ex[index].cmd;
+
+ return __PEDIT_CMD_MAX;
+}
+
+static inline u32 tcf_pedit_mask(const struct tc_action *a, int index)
+{
+ return to_pedit(a)->tcfp_keys[index].mask;
+}
+
+static inline u32 tcf_pedit_val(const struct tc_action *a, int index)
+{
+ return to_pedit(a)->tcfp_keys[index].val;
+}
+
+static inline u32 tcf_pedit_offset(const struct tc_action *a, int index)
+{
+ return to_pedit(a)->tcfp_keys[index].off;
+}
#endif /* __NET_TC_PED_H */
diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h
index 48cca32..c2090df 100644
--- a/include/net/tc_act/tc_vlan.h
+++ b/include/net/tc_act/tc_vlan.h
@@ -13,9 +13,6 @@
#include <net/act_api.h>
#include <linux/tc_act/tc_vlan.h>
-#define VLAN_F_POP 0x1
-#define VLAN_F_PUSH 0x2
-
struct tcf_vlan {
struct tc_action common;
int tcfv_action;
@@ -49,4 +46,9 @@ static inline __be16 tcf_vlan_push_proto(const struct tc_action *a)
return to_vlan(a)->tcfv_push_proto;
}
+static inline u8 tcf_vlan_push_prio(const struct tc_action *a)
+{
+ return to_vlan(a)->tcfv_push_prio;
+}
+
#endif /* __NET_TC_VLAN_H */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6ec4ea6..cc6ae0a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -78,6 +78,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
/* Maximal number of ACKs sent quickly to accelerate slow-start. */
#define TCP_MAX_QUICKACKS 16U
+/* Maximal number of window scale according to RFC1323 */
+#define TCP_MAX_WSCALE 14U
+
/* urg_data states */
#define TCP_URG_VALID 0x0100
#define TCP_URG_NOTYET 0x0200
@@ -406,11 +409,7 @@ void tcp_clear_retrans(struct tcp_sock *tp);
void tcp_update_metrics(struct sock *sk);
void tcp_init_metrics(struct sock *sk);
void tcp_metrics_init(void);
-bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst,
- bool paws_check, bool timestamps);
-bool tcp_remember_stamp(struct sock *sk);
-bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw);
-void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst);
+bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
void tcp_disable_fack(struct tcp_sock *tp);
void tcp_close(struct sock *sk, long timeout);
void tcp_init_sock(struct sock *sk);
@@ -1252,9 +1251,11 @@ void tcp_select_initial_window(int __space, __u32 mss, __u32 *rcv_wnd,
static inline int tcp_win_from_space(int space)
{
- return sysctl_tcp_adv_win_scale<=0 ?
- (space>>(-sysctl_tcp_adv_win_scale)) :
- space - (space>>sysctl_tcp_adv_win_scale);
+ int tcp_adv_win_scale = sysctl_tcp_adv_win_scale;
+
+ return tcp_adv_win_scale <= 0 ?
+ (space>>(-tcp_adv_win_scale)) :
+ space - (space>>tcp_adv_win_scale);
}
/* Note: caller must be prepared to deal with negative returns */
@@ -1814,9 +1815,8 @@ struct tcp_request_sock_ops {
__u16 *mss);
#endif
struct dst_entry *(*route_req)(const struct sock *sk, struct flowi *fl,
- const struct request_sock *req,
- bool *strict);
- __u32 (*init_seq)(const struct sk_buff *skb, u32 *tsoff);
+ const struct request_sock *req);
+ __u32 (*init_seq_tsoff)(const struct sk_buff *skb, u32 *tsoff);
int (*send_synack)(const struct sock *sk, struct dst_entry *dst,
struct flowi *fl, struct request_sock *req,
struct tcp_fastopen_cookie *foc,
diff --git a/include/net/udp.h b/include/net/udp.h
index c9d8b8e..3391dbd 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -372,4 +372,5 @@ void udp_encap_enable(void);
#if IS_ENABLED(CONFIG_IPV6)
void udpv6_encap_enable(void);
#endif
+
#endif /* _UDP_H */
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 0f1813c..99e4423 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1863,6 +1863,9 @@ struct ib_port_immutable {
};
struct ib_device {
+ /* Do not access @dma_device directly from ULP nor from HW drivers. */
+ struct device *dma_device;
+
char name[IB_DEVICE_NAME_MAX];
struct list_head event_handler_list;
@@ -3007,7 +3010,7 @@ static inline int ib_req_ncomp_notif(struct ib_cq *cq, int wc_cnt)
*/
static inline int ib_dma_mapping_error(struct ib_device *dev, u64 dma_addr)
{
- return dma_mapping_error(&dev->dev, dma_addr);
+ return dma_mapping_error(dev->dma_device, dma_addr);
}
/**
@@ -3021,7 +3024,7 @@ static inline u64 ib_dma_map_single(struct ib_device *dev,
void *cpu_addr, size_t size,
enum dma_data_direction direction)
{
- return dma_map_single(&dev->dev, cpu_addr, size, direction);
+ return dma_map_single(dev->dma_device, cpu_addr, size, direction);
}
/**
@@ -3035,7 +3038,7 @@ static inline void ib_dma_unmap_single(struct ib_device *dev,
u64 addr, size_t size,
enum dma_data_direction direction)
{
- dma_unmap_single(&dev->dev, addr, size, direction);
+ dma_unmap_single(dev->dma_device, addr, size, direction);
}
/**
@@ -3052,7 +3055,7 @@ static inline u64 ib_dma_map_page(struct ib_device *dev,
size_t size,
enum dma_data_direction direction)
{
- return dma_map_page(&dev->dev, page, offset, size, direction);
+ return dma_map_page(dev->dma_device, page, offset, size, direction);
}
/**
@@ -3066,7 +3069,7 @@ static inline void ib_dma_unmap_page(struct ib_device *dev,
u64 addr, size_t size,
enum dma_data_direction direction)
{
- dma_unmap_page(&dev->dev, addr, size, direction);
+ dma_unmap_page(dev->dma_device, addr, size, direction);
}
/**
@@ -3080,7 +3083,7 @@ static inline int ib_dma_map_sg(struct ib_device *dev,
struct scatterlist *sg, int nents,
enum dma_data_direction direction)
{
- return dma_map_sg(&dev->dev, sg, nents, direction);
+ return dma_map_sg(dev->dma_device, sg, nents, direction);
}
/**
@@ -3094,7 +3097,7 @@ static inline void ib_dma_unmap_sg(struct ib_device *dev,
struct scatterlist *sg, int nents,
enum dma_data_direction direction)
{
- dma_unmap_sg(&dev->dev, sg, nents, direction);
+ dma_unmap_sg(dev->dma_device, sg, nents, direction);
}
static inline int ib_dma_map_sg_attrs(struct ib_device *dev,
@@ -3102,7 +3105,8 @@ static inline int ib_dma_map_sg_attrs(struct ib_device *dev,
enum dma_data_direction direction,
unsigned long dma_attrs)
{
- return dma_map_sg_attrs(&dev->dev, sg, nents, direction, dma_attrs);
+ return dma_map_sg_attrs(dev->dma_device, sg, nents, direction,
+ dma_attrs);
}
static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev,
@@ -3110,7 +3114,7 @@ static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev,
enum dma_data_direction direction,
unsigned long dma_attrs)
{
- dma_unmap_sg_attrs(&dev->dev, sg, nents, direction, dma_attrs);
+ dma_unmap_sg_attrs(dev->dma_device, sg, nents, direction, dma_attrs);
}
/**
* ib_sg_dma_address - Return the DMA address from a scatter/gather entry
@@ -3152,7 +3156,7 @@ static inline void ib_dma_sync_single_for_cpu(struct ib_device *dev,
size_t size,
enum dma_data_direction dir)
{
- dma_sync_single_for_cpu(&dev->dev, addr, size, dir);
+ dma_sync_single_for_cpu(dev->dma_device, addr, size, dir);
}
/**
@@ -3167,7 +3171,7 @@ static inline void ib_dma_sync_single_for_device(struct ib_device *dev,
size_t size,
enum dma_data_direction dir)
{
- dma_sync_single_for_device(&dev->dev, addr, size, dir);
+ dma_sync_single_for_device(dev->dma_device, addr, size, dir);
}
/**
@@ -3182,7 +3186,7 @@ static inline void *ib_dma_alloc_coherent(struct ib_device *dev,
dma_addr_t *dma_handle,
gfp_t flag)
{
- return dma_alloc_coherent(&dev->dev, size, dma_handle, flag);
+ return dma_alloc_coherent(dev->dma_device, size, dma_handle, flag);
}
/**
@@ -3196,7 +3200,7 @@ static inline void ib_dma_free_coherent(struct ib_device *dev,
size_t size, void *cpu_addr,
dma_addr_t dma_handle)
{
- dma_free_coherent(&dev->dev, size, cpu_addr, dma_handle);
+ dma_free_coherent(dev->dma_device, size, cpu_addr, dma_handle);
}
/**
diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h
index b0e275d..583875e 100644
--- a/include/scsi/libiscsi.h
+++ b/include/scsi/libiscsi.h
@@ -196,6 +196,7 @@ struct iscsi_conn {
struct iscsi_task *task; /* xmit task in progress */
/* xmit */
+ spinlock_t taskqueuelock; /* protects the next three lists */
struct list_head mgmtqueue; /* mgmt (control) xmit queue */
struct list_head cmdqueue; /* data-path cmd queue */
struct list_head requeue; /* tasks needing another run */
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 6f22b39..080c7ce 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -472,6 +472,10 @@ static inline int scsi_device_created(struct scsi_device *sdev)
sdev->sdev_state == SDEV_CREATED_BLOCK;
}
+int scsi_internal_device_block(struct scsi_device *sdev, bool wait);
+int scsi_internal_device_unblock(struct scsi_device *sdev,
+ enum scsi_device_state new_state);
+
/* accessor functions for the SCSI parameters */
static inline int scsi_device_sync(struct scsi_device *sdev)
{
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index b54b98d..1b0f447 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -4,7 +4,12 @@
#include <linux/types.h>
#include <target/target_core_base.h>
-#define TRANSPORT_FLAG_PASSTHROUGH 1
+#define TRANSPORT_FLAG_PASSTHROUGH 0x1
+/*
+ * ALUA commands, state checks and setup operations are handled by the
+ * backend module.
+ */
+#define TRANSPORT_FLAG_PASSTHROUGH_ALUA 0x2
struct request_queue;
struct scatterlist;
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 37c274e..4b784b6 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -299,7 +299,7 @@ struct t10_alua_tg_pt_gp {
struct list_head tg_pt_gp_lun_list;
struct se_lun *tg_pt_gp_alua_lun;
struct se_node_acl *tg_pt_gp_alua_nacl;
- struct delayed_work tg_pt_gp_transition_work;
+ struct work_struct tg_pt_gp_transition_work;
struct completion *tg_pt_gp_transition_complete;
};
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 39123c0..29a3d53 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -683,6 +683,57 @@ TRACE_EVENT(rxrpc_rx_ack,
__entry->n_acks)
);
+TRACE_EVENT(rxrpc_rx_abort,
+ TP_PROTO(struct rxrpc_call *call, rxrpc_serial_t serial,
+ u32 abort_code),
+
+ TP_ARGS(call, serial, abort_code),
+
+ TP_STRUCT__entry(
+ __field(struct rxrpc_call *, call )
+ __field(rxrpc_serial_t, serial )
+ __field(u32, abort_code )
+ ),
+
+ TP_fast_assign(
+ __entry->call = call;
+ __entry->serial = serial;
+ __entry->abort_code = abort_code;
+ ),
+
+ TP_printk("c=%p ABORT %08x ac=%d",
+ __entry->call,
+ __entry->serial,
+ __entry->abort_code)
+ );
+
+TRACE_EVENT(rxrpc_rx_rwind_change,
+ TP_PROTO(struct rxrpc_call *call, rxrpc_serial_t serial,
+ u32 rwind, bool wake),
+
+ TP_ARGS(call, serial, rwind, wake),
+
+ TP_STRUCT__entry(
+ __field(struct rxrpc_call *, call )
+ __field(rxrpc_serial_t, serial )
+ __field(u32, rwind )
+ __field(bool, wake )
+ ),
+
+ TP_fast_assign(
+ __entry->call = call;
+ __entry->serial = serial;
+ __entry->rwind = rwind;
+ __entry->wake = wake;
+ ),
+
+ TP_printk("c=%p %08x rw=%u%s",
+ __entry->call,
+ __entry->serial,
+ __entry->rwind,
+ __entry->wake ? " wake" : "")
+ );
+
TRACE_EVENT(rxrpc_tx_data,
TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq,
rxrpc_serial_t serial, u8 flags, bool retrans, bool lose),
@@ -1087,6 +1138,56 @@ TRACE_EVENT(rxrpc_improper_term,
__entry->abort_code)
);
+TRACE_EVENT(rxrpc_rx_eproto,
+ TP_PROTO(struct rxrpc_call *call, rxrpc_serial_t serial,
+ const char *why),
+
+ TP_ARGS(call, serial, why),
+
+ TP_STRUCT__entry(
+ __field(struct rxrpc_call *, call )
+ __field(rxrpc_serial_t, serial )
+ __field(const char *, why )
+ ),
+
+ TP_fast_assign(
+ __entry->call = call;
+ __entry->serial = serial;
+ __entry->why = why;
+ ),
+
+ TP_printk("c=%p EPROTO %08x %s",
+ __entry->call,
+ __entry->serial,
+ __entry->why)
+ );
+
+TRACE_EVENT(rxrpc_connect_call,
+ TP_PROTO(struct rxrpc_call *call),
+
+ TP_ARGS(call),
+
+ TP_STRUCT__entry(
+ __field(struct rxrpc_call *, call )
+ __field(unsigned long, user_call_ID )
+ __field(u32, cid )
+ __field(u32, call_id )
+ ),
+
+ TP_fast_assign(
+ __entry->call = call;
+ __entry->user_call_ID = call->user_call_ID;
+ __entry->cid = call->cid;
+ __entry->call_id = call->call_id;
+ ),
+
+ TP_printk("c=%p u=%p %08x:%08x",
+ __entry->call,
+ (void *)__entry->user_call_ID,
+ __entry->cid,
+ __entry->call_id)
+ );
+
#endif /* _TRACE_RXRPC_H */
/* This part must be outside protection */
diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h
index 14e49c7..b35533b 100644
--- a/include/trace/events/syscalls.h
+++ b/include/trace/events/syscalls.h
@@ -1,5 +1,6 @@
#undef TRACE_SYSTEM
#define TRACE_SYSTEM raw_syscalls
+#undef TRACE_INCLUDE_FILE
#define TRACE_INCLUDE_FILE syscalls
#if !defined(_TRACE_EVENTS_SYSCALLS_H) || defined(TRACE_HEADER_MULTI_READ)
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 2c748dd..2b48856 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -94,4 +94,10 @@
#define SCM_TIMESTAMPING_OPT_STATS 54
+#define SO_MEMINFO 55
+
+#define SO_INCOMING_NAPI_ID 56
+
+#define SO_COOKIE 57
+
#endif /* __ASM_GENERIC_SOCKET_H */
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 9b1462e..a076cf1 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -730,9 +730,11 @@ __SYSCALL(__NR_pkey_mprotect, sys_pkey_mprotect)
__SYSCALL(__NR_pkey_alloc, sys_pkey_alloc)
#define __NR_pkey_free 290
__SYSCALL(__NR_pkey_free, sys_pkey_free)
+#define __NR_statx 291
+__SYSCALL(__NR_statx, sys_statx)
#undef __NR_syscalls
-#define __NR_syscalls 291
+#define __NR_syscalls 292
/*
* All syscalls below here should go away really,
diff --git a/include/uapi/drm/omap_drm.h b/include/uapi/drm/omap_drm.h
index 407cb55..7fb9786 100644
--- a/include/uapi/drm/omap_drm.h
+++ b/include/uapi/drm/omap_drm.h
@@ -33,8 +33,8 @@ extern "C" {
#define OMAP_PARAM_CHIPSET_ID 1 /* ie. 0x3430, 0x4430, etc */
struct drm_omap_param {
- uint64_t param; /* in */
- uint64_t value; /* in (set_param), out (get_param) */
+ __u64 param; /* in */
+ __u64 value; /* in (set_param), out (get_param) */
};
#define OMAP_BO_SCANOUT 0x00000001 /* scanout capable (phys contiguous) */
@@ -53,18 +53,18 @@ struct drm_omap_param {
#define OMAP_BO_TILED (OMAP_BO_TILED_8 | OMAP_BO_TILED_16 | OMAP_BO_TILED_32)
union omap_gem_size {
- uint32_t bytes; /* (for non-tiled formats) */
+ __u32 bytes; /* (for non-tiled formats) */
struct {
- uint16_t width;
- uint16_t height;
+ __u16 width;
+ __u16 height;
} tiled; /* (for tiled formats) */
};
struct drm_omap_gem_new {
union omap_gem_size size; /* in */
- uint32_t flags; /* in */
- uint32_t handle; /* out */
- uint32_t __pad;
+ __u32 flags; /* in */
+ __u32 handle; /* out */
+ __u32 __pad;
};
/* mask of operations: */
@@ -74,33 +74,33 @@ enum omap_gem_op {
};
struct drm_omap_gem_cpu_prep {
- uint32_t handle; /* buffer handle (in) */
- uint32_t op; /* mask of omap_gem_op (in) */
+ __u32 handle; /* buffer handle (in) */
+ __u32 op; /* mask of omap_gem_op (in) */
};
struct drm_omap_gem_cpu_fini {
- uint32_t handle; /* buffer handle (in) */
- uint32_t op; /* mask of omap_gem_op (in) */
+ __u32 handle; /* buffer handle (in) */
+ __u32 op; /* mask of omap_gem_op (in) */
/* TODO maybe here we pass down info about what regions are touched
* by sw so we can be clever about cache ops? For now a placeholder,
* set to zero and we just do full buffer flush..
*/
- uint32_t nregions;
- uint32_t __pad;
+ __u32 nregions;
+ __u32 __pad;
};
struct drm_omap_gem_info {
- uint32_t handle; /* buffer handle (in) */
- uint32_t pad;
- uint64_t offset; /* mmap offset (out) */
+ __u32 handle; /* buffer handle (in) */
+ __u32 pad;
+ __u64 offset; /* mmap offset (out) */
/* note: in case of tiled buffers, the user virtual size can be
* different from the physical size (ie. how many pages are needed
* to back the object) which is returned in DRM_IOCTL_GEM_OPEN..
* This size here is the one that should be used if you want to
* mmap() the buffer:
*/
- uint32_t size; /* virtual size for mmap'ing (out) */
- uint32_t __pad;
+ __u32 size; /* virtual size for mmap'ing (out) */
+ __u32 __pad;
};
#define DRM_OMAP_GET_PARAM 0x00
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0539a0c..a1d9538 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -81,6 +81,7 @@ enum bpf_cmd {
BPF_OBJ_GET,
BPF_PROG_ATTACH,
BPF_PROG_DETACH,
+ BPF_PROG_TEST_RUN,
};
enum bpf_map_type {
@@ -96,6 +97,8 @@ enum bpf_map_type {
BPF_MAP_TYPE_LRU_HASH,
BPF_MAP_TYPE_LRU_PERCPU_HASH,
BPF_MAP_TYPE_LPM_TRIE,
+ BPF_MAP_TYPE_ARRAY_OF_MAPS,
+ BPF_MAP_TYPE_HASH_OF_MAPS,
};
enum bpf_prog_type {
@@ -152,6 +155,7 @@ union bpf_attr {
__u32 value_size; /* size of value in bytes */
__u32 max_entries; /* max number of entries in a map */
__u32 map_flags; /* prealloc or not */
+ __u32 inner_map_fd; /* fd pointing to the inner map */
};
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -186,6 +190,17 @@ union bpf_attr {
__u32 attach_type;
__u32 attach_flags;
};
+
+ struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
+ __u32 prog_fd;
+ __u32 retval;
+ __u32 data_size_in;
+ __u32 data_size_out;
+ __aligned_u64 data_in;
+ __aligned_u64 data_out;
+ __u32 repeat;
+ __u32 duration;
+ } test;
} __attribute__((aligned(8)));
/* BPF helper function descriptions:
@@ -456,6 +471,18 @@ union bpf_attr {
* Return:
* > 0 length of the string including the trailing NUL on success
* < 0 error
+ *
+ * u64 bpf_bpf_get_socket_cookie(skb)
+ * Get the cookie for the socket stored inside sk_buff.
+ * @skb: pointer to skb
+ * Return: 8 Bytes non-decreasing number on success or 0 if the socket
+ * field is missing inside sk_buff
+ *
+ * u32 bpf_get_socket_uid(skb)
+ * Get the owner uid of the socket stored inside sk_buff.
+ * @skb: pointer to skb
+ * Return: uid of the socket owner on success or 0 if the socket pointer
+ * inside sk_buff is NULL
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -503,7 +530,9 @@ union bpf_attr {
FN(get_numa_node_id), \
FN(skb_change_head), \
FN(xdp_adjust_head), \
- FN(probe_read_str),
+ FN(probe_read_str), \
+ FN(get_socket_cookie), \
+ FN(get_socket_uid),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index db4c253..dcfc3a5 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -713,33 +713,6 @@ enum btrfs_err_code {
BTRFS_ERROR_DEV_ONLY_WRITABLE,
BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS
};
-/* An error code to error string mapping for the kernel
-* error codes
-*/
-static inline char *btrfs_err_str(enum btrfs_err_code err_code)
-{
- switch (err_code) {
- case BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET:
- return "unable to go below two devices on raid1";
- case BTRFS_ERROR_DEV_RAID10_MIN_NOT_MET:
- return "unable to go below four devices on raid10";
- case BTRFS_ERROR_DEV_RAID5_MIN_NOT_MET:
- return "unable to go below two devices on raid5";
- case BTRFS_ERROR_DEV_RAID6_MIN_NOT_MET:
- return "unable to go below three devices on raid6";
- case BTRFS_ERROR_DEV_TGT_REPLACE:
- return "unable to remove the dev_replace target dev";
- case BTRFS_ERROR_DEV_MISSING_NOT_FOUND:
- return "no missing devices found to remove";
- case BTRFS_ERROR_DEV_ONLY_WRITABLE:
- return "unable to remove the only writeable device";
- case BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS:
- return "add/delete/balance/replace/resize operation "\
- "in progress";
- default:
- return NULL;
- }
-}
#define BTRFS_IOC_SNAP_CREATE _IOW(BTRFS_IOCTL_MAGIC, 1, \
struct btrfs_ioctl_vol_args)
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 0f1f3a1..b47bee2 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -65,8 +65,12 @@ enum devlink_command {
#define DEVLINK_CMD_ESWITCH_MODE_SET /* obsolete, never use this! */ \
DEVLINK_CMD_ESWITCH_SET
- /* add new commands above here */
+ DEVLINK_CMD_DPIPE_TABLE_GET,
+ DEVLINK_CMD_DPIPE_ENTRIES_GET,
+ DEVLINK_CMD_DPIPE_HEADERS_GET,
+ DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET,
+ /* add new commands above here */
__DEVLINK_CMD_MAX,
DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
};
@@ -148,10 +152,71 @@ enum devlink_attr {
DEVLINK_ATTR_ESWITCH_MODE, /* u16 */
DEVLINK_ATTR_ESWITCH_INLINE_MODE, /* u8 */
+ DEVLINK_ATTR_DPIPE_TABLES, /* nested */
+ DEVLINK_ATTR_DPIPE_TABLE, /* nested */
+ DEVLINK_ATTR_DPIPE_TABLE_NAME, /* string */
+ DEVLINK_ATTR_DPIPE_TABLE_SIZE, /* u64 */
+ DEVLINK_ATTR_DPIPE_TABLE_MATCHES, /* nested */
+ DEVLINK_ATTR_DPIPE_TABLE_ACTIONS, /* nested */
+ DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED, /* u8 */
+
+ DEVLINK_ATTR_DPIPE_ENTRIES, /* nested */
+ DEVLINK_ATTR_DPIPE_ENTRY, /* nested */
+ DEVLINK_ATTR_DPIPE_ENTRY_INDEX, /* u64 */
+ DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES, /* nested */
+ DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES, /* nested */
+ DEVLINK_ATTR_DPIPE_ENTRY_COUNTER, /* u64 */
+
+ DEVLINK_ATTR_DPIPE_MATCH, /* nested */
+ DEVLINK_ATTR_DPIPE_MATCH_VALUE, /* nested */
+ DEVLINK_ATTR_DPIPE_MATCH_TYPE, /* u32 */
+
+ DEVLINK_ATTR_DPIPE_ACTION, /* nested */
+ DEVLINK_ATTR_DPIPE_ACTION_VALUE, /* nested */
+ DEVLINK_ATTR_DPIPE_ACTION_TYPE, /* u32 */
+
+ DEVLINK_ATTR_DPIPE_VALUE,
+ DEVLINK_ATTR_DPIPE_VALUE_MASK,
+ DEVLINK_ATTR_DPIPE_VALUE_MAPPING, /* u32 */
+
+ DEVLINK_ATTR_DPIPE_HEADERS, /* nested */
+ DEVLINK_ATTR_DPIPE_HEADER, /* nested */
+ DEVLINK_ATTR_DPIPE_HEADER_NAME, /* string */
+ DEVLINK_ATTR_DPIPE_HEADER_ID, /* u32 */
+ DEVLINK_ATTR_DPIPE_HEADER_FIELDS, /* nested */
+ DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, /* u8 */
+ DEVLINK_ATTR_DPIPE_HEADER_INDEX, /* u32 */
+
+ DEVLINK_ATTR_DPIPE_FIELD, /* nested */
+ DEVLINK_ATTR_DPIPE_FIELD_NAME, /* string */
+ DEVLINK_ATTR_DPIPE_FIELD_ID, /* u32 */
+ DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH, /* u32 */
+ DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE, /* u32 */
+
+ DEVLINK_ATTR_PAD,
+
/* add new attributes above here, update the policy in devlink.c */
__DEVLINK_ATTR_MAX,
DEVLINK_ATTR_MAX = __DEVLINK_ATTR_MAX - 1
};
+/* Mapping between internal resource described by the field and system
+ * structure
+ */
+enum devlink_dpipe_field_mapping_type {
+ DEVLINK_DPIPE_FIELD_MAPPING_TYPE_NONE,
+ DEVLINK_DPIPE_FIELD_MAPPING_TYPE_IFINDEX,
+};
+
+/* Match type - specify the type of the match */
+enum devlink_dpipe_match_type {
+ DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT,
+};
+
+/* Action type - specify the action type */
+enum devlink_dpipe_action_type {
+ DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY,
+};
+
#endif /* _UAPI_LINUX_DEVLINK_H_ */
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 3dc91a4..5f4ea28 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1487,6 +1487,7 @@ enum ethtool_link_mode_bit_indices {
*/
/* The forced speed, in units of 1Mb. All values 0 to INT_MAX are legal. */
+/* Update drivers/net/phy/phy.c:phy_speed_to_str() when adding new values */
#define SPEED_10 10
#define SPEED_100 100
#define SPEED_1000 1000
diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h
index 72a04a0..57d1edb 100644
--- a/include/uapi/linux/gtp.h
+++ b/include/uapi/linux/gtp.h
@@ -19,7 +19,8 @@ enum gtp_attrs {
GTPA_LINK,
GTPA_VERSION,
GTPA_TID, /* for GTPv0 only */
- GTPA_SGSN_ADDRESS,
+ GTPA_PEER_ADDRESS, /* Remote GSN peer, either SGSN or GGSN */
+#define GTPA_SGSN_ADDRESS GTPA_PEER_ADDRESS /* maintain legacy attr name */
GTPA_MS_ADDRESS,
GTPA_FLOW,
GTPA_NET_NS_FD,
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 320fc1e..8b405af 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -538,11 +538,18 @@ enum {
#define IFLA_PPP_MAX (__IFLA_PPP_MAX - 1)
/* GTP section */
+
+enum ifla_gtp_role {
+ GTP_ROLE_GGSN = 0,
+ GTP_ROLE_SGSN,
+};
+
enum {
IFLA_GTP_UNSPEC,
IFLA_GTP_FD0,
IFLA_GTP_FD1,
IFLA_GTP_PDP_HASHSIZE,
+ IFLA_GTP_ROLE,
__IFLA_GTP_MAX,
};
#define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1)
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index d8f6a1a..2ae5917 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -184,6 +184,7 @@ enum {
DEVCONF_ENHANCED_DAD,
DEVCONF_ADDR_GEN_MODE,
DEVCONF_DISABLE_POLICY,
+ DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN,
DEVCONF_MAX
};
diff --git a/include/uapi/linux/mpls_iptunnel.h b/include/uapi/linux/mpls_iptunnel.h
index d80a049..f5e4509 100644
--- a/include/uapi/linux/mpls_iptunnel.h
+++ b/include/uapi/linux/mpls_iptunnel.h
@@ -16,11 +16,13 @@
/* MPLS tunnel attributes
* [RTA_ENCAP] = {
* [MPLS_IPTUNNEL_DST]
+ * [MPLS_IPTUNNEL_TTL]
* }
*/
enum {
MPLS_IPTUNNEL_UNSPEC,
MPLS_IPTUNNEL_DST,
+ MPLS_IPTUNNEL_TTL,
__MPLS_IPTUNNEL_MAX,
};
#define MPLS_IPTUNNEL_MAX (__MPLS_IPTUNNEL_MAX - 1)
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 05215d3..8f38426 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -816,6 +816,17 @@ enum nft_rt_keys {
};
/**
+ * enum nft_hash_types - nf_tables hash expression types
+ *
+ * @NFT_HASH_JENKINS: Jenkins Hash
+ * @NFT_HASH_SYM: Symmetric Hash
+ */
+enum nft_hash_types {
+ NFT_HASH_JENKINS,
+ NFT_HASH_SYM,
+};
+
+/**
* enum nft_hash_attributes - nf_tables hash expression netlink attributes
*
* @NFTA_HASH_SREG: source register (NLA_U32)
@@ -824,6 +835,7 @@ enum nft_rt_keys {
* @NFTA_HASH_MODULUS: modulus value (NLA_U32)
* @NFTA_HASH_SEED: seed value (NLA_U32)
* @NFTA_HASH_OFFSET: add this offset value to hash result (NLA_U32)
+ * @NFTA_HASH_TYPE: hash operation (NLA_U32: nft_hash_types)
*/
enum nft_hash_attributes {
NFTA_HASH_UNSPEC,
@@ -833,6 +845,7 @@ enum nft_hash_attributes {
NFTA_HASH_MODULUS,
NFTA_HASH_SEED,
NFTA_HASH_OFFSET,
+ NFTA_HASH_TYPE,
__NFTA_HASH_MAX,
};
#define NFTA_HASH_MAX (__NFTA_HASH_MAX - 1)
@@ -1244,12 +1257,23 @@ enum nft_fib_flags {
NFTA_FIB_F_MARK = 1 << 2, /* use skb->mark */
NFTA_FIB_F_IIF = 1 << 3, /* restrict to iif */
NFTA_FIB_F_OIF = 1 << 4, /* restrict to oif */
+ NFTA_FIB_F_PRESENT = 1 << 5, /* check existence only */
};
+enum nft_ct_helper_attributes {
+ NFTA_CT_HELPER_UNSPEC,
+ NFTA_CT_HELPER_NAME,
+ NFTA_CT_HELPER_L3PROTO,
+ NFTA_CT_HELPER_L4PROTO,
+ __NFTA_CT_HELPER_MAX,
+};
+#define NFTA_CT_HELPER_MAX (__NFTA_CT_HELPER_MAX - 1)
+
#define NFT_OBJECT_UNSPEC 0
#define NFT_OBJECT_COUNTER 1
#define NFT_OBJECT_QUOTA 2
-#define __NFT_OBJECT_MAX 3
+#define NFT_OBJECT_CT_HELPER 3
+#define __NFT_OBJECT_MAX 4
#define NFT_OBJECT_MAX (__NFT_OBJECT_MAX - 1)
/**
diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h
index f3946a2..b2c9c26 100644
--- a/include/uapi/linux/netlink.h
+++ b/include/uapi/linux/netlink.h
@@ -50,12 +50,12 @@ struct nlmsghdr {
/* Flags values */
-#define NLM_F_REQUEST 1 /* It is request message. */
-#define NLM_F_MULTI 2 /* Multipart message, terminated by NLMSG_DONE */
-#define NLM_F_ACK 4 /* Reply with ack, with zero or error code */
-#define NLM_F_ECHO 8 /* Echo this request */
-#define NLM_F_DUMP_INTR 16 /* Dump was inconsistent due to sequence change */
-#define NLM_F_DUMP_FILTERED 32 /* Dump was filtered as requested */
+#define NLM_F_REQUEST 0x01 /* It is request message. */
+#define NLM_F_MULTI 0x02 /* Multipart message, terminated by NLMSG_DONE */
+#define NLM_F_ACK 0x04 /* Reply with ack, with zero or error code */
+#define NLM_F_ECHO 0x08 /* Echo this request */
+#define NLM_F_DUMP_INTR 0x10 /* Dump was inconsistent due to sequence change */
+#define NLM_F_DUMP_FILTERED 0x20 /* Dump was filtered as requested */
/* Modifiers to GET request */
#define NLM_F_ROOT 0x100 /* specify tree root */
diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h
index 76b4d87..6dcd4de3 100644
--- a/include/uapi/linux/netlink_diag.h
+++ b/include/uapi/linux/netlink_diag.h
@@ -38,6 +38,7 @@ enum {
NETLINK_DIAG_GROUPS,
NETLINK_DIAG_RX_RING,
NETLINK_DIAG_TX_RING,
+ NETLINK_DIAG_FLAGS,
__NETLINK_DIAG_MAX,
};
@@ -52,5 +53,14 @@ enum {
/* deprecated since 4.6 */
#define NDIAG_SHOW_RING_CFG 0x00000004 /* show ring configuration */
#endif
+#define NDIAG_SHOW_FLAGS 0x00000008 /* show flags of a netlink socket */
+
+/* flags */
+#define NDIAG_FLAG_CB_RUNNING 0x00000001
+#define NDIAG_FLAG_PKTINFO 0x00000002
+#define NDIAG_FLAG_BROADCAST_ERROR 0x00000004
+#define NDIAG_FLAG_NO_ENOBUFS 0x00000008
+#define NDIAG_FLAG_LISTEN_ALL_NSID 0x00000010
+#define NDIAG_FLAG_CAP_ACK 0x00000020
#endif
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 7f41f7d..66d1c3c 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -578,10 +578,25 @@ enum ovs_sample_attr {
OVS_SAMPLE_ATTR_PROBABILITY, /* u32 number */
OVS_SAMPLE_ATTR_ACTIONS, /* Nested OVS_ACTION_ATTR_* attributes. */
__OVS_SAMPLE_ATTR_MAX,
+
+#ifdef __KERNEL__
+ OVS_SAMPLE_ATTR_ARG /* struct sample_arg */
+#endif
};
#define OVS_SAMPLE_ATTR_MAX (__OVS_SAMPLE_ATTR_MAX - 1)
+#ifdef __KERNEL__
+struct sample_arg {
+ bool exec; /* When true, actions in sample will not
+ * change flow keys. False otherwise.
+ */
+ u32 probability; /* Same value as
+ * 'OVS_SAMPLE_ATTR_PROBABILITY'.
+ */
+};
+#endif
+
/**
* enum ovs_userspace_attr - Attributes for %OVS_ACTION_ATTR_USERSPACE action.
* @OVS_USERSPACE_ATTR_PID: u32 Netlink PID to which the %OVS_PACKET_CMD_ACTION
diff --git a/include/uapi/linux/packet_diag.h b/include/uapi/linux/packet_diag.h
index d08c63f..0c5d5dd 100644
--- a/include/uapi/linux/packet_diag.h
+++ b/include/uapi/linux/packet_diag.h
@@ -64,7 +64,7 @@ struct packet_diag_mclist {
__u32 pdmc_count;
__u16 pdmc_type;
__u16 pdmc_alen;
- __u8 pdmc_addr[MAX_ADDR_LEN];
+ __u8 pdmc_addr[32]; /* MAX_ADDR_LEN */
};
struct packet_diag_ring {
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index df7451d..099bf55 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -617,6 +617,14 @@ struct tc_drr_stats {
#define TC_QOPT_BITMASK 15
#define TC_QOPT_MAX_QUEUE 16
+enum {
+ TC_MQPRIO_HW_OFFLOAD_NONE, /* no offload requested */
+ TC_MQPRIO_HW_OFFLOAD_TCS, /* offload TCs, no queue counts */
+ __TC_MQPRIO_HW_OFFLOAD_MAX
+};
+
+#define TC_MQPRIO_HW_OFFLOAD_MAX (__TC_MQPRIO_HW_OFFLOAD_MAX - 1)
+
struct tc_mqprio_qopt {
__u8 num_tc;
__u8 prio_tc_map[TC_QOPT_BITMASK + 1];
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 6546917..cce0613 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -122,6 +122,8 @@ enum {
RTM_NEWNETCONF = 80,
#define RTM_NEWNETCONF RTM_NEWNETCONF
+ RTM_DELNETCONF,
+#define RTM_DELNETCONF RTM_DELNETCONF
RTM_GETNETCONF = 82,
#define RTM_GETNETCONF RTM_GETNETCONF
@@ -319,6 +321,7 @@ enum rtattr_type_t {
RTA_EXPIRES,
RTA_PAD,
RTA_UID,
+ RTA_TTL_PROPAGATE,
__RTA_MAX
};
@@ -545,6 +548,7 @@ enum {
TCA_STATS2,
TCA_STAB,
TCA_PAD,
+ TCA_DUMP_INVISIBLE,
__TCA_MAX
};
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index d3ae381..ced9d8b 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -115,6 +115,8 @@ typedef __s32 sctp_assoc_t;
#define SCTP_PR_SUPPORTED 113
#define SCTP_DEFAULT_PRINFO 114
#define SCTP_PR_ASSOC_STATUS 115
+#define SCTP_PR_STREAM_STATUS 116
+#define SCTP_RECONFIG_SUPPORTED 117
#define SCTP_ENABLE_STREAM_RESET 118
#define SCTP_RESET_STREAMS 119
#define SCTP_RESET_ASSOC 120
@@ -502,6 +504,28 @@ struct sctp_stream_reset_event {
__u16 strreset_stream_list[];
};
+#define SCTP_ASSOC_RESET_DENIED 0x0004
+#define SCTP_ASSOC_RESET_FAILED 0x0008
+struct sctp_assoc_reset_event {
+ __u16 assocreset_type;
+ __u16 assocreset_flags;
+ __u32 assocreset_length;
+ sctp_assoc_t assocreset_assoc_id;
+ __u32 assocreset_local_tsn;
+ __u32 assocreset_remote_tsn;
+};
+
+#define SCTP_ASSOC_CHANGE_DENIED 0x0004
+#define SCTP_ASSOC_CHANGE_FAILED 0x0008
+struct sctp_stream_change_event {
+ __u16 strchange_type;
+ __u16 strchange_flags;
+ __u32 strchange_length;
+ sctp_assoc_t strchange_assoc_id;
+ __u16 strchange_instrms;
+ __u16 strchange_outstrms;
+};
+
/*
* Described in Section 7.3
* Ancillary Data and Notification Interest Options
@@ -518,6 +542,8 @@ struct sctp_event_subscribe {
__u8 sctp_authentication_event;
__u8 sctp_sender_dry_event;
__u8 sctp_stream_reset_event;
+ __u8 sctp_assoc_reset_event;
+ __u8 sctp_stream_change_event;
};
/*
@@ -543,6 +569,8 @@ union sctp_notification {
struct sctp_authkey_event sn_authkey_event;
struct sctp_sender_dry_event sn_sender_dry_event;
struct sctp_stream_reset_event sn_strreset_event;
+ struct sctp_assoc_reset_event sn_assocreset_event;
+ struct sctp_stream_change_event sn_strchange_event;
};
/* Section 5.3.1
@@ -572,6 +600,10 @@ enum sctp_sn_type {
#define SCTP_SENDER_DRY_EVENT SCTP_SENDER_DRY_EVENT
SCTP_STREAM_RESET_EVENT,
#define SCTP_STREAM_RESET_EVENT SCTP_STREAM_RESET_EVENT
+ SCTP_ASSOC_RESET_EVENT,
+#define SCTP_ASSOC_RESET_EVENT SCTP_ASSOC_RESET_EVENT
+ SCTP_STREAM_CHANGE_EVENT,
+#define SCTP_STREAM_CHANGE_EVENT SCTP_STREAM_CHANGE_EVENT
};
/* Notification error codes used to fill up the error fields in some
diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index 3b2bed7..cec0e17 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -177,7 +177,6 @@ enum
LINUX_MIB_TIMEWAITED, /* TimeWaited */
LINUX_MIB_TIMEWAITRECYCLED, /* TimeWaitRecycled */
LINUX_MIB_TIMEWAITKILLED, /* TimeWaitKilled */
- LINUX_MIB_PAWSPASSIVEREJECTED, /* PAWSPassiveRejected */
LINUX_MIB_PAWSACTIVEREJECTED, /* PAWSActiveRejected */
LINUX_MIB_PAWSESTABREJECTED, /* PAWSEstabRejected */
LINUX_MIB_DELAYEDACKS, /* DelayedACKs */
diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h
index d2b1215..e13d480 100644
--- a/include/uapi/linux/sysctl.h
+++ b/include/uapi/linux/sysctl.h
@@ -568,6 +568,7 @@ enum {
NET_IPV6_PROXY_NDP=23,
NET_IPV6_ACCEPT_SOURCE_ROUTE=25,
NET_IPV6_ACCEPT_RA_FROM_LOCAL=26,
+ NET_IPV6_ACCEPT_RA_RT_INFO_MIN_PLEN=27,
__NET_IPV6_MAX
};
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index c055947..3b05953 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -18,8 +18,7 @@
* means the userland is reading).
*/
#define UFFD_API ((__u64)0xAA)
-#define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_EXIT | \
- UFFD_FEATURE_EVENT_FORK | \
+#define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_FORK | \
UFFD_FEATURE_EVENT_REMAP | \
UFFD_FEATURE_EVENT_REMOVE | \
UFFD_FEATURE_EVENT_UNMAP | \
@@ -113,7 +112,6 @@ struct uffd_msg {
#define UFFD_EVENT_REMAP 0x14
#define UFFD_EVENT_REMOVE 0x15
#define UFFD_EVENT_UNMAP 0x16
-#define UFFD_EVENT_EXIT 0x17
/* flags for UFFD_EVENT_PAGEFAULT */
#define UFFD_PAGEFAULT_FLAG_WRITE (1<<0) /* If this was a write fault */
@@ -163,7 +161,6 @@ struct uffdio_api {
#define UFFD_FEATURE_MISSING_HUGETLBFS (1<<4)
#define UFFD_FEATURE_MISSING_SHMEM (1<<5)
#define UFFD_FEATURE_EVENT_UNMAP (1<<6)
-#define UFFD_FEATURE_EVENT_EXIT (1<<7)
__u64 features;
__u64 ioctls;
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index da7cd62..0b3d308 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -34,6 +34,7 @@
#define MLX5_ABI_USER_H
#include <linux/types.h>
+#include <linux/if_ether.h> /* For ETH_ALEN. */
enum {
MLX5_QP_FLAG_SIGNATURE = 1 << 0,
@@ -66,7 +67,7 @@ struct mlx5_ib_alloc_ucontext_req {
};
enum mlx5_lib_caps {
- MLX5_LIB_CAP_4K_UAR = (u64)1 << 0,
+ MLX5_LIB_CAP_4K_UAR = (__u64)1 << 0,
};
struct mlx5_ib_alloc_ucontext_req_v2 {
diff --git a/include/video/exynos5433_decon.h b/include/video/exynos5433_decon.h
index ef8e2a8..6b083d3 100644
--- a/include/video/exynos5433_decon.h
+++ b/include/video/exynos5433_decon.h
@@ -46,6 +46,7 @@
#define DECON_FRAMEFIFO_STATUS 0x0524
#define DECON_CMU 0x1404
#define DECON_UPDATE 0x1410
+#define DECON_CRFMID 0x1414
#define DECON_UPDATE_SCHEME 0x1438
#define DECON_VIDCON1 0x2000
#define DECON_VIDCON2 0x2004
@@ -126,6 +127,10 @@
/* VIDINTCON0 */
#define VIDINTCON0_FRAMEDONE (1 << 17)
+#define VIDINTCON0_FRAMESEL_BP (0 << 15)
+#define VIDINTCON0_FRAMESEL_VS (1 << 15)
+#define VIDINTCON0_FRAMESEL_AC (2 << 15)
+#define VIDINTCON0_FRAMESEL_FP (3 << 15)
#define VIDINTCON0_INTFRMEN (1 << 12)
#define VIDINTCON0_INTEN (1 << 0)
@@ -142,6 +147,13 @@
#define STANDALONE_UPDATE_F (1 << 0)
/* DECON_VIDCON1 */
+#define VIDCON1_LINECNT_MASK (0x0fff << 16)
+#define VIDCON1_I80_ACTIVE (1 << 15)
+#define VIDCON1_VSTATUS_MASK (0x3 << 13)
+#define VIDCON1_VSTATUS_VS (0 << 13)
+#define VIDCON1_VSTATUS_BP (1 << 13)
+#define VIDCON1_VSTATUS_AC (2 << 13)
+#define VIDCON1_VSTATUS_FP (3 << 13)
#define VIDCON1_VCLK_MASK (0x3 << 9)
#define VIDCON1_VCLK_RUN_VDEN_DISABLE (0x3 << 9)
#define VIDCON1_VCLK_HOLD (0x0 << 9)
diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h
index a0083be..1f6d78f 100644
--- a/include/xen/swiotlb-xen.h
+++ b/include/xen/swiotlb-xen.h
@@ -2,6 +2,7 @@
#define __LINUX_SWIOTLB_XEN_H
#include <linux/dma-direction.h>
+#include <linux/scatterlist.h>
#include <linux/swiotlb.h>
extern int xen_swiotlb_init(int verbose, bool early);
@@ -55,4 +56,14 @@ xen_swiotlb_dma_supported(struct device *hwdev, u64 mask);
extern int
xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask);
+
+extern int
+xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ unsigned long attrs);
+
+extern int
+xen_swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
+ void *cpu_addr, dma_addr_t handle, size_t size,
+ unsigned long attrs);
#endif /* __LINUX_SWIOTLB_XEN_H */
diff --git a/init/main.c b/init/main.c
index eae2f15..b0c11cb 100644
--- a/init/main.c
+++ b/init/main.c
@@ -882,7 +882,6 @@ static void __init do_basic_setup(void)
do_ctors();
usermodehelper_enable();
do_initcalls();
- random_int_secret_init();
}
static void __init do_pre_smp_initcalls(void)
@@ -1023,6 +1022,8 @@ static noinline void __init kernel_init_freeable(void)
workqueue_init();
+ init_mm_internals();
+
do_pre_smp_initcalls();
lockup_detector_init();
diff --git a/kernel/audit.c b/kernel/audit.c
index e794544..2f4964c 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -54,6 +54,10 @@
#include <linux/kthread.h>
#include <linux/kernel.h>
#include <linux/syscalls.h>
+#include <linux/spinlock.h>
+#include <linux/rcupdate.h>
+#include <linux/mutex.h>
+#include <linux/gfp.h>
#include <linux/audit.h>
@@ -90,13 +94,34 @@ static u32 audit_default;
/* If auditing cannot proceed, audit_failure selects what happens. */
static u32 audit_failure = AUDIT_FAIL_PRINTK;
-/*
- * If audit records are to be written to the netlink socket, audit_pid
- * contains the pid of the auditd process and audit_nlk_portid contains
- * the portid to use to send netlink messages to that process.
+/* private audit network namespace index */
+static unsigned int audit_net_id;
+
+/**
+ * struct audit_net - audit private network namespace data
+ * @sk: communication socket
*/
-int audit_pid;
-static __u32 audit_nlk_portid;
+struct audit_net {
+ struct sock *sk;
+};
+
+/**
+ * struct auditd_connection - kernel/auditd connection state
+ * @pid: auditd PID
+ * @portid: netlink portid
+ * @net: the associated network namespace
+ * @lock: spinlock to protect write access
+ *
+ * Description:
+ * This struct is RCU protected; you must either hold the RCU lock for reading
+ * or the included spinlock for writing.
+ */
+static struct auditd_connection {
+ int pid;
+ u32 portid;
+ struct net *net;
+ spinlock_t lock;
+} auditd_conn;
/* If audit_rate_limit is non-zero, limit the rate of sending audit records
* to that number per second. This prevents DoS attacks, but results in
@@ -123,10 +148,6 @@ u32 audit_sig_sid = 0;
*/
static atomic_t audit_lost = ATOMIC_INIT(0);
-/* The netlink socket. */
-static struct sock *audit_sock;
-static unsigned int audit_net_id;
-
/* Hash for inode-based rules */
struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS];
@@ -139,6 +160,7 @@ static LIST_HEAD(audit_freelist);
/* queue msgs to send via kauditd_task */
static struct sk_buff_head audit_queue;
+static void kauditd_hold_skb(struct sk_buff *skb);
/* queue msgs due to temporary unicast send problems */
static struct sk_buff_head audit_retry_queue;
/* queue msgs waiting for new auditd connection */
@@ -192,6 +214,43 @@ struct audit_reply {
struct sk_buff *skb;
};
+/**
+ * auditd_test_task - Check to see if a given task is an audit daemon
+ * @task: the task to check
+ *
+ * Description:
+ * Return 1 if the task is a registered audit daemon, 0 otherwise.
+ */
+int auditd_test_task(const struct task_struct *task)
+{
+ int rc;
+
+ rcu_read_lock();
+ rc = (auditd_conn.pid && task->tgid == auditd_conn.pid ? 1 : 0);
+ rcu_read_unlock();
+
+ return rc;
+}
+
+/**
+ * audit_get_sk - Return the audit socket for the given network namespace
+ * @net: the destination network namespace
+ *
+ * Description:
+ * Returns the sock pointer if valid, NULL otherwise. The caller must ensure
+ * that a reference is held for the network namespace while the sock is in use.
+ */
+static struct sock *audit_get_sk(const struct net *net)
+{
+ struct audit_net *aunet;
+
+ if (!net)
+ return NULL;
+
+ aunet = net_generic(net, audit_net_id);
+ return aunet->sk;
+}
+
static void audit_set_portid(struct audit_buffer *ab, __u32 portid)
{
if (ab) {
@@ -210,9 +269,7 @@ void audit_panic(const char *message)
pr_err("%s\n", message);
break;
case AUDIT_FAIL_PANIC:
- /* test audit_pid since printk is always losey, why bother? */
- if (audit_pid)
- panic("audit: %s\n", message);
+ panic("audit: %s\n", message);
break;
}
}
@@ -370,21 +427,87 @@ static int audit_set_failure(u32 state)
return audit_do_config_change("audit_failure", &audit_failure, state);
}
-/*
- * For one reason or another this nlh isn't getting delivered to the userspace
- * audit daemon, just send it to printk.
+/**
+ * auditd_set - Set/Reset the auditd connection state
+ * @pid: auditd PID
+ * @portid: auditd netlink portid
+ * @net: auditd network namespace pointer
+ *
+ * Description:
+ * This function will obtain and drop network namespace references as
+ * necessary.
+ */
+static void auditd_set(int pid, u32 portid, struct net *net)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&auditd_conn.lock, flags);
+ auditd_conn.pid = pid;
+ auditd_conn.portid = portid;
+ if (auditd_conn.net)
+ put_net(auditd_conn.net);
+ if (net)
+ auditd_conn.net = get_net(net);
+ else
+ auditd_conn.net = NULL;
+ spin_unlock_irqrestore(&auditd_conn.lock, flags);
+}
+
+/**
+ * auditd_reset - Disconnect the auditd connection
+ *
+ * Description:
+ * Break the auditd/kauditd connection and move all the queued records into the
+ * hold queue in case auditd reconnects.
+ */
+static void auditd_reset(void)
+{
+ struct sk_buff *skb;
+
+ /* if it isn't already broken, break the connection */
+ rcu_read_lock();
+ if (auditd_conn.pid)
+ auditd_set(0, 0, NULL);
+ rcu_read_unlock();
+
+ /* flush all of the main and retry queues to the hold queue */
+ while ((skb = skb_dequeue(&audit_retry_queue)))
+ kauditd_hold_skb(skb);
+ while ((skb = skb_dequeue(&audit_queue)))
+ kauditd_hold_skb(skb);
+}
+
+/**
+ * kauditd_print_skb - Print the audit record to the ring buffer
+ * @skb: audit record
+ *
+ * Whatever the reason, this packet may not make it to the auditd connection
+ * so write it via printk so the information isn't completely lost.
*/
static void kauditd_printk_skb(struct sk_buff *skb)
{
struct nlmsghdr *nlh = nlmsg_hdr(skb);
char *data = nlmsg_data(nlh);
- if (nlh->nlmsg_type != AUDIT_EOE) {
- if (printk_ratelimit())
- pr_notice("type=%d %s\n", nlh->nlmsg_type, data);
- else
- audit_log_lost("printk limit exceeded");
- }
+ if (nlh->nlmsg_type != AUDIT_EOE && printk_ratelimit())
+ pr_notice("type=%d %s\n", nlh->nlmsg_type, data);
+}
+
+/**
+ * kauditd_rehold_skb - Handle a audit record send failure in the hold queue
+ * @skb: audit record
+ *
+ * Description:
+ * This should only be used by the kauditd_thread when it fails to flush the
+ * hold queue.
+ */
+static void kauditd_rehold_skb(struct sk_buff *skb)
+{
+ /* put the record back in the queue at the same place */
+ skb_queue_head(&audit_hold_queue, skb);
+
+ /* fail the auditd connection */
+ auditd_reset();
}
/**
@@ -421,6 +544,9 @@ static void kauditd_hold_skb(struct sk_buff *skb)
/* we have no other options - drop the message */
audit_log_lost("kauditd hold queue overflow");
kfree_skb(skb);
+
+ /* fail the auditd connection */
+ auditd_reset();
}
/**
@@ -441,51 +567,122 @@ static void kauditd_retry_skb(struct sk_buff *skb)
}
/**
- * auditd_reset - Disconnect the auditd connection
+ * auditd_send_unicast_skb - Send a record via unicast to auditd
+ * @skb: audit record
*
* Description:
- * Break the auditd/kauditd connection and move all the records in the retry
- * queue into the hold queue in case auditd reconnects. The audit_cmd_mutex
- * must be held when calling this function.
+ * Send a skb to the audit daemon, returns positive/zero values on success and
+ * negative values on failure; in all cases the skb will be consumed by this
+ * function. If the send results in -ECONNREFUSED the connection with auditd
+ * will be reset. This function may sleep so callers should not hold any locks
+ * where this would cause a problem.
*/
-static void auditd_reset(void)
+static int auditd_send_unicast_skb(struct sk_buff *skb)
{
- struct sk_buff *skb;
+ int rc;
+ u32 portid;
+ struct net *net;
+ struct sock *sk;
- /* break the connection */
- if (audit_sock) {
- sock_put(audit_sock);
- audit_sock = NULL;
+ /* NOTE: we can't call netlink_unicast while in the RCU section so
+ * take a reference to the network namespace and grab local
+ * copies of the namespace, the sock, and the portid; the
+ * namespace and sock aren't going to go away while we hold a
+ * reference and if the portid does become invalid after the RCU
+ * section netlink_unicast() should safely return an error */
+
+ rcu_read_lock();
+ if (!auditd_conn.pid) {
+ rcu_read_unlock();
+ rc = -ECONNREFUSED;
+ goto err;
}
- audit_pid = 0;
- audit_nlk_portid = 0;
+ net = auditd_conn.net;
+ get_net(net);
+ sk = audit_get_sk(net);
+ portid = auditd_conn.portid;
+ rcu_read_unlock();
- /* flush all of the retry queue to the hold queue */
- while ((skb = skb_dequeue(&audit_retry_queue)))
- kauditd_hold_skb(skb);
+ rc = netlink_unicast(sk, skb, portid, 0);
+ put_net(net);
+ if (rc < 0)
+ goto err;
+
+ return rc;
+
+err:
+ if (rc == -ECONNREFUSED)
+ auditd_reset();
+ return rc;
}
/**
- * kauditd_send_unicast_skb - Send a record via unicast to auditd
- * @skb: audit record
+ * kauditd_send_queue - Helper for kauditd_thread to flush skb queues
+ * @sk: the sending sock
+ * @portid: the netlink destination
+ * @queue: the skb queue to process
+ * @retry_limit: limit on number of netlink unicast failures
+ * @skb_hook: per-skb hook for additional processing
+ * @err_hook: hook called if the skb fails the netlink unicast send
+ *
+ * Description:
+ * Run through the given queue and attempt to send the audit records to auditd,
+ * returns zero on success, negative values on failure. It is up to the caller
+ * to ensure that the @sk is valid for the duration of this function.
+ *
*/
-static int kauditd_send_unicast_skb(struct sk_buff *skb)
+static int kauditd_send_queue(struct sock *sk, u32 portid,
+ struct sk_buff_head *queue,
+ unsigned int retry_limit,
+ void (*skb_hook)(struct sk_buff *skb),
+ void (*err_hook)(struct sk_buff *skb))
{
- int rc;
+ int rc = 0;
+ struct sk_buff *skb;
+ static unsigned int failed = 0;
- /* if we know nothing is connected, don't even try the netlink call */
- if (!audit_pid)
- return -ECONNREFUSED;
+ /* NOTE: kauditd_thread takes care of all our locking, we just use
+ * the netlink info passed to us (e.g. sk and portid) */
- /* get an extra skb reference in case we fail to send */
- skb_get(skb);
- rc = netlink_unicast(audit_sock, skb, audit_nlk_portid, 0);
- if (rc >= 0) {
- consume_skb(skb);
- rc = 0;
+ while ((skb = skb_dequeue(queue))) {
+ /* call the skb_hook for each skb we touch */
+ if (skb_hook)
+ (*skb_hook)(skb);
+
+ /* can we send to anyone via unicast? */
+ if (!sk) {
+ if (err_hook)
+ (*err_hook)(skb);
+ continue;
+ }
+
+ /* grab an extra skb reference in case of error */
+ skb_get(skb);
+ rc = netlink_unicast(sk, skb, portid, 0);
+ if (rc < 0) {
+ /* fatal failure for our queue flush attempt? */
+ if (++failed >= retry_limit ||
+ rc == -ECONNREFUSED || rc == -EPERM) {
+ /* yes - error processing for the queue */
+ sk = NULL;
+ if (err_hook)
+ (*err_hook)(skb);
+ if (!skb_hook)
+ goto out;
+ /* keep processing with the skb_hook */
+ continue;
+ } else
+ /* no - requeue to preserve ordering */
+ skb_queue_head(queue, skb);
+ } else {
+ /* it worked - drop the extra reference and continue */
+ consume_skb(skb);
+ failed = 0;
+ }
}
- return rc;
+out:
+ return (rc >= 0 ? 0 : rc);
}
/*
@@ -493,16 +690,19 @@ static int kauditd_send_unicast_skb(struct sk_buff *skb)
* @skb: audit record
*
* Description:
- * This function doesn't consume an skb as might be expected since it has to
- * copy it anyways.
+ * Write a multicast message to anyone listening in the initial network
+ * namespace. This function doesn't consume an skb as might be expected since
+ * it has to copy it anyways.
*/
static void kauditd_send_multicast_skb(struct sk_buff *skb)
{
struct sk_buff *copy;
- struct audit_net *aunet = net_generic(&init_net, audit_net_id);
- struct sock *sock = aunet->nlsk;
+ struct sock *sock = audit_get_sk(&init_net);
struct nlmsghdr *nlh;
+ /* NOTE: we are not taking an additional reference for init_net since
+ * we don't have to worry about it going away */
+
if (!netlink_has_listeners(sock, AUDIT_NLGRP_READLOG))
return;
@@ -526,149 +726,75 @@ static void kauditd_send_multicast_skb(struct sk_buff *skb)
}
/**
- * kauditd_wake_condition - Return true when it is time to wake kauditd_thread
- *
- * Description:
- * This function is for use by the wait_event_freezable() call in
- * kauditd_thread().
+ * kauditd_thread - Worker thread to send audit records to userspace
+ * @dummy: unused
*/
-static int kauditd_wake_condition(void)
-{
- static int pid_last = 0;
- int rc;
- int pid = audit_pid;
-
- /* wake on new messages or a change in the connected auditd */
- rc = skb_queue_len(&audit_queue) || (pid && pid != pid_last);
- if (rc)
- pid_last = pid;
-
- return rc;
-}
-
static int kauditd_thread(void *dummy)
{
int rc;
- int auditd = 0;
- int reschedule = 0;
- struct sk_buff *skb;
- struct nlmsghdr *nlh;
+ u32 portid = 0;
+ struct net *net = NULL;
+ struct sock *sk = NULL;
#define UNICAST_RETRIES 5
-#define AUDITD_BAD(x,y) \
- ((x) == -ECONNREFUSED || (x) == -EPERM || ++(y) >= UNICAST_RETRIES)
-
- /* NOTE: we do invalidate the auditd connection flag on any sending
- * errors, but we only "restore" the connection flag at specific places
- * in the loop in order to help ensure proper ordering of audit
- * records */
set_freezable();
while (!kthread_should_stop()) {
- /* NOTE: possible area for future improvement is to look at
- * the hold and retry queues, since only this thread
- * has access to these queues we might be able to do
- * our own queuing and skip some/all of the locking */
-
- /* NOTE: it might be a fun experiment to split the hold and
- * retry queue handling to another thread, but the
- * synchronization issues and other overhead might kill
- * any performance gains */
+ /* NOTE: see the lock comments in auditd_send_unicast_skb() */
+ rcu_read_lock();
+ if (!auditd_conn.pid) {
+ rcu_read_unlock();
+ goto main_queue;
+ }
+ net = auditd_conn.net;
+ get_net(net);
+ sk = audit_get_sk(net);
+ portid = auditd_conn.portid;
+ rcu_read_unlock();
/* attempt to flush the hold queue */
- while (auditd && (skb = skb_dequeue(&audit_hold_queue))) {
- rc = kauditd_send_unicast_skb(skb);
- if (rc) {
- /* requeue to the same spot */
- skb_queue_head(&audit_hold_queue, skb);
-
- auditd = 0;
- if (AUDITD_BAD(rc, reschedule)) {
- mutex_lock(&audit_cmd_mutex);
- auditd_reset();
- mutex_unlock(&audit_cmd_mutex);
- reschedule = 0;
- }
- } else
- /* we were able to send successfully */
- reschedule = 0;
+ rc = kauditd_send_queue(sk, portid,
+ &audit_hold_queue, UNICAST_RETRIES,
+ NULL, kauditd_rehold_skb);
+ if (rc < 0) {
+ sk = NULL;
+ goto main_queue;
}
/* attempt to flush the retry queue */
- while (auditd && (skb = skb_dequeue(&audit_retry_queue))) {
- rc = kauditd_send_unicast_skb(skb);
- if (rc) {
- auditd = 0;
- if (AUDITD_BAD(rc, reschedule)) {
- kauditd_hold_skb(skb);
- mutex_lock(&audit_cmd_mutex);
- auditd_reset();
- mutex_unlock(&audit_cmd_mutex);
- reschedule = 0;
- } else
- /* temporary problem (we hope), queue
- * to the same spot and retry */
- skb_queue_head(&audit_retry_queue, skb);
- } else
- /* we were able to send successfully */
- reschedule = 0;
+ rc = kauditd_send_queue(sk, portid,
+ &audit_retry_queue, UNICAST_RETRIES,
+ NULL, kauditd_hold_skb);
+ if (rc < 0) {
+ sk = NULL;
+ goto main_queue;
}
- /* standard queue processing, try to be as quick as possible */
-quick_loop:
- skb = skb_dequeue(&audit_queue);
- if (skb) {
- /* setup the netlink header, see the comments in
- * kauditd_send_multicast_skb() for length quirks */
- nlh = nlmsg_hdr(skb);
- nlh->nlmsg_len = skb->len - NLMSG_HDRLEN;
+main_queue:
+ /* process the main queue - do the multicast send and attempt
+ * unicast, dump failed record sends to the retry queue; if
+ * sk == NULL due to previous failures we will just do the
+ * multicast send and move the record to the retry queue */
+ kauditd_send_queue(sk, portid, &audit_queue, 1,
+ kauditd_send_multicast_skb,
+ kauditd_retry_skb);
- /* attempt to send to any multicast listeners */
- kauditd_send_multicast_skb(skb);
-
- /* attempt to send to auditd, queue on failure */
- if (auditd) {
- rc = kauditd_send_unicast_skb(skb);
- if (rc) {
- auditd = 0;
- if (AUDITD_BAD(rc, reschedule)) {
- mutex_lock(&audit_cmd_mutex);
- auditd_reset();
- mutex_unlock(&audit_cmd_mutex);
- reschedule = 0;
- }
-
- /* move to the retry queue */
- kauditd_retry_skb(skb);
- } else
- /* everything is working so go fast! */
- goto quick_loop;
- } else if (reschedule)
- /* we are currently having problems, move to
- * the retry queue */
- kauditd_retry_skb(skb);
- else
- /* dump the message via printk and hold it */
- kauditd_hold_skb(skb);
- } else {
- /* we have flushed the backlog so wake everyone */
- wake_up(&audit_backlog_wait);
-
- /* if everything is okay with auditd (if present), go
- * to sleep until there is something new in the queue
- * or we have a change in the connected auditd;
- * otherwise simply reschedule to give things a chance
- * to recover */
- if (reschedule) {
- set_current_state(TASK_INTERRUPTIBLE);
- schedule();
- } else
- wait_event_freezable(kauditd_wait,
- kauditd_wake_condition());
-
- /* update the auditd connection status */
- auditd = (audit_pid ? 1 : 0);
+ /* drop our netns reference, no auditd sends past this line */
+ if (net) {
+ put_net(net);
+ net = NULL;
}
+ sk = NULL;
+
+ /* we have processed all the queues so wake everyone */
+ wake_up(&audit_backlog_wait);
+
+ /* NOTE: we want to wake up if there is anything on the queue,
+ * regardless of if an auditd is connected, as we need to
+ * do the multicast send and rotate records from the
+ * main queue to the retry/hold queues */
+ wait_event_freezable(kauditd_wait,
+ (skb_queue_len(&audit_queue) ? 1 : 0));
}
return 0;
@@ -678,17 +804,16 @@ int audit_send_list(void *_dest)
{
struct audit_netlink_list *dest = _dest;
struct sk_buff *skb;
- struct net *net = dest->net;
- struct audit_net *aunet = net_generic(net, audit_net_id);
+ struct sock *sk = audit_get_sk(dest->net);
/* wait for parent to finish and send an ACK */
mutex_lock(&audit_cmd_mutex);
mutex_unlock(&audit_cmd_mutex);
while ((skb = __skb_dequeue(&dest->q)) != NULL)
- netlink_unicast(aunet->nlsk, skb, dest->portid, 0);
+ netlink_unicast(sk, skb, dest->portid, 0);
- put_net(net);
+ put_net(dest->net);
kfree(dest);
return 0;
@@ -722,16 +847,15 @@ struct sk_buff *audit_make_reply(__u32 portid, int seq, int type, int done,
static int audit_send_reply_thread(void *arg)
{
struct audit_reply *reply = (struct audit_reply *)arg;
- struct net *net = reply->net;
- struct audit_net *aunet = net_generic(net, audit_net_id);
+ struct sock *sk = audit_get_sk(reply->net);
mutex_lock(&audit_cmd_mutex);
mutex_unlock(&audit_cmd_mutex);
/* Ignore failure. It'll only happen if the sender goes away,
because our timeout is set to infinite. */
- netlink_unicast(aunet->nlsk , reply->skb, reply->portid, 0);
- put_net(net);
+ netlink_unicast(sk, reply->skb, reply->portid, 0);
+ put_net(reply->net);
kfree(reply);
return 0;
}
@@ -949,12 +1073,12 @@ static int audit_set_feature(struct sk_buff *skb)
static int audit_replace(pid_t pid)
{
- struct sk_buff *skb = audit_make_reply(0, 0, AUDIT_REPLACE, 0, 0,
- &pid, sizeof(pid));
+ struct sk_buff *skb;
+ skb = audit_make_reply(0, 0, AUDIT_REPLACE, 0, 0, &pid, sizeof(pid));
if (!skb)
return -ENOMEM;
- return netlink_unicast(audit_sock, skb, audit_nlk_portid, 0);
+ return auditd_send_unicast_skb(skb);
}
static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
@@ -981,7 +1105,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
memset(&s, 0, sizeof(s));
s.enabled = audit_enabled;
s.failure = audit_failure;
- s.pid = audit_pid;
+ rcu_read_lock();
+ s.pid = auditd_conn.pid;
+ rcu_read_unlock();
s.rate_limit = audit_rate_limit;
s.backlog_limit = audit_backlog_limit;
s.lost = atomic_read(&audit_lost);
@@ -1014,30 +1140,44 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
* from the initial pid namespace, but something
* to keep in mind if this changes */
int new_pid = s.pid;
+ pid_t auditd_pid;
pid_t requesting_pid = task_tgid_vnr(current);
- if ((!new_pid) && (requesting_pid != audit_pid)) {
- audit_log_config_change("audit_pid", new_pid, audit_pid, 0);
+ /* test the auditd connection */
+ audit_replace(requesting_pid);
+
+ rcu_read_lock();
+ auditd_pid = auditd_conn.pid;
+ /* only the current auditd can unregister itself */
+ if ((!new_pid) && (requesting_pid != auditd_pid)) {
+ rcu_read_unlock();
+ audit_log_config_change("audit_pid", new_pid,
+ auditd_pid, 0);
return -EACCES;
}
- if (audit_pid && new_pid &&
- audit_replace(requesting_pid) != -ECONNREFUSED) {
- audit_log_config_change("audit_pid", new_pid, audit_pid, 0);
+ /* replacing a healthy auditd is not allowed */
+ if (auditd_pid && new_pid) {
+ rcu_read_unlock();
+ audit_log_config_change("audit_pid", new_pid,
+ auditd_pid, 0);
return -EEXIST;
}
+ rcu_read_unlock();
+
if (audit_enabled != AUDIT_OFF)
- audit_log_config_change("audit_pid", new_pid, audit_pid, 1);
+ audit_log_config_change("audit_pid", new_pid,
+ auditd_pid, 1);
+
if (new_pid) {
- if (audit_sock)
- sock_put(audit_sock);
- audit_pid = new_pid;
- audit_nlk_portid = NETLINK_CB(skb).portid;
- sock_hold(skb->sk);
- audit_sock = skb->sk;
- } else {
+ /* register a new auditd connection */
+ auditd_set(new_pid,
+ NETLINK_CB(skb).portid,
+ sock_net(NETLINK_CB(skb).sk));
+ /* try to process any backlog */
+ wake_up_interruptible(&kauditd_wait);
+ } else
+ /* unregister the auditd connection */
auditd_reset();
- }
- wake_up_interruptible(&kauditd_wait);
}
if (s.mask & AUDIT_STATUS_RATE_LIMIT) {
err = audit_set_rate_limit(s.rate_limit);
@@ -1090,7 +1230,6 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
if (err)
break;
}
- mutex_unlock(&audit_cmd_mutex);
audit_log_common_recv_msg(&ab, msg_type);
if (msg_type != AUDIT_USER_TTY)
audit_log_format(ab, " msg='%.*s'",
@@ -1108,7 +1247,6 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
}
audit_set_portid(ab, NETLINK_CB(skb).portid);
audit_log_end(ab);
- mutex_lock(&audit_cmd_mutex);
}
break;
case AUDIT_ADD_RULE:
@@ -1298,26 +1436,26 @@ static int __net_init audit_net_init(struct net *net)
struct audit_net *aunet = net_generic(net, audit_net_id);
- aunet->nlsk = netlink_kernel_create(net, NETLINK_AUDIT, &cfg);
- if (aunet->nlsk == NULL) {
+ aunet->sk = netlink_kernel_create(net, NETLINK_AUDIT, &cfg);
+ if (aunet->sk == NULL) {
audit_panic("cannot initialize netlink socket in namespace");
return -ENOMEM;
}
- aunet->nlsk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
+ aunet->sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
+
return 0;
}
static void __net_exit audit_net_exit(struct net *net)
{
struct audit_net *aunet = net_generic(net, audit_net_id);
- struct sock *sock = aunet->nlsk;
- mutex_lock(&audit_cmd_mutex);
- if (sock == audit_sock)
- auditd_reset();
- mutex_unlock(&audit_cmd_mutex);
- netlink_kernel_release(sock);
- aunet->nlsk = NULL;
+ rcu_read_lock();
+ if (net == auditd_conn.net)
+ auditd_reset();
+ rcu_read_unlock();
+
+ netlink_kernel_release(aunet->sk);
}
static struct pernet_operations audit_net_ops __net_initdata = {
@@ -1335,20 +1473,24 @@ static int __init audit_init(void)
if (audit_initialized == AUDIT_DISABLED)
return 0;
- pr_info("initializing netlink subsys (%s)\n",
- audit_default ? "enabled" : "disabled");
- register_pernet_subsys(&audit_net_ops);
+ memset(&auditd_conn, 0, sizeof(auditd_conn));
+ spin_lock_init(&auditd_conn.lock);
skb_queue_head_init(&audit_queue);
skb_queue_head_init(&audit_retry_queue);
skb_queue_head_init(&audit_hold_queue);
- audit_initialized = AUDIT_INITIALIZED;
- audit_enabled = audit_default;
- audit_ever_enabled |= !!audit_default;
for (i = 0; i < AUDIT_INODE_BUCKETS; i++)
INIT_LIST_HEAD(&audit_inode_hash[i]);
+ pr_info("initializing netlink subsys (%s)\n",
+ audit_default ? "enabled" : "disabled");
+ register_pernet_subsys(&audit_net_ops);
+
+ audit_initialized = AUDIT_INITIALIZED;
+ audit_enabled = audit_default;
+ audit_ever_enabled |= !!audit_default;
+
kauditd_task = kthread_run(kauditd_thread, NULL, "kauditd");
if (IS_ERR(kauditd_task)) {
int err = PTR_ERR(kauditd_task);
@@ -1519,20 +1661,16 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
if (unlikely(!audit_filter(type, AUDIT_FILTER_TYPE)))
return NULL;
- /* don't ever fail/sleep on these two conditions:
+ /* NOTE: don't ever fail/sleep on these two conditions:
* 1. auditd generated record - since we need auditd to drain the
* queue; also, when we are checking for auditd, compare PIDs using
* task_tgid_vnr() since auditd_pid is set in audit_receive_msg()
* using a PID anchored in the caller's namespace
- * 2. audit command message - record types 1000 through 1099 inclusive
- * are command messages/records used to manage the kernel subsystem
- * and the audit userspace, blocking on these messages could cause
- * problems under load so don't do it (note: not all of these
- * command types are valid as record types, but it is quicker to
- * just check two ints than a series of ints in a if/switch stmt) */
- if (!((audit_pid && audit_pid == task_tgid_vnr(current)) ||
- (type >= 1000 && type <= 1099))) {
- long sleep_time = audit_backlog_wait_time;
+ * 2. generator holding the audit_cmd_mutex - we don't want to block
+ * while holding the mutex */
+ if (!(auditd_test_task(current) ||
+ (current == __mutex_owner(&audit_cmd_mutex)))) {
+ long stime = audit_backlog_wait_time;
while (audit_backlog_limit &&
(skb_queue_len(&audit_queue) > audit_backlog_limit)) {
@@ -1541,14 +1679,13 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
/* sleep if we are allowed and we haven't exhausted our
* backlog wait limit */
- if ((gfp_mask & __GFP_DIRECT_RECLAIM) &&
- (sleep_time > 0)) {
+ if (gfpflags_allow_blocking(gfp_mask) && (stime > 0)) {
DECLARE_WAITQUEUE(wait, current);
add_wait_queue_exclusive(&audit_backlog_wait,
&wait);
set_current_state(TASK_UNINTERRUPTIBLE);
- sleep_time = schedule_timeout(sleep_time);
+ stime = schedule_timeout(stime);
remove_wait_queue(&audit_backlog_wait, &wait);
} else {
if (audit_rate_check() && printk_ratelimit())
@@ -2127,15 +2264,27 @@ void audit_log_link_denied(const char *operation, const struct path *link)
*/
void audit_log_end(struct audit_buffer *ab)
{
+ struct sk_buff *skb;
+ struct nlmsghdr *nlh;
+
if (!ab)
return;
- if (!audit_rate_check()) {
- audit_log_lost("rate limit exceeded");
- } else {
- skb_queue_tail(&audit_queue, ab->skb);
- wake_up_interruptible(&kauditd_wait);
+
+ if (audit_rate_check()) {
+ skb = ab->skb;
ab->skb = NULL;
- }
+
+ /* setup the netlink header, see the comments in
+ * kauditd_send_multicast_skb() for length quirks */
+ nlh = nlmsg_hdr(skb);
+ nlh->nlmsg_len = skb->len - NLMSG_HDRLEN;
+
+ /* queue the netlink packet and poke the kauditd thread */
+ skb_queue_tail(&audit_queue, skb);
+ wake_up_interruptible(&kauditd_wait);
+ } else
+ audit_log_lost("rate limit exceeded");
+
audit_buffer_free(ab);
}
diff --git a/kernel/audit.h b/kernel/audit.h
index ca57988..0f1cf6d 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -218,7 +218,7 @@ extern void audit_log_name(struct audit_context *context,
struct audit_names *n, const struct path *path,
int record_num, int *call_panic);
-extern int audit_pid;
+extern int auditd_test_task(const struct task_struct *task);
#define AUDIT_INODE_BUCKETS 32
extern struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS];
@@ -250,10 +250,6 @@ struct audit_netlink_list {
int audit_send_list(void *);
-struct audit_net {
- struct sock *nlsk;
-};
-
extern int selinux_audit_rule_update(void);
extern struct mutex audit_filter_mutex;
@@ -340,8 +336,7 @@ extern int audit_filter(int msgtype, unsigned int listtype);
extern int __audit_signal_info(int sig, struct task_struct *t);
static inline int audit_signal_info(int sig, struct task_struct *t)
{
- if (unlikely((audit_pid && t->tgid == audit_pid) ||
- (audit_signals && !audit_dummy_context())))
+ if (auditd_test_task(t) || (audit_signals && !audit_dummy_context()))
return __audit_signal_info(sig, t);
return 0;
}
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index d6a8de5..e59ffc7 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -762,7 +762,7 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk,
struct audit_entry *e;
enum audit_state state;
- if (audit_pid && tsk->tgid == audit_pid)
+ if (auditd_test_task(tsk))
return AUDIT_DISABLED;
rcu_read_lock();
@@ -816,7 +816,7 @@ void audit_filter_inodes(struct task_struct *tsk, struct audit_context *ctx)
{
struct audit_names *n;
- if (audit_pid && tsk->tgid == audit_pid)
+ if (auditd_test_task(tsk))
return;
rcu_read_lock();
@@ -2256,7 +2256,7 @@ int __audit_signal_info(int sig, struct task_struct *t)
struct audit_context *ctx = tsk->audit_context;
kuid_t uid = current_uid(), t_uid = task_uid(t);
- if (audit_pid && t->tgid == audit_pid) {
+ if (auditd_test_task(t)) {
if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2) {
audit_sig_pid = task_tgid_nr(tsk);
if (uid_valid(tsk->loginuid))
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index e1ce4f4..e1e5e65 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1,7 +1,7 @@
obj-y := core.o
obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o
-obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o
+obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
ifeq ($(CONFIG_PERF_EVENTS),y)
obj-$(CONFIG_BPF_SYSCALL) += stackmap.o
endif
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 6b6f41f..bc9da93d 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -1,4 +1,5 @@
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ * Copyright (c) 2016,2017 Facebook
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
@@ -16,6 +17,8 @@
#include <linux/filter.h>
#include <linux/perf_event.h>
+#include "map_in_map.h"
+
static void bpf_array_free_percpu(struct bpf_array *array)
{
int i;
@@ -113,6 +116,30 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key)
return array->value + array->elem_size * index;
}
+/* emit BPF instructions equivalent to C code of array_map_lookup_elem() */
+static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
+{
+ struct bpf_insn *insn = insn_buf;
+ u32 elem_size = round_up(map->value_size, 8);
+ const int ret = BPF_REG_0;
+ const int map_ptr = BPF_REG_1;
+ const int index = BPF_REG_2;
+
+ *insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
+ *insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
+ *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 3);
+
+ if (is_power_of_2(elem_size)) {
+ *insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size));
+ } else {
+ *insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size);
+ }
+ *insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr);
+ *insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
+ *insn++ = BPF_MOV64_IMM(ret, 0);
+ return insn - insn_buf;
+}
+
/* Called from eBPF program */
static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key)
{
@@ -267,6 +294,7 @@ static const struct bpf_map_ops array_ops = {
.map_lookup_elem = array_map_lookup_elem,
.map_update_elem = array_map_update_elem,
.map_delete_elem = array_map_delete_elem,
+ .map_gen_lookup = array_map_gen_lookup,
};
static struct bpf_map_type_list array_type __ro_after_init = {
@@ -576,3 +604,64 @@ static int __init register_cgroup_array_map(void)
}
late_initcall(register_cgroup_array_map);
#endif
+
+static struct bpf_map *array_of_map_alloc(union bpf_attr *attr)
+{
+ struct bpf_map *map, *inner_map_meta;
+
+ inner_map_meta = bpf_map_meta_alloc(attr->inner_map_fd);
+ if (IS_ERR(inner_map_meta))
+ return inner_map_meta;
+
+ map = fd_array_map_alloc(attr);
+ if (IS_ERR(map)) {
+ bpf_map_meta_free(inner_map_meta);
+ return map;
+ }
+
+ map->inner_map_meta = inner_map_meta;
+
+ return map;
+}
+
+static void array_of_map_free(struct bpf_map *map)
+{
+ /* map->inner_map_meta is only accessed by syscall which
+ * is protected by fdget/fdput.
+ */
+ bpf_map_meta_free(map->inner_map_meta);
+ bpf_fd_array_map_clear(map);
+ fd_array_map_free(map);
+}
+
+static void *array_of_map_lookup_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_map **inner_map = array_map_lookup_elem(map, key);
+
+ if (!inner_map)
+ return NULL;
+
+ return READ_ONCE(*inner_map);
+}
+
+static const struct bpf_map_ops array_of_map_ops = {
+ .map_alloc = array_of_map_alloc,
+ .map_free = array_of_map_free,
+ .map_get_next_key = array_map_get_next_key,
+ .map_lookup_elem = array_of_map_lookup_elem,
+ .map_delete_elem = fd_array_map_delete_elem,
+ .map_fd_get_ptr = bpf_map_fd_get_ptr,
+ .map_fd_put_ptr = bpf_map_fd_put_ptr,
+};
+
+static struct bpf_map_type_list array_of_map_type __ro_after_init = {
+ .ops = &array_of_map_ops,
+ .type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
+};
+
+static int __init register_array_of_map(void)
+{
+ bpf_register_map_type(&array_of_map_type);
+ return 0;
+}
+late_initcall(register_array_of_map);
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 3ea87fb..d5b0623 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -13,11 +13,13 @@
#include <linux/bpf.h>
#include <linux/jhash.h>
#include <linux/filter.h>
+#include <linux/rculist_nulls.h>
#include "percpu_freelist.h"
#include "bpf_lru_list.h"
+#include "map_in_map.h"
struct bucket {
- struct hlist_head head;
+ struct hlist_nulls_head head;
raw_spinlock_t lock;
};
@@ -29,28 +31,26 @@ struct bpf_htab {
struct pcpu_freelist freelist;
struct bpf_lru lru;
};
- void __percpu *extra_elems;
+ struct htab_elem *__percpu *extra_elems;
atomic_t count; /* number of elements in this hashtable */
u32 n_buckets; /* number of hash buckets */
u32 elem_size; /* size of each element in bytes */
};
-enum extra_elem_state {
- HTAB_NOT_AN_EXTRA_ELEM = 0,
- HTAB_EXTRA_ELEM_FREE,
- HTAB_EXTRA_ELEM_USED
-};
-
/* each htab element is struct htab_elem + key + value */
struct htab_elem {
union {
- struct hlist_node hash_node;
- struct bpf_htab *htab;
- struct pcpu_freelist_node fnode;
+ struct hlist_nulls_node hash_node;
+ struct {
+ void *padding;
+ union {
+ struct bpf_htab *htab;
+ struct pcpu_freelist_node fnode;
+ };
+ };
};
union {
struct rcu_head rcu;
- enum extra_elem_state state;
struct bpf_lru_node lru_node;
};
u32 hash;
@@ -71,6 +71,11 @@ static bool htab_is_percpu(const struct bpf_htab *htab)
htab->map.map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
}
+static bool htab_is_prealloc(const struct bpf_htab *htab)
+{
+ return !(htab->map.map_flags & BPF_F_NO_PREALLOC);
+}
+
static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size,
void __percpu *pptr)
{
@@ -82,6 +87,11 @@ static inline void __percpu *htab_elem_get_ptr(struct htab_elem *l, u32 key_size
return *(void __percpu **)(l->key + key_size);
}
+static void *fd_htab_map_get_ptr(const struct bpf_map *map, struct htab_elem *l)
+{
+ return *(void **)(l->key + roundup(map->key_size, 8));
+}
+
static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i)
{
return (struct htab_elem *) (htab->elems + i * htab->elem_size);
@@ -122,17 +132,20 @@ static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key,
static int prealloc_init(struct bpf_htab *htab)
{
+ u32 num_entries = htab->map.max_entries;
int err = -ENOMEM, i;
- htab->elems = bpf_map_area_alloc(htab->elem_size *
- htab->map.max_entries);
+ if (!htab_is_percpu(htab) && !htab_is_lru(htab))
+ num_entries += num_possible_cpus();
+
+ htab->elems = bpf_map_area_alloc(htab->elem_size * num_entries);
if (!htab->elems)
return -ENOMEM;
if (!htab_is_percpu(htab))
goto skip_percpu_elems;
- for (i = 0; i < htab->map.max_entries; i++) {
+ for (i = 0; i < num_entries; i++) {
u32 size = round_up(htab->map.value_size, 8);
void __percpu *pptr;
@@ -160,10 +173,11 @@ static int prealloc_init(struct bpf_htab *htab)
if (htab_is_lru(htab))
bpf_lru_populate(&htab->lru, htab->elems,
offsetof(struct htab_elem, lru_node),
- htab->elem_size, htab->map.max_entries);
+ htab->elem_size, num_entries);
else
- pcpu_freelist_populate(&htab->freelist, htab->elems,
- htab->elem_size, htab->map.max_entries);
+ pcpu_freelist_populate(&htab->freelist,
+ htab->elems + offsetof(struct htab_elem, fnode),
+ htab->elem_size, num_entries);
return 0;
@@ -184,16 +198,22 @@ static void prealloc_destroy(struct bpf_htab *htab)
static int alloc_extra_elems(struct bpf_htab *htab)
{
- void __percpu *pptr;
+ struct htab_elem *__percpu *pptr, *l_new;
+ struct pcpu_freelist_node *l;
int cpu;
- pptr = __alloc_percpu_gfp(htab->elem_size, 8, GFP_USER | __GFP_NOWARN);
+ pptr = __alloc_percpu_gfp(sizeof(struct htab_elem *), 8,
+ GFP_USER | __GFP_NOWARN);
if (!pptr)
return -ENOMEM;
for_each_possible_cpu(cpu) {
- ((struct htab_elem *)per_cpu_ptr(pptr, cpu))->state =
- HTAB_EXTRA_ELEM_FREE;
+ l = pcpu_freelist_pop(&htab->freelist);
+ /* pop will succeed, since prealloc_init()
+ * preallocated extra num_possible_cpus elements
+ */
+ l_new = container_of(l, struct htab_elem, fnode);
+ *per_cpu_ptr(pptr, cpu) = l_new;
}
htab->extra_elems = pptr;
return 0;
@@ -217,6 +237,11 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
int err, i;
u64 cost;
+ BUILD_BUG_ON(offsetof(struct htab_elem, htab) !=
+ offsetof(struct htab_elem, hash_node.pprev));
+ BUILD_BUG_ON(offsetof(struct htab_elem, fnode.next) !=
+ offsetof(struct htab_elem, hash_node.pprev));
+
if (lru && !capable(CAP_SYS_ADMIN))
/* LRU implementation is much complicated than other
* maps. Hence, limit to CAP_SYS_ADMIN for now.
@@ -326,29 +351,29 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
goto free_htab;
for (i = 0; i < htab->n_buckets; i++) {
- INIT_HLIST_HEAD(&htab->buckets[i].head);
+ INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i);
raw_spin_lock_init(&htab->buckets[i].lock);
}
- if (!percpu && !lru) {
- /* lru itself can remove the least used element, so
- * there is no need for an extra elem during map_update.
- */
- err = alloc_extra_elems(htab);
- if (err)
- goto free_buckets;
- }
-
if (prealloc) {
err = prealloc_init(htab);
if (err)
- goto free_extra_elems;
+ goto free_buckets;
+
+ if (!percpu && !lru) {
+ /* lru itself can remove the least used element, so
+ * there is no need for an extra elem during map_update.
+ */
+ err = alloc_extra_elems(htab);
+ if (err)
+ goto free_prealloc;
+ }
}
return &htab->map;
-free_extra_elems:
- free_percpu(htab->extra_elems);
+free_prealloc:
+ prealloc_destroy(htab);
free_buckets:
bpf_map_area_free(htab->buckets);
free_htab:
@@ -366,28 +391,56 @@ static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
return &htab->buckets[hash & (htab->n_buckets - 1)];
}
-static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
+static inline struct hlist_nulls_head *select_bucket(struct bpf_htab *htab, u32 hash)
{
return &__select_bucket(htab, hash)->head;
}
-static struct htab_elem *lookup_elem_raw(struct hlist_head *head, u32 hash,
+/* this lookup function can only be called with bucket lock taken */
+static struct htab_elem *lookup_elem_raw(struct hlist_nulls_head *head, u32 hash,
void *key, u32 key_size)
{
+ struct hlist_nulls_node *n;
struct htab_elem *l;
- hlist_for_each_entry_rcu(l, head, hash_node)
+ hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
if (l->hash == hash && !memcmp(&l->key, key, key_size))
return l;
return NULL;
}
-/* Called from syscall or from eBPF program */
+/* can be called without bucket lock. it will repeat the loop in
+ * the unlikely event when elements moved from one bucket into another
+ * while link list is being walked
+ */
+static struct htab_elem *lookup_nulls_elem_raw(struct hlist_nulls_head *head,
+ u32 hash, void *key,
+ u32 key_size, u32 n_buckets)
+{
+ struct hlist_nulls_node *n;
+ struct htab_elem *l;
+
+again:
+ hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
+ if (l->hash == hash && !memcmp(&l->key, key, key_size))
+ return l;
+
+ if (unlikely(get_nulls_value(n) != (hash & (n_buckets - 1))))
+ goto again;
+
+ return NULL;
+}
+
+/* Called from syscall or from eBPF program directly, so
+ * arguments have to match bpf_map_lookup_elem() exactly.
+ * The return value is adjusted by BPF instructions
+ * in htab_map_gen_lookup().
+ */
static void *__htab_map_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
- struct hlist_head *head;
+ struct hlist_nulls_head *head;
struct htab_elem *l;
u32 hash, key_size;
@@ -400,7 +453,7 @@ static void *__htab_map_lookup_elem(struct bpf_map *map, void *key)
head = select_bucket(htab, hash);
- l = lookup_elem_raw(head, hash, key, key_size);
+ l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets);
return l;
}
@@ -415,6 +468,30 @@ static void *htab_map_lookup_elem(struct bpf_map *map, void *key)
return NULL;
}
+/* inline bpf_map_lookup_elem() call.
+ * Instead of:
+ * bpf_prog
+ * bpf_map_lookup_elem
+ * map->ops->map_lookup_elem
+ * htab_map_lookup_elem
+ * __htab_map_lookup_elem
+ * do:
+ * bpf_prog
+ * __htab_map_lookup_elem
+ */
+static u32 htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
+{
+ struct bpf_insn *insn = insn_buf;
+ const int ret = BPF_REG_0;
+
+ *insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem);
+ *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1);
+ *insn++ = BPF_ALU64_IMM(BPF_ADD, ret,
+ offsetof(struct htab_elem, key) +
+ round_up(map->key_size, 8));
+ return insn - insn_buf;
+}
+
static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key)
{
struct htab_elem *l = __htab_map_lookup_elem(map, key);
@@ -433,8 +510,9 @@ static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key)
static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
{
struct bpf_htab *htab = (struct bpf_htab *)arg;
- struct htab_elem *l, *tgt_l;
- struct hlist_head *head;
+ struct htab_elem *l = NULL, *tgt_l;
+ struct hlist_nulls_head *head;
+ struct hlist_nulls_node *n;
unsigned long flags;
struct bucket *b;
@@ -444,9 +522,9 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
raw_spin_lock_irqsave(&b->lock, flags);
- hlist_for_each_entry_rcu(l, head, hash_node)
+ hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
if (l == tgt_l) {
- hlist_del_rcu(&l->hash_node);
+ hlist_nulls_del_rcu(&l->hash_node);
break;
}
@@ -459,7 +537,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
{
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
- struct hlist_head *head;
+ struct hlist_nulls_head *head;
struct htab_elem *l, *next_l;
u32 hash, key_size;
int i;
@@ -473,7 +551,7 @@ static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
head = select_bucket(htab, hash);
/* lookup the key */
- l = lookup_elem_raw(head, hash, key, key_size);
+ l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets);
if (!l) {
i = 0;
@@ -481,7 +559,7 @@ static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
}
/* key was found, get next key in the same bucket */
- next_l = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&l->hash_node)),
+ next_l = hlist_nulls_entry_safe(rcu_dereference_raw(hlist_nulls_next_rcu(&l->hash_node)),
struct htab_elem, hash_node);
if (next_l) {
@@ -500,7 +578,7 @@ static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
head = select_bucket(htab, i);
/* pick first element in the bucket */
- next_l = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),
+ next_l = hlist_nulls_entry_safe(rcu_dereference_raw(hlist_nulls_first_rcu(head)),
struct htab_elem, hash_node);
if (next_l) {
/* if it's not empty, just return it */
@@ -538,12 +616,15 @@ static void htab_elem_free_rcu(struct rcu_head *head)
static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
{
- if (l->state == HTAB_EXTRA_ELEM_USED) {
- l->state = HTAB_EXTRA_ELEM_FREE;
- return;
+ struct bpf_map *map = &htab->map;
+
+ if (map->ops->map_fd_put_ptr) {
+ void *ptr = fd_htab_map_get_ptr(map, l);
+
+ map->ops->map_fd_put_ptr(ptr);
}
- if (!(htab->map.map_flags & BPF_F_NO_PREALLOC)) {
+ if (htab_is_prealloc(htab)) {
pcpu_freelist_push(&htab->freelist, &l->fnode);
} else {
atomic_dec(&htab->count);
@@ -573,43 +654,43 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr,
static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
void *value, u32 key_size, u32 hash,
bool percpu, bool onallcpus,
- bool old_elem_exists)
+ struct htab_elem *old_elem)
{
u32 size = htab->map.value_size;
- bool prealloc = !(htab->map.map_flags & BPF_F_NO_PREALLOC);
- struct htab_elem *l_new;
+ bool prealloc = htab_is_prealloc(htab);
+ struct htab_elem *l_new, **pl_new;
void __percpu *pptr;
- int err = 0;
if (prealloc) {
- l_new = (struct htab_elem *)pcpu_freelist_pop(&htab->freelist);
- if (!l_new)
- err = -E2BIG;
- } else {
- if (atomic_inc_return(&htab->count) > htab->map.max_entries) {
- atomic_dec(&htab->count);
- err = -E2BIG;
+ if (old_elem) {
+ /* if we're updating the existing element,
+ * use per-cpu extra elems to avoid freelist_pop/push
+ */
+ pl_new = this_cpu_ptr(htab->extra_elems);
+ l_new = *pl_new;
+ *pl_new = old_elem;
} else {
- l_new = kmalloc(htab->elem_size,
- GFP_ATOMIC | __GFP_NOWARN);
- if (!l_new)
- return ERR_PTR(-ENOMEM);
+ struct pcpu_freelist_node *l;
+
+ l = pcpu_freelist_pop(&htab->freelist);
+ if (!l)
+ return ERR_PTR(-E2BIG);
+ l_new = container_of(l, struct htab_elem, fnode);
}
- }
-
- if (err) {
- if (!old_elem_exists)
- return ERR_PTR(err);
-
- /* if we're updating the existing element and the hash table
- * is full, use per-cpu extra elems
- */
- l_new = this_cpu_ptr(htab->extra_elems);
- if (l_new->state != HTAB_EXTRA_ELEM_FREE)
- return ERR_PTR(-E2BIG);
- l_new->state = HTAB_EXTRA_ELEM_USED;
} else {
- l_new->state = HTAB_NOT_AN_EXTRA_ELEM;
+ if (atomic_inc_return(&htab->count) > htab->map.max_entries)
+ if (!old_elem) {
+ /* when map is full and update() is replacing
+ * old element, it's ok to allocate, since
+ * old element will be freed immediately.
+ * Otherwise return an error
+ */
+ atomic_dec(&htab->count);
+ return ERR_PTR(-E2BIG);
+ }
+ l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN);
+ if (!l_new)
+ return ERR_PTR(-ENOMEM);
}
memcpy(l_new->key, key, key_size);
@@ -661,7 +742,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
{
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
struct htab_elem *l_new = NULL, *l_old;
- struct hlist_head *head;
+ struct hlist_nulls_head *head;
unsigned long flags;
struct bucket *b;
u32 key_size, hash;
@@ -690,7 +771,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
goto err;
l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false,
- !!l_old);
+ l_old);
if (IS_ERR(l_new)) {
/* all pre-allocated elements are in use or memory exhausted */
ret = PTR_ERR(l_new);
@@ -700,10 +781,11 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
/* add new element to the head of the list, so that
* concurrent search will find it before old elem
*/
- hlist_add_head_rcu(&l_new->hash_node, head);
+ hlist_nulls_add_head_rcu(&l_new->hash_node, head);
if (l_old) {
- hlist_del_rcu(&l_old->hash_node);
- free_htab_elem(htab, l_old);
+ hlist_nulls_del_rcu(&l_old->hash_node);
+ if (!htab_is_prealloc(htab))
+ free_htab_elem(htab, l_old);
}
ret = 0;
err:
@@ -716,7 +798,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
{
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
struct htab_elem *l_new, *l_old = NULL;
- struct hlist_head *head;
+ struct hlist_nulls_head *head;
unsigned long flags;
struct bucket *b;
u32 key_size, hash;
@@ -757,10 +839,10 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
/* add new element to the head of the list, so that
* concurrent search will find it before old elem
*/
- hlist_add_head_rcu(&l_new->hash_node, head);
+ hlist_nulls_add_head_rcu(&l_new->hash_node, head);
if (l_old) {
bpf_lru_node_set_ref(&l_new->lru_node);
- hlist_del_rcu(&l_old->hash_node);
+ hlist_nulls_del_rcu(&l_old->hash_node);
}
ret = 0;
@@ -781,7 +863,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
{
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
struct htab_elem *l_new = NULL, *l_old;
- struct hlist_head *head;
+ struct hlist_nulls_head *head;
unsigned long flags;
struct bucket *b;
u32 key_size, hash;
@@ -815,12 +897,12 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
value, onallcpus);
} else {
l_new = alloc_htab_elem(htab, key, value, key_size,
- hash, true, onallcpus, false);
+ hash, true, onallcpus, NULL);
if (IS_ERR(l_new)) {
ret = PTR_ERR(l_new);
goto err;
}
- hlist_add_head_rcu(&l_new->hash_node, head);
+ hlist_nulls_add_head_rcu(&l_new->hash_node, head);
}
ret = 0;
err:
@@ -834,7 +916,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
{
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
struct htab_elem *l_new = NULL, *l_old;
- struct hlist_head *head;
+ struct hlist_nulls_head *head;
unsigned long flags;
struct bucket *b;
u32 key_size, hash;
@@ -882,7 +964,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
} else {
pcpu_copy_value(htab, htab_elem_get_ptr(l_new, key_size),
value, onallcpus);
- hlist_add_head_rcu(&l_new->hash_node, head);
+ hlist_nulls_add_head_rcu(&l_new->hash_node, head);
l_new = NULL;
}
ret = 0;
@@ -910,7 +992,7 @@ static int htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
static int htab_map_delete_elem(struct bpf_map *map, void *key)
{
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
- struct hlist_head *head;
+ struct hlist_nulls_head *head;
struct bucket *b;
struct htab_elem *l;
unsigned long flags;
@@ -930,7 +1012,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key)
l = lookup_elem_raw(head, hash, key, key_size);
if (l) {
- hlist_del_rcu(&l->hash_node);
+ hlist_nulls_del_rcu(&l->hash_node);
free_htab_elem(htab, l);
ret = 0;
}
@@ -942,7 +1024,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key)
static int htab_lru_map_delete_elem(struct bpf_map *map, void *key)
{
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
- struct hlist_head *head;
+ struct hlist_nulls_head *head;
struct bucket *b;
struct htab_elem *l;
unsigned long flags;
@@ -962,7 +1044,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key)
l = lookup_elem_raw(head, hash, key, key_size);
if (l) {
- hlist_del_rcu(&l->hash_node);
+ hlist_nulls_del_rcu(&l->hash_node);
ret = 0;
}
@@ -977,17 +1059,17 @@ static void delete_all_elements(struct bpf_htab *htab)
int i;
for (i = 0; i < htab->n_buckets; i++) {
- struct hlist_head *head = select_bucket(htab, i);
- struct hlist_node *n;
+ struct hlist_nulls_head *head = select_bucket(htab, i);
+ struct hlist_nulls_node *n;
struct htab_elem *l;
- hlist_for_each_entry_safe(l, n, head, hash_node) {
- hlist_del_rcu(&l->hash_node);
- if (l->state != HTAB_EXTRA_ELEM_USED)
- htab_elem_free(htab, l);
+ hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
+ hlist_nulls_del_rcu(&l->hash_node);
+ htab_elem_free(htab, l);
}
}
}
+
/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
static void htab_map_free(struct bpf_map *map)
{
@@ -1004,7 +1086,7 @@ static void htab_map_free(struct bpf_map *map)
* not have executed. Wait for them.
*/
rcu_barrier();
- if (htab->map.map_flags & BPF_F_NO_PREALLOC)
+ if (!htab_is_prealloc(htab))
delete_all_elements(htab);
else
prealloc_destroy(htab);
@@ -1021,6 +1103,7 @@ static const struct bpf_map_ops htab_ops = {
.map_lookup_elem = htab_map_lookup_elem,
.map_update_elem = htab_map_update_elem,
.map_delete_elem = htab_map_delete_elem,
+ .map_gen_lookup = htab_map_gen_lookup,
};
static struct bpf_map_type_list htab_type __ro_after_init = {
@@ -1143,12 +1226,118 @@ static struct bpf_map_type_list htab_lru_percpu_type __ro_after_init = {
.type = BPF_MAP_TYPE_LRU_PERCPU_HASH,
};
+static struct bpf_map *fd_htab_map_alloc(union bpf_attr *attr)
+{
+ struct bpf_map *map;
+
+ if (attr->value_size != sizeof(u32))
+ return ERR_PTR(-EINVAL);
+
+ /* pointer is stored internally */
+ attr->value_size = sizeof(void *);
+ map = htab_map_alloc(attr);
+ attr->value_size = sizeof(u32);
+
+ return map;
+}
+
+static void fd_htab_map_free(struct bpf_map *map)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct hlist_nulls_node *n;
+ struct hlist_nulls_head *head;
+ struct htab_elem *l;
+ int i;
+
+ for (i = 0; i < htab->n_buckets; i++) {
+ head = select_bucket(htab, i);
+
+ hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
+ void *ptr = fd_htab_map_get_ptr(map, l);
+
+ map->ops->map_fd_put_ptr(ptr);
+ }
+ }
+
+ htab_map_free(map);
+}
+
+/* only called from syscall */
+int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
+ void *key, void *value, u64 map_flags)
+{
+ void *ptr;
+ int ret;
+ u32 ufd = *(u32 *)value;
+
+ ptr = map->ops->map_fd_get_ptr(map, map_file, ufd);
+ if (IS_ERR(ptr))
+ return PTR_ERR(ptr);
+
+ ret = htab_map_update_elem(map, key, &ptr, map_flags);
+ if (ret)
+ map->ops->map_fd_put_ptr(ptr);
+
+ return ret;
+}
+
+static struct bpf_map *htab_of_map_alloc(union bpf_attr *attr)
+{
+ struct bpf_map *map, *inner_map_meta;
+
+ inner_map_meta = bpf_map_meta_alloc(attr->inner_map_fd);
+ if (IS_ERR(inner_map_meta))
+ return inner_map_meta;
+
+ map = fd_htab_map_alloc(attr);
+ if (IS_ERR(map)) {
+ bpf_map_meta_free(inner_map_meta);
+ return map;
+ }
+
+ map->inner_map_meta = inner_map_meta;
+
+ return map;
+}
+
+static void *htab_of_map_lookup_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_map **inner_map = htab_map_lookup_elem(map, key);
+
+ if (!inner_map)
+ return NULL;
+
+ return READ_ONCE(*inner_map);
+}
+
+static void htab_of_map_free(struct bpf_map *map)
+{
+ bpf_map_meta_free(map->inner_map_meta);
+ fd_htab_map_free(map);
+}
+
+static const struct bpf_map_ops htab_of_map_ops = {
+ .map_alloc = htab_of_map_alloc,
+ .map_free = htab_of_map_free,
+ .map_get_next_key = htab_map_get_next_key,
+ .map_lookup_elem = htab_of_map_lookup_elem,
+ .map_delete_elem = htab_map_delete_elem,
+ .map_fd_get_ptr = bpf_map_fd_get_ptr,
+ .map_fd_put_ptr = bpf_map_fd_put_ptr,
+};
+
+static struct bpf_map_type_list htab_of_map_type __ro_after_init = {
+ .ops = &htab_of_map_ops,
+ .type = BPF_MAP_TYPE_HASH_OF_MAPS,
+};
+
static int __init register_htab_map(void)
{
bpf_register_map_type(&htab_type);
bpf_register_map_type(&htab_percpu_type);
bpf_register_map_type(&htab_lru_type);
bpf_register_map_type(&htab_lru_percpu_type);
+ bpf_register_map_type(&htab_of_map_type);
return 0;
}
late_initcall(register_htab_map);
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
new file mode 100644
index 0000000..59bcdf8
--- /dev/null
+++ b/kernel/bpf/map_in_map.c
@@ -0,0 +1,97 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/slab.h>
+#include <linux/bpf.h>
+
+#include "map_in_map.h"
+
+struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
+{
+ struct bpf_map *inner_map, *inner_map_meta;
+ struct fd f;
+
+ f = fdget(inner_map_ufd);
+ inner_map = __bpf_map_get(f);
+ if (IS_ERR(inner_map))
+ return inner_map;
+
+ /* prog_array->owner_prog_type and owner_jited
+ * is a runtime binding. Doing static check alone
+ * in the verifier is not enough.
+ */
+ if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
+ fdput(f);
+ return ERR_PTR(-ENOTSUPP);
+ }
+
+ /* Does not support >1 level map-in-map */
+ if (inner_map->inner_map_meta) {
+ fdput(f);
+ return ERR_PTR(-EINVAL);
+ }
+
+ inner_map_meta = kzalloc(sizeof(*inner_map_meta), GFP_USER);
+ if (!inner_map_meta) {
+ fdput(f);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ inner_map_meta->map_type = inner_map->map_type;
+ inner_map_meta->key_size = inner_map->key_size;
+ inner_map_meta->value_size = inner_map->value_size;
+ inner_map_meta->map_flags = inner_map->map_flags;
+ inner_map_meta->ops = inner_map->ops;
+ inner_map_meta->max_entries = inner_map->max_entries;
+
+ fdput(f);
+ return inner_map_meta;
+}
+
+void bpf_map_meta_free(struct bpf_map *map_meta)
+{
+ kfree(map_meta);
+}
+
+bool bpf_map_meta_equal(const struct bpf_map *meta0,
+ const struct bpf_map *meta1)
+{
+ /* No need to compare ops because it is covered by map_type */
+ return meta0->map_type == meta1->map_type &&
+ meta0->key_size == meta1->key_size &&
+ meta0->value_size == meta1->value_size &&
+ meta0->map_flags == meta1->map_flags &&
+ meta0->max_entries == meta1->max_entries;
+}
+
+void *bpf_map_fd_get_ptr(struct bpf_map *map,
+ struct file *map_file /* not used */,
+ int ufd)
+{
+ struct bpf_map *inner_map;
+ struct fd f;
+
+ f = fdget(ufd);
+ inner_map = __bpf_map_get(f);
+ if (IS_ERR(inner_map))
+ return inner_map;
+
+ if (bpf_map_meta_equal(map->inner_map_meta, inner_map))
+ inner_map = bpf_map_inc(inner_map, false);
+ else
+ inner_map = ERR_PTR(-EINVAL);
+
+ fdput(f);
+ return inner_map;
+}
+
+void bpf_map_fd_put_ptr(void *ptr)
+{
+ /* ptr->ops->map_free() has to go through one
+ * rcu grace period by itself.
+ */
+ bpf_map_put(ptr);
+}
diff --git a/kernel/bpf/map_in_map.h b/kernel/bpf/map_in_map.h
new file mode 100644
index 0000000..177fadb6
--- /dev/null
+++ b/kernel/bpf/map_in_map.h
@@ -0,0 +1,23 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef __MAP_IN_MAP_H__
+#define __MAP_IN_MAP_H__
+
+#include <linux/types.h>
+
+struct file;
+struct bpf_map;
+
+struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd);
+void bpf_map_meta_free(struct bpf_map *map_meta);
+bool bpf_map_meta_equal(const struct bpf_map *meta0,
+ const struct bpf_map *meta1);
+void *bpf_map_fd_get_ptr(struct bpf_map *map, struct file *map_file,
+ int ufd);
+void bpf_map_fd_put_ptr(void *ptr);
+
+#endif
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 7af0dcc..ab0cf4c4 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -215,7 +215,7 @@ int bpf_map_new_fd(struct bpf_map *map)
offsetof(union bpf_attr, CMD##_LAST_FIELD) - \
sizeof(attr->CMD##_LAST_FIELD)) != NULL
-#define BPF_MAP_CREATE_LAST_FIELD map_flags
+#define BPF_MAP_CREATE_LAST_FIELD inner_map_fd
/* called via syscall */
static int map_create(union bpf_attr *attr)
{
@@ -352,6 +352,9 @@ static int map_lookup_elem(union bpf_attr *attr)
err = bpf_percpu_array_copy(map, key, value);
} else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) {
err = bpf_stackmap_copy(map, key, value);
+ } else if (map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
+ map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+ err = -ENOTSUPP;
} else {
rcu_read_lock();
ptr = map->ops->map_lookup_elem(map, key);
@@ -438,11 +441,17 @@ static int map_update_elem(union bpf_attr *attr)
err = bpf_percpu_array_update(map, key, value, attr->flags);
} else if (map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY ||
map->map_type == BPF_MAP_TYPE_PROG_ARRAY ||
- map->map_type == BPF_MAP_TYPE_CGROUP_ARRAY) {
+ map->map_type == BPF_MAP_TYPE_CGROUP_ARRAY ||
+ map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) {
rcu_read_lock();
err = bpf_fd_array_map_update_elem(map, f.file, key, value,
attr->flags);
rcu_read_unlock();
+ } else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+ rcu_read_lock();
+ err = bpf_fd_htab_map_update_elem(map, f.file, key, value,
+ attr->flags);
+ rcu_read_unlock();
} else {
rcu_read_lock();
err = map->ops->map_update_elem(map, key, value, attr->flags);
@@ -586,59 +595,6 @@ void bpf_register_prog_type(struct bpf_prog_type_list *tl)
list_add(&tl->list_node, &bpf_prog_types);
}
-/* fixup insn->imm field of bpf_call instructions:
- * if (insn->imm == BPF_FUNC_map_lookup_elem)
- * insn->imm = bpf_map_lookup_elem - __bpf_call_base;
- * else if (insn->imm == BPF_FUNC_map_update_elem)
- * insn->imm = bpf_map_update_elem - __bpf_call_base;
- * else ...
- *
- * this function is called after eBPF program passed verification
- */
-static void fixup_bpf_calls(struct bpf_prog *prog)
-{
- const struct bpf_func_proto *fn;
- int i;
-
- for (i = 0; i < prog->len; i++) {
- struct bpf_insn *insn = &prog->insnsi[i];
-
- if (insn->code == (BPF_JMP | BPF_CALL)) {
- /* we reach here when program has bpf_call instructions
- * and it passed bpf_check(), means that
- * ops->get_func_proto must have been supplied, check it
- */
- BUG_ON(!prog->aux->ops->get_func_proto);
-
- if (insn->imm == BPF_FUNC_get_route_realm)
- prog->dst_needed = 1;
- if (insn->imm == BPF_FUNC_get_prandom_u32)
- bpf_user_rnd_init_once();
- if (insn->imm == BPF_FUNC_xdp_adjust_head)
- prog->xdp_adjust_head = 1;
- if (insn->imm == BPF_FUNC_tail_call) {
- /* mark bpf_tail_call as different opcode
- * to avoid conditional branch in
- * interpeter for every normal call
- * and to prevent accidental JITing by
- * JIT compiler that doesn't support
- * bpf_tail_call yet
- */
- insn->imm = 0;
- insn->code |= BPF_X;
- continue;
- }
-
- fn = prog->aux->ops->get_func_proto(insn->imm);
- /* all functions that have prototype and verifier allowed
- * programs to call them, must be real in-kernel functions
- */
- BUG_ON(!fn->func);
- insn->imm = fn->func - __bpf_call_base;
- }
- }
-}
-
/* drop refcnt on maps used by eBPF program and free auxilary data */
static void free_used_maps(struct bpf_prog_aux *aux)
{
@@ -892,9 +848,6 @@ static int bpf_prog_load(union bpf_attr *attr)
if (err < 0)
goto free_used_maps;
- /* fixup BPF_CALL->imm field */
- fixup_bpf_calls(prog);
-
/* eBPF program is ready to be JITed */
prog = bpf_prog_select_runtime(prog, &err);
if (err < 0)
@@ -1020,6 +973,28 @@ static int bpf_prog_detach(const union bpf_attr *attr)
}
#endif /* CONFIG_CGROUP_BPF */
+#define BPF_PROG_TEST_RUN_LAST_FIELD test.duration
+
+static int bpf_prog_test_run(const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ struct bpf_prog *prog;
+ int ret = -ENOTSUPP;
+
+ if (CHECK_ATTR(BPF_PROG_TEST_RUN))
+ return -EINVAL;
+
+ prog = bpf_prog_get(attr->test.prog_fd);
+ if (IS_ERR(prog))
+ return PTR_ERR(prog);
+
+ if (prog->aux->ops->test_run)
+ ret = prog->aux->ops->test_run(prog, attr, uattr);
+
+ bpf_prog_put(prog);
+ return ret;
+}
+
SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
{
union bpf_attr attr = {};
@@ -1086,7 +1061,6 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_OBJ_GET:
err = bpf_obj_get(&attr);
break;
-
#ifdef CONFIG_CGROUP_BPF
case BPF_PROG_ATTACH:
err = bpf_prog_attach(&attr);
@@ -1095,7 +1069,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
err = bpf_prog_detach(&attr);
break;
#endif
-
+ case BPF_PROG_TEST_RUN:
+ err = bpf_prog_test_run(&attr, uattr);
+ break;
default:
err = -EINVAL;
break;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 796b68d..62e1e44 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -143,6 +143,8 @@ struct bpf_verifier_stack_elem {
#define BPF_COMPLEXITY_LIMIT_INSNS 65536
#define BPF_COMPLEXITY_LIMIT_STACK 1024
+#define BPF_MAP_PTR_POISON ((void *)0xeB9F + POISON_POINTER_DELTA)
+
struct bpf_call_arg_meta {
struct bpf_map *map_ptr;
bool raw_mode;
@@ -765,38 +767,56 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
}
}
-static int check_ptr_alignment(struct bpf_verifier_env *env,
- struct bpf_reg_state *reg, int off, int size)
+static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg,
+ int off, int size)
{
- if (reg->type != PTR_TO_PACKET && reg->type != PTR_TO_MAP_VALUE_ADJ) {
- if (off % size != 0) {
- verbose("misaligned access off %d size %d\n",
- off, size);
- return -EACCES;
- } else {
- return 0;
- }
- }
-
- if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
- /* misaligned access to packet is ok on x86,arm,arm64 */
- return 0;
-
if (reg->id && size != 1) {
- verbose("Unknown packet alignment. Only byte-sized access allowed\n");
+ verbose("Unknown alignment. Only byte-sized access allowed in packet access.\n");
return -EACCES;
}
/* skb->data is NET_IP_ALIGN-ed */
- if (reg->type == PTR_TO_PACKET &&
- (NET_IP_ALIGN + reg->off + off) % size != 0) {
+ if ((NET_IP_ALIGN + reg->off + off) % size != 0) {
verbose("misaligned packet access off %d+%d+%d size %d\n",
NET_IP_ALIGN, reg->off, off, size);
return -EACCES;
}
+
return 0;
}
+static int check_val_ptr_alignment(const struct bpf_reg_state *reg,
+ int size)
+{
+ if (size != 1) {
+ verbose("Unknown alignment. Only byte-sized access allowed in value access.\n");
+ return -EACCES;
+ }
+
+ return 0;
+}
+
+static int check_ptr_alignment(const struct bpf_reg_state *reg,
+ int off, int size)
+{
+ switch (reg->type) {
+ case PTR_TO_PACKET:
+ return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 :
+ check_pkt_ptr_alignment(reg, off, size);
+ case PTR_TO_MAP_VALUE_ADJ:
+ return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 :
+ check_val_ptr_alignment(reg, size);
+ default:
+ if (off % size != 0) {
+ verbose("misaligned access off %d size %d\n",
+ off, size);
+ return -EACCES;
+ }
+
+ return 0;
+ }
+}
+
/* check whether memory at (regno + off) is accessible for t = (read | write)
* if t==write, value_regno is a register which value is stored into memory
* if t==read, value_regno is a register which will receive the value from memory
@@ -818,7 +838,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off,
if (size < 0)
return size;
- err = check_ptr_alignment(env, reg, off, size);
+ err = check_ptr_alignment(reg, off, size);
if (err)
return err;
@@ -1197,6 +1217,10 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
func_id != BPF_FUNC_current_task_under_cgroup)
goto error;
break;
+ case BPF_MAP_TYPE_ARRAY_OF_MAPS:
+ case BPF_MAP_TYPE_HASH_OF_MAPS:
+ if (func_id != BPF_FUNC_map_lookup_elem)
+ goto error;
default:
break;
}
@@ -1273,7 +1297,7 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
}
}
-static int check_call(struct bpf_verifier_env *env, int func_id)
+static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
{
struct bpf_verifier_state *state = &env->cur_state;
const struct bpf_func_proto *fn = NULL;
@@ -1357,6 +1381,8 @@ static int check_call(struct bpf_verifier_env *env, int func_id)
} else if (fn->ret_type == RET_VOID) {
regs[BPF_REG_0].type = NOT_INIT;
} else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) {
+ struct bpf_insn_aux_data *insn_aux;
+
regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
regs[BPF_REG_0].max_value = regs[BPF_REG_0].min_value = 0;
/* remember map_ptr, so that check_map_access()
@@ -1369,6 +1395,11 @@ static int check_call(struct bpf_verifier_env *env, int func_id)
}
regs[BPF_REG_0].map_ptr = meta.map_ptr;
regs[BPF_REG_0].id = ++env->id_gen;
+ insn_aux = &env->insn_aux_data[insn_idx];
+ if (!insn_aux->map_ptr)
+ insn_aux->map_ptr = meta.map_ptr;
+ else if (insn_aux->map_ptr != meta.map_ptr)
+ insn_aux->map_ptr = BPF_MAP_PTR_POISON;
} else {
verbose("unknown return type %d of func %s#%d\n",
fn->ret_type, func_id_name(func_id), func_id);
@@ -1925,6 +1956,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
* register as unknown.
*/
if (env->allow_ptr_leaks &&
+ BPF_CLASS(insn->code) == BPF_ALU64 && opcode == BPF_ADD &&
(dst_reg->type == PTR_TO_MAP_VALUE ||
dst_reg->type == PTR_TO_MAP_VALUE_ADJ))
dst_reg->type = PTR_TO_MAP_VALUE_ADJ;
@@ -1973,14 +2005,15 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state,
for (i = 0; i < MAX_BPF_REG; i++)
if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id)
- regs[i].range = dst_reg->off;
+ /* keep the maximum range already checked */
+ regs[i].range = max(regs[i].range, dst_reg->off);
for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
if (state->stack_slot_type[i] != STACK_SPILL)
continue;
reg = &state->spilled_regs[i / BPF_REG_SIZE];
if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id)
- reg->range = dst_reg->off;
+ reg->range = max(reg->range, dst_reg->off);
}
}
@@ -2092,14 +2125,19 @@ static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id,
struct bpf_reg_state *reg = ®s[regno];
if (reg->type == PTR_TO_MAP_VALUE_OR_NULL && reg->id == id) {
- reg->type = type;
+ if (type == UNKNOWN_VALUE) {
+ __mark_reg_unknown_value(regs, regno);
+ } else if (reg->map_ptr->inner_map_meta) {
+ reg->type = CONST_PTR_TO_MAP;
+ reg->map_ptr = reg->map_ptr->inner_map_meta;
+ } else {
+ reg->type = type;
+ }
/* We don't need id from this point onwards anymore, thus we
* should better reset it, so that state pruning has chances
* to take effect.
*/
reg->id = 0;
- if (type == UNKNOWN_VALUE)
- __mark_reg_unknown_value(regs, regno);
}
}
@@ -2940,7 +2978,7 @@ static int do_check(struct bpf_verifier_env *env)
return -EINVAL;
}
- err = check_call(env, insn->imm);
+ err = check_call(env, insn->imm, insn_idx);
if (err)
return err;
@@ -3024,16 +3062,33 @@ static int do_check(struct bpf_verifier_env *env)
return 0;
}
+static int check_map_prealloc(struct bpf_map *map)
+{
+ return (map->map_type != BPF_MAP_TYPE_HASH &&
+ map->map_type != BPF_MAP_TYPE_PERCPU_HASH &&
+ map->map_type != BPF_MAP_TYPE_HASH_OF_MAPS) ||
+ !(map->map_flags & BPF_F_NO_PREALLOC);
+}
+
static int check_map_prog_compatibility(struct bpf_map *map,
struct bpf_prog *prog)
{
- if (prog->type == BPF_PROG_TYPE_PERF_EVENT &&
- (map->map_type == BPF_MAP_TYPE_HASH ||
- map->map_type == BPF_MAP_TYPE_PERCPU_HASH) &&
- (map->map_flags & BPF_F_NO_PREALLOC)) {
- verbose("perf_event programs can only use preallocated hash map\n");
- return -EINVAL;
+ /* Make sure that BPF_PROG_TYPE_PERF_EVENT programs only use
+ * preallocated hash maps, since doing memory allocation
+ * in overflow_handler can crash depending on where nmi got
+ * triggered.
+ */
+ if (prog->type == BPF_PROG_TYPE_PERF_EVENT) {
+ if (!check_map_prealloc(map)) {
+ verbose("perf_event programs can only use preallocated hash map\n");
+ return -EINVAL;
+ }
+ if (map->inner_map_meta &&
+ !check_map_prealloc(map->inner_map_meta)) {
+ verbose("perf_event programs can only use preallocated inner hash map\n");
+ return -EINVAL;
+ }
}
return 0;
}
@@ -3162,6 +3217,41 @@ static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env)
insn->src_reg = 0;
}
+/* single env->prog->insni[off] instruction was replaced with the range
+ * insni[off, off + cnt). Adjust corresponding insn_aux_data by copying
+ * [0, off) and [off, end) to new locations, so the patched range stays zero
+ */
+static int adjust_insn_aux_data(struct bpf_verifier_env *env, u32 prog_len,
+ u32 off, u32 cnt)
+{
+ struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data;
+
+ if (cnt == 1)
+ return 0;
+ new_data = vzalloc(sizeof(struct bpf_insn_aux_data) * prog_len);
+ if (!new_data)
+ return -ENOMEM;
+ memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off);
+ memcpy(new_data + off + cnt - 1, old_data + off,
+ sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1));
+ env->insn_aux_data = new_data;
+ vfree(old_data);
+ return 0;
+}
+
+static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off,
+ const struct bpf_insn *patch, u32 len)
+{
+ struct bpf_prog *new_prog;
+
+ new_prog = bpf_patch_insn_single(env->prog, off, patch, len);
+ if (!new_prog)
+ return NULL;
+ if (adjust_insn_aux_data(env, new_prog->len, off, len))
+ return NULL;
+ return new_prog;
+}
+
/* convert load instructions that access fields of 'struct __sk_buff'
* into sequence of instructions that access fields of 'struct sk_buff'
*/
@@ -3181,10 +3271,10 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
verbose("bpf verifier is misconfigured\n");
return -EINVAL;
} else if (cnt) {
- new_prog = bpf_patch_insn_single(env->prog, 0,
- insn_buf, cnt);
+ new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt);
if (!new_prog)
return -ENOMEM;
+
env->prog = new_prog;
delta += cnt - 1;
}
@@ -3209,7 +3299,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
else
continue;
- if (env->insn_aux_data[i].ptr_type != PTR_TO_CTX)
+ if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX)
continue;
cnt = ops->convert_ctx_access(type, insn, insn_buf, env->prog);
@@ -3218,8 +3308,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
return -EINVAL;
}
- new_prog = bpf_patch_insn_single(env->prog, i + delta, insn_buf,
- cnt);
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
if (!new_prog)
return -ENOMEM;
@@ -3233,6 +3322,84 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
return 0;
}
+/* fixup insn->imm field of bpf_call instructions
+ * and inline eligible helpers as explicit sequence of BPF instructions
+ *
+ * this function is called after eBPF program passed verification
+ */
+static int fixup_bpf_calls(struct bpf_verifier_env *env)
+{
+ struct bpf_prog *prog = env->prog;
+ struct bpf_insn *insn = prog->insnsi;
+ const struct bpf_func_proto *fn;
+ const int insn_cnt = prog->len;
+ struct bpf_insn insn_buf[16];
+ struct bpf_prog *new_prog;
+ struct bpf_map *map_ptr;
+ int i, cnt, delta = 0;
+
+ for (i = 0; i < insn_cnt; i++, insn++) {
+ if (insn->code != (BPF_JMP | BPF_CALL))
+ continue;
+
+ if (insn->imm == BPF_FUNC_get_route_realm)
+ prog->dst_needed = 1;
+ if (insn->imm == BPF_FUNC_get_prandom_u32)
+ bpf_user_rnd_init_once();
+ if (insn->imm == BPF_FUNC_xdp_adjust_head)
+ prog->xdp_adjust_head = 1;
+ if (insn->imm == BPF_FUNC_tail_call) {
+ /* mark bpf_tail_call as different opcode to avoid
+ * conditional branch in the interpeter for every normal
+ * call and to prevent accidental JITing by JIT compiler
+ * that doesn't support bpf_tail_call yet
+ */
+ insn->imm = 0;
+ insn->code |= BPF_X;
+ continue;
+ }
+
+ if (ebpf_jit_enabled() && insn->imm == BPF_FUNC_map_lookup_elem) {
+ map_ptr = env->insn_aux_data[i + delta].map_ptr;
+ if (map_ptr == BPF_MAP_PTR_POISON ||
+ !map_ptr->ops->map_gen_lookup)
+ goto patch_call_imm;
+
+ cnt = map_ptr->ops->map_gen_lookup(map_ptr, insn_buf);
+ if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
+ verbose("bpf verifier is misconfigured\n");
+ return -EINVAL;
+ }
+
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf,
+ cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+
+ /* keep walking new program and skip insns we just inserted */
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
+patch_call_imm:
+ fn = prog->aux->ops->get_func_proto(insn->imm);
+ /* all functions that have prototype and verifier allowed
+ * programs to call them, must be real in-kernel functions
+ */
+ if (!fn->func) {
+ verbose("kernel subsystem misconfigured func %s#%d\n",
+ func_id_name(insn->imm), insn->imm);
+ return -EFAULT;
+ }
+ insn->imm = fn->func - __bpf_call_base;
+ }
+
+ return 0;
+}
+
static void free_states(struct bpf_verifier_env *env)
{
struct bpf_verifier_state_list *sl, *sln;
@@ -3328,6 +3495,9 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
/* program is valid, convert *(u32*)(ctx + off) accesses */
ret = convert_ctx_accesses(env);
+ if (ret == 0)
+ ret = fixup_bpf_calls(env);
+
if (log_level && log_len >= log_size - 1) {
BUG_ON(log_len >= log_size);
/* verifier log exceeded user supplied buffer */
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 56eba9c..1dc22f6 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -1329,7 +1329,7 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v)
struct task_struct *task;
int count = 0;
- seq_printf(seq, "css_set %p\n", cset);
+ seq_printf(seq, "css_set %pK\n", cset);
list_for_each_entry(task, &cset->tasks, cg_list) {
if (count++ > MAX_TASKS_SHOWN_PER_CSS)
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 0125589c..4885132 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2669,7 +2669,7 @@ static bool css_visible(struct cgroup_subsys_state *css)
*
* Returns 0 on success, -errno on failure. On failure, csses which have
* been processed already aren't cleaned up. The caller is responsible for
- * cleaning up with cgroup_apply_control_disble().
+ * cleaning up with cgroup_apply_control_disable().
*/
static int cgroup_apply_control_enable(struct cgroup *cgrp)
{
diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c
index e756dae..2237201 100644
--- a/kernel/cgroup/pids.c
+++ b/kernel/cgroup/pids.c
@@ -229,7 +229,7 @@ static int pids_can_fork(struct task_struct *task)
/* Only log the first time events_limit is incremented. */
if (atomic64_inc_return(&pids->events_limit) == 1) {
pr_info("cgroup: fork rejected by pids controller in ");
- pr_cont_cgroup_path(task_cgroup(current, pids_cgrp_id));
+ pr_cont_cgroup_path(css->cgroup);
pr_cont("\n");
}
cgroup_file_notify(&pids->events_file);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index f7c0632..37b223e 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1335,26 +1335,21 @@ static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name,
struct cpuhp_step *sp;
int ret = 0;
- mutex_lock(&cpuhp_state_mutex);
-
if (state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN) {
ret = cpuhp_reserve_state(state);
if (ret < 0)
- goto out;
+ return ret;
state = ret;
}
sp = cpuhp_get_step(state);
- if (name && sp->name) {
- ret = -EBUSY;
- goto out;
- }
+ if (name && sp->name)
+ return -EBUSY;
+
sp->startup.single = startup;
sp->teardown.single = teardown;
sp->name = name;
sp->multi_instance = multi_instance;
INIT_HLIST_HEAD(&sp->list);
-out:
- mutex_unlock(&cpuhp_state_mutex);
return ret;
}
@@ -1428,6 +1423,7 @@ int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
return -EINVAL;
get_online_cpus();
+ mutex_lock(&cpuhp_state_mutex);
if (!invoke || !sp->startup.multi)
goto add_node;
@@ -1447,16 +1443,14 @@ int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
if (ret) {
if (sp->teardown.multi)
cpuhp_rollback_install(cpu, state, node);
- goto err;
+ goto unlock;
}
}
add_node:
ret = 0;
- mutex_lock(&cpuhp_state_mutex);
hlist_add_head(node, &sp->list);
+unlock:
mutex_unlock(&cpuhp_state_mutex);
-
-err:
put_online_cpus();
return ret;
}
@@ -1491,6 +1485,7 @@ int __cpuhp_setup_state(enum cpuhp_state state,
return -EINVAL;
get_online_cpus();
+ mutex_lock(&cpuhp_state_mutex);
ret = cpuhp_store_callbacks(state, name, startup, teardown,
multi_instance);
@@ -1524,6 +1519,7 @@ int __cpuhp_setup_state(enum cpuhp_state state,
}
}
out:
+ mutex_unlock(&cpuhp_state_mutex);
put_online_cpus();
/*
* If the requested state is CPUHP_AP_ONLINE_DYN, return the
@@ -1547,6 +1543,8 @@ int __cpuhp_state_remove_instance(enum cpuhp_state state,
return -EINVAL;
get_online_cpus();
+ mutex_lock(&cpuhp_state_mutex);
+
if (!invoke || !cpuhp_get_teardown_cb(state))
goto remove;
/*
@@ -1563,7 +1561,6 @@ int __cpuhp_state_remove_instance(enum cpuhp_state state,
}
remove:
- mutex_lock(&cpuhp_state_mutex);
hlist_del(node);
mutex_unlock(&cpuhp_state_mutex);
put_online_cpus();
@@ -1571,6 +1568,7 @@ int __cpuhp_state_remove_instance(enum cpuhp_state state,
return 0;
}
EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance);
+
/**
* __cpuhp_remove_state - Remove the callbacks for an hotplug machine state
* @state: The state to remove
@@ -1589,6 +1587,7 @@ void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
get_online_cpus();
+ mutex_lock(&cpuhp_state_mutex);
if (sp->multi_instance) {
WARN(!hlist_empty(&sp->list),
"Error: Removing state %d which has instances left.\n",
@@ -1613,6 +1612,7 @@ void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
}
remove:
cpuhp_store_callbacks(state, NULL, NULL, NULL, false);
+ mutex_unlock(&cpuhp_state_mutex);
put_online_cpus();
}
EXPORT_SYMBOL(__cpuhp_remove_state);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6f41548f..ff01cba 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -998,7 +998,7 @@ list_update_cgroup_event(struct perf_event *event,
*/
#define PERF_CPU_HRTIMER (1000 / HZ)
/*
- * function must be called with interrupts disbled
+ * function must be called with interrupts disabled
*/
static enum hrtimer_restart perf_mux_hrtimer_handler(struct hrtimer *hr)
{
@@ -4256,7 +4256,7 @@ int perf_event_release_kernel(struct perf_event *event)
raw_spin_lock_irq(&ctx->lock);
/*
- * Mark this even as STATE_DEAD, there is no external reference to it
+ * Mark this event as STATE_DEAD, there is no external reference to it
* anymore.
*
* Anybody acquiring event->child_mutex after the below loop _must_
@@ -10417,21 +10417,22 @@ void perf_event_free_task(struct task_struct *task)
continue;
mutex_lock(&ctx->mutex);
-again:
- list_for_each_entry_safe(event, tmp, &ctx->pinned_groups,
- group_entry)
- perf_free_event(event, ctx);
+ raw_spin_lock_irq(&ctx->lock);
+ /*
+ * Destroy the task <-> ctx relation and mark the context dead.
+ *
+ * This is important because even though the task hasn't been
+ * exposed yet the context has been (through child_list).
+ */
+ RCU_INIT_POINTER(task->perf_event_ctxp[ctxn], NULL);
+ WRITE_ONCE(ctx->task, TASK_TOMBSTONE);
+ put_task_struct(task); /* cannot be last */
+ raw_spin_unlock_irq(&ctx->lock);
- list_for_each_entry_safe(event, tmp, &ctx->flexible_groups,
- group_entry)
+ list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry)
perf_free_event(event, ctx);
- if (!list_empty(&ctx->pinned_groups) ||
- !list_empty(&ctx->flexible_groups))
- goto again;
-
mutex_unlock(&ctx->mutex);
-
put_ctx(ctx);
}
}
@@ -10469,7 +10470,12 @@ const struct perf_event_attr *perf_event_attrs(struct perf_event *event)
}
/*
- * inherit a event from parent task to child task:
+ * Inherit a event from parent task to child task.
+ *
+ * Returns:
+ * - valid pointer on success
+ * - NULL for orphaned events
+ * - IS_ERR() on error
*/
static struct perf_event *
inherit_event(struct perf_event *parent_event,
@@ -10563,6 +10569,16 @@ inherit_event(struct perf_event *parent_event,
return child_event;
}
+/*
+ * Inherits an event group.
+ *
+ * This will quietly suppress orphaned events; !inherit_event() is not an error.
+ * This matches with perf_event_release_kernel() removing all child events.
+ *
+ * Returns:
+ * - 0 on success
+ * - <0 on error
+ */
static int inherit_group(struct perf_event *parent_event,
struct task_struct *parent,
struct perf_event_context *parent_ctx,
@@ -10577,6 +10593,11 @@ static int inherit_group(struct perf_event *parent_event,
child, NULL, child_ctx);
if (IS_ERR(leader))
return PTR_ERR(leader);
+ /*
+ * @leader can be NULL here because of is_orphaned_event(). In this
+ * case inherit_event() will create individual events, similar to what
+ * perf_group_detach() would do anyway.
+ */
list_for_each_entry(sub, &parent_event->sibling_list, group_entry) {
child_ctr = inherit_event(sub, parent, parent_ctx,
child, leader, child_ctx);
@@ -10586,6 +10607,17 @@ static int inherit_group(struct perf_event *parent_event,
return 0;
}
+/*
+ * Creates the child task context and tries to inherit the event-group.
+ *
+ * Clears @inherited_all on !attr.inherited or error. Note that we'll leave
+ * inherited_all set when we 'fail' to inherit an orphaned event; this is
+ * consistent with perf_event_release_kernel() removing all child events.
+ *
+ * Returns:
+ * - 0 on success
+ * - <0 on error
+ */
static int
inherit_task_group(struct perf_event *event, struct task_struct *parent,
struct perf_event_context *parent_ctx,
@@ -10608,7 +10640,6 @@ inherit_task_group(struct perf_event *event, struct task_struct *parent,
* First allocate and initialize a context for the
* child.
*/
-
child_ctx = alloc_perf_context(parent_ctx->pmu, child);
if (!child_ctx)
return -ENOMEM;
@@ -10670,7 +10701,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
ret = inherit_task_group(event, parent, parent_ctx,
child, ctxn, &inherited_all);
if (ret)
- break;
+ goto out_unlock;
}
/*
@@ -10686,7 +10717,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
ret = inherit_task_group(event, parent, parent_ctx,
child, ctxn, &inherited_all);
if (ret)
- break;
+ goto out_unlock;
}
raw_spin_lock_irqsave(&parent_ctx->lock, flags);
@@ -10714,6 +10745,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
}
raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
+out_unlock:
mutex_unlock(&parent_ctx->mutex);
perf_unpin_context(parent_ctx);
diff --git a/kernel/exit.c b/kernel/exit.c
index e126ebf..516acdb 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -554,7 +554,6 @@ static void exit_mm(void)
enter_lazy_tlb(mm, current);
task_unlock(current);
mm_update_next_owner(mm);
- userfaultfd_exit(mm);
mmput(mm);
if (test_thread_flag(TIF_MEMDIE))
exit_oom_victim();
diff --git a/kernel/futex.c b/kernel/futex.c
index 229a744..45858ec 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2815,7 +2815,6 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
{
struct hrtimer_sleeper timeout, *to = NULL;
struct rt_mutex_waiter rt_waiter;
- struct rt_mutex *pi_mutex = NULL;
struct futex_hash_bucket *hb;
union futex_key key2 = FUTEX_KEY_INIT;
struct futex_q q = futex_q_init;
@@ -2899,6 +2898,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
if (q.pi_state && (q.pi_state->owner != current)) {
spin_lock(q.lock_ptr);
ret = fixup_pi_state_owner(uaddr2, &q, current);
+ if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current)
+ rt_mutex_unlock(&q.pi_state->pi_mutex);
/*
* Drop the reference to the pi state which
* the requeue_pi() code acquired for us.
@@ -2907,6 +2908,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
spin_unlock(q.lock_ptr);
}
} else {
+ struct rt_mutex *pi_mutex;
+
/*
* We have been woken up by futex_unlock_pi(), a timeout, or a
* signal. futex_unlock_pi() will not destroy the lock_ptr nor
@@ -2930,18 +2933,19 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
if (res)
ret = (res < 0) ? res : 0;
+ /*
+ * If fixup_pi_state_owner() faulted and was unable to handle
+ * the fault, unlock the rt_mutex and return the fault to
+ * userspace.
+ */
+ if (ret && rt_mutex_owner(pi_mutex) == current)
+ rt_mutex_unlock(pi_mutex);
+
/* Unqueue and drop the lock. */
unqueue_me_pi(&q);
}
- /*
- * If fixup_pi_state_owner() faulted and was unable to handle the
- * fault, unlock the rt_mutex and return the fault to userspace.
- */
- if (ret == -EFAULT) {
- if (pi_mutex && rt_mutex_owner(pi_mutex) == current)
- rt_mutex_unlock(pi_mutex);
- } else if (ret == -EINTR) {
+ if (ret == -EINTR) {
/*
* We've already been requeued, but cannot restart by calling
* futex_lock_pi() directly. We could restart this syscall, but
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index b56a558..b118735 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -614,13 +614,13 @@ static int kexec_calculate_store_digests(struct kimage *image)
ret = crypto_shash_final(desc, digest);
if (ret)
goto out_free_digest;
- ret = kexec_purgatory_get_set_symbol(image, "sha_regions",
- sha_regions, sha_region_sz, 0);
+ ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha_regions",
+ sha_regions, sha_region_sz, 0);
if (ret)
goto out_free_digest;
- ret = kexec_purgatory_get_set_symbol(image, "sha256_digest",
- digest, SHA256_DIGEST_SIZE, 0);
+ ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha256_digest",
+ digest, SHA256_DIGEST_SIZE, 0);
if (ret)
goto out_free_digest;
}
diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h
index 4cef7e4..799a8a452 100644
--- a/kernel/kexec_internal.h
+++ b/kernel/kexec_internal.h
@@ -15,11 +15,7 @@ int kimage_is_destination_range(struct kimage *image,
extern struct mutex kexec_mutex;
#ifdef CONFIG_KEXEC_FILE
-struct kexec_sha_region {
- unsigned long start;
- unsigned long len;
-};
-
+#include <linux/purgatory.h>
void kimage_file_post_load_cleanup(struct kimage *image);
#else /* CONFIG_KEXEC_FILE */
static inline void kimage_file_post_load_cleanup(struct kimage *image) { }
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 12e38c2..a95e5d1 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3262,10 +3262,17 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
if (depth) {
hlock = curr->held_locks + depth - 1;
if (hlock->class_idx == class_idx && nest_lock) {
- if (hlock->references)
+ if (hlock->references) {
+ /*
+ * Check: unsigned int references:12, overflow.
+ */
+ if (DEBUG_LOCKS_WARN_ON(hlock->references == (1 << 12)-1))
+ return 0;
+
hlock->references++;
- else
+ } else {
hlock->references = 2;
+ }
return 1;
}
diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c
index 7bc24d4..c65f798 100644
--- a/kernel/locking/rwsem-spinlock.c
+++ b/kernel/locking/rwsem-spinlock.c
@@ -213,10 +213,9 @@ int __sched __down_write_common(struct rw_semaphore *sem, int state)
*/
if (sem->count == 0)
break;
- if (signal_pending_state(state, current)) {
- ret = -EINTR;
- goto out;
- }
+ if (signal_pending_state(state, current))
+ goto out_nolock;
+
set_current_state(state);
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
schedule();
@@ -224,12 +223,19 @@ int __sched __down_write_common(struct rw_semaphore *sem, int state)
}
/* got the lock */
sem->count = -1;
-out:
list_del(&waiter.list);
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
return ret;
+
+out_nolock:
+ list_del(&waiter.list);
+ if (!list_empty(&sem->wait_list))
+ __rwsem_do_wake(sem, 1);
+ raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+ return -EINTR;
}
void __sched __down_write(struct rw_semaphore *sem)
diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c
index da6c9a3..6b7abb3 100644
--- a/kernel/locking/test-ww_mutex.c
+++ b/kernel/locking/test-ww_mutex.c
@@ -50,7 +50,7 @@ static void test_mutex_work(struct work_struct *work)
if (mtx->flags & TEST_MTX_TRY) {
while (!ww_mutex_trylock(&mtx->mutex))
- cpu_relax();
+ cond_resched();
} else {
ww_mutex_lock(&mtx->mutex, NULL);
}
@@ -88,7 +88,7 @@ static int __test_mutex(unsigned int flags)
ret = -EINVAL;
break;
}
- cpu_relax();
+ cond_resched();
} while (time_before(jiffies, timeout));
} else {
ret = wait_for_completion_timeout(&mtx.done, TIMEOUT);
@@ -627,7 +627,7 @@ static int __init test_ww_mutex_init(void)
if (ret)
return ret;
- ret = stress(4096, hweight32(STRESS_ALL)*ncpus, 1<<12, STRESS_ALL);
+ ret = stress(4095, hweight32(STRESS_ALL)*ncpus, 1<<12, STRESS_ALL);
if (ret)
return ret;
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 0612323..07e85e5 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -247,11 +247,9 @@ static void devm_memremap_pages_release(struct device *dev, void *data)
align_start = res->start & ~(SECTION_SIZE - 1);
align_size = ALIGN(resource_size(res), SECTION_SIZE);
- lock_device_hotplug();
mem_hotplug_begin();
arch_remove_memory(align_start, align_size);
mem_hotplug_done();
- unlock_device_hotplug();
untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
pgmap_radix_release(res);
@@ -364,11 +362,9 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
if (error)
goto err_pfn_remap;
- lock_device_hotplug();
mem_hotplug_begin();
error = arch_add_memory(nid, align_start, align_size, true);
mem_hotplug_done();
- unlock_device_hotplug();
if (error)
goto err_add_memory;
diff --git a/kernel/padata.c b/kernel/padata.c
index 05316c9..3202aa1 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -186,19 +186,20 @@ static struct padata_priv *padata_get_next(struct parallel_data *pd)
reorder = &next_queue->reorder;
+ spin_lock(&reorder->lock);
if (!list_empty(&reorder->list)) {
padata = list_entry(reorder->list.next,
struct padata_priv, list);
- spin_lock(&reorder->lock);
list_del_init(&padata->list);
atomic_dec(&pd->reorder_objects);
- spin_unlock(&reorder->lock);
pd->processed++;
+ spin_unlock(&reorder->lock);
goto out;
}
+ spin_unlock(&reorder->lock);
if (__this_cpu_read(pd->pqueue->cpu_index) == next_queue->cpu_index) {
padata = ERR_PTR(-ENODATA);
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index a08795e..00a45c4 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -96,10 +96,10 @@ static DEFINE_STATIC_KEY_FALSE(__sched_clock_stable);
static int __sched_clock_stable_early = 1;
/*
- * We want: ktime_get_ns() + gtod_offset == sched_clock() + raw_offset
+ * We want: ktime_get_ns() + __gtod_offset == sched_clock() + __sched_clock_offset
*/
-static __read_mostly u64 raw_offset;
-static __read_mostly u64 gtod_offset;
+__read_mostly u64 __sched_clock_offset;
+static __read_mostly u64 __gtod_offset;
struct sched_clock_data {
u64 tick_raw;
@@ -131,17 +131,24 @@ static void __set_sched_clock_stable(void)
/*
* Attempt to make the (initial) unstable->stable transition continuous.
*/
- raw_offset = (scd->tick_gtod + gtod_offset) - (scd->tick_raw);
+ __sched_clock_offset = (scd->tick_gtod + __gtod_offset) - (scd->tick_raw);
printk(KERN_INFO "sched_clock: Marking stable (%lld, %lld)->(%lld, %lld)\n",
- scd->tick_gtod, gtod_offset,
- scd->tick_raw, raw_offset);
+ scd->tick_gtod, __gtod_offset,
+ scd->tick_raw, __sched_clock_offset);
static_branch_enable(&__sched_clock_stable);
tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE);
}
-static void __clear_sched_clock_stable(struct work_struct *work)
+static void __sched_clock_work(struct work_struct *work)
+{
+ static_branch_disable(&__sched_clock_stable);
+}
+
+static DECLARE_WORK(sched_clock_work, __sched_clock_work);
+
+static void __clear_sched_clock_stable(void)
{
struct sched_clock_data *scd = this_scd();
@@ -154,17 +161,17 @@ static void __clear_sched_clock_stable(struct work_struct *work)
*
* Still do what we can.
*/
- gtod_offset = (scd->tick_raw + raw_offset) - (scd->tick_gtod);
+ __gtod_offset = (scd->tick_raw + __sched_clock_offset) - (scd->tick_gtod);
printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n",
- scd->tick_gtod, gtod_offset,
- scd->tick_raw, raw_offset);
+ scd->tick_gtod, __gtod_offset,
+ scd->tick_raw, __sched_clock_offset);
- static_branch_disable(&__sched_clock_stable);
tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE);
-}
-static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable);
+ if (sched_clock_stable())
+ schedule_work(&sched_clock_work);
+}
void clear_sched_clock_stable(void)
{
@@ -173,7 +180,7 @@ void clear_sched_clock_stable(void)
smp_mb(); /* matches sched_clock_init_late() */
if (sched_clock_running == 2)
- schedule_work(&sched_clock_work);
+ __clear_sched_clock_stable();
}
void sched_clock_init_late(void)
@@ -214,7 +221,7 @@ static inline u64 wrap_max(u64 x, u64 y)
*/
static u64 sched_clock_local(struct sched_clock_data *scd)
{
- u64 now, clock, old_clock, min_clock, max_clock;
+ u64 now, clock, old_clock, min_clock, max_clock, gtod;
s64 delta;
again:
@@ -231,9 +238,10 @@ static u64 sched_clock_local(struct sched_clock_data *scd)
* scd->tick_gtod + TICK_NSEC);
*/
- clock = scd->tick_gtod + gtod_offset + delta;
- min_clock = wrap_max(scd->tick_gtod, old_clock);
- max_clock = wrap_max(old_clock, scd->tick_gtod + TICK_NSEC);
+ gtod = scd->tick_gtod + __gtod_offset;
+ clock = gtod + delta;
+ min_clock = wrap_max(gtod, old_clock);
+ max_clock = wrap_max(old_clock, gtod + TICK_NSEC);
clock = wrap_max(clock, min_clock);
clock = wrap_min(clock, max_clock);
@@ -317,7 +325,7 @@ u64 sched_clock_cpu(int cpu)
u64 clock;
if (sched_clock_stable())
- return sched_clock() + raw_offset;
+ return sched_clock() + __sched_clock_offset;
if (unlikely(!sched_clock_running))
return 0ull;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9563838..3b31fc0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3287,10 +3287,15 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
struct task_struct *p;
/*
- * Optimization: we know that if all tasks are in
- * the fair class we can call that function directly:
+ * Optimization: we know that if all tasks are in the fair class we can
+ * call that function directly, but only if the @prev task wasn't of a
+ * higher scheduling class, because otherwise those loose the
+ * opportunity to pull in more work from other CPUs.
*/
- if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
+ if (likely((prev->sched_class == &idle_sched_class ||
+ prev->sched_class == &fair_sched_class) &&
+ rq->nr_running == rq->cfs.h_nr_running)) {
+
p = fair_sched_class.pick_next_task(rq, prev, rf);
if (unlikely(p == RETRY_TASK))
goto again;
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 8f8de3d..54c5775 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -36,6 +36,7 @@ struct sugov_policy {
u64 last_freq_update_time;
s64 freq_update_delay_ns;
unsigned int next_freq;
+ unsigned int cached_raw_freq;
/* The next fields are only needed if fast switch cannot be used. */
struct irq_work irq_work;
@@ -52,7 +53,6 @@ struct sugov_cpu {
struct update_util_data update_util;
struct sugov_policy *sg_policy;
- unsigned int cached_raw_freq;
unsigned long iowait_boost;
unsigned long iowait_boost_max;
u64 last_update;
@@ -116,7 +116,7 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
/**
* get_next_freq - Compute a new frequency for a given cpufreq policy.
- * @sg_cpu: schedutil cpu object to compute the new frequency for.
+ * @sg_policy: schedutil policy object to compute the new frequency for.
* @util: Current CPU utilization.
* @max: CPU capacity.
*
@@ -136,19 +136,18 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
* next_freq (as calculated above) is returned, subject to policy min/max and
* cpufreq driver limitations.
*/
-static unsigned int get_next_freq(struct sugov_cpu *sg_cpu, unsigned long util,
- unsigned long max)
+static unsigned int get_next_freq(struct sugov_policy *sg_policy,
+ unsigned long util, unsigned long max)
{
- struct sugov_policy *sg_policy = sg_cpu->sg_policy;
struct cpufreq_policy *policy = sg_policy->policy;
unsigned int freq = arch_scale_freq_invariant() ?
policy->cpuinfo.max_freq : policy->cur;
freq = (freq + (freq >> 2)) * util / max;
- if (freq == sg_cpu->cached_raw_freq && sg_policy->next_freq != UINT_MAX)
+ if (freq == sg_policy->cached_raw_freq && sg_policy->next_freq != UINT_MAX)
return sg_policy->next_freq;
- sg_cpu->cached_raw_freq = freq;
+ sg_policy->cached_raw_freq = freq;
return cpufreq_driver_resolve_freq(policy, freq);
}
@@ -213,7 +212,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
} else {
sugov_get_util(&util, &max);
sugov_iowait_boost(sg_cpu, &util, &max);
- next_f = get_next_freq(sg_cpu, util, max);
+ next_f = get_next_freq(sg_policy, util, max);
}
sugov_update_commit(sg_policy, time, next_f);
}
@@ -267,7 +266,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
sugov_iowait_boost(j_sg_cpu, &util, &max);
}
- return get_next_freq(sg_cpu, util, max);
+ return get_next_freq(sg_policy, util, max);
}
static void sugov_update_shared(struct update_util_data *hook, u64 time,
@@ -580,25 +579,19 @@ static int sugov_start(struct cpufreq_policy *policy)
sg_policy->next_freq = UINT_MAX;
sg_policy->work_in_progress = false;
sg_policy->need_freq_update = false;
+ sg_policy->cached_raw_freq = 0;
for_each_cpu(cpu, policy->cpus) {
struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);
+ memset(sg_cpu, 0, sizeof(*sg_cpu));
sg_cpu->sg_policy = sg_policy;
- if (policy_is_shared(policy)) {
- sg_cpu->util = 0;
- sg_cpu->max = 0;
- sg_cpu->flags = SCHED_CPUFREQ_RT;
- sg_cpu->last_update = 0;
- sg_cpu->cached_raw_freq = 0;
- sg_cpu->iowait_boost = 0;
- sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq;
- cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
- sugov_update_shared);
- } else {
- cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
- sugov_update_single);
- }
+ sg_cpu->flags = SCHED_CPUFREQ_RT;
+ sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq;
+ cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
+ policy_is_shared(policy) ?
+ sugov_update_shared :
+ sugov_update_single);
}
return 0;
}
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 99b2c33..a2ce590 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -445,13 +445,13 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
*
* This function returns true if:
*
- * runtime / (deadline - t) > dl_runtime / dl_period ,
+ * runtime / (deadline - t) > dl_runtime / dl_deadline ,
*
* IOW we can't recycle current parameters.
*
- * Notice that the bandwidth check is done against the period. For
+ * Notice that the bandwidth check is done against the deadline. For
* task with deadline equal to period this is the same of using
- * dl_deadline instead of dl_period in the equation above.
+ * dl_period instead of dl_deadline in the equation above.
*/
static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
struct sched_dl_entity *pi_se, u64 t)
@@ -476,7 +476,7 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
* of anything below microseconds resolution is actually fiction
* (but still we want to give the user that illusion >;).
*/
- left = (pi_se->dl_period >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
+ left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
right = ((dl_se->deadline - t) >> DL_SCALE) *
(pi_se->dl_runtime >> DL_SCALE);
@@ -505,10 +505,15 @@ static void update_dl_entity(struct sched_dl_entity *dl_se,
}
}
+static inline u64 dl_next_period(struct sched_dl_entity *dl_se)
+{
+ return dl_se->deadline - dl_se->dl_deadline + dl_se->dl_period;
+}
+
/*
* If the entity depleted all its runtime, and if we want it to sleep
* while waiting for some new execution time to become available, we
- * set the bandwidth enforcement timer to the replenishment instant
+ * set the bandwidth replenishment timer to the replenishment instant
* and try to activate it.
*
* Notice that it is important for the caller to know if the timer
@@ -530,7 +535,7 @@ static int start_dl_timer(struct task_struct *p)
* that it is actually coming from rq->clock and not from
* hrtimer's time base reading.
*/
- act = ns_to_ktime(dl_se->deadline);
+ act = ns_to_ktime(dl_next_period(dl_se));
now = hrtimer_cb_get_time(timer);
delta = ktime_to_ns(now) - rq_clock(rq);
act = ktime_add_ns(act, delta);
@@ -638,6 +643,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
lockdep_unpin_lock(&rq->lock, rf.cookie);
rq = dl_task_offline_migration(rq, p);
rf.cookie = lockdep_pin_lock(&rq->lock);
+ update_rq_clock(rq);
/*
* Now that the task has been migrated to the new RQ and we
@@ -689,6 +695,37 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
timer->function = dl_task_timer;
}
+/*
+ * During the activation, CBS checks if it can reuse the current task's
+ * runtime and period. If the deadline of the task is in the past, CBS
+ * cannot use the runtime, and so it replenishes the task. This rule
+ * works fine for implicit deadline tasks (deadline == period), and the
+ * CBS was designed for implicit deadline tasks. However, a task with
+ * constrained deadline (deadine < period) might be awakened after the
+ * deadline, but before the next period. In this case, replenishing the
+ * task would allow it to run for runtime / deadline. As in this case
+ * deadline < period, CBS enables a task to run for more than the
+ * runtime / period. In a very loaded system, this can cause a domino
+ * effect, making other tasks miss their deadlines.
+ *
+ * To avoid this problem, in the activation of a constrained deadline
+ * task after the deadline but before the next period, throttle the
+ * task and set the replenishing timer to the begin of the next period,
+ * unless it is boosted.
+ */
+static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se)
+{
+ struct task_struct *p = dl_task_of(dl_se);
+ struct rq *rq = rq_of_dl_rq(dl_rq_of_se(dl_se));
+
+ if (dl_time_before(dl_se->deadline, rq_clock(rq)) &&
+ dl_time_before(rq_clock(rq), dl_next_period(dl_se))) {
+ if (unlikely(dl_se->dl_boosted || !start_dl_timer(p)))
+ return;
+ dl_se->dl_throttled = 1;
+ }
+}
+
static
int dl_runtime_exceeded(struct sched_dl_entity *dl_se)
{
@@ -922,6 +959,11 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
__dequeue_dl_entity(dl_se);
}
+static inline bool dl_is_constrained(struct sched_dl_entity *dl_se)
+{
+ return dl_se->dl_deadline < dl_se->dl_period;
+}
+
static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
{
struct task_struct *pi_task = rt_mutex_get_top_task(p);
@@ -948,6 +990,15 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
}
/*
+ * Check if a constrained deadline task was activated
+ * after the deadline but before the next period.
+ * If that is the case, the task will be throttled and
+ * the replenishment timer will be set to the next period.
+ */
+ if (!p->dl.dl_throttled && dl_is_constrained(&p->dl))
+ dl_check_constrained_dl(&p->dl);
+
+ /*
* If p is throttled, we do nothing. In fact, if it exhausted
* its budget it needs a replenishment and, since it now is on
* its rq, the bandwidth timer callback (which clearly has not
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 3e88b35..dea1389 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5799,7 +5799,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
* Due to large variance we need a large fuzz factor; hackbench in
* particularly is sensitive here.
*/
- if ((avg_idle / 512) < avg_cost)
+ if (sched_feat(SIS_AVG_CPU) && (avg_idle / 512) < avg_cost)
return -1;
time = local_clock();
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 69631fa..1b3c818 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -51,6 +51,11 @@ SCHED_FEAT(NONTASK_CAPACITY, true)
*/
SCHED_FEAT(TTWU_QUEUE, true)
+/*
+ * When doing wakeups, attempt to limit superfluous scans of the LLC domain.
+ */
+SCHED_FEAT(SIS_AVG_CPU, false)
+
#ifdef HAVE_RT_PUSH_IPI
/*
* In order to avoid a thundering herd attack of CPUs that are
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index 7296b73..f15fb2b 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -169,7 +169,7 @@ static inline int calc_load_write_idx(void)
* If the folding window started, make sure we start writing in the
* next idle-delta.
*/
- if (!time_before(jiffies, calc_load_update))
+ if (!time_before(jiffies, READ_ONCE(calc_load_update)))
idx++;
return idx & 1;
@@ -202,8 +202,9 @@ void calc_load_exit_idle(void)
struct rq *this_rq = this_rq();
/*
- * If we're still before the sample window, we're done.
+ * If we're still before the pending sample window, we're done.
*/
+ this_rq->calc_load_update = READ_ONCE(calc_load_update);
if (time_before(jiffies, this_rq->calc_load_update))
return;
@@ -212,7 +213,6 @@ void calc_load_exit_idle(void)
* accounted through the nohz accounting, so skip the entire deal and
* sync up for the next window.
*/
- this_rq->calc_load_update = calc_load_update;
if (time_before(jiffies, this_rq->calc_load_update + 10))
this_rq->calc_load_update += LOAD_FREQ;
}
@@ -308,13 +308,15 @@ calc_load_n(unsigned long load, unsigned long exp,
*/
static void calc_global_nohz(void)
{
+ unsigned long sample_window;
long delta, active, n;
- if (!time_before(jiffies, calc_load_update + 10)) {
+ sample_window = READ_ONCE(calc_load_update);
+ if (!time_before(jiffies, sample_window + 10)) {
/*
* Catch-up, fold however many we are behind still
*/
- delta = jiffies - calc_load_update - 10;
+ delta = jiffies - sample_window - 10;
n = 1 + (delta / LOAD_FREQ);
active = atomic_long_read(&calc_load_tasks);
@@ -324,7 +326,7 @@ static void calc_global_nohz(void)
avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
- calc_load_update += n * LOAD_FREQ;
+ WRITE_ONCE(calc_load_update, sample_window + n * LOAD_FREQ);
}
/*
@@ -352,9 +354,11 @@ static inline void calc_global_nohz(void) { }
*/
void calc_global_load(unsigned long ticks)
{
+ unsigned long sample_window;
long active, delta;
- if (time_before(jiffies, calc_load_update + 10))
+ sample_window = READ_ONCE(calc_load_update);
+ if (time_before(jiffies, sample_window + 10))
return;
/*
@@ -371,7 +375,7 @@ void calc_global_load(unsigned long ticks)
avenrun[1] = calc_load(avenrun[1], EXP_5, active);
avenrun[2] = calc_load(avenrun[2], EXP_15, active);
- calc_load_update += LOAD_FREQ;
+ WRITE_ONCE(calc_load_update, sample_window + LOAD_FREQ);
/*
* In case we idled for multiple LOAD_FREQ intervals, catch up in bulk.
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 4d2ea6f..b8c84c6 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -242,6 +242,45 @@ long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state)
}
EXPORT_SYMBOL(prepare_to_wait_event);
+/*
+ * Note! These two wait functions are entered with the
+ * wait-queue lock held (and interrupts off in the _irq
+ * case), so there is no race with testing the wakeup
+ * condition in the caller before they add the wait
+ * entry to the wake queue.
+ */
+int do_wait_intr(wait_queue_head_t *wq, wait_queue_t *wait)
+{
+ if (likely(list_empty(&wait->task_list)))
+ __add_wait_queue_tail(wq, wait);
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (signal_pending(current))
+ return -ERESTARTSYS;
+
+ spin_unlock(&wq->lock);
+ schedule();
+ spin_lock(&wq->lock);
+ return 0;
+}
+EXPORT_SYMBOL(do_wait_intr);
+
+int do_wait_intr_irq(wait_queue_head_t *wq, wait_queue_t *wait)
+{
+ if (likely(list_empty(&wait->task_list)))
+ __add_wait_queue_tail(wq, wait);
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (signal_pending(current))
+ return -ERESTARTSYS;
+
+ spin_unlock_irq(&wq->lock);
+ schedule();
+ spin_lock_irq(&wq->lock);
+ return 0;
+}
+EXPORT_SYMBOL(do_wait_intr_irq);
+
/**
* finish_wait - clean up after waiting in a queue
* @q: waitqueue waited on
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 7906b3f..4977191 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -125,7 +125,7 @@ int register_refined_jiffies(long cycles_per_second)
shift_hz += cycles_per_tick/2;
do_div(shift_hz, cycles_per_tick);
/* Calculate nsec_per_tick using shift_hz */
- nsec_per_tick = (u64)TICK_NSEC << 8;
+ nsec_per_tick = (u64)NSEC_PER_SEC << 8;
nsec_per_tick += (u32)shift_hz/2;
do_div(nsec_per_tick, (u32)shift_hz);
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index d503800..d4a06e7 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -429,7 +429,7 @@
If unsure, say N.
-config KPROBE_EVENT
+config KPROBE_EVENTS
depends on KPROBES
depends on HAVE_REGS_AND_STACK_ACCESS_API
bool "Enable kprobes-based dynamic events"
@@ -447,7 +447,7 @@
This option is also required by perf-probe subcommand of perf tools.
If you want to use perf tools, this option is strongly recommended.
-config UPROBE_EVENT
+config UPROBE_EVENTS
bool "Enable uprobes-based dynamic events"
depends on ARCH_SUPPORTS_UPROBES
depends on MMU
@@ -466,7 +466,7 @@
config BPF_EVENTS
depends on BPF_SYSCALL
- depends on (KPROBE_EVENT || UPROBE_EVENT) && PERF_EVENTS
+ depends on (KPROBE_EVENTS || UPROBE_EVENTS) && PERF_EVENTS
bool
default y
help
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index e579808..90f2701 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -57,7 +57,7 @@
obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o
obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o
obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o
-obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
+obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o
obj-$(CONFIG_TRACEPOINTS) += power-traces.o
ifeq ($(CONFIG_PM),y)
obj-$(CONFIG_TRACEPOINTS) += rpm-traces.o
@@ -66,7 +66,7 @@
obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
endif
obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
-obj-$(CONFIG_UPROBE_EVENT) += trace_uprobe.o
+obj-$(CONFIG_UPROBE_EVENTS) += trace_uprobe.o
obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 0d1597c..b9691ee 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -4416,16 +4416,24 @@ static int __init set_graph_notrace_function(char *str)
}
__setup("ftrace_graph_notrace=", set_graph_notrace_function);
+static int __init set_graph_max_depth_function(char *str)
+{
+ if (!str)
+ return 0;
+ fgraph_max_depth = simple_strtoul(str, NULL, 0);
+ return 1;
+}
+__setup("ftrace_graph_max_depth=", set_graph_max_depth_function);
+
static void __init set_ftrace_early_graph(char *buf, int enable)
{
int ret;
char *func;
struct ftrace_hash *hash;
- if (enable)
- hash = ftrace_graph_hash;
- else
- hash = ftrace_graph_notrace_hash;
+ hash = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS);
+ if (WARN_ON(!hash))
+ return;
while (buf) {
func = strsep(&buf, ",");
@@ -4435,6 +4443,11 @@ static void __init set_ftrace_early_graph(char *buf, int enable)
printk(KERN_DEBUG "ftrace: function %s not "
"traceable\n", func);
}
+
+ if (enable)
+ ftrace_graph_hash = hash;
+ else
+ ftrace_graph_notrace_hash = hash;
}
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
@@ -5488,7 +5501,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
* Normally the mcount trampoline will call the ops->func, but there
* are times that it should not. For example, if the ops does not
* have its own recursion protection, then it should call the
- * ftrace_ops_recurs_func() instead.
+ * ftrace_ops_assist_func() instead.
*
* Returns the function that the trampoline should call for @ops.
*/
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 707445c..f351095 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4341,22 +4341,22 @@ static const char readme_msg[] =
"\t\t\t traces\n"
#endif
#endif /* CONFIG_STACK_TRACER */
-#ifdef CONFIG_KPROBE_EVENT
+#ifdef CONFIG_KPROBE_EVENTS
" kprobe_events\t\t- Add/remove/show the kernel dynamic events\n"
"\t\t\t Write into this file to define/undefine new trace events.\n"
#endif
-#ifdef CONFIG_UPROBE_EVENT
+#ifdef CONFIG_UPROBE_EVENTS
" uprobe_events\t\t- Add/remove/show the userspace dynamic events\n"
"\t\t\t Write into this file to define/undefine new trace events.\n"
#endif
-#if defined(CONFIG_KPROBE_EVENT) || defined(CONFIG_UPROBE_EVENT)
+#if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS)
"\t accepts: event-definitions (one definition per line)\n"
"\t Format: p|r[:[<group>/]<event>] <place> [<args>]\n"
"\t -:[<group>/]<event>\n"
-#ifdef CONFIG_KPROBE_EVENT
+#ifdef CONFIG_KPROBE_EVENTS
"\t place: [<module>:]<symbol>[+<offset>]|<memaddr>\n"
#endif
-#ifdef CONFIG_UPROBE_EVENT
+#ifdef CONFIG_UPROBE_EVENTS
"\t place: <path>:<offset>\n"
#endif
"\t args: <name>=fetcharg[:type]\n"
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 0c0ae54..903273c 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -248,7 +248,7 @@ ASSIGN_FETCH_FUNC(file_offset, ftype), \
#define FETCH_TYPE_STRING 0
#define FETCH_TYPE_STRSIZE 1
-#ifdef CONFIG_KPROBE_EVENT
+#ifdef CONFIG_KPROBE_EVENTS
struct symbol_cache;
unsigned long update_symbol_cache(struct symbol_cache *sc);
void free_symbol_cache(struct symbol_cache *sc);
@@ -278,7 +278,7 @@ alloc_symbol_cache(const char *sym, long offset)
{
return NULL;
}
-#endif /* CONFIG_KPROBE_EVENT */
+#endif /* CONFIG_KPROBE_EVENTS */
struct probe_arg {
struct fetch_param fetch;
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 1d68b5b..5fb1f2c 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -65,7 +65,7 @@ void stack_trace_print(void)
}
/*
- * When arch-specific code overides this function, the following
+ * When arch-specific code overrides this function, the following
* data should be filled up, assuming stack_trace_max_lock is held to
* prevent concurrent updates.
* stack_trace_index[]
diff --git a/kernel/ucount.c b/kernel/ucount.c
index 62630a4..b4eeee0 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -144,7 +144,7 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
new->ns = ns;
new->uid = uid;
- atomic_set(&new->count, 0);
+ new->count = 0;
spin_lock_irq(&ucounts_lock);
ucounts = find_ucounts(ns, uid, hashent);
@@ -155,8 +155,10 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
ucounts = new;
}
}
- if (!atomic_add_unless(&ucounts->count, 1, INT_MAX))
+ if (ucounts->count == INT_MAX)
ucounts = NULL;
+ else
+ ucounts->count += 1;
spin_unlock_irq(&ucounts_lock);
return ucounts;
}
@@ -165,13 +167,15 @@ static void put_ucounts(struct ucounts *ucounts)
{
unsigned long flags;
- if (atomic_dec_and_test(&ucounts->count)) {
- spin_lock_irqsave(&ucounts_lock, flags);
+ spin_lock_irqsave(&ucounts_lock, flags);
+ ucounts->count -= 1;
+ if (!ucounts->count)
hlist_del_init(&ucounts->node);
- spin_unlock_irqrestore(&ucounts_lock, flags);
+ else
+ ucounts = NULL;
+ spin_unlock_irqrestore(&ucounts_lock, flags);
- kfree(ucounts);
- }
+ kfree(ucounts);
}
static inline bool atomic_inc_below(atomic_t *v, int u)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 072cbc9..c0168b7 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1507,6 +1507,7 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
struct timer_list *timer = &dwork->timer;
struct work_struct *work = &dwork->work;
+ WARN_ON_ONCE(!wq);
WARN_ON_ONCE(timer->function != delayed_work_timer_fn ||
timer->data != (unsigned long)dwork);
WARN_ON_ONCE(timer_pending(timer));
diff --git a/lib/ioremap.c b/lib/ioremap.c
index a3e14ce..4bb3020 100644
--- a/lib/ioremap.c
+++ b/lib/ioremap.c
@@ -14,6 +14,7 @@
#include <asm/pgtable.h>
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+static int __read_mostly ioremap_p4d_capable;
static int __read_mostly ioremap_pud_capable;
static int __read_mostly ioremap_pmd_capable;
static int __read_mostly ioremap_huge_disabled;
@@ -35,6 +36,11 @@ void __init ioremap_huge_init(void)
}
}
+static inline int ioremap_p4d_enabled(void)
+{
+ return ioremap_p4d_capable;
+}
+
static inline int ioremap_pud_enabled(void)
{
return ioremap_pud_capable;
@@ -46,6 +52,7 @@ static inline int ioremap_pmd_enabled(void)
}
#else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */
+static inline int ioremap_p4d_enabled(void) { return 0; }
static inline int ioremap_pud_enabled(void) { return 0; }
static inline int ioremap_pmd_enabled(void) { return 0; }
#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
@@ -94,14 +101,14 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
return 0;
}
-static inline int ioremap_pud_range(pgd_t *pgd, unsigned long addr,
+static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr,
unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
{
pud_t *pud;
unsigned long next;
phys_addr -= addr;
- pud = pud_alloc(&init_mm, pgd, addr);
+ pud = pud_alloc(&init_mm, p4d, addr);
if (!pud)
return -ENOMEM;
do {
@@ -120,6 +127,32 @@ static inline int ioremap_pud_range(pgd_t *pgd, unsigned long addr,
return 0;
}
+static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr,
+ unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
+{
+ p4d_t *p4d;
+ unsigned long next;
+
+ phys_addr -= addr;
+ p4d = p4d_alloc(&init_mm, pgd, addr);
+ if (!p4d)
+ return -ENOMEM;
+ do {
+ next = p4d_addr_end(addr, end);
+
+ if (ioremap_p4d_enabled() &&
+ ((next - addr) == P4D_SIZE) &&
+ IS_ALIGNED(phys_addr + addr, P4D_SIZE)) {
+ if (p4d_set_huge(p4d, phys_addr + addr, prot))
+ continue;
+ }
+
+ if (ioremap_pud_range(p4d, addr, next, phys_addr + addr, prot))
+ return -ENOMEM;
+ } while (p4d++, addr = next, addr != end);
+ return 0;
+}
+
int ioremap_page_range(unsigned long addr,
unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
{
@@ -135,7 +168,7 @@ int ioremap_page_range(unsigned long addr,
pgd = pgd_offset_k(addr);
do {
next = pgd_addr_end(addr, end);
- err = ioremap_pud_range(pgd, addr, next, phys_addr+addr, prot);
+ err = ioremap_p4d_range(pgd, addr, next, phys_addr+addr, prot);
if (err)
break;
} while (pgd++, addr = next, addr != end);
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 5ed506d..691a9ad 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -2129,8 +2129,8 @@ int ida_pre_get(struct ida *ida, gfp_t gfp)
struct ida_bitmap *bitmap = kmalloc(sizeof(*bitmap), gfp);
if (!bitmap)
return 0;
- bitmap = this_cpu_cmpxchg(ida_bitmap, NULL, bitmap);
- kfree(bitmap);
+ if (this_cpu_cmpxchg(ida_bitmap, NULL, bitmap))
+ kfree(bitmap);
}
return 1;
diff --git a/lib/refcount.c b/lib/refcount.c
index 1d33366..aa09ad3 100644
--- a/lib/refcount.c
+++ b/lib/refcount.c
@@ -58,7 +58,7 @@ bool refcount_add_not_zero(unsigned int i, refcount_t *r)
val = old;
}
- WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
+ WARN_ONCE(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
return true;
}
@@ -66,7 +66,7 @@ EXPORT_SYMBOL_GPL(refcount_add_not_zero);
void refcount_add(unsigned int i, refcount_t *r)
{
- WARN(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n");
+ WARN_ONCE(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n");
}
EXPORT_SYMBOL_GPL(refcount_add);
@@ -97,7 +97,7 @@ bool refcount_inc_not_zero(refcount_t *r)
val = old;
}
- WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
+ WARN_ONCE(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
return true;
}
@@ -111,7 +111,7 @@ EXPORT_SYMBOL_GPL(refcount_inc_not_zero);
*/
void refcount_inc(refcount_t *r)
{
- WARN(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n");
+ WARN_ONCE(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n");
}
EXPORT_SYMBOL_GPL(refcount_inc);
@@ -125,7 +125,7 @@ bool refcount_sub_and_test(unsigned int i, refcount_t *r)
new = val - i;
if (new > val) {
- WARN(new > val, "refcount_t: underflow; use-after-free.\n");
+ WARN_ONCE(new > val, "refcount_t: underflow; use-after-free.\n");
return false;
}
@@ -164,7 +164,7 @@ EXPORT_SYMBOL_GPL(refcount_dec_and_test);
void refcount_dec(refcount_t *r)
{
- WARN(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n");
+ WARN_ONCE(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n");
}
EXPORT_SYMBOL_GPL(refcount_dec);
@@ -204,7 +204,7 @@ bool refcount_dec_not_one(refcount_t *r)
new = val - 1;
if (new > val) {
- WARN(new > val, "refcount_t: underflow; use-after-free.\n");
+ WARN_ONCE(new > val, "refcount_t: underflow; use-after-free.\n");
return true;
}
diff --git a/lib/syscall.c b/lib/syscall.c
index 17d5ff5..2c6cd1b 100644
--- a/lib/syscall.c
+++ b/lib/syscall.c
@@ -12,6 +12,7 @@ static int collect_syscall(struct task_struct *target, long *callno,
if (!try_get_task_stack(target)) {
/* Task has no stack, so the task isn't in a syscall. */
+ *sp = *pc = 0;
*callno = -1;
return 0;
}
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index 0b1d314..a25c976 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -20,6 +20,7 @@
#include <linux/string.h>
#include <linux/uaccess.h>
#include <linux/module.h>
+#include <linux/kasan.h>
/*
* Note: test functions are marked noinline so that their names appear in
@@ -474,6 +475,12 @@ static noinline void __init use_after_scope_test(void)
static int __init kmalloc_tests_init(void)
{
+ /*
+ * Temporarily enable multi-shot mode. Otherwise, we'd only get a
+ * report for the first case.
+ */
+ bool multishot = kasan_save_enable_multi_shot();
+
kmalloc_oob_right();
kmalloc_oob_left();
kmalloc_node_oob_right();
@@ -499,6 +506,9 @@ static int __init kmalloc_tests_init(void)
ksize_unpoisons_memory();
copy_user_test();
use_after_scope_test();
+
+ kasan_restore_multi_shot(multishot);
+
return -EAGAIN;
}
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 6d861d0..c6f2a37 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -683,33 +683,26 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi)
static void cgwb_bdi_destroy(struct backing_dev_info *bdi)
{
struct radix_tree_iter iter;
- struct rb_node *rbn;
void **slot;
WARN_ON(test_bit(WB_registered, &bdi->wb.state));
spin_lock_irq(&cgwb_lock);
-
radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0)
cgwb_kill(*slot);
-
- while ((rbn = rb_first(&bdi->cgwb_congested_tree))) {
- struct bdi_writeback_congested *congested =
- rb_entry(rbn, struct bdi_writeback_congested, rb_node);
-
- rb_erase(rbn, &bdi->cgwb_congested_tree);
- congested->bdi = NULL; /* mark @congested unlinked */
- }
-
spin_unlock_irq(&cgwb_lock);
/*
- * All cgwb's and their congested states must be shutdown and
- * released before returning. Drain the usage counter to wait for
- * all cgwb's and cgwb_congested's ever created on @bdi.
+ * All cgwb's must be shutdown and released before returning. Drain
+ * the usage counter to wait for all cgwb's ever created on @bdi.
*/
atomic_dec(&bdi->usage_cnt);
wait_event(cgwb_release_wait, !atomic_read(&bdi->usage_cnt));
+ /*
+ * Grab back our reference so that we hold it when @bdi gets
+ * re-registered.
+ */
+ atomic_inc(&bdi->usage_cnt);
}
/**
@@ -749,6 +742,21 @@ void wb_blkcg_offline(struct blkcg *blkcg)
spin_unlock_irq(&cgwb_lock);
}
+static void cgwb_bdi_exit(struct backing_dev_info *bdi)
+{
+ struct rb_node *rbn;
+
+ spin_lock_irq(&cgwb_lock);
+ while ((rbn = rb_first(&bdi->cgwb_congested_tree))) {
+ struct bdi_writeback_congested *congested =
+ rb_entry(rbn, struct bdi_writeback_congested, rb_node);
+
+ rb_erase(rbn, &bdi->cgwb_congested_tree);
+ congested->bdi = NULL; /* mark @congested unlinked */
+ }
+ spin_unlock_irq(&cgwb_lock);
+}
+
#else /* CONFIG_CGROUP_WRITEBACK */
static int cgwb_bdi_init(struct backing_dev_info *bdi)
@@ -769,7 +777,9 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi)
return 0;
}
-static void cgwb_bdi_destroy(struct backing_dev_info *bdi)
+static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { }
+
+static void cgwb_bdi_exit(struct backing_dev_info *bdi)
{
wb_congested_put(bdi->wb_congested);
}
@@ -857,6 +867,8 @@ int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner)
MINOR(owner->devt));
if (rc)
return rc;
+ /* Leaking owner reference... */
+ WARN_ON(bdi->owner);
bdi->owner = owner;
get_device(owner);
return 0;
@@ -898,6 +910,7 @@ static void bdi_exit(struct backing_dev_info *bdi)
{
WARN_ON_ONCE(bdi->dev);
wb_exit(&bdi->wb);
+ cgwb_bdi_exit(bdi);
}
static void release_bdi(struct kref *ref)
diff --git a/mm/gup.c b/mm/gup.c
index 9c047e9..04aa405 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -226,6 +226,7 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
unsigned int *page_mask)
{
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
spinlock_t *ptl;
@@ -243,8 +244,13 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
pgd = pgd_offset(mm, address);
if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
return no_page_table(vma, flags);
-
- pud = pud_offset(pgd, address);
+ p4d = p4d_offset(pgd, address);
+ if (p4d_none(*p4d))
+ return no_page_table(vma, flags);
+ BUILD_BUG_ON(p4d_huge(*p4d));
+ if (unlikely(p4d_bad(*p4d)))
+ return no_page_table(vma, flags);
+ pud = pud_offset(p4d, address);
if (pud_none(*pud))
return no_page_table(vma, flags);
if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
@@ -325,6 +331,7 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
struct page **page)
{
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
@@ -338,7 +345,9 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
else
pgd = pgd_offset_gate(mm, address);
BUG_ON(pgd_none(*pgd));
- pud = pud_offset(pgd, address);
+ p4d = p4d_offset(pgd, address);
+ BUG_ON(p4d_none(*p4d));
+ pud = pud_offset(p4d, address);
BUG_ON(pud_none(*pud));
pmd = pmd_offset(pud, address);
if (pmd_none(*pmd))
@@ -1400,13 +1409,13 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
return 1;
}
-static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
+static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end,
int write, struct page **pages, int *nr)
{
unsigned long next;
pud_t *pudp;
- pudp = pud_offset(&pgd, addr);
+ pudp = pud_offset(&p4d, addr);
do {
pud_t pud = READ_ONCE(*pudp);
@@ -1428,6 +1437,31 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
return 1;
}
+static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end,
+ int write, struct page **pages, int *nr)
+{
+ unsigned long next;
+ p4d_t *p4dp;
+
+ p4dp = p4d_offset(&pgd, addr);
+ do {
+ p4d_t p4d = READ_ONCE(*p4dp);
+
+ next = p4d_addr_end(addr, end);
+ if (p4d_none(p4d))
+ return 0;
+ BUILD_BUG_ON(p4d_huge(p4d));
+ if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) {
+ if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr,
+ P4D_SHIFT, next, write, pages, nr))
+ return 0;
+ } else if (!gup_pud_range(p4d, addr, next, write, pages, nr))
+ return 0;
+ } while (p4dp++, addr = next, addr != end);
+
+ return 1;
+}
+
/*
* Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to
* the regular GUP. It will only return non-negative values.
@@ -1478,7 +1512,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr,
PGDIR_SHIFT, next, write, pages, &nr))
break;
- } else if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+ } else if (!gup_p4d_range(pgd, addr, next, write, pages, &nr))
break;
} while (pgdp++, addr = next, addr != end);
local_irq_restore(flags);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d36b2af..1ebc93e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1828,7 +1828,7 @@ static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud,
VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma);
VM_BUG_ON(!pud_trans_huge(*pud) && !pud_devmap(*pud));
- count_vm_event(THP_SPLIT_PMD);
+ count_vm_event(THP_SPLIT_PUD);
pudp_huge_clear_flush_notify(vma, haddr, pud);
}
@@ -2048,6 +2048,7 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
bool freeze, struct page *page)
{
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
@@ -2055,7 +2056,11 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
if (!pgd_present(*pgd))
return;
- pud = pud_offset(pgd, address);
+ p4d = p4d_offset(pgd, address);
+ if (!p4d_present(*p4d))
+ return;
+
+ pud = pud_offset(p4d, address);
if (!pud_present(*pud))
return;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a7aa811..e582887 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4403,7 +4403,9 @@ int hugetlb_reserve_pages(struct inode *inode,
return 0;
out_err:
if (!vma || vma->vm_flags & VM_MAYSHARE)
- region_abort(resv_map, from, to);
+ /* Don't call region_abort if region_chg failed */
+ if (chg >= 0)
+ region_abort(resv_map, from, to);
if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER))
kref_put(&resv_map->refs, resv_map_release);
return ret;
@@ -4555,7 +4557,8 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
{
pgd_t *pgd = pgd_offset(mm, *addr);
- pud_t *pud = pud_offset(pgd, *addr);
+ p4d_t *p4d = p4d_offset(pgd, *addr);
+ pud_t *pud = pud_offset(p4d, *addr);
BUG_ON(page_count(virt_to_page(ptep)) == 0);
if (page_count(virt_to_page(ptep)) == 1)
@@ -4586,11 +4589,13 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
unsigned long addr, unsigned long sz)
{
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
pte_t *pte = NULL;
pgd = pgd_offset(mm, addr);
- pud = pud_alloc(mm, pgd, addr);
+ p4d = p4d_offset(pgd, addr);
+ pud = pud_alloc(mm, p4d, addr);
if (pud) {
if (sz == PUD_SIZE) {
pte = (pte_t *)pud;
@@ -4610,18 +4615,22 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
- pmd_t *pmd = NULL;
+ pmd_t *pmd;
pgd = pgd_offset(mm, addr);
- if (pgd_present(*pgd)) {
- pud = pud_offset(pgd, addr);
- if (pud_present(*pud)) {
- if (pud_huge(*pud))
- return (pte_t *)pud;
- pmd = pmd_offset(pud, addr);
- }
- }
+ if (!pgd_present(*pgd))
+ return NULL;
+ p4d = p4d_offset(pgd, addr);
+ if (!p4d_present(*p4d))
+ return NULL;
+ pud = pud_offset(p4d, addr);
+ if (!pud_present(*pud))
+ return NULL;
+ if (pud_huge(*pud))
+ return (pte_t *)pud;
+ pmd = pmd_offset(pud, addr);
return (pte_t *) pmd;
}
@@ -4644,6 +4653,7 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
{
struct page *page = NULL;
spinlock_t *ptl;
+ pte_t pte;
retry:
ptl = pmd_lockptr(mm, pmd);
spin_lock(ptl);
@@ -4653,12 +4663,13 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
*/
if (!pmd_huge(*pmd))
goto out;
- if (pmd_present(*pmd)) {
+ pte = huge_ptep_get((pte_t *)pmd);
+ if (pte_present(pte)) {
page = pmd_page(*pmd) + ((address & ~PMD_MASK) >> PAGE_SHIFT);
if (flags & FOLL_GET)
get_page(page);
} else {
- if (is_hugetlb_entry_migration(huge_ptep_get((pte_t *)pmd))) {
+ if (is_hugetlb_entry_migration(pte)) {
spin_unlock(ptl);
__migration_entry_wait(mm, (pte_t *)pmd, ptl);
goto retry;
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index 1c260e6..dd2dea8 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -96,11 +96,6 @@ static inline const void *kasan_shadow_to_mem(const void *shadow_addr)
<< KASAN_SHADOW_SCALE_SHIFT);
}
-static inline bool kasan_report_enabled(void)
-{
- return !current->kasan_depth;
-}
-
void kasan_report(unsigned long addr, size_t size,
bool is_write, unsigned long ip);
void kasan_report_double_free(struct kmem_cache *cache, void *object,
diff --git a/mm/kasan/kasan_init.c b/mm/kasan/kasan_init.c
index 31238da..b96a5f7 100644
--- a/mm/kasan/kasan_init.c
+++ b/mm/kasan/kasan_init.c
@@ -30,6 +30,9 @@
*/
unsigned char kasan_zero_page[PAGE_SIZE] __page_aligned_bss;
+#if CONFIG_PGTABLE_LEVELS > 4
+p4d_t kasan_zero_p4d[PTRS_PER_P4D] __page_aligned_bss;
+#endif
#if CONFIG_PGTABLE_LEVELS > 3
pud_t kasan_zero_pud[PTRS_PER_PUD] __page_aligned_bss;
#endif
@@ -82,10 +85,10 @@ static void __init zero_pmd_populate(pud_t *pud, unsigned long addr,
} while (pmd++, addr = next, addr != end);
}
-static void __init zero_pud_populate(pgd_t *pgd, unsigned long addr,
+static void __init zero_pud_populate(p4d_t *p4d, unsigned long addr,
unsigned long end)
{
- pud_t *pud = pud_offset(pgd, addr);
+ pud_t *pud = pud_offset(p4d, addr);
unsigned long next;
do {
@@ -107,6 +110,23 @@ static void __init zero_pud_populate(pgd_t *pgd, unsigned long addr,
} while (pud++, addr = next, addr != end);
}
+static void __init zero_p4d_populate(pgd_t *pgd, unsigned long addr,
+ unsigned long end)
+{
+ p4d_t *p4d = p4d_offset(pgd, addr);
+ unsigned long next;
+
+ do {
+ next = p4d_addr_end(addr, end);
+
+ if (p4d_none(*p4d)) {
+ p4d_populate(&init_mm, p4d,
+ early_alloc(PAGE_SIZE, NUMA_NO_NODE));
+ }
+ zero_pud_populate(p4d, addr, next);
+ } while (p4d++, addr = next, addr != end);
+}
+
/**
* kasan_populate_zero_shadow - populate shadow memory region with
* kasan_zero_page
@@ -125,6 +145,7 @@ void __init kasan_populate_zero_shadow(const void *shadow_start,
next = pgd_addr_end(addr, end);
if (IS_ALIGNED(addr, PGDIR_SIZE) && end - addr >= PGDIR_SIZE) {
+ p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
@@ -135,9 +156,22 @@ void __init kasan_populate_zero_shadow(const void *shadow_start,
* 3,2 - level page tables where we don't have
* puds,pmds, so pgd_populate(), pud_populate()
* is noops.
+ *
+ * The ifndef is required to avoid build breakage.
+ *
+ * With 5level-fixup.h, pgd_populate() is not nop and
+ * we reference kasan_zero_p4d. It's not defined
+ * unless 5-level paging enabled.
+ *
+ * The ifndef can be dropped once all KASAN-enabled
+ * architectures will switch to pgtable-nop4d.h.
*/
- pgd_populate(&init_mm, pgd, lm_alias(kasan_zero_pud));
- pud = pud_offset(pgd, addr);
+#ifndef __ARCH_HAS_5LEVEL_HACK
+ pgd_populate(&init_mm, pgd, lm_alias(kasan_zero_p4d));
+#endif
+ p4d = p4d_offset(pgd, addr);
+ p4d_populate(&init_mm, p4d, lm_alias(kasan_zero_pud));
+ pud = pud_offset(p4d, addr);
pud_populate(&init_mm, pud, lm_alias(kasan_zero_pmd));
pmd = pmd_offset(pud, addr);
pmd_populate_kernel(&init_mm, pmd, lm_alias(kasan_zero_pte));
@@ -148,6 +182,6 @@ void __init kasan_populate_zero_shadow(const void *shadow_start,
pgd_populate(&init_mm, pgd,
early_alloc(PAGE_SIZE, NUMA_NO_NODE));
}
- zero_pud_populate(pgd, addr, next);
+ zero_p4d_populate(pgd, addr, next);
} while (pgd++, addr = next, addr != end);
}
diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c
index 6f1ed16..3a8ddf8 100644
--- a/mm/kasan/quarantine.c
+++ b/mm/kasan/quarantine.c
@@ -25,6 +25,7 @@
#include <linux/printk.h>
#include <linux/shrinker.h>
#include <linux/slab.h>
+#include <linux/srcu.h>
#include <linux/string.h>
#include <linux/types.h>
@@ -103,6 +104,7 @@ static int quarantine_tail;
/* Total size of all objects in global_quarantine across all batches. */
static unsigned long quarantine_size;
static DEFINE_SPINLOCK(quarantine_lock);
+DEFINE_STATIC_SRCU(remove_cache_srcu);
/* Maximum size of the global queue. */
static unsigned long quarantine_max_size;
@@ -173,17 +175,22 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache)
struct qlist_head *q;
struct qlist_head temp = QLIST_INIT;
+ /*
+ * Note: irq must be disabled until after we move the batch to the
+ * global quarantine. Otherwise quarantine_remove_cache() can miss
+ * some objects belonging to the cache if they are in our local temp
+ * list. quarantine_remove_cache() executes on_each_cpu() at the
+ * beginning which ensures that it either sees the objects in per-cpu
+ * lists or in the global quarantine.
+ */
local_irq_save(flags);
q = this_cpu_ptr(&cpu_quarantine);
qlist_put(q, &info->quarantine_link, cache->size);
- if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE))
+ if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) {
qlist_move_all(q, &temp);
- local_irq_restore(flags);
-
- if (unlikely(!qlist_empty(&temp))) {
- spin_lock_irqsave(&quarantine_lock, flags);
+ spin_lock(&quarantine_lock);
WRITE_ONCE(quarantine_size, quarantine_size + temp.bytes);
qlist_move_all(&temp, &global_quarantine[quarantine_tail]);
if (global_quarantine[quarantine_tail].bytes >=
@@ -196,20 +203,33 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache)
if (new_tail != quarantine_head)
quarantine_tail = new_tail;
}
- spin_unlock_irqrestore(&quarantine_lock, flags);
+ spin_unlock(&quarantine_lock);
}
+
+ local_irq_restore(flags);
}
void quarantine_reduce(void)
{
size_t total_size, new_quarantine_size, percpu_quarantines;
unsigned long flags;
+ int srcu_idx;
struct qlist_head to_free = QLIST_INIT;
if (likely(READ_ONCE(quarantine_size) <=
READ_ONCE(quarantine_max_size)))
return;
+ /*
+ * srcu critical section ensures that quarantine_remove_cache()
+ * will not miss objects belonging to the cache while they are in our
+ * local to_free list. srcu is chosen because (1) it gives us private
+ * grace period domain that does not interfere with anything else,
+ * and (2) it allows synchronize_srcu() to return without waiting
+ * if there are no pending read critical sections (which is the
+ * expected case).
+ */
+ srcu_idx = srcu_read_lock(&remove_cache_srcu);
spin_lock_irqsave(&quarantine_lock, flags);
/*
@@ -237,6 +257,7 @@ void quarantine_reduce(void)
spin_unlock_irqrestore(&quarantine_lock, flags);
qlist_free_all(&to_free, NULL);
+ srcu_read_unlock(&remove_cache_srcu, srcu_idx);
}
static void qlist_move_cache(struct qlist_head *from,
@@ -280,12 +301,28 @@ void quarantine_remove_cache(struct kmem_cache *cache)
unsigned long flags, i;
struct qlist_head to_free = QLIST_INIT;
+ /*
+ * Must be careful to not miss any objects that are being moved from
+ * per-cpu list to the global quarantine in quarantine_put(),
+ * nor objects being freed in quarantine_reduce(). on_each_cpu()
+ * achieves the first goal, while synchronize_srcu() achieves the
+ * second.
+ */
on_each_cpu(per_cpu_remove_cache, cache, 1);
spin_lock_irqsave(&quarantine_lock, flags);
- for (i = 0; i < QUARANTINE_BATCHES; i++)
+ for (i = 0; i < QUARANTINE_BATCHES; i++) {
+ if (qlist_empty(&global_quarantine[i]))
+ continue;
qlist_move_cache(&global_quarantine[i], &to_free, cache);
+ /* Scanning whole quarantine can take a while. */
+ spin_unlock_irqrestore(&quarantine_lock, flags);
+ cond_resched();
+ spin_lock_irqsave(&quarantine_lock, flags);
+ }
spin_unlock_irqrestore(&quarantine_lock, flags);
qlist_free_all(&to_free, cache);
+
+ synchronize_srcu(&remove_cache_srcu);
}
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index f479365..ab42a08 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -13,7 +13,9 @@
*
*/
+#include <linux/bitops.h>
#include <linux/ftrace.h>
+#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/printk.h>
@@ -293,6 +295,40 @@ static void kasan_report_error(struct kasan_access_info *info)
kasan_end_report(&flags);
}
+static unsigned long kasan_flags;
+
+#define KASAN_BIT_REPORTED 0
+#define KASAN_BIT_MULTI_SHOT 1
+
+bool kasan_save_enable_multi_shot(void)
+{
+ return test_and_set_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags);
+}
+EXPORT_SYMBOL_GPL(kasan_save_enable_multi_shot);
+
+void kasan_restore_multi_shot(bool enabled)
+{
+ if (!enabled)
+ clear_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags);
+}
+EXPORT_SYMBOL_GPL(kasan_restore_multi_shot);
+
+static int __init kasan_set_multi_shot(char *str)
+{
+ set_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags);
+ return 1;
+}
+__setup("kasan_multi_shot", kasan_set_multi_shot);
+
+static inline bool kasan_report_enabled(void)
+{
+ if (current->kasan_depth)
+ return false;
+ if (test_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags))
+ return true;
+ return !test_and_set_bit(KASAN_BIT_REPORTED, &kasan_flags);
+}
+
void kasan_report(unsigned long addr, size_t size,
bool is_write, unsigned long ip)
{
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 26c874e..20036d4 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1416,7 +1416,7 @@ static void kmemleak_scan(void)
/* data/bss scanning */
scan_large_block(_sdata, _edata);
scan_large_block(__bss_start, __bss_stop);
- scan_large_block(__start_data_ro_after_init, __end_data_ro_after_init);
+ scan_large_block(__start_ro_after_init, __end_ro_after_init);
#ifdef CONFIG_SMP
/* per-cpu sections scanning */
diff --git a/mm/madvise.c b/mm/madvise.c
index dc5927c..7a2abf0 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -513,7 +513,43 @@ static long madvise_dontneed(struct vm_area_struct *vma,
if (!can_madv_dontneed_vma(vma))
return -EINVAL;
- userfaultfd_remove(vma, prev, start, end);
+ if (!userfaultfd_remove(vma, start, end)) {
+ *prev = NULL; /* mmap_sem has been dropped, prev is stale */
+
+ down_read(¤t->mm->mmap_sem);
+ vma = find_vma(current->mm, start);
+ if (!vma)
+ return -ENOMEM;
+ if (start < vma->vm_start) {
+ /*
+ * This "vma" under revalidation is the one
+ * with the lowest vma->vm_start where start
+ * is also < vma->vm_end. If start <
+ * vma->vm_start it means an hole materialized
+ * in the user address space within the
+ * virtual range passed to MADV_DONTNEED.
+ */
+ return -ENOMEM;
+ }
+ if (!can_madv_dontneed_vma(vma))
+ return -EINVAL;
+ if (end > vma->vm_end) {
+ /*
+ * Don't fail if end > vma->vm_end. If the old
+ * vma was splitted while the mmap_sem was
+ * released the effect of the concurrent
+ * operation may not cause MADV_DONTNEED to
+ * have an undefined result. There may be an
+ * adjacent next vma that we'll walk
+ * next. userfaultfd_remove() will generate an
+ * UFFD_EVENT_REMOVE repetition on the
+ * end-vma->vm_end range, but the manager can
+ * handle a repetition fine.
+ */
+ end = vma->vm_end;
+ }
+ VM_WARN_ON(start >= end);
+ }
zap_page_range(vma, start, end - start);
return 0;
}
@@ -554,8 +590,10 @@ static long madvise_remove(struct vm_area_struct *vma,
* mmap_sem.
*/
get_file(f);
- userfaultfd_remove(vma, prev, start, end);
- up_read(¤t->mm->mmap_sem);
+ if (userfaultfd_remove(vma, start, end)) {
+ /* mmap_sem was not released by userfaultfd_remove() */
+ up_read(¤t->mm->mmap_sem);
+ }
error = vfs_fallocate(f,
FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
offset, end - start);
diff --git a/mm/memblock.c b/mm/memblock.c
index b64b478..696f06d1 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1118,7 +1118,10 @@ unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn,
}
} while (left < right);
- return min(PHYS_PFN(type->regions[right].base), max_pfn);
+ if (right == type->cnt)
+ return max_pfn;
+ else
+ return min(PHYS_PFN(type->regions[right].base), max_pfn);
}
/**
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c52ec89..2bd7541 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -466,6 +466,8 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
struct mem_cgroup_tree_per_node *mctz;
mctz = soft_limit_tree_from_page(page);
+ if (!mctz)
+ return;
/*
* Necessary to update all ancestors when hierarchy is used.
* because their event counter is not touched.
@@ -503,7 +505,8 @@ static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
for_each_node(nid) {
mz = mem_cgroup_nodeinfo(memcg, nid);
mctz = soft_limit_tree_node(nid);
- mem_cgroup_remove_exceeded(mz, mctz);
+ if (mctz)
+ mem_cgroup_remove_exceeded(mz, mctz);
}
}
@@ -2558,7 +2561,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
* is empty. Do it lockless to prevent lock bouncing. Races
* are acceptable as soft limit is best effort anyway.
*/
- if (RB_EMPTY_ROOT(&mctz->rb_root))
+ if (!mctz || RB_EMPTY_ROOT(&mctz->rb_root))
return 0;
/*
@@ -4135,17 +4138,22 @@ static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
kfree(memcg->nodeinfo[node]);
}
-static void mem_cgroup_free(struct mem_cgroup *memcg)
+static void __mem_cgroup_free(struct mem_cgroup *memcg)
{
int node;
- memcg_wb_domain_exit(memcg);
for_each_node(node)
free_mem_cgroup_per_node_info(memcg, node);
free_percpu(memcg->stat);
kfree(memcg);
}
+static void mem_cgroup_free(struct mem_cgroup *memcg)
+{
+ memcg_wb_domain_exit(memcg);
+ __mem_cgroup_free(memcg);
+}
+
static struct mem_cgroup *mem_cgroup_alloc(void)
{
struct mem_cgroup *memcg;
@@ -4196,7 +4204,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
fail:
if (memcg->id.id > 0)
idr_remove(&mem_cgroup_idr, memcg->id.id);
- mem_cgroup_free(memcg);
+ __mem_cgroup_free(memcg);
return NULL;
}
diff --git a/mm/memory.c b/mm/memory.c
index a97a4ce..235ba51 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -445,7 +445,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
mm_dec_nr_pmds(tlb->mm);
}
-static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
+static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
@@ -454,7 +454,7 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
unsigned long start;
start = addr;
- pud = pud_offset(pgd, addr);
+ pud = pud_offset(p4d, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
@@ -462,6 +462,39 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
free_pmd_range(tlb, pud, addr, next, floor, ceiling);
} while (pud++, addr = next, addr != end);
+ start &= P4D_MASK;
+ if (start < floor)
+ return;
+ if (ceiling) {
+ ceiling &= P4D_MASK;
+ if (!ceiling)
+ return;
+ }
+ if (end - 1 > ceiling - 1)
+ return;
+
+ pud = pud_offset(p4d, start);
+ p4d_clear(p4d);
+ pud_free_tlb(tlb, pud, start);
+}
+
+static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd,
+ unsigned long addr, unsigned long end,
+ unsigned long floor, unsigned long ceiling)
+{
+ p4d_t *p4d;
+ unsigned long next;
+ unsigned long start;
+
+ start = addr;
+ p4d = p4d_offset(pgd, addr);
+ do {
+ next = p4d_addr_end(addr, end);
+ if (p4d_none_or_clear_bad(p4d))
+ continue;
+ free_pud_range(tlb, p4d, addr, next, floor, ceiling);
+ } while (p4d++, addr = next, addr != end);
+
start &= PGDIR_MASK;
if (start < floor)
return;
@@ -473,9 +506,9 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
if (end - 1 > ceiling - 1)
return;
- pud = pud_offset(pgd, start);
+ p4d = p4d_offset(pgd, start);
pgd_clear(pgd);
- pud_free_tlb(tlb, pud, start);
+ p4d_free_tlb(tlb, p4d, start);
}
/*
@@ -539,7 +572,7 @@ void free_pgd_range(struct mmu_gather *tlb,
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
- free_pud_range(tlb, pgd, addr, next, floor, ceiling);
+ free_p4d_range(tlb, pgd, addr, next, floor, ceiling);
} while (pgd++, addr = next, addr != end);
}
@@ -658,7 +691,8 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
pte_t pte, struct page *page)
{
pgd_t *pgd = pgd_offset(vma->vm_mm, addr);
- pud_t *pud = pud_offset(pgd, addr);
+ p4d_t *p4d = p4d_offset(pgd, addr);
+ pud_t *pud = pud_offset(p4d, addr);
pmd_t *pmd = pmd_offset(pud, addr);
struct address_space *mapping;
pgoff_t index;
@@ -1023,16 +1057,16 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src
}
static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
- pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
+ p4d_t *dst_p4d, p4d_t *src_p4d, struct vm_area_struct *vma,
unsigned long addr, unsigned long end)
{
pud_t *src_pud, *dst_pud;
unsigned long next;
- dst_pud = pud_alloc(dst_mm, dst_pgd, addr);
+ dst_pud = pud_alloc(dst_mm, dst_p4d, addr);
if (!dst_pud)
return -ENOMEM;
- src_pud = pud_offset(src_pgd, addr);
+ src_pud = pud_offset(src_p4d, addr);
do {
next = pud_addr_end(addr, end);
if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) {
@@ -1056,6 +1090,28 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src
return 0;
}
+static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+ pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
+ unsigned long addr, unsigned long end)
+{
+ p4d_t *src_p4d, *dst_p4d;
+ unsigned long next;
+
+ dst_p4d = p4d_alloc(dst_mm, dst_pgd, addr);
+ if (!dst_p4d)
+ return -ENOMEM;
+ src_p4d = p4d_offset(src_pgd, addr);
+ do {
+ next = p4d_addr_end(addr, end);
+ if (p4d_none_or_clear_bad(src_p4d))
+ continue;
+ if (copy_pud_range(dst_mm, src_mm, dst_p4d, src_p4d,
+ vma, addr, next))
+ return -ENOMEM;
+ } while (dst_p4d++, src_p4d++, addr = next, addr != end);
+ return 0;
+}
+
int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
struct vm_area_struct *vma)
{
@@ -1111,7 +1167,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(src_pgd))
continue;
- if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd,
+ if (unlikely(copy_p4d_range(dst_mm, src_mm, dst_pgd, src_pgd,
vma, addr, next))) {
ret = -ENOMEM;
break;
@@ -1267,14 +1323,14 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
}
static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
- struct vm_area_struct *vma, pgd_t *pgd,
+ struct vm_area_struct *vma, p4d_t *p4d,
unsigned long addr, unsigned long end,
struct zap_details *details)
{
pud_t *pud;
unsigned long next;
- pud = pud_offset(pgd, addr);
+ pud = pud_offset(p4d, addr);
do {
next = pud_addr_end(addr, end);
if (pud_trans_huge(*pud) || pud_devmap(*pud)) {
@@ -1295,6 +1351,25 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
return addr;
}
+static inline unsigned long zap_p4d_range(struct mmu_gather *tlb,
+ struct vm_area_struct *vma, pgd_t *pgd,
+ unsigned long addr, unsigned long end,
+ struct zap_details *details)
+{
+ p4d_t *p4d;
+ unsigned long next;
+
+ p4d = p4d_offset(pgd, addr);
+ do {
+ next = p4d_addr_end(addr, end);
+ if (p4d_none_or_clear_bad(p4d))
+ continue;
+ next = zap_pud_range(tlb, vma, p4d, addr, next, details);
+ } while (p4d++, addr = next, addr != end);
+
+ return addr;
+}
+
void unmap_page_range(struct mmu_gather *tlb,
struct vm_area_struct *vma,
unsigned long addr, unsigned long end,
@@ -1310,7 +1385,7 @@ void unmap_page_range(struct mmu_gather *tlb,
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
- next = zap_pud_range(tlb, vma, pgd, addr, next, details);
+ next = zap_p4d_range(tlb, vma, pgd, addr, next, details);
} while (pgd++, addr = next, addr != end);
tlb_end_vma(tlb, vma);
}
@@ -1465,16 +1540,24 @@ EXPORT_SYMBOL_GPL(zap_vma_ptes);
pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
spinlock_t **ptl)
{
- pgd_t *pgd = pgd_offset(mm, addr);
- pud_t *pud = pud_alloc(mm, pgd, addr);
- if (pud) {
- pmd_t *pmd = pmd_alloc(mm, pud, addr);
- if (pmd) {
- VM_BUG_ON(pmd_trans_huge(*pmd));
- return pte_alloc_map_lock(mm, pmd, addr, ptl);
- }
- }
- return NULL;
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+
+ pgd = pgd_offset(mm, addr);
+ p4d = p4d_alloc(mm, pgd, addr);
+ if (!p4d)
+ return NULL;
+ pud = pud_alloc(mm, p4d, addr);
+ if (!pud)
+ return NULL;
+ pmd = pmd_alloc(mm, pud, addr);
+ if (!pmd)
+ return NULL;
+
+ VM_BUG_ON(pmd_trans_huge(*pmd));
+ return pte_alloc_map_lock(mm, pmd, addr, ptl);
}
/*
@@ -1740,7 +1823,7 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
return 0;
}
-static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
+static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d,
unsigned long addr, unsigned long end,
unsigned long pfn, pgprot_t prot)
{
@@ -1748,7 +1831,7 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
unsigned long next;
pfn -= addr >> PAGE_SHIFT;
- pud = pud_alloc(mm, pgd, addr);
+ pud = pud_alloc(mm, p4d, addr);
if (!pud)
return -ENOMEM;
do {
@@ -1760,6 +1843,26 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
return 0;
}
+static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd,
+ unsigned long addr, unsigned long end,
+ unsigned long pfn, pgprot_t prot)
+{
+ p4d_t *p4d;
+ unsigned long next;
+
+ pfn -= addr >> PAGE_SHIFT;
+ p4d = p4d_alloc(mm, pgd, addr);
+ if (!p4d)
+ return -ENOMEM;
+ do {
+ next = p4d_addr_end(addr, end);
+ if (remap_pud_range(mm, p4d, addr, next,
+ pfn + (addr >> PAGE_SHIFT), prot))
+ return -ENOMEM;
+ } while (p4d++, addr = next, addr != end);
+ return 0;
+}
+
/**
* remap_pfn_range - remap kernel memory to userspace
* @vma: user vma to map to
@@ -1816,7 +1919,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
flush_cache_range(vma, addr, end);
do {
next = pgd_addr_end(addr, end);
- err = remap_pud_range(mm, pgd, addr, next,
+ err = remap_p4d_range(mm, pgd, addr, next,
pfn + (addr >> PAGE_SHIFT), prot);
if (err)
break;
@@ -1932,7 +2035,7 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
return err;
}
-static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd,
+static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
unsigned long addr, unsigned long end,
pte_fn_t fn, void *data)
{
@@ -1940,7 +2043,7 @@ static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd,
unsigned long next;
int err;
- pud = pud_alloc(mm, pgd, addr);
+ pud = pud_alloc(mm, p4d, addr);
if (!pud)
return -ENOMEM;
do {
@@ -1952,6 +2055,26 @@ static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd,
return err;
}
+static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd,
+ unsigned long addr, unsigned long end,
+ pte_fn_t fn, void *data)
+{
+ p4d_t *p4d;
+ unsigned long next;
+ int err;
+
+ p4d = p4d_alloc(mm, pgd, addr);
+ if (!p4d)
+ return -ENOMEM;
+ do {
+ next = p4d_addr_end(addr, end);
+ err = apply_to_pud_range(mm, p4d, addr, next, fn, data);
+ if (err)
+ break;
+ } while (p4d++, addr = next, addr != end);
+ return err;
+}
+
/*
* Scan a region of virtual memory, filling in page tables as necessary
* and calling a provided function on each leaf page table.
@@ -1970,7 +2093,7 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
pgd = pgd_offset(mm, addr);
do {
next = pgd_addr_end(addr, end);
- err = apply_to_pud_range(mm, pgd, addr, next, fn, data);
+ err = apply_to_p4d_range(mm, pgd, addr, next, fn, data);
if (err)
break;
} while (pgd++, addr = next, addr != end);
@@ -3653,11 +3776,15 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
};
struct mm_struct *mm = vma->vm_mm;
pgd_t *pgd;
+ p4d_t *p4d;
int ret;
pgd = pgd_offset(mm, address);
+ p4d = p4d_alloc(mm, pgd, address);
+ if (!p4d)
+ return VM_FAULT_OOM;
- vmf.pud = pud_alloc(mm, pgd, address);
+ vmf.pud = pud_alloc(mm, p4d, address);
if (!vmf.pud)
return VM_FAULT_OOM;
if (pud_none(*vmf.pud) && transparent_hugepage_enabled(vma)) {
@@ -3779,12 +3906,35 @@ int handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
}
EXPORT_SYMBOL_GPL(handle_mm_fault);
+#ifndef __PAGETABLE_P4D_FOLDED
+/*
+ * Allocate p4d page table.
+ * We've already handled the fast-path in-line.
+ */
+int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+{
+ p4d_t *new = p4d_alloc_one(mm, address);
+ if (!new)
+ return -ENOMEM;
+
+ smp_wmb(); /* See comment in __pte_alloc */
+
+ spin_lock(&mm->page_table_lock);
+ if (pgd_present(*pgd)) /* Another has populated it */
+ p4d_free(mm, new);
+ else
+ pgd_populate(mm, pgd, new);
+ spin_unlock(&mm->page_table_lock);
+ return 0;
+}
+#endif /* __PAGETABLE_P4D_FOLDED */
+
#ifndef __PAGETABLE_PUD_FOLDED
/*
* Allocate page upper directory.
* We've already handled the fast-path in-line.
*/
-int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address)
{
pud_t *new = pud_alloc_one(mm, address);
if (!new)
@@ -3793,10 +3943,17 @@ int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
smp_wmb(); /* See comment in __pte_alloc */
spin_lock(&mm->page_table_lock);
- if (pgd_present(*pgd)) /* Another has populated it */
+#ifndef __ARCH_HAS_5LEVEL_HACK
+ if (p4d_present(*p4d)) /* Another has populated it */
pud_free(mm, new);
else
- pgd_populate(mm, pgd, new);
+ p4d_populate(mm, p4d, new);
+#else
+ if (pgd_present(*p4d)) /* Another has populated it */
+ pud_free(mm, new);
+ else
+ pgd_populate(mm, p4d, new);
+#endif /* __ARCH_HAS_5LEVEL_HACK */
spin_unlock(&mm->page_table_lock);
return 0;
}
@@ -3839,6 +3996,7 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
{
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pte_t *ptep;
@@ -3847,7 +4005,11 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
goto out;
- pud = pud_offset(pgd, address);
+ p4d = p4d_offset(pgd, address);
+ if (p4d_none(*p4d) || unlikely(p4d_bad(*p4d)))
+ goto out;
+
+ pud = pud_offset(p4d, address);
if (pud_none(*pud) || unlikely(pud_bad(*pud)))
goto out;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 295479b..6fa7208 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -125,9 +125,12 @@ void put_online_mems(void)
}
+/* Serializes write accesses to mem_hotplug.active_writer. */
+static DEFINE_MUTEX(memory_add_remove_lock);
+
void mem_hotplug_begin(void)
{
- assert_held_device_hotplug();
+ mutex_lock(&memory_add_remove_lock);
mem_hotplug.active_writer = current;
@@ -147,6 +150,7 @@ void mem_hotplug_done(void)
mem_hotplug.active_writer = NULL;
mutex_unlock(&mem_hotplug.lock);
memhp_lock_release();
+ mutex_unlock(&memory_add_remove_lock);
}
/* add this memory to iomem resource */
diff --git a/mm/migrate.c b/mm/migrate.c
index 9a0897a..ed97c2c 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -209,8 +209,11 @@ static int remove_migration_pte(struct page *page, struct vm_area_struct *vma,
VM_BUG_ON_PAGE(PageTail(page), page);
while (page_vma_mapped_walk(&pvmw)) {
- new = page - pvmw.page->index +
- linear_page_index(vma, pvmw.address);
+ if (PageKsm(page))
+ new = page;
+ else
+ new = page - pvmw.page->index +
+ linear_page_index(vma, pvmw.address);
get_page(new);
pte = pte_mkold(mk_pte(new, READ_ONCE(vma->vm_page_prot)));
diff --git a/mm/mlock.c b/mm/mlock.c
index 1050511..0dd9ca1 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -380,6 +380,7 @@ static unsigned long __munlock_pagevec_fill(struct pagevec *pvec,
pte = get_locked_pte(vma->vm_mm, start, &ptl);
/* Make sure we do not cross the page table boundary */
end = pgd_addr_end(start, end);
+ end = p4d_addr_end(start, end);
end = pud_addr_end(start, end);
end = pmd_addr_end(start, end);
@@ -442,7 +443,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
while (start < end) {
struct page *page;
- unsigned int page_mask;
+ unsigned int page_mask = 0;
unsigned long page_increm;
struct pagevec pvec;
struct zone *zone;
@@ -456,8 +457,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
* suits munlock very well (and if somehow an abnormal page
* has sneaked into the range, we won't oops here: great).
*/
- page = follow_page_mask(vma, start, FOLL_GET | FOLL_DUMP,
- &page_mask);
+ page = follow_page(vma, start, FOLL_GET | FOLL_DUMP);
if (page && !IS_ERR(page)) {
if (PageTransTail(page)) {
@@ -468,8 +468,8 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
/*
* Any THP page found by follow_page_mask() may
* have gotten split before reaching
- * munlock_vma_page(), so we need to recompute
- * the page_mask here.
+ * munlock_vma_page(), so we need to compute
+ * the page_mask here instead.
*/
page_mask = munlock_vma_page(page);
unlock_page(page);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 848e946..8edd0d5 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -193,14 +193,14 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
}
static inline unsigned long change_pud_range(struct vm_area_struct *vma,
- pgd_t *pgd, unsigned long addr, unsigned long end,
+ p4d_t *p4d, unsigned long addr, unsigned long end,
pgprot_t newprot, int dirty_accountable, int prot_numa)
{
pud_t *pud;
unsigned long next;
unsigned long pages = 0;
- pud = pud_offset(pgd, addr);
+ pud = pud_offset(p4d, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
@@ -212,6 +212,26 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma,
return pages;
}
+static inline unsigned long change_p4d_range(struct vm_area_struct *vma,
+ pgd_t *pgd, unsigned long addr, unsigned long end,
+ pgprot_t newprot, int dirty_accountable, int prot_numa)
+{
+ p4d_t *p4d;
+ unsigned long next;
+ unsigned long pages = 0;
+
+ p4d = p4d_offset(pgd, addr);
+ do {
+ next = p4d_addr_end(addr, end);
+ if (p4d_none_or_clear_bad(p4d))
+ continue;
+ pages += change_pud_range(vma, p4d, addr, next, newprot,
+ dirty_accountable, prot_numa);
+ } while (p4d++, addr = next, addr != end);
+
+ return pages;
+}
+
static unsigned long change_protection_range(struct vm_area_struct *vma,
unsigned long addr, unsigned long end, pgprot_t newprot,
int dirty_accountable, int prot_numa)
@@ -230,7 +250,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
- pages += change_pud_range(vma, pgd, addr, next, newprot,
+ pages += change_p4d_range(vma, pgd, addr, next, newprot,
dirty_accountable, prot_numa);
} while (pgd++, addr = next, addr != end);
diff --git a/mm/mremap.c b/mm/mremap.c
index 8233b01..cd8a1b1 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -32,6 +32,7 @@
static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
@@ -39,7 +40,11 @@ static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
if (pgd_none_or_clear_bad(pgd))
return NULL;
- pud = pud_offset(pgd, addr);
+ p4d = p4d_offset(pgd, addr);
+ if (p4d_none_or_clear_bad(p4d))
+ return NULL;
+
+ pud = pud_offset(p4d, addr);
if (pud_none_or_clear_bad(pud))
return NULL;
@@ -54,11 +59,15 @@ static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr)
{
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pgd = pgd_offset(mm, addr);
- pud = pud_alloc(mm, pgd, addr);
+ p4d = p4d_alloc(mm, pgd, addr);
+ if (!p4d)
+ return NULL;
+ pud = pud_alloc(mm, p4d, addr);
if (!pud)
return NULL;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index eaa64d2..6cbde31 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -873,7 +873,8 @@ static inline void __free_one_page(struct page *page,
higher_page = page + (combined_pfn - pfn);
buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1);
higher_buddy = higher_page + (buddy_pfn - combined_pfn);
- if (page_is_buddy(higher_page, higher_buddy, order + 1)) {
+ if (pfn_valid_within(buddy_pfn) &&
+ page_is_buddy(higher_page, higher_buddy, order + 1)) {
list_add_tail(&page->lru,
&zone->free_area[order].free_list[migratetype]);
goto out;
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index a23001a..c4c9def 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -104,6 +104,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
struct mm_struct *mm = pvmw->vma->vm_mm;
struct page *page = pvmw->page;
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
/* The only possible pmd mapping has been handled on last iteration */
@@ -133,7 +134,10 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
pgd = pgd_offset(mm, pvmw->address);
if (!pgd_present(*pgd))
return false;
- pud = pud_offset(pgd, pvmw->address);
+ p4d = p4d_offset(pgd, pvmw->address);
+ if (!p4d_present(*p4d))
+ return false;
+ pud = pud_offset(p4d, pvmw->address);
if (!pud_present(*pud))
return false;
pvmw->pmd = pmd_offset(pud, pvmw->address);
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 0376157..60f7856 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -69,14 +69,14 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
return err;
}
-static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
+static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
pud_t *pud;
unsigned long next;
int err = 0;
- pud = pud_offset(pgd, addr);
+ pud = pud_offset(p4d, addr);
do {
again:
next = pud_addr_end(addr, end);
@@ -113,6 +113,32 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
return err;
}
+static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
+ struct mm_walk *walk)
+{
+ p4d_t *p4d;
+ unsigned long next;
+ int err = 0;
+
+ p4d = p4d_offset(pgd, addr);
+ do {
+ next = p4d_addr_end(addr, end);
+ if (p4d_none_or_clear_bad(p4d)) {
+ if (walk->pte_hole)
+ err = walk->pte_hole(addr, next, walk);
+ if (err)
+ break;
+ continue;
+ }
+ if (walk->pmd_entry || walk->pte_entry)
+ err = walk_pud_range(p4d, addr, next, walk);
+ if (err)
+ break;
+ } while (p4d++, addr = next, addr != end);
+
+ return err;
+}
+
static int walk_pgd_range(unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
@@ -131,7 +157,7 @@ static int walk_pgd_range(unsigned long addr, unsigned long end,
continue;
}
if (walk->pmd_entry || walk->pte_entry)
- err = walk_pud_range(pgd, addr, next, walk);
+ err = walk_p4d_range(pgd, addr, next, walk);
if (err)
break;
} while (pgd++, addr = next, addr != end);
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index 538998a..9ac6394 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -21,7 +21,6 @@ static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk,
/**
* pcpu_get_pages - get temp pages array
- * @chunk: chunk of interest
*
* Returns pointer to array of pointers to struct page which can be indexed
* with pcpu_page_idx(). Note that there is only one array and accesses
@@ -30,7 +29,7 @@ static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk,
* RETURNS:
* Pointer to temp pages array on success.
*/
-static struct page **pcpu_get_pages(struct pcpu_chunk *chunk_alloc)
+static struct page **pcpu_get_pages(void)
{
static struct page **pages;
size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]);
@@ -275,7 +274,7 @@ static int pcpu_populate_chunk(struct pcpu_chunk *chunk,
{
struct page **pages;
- pages = pcpu_get_pages(chunk);
+ pages = pcpu_get_pages();
if (!pages)
return -ENOMEM;
@@ -313,7 +312,7 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
* successful population attempt so the temp pages array must
* be available now.
*/
- pages = pcpu_get_pages(chunk);
+ pages = pcpu_get_pages();
BUG_ON(!pages);
/* unmap and free */
diff --git a/mm/percpu.c b/mm/percpu.c
index 5696039..60a6488 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1011,8 +1011,11 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
mutex_unlock(&pcpu_alloc_mutex);
}
- if (chunk != pcpu_reserved_chunk)
+ if (chunk != pcpu_reserved_chunk) {
+ spin_lock_irqsave(&pcpu_lock, flags);
pcpu_nr_empty_pop_pages -= occ_pages;
+ spin_unlock_irqrestore(&pcpu_lock, flags);
+ }
if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW)
pcpu_schedule_balance_work();
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 4ed5908..c99d951 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -22,6 +22,12 @@ void pgd_clear_bad(pgd_t *pgd)
pgd_clear(pgd);
}
+void p4d_clear_bad(p4d_t *p4d)
+{
+ p4d_ERROR(*p4d);
+ p4d_clear(p4d);
+}
+
void pud_clear_bad(pud_t *pud)
{
pud_ERROR(*pud);
diff --git a/mm/rmap.c b/mm/rmap.c
index 2da487d..f683801 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -684,6 +684,7 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
{
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
pmd_t *pmd = NULL;
pmd_t pmde;
@@ -692,7 +693,11 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
if (!pgd_present(*pgd))
goto out;
- pud = pud_offset(pgd, address);
+ p4d = p4d_offset(pgd, address);
+ if (!p4d_present(*p4d))
+ goto out;
+
+ pud = pud_offset(p4d, address);
if (!pud_present(*pud))
goto out;
@@ -1154,7 +1159,7 @@ void page_add_file_rmap(struct page *page, bool compound)
goto out;
}
__mod_node_page_state(page_pgdat(page), NR_FILE_MAPPED, nr);
- mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED);
+ mem_cgroup_update_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED, nr);
out:
unlock_page_memcg(page);
}
@@ -1194,7 +1199,7 @@ static void page_remove_file_rmap(struct page *page, bool compound)
* pte lock(a spinlock) is held, which implies preemption disabled.
*/
__mod_node_page_state(page_pgdat(page), NR_FILE_MAPPED, -nr);
- mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED);
+ mem_cgroup_update_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED, -nr);
if (unlikely(PageMlocked(page)))
clear_page_mlock(page);
@@ -1316,12 +1321,6 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
}
while (page_vma_mapped_walk(&pvmw)) {
- subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
- address = pvmw.address;
-
- /* Unexpected PMD-mapped THP? */
- VM_BUG_ON_PAGE(!pvmw.pte, page);
-
/*
* If the page is mlock()d, we cannot swap it out.
* If it's recently referenced (perhaps page_referenced
@@ -1345,6 +1344,13 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
continue;
}
+ /* Unexpected PMD-mapped THP? */
+ VM_BUG_ON_PAGE(!pvmw.pte, page);
+
+ subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
+ address = pvmw.address;
+
+
if (!(flags & TTU_IGNORE_ACCESS)) {
if (ptep_clear_flush_young_notify(vma, address,
pvmw.pte)) {
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 574c67b..a56c398 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -196,9 +196,9 @@ pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node)
return pmd;
}
-pud_t * __meminit vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node)
+pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node)
{
- pud_t *pud = pud_offset(pgd, addr);
+ pud_t *pud = pud_offset(p4d, addr);
if (pud_none(*pud)) {
void *p = vmemmap_alloc_block(PAGE_SIZE, node);
if (!p)
@@ -208,6 +208,18 @@ pud_t * __meminit vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node)
return pud;
}
+p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node)
+{
+ p4d_t *p4d = p4d_offset(pgd, addr);
+ if (p4d_none(*p4d)) {
+ void *p = vmemmap_alloc_block(PAGE_SIZE, node);
+ if (!p)
+ return NULL;
+ p4d_populate(&init_mm, p4d, p);
+ }
+ return p4d;
+}
+
pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
{
pgd_t *pgd = pgd_offset_k(addr);
@@ -225,6 +237,7 @@ int __meminit vmemmap_populate_basepages(unsigned long start,
{
unsigned long addr = start;
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
@@ -233,7 +246,10 @@ int __meminit vmemmap_populate_basepages(unsigned long start,
pgd = vmemmap_pgd_populate(addr, node);
if (!pgd)
return -ENOMEM;
- pud = vmemmap_pud_populate(pgd, addr, node);
+ p4d = vmemmap_p4d_populate(pgd, addr, node);
+ if (!p4d)
+ return -ENOMEM;
+ pud = vmemmap_pud_populate(p4d, addr, node);
if (!pud)
return -ENOMEM;
pmd = vmemmap_pmd_populate(pud, addr, node);
diff --git a/mm/swap_slots.c b/mm/swap_slots.c
index 9b5bc86..b1ccb58 100644
--- a/mm/swap_slots.c
+++ b/mm/swap_slots.c
@@ -267,8 +267,6 @@ int free_swap_slot(swp_entry_t entry)
{
struct swap_slots_cache *cache;
- BUG_ON(!swap_slot_cache_initialized);
-
cache = &get_cpu_var(swp_slots);
if (use_swap_slot_cache && cache->slots_ret) {
spin_lock_irq(&cache->free_lock);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 521ef9b..1781308 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1517,7 +1517,7 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
return 0;
}
-static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
+static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d,
unsigned long addr, unsigned long end,
swp_entry_t entry, struct page *page)
{
@@ -1525,7 +1525,7 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
unsigned long next;
int ret;
- pud = pud_offset(pgd, addr);
+ pud = pud_offset(p4d, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
@@ -1537,6 +1537,26 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
return 0;
}
+static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd,
+ unsigned long addr, unsigned long end,
+ swp_entry_t entry, struct page *page)
+{
+ p4d_t *p4d;
+ unsigned long next;
+ int ret;
+
+ p4d = p4d_offset(pgd, addr);
+ do {
+ next = p4d_addr_end(addr, end);
+ if (p4d_none_or_clear_bad(p4d))
+ continue;
+ ret = unuse_pud_range(vma, p4d, addr, next, entry, page);
+ if (ret)
+ return ret;
+ } while (p4d++, addr = next, addr != end);
+ return 0;
+}
+
static int unuse_vma(struct vm_area_struct *vma,
swp_entry_t entry, struct page *page)
{
@@ -1560,7 +1580,7 @@ static int unuse_vma(struct vm_area_struct *vma,
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
- ret = unuse_pud_range(vma, pgd, addr, next, entry, page);
+ ret = unuse_p4d_range(vma, pgd, addr, next, entry, page);
if (ret)
return ret;
} while (pgd++, addr = next, addr != end);
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 479e631..8bcb501 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -128,19 +128,22 @@ static int mfill_zeropage_pte(struct mm_struct *dst_mm,
static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address)
{
pgd_t *pgd;
+ p4d_t *p4d;
pud_t *pud;
- pmd_t *pmd = NULL;
pgd = pgd_offset(mm, address);
- pud = pud_alloc(mm, pgd, address);
- if (pud)
- /*
- * Note that we didn't run this because the pmd was
- * missing, the *pmd may be already established and in
- * turn it may also be a trans_huge_pmd.
- */
- pmd = pmd_alloc(mm, pud, address);
- return pmd;
+ p4d = p4d_alloc(mm, pgd, address);
+ if (!p4d)
+ return NULL;
+ pud = pud_alloc(mm, p4d, address);
+ if (!pud)
+ return NULL;
+ /*
+ * Note that we didn't run this because the pmd was
+ * missing, the *pmd may be already established and in
+ * turn it may also be a trans_huge_pmd.
+ */
+ return pmd_alloc(mm, pud, address);
}
#ifdef CONFIG_HUGETLB_PAGE
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index b4024d6..0b05762 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -86,12 +86,12 @@ static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end)
} while (pmd++, addr = next, addr != end);
}
-static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end)
+static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end)
{
pud_t *pud;
unsigned long next;
- pud = pud_offset(pgd, addr);
+ pud = pud_offset(p4d, addr);
do {
next = pud_addr_end(addr, end);
if (pud_clear_huge(pud))
@@ -102,6 +102,22 @@ static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end)
} while (pud++, addr = next, addr != end);
}
+static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end)
+{
+ p4d_t *p4d;
+ unsigned long next;
+
+ p4d = p4d_offset(pgd, addr);
+ do {
+ next = p4d_addr_end(addr, end);
+ if (p4d_clear_huge(p4d))
+ continue;
+ if (p4d_none_or_clear_bad(p4d))
+ continue;
+ vunmap_pud_range(p4d, addr, next);
+ } while (p4d++, addr = next, addr != end);
+}
+
static void vunmap_page_range(unsigned long addr, unsigned long end)
{
pgd_t *pgd;
@@ -113,7 +129,7 @@ static void vunmap_page_range(unsigned long addr, unsigned long end)
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
- vunmap_pud_range(pgd, addr, next);
+ vunmap_p4d_range(pgd, addr, next);
} while (pgd++, addr = next, addr != end);
}
@@ -160,13 +176,13 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr,
return 0;
}
-static int vmap_pud_range(pgd_t *pgd, unsigned long addr,
+static int vmap_pud_range(p4d_t *p4d, unsigned long addr,
unsigned long end, pgprot_t prot, struct page **pages, int *nr)
{
pud_t *pud;
unsigned long next;
- pud = pud_alloc(&init_mm, pgd, addr);
+ pud = pud_alloc(&init_mm, p4d, addr);
if (!pud)
return -ENOMEM;
do {
@@ -177,6 +193,23 @@ static int vmap_pud_range(pgd_t *pgd, unsigned long addr,
return 0;
}
+static int vmap_p4d_range(pgd_t *pgd, unsigned long addr,
+ unsigned long end, pgprot_t prot, struct page **pages, int *nr)
+{
+ p4d_t *p4d;
+ unsigned long next;
+
+ p4d = p4d_alloc(&init_mm, pgd, addr);
+ if (!p4d)
+ return -ENOMEM;
+ do {
+ next = p4d_addr_end(addr, end);
+ if (vmap_pud_range(p4d, addr, next, prot, pages, nr))
+ return -ENOMEM;
+ } while (p4d++, addr = next, addr != end);
+ return 0;
+}
+
/*
* Set up page tables in kva (addr, end). The ptes shall have prot "prot", and
* will have pfns corresponding to the "pages" array.
@@ -196,7 +229,7 @@ static int vmap_page_range_noflush(unsigned long start, unsigned long end,
pgd = pgd_offset_k(addr);
do {
next = pgd_addr_end(addr, end);
- err = vmap_pud_range(pgd, addr, next, prot, pages, &nr);
+ err = vmap_p4d_range(pgd, addr, next, prot, pages, &nr);
if (err)
return err;
} while (pgd++, addr = next, addr != end);
@@ -237,6 +270,10 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
unsigned long addr = (unsigned long) vmalloc_addr;
struct page *page = NULL;
pgd_t *pgd = pgd_offset_k(addr);
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *ptep, pte;
/*
* XXX we might need to change this if we add VIRTUAL_BUG_ON for
@@ -244,21 +281,23 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
*/
VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr));
- if (!pgd_none(*pgd)) {
- pud_t *pud = pud_offset(pgd, addr);
- if (!pud_none(*pud)) {
- pmd_t *pmd = pmd_offset(pud, addr);
- if (!pmd_none(*pmd)) {
- pte_t *ptep, pte;
+ if (pgd_none(*pgd))
+ return NULL;
+ p4d = p4d_offset(pgd, addr);
+ if (p4d_none(*p4d))
+ return NULL;
+ pud = pud_offset(p4d, addr);
+ if (pud_none(*pud))
+ return NULL;
+ pmd = pmd_offset(pud, addr);
+ if (pmd_none(*pmd))
+ return NULL;
- ptep = pte_offset_map(pmd, addr);
- pte = *ptep;
- if (pte_present(pte))
- page = pte_page(pte);
- pte_unmap(ptep);
- }
- }
- }
+ ptep = pte_offset_map(pmd, addr);
+ pte = *ptep;
+ if (pte_present(pte))
+ page = pte_page(pte);
+ pte_unmap(ptep);
return page;
}
EXPORT_SYMBOL(vmalloc_to_page);
@@ -1644,7 +1683,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
if (fatal_signal_pending(current)) {
area->nr_pages = i;
- goto fail;
+ goto fail_no_warn;
}
if (node == NUMA_NO_NODE)
@@ -1670,6 +1709,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
warn_alloc(gfp_mask, NULL,
"vmalloc: allocation failure, allocated %ld of %ld bytes",
(area->nr_pages*PAGE_SIZE), area->size);
+fail_no_warn:
vfree(area->addr);
return NULL;
}
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 69f9aff..89f9539 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1065,6 +1065,9 @@ const char * const vmstat_text[] = {
"thp_split_page_failed",
"thp_deferred_split_page",
"thp_split_pmd",
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+ "thp_split_pud",
+#endif
"thp_zero_page_alloc",
"thp_zero_page_alloc_failed",
#endif
@@ -1761,7 +1764,7 @@ static int vmstat_cpu_dead(unsigned int cpu)
#endif
-static int __init setup_vmstat(void)
+void __init init_mm_internals(void)
{
#ifdef CONFIG_SMP
int ret;
@@ -1789,9 +1792,7 @@ static int __init setup_vmstat(void)
proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations);
proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations);
#endif
- return 0;
}
-module_init(setup_vmstat)
#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION)
diff --git a/mm/workingset.c b/mm/workingset.c
index ac839fc..eda05c7 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -532,7 +532,7 @@ static int __init workingset_init(void)
pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n",
timestamp_bits, max_order, bucket_order);
- ret = list_lru_init_key(&shadow_nodes, &shadow_nodes_key);
+ ret = __list_lru_init(&shadow_nodes, true, &shadow_nodes_key);
if (ret)
goto err;
ret = register_shrinker(&workingset_shadow_shrinker);
diff --git a/mm/z3fold.c b/mm/z3fold.c
index 8970a2f..f9492bc 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -667,6 +667,7 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
z3fold_page_unlock(zhdr);
spin_lock(&pool->lock);
if (kref_put(&zhdr->refcount, release_z3fold_page)) {
+ spin_unlock(&pool->lock);
atomic64_dec(&pool->pages_nr);
return 0;
}
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index e97ab82..9ee5787 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -562,8 +562,7 @@ static int vlan_dev_init(struct net_device *dev)
NETIF_F_HIGHDMA | NETIF_F_SCTP_CRC |
NETIF_F_ALL_FCOE;
- dev->features |= real_dev->vlan_features | NETIF_F_LLTX |
- NETIF_F_GSO_SOFTWARE;
+ dev->features |= dev->hw_features | NETIF_F_LLTX;
dev->gso_max_size = real_dev->gso_max_size;
dev->gso_max_segs = real_dev->gso_max_segs;
if (dev->features & NETIF_F_VLAN_FEATURES)
diff --git a/net/Makefile b/net/Makefile
index 9b681550..9086ffb 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -12,7 +12,7 @@
# LLC has to be linked before the files in net/802/
obj-$(CONFIG_LLC) += llc/
-obj-$(CONFIG_NET) += ethernet/ 802/ sched/ netlink/
+obj-$(CONFIG_NET) += ethernet/ 802/ sched/ netlink/ bpf/
obj-$(CONFIG_NETFILTER) += netfilter/
obj-$(CONFIG_INET) += ipv4/
obj-$(CONFIG_XFRM) += xfrm/
diff --git a/net/atm/clip.c b/net/atm/clip.c
index 53b4ac0..ec527b6 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -106,7 +106,7 @@ static void unlink_clip_vcc(struct clip_vcc *clip_vcc)
entry->expires = jiffies - 1;
/* force resolution or expiration */
error = neigh_update(entry->neigh, NULL, NUD_NONE,
- NEIGH_UPDATE_F_ADMIN);
+ NEIGH_UPDATE_F_ADMIN, 0);
if (error)
pr_crit("neigh_update failed with %d\n", error);
goto out;
@@ -481,7 +481,7 @@ static int clip_setentry(struct atm_vcc *vcc, __be32 ip)
link_vcc(clip_vcc, entry);
}
error = neigh_update(neigh, llc_oui, NUD_PERMANENT,
- NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN);
+ NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN, 0);
neigh_release(neigh);
return error;
}
diff --git a/net/atm/common.c b/net/atm/common.c
index 9613381..f06422f 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -62,21 +62,16 @@ static void vcc_remove_socket(struct sock *sk)
write_unlock_irq(&vcc_sklist_lock);
}
-static struct sk_buff *alloc_tx(struct atm_vcc *vcc, unsigned int size)
+static bool vcc_tx_ready(struct atm_vcc *vcc, unsigned int size)
{
- struct sk_buff *skb;
struct sock *sk = sk_atm(vcc);
if (sk_wmem_alloc_get(sk) && !atm_may_send(vcc, size)) {
pr_debug("Sorry: wmem_alloc = %d, size = %d, sndbuf = %d\n",
sk_wmem_alloc_get(sk), size, sk->sk_sndbuf);
- return NULL;
+ return false;
}
- while (!(skb = alloc_skb(size, GFP_KERNEL)))
- schedule();
- pr_debug("%d += %d\n", sk_wmem_alloc_get(sk), skb->truesize);
- atomic_add(skb->truesize, &sk->sk_wmem_alloc);
- return skb;
+ return true;
}
static void vcc_sock_destruct(struct sock *sk)
@@ -606,7 +601,7 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size)
eff = (size+3) & ~3; /* align to word boundary */
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
error = 0;
- while (!(skb = alloc_tx(vcc, eff))) {
+ while (!vcc_tx_ready(vcc, eff)) {
if (m->msg_flags & MSG_DONTWAIT) {
error = -EAGAIN;
break;
@@ -628,6 +623,15 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size)
finish_wait(sk_sleep(sk), &wait);
if (error)
goto out;
+
+ skb = alloc_skb(eff, GFP_KERNEL);
+ if (!skb) {
+ error = -ENOMEM;
+ goto out;
+ }
+ pr_debug("%d += %d\n", sk_wmem_alloc_get(sk), skb->truesize);
+ atomic_add(skb->truesize, &sk->sk_wmem_alloc);
+
skb->dev = NULL; /* for paths shared with net_device interfaces */
ATM_SKB(skb)->atm_options = vcc->atm_options;
if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) {
diff --git a/net/atm/svc.c b/net/atm/svc.c
index db9794e..5589de7 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -318,7 +318,8 @@ static int svc_listen(struct socket *sock, int backlog)
return error;
}
-static int svc_accept(struct socket *sock, struct socket *newsock, int flags)
+static int svc_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sock *sk = sock->sk;
struct sk_buff *skb;
@@ -329,7 +330,7 @@ static int svc_accept(struct socket *sock, struct socket *newsock, int flags)
lock_sock(sk);
- error = svc_create(sock_net(sk), newsock, 0, 0);
+ error = svc_create(sock_net(sk), newsock, 0, kern);
if (error)
goto out;
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index a8e42ce..b7c4867 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1320,7 +1320,8 @@ static int __must_check ax25_connect(struct socket *sock,
return err;
}
-static int ax25_accept(struct socket *sock, struct socket *newsock, int flags)
+static int ax25_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sk_buff *skb;
struct sock *newsk;
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 7c3d994e..495ba7c 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -679,15 +679,11 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff,
{
struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
struct batadv_forw_packet *forw_packet_aggr;
+ struct sk_buff *skb;
unsigned char *skb_buff;
unsigned int skb_size;
atomic_t *queue_left = own_packet ? NULL : &bat_priv->batman_queue_left;
- forw_packet_aggr = batadv_forw_packet_alloc(if_incoming, if_outgoing,
- queue_left, bat_priv);
- if (!forw_packet_aggr)
- return;
-
if (atomic_read(&bat_priv->aggregated_ogms) &&
packet_len < BATADV_MAX_AGGREGATION_BYTES)
skb_size = BATADV_MAX_AGGREGATION_BYTES;
@@ -696,9 +692,14 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff,
skb_size += ETH_HLEN;
- forw_packet_aggr->skb = netdev_alloc_skb_ip_align(NULL, skb_size);
- if (!forw_packet_aggr->skb) {
- batadv_forw_packet_free(forw_packet_aggr, true);
+ skb = netdev_alloc_skb_ip_align(NULL, skb_size);
+ if (!skb)
+ return;
+
+ forw_packet_aggr = batadv_forw_packet_alloc(if_incoming, if_outgoing,
+ queue_left, bat_priv, skb);
+ if (!forw_packet_aggr) {
+ kfree_skb(skb);
return;
}
@@ -2477,6 +2478,16 @@ static void batadv_iv_iface_activate(struct batadv_hard_iface *hard_iface)
batadv_iv_ogm_schedule(hard_iface);
}
+/**
+ * batadv_iv_init_sel_class - initialize GW selection class
+ * @bat_priv: the bat priv with all the soft interface information
+ */
+static void batadv_iv_init_sel_class(struct batadv_priv *bat_priv)
+{
+ /* set default TQ difference threshold to 20 */
+ atomic_set(&bat_priv->gw.sel_class, 20);
+}
+
static struct batadv_gw_node *
batadv_iv_gw_get_best_gw_node(struct batadv_priv *bat_priv)
{
@@ -2823,6 +2834,7 @@ static struct batadv_algo_ops batadv_batman_iv __read_mostly = {
.del_if = batadv_iv_ogm_orig_del_if,
},
.gw = {
+ .init_sel_class = batadv_iv_init_sel_class,
.get_best_gw_node = batadv_iv_gw_get_best_gw_node,
.is_eligible = batadv_iv_gw_is_eligible,
#ifdef CONFIG_BATMAN_ADV_DEBUGFS
diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c
index 0acd081..a36c8e7 100644
--- a/net/batman-adv/bat_v.c
+++ b/net/batman-adv/bat_v.c
@@ -668,6 +668,16 @@ static bool batadv_v_neigh_is_sob(struct batadv_neigh_node *neigh1,
return ret;
}
+/**
+ * batadv_v_init_sel_class - initialize GW selection class
+ * @bat_priv: the bat priv with all the soft interface information
+ */
+static void batadv_v_init_sel_class(struct batadv_priv *bat_priv)
+{
+ /* set default throughput difference threshold to 5Mbps */
+ atomic_set(&bat_priv->gw.sel_class, 50);
+}
+
static ssize_t batadv_v_store_sel_class(struct batadv_priv *bat_priv,
char *buff, size_t count)
{
@@ -1052,6 +1062,7 @@ static struct batadv_algo_ops batadv_batman_v __read_mostly = {
.dump = batadv_v_orig_dump,
},
.gw = {
+ .init_sel_class = batadv_v_init_sel_class,
.store_sel_class = batadv_v_store_sel_class,
.show_sel_class = batadv_v_show_sel_class,
.get_best_gw_node = batadv_v_gw_get_best_gw_node,
@@ -1092,9 +1103,6 @@ int batadv_v_mesh_init(struct batadv_priv *bat_priv)
if (ret < 0)
return ret;
- /* set default throughput difference threshold to 5Mbps */
- atomic_set(&bat_priv->gw.sel_class, 50);
-
return 0;
}
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index ba8420d..d07e89e 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -395,7 +395,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac,
ether_addr_copy(ethhdr->h_source, mac);
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"bla_send_claim(): CLAIM %pM on vid %d\n", mac,
- BATADV_PRINT_VID(vid));
+ batadv_print_vid(vid));
break;
case BATADV_CLAIM_TYPE_UNCLAIM:
/* unclaim frame
@@ -404,7 +404,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac,
ether_addr_copy(hw_src, mac);
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"bla_send_claim(): UNCLAIM %pM on vid %d\n", mac,
- BATADV_PRINT_VID(vid));
+ batadv_print_vid(vid));
break;
case BATADV_CLAIM_TYPE_ANNOUNCE:
/* announcement frame
@@ -413,7 +413,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac,
ether_addr_copy(hw_src, mac);
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"bla_send_claim(): ANNOUNCE of %pM on vid %d\n",
- ethhdr->h_source, BATADV_PRINT_VID(vid));
+ ethhdr->h_source, batadv_print_vid(vid));
break;
case BATADV_CLAIM_TYPE_REQUEST:
/* request frame
@@ -425,14 +425,14 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac,
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"bla_send_claim(): REQUEST of %pM to %pM on vid %d\n",
ethhdr->h_source, ethhdr->h_dest,
- BATADV_PRINT_VID(vid));
+ batadv_print_vid(vid));
break;
case BATADV_CLAIM_TYPE_LOOPDETECT:
ether_addr_copy(ethhdr->h_source, mac);
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"bla_send_claim(): LOOPDETECT of %pM to %pM on vid %d\n",
ethhdr->h_source, ethhdr->h_dest,
- BATADV_PRINT_VID(vid));
+ batadv_print_vid(vid));
break;
}
@@ -475,9 +475,9 @@ static void batadv_bla_loopdetect_report(struct work_struct *work)
batadv_info(bat_priv->soft_iface,
"Possible loop on VLAN %d detected which can't be handled by BLA - please check your network setup!\n",
- BATADV_PRINT_VID(backbone_gw->vid));
+ batadv_print_vid(backbone_gw->vid));
snprintf(vid_str, sizeof(vid_str), "%d",
- BATADV_PRINT_VID(backbone_gw->vid));
+ batadv_print_vid(backbone_gw->vid));
vid_str[sizeof(vid_str) - 1] = 0;
batadv_throw_uevent(bat_priv, BATADV_UEV_BLA, BATADV_UEV_LOOPDETECT,
@@ -510,7 +510,7 @@ batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, u8 *orig,
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"bla_get_backbone_gw(): not found (%pM, %d), creating new entry\n",
- orig, BATADV_PRINT_VID(vid));
+ orig, batadv_print_vid(vid));
entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
if (!entry)
@@ -719,7 +719,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv,
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"bla_add_claim(): adding new entry %pM, vid %d to hash ...\n",
- mac, BATADV_PRINT_VID(vid));
+ mac, batadv_print_vid(vid));
kref_get(&claim->refcount);
hash_added = batadv_hash_add(bat_priv->bla.claim_hash,
@@ -739,8 +739,8 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv,
goto claim_free_ref;
batadv_dbg(BATADV_DBG_BLA, bat_priv,
- "bla_add_claim(): changing ownership for %pM, vid %d\n",
- mac, BATADV_PRINT_VID(vid));
+ "bla_add_claim(): changing ownership for %pM, vid %d to gw %pM\n",
+ mac, batadv_print_vid(vid), backbone_gw->orig);
remove_crc = true;
}
@@ -809,7 +809,7 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv,
return;
batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_del_claim(): %pM, vid %d\n",
- mac, BATADV_PRINT_VID(vid));
+ mac, batadv_print_vid(vid));
batadv_hash_remove(bat_priv->bla.claim_hash, batadv_compare_claim,
batadv_choose_claim, claim);
@@ -849,7 +849,7 @@ static bool batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr,
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"handle_announce(): ANNOUNCE vid %d (sent by %pM)... CRC = %#.4x\n",
- BATADV_PRINT_VID(vid), backbone_gw->orig, crc);
+ batadv_print_vid(vid), backbone_gw->orig, crc);
spin_lock_bh(&backbone_gw->crc_lock);
backbone_crc = backbone_gw->crc;
@@ -859,7 +859,7 @@ static bool batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr,
batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv,
"handle_announce(): CRC FAILED for %pM/%d (my = %#.4x, sent = %#.4x)\n",
backbone_gw->orig,
- BATADV_PRINT_VID(backbone_gw->vid),
+ batadv_print_vid(backbone_gw->vid),
backbone_crc, crc);
batadv_bla_send_request(backbone_gw);
@@ -904,7 +904,7 @@ static bool batadv_handle_request(struct batadv_priv *bat_priv,
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"handle_request(): REQUEST vid %d (sent by %pM)...\n",
- BATADV_PRINT_VID(vid), ethhdr->h_source);
+ batadv_print_vid(vid), ethhdr->h_source);
batadv_bla_answer_request(bat_priv, primary_if, vid);
return true;
@@ -941,7 +941,7 @@ static bool batadv_handle_unclaim(struct batadv_priv *bat_priv,
/* this must be an UNCLAIM frame */
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"handle_unclaim(): UNCLAIM %pM on vid %d (sent by %pM)...\n",
- claim_addr, BATADV_PRINT_VID(vid), backbone_gw->orig);
+ claim_addr, batadv_print_vid(vid), backbone_gw->orig);
batadv_bla_del_claim(bat_priv, claim_addr, vid);
batadv_backbone_gw_put(backbone_gw);
@@ -1161,7 +1161,7 @@ static bool batadv_bla_process_claim(struct batadv_priv *bat_priv,
if (ret == 1)
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"bla_process_claim(): received a claim frame from another group. From: %pM on vid %d ...(hw_src %pM, hw_dst %pM)\n",
- ethhdr->h_source, BATADV_PRINT_VID(vid), hw_src,
+ ethhdr->h_source, batadv_print_vid(vid), hw_src,
hw_dst);
if (ret < 2)
@@ -1197,7 +1197,7 @@ static bool batadv_bla_process_claim(struct batadv_priv *bat_priv,
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"bla_process_claim(): ERROR - this looks like a claim frame, but is useless. eth src %pM on vid %d ...(hw_src %pM, hw_dst %pM)\n",
- ethhdr->h_source, BATADV_PRINT_VID(vid), hw_src, hw_dst);
+ ethhdr->h_source, batadv_print_vid(vid), hw_src, hw_dst);
return true;
}
@@ -1295,10 +1295,13 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv,
goto skip;
batadv_dbg(BATADV_DBG_BLA, bat_priv,
- "bla_purge_claims(): %pM, vid %d, time out\n",
- claim->addr, claim->vid);
+ "bla_purge_claims(): timed out.\n");
purge_now:
+ batadv_dbg(BATADV_DBG_BLA, bat_priv,
+ "bla_purge_claims(): %pM, vid %d\n",
+ claim->addr, claim->vid);
+
batadv_handle_unclaim(bat_priv, primary_if,
backbone_gw->orig,
claim->addr, claim->vid);
@@ -1846,6 +1849,13 @@ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb,
/* possible optimization: race for a claim */
/* No claim exists yet, claim it for us!
*/
+
+ batadv_dbg(BATADV_DBG_BLA, bat_priv,
+ "bla_rx(): Unclaimed MAC %pM found. Claim it. Local: %s\n",
+ ethhdr->h_source,
+ batadv_is_my_client(bat_priv,
+ ethhdr->h_source, vid) ?
+ "yes" : "no");
batadv_handle_claim(bat_priv, primary_if,
primary_if->net_dev->dev_addr,
ethhdr->h_source, vid);
@@ -1963,10 +1973,22 @@ bool batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb,
/* if yes, the client has roamed and we have
* to unclaim it.
*/
- batadv_handle_unclaim(bat_priv, primary_if,
- primary_if->net_dev->dev_addr,
- ethhdr->h_source, vid);
- goto allow;
+ if (batadv_has_timed_out(claim->lasttime, 100)) {
+ /* only unclaim if the last claim entry is
+ * older than 100 ms to make sure we really
+ * have a roaming client here.
+ */
+ batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_tx(): Roaming client %pM detected. Unclaim it.\n",
+ ethhdr->h_source);
+ batadv_handle_unclaim(bat_priv, primary_if,
+ primary_if->net_dev->dev_addr,
+ ethhdr->h_source, vid);
+ goto allow;
+ } else {
+ batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_tx(): Race for claim %pM detected. Drop packet.\n",
+ ethhdr->h_source);
+ goto handled;
+ }
}
/* check if it is a multicast/broadcast frame */
@@ -2042,7 +2064,7 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset)
backbone_crc = backbone_gw->crc;
spin_unlock_bh(&backbone_gw->crc_lock);
seq_printf(seq, " * %pM on %5d by %pM [%c] (%#.4x)\n",
- claim->addr, BATADV_PRINT_VID(claim->vid),
+ claim->addr, batadv_print_vid(claim->vid),
backbone_gw->orig,
(is_own ? 'x' : ' '),
backbone_crc);
@@ -2274,7 +2296,7 @@ int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset)
seq_printf(seq, " * %pM on %5d %4i.%03is (%#.4x)\n",
backbone_gw->orig,
- BATADV_PRINT_VID(backbone_gw->vid), secs,
+ batadv_print_vid(backbone_gw->vid), secs,
msecs, backbone_crc);
}
rcu_read_unlock();
@@ -2449,3 +2471,52 @@ int batadv_bla_backbone_dump(struct sk_buff *msg, struct netlink_callback *cb)
return ret;
}
+
+#ifdef CONFIG_BATMAN_ADV_DAT
+/**
+ * batadv_bla_check_claim - check if address is claimed
+ *
+ * @bat_priv: the bat priv with all the soft interface information
+ * @addr: mac address of which the claim status is checked
+ * @vid: the VLAN ID
+ *
+ * addr is checked if this address is claimed by the local device itself.
+ *
+ * Return: true if bla is disabled or the mac is claimed by the device,
+ * false if the device addr is already claimed by another gateway
+ */
+bool batadv_bla_check_claim(struct batadv_priv *bat_priv,
+ u8 *addr, unsigned short vid)
+{
+ struct batadv_bla_claim search_claim;
+ struct batadv_bla_claim *claim = NULL;
+ struct batadv_hard_iface *primary_if = NULL;
+ bool ret = true;
+
+ if (!atomic_read(&bat_priv->bridge_loop_avoidance))
+ return ret;
+
+ primary_if = batadv_primary_if_get_selected(bat_priv);
+ if (!primary_if)
+ return ret;
+
+ /* First look if the mac address is claimed */
+ ether_addr_copy(search_claim.addr, addr);
+ search_claim.vid = vid;
+
+ claim = batadv_claim_hash_find(bat_priv, &search_claim);
+
+ /* If there is a claim and we are not owner of the claim,
+ * return false.
+ */
+ if (claim) {
+ if (!batadv_compare_eth(claim->backbone_gw->orig,
+ primary_if->net_dev->dev_addr))
+ ret = false;
+ batadv_claim_put(claim);
+ }
+
+ batadv_hardif_put(primary_if);
+ return ret;
+}
+#endif
diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h
index e157986..2347757 100644
--- a/net/batman-adv/bridge_loop_avoidance.h
+++ b/net/batman-adv/bridge_loop_avoidance.h
@@ -69,6 +69,10 @@ void batadv_bla_status_update(struct net_device *net_dev);
int batadv_bla_init(struct batadv_priv *bat_priv);
void batadv_bla_free(struct batadv_priv *bat_priv);
int batadv_bla_claim_dump(struct sk_buff *msg, struct netlink_callback *cb);
+#ifdef CONFIG_BATMAN_ADV_DAT
+bool batadv_bla_check_claim(struct batadv_priv *bat_priv, u8 *addr,
+ unsigned short vid);
+#endif
#define BATADV_BLA_CRC_INIT 0
#else /* ifdef CONFIG_BATMAN_ADV_BLA */
@@ -145,6 +149,13 @@ static inline int batadv_bla_backbone_dump(struct sk_buff *msg,
return -EOPNOTSUPP;
}
+static inline
+bool batadv_bla_check_claim(struct batadv_priv *bat_priv, u8 *addr,
+ unsigned short vid)
+{
+ return true;
+}
+
#endif /* ifdef CONFIG_BATMAN_ADV_BLA */
#endif /* ifndef _NET_BATMAN_ADV_BLA_H_ */
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index 1bfd1db..013e970 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -43,6 +43,7 @@
#include <linux/workqueue.h>
#include <net/arp.h>
+#include "bridge_loop_avoidance.h"
#include "hard-interface.h"
#include "hash.h"
#include "log.h"
@@ -330,7 +331,7 @@ static void batadv_dat_entry_add(struct batadv_priv *bat_priv, __be32 ip,
batadv_dbg(BATADV_DBG_DAT, bat_priv,
"Entry updated: %pI4 %pM (vid: %d)\n",
&dat_entry->ip, dat_entry->mac_addr,
- BATADV_PRINT_VID(vid));
+ batadv_print_vid(vid));
goto out;
}
@@ -356,7 +357,7 @@ static void batadv_dat_entry_add(struct batadv_priv *bat_priv, __be32 ip,
}
batadv_dbg(BATADV_DBG_DAT, bat_priv, "New entry added: %pI4 %pM (vid: %d)\n",
- &dat_entry->ip, dat_entry->mac_addr, BATADV_PRINT_VID(vid));
+ &dat_entry->ip, dat_entry->mac_addr, batadv_print_vid(vid));
out:
if (dat_entry)
@@ -835,7 +836,7 @@ int batadv_dat_cache_seq_print_text(struct seq_file *seq, void *offset)
seq_printf(seq, " * %15pI4 %14pM %4i %6i:%02i\n",
&dat_entry->ip, dat_entry->mac_addr,
- BATADV_PRINT_VID(dat_entry->vid),
+ batadv_print_vid(dat_entry->vid),
last_seen_mins, last_seen_secs);
}
rcu_read_unlock();
@@ -1002,6 +1003,7 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
bool ret = false;
struct batadv_dat_entry *dat_entry = NULL;
struct sk_buff *skb_new;
+ struct net_device *soft_iface = bat_priv->soft_iface;
int hdr_size = 0;
unsigned short vid;
@@ -1040,16 +1042,30 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
goto out;
}
+ /* If BLA is enabled, only send ARP replies if we have claimed
+ * the destination for the ARP request or if no one else of
+ * the backbone gws belonging to our backbone has claimed the
+ * destination.
+ */
+ if (!batadv_bla_check_claim(bat_priv,
+ dat_entry->mac_addr, vid)) {
+ batadv_dbg(BATADV_DBG_DAT, bat_priv,
+ "Device %pM claimed by another backbone gw. Don't send ARP reply!",
+ dat_entry->mac_addr);
+ ret = true;
+ goto out;
+ }
+
skb_new = batadv_dat_arp_create_reply(bat_priv, ip_dst, ip_src,
dat_entry->mac_addr,
hw_src, vid);
if (!skb_new)
goto out;
- skb_new->protocol = eth_type_trans(skb_new,
- bat_priv->soft_iface);
- bat_priv->stats.rx_packets++;
- bat_priv->stats.rx_bytes += skb->len + ETH_HLEN + hdr_size;
+ skb_new->protocol = eth_type_trans(skb_new, soft_iface);
+
+ soft_iface->stats.rx_packets++;
+ soft_iface->stats.rx_bytes += skb->len + ETH_HLEN + hdr_size;
netif_rx(skb_new);
batadv_dbg(BATADV_DBG_DAT, bat_priv, "ARP request replied locally\n");
@@ -1188,6 +1204,7 @@ void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv,
bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv,
struct sk_buff *skb, int hdr_size)
{
+ struct batadv_dat_entry *dat_entry = NULL;
u16 type;
__be32 ip_src, ip_dst;
u8 *hw_src, *hw_dst;
@@ -1210,12 +1227,41 @@ bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv,
hw_dst = batadv_arp_hw_dst(skb, hdr_size);
ip_dst = batadv_arp_ip_dst(skb, hdr_size);
+ /* If ip_dst is already in cache and has the right mac address,
+ * drop this frame if this ARP reply is destined for us because it's
+ * most probably an ARP reply generated by another node of the DHT.
+ * We have most probably received already a reply earlier. Delivering
+ * this frame would lead to doubled receive of an ARP reply.
+ */
+ dat_entry = batadv_dat_entry_hash_find(bat_priv, ip_src, vid);
+ if (dat_entry && batadv_compare_eth(hw_src, dat_entry->mac_addr)) {
+ batadv_dbg(BATADV_DBG_DAT, bat_priv, "Doubled ARP reply removed: ARP MSG = [src: %pM-%pI4 dst: %pM-%pI4]; dat_entry: %pM-%pI4\n",
+ hw_src, &ip_src, hw_dst, &ip_dst,
+ dat_entry->mac_addr, &dat_entry->ip);
+ dropped = true;
+ goto out;
+ }
+
/* Update our internal cache with both the IP addresses the node got
* within the ARP reply
*/
batadv_dat_entry_add(bat_priv, ip_src, hw_src, vid);
batadv_dat_entry_add(bat_priv, ip_dst, hw_dst, vid);
+ /* If BLA is enabled, only forward ARP replies if we have claimed the
+ * source of the ARP reply or if no one else of the same backbone has
+ * already claimed that client. This prevents that different gateways
+ * to the same backbone all forward the ARP reply leading to multiple
+ * replies in the backbone.
+ */
+ if (!batadv_bla_check_claim(bat_priv, hw_src, vid)) {
+ batadv_dbg(BATADV_DBG_DAT, bat_priv,
+ "Device %pM claimed by another backbone gw. Drop ARP reply.\n",
+ hw_src);
+ dropped = true;
+ goto out;
+ }
+
/* if this REPLY is directed to a client of mine, let's deliver the
* packet to the interface
*/
@@ -1228,6 +1274,8 @@ bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv,
out:
if (dropped)
kfree_skb(skb);
+ if (dat_entry)
+ batadv_dat_entry_put(dat_entry);
/* if dropped == false -> deliver to the interface */
return dropped;
}
@@ -1256,7 +1304,7 @@ bool batadv_dat_drop_broadcast_packet(struct batadv_priv *bat_priv,
/* If this packet is an ARP_REQUEST and the node already has the
* information that it is going to ask, then the packet can be dropped
*/
- if (forw_packet->num_packets)
+ if (batadv_forw_packet_is_rebroadcast(forw_packet))
goto out;
vid = batadv_dat_get_vid(forw_packet->skb, &hdr_size);
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index 11a23fd..8f964be 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -404,7 +404,7 @@ bool batadv_frag_skb_fwd(struct sk_buff *skb,
* batadv_frag_create - create a fragment from skb
* @skb: skb to create fragment from
* @frag_head: header to use in new fragment
- * @mtu: size of new fragment
+ * @fragment_size: size of new fragment
*
* Split the passed skb into two fragments: A new one with size matching the
* passed mtu and the old one with the rest. The new skb contains data from the
@@ -414,11 +414,11 @@ bool batadv_frag_skb_fwd(struct sk_buff *skb,
*/
static struct sk_buff *batadv_frag_create(struct sk_buff *skb,
struct batadv_frag_packet *frag_head,
- unsigned int mtu)
+ unsigned int fragment_size)
{
struct sk_buff *skb_fragment;
unsigned int header_size = sizeof(*frag_head);
- unsigned int fragment_size = mtu - header_size;
+ unsigned int mtu = fragment_size + header_size;
skb_fragment = netdev_alloc_skb(NULL, mtu + ETH_HLEN);
if (!skb_fragment)
@@ -456,7 +456,7 @@ int batadv_frag_send_packet(struct sk_buff *skb,
struct sk_buff *skb_fragment;
unsigned int mtu = neigh_node->if_incoming->net_dev->mtu;
unsigned int header_size = sizeof(frag_header);
- unsigned int max_fragment_size, max_packet_size;
+ unsigned int max_fragment_size, num_fragments;
int ret;
/* To avoid merge and refragmentation at next-hops we never send
@@ -464,10 +464,15 @@ int batadv_frag_send_packet(struct sk_buff *skb,
*/
mtu = min_t(unsigned int, mtu, BATADV_FRAG_MAX_FRAG_SIZE);
max_fragment_size = mtu - header_size;
- max_packet_size = max_fragment_size * BATADV_FRAG_MAX_FRAGMENTS;
+
+ if (skb->len == 0 || max_fragment_size == 0)
+ return -EINVAL;
+
+ num_fragments = (skb->len - 1) / max_fragment_size + 1;
+ max_fragment_size = (skb->len - 1) / num_fragments + 1;
/* Don't even try to fragment, if we need more than 16 fragments */
- if (skb->len > max_packet_size) {
+ if (num_fragments > BATADV_FRAG_MAX_FRAGMENTS) {
ret = -EAGAIN;
goto free_skb;
}
@@ -507,7 +512,8 @@ int batadv_frag_send_packet(struct sk_buff *skb,
goto put_primary_if;
}
- skb_fragment = batadv_frag_create(skb, &frag_header, mtu);
+ skb_fragment = batadv_frag_create(skb, &frag_header,
+ max_fragment_size);
if (!skb_fragment) {
ret = -ENOMEM;
goto put_primary_if;
diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c
index 5db2e43..33940c5 100644
--- a/net/batman-adv/gateway_common.c
+++ b/net/batman-adv/gateway_common.c
@@ -253,6 +253,11 @@ static void batadv_gw_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
*/
void batadv_gw_init(struct batadv_priv *bat_priv)
{
+ if (bat_priv->algo_ops->gw.init_sel_class)
+ bat_priv->algo_ops->gw.init_sel_class(bat_priv);
+ else
+ atomic_set(&bat_priv->gw.sel_class, 1);
+
batadv_tvlv_handler_register(bat_priv, batadv_gw_tvlv_ogm_handler_v1,
NULL, BATADV_TVLV_GW, 1,
BATADV_TVLV_HANDLER_OGM_CIFNOTFND);
diff --git a/net/batman-adv/log.h b/net/batman-adv/log.h
index 7a2b9f4..65ce97e 100644
--- a/net/batman-adv/log.h
+++ b/net/batman-adv/log.h
@@ -73,9 +73,10 @@ __printf(2, 3);
/* possibly ratelimited debug output */
#define _batadv_dbg(type, bat_priv, ratelimited, fmt, arg...) \
do { \
- if (atomic_read(&(bat_priv)->log_level) & (type) && \
+ struct batadv_priv *__batpriv = (bat_priv); \
+ if (atomic_read(&__batpriv->log_level) & (type) && \
(!(ratelimited) || net_ratelimit())) \
- batadv_debug_log(bat_priv, fmt, ## arg); \
+ batadv_debug_log(__batpriv, fmt, ## arg); \
} \
while (0)
#else /* !CONFIG_BATMAN_ADV_DEBUG */
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 5000c54..fb381fb 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -516,6 +516,9 @@ static void batadv_recv_handler_init(void)
BUILD_BUG_ON(sizeof(struct batadv_tvlv_tt_change) != 12);
BUILD_BUG_ON(sizeof(struct batadv_tvlv_roam_adv) != 8);
+ i = FIELD_SIZEOF(struct sk_buff, cb);
+ BUILD_BUG_ON(sizeof(struct batadv_skb_cb) > i);
+
/* broadcast packet */
batadv_rx_handler[BATADV_BCAST] = batadv_recv_bcast_packet;
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 57a8103..810f7d0 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -24,7 +24,7 @@
#define BATADV_DRIVER_DEVICE "batman-adv"
#ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2017.0"
+#define BATADV_SOURCE_VERSION "2017.1"
#endif
/* B.A.T.M.A.N. parameters */
@@ -193,6 +193,7 @@ enum batadv_uev_type {
#include <linux/percpu.h>
#include <linux/types.h>
+#include "packet.h"
#include "types.h"
struct net_device;
@@ -200,8 +201,19 @@ struct packet_type;
struct seq_file;
struct sk_buff;
-#define BATADV_PRINT_VID(vid) (((vid) & BATADV_VLAN_HAS_TAG) ? \
- (int)((vid) & VLAN_VID_MASK) : -1)
+/**
+ * batadv_print_vid - return printable version of vid information
+ * @vid: the VLAN identifier
+ *
+ * Return: -1 when no VLAN is used, VLAN id otherwise
+ */
+static inline int batadv_print_vid(unsigned short vid)
+{
+ if (vid & BATADV_VLAN_HAS_TAG)
+ return (int)(vid & VLAN_VID_MASK);
+ else
+ return -1;
+}
extern struct list_head batadv_hardif_list;
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index 952ba81..d327670 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -494,9 +494,8 @@ static bool batadv_mcast_mla_tvlv_update(struct batadv_priv *bat_priv)
if (!bridged)
goto update;
-#if !IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING)
- pr_warn_once("No bridge IGMP snooping compiled - multicast optimizations disabled\n");
-#endif
+ if (!IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING))
+ pr_warn_once("No bridge IGMP snooping compiled - multicast optimizations disabled\n");
querier4.exists = br_multicast_has_querier_anywhere(dev, ETH_P_IP);
querier4.shadowing = br_multicast_has_querier_adjacent(dev, ETH_P_IP);
@@ -671,7 +670,6 @@ static int batadv_mcast_forw_mode_check_ipv4(struct batadv_priv *bat_priv,
return 0;
}
-#if IS_ENABLED(CONFIG_IPV6)
/**
* batadv_mcast_is_report_ipv6 - check for MLD reports
* @skb: the ethernet frame destined for the mesh
@@ -736,7 +734,6 @@ static int batadv_mcast_forw_mode_check_ipv6(struct batadv_priv *bat_priv,
return 0;
}
-#endif
/**
* batadv_mcast_forw_mode_check - check for optimized forwarding potential
@@ -765,11 +762,12 @@ static int batadv_mcast_forw_mode_check(struct batadv_priv *bat_priv,
case ETH_P_IP:
return batadv_mcast_forw_mode_check_ipv4(bat_priv, skb,
is_unsnoopable);
-#if IS_ENABLED(CONFIG_IPV6)
case ETH_P_IPV6:
+ if (!IS_ENABLED(CONFIG_IPV6))
+ return -EINVAL;
+
return batadv_mcast_forw_mode_check_ipv6(bat_priv, skb,
is_unsnoopable);
-#endif
default:
return -EINVAL;
}
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index 7fd740b..e1ebe14 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -941,15 +941,17 @@ int batadv_recv_unicast_packet(struct sk_buff *skb,
struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface);
struct batadv_unicast_packet *unicast_packet;
struct batadv_unicast_4addr_packet *unicast_4addr_packet;
- u8 *orig_addr;
- struct batadv_orig_node *orig_node = NULL;
+ u8 *orig_addr, *orig_addr_gw;
+ struct batadv_orig_node *orig_node = NULL, *orig_node_gw = NULL;
int check, hdr_size = sizeof(*unicast_packet);
enum batadv_subtype subtype;
- bool is4addr;
+ struct ethhdr *ethhdr;
int ret = NET_RX_DROP;
+ bool is4addr, is_gw;
unicast_packet = (struct batadv_unicast_packet *)skb->data;
unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data;
+ ethhdr = eth_hdr(skb);
is4addr = unicast_packet->packet_type == BATADV_UNICAST_4ADDR;
/* the caller function should have already pulled 2 bytes */
@@ -972,6 +974,23 @@ int batadv_recv_unicast_packet(struct sk_buff *skb,
/* packet for me */
if (batadv_is_my_mac(bat_priv, unicast_packet->dest)) {
+ /* If this is a unicast packet from another backgone gw,
+ * drop it.
+ */
+ orig_addr_gw = ethhdr->h_source;
+ orig_node_gw = batadv_orig_hash_find(bat_priv, orig_addr_gw);
+ if (orig_node_gw) {
+ is_gw = batadv_bla_is_backbone_gw(skb, orig_node_gw,
+ hdr_size);
+ batadv_orig_node_put(orig_node_gw);
+ if (is_gw) {
+ batadv_dbg(BATADV_DBG_BLA, bat_priv,
+ "recv_unicast_packet(): Dropped unicast pkt received from another backbone gw %pM.\n",
+ orig_addr_gw);
+ return NET_RX_DROP;
+ }
+ }
+
if (is4addr) {
subtype = unicast_4addr_packet->subtype;
batadv_dat_inc_counter(bat_priv, subtype);
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index 1489ec2..403df59 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -482,6 +482,7 @@ void batadv_forw_packet_free(struct batadv_forw_packet *forw_packet,
* @if_outgoing: The (optional) if_outgoing to be grabbed
* @queue_left: The (optional) queue counter to decrease
* @bat_priv: The bat_priv for the mesh of this forw_packet
+ * @skb: The raw packet this forwarding packet shall contain
*
* Allocates a forwarding packet and tries to get a reference to the
* (optional) if_incoming, if_outgoing and queue_left. If queue_left
@@ -493,7 +494,8 @@ struct batadv_forw_packet *
batadv_forw_packet_alloc(struct batadv_hard_iface *if_incoming,
struct batadv_hard_iface *if_outgoing,
atomic_t *queue_left,
- struct batadv_priv *bat_priv)
+ struct batadv_priv *bat_priv,
+ struct sk_buff *skb)
{
struct batadv_forw_packet *forw_packet;
const char *qname;
@@ -525,7 +527,7 @@ batadv_forw_packet_alloc(struct batadv_hard_iface *if_incoming,
INIT_HLIST_NODE(&forw_packet->list);
INIT_HLIST_NODE(&forw_packet->cleanup_list);
- forw_packet->skb = NULL;
+ forw_packet->skb = skb;
forw_packet->queue_left = queue_left;
forw_packet->if_incoming = if_incoming;
forw_packet->if_outgoing = if_outgoing;
@@ -756,22 +758,23 @@ int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv,
if (!primary_if)
goto err;
+ newskb = skb_copy(skb, GFP_ATOMIC);
+ if (!newskb) {
+ batadv_hardif_put(primary_if);
+ goto err;
+ }
+
forw_packet = batadv_forw_packet_alloc(primary_if, NULL,
&bat_priv->bcast_queue_left,
- bat_priv);
+ bat_priv, newskb);
batadv_hardif_put(primary_if);
if (!forw_packet)
- goto err;
-
- newskb = skb_copy(skb, GFP_ATOMIC);
- if (!newskb)
goto err_packet_free;
/* as we have a copy now, it is safe to decrease the TTL */
bcast_packet = (struct batadv_bcast_packet *)newskb->data;
bcast_packet->ttl--;
- forw_packet->skb = newskb;
forw_packet->own = own_packet;
INIT_DELAYED_WORK(&forw_packet->delayed_work,
@@ -781,11 +784,60 @@ int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv,
return NETDEV_TX_OK;
err_packet_free:
- batadv_forw_packet_free(forw_packet, true);
+ kfree_skb(newskb);
err:
return NETDEV_TX_BUSY;
}
+/**
+ * batadv_forw_packet_bcasts_left - check if a retransmission is necessary
+ * @forw_packet: the forwarding packet to check
+ * @hard_iface: the interface to check on
+ *
+ * Checks whether a given packet has any (re)transmissions left on the provided
+ * interface.
+ *
+ * hard_iface may be NULL: In that case the number of transmissions this skb had
+ * so far is compared with the maximum amount of retransmissions independent of
+ * any interface instead.
+ *
+ * Return: True if (re)transmissions are left, false otherwise.
+ */
+static bool
+batadv_forw_packet_bcasts_left(struct batadv_forw_packet *forw_packet,
+ struct batadv_hard_iface *hard_iface)
+{
+ unsigned int max;
+
+ if (hard_iface)
+ max = hard_iface->num_bcasts;
+ else
+ max = BATADV_NUM_BCASTS_MAX;
+
+ return BATADV_SKB_CB(forw_packet->skb)->num_bcasts < max;
+}
+
+/**
+ * batadv_forw_packet_bcasts_inc - increment retransmission counter of a packet
+ * @forw_packet: the packet to increase the counter for
+ */
+static void
+batadv_forw_packet_bcasts_inc(struct batadv_forw_packet *forw_packet)
+{
+ BATADV_SKB_CB(forw_packet->skb)->num_bcasts++;
+}
+
+/**
+ * batadv_forw_packet_is_rebroadcast - check packet for previous transmissions
+ * @forw_packet: the packet to check
+ *
+ * Return: True if this packet was transmitted before, false otherwise.
+ */
+bool batadv_forw_packet_is_rebroadcast(struct batadv_forw_packet *forw_packet)
+{
+ return BATADV_SKB_CB(forw_packet->skb)->num_bcasts > 0;
+}
+
static void batadv_send_outstanding_bcast_packet(struct work_struct *work)
{
struct batadv_hard_iface *hard_iface;
@@ -826,7 +878,7 @@ static void batadv_send_outstanding_bcast_packet(struct work_struct *work)
if (hard_iface->soft_iface != soft_iface)
continue;
- if (forw_packet->num_packets >= hard_iface->num_bcasts)
+ if (!batadv_forw_packet_bcasts_left(forw_packet, hard_iface))
continue;
if (forw_packet->own) {
@@ -884,10 +936,10 @@ static void batadv_send_outstanding_bcast_packet(struct work_struct *work)
}
rcu_read_unlock();
- forw_packet->num_packets++;
+ batadv_forw_packet_bcasts_inc(forw_packet);
/* if we still have some more bcasts to send */
- if (forw_packet->num_packets < BATADV_NUM_BCASTS_MAX) {
+ if (batadv_forw_packet_bcasts_left(forw_packet, NULL)) {
batadv_forw_packet_bcast_queue(bat_priv, forw_packet,
send_time);
return;
diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h
index f21166d..a16b34f 100644
--- a/net/batman-adv/send.h
+++ b/net/batman-adv/send.h
@@ -34,11 +34,13 @@ struct batadv_forw_packet *
batadv_forw_packet_alloc(struct batadv_hard_iface *if_incoming,
struct batadv_hard_iface *if_outgoing,
atomic_t *queue_left,
- struct batadv_priv *bat_priv);
+ struct batadv_priv *bat_priv,
+ struct sk_buff *skb);
bool batadv_forw_packet_steal(struct batadv_forw_packet *packet, spinlock_t *l);
void batadv_forw_packet_ogmv1_queue(struct batadv_priv *bat_priv,
struct batadv_forw_packet *forw_packet,
unsigned long send_time);
+bool batadv_forw_packet_is_rebroadcast(struct batadv_forw_packet *forw_packet);
int batadv_send_skb_to_orig(struct sk_buff *skb,
struct batadv_orig_node *orig_node,
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 5d099b2..b25789a 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -64,28 +64,6 @@
#include "sysfs.h"
#include "translation-table.h"
-static int batadv_get_settings(struct net_device *dev, struct ethtool_cmd *cmd);
-static void batadv_get_drvinfo(struct net_device *dev,
- struct ethtool_drvinfo *info);
-static u32 batadv_get_msglevel(struct net_device *dev);
-static void batadv_set_msglevel(struct net_device *dev, u32 value);
-static u32 batadv_get_link(struct net_device *dev);
-static void batadv_get_strings(struct net_device *dev, u32 stringset, u8 *data);
-static void batadv_get_ethtool_stats(struct net_device *dev,
- struct ethtool_stats *stats, u64 *data);
-static int batadv_get_sset_count(struct net_device *dev, int stringset);
-
-static const struct ethtool_ops batadv_ethtool_ops = {
- .get_settings = batadv_get_settings,
- .get_drvinfo = batadv_get_drvinfo,
- .get_msglevel = batadv_get_msglevel,
- .set_msglevel = batadv_set_msglevel,
- .get_link = batadv_get_link,
- .get_strings = batadv_get_strings,
- .get_ethtool_stats = batadv_get_ethtool_stats,
- .get_sset_count = batadv_get_sset_count,
-};
-
int batadv_skb_head_push(struct sk_buff *skb, unsigned int len)
{
int result;
@@ -140,7 +118,7 @@ static u64 batadv_sum_counter(struct batadv_priv *bat_priv, size_t idx)
static struct net_device_stats *batadv_interface_stats(struct net_device *dev)
{
struct batadv_priv *bat_priv = netdev_priv(dev);
- struct net_device_stats *stats = &bat_priv->stats;
+ struct net_device_stats *stats = &dev->stats;
stats->tx_packets = batadv_sum_counter(bat_priv, BATADV_CNT_TX);
stats->tx_bytes = batadv_sum_counter(bat_priv, BATADV_CNT_TX_BYTES);
@@ -230,6 +208,9 @@ static int batadv_interface_tx(struct sk_buff *skb,
if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE)
goto dropped;
+ /* reset control block to avoid left overs from previous users */
+ memset(skb->cb, 0, sizeof(struct batadv_skb_cb));
+
netif_trans_update(soft_iface);
vid = batadv_get_vid(skb, 0);
ethhdr = eth_hdr(skb);
@@ -819,7 +800,6 @@ static int batadv_softif_init_late(struct net_device *dev)
atomic_set(&bat_priv->mcast.num_want_all_ipv6, 0);
#endif
atomic_set(&bat_priv->gw.mode, BATADV_GW_MODE_OFF);
- atomic_set(&bat_priv->gw.sel_class, 20);
atomic_set(&bat_priv->gw.bandwidth_down, 100);
atomic_set(&bat_priv->gw.bandwidth_up, 20);
atomic_set(&bat_priv->orig_interval, 1000);
@@ -948,6 +928,98 @@ static const struct net_device_ops batadv_netdev_ops = {
.ndo_del_slave = batadv_softif_slave_del,
};
+static void batadv_get_drvinfo(struct net_device *dev,
+ struct ethtool_drvinfo *info)
+{
+ strlcpy(info->driver, "B.A.T.M.A.N. advanced", sizeof(info->driver));
+ strlcpy(info->version, BATADV_SOURCE_VERSION, sizeof(info->version));
+ strlcpy(info->fw_version, "N/A", sizeof(info->fw_version));
+ strlcpy(info->bus_info, "batman", sizeof(info->bus_info));
+}
+
+/* Inspired by drivers/net/ethernet/dlink/sundance.c:1702
+ * Declare each description string in struct.name[] to get fixed sized buffer
+ * and compile time checking for strings longer than ETH_GSTRING_LEN.
+ */
+static const struct {
+ const char name[ETH_GSTRING_LEN];
+} batadv_counters_strings[] = {
+ { "tx" },
+ { "tx_bytes" },
+ { "tx_dropped" },
+ { "rx" },
+ { "rx_bytes" },
+ { "forward" },
+ { "forward_bytes" },
+ { "mgmt_tx" },
+ { "mgmt_tx_bytes" },
+ { "mgmt_rx" },
+ { "mgmt_rx_bytes" },
+ { "frag_tx" },
+ { "frag_tx_bytes" },
+ { "frag_rx" },
+ { "frag_rx_bytes" },
+ { "frag_fwd" },
+ { "frag_fwd_bytes" },
+ { "tt_request_tx" },
+ { "tt_request_rx" },
+ { "tt_response_tx" },
+ { "tt_response_rx" },
+ { "tt_roam_adv_tx" },
+ { "tt_roam_adv_rx" },
+#ifdef CONFIG_BATMAN_ADV_DAT
+ { "dat_get_tx" },
+ { "dat_get_rx" },
+ { "dat_put_tx" },
+ { "dat_put_rx" },
+ { "dat_cached_reply_tx" },
+#endif
+#ifdef CONFIG_BATMAN_ADV_NC
+ { "nc_code" },
+ { "nc_code_bytes" },
+ { "nc_recode" },
+ { "nc_recode_bytes" },
+ { "nc_buffer" },
+ { "nc_decode" },
+ { "nc_decode_bytes" },
+ { "nc_decode_failed" },
+ { "nc_sniffed" },
+#endif
+};
+
+static void batadv_get_strings(struct net_device *dev, u32 stringset, u8 *data)
+{
+ if (stringset == ETH_SS_STATS)
+ memcpy(data, batadv_counters_strings,
+ sizeof(batadv_counters_strings));
+}
+
+static void batadv_get_ethtool_stats(struct net_device *dev,
+ struct ethtool_stats *stats, u64 *data)
+{
+ struct batadv_priv *bat_priv = netdev_priv(dev);
+ int i;
+
+ for (i = 0; i < BATADV_CNT_NUM; i++)
+ data[i] = batadv_sum_counter(bat_priv, i);
+}
+
+static int batadv_get_sset_count(struct net_device *dev, int stringset)
+{
+ if (stringset == ETH_SS_STATS)
+ return BATADV_CNT_NUM;
+
+ return -EOPNOTSUPP;
+}
+
+static const struct ethtool_ops batadv_ethtool_ops = {
+ .get_drvinfo = batadv_get_drvinfo,
+ .get_link = ethtool_op_get_link,
+ .get_strings = batadv_get_strings,
+ .get_ethtool_stats = batadv_get_ethtool_stats,
+ .get_sset_count = batadv_get_sset_count,
+};
+
/**
* batadv_softif_free - Deconstructor of batadv_soft_interface
* @dev: Device to cleanup and remove
@@ -972,8 +1044,6 @@ static void batadv_softif_free(struct net_device *dev)
*/
static void batadv_softif_init_early(struct net_device *dev)
{
- struct batadv_priv *priv = netdev_priv(dev);
-
ether_setup(dev);
dev->netdev_ops = &batadv_netdev_ops;
@@ -990,8 +1060,6 @@ static void batadv_softif_init_early(struct net_device *dev)
eth_hw_addr_random(dev);
dev->ethtool_ops = &batadv_ethtool_ops;
-
- memset(priv, 0, sizeof(*priv));
}
struct net_device *batadv_softif_create(struct net *net, const char *name)
@@ -1084,118 +1152,3 @@ struct rtnl_link_ops batadv_link_ops __read_mostly = {
.setup = batadv_softif_init_early,
.dellink = batadv_softif_destroy_netlink,
};
-
-/* ethtool */
-static int batadv_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
- cmd->supported = 0;
- cmd->advertising = 0;
- ethtool_cmd_speed_set(cmd, SPEED_10);
- cmd->duplex = DUPLEX_FULL;
- cmd->port = PORT_TP;
- cmd->phy_address = 0;
- cmd->transceiver = XCVR_INTERNAL;
- cmd->autoneg = AUTONEG_DISABLE;
- cmd->maxtxpkt = 0;
- cmd->maxrxpkt = 0;
-
- return 0;
-}
-
-static void batadv_get_drvinfo(struct net_device *dev,
- struct ethtool_drvinfo *info)
-{
- strlcpy(info->driver, "B.A.T.M.A.N. advanced", sizeof(info->driver));
- strlcpy(info->version, BATADV_SOURCE_VERSION, sizeof(info->version));
- strlcpy(info->fw_version, "N/A", sizeof(info->fw_version));
- strlcpy(info->bus_info, "batman", sizeof(info->bus_info));
-}
-
-static u32 batadv_get_msglevel(struct net_device *dev)
-{
- return -EOPNOTSUPP;
-}
-
-static void batadv_set_msglevel(struct net_device *dev, u32 value)
-{
-}
-
-static u32 batadv_get_link(struct net_device *dev)
-{
- return 1;
-}
-
-/* Inspired by drivers/net/ethernet/dlink/sundance.c:1702
- * Declare each description string in struct.name[] to get fixed sized buffer
- * and compile time checking for strings longer than ETH_GSTRING_LEN.
- */
-static const struct {
- const char name[ETH_GSTRING_LEN];
-} batadv_counters_strings[] = {
- { "tx" },
- { "tx_bytes" },
- { "tx_dropped" },
- { "rx" },
- { "rx_bytes" },
- { "forward" },
- { "forward_bytes" },
- { "mgmt_tx" },
- { "mgmt_tx_bytes" },
- { "mgmt_rx" },
- { "mgmt_rx_bytes" },
- { "frag_tx" },
- { "frag_tx_bytes" },
- { "frag_rx" },
- { "frag_rx_bytes" },
- { "frag_fwd" },
- { "frag_fwd_bytes" },
- { "tt_request_tx" },
- { "tt_request_rx" },
- { "tt_response_tx" },
- { "tt_response_rx" },
- { "tt_roam_adv_tx" },
- { "tt_roam_adv_rx" },
-#ifdef CONFIG_BATMAN_ADV_DAT
- { "dat_get_tx" },
- { "dat_get_rx" },
- { "dat_put_tx" },
- { "dat_put_rx" },
- { "dat_cached_reply_tx" },
-#endif
-#ifdef CONFIG_BATMAN_ADV_NC
- { "nc_code" },
- { "nc_code_bytes" },
- { "nc_recode" },
- { "nc_recode_bytes" },
- { "nc_buffer" },
- { "nc_decode" },
- { "nc_decode_bytes" },
- { "nc_decode_failed" },
- { "nc_sniffed" },
-#endif
-};
-
-static void batadv_get_strings(struct net_device *dev, u32 stringset, u8 *data)
-{
- if (stringset == ETH_SS_STATS)
- memcpy(data, batadv_counters_strings,
- sizeof(batadv_counters_strings));
-}
-
-static void batadv_get_ethtool_stats(struct net_device *dev,
- struct ethtool_stats *stats, u64 *data)
-{
- struct batadv_priv *bat_priv = netdev_priv(dev);
- int i;
-
- for (i = 0; i < BATADV_CNT_NUM; i++)
- data[i] = batadv_sum_counter(bat_priv, i);
-}
-
-static int batadv_get_sset_count(struct net_device *dev, int stringset)
-{
- if (stringset == ETH_SS_STATS)
- return BATADV_CNT_NUM;
-
- return -EOPNOTSUPP;
-}
diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c
index c94ebde..556f9a8 100644
--- a/net/batman-adv/tp_meter.c
+++ b/net/batman-adv/tp_meter.c
@@ -873,8 +873,8 @@ static int batadv_tp_send(void *arg)
/* something went wrong during the preparation/transmission */
if (unlikely(err && err != BATADV_TP_REASON_CANT_SEND)) {
batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
- "Meter: batadv_tp_send() cannot send packets (%d)\n",
- err);
+ "Meter: %s() cannot send packets (%d)\n",
+ __func__, err);
/* ensure nobody else tries to stop the thread now */
if (atomic_dec_and_test(&tp_vars->sending))
tp_vars->reason = err;
@@ -979,7 +979,8 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst,
if (!tp_vars) {
spin_unlock_bh(&bat_priv->tp_list_lock);
batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
- "Meter: batadv_tp_start cannot allocate list elements\n");
+ "Meter: %s cannot allocate list elements\n",
+ __func__);
batadv_tp_batctl_error_notify(BATADV_TP_REASON_MEMORY_ERROR,
dst, bat_priv, session_cookie);
return;
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 6077a87..e75b493 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -617,7 +617,7 @@ static void batadv_tt_global_free(struct batadv_priv *bat_priv,
batadv_dbg(BATADV_DBG_TT, bat_priv,
"Deleting global tt entry %pM (vid: %d): %s\n",
tt_global->common.addr,
- BATADV_PRINT_VID(tt_global->common.vid), message);
+ batadv_print_vid(tt_global->common.vid), message);
batadv_hash_remove(bat_priv->tt.global_hash, batadv_compare_tt,
batadv_choose_tt, &tt_global->common);
@@ -671,7 +671,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr,
if (tt_local->common.flags & BATADV_TT_CLIENT_PENDING) {
batadv_dbg(BATADV_DBG_TT, bat_priv,
"Re-adding pending client %pM (vid: %d)\n",
- addr, BATADV_PRINT_VID(vid));
+ addr, batadv_print_vid(vid));
/* whatever the reason why the PENDING flag was set,
* this is a client which was enqueued to be removed in
* this orig_interval. Since it popped up again, the
@@ -684,7 +684,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr,
if (tt_local->common.flags & BATADV_TT_CLIENT_ROAM) {
batadv_dbg(BATADV_DBG_TT, bat_priv,
"Roaming client %pM (vid: %d) came back to its original location\n",
- addr, BATADV_PRINT_VID(vid));
+ addr, batadv_print_vid(vid));
/* the ROAM flag is set because this client roamed away
* and the node got a roaming_advertisement message. Now
* that the client popped up again at its original
@@ -716,7 +716,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr,
if (!vlan) {
net_ratelimited_function(batadv_info, soft_iface,
"adding TT local entry %pM to non-existent VLAN %d\n",
- addr, BATADV_PRINT_VID(vid));
+ addr, batadv_print_vid(vid));
kmem_cache_free(batadv_tl_cache, tt_local);
tt_local = NULL;
goto out;
@@ -724,7 +724,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr,
batadv_dbg(BATADV_DBG_TT, bat_priv,
"Creating new local tt entry: %pM (vid: %d, ttvn: %d)\n",
- addr, BATADV_PRINT_VID(vid),
+ addr, batadv_print_vid(vid),
(u8)atomic_read(&bat_priv->tt.vn));
ether_addr_copy(tt_local->common.addr, addr);
@@ -1097,7 +1097,7 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset)
seq_printf(seq,
" * %pM %4i [%c%c%c%c%c%c] %3u.%03u (%#.8x)\n",
tt_common_entry->addr,
- BATADV_PRINT_VID(tt_common_entry->vid),
+ batadv_print_vid(tt_common_entry->vid),
((tt_common_entry->flags &
BATADV_TT_CLIENT_ROAM) ? 'R' : '.'),
no_purge ? 'P' : '.',
@@ -1296,7 +1296,7 @@ batadv_tt_local_set_pending(struct batadv_priv *bat_priv,
batadv_dbg(BATADV_DBG_TT, bat_priv,
"Local tt entry (%pM, vid: %d) pending to be removed: %s\n",
tt_local_entry->common.addr,
- BATADV_PRINT_VID(tt_local_entry->common.vid), message);
+ batadv_print_vid(tt_local_entry->common.vid), message);
}
/**
@@ -1727,7 +1727,7 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv,
batadv_dbg(BATADV_DBG_TT, bat_priv,
"Creating new global tt entry: %pM (vid: %d, via %pM)\n",
- common->addr, BATADV_PRINT_VID(common->vid),
+ common->addr, batadv_print_vid(common->vid),
orig_node->orig);
ret = true;
@@ -1835,7 +1835,7 @@ batadv_tt_global_print_entry(struct batadv_priv *bat_priv,
if (!vlan) {
seq_printf(seq,
" * Cannot retrieve VLAN %d for originator %pM\n",
- BATADV_PRINT_VID(tt_common_entry->vid),
+ batadv_print_vid(tt_common_entry->vid),
best_entry->orig_node->orig);
goto print_list;
}
@@ -1844,7 +1844,7 @@ batadv_tt_global_print_entry(struct batadv_priv *bat_priv,
seq_printf(seq,
" %c %pM %4i (%3u) via %pM (%3u) (%#.8x) [%c%c%c%c]\n",
'*', tt_global_entry->common.addr,
- BATADV_PRINT_VID(tt_global_entry->common.vid),
+ batadv_print_vid(tt_global_entry->common.vid),
best_entry->ttvn, best_entry->orig_node->orig,
last_ttvn, vlan->tt.crc,
((flags & BATADV_TT_CLIENT_ROAM) ? 'R' : '.'),
@@ -1867,7 +1867,7 @@ batadv_tt_global_print_entry(struct batadv_priv *bat_priv,
if (!vlan) {
seq_printf(seq,
" + Cannot retrieve VLAN %d for originator %pM\n",
- BATADV_PRINT_VID(tt_common_entry->vid),
+ batadv_print_vid(tt_common_entry->vid),
orig_entry->orig_node->orig);
continue;
}
@@ -1876,7 +1876,7 @@ batadv_tt_global_print_entry(struct batadv_priv *bat_priv,
seq_printf(seq,
" %c %pM %4d (%3u) via %pM (%3u) (%#.8x) [%c%c%c%c]\n",
'+', tt_global_entry->common.addr,
- BATADV_PRINT_VID(tt_global_entry->common.vid),
+ batadv_print_vid(tt_global_entry->common.vid),
orig_entry->ttvn, orig_entry->orig_node->orig,
last_ttvn, vlan->tt.crc,
((flags & BATADV_TT_CLIENT_ROAM) ? 'R' : '.'),
@@ -2213,7 +2213,7 @@ batadv_tt_global_del_orig_node(struct batadv_priv *bat_priv,
"Deleting %pM from global tt entry %pM (vid: %d): %s\n",
orig_node->orig,
tt_global_entry->common.addr,
- BATADV_PRINT_VID(vid), message);
+ batadv_print_vid(vid), message);
_batadv_tt_global_del_orig_entry(tt_global_entry,
orig_entry);
}
@@ -2253,12 +2253,13 @@ batadv_tt_global_del_roaming(struct batadv_priv *bat_priv,
/* its the last one, mark for roaming. */
tt_global_entry->common.flags |= BATADV_TT_CLIENT_ROAM;
tt_global_entry->roam_at = jiffies;
- } else
+ } else {
/* there is another entry, we can simply delete this
* one and can still use the other one.
*/
batadv_tt_global_del_orig_node(bat_priv, tt_global_entry,
orig_node, message);
+ }
}
/**
@@ -2314,10 +2315,11 @@ static void batadv_tt_global_del(struct batadv_priv *bat_priv,
/* local entry exists, case 2: client roamed to us. */
batadv_tt_global_del_orig_list(tt_global_entry);
batadv_tt_global_free(bat_priv, tt_global_entry, message);
- } else
+ } else {
/* no local entry exists, case 1: check for roaming */
batadv_tt_global_del_roaming(bat_priv, tt_global_entry,
orig_node, message);
+ }
out:
if (tt_global_entry)
@@ -2375,7 +2377,7 @@ void batadv_tt_global_del_orig(struct batadv_priv *bat_priv,
batadv_dbg(BATADV_DBG_TT, bat_priv,
"Deleting global tt entry %pM (vid: %d): %s\n",
tt_global->common.addr,
- BATADV_PRINT_VID(vid), message);
+ batadv_print_vid(vid), message);
hlist_del_rcu(&tt_common_entry->hash_entry);
batadv_tt_global_entry_put(tt_global);
}
@@ -2435,7 +2437,7 @@ static void batadv_tt_global_purge(struct batadv_priv *bat_priv)
batadv_dbg(BATADV_DBG_TT, bat_priv,
"Deleting global tt entry %pM (vid: %d): %s\n",
tt_global->common.addr,
- BATADV_PRINT_VID(tt_global->common.vid),
+ batadv_print_vid(tt_global->common.vid),
msg);
hlist_del_rcu(&tt_common->hash_entry);
@@ -3650,7 +3652,7 @@ static void batadv_send_roam_adv(struct batadv_priv *bat_priv, u8 *client,
batadv_dbg(BATADV_DBG_TT, bat_priv,
"Sending ROAMING_ADV to %pM (client %pM, vid: %d)\n",
- orig_node->orig, client, BATADV_PRINT_VID(vid));
+ orig_node->orig, client, batadv_print_vid(vid));
batadv_inc_counter(bat_priv, BATADV_CNT_TT_ROAM_ADV_TX);
@@ -3773,7 +3775,7 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv)
batadv_dbg(BATADV_DBG_TT, bat_priv,
"Deleting local tt entry (%pM, vid: %d): pending\n",
tt_common->addr,
- BATADV_PRINT_VID(tt_common->vid));
+ batadv_print_vid(tt_common->vid));
batadv_tt_local_size_dec(bat_priv, tt_common->vid);
hlist_del_rcu(&tt_common->hash_entry);
@@ -4017,7 +4019,7 @@ bool batadv_tt_add_temporary_global_entry(struct batadv_priv *bat_priv,
batadv_dbg(BATADV_DBG_TT, bat_priv,
"Added temporary global client (addr: %pM, vid: %d, orig: %pM)\n",
- addr, BATADV_PRINT_VID(vid), orig_node->orig);
+ addr, batadv_print_vid(vid), orig_node->orig);
ret = true;
out:
return ret;
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 66b25e4..ea43a64 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -1000,7 +1000,6 @@ struct batadv_priv_bat_v {
* struct batadv_priv - per mesh interface data
* @mesh_state: current status of the mesh (inactive/active/deactivating)
* @soft_iface: net device which holds this struct as private data
- * @stats: structure holding the data for the ndo_get_stats() call
* @bat_counters: mesh internal traffic statistic counters (see batadv_counters)
* @aggregated_ogms: bool indicating whether OGM aggregation is enabled
* @bonding: bool indicating whether traffic bonding is enabled
@@ -1055,7 +1054,6 @@ struct batadv_priv_bat_v {
struct batadv_priv {
atomic_t mesh_state;
struct net_device *soft_iface;
- struct net_device_stats stats;
u64 __percpu *bat_counters; /* Per cpu counters */
atomic_t aggregated_ogms;
atomic_t bonding;
@@ -1377,9 +1375,11 @@ struct batadv_nc_packet {
* relevant to batman-adv in the skb->cb buffer in skbs.
* @decoded: Marks a skb as decoded, which is checked when searching for coding
* opportunities in network-coding.c
+ * @num_bcasts: Counter for broadcast packet retransmissions
*/
struct batadv_skb_cb {
bool decoded;
+ unsigned int num_bcasts;
};
/**
@@ -1392,7 +1392,7 @@ struct batadv_skb_cb {
* @skb: bcast packet's skb buffer
* @packet_len: size of aggregated OGM packet inside the skb buffer
* @direct_link_flags: direct link flags for aggregated OGM packets
- * @num_packets: counter for bcast packet retransmission
+ * @num_packets: counter for aggregated OGMv1 packets
* @delayed_work: work queue callback item for packet sending
* @if_incoming: pointer to incoming hard-iface or primary iface if
* locally generated packet
@@ -1489,6 +1489,7 @@ struct batadv_algo_orig_ops {
/**
* struct batadv_algo_gw_ops - mesh algorithm callbacks (GW specific)
+ * @init_sel_class: initialize GW selection class (optional)
* @store_sel_class: parse and stores a new GW selection class (optional)
* @show_sel_class: prints the current GW selection class (optional)
* @get_best_gw_node: select the best GW from the list of available nodes
@@ -1499,6 +1500,7 @@ struct batadv_algo_orig_ops {
* @dump: dump gateways to a netlink socket (optional)
*/
struct batadv_algo_gw_ops {
+ void (*init_sel_class)(struct batadv_priv *bat_priv);
ssize_t (*store_sel_class)(struct batadv_priv *bat_priv, char *buff,
size_t count);
ssize_t (*show_sel_class)(struct batadv_priv *bat_priv, char *buff);
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index f307b14..507b80d 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -301,7 +301,7 @@ static int l2cap_sock_listen(struct socket *sock, int backlog)
}
static int l2cap_sock_accept(struct socket *sock, struct socket *newsock,
- int flags)
+ int flags, bool kern)
{
DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct sock *sk = sock->sk, *nsk;
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index aa1a814..ac3c650c 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -471,7 +471,8 @@ static int rfcomm_sock_listen(struct socket *sock, int backlog)
return err;
}
-static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int flags)
+static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct sock *sk = sock->sk, *nsk;
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index e4e9a2d..728e0c8 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -627,7 +627,7 @@ static int sco_sock_listen(struct socket *sock, int backlog)
}
static int sco_sock_accept(struct socket *sock, struct socket *newsock,
- int flags)
+ int flags, bool kern)
{
DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct sock *sk = sock->sk, *ch;
diff --git a/net/bpf/Makefile b/net/bpf/Makefile
new file mode 100644
index 0000000..27b2992
--- /dev/null
+++ b/net/bpf/Makefile
@@ -0,0 +1 @@
+obj-y := test_run.o
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
new file mode 100644
index 0000000..8a6d0a3
--- /dev/null
+++ b/net/bpf/test_run.c
@@ -0,0 +1,172 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/bpf.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/etherdevice.h>
+#include <linux/filter.h>
+#include <linux/sched/signal.h>
+
+static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx)
+{
+ u32 ret;
+
+ preempt_disable();
+ rcu_read_lock();
+ ret = BPF_PROG_RUN(prog, ctx);
+ rcu_read_unlock();
+ preempt_enable();
+
+ return ret;
+}
+
+static u32 bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *time)
+{
+ u64 time_start, time_spent = 0;
+ u32 ret = 0, i;
+
+ if (!repeat)
+ repeat = 1;
+ time_start = ktime_get_ns();
+ for (i = 0; i < repeat; i++) {
+ ret = bpf_test_run_one(prog, ctx);
+ if (need_resched()) {
+ if (signal_pending(current))
+ break;
+ time_spent += ktime_get_ns() - time_start;
+ cond_resched();
+ time_start = ktime_get_ns();
+ }
+ }
+ time_spent += ktime_get_ns() - time_start;
+ do_div(time_spent, repeat);
+ *time = time_spent > U32_MAX ? U32_MAX : (u32)time_spent;
+
+ return ret;
+}
+
+static int bpf_test_finish(union bpf_attr __user *uattr, const void *data,
+ u32 size, u32 retval, u32 duration)
+{
+ void __user *data_out = u64_to_user_ptr(uattr->test.data_out);
+ int err = -EFAULT;
+
+ if (data_out && copy_to_user(data_out, data, size))
+ goto out;
+ if (copy_to_user(&uattr->test.data_size_out, &size, sizeof(size)))
+ goto out;
+ if (copy_to_user(&uattr->test.retval, &retval, sizeof(retval)))
+ goto out;
+ if (copy_to_user(&uattr->test.duration, &duration, sizeof(duration)))
+ goto out;
+ err = 0;
+out:
+ return err;
+}
+
+static void *bpf_test_init(const union bpf_attr *kattr, u32 size,
+ u32 headroom, u32 tailroom)
+{
+ void __user *data_in = u64_to_user_ptr(kattr->test.data_in);
+ void *data;
+
+ if (size < ETH_HLEN || size > PAGE_SIZE - headroom - tailroom)
+ return ERR_PTR(-EINVAL);
+
+ data = kzalloc(size + headroom + tailroom, GFP_USER);
+ if (!data)
+ return ERR_PTR(-ENOMEM);
+
+ if (copy_from_user(data + headroom, data_in, size)) {
+ kfree(data);
+ return ERR_PTR(-EFAULT);
+ }
+ return data;
+}
+
+int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
+ union bpf_attr __user *uattr)
+{
+ bool is_l2 = false, is_direct_pkt_access = false;
+ u32 size = kattr->test.data_size_in;
+ u32 repeat = kattr->test.repeat;
+ u32 retval, duration;
+ struct sk_buff *skb;
+ void *data;
+ int ret;
+
+ data = bpf_test_init(kattr, size, NET_SKB_PAD,
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
+ if (IS_ERR(data))
+ return PTR_ERR(data);
+
+ switch (prog->type) {
+ case BPF_PROG_TYPE_SCHED_CLS:
+ case BPF_PROG_TYPE_SCHED_ACT:
+ is_l2 = true;
+ /* fall through */
+ case BPF_PROG_TYPE_LWT_IN:
+ case BPF_PROG_TYPE_LWT_OUT:
+ case BPF_PROG_TYPE_LWT_XMIT:
+ is_direct_pkt_access = true;
+ break;
+ default:
+ break;
+ }
+
+ skb = build_skb(data, 0);
+ if (!skb) {
+ kfree(data);
+ return -ENOMEM;
+ }
+
+ skb_reserve(skb, NET_SKB_PAD);
+ __skb_put(skb, size);
+ skb->protocol = eth_type_trans(skb, current->nsproxy->net_ns->loopback_dev);
+ skb_reset_network_header(skb);
+
+ if (is_l2)
+ __skb_push(skb, ETH_HLEN);
+ if (is_direct_pkt_access)
+ bpf_compute_data_end(skb);
+ retval = bpf_test_run(prog, skb, repeat, &duration);
+ if (!is_l2)
+ __skb_push(skb, ETH_HLEN);
+ size = skb->len;
+ /* bpf program can never convert linear skb to non-linear */
+ if (WARN_ON_ONCE(skb_is_nonlinear(skb)))
+ size = skb_headlen(skb);
+ ret = bpf_test_finish(uattr, skb->data, size, retval, duration);
+ kfree_skb(skb);
+ return ret;
+}
+
+int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
+ union bpf_attr __user *uattr)
+{
+ u32 size = kattr->test.data_size_in;
+ u32 repeat = kattr->test.repeat;
+ struct xdp_buff xdp = {};
+ u32 retval, duration;
+ void *data;
+ int ret;
+
+ data = bpf_test_init(kattr, size, XDP_PACKET_HEADROOM, 0);
+ if (IS_ERR(data))
+ return PTR_ERR(data);
+
+ xdp.data_hard_start = data;
+ xdp.data = data + XDP_PACKET_HEADROOM;
+ xdp.data_end = xdp.data + size;
+
+ retval = bpf_test_run(prog, &xdp, repeat, &duration);
+ if (xdp.data != data + XDP_PACKET_HEADROOM)
+ size = xdp.data_end - xdp.data;
+ ret = bpf_test_finish(uattr, xdp.data, size, retval, duration);
+ kfree(data);
+ return ret;
+}
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 4f598dc..5a40a87 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -106,7 +106,7 @@ static struct net_bridge_fdb_entry *br_fdb_find(struct net_bridge *br,
struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)];
struct net_bridge_fdb_entry *fdb;
- WARN_ON_ONCE(!br_hash_lock_held(br));
+ lockdep_assert_held_once(&br->hash_lock);
rcu_read_lock();
fdb = fdb_find_rcu(head, addr, vid);
@@ -594,6 +594,9 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
fdb->updated = now;
if (unlikely(added_by_user))
fdb->added_by_user = 1;
+ /* Take over HW learned entry */
+ if (unlikely(fdb->added_by_external_learn))
+ fdb->added_by_external_learn = 0;
if (unlikely(fdb_modified))
fdb_notify(br, fdb, RTM_NEWNEIGH);
}
@@ -854,6 +857,8 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br,
br_fdb_update(br, p, addr, vid, true);
rcu_read_unlock();
local_bh_enable();
+ } else if (ndm->ndm_flags & NTF_EXT_LEARNED) {
+ err = br_fdb_external_learn_add(br, p, addr, vid);
} else {
spin_lock_bh(&br->hash_lock);
err = fdb_add_entry(br, p, addr, ndm->ndm_state,
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 8ac1770..6eb52d4 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -22,6 +22,7 @@
#include <linux/rtnetlink.h>
#include <linux/if_ether.h>
#include <linux/slab.h>
+#include <net/dsa.h>
#include <net/sock.h>
#include <linux/if_vlan.h>
#include <net/switchdev.h>
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 236f342..013f2290b 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -30,6 +30,7 @@ EXPORT_SYMBOL(br_should_route_hook);
static int
br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb)
{
+ br_drop_fake_rtable(skb);
return netif_receive_skb(skb);
}
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 95087e6..067cf03 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -521,21 +521,6 @@ static unsigned int br_nf_pre_routing(void *priv,
}
-/* PF_BRIDGE/LOCAL_IN ************************************************/
-/* The packet is locally destined, which requires a real
- * dst_entry, so detach the fake one. On the way up, the
- * packet would pass through PRE_ROUTING again (which already
- * took place when the packet entered the bridge), but we
- * register an IPv4 PRE_ROUTING 'sabotage' hook that will
- * prevent this from happening. */
-static unsigned int br_nf_local_in(void *priv,
- struct sk_buff *skb,
- const struct nf_hook_state *state)
-{
- br_drop_fake_rtable(skb);
- return NF_ACCEPT;
-}
-
/* PF_BRIDGE/FORWARD *************************************************/
static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
@@ -721,18 +706,20 @@ static unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb)
static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct nf_bridge_info *nf_bridge;
- unsigned int mtu_reserved;
+ struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
+ unsigned int mtu, mtu_reserved;
mtu_reserved = nf_bridge_mtu_reduction(skb);
+ mtu = skb->dev->mtu;
- if (skb_is_gso(skb) || skb->len + mtu_reserved <= skb->dev->mtu) {
+ if (nf_bridge->frag_max_size && nf_bridge->frag_max_size < mtu)
+ mtu = nf_bridge->frag_max_size;
+
+ if (skb_is_gso(skb) || skb->len + mtu_reserved <= mtu) {
nf_bridge_info_free(skb);
return br_dev_queue_push_xmit(net, sk, skb);
}
- nf_bridge = nf_bridge_info_get(skb);
-
/* This is wrong! We should preserve the original fragment
* boundaries by preserving frag_list rather than refragmenting.
*/
@@ -908,12 +895,6 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = {
.priority = NF_BR_PRI_BRNF,
},
{
- .hook = br_nf_local_in,
- .pf = NFPROTO_BRIDGE,
- .hooknum = NF_BR_LOCAL_IN,
- .priority = NF_BR_PRI_BRNF,
- },
- {
.hook = br_nf_forward_ip,
.pf = NFPROTO_BRIDGE,
.hooknum = NF_BR_FORWARD,
@@ -1016,13 +997,10 @@ int br_nf_hook_thresh(unsigned int hook, struct net *net,
if (!elem)
return okfn(net, sk, skb);
- /* We may already have this, but read-locks nest anyway */
- rcu_read_lock();
nf_hook_state_init(&state, hook, NFPROTO_BRIDGE, indev, outdev,
sk, net, okfn);
ret = nf_hook_slow(skb, &state, elem);
- rcu_read_unlock();
if (ret == 1)
ret = okfn(net, sk, skb);
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 2288fca..6136818 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -531,15 +531,6 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p,
const unsigned char *addr, u16 vid);
-static inline bool br_hash_lock_held(struct net_bridge *br)
-{
-#ifdef CONFIG_LOCKDEP
- return lockdep_is_held(&br->hash_lock);
-#else
- return true;
-#endif
-}
-
/* br_forward.c */
enum br_pkt_type {
BR_PKT_UNICAST,
diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c
index 98b9c8e..707caea 100644
--- a/net/bridge/netfilter/ebt_log.c
+++ b/net/bridge/netfilter/ebt_log.c
@@ -62,10 +62,10 @@ print_ports(const struct sk_buff *skb, uint8_t protocol, int offset)
pptr = skb_header_pointer(skb, offset,
sizeof(_ports), &_ports);
if (pptr == NULL) {
- printk(" INCOMPLETE TCP/UDP header");
+ pr_cont(" INCOMPLETE TCP/UDP header");
return;
}
- printk(" SPT=%u DPT=%u", ntohs(pptr->src), ntohs(pptr->dst));
+ pr_cont(" SPT=%u DPT=%u", ntohs(pptr->src), ntohs(pptr->dst));
}
}
@@ -100,11 +100,11 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum,
ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph);
if (ih == NULL) {
- printk(" INCOMPLETE IP header");
+ pr_cont(" INCOMPLETE IP header");
goto out;
}
- printk(" IP SRC=%pI4 IP DST=%pI4, IP tos=0x%02X, IP proto=%d",
- &ih->saddr, &ih->daddr, ih->tos, ih->protocol);
+ pr_cont(" IP SRC=%pI4 IP DST=%pI4, IP tos=0x%02X, IP proto=%d",
+ &ih->saddr, &ih->daddr, ih->tos, ih->protocol);
print_ports(skb, ih->protocol, ih->ihl*4);
goto out;
}
@@ -120,11 +120,11 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum,
ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph);
if (ih == NULL) {
- printk(" INCOMPLETE IPv6 header");
+ pr_cont(" INCOMPLETE IPv6 header");
goto out;
}
- printk(" IPv6 SRC=%pI6 IPv6 DST=%pI6, IPv6 priority=0x%01X, Next Header=%d",
- &ih->saddr, &ih->daddr, ih->priority, ih->nexthdr);
+ pr_cont(" IPv6 SRC=%pI6 IPv6 DST=%pI6, IPv6 priority=0x%01X, Next Header=%d",
+ &ih->saddr, &ih->daddr, ih->priority, ih->nexthdr);
nexthdr = ih->nexthdr;
offset_ph = ipv6_skip_exthdr(skb, sizeof(_iph), &nexthdr, &frag_off);
if (offset_ph == -1)
@@ -142,12 +142,12 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum,
ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph);
if (ah == NULL) {
- printk(" INCOMPLETE ARP header");
+ pr_cont(" INCOMPLETE ARP header");
goto out;
}
- printk(" ARP HTYPE=%d, PTYPE=0x%04x, OPCODE=%d",
- ntohs(ah->ar_hrd), ntohs(ah->ar_pro),
- ntohs(ah->ar_op));
+ pr_cont(" ARP HTYPE=%d, PTYPE=0x%04x, OPCODE=%d",
+ ntohs(ah->ar_hrd), ntohs(ah->ar_pro),
+ ntohs(ah->ar_op));
/* If it's for Ethernet and the lengths are OK,
* then log the ARP payload
@@ -161,17 +161,17 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum,
ap = skb_header_pointer(skb, sizeof(_arph),
sizeof(_arpp), &_arpp);
if (ap == NULL) {
- printk(" INCOMPLETE ARP payload");
+ pr_cont(" INCOMPLETE ARP payload");
goto out;
}
- printk(" ARP MAC SRC=%pM ARP IP SRC=%pI4 ARP MAC DST=%pM ARP IP DST=%pI4",
- ap->mac_src, ap->ip_src, ap->mac_dst, ap->ip_dst);
+ pr_cont(" ARP MAC SRC=%pM ARP IP SRC=%pI4 ARP MAC DST=%pM ARP IP DST=%pI4",
+ ap->mac_src, ap->ip_src,
+ ap->mac_dst, ap->ip_dst);
}
}
out:
- printk("\n");
+ pr_cont("\n");
spin_unlock_bh(&ebt_log_lock);
-
}
static unsigned int
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index 206dc26..346ef6b 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -375,11 +375,7 @@ static int nft_reject_bridge_init(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
{
struct nft_reject *priv = nft_expr_priv(expr);
- int icmp_code, err;
-
- err = nft_reject_bridge_validate(ctx, expr, NULL);
- if (err < 0)
- return err;
+ int icmp_code;
if (tb[NFTA_REJECT_TYPE] == NULL)
return -EINVAL;
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 5488e4a..abf7d85 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -75,9 +75,7 @@ static int stats_timer __read_mostly = 1;
module_param(stats_timer, int, S_IRUGO);
MODULE_PARM_DESC(stats_timer, "enable timer for statistics (default:on)");
-/* receive filters subscribed for 'all' CAN devices */
-struct dev_rcv_lists can_rx_alldev_list;
-static DEFINE_SPINLOCK(can_rcvlists_lock);
+static int can_net_id;
static struct kmem_cache *rcv_cache __read_mostly;
@@ -145,9 +143,6 @@ static int can_create(struct net *net, struct socket *sock, int protocol,
if (protocol < 0 || protocol >= CAN_NPROTO)
return -EINVAL;
- if (!net_eq(net, &init_net))
- return -EAFNOSUPPORT;
-
cp = can_get_proto(protocol);
#ifdef CONFIG_MODULES
@@ -331,10 +326,11 @@ EXPORT_SYMBOL(can_send);
* af_can rx path
*/
-static struct dev_rcv_lists *find_dev_rcv_lists(struct net_device *dev)
+static struct dev_rcv_lists *find_dev_rcv_lists(struct net *net,
+ struct net_device *dev)
{
if (!dev)
- return &can_rx_alldev_list;
+ return net->can.can_rx_alldev_list;
else
return (struct dev_rcv_lists *)dev->ml_priv;
}
@@ -467,9 +463,9 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask,
* -ENOMEM on missing cache mem to create subscription entry
* -ENODEV unknown device
*/
-int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
- void (*func)(struct sk_buff *, void *), void *data,
- char *ident, struct sock *sk)
+int can_rx_register(struct net *net, struct net_device *dev, canid_t can_id,
+ canid_t mask, void (*func)(struct sk_buff *, void *),
+ void *data, char *ident, struct sock *sk)
{
struct receiver *r;
struct hlist_head *rl;
@@ -481,13 +477,16 @@ int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
if (dev && dev->type != ARPHRD_CAN)
return -ENODEV;
+ if (dev && !net_eq(net, dev_net(dev)))
+ return -ENODEV;
+
r = kmem_cache_alloc(rcv_cache, GFP_KERNEL);
if (!r)
return -ENOMEM;
- spin_lock(&can_rcvlists_lock);
+ spin_lock(&net->can.can_rcvlists_lock);
- d = find_dev_rcv_lists(dev);
+ d = find_dev_rcv_lists(net, dev);
if (d) {
rl = find_rcv_list(&can_id, &mask, d);
@@ -510,7 +509,7 @@ int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
err = -ENODEV;
}
- spin_unlock(&can_rcvlists_lock);
+ spin_unlock(&net->can.can_rcvlists_lock);
return err;
}
@@ -540,8 +539,9 @@ static void can_rx_delete_receiver(struct rcu_head *rp)
* Description:
* Removes subscription entry depending on given (subscription) values.
*/
-void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask,
- void (*func)(struct sk_buff *, void *), void *data)
+void can_rx_unregister(struct net *net, struct net_device *dev, canid_t can_id,
+ canid_t mask, void (*func)(struct sk_buff *, void *),
+ void *data)
{
struct receiver *r = NULL;
struct hlist_head *rl;
@@ -550,9 +550,12 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask,
if (dev && dev->type != ARPHRD_CAN)
return;
- spin_lock(&can_rcvlists_lock);
+ if (dev && !net_eq(net, dev_net(dev)))
+ return;
- d = find_dev_rcv_lists(dev);
+ spin_lock(&net->can.can_rcvlists_lock);
+
+ d = find_dev_rcv_lists(net, dev);
if (!d) {
pr_err("BUG: receive list not found for "
"dev %s, id %03X, mask %03X\n",
@@ -598,7 +601,7 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask,
}
out:
- spin_unlock(&can_rcvlists_lock);
+ spin_unlock(&net->can.can_rcvlists_lock);
/* schedule the receiver item for deletion */
if (r) {
@@ -696,10 +699,10 @@ static void can_receive(struct sk_buff *skb, struct net_device *dev)
rcu_read_lock();
/* deliver the packet to sockets listening on all devices */
- matches = can_rcv_filter(&can_rx_alldev_list, skb);
+ matches = can_rcv_filter(dev_net(dev)->can.can_rx_alldev_list, skb);
/* find receive list for this device */
- d = find_dev_rcv_lists(dev);
+ d = find_dev_rcv_lists(dev_net(dev), dev);
if (d)
matches += can_rcv_filter(d, skb);
@@ -719,9 +722,6 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev,
{
struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
- if (unlikely(!net_eq(dev_net(dev), &init_net)))
- goto drop;
-
if (WARN_ONCE(dev->type != ARPHRD_CAN ||
skb->len != CAN_MTU ||
cfd->len > CAN_MAX_DLEN,
@@ -743,9 +743,6 @@ static int canfd_rcv(struct sk_buff *skb, struct net_device *dev,
{
struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
- if (unlikely(!net_eq(dev_net(dev), &init_net)))
- goto drop;
-
if (WARN_ONCE(dev->type != ARPHRD_CAN ||
skb->len != CANFD_MTU ||
cfd->len > CANFD_MAX_DLEN,
@@ -835,9 +832,6 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg,
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct dev_rcv_lists *d;
- if (!net_eq(dev_net(dev), &init_net))
- return NOTIFY_DONE;
-
if (dev->type != ARPHRD_CAN)
return NOTIFY_DONE;
@@ -855,7 +849,7 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg,
break;
case NETDEV_UNREGISTER:
- spin_lock(&can_rcvlists_lock);
+ spin_lock(&dev_net(dev)->can.can_rcvlists_lock);
d = dev->ml_priv;
if (d) {
@@ -869,7 +863,7 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg,
pr_err("can: notifier: receive list not found for dev "
"%s\n", dev->name);
- spin_unlock(&can_rcvlists_lock);
+ spin_unlock(&dev_net(dev)->can.can_rcvlists_lock);
break;
}
@@ -877,6 +871,40 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg,
return NOTIFY_DONE;
}
+static int can_pernet_init(struct net *net)
+{
+ net->can.can_rcvlists_lock =
+ __SPIN_LOCK_UNLOCKED(net->can.can_rcvlists_lock);
+ net->can.can_rx_alldev_list =
+ kzalloc(sizeof(struct dev_rcv_lists), GFP_KERNEL);
+
+ if (IS_ENABLED(CONFIG_PROC_FS))
+ can_init_proc(net);
+
+ return 0;
+}
+
+static void can_pernet_exit(struct net *net)
+{
+ struct net_device *dev;
+
+ if (IS_ENABLED(CONFIG_PROC_FS))
+ can_remove_proc(net);
+
+ /* remove created dev_rcv_lists from still registered CAN devices */
+ rcu_read_lock();
+ for_each_netdev_rcu(net, dev) {
+ if (dev->type == ARPHRD_CAN && dev->ml_priv) {
+ struct dev_rcv_lists *d = dev->ml_priv;
+
+ BUG_ON(d->entries);
+ kfree(d);
+ dev->ml_priv = NULL;
+ }
+ }
+ rcu_read_unlock();
+}
+
/*
* af_can module init/exit functions
*/
@@ -902,6 +930,13 @@ static struct notifier_block can_netdev_notifier __read_mostly = {
.notifier_call = can_notifier,
};
+static struct pernet_operations can_pernet_ops __read_mostly = {
+ .init = can_pernet_init,
+ .exit = can_pernet_exit,
+ .id = &can_net_id,
+ .size = 0,
+};
+
static __init int can_init(void)
{
/* check for correct padding to be able to use the structs similarly */
@@ -912,8 +947,6 @@ static __init int can_init(void)
pr_info("can: controller area network core (" CAN_VERSION_STRING ")\n");
- memset(&can_rx_alldev_list, 0, sizeof(can_rx_alldev_list));
-
rcv_cache = kmem_cache_create("can_receiver", sizeof(struct receiver),
0, 0, NULL);
if (!rcv_cache)
@@ -925,9 +958,10 @@ static __init int can_init(void)
setup_timer(&can_stattimer, can_stat_update, 0);
mod_timer(&can_stattimer, round_jiffies(jiffies + HZ));
}
- can_init_proc();
}
+ register_pernet_subsys(&can_pernet_ops);
+
/* protocol register */
sock_register(&can_family_ops);
register_netdevice_notifier(&can_netdev_notifier);
@@ -939,13 +973,9 @@ static __init int can_init(void)
static __exit void can_exit(void)
{
- struct net_device *dev;
-
if (IS_ENABLED(CONFIG_PROC_FS)) {
if (stats_timer)
del_timer_sync(&can_stattimer);
-
- can_remove_proc();
}
/* protocol unregister */
@@ -954,19 +984,7 @@ static __exit void can_exit(void)
unregister_netdevice_notifier(&can_netdev_notifier);
sock_unregister(PF_CAN);
- /* remove created dev_rcv_lists from still registered CAN devices */
- rcu_read_lock();
- for_each_netdev_rcu(&init_net, dev) {
- if (dev->type == ARPHRD_CAN && dev->ml_priv) {
-
- struct dev_rcv_lists *d = dev->ml_priv;
-
- BUG_ON(d->entries);
- kfree(d);
- dev->ml_priv = NULL;
- }
- }
- rcu_read_unlock();
+ unregister_pernet_subsys(&can_pernet_ops);
rcu_barrier(); /* Wait for completion of call_rcu()'s */
diff --git a/net/can/af_can.h b/net/can/af_can.h
index b86f512..f273c9d 100644
--- a/net/can/af_can.h
+++ b/net/can/af_can.h
@@ -114,8 +114,8 @@ struct s_pstats {
extern struct dev_rcv_lists can_rx_alldev_list;
/* function prototypes for the CAN networklayer procfs (proc.c) */
-void can_init_proc(void);
-void can_remove_proc(void);
+void can_init_proc(struct net *net);
+void can_remove_proc(struct net *net);
void can_stat_update(unsigned long data);
/* structures and variables from af_can.c needed in proc.c for reading */
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 95d13b2..1976629 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -764,8 +764,8 @@ static void bcm_remove_op(struct bcm_op *op)
static void bcm_rx_unreg(struct net_device *dev, struct bcm_op *op)
{
if (op->rx_reg_dev == dev) {
- can_rx_unregister(dev, op->can_id, REGMASK(op->can_id),
- bcm_rx_handler, op);
+ can_rx_unregister(&init_net, dev, op->can_id,
+ REGMASK(op->can_id), bcm_rx_handler, op);
/* mark as removed subscription */
op->rx_reg_dev = NULL;
@@ -808,7 +808,7 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh,
}
}
} else
- can_rx_unregister(NULL, op->can_id,
+ can_rx_unregister(&init_net, NULL, op->can_id,
REGMASK(op->can_id),
bcm_rx_handler, op);
@@ -1222,7 +1222,8 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
dev = dev_get_by_index(&init_net, ifindex);
if (dev) {
- err = can_rx_register(dev, op->can_id,
+ err = can_rx_register(&init_net, dev,
+ op->can_id,
REGMASK(op->can_id),
bcm_rx_handler, op,
"bcm", sk);
@@ -1232,7 +1233,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
}
} else
- err = can_rx_register(NULL, op->can_id,
+ err = can_rx_register(&init_net, NULL, op->can_id,
REGMASK(op->can_id),
bcm_rx_handler, op, "bcm", sk);
if (err) {
@@ -1528,7 +1529,7 @@ static int bcm_release(struct socket *sock)
}
}
} else
- can_rx_unregister(NULL, op->can_id,
+ can_rx_unregister(&init_net, NULL, op->can_id,
REGMASK(op->can_id),
bcm_rx_handler, op);
diff --git a/net/can/gw.c b/net/can/gw.c
index 7056a1a..3c117a33 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -440,14 +440,14 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data)
static inline int cgw_register_filter(struct cgw_job *gwj)
{
- return can_rx_register(gwj->src.dev, gwj->ccgw.filter.can_id,
+ return can_rx_register(&init_net, gwj->src.dev, gwj->ccgw.filter.can_id,
gwj->ccgw.filter.can_mask, can_can_gw_rcv,
gwj, "gw", NULL);
}
static inline void cgw_unregister_filter(struct cgw_job *gwj)
{
- can_rx_unregister(gwj->src.dev, gwj->ccgw.filter.can_id,
+ can_rx_unregister(&init_net, gwj->src.dev, gwj->ccgw.filter.can_id,
gwj->ccgw.filter.can_mask, can_can_gw_rcv, gwj);
}
diff --git a/net/can/proc.c b/net/can/proc.c
index 85ef7bb..9a8d54d 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -62,17 +62,6 @@
#define CAN_PROC_RCVLIST_EFF "rcvlist_eff"
#define CAN_PROC_RCVLIST_ERR "rcvlist_err"
-static struct proc_dir_entry *can_dir;
-static struct proc_dir_entry *pde_version;
-static struct proc_dir_entry *pde_stats;
-static struct proc_dir_entry *pde_reset_stats;
-static struct proc_dir_entry *pde_rcvlist_all;
-static struct proc_dir_entry *pde_rcvlist_fil;
-static struct proc_dir_entry *pde_rcvlist_inv;
-static struct proc_dir_entry *pde_rcvlist_sff;
-static struct proc_dir_entry *pde_rcvlist_eff;
-static struct proc_dir_entry *pde_rcvlist_err;
-
static int user_reset;
static const char rx_list_name[][8] = {
@@ -351,20 +340,21 @@ static inline void can_rcvlist_proc_show_one(struct seq_file *m, int idx,
static int can_rcvlist_proc_show(struct seq_file *m, void *v)
{
/* double cast to prevent GCC warning */
- int idx = (int)(long)m->private;
+ int idx = (int)(long)PDE_DATA(m->file->f_inode);
struct net_device *dev;
struct dev_rcv_lists *d;
+ struct net *net = m->private;
seq_printf(m, "\nreceive list '%s':\n", rx_list_name[idx]);
rcu_read_lock();
/* receive list for 'all' CAN devices (dev == NULL) */
- d = &can_rx_alldev_list;
+ d = net->can.can_rx_alldev_list;
can_rcvlist_proc_show_one(m, idx, NULL, d);
/* receive list for registered CAN devices */
- for_each_netdev_rcu(&init_net, dev) {
+ for_each_netdev_rcu(net, dev) {
if (dev->type == ARPHRD_CAN && dev->ml_priv)
can_rcvlist_proc_show_one(m, idx, dev, dev->ml_priv);
}
@@ -377,7 +367,7 @@ static int can_rcvlist_proc_show(struct seq_file *m, void *v)
static int can_rcvlist_proc_open(struct inode *inode, struct file *file)
{
- return single_open(file, can_rcvlist_proc_show, PDE_DATA(inode));
+ return single_open_net(inode, file, can_rcvlist_proc_show);
}
static const struct file_operations can_rcvlist_proc_fops = {
@@ -417,6 +407,7 @@ static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v)
{
struct net_device *dev;
struct dev_rcv_lists *d;
+ struct net *net = m->private;
/* RX_SFF */
seq_puts(m, "\nreceive list 'rx_sff':\n");
@@ -424,11 +415,11 @@ static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v)
rcu_read_lock();
/* sff receive list for 'all' CAN devices (dev == NULL) */
- d = &can_rx_alldev_list;
+ d = net->can.can_rx_alldev_list;
can_rcvlist_proc_show_array(m, NULL, d->rx_sff, ARRAY_SIZE(d->rx_sff));
/* sff receive list for registered CAN devices */
- for_each_netdev_rcu(&init_net, dev) {
+ for_each_netdev_rcu(net, dev) {
if (dev->type == ARPHRD_CAN && dev->ml_priv) {
d = dev->ml_priv;
can_rcvlist_proc_show_array(m, dev, d->rx_sff,
@@ -444,7 +435,7 @@ static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v)
static int can_rcvlist_sff_proc_open(struct inode *inode, struct file *file)
{
- return single_open(file, can_rcvlist_sff_proc_show, NULL);
+ return single_open_net(inode, file, can_rcvlist_sff_proc_show);
}
static const struct file_operations can_rcvlist_sff_proc_fops = {
@@ -460,6 +451,7 @@ static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v)
{
struct net_device *dev;
struct dev_rcv_lists *d;
+ struct net *net = m->private;
/* RX_EFF */
seq_puts(m, "\nreceive list 'rx_eff':\n");
@@ -467,11 +459,11 @@ static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v)
rcu_read_lock();
/* eff receive list for 'all' CAN devices (dev == NULL) */
- d = &can_rx_alldev_list;
+ d = net->can.can_rx_alldev_list;
can_rcvlist_proc_show_array(m, NULL, d->rx_eff, ARRAY_SIZE(d->rx_eff));
/* eff receive list for registered CAN devices */
- for_each_netdev_rcu(&init_net, dev) {
+ for_each_netdev_rcu(net, dev) {
if (dev->type == ARPHRD_CAN && dev->ml_priv) {
d = dev->ml_priv;
can_rcvlist_proc_show_array(m, dev, d->rx_eff,
@@ -487,7 +479,7 @@ static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v)
static int can_rcvlist_eff_proc_open(struct inode *inode, struct file *file)
{
- return single_open(file, can_rcvlist_eff_proc_show, NULL);
+ return single_open_net(inode, file, can_rcvlist_eff_proc_show);
}
static const struct file_operations can_rcvlist_eff_proc_fops = {
@@ -499,81 +491,85 @@ static const struct file_operations can_rcvlist_eff_proc_fops = {
};
/*
- * proc utility functions
- */
-
-static void can_remove_proc_readentry(const char *name)
-{
- if (can_dir)
- remove_proc_entry(name, can_dir);
-}
-
-/*
* can_init_proc - create main CAN proc directory and procfs entries
*/
-void can_init_proc(void)
+void can_init_proc(struct net *net)
{
/* create /proc/net/can directory */
- can_dir = proc_mkdir("can", init_net.proc_net);
+ net->can.proc_dir = proc_net_mkdir(net, "can", net->proc_net);
- if (!can_dir) {
- pr_info("can: failed to create /proc/net/can.\n");
+ if (!net->can.proc_dir) {
+ printk(KERN_INFO "can: failed to create /proc/net/can . "
+ "CONFIG_PROC_FS missing?\n");
return;
}
/* own procfs entries from the AF_CAN core */
- pde_version = proc_create(CAN_PROC_VERSION, 0644, can_dir,
- &can_version_proc_fops);
- pde_stats = proc_create(CAN_PROC_STATS, 0644, can_dir,
- &can_stats_proc_fops);
- pde_reset_stats = proc_create(CAN_PROC_RESET_STATS, 0644, can_dir,
- &can_reset_stats_proc_fops);
- pde_rcvlist_err = proc_create_data(CAN_PROC_RCVLIST_ERR, 0644, can_dir,
- &can_rcvlist_proc_fops, (void *)RX_ERR);
- pde_rcvlist_all = proc_create_data(CAN_PROC_RCVLIST_ALL, 0644, can_dir,
- &can_rcvlist_proc_fops, (void *)RX_ALL);
- pde_rcvlist_fil = proc_create_data(CAN_PROC_RCVLIST_FIL, 0644, can_dir,
- &can_rcvlist_proc_fops, (void *)RX_FIL);
- pde_rcvlist_inv = proc_create_data(CAN_PROC_RCVLIST_INV, 0644, can_dir,
- &can_rcvlist_proc_fops, (void *)RX_INV);
- pde_rcvlist_eff = proc_create(CAN_PROC_RCVLIST_EFF, 0644, can_dir,
- &can_rcvlist_eff_proc_fops);
- pde_rcvlist_sff = proc_create(CAN_PROC_RCVLIST_SFF, 0644, can_dir,
- &can_rcvlist_sff_proc_fops);
+ net->can.pde_version = proc_create(CAN_PROC_VERSION, 0644,
+ net->can.proc_dir,
+ &can_version_proc_fops);
+ net->can.pde_stats = proc_create(CAN_PROC_STATS, 0644,
+ net->can.proc_dir,
+ &can_stats_proc_fops);
+ net->can.pde_reset_stats = proc_create(CAN_PROC_RESET_STATS, 0644,
+ net->can.proc_dir,
+ &can_reset_stats_proc_fops);
+ net->can.pde_rcvlist_err = proc_create_data(CAN_PROC_RCVLIST_ERR, 0644,
+ net->can.proc_dir,
+ &can_rcvlist_proc_fops,
+ (void *)RX_ERR);
+ net->can.pde_rcvlist_all = proc_create_data(CAN_PROC_RCVLIST_ALL, 0644,
+ net->can.proc_dir,
+ &can_rcvlist_proc_fops,
+ (void *)RX_ALL);
+ net->can.pde_rcvlist_fil = proc_create_data(CAN_PROC_RCVLIST_FIL, 0644,
+ net->can.proc_dir,
+ &can_rcvlist_proc_fops,
+ (void *)RX_FIL);
+ net->can.pde_rcvlist_inv = proc_create_data(CAN_PROC_RCVLIST_INV, 0644,
+ net->can.proc_dir,
+ &can_rcvlist_proc_fops,
+ (void *)RX_INV);
+ net->can.pde_rcvlist_eff = proc_create(CAN_PROC_RCVLIST_EFF, 0644,
+ net->can.proc_dir,
+ &can_rcvlist_eff_proc_fops);
+ net->can.pde_rcvlist_sff = proc_create(CAN_PROC_RCVLIST_SFF, 0644,
+ net->can.proc_dir,
+ &can_rcvlist_sff_proc_fops);
}
/*
* can_remove_proc - remove procfs entries and main CAN proc directory
*/
-void can_remove_proc(void)
+void can_remove_proc(struct net *net)
{
- if (pde_version)
- can_remove_proc_readentry(CAN_PROC_VERSION);
+ if (net->can.pde_version)
+ remove_proc_entry(CAN_PROC_VERSION, net->can.proc_dir);
- if (pde_stats)
- can_remove_proc_readentry(CAN_PROC_STATS);
+ if (net->can.pde_stats)
+ remove_proc_entry(CAN_PROC_STATS, net->can.proc_dir);
- if (pde_reset_stats)
- can_remove_proc_readentry(CAN_PROC_RESET_STATS);
+ if (net->can.pde_reset_stats)
+ remove_proc_entry(CAN_PROC_RESET_STATS, net->can.proc_dir);
- if (pde_rcvlist_err)
- can_remove_proc_readentry(CAN_PROC_RCVLIST_ERR);
+ if (net->can.pde_rcvlist_err)
+ remove_proc_entry(CAN_PROC_RCVLIST_ERR, net->can.proc_dir);
- if (pde_rcvlist_all)
- can_remove_proc_readentry(CAN_PROC_RCVLIST_ALL);
+ if (net->can.pde_rcvlist_all)
+ remove_proc_entry(CAN_PROC_RCVLIST_ALL, net->can.proc_dir);
- if (pde_rcvlist_fil)
- can_remove_proc_readentry(CAN_PROC_RCVLIST_FIL);
+ if (net->can.pde_rcvlist_fil)
+ remove_proc_entry(CAN_PROC_RCVLIST_FIL, net->can.proc_dir);
- if (pde_rcvlist_inv)
- can_remove_proc_readentry(CAN_PROC_RCVLIST_INV);
+ if (net->can.pde_rcvlist_inv)
+ remove_proc_entry(CAN_PROC_RCVLIST_INV, net->can.proc_dir);
- if (pde_rcvlist_eff)
- can_remove_proc_readentry(CAN_PROC_RCVLIST_EFF);
+ if (net->can.pde_rcvlist_eff)
+ remove_proc_entry(CAN_PROC_RCVLIST_EFF, net->can.proc_dir);
- if (pde_rcvlist_sff)
- can_remove_proc_readentry(CAN_PROC_RCVLIST_SFF);
+ if (net->can.pde_rcvlist_sff)
+ remove_proc_entry(CAN_PROC_RCVLIST_SFF, net->can.proc_dir);
- if (can_dir)
- remove_proc_entry("can", init_net.proc_net);
+ if (net->can.proc_dir)
+ remove_proc_entry("can", net->proc_net);
}
diff --git a/net/can/raw.c b/net/can/raw.c
index 6dc546a..864c80d 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -181,20 +181,21 @@ static void raw_rcv(struct sk_buff *oskb, void *data)
kfree_skb(skb);
}
-static int raw_enable_filters(struct net_device *dev, struct sock *sk,
- struct can_filter *filter, int count)
+static int raw_enable_filters(struct net *net, struct net_device *dev,
+ struct sock *sk, struct can_filter *filter,
+ int count)
{
int err = 0;
int i;
for (i = 0; i < count; i++) {
- err = can_rx_register(dev, filter[i].can_id,
+ err = can_rx_register(net, dev, filter[i].can_id,
filter[i].can_mask,
raw_rcv, sk, "raw", sk);
if (err) {
/* clean up successfully registered filters */
while (--i >= 0)
- can_rx_unregister(dev, filter[i].can_id,
+ can_rx_unregister(net, dev, filter[i].can_id,
filter[i].can_mask,
raw_rcv, sk);
break;
@@ -204,57 +205,62 @@ static int raw_enable_filters(struct net_device *dev, struct sock *sk,
return err;
}
-static int raw_enable_errfilter(struct net_device *dev, struct sock *sk,
- can_err_mask_t err_mask)
+static int raw_enable_errfilter(struct net *net, struct net_device *dev,
+ struct sock *sk, can_err_mask_t err_mask)
{
int err = 0;
if (err_mask)
- err = can_rx_register(dev, 0, err_mask | CAN_ERR_FLAG,
+ err = can_rx_register(net, dev, 0, err_mask | CAN_ERR_FLAG,
raw_rcv, sk, "raw", sk);
return err;
}
-static void raw_disable_filters(struct net_device *dev, struct sock *sk,
- struct can_filter *filter, int count)
+static void raw_disable_filters(struct net *net, struct net_device *dev,
+ struct sock *sk, struct can_filter *filter,
+ int count)
{
int i;
for (i = 0; i < count; i++)
- can_rx_unregister(dev, filter[i].can_id, filter[i].can_mask,
- raw_rcv, sk);
+ can_rx_unregister(net, dev, filter[i].can_id,
+ filter[i].can_mask, raw_rcv, sk);
}
-static inline void raw_disable_errfilter(struct net_device *dev,
+static inline void raw_disable_errfilter(struct net *net,
+ struct net_device *dev,
struct sock *sk,
can_err_mask_t err_mask)
{
if (err_mask)
- can_rx_unregister(dev, 0, err_mask | CAN_ERR_FLAG,
+ can_rx_unregister(net, dev, 0, err_mask | CAN_ERR_FLAG,
raw_rcv, sk);
}
-static inline void raw_disable_allfilters(struct net_device *dev,
+static inline void raw_disable_allfilters(struct net *net,
+ struct net_device *dev,
struct sock *sk)
{
struct raw_sock *ro = raw_sk(sk);
- raw_disable_filters(dev, sk, ro->filter, ro->count);
- raw_disable_errfilter(dev, sk, ro->err_mask);
+ raw_disable_filters(net, dev, sk, ro->filter, ro->count);
+ raw_disable_errfilter(net, dev, sk, ro->err_mask);
}
-static int raw_enable_allfilters(struct net_device *dev, struct sock *sk)
+static int raw_enable_allfilters(struct net *net, struct net_device *dev,
+ struct sock *sk)
{
struct raw_sock *ro = raw_sk(sk);
int err;
- err = raw_enable_filters(dev, sk, ro->filter, ro->count);
+ err = raw_enable_filters(net, dev, sk, ro->filter, ro->count);
if (!err) {
- err = raw_enable_errfilter(dev, sk, ro->err_mask);
+ err = raw_enable_errfilter(net, dev, sk, ro->err_mask);
if (err)
- raw_disable_filters(dev, sk, ro->filter, ro->count);
+ raw_disable_filters(net, dev, sk, ro->filter,
+ ro->count);
}
return err;
@@ -267,7 +273,7 @@ static int raw_notifier(struct notifier_block *nb,
struct raw_sock *ro = container_of(nb, struct raw_sock, notifier);
struct sock *sk = &ro->sk;
- if (!net_eq(dev_net(dev), &init_net))
+ if (!net_eq(dev_net(dev), sock_net(sk)))
return NOTIFY_DONE;
if (dev->type != ARPHRD_CAN)
@@ -282,7 +288,7 @@ static int raw_notifier(struct notifier_block *nb,
lock_sock(sk);
/* remove current filters & unregister */
if (ro->bound)
- raw_disable_allfilters(dev, sk);
+ raw_disable_allfilters(dev_net(dev), dev, sk);
if (ro->count > 1)
kfree(ro->filter);
@@ -358,13 +364,13 @@ static int raw_release(struct socket *sock)
if (ro->ifindex) {
struct net_device *dev;
- dev = dev_get_by_index(&init_net, ro->ifindex);
+ dev = dev_get_by_index(sock_net(sk), ro->ifindex);
if (dev) {
- raw_disable_allfilters(dev, sk);
+ raw_disable_allfilters(dev_net(dev), dev, sk);
dev_put(dev);
}
} else
- raw_disable_allfilters(NULL, sk);
+ raw_disable_allfilters(sock_net(sk), NULL, sk);
}
if (ro->count > 1)
@@ -404,7 +410,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len)
if (addr->can_ifindex) {
struct net_device *dev;
- dev = dev_get_by_index(&init_net, addr->can_ifindex);
+ dev = dev_get_by_index(sock_net(sk), addr->can_ifindex);
if (!dev) {
err = -ENODEV;
goto out;
@@ -420,13 +426,13 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len)
ifindex = dev->ifindex;
/* filters set by default/setsockopt */
- err = raw_enable_allfilters(dev, sk);
+ err = raw_enable_allfilters(sock_net(sk), dev, sk);
dev_put(dev);
} else {
ifindex = 0;
/* filters set by default/setsockopt */
- err = raw_enable_allfilters(NULL, sk);
+ err = raw_enable_allfilters(sock_net(sk), NULL, sk);
}
if (!err) {
@@ -435,13 +441,15 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len)
if (ro->ifindex) {
struct net_device *dev;
- dev = dev_get_by_index(&init_net, ro->ifindex);
+ dev = dev_get_by_index(sock_net(sk),
+ ro->ifindex);
if (dev) {
- raw_disable_allfilters(dev, sk);
+ raw_disable_allfilters(dev_net(dev),
+ dev, sk);
dev_put(dev);
}
} else
- raw_disable_allfilters(NULL, sk);
+ raw_disable_allfilters(sock_net(sk), NULL, sk);
}
ro->ifindex = ifindex;
ro->bound = 1;
@@ -517,15 +525,16 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
lock_sock(sk);
if (ro->bound && ro->ifindex)
- dev = dev_get_by_index(&init_net, ro->ifindex);
+ dev = dev_get_by_index(sock_net(sk), ro->ifindex);
if (ro->bound) {
/* (try to) register the new filters */
if (count == 1)
- err = raw_enable_filters(dev, sk, &sfilter, 1);
+ err = raw_enable_filters(sock_net(sk), dev, sk,
+ &sfilter, 1);
else
- err = raw_enable_filters(dev, sk, filter,
- count);
+ err = raw_enable_filters(sock_net(sk), dev, sk,
+ filter, count);
if (err) {
if (count > 1)
kfree(filter);
@@ -533,7 +542,8 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
}
/* remove old filter registrations */
- raw_disable_filters(dev, sk, ro->filter, ro->count);
+ raw_disable_filters(sock_net(sk), dev, sk, ro->filter,
+ ro->count);
}
/* remove old filter space */
@@ -569,18 +579,20 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
lock_sock(sk);
if (ro->bound && ro->ifindex)
- dev = dev_get_by_index(&init_net, ro->ifindex);
+ dev = dev_get_by_index(sock_net(sk), ro->ifindex);
/* remove current error mask */
if (ro->bound) {
/* (try to) register the new err_mask */
- err = raw_enable_errfilter(dev, sk, err_mask);
+ err = raw_enable_errfilter(sock_net(sk), dev, sk,
+ err_mask);
if (err)
goto out_err;
/* remove old err_mask registration */
- raw_disable_errfilter(dev, sk, ro->err_mask);
+ raw_disable_errfilter(sock_net(sk), dev, sk,
+ ro->err_mask);
}
/* link new err_mask to the socket */
@@ -741,7 +753,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
return -EINVAL;
}
- dev = dev_get_by_index(&init_net, ifindex);
+ dev = dev_get_by_index(sock_net(sk), ifindex);
if (!dev)
return -ENXIO;
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 464e885..1085338 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -230,6 +230,7 @@ enum {
Opt_osdkeepalivetimeout,
Opt_mount_timeout,
Opt_osd_idle_ttl,
+ Opt_osd_request_timeout,
Opt_last_int,
/* int args above */
Opt_fsid,
@@ -256,6 +257,7 @@ static match_table_t opt_tokens = {
{Opt_osdkeepalivetimeout, "osdkeepalive=%d"},
{Opt_mount_timeout, "mount_timeout=%d"},
{Opt_osd_idle_ttl, "osd_idle_ttl=%d"},
+ {Opt_osd_request_timeout, "osd_request_timeout=%d"},
/* int args above */
{Opt_fsid, "fsid=%s"},
{Opt_name, "name=%s"},
@@ -361,6 +363,7 @@ ceph_parse_options(char *options, const char *dev_name,
opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT;
opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT;
opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT;
+ opt->osd_request_timeout = CEPH_OSD_REQUEST_TIMEOUT_DEFAULT;
/* get mon ip(s) */
/* ip1[:port1][,ip2[:port2]...] */
@@ -473,6 +476,15 @@ ceph_parse_options(char *options, const char *dev_name,
}
opt->mount_timeout = msecs_to_jiffies(intval * 1000);
break;
+ case Opt_osd_request_timeout:
+ /* 0 is "wait forever" (i.e. infinite timeout) */
+ if (intval < 0 || intval > INT_MAX / 1000) {
+ pr_err("osd_request_timeout out of range\n");
+ err = -EINVAL;
+ goto out;
+ }
+ opt->osd_request_timeout = msecs_to_jiffies(intval * 1000);
+ break;
case Opt_share:
opt->flags &= ~CEPH_OPT_NOSHARE;
@@ -557,6 +569,9 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client)
if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT)
seq_printf(m, "osdkeepalivetimeout=%d,",
jiffies_to_msecs(opt->osd_keepalive_timeout) / 1000);
+ if (opt->osd_request_timeout != CEPH_OSD_REQUEST_TIMEOUT_DEFAULT)
+ seq_printf(m, "osd_request_timeout=%d,",
+ jiffies_to_msecs(opt->osd_request_timeout) / 1000);
/* drop redundant comma */
if (m->count != pos)
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 38dcf1e..f76bb33 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -7,6 +7,7 @@
#include <linux/kthread.h>
#include <linux/net.h>
#include <linux/nsproxy.h>
+#include <linux/sched/mm.h>
#include <linux/slab.h>
#include <linux/socket.h>
#include <linux/string.h>
@@ -469,11 +470,16 @@ static int ceph_tcp_connect(struct ceph_connection *con)
{
struct sockaddr_storage *paddr = &con->peer_addr.in_addr;
struct socket *sock;
+ unsigned int noio_flag;
int ret;
BUG_ON(con->sock);
+
+ /* sock_create_kern() allocates with GFP_KERNEL */
+ noio_flag = memalloc_noio_save();
ret = sock_create_kern(read_pnet(&con->msgr->net), paddr->ss_family,
SOCK_STREAM, IPPROTO_TCP, &sock);
+ memalloc_noio_restore(noio_flag);
if (ret)
return ret;
sock->sk->sk_allocation = GFP_NOFS;
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index b65bbf9..e15ea9e 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1709,6 +1709,8 @@ static void account_request(struct ceph_osd_request *req)
req->r_flags |= CEPH_OSD_FLAG_ONDISK;
atomic_inc(&req->r_osdc->num_requests);
+
+ req->r_start_stamp = jiffies;
}
static void submit_request(struct ceph_osd_request *req, bool wrlocked)
@@ -1789,6 +1791,14 @@ static void cancel_request(struct ceph_osd_request *req)
ceph_osdc_put_request(req);
}
+static void abort_request(struct ceph_osd_request *req, int err)
+{
+ dout("%s req %p tid %llu err %d\n", __func__, req, req->r_tid, err);
+
+ cancel_map_check(req);
+ complete_request(req, err);
+}
+
static void check_pool_dne(struct ceph_osd_request *req)
{
struct ceph_osd_client *osdc = req->r_osdc;
@@ -2487,6 +2497,7 @@ static void handle_timeout(struct work_struct *work)
container_of(work, struct ceph_osd_client, timeout_work.work);
struct ceph_options *opts = osdc->client->options;
unsigned long cutoff = jiffies - opts->osd_keepalive_timeout;
+ unsigned long expiry_cutoff = jiffies - opts->osd_request_timeout;
LIST_HEAD(slow_osds);
struct rb_node *n, *p;
@@ -2502,15 +2513,23 @@ static void handle_timeout(struct work_struct *work)
struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);
bool found = false;
- for (p = rb_first(&osd->o_requests); p; p = rb_next(p)) {
+ for (p = rb_first(&osd->o_requests); p; ) {
struct ceph_osd_request *req =
rb_entry(p, struct ceph_osd_request, r_node);
+ p = rb_next(p); /* abort_request() */
+
if (time_before(req->r_stamp, cutoff)) {
dout(" req %p tid %llu on osd%d is laggy\n",
req, req->r_tid, osd->o_osd);
found = true;
}
+ if (opts->osd_request_timeout &&
+ time_before(req->r_start_stamp, expiry_cutoff)) {
+ pr_err_ratelimited("tid %llu on osd%d timeout\n",
+ req->r_tid, osd->o_osd);
+ abort_request(req, -ETIMEDOUT);
+ }
}
for (p = rb_first(&osd->o_linger_requests); p; p = rb_next(p)) {
struct ceph_osd_linger_request *lreq =
@@ -2530,6 +2549,21 @@ static void handle_timeout(struct work_struct *work)
list_move_tail(&osd->o_keepalive_item, &slow_osds);
}
+ if (opts->osd_request_timeout) {
+ for (p = rb_first(&osdc->homeless_osd.o_requests); p; ) {
+ struct ceph_osd_request *req =
+ rb_entry(p, struct ceph_osd_request, r_node);
+
+ p = rb_next(p); /* abort_request() */
+
+ if (time_before(req->r_start_stamp, expiry_cutoff)) {
+ pr_err_ratelimited("tid %llu on osd%d timeout\n",
+ req->r_tid, osdc->homeless_osd.o_osd);
+ abort_request(req, -ETIMEDOUT);
+ }
+ }
+ }
+
if (atomic_read(&osdc->num_homeless) || !list_empty(&slow_osds))
maybe_request_map(osdc);
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 6824c0e..ffe9e90 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -390,9 +390,8 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
dout("crush decode tunable chooseleaf_stable = %d\n",
c->chooseleaf_stable);
- crush_finalize(c);
-
done:
+ crush_finalize(c);
dout("crush_decode success\n");
return c;
@@ -1380,7 +1379,6 @@ static int decode_new_up_state_weight(void **p, void *end,
if ((map->osd_state[osd] & CEPH_OSD_EXISTS) &&
(xorstate & CEPH_OSD_EXISTS)) {
pr_info("osd%d does not exist\n", osd);
- map->osd_weight[osd] = CEPH_OSD_IN;
ret = set_primary_affinity(map, osd,
CEPH_OSD_DEFAULT_PRIMARY_AFFINITY);
if (ret)
diff --git a/net/core/datagram.c b/net/core/datagram.c
index ea63334..4608aa2 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -256,8 +256,12 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
}
spin_unlock_irqrestore(&queue->lock, cpu_flags);
- } while (sk_can_busy_loop(sk) &&
- sk_busy_loop(sk, flags & MSG_DONTWAIT));
+
+ if (!sk_can_busy_loop(sk))
+ break;
+
+ sk_busy_loop(sk, flags & MSG_DONTWAIT);
+ } while (!skb_queue_empty(&sk->sk_receive_queue));
error = -EAGAIN;
diff --git a/net/core/dev.c b/net/core/dev.c
index 8637b2b..ef9fe60e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1304,6 +1304,7 @@ void netdev_notify_peers(struct net_device *dev)
{
rtnl_lock();
call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev);
+ call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev);
rtnl_unlock();
}
EXPORT_SYMBOL(netdev_notify_peers);
@@ -5059,27 +5060,28 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock)
do_softirq();
}
-bool sk_busy_loop(struct sock *sk, int nonblock)
+void napi_busy_loop(unsigned int napi_id,
+ bool (*loop_end)(void *, unsigned long),
+ void *loop_end_arg)
{
- unsigned long end_time = !nonblock ? sk_busy_loop_end_time(sk) : 0;
+ unsigned long start_time = loop_end ? busy_loop_current_time() : 0;
int (*napi_poll)(struct napi_struct *napi, int budget);
void *have_poll_lock = NULL;
struct napi_struct *napi;
- int rc;
restart:
- rc = false;
napi_poll = NULL;
rcu_read_lock();
- napi = napi_by_id(sk->sk_napi_id);
+ napi = napi_by_id(napi_id);
if (!napi)
goto out;
preempt_disable();
for (;;) {
- rc = 0;
+ int work = 0;
+
local_bh_disable();
if (!napi_poll) {
unsigned long val = READ_ONCE(napi->state);
@@ -5097,16 +5099,15 @@ bool sk_busy_loop(struct sock *sk, int nonblock)
have_poll_lock = netpoll_poll_lock(napi);
napi_poll = napi->poll;
}
- rc = napi_poll(napi, BUSY_POLL_BUDGET);
- trace_napi_poll(napi, rc, BUSY_POLL_BUDGET);
+ work = napi_poll(napi, BUSY_POLL_BUDGET);
+ trace_napi_poll(napi, work, BUSY_POLL_BUDGET);
count:
- if (rc > 0)
- __NET_ADD_STATS(sock_net(sk),
- LINUX_MIB_BUSYPOLLRXPACKETS, rc);
+ if (work > 0)
+ __NET_ADD_STATS(dev_net(napi->dev),
+ LINUX_MIB_BUSYPOLLRXPACKETS, work);
local_bh_enable();
- if (nonblock || !skb_queue_empty(&sk->sk_receive_queue) ||
- busy_loop_timeout(end_time))
+ if (!loop_end || loop_end(loop_end_arg, start_time))
break;
if (unlikely(need_resched())) {
@@ -5115,9 +5116,8 @@ bool sk_busy_loop(struct sock *sk, int nonblock)
preempt_enable();
rcu_read_unlock();
cond_resched();
- rc = !skb_queue_empty(&sk->sk_receive_queue);
- if (rc || busy_loop_timeout(end_time))
- return rc;
+ if (loop_end(loop_end_arg, start_time))
+ return;
goto restart;
}
cpu_relax();
@@ -5125,12 +5125,10 @@ bool sk_busy_loop(struct sock *sk, int nonblock)
if (napi_poll)
busy_poll_stop(napi, have_poll_lock);
preempt_enable();
- rc = !skb_queue_empty(&sk->sk_receive_queue);
out:
rcu_read_unlock();
- return rc;
}
-EXPORT_SYMBOL(sk_busy_loop);
+EXPORT_SYMBOL(napi_busy_loop);
#endif /* CONFIG_NET_RX_BUSY_POLL */
@@ -5142,10 +5140,10 @@ static void napi_hash_add(struct napi_struct *napi)
spin_lock(&napi_hash_lock);
- /* 0..NR_CPUS+1 range is reserved for sender_cpu use */
+ /* 0..NR_CPUS range is reserved for sender_cpu use */
do {
- if (unlikely(++napi_gen_id < NR_CPUS + 1))
- napi_gen_id = NR_CPUS + 1;
+ if (unlikely(++napi_gen_id < MIN_NAPI_ID))
+ napi_gen_id = MIN_NAPI_ID;
} while (napi_by_id(napi_gen_id));
napi->napi_id = napi_gen_id;
diff --git a/net/core/devlink.c b/net/core/devlink.c
index e9c1e6a..24b7660 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -1493,10 +1493,688 @@ static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb,
if (err)
return err;
}
-
return 0;
}
+int devlink_dpipe_match_put(struct sk_buff *skb,
+ struct devlink_dpipe_match *match)
+{
+ struct devlink_dpipe_header *header = match->header;
+ struct devlink_dpipe_field *field = &header->fields[match->field_id];
+ struct nlattr *match_attr;
+
+ match_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_MATCH);
+ if (!match_attr)
+ return -EMSGSIZE;
+
+ if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_MATCH_TYPE, match->type) ||
+ nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, match->header_index) ||
+ nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) ||
+ nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) ||
+ nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, match_attr);
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(skb, match_attr);
+ return -EMSGSIZE;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_match_put);
+
+static int devlink_dpipe_matches_put(struct devlink_dpipe_table *table,
+ struct sk_buff *skb)
+{
+ struct nlattr *matches_attr;
+
+ matches_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE_MATCHES);
+ if (!matches_attr)
+ return -EMSGSIZE;
+
+ if (table->table_ops->matches_dump(table->priv, skb))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, matches_attr);
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(skb, matches_attr);
+ return -EMSGSIZE;
+}
+
+int devlink_dpipe_action_put(struct sk_buff *skb,
+ struct devlink_dpipe_action *action)
+{
+ struct devlink_dpipe_header *header = action->header;
+ struct devlink_dpipe_field *field = &header->fields[action->field_id];
+ struct nlattr *action_attr;
+
+ action_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_ACTION);
+ if (!action_attr)
+ return -EMSGSIZE;
+
+ if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_ACTION_TYPE, action->type) ||
+ nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, action->header_index) ||
+ nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) ||
+ nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) ||
+ nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, action_attr);
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(skb, action_attr);
+ return -EMSGSIZE;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_action_put);
+
+static int devlink_dpipe_actions_put(struct devlink_dpipe_table *table,
+ struct sk_buff *skb)
+{
+ struct nlattr *actions_attr;
+
+ actions_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE_ACTIONS);
+ if (!actions_attr)
+ return -EMSGSIZE;
+
+ if (table->table_ops->actions_dump(table->priv, skb))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, actions_attr);
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(skb, actions_attr);
+ return -EMSGSIZE;
+}
+
+static int devlink_dpipe_table_put(struct sk_buff *skb,
+ struct devlink_dpipe_table *table)
+{
+ struct nlattr *table_attr;
+
+ table_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE);
+ if (!table_attr)
+ return -EMSGSIZE;
+
+ if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_TABLE_NAME, table->name) ||
+ nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_SIZE, table->size,
+ DEVLINK_ATTR_PAD))
+ goto nla_put_failure;
+ if (nla_put_u8(skb, DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED,
+ table->counters_enabled))
+ goto nla_put_failure;
+
+ if (devlink_dpipe_matches_put(table, skb))
+ goto nla_put_failure;
+
+ if (devlink_dpipe_actions_put(table, skb))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, table_attr);
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(skb, table_attr);
+ return -EMSGSIZE;
+}
+
+static int devlink_dpipe_send_and_alloc_skb(struct sk_buff **pskb,
+ struct genl_info *info)
+{
+ int err;
+
+ if (*pskb) {
+ err = genlmsg_reply(*pskb, info);
+ if (err)
+ return err;
+ }
+ *pskb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!*pskb)
+ return -ENOMEM;
+ return 0;
+}
+
+static int devlink_dpipe_tables_fill(struct genl_info *info,
+ enum devlink_command cmd, int flags,
+ struct list_head *dpipe_tables,
+ const char *table_name)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ struct devlink_dpipe_table *table;
+ struct nlattr *tables_attr;
+ struct sk_buff *skb = NULL;
+ struct nlmsghdr *nlh;
+ bool incomplete;
+ void *hdr;
+ int i;
+ int err;
+
+ table = list_first_entry(dpipe_tables,
+ struct devlink_dpipe_table, list);
+start_again:
+ err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+ if (err)
+ return err;
+
+ hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq,
+ &devlink_nl_family, NLM_F_MULTI, cmd);
+ if (!hdr)
+ return -EMSGSIZE;
+
+ if (devlink_nl_put_handle(skb, devlink))
+ goto nla_put_failure;
+ tables_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLES);
+ if (!tables_attr)
+ goto nla_put_failure;
+
+ i = 0;
+ incomplete = false;
+ list_for_each_entry_from(table, dpipe_tables, list) {
+ if (!table_name) {
+ err = devlink_dpipe_table_put(skb, table);
+ if (err) {
+ if (!i)
+ goto err_table_put;
+ incomplete = true;
+ break;
+ }
+ } else {
+ if (!strcmp(table->name, table_name)) {
+ err = devlink_dpipe_table_put(skb, table);
+ if (err)
+ break;
+ }
+ }
+ i++;
+ }
+
+ nla_nest_end(skb, tables_attr);
+ genlmsg_end(skb, hdr);
+ if (incomplete)
+ goto start_again;
+
+send_done:
+ nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq,
+ NLMSG_DONE, 0, flags | NLM_F_MULTI);
+ if (!nlh) {
+ err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+ if (err)
+ goto err_skb_send_alloc;
+ goto send_done;
+ }
+
+ return genlmsg_reply(skb, info);
+
+nla_put_failure:
+ err = -EMSGSIZE;
+err_table_put:
+err_skb_send_alloc:
+ genlmsg_cancel(skb, hdr);
+ nlmsg_free(skb);
+ return err;
+}
+
+static int devlink_nl_cmd_dpipe_table_get(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ const char *table_name = NULL;
+
+ if (info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME])
+ table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]);
+
+ return devlink_dpipe_tables_fill(info, DEVLINK_CMD_DPIPE_TABLE_GET, 0,
+ &devlink->dpipe_table_list,
+ table_name);
+}
+
+static int devlink_dpipe_value_put(struct sk_buff *skb,
+ struct devlink_dpipe_value *value)
+{
+ if (nla_put(skb, DEVLINK_ATTR_DPIPE_VALUE,
+ value->value_size, value->value))
+ return -EMSGSIZE;
+ if (value->mask)
+ if (nla_put(skb, DEVLINK_ATTR_DPIPE_VALUE_MASK,
+ value->value_size, value->mask))
+ return -EMSGSIZE;
+ if (value->mapping_valid)
+ if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_VALUE_MAPPING,
+ value->mapping_value))
+ return -EMSGSIZE;
+ return 0;
+}
+
+static int devlink_dpipe_action_value_put(struct sk_buff *skb,
+ struct devlink_dpipe_value *value)
+{
+ if (!value->action)
+ return -EINVAL;
+ if (devlink_dpipe_action_put(skb, value->action))
+ return -EMSGSIZE;
+ if (devlink_dpipe_value_put(skb, value))
+ return -EMSGSIZE;
+ return 0;
+}
+
+static int devlink_dpipe_action_values_put(struct sk_buff *skb,
+ struct devlink_dpipe_value *values,
+ unsigned int values_count)
+{
+ struct nlattr *action_attr;
+ int i;
+ int err;
+
+ for (i = 0; i < values_count; i++) {
+ action_attr = nla_nest_start(skb,
+ DEVLINK_ATTR_DPIPE_ACTION_VALUE);
+ if (!action_attr)
+ return -EMSGSIZE;
+ err = devlink_dpipe_action_value_put(skb, &values[i]);
+ if (err)
+ goto err_action_value_put;
+ nla_nest_end(skb, action_attr);
+ }
+ return 0;
+
+err_action_value_put:
+ nla_nest_cancel(skb, action_attr);
+ return err;
+}
+
+static int devlink_dpipe_match_value_put(struct sk_buff *skb,
+ struct devlink_dpipe_value *value)
+{
+ if (!value->match)
+ return -EINVAL;
+ if (devlink_dpipe_match_put(skb, value->match))
+ return -EMSGSIZE;
+ if (devlink_dpipe_value_put(skb, value))
+ return -EMSGSIZE;
+ return 0;
+}
+
+static int devlink_dpipe_match_values_put(struct sk_buff *skb,
+ struct devlink_dpipe_value *values,
+ unsigned int values_count)
+{
+ struct nlattr *match_attr;
+ int i;
+ int err;
+
+ for (i = 0; i < values_count; i++) {
+ match_attr = nla_nest_start(skb,
+ DEVLINK_ATTR_DPIPE_MATCH_VALUE);
+ if (!match_attr)
+ return -EMSGSIZE;
+ err = devlink_dpipe_match_value_put(skb, &values[i]);
+ if (err)
+ goto err_match_value_put;
+ nla_nest_end(skb, match_attr);
+ }
+ return 0;
+
+err_match_value_put:
+ nla_nest_cancel(skb, match_attr);
+ return err;
+}
+
+static int devlink_dpipe_entry_put(struct sk_buff *skb,
+ struct devlink_dpipe_entry *entry)
+{
+ struct nlattr *entry_attr, *matches_attr, *actions_attr;
+ int err;
+
+ entry_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_ENTRY);
+ if (!entry_attr)
+ return -EMSGSIZE;
+
+ if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_ENTRY_INDEX, entry->index,
+ DEVLINK_ATTR_PAD))
+ goto nla_put_failure;
+ if (entry->counter_valid)
+ if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_ENTRY_COUNTER,
+ entry->counter, DEVLINK_ATTR_PAD))
+ goto nla_put_failure;
+
+ matches_attr = nla_nest_start(skb,
+ DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES);
+ if (!matches_attr)
+ goto nla_put_failure;
+
+ err = devlink_dpipe_match_values_put(skb, entry->match_values,
+ entry->match_values_count);
+ if (err) {
+ nla_nest_cancel(skb, matches_attr);
+ goto err_match_values_put;
+ }
+ nla_nest_end(skb, matches_attr);
+
+ actions_attr = nla_nest_start(skb,
+ DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES);
+ if (!actions_attr)
+ goto nla_put_failure;
+
+ err = devlink_dpipe_action_values_put(skb, entry->action_values,
+ entry->action_values_count);
+ if (err) {
+ nla_nest_cancel(skb, actions_attr);
+ goto err_action_values_put;
+ }
+ nla_nest_end(skb, actions_attr);
+
+ nla_nest_end(skb, entry_attr);
+ return 0;
+
+nla_put_failure:
+ err = -EMSGSIZE;
+err_match_values_put:
+err_action_values_put:
+ nla_nest_cancel(skb, entry_attr);
+ return err;
+}
+
+static struct devlink_dpipe_table *
+devlink_dpipe_table_find(struct list_head *dpipe_tables,
+ const char *table_name)
+{
+ struct devlink_dpipe_table *table;
+
+ list_for_each_entry_rcu(table, dpipe_tables, list) {
+ if (!strcmp(table->name, table_name))
+ return table;
+ }
+ return NULL;
+}
+
+int devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+ struct devlink *devlink;
+ int err;
+
+ err = devlink_dpipe_send_and_alloc_skb(&dump_ctx->skb,
+ dump_ctx->info);
+ if (err)
+ return err;
+
+ dump_ctx->hdr = genlmsg_put(dump_ctx->skb,
+ dump_ctx->info->snd_portid,
+ dump_ctx->info->snd_seq,
+ &devlink_nl_family, NLM_F_MULTI,
+ dump_ctx->cmd);
+ if (!dump_ctx->hdr)
+ goto nla_put_failure;
+
+ devlink = dump_ctx->info->user_ptr[0];
+ if (devlink_nl_put_handle(dump_ctx->skb, devlink))
+ goto nla_put_failure;
+ dump_ctx->nest = nla_nest_start(dump_ctx->skb,
+ DEVLINK_ATTR_DPIPE_ENTRIES);
+ if (!dump_ctx->nest)
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ genlmsg_cancel(dump_ctx->skb, dump_ctx->hdr);
+ nlmsg_free(dump_ctx->skb);
+ return -EMSGSIZE;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_prepare);
+
+int devlink_dpipe_entry_ctx_append(struct devlink_dpipe_dump_ctx *dump_ctx,
+ struct devlink_dpipe_entry *entry)
+{
+ return devlink_dpipe_entry_put(dump_ctx->skb, entry);
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_append);
+
+int devlink_dpipe_entry_ctx_close(struct devlink_dpipe_dump_ctx *dump_ctx)
+{
+ nla_nest_end(dump_ctx->skb, dump_ctx->nest);
+ genlmsg_end(dump_ctx->skb, dump_ctx->hdr);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_close);
+
+static int devlink_dpipe_entries_fill(struct genl_info *info,
+ enum devlink_command cmd, int flags,
+ struct devlink_dpipe_table *table)
+{
+ struct devlink_dpipe_dump_ctx dump_ctx;
+ struct nlmsghdr *nlh;
+ int err;
+
+ dump_ctx.skb = NULL;
+ dump_ctx.cmd = cmd;
+ dump_ctx.info = info;
+
+ err = table->table_ops->entries_dump(table->priv,
+ table->counters_enabled,
+ &dump_ctx);
+ if (err)
+ goto err_entries_dump;
+
+send_done:
+ nlh = nlmsg_put(dump_ctx.skb, info->snd_portid, info->snd_seq,
+ NLMSG_DONE, 0, flags | NLM_F_MULTI);
+ if (!nlh) {
+ err = devlink_dpipe_send_and_alloc_skb(&dump_ctx.skb, info);
+ if (err)
+ goto err_skb_send_alloc;
+ goto send_done;
+ }
+ return genlmsg_reply(dump_ctx.skb, info);
+
+err_entries_dump:
+err_skb_send_alloc:
+ genlmsg_cancel(dump_ctx.skb, dump_ctx.hdr);
+ nlmsg_free(dump_ctx.skb);
+ return err;
+}
+
+static int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ struct devlink_dpipe_table *table;
+ const char *table_name;
+
+ if (!info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME])
+ return -EINVAL;
+
+ table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]);
+ table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
+ table_name);
+ if (!table)
+ return -EINVAL;
+
+ if (!table->table_ops->entries_dump)
+ return -EINVAL;
+
+ return devlink_dpipe_entries_fill(info, DEVLINK_CMD_DPIPE_ENTRIES_GET,
+ 0, table);
+}
+
+static int devlink_dpipe_fields_put(struct sk_buff *skb,
+ const struct devlink_dpipe_header *header)
+{
+ struct devlink_dpipe_field *field;
+ struct nlattr *field_attr;
+ int i;
+
+ for (i = 0; i < header->fields_count; i++) {
+ field = &header->fields[i];
+ field_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_FIELD);
+ if (!field_attr)
+ return -EMSGSIZE;
+ if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_FIELD_NAME, field->name) ||
+ nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) ||
+ nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH, field->bitwidth) ||
+ nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE, field->mapping_type))
+ goto nla_put_failure;
+ nla_nest_end(skb, field_attr);
+ }
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(skb, field_attr);
+ return -EMSGSIZE;
+}
+
+static int devlink_dpipe_header_put(struct sk_buff *skb,
+ struct devlink_dpipe_header *header)
+{
+ struct nlattr *fields_attr, *header_attr;
+ int err;
+
+ header_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADER);
+ if (!header)
+ return -EMSGSIZE;
+
+ if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_HEADER_NAME, header->name) ||
+ nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) ||
+ nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global))
+ goto nla_put_failure;
+
+ fields_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADER_FIELDS);
+ if (!fields_attr)
+ goto nla_put_failure;
+
+ err = devlink_dpipe_fields_put(skb, header);
+ if (err) {
+ nla_nest_cancel(skb, fields_attr);
+ goto nla_put_failure;
+ }
+ nla_nest_end(skb, fields_attr);
+ nla_nest_end(skb, header_attr);
+ return 0;
+
+nla_put_failure:
+ err = -EMSGSIZE;
+ nla_nest_cancel(skb, header_attr);
+ return err;
+}
+
+static int devlink_dpipe_headers_fill(struct genl_info *info,
+ enum devlink_command cmd, int flags,
+ struct devlink_dpipe_headers *
+ dpipe_headers)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ struct nlattr *headers_attr;
+ struct sk_buff *skb = NULL;
+ struct nlmsghdr *nlh;
+ void *hdr;
+ int i, j;
+ int err;
+
+ i = 0;
+start_again:
+ err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+ if (err)
+ return err;
+
+ hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq,
+ &devlink_nl_family, NLM_F_MULTI, cmd);
+ if (!hdr)
+ return -EMSGSIZE;
+
+ if (devlink_nl_put_handle(skb, devlink))
+ goto nla_put_failure;
+ headers_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADERS);
+ if (!headers_attr)
+ goto nla_put_failure;
+
+ j = 0;
+ for (; i < dpipe_headers->headers_count; i++) {
+ err = devlink_dpipe_header_put(skb, dpipe_headers->headers[i]);
+ if (err) {
+ if (!j)
+ goto err_table_put;
+ break;
+ }
+ j++;
+ }
+ nla_nest_end(skb, headers_attr);
+ genlmsg_end(skb, hdr);
+ if (i != dpipe_headers->headers_count)
+ goto start_again;
+
+send_done:
+ nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq,
+ NLMSG_DONE, 0, flags | NLM_F_MULTI);
+ if (!nlh) {
+ err = devlink_dpipe_send_and_alloc_skb(&skb, info);
+ if (err)
+ goto err_skb_send_alloc;
+ goto send_done;
+ }
+ return genlmsg_reply(skb, info);
+
+nla_put_failure:
+ err = -EMSGSIZE;
+err_table_put:
+err_skb_send_alloc:
+ genlmsg_cancel(skb, hdr);
+ nlmsg_free(skb);
+ return err;
+}
+
+static int devlink_nl_cmd_dpipe_headers_get(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+
+ if (!devlink->dpipe_headers)
+ return -EOPNOTSUPP;
+ return devlink_dpipe_headers_fill(info, DEVLINK_CMD_DPIPE_HEADERS_GET,
+ 0, devlink->dpipe_headers);
+}
+
+static int devlink_dpipe_table_counters_set(struct devlink *devlink,
+ const char *table_name,
+ bool enable)
+{
+ struct devlink_dpipe_table *table;
+
+ table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
+ table_name);
+ if (!table)
+ return -EINVAL;
+
+ if (table->counter_control_extern)
+ return -EOPNOTSUPP;
+
+ if (!(table->counters_enabled ^ enable))
+ return 0;
+
+ table->counters_enabled = enable;
+ if (table->table_ops->counters_set_update)
+ table->table_ops->counters_set_update(table->priv, enable);
+ return 0;
+}
+
+static int devlink_nl_cmd_dpipe_table_counters_set(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink *devlink = info->user_ptr[0];
+ const char *table_name;
+ bool counters_enable;
+
+ if (!info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME] ||
+ !info->attrs[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED])
+ return -EINVAL;
+
+ table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]);
+ counters_enable = !!nla_get_u8(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED]);
+
+ return devlink_dpipe_table_counters_set(devlink, table_name,
+ counters_enable);
+}
+
static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING },
[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING },
@@ -1512,6 +2190,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
[DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 },
[DEVLINK_ATTR_ESWITCH_MODE] = { .type = NLA_U16 },
[DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .type = NLA_U8 },
+ [DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING },
+ [DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .type = NLA_U8 },
};
static const struct genl_ops devlink_nl_ops[] = {
@@ -1644,6 +2324,34 @@ static const struct genl_ops devlink_nl_ops[] = {
.flags = GENL_ADMIN_PERM,
.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
},
+ {
+ .cmd = DEVLINK_CMD_DPIPE_TABLE_GET,
+ .doit = devlink_nl_cmd_dpipe_table_get,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
+ {
+ .cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET,
+ .doit = devlink_nl_cmd_dpipe_entries_get,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
+ {
+ .cmd = DEVLINK_CMD_DPIPE_HEADERS_GET,
+ .doit = devlink_nl_cmd_dpipe_headers_get,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
+ {
+ .cmd = DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET,
+ .doit = devlink_nl_cmd_dpipe_table_counters_set,
+ .policy = devlink_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+ },
};
static struct genl_family devlink_nl_family __ro_after_init = {
@@ -1680,6 +2388,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
devlink_net_set(devlink, &init_net);
INIT_LIST_HEAD(&devlink->port_list);
INIT_LIST_HEAD(&devlink->sb_list);
+ INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list);
return devlink;
}
EXPORT_SYMBOL_GPL(devlink_alloc);
@@ -1880,6 +2589,133 @@ void devlink_sb_unregister(struct devlink *devlink, unsigned int sb_index)
}
EXPORT_SYMBOL_GPL(devlink_sb_unregister);
+/**
+ * devlink_dpipe_headers_register - register dpipe headers
+ *
+ * @devlink: devlink
+ * @dpipe_headers: dpipe header array
+ *
+ * Register the headers supported by hardware.
+ */
+int devlink_dpipe_headers_register(struct devlink *devlink,
+ struct devlink_dpipe_headers *dpipe_headers)
+{
+ mutex_lock(&devlink_mutex);
+ devlink->dpipe_headers = dpipe_headers;
+ mutex_unlock(&devlink_mutex);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_headers_register);
+
+/**
+ * devlink_dpipe_headers_unregister - unregister dpipe headers
+ *
+ * @devlink: devlink
+ *
+ * Unregister the headers supported by hardware.
+ */
+void devlink_dpipe_headers_unregister(struct devlink *devlink)
+{
+ mutex_lock(&devlink_mutex);
+ devlink->dpipe_headers = NULL;
+ mutex_unlock(&devlink_mutex);
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_headers_unregister);
+
+/**
+ * devlink_dpipe_table_counter_enabled - check if counter allocation
+ * required
+ * @devlink: devlink
+ * @table_name: tables name
+ *
+ * Used by driver to check if counter allocation is required.
+ * After counter allocation is turned on the table entries
+ * are updated to include counter statistics.
+ *
+ * After that point on the driver must respect the counter
+ * state so that each entry added to the table is added
+ * with a counter.
+ */
+bool devlink_dpipe_table_counter_enabled(struct devlink *devlink,
+ const char *table_name)
+{
+ struct devlink_dpipe_table *table;
+ bool enabled;
+
+ rcu_read_lock();
+ table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
+ table_name);
+ enabled = false;
+ if (table)
+ enabled = table->counters_enabled;
+ rcu_read_unlock();
+ return enabled;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_table_counter_enabled);
+
+/**
+ * devlink_dpipe_table_register - register dpipe table
+ *
+ * @devlink: devlink
+ * @table_name: table name
+ * @table_ops: table ops
+ * @priv: priv
+ * @size: size
+ * @counter_control_extern: external control for counters
+ */
+int devlink_dpipe_table_register(struct devlink *devlink,
+ const char *table_name,
+ struct devlink_dpipe_table_ops *table_ops,
+ void *priv, u64 size,
+ bool counter_control_extern)
+{
+ struct devlink_dpipe_table *table;
+
+ if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name))
+ return -EEXIST;
+
+ table = kzalloc(sizeof(*table), GFP_KERNEL);
+ if (!table)
+ return -ENOMEM;
+
+ table->name = table_name;
+ table->table_ops = table_ops;
+ table->priv = priv;
+ table->size = size;
+ table->counter_control_extern = counter_control_extern;
+
+ mutex_lock(&devlink_mutex);
+ list_add_tail_rcu(&table->list, &devlink->dpipe_table_list);
+ mutex_unlock(&devlink_mutex);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_table_register);
+
+/**
+ * devlink_dpipe_table_unregister - unregister dpipe table
+ *
+ * @devlink: devlink
+ * @table_name: table name
+ */
+void devlink_dpipe_table_unregister(struct devlink *devlink,
+ const char *table_name)
+{
+ struct devlink_dpipe_table *table;
+
+ mutex_lock(&devlink_mutex);
+ table = devlink_dpipe_table_find(&devlink->dpipe_table_list,
+ table_name);
+ if (!table)
+ goto unlock;
+ list_del_rcu(&table->list);
+ mutex_unlock(&devlink_mutex);
+ kfree_rcu(table, rcu);
+ return;
+unlock:
+ mutex_unlock(&devlink_mutex);
+}
+EXPORT_SYMBOL_GPL(devlink_dpipe_table_unregister);
+
static int __init devlink_module_init(void)
{
return genl_register_family(&devlink_nl_family);
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index fb55327..70ccda2 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -412,9 +412,8 @@ static int __init init_net_drop_monitor(void)
for_each_possible_cpu(cpu) {
data = &per_cpu(dm_cpu_data, cpu);
INIT_WORK(&data->dm_alert_work, send_dm_alert);
- init_timer(&data->send_timer);
- data->send_timer.data = (unsigned long)data;
- data->send_timer.function = sched_send_work;
+ setup_timer(&data->send_timer, sched_send_work,
+ (unsigned long)data);
spin_lock_init(&data->lock);
reset_per_cpu_data(data);
}
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index aecb2c7..905a88a 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -109,6 +109,7 @@ static const char
rss_hash_func_strings[ETH_RSS_HASH_FUNCS_COUNT][ETH_GSTRING_LEN] = {
[ETH_RSS_HASH_TOP_BIT] = "toeplitz",
[ETH_RSS_HASH_XOR_BIT] = "xor",
+ [ETH_RSS_HASH_CRC32_BIT] = "crc32",
};
static const char
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index b6791d9..816e3cc 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -23,6 +23,20 @@ static const struct fib_kuid_range fib_kuid_range_unset = {
KUIDT_INIT(~0),
};
+bool fib_rule_matchall(const struct fib_rule *rule)
+{
+ if (rule->iifindex || rule->oifindex || rule->mark || rule->tun_id ||
+ rule->flags)
+ return false;
+ if (rule->suppress_ifgroup != -1 || rule->suppress_prefixlen != -1)
+ return false;
+ if (!uid_eq(rule->uid_range.start, fib_kuid_range_unset.start) ||
+ !uid_eq(rule->uid_range.end, fib_kuid_range_unset.end))
+ return false;
+ return true;
+}
+EXPORT_SYMBOL_GPL(fib_rule_matchall);
+
int fib_default_rule_add(struct fib_rules_ops *ops,
u32 pref, u32 table, u32 flags)
{
diff --git a/net/core/filter.c b/net/core/filter.c
index ebaeaf2..15e9a81 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -26,6 +26,7 @@
#include <linux/mm.h>
#include <linux/fcntl.h>
#include <linux/socket.h>
+#include <linux/sock_diag.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
@@ -928,7 +929,7 @@ static void sk_filter_release_rcu(struct rcu_head *rcu)
*/
static void sk_filter_release(struct sk_filter *fp)
{
- if (atomic_dec_and_test(&fp->refcnt))
+ if (refcount_dec_and_test(&fp->refcnt))
call_rcu(&fp->rcu, sk_filter_release_rcu);
}
@@ -943,20 +944,27 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
/* try to charge the socket memory if there is space available
* return true on success
*/
-bool sk_filter_charge(struct sock *sk, struct sk_filter *fp)
+static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp)
{
u32 filter_size = bpf_prog_size(fp->prog->len);
/* same check as in sock_kmalloc() */
if (filter_size <= sysctl_optmem_max &&
atomic_read(&sk->sk_omem_alloc) + filter_size < sysctl_optmem_max) {
- atomic_inc(&fp->refcnt);
atomic_add(filter_size, &sk->sk_omem_alloc);
return true;
}
return false;
}
+bool sk_filter_charge(struct sock *sk, struct sk_filter *fp)
+{
+ bool ret = __sk_filter_charge(sk, fp);
+ if (ret)
+ refcount_inc(&fp->refcnt);
+ return ret;
+}
+
static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
{
struct sock_filter *old_prog;
@@ -1179,12 +1187,12 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk)
return -ENOMEM;
fp->prog = prog;
- atomic_set(&fp->refcnt, 0);
- if (!sk_filter_charge(sk, fp)) {
+ if (!__sk_filter_charge(sk, fp)) {
kfree(fp);
return -ENOMEM;
}
+ refcount_set(&fp->refcnt, 1);
old_fp = rcu_dereference_protected(sk->sk_filter,
lockdep_sock_is_held(sk));
@@ -2599,6 +2607,36 @@ static const struct bpf_func_proto bpf_xdp_event_output_proto = {
.arg5_type = ARG_CONST_SIZE,
};
+BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb)
+{
+ return skb->sk ? sock_gen_cookie(skb->sk) : 0;
+}
+
+static const struct bpf_func_proto bpf_get_socket_cookie_proto = {
+ .func = bpf_get_socket_cookie,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+
+BPF_CALL_1(bpf_get_socket_uid, struct sk_buff *, skb)
+{
+ struct sock *sk = sk_to_full_sk(skb->sk);
+ kuid_t kuid;
+
+ if (!sk || !sk_fullsock(sk))
+ return overflowuid;
+ kuid = sock_net_uid(sock_net(sk), sk);
+ return from_kuid_munged(sock_net(sk)->user_ns, kuid);
+}
+
+static const struct bpf_func_proto bpf_get_socket_uid_proto = {
+ .func = bpf_get_socket_uid,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+
static const struct bpf_func_proto *
bpf_base_func_proto(enum bpf_func_id func_id)
{
@@ -2633,6 +2671,10 @@ sk_filter_func_proto(enum bpf_func_id func_id)
switch (func_id) {
case BPF_FUNC_skb_load_bytes:
return &bpf_skb_load_bytes_proto;
+ case BPF_FUNC_get_socket_cookie:
+ return &bpf_get_socket_cookie_proto;
+ case BPF_FUNC_get_socket_uid:
+ return &bpf_get_socket_uid_proto;
default:
return bpf_base_func_proto(func_id);
}
@@ -2692,6 +2734,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id)
return &bpf_get_smp_processor_id_proto;
case BPF_FUNC_skb_under_cgroup:
return &bpf_skb_under_cgroup_proto;
+ case BPF_FUNC_get_socket_cookie:
+ return &bpf_get_socket_cookie_proto;
+ case BPF_FUNC_get_socket_uid:
+ return &bpf_get_socket_uid_proto;
default:
return bpf_base_func_proto(func_id);
}
@@ -3263,24 +3309,28 @@ static const struct bpf_verifier_ops tc_cls_act_ops = {
.is_valid_access = tc_cls_act_is_valid_access,
.convert_ctx_access = tc_cls_act_convert_ctx_access,
.gen_prologue = tc_cls_act_prologue,
+ .test_run = bpf_prog_test_run_skb,
};
static const struct bpf_verifier_ops xdp_ops = {
.get_func_proto = xdp_func_proto,
.is_valid_access = xdp_is_valid_access,
.convert_ctx_access = xdp_convert_ctx_access,
+ .test_run = bpf_prog_test_run_xdp,
};
static const struct bpf_verifier_ops cg_skb_ops = {
.get_func_proto = cg_skb_func_proto,
.is_valid_access = sk_filter_is_valid_access,
.convert_ctx_access = bpf_convert_ctx_access,
+ .test_run = bpf_prog_test_run_skb,
};
static const struct bpf_verifier_ops lwt_inout_ops = {
.get_func_proto = lwt_inout_func_proto,
.is_valid_access = lwt_is_valid_access,
.convert_ctx_access = bpf_convert_ctx_access,
+ .test_run = bpf_prog_test_run_skb,
};
static const struct bpf_verifier_ops lwt_xmit_ops = {
@@ -3288,6 +3338,7 @@ static const struct bpf_verifier_ops lwt_xmit_ops = {
.is_valid_access = lwt_is_valid_access,
.convert_ctx_access = bpf_convert_ctx_access,
.gen_prologue = tc_cls_act_prologue,
+ .test_run = bpf_prog_test_run_skb,
};
static const struct bpf_verifier_ops cg_sock_ops = {
diff --git a/net/core/flow.c b/net/core/flow.c
index f765c11..f7f5d19 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -47,7 +47,7 @@ struct flow_flush_info {
static struct kmem_cache *flow_cachep __read_mostly;
-#define flow_cache_hash_size(cache) (1 << (cache)->hash_shift)
+#define flow_cache_hash_size(cache) (1U << (cache)->hash_shift)
#define FLOW_HASH_RND_PERIOD (10 * 60 * HZ)
static void flow_cache_new_hashrnd(unsigned long arg)
@@ -99,7 +99,8 @@ static void flow_cache_gc_task(struct work_struct *work)
}
static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp,
- int deleted, struct list_head *gc_list,
+ unsigned int deleted,
+ struct list_head *gc_list,
struct netns_xfrm *xfrm)
{
if (deleted) {
@@ -114,17 +115,18 @@ static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp,
static void __flow_cache_shrink(struct flow_cache *fc,
struct flow_cache_percpu *fcp,
- int shrink_to)
+ unsigned int shrink_to)
{
struct flow_cache_entry *fle;
struct hlist_node *tmp;
LIST_HEAD(gc_list);
- int i, deleted = 0;
+ unsigned int deleted = 0;
struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
flow_cache_global);
+ unsigned int i;
for (i = 0; i < flow_cache_hash_size(fc); i++) {
- int saved = 0;
+ unsigned int saved = 0;
hlist_for_each_entry_safe(fle, tmp,
&fcp->hash_table[i], u.hlist) {
@@ -145,7 +147,7 @@ static void __flow_cache_shrink(struct flow_cache *fc,
static void flow_cache_shrink(struct flow_cache *fc,
struct flow_cache_percpu *fcp)
{
- int shrink_to = fc->low_watermark / flow_cache_hash_size(fc);
+ unsigned int shrink_to = fc->low_watermark / flow_cache_hash_size(fc);
__flow_cache_shrink(fc, fcp, shrink_to);
}
@@ -161,7 +163,7 @@ static void flow_new_hash_rnd(struct flow_cache *fc,
static u32 flow_hash_code(struct flow_cache *fc,
struct flow_cache_percpu *fcp,
const struct flowi *key,
- size_t keysize)
+ unsigned int keysize)
{
const u32 *k = (const u32 *) key;
const u32 length = keysize * sizeof(flow_compare_t) / sizeof(u32);
@@ -174,7 +176,7 @@ static u32 flow_hash_code(struct flow_cache *fc,
* important assumptions that we can here, such as alignment.
*/
static int flow_key_compare(const struct flowi *key1, const struct flowi *key2,
- size_t keysize)
+ unsigned int keysize)
{
const flow_compare_t *k1, *k1_lim, *k2;
@@ -199,7 +201,7 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
struct flow_cache_percpu *fcp;
struct flow_cache_entry *fle, *tfle;
struct flow_cache_object *flo;
- size_t keysize;
+ unsigned int keysize;
unsigned int hash;
local_bh_disable();
@@ -295,9 +297,10 @@ static void flow_cache_flush_tasklet(unsigned long data)
struct flow_cache_entry *fle;
struct hlist_node *tmp;
LIST_HEAD(gc_list);
- int i, deleted = 0;
+ unsigned int deleted = 0;
struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
flow_cache_global);
+ unsigned int i;
fcp = this_cpu_ptr(fc->percpu);
for (i = 0; i < flow_cache_hash_size(fc); i++) {
@@ -327,7 +330,7 @@ static void flow_cache_flush_tasklet(unsigned long data)
static int flow_cache_percpu_empty(struct flow_cache *fc, int cpu)
{
struct flow_cache_percpu *fcp;
- int i;
+ unsigned int i;
fcp = per_cpu_ptr(fc->percpu, cpu);
for (i = 0; i < flow_cache_hash_size(fc); i++)
@@ -402,12 +405,12 @@ void flow_cache_flush_deferred(struct net *net)
static int flow_cache_cpu_prepare(struct flow_cache *fc, int cpu)
{
struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu);
- size_t sz = sizeof(struct hlist_head) * flow_cache_hash_size(fc);
+ unsigned int sz = sizeof(struct hlist_head) * flow_cache_hash_size(fc);
if (!fcp->hash_table) {
fcp->hash_table = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu));
if (!fcp->hash_table) {
- pr_err("NET: failed to allocate flow cache sz %zu\n", sz);
+ pr_err("NET: failed to allocate flow cache sz %u\n", sz);
return -ENOMEM;
}
fcp->hash_rnd_recalc = 1;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index c35aae1..c9cf425 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -113,6 +113,216 @@ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
}
EXPORT_SYMBOL(__skb_flow_get_ports);
+enum flow_dissect_ret {
+ FLOW_DISSECT_RET_OUT_GOOD,
+ FLOW_DISSECT_RET_OUT_BAD,
+ FLOW_DISSECT_RET_OUT_PROTO_AGAIN,
+};
+
+static enum flow_dissect_ret
+__skb_flow_dissect_mpls(const struct sk_buff *skb,
+ struct flow_dissector *flow_dissector,
+ void *target_container, void *data, int nhoff, int hlen)
+{
+ struct flow_dissector_key_keyid *key_keyid;
+ struct mpls_label *hdr, _hdr[2];
+
+ if (!dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_MPLS_ENTROPY))
+ return FLOW_DISSECT_RET_OUT_GOOD;
+
+ hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data,
+ hlen, &_hdr);
+ if (!hdr)
+ return FLOW_DISSECT_RET_OUT_BAD;
+
+ if ((ntohl(hdr[0].entry) & MPLS_LS_LABEL_MASK) >>
+ MPLS_LS_LABEL_SHIFT == MPLS_LABEL_ENTROPY) {
+ key_keyid = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_MPLS_ENTROPY,
+ target_container);
+ key_keyid->keyid = hdr[1].entry & htonl(MPLS_LS_LABEL_MASK);
+ }
+ return FLOW_DISSECT_RET_OUT_GOOD;
+}
+
+static enum flow_dissect_ret
+__skb_flow_dissect_arp(const struct sk_buff *skb,
+ struct flow_dissector *flow_dissector,
+ void *target_container, void *data, int nhoff, int hlen)
+{
+ struct flow_dissector_key_arp *key_arp;
+ struct {
+ unsigned char ar_sha[ETH_ALEN];
+ unsigned char ar_sip[4];
+ unsigned char ar_tha[ETH_ALEN];
+ unsigned char ar_tip[4];
+ } *arp_eth, _arp_eth;
+ const struct arphdr *arp;
+ struct arphdr _arp;
+
+ if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ARP))
+ return FLOW_DISSECT_RET_OUT_GOOD;
+
+ arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data,
+ hlen, &_arp);
+ if (!arp)
+ return FLOW_DISSECT_RET_OUT_BAD;
+
+ if (arp->ar_hrd != htons(ARPHRD_ETHER) ||
+ arp->ar_pro != htons(ETH_P_IP) ||
+ arp->ar_hln != ETH_ALEN ||
+ arp->ar_pln != 4 ||
+ (arp->ar_op != htons(ARPOP_REPLY) &&
+ arp->ar_op != htons(ARPOP_REQUEST)))
+ return FLOW_DISSECT_RET_OUT_BAD;
+
+ arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp),
+ sizeof(_arp_eth), data,
+ hlen, &_arp_eth);
+ if (!arp_eth)
+ return FLOW_DISSECT_RET_OUT_BAD;
+
+ key_arp = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_ARP,
+ target_container);
+
+ memcpy(&key_arp->sip, arp_eth->ar_sip, sizeof(key_arp->sip));
+ memcpy(&key_arp->tip, arp_eth->ar_tip, sizeof(key_arp->tip));
+
+ /* Only store the lower byte of the opcode;
+ * this covers ARPOP_REPLY and ARPOP_REQUEST.
+ */
+ key_arp->op = ntohs(arp->ar_op) & 0xff;
+
+ ether_addr_copy(key_arp->sha, arp_eth->ar_sha);
+ ether_addr_copy(key_arp->tha, arp_eth->ar_tha);
+
+ return FLOW_DISSECT_RET_OUT_GOOD;
+}
+
+static enum flow_dissect_ret
+__skb_flow_dissect_gre(const struct sk_buff *skb,
+ struct flow_dissector_key_control *key_control,
+ struct flow_dissector *flow_dissector,
+ void *target_container, void *data,
+ __be16 *p_proto, int *p_nhoff, int *p_hlen,
+ unsigned int flags)
+{
+ struct flow_dissector_key_keyid *key_keyid;
+ struct gre_base_hdr *hdr, _hdr;
+ int offset = 0;
+ u16 gre_ver;
+
+ hdr = __skb_header_pointer(skb, *p_nhoff, sizeof(_hdr),
+ data, *p_hlen, &_hdr);
+ if (!hdr)
+ return FLOW_DISSECT_RET_OUT_BAD;
+
+ /* Only look inside GRE without routing */
+ if (hdr->flags & GRE_ROUTING)
+ return FLOW_DISSECT_RET_OUT_GOOD;
+
+ /* Only look inside GRE for version 0 and 1 */
+ gre_ver = ntohs(hdr->flags & GRE_VERSION);
+ if (gre_ver > 1)
+ return FLOW_DISSECT_RET_OUT_GOOD;
+
+ *p_proto = hdr->protocol;
+ if (gre_ver) {
+ /* Version1 must be PPTP, and check the flags */
+ if (!(*p_proto == GRE_PROTO_PPP && (hdr->flags & GRE_KEY)))
+ return FLOW_DISSECT_RET_OUT_GOOD;
+ }
+
+ offset += sizeof(struct gre_base_hdr);
+
+ if (hdr->flags & GRE_CSUM)
+ offset += sizeof(((struct gre_full_hdr *) 0)->csum) +
+ sizeof(((struct gre_full_hdr *) 0)->reserved1);
+
+ if (hdr->flags & GRE_KEY) {
+ const __be32 *keyid;
+ __be32 _keyid;
+
+ keyid = __skb_header_pointer(skb, *p_nhoff + offset,
+ sizeof(_keyid),
+ data, *p_hlen, &_keyid);
+ if (!keyid)
+ return FLOW_DISSECT_RET_OUT_BAD;
+
+ if (dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_GRE_KEYID)) {
+ key_keyid = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_GRE_KEYID,
+ target_container);
+ if (gre_ver == 0)
+ key_keyid->keyid = *keyid;
+ else
+ key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK;
+ }
+ offset += sizeof(((struct gre_full_hdr *) 0)->key);
+ }
+
+ if (hdr->flags & GRE_SEQ)
+ offset += sizeof(((struct pptp_gre_header *) 0)->seq);
+
+ if (gre_ver == 0) {
+ if (*p_proto == htons(ETH_P_TEB)) {
+ const struct ethhdr *eth;
+ struct ethhdr _eth;
+
+ eth = __skb_header_pointer(skb, *p_nhoff + offset,
+ sizeof(_eth),
+ data, *p_hlen, &_eth);
+ if (!eth)
+ return FLOW_DISSECT_RET_OUT_BAD;
+ *p_proto = eth->h_proto;
+ offset += sizeof(*eth);
+
+ /* Cap headers that we access via pointers at the
+ * end of the Ethernet header as our maximum alignment
+ * at that point is only 2 bytes.
+ */
+ if (NET_IP_ALIGN)
+ *p_hlen = *p_nhoff + offset;
+ }
+ } else { /* version 1, must be PPTP */
+ u8 _ppp_hdr[PPP_HDRLEN];
+ u8 *ppp_hdr;
+
+ if (hdr->flags & GRE_ACK)
+ offset += sizeof(((struct pptp_gre_header *) 0)->ack);
+
+ ppp_hdr = __skb_header_pointer(skb, *p_nhoff + offset,
+ sizeof(_ppp_hdr),
+ data, *p_hlen, _ppp_hdr);
+ if (!ppp_hdr)
+ return FLOW_DISSECT_RET_OUT_BAD;
+
+ switch (PPP_PROTOCOL(ppp_hdr)) {
+ case PPP_IP:
+ *p_proto = htons(ETH_P_IP);
+ break;
+ case PPP_IPV6:
+ *p_proto = htons(ETH_P_IPV6);
+ break;
+ default:
+ /* Could probably catch some more like MPLS */
+ break;
+ }
+
+ offset += PPP_HDRLEN;
+ }
+
+ *p_nhoff += offset;
+ key_control->flags |= FLOW_DIS_ENCAPSULATION;
+ if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP)
+ return FLOW_DISSECT_RET_OUT_GOOD;
+
+ return FLOW_DISSECT_RET_OUT_PROTO_AGAIN;
+}
+
/**
* __skb_flow_dissect - extract the flow_keys struct and return it
* @skb: sk_buff to extract the flow from, can be NULL if the rest are specified
@@ -138,12 +348,10 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
struct flow_dissector_key_control *key_control;
struct flow_dissector_key_basic *key_basic;
struct flow_dissector_key_addrs *key_addrs;
- struct flow_dissector_key_arp *key_arp;
struct flow_dissector_key_ports *key_ports;
struct flow_dissector_key_icmp *key_icmp;
struct flow_dissector_key_tags *key_tags;
struct flow_dissector_key_vlan *key_vlan;
- struct flow_dissector_key_keyid *key_keyid;
bool skip_vlan = false;
u8 ip_proto = 0;
bool ret;
@@ -181,7 +389,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
memcpy(key_eth_addrs, ð->h_dest, sizeof(*key_eth_addrs));
}
-again:
+proto_again:
switch (proto) {
case htons(ETH_P_IP): {
const struct iphdr *iph;
@@ -284,7 +492,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
proto = vlan->h_vlan_encapsulated_proto;
nhoff += sizeof(*vlan);
if (skip_vlan)
- goto again;
+ goto proto_again;
}
skip_vlan = true;
@@ -307,7 +515,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
}
}
- goto again;
+ goto proto_again;
}
case htons(ETH_P_PPP_SES): {
struct {
@@ -349,31 +557,17 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
}
case htons(ETH_P_MPLS_UC):
- case htons(ETH_P_MPLS_MC): {
- struct mpls_label *hdr, _hdr[2];
+ case htons(ETH_P_MPLS_MC):
mpls:
- hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data,
- hlen, &_hdr);
- if (!hdr)
- goto out_bad;
-
- if ((ntohl(hdr[0].entry) & MPLS_LS_LABEL_MASK) >>
- MPLS_LS_LABEL_SHIFT == MPLS_LABEL_ENTROPY) {
- if (dissector_uses_key(flow_dissector,
- FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) {
- key_keyid = skb_flow_dissector_target(flow_dissector,
- FLOW_DISSECTOR_KEY_MPLS_ENTROPY,
- target_container);
- key_keyid->keyid = hdr[1].entry &
- htonl(MPLS_LS_LABEL_MASK);
- }
-
+ switch (__skb_flow_dissect_mpls(skb, flow_dissector,
+ target_container, data,
+ nhoff, hlen)) {
+ case FLOW_DISSECT_RET_OUT_GOOD:
goto out_good;
+ case FLOW_DISSECT_RET_OUT_BAD:
+ default:
+ goto out_bad;
}
-
- goto out_good;
- }
-
case htons(ETH_P_FCOE):
if ((hlen - nhoff) < FCOE_HEADER_LEN)
goto out_bad;
@@ -382,177 +576,33 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
goto out_good;
case htons(ETH_P_ARP):
- case htons(ETH_P_RARP): {
- struct {
- unsigned char ar_sha[ETH_ALEN];
- unsigned char ar_sip[4];
- unsigned char ar_tha[ETH_ALEN];
- unsigned char ar_tip[4];
- } *arp_eth, _arp_eth;
- const struct arphdr *arp;
- struct arphdr *_arp;
-
- arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data,
- hlen, &_arp);
- if (!arp)
+ case htons(ETH_P_RARP):
+ switch (__skb_flow_dissect_arp(skb, flow_dissector,
+ target_container, data,
+ nhoff, hlen)) {
+ case FLOW_DISSECT_RET_OUT_GOOD:
+ goto out_good;
+ case FLOW_DISSECT_RET_OUT_BAD:
+ default:
goto out_bad;
-
- if (arp->ar_hrd != htons(ARPHRD_ETHER) ||
- arp->ar_pro != htons(ETH_P_IP) ||
- arp->ar_hln != ETH_ALEN ||
- arp->ar_pln != 4 ||
- (arp->ar_op != htons(ARPOP_REPLY) &&
- arp->ar_op != htons(ARPOP_REQUEST)))
- goto out_bad;
-
- arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp),
- sizeof(_arp_eth), data,
- hlen,
- &_arp_eth);
- if (!arp_eth)
- goto out_bad;
-
- if (dissector_uses_key(flow_dissector,
- FLOW_DISSECTOR_KEY_ARP)) {
-
- key_arp = skb_flow_dissector_target(flow_dissector,
- FLOW_DISSECTOR_KEY_ARP,
- target_container);
-
- memcpy(&key_arp->sip, arp_eth->ar_sip,
- sizeof(key_arp->sip));
- memcpy(&key_arp->tip, arp_eth->ar_tip,
- sizeof(key_arp->tip));
-
- /* Only store the lower byte of the opcode;
- * this covers ARPOP_REPLY and ARPOP_REQUEST.
- */
- key_arp->op = ntohs(arp->ar_op) & 0xff;
-
- ether_addr_copy(key_arp->sha, arp_eth->ar_sha);
- ether_addr_copy(key_arp->tha, arp_eth->ar_tha);
}
-
- goto out_good;
- }
-
default:
goto out_bad;
}
ip_proto_again:
switch (ip_proto) {
- case IPPROTO_GRE: {
- struct gre_base_hdr *hdr, _hdr;
- u16 gre_ver;
- int offset = 0;
-
- hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
- if (!hdr)
- goto out_bad;
-
- /* Only look inside GRE without routing */
- if (hdr->flags & GRE_ROUTING)
- break;
-
- /* Only look inside GRE for version 0 and 1 */
- gre_ver = ntohs(hdr->flags & GRE_VERSION);
- if (gre_ver > 1)
- break;
-
- proto = hdr->protocol;
- if (gre_ver) {
- /* Version1 must be PPTP, and check the flags */
- if (!(proto == GRE_PROTO_PPP && (hdr->flags & GRE_KEY)))
- break;
- }
-
- offset += sizeof(struct gre_base_hdr);
-
- if (hdr->flags & GRE_CSUM)
- offset += sizeof(((struct gre_full_hdr *)0)->csum) +
- sizeof(((struct gre_full_hdr *)0)->reserved1);
-
- if (hdr->flags & GRE_KEY) {
- const __be32 *keyid;
- __be32 _keyid;
-
- keyid = __skb_header_pointer(skb, nhoff + offset, sizeof(_keyid),
- data, hlen, &_keyid);
- if (!keyid)
- goto out_bad;
-
- if (dissector_uses_key(flow_dissector,
- FLOW_DISSECTOR_KEY_GRE_KEYID)) {
- key_keyid = skb_flow_dissector_target(flow_dissector,
- FLOW_DISSECTOR_KEY_GRE_KEYID,
- target_container);
- if (gre_ver == 0)
- key_keyid->keyid = *keyid;
- else
- key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK;
- }
- offset += sizeof(((struct gre_full_hdr *)0)->key);
- }
-
- if (hdr->flags & GRE_SEQ)
- offset += sizeof(((struct pptp_gre_header *)0)->seq);
-
- if (gre_ver == 0) {
- if (proto == htons(ETH_P_TEB)) {
- const struct ethhdr *eth;
- struct ethhdr _eth;
-
- eth = __skb_header_pointer(skb, nhoff + offset,
- sizeof(_eth),
- data, hlen, &_eth);
- if (!eth)
- goto out_bad;
- proto = eth->h_proto;
- offset += sizeof(*eth);
-
- /* Cap headers that we access via pointers at the
- * end of the Ethernet header as our maximum alignment
- * at that point is only 2 bytes.
- */
- if (NET_IP_ALIGN)
- hlen = (nhoff + offset);
- }
- } else { /* version 1, must be PPTP */
- u8 _ppp_hdr[PPP_HDRLEN];
- u8 *ppp_hdr;
-
- if (hdr->flags & GRE_ACK)
- offset += sizeof(((struct pptp_gre_header *)0)->ack);
-
- ppp_hdr = __skb_header_pointer(skb, nhoff + offset,
- sizeof(_ppp_hdr),
- data, hlen, _ppp_hdr);
- if (!ppp_hdr)
- goto out_bad;
-
- switch (PPP_PROTOCOL(ppp_hdr)) {
- case PPP_IP:
- proto = htons(ETH_P_IP);
- break;
- case PPP_IPV6:
- proto = htons(ETH_P_IPV6);
- break;
- default:
- /* Could probably catch some more like MPLS */
- break;
- }
-
- offset += PPP_HDRLEN;
- }
-
- nhoff += offset;
- key_control->flags |= FLOW_DIS_ENCAPSULATION;
- if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP)
+ case IPPROTO_GRE:
+ switch (__skb_flow_dissect_gre(skb, key_control, flow_dissector,
+ target_container, data,
+ &proto, &nhoff, &hlen, flags)) {
+ case FLOW_DISSECT_RET_OUT_GOOD:
goto out_good;
-
- goto again;
- }
+ case FLOW_DISSECT_RET_OUT_BAD:
+ goto out_bad;
+ case FLOW_DISSECT_RET_OUT_PROTO_AGAIN:
+ goto proto_again;
+ }
case NEXTHDR_HOP:
case NEXTHDR_ROUTING:
case NEXTHDR_DEST: {
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index 6df9f8f..b588819 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -162,7 +162,6 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining)
struct rtnexthop *rtnh = (struct rtnexthop *)attr;
struct nlattr *nla_entype;
struct nlattr *attrs;
- struct nlattr *nla;
u16 encap_type;
int attrlen;
@@ -170,7 +169,6 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining)
attrlen = rtnh_attrlen(rtnh);
if (attrlen > 0) {
attrs = rtnh_attrs(rtnh);
- nla = nla_find(attrs, attrlen, RTA_ENCAP);
nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
if (nla_entype) {
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index e7c12ca..8ae87c5 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -52,8 +52,9 @@ do { \
#define PNEIGH_HASHMASK 0xF
static void neigh_timer_handler(unsigned long arg);
-static void __neigh_notify(struct neighbour *n, int type, int flags);
-static void neigh_update_notify(struct neighbour *neigh);
+static void __neigh_notify(struct neighbour *n, int type, int flags,
+ u32 pid);
+static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid);
static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
#ifdef CONFIG_PROC_FS
@@ -99,7 +100,7 @@ static void neigh_cleanup_and_release(struct neighbour *neigh)
if (neigh->parms->neigh_cleanup)
neigh->parms->neigh_cleanup(neigh);
- __neigh_notify(neigh, RTM_DELNEIGH, 0);
+ __neigh_notify(neigh, RTM_DELNEIGH, 0, 0);
call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh);
neigh_release(neigh);
}
@@ -860,7 +861,8 @@ static void neigh_probe(struct neighbour *neigh)
if (skb)
skb = skb_clone(skb, GFP_ATOMIC);
write_unlock(&neigh->lock);
- neigh->ops->solicit(neigh, skb);
+ if (neigh->ops->solicit)
+ neigh->ops->solicit(neigh, skb);
atomic_inc(&neigh->probes);
kfree_skb(skb);
}
@@ -948,7 +950,7 @@ static void neigh_timer_handler(unsigned long arg)
}
if (notify)
- neigh_update_notify(neigh);
+ neigh_update_notify(neigh, 0);
neigh_release(neigh);
}
@@ -1072,7 +1074,7 @@ static void neigh_update_hhs(struct neighbour *neigh)
*/
int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
- u32 flags)
+ u32 flags, u32 nlmsg_pid)
{
u8 old;
int err;
@@ -1229,7 +1231,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
write_unlock_bh(&neigh->lock);
if (notify)
- neigh_update_notify(neigh);
+ neigh_update_notify(neigh, nlmsg_pid);
return err;
}
@@ -1260,7 +1262,7 @@ struct neighbour *neigh_event_ns(struct neigh_table *tbl,
lladdr || !dev->addr_len);
if (neigh)
neigh_update(neigh, lladdr, NUD_STALE,
- NEIGH_UPDATE_F_OVERRIDE);
+ NEIGH_UPDATE_F_OVERRIDE, 0);
return neigh;
}
EXPORT_SYMBOL(neigh_event_ns);
@@ -1638,7 +1640,8 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh)
err = neigh_update(neigh, NULL, NUD_FAILED,
NEIGH_UPDATE_F_OVERRIDE |
- NEIGH_UPDATE_F_ADMIN);
+ NEIGH_UPDATE_F_ADMIN,
+ NETLINK_CB(skb).portid);
neigh_release(neigh);
out:
@@ -1729,7 +1732,8 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh)
neigh_event_send(neigh, NULL);
err = 0;
} else
- err = neigh_update(neigh, lladdr, ndm->ndm_state, flags);
+ err = neigh_update(neigh, lladdr, ndm->ndm_state, flags,
+ NETLINK_CB(skb).portid);
neigh_release(neigh);
out:
@@ -2229,10 +2233,10 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn,
return -EMSGSIZE;
}
-static void neigh_update_notify(struct neighbour *neigh)
+static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid)
{
call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh);
- __neigh_notify(neigh, RTM_NEWNEIGH, 0);
+ __neigh_notify(neigh, RTM_NEWNEIGH, 0, nlmsg_pid);
}
static bool neigh_master_filtered(struct net_device *dev, int master_idx)
@@ -2830,7 +2834,8 @@ static inline size_t neigh_nlmsg_size(void)
+ nla_total_size(4); /* NDA_PROBES */
}
-static void __neigh_notify(struct neighbour *n, int type, int flags)
+static void __neigh_notify(struct neighbour *n, int type, int flags,
+ u32 pid)
{
struct net *net = dev_net(n->dev);
struct sk_buff *skb;
@@ -2840,7 +2845,7 @@ static void __neigh_notify(struct neighbour *n, int type, int flags)
if (skb == NULL)
goto errout;
- err = neigh_fill_info(skb, n, 0, 0, type, flags);
+ err = neigh_fill_info(skb, n, pid, 0, type, flags);
if (err < 0) {
/* -EMSGSIZE implies BUG in neigh_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
@@ -2856,7 +2861,7 @@ static void __neigh_notify(struct neighbour *n, int type, int flags)
void neigh_app_ns(struct neighbour *n)
{
- __neigh_notify(n, RTM_GETNEIGH, NLM_F_REQUEST);
+ __neigh_notify(n, RTM_GETNEIGH, NLM_F_REQUEST, 0);
}
EXPORT_SYMBOL(neigh_app_ns);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 3945821..65ea0ff 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -953,7 +953,7 @@ net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num)
while (--i >= new_num) {
struct kobject *kobj = &dev->_rx[i].kobj;
- if (!list_empty(&dev_net(dev)->exit_list))
+ if (!atomic_read(&dev_net(dev)->count))
kobj->uevent_suppress = 1;
if (dev->sysfs_rx_queue_group)
sysfs_remove_group(kobj, dev->sysfs_rx_queue_group);
@@ -1371,7 +1371,7 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num)
while (--i >= new_num) {
struct netdev_queue *queue = dev->_tx + i;
- if (!list_empty(&dev_net(dev)->exit_list))
+ if (!atomic_read(&dev_net(dev)->count))
queue->kobj.uevent_suppress = 1;
#ifdef CONFIG_BQL
sysfs_remove_group(&queue->kobj, &dql_group);
@@ -1558,7 +1558,7 @@ void netdev_unregister_kobject(struct net_device *ndev)
{
struct device *dev = &(ndev->dev);
- if (!list_empty(&dev_net(ndev)->exit_list))
+ if (!atomic_read(&dev_net(ndev)->count))
dev_set_uevent_suppress(dev, 1);
kobject_get(&dev->kobj);
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index 6ae5603..029a61a 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -71,27 +71,17 @@ static int update_classid_sock(const void *v, struct file *file, unsigned n)
return 0;
}
-static void update_classid(struct cgroup_subsys_state *css, void *v)
-{
- struct css_task_iter it;
- struct task_struct *p;
-
- css_task_iter_start(css, &it);
- while ((p = css_task_iter_next(&it))) {
- task_lock(p);
- iterate_fd(p->files, 0, update_classid_sock, v);
- task_unlock(p);
- }
- css_task_iter_end(&it);
-}
-
static void cgrp_attach(struct cgroup_taskset *tset)
{
struct cgroup_subsys_state *css;
+ struct task_struct *p;
- cgroup_taskset_first(tset, &css);
- update_classid(css,
- (void *)(unsigned long)css_cls_state(css)->classid);
+ cgroup_taskset_for_each(p, css, tset) {
+ task_lock(p);
+ iterate_fd(p->files, 0, update_classid_sock,
+ (void *)(unsigned long)css_cls_state(css)->classid);
+ task_unlock(p);
+ }
}
static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft)
@@ -103,12 +93,22 @@ static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft,
u64 value)
{
struct cgroup_cls_state *cs = css_cls_state(css);
+ struct css_task_iter it;
+ struct task_struct *p;
cgroup_sk_alloc_disable();
cs->classid = (u32)value;
- update_classid(css, (void *)(unsigned long)cs->classid);
+ css_task_iter_start(css, &it);
+ while ((p = css_task_iter_next(&it))) {
+ task_lock(p);
+ iterate_fd(p->files, 0, update_classid_sock,
+ (void *)(unsigned long)cs->classid);
+ task_unlock(p);
+ }
+ css_task_iter_end(&it);
+
return 0;
}
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 0f9275e..1c48109 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -11,6 +11,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/module.h>
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index c4e84c5..58419da 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -4116,22 +4116,25 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
switch (event) {
- case NETDEV_UP:
- case NETDEV_DOWN:
- case NETDEV_PRE_UP:
- case NETDEV_POST_INIT:
- case NETDEV_REGISTER:
- case NETDEV_CHANGE:
- case NETDEV_PRE_TYPE_CHANGE:
- case NETDEV_GOING_DOWN:
- case NETDEV_UNREGISTER:
- case NETDEV_UNREGISTER_FINAL:
- case NETDEV_RELEASE:
- case NETDEV_JOIN:
- case NETDEV_BONDING_INFO:
+ case NETDEV_REBOOT:
+ case NETDEV_CHANGEMTU:
+ case NETDEV_CHANGEADDR:
+ case NETDEV_CHANGENAME:
+ case NETDEV_FEAT_CHANGE:
+ case NETDEV_BONDING_FAILOVER:
+ case NETDEV_POST_TYPE_CHANGE:
+ case NETDEV_NOTIFY_PEERS:
+ case NETDEV_CHANGEUPPER:
+ case NETDEV_RESEND_IGMP:
+ case NETDEV_PRECHANGEMTU:
+ case NETDEV_CHANGEINFODATA:
+ case NETDEV_PRECHANGEUPPER:
+ case NETDEV_CHANGELOWERSTATE:
+ case NETDEV_UDP_TUNNEL_PUSH_INFO:
+ case NETDEV_CHANGE_TX_QUEUE_LEN:
+ rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
break;
default:
- rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
break;
}
return NOTIFY_DONE;
@@ -4185,6 +4188,7 @@ void __init rtnetlink_init(void)
rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all, NULL);
rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, NULL);
+ rtnl_register(PF_UNSPEC, RTM_GETNETCONF, NULL, rtnl_dump_all, NULL);
rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, NULL);
rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, NULL);
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 758f140b..6bd2f8f 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -20,9 +20,11 @@
#include <net/tcp.h>
static siphash_key_t net_secret __read_mostly;
+static siphash_key_t ts_secret __read_mostly;
static __always_inline void net_secret_init(void)
{
+ net_get_random_once(&ts_secret, sizeof(ts_secret));
net_get_random_once(&net_secret, sizeof(net_secret));
}
#endif
@@ -45,8 +47,25 @@ static u32 seq_scale(u32 seq)
#endif
#if IS_ENABLED(CONFIG_IPV6)
-u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
- __be16 sport, __be16 dport, u32 *tsoff)
+static u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr)
+{
+ const struct {
+ struct in6_addr saddr;
+ struct in6_addr daddr;
+ } __aligned(SIPHASH_ALIGNMENT) combined = {
+ .saddr = *(struct in6_addr *)saddr,
+ .daddr = *(struct in6_addr *)daddr,
+ };
+
+ if (sysctl_tcp_timestamps != 1)
+ return 0;
+
+ return siphash(&combined, offsetofend(typeof(combined), daddr),
+ &ts_secret);
+}
+
+u32 secure_tcpv6_seq_and_tsoff(const __be32 *saddr, const __be32 *daddr,
+ __be16 sport, __be16 dport, u32 *tsoff)
{
const struct {
struct in6_addr saddr;
@@ -63,10 +82,10 @@ u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
net_secret_init();
hash = siphash(&combined, offsetofend(typeof(combined), dport),
&net_secret);
- *tsoff = sysctl_tcp_timestamps == 1 ? (hash >> 32) : 0;
+ *tsoff = secure_tcpv6_ts_off(saddr, daddr);
return seq_scale(hash);
}
-EXPORT_SYMBOL(secure_tcpv6_sequence_number);
+EXPORT_SYMBOL(secure_tcpv6_seq_and_tsoff);
u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
__be16 dport)
@@ -88,22 +107,29 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
#endif
#ifdef CONFIG_INET
+static u32 secure_tcp_ts_off(__be32 saddr, __be32 daddr)
+{
+ if (sysctl_tcp_timestamps != 1)
+ return 0;
-/* secure_tcp_sequence_number(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d),
+ return siphash_2u32((__force u32)saddr, (__force u32)daddr,
+ &ts_secret);
+}
+
+/* secure_tcp_seq_and_tsoff(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d),
* but fortunately, `sport' cannot be 0 in any circumstances. If this changes,
* it would be easy enough to have the former function use siphash_4u32, passing
* the arguments as separate u32.
*/
-
-u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
- __be16 sport, __be16 dport, u32 *tsoff)
+u32 secure_tcp_seq_and_tsoff(__be32 saddr, __be32 daddr,
+ __be16 sport, __be16 dport, u32 *tsoff)
{
u64 hash;
net_secret_init();
hash = siphash_3u32((__force u32)saddr, (__force u32)daddr,
(__force u32)sport << 16 | (__force u32)dport,
&net_secret);
- *tsoff = sysctl_tcp_timestamps == 1 ? (hash >> 32) : 0;
+ *tsoff = secure_tcp_ts_off(saddr, daddr);
return seq_scale(hash);
}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f355795..9f78109 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3694,6 +3694,15 @@ static void sock_rmem_free(struct sk_buff *skb)
atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
}
+static void skb_set_err_queue(struct sk_buff *skb)
+{
+ /* pkt_type of skbs received on local sockets is never PACKET_OUTGOING.
+ * So, it is safe to (mis)use it to mark skbs on the error queue.
+ */
+ skb->pkt_type = PACKET_OUTGOING;
+ BUILD_BUG_ON(PACKET_OUTGOING == 0);
+}
+
/*
* Note: We dont mem charge error packets (no sk_forward_alloc changes)
*/
@@ -3707,6 +3716,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
skb->sk = sk;
skb->destructor = sock_rmem_free;
atomic_add(skb->truesize, &sk->sk_rmem_alloc);
+ skb_set_err_queue(skb);
/* before exiting rcu section, make sure dst is refcounted */
skb_dst_force(skb);
@@ -3783,16 +3793,20 @@ EXPORT_SYMBOL(skb_clone_sk);
static void __skb_complete_tx_timestamp(struct sk_buff *skb,
struct sock *sk,
- int tstype)
+ int tstype,
+ bool opt_stats)
{
struct sock_exterr_skb *serr;
int err;
+ BUILD_BUG_ON(sizeof(struct sock_exterr_skb) > sizeof(skb->cb));
+
serr = SKB_EXT_ERR(skb);
memset(serr, 0, sizeof(*serr));
serr->ee.ee_errno = ENOMSG;
serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
serr->ee.ee_info = tstype;
+ serr->opt_stats = opt_stats;
if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) {
serr->ee.ee_data = skb_shinfo(skb)->tskey;
if (sk->sk_protocol == IPPROTO_TCP &&
@@ -3828,13 +3842,14 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
if (!skb_may_tx_timestamp(sk, false))
return;
- /* take a reference to prevent skb_orphan() from freeing the socket */
- sock_hold(sk);
-
- *skb_hwtstamps(skb) = *hwtstamps;
- __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
-
- sock_put(sk);
+ /* Take a reference to prevent skb_orphan() from freeing the socket,
+ * but only if the socket refcount is not zero.
+ */
+ if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) {
+ *skb_hwtstamps(skb) = *hwtstamps;
+ __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND, false);
+ sock_put(sk);
+ }
}
EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);
@@ -3843,7 +3858,7 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
struct sock *sk, int tstype)
{
struct sk_buff *skb;
- bool tsonly;
+ bool tsonly, opt_stats = false;
if (!sk)
return;
@@ -3856,9 +3871,10 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
#ifdef CONFIG_INET
if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) &&
sk->sk_protocol == IPPROTO_TCP &&
- sk->sk_type == SOCK_STREAM)
+ sk->sk_type == SOCK_STREAM) {
skb = tcp_get_timestamping_opt_stats(sk);
- else
+ opt_stats = true;
+ } else
#endif
skb = alloc_skb(0, GFP_ATOMIC);
} else {
@@ -3877,7 +3893,7 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
else
skb->tstamp = ktime_get_real();
- __skb_complete_tx_timestamp(skb, sk, tstype);
+ __skb_complete_tx_timestamp(skb, sk, tstype, opt_stats);
}
EXPORT_SYMBOL_GPL(__skb_tstamp_tx);
@@ -3893,7 +3909,7 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked)
{
struct sock *sk = skb->sk;
struct sock_exterr_skb *serr;
- int err;
+ int err = 1;
skb->wifi_acked_valid = 1;
skb->wifi_acked = acked;
@@ -3903,14 +3919,15 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked)
serr->ee.ee_errno = ENOMSG;
serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS;
- /* take a reference to prevent skb_orphan() from freeing the socket */
- sock_hold(sk);
-
- err = sock_queue_err_skb(sk, skb);
+ /* Take a reference to prevent skb_orphan() from freeing the socket,
+ * but only if the socket refcount is not zero.
+ */
+ if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) {
+ err = sock_queue_err_skb(sk, skb);
+ sock_put(sk);
+ }
if (err)
kfree_skb(skb);
-
- sock_put(sk);
}
EXPORT_SYMBOL_GPL(skb_complete_wifi_ack);
diff --git a/net/core/sock.c b/net/core/sock.c
index f6fd79f..a06bb7a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -197,73 +197,117 @@ EXPORT_SYMBOL(sk_net_capable);
/*
* Each address family might have different locking rules, so we have
- * one slock key per address family:
+ * one slock key per address family and separate keys for internal and
+ * userspace sockets.
*/
static struct lock_class_key af_family_keys[AF_MAX];
+static struct lock_class_key af_family_kern_keys[AF_MAX];
static struct lock_class_key af_family_slock_keys[AF_MAX];
+static struct lock_class_key af_family_kern_slock_keys[AF_MAX];
/*
* Make lock validator output more readable. (we pre-construct these
* strings build-time, so that runtime initialization of socket
* locks is fast):
*/
+
+#define _sock_locks(x) \
+ x "AF_UNSPEC", x "AF_UNIX" , x "AF_INET" , \
+ x "AF_AX25" , x "AF_IPX" , x "AF_APPLETALK", \
+ x "AF_NETROM", x "AF_BRIDGE" , x "AF_ATMPVC" , \
+ x "AF_X25" , x "AF_INET6" , x "AF_ROSE" , \
+ x "AF_DECnet", x "AF_NETBEUI" , x "AF_SECURITY" , \
+ x "AF_KEY" , x "AF_NETLINK" , x "AF_PACKET" , \
+ x "AF_ASH" , x "AF_ECONET" , x "AF_ATMSVC" , \
+ x "AF_RDS" , x "AF_SNA" , x "AF_IRDA" , \
+ x "AF_PPPOX" , x "AF_WANPIPE" , x "AF_LLC" , \
+ x "27" , x "28" , x "AF_CAN" , \
+ x "AF_TIPC" , x "AF_BLUETOOTH", x "IUCV" , \
+ x "AF_RXRPC" , x "AF_ISDN" , x "AF_PHONET" , \
+ x "AF_IEEE802154", x "AF_CAIF" , x "AF_ALG" , \
+ x "AF_NFC" , x "AF_VSOCK" , x "AF_KCM" , \
+ x "AF_QIPCRTR", x "AF_SMC" , x "AF_MAX"
+
static const char *const af_family_key_strings[AF_MAX+1] = {
- "sk_lock-AF_UNSPEC", "sk_lock-AF_UNIX" , "sk_lock-AF_INET" ,
- "sk_lock-AF_AX25" , "sk_lock-AF_IPX" , "sk_lock-AF_APPLETALK",
- "sk_lock-AF_NETROM", "sk_lock-AF_BRIDGE" , "sk_lock-AF_ATMPVC" ,
- "sk_lock-AF_X25" , "sk_lock-AF_INET6" , "sk_lock-AF_ROSE" ,
- "sk_lock-AF_DECnet", "sk_lock-AF_NETBEUI" , "sk_lock-AF_SECURITY" ,
- "sk_lock-AF_KEY" , "sk_lock-AF_NETLINK" , "sk_lock-AF_PACKET" ,
- "sk_lock-AF_ASH" , "sk_lock-AF_ECONET" , "sk_lock-AF_ATMSVC" ,
- "sk_lock-AF_RDS" , "sk_lock-AF_SNA" , "sk_lock-AF_IRDA" ,
- "sk_lock-AF_PPPOX" , "sk_lock-AF_WANPIPE" , "sk_lock-AF_LLC" ,
- "sk_lock-27" , "sk_lock-28" , "sk_lock-AF_CAN" ,
- "sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV" ,
- "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN" , "sk_lock-AF_PHONET" ,
- "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG" ,
- "sk_lock-AF_NFC" , "sk_lock-AF_VSOCK" , "sk_lock-AF_KCM" ,
- "sk_lock-AF_QIPCRTR", "sk_lock-AF_SMC" , "sk_lock-AF_MAX"
+ _sock_locks("sk_lock-")
};
static const char *const af_family_slock_key_strings[AF_MAX+1] = {
- "slock-AF_UNSPEC", "slock-AF_UNIX" , "slock-AF_INET" ,
- "slock-AF_AX25" , "slock-AF_IPX" , "slock-AF_APPLETALK",
- "slock-AF_NETROM", "slock-AF_BRIDGE" , "slock-AF_ATMPVC" ,
- "slock-AF_X25" , "slock-AF_INET6" , "slock-AF_ROSE" ,
- "slock-AF_DECnet", "slock-AF_NETBEUI" , "slock-AF_SECURITY" ,
- "slock-AF_KEY" , "slock-AF_NETLINK" , "slock-AF_PACKET" ,
- "slock-AF_ASH" , "slock-AF_ECONET" , "slock-AF_ATMSVC" ,
- "slock-AF_RDS" , "slock-AF_SNA" , "slock-AF_IRDA" ,
- "slock-AF_PPPOX" , "slock-AF_WANPIPE" , "slock-AF_LLC" ,
- "slock-27" , "slock-28" , "slock-AF_CAN" ,
- "slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_IUCV" ,
- "slock-AF_RXRPC" , "slock-AF_ISDN" , "slock-AF_PHONET" ,
- "slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG" ,
- "slock-AF_NFC" , "slock-AF_VSOCK" ,"slock-AF_KCM" ,
- "slock-AF_QIPCRTR", "slock-AF_SMC" , "slock-AF_MAX"
+ _sock_locks("slock-")
};
static const char *const af_family_clock_key_strings[AF_MAX+1] = {
- "clock-AF_UNSPEC", "clock-AF_UNIX" , "clock-AF_INET" ,
- "clock-AF_AX25" , "clock-AF_IPX" , "clock-AF_APPLETALK",
- "clock-AF_NETROM", "clock-AF_BRIDGE" , "clock-AF_ATMPVC" ,
- "clock-AF_X25" , "clock-AF_INET6" , "clock-AF_ROSE" ,
- "clock-AF_DECnet", "clock-AF_NETBEUI" , "clock-AF_SECURITY" ,
- "clock-AF_KEY" , "clock-AF_NETLINK" , "clock-AF_PACKET" ,
- "clock-AF_ASH" , "clock-AF_ECONET" , "clock-AF_ATMSVC" ,
- "clock-AF_RDS" , "clock-AF_SNA" , "clock-AF_IRDA" ,
- "clock-AF_PPPOX" , "clock-AF_WANPIPE" , "clock-AF_LLC" ,
- "clock-27" , "clock-28" , "clock-AF_CAN" ,
- "clock-AF_TIPC" , "clock-AF_BLUETOOTH", "clock-AF_IUCV" ,
- "clock-AF_RXRPC" , "clock-AF_ISDN" , "clock-AF_PHONET" ,
- "clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG" ,
- "clock-AF_NFC" , "clock-AF_VSOCK" , "clock-AF_KCM" ,
- "clock-AF_QIPCRTR", "clock-AF_SMC" , "clock-AF_MAX"
+ _sock_locks("clock-")
+};
+
+static const char *const af_family_kern_key_strings[AF_MAX+1] = {
+ _sock_locks("k-sk_lock-")
+};
+static const char *const af_family_kern_slock_key_strings[AF_MAX+1] = {
+ _sock_locks("k-slock-")
+};
+static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = {
+ _sock_locks("k-clock-")
+};
+static const char *const af_family_rlock_key_strings[AF_MAX+1] = {
+ "rlock-AF_UNSPEC", "rlock-AF_UNIX" , "rlock-AF_INET" ,
+ "rlock-AF_AX25" , "rlock-AF_IPX" , "rlock-AF_APPLETALK",
+ "rlock-AF_NETROM", "rlock-AF_BRIDGE" , "rlock-AF_ATMPVC" ,
+ "rlock-AF_X25" , "rlock-AF_INET6" , "rlock-AF_ROSE" ,
+ "rlock-AF_DECnet", "rlock-AF_NETBEUI" , "rlock-AF_SECURITY" ,
+ "rlock-AF_KEY" , "rlock-AF_NETLINK" , "rlock-AF_PACKET" ,
+ "rlock-AF_ASH" , "rlock-AF_ECONET" , "rlock-AF_ATMSVC" ,
+ "rlock-AF_RDS" , "rlock-AF_SNA" , "rlock-AF_IRDA" ,
+ "rlock-AF_PPPOX" , "rlock-AF_WANPIPE" , "rlock-AF_LLC" ,
+ "rlock-27" , "rlock-28" , "rlock-AF_CAN" ,
+ "rlock-AF_TIPC" , "rlock-AF_BLUETOOTH", "rlock-AF_IUCV" ,
+ "rlock-AF_RXRPC" , "rlock-AF_ISDN" , "rlock-AF_PHONET" ,
+ "rlock-AF_IEEE802154", "rlock-AF_CAIF" , "rlock-AF_ALG" ,
+ "rlock-AF_NFC" , "rlock-AF_VSOCK" , "rlock-AF_KCM" ,
+ "rlock-AF_QIPCRTR", "rlock-AF_SMC" , "rlock-AF_MAX"
+};
+static const char *const af_family_wlock_key_strings[AF_MAX+1] = {
+ "wlock-AF_UNSPEC", "wlock-AF_UNIX" , "wlock-AF_INET" ,
+ "wlock-AF_AX25" , "wlock-AF_IPX" , "wlock-AF_APPLETALK",
+ "wlock-AF_NETROM", "wlock-AF_BRIDGE" , "wlock-AF_ATMPVC" ,
+ "wlock-AF_X25" , "wlock-AF_INET6" , "wlock-AF_ROSE" ,
+ "wlock-AF_DECnet", "wlock-AF_NETBEUI" , "wlock-AF_SECURITY" ,
+ "wlock-AF_KEY" , "wlock-AF_NETLINK" , "wlock-AF_PACKET" ,
+ "wlock-AF_ASH" , "wlock-AF_ECONET" , "wlock-AF_ATMSVC" ,
+ "wlock-AF_RDS" , "wlock-AF_SNA" , "wlock-AF_IRDA" ,
+ "wlock-AF_PPPOX" , "wlock-AF_WANPIPE" , "wlock-AF_LLC" ,
+ "wlock-27" , "wlock-28" , "wlock-AF_CAN" ,
+ "wlock-AF_TIPC" , "wlock-AF_BLUETOOTH", "wlock-AF_IUCV" ,
+ "wlock-AF_RXRPC" , "wlock-AF_ISDN" , "wlock-AF_PHONET" ,
+ "wlock-AF_IEEE802154", "wlock-AF_CAIF" , "wlock-AF_ALG" ,
+ "wlock-AF_NFC" , "wlock-AF_VSOCK" , "wlock-AF_KCM" ,
+ "wlock-AF_QIPCRTR", "wlock-AF_SMC" , "wlock-AF_MAX"
+};
+static const char *const af_family_elock_key_strings[AF_MAX+1] = {
+ "elock-AF_UNSPEC", "elock-AF_UNIX" , "elock-AF_INET" ,
+ "elock-AF_AX25" , "elock-AF_IPX" , "elock-AF_APPLETALK",
+ "elock-AF_NETROM", "elock-AF_BRIDGE" , "elock-AF_ATMPVC" ,
+ "elock-AF_X25" , "elock-AF_INET6" , "elock-AF_ROSE" ,
+ "elock-AF_DECnet", "elock-AF_NETBEUI" , "elock-AF_SECURITY" ,
+ "elock-AF_KEY" , "elock-AF_NETLINK" , "elock-AF_PACKET" ,
+ "elock-AF_ASH" , "elock-AF_ECONET" , "elock-AF_ATMSVC" ,
+ "elock-AF_RDS" , "elock-AF_SNA" , "elock-AF_IRDA" ,
+ "elock-AF_PPPOX" , "elock-AF_WANPIPE" , "elock-AF_LLC" ,
+ "elock-27" , "elock-28" , "elock-AF_CAN" ,
+ "elock-AF_TIPC" , "elock-AF_BLUETOOTH", "elock-AF_IUCV" ,
+ "elock-AF_RXRPC" , "elock-AF_ISDN" , "elock-AF_PHONET" ,
+ "elock-AF_IEEE802154", "elock-AF_CAIF" , "elock-AF_ALG" ,
+ "elock-AF_NFC" , "elock-AF_VSOCK" , "elock-AF_KCM" ,
+ "elock-AF_QIPCRTR", "elock-AF_SMC" , "elock-AF_MAX"
};
/*
- * sk_callback_lock locking rules are per-address-family,
+ * sk_callback_lock and sk queues locking rules are per-address-family,
* so split the lock classes by using a per-AF key:
*/
static struct lock_class_key af_callback_keys[AF_MAX];
+static struct lock_class_key af_rlock_keys[AF_MAX];
+static struct lock_class_key af_wlock_keys[AF_MAX];
+static struct lock_class_key af_elock_keys[AF_MAX];
+static struct lock_class_key af_kern_callback_keys[AF_MAX];
/* Take into consideration the size of the struct sk_buff overhead in the
* determination of these values, since that is non-constant across
@@ -1039,6 +1083,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
union {
int val;
+ u64 val64;
struct linger ling;
struct timeval tm;
} v;
@@ -1269,6 +1314,40 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
v.val = sk->sk_incoming_cpu;
break;
+ case SO_MEMINFO:
+ {
+ u32 meminfo[SK_MEMINFO_VARS];
+
+ if (get_user(len, optlen))
+ return -EFAULT;
+
+ sk_get_meminfo(sk, meminfo);
+
+ len = min_t(unsigned int, len, sizeof(meminfo));
+ if (copy_to_user(optval, &meminfo, len))
+ return -EFAULT;
+
+ goto lenout;
+ }
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+ case SO_INCOMING_NAPI_ID:
+ v.val = READ_ONCE(sk->sk_napi_id);
+
+ /* aggregate non-NAPI IDs down to 0 */
+ if (v.val < MIN_NAPI_ID)
+ v.val = 0;
+
+ break;
+#endif
+
+ case SO_COOKIE:
+ lv = sizeof(u64);
+ if (len < lv)
+ return -EINVAL;
+ v.val64 = sock_gen_cookie(sk);
+ break;
+
default:
/* We implement the SO_SNDLOWAT etc to not be settable
* (1003.1g 7).
@@ -1293,7 +1372,16 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
*/
static inline void sock_lock_init(struct sock *sk)
{
- sock_lock_init_class_and_name(sk,
+ if (sk->sk_kern_sock)
+ sock_lock_init_class_and_name(
+ sk,
+ af_family_kern_slock_key_strings[sk->sk_family],
+ af_family_kern_slock_keys + sk->sk_family,
+ af_family_kern_key_strings[sk->sk_family],
+ af_family_kern_keys + sk->sk_family);
+ else
+ sock_lock_init_class_and_name(
+ sk,
af_family_slock_key_strings[sk->sk_family],
af_family_slock_keys + sk->sk_family,
af_family_key_strings[sk->sk_family],
@@ -1399,6 +1487,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
* why we need sk_prot_creator -acme
*/
sk->sk_prot = sk->sk_prot_creator = prot;
+ sk->sk_kern_sock = kern;
sock_lock_init(sk);
sk->sk_net_refcnt = kern ? 0 : 1;
if (likely(sk->sk_net_refcnt))
@@ -1442,6 +1531,11 @@ static void __sk_destruct(struct rcu_head *head)
pr_debug("%s: optmem leakage (%d bytes) detected\n",
__func__, atomic_read(&sk->sk_omem_alloc));
+ if (sk->sk_frag.page) {
+ put_page(sk->sk_frag.page);
+ sk->sk_frag.page = NULL;
+ }
+
if (sk->sk_peer_cred)
put_cred(sk->sk_peer_cred);
put_pid(sk->sk_peer_pid);
@@ -1478,6 +1572,27 @@ void sk_free(struct sock *sk)
}
EXPORT_SYMBOL(sk_free);
+static void sk_init_common(struct sock *sk)
+{
+ skb_queue_head_init(&sk->sk_receive_queue);
+ skb_queue_head_init(&sk->sk_write_queue);
+ skb_queue_head_init(&sk->sk_error_queue);
+
+ rwlock_init(&sk->sk_callback_lock);
+ lockdep_set_class_and_name(&sk->sk_receive_queue.lock,
+ af_rlock_keys + sk->sk_family,
+ af_family_rlock_key_strings[sk->sk_family]);
+ lockdep_set_class_and_name(&sk->sk_write_queue.lock,
+ af_wlock_keys + sk->sk_family,
+ af_family_wlock_key_strings[sk->sk_family]);
+ lockdep_set_class_and_name(&sk->sk_error_queue.lock,
+ af_elock_keys + sk->sk_family,
+ af_family_elock_key_strings[sk->sk_family]);
+ lockdep_set_class_and_name(&sk->sk_callback_lock,
+ af_callback_keys + sk->sk_family,
+ af_family_clock_key_strings[sk->sk_family]);
+}
+
/**
* sk_clone_lock - clone a socket, and lock its clone
* @sk: the socket to clone
@@ -1511,13 +1626,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
*/
atomic_set(&newsk->sk_wmem_alloc, 1);
atomic_set(&newsk->sk_omem_alloc, 0);
- skb_queue_head_init(&newsk->sk_receive_queue);
- skb_queue_head_init(&newsk->sk_write_queue);
-
- rwlock_init(&newsk->sk_callback_lock);
- lockdep_set_class_and_name(&newsk->sk_callback_lock,
- af_callback_keys + newsk->sk_family,
- af_family_clock_key_strings[newsk->sk_family]);
+ sk_init_common(newsk);
newsk->sk_dst_cache = NULL;
newsk->sk_dst_pending_confirm = 0;
@@ -1528,7 +1637,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;
sock_reset_flag(newsk, SOCK_DONE);
- skb_queue_head_init(&newsk->sk_error_queue);
filter = rcu_dereference_protected(newsk->sk_filter, 1);
if (filter != NULL)
@@ -1539,6 +1647,12 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
is_charged = sk_filter_charge(newsk, filter);
if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) {
+ /* We need to make sure that we don't uncharge the new
+ * socket if we couldn't charge it in the first place
+ * as otherwise we uncharge the parent's filter.
+ */
+ if (!is_charged)
+ RCU_INIT_POINTER(newsk->sk_filter, NULL);
sk_free_unlock_clone(newsk);
newsk = NULL;
goto out;
@@ -2277,7 +2391,8 @@ int sock_no_socketpair(struct socket *sock1, struct socket *sock2)
}
EXPORT_SYMBOL(sock_no_socketpair);
-int sock_no_accept(struct socket *sock, struct socket *newsock, int flags)
+int sock_no_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
return -EOPNOTSUPP;
}
@@ -2454,10 +2569,7 @@ EXPORT_SYMBOL(sk_stop_timer);
void sock_init_data(struct socket *sock, struct sock *sk)
{
- skb_queue_head_init(&sk->sk_receive_queue);
- skb_queue_head_init(&sk->sk_write_queue);
- skb_queue_head_init(&sk->sk_error_queue);
-
+ sk_init_common(sk);
sk->sk_send_head = NULL;
init_timer(&sk->sk_timer);
@@ -2481,7 +2593,14 @@ void sock_init_data(struct socket *sock, struct sock *sk)
}
rwlock_init(&sk->sk_callback_lock);
- lockdep_set_class_and_name(&sk->sk_callback_lock,
+ if (sk->sk_kern_sock)
+ lockdep_set_class_and_name(
+ &sk->sk_callback_lock,
+ af_kern_callback_keys + sk->sk_family,
+ af_family_kern_clock_key_strings[sk->sk_family]);
+ else
+ lockdep_set_class_and_name(
+ &sk->sk_callback_lock,
af_callback_keys + sk->sk_family,
af_family_clock_key_strings[sk->sk_family]);
@@ -2502,7 +2621,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT;
sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
- sk->sk_stamp = ktime_set(-1L, 0);
+ sk->sk_stamp = SK_DEFAULT_STAMP;
#ifdef CONFIG_NET_RX_BUSY_POLL
sk->sk_napi_id = 0;
@@ -2779,15 +2898,25 @@ void sk_common_release(struct sock *sk)
sk_refcnt_debug_release(sk);
- if (sk->sk_frag.page) {
- put_page(sk->sk_frag.page);
- sk->sk_frag.page = NULL;
- }
-
sock_put(sk);
}
EXPORT_SYMBOL(sk_common_release);
+void sk_get_meminfo(const struct sock *sk, u32 *mem)
+{
+ memset(mem, 0, sizeof(*mem) * SK_MEMINFO_VARS);
+
+ mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk);
+ mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf;
+ mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk);
+ mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf;
+ mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
+ mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
+ mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
+ mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len;
+ mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops);
+}
+
#ifdef CONFIG_PROC_FS
#define PROTO_INUSE_NR 64 /* should be enough for the first time */
struct prot_inuse {
@@ -3128,3 +3257,14 @@ static int __init proto_init(void)
subsys_initcall(proto_init);
#endif /* PROC_FS */
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+bool sk_busy_loop_end(void *p, unsigned long start_time)
+{
+ struct sock *sk = p;
+
+ return !skb_queue_empty(&sk->sk_receive_queue) ||
+ sk_busy_loop_timeout(sk, start_time);
+}
+EXPORT_SYMBOL(sk_busy_loop_end);
+#endif /* CONFIG_NET_RX_BUSY_POLL */
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index 6b10573..fb9d0e2 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -19,7 +19,7 @@ static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh);
static DEFINE_MUTEX(sock_diag_table_mutex);
static struct workqueue_struct *broadcast_wq;
-static u64 sock_gen_cookie(struct sock *sk)
+u64 sock_gen_cookie(struct sock *sk)
{
while (1) {
u64 res = atomic64_read(&sk->sk_cookie);
@@ -59,15 +59,7 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype)
{
u32 mem[SK_MEMINFO_VARS];
- mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk);
- mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf;
- mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk);
- mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf;
- mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
- mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
- mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
- mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len;
- mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops);
+ sk_get_meminfo(sk, mem);
return nla_put(skb, attrtype, sizeof(mem), &mem);
}
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index 9a1a352..eed1ebf 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -13,9 +13,9 @@
static DEFINE_SPINLOCK(reuseport_lock);
-static struct sock_reuseport *__reuseport_alloc(u16 max_socks)
+static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks)
{
- size_t size = sizeof(struct sock_reuseport) +
+ unsigned int size = sizeof(struct sock_reuseport) +
sizeof(struct sock *) * max_socks;
struct sock_reuseport *reuse = kzalloc(size, GFP_ATOMIC);
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 4ead336..7f9cc40 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -408,14 +408,16 @@ static struct ctl_table net_core_table[] = {
.data = &sysctl_net_busy_poll,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
},
{
.procname = "busy_read",
.data = &sysctl_net_busy_read,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
},
#endif
#ifdef CONFIG_NET_SCHED
diff --git a/net/core/utils.c b/net/core/utils.c
index 6592d7b..d758880c 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -51,7 +51,7 @@ EXPORT_SYMBOL(net_ratelimit);
__be32 in_aton(const char *str)
{
- unsigned long l;
+ unsigned int l;
unsigned int val;
int i;
diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index f053198..5e3a730 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -749,6 +749,7 @@ static void ccid2_hc_tx_exit(struct sock *sk)
for (i = 0; i < hc->tx_seqbufc; i++)
kfree(hc->tx_seqbuf[i]);
hc->tx_seqbufc = 0;
+ dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks);
}
static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb)
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 409d0cf..b99168b 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -289,7 +289,8 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
switch (type) {
case ICMP_REDIRECT:
- dccp_do_redirect(skb, sk);
+ if (!sock_owned_by_user(sk))
+ dccp_do_redirect(skb, sk);
goto out;
case ICMP_SOURCE_QUENCH:
/* Just silently ignore these. */
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 233b573..d9b6a4e 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -122,10 +122,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
np = inet6_sk(sk);
if (type == NDISC_REDIRECT) {
- struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
+ if (!sock_owned_by_user(sk)) {
+ struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
- if (dst)
- dst->ops->redirect(dst, sk, skb);
+ if (dst)
+ dst->ops->redirect(dst, sk, skb);
+ }
goto out;
}
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index e267e6f..abd07a4 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -142,6 +142,13 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
struct dccp_request_sock *dreq = dccp_rsk(req);
bool own_req;
+ /* TCP/DCCP listeners became lockless.
+ * DCCP stores complex state in its request_sock, so we need
+ * a protection for them, now this code runs without being protected
+ * by the parent (listener) lock.
+ */
+ spin_lock_bh(&dreq->dreq_lock);
+
/* Check for retransmitted REQUEST */
if (dccp_hdr(skb)->dccph_type == DCCP_PKT_REQUEST) {
@@ -156,7 +163,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
inet_rtx_syn_ack(sk, req);
}
/* Network Duplicate, discard packet */
- return NULL;
+ goto out;
}
DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_PACKET_ERROR;
@@ -182,20 +189,20 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
req, &own_req);
- if (!child)
- goto listen_overflow;
+ if (child) {
+ child = inet_csk_complete_hashdance(sk, child, req, own_req);
+ goto out;
+ }
- return inet_csk_complete_hashdance(sk, child, req, own_req);
-
-listen_overflow:
- dccp_pr_debug("listen_overflow!\n");
DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY;
drop:
if (dccp_hdr(skb)->dccph_type != DCCP_PKT_RESET)
req->rsk_ops->send_reset(sk, skb);
inet_csk_reqsk_queue_drop(sk, req);
- return NULL;
+out:
+ spin_unlock_bh(&dreq->dreq_lock);
+ return child;
}
EXPORT_SYMBOL_GPL(dccp_check_req);
@@ -246,6 +253,7 @@ int dccp_reqsk_init(struct request_sock *req,
{
struct dccp_request_sock *dreq = dccp_rsk(req);
+ spin_lock_init(&dreq->dreq_lock);
inet_rsk(req)->ir_rmt_port = dccp_hdr(skb)->dccph_sport;
inet_rsk(req)->ir_num = ntohs(dccp_hdr(skb)->dccph_dport);
inet_rsk(req)->acked = 0;
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 0ec8cb4..9afa2a5 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -1071,7 +1071,8 @@ static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo)
return skb == NULL ? ERR_PTR(err) : skb;
}
-static int dn_accept(struct socket *sock, struct socket *newsock, int flags)
+static int dn_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sock *sk = sock->sk, *newsk;
struct sk_buff *skb = NULL;
@@ -1100,7 +1101,7 @@ static int dn_accept(struct socket *sock, struct socket *newsock, int flags)
cb = DN_SKB_CB(skb);
sk->sk_ack_backlog--;
- newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, 0);
+ newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, kern);
if (newsk == NULL) {
release_sock(sk);
kfree_skb(skb);
diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index 9649238..aa21f49 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -6,7 +6,7 @@
config NET_DSA
tristate "Distributed Switch Architecture"
- depends on HAVE_NET_DSA
+ depends on HAVE_NET_DSA && MAY_USE_DEVLINK
select NET_SWITCHDEV
select PHYLIB
---help---
@@ -31,4 +31,6 @@
config NET_DSA_TAG_QCA
bool
+config NET_DSA_TAG_MTK
+ bool
endif
diff --git a/net/dsa/Makefile b/net/dsa/Makefile
index 31d3437..9b1d478 100644
--- a/net/dsa/Makefile
+++ b/net/dsa/Makefile
@@ -8,3 +8,4 @@
dsa_core-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o
dsa_core-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o
dsa_core-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o
+dsa_core-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index b6d4f6a..1fb9cf7 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -14,15 +14,17 @@
#include <linux/platform_device.h>
#include <linux/slab.h>
#include <linux/module.h>
-#include <net/dsa.h>
#include <linux/of.h>
#include <linux/of_mdio.h>
#include <linux/of_platform.h>
#include <linux/of_net.h>
#include <linux/of_gpio.h>
+#include <linux/netdevice.h>
#include <linux/sysfs.h>
#include <linux/phy_fixed.h>
#include <linux/gpio/consumer.h>
+#include <linux/etherdevice.h>
+#include <net/dsa.h>
#include "dsa_priv.h"
static struct sk_buff *dsa_slave_notag_xmit(struct sk_buff *skb,
@@ -53,6 +55,9 @@ const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = {
#ifdef CONFIG_NET_DSA_TAG_QCA
[DSA_TAG_PROTO_QCA] = &qca_netdev_ops,
#endif
+#ifdef CONFIG_NET_DSA_TAG_MTK
+ [DSA_TAG_PROTO_MTK] = &mtk_netdev_ops,
+#endif
[DSA_TAG_PROTO_NONE] = &none_ops,
};
@@ -896,13 +901,34 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev)
{
struct dsa_switch_tree *dst = dev->dsa_ptr;
+ struct sk_buff *nskb = NULL;
if (unlikely(dst == NULL)) {
kfree_skb(skb);
return 0;
}
- return dst->rcv(skb, dev, pt, orig_dev);
+ skb = skb_unshare(skb, GFP_ATOMIC);
+ if (!skb)
+ return 0;
+
+ nskb = dst->rcv(skb, dev, pt, orig_dev);
+ if (!nskb) {
+ kfree_skb(skb);
+ return 0;
+ }
+
+ skb = nskb;
+ skb_push(skb, ETH_HLEN);
+ skb->pkt_type = PACKET_HOST;
+ skb->protocol = eth_type_trans(skb, skb->dev);
+
+ skb->dev->stats.rx_packets++;
+ skb->dev->stats.rx_bytes += skb->len;
+
+ netif_receive_skb(skb);
+
+ return 0;
}
static struct packet_type dsa_pack_type __read_mostly = {
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 737be64..033b3bf 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -13,16 +13,20 @@
#include <linux/device.h>
#include <linux/err.h>
#include <linux/list.h>
+#include <linux/netdevice.h>
#include <linux/slab.h>
#include <linux/rtnetlink.h>
-#include <net/dsa.h>
#include <linux/of.h>
#include <linux/of_net.h>
+#include <net/dsa.h>
#include "dsa_priv.h"
static LIST_HEAD(dsa_switch_trees);
static DEFINE_MUTEX(dsa2_mutex);
+static const struct devlink_ops dsa_devlink_ops = {
+};
+
static struct dsa_switch_tree *dsa_get_dst(u32 tree)
{
struct dsa_switch_tree *dst;
@@ -222,12 +226,18 @@ static int dsa_dsa_port_apply(struct dsa_port *port, u32 index,
return err;
}
- return 0;
+ memset(&ds->ports[index].devlink_port, 0,
+ sizeof(ds->ports[index].devlink_port));
+
+ return devlink_port_register(ds->devlink,
+ &ds->ports[index].devlink_port,
+ index);
}
static void dsa_dsa_port_unapply(struct dsa_port *port, u32 index,
struct dsa_switch *ds)
{
+ devlink_port_unregister(&ds->ports[index].devlink_port);
dsa_cpu_dsa_destroy(port);
}
@@ -245,12 +255,17 @@ static int dsa_cpu_port_apply(struct dsa_port *port, u32 index,
ds->cpu_port_mask |= BIT(index);
- return 0;
+ memset(&ds->ports[index].devlink_port, 0,
+ sizeof(ds->ports[index].devlink_port));
+ err = devlink_port_register(ds->devlink, &ds->ports[index].devlink_port,
+ index);
+ return err;
}
static void dsa_cpu_port_unapply(struct dsa_port *port, u32 index,
struct dsa_switch *ds)
{
+ devlink_port_unregister(&ds->ports[index].devlink_port);
dsa_cpu_dsa_destroy(port);
ds->cpu_port_mask &= ~BIT(index);
@@ -275,12 +290,23 @@ static int dsa_user_port_apply(struct dsa_port *port, u32 index,
return err;
}
+ memset(&ds->ports[index].devlink_port, 0,
+ sizeof(ds->ports[index].devlink_port));
+ err = devlink_port_register(ds->devlink, &ds->ports[index].devlink_port,
+ index);
+ if (err)
+ return err;
+
+ devlink_port_type_eth_set(&ds->ports[index].devlink_port,
+ ds->ports[index].netdev);
+
return 0;
}
static void dsa_user_port_unapply(struct dsa_port *port, u32 index,
struct dsa_switch *ds)
{
+ devlink_port_unregister(&ds->ports[index].devlink_port);
if (ds->ports[index].netdev) {
dsa_slave_destroy(ds->ports[index].netdev);
ds->ports[index].netdev = NULL;
@@ -301,6 +327,17 @@ static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds)
*/
ds->phys_mii_mask = ds->enabled_port_mask;
+ /* Add the switch to devlink before calling setup, so that setup can
+ * add dpipe tables
+ */
+ ds->devlink = devlink_alloc(&dsa_devlink_ops, 0);
+ if (!ds->devlink)
+ return -ENOMEM;
+
+ err = devlink_register(ds->devlink, ds->dev);
+ if (err)
+ return err;
+
err = ds->ops->setup(ds);
if (err < 0)
return err;
@@ -381,6 +418,13 @@ static void dsa_ds_unapply(struct dsa_switch_tree *dst, struct dsa_switch *ds)
mdiobus_unregister(ds->slave_mii_bus);
dsa_switch_unregister_notifier(ds);
+
+ if (ds->devlink) {
+ devlink_unregister(ds->devlink);
+ devlink_free(ds->devlink);
+ ds->devlink = NULL;
+ }
+
}
static int dsa_dst_apply(struct dsa_switch_tree *dst)
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 0706a51..107138a 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -17,8 +17,9 @@
struct dsa_device_ops {
struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev);
- int (*rcv)(struct sk_buff *skb, struct net_device *dev,
- struct packet_type *pt, struct net_device *orig_dev);
+ struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev,
+ struct packet_type *pt,
+ struct net_device *orig_dev);
};
struct dsa_slave_priv {
@@ -85,4 +86,7 @@ extern const struct dsa_device_ops brcm_netdev_ops;
/* tag_qca.c */
extern const struct dsa_device_ops qca_netdev_ops;
+/* tag_mtk.c */
+extern const struct dsa_device_ops mtk_netdev_ops;
+
#endif
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index c34872e..7693182 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -17,6 +17,7 @@
#include <linux/of_mdio.h>
#include <linux/mdio.h>
#include <linux/list.h>
+#include <net/dsa.h>
#include <net/rtnetlink.h>
#include <net/switchdev.h>
#include <net/pkt_cls.h>
@@ -419,8 +420,8 @@ static int dsa_slave_vlan_filtering(struct net_device *dev,
return 0;
}
-static int dsa_fastest_ageing_time(struct dsa_switch *ds,
- unsigned int ageing_time)
+static unsigned int dsa_fastest_ageing_time(struct dsa_switch *ds,
+ unsigned int ageing_time)
{
int i;
@@ -443,9 +444,13 @@ static int dsa_slave_ageing_time(struct net_device *dev,
unsigned long ageing_jiffies = clock_t_to_jiffies(attr->u.ageing_time);
unsigned int ageing_time = jiffies_to_msecs(ageing_jiffies);
- /* bridge skips -EOPNOTSUPP, so skip the prepare phase */
- if (switchdev_trans_ph_prepare(trans))
+ if (switchdev_trans_ph_prepare(trans)) {
+ if (ds->ageing_time_min && ageing_time < ds->ageing_time_min)
+ return -ERANGE;
+ if (ds->ageing_time_max && ageing_time > ds->ageing_time_max)
+ return -ERANGE;
return 0;
+ }
/* Keep the fastest ageing time in case of multiple bridges */
p->dp->ageing_time = ageing_time;
diff --git a/net/dsa/switch.c b/net/dsa/switch.c
index 6456dac..ca6e26e 100644
--- a/net/dsa/switch.c
+++ b/net/dsa/switch.c
@@ -1,7 +1,8 @@
/*
* Handling of a single switch chip, part of a switch fabric
*
- * Copyright (c) 2017 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ * Copyright (c) 2017 Savoir-faire Linux Inc.
+ * Vivien Didelot <vivien.didelot@savoirfairelinux.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -19,9 +20,9 @@ static int dsa_switch_bridge_join(struct dsa_switch *ds,
if (ds->index == info->sw_index && ds->ops->port_bridge_join)
return ds->ops->port_bridge_join(ds, info->port, info->br);
- if (ds->index != info->sw_index)
- dev_dbg(ds->dev, "crosschip DSA port %d.%d bridged to %s\n",
- info->sw_index, info->port, netdev_name(info->br));
+ if (ds->index != info->sw_index && ds->ops->crosschip_bridge_join)
+ return ds->ops->crosschip_bridge_join(ds, info->sw_index,
+ info->port, info->br);
return 0;
}
@@ -32,9 +33,9 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds,
if (ds->index == info->sw_index && ds->ops->port_bridge_leave)
ds->ops->port_bridge_leave(ds, info->port, info->br);
- if (ds->index != info->sw_index)
- dev_dbg(ds->dev, "crosschip DSA port %d.%d unbridged from %s\n",
- info->sw_index, info->port, netdev_name(info->br));
+ if (ds->index != info->sw_index && ds->ops->crosschip_bridge_leave)
+ ds->ops->crosschip_bridge_leave(ds, info->sw_index, info->port,
+ info->br);
return 0;
}
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index 5d925b6..2a9b52c 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -12,6 +12,7 @@
#include <linux/etherdevice.h>
#include <linux/list.h>
#include <linux/slab.h>
+#include <net/dsa.h>
#include "dsa_priv.h"
/* This tag length is 4 bytes, older ones were 6 bytes, we do not
@@ -91,23 +92,17 @@ static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev
return NULL;
}
-static int brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev,
- struct packet_type *pt, struct net_device *orig_dev)
+static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev,
+ struct packet_type *pt,
+ struct net_device *orig_dev)
{
struct dsa_switch_tree *dst = dev->dsa_ptr;
struct dsa_switch *ds;
int source_port;
u8 *brcm_tag;
- if (unlikely(dst == NULL))
- goto out_drop;
-
ds = dst->cpu_switch;
- skb = skb_unshare(skb, GFP_ATOMIC);
- if (skb == NULL)
- goto out;
-
if (unlikely(!pskb_may_pull(skb, BRCM_TAG_LEN)))
goto out_drop;
@@ -139,22 +134,12 @@ static int brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev,
skb->data - ETH_HLEN - BRCM_TAG_LEN,
2 * ETH_ALEN);
- skb_push(skb, ETH_HLEN);
- skb->pkt_type = PACKET_HOST;
skb->dev = ds->ports[source_port].netdev;
- skb->protocol = eth_type_trans(skb, skb->dev);
- skb->dev->stats.rx_packets++;
- skb->dev->stats.rx_bytes += skb->len;
-
- netif_receive_skb(skb);
-
- return 0;
+ return skb;
out_drop:
- kfree_skb(skb);
-out:
- return 0;
+ return NULL;
}
const struct dsa_device_ops brcm_netdev_ops = {
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index 72579ce..1c6633f 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -11,6 +11,7 @@
#include <linux/etherdevice.h>
#include <linux/list.h>
#include <linux/slab.h>
+#include <net/dsa.h>
#include "dsa_priv.h"
#define DSA_HLEN 4
@@ -67,8 +68,9 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev)
return NULL;
}
-static int dsa_rcv(struct sk_buff *skb, struct net_device *dev,
- struct packet_type *pt, struct net_device *orig_dev)
+static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
+ struct packet_type *pt,
+ struct net_device *orig_dev)
{
struct dsa_switch_tree *dst = dev->dsa_ptr;
struct dsa_switch *ds;
@@ -76,13 +78,6 @@ static int dsa_rcv(struct sk_buff *skb, struct net_device *dev,
int source_device;
int source_port;
- if (unlikely(dst == NULL))
- goto out_drop;
-
- skb = skb_unshare(skb, GFP_ATOMIC);
- if (skb == NULL)
- goto out;
-
if (unlikely(!pskb_may_pull(skb, DSA_HLEN)))
goto out_drop;
@@ -164,21 +159,11 @@ static int dsa_rcv(struct sk_buff *skb, struct net_device *dev,
}
skb->dev = ds->ports[source_port].netdev;
- skb_push(skb, ETH_HLEN);
- skb->pkt_type = PACKET_HOST;
- skb->protocol = eth_type_trans(skb, skb->dev);
- skb->dev->stats.rx_packets++;
- skb->dev->stats.rx_bytes += skb->len;
-
- netif_receive_skb(skb);
-
- return 0;
+ return skb;
out_drop:
- kfree_skb(skb);
-out:
- return 0;
+ return NULL;
}
const struct dsa_device_ops dsa_netdev_ops = {
diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c
index 648c051..d9c668a 100644
--- a/net/dsa/tag_edsa.c
+++ b/net/dsa/tag_edsa.c
@@ -11,6 +11,7 @@
#include <linux/etherdevice.h>
#include <linux/list.h>
#include <linux/slab.h>
+#include <net/dsa.h>
#include "dsa_priv.h"
#define DSA_HLEN 4
@@ -80,8 +81,9 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev)
return NULL;
}
-static int edsa_rcv(struct sk_buff *skb, struct net_device *dev,
- struct packet_type *pt, struct net_device *orig_dev)
+static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev,
+ struct packet_type *pt,
+ struct net_device *orig_dev)
{
struct dsa_switch_tree *dst = dev->dsa_ptr;
struct dsa_switch *ds;
@@ -89,13 +91,6 @@ static int edsa_rcv(struct sk_buff *skb, struct net_device *dev,
int source_device;
int source_port;
- if (unlikely(dst == NULL))
- goto out_drop;
-
- skb = skb_unshare(skb, GFP_ATOMIC);
- if (skb == NULL)
- goto out;
-
if (unlikely(!pskb_may_pull(skb, EDSA_HLEN)))
goto out_drop;
@@ -183,21 +178,11 @@ static int edsa_rcv(struct sk_buff *skb, struct net_device *dev,
}
skb->dev = ds->ports[source_port].netdev;
- skb_push(skb, ETH_HLEN);
- skb->pkt_type = PACKET_HOST;
- skb->protocol = eth_type_trans(skb, skb->dev);
- skb->dev->stats.rx_packets++;
- skb->dev->stats.rx_bytes += skb->len;
-
- netif_receive_skb(skb);
-
- return 0;
+ return skb;
out_drop:
- kfree_skb(skb);
-out:
- return 0;
+ return NULL;
}
const struct dsa_device_ops edsa_netdev_ops = {
diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
new file mode 100644
index 0000000..837cddd
--- /dev/null
+++ b/net/dsa/tag_mtk.c
@@ -0,0 +1,100 @@
+/*
+ * Mediatek DSA Tag support
+ * Copyright (C) 2017 Landen Chao <landen.chao@mediatek.com>
+ * Sean Wang <sean.wang@mediatek.com>
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/etherdevice.h>
+#include <net/dsa.h>
+#include "dsa_priv.h"
+
+#define MTK_HDR_LEN 4
+#define MTK_HDR_RECV_SOURCE_PORT_MASK GENMASK(2, 0)
+#define MTK_HDR_XMIT_DP_BIT_MASK GENMASK(5, 0)
+
+static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ struct dsa_slave_priv *p = netdev_priv(dev);
+ u8 *mtk_tag;
+
+ if (skb_cow_head(skb, MTK_HDR_LEN) < 0)
+ goto out_free;
+
+ skb_push(skb, MTK_HDR_LEN);
+
+ memmove(skb->data, skb->data + MTK_HDR_LEN, 2 * ETH_ALEN);
+
+ /* Build the tag after the MAC Source Address */
+ mtk_tag = skb->data + 2 * ETH_ALEN;
+ mtk_tag[0] = 0;
+ mtk_tag[1] = (1 << p->dp->index) & MTK_HDR_XMIT_DP_BIT_MASK;
+ mtk_tag[2] = 0;
+ mtk_tag[3] = 0;
+
+ return skb;
+
+out_free:
+ kfree_skb(skb);
+ return NULL;
+}
+
+static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev,
+ struct packet_type *pt,
+ struct net_device *orig_dev)
+{
+ struct dsa_switch_tree *dst = dev->dsa_ptr;
+ struct dsa_switch *ds;
+ int port;
+ __be16 *phdr, hdr;
+
+ if (unlikely(!pskb_may_pull(skb, MTK_HDR_LEN)))
+ goto out_drop;
+
+ /* The MTK header is added by the switch between src addr
+ * and ethertype at this point, skb->data points to 2 bytes
+ * after src addr so header should be 2 bytes right before.
+ */
+ phdr = (__be16 *)(skb->data - 2);
+ hdr = ntohs(*phdr);
+
+ /* Remove MTK tag and recalculate checksum. */
+ skb_pull_rcsum(skb, MTK_HDR_LEN);
+
+ memmove(skb->data - ETH_HLEN,
+ skb->data - ETH_HLEN - MTK_HDR_LEN,
+ 2 * ETH_ALEN);
+
+ /* This protocol doesn't support cascading multiple
+ * switches so it's safe to assume the switch is first
+ * in the tree.
+ */
+ ds = dst->ds[0];
+ if (!ds)
+ goto out_drop;
+
+ /* Get source port information */
+ port = (hdr & MTK_HDR_RECV_SOURCE_PORT_MASK);
+ if (!ds->ports[port].netdev)
+ goto out_drop;
+
+ skb->dev = ds->ports[port].netdev;
+
+ return skb;
+
+out_drop:
+ return NULL;
+}
+
+const struct dsa_device_ops mtk_netdev_ops = {
+ .xmit = mtk_tag_xmit,
+ .rcv = mtk_tag_rcv,
+};
diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index 30240f3..3ba3f59 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -12,6 +12,7 @@
*/
#include <linux/etherdevice.h>
+#include <net/dsa.h>
#include "dsa_priv.h"
#define QCA_HDR_LEN 2
@@ -65,8 +66,9 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev)
return NULL;
}
-static int qca_tag_rcv(struct sk_buff *skb, struct net_device *dev,
- struct packet_type *pt, struct net_device *orig_dev)
+static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev,
+ struct packet_type *pt,
+ struct net_device *orig_dev)
{
struct dsa_switch_tree *dst = dev->dsa_ptr;
struct dsa_switch *ds;
@@ -74,13 +76,6 @@ static int qca_tag_rcv(struct sk_buff *skb, struct net_device *dev,
int port;
__be16 *phdr, hdr;
- if (unlikely(!dst))
- goto out_drop;
-
- skb = skb_unshare(skb, GFP_ATOMIC);
- if (!skb)
- goto out;
-
if (unlikely(!pskb_may_pull(skb, QCA_HDR_LEN)))
goto out_drop;
@@ -114,22 +109,12 @@ static int qca_tag_rcv(struct sk_buff *skb, struct net_device *dev,
goto out_drop;
/* Update skb & forward the frame accordingly */
- skb_push(skb, ETH_HLEN);
- skb->pkt_type = PACKET_HOST;
skb->dev = ds->ports[port].netdev;
- skb->protocol = eth_type_trans(skb, skb->dev);
- skb->dev->stats.rx_packets++;
- skb->dev->stats.rx_bytes += skb->len;
-
- netif_receive_skb(skb);
-
- return 0;
+ return skb;
out_drop:
- kfree_skb(skb);
-out:
- return 0;
+ return NULL;
}
const struct dsa_device_ops qca_netdev_ops = {
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index 26f9771..aafc2fc 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -11,6 +11,7 @@
#include <linux/etherdevice.h>
#include <linux/list.h>
#include <linux/slab.h>
+#include <net/dsa.h>
#include "dsa_priv.h"
static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev)
@@ -57,22 +58,17 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev)
return nskb;
}
-static int trailer_rcv(struct sk_buff *skb, struct net_device *dev,
- struct packet_type *pt, struct net_device *orig_dev)
+static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev,
+ struct packet_type *pt,
+ struct net_device *orig_dev)
{
struct dsa_switch_tree *dst = dev->dsa_ptr;
struct dsa_switch *ds;
u8 *trailer;
int source_port;
- if (unlikely(dst == NULL))
- goto out_drop;
ds = dst->cpu_switch;
- skb = skb_unshare(skb, GFP_ATOMIC);
- if (skb == NULL)
- goto out;
-
if (skb_linearize(skb))
goto out_drop;
@@ -88,21 +84,11 @@ static int trailer_rcv(struct sk_buff *skb, struct net_device *dev,
pskb_trim_rcsum(skb, skb->len - 4);
skb->dev = ds->ports[source_port].netdev;
- skb_push(skb, ETH_HLEN);
- skb->pkt_type = PACKET_HOST;
- skb->protocol = eth_type_trans(skb, skb->dev);
- skb->dev->stats.rx_packets++;
- skb->dev->stats.rx_bytes += skb->len;
-
- netif_receive_skb(skb);
-
- return 0;
+ return skb;
out_drop:
- kfree_skb(skb);
-out:
- return 0;
+ return NULL;
}
const struct dsa_device_ops trailer_netdev_ops = {
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index c6d4238..f83de23 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -11,7 +11,7 @@
tcp_rate.o tcp_recovery.o \
tcp_offload.o datagram.o raw.o udp.o udplite.o \
udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \
- fib_frontend.o fib_semantics.o fib_trie.o \
+ fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \
inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o
obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 602d40f..d1a1170 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -689,11 +689,12 @@ EXPORT_SYMBOL(inet_stream_connect);
* Accept a pending connection. The TCP layer now gives BSD semantics.
*/
-int inet_accept(struct socket *sock, struct socket *newsock, int flags)
+int inet_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sock *sk1 = sock->sk;
int err = -EINVAL;
- struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err);
+ struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err, kern);
if (!sk2)
goto do_err;
@@ -1487,8 +1488,10 @@ int inet_gro_complete(struct sk_buff *skb, int nhoff)
int proto = iph->protocol;
int err = -ENOSYS;
- if (skb->encapsulation)
+ if (skb->encapsulation) {
+ skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IP));
skb_set_inner_network_header(skb, nhoff);
+ }
csum_replace2(&iph->check, iph->tot_len, newlen);
iph->tot_len = newlen;
@@ -1596,8 +1599,9 @@ static const struct net_protocol igmp_protocol = {
};
#endif
-static const struct net_protocol tcp_protocol = {
+static struct net_protocol tcp_protocol = {
.early_demux = tcp_v4_early_demux,
+ .early_demux_handler = tcp_v4_early_demux,
.handler = tcp_v4_rcv,
.err_handler = tcp_v4_err,
.no_policy = 1,
@@ -1605,8 +1609,9 @@ static const struct net_protocol tcp_protocol = {
.icmp_strict_tag_validation = 1,
};
-static const struct net_protocol udp_protocol = {
+static struct net_protocol udp_protocol = {
.early_demux = udp_v4_early_demux,
+ .early_demux_handler = udp_v4_early_demux,
.handler = udp_rcv,
.err_handler = udp_err,
.no_policy = 1,
@@ -1717,6 +1722,8 @@ static __net_init int inet_init_net(struct net *net)
net->ipv4.sysctl_ip_default_ttl = IPDEFTTL;
net->ipv4.sysctl_ip_dynaddr = 0;
net->ipv4.sysctl_ip_early_demux = 1;
+ net->ipv4.sysctl_udp_early_demux = 1;
+ net->ipv4.sysctl_tcp_early_demux = 1;
#ifdef CONFIG_SYSCTL
net->ipv4.sysctl_ip_prot_sock = PROT_SOCK;
#endif
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 51b27ae..0937b34 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -872,7 +872,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb)
skb->pkt_type != PACKET_HOST)
state = NUD_STALE;
neigh_update(n, sha, state,
- override ? NEIGH_UPDATE_F_OVERRIDE : 0);
+ override ? NEIGH_UPDATE_F_OVERRIDE : 0, 0);
neigh_release(n);
}
@@ -1033,7 +1033,7 @@ static int arp_req_set(struct net *net, struct arpreq *r,
err = neigh_update(neigh, (r->arp_flags & ATF_COM) ?
r->arp_ha.sa_data : NULL, state,
NEIGH_UPDATE_F_OVERRIDE |
- NEIGH_UPDATE_F_ADMIN);
+ NEIGH_UPDATE_F_ADMIN, 0);
neigh_release(neigh);
}
return err;
@@ -1084,7 +1084,7 @@ static int arp_invalidate(struct net_device *dev, __be32 ip)
if (neigh->nud_state & ~NUD_NOARP)
err = neigh_update(neigh, NULL, NUD_FAILED,
NEIGH_UPDATE_F_OVERRIDE|
- NEIGH_UPDATE_F_ADMIN);
+ NEIGH_UPDATE_F_ADMIN, 0);
neigh_release(neigh);
}
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index cebedd5..6d3602e 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1192,6 +1192,18 @@ static int inet_gifconf(struct net_device *dev, char __user *buf, int len)
return done;
}
+static __be32 in_dev_select_addr(const struct in_device *in_dev,
+ int scope)
+{
+ for_primary_ifa(in_dev) {
+ if (ifa->ifa_scope != RT_SCOPE_LINK &&
+ ifa->ifa_scope <= scope)
+ return ifa->ifa_local;
+ } endfor_ifa(in_dev);
+
+ return 0;
+}
+
__be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope)
{
__be32 addr = 0;
@@ -1228,13 +1240,9 @@ __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope)
if (master_idx &&
(dev = dev_get_by_index_rcu(net, master_idx)) &&
(in_dev = __in_dev_get_rcu(dev))) {
- for_primary_ifa(in_dev) {
- if (ifa->ifa_scope != RT_SCOPE_LINK &&
- ifa->ifa_scope <= scope) {
- addr = ifa->ifa_local;
- goto out_unlock;
- }
- } endfor_ifa(in_dev);
+ addr = in_dev_select_addr(in_dev, scope);
+ if (addr)
+ goto out_unlock;
}
/* Not loopback addresses on loopback should be preferred
@@ -1249,13 +1257,9 @@ __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope)
if (!in_dev)
continue;
- for_primary_ifa(in_dev) {
- if (ifa->ifa_scope != RT_SCOPE_LINK &&
- ifa->ifa_scope <= scope) {
- addr = ifa->ifa_local;
- goto out_unlock;
- }
- } endfor_ifa(in_dev);
+ addr = in_dev_select_addr(in_dev, scope);
+ if (addr)
+ goto out_unlock;
}
out_unlock:
rcu_read_unlock();
@@ -1798,6 +1802,9 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0)
goto nla_put_failure;
+ if (!devconf)
+ goto out;
+
if ((all || type == NETCONFA_FORWARDING) &&
nla_put_s32(skb, NETCONFA_FORWARDING,
IPV4_DEVCONF(*devconf, FORWARDING)) < 0)
@@ -1819,6 +1826,7 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
IPV4_DEVCONF(*devconf, IGNORE_ROUTES_WITH_LINKDOWN)) < 0)
goto nla_put_failure;
+out:
nlmsg_end(skb, nlh);
return 0;
@@ -1827,8 +1835,8 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
return -EMSGSIZE;
}
-void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
- struct ipv4_devconf *devconf)
+void inet_netconf_notify_devconf(struct net *net, int event, int type,
+ int ifindex, struct ipv4_devconf *devconf)
{
struct sk_buff *skb;
int err = -ENOBUFS;
@@ -1838,7 +1846,7 @@ void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
goto errout;
err = inet_netconf_fill_devconf(skb, ifindex, devconf, 0, 0,
- RTM_NEWNETCONF, 0, type);
+ event, 0, type);
if (err < 0) {
/* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */
WARN_ON(err == -EMSGSIZE);
@@ -2017,10 +2025,12 @@ static void inet_forward_change(struct net *net)
IPV4_DEVCONF_ALL(net, ACCEPT_REDIRECTS) = !on;
IPV4_DEVCONF_DFLT(net, FORWARDING) = on;
- inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+ inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+ NETCONFA_FORWARDING,
NETCONFA_IFINDEX_ALL,
net->ipv4.devconf_all);
- inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+ inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+ NETCONFA_FORWARDING,
NETCONFA_IFINDEX_DEFAULT,
net->ipv4.devconf_dflt);
@@ -2033,7 +2043,8 @@ static void inet_forward_change(struct net *net)
in_dev = __in_dev_get_rtnl(dev);
if (in_dev) {
IN_DEV_CONF_SET(in_dev, FORWARDING, on);
- inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+ inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+ NETCONFA_FORWARDING,
dev->ifindex, &in_dev->cnf);
}
}
@@ -2078,19 +2089,22 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write,
if (i == IPV4_DEVCONF_RP_FILTER - 1 &&
new_value != old_value) {
ifindex = devinet_conf_ifindex(net, cnf);
- inet_netconf_notify_devconf(net, NETCONFA_RP_FILTER,
+ inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+ NETCONFA_RP_FILTER,
ifindex, cnf);
}
if (i == IPV4_DEVCONF_PROXY_ARP - 1 &&
new_value != old_value) {
ifindex = devinet_conf_ifindex(net, cnf);
- inet_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH,
+ inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+ NETCONFA_PROXY_NEIGH,
ifindex, cnf);
}
if (i == IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN - 1 &&
new_value != old_value) {
ifindex = devinet_conf_ifindex(net, cnf);
- inet_netconf_notify_devconf(net, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
+ inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+ NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
ifindex, cnf);
}
}
@@ -2125,7 +2139,7 @@ static int devinet_sysctl_forward(struct ctl_table *ctl, int write,
container_of(cnf, struct in_device, cnf);
if (*valp)
dev_disable_lro(idev->dev);
- inet_netconf_notify_devconf(net,
+ inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
NETCONFA_FORWARDING,
idev->dev->ifindex,
cnf);
@@ -2133,7 +2147,8 @@ static int devinet_sysctl_forward(struct ctl_table *ctl, int write,
rtnl_unlock();
rt_cache_flush(net);
} else
- inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+ inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+ NETCONFA_FORWARDING,
NETCONFA_IFINDEX_DEFAULT,
net->ipv4.devconf_dflt);
}
@@ -2255,7 +2270,8 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name,
p->sysctl = t;
- inet_netconf_notify_devconf(net, NETCONFA_ALL, ifindex, p);
+ inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL,
+ ifindex, p);
return 0;
free:
@@ -2264,16 +2280,18 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name,
return -ENOBUFS;
}
-static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf)
+static void __devinet_sysctl_unregister(struct net *net,
+ struct ipv4_devconf *cnf, int ifindex)
{
struct devinet_sysctl_table *t = cnf->sysctl;
- if (!t)
- return;
+ if (t) {
+ cnf->sysctl = NULL;
+ unregister_net_sysctl_table(t->sysctl_header);
+ kfree(t);
+ }
- cnf->sysctl = NULL;
- unregister_net_sysctl_table(t->sysctl_header);
- kfree(t);
+ inet_netconf_notify_devconf(net, RTM_DELNETCONF, 0, ifindex, NULL);
}
static int devinet_sysctl_register(struct in_device *idev)
@@ -2295,7 +2313,9 @@ static int devinet_sysctl_register(struct in_device *idev)
static void devinet_sysctl_unregister(struct in_device *idev)
{
- __devinet_sysctl_unregister(&idev->cnf);
+ struct net *net = dev_net(idev->dev);
+
+ __devinet_sysctl_unregister(net, &idev->cnf, idev->dev->ifindex);
neigh_sysctl_unregister(idev->arp_parms);
}
@@ -2370,9 +2390,9 @@ static __net_init int devinet_init_net(struct net *net)
#ifdef CONFIG_SYSCTL
err_reg_ctl:
- __devinet_sysctl_unregister(dflt);
+ __devinet_sysctl_unregister(net, dflt, NETCONFA_IFINDEX_DEFAULT);
err_reg_dflt:
- __devinet_sysctl_unregister(all);
+ __devinet_sysctl_unregister(net, all, NETCONFA_IFINDEX_ALL);
err_reg_all:
if (tbl != ctl_forward_entry)
kfree(tbl);
@@ -2394,8 +2414,10 @@ static __net_exit void devinet_exit_net(struct net *net)
tbl = net->ipv4.forw_hdr->ctl_table_arg;
unregister_net_sysctl_table(net->ipv4.forw_hdr);
- __devinet_sysctl_unregister(net->ipv4.devconf_dflt);
- __devinet_sysctl_unregister(net->ipv4.devconf_all);
+ __devinet_sysctl_unregister(net, net->ipv4.devconf_dflt,
+ NETCONFA_IFINDEX_DEFAULT);
+ __devinet_sysctl_unregister(net, net->ipv4.devconf_all,
+ NETCONFA_IFINDEX_ALL);
kfree(tbl);
#endif
kfree(net->ipv4.devconf_dflt);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 42bfd08..8f2133f 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1083,7 +1083,8 @@ static void nl_fib_input(struct sk_buff *skb)
net = sock_net(skb->sk);
nlh = nlmsg_hdr(skb);
- if (skb->len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len ||
+ if (skb->len < nlmsg_total_size(sizeof(*frn)) ||
+ skb->len < nlh->nlmsg_len ||
nlmsg_len(nlh) < sizeof(*frn))
return;
diff --git a/net/ipv4/fib_notifier.c b/net/ipv4/fib_notifier.c
new file mode 100644
index 0000000..e0714d9
--- /dev/null
+++ b/net/ipv4/fib_notifier.c
@@ -0,0 +1,86 @@
+#include <linux/rtnetlink.h>
+#include <linux/notifier.h>
+#include <linux/rcupdate.h>
+#include <linux/kernel.h>
+#include <net/net_namespace.h>
+#include <net/netns/ipv4.h>
+#include <net/ip_fib.h>
+
+static ATOMIC_NOTIFIER_HEAD(fib_chain);
+
+int call_fib_notifier(struct notifier_block *nb, struct net *net,
+ enum fib_event_type event_type,
+ struct fib_notifier_info *info)
+{
+ info->net = net;
+ return nb->notifier_call(nb, event_type, info);
+}
+
+int call_fib_notifiers(struct net *net, enum fib_event_type event_type,
+ struct fib_notifier_info *info)
+{
+ net->ipv4.fib_seq++;
+ info->net = net;
+ return atomic_notifier_call_chain(&fib_chain, event_type, info);
+}
+
+static unsigned int fib_seq_sum(void)
+{
+ unsigned int fib_seq = 0;
+ struct net *net;
+
+ rtnl_lock();
+ for_each_net(net)
+ fib_seq += net->ipv4.fib_seq;
+ rtnl_unlock();
+
+ return fib_seq;
+}
+
+static bool fib_dump_is_consistent(struct notifier_block *nb,
+ void (*cb)(struct notifier_block *nb),
+ unsigned int fib_seq)
+{
+ atomic_notifier_chain_register(&fib_chain, nb);
+ if (fib_seq == fib_seq_sum())
+ return true;
+ atomic_notifier_chain_unregister(&fib_chain, nb);
+ if (cb)
+ cb(nb);
+ return false;
+}
+
+#define FIB_DUMP_MAX_RETRIES 5
+int register_fib_notifier(struct notifier_block *nb,
+ void (*cb)(struct notifier_block *nb))
+{
+ int retries = 0;
+
+ do {
+ unsigned int fib_seq = fib_seq_sum();
+ struct net *net;
+
+ /* Mutex semantics guarantee that every change done to
+ * FIB tries before we read the change sequence counter
+ * is now visible to us.
+ */
+ rcu_read_lock();
+ for_each_net_rcu(net) {
+ fib_rules_notify(net, nb);
+ fib_notify(net, nb);
+ }
+ rcu_read_unlock();
+
+ if (fib_dump_is_consistent(nb, cb, fib_seq))
+ return 0;
+ } while (++retries < FIB_DUMP_MAX_RETRIES);
+
+ return -EBUSY;
+}
+EXPORT_SYMBOL(register_fib_notifier);
+
+int unregister_fib_notifier(struct notifier_block *nb)
+{
+ return atomic_notifier_chain_unregister(&fib_chain, nb);
+}
+EXPORT_SYMBOL(unregister_fib_notifier);
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 2e50062..778ecf9 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -47,6 +47,27 @@ struct fib4_rule {
#endif
};
+static bool fib4_rule_matchall(const struct fib_rule *rule)
+{
+ struct fib4_rule *r = container_of(rule, struct fib4_rule, common);
+
+ if (r->dst_len || r->src_len || r->tos)
+ return false;
+ return fib_rule_matchall(rule);
+}
+
+bool fib4_rule_default(const struct fib_rule *rule)
+{
+ if (!fib4_rule_matchall(rule) || rule->action != FR_ACT_TO_TBL ||
+ rule->l3mdev)
+ return false;
+ if (rule->table != RT_TABLE_LOCAL && rule->table != RT_TABLE_MAIN &&
+ rule->table != RT_TABLE_DEFAULT)
+ return false;
+ return true;
+}
+EXPORT_SYMBOL_GPL(fib4_rule_default);
+
int __fib_lookup(struct net *net, struct flowi4 *flp,
struct fib_result *res, unsigned int flags)
{
@@ -164,12 +185,36 @@ static struct fib_table *fib_empty_table(struct net *net)
return NULL;
}
-static int call_fib_rule_notifiers(struct net *net,
- enum fib_event_type event_type)
+static int call_fib_rule_notifier(struct notifier_block *nb, struct net *net,
+ enum fib_event_type event_type,
+ struct fib_rule *rule)
{
- struct fib_notifier_info info;
+ struct fib_rule_notifier_info info = {
+ .rule = rule,
+ };
- return call_fib_notifiers(net, event_type, &info);
+ return call_fib_notifier(nb, net, event_type, &info.info);
+}
+
+static int call_fib_rule_notifiers(struct net *net,
+ enum fib_event_type event_type,
+ struct fib_rule *rule)
+{
+ struct fib_rule_notifier_info info = {
+ .rule = rule,
+ };
+
+ return call_fib_notifiers(net, event_type, &info.info);
+}
+
+/* Called with rcu_read_lock() */
+void fib_rules_notify(struct net *net, struct notifier_block *nb)
+{
+ struct fib_rules_ops *ops = net->ipv4.rules_ops;
+ struct fib_rule *rule;
+
+ list_for_each_entry_rcu(rule, &ops->rules_list, list)
+ call_fib_rule_notifier(nb, net, FIB_EVENT_RULE_ADD, rule);
}
static const struct nla_policy fib4_rule_policy[FRA_MAX+1] = {
@@ -228,7 +273,7 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
rule4->tos = frh->tos;
net->ipv4.fib_has_custom_rules = true;
- call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD);
+ call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule);
err = 0;
errout:
@@ -250,7 +295,7 @@ static int fib4_rule_delete(struct fib_rule *rule)
net->ipv4.fib_num_tclassid_users--;
#endif
net->ipv4.fib_has_custom_rules = true;
- call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL);
+ call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule);
errout:
return err;
}
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 317026a..da449dd 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -57,7 +57,6 @@ static unsigned int fib_info_cnt;
static struct hlist_head fib_info_devhash[DEVINDEX_HASHSIZE];
#ifdef CONFIG_IP_ROUTE_MULTIPATH
-u32 fib_multipath_secret __read_mostly;
#define for_nexthops(fi) { \
int nhsel; const struct fib_nh *nh; \
@@ -576,9 +575,6 @@ static void fib_rebalance(struct fib_info *fi)
atomic_set(&nexthop_nh->nh_upper_bound, upper_bound);
} endfor_nexthops(fi);
-
- net_get_random_once(&fib_multipath_secret,
- sizeof(fib_multipath_secret));
}
static inline void fib_add_weight(struct fib_info *fi,
@@ -1641,7 +1637,7 @@ void fib_select_multipath(struct fib_result *res, int hash)
#endif
void fib_select_path(struct net *net, struct fib_result *res,
- struct flowi4 *fl4, int mp_hash)
+ struct flowi4 *fl4, const struct sk_buff *skb)
{
bool oif_check;
@@ -1650,10 +1646,9 @@ void fib_select_path(struct net *net, struct fib_result *res,
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (res->fi->fib_nhs > 1 && oif_check) {
- if (mp_hash < 0)
- mp_hash = get_hash_from_flowi4(fl4) >> 1;
+ int h = fib_multipath_hash(res->fi, fl4, skb);
- fib_select_multipath(res, mp_hash);
+ fib_select_multipath(res, h);
}
else
#endif
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 2f0d823..1201409 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -84,43 +84,6 @@
#include <trace/events/fib.h>
#include "fib_lookup.h"
-static unsigned int fib_seq_sum(void)
-{
- unsigned int fib_seq = 0;
- struct net *net;
-
- rtnl_lock();
- for_each_net(net)
- fib_seq += net->ipv4.fib_seq;
- rtnl_unlock();
-
- return fib_seq;
-}
-
-static ATOMIC_NOTIFIER_HEAD(fib_chain);
-
-static int call_fib_notifier(struct notifier_block *nb, struct net *net,
- enum fib_event_type event_type,
- struct fib_notifier_info *info)
-{
- info->net = net;
- return nb->notifier_call(nb, event_type, info);
-}
-
-static void fib_rules_notify(struct net *net, struct notifier_block *nb,
- enum fib_event_type event_type)
-{
-#ifdef CONFIG_IP_MULTIPLE_TABLES
- struct fib_notifier_info info;
-
- if (net->ipv4.fib_has_custom_rules)
- call_fib_notifier(nb, net, event_type, &info);
-#endif
-}
-
-static void fib_notify(struct net *net, struct notifier_block *nb,
- enum fib_event_type event_type);
-
static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net,
enum fib_event_type event_type, u32 dst,
int dst_len, struct fib_info *fi,
@@ -137,62 +100,6 @@ static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net,
return call_fib_notifier(nb, net, event_type, &info.info);
}
-static bool fib_dump_is_consistent(struct notifier_block *nb,
- void (*cb)(struct notifier_block *nb),
- unsigned int fib_seq)
-{
- atomic_notifier_chain_register(&fib_chain, nb);
- if (fib_seq == fib_seq_sum())
- return true;
- atomic_notifier_chain_unregister(&fib_chain, nb);
- if (cb)
- cb(nb);
- return false;
-}
-
-#define FIB_DUMP_MAX_RETRIES 5
-int register_fib_notifier(struct notifier_block *nb,
- void (*cb)(struct notifier_block *nb))
-{
- int retries = 0;
-
- do {
- unsigned int fib_seq = fib_seq_sum();
- struct net *net;
-
- /* Mutex semantics guarantee that every change done to
- * FIB tries before we read the change sequence counter
- * is now visible to us.
- */
- rcu_read_lock();
- for_each_net_rcu(net) {
- fib_rules_notify(net, nb, FIB_EVENT_RULE_ADD);
- fib_notify(net, nb, FIB_EVENT_ENTRY_ADD);
- }
- rcu_read_unlock();
-
- if (fib_dump_is_consistent(nb, cb, fib_seq))
- return 0;
- } while (++retries < FIB_DUMP_MAX_RETRIES);
-
- return -EBUSY;
-}
-EXPORT_SYMBOL(register_fib_notifier);
-
-int unregister_fib_notifier(struct notifier_block *nb)
-{
- return atomic_notifier_chain_unregister(&fib_chain, nb);
-}
-EXPORT_SYMBOL(unregister_fib_notifier);
-
-int call_fib_notifiers(struct net *net, enum fib_event_type event_type,
- struct fib_notifier_info *info)
-{
- net->ipv4.fib_seq++;
- info->net = net;
- return atomic_notifier_call_chain(&fib_chain, event_type, info);
-}
-
static int call_fib_entry_notifiers(struct net *net,
enum fib_event_type event_type, u32 dst,
int dst_len, struct fib_info *fi,
@@ -1995,8 +1902,7 @@ int fib_table_flush(struct net *net, struct fib_table *tb)
}
static void fib_leaf_notify(struct net *net, struct key_vector *l,
- struct fib_table *tb, struct notifier_block *nb,
- enum fib_event_type event_type)
+ struct fib_table *tb, struct notifier_block *nb)
{
struct fib_alias *fa;
@@ -2012,22 +1918,21 @@ static void fib_leaf_notify(struct net *net, struct key_vector *l,
if (tb->tb_id != fa->tb_id)
continue;
- call_fib_entry_notifier(nb, net, event_type, l->key,
+ call_fib_entry_notifier(nb, net, FIB_EVENT_ENTRY_ADD, l->key,
KEYLENGTH - fa->fa_slen, fi, fa->fa_tos,
fa->fa_type, fa->tb_id);
}
}
static void fib_table_notify(struct net *net, struct fib_table *tb,
- struct notifier_block *nb,
- enum fib_event_type event_type)
+ struct notifier_block *nb)
{
struct trie *t = (struct trie *)tb->tb_data;
struct key_vector *l, *tp = t->kv;
t_key key = 0;
while ((l = leaf_walk_rcu(&tp, key)) != NULL) {
- fib_leaf_notify(net, l, tb, nb, event_type);
+ fib_leaf_notify(net, l, tb, nb);
key = l->key + 1;
/* stop in case of wrap around */
@@ -2036,8 +1941,7 @@ static void fib_table_notify(struct net *net, struct fib_table *tb,
}
}
-static void fib_notify(struct net *net, struct notifier_block *nb,
- enum fib_event_type event_type)
+void fib_notify(struct net *net, struct notifier_block *nb)
{
unsigned int h;
@@ -2046,7 +1950,7 @@ static void fib_notify(struct net *net, struct notifier_block *nb,
struct fib_table *tb;
hlist_for_each_entry_rcu(tb, head, tb_hlist)
- fib_table_notify(net, tb, nb, event_type);
+ fib_table_notify(net, tb, nb);
}
}
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index fc310db..43318b5 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -464,22 +464,6 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
local_bh_enable();
}
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
-
-/* Source and destination is swapped. See ip_multipath_icmp_hash */
-static int icmp_multipath_hash_skb(const struct sk_buff *skb)
-{
- const struct iphdr *iph = ip_hdr(skb);
-
- return fib_multipath_hash(iph->daddr, iph->saddr);
-}
-
-#else
-
-#define icmp_multipath_hash_skb(skb) (-1)
-
-#endif
-
static struct rtable *icmp_route_lookup(struct net *net,
struct flowi4 *fl4,
struct sk_buff *skb_in,
@@ -505,8 +489,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev);
security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));
- rt = __ip_route_output_key_hash(net, fl4,
- icmp_multipath_hash_skb(skb_in));
+ rt = __ip_route_output_key_hash(net, fl4, skb_in);
if (IS_ERR(rt))
return rt;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index b4d5980..5e313c1 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -424,7 +424,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo)
/*
* This will accept the next outstanding connection.
*/
-struct sock *inet_csk_accept(struct sock *sk, int flags, int *err)
+struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct request_sock_queue *queue = &icsk->icsk_accept_queue;
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index bbe7f72..b3cdeec 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -198,6 +198,7 @@ static void ip_expire(unsigned long arg)
qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
net = container_of(qp->q.net, struct net, ipv4.frags);
+ rcu_read_lock();
spin_lock(&qp->q.lock);
if (qp->q.flags & INET_FRAG_COMPLETE)
@@ -207,7 +208,7 @@ static void ip_expire(unsigned long arg)
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
if (!inet_frag_evicting(&qp->q)) {
- struct sk_buff *head = qp->q.fragments;
+ struct sk_buff *clone, *head = qp->q.fragments;
const struct iphdr *iph;
int err;
@@ -216,32 +217,40 @@ static void ip_expire(unsigned long arg)
if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
goto out;
- rcu_read_lock();
head->dev = dev_get_by_index_rcu(net, qp->iif);
if (!head->dev)
- goto out_rcu_unlock;
+ goto out;
+
/* skb has no dst, perform route lookup again */
iph = ip_hdr(head);
err = ip_route_input_noref(head, iph->daddr, iph->saddr,
iph->tos, head->dev);
if (err)
- goto out_rcu_unlock;
+ goto out;
/* Only an end host needs to send an ICMP
* "Fragment Reassembly Timeout" message, per RFC792.
*/
if (frag_expire_skip_icmp(qp->user) &&
(skb_rtable(head)->rt_type != RTN_LOCAL))
- goto out_rcu_unlock;
+ goto out;
+
+ clone = skb_clone(head, GFP_ATOMIC);
/* Send an ICMP "Fragment Reassembly Timeout" message. */
- icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
-out_rcu_unlock:
- rcu_read_unlock();
+ if (clone) {
+ spin_unlock(&qp->q.lock);
+ icmp_send(clone, ICMP_TIME_EXCEEDED,
+ ICMP_EXC_FRAGTIME, 0);
+ consume_skb(clone);
+ goto out_rcu_unlock;
+ }
}
out:
spin_unlock(&qp->q.lock);
+out_rcu_unlock:
+ rcu_read_unlock();
ipq_put(qp);
}
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index d6feabb..fa2dc8f 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -313,6 +313,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
const struct iphdr *iph = ip_hdr(skb);
struct rtable *rt;
struct net_device *dev = skb->dev;
+ void (*edemux)(struct sk_buff *skb);
/* if ingress device is enslaved to an L3 master device pass the
* skb to its handler for processing
@@ -329,8 +330,8 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
int protocol = iph->protocol;
ipprot = rcu_dereference(inet_protos[protocol]);
- if (ipprot && ipprot->early_demux) {
- ipprot->early_demux(skb);
+ if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) {
+ edemux(skb);
/* must reload iph, skb->head might have changed */
iph = ip_hdr(skb);
}
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 737ce82..7a3fd25 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -966,7 +966,7 @@ static int __ip_append_data(struct sock *sk,
cork->length += length;
if ((((length + fragheaderlen) > mtu) || (skb && skb_is_gso(skb))) &&
(sk->sk_protocol == IPPROTO_UDP) &&
- (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
+ (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) &&
(sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) {
err = ip_ufo_append_data(sk, queue, getfrag, from, length,
hh_len, fragheaderlen, transhdrlen,
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index fd9f34b..c3b12b1 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -57,6 +57,7 @@
#include <linux/export.h>
#include <net/net_namespace.h>
#include <net/arp.h>
+#include <net/dsa.h>
#include <net/ip.h>
#include <net/ipconfig.h>
#include <net/route.h>
@@ -306,7 +307,7 @@ static void __init ic_close_devs(void)
while ((d = next)) {
next = d->next;
dev = d->dev;
- if ((!ic_dev || dev != ic_dev->dev) && !netdev_uses_dsa(dev)) {
+ if (d != ic_dev && !netdev_uses_dsa(dev)) {
pr_debug("IP-Config: Downing %s\n", dev->name);
dev_change_flags(dev, d->flags);
}
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index c0317c9..5bca64f 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -631,7 +631,7 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify,
in_dev = __in_dev_get_rtnl(dev);
if (in_dev) {
IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)--;
- inet_netconf_notify_devconf(dev_net(dev),
+ inet_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
NETCONFA_MC_FORWARDING,
dev->ifindex, &in_dev->cnf);
ip_rt_multicast_event(in_dev);
@@ -820,8 +820,8 @@ static int vif_add(struct net *net, struct mr_table *mrt,
return -EADDRNOTAVAIL;
}
IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)++;
- inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING, dev->ifindex,
- &in_dev->cnf);
+ inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING,
+ dev->ifindex, &in_dev->cnf);
ip_rt_multicast_event(in_dev);
/* Fill in the VIF structures */
@@ -1282,7 +1282,8 @@ static void mrtsock_destruct(struct sock *sk)
ipmr_for_each_table(mrt, net) {
if (sk == rtnl_dereference(mrt->mroute_sk)) {
IPV4_DEVCONF_ALL(net, MC_FORWARDING)--;
- inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING,
+ inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+ NETCONFA_MC_FORWARDING,
NETCONFA_IFINDEX_ALL,
net->ipv4.devconf_all);
RCU_INIT_POINTER(mrt->mroute_sk, NULL);
@@ -1344,7 +1345,8 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
if (ret == 0) {
rcu_assign_pointer(mrt->mroute_sk, sk);
IPV4_DEVCONF_ALL(net, MC_FORWARDING)++;
- inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING,
+ inet_netconf_notify_devconf(net, RTM_NEWNETCONF,
+ NETCONFA_MC_FORWARDING,
NETCONFA_IFINDEX_ALL,
net->ipv4.devconf_all);
}
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 6241a81..f17dab1 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -562,8 +562,6 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
XT_ERROR_TARGET) == 0)
++newinfo->stacksize;
}
- if (ret != 0)
- goto out_free;
ret = -EINVAL;
if (i != repl->num_entries)
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 52f2645..fcbdc0c 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -22,6 +22,7 @@
#include <linux/icmp.h>
#include <linux/if_arp.h>
#include <linux/seq_file.h>
+#include <linux/refcount.h>
#include <linux/netfilter_arp.h>
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter_ipv4/ip_tables.h>
@@ -40,8 +41,8 @@ MODULE_DESCRIPTION("Xtables: CLUSTERIP target");
struct clusterip_config {
struct list_head list; /* list of all configs */
- atomic_t refcount; /* reference count */
- atomic_t entries; /* number of entries/rules
+ refcount_t refcount; /* reference count */
+ refcount_t entries; /* number of entries/rules
* referencing us */
__be32 clusterip; /* the IP address */
@@ -77,7 +78,7 @@ struct clusterip_net {
static inline void
clusterip_config_get(struct clusterip_config *c)
{
- atomic_inc(&c->refcount);
+ refcount_inc(&c->refcount);
}
@@ -89,7 +90,7 @@ static void clusterip_config_rcu_free(struct rcu_head *head)
static inline void
clusterip_config_put(struct clusterip_config *c)
{
- if (atomic_dec_and_test(&c->refcount))
+ if (refcount_dec_and_test(&c->refcount))
call_rcu_bh(&c->rcu, clusterip_config_rcu_free);
}
@@ -103,7 +104,7 @@ clusterip_config_entry_put(struct clusterip_config *c)
struct clusterip_net *cn = net_generic(net, clusterip_net_id);
local_bh_disable();
- if (atomic_dec_and_lock(&c->entries, &cn->lock)) {
+ if (refcount_dec_and_lock(&c->entries, &cn->lock)) {
list_del_rcu(&c->list);
spin_unlock(&cn->lock);
local_bh_enable();
@@ -149,10 +150,10 @@ clusterip_config_find_get(struct net *net, __be32 clusterip, int entry)
c = NULL;
else
#endif
- if (unlikely(!atomic_inc_not_zero(&c->refcount)))
+ if (unlikely(!refcount_inc_not_zero(&c->refcount)))
c = NULL;
else if (entry)
- atomic_inc(&c->entries);
+ refcount_inc(&c->entries);
}
rcu_read_unlock_bh();
@@ -188,8 +189,8 @@ clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip,
clusterip_config_init_nodelist(c, i);
c->hash_mode = i->hash_mode;
c->hash_initval = i->hash_initval;
- atomic_set(&c->refcount, 1);
- atomic_set(&c->entries, 1);
+ refcount_set(&c->refcount, 1);
+ refcount_set(&c->entries, 1);
spin_lock_bh(&cn->lock);
if (__clusterip_config_find(net, ip)) {
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index bc1486f..2e14ed1 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -165,6 +165,10 @@ static unsigned int ipv4_conntrack_local(void *priv,
if (skb->len < sizeof(struct iphdr) ||
ip_hdrlen(skb) < sizeof(struct iphdr))
return NF_ACCEPT;
+
+ if (ip_is_fragment(ip_hdr(skb))) /* IP_NODEFRAG setsockopt set */
+ return NF_ACCEPT;
+
return nf_conntrack_in(state->net, PF_INET, state->hook, skb);
}
diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
index f8aad03..6f5e8d0 100644
--- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
@@ -255,11 +255,6 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb,
/* maniptype == SRC for postrouting. */
enum nf_nat_manip_type maniptype = HOOK2MANIP(state->hook);
- /* We never see fragments: conntrack defrags on pre-routing
- * and local-out, and nf_nat_out protects post-routing.
- */
- NF_CT_ASSERT(!ip_is_fragment(ip_hdr(skb)));
-
ct = nf_ct_get(skb, &ctinfo);
/* Can't track? It's not due to stress, or conntrack would
* have dropped it. Hence it's the user's responsibilty to
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c
index c9b52c3..da04b9c 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c
@@ -998,18 +998,6 @@ static unsigned char snmp_trap_decode(struct asn1_ctx *ctx,
*
*****************************************************************************/
-static void hex_dump(const unsigned char *buf, size_t len)
-{
- size_t i;
-
- for (i = 0; i < len; i++) {
- if (i && !(i % 16))
- printk("\n");
- printk("%02x ", *(buf + i));
- }
- printk("\n");
-}
-
/*
* Parse and mangle SNMP message according to mapping.
* (And this is the fucking 'basic' method).
@@ -1026,7 +1014,8 @@ static int snmp_parse_mangle(unsigned char *msg,
struct snmp_object *obj;
if (debug > 1)
- hex_dump(msg, len);
+ print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_NONE, 16, 1,
+ msg, len, 0);
asn1_open(&ctx, msg, len);
@@ -1260,16 +1249,6 @@ static const struct nf_conntrack_expect_policy snmp_exp_policy = {
.timeout = 180,
};
-static struct nf_conntrack_helper snmp_helper __read_mostly = {
- .me = THIS_MODULE,
- .help = help,
- .expect_policy = &snmp_exp_policy,
- .name = "snmp",
- .tuple.src.l3num = AF_INET,
- .tuple.src.u.udp.port = cpu_to_be16(SNMP_PORT),
- .tuple.dst.protonum = IPPROTO_UDP,
-};
-
static struct nf_conntrack_helper snmp_trap_helper __read_mostly = {
.me = THIS_MODULE,
.help = help,
@@ -1288,22 +1267,16 @@ static struct nf_conntrack_helper snmp_trap_helper __read_mostly = {
static int __init nf_nat_snmp_basic_init(void)
{
- int ret = 0;
-
BUG_ON(nf_nat_snmp_hook != NULL);
RCU_INIT_POINTER(nf_nat_snmp_hook, help);
- ret = nf_conntrack_helper_register(&snmp_trap_helper);
- if (ret < 0) {
- nf_conntrack_helper_unregister(&snmp_helper);
- return ret;
- }
- return ret;
+ return nf_conntrack_helper_register(&snmp_trap_helper);
}
static void __exit nf_nat_snmp_basic_fini(void)
{
RCU_INIT_POINTER(nf_nat_snmp_hook, NULL);
+ synchronize_rcu();
nf_conntrack_helper_unregister(&snmp_trap_helper);
}
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index 146d861..7cd8d0d 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -104,7 +104,6 @@ EXPORT_SYMBOL_GPL(nf_reject_ip_tcphdr_put);
void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
{
struct sk_buff *nskb;
- const struct iphdr *oiph;
struct iphdr *niph;
const struct tcphdr *oth;
struct tcphdr _oth;
@@ -116,8 +115,6 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
return;
- oiph = ip_hdr(oldskb);
-
nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
LL_MAX_HEADER, GFP_ATOMIC);
if (!nskb)
diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c
index 29812919..f4e4462 100644
--- a/net/ipv4/netfilter/nft_fib_ipv4.c
+++ b/net/ipv4/netfilter/nft_fib_ipv4.c
@@ -90,7 +90,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
if (nft_hook(pkt) == NF_INET_PRE_ROUTING &&
nft_fib_is_loopback(pkt->skb, nft_in(pkt))) {
- nft_fib_store_result(dest, priv->result, pkt,
+ nft_fib_store_result(dest, priv, pkt,
nft_in(pkt)->ifindex);
return;
}
@@ -99,7 +99,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
if (ipv4_is_zeronet(iph->saddr)) {
if (ipv4_is_lbcast(iph->daddr) ||
ipv4_is_local_multicast(iph->daddr)) {
- nft_fib_store_result(dest, priv->result, pkt,
+ nft_fib_store_result(dest, priv, pkt,
get_ifindex(pkt->skb->dev));
return;
}
diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c
index a0ea8aa..f186772 100644
--- a/net/ipv4/netfilter/nft_masq_ipv4.c
+++ b/net/ipv4/netfilter/nft_masq_ipv4.c
@@ -26,10 +26,10 @@ static void nft_masq_ipv4_eval(const struct nft_expr *expr,
memset(&range, 0, sizeof(range));
range.flags = priv->flags;
if (priv->sreg_proto_min) {
- range.min_proto.all =
- *(__be16 *)®s->data[priv->sreg_proto_min];
- range.max_proto.all =
- *(__be16 *)®s->data[priv->sreg_proto_max];
+ range.min_proto.all = (__force __be16)nft_reg_load16(
+ ®s->data[priv->sreg_proto_min]);
+ range.max_proto.all = (__force __be16)nft_reg_load16(
+ ®s->data[priv->sreg_proto_max]);
}
regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, nft_hook(pkt),
&range, nft_out(pkt));
diff --git a/net/ipv4/netfilter/nft_redir_ipv4.c b/net/ipv4/netfilter/nft_redir_ipv4.c
index 1650ed2..5120be1 100644
--- a/net/ipv4/netfilter/nft_redir_ipv4.c
+++ b/net/ipv4/netfilter/nft_redir_ipv4.c
@@ -26,10 +26,10 @@ static void nft_redir_ipv4_eval(const struct nft_expr *expr,
memset(&mr, 0, sizeof(mr));
if (priv->sreg_proto_min) {
- mr.range[0].min.all =
- *(__be16 *)®s->data[priv->sreg_proto_min];
- mr.range[0].max.all =
- *(__be16 *)®s->data[priv->sreg_proto_max];
+ mr.range[0].min.all = (__force __be16)nft_reg_load16(
+ ®s->data[priv->sreg_proto_min]);
+ mr.range[0].max.all = (__force __be16)nft_reg_load16(
+ ®s->data[priv->sreg_proto_max]);
mr.range[0].flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
}
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 2af6244..ccfbce1 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -156,17 +156,18 @@ int ping_hash(struct sock *sk)
void ping_unhash(struct sock *sk)
{
struct inet_sock *isk = inet_sk(sk);
+
pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
+ write_lock_bh(&ping_table.lock);
if (sk_hashed(sk)) {
- write_lock_bh(&ping_table.lock);
hlist_nulls_del(&sk->sk_nulls_node);
sk_nulls_node_init(&sk->sk_nulls_node);
sock_put(sk);
isk->inet_num = 0;
isk->inet_sport = 0;
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
- write_unlock_bh(&ping_table.lock);
}
+ write_unlock_bh(&ping_table.lock);
}
EXPORT_SYMBOL_GPL(ping_unhash);
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 69cf49e..4ccbf46 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -199,7 +199,6 @@ static const struct snmp_mib snmp4_net_list[] = {
SNMP_MIB_ITEM("TW", LINUX_MIB_TIMEWAITED),
SNMP_MIB_ITEM("TWRecycled", LINUX_MIB_TIMEWAITRECYCLED),
SNMP_MIB_ITEM("TWKilled", LINUX_MIB_TIMEWAITKILLED),
- SNMP_MIB_ITEM("PAWSPassive", LINUX_MIB_PAWSPASSIVEREJECTED),
SNMP_MIB_ITEM("PAWSActive", LINUX_MIB_PAWSACTIVEREJECTED),
SNMP_MIB_ITEM("PAWSEstab", LINUX_MIB_PAWSESTABREJECTED),
SNMP_MIB_ITEM("DelayedACKs", LINUX_MIB_DELAYEDACKS),
diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c
index 4b7c0ec..32a691b 100644
--- a/net/ipv4/protocol.c
+++ b/net/ipv4/protocol.c
@@ -28,7 +28,7 @@
#include <linux/spinlock.h>
#include <net/protocol.h>
-const struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly;
+struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly;
const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS] __read_mostly;
EXPORT_SYMBOL(inet_offloads);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 8471dd1..5e1e605 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1734,45 +1734,97 @@ static int __mkroute_input(struct sk_buff *skb,
}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
-
/* To make ICMP packets follow the right flow, the multipath hash is
- * calculated from the inner IP addresses in reverse order.
+ * calculated from the inner IP addresses.
*/
-static int ip_multipath_icmp_hash(struct sk_buff *skb)
+static void ip_multipath_l3_keys(const struct sk_buff *skb,
+ struct flow_keys *hash_keys)
{
const struct iphdr *outer_iph = ip_hdr(skb);
- struct icmphdr _icmph;
+ const struct iphdr *inner_iph;
const struct icmphdr *icmph;
struct iphdr _inner_iph;
- const struct iphdr *inner_iph;
+ struct icmphdr _icmph;
+
+ hash_keys->addrs.v4addrs.src = outer_iph->saddr;
+ hash_keys->addrs.v4addrs.dst = outer_iph->daddr;
+ if (likely(outer_iph->protocol != IPPROTO_ICMP))
+ return;
if (unlikely((outer_iph->frag_off & htons(IP_OFFSET)) != 0))
- goto standard_hash;
+ return;
icmph = skb_header_pointer(skb, outer_iph->ihl * 4, sizeof(_icmph),
&_icmph);
if (!icmph)
- goto standard_hash;
+ return;
if (icmph->type != ICMP_DEST_UNREACH &&
icmph->type != ICMP_REDIRECT &&
icmph->type != ICMP_TIME_EXCEEDED &&
- icmph->type != ICMP_PARAMETERPROB) {
- goto standard_hash;
- }
+ icmph->type != ICMP_PARAMETERPROB)
+ return;
inner_iph = skb_header_pointer(skb,
outer_iph->ihl * 4 + sizeof(_icmph),
sizeof(_inner_iph), &_inner_iph);
if (!inner_iph)
- goto standard_hash;
-
- return fib_multipath_hash(inner_iph->daddr, inner_iph->saddr);
-
-standard_hash:
- return fib_multipath_hash(outer_iph->saddr, outer_iph->daddr);
+ return;
+ hash_keys->addrs.v4addrs.src = inner_iph->saddr;
+ hash_keys->addrs.v4addrs.dst = inner_iph->daddr;
}
+/* if skb is set it will be used and fl4 can be NULL */
+int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
+ const struct sk_buff *skb)
+{
+ struct net *net = fi->fib_net;
+ struct flow_keys hash_keys;
+ u32 mhash;
+
+ switch (net->ipv4.sysctl_fib_multipath_hash_policy) {
+ case 0:
+ memset(&hash_keys, 0, sizeof(hash_keys));
+ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+ if (skb) {
+ ip_multipath_l3_keys(skb, &hash_keys);
+ } else {
+ hash_keys.addrs.v4addrs.src = fl4->saddr;
+ hash_keys.addrs.v4addrs.dst = fl4->daddr;
+ }
+ break;
+ case 1:
+ /* skb is currently provided only when forwarding */
+ if (skb) {
+ unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP;
+ struct flow_keys keys;
+
+ /* short-circuit if we already have L4 hash present */
+ if (skb->l4_hash)
+ return skb_get_hash_raw(skb) >> 1;
+ memset(&hash_keys, 0, sizeof(hash_keys));
+ skb_flow_dissect_flow_keys(skb, &keys, flag);
+ hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src;
+ hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst;
+ hash_keys.ports.src = keys.ports.src;
+ hash_keys.ports.dst = keys.ports.dst;
+ hash_keys.basic.ip_proto = keys.basic.ip_proto;
+ } else {
+ memset(&hash_keys, 0, sizeof(hash_keys));
+ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+ hash_keys.addrs.v4addrs.src = fl4->saddr;
+ hash_keys.addrs.v4addrs.dst = fl4->daddr;
+ hash_keys.ports.src = fl4->fl4_sport;
+ hash_keys.ports.dst = fl4->fl4_dport;
+ hash_keys.basic.ip_proto = fl4->flowi4_proto;
+ }
+ break;
+ }
+ mhash = flow_hash_from_keys(&hash_keys);
+
+ return mhash >> 1;
+}
+EXPORT_SYMBOL_GPL(fib_multipath_hash);
#endif /* CONFIG_IP_ROUTE_MULTIPATH */
static int ip_mkroute_input(struct sk_buff *skb,
@@ -1782,12 +1834,8 @@ static int ip_mkroute_input(struct sk_buff *skb,
{
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (res->fi && res->fi->fib_nhs > 1) {
- int h;
+ int h = fib_multipath_hash(res->fi, NULL, skb);
- if (unlikely(ip_hdr(skb)->protocol == IPPROTO_ICMP))
- h = ip_multipath_icmp_hash(skb);
- else
- h = fib_multipath_hash(saddr, daddr);
fib_select_multipath(res, h);
}
#endif
@@ -2203,7 +2251,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
*/
struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
- int mp_hash)
+ const struct sk_buff *skb)
{
struct net_device *dev_out = NULL;
__u8 tos = RT_FL_TOS(fl4);
@@ -2365,7 +2413,7 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
goto make_route;
}
- fib_select_path(net, &res, fl4, mp_hash);
+ fib_select_path(net, &res, fl4, skb);
dev_out = FIB_RES_DEV(res);
fl4->flowi4_oif = dev_out->ifindex;
@@ -2619,10 +2667,6 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
skb_reset_mac_header(skb);
skb_reset_network_header(skb);
- /* Bugfix: need to give ip_route_input enough of an IP header to not gag. */
- ip_hdr(skb)->protocol = IPPROTO_ICMP;
- skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr));
-
src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0;
dst = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0;
iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0;
@@ -2632,6 +2676,15 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
else
uid = (iif ? INVALID_UID : current_uid());
+ /* Bugfix: need to give ip_route_input enough of an IP header to
+ * not gag.
+ */
+ ip_hdr(skb)->protocol = IPPROTO_UDP;
+ ip_hdr(skb)->saddr = src;
+ ip_hdr(skb)->daddr = dst;
+
+ skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr));
+
memset(&fl4, 0, sizeof(fl4));
fl4.daddr = dst;
fl4.saddr = src;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index d6880a6..6fb2569 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -24,6 +24,7 @@
#include <net/cipso_ipv4.h>
#include <net/inet_frag.h>
#include <net/ping.h>
+#include <net/protocol.h>
static int zero;
static int one = 1;
@@ -294,6 +295,58 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
return ret;
}
+static void proc_configure_early_demux(int enabled, int protocol)
+{
+ struct net_protocol *ipprot;
+#if IS_ENABLED(CONFIG_IPV6)
+ struct inet6_protocol *ip6prot;
+#endif
+
+ ipprot = rcu_dereference(inet_protos[protocol]);
+ if (ipprot)
+ ipprot->early_demux = enabled ? ipprot->early_demux_handler :
+ NULL;
+
+#if IS_ENABLED(CONFIG_IPV6)
+ ip6prot = rcu_dereference(inet6_protos[protocol]);
+ if (ip6prot)
+ ip6prot->early_demux = enabled ? ip6prot->early_demux_handler :
+ NULL;
+#endif
+}
+
+static int proc_tcp_early_demux(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ int ret = 0;
+
+ ret = proc_dointvec(table, write, buffer, lenp, ppos);
+
+ if (write && !ret) {
+ int enabled = init_net.ipv4.sysctl_tcp_early_demux;
+
+ proc_configure_early_demux(enabled, IPPROTO_TCP);
+ }
+
+ return ret;
+}
+
+static int proc_udp_early_demux(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ int ret = 0;
+
+ ret = proc_dointvec(table, write, buffer, lenp, ppos);
+
+ if (write && !ret) {
+ int enabled = init_net.ipv4.sysctl_udp_early_demux;
+
+ proc_configure_early_demux(enabled, IPPROTO_UDP);
+ }
+
+ return ret;
+}
+
static struct ctl_table ipv4_table[] = {
{
.procname = "tcp_timestamps",
@@ -750,6 +803,20 @@ static struct ctl_table ipv4_net_table[] = {
.proc_handler = proc_dointvec
},
{
+ .procname = "udp_early_demux",
+ .data = &init_net.ipv4.sysctl_udp_early_demux,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_udp_early_demux
+ },
+ {
+ .procname = "tcp_early_demux",
+ .data = &init_net.ipv4.sysctl_tcp_early_demux,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_tcp_early_demux
+ },
+ {
.procname = "ip_default_ttl",
.data = &init_net.ipv4.sysctl_ip_default_ttl,
.maxlen = sizeof(int),
@@ -981,13 +1048,6 @@ static struct ctl_table ipv4_net_table[] = {
.proc_handler = proc_dointvec
},
{
- .procname = "tcp_tw_recycle",
- .data = &init_net.ipv4.tcp_death_row.sysctl_tw_recycle,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
.procname = "tcp_max_syn_backlog",
.data = &init_net.ipv4.sysctl_max_syn_backlog,
.maxlen = sizeof(int),
@@ -1004,6 +1064,15 @@ static struct ctl_table ipv4_net_table[] = {
.extra1 = &zero,
.extra2 = &one,
},
+ {
+ .procname = "fib_multipath_hash_policy",
+ .data = &init_net.ipv4.sysctl_fib_multipath_hash_policy,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
#endif
{
.procname = "ip_unprivileged_port_start",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index cf45555..94f0b5b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2393,7 +2393,7 @@ static int tcp_repair_options_est(struct tcp_sock *tp,
u16 snd_wscale = opt.opt_val & 0xFFFF;
u16 rcv_wscale = opt.opt_val >> 16;
- if (snd_wscale > 14 || rcv_wscale > 14)
+ if (snd_wscale > TCP_MAX_WSCALE || rcv_wscale > TCP_MAX_WSCALE)
return -EFBIG;
tp->rx_opt.snd_wscale = snd_wscale;
@@ -2470,7 +2470,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
/* Values greater than interface MTU won't take effect. However
* at the point when this call is done we typically don't yet
* know which interface is going to be used */
- if (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW) {
+ if (val && (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW)) {
err = -EINVAL;
break;
}
@@ -2770,7 +2770,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
{
const struct tcp_sock *tp = tcp_sk(sk); /* iff sk_type == SOCK_STREAM */
const struct inet_connection_sock *icsk = inet_csk(sk);
- u32 now = tcp_time_stamp, intv;
+ u32 now, intv;
u64 rate64;
bool slow;
u32 rate;
@@ -2839,6 +2839,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
info->tcpi_retrans = tp->retrans_out;
info->tcpi_fackets = tp->fackets_out;
+ now = tcp_time_stamp;
info->tcpi_last_data_sent = jiffies_to_msecs(now - tp->lsndtime);
info->tcpi_last_data_recv = jiffies_to_msecs(now - icsk->icsk_ack.lrcvtime);
info->tcpi_last_ack_recv = jiffies_to_msecs(now - tp->rcv_tstamp);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 39c393c..31f2765 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -126,7 +126,8 @@ int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2;
#define REXMIT_LOST 1 /* retransmit packets marked lost */
#define REXMIT_NEW 2 /* FRTO-style transmit of unsent/new packets */
-static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb)
+static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb,
+ unsigned int len)
{
static bool __once __read_mostly;
@@ -137,8 +138,9 @@ static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb)
rcu_read_lock();
dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif);
- pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n",
- dev ? dev->name : "Unknown driver");
+ if (!dev || len >= dev->mtu)
+ pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n",
+ dev ? dev->name : "Unknown driver");
rcu_read_unlock();
}
}
@@ -161,8 +163,10 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
if (len >= icsk->icsk_ack.rcv_mss) {
icsk->icsk_ack.rcv_mss = min_t(unsigned int, len,
tcp_sk(sk)->advmss);
- if (unlikely(icsk->icsk_ack.rcv_mss != len))
- tcp_gro_dev_warn(sk, skb);
+ /* Account for possibly-removed options */
+ if (unlikely(len > icsk->icsk_ack.rcv_mss +
+ MAX_TCP_OPTION_SPACE))
+ tcp_gro_dev_warn(sk, skb, len);
} else {
/* Otherwise, we make more careful check taking into account,
* that SACKs block is variable.
@@ -874,22 +878,11 @@ static void tcp_update_reordering(struct sock *sk, const int metric,
const int ts)
{
struct tcp_sock *tp = tcp_sk(sk);
- if (metric > tp->reordering) {
- int mib_idx;
+ int mib_idx;
+ if (metric > tp->reordering) {
tp->reordering = min(sysctl_tcp_max_reordering, metric);
- /* This exciting event is worth to be remembered. 8) */
- if (ts)
- mib_idx = LINUX_MIB_TCPTSREORDER;
- else if (tcp_is_reno(tp))
- mib_idx = LINUX_MIB_TCPRENOREORDER;
- else if (tcp_is_fack(tp))
- mib_idx = LINUX_MIB_TCPFACKREORDER;
- else
- mib_idx = LINUX_MIB_TCPSACKREORDER;
-
- NET_INC_STATS(sock_net(sk), mib_idx);
#if FASTRETRANS_DEBUG > 1
pr_debug("Disorder%d %d %u f%u s%u rr%d\n",
tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state,
@@ -902,6 +895,18 @@ static void tcp_update_reordering(struct sock *sk, const int metric,
}
tp->rack.reord = 1;
+
+ /* This exciting event is worth to be remembered. 8) */
+ if (ts)
+ mib_idx = LINUX_MIB_TCPTSREORDER;
+ else if (tcp_is_reno(tp))
+ mib_idx = LINUX_MIB_TCPRENOREORDER;
+ else if (tcp_is_fack(tp))
+ mib_idx = LINUX_MIB_TCPFACKREORDER;
+ else
+ mib_idx = LINUX_MIB_TCPSACKREORDER;
+
+ NET_INC_STATS(sock_net(sk), mib_idx);
}
/* This must be called before lost_out is incremented */
@@ -3759,11 +3764,12 @@ void tcp_parse_options(const struct sk_buff *skb,
!estab && sysctl_tcp_window_scaling) {
__u8 snd_wscale = *(__u8 *)ptr;
opt_rx->wscale_ok = 1;
- if (snd_wscale > 14) {
- net_info_ratelimited("%s: Illegal window scaling value %d >14 received\n",
+ if (snd_wscale > TCP_MAX_WSCALE) {
+ net_info_ratelimited("%s: Illegal window scaling value %d > %u received\n",
__func__,
- snd_wscale);
- snd_wscale = 14;
+ snd_wscale,
+ TCP_MAX_WSCALE);
+ snd_wscale = TCP_MAX_WSCALE;
}
opt_rx->snd_wscale = snd_wscale;
}
@@ -5541,6 +5547,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
struct inet_connection_sock *icsk = inet_csk(sk);
tcp_set_state(sk, TCP_ESTABLISHED);
+ icsk->icsk_ack.lrcvtime = tcp_time_stamp;
if (skb) {
icsk->icsk_af_ops->sk_rx_dst_set(sk, skb);
@@ -5759,7 +5766,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
* to stand against the temptation 8) --ANK
*/
inet_csk_schedule_ack(sk);
- icsk->icsk_ack.lrcvtime = tcp_time_stamp;
tcp_enter_quickack_mode(sk);
inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
TCP_DELACK_MAX, TCP_RTO_MAX);
@@ -6324,36 +6330,14 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
goto drop_and_free;
if (isn && tmp_opt.tstamp_ok)
- af_ops->init_seq(skb, &tcp_rsk(req)->ts_off);
+ af_ops->init_seq_tsoff(skb, &tcp_rsk(req)->ts_off);
if (!want_cookie && !isn) {
- /* VJ's idea. We save last timestamp seen
- * from the destination in peer table, when entering
- * state TIME-WAIT, and check against it before
- * accepting new connection request.
- *
- * If "isn" is not zero, this request hit alive
- * timewait bucket, so that all the necessary checks
- * are made in the function processing timewait state.
- */
- if (net->ipv4.tcp_death_row.sysctl_tw_recycle) {
- bool strict;
-
- dst = af_ops->route_req(sk, &fl, req, &strict);
-
- if (dst && strict &&
- !tcp_peer_is_proven(req, dst, true,
- tmp_opt.saw_tstamp)) {
- NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED);
- goto drop_and_release;
- }
- }
/* Kill the following clause, if you dislike this way. */
- else if (!net->ipv4.sysctl_tcp_syncookies &&
- (net->ipv4.sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
- (net->ipv4.sysctl_max_syn_backlog >> 2)) &&
- !tcp_peer_is_proven(req, dst, false,
- tmp_opt.saw_tstamp)) {
+ if (!net->ipv4.sysctl_tcp_syncookies &&
+ (net->ipv4.sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
+ (net->ipv4.sysctl_max_syn_backlog >> 2)) &&
+ !tcp_peer_is_proven(req, dst)) {
/* Without syncookies last quarter of
* backlog is filled with destinations,
* proven to be alive.
@@ -6366,10 +6350,10 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
goto drop_and_release;
}
- isn = af_ops->init_seq(skb, &tcp_rsk(req)->ts_off);
+ isn = af_ops->init_seq_tsoff(skb, &tcp_rsk(req)->ts_off);
}
if (!dst) {
- dst = af_ops->route_req(sk, &fl, req, NULL);
+ dst = af_ops->route_req(sk, &fl, req);
if (!dst)
goto drop_and_free;
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 9a89b8d..20cbd2f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -94,12 +94,12 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
struct inet_hashinfo tcp_hashinfo;
EXPORT_SYMBOL(tcp_hashinfo);
-static u32 tcp_v4_init_sequence(const struct sk_buff *skb, u32 *tsoff)
+static u32 tcp_v4_init_seq_and_tsoff(const struct sk_buff *skb, u32 *tsoff)
{
- return secure_tcp_sequence_number(ip_hdr(skb)->daddr,
- ip_hdr(skb)->saddr,
- tcp_hdr(skb)->dest,
- tcp_hdr(skb)->source, tsoff);
+ return secure_tcp_seq_and_tsoff(ip_hdr(skb)->daddr,
+ ip_hdr(skb)->saddr,
+ tcp_hdr(skb)->dest,
+ tcp_hdr(skb)->source, tsoff);
}
int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
@@ -198,10 +198,6 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
tp->write_seq = 0;
}
- if (tcp_death_row->sysctl_tw_recycle &&
- !tp->rx_opt.ts_recent_stamp && fl4->daddr == daddr)
- tcp_fetch_timewait_stamp(sk, &rt->dst);
-
inet->inet_dport = usin->sin_port;
sk_daddr_set(sk, daddr);
@@ -236,11 +232,11 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
rt = NULL;
if (likely(!tp->repair)) {
- seq = secure_tcp_sequence_number(inet->inet_saddr,
- inet->inet_daddr,
- inet->inet_sport,
- usin->sin_port,
- &tp->tsoffset);
+ seq = secure_tcp_seq_and_tsoff(inet->inet_saddr,
+ inet->inet_daddr,
+ inet->inet_sport,
+ usin->sin_port,
+ &tp->tsoffset);
if (!tp->write_seq)
tp->write_seq = seq;
}
@@ -279,10 +275,13 @@ EXPORT_SYMBOL(tcp_v4_connect);
*/
void tcp_v4_mtu_reduced(struct sock *sk)
{
- struct dst_entry *dst;
struct inet_sock *inet = inet_sk(sk);
- u32 mtu = tcp_sk(sk)->mtu_info;
+ struct dst_entry *dst;
+ u32 mtu;
+ if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
+ return;
+ mtu = tcp_sk(sk)->mtu_info;
dst = inet_csk_update_pmtu(sk, mtu);
if (!dst)
return;
@@ -428,7 +427,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
switch (type) {
case ICMP_REDIRECT:
- do_redirect(icmp_skb, sk);
+ if (!sock_owned_by_user(sk))
+ do_redirect(icmp_skb, sk);
goto out;
case ICMP_SOURCE_QUENCH:
/* Just silently ignore these. */
@@ -1213,19 +1213,9 @@ static void tcp_v4_init_req(struct request_sock *req,
static struct dst_entry *tcp_v4_route_req(const struct sock *sk,
struct flowi *fl,
- const struct request_sock *req,
- bool *strict)
+ const struct request_sock *req)
{
- struct dst_entry *dst = inet_csk_route_req(sk, &fl->u.ip4, req);
-
- if (strict) {
- if (fl->u.ip4.daddr == inet_rsk(req)->ir_rmt_addr)
- *strict = true;
- else
- *strict = false;
- }
-
- return dst;
+ return inet_csk_route_req(sk, &fl->u.ip4, req);
}
struct request_sock_ops tcp_request_sock_ops __read_mostly = {
@@ -1249,7 +1239,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
.cookie_init_seq = cookie_v4_init_sequence,
#endif
.route_req = tcp_v4_route_req,
- .init_seq = tcp_v4_init_sequence,
+ .init_seq_tsoff = tcp_v4_init_seq_and_tsoff,
.send_synack = tcp_v4_send_synack,
};
@@ -1419,8 +1409,6 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
if (!nsk)
goto discard;
if (nsk != sk) {
- sock_rps_save_rxhash(nsk, skb);
- sk_mark_napi_id(nsk, skb);
if (tcp_child_process(sk, nsk, skb)) {
rsk = nsk;
goto reset;
@@ -2462,7 +2450,6 @@ static int __net_init tcp_sk_init(struct net *net)
net->ipv4.sysctl_tcp_tw_reuse = 0;
cnt = tcp_hashinfo.ehash_mask + 1;
- net->ipv4.tcp_death_row.sysctl_tw_recycle = 0;
net->ipv4.tcp_death_row.sysctl_max_tw_buckets = (cnt + 1) / 2;
net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo;
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 0f46e5f..9d0d4f3 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -45,8 +45,6 @@ struct tcp_metrics_block {
struct inetpeer_addr tcpm_saddr;
struct inetpeer_addr tcpm_daddr;
unsigned long tcpm_stamp;
- u32 tcpm_ts;
- u32 tcpm_ts_stamp;
u32 tcpm_lock;
u32 tcpm_vals[TCP_METRIC_MAX_KERNEL + 1];
struct tcp_fastopen_metrics tcpm_fastopen;
@@ -123,8 +121,6 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm,
tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH);
tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND);
tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING);
- tm->tcpm_ts = 0;
- tm->tcpm_ts_stamp = 0;
if (fastopen_clear) {
tm->tcpm_fastopen.mss = 0;
tm->tcpm_fastopen.syn_loss = 0;
@@ -273,48 +269,6 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req,
return tm;
}
-static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock *tw)
-{
- struct tcp_metrics_block *tm;
- struct inetpeer_addr saddr, daddr;
- unsigned int hash;
- struct net *net;
-
- if (tw->tw_family == AF_INET) {
- inetpeer_set_addr_v4(&saddr, tw->tw_rcv_saddr);
- inetpeer_set_addr_v4(&daddr, tw->tw_daddr);
- hash = ipv4_addr_hash(tw->tw_daddr);
- }
-#if IS_ENABLED(CONFIG_IPV6)
- else if (tw->tw_family == AF_INET6) {
- if (ipv6_addr_v4mapped(&tw->tw_v6_daddr)) {
- inetpeer_set_addr_v4(&saddr, tw->tw_rcv_saddr);
- inetpeer_set_addr_v4(&daddr, tw->tw_daddr);
- hash = ipv4_addr_hash(tw->tw_daddr);
- } else {
- inetpeer_set_addr_v6(&saddr, &tw->tw_v6_rcv_saddr);
- inetpeer_set_addr_v6(&daddr, &tw->tw_v6_daddr);
- hash = ipv6_addr_hash(&tw->tw_v6_daddr);
- }
- }
-#endif
- else
- return NULL;
-
- net = twsk_net(tw);
- hash ^= net_hash_mix(net);
- hash = hash_32(hash, tcp_metrics_hash_log);
-
- for (tm = rcu_dereference(tcp_metrics_hash[hash].chain); tm;
- tm = rcu_dereference(tm->tcpm_next)) {
- if (addr_same(&tm->tcpm_saddr, &saddr) &&
- addr_same(&tm->tcpm_daddr, &daddr) &&
- net_eq(tm_net(tm), net))
- break;
- }
- return tm;
-}
-
static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
struct dst_entry *dst,
bool create)
@@ -573,8 +527,7 @@ void tcp_init_metrics(struct sock *sk)
tp->snd_cwnd_stamp = tcp_time_stamp;
}
-bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst,
- bool paws_check, bool timestamps)
+bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst)
{
struct tcp_metrics_block *tm;
bool ret;
@@ -584,94 +537,10 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst,
rcu_read_lock();
tm = __tcp_get_metrics_req(req, dst);
- if (paws_check) {
- if (tm &&
- (u32)get_seconds() - tm->tcpm_ts_stamp < TCP_PAWS_MSL &&
- ((s32)(tm->tcpm_ts - req->ts_recent) > TCP_PAWS_WINDOW ||
- !timestamps))
- ret = false;
- else
- ret = true;
- } else {
- if (tm && tcp_metric_get(tm, TCP_METRIC_RTT) && tm->tcpm_ts_stamp)
- ret = true;
- else
- ret = false;
- }
- rcu_read_unlock();
-
- return ret;
-}
-
-void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst)
-{
- struct tcp_metrics_block *tm;
-
- rcu_read_lock();
- tm = tcp_get_metrics(sk, dst, true);
- if (tm) {
- struct tcp_sock *tp = tcp_sk(sk);
-
- if ((u32)get_seconds() - tm->tcpm_ts_stamp <= TCP_PAWS_MSL) {
- tp->rx_opt.ts_recent_stamp = tm->tcpm_ts_stamp;
- tp->rx_opt.ts_recent = tm->tcpm_ts;
- }
- }
- rcu_read_unlock();
-}
-EXPORT_SYMBOL_GPL(tcp_fetch_timewait_stamp);
-
-/* VJ's idea. Save last timestamp seen from this destination and hold
- * it at least for normal timewait interval to use for duplicate
- * segment detection in subsequent connections, before they enter
- * synchronized state.
- */
-bool tcp_remember_stamp(struct sock *sk)
-{
- struct dst_entry *dst = __sk_dst_get(sk);
- bool ret = false;
-
- if (dst) {
- struct tcp_metrics_block *tm;
-
- rcu_read_lock();
- tm = tcp_get_metrics(sk, dst, true);
- if (tm) {
- struct tcp_sock *tp = tcp_sk(sk);
-
- if ((s32)(tm->tcpm_ts - tp->rx_opt.ts_recent) <= 0 ||
- ((u32)get_seconds() - tm->tcpm_ts_stamp > TCP_PAWS_MSL &&
- tm->tcpm_ts_stamp <= (u32)tp->rx_opt.ts_recent_stamp)) {
- tm->tcpm_ts_stamp = (u32)tp->rx_opt.ts_recent_stamp;
- tm->tcpm_ts = tp->rx_opt.ts_recent;
- }
- ret = true;
- }
- rcu_read_unlock();
- }
- return ret;
-}
-
-bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw)
-{
- struct tcp_metrics_block *tm;
- bool ret = false;
-
- rcu_read_lock();
- tm = __tcp_get_metrics_tw(tw);
- if (tm) {
- const struct tcp_timewait_sock *tcptw;
- struct sock *sk = (struct sock *) tw;
-
- tcptw = tcp_twsk(sk);
- if ((s32)(tm->tcpm_ts - tcptw->tw_ts_recent) <= 0 ||
- ((u32)get_seconds() - tm->tcpm_ts_stamp > TCP_PAWS_MSL &&
- tm->tcpm_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) {
- tm->tcpm_ts_stamp = (u32)tcptw->tw_ts_recent_stamp;
- tm->tcpm_ts = tcptw->tw_ts_recent;
- }
+ if (tm && tcp_metric_get(tm, TCP_METRIC_RTT))
ret = true;
- }
+ else
+ ret = false;
rcu_read_unlock();
return ret;
@@ -791,14 +660,6 @@ static int tcp_metrics_fill_info(struct sk_buff *msg,
jiffies - tm->tcpm_stamp,
TCP_METRICS_ATTR_PAD) < 0)
goto nla_put_failure;
- if (tm->tcpm_ts_stamp) {
- if (nla_put_s32(msg, TCP_METRICS_ATTR_TW_TS_STAMP,
- (s32) (get_seconds() - tm->tcpm_ts_stamp)) < 0)
- goto nla_put_failure;
- if (nla_put_u32(msg, TCP_METRICS_ATTR_TW_TSVAL,
- tm->tcpm_ts) < 0)
- goto nla_put_failure;
- }
{
int n = 0;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 7e16243..8f6373b 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -26,6 +26,7 @@
#include <net/tcp.h>
#include <net/inet_common.h>
#include <net/xfrm.h>
+#include <net/busy_poll.h>
int sysctl_tcp_abort_on_overflow __read_mostly;
@@ -94,7 +95,6 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
struct tcp_options_received tmp_opt;
struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
bool paws_reject = false;
- struct inet_timewait_death_row *tcp_death_row = &sock_net((struct sock*)tw)->ipv4.tcp_death_row;
tmp_opt.saw_tstamp = 0;
if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
@@ -149,12 +149,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
tcptw->tw_ts_recent = tmp_opt.rcv_tsval;
}
- if (tcp_death_row->sysctl_tw_recycle &&
- tcptw->tw_ts_recent_stamp &&
- tcp_tw_remember_stamp(tw))
- inet_twsk_reschedule(tw, tw->tw_timeout);
- else
- inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);
+ inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);
return TCP_TW_ACK;
}
@@ -259,12 +254,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
const struct inet_connection_sock *icsk = inet_csk(sk);
const struct tcp_sock *tp = tcp_sk(sk);
struct inet_timewait_sock *tw;
- bool recycle_ok = false;
struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
- if (tcp_death_row->sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp)
- recycle_ok = tcp_remember_stamp(sk);
-
tw = inet_twsk_alloc(sk, tcp_death_row, state);
if (tw) {
@@ -317,13 +308,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
if (timeo < rto)
timeo = rto;
- if (recycle_ok) {
- tw->tw_timeout = rto;
- } else {
- tw->tw_timeout = TCP_TIMEWAIT_LEN;
- if (state == TCP_TIME_WAIT)
- timeo = TCP_TIMEWAIT_LEN;
- }
+ tw->tw_timeout = TCP_TIMEWAIT_LEN;
+ if (state == TCP_TIME_WAIT)
+ timeo = TCP_TIMEWAIT_LEN;
inet_twsk_schedule(tw, timeo);
/* Linkage updates. */
@@ -460,6 +447,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
minmax_reset(&newtp->rtt_min, tcp_time_stamp, ~0U);
newicsk->icsk_rto = TCP_TIMEOUT_INIT;
+ newicsk->icsk_ack.lrcvtime = tcp_time_stamp;
newtp->packets_out = 0;
newtp->retrans_out = 0;
@@ -812,6 +800,9 @@ int tcp_child_process(struct sock *parent, struct sock *child,
int ret = 0;
int state = child->sk_state;
+ /* record NAPI ID of child */
+ sk_mark_napi_id(child, skb);
+
tcp_segs_in(tcp_sk(child), skb);
if (!sock_owned_by_user(child)) {
ret = tcp_rcv_state_process(child, skb);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 22548b5..0e807a8 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -212,12 +212,12 @@ void tcp_select_initial_window(int __space, __u32 mss,
/* If no clamp set the clamp to the max possible scaled window */
if (*window_clamp == 0)
- (*window_clamp) = (65535 << 14);
+ (*window_clamp) = (U16_MAX << TCP_MAX_WSCALE);
space = min(*window_clamp, space);
/* Quantize space offering to a multiple of mss if possible. */
if (space > mss)
- space = (space / mss) * mss;
+ space = rounddown(space, mss);
/* NOTE: offering an initial window larger than 32767
* will break some buggy TCP stacks. If the admin tells us
@@ -234,13 +234,11 @@ void tcp_select_initial_window(int __space, __u32 mss,
(*rcv_wscale) = 0;
if (wscale_ok) {
- /* Set window scaling on max possible window
- * See RFC1323 for an explanation of the limit to 14
- */
+ /* Set window scaling on max possible window */
space = max_t(u32, space, sysctl_tcp_rmem[2]);
space = max_t(u32, space, sysctl_rmem_max);
space = min_t(u32, space, *window_clamp);
- while (space > 65535 && (*rcv_wscale) < 14) {
+ while (space > U16_MAX && (*rcv_wscale) < TCP_MAX_WSCALE) {
space >>= 1;
(*rcv_wscale)++;
}
@@ -253,7 +251,7 @@ void tcp_select_initial_window(int __space, __u32 mss,
}
/* Set the clamp no higher than max representable value */
- (*window_clamp) = min(65535U << (*rcv_wscale), *window_clamp);
+ (*window_clamp) = min_t(__u32, U16_MAX << (*rcv_wscale), *window_clamp);
}
EXPORT_SYMBOL(tcp_select_initial_window);
@@ -2561,7 +2559,6 @@ u32 __tcp_select_window(struct sock *sk)
/* Don't do rounding if we are using window scaling, since the
* scaled window will not line up with the MSS boundary anyway.
*/
- window = tp->rcv_wnd;
if (tp->rx_opt.rcv_wscale) {
window = free_space;
@@ -2569,10 +2566,9 @@ u32 __tcp_select_window(struct sock *sk)
* Import case: prevent zero window announcement if
* 1<<rcv_wscale > mss.
*/
- if (((window >> tp->rx_opt.rcv_wscale) << tp->rx_opt.rcv_wscale) != window)
- window = (((window >> tp->rx_opt.rcv_wscale) + 1)
- << tp->rx_opt.rcv_wscale);
+ window = ALIGN(window, (1 << tp->rx_opt.rcv_wscale));
} else {
+ window = tp->rcv_wnd;
/* Get the largest window that is a nice multiple of mss.
* Window clamp already applied above.
* If our current window offering is within 1 mss of the
@@ -2582,7 +2578,7 @@ u32 __tcp_select_window(struct sock *sk)
* is too small.
*/
if (window <= free_space - mss || window > free_space)
- window = (free_space / mss) * mss;
+ window = rounddown(free_space, mss);
else if (mss == full_space &&
free_space > window + (full_space >> 1))
window = free_space;
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index 4ecb38a..d8acbd9 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -12,7 +12,8 @@ static void tcp_rack_mark_skb_lost(struct sock *sk, struct sk_buff *skb)
/* Account for retransmits that are lost again */
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
tp->retrans_out -= tcp_skb_pcount(skb);
- NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT);
+ NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT,
+ tcp_skb_pcount(skb));
}
}
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 40d8935..b2ab411 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -249,7 +249,8 @@ void tcp_delack_timer_handler(struct sock *sk)
sk_mem_reclaim_partial(sk);
- if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
+ if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+ !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
goto out;
if (time_after(icsk->icsk_ack.timeout, jiffies)) {
@@ -552,7 +553,8 @@ void tcp_write_timer_handler(struct sock *sk)
struct inet_connection_sock *icsk = inet_csk(sk);
int event;
- if (sk->sk_state == TCP_CLOSE || !icsk->icsk_pending)
+ if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+ !icsk->icsk_pending)
goto out;
if (time_after(icsk->icsk_timeout, jiffies)) {
diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c
index fed66dc..9775453 100644
--- a/net/ipv4/tcp_westwood.c
+++ b/net/ipv4/tcp_westwood.c
@@ -265,8 +265,8 @@ static size_t tcp_westwood_info(struct sock *sk, u32 ext, int *attr,
if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
info->vegas.tcpv_enabled = 1;
info->vegas.tcpv_rttcnt = 0;
- info->vegas.tcpv_rtt = jiffies_to_usecs(ca->rtt),
- info->vegas.tcpv_minrtt = jiffies_to_usecs(ca->rtt_min),
+ info->vegas.tcpv_rtt = jiffies_to_usecs(ca->rtt);
+ info->vegas.tcpv_minrtt = jiffies_to_usecs(ca->rtt_min);
*attr = INET_DIAG_VEGASINFO;
return sizeof(struct tcpvegas_info);
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index e2afe677..48c4529 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -307,6 +307,7 @@
bool "IPv6: Segment Routing Header encapsulation support"
depends on IPV6
select LWTUNNEL
+ select DST_CACHE
---help---
Support for encapsulation of packets within an outer IPv6
header and a Segment Routing Header using the lightweight
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 8c69768..67ec87e 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -224,6 +224,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
.accept_ra_rtr_pref = 1,
.rtr_probe_interval = 60 * HZ,
#ifdef CONFIG_IPV6_ROUTE_INFO
+ .accept_ra_rt_info_min_plen = 0,
.accept_ra_rt_info_max_plen = 0,
#endif
#endif
@@ -277,6 +278,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
.accept_ra_rtr_pref = 1,
.rtr_probe_interval = 60 * HZ,
#ifdef CONFIG_IPV6_ROUTE_INFO
+ .accept_ra_rt_info_min_plen = 0,
.accept_ra_rt_info_max_plen = 0,
#endif
#endif
@@ -547,6 +549,9 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0)
goto nla_put_failure;
+ if (!devconf)
+ goto out;
+
if ((all || type == NETCONFA_FORWARDING) &&
nla_put_s32(skb, NETCONFA_FORWARDING, devconf->forwarding) < 0)
goto nla_put_failure;
@@ -565,6 +570,7 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
devconf->ignore_routes_with_linkdown) < 0)
goto nla_put_failure;
+out:
nlmsg_end(skb, nlh);
return 0;
@@ -573,8 +579,8 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
return -EMSGSIZE;
}
-void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
- struct ipv6_devconf *devconf)
+void inet6_netconf_notify_devconf(struct net *net, int event, int type,
+ int ifindex, struct ipv6_devconf *devconf)
{
struct sk_buff *skb;
int err = -ENOBUFS;
@@ -584,7 +590,7 @@ void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
goto errout;
err = inet6_netconf_fill_devconf(skb, ifindex, devconf, 0, 0,
- RTM_NEWNETCONF, 0, type);
+ event, 0, type);
if (err < 0) {
/* -EMSGSIZE implies BUG in inet6_netconf_msgsize_devconf() */
WARN_ON(err == -EMSGSIZE);
@@ -767,7 +773,8 @@ static void dev_forward_change(struct inet6_dev *idev)
else
addrconf_leave_anycast(ifa);
}
- inet6_netconf_notify_devconf(dev_net(dev), NETCONFA_FORWARDING,
+ inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
+ NETCONFA_FORWARDING,
dev->ifindex, &idev->cnf);
}
@@ -802,7 +809,8 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf)
if (p == &net->ipv6.devconf_dflt->forwarding) {
if ((!newf) ^ (!old))
- inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+ inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+ NETCONFA_FORWARDING,
NETCONFA_IFINDEX_DEFAULT,
net->ipv6.devconf_dflt);
rtnl_unlock();
@@ -814,13 +822,15 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf)
net->ipv6.devconf_dflt->forwarding = newf;
if ((!newf) ^ (!old_dflt))
- inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+ inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+ NETCONFA_FORWARDING,
NETCONFA_IFINDEX_DEFAULT,
net->ipv6.devconf_dflt);
addrconf_forward_change(net, newf);
if ((!newf) ^ (!old))
- inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+ inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+ NETCONFA_FORWARDING,
NETCONFA_IFINDEX_ALL,
net->ipv6.devconf_all);
} else if ((!newf) ^ (!old))
@@ -845,6 +855,7 @@ static void addrconf_linkdown_change(struct net *net, __s32 newf)
idev->cnf.ignore_routes_with_linkdown = newf;
if (changed)
inet6_netconf_notify_devconf(dev_net(dev),
+ RTM_NEWNETCONF,
NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
dev->ifindex,
&idev->cnf);
@@ -867,6 +878,7 @@ static int addrconf_fixup_linkdown(struct ctl_table *table, int *p, int newf)
if (p == &net->ipv6.devconf_dflt->ignore_routes_with_linkdown) {
if ((!newf) ^ (!old))
inet6_netconf_notify_devconf(net,
+ RTM_NEWNETCONF,
NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
NETCONFA_IFINDEX_DEFAULT,
net->ipv6.devconf_dflt);
@@ -879,6 +891,7 @@ static int addrconf_fixup_linkdown(struct ctl_table *table, int *p, int newf)
addrconf_linkdown_change(net, newf);
if ((!newf) ^ (!old))
inet6_netconf_notify_devconf(net,
+ RTM_NEWNETCONF,
NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
NETCONFA_IFINDEX_ALL,
net->ipv6.devconf_all);
@@ -4979,6 +4992,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
array[DEVCONF_RTR_PROBE_INTERVAL] =
jiffies_to_msecs(cnf->rtr_probe_interval);
#ifdef CONFIG_IPV6_ROUTE_INFO
+ array[DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN] = cnf->accept_ra_rt_info_min_plen;
array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = cnf->accept_ra_rt_info_max_plen;
#endif
#endif
@@ -5672,17 +5686,20 @@ int addrconf_sysctl_proxy_ndp(struct ctl_table *ctl, int write,
return restart_syscall();
if (valp == &net->ipv6.devconf_dflt->proxy_ndp)
- inet6_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH,
+ inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+ NETCONFA_PROXY_NEIGH,
NETCONFA_IFINDEX_DEFAULT,
net->ipv6.devconf_dflt);
else if (valp == &net->ipv6.devconf_all->proxy_ndp)
- inet6_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH,
+ inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+ NETCONFA_PROXY_NEIGH,
NETCONFA_IFINDEX_ALL,
net->ipv6.devconf_all);
else {
struct inet6_dev *idev = ctl->extra1;
- inet6_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH,
+ inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+ NETCONFA_PROXY_NEIGH,
idev->dev->ifindex,
&idev->cnf);
}
@@ -6122,6 +6139,13 @@ static const struct ctl_table addrconf_sysctl[] = {
},
#ifdef CONFIG_IPV6_ROUTE_INFO
{
+ .procname = "accept_ra_rt_info_min_plen",
+ .data = &ipv6_devconf.accept_ra_rt_info_min_plen,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "accept_ra_rt_info_max_plen",
.data = &ipv6_devconf.accept_ra_rt_info_max_plen,
.maxlen = sizeof(int),
@@ -6338,7 +6362,8 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name,
ifindex = NETCONFA_IFINDEX_DEFAULT;
else
ifindex = idev->dev->ifindex;
- inet6_netconf_notify_devconf(net, NETCONFA_ALL, ifindex, p);
+ inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL,
+ ifindex, p);
return 0;
free:
@@ -6347,7 +6372,8 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name,
return -ENOBUFS;
}
-static void __addrconf_sysctl_unregister(struct ipv6_devconf *p)
+static void __addrconf_sysctl_unregister(struct net *net,
+ struct ipv6_devconf *p, int ifindex)
{
struct ctl_table *table;
@@ -6358,6 +6384,8 @@ static void __addrconf_sysctl_unregister(struct ipv6_devconf *p)
unregister_net_sysctl_table(p->sysctl_header);
p->sysctl_header = NULL;
kfree(table);
+
+ inet6_netconf_notify_devconf(net, RTM_DELNETCONF, 0, ifindex, NULL);
}
static int addrconf_sysctl_register(struct inet6_dev *idev)
@@ -6381,7 +6409,8 @@ static int addrconf_sysctl_register(struct inet6_dev *idev)
static void addrconf_sysctl_unregister(struct inet6_dev *idev)
{
- __addrconf_sysctl_unregister(&idev->cnf);
+ __addrconf_sysctl_unregister(dev_net(idev->dev), &idev->cnf,
+ idev->dev->ifindex);
neigh_sysctl_unregister(idev->nd_parms);
}
@@ -6424,7 +6453,7 @@ static int __net_init addrconf_init_net(struct net *net)
#ifdef CONFIG_SYSCTL
err_reg_dflt:
- __addrconf_sysctl_unregister(all);
+ __addrconf_sysctl_unregister(net, all, NETCONFA_IFINDEX_ALL);
err_reg_all:
kfree(dflt);
#endif
@@ -6437,8 +6466,10 @@ static int __net_init addrconf_init_net(struct net *net)
static void __net_exit addrconf_exit_net(struct net *net)
{
#ifdef CONFIG_SYSCTL
- __addrconf_sysctl_unregister(net->ipv6.devconf_dflt);
- __addrconf_sysctl_unregister(net->ipv6.devconf_all);
+ __addrconf_sysctl_unregister(net, net->ipv6.devconf_dflt,
+ NETCONFA_IFINDEX_DEFAULT);
+ __addrconf_sysctl_unregister(net, net->ipv6.devconf_all,
+ NETCONFA_IFINDEX_ALL);
#endif
kfree(net->ipv6.devconf_dflt);
kfree(net->ipv6.devconf_all);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 04db406..1635d21 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -920,12 +920,12 @@ static int __init inet6_init(void)
err = register_pernet_subsys(&inet6_net_ops);
if (err)
goto register_pernet_fail;
- err = icmpv6_init();
- if (err)
- goto icmp_fail;
err = ip6_mr_init();
if (err)
goto ipmr_fail;
+ err = icmpv6_init();
+ if (err)
+ goto icmp_fail;
err = ndisc_init();
if (err)
goto ndisc_fail;
@@ -1005,6 +1005,10 @@ static int __init inet6_init(void)
if (err)
goto seg6_fail;
+ err = igmp6_late_init();
+ if (err)
+ goto igmp6_late_err;
+
#ifdef CONFIG_SYSCTL
err = ipv6_sysctl_register();
if (err)
@@ -1015,8 +1019,10 @@ static int __init inet6_init(void)
#ifdef CONFIG_SYSCTL
sysctl_fail:
- seg6_exit();
+ igmp6_late_cleanup();
#endif
+igmp6_late_err:
+ seg6_exit();
seg6_fail:
calipso_exit();
calipso_fail:
@@ -1061,10 +1067,10 @@ static int __init inet6_init(void)
ndisc_cleanup();
ndisc_fail:
ip6_mr_cleanup();
-ipmr_fail:
- icmpv6_cleanup();
icmp_fail:
unregister_pernet_subsys(&inet6_net_ops);
+ipmr_fail:
+ icmpv6_cleanup();
register_pernet_fail:
sock_unregister(PF_INET6);
rtnl_unregister_all(PF_INET6);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index e426674..d4bf2c6 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -923,6 +923,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
ins = &rt->dst.rt6_next;
iter = *ins;
while (iter) {
+ if (iter->rt6i_metric > rt->rt6i_metric)
+ break;
if (rt6_qualify_for_ecmp(iter)) {
*ins = iter->dst.rt6_next;
fib6_purge_rt(iter, fn, info->nl_net);
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index aacfb4b..b04539d 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -49,6 +49,8 @@
int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
+ void (*edemux)(struct sk_buff *skb);
+
/* if ingress device is enslaved to an L3 master device pass the
* skb to its handler for processing
*/
@@ -60,8 +62,8 @@ int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
const struct inet6_protocol *ipprot;
ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]);
- if (ipprot && ipprot->early_demux)
- ipprot->early_demux(skb);
+ if (ipprot && (edemux = READ_ONCE(ipprot->early_demux)))
+ edemux(skb);
}
if (!skb_valid_dst(skb))
ip6_route_input(skb);
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 0838e6d..93e58a5 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -294,8 +294,10 @@ static int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff);
int err = -ENOSYS;
- if (skb->encapsulation)
+ if (skb->encapsulation) {
+ skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IPV6));
skb_set_inner_network_header(skb, nhoff);
+ }
iph->payload_len = htons(skb->len - nhoff - sizeof(*iph));
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 528b3c1..58f6288 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -768,13 +768,14 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
* Fragment the datagram.
*/
- *prevhdr = NEXTHDR_FRAGMENT;
troom = rt->dst.dev->needed_tailroom;
/*
* Keep copying data until we run out.
*/
while (left > 0) {
+ u8 *fragnexthdr_offset;
+
len = left;
/* IF: it doesn't fit, use 'mtu' - the data space left */
if (len > mtu)
@@ -819,6 +820,10 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
*/
skb_copy_from_linear_data(skb, skb_network_header(frag), hlen);
+ fragnexthdr_offset = skb_network_header(frag);
+ fragnexthdr_offset += prevhdr - skb_network_header(skb);
+ *fragnexthdr_offset = NEXTHDR_FRAGMENT;
+
/*
* Build fragment header.
*/
@@ -1385,7 +1390,7 @@ static int __ip6_append_data(struct sock *sk,
if ((((length + fragheaderlen) > mtu) ||
(skb && skb_is_gso(skb))) &&
(sk->sk_protocol == IPPROTO_UDP) &&
- (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
+ (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) &&
(sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) {
err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
hh_len, fragheaderlen, exthdrlen,
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 644ba59..3d8a3b6 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -485,11 +485,15 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
if (!skb->ignore_df && skb->len > mtu) {
skb_dst(skb)->ops->update_pmtu(dst, NULL, skb, mtu);
- if (skb->protocol == htons(ETH_P_IPV6))
+ if (skb->protocol == htons(ETH_P_IPV6)) {
+ if (mtu < IPV6_MIN_MTU)
+ mtu = IPV6_MIN_MTU;
+
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
- else
+ } else {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
+ }
return -EMSGSIZE;
}
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 6ba6c90..fb4546e 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -815,7 +815,7 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head)
in6_dev = __in6_dev_get(dev);
if (in6_dev) {
in6_dev->cnf.mc_forwarding--;
- inet6_netconf_notify_devconf(dev_net(dev),
+ inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
NETCONFA_MC_FORWARDING,
dev->ifindex, &in6_dev->cnf);
}
@@ -974,7 +974,7 @@ static int mif6_add(struct net *net, struct mr6_table *mrt,
in6_dev = __in6_dev_get(dev);
if (in6_dev) {
in6_dev->cnf.mc_forwarding++;
- inet6_netconf_notify_devconf(dev_net(dev),
+ inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
NETCONFA_MC_FORWARDING,
dev->ifindex, &in6_dev->cnf);
}
@@ -1599,7 +1599,8 @@ static int ip6mr_sk_init(struct mr6_table *mrt, struct sock *sk)
write_unlock_bh(&mrt_lock);
if (!err)
- inet6_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING,
+ inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+ NETCONFA_MC_FORWARDING,
NETCONFA_IFINDEX_ALL,
net->ipv6.devconf_all);
rtnl_unlock();
@@ -1620,7 +1621,7 @@ int ip6mr_sk_done(struct sock *sk)
mrt->mroute6_sk = NULL;
net->ipv6.devconf_all->mc_forwarding--;
write_unlock_bh(&mrt_lock);
- inet6_netconf_notify_devconf(net,
+ inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
NETCONFA_MC_FORWARDING,
NETCONFA_IFINDEX_ALL,
net->ipv6.devconf_all);
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 1bdc703..07403fa 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2463,7 +2463,6 @@ static void mld_ifc_event(struct inet6_dev *idev)
mld_ifc_start_timer(idev, 1);
}
-
static void igmp6_timer_handler(unsigned long data)
{
struct ifmcaddr6 *ma = (struct ifmcaddr6 *) data;
@@ -2599,6 +2598,44 @@ void ipv6_mc_destroy_dev(struct inet6_dev *idev)
write_unlock_bh(&idev->lock);
}
+static void ipv6_mc_rejoin_groups(struct inet6_dev *idev)
+{
+ struct ifmcaddr6 *pmc;
+
+ ASSERT_RTNL();
+
+ if (mld_in_v1_mode(idev)) {
+ read_lock_bh(&idev->lock);
+ for (pmc = idev->mc_list; pmc; pmc = pmc->next)
+ igmp6_join_group(pmc);
+ read_unlock_bh(&idev->lock);
+ } else
+ mld_send_report(idev, NULL);
+}
+
+static int ipv6_mc_netdev_event(struct notifier_block *this,
+ unsigned long event,
+ void *ptr)
+{
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct inet6_dev *idev = __in6_dev_get(dev);
+
+ switch (event) {
+ case NETDEV_RESEND_IGMP:
+ if (idev)
+ ipv6_mc_rejoin_groups(idev);
+ break;
+ default:
+ break;
+ }
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block igmp6_netdev_notifier = {
+ .notifier_call = ipv6_mc_netdev_event,
+};
+
#ifdef CONFIG_PROC_FS
struct igmp6_mc_iter_state {
struct seq_net_private p;
@@ -2970,7 +3007,17 @@ int __init igmp6_init(void)
return register_pernet_subsys(&igmp6_net_ops);
}
+int __init igmp6_late_init(void)
+{
+ return register_netdevice_notifier(&igmp6_netdev_notifier);
+}
+
void igmp6_cleanup(void)
{
unregister_pernet_subsys(&igmp6_net_ops);
}
+
+void igmp6_late_cleanup(void)
+{
+ unregister_netdevice_notifier(&igmp6_netdev_notifier);
+}
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 7ebac63..b5812b3 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -732,7 +732,7 @@ void ndisc_update(const struct net_device *dev, struct neighbour *neigh,
const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type,
struct ndisc_options *ndopts)
{
- neigh_update(neigh, lladdr, new, flags);
+ neigh_update(neigh, lladdr, new, flags, 0);
/* report ndisc ops about neighbour update */
ndisc_ops_update(dev, neigh, flags, icmp6_type, ndopts);
}
@@ -1418,6 +1418,8 @@ static void ndisc_router_discovery(struct sk_buff *skb)
if (ri->prefix_len == 0 &&
!in6_dev->cnf.accept_ra_defrtr)
continue;
+ if (ri->prefix_len < in6_dev->cnf.accept_ra_rt_info_min_plen)
+ continue;
if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen)
continue;
rt6_route_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3,
diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c
index 765facf..e8d88d8 100644
--- a/net/ipv6/netfilter/nft_fib_ipv6.c
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -159,7 +159,7 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
if (nft_hook(pkt) == NF_INET_PRE_ROUTING &&
nft_fib_is_loopback(pkt->skb, nft_in(pkt))) {
- nft_fib_store_result(dest, priv->result, pkt,
+ nft_fib_store_result(dest, priv, pkt,
nft_in(pkt)->ifindex);
return;
}
diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c
index 6c5b5b1..4146536 100644
--- a/net/ipv6/netfilter/nft_masq_ipv6.c
+++ b/net/ipv6/netfilter/nft_masq_ipv6.c
@@ -27,10 +27,10 @@ static void nft_masq_ipv6_eval(const struct nft_expr *expr,
memset(&range, 0, sizeof(range));
range.flags = priv->flags;
if (priv->sreg_proto_min) {
- range.min_proto.all =
- *(__be16 *)®s->data[priv->sreg_proto_min];
- range.max_proto.all =
- *(__be16 *)®s->data[priv->sreg_proto_max];
+ range.min_proto.all = (__force __be16)nft_reg_load16(
+ ®s->data[priv->sreg_proto_min]);
+ range.max_proto.all = (__force __be16)nft_reg_load16(
+ ®s->data[priv->sreg_proto_max]);
}
regs->verdict.code = nf_nat_masquerade_ipv6(pkt->skb, &range,
nft_out(pkt));
diff --git a/net/ipv6/netfilter/nft_redir_ipv6.c b/net/ipv6/netfilter/nft_redir_ipv6.c
index f5ac080..a27e424 100644
--- a/net/ipv6/netfilter/nft_redir_ipv6.c
+++ b/net/ipv6/netfilter/nft_redir_ipv6.c
@@ -26,10 +26,10 @@ static void nft_redir_ipv6_eval(const struct nft_expr *expr,
memset(&range, 0, sizeof(range));
if (priv->sreg_proto_min) {
- range.min_proto.all =
- *(__be16 *)®s->data[priv->sreg_proto_min],
- range.max_proto.all =
- *(__be16 *)®s->data[priv->sreg_proto_max],
+ range.min_proto.all = (__force __be16)nft_reg_load16(
+ ®s->data[priv->sreg_proto_min]);
+ range.max_proto.all = (__force __be16)nft_reg_load16(
+ ®s->data[priv->sreg_proto_max]);
range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
}
diff --git a/net/ipv6/protocol.c b/net/ipv6/protocol.c
index e3770ab..b5d54d4 100644
--- a/net/ipv6/protocol.c
+++ b/net/ipv6/protocol.c
@@ -26,7 +26,7 @@
#include <net/protocol.h>
#if IS_ENABLED(CONFIG_IPV6)
-const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS] __read_mostly;
+struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS] __read_mostly;
EXPORT_SYMBOL(inet6_protos);
int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char protocol)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 229bfcc..9db14189 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3299,7 +3299,6 @@ static size_t rt6_nlmsg_size(struct rt6_info *rt)
nexthop_len = nla_total_size(0) /* RTA_MULTIPATH */
+ NLA_ALIGN(sizeof(struct rtnexthop))
+ nla_total_size(16) /* RTA_GATEWAY */
- + nla_total_size(4) /* RTA_OIF */
+ lwtunnel_get_encap_size(rt->dst.lwtstate);
nexthop_len *= rt->rt6i_nsiblings;
@@ -3323,7 +3322,7 @@ static size_t rt6_nlmsg_size(struct rt6_info *rt)
}
static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt,
- unsigned int *flags)
+ unsigned int *flags, bool skip_oif)
{
if (!netif_running(rt->dst.dev) || !netif_carrier_ok(rt->dst.dev)) {
*flags |= RTNH_F_LINKDOWN;
@@ -3336,7 +3335,8 @@ static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt,
goto nla_put_failure;
}
- if (rt->dst.dev &&
+ /* not needed for multipath encoding b/c it has a rtnexthop struct */
+ if (!skip_oif && rt->dst.dev &&
nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex))
goto nla_put_failure;
@@ -3350,6 +3350,7 @@ static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt,
return -EMSGSIZE;
}
+/* add multipath next hop */
static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt)
{
struct rtnexthop *rtnh;
@@ -3362,7 +3363,7 @@ static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt)
rtnh->rtnh_hops = 0;
rtnh->rtnh_ifindex = rt->dst.dev ? rt->dst.dev->ifindex : 0;
- if (rt6_nexthop_info(skb, rt, &flags) < 0)
+ if (rt6_nexthop_info(skb, rt, &flags, true) < 0)
goto nla_put_failure;
rtnh->rtnh_flags = flags;
@@ -3422,6 +3423,8 @@ static int rt6_fill_node(struct net *net,
}
else if (rt->rt6i_flags & RTF_LOCAL)
rtm->rtm_type = RTN_LOCAL;
+ else if (rt->rt6i_flags & RTF_ANYCAST)
+ rtm->rtm_type = RTN_ANYCAST;
else if (rt->dst.dev && (rt->dst.dev->flags & IFF_LOOPBACK))
rtm->rtm_type = RTN_LOCAL;
else
@@ -3515,7 +3518,7 @@ static int rt6_fill_node(struct net *net,
nla_nest_end(skb, mp);
} else {
- if (rt6_nexthop_info(skb, rt, &rtm->rtm_flags) < 0)
+ if (rt6_nexthop_info(skb, rt, &rtm->rtm_flags, false) < 0)
goto nla_put_failure;
}
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 8558225..a644aae 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -26,17 +26,13 @@
#include <linux/seg6_iptunnel.h>
#include <net/addrconf.h>
#include <net/ip6_route.h>
-#ifdef CONFIG_DST_CACHE
#include <net/dst_cache.h>
-#endif
#ifdef CONFIG_IPV6_SEG6_HMAC
#include <net/seg6_hmac.h>
#endif
struct seg6_lwt {
-#ifdef CONFIG_DST_CACHE
struct dst_cache cache;
-#endif
struct seg6_iptunnel_encap tuninfo[0];
};
@@ -105,7 +101,7 @@ static int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
hdrlen = (osrh->hdrlen + 1) << 3;
tot_len = hdrlen + sizeof(*hdr);
- err = pskb_expand_head(skb, tot_len, 0, GFP_ATOMIC);
+ err = skb_cow_head(skb, tot_len);
if (unlikely(err))
return err;
@@ -156,7 +152,7 @@ static int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
hdrlen = (osrh->hdrlen + 1) << 3;
- err = pskb_expand_head(skb, hdrlen, 0, GFP_ATOMIC);
+ err = skb_cow_head(skb, hdrlen);
if (unlikely(err))
return err;
@@ -237,6 +233,9 @@ static int seg6_do_srh(struct sk_buff *skb)
static int seg6_input(struct sk_buff *skb)
{
+ struct dst_entry *orig_dst = skb_dst(skb);
+ struct dst_entry *dst = NULL;
+ struct seg6_lwt *slwt;
int err;
err = seg6_do_srh(skb);
@@ -245,8 +244,26 @@ static int seg6_input(struct sk_buff *skb)
return err;
}
+ slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
+
+ preempt_disable();
+ dst = dst_cache_get(&slwt->cache);
+ preempt_enable();
+
skb_dst_drop(skb);
- ip6_route_input(skb);
+
+ if (!dst) {
+ ip6_route_input(skb);
+ dst = skb_dst(skb);
+ if (!dst->error) {
+ preempt_disable();
+ dst_cache_set_ip6(&slwt->cache, dst,
+ &ipv6_hdr(skb)->saddr);
+ preempt_enable();
+ }
+ } else {
+ skb_dst_set(skb, dst);
+ }
return dst_input(skb);
}
@@ -264,11 +281,9 @@ static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
-#ifdef CONFIG_DST_CACHE
preempt_disable();
dst = dst_cache_get(&slwt->cache);
preempt_enable();
-#endif
if (unlikely(!dst)) {
struct ipv6hdr *hdr = ipv6_hdr(skb);
@@ -287,11 +302,9 @@ static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
goto drop;
}
-#ifdef CONFIG_DST_CACHE
preempt_disable();
dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr);
preempt_enable();
-#endif
}
skb_dst_drop(skb);
@@ -355,13 +368,11 @@ static int seg6_build_state(struct nlattr *nla,
slwt = seg6_lwt_lwtunnel(newts);
-#ifdef CONFIG_DST_CACHE
err = dst_cache_init(&slwt->cache, GFP_KERNEL);
if (err) {
kfree(newts);
return err;
}
-#endif
memcpy(&slwt->tuninfo, tuninfo, tuninfo_len);
@@ -375,12 +386,10 @@ static int seg6_build_state(struct nlattr *nla,
return 0;
}
-#ifdef CONFIG_DST_CACHE
static void seg6_destroy_state(struct lwtunnel_state *lwt)
{
dst_cache_destroy(&seg6_lwt_lwtunnel(lwt)->cache);
}
-#endif
static int seg6_fill_encap_info(struct sk_buff *skb,
struct lwtunnel_state *lwtstate)
@@ -414,9 +423,7 @@ static int seg6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
static const struct lwtunnel_encap_ops seg6_iptun_ops = {
.build_state = seg6_build_state,
-#ifdef CONFIG_DST_CACHE
.destroy_state = seg6_destroy_state,
-#endif
.output = seg6_output,
.input = seg6_input,
.fill_encap = seg6_fill_encap_info,
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 60a5295..8e42e8f 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -101,12 +101,12 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
}
}
-static u32 tcp_v6_init_sequence(const struct sk_buff *skb, u32 *tsoff)
+static u32 tcp_v6_init_seq_and_tsoff(const struct sk_buff *skb, u32 *tsoff)
{
- return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32,
- ipv6_hdr(skb)->saddr.s6_addr32,
- tcp_hdr(skb)->dest,
- tcp_hdr(skb)->source, tsoff);
+ return secure_tcpv6_seq_and_tsoff(ipv6_hdr(skb)->daddr.s6_addr32,
+ ipv6_hdr(skb)->saddr.s6_addr32,
+ tcp_hdr(skb)->dest,
+ tcp_hdr(skb)->source, tsoff);
}
static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
@@ -265,11 +265,6 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
sk->sk_gso_type = SKB_GSO_TCPV6;
ip6_dst_store(sk, dst, NULL, NULL);
- if (tcp_death_row->sysctl_tw_recycle &&
- !tp->rx_opt.ts_recent_stamp &&
- ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr))
- tcp_fetch_timewait_stamp(sk, dst);
-
icsk->icsk_ext_hdr_len = 0;
if (opt)
icsk->icsk_ext_hdr_len = opt->opt_flen +
@@ -287,11 +282,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
sk_set_txhash(sk);
if (likely(!tp->repair)) {
- seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32,
- sk->sk_v6_daddr.s6_addr32,
- inet->inet_sport,
- inet->inet_dport,
- &tp->tsoffset);
+ seq = secure_tcpv6_seq_and_tsoff(np->saddr.s6_addr32,
+ sk->sk_v6_daddr.s6_addr32,
+ inet->inet_sport,
+ inet->inet_dport,
+ &tp->tsoffset);
if (!tp->write_seq)
tp->write_seq = seq;
}
@@ -391,10 +386,12 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
np = inet6_sk(sk);
if (type == NDISC_REDIRECT) {
- struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
+ if (!sock_owned_by_user(sk)) {
+ struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
- if (dst)
- dst->ops->redirect(dst, sk, skb);
+ if (dst)
+ dst->ops->redirect(dst, sk, skb);
+ }
goto out;
}
@@ -725,11 +722,8 @@ static void tcp_v6_init_req(struct request_sock *req,
static struct dst_entry *tcp_v6_route_req(const struct sock *sk,
struct flowi *fl,
- const struct request_sock *req,
- bool *strict)
+ const struct request_sock *req)
{
- if (strict)
- *strict = true;
return inet6_csk_route_req(sk, &fl->u.ip6, req, IPPROTO_TCP);
}
@@ -755,7 +749,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
.cookie_init_seq = cookie_v6_init_sequence,
#endif
.route_req = tcp_v6_route_req,
- .init_seq = tcp_v6_init_sequence,
+ .init_seq_tsoff = tcp_v6_init_seq_and_tsoff,
.send_synack = tcp_v6_send_synack,
};
@@ -1299,8 +1293,6 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
goto discard;
if (nsk != sk) {
- sock_rps_save_rxhash(nsk, skb);
- sk_mark_napi_id(nsk, skb);
if (tcp_child_process(sk, nsk, skb))
goto reset;
if (opt_skb)
@@ -1931,8 +1923,9 @@ struct proto tcpv6_prot = {
.diag_destroy = tcp_abort,
};
-static const struct inet6_protocol tcpv6_protocol = {
+static struct inet6_protocol tcpv6_protocol = {
.early_demux = tcp_v6_early_demux,
+ .early_demux_handler = tcp_v6_early_demux,
.handler = tcp_v6_rcv,
.err_handler = tcp_v6_err,
.flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 4e4c401..fd4b1c9 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -864,6 +864,64 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
return 0;
}
+static struct sock *__udp6_lib_demux_lookup(struct net *net,
+ __be16 loc_port, const struct in6_addr *loc_addr,
+ __be16 rmt_port, const struct in6_addr *rmt_addr,
+ int dif)
+{
+ struct sock *sk;
+
+ rcu_read_lock();
+ sk = __udp6_lib_lookup(net, rmt_addr, rmt_port, loc_addr, loc_port,
+ dif, &udp_table, NULL);
+ if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
+ sk = NULL;
+ rcu_read_unlock();
+
+ return sk;
+}
+
+static void udp_v6_early_demux(struct sk_buff *skb)
+{
+ struct net *net = dev_net(skb->dev);
+ const struct udphdr *uh;
+ struct sock *sk;
+ struct dst_entry *dst;
+ int dif = skb->dev->ifindex;
+
+ if (!pskb_may_pull(skb, skb_transport_offset(skb) +
+ sizeof(struct udphdr)))
+ return;
+
+ uh = udp_hdr(skb);
+
+ if (skb->pkt_type == PACKET_HOST)
+ sk = __udp6_lib_demux_lookup(net, uh->dest,
+ &ipv6_hdr(skb)->daddr,
+ uh->source, &ipv6_hdr(skb)->saddr,
+ dif);
+ else
+ return;
+
+ if (!sk)
+ return;
+
+ skb->sk = sk;
+ skb->destructor = sock_efree;
+ dst = READ_ONCE(sk->sk_rx_dst);
+
+ if (dst)
+ dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie);
+ if (dst) {
+ if (dst->flags & DST_NOCACHE) {
+ if (likely(atomic_inc_not_zero(&dst->__refcnt)))
+ skb_dst_set(skb, dst);
+ } else {
+ skb_dst_set_noref(skb, dst);
+ }
+ }
+}
+
static __inline__ int udpv6_rcv(struct sk_buff *skb)
{
return __udp6_lib_rcv(skb, &udp_table, IPPROTO_UDP);
@@ -1035,6 +1093,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
ipc6.hlimit = -1;
ipc6.tclass = -1;
ipc6.dontfrag = -1;
+ sockc.tsflags = sk->sk_tsflags;
/* destination address check */
if (sin6) {
@@ -1159,7 +1218,6 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
fl6.flowi6_mark = sk->sk_mark;
fl6.flowi6_uid = sk->sk_uid;
- sockc.tsflags = sk->sk_tsflags;
if (msg->msg_controllen) {
opt = &opt_space;
@@ -1378,7 +1436,9 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname,
}
#endif
-static const struct inet6_protocol udpv6_protocol = {
+static struct inet6_protocol udpv6_protocol = {
+ .early_demux = udp_v6_early_demux,
+ .early_demux_handler = udp_v6_early_demux,
.handler = udpv6_rcv,
.err_handler = udpv6_err,
.flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 81adc29..8d77ad5 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -828,7 +828,8 @@ static int irda_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
* Wait for incoming connection
*
*/
-static int irda_accept(struct socket *sock, struct socket *newsock, int flags)
+static int irda_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sock *sk = sock->sk;
struct irda_sock *new, *self = irda_sk(sk);
@@ -836,7 +837,7 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags)
struct sk_buff *skb = NULL;
int err;
- err = irda_create(sock_net(sk), newsock, sk->sk_protocol, 0);
+ err = irda_create(sock_net(sk), newsock, sk->sk_protocol, kern);
if (err)
return err;
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 89bbde1..84de7b6 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -938,7 +938,7 @@ static int iucv_sock_listen(struct socket *sock, int backlog)
/* Accept a pending connection */
static int iucv_sock_accept(struct socket *sock, struct socket *newsock,
- int flags)
+ int flags, bool kern)
{
DECLARE_WAITQUEUE(wait, current);
struct sock *sk = sock->sk, *nsk;
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 309062f..31762f7 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1687,7 +1687,7 @@ static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
struct kcm_attach info;
if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
- err = -EFAULT;
+ return -EFAULT;
err = kcm_attach_ioctl(sock, &info);
@@ -1697,7 +1697,7 @@ static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
struct kcm_unattach info;
if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
- err = -EFAULT;
+ return -EFAULT;
err = kcm_unattach_ioctl(sock, &info);
@@ -1708,7 +1708,7 @@ static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
struct socket *newsock = NULL;
if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
- err = -EFAULT;
+ return -EFAULT;
err = kcm_clone(sock, &info, &newsock);
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 8adab63..e37d955 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -278,7 +278,57 @@ struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunn
}
EXPORT_SYMBOL_GPL(l2tp_session_find);
-struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth)
+/* Like l2tp_session_find() but takes a reference on the returned session.
+ * Optionally calls session->ref() too if do_ref is true.
+ */
+struct l2tp_session *l2tp_session_get(struct net *net,
+ struct l2tp_tunnel *tunnel,
+ u32 session_id, bool do_ref)
+{
+ struct hlist_head *session_list;
+ struct l2tp_session *session;
+
+ if (!tunnel) {
+ struct l2tp_net *pn = l2tp_pernet(net);
+
+ session_list = l2tp_session_id_hash_2(pn, session_id);
+
+ rcu_read_lock_bh();
+ hlist_for_each_entry_rcu(session, session_list, global_hlist) {
+ if (session->session_id == session_id) {
+ l2tp_session_inc_refcount(session);
+ if (do_ref && session->ref)
+ session->ref(session);
+ rcu_read_unlock_bh();
+
+ return session;
+ }
+ }
+ rcu_read_unlock_bh();
+
+ return NULL;
+ }
+
+ session_list = l2tp_session_id_hash(tunnel, session_id);
+ read_lock_bh(&tunnel->hlist_lock);
+ hlist_for_each_entry(session, session_list, hlist) {
+ if (session->session_id == session_id) {
+ l2tp_session_inc_refcount(session);
+ if (do_ref && session->ref)
+ session->ref(session);
+ read_unlock_bh(&tunnel->hlist_lock);
+
+ return session;
+ }
+ }
+ read_unlock_bh(&tunnel->hlist_lock);
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(l2tp_session_get);
+
+struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth,
+ bool do_ref)
{
int hash;
struct l2tp_session *session;
@@ -288,6 +338,9 @@ struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth)
for (hash = 0; hash < L2TP_HASH_SIZE; hash++) {
hlist_for_each_entry(session, &tunnel->session_hlist[hash], hlist) {
if (++count > nth) {
+ l2tp_session_inc_refcount(session);
+ if (do_ref && session->ref)
+ session->ref(session);
read_unlock_bh(&tunnel->hlist_lock);
return session;
}
@@ -298,12 +351,13 @@ struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth)
return NULL;
}
-EXPORT_SYMBOL_GPL(l2tp_session_find_nth);
+EXPORT_SYMBOL_GPL(l2tp_session_get_nth);
/* Lookup a session by interface name.
* This is very inefficient but is only used by management interfaces.
*/
-struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname)
+struct l2tp_session *l2tp_session_get_by_ifname(struct net *net, char *ifname,
+ bool do_ref)
{
struct l2tp_net *pn = l2tp_pernet(net);
int hash;
@@ -313,7 +367,11 @@ struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname)
for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) {
hlist_for_each_entry_rcu(session, &pn->l2tp_session_hlist[hash], global_hlist) {
if (!strcmp(session->ifname, ifname)) {
+ l2tp_session_inc_refcount(session);
+ if (do_ref && session->ref)
+ session->ref(session);
rcu_read_unlock_bh();
+
return session;
}
}
@@ -323,7 +381,49 @@ struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname)
return NULL;
}
-EXPORT_SYMBOL_GPL(l2tp_session_find_by_ifname);
+EXPORT_SYMBOL_GPL(l2tp_session_get_by_ifname);
+
+static int l2tp_session_add_to_tunnel(struct l2tp_tunnel *tunnel,
+ struct l2tp_session *session)
+{
+ struct l2tp_session *session_walk;
+ struct hlist_head *g_head;
+ struct hlist_head *head;
+ struct l2tp_net *pn;
+
+ head = l2tp_session_id_hash(tunnel, session->session_id);
+
+ write_lock_bh(&tunnel->hlist_lock);
+ hlist_for_each_entry(session_walk, head, hlist)
+ if (session_walk->session_id == session->session_id)
+ goto exist;
+
+ if (tunnel->version == L2TP_HDR_VER_3) {
+ pn = l2tp_pernet(tunnel->l2tp_net);
+ g_head = l2tp_session_id_hash_2(l2tp_pernet(tunnel->l2tp_net),
+ session->session_id);
+
+ spin_lock_bh(&pn->l2tp_session_hlist_lock);
+ hlist_for_each_entry(session_walk, g_head, global_hlist)
+ if (session_walk->session_id == session->session_id)
+ goto exist_glob;
+
+ hlist_add_head_rcu(&session->global_hlist, g_head);
+ spin_unlock_bh(&pn->l2tp_session_hlist_lock);
+ }
+
+ hlist_add_head(&session->hlist, head);
+ write_unlock_bh(&tunnel->hlist_lock);
+
+ return 0;
+
+exist_glob:
+ spin_unlock_bh(&pn->l2tp_session_hlist_lock);
+exist:
+ write_unlock_bh(&tunnel->hlist_lock);
+
+ return -EEXIST;
+}
/* Lookup a tunnel by id
*/
@@ -633,6 +733,9 @@ static int l2tp_recv_data_seq(struct l2tp_session *session, struct sk_buff *skb)
* a data (not control) frame before coming here. Fields up to the
* session-id have already been parsed and ptr points to the data
* after the session-id.
+ *
+ * session->ref() must have been called prior to l2tp_recv_common().
+ * session->deref() will be called automatically after skb is processed.
*/
void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
unsigned char *ptr, unsigned char *optr, u16 hdrflags,
@@ -642,14 +745,6 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
int offset;
u32 ns, nr;
- /* The ref count is increased since we now hold a pointer to
- * the session. Take care to decrement the refcnt when exiting
- * this function from now on...
- */
- l2tp_session_inc_refcount(session);
- if (session->ref)
- (*session->ref)(session);
-
/* Parse and check optional cookie */
if (session->peer_cookie_len > 0) {
if (memcmp(ptr, &session->peer_cookie[0], session->peer_cookie_len)) {
@@ -802,8 +897,6 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
/* Try to dequeue as many skbs from reorder_q as we can. */
l2tp_recv_dequeue(session);
- l2tp_session_dec_refcount(session);
-
return;
discard:
@@ -812,8 +905,6 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
if (session->deref)
(*session->deref)(session);
-
- l2tp_session_dec_refcount(session);
}
EXPORT_SYMBOL(l2tp_recv_common);
@@ -920,8 +1011,14 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
}
/* Find the session context */
- session = l2tp_session_find(tunnel->l2tp_net, tunnel, session_id);
+ session = l2tp_session_get(tunnel->l2tp_net, tunnel, session_id, true);
if (!session || !session->recv_skb) {
+ if (session) {
+ if (session->deref)
+ session->deref(session);
+ l2tp_session_dec_refcount(session);
+ }
+
/* Not found? Pass to userspace to deal with */
l2tp_info(tunnel, L2TP_MSG_DATA,
"%s: no session found (%u/%u). Passing up.\n",
@@ -930,6 +1027,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
}
l2tp_recv_common(session, skb, ptr, optr, hdrflags, length, payload_hook);
+ l2tp_session_dec_refcount(session);
return 0;
@@ -1738,6 +1836,7 @@ EXPORT_SYMBOL_GPL(l2tp_session_set_header_len);
struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg)
{
struct l2tp_session *session;
+ int err;
session = kzalloc(sizeof(struct l2tp_session) + priv_size, GFP_KERNEL);
if (session != NULL) {
@@ -1793,6 +1892,13 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn
l2tp_session_set_header_len(session, tunnel->version);
+ err = l2tp_session_add_to_tunnel(tunnel, session);
+ if (err) {
+ kfree(session);
+
+ return ERR_PTR(err);
+ }
+
/* Bump the reference count. The session context is deleted
* only when this drops to zero.
*/
@@ -1802,28 +1908,14 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn
/* Ensure tunnel socket isn't deleted */
sock_hold(tunnel->sock);
- /* Add session to the tunnel's hash list */
- write_lock_bh(&tunnel->hlist_lock);
- hlist_add_head(&session->hlist,
- l2tp_session_id_hash(tunnel, session_id));
- write_unlock_bh(&tunnel->hlist_lock);
-
- /* And to the global session list if L2TPv3 */
- if (tunnel->version != L2TP_HDR_VER_2) {
- struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net);
-
- spin_lock_bh(&pn->l2tp_session_hlist_lock);
- hlist_add_head_rcu(&session->global_hlist,
- l2tp_session_id_hash_2(pn, session_id));
- spin_unlock_bh(&pn->l2tp_session_hlist_lock);
- }
-
/* Ignore management session in session count value */
if (session->session_id != 0)
atomic_inc(&l2tp_session_count);
+
+ return session;
}
- return session;
+ return ERR_PTR(-ENOMEM);
}
EXPORT_SYMBOL_GPL(l2tp_session_create);
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index aebf281..8ce7818 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -230,11 +230,16 @@ static inline struct l2tp_tunnel *l2tp_sock_to_tunnel(struct sock *sk)
return tunnel;
}
+struct l2tp_session *l2tp_session_get(struct net *net,
+ struct l2tp_tunnel *tunnel,
+ u32 session_id, bool do_ref);
struct l2tp_session *l2tp_session_find(struct net *net,
struct l2tp_tunnel *tunnel,
u32 session_id);
-struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth);
-struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname);
+struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth,
+ bool do_ref);
+struct l2tp_session *l2tp_session_get_by_ifname(struct net *net, char *ifname,
+ bool do_ref);
struct l2tp_tunnel *l2tp_tunnel_find(struct net *net, u32 tunnel_id);
struct l2tp_tunnel *l2tp_tunnel_find_nth(struct net *net, int nth);
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index 2d6760a..d100aed 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -53,7 +53,7 @@ static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd)
static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd)
{
- pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx);
+ pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true);
pd->session_idx++;
if (pd->session == NULL) {
@@ -238,10 +238,14 @@ static int l2tp_dfs_seq_show(struct seq_file *m, void *v)
}
/* Show the tunnel or session context */
- if (pd->session == NULL)
+ if (!pd->session) {
l2tp_dfs_seq_tunnel_show(m, pd->tunnel);
- else
+ } else {
l2tp_dfs_seq_session_show(m, pd->session);
+ if (pd->session->deref)
+ pd->session->deref(pd->session);
+ l2tp_session_dec_refcount(pd->session);
+ }
out:
return 0;
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index 8bf18a5..138566a 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -30,6 +30,9 @@
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/udp.h>
#include "l2tp_core.h"
@@ -204,6 +207,53 @@ static void l2tp_eth_show(struct seq_file *m, void *arg)
}
#endif
+static void l2tp_eth_adjust_mtu(struct l2tp_tunnel *tunnel,
+ struct l2tp_session *session,
+ struct net_device *dev)
+{
+ unsigned int overhead = 0;
+ struct dst_entry *dst;
+ u32 l3_overhead = 0;
+
+ /* if the encap is UDP, account for UDP header size */
+ if (tunnel->encap == L2TP_ENCAPTYPE_UDP) {
+ overhead += sizeof(struct udphdr);
+ dev->needed_headroom += sizeof(struct udphdr);
+ }
+ if (session->mtu != 0) {
+ dev->mtu = session->mtu;
+ dev->needed_headroom += session->hdr_len;
+ return;
+ }
+ l3_overhead = kernel_sock_ip_overhead(tunnel->sock);
+ if (l3_overhead == 0) {
+ /* L3 Overhead couldn't be identified, this could be
+ * because tunnel->sock was NULL or the socket's
+ * address family was not IPv4 or IPv6,
+ * dev mtu stays at 1500.
+ */
+ return;
+ }
+ /* Adjust MTU, factor overhead - underlay L3, overlay L2 hdr
+ * UDP overhead, if any, was already factored in above.
+ */
+ overhead += session->hdr_len + ETH_HLEN + l3_overhead;
+
+ /* If PMTU discovery was enabled, use discovered MTU on L2TP device */
+ dst = sk_dst_get(tunnel->sock);
+ if (dst) {
+ /* dst_mtu will use PMTU if found, else fallback to intf MTU */
+ u32 pmtu = dst_mtu(dst);
+
+ if (pmtu != 0)
+ dev->mtu = pmtu;
+ dst_release(dst);
+ }
+ session->mtu = dev->mtu - overhead;
+ dev->mtu = session->mtu;
+ dev->needed_headroom += session->hdr_len;
+}
+
static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg)
{
struct net_device *dev;
@@ -221,12 +271,6 @@ static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 p
goto out;
}
- session = l2tp_session_find(net, tunnel, session_id);
- if (session) {
- rc = -EEXIST;
- goto out;
- }
-
if (cfg->ifname) {
dev = dev_get_by_name(net, cfg->ifname);
if (dev) {
@@ -240,8 +284,8 @@ static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 p
session = l2tp_session_create(sizeof(*spriv), tunnel, session_id,
peer_session_id, cfg);
- if (!session) {
- rc = -ENOMEM;
+ if (IS_ERR(session)) {
+ rc = PTR_ERR(session);
goto out;
}
@@ -253,12 +297,9 @@ static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 p
}
dev_net_set(dev, net);
- if (session->mtu == 0)
- session->mtu = dev->mtu - session->hdr_len;
- dev->mtu = session->mtu;
- dev->needed_headroom += session->hdr_len;
dev->min_mtu = 0;
dev->max_mtu = ETH_MAX_MTU;
+ l2tp_eth_adjust_mtu(tunnel, session, dev);
priv = netdev_priv(dev);
priv->dev = dev;
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index d25038c..4d322c1 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -143,19 +143,19 @@ static int l2tp_ip_recv(struct sk_buff *skb)
}
/* Ok, this is a data packet. Lookup the session. */
- session = l2tp_session_find(net, NULL, session_id);
- if (session == NULL)
+ session = l2tp_session_get(net, NULL, session_id, true);
+ if (!session)
goto discard;
tunnel = session->tunnel;
- if (tunnel == NULL)
- goto discard;
+ if (!tunnel)
+ goto discard_sess;
/* Trace packet contents, if enabled */
if (tunnel->debug & L2TP_MSG_DATA) {
length = min(32u, skb->len);
if (!pskb_may_pull(skb, length))
- goto discard;
+ goto discard_sess;
/* Point to L2TP header */
optr = ptr = skb->data;
@@ -165,6 +165,7 @@ static int l2tp_ip_recv(struct sk_buff *skb)
}
l2tp_recv_common(session, skb, ptr, optr, 0, skb->len, tunnel->recv_payload_hook);
+ l2tp_session_dec_refcount(session);
return 0;
@@ -178,9 +179,10 @@ static int l2tp_ip_recv(struct sk_buff *skb)
tunnel_id = ntohl(*(__be32 *) &skb->data[4]);
tunnel = l2tp_tunnel_find(net, tunnel_id);
- if (tunnel != NULL)
+ if (tunnel) {
sk = tunnel->sock;
- else {
+ sock_hold(sk);
+ } else {
struct iphdr *iph = (struct iphdr *) skb_network_header(skb);
read_lock_bh(&l2tp_ip_lock);
@@ -202,6 +204,12 @@ static int l2tp_ip_recv(struct sk_buff *skb)
return sk_receive_skb(sk, skb, 1);
+discard_sess:
+ if (session->deref)
+ session->deref(session);
+ l2tp_session_dec_refcount(session);
+ goto discard;
+
discard_put:
sock_put(sk);
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index a4abcbc..88b397c 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -156,19 +156,19 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
}
/* Ok, this is a data packet. Lookup the session. */
- session = l2tp_session_find(net, NULL, session_id);
- if (session == NULL)
+ session = l2tp_session_get(net, NULL, session_id, true);
+ if (!session)
goto discard;
tunnel = session->tunnel;
- if (tunnel == NULL)
- goto discard;
+ if (!tunnel)
+ goto discard_sess;
/* Trace packet contents, if enabled */
if (tunnel->debug & L2TP_MSG_DATA) {
length = min(32u, skb->len);
if (!pskb_may_pull(skb, length))
- goto discard;
+ goto discard_sess;
/* Point to L2TP header */
optr = ptr = skb->data;
@@ -179,6 +179,8 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
l2tp_recv_common(session, skb, ptr, optr, 0, skb->len,
tunnel->recv_payload_hook);
+ l2tp_session_dec_refcount(session);
+
return 0;
pass_up:
@@ -191,9 +193,10 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
tunnel_id = ntohl(*(__be32 *) &skb->data[4]);
tunnel = l2tp_tunnel_find(net, tunnel_id);
- if (tunnel != NULL)
+ if (tunnel) {
sk = tunnel->sock;
- else {
+ sock_hold(sk);
+ } else {
struct ipv6hdr *iph = ipv6_hdr(skb);
read_lock_bh(&l2tp_ip6_lock);
@@ -215,6 +218,12 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
return sk_receive_skb(sk, skb, 1);
+discard_sess:
+ if (session->deref)
+ session->deref(session);
+ l2tp_session_dec_refcount(session);
+ goto discard;
+
discard_put:
sock_put(sk);
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 3620fba..7e3e669 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -48,7 +48,8 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq,
/* Accessed under genl lock */
static const struct l2tp_nl_cmd_ops *l2tp_nl_cmd_ops[__L2TP_PWTYPE_MAX];
-static struct l2tp_session *l2tp_nl_session_find(struct genl_info *info)
+static struct l2tp_session *l2tp_nl_session_get(struct genl_info *info,
+ bool do_ref)
{
u32 tunnel_id;
u32 session_id;
@@ -59,14 +60,15 @@ static struct l2tp_session *l2tp_nl_session_find(struct genl_info *info)
if (info->attrs[L2TP_ATTR_IFNAME]) {
ifname = nla_data(info->attrs[L2TP_ATTR_IFNAME]);
- session = l2tp_session_find_by_ifname(net, ifname);
+ session = l2tp_session_get_by_ifname(net, ifname, do_ref);
} else if ((info->attrs[L2TP_ATTR_SESSION_ID]) &&
(info->attrs[L2TP_ATTR_CONN_ID])) {
tunnel_id = nla_get_u32(info->attrs[L2TP_ATTR_CONN_ID]);
session_id = nla_get_u32(info->attrs[L2TP_ATTR_SESSION_ID]);
tunnel = l2tp_tunnel_find(net, tunnel_id);
if (tunnel)
- session = l2tp_session_find(net, tunnel, session_id);
+ session = l2tp_session_get(net, tunnel, session_id,
+ do_ref);
}
return session;
@@ -642,10 +644,12 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf
session_id, peer_session_id, &cfg);
if (ret >= 0) {
- session = l2tp_session_find(net, tunnel, session_id);
- if (session)
+ session = l2tp_session_get(net, tunnel, session_id, false);
+ if (session) {
ret = l2tp_session_notify(&l2tp_nl_family, info, session,
L2TP_CMD_SESSION_CREATE);
+ l2tp_session_dec_refcount(session);
+ }
}
out:
@@ -658,7 +662,7 @@ static int l2tp_nl_cmd_session_delete(struct sk_buff *skb, struct genl_info *inf
struct l2tp_session *session;
u16 pw_type;
- session = l2tp_nl_session_find(info);
+ session = l2tp_nl_session_get(info, true);
if (session == NULL) {
ret = -ENODEV;
goto out;
@@ -672,6 +676,10 @@ static int l2tp_nl_cmd_session_delete(struct sk_buff *skb, struct genl_info *inf
if (l2tp_nl_cmd_ops[pw_type] && l2tp_nl_cmd_ops[pw_type]->session_delete)
ret = (*l2tp_nl_cmd_ops[pw_type]->session_delete)(session);
+ if (session->deref)
+ session->deref(session);
+ l2tp_session_dec_refcount(session);
+
out:
return ret;
}
@@ -681,7 +689,7 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf
int ret = 0;
struct l2tp_session *session;
- session = l2tp_nl_session_find(info);
+ session = l2tp_nl_session_get(info, false);
if (session == NULL) {
ret = -ENODEV;
goto out;
@@ -716,6 +724,8 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf
ret = l2tp_session_notify(&l2tp_nl_family, info,
session, L2TP_CMD_SESSION_MODIFY);
+ l2tp_session_dec_refcount(session);
+
out:
return ret;
}
@@ -811,29 +821,34 @@ static int l2tp_nl_cmd_session_get(struct sk_buff *skb, struct genl_info *info)
struct sk_buff *msg;
int ret;
- session = l2tp_nl_session_find(info);
+ session = l2tp_nl_session_get(info, false);
if (session == NULL) {
ret = -ENODEV;
- goto out;
+ goto err;
}
msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
if (!msg) {
ret = -ENOMEM;
- goto out;
+ goto err_ref;
}
ret = l2tp_nl_session_send(msg, info->snd_portid, info->snd_seq,
0, session, L2TP_CMD_SESSION_GET);
if (ret < 0)
- goto err_out;
+ goto err_ref_msg;
- return genlmsg_unicast(genl_info_net(info), msg, info->snd_portid);
+ ret = genlmsg_unicast(genl_info_net(info), msg, info->snd_portid);
-err_out:
+ l2tp_session_dec_refcount(session);
+
+ return ret;
+
+err_ref_msg:
nlmsg_free(msg);
-
-out:
+err_ref:
+ l2tp_session_dec_refcount(session);
+err:
return ret;
}
@@ -852,7 +867,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
goto out;
}
- session = l2tp_session_find_nth(tunnel, si);
+ session = l2tp_session_get_nth(tunnel, si, false);
if (session == NULL) {
ti++;
tunnel = NULL;
@@ -862,8 +877,11 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
- session, L2TP_CMD_SESSION_GET) < 0)
+ session, L2TP_CMD_SESSION_GET) < 0) {
+ l2tp_session_dec_refcount(session);
break;
+ }
+ l2tp_session_dec_refcount(session);
si++;
}
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 36cc56f..861b255 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -450,6 +450,10 @@ static void pppol2tp_session_close(struct l2tp_session *session)
static void pppol2tp_session_destruct(struct sock *sk)
{
struct l2tp_session *session = sk->sk_user_data;
+
+ skb_queue_purge(&sk->sk_receive_queue);
+ skb_queue_purge(&sk->sk_write_queue);
+
if (session) {
sk->sk_user_data = NULL;
BUG_ON(session->magic != L2TP_SESSION_MAGIC);
@@ -488,9 +492,6 @@ static int pppol2tp_release(struct socket *sock)
l2tp_session_queue_purge(session);
sock_put(sk);
}
- skb_queue_purge(&sk->sk_receive_queue);
- skb_queue_purge(&sk->sk_write_queue);
-
release_sock(sk);
/* This will delete the session context via
@@ -582,6 +583,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
int error = 0;
u32 tunnel_id, peer_tunnel_id;
u32 session_id, peer_session_id;
+ bool drop_refcnt = false;
int ver = 2;
int fd;
@@ -683,36 +685,36 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
if (tunnel->peer_tunnel_id == 0)
tunnel->peer_tunnel_id = peer_tunnel_id;
- /* Create session if it doesn't already exist. We handle the
- * case where a session was previously created by the netlink
- * interface by checking that the session doesn't already have
- * a socket and its tunnel socket are what we expect. If any
- * of those checks fail, return EEXIST to the caller.
- */
- session = l2tp_session_find(sock_net(sk), tunnel, session_id);
- if (session == NULL) {
- /* Default MTU must allow space for UDP/L2TP/PPP
- * headers.
- */
- cfg.mtu = cfg.mru = 1500 - PPPOL2TP_HEADER_OVERHEAD;
+ session = l2tp_session_get(sock_net(sk), tunnel, session_id, false);
+ if (session) {
+ drop_refcnt = true;
+ ps = l2tp_session_priv(session);
- /* Allocate and initialize a new session context. */
- session = l2tp_session_create(sizeof(struct pppol2tp_session),
- tunnel, session_id,
- peer_session_id, &cfg);
- if (session == NULL) {
- error = -ENOMEM;
+ /* Using a pre-existing session is fine as long as it hasn't
+ * been connected yet.
+ */
+ if (ps->sock) {
+ error = -EEXIST;
+ goto end;
+ }
+
+ /* consistency checks */
+ if (ps->tunnel_sock != tunnel->sock) {
+ error = -EEXIST;
goto end;
}
} else {
- ps = l2tp_session_priv(session);
- error = -EEXIST;
- if (ps->sock != NULL)
- goto end;
+ /* Default MTU must allow space for UDP/L2TP/PPP headers */
+ cfg.mtu = 1500 - PPPOL2TP_HEADER_OVERHEAD;
+ cfg.mru = cfg.mtu;
- /* consistency checks */
- if (ps->tunnel_sock != tunnel->sock)
+ session = l2tp_session_create(sizeof(struct pppol2tp_session),
+ tunnel, session_id,
+ peer_session_id, &cfg);
+ if (IS_ERR(session)) {
+ error = PTR_ERR(session);
goto end;
+ }
}
/* Associate session with its PPPoL2TP socket */
@@ -777,6 +779,8 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
session->name);
end:
+ if (drop_refcnt)
+ l2tp_session_dec_refcount(session);
release_sock(sk);
return error;
@@ -804,12 +808,6 @@ static int pppol2tp_session_create(struct net *net, u32 tunnel_id, u32 session_i
if (tunnel->sock == NULL)
goto out;
- /* Check that this session doesn't already exist */
- error = -EEXIST;
- session = l2tp_session_find(net, tunnel, session_id);
- if (session != NULL)
- goto out;
-
/* Default MTU values. */
if (cfg->mtu == 0)
cfg->mtu = 1500 - PPPOL2TP_HEADER_OVERHEAD;
@@ -817,12 +815,13 @@ static int pppol2tp_session_create(struct net *net, u32 tunnel_id, u32 session_i
cfg->mru = cfg->mtu;
/* Allocate and initialize a new session context. */
- error = -ENOMEM;
session = l2tp_session_create(sizeof(struct pppol2tp_session),
tunnel, session_id,
peer_session_id, cfg);
- if (session == NULL)
+ if (IS_ERR(session)) {
+ error = PTR_ERR(session);
goto out;
+ }
ps = l2tp_session_priv(session);
ps->tunnel_sock = tunnel->sock;
@@ -1140,11 +1139,18 @@ static int pppol2tp_tunnel_ioctl(struct l2tp_tunnel *tunnel,
if (stats.session_id != 0) {
/* resend to session ioctl handler */
struct l2tp_session *session =
- l2tp_session_find(sock_net(sk), tunnel, stats.session_id);
- if (session != NULL)
- err = pppol2tp_session_ioctl(session, cmd, arg);
- else
+ l2tp_session_get(sock_net(sk), tunnel,
+ stats.session_id, true);
+
+ if (session) {
+ err = pppol2tp_session_ioctl(session, cmd,
+ arg);
+ if (session->deref)
+ session->deref(session);
+ l2tp_session_dec_refcount(session);
+ } else {
err = -EBADR;
+ }
break;
}
#ifdef CONFIG_XFRM
@@ -1554,7 +1560,7 @@ static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd)
static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd)
{
- pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx);
+ pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true);
pd->session_idx++;
if (pd->session == NULL) {
@@ -1681,10 +1687,14 @@ static int pppol2tp_seq_show(struct seq_file *m, void *v)
/* Show the tunnel or session context.
*/
- if (pd->session == NULL)
+ if (!pd->session) {
pppol2tp_seq_tunnel_show(m, pd->tunnel);
- else
+ } else {
pppol2tp_seq_session_show(m, pd->session);
+ if (pd->session->deref)
+ pd->session->deref(pd->session);
+ l2tp_session_dec_refcount(pd->session);
+ }
out:
return 0;
@@ -1843,4 +1853,4 @@ MODULE_DESCRIPTION("PPP over L2TP over UDP");
MODULE_LICENSE("GPL");
MODULE_VERSION(PPPOL2TP_DRV_VERSION);
MODULE_ALIAS_NET_PF_PROTO(PF_PPPOX, PX_PROTO_OL2TP);
-MODULE_ALIAS_L2TP_PWTYPE(11);
+MODULE_ALIAS_L2TP_PWTYPE(7);
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 06186d6..cb4fff7 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -641,11 +641,13 @@ static void llc_cmsg_rcv(struct msghdr *msg, struct sk_buff *skb)
* @sock: Socket which connections arrive on.
* @newsock: Socket to move incoming connection to.
* @flags: User specified operational flags.
+ * @kern: If the socket is kernel internal
*
* Accept a new incoming connection.
* Returns 0 upon success, negative otherwise.
*/
-static int llc_ui_accept(struct socket *sock, struct socket *newsock, int flags)
+static int llc_ui_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sock *sk = sock->sk, *newsk;
struct llc_sock *llc, *newllc;
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 40813dd..5bb0c50 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -718,7 +718,8 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
ieee80211_recalc_ps(local);
if (sdata->vif.type == NL80211_IFTYPE_MONITOR ||
- sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
+ sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
+ local->ops->wake_tx_queue) {
/* XXX: for AP_VLAN, actually track AP queues */
netif_tx_start_all_queues(dev);
} else if (dev) {
diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h
index 56ccffa..62141dc 100644
--- a/net/mac802154/ieee802154_i.h
+++ b/net/mac802154/ieee802154_i.h
@@ -19,6 +19,7 @@
#ifndef __IEEE802154_I_H
#define __IEEE802154_I_H
+#include <linux/interrupt.h>
#include <linux/mutex.h>
#include <linux/hrtimer.h>
#include <net/cfg802154.h>
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 3818686..5928d22 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -24,6 +24,9 @@
#include <net/nexthop.h>
#include "internal.h"
+/* max memory we will use for mpls_route */
+#define MAX_MPLS_ROUTE_MEM 4096
+
/* Maximum number of labels to look ahead at when selecting a path of
* a multipath route
*/
@@ -32,7 +35,9 @@
#define MPLS_NEIGH_TABLE_UNSPEC (NEIGH_LINK_TABLE + 1)
static int zero = 0;
+static int one = 1;
static int label_limit = (1 << 20) - 1;
+static int ttl_max = 255;
static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt,
struct nlmsghdr *nlh, struct net *net, u32 portid,
@@ -58,10 +63,7 @@ EXPORT_SYMBOL_GPL(mpls_output_possible);
static u8 *__mpls_nh_via(struct mpls_route *rt, struct mpls_nh *nh)
{
- u8 *nh0_via = PTR_ALIGN((u8 *)&rt->rt_nh[rt->rt_nhn], VIA_ALEN_ALIGN);
- int nh_index = nh - rt->rt_nh;
-
- return nh0_via + rt->rt_max_alen * nh_index;
+ return (u8 *)nh + rt->rt_via_offset;
}
static const u8 *mpls_nh_via(const struct mpls_route *rt,
@@ -187,21 +189,32 @@ static u32 mpls_multipath_hash(struct mpls_route *rt, struct sk_buff *skb)
return hash;
}
+static struct mpls_nh *mpls_get_nexthop(struct mpls_route *rt, u8 index)
+{
+ return (struct mpls_nh *)((u8 *)rt->rt_nh + index * rt->rt_nh_size);
+}
+
+/* number of alive nexthops (rt->rt_nhn_alive) and the flags for
+ * a next hop (nh->nh_flags) are modified by netdev event handlers.
+ * Since those fields can change at any moment, use READ_ONCE to
+ * access both.
+ */
static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
struct sk_buff *skb)
{
- int alive = ACCESS_ONCE(rt->rt_nhn_alive);
u32 hash = 0;
int nh_index = 0;
int n = 0;
+ u8 alive;
/* No need to look further into packet if there's only
* one path
*/
if (rt->rt_nhn == 1)
- goto out;
+ return rt->rt_nh;
- if (alive <= 0)
+ alive = READ_ONCE(rt->rt_nhn_alive);
+ if (alive == 0)
return NULL;
hash = mpls_multipath_hash(rt, skb);
@@ -209,7 +222,9 @@ static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
if (alive == rt->rt_nhn)
goto out;
for_nexthops(rt) {
- if (nh->nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
+ unsigned int nh_flags = READ_ONCE(nh->nh_flags);
+
+ if (nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
continue;
if (n == nh_index)
return nh;
@@ -217,11 +232,11 @@ static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
} endfor_nexthops(rt);
out:
- return &rt->rt_nh[nh_index];
+ return mpls_get_nexthop(rt, nh_index);
}
-static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb,
- struct mpls_entry_decoded dec)
+static bool mpls_egress(struct net *net, struct mpls_route *rt,
+ struct sk_buff *skb, struct mpls_entry_decoded dec)
{
enum mpls_payload_type payload_type;
bool success = false;
@@ -246,22 +261,46 @@ static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb,
switch (payload_type) {
case MPT_IPV4: {
struct iphdr *hdr4 = ip_hdr(skb);
+ u8 new_ttl;
skb->protocol = htons(ETH_P_IP);
+
+ /* If propagating TTL, take the decremented TTL from
+ * the incoming MPLS header, otherwise decrement the
+ * TTL, but only if not 0 to avoid underflow.
+ */
+ if (rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED ||
+ (rt->rt_ttl_propagate == MPLS_TTL_PROP_DEFAULT &&
+ net->mpls.ip_ttl_propagate))
+ new_ttl = dec.ttl;
+ else
+ new_ttl = hdr4->ttl ? hdr4->ttl - 1 : 0;
+
csum_replace2(&hdr4->check,
htons(hdr4->ttl << 8),
- htons(dec.ttl << 8));
- hdr4->ttl = dec.ttl;
+ htons(new_ttl << 8));
+ hdr4->ttl = new_ttl;
success = true;
break;
}
case MPT_IPV6: {
struct ipv6hdr *hdr6 = ipv6_hdr(skb);
skb->protocol = htons(ETH_P_IPV6);
- hdr6->hop_limit = dec.ttl;
+
+ /* If propagating TTL, take the decremented TTL from
+ * the incoming MPLS header, otherwise decrement the
+ * hop limit, but only if not 0 to avoid underflow.
+ */
+ if (rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED ||
+ (rt->rt_ttl_propagate == MPLS_TTL_PROP_DEFAULT &&
+ net->mpls.ip_ttl_propagate))
+ hdr6->hop_limit = dec.ttl;
+ else if (hdr6->hop_limit)
+ hdr6->hop_limit = hdr6->hop_limit - 1;
success = true;
break;
}
case MPT_UNSPEC:
+ /* Should have decided which protocol it is by now */
break;
}
@@ -361,7 +400,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
if (unlikely(!new_header_size && dec.bos)) {
/* Penultimate hop popping */
- if (!mpls_egress(rt, skb, dec))
+ if (!mpls_egress(dev_net(out_dev), rt, skb, dec))
goto err;
} else {
bool bos;
@@ -412,6 +451,7 @@ static struct packet_type mpls_packet_type __read_mostly = {
static const struct nla_policy rtm_mpls_policy[RTA_MAX+1] = {
[RTA_DST] = { .type = NLA_U32 },
[RTA_OIF] = { .type = NLA_U32 },
+ [RTA_TTL_PROPAGATE] = { .type = NLA_U8 },
};
struct mpls_route_config {
@@ -421,6 +461,7 @@ struct mpls_route_config {
u8 rc_via_alen;
u8 rc_via[MAX_VIA_ALEN];
u32 rc_label;
+ u8 rc_ttl_propagate;
u8 rc_output_labels;
u32 rc_output_label[MAX_NEW_LABELS];
u32 rc_nlflags;
@@ -430,20 +471,27 @@ struct mpls_route_config {
int rc_mp_len;
};
-static struct mpls_route *mpls_rt_alloc(int num_nh, u8 max_alen)
+/* all nexthops within a route have the same size based on max
+ * number of labels and max via length for a hop
+ */
+static struct mpls_route *mpls_rt_alloc(u8 num_nh, u8 max_alen, u8 max_labels)
{
- u8 max_alen_aligned = ALIGN(max_alen, VIA_ALEN_ALIGN);
+ u8 nh_size = MPLS_NH_SIZE(max_labels, max_alen);
struct mpls_route *rt;
+ size_t size;
- rt = kzalloc(ALIGN(sizeof(*rt) + num_nh * sizeof(*rt->rt_nh),
- VIA_ALEN_ALIGN) +
- num_nh * max_alen_aligned,
- GFP_KERNEL);
- if (rt) {
- rt->rt_nhn = num_nh;
- rt->rt_nhn_alive = num_nh;
- rt->rt_max_alen = max_alen_aligned;
- }
+ size = sizeof(*rt) + num_nh * nh_size;
+ if (size > MAX_MPLS_ROUTE_MEM)
+ return ERR_PTR(-EINVAL);
+
+ rt = kzalloc(size, GFP_KERNEL);
+ if (!rt)
+ return ERR_PTR(-ENOMEM);
+
+ rt->rt_nhn = num_nh;
+ rt->rt_nhn_alive = num_nh;
+ rt->rt_nh_size = nh_size;
+ rt->rt_via_offset = MPLS_NH_VIA_OFF(max_labels);
return rt;
}
@@ -648,9 +696,6 @@ static int mpls_nh_build_from_cfg(struct mpls_route_config *cfg,
return -ENOMEM;
err = -EINVAL;
- /* Ensure only a supported number of labels are present */
- if (cfg->rc_output_labels > MAX_NEW_LABELS)
- goto errout;
nh->nh_labels = cfg->rc_output_labels;
for (i = 0; i < nh->nh_labels; i++)
@@ -675,7 +720,7 @@ static int mpls_nh_build_from_cfg(struct mpls_route_config *cfg,
static int mpls_nh_build(struct net *net, struct mpls_route *rt,
struct mpls_nh *nh, int oif, struct nlattr *via,
- struct nlattr *newdst)
+ struct nlattr *newdst, u8 max_labels)
{
int err = -ENOMEM;
@@ -683,7 +728,7 @@ static int mpls_nh_build(struct net *net, struct mpls_route *rt,
goto errout;
if (newdst) {
- err = nla_get_labels(newdst, MAX_NEW_LABELS,
+ err = nla_get_labels(newdst, max_labels,
&nh->nh_labels, nh->nh_label);
if (err)
goto errout;
@@ -708,22 +753,20 @@ static int mpls_nh_build(struct net *net, struct mpls_route *rt,
return err;
}
-static int mpls_count_nexthops(struct rtnexthop *rtnh, int len,
- u8 cfg_via_alen, u8 *max_via_alen)
+static u8 mpls_count_nexthops(struct rtnexthop *rtnh, int len,
+ u8 cfg_via_alen, u8 *max_via_alen,
+ u8 *max_labels)
{
- int nhs = 0;
int remaining = len;
-
- if (!rtnh) {
- *max_via_alen = cfg_via_alen;
- return 1;
- }
+ u8 nhs = 0;
*max_via_alen = 0;
+ *max_labels = 0;
while (rtnh_ok(rtnh, remaining)) {
struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
int attrlen;
+ u8 n_labels = 0;
attrlen = rtnh_attrlen(rtnh);
nla = nla_find(attrs, attrlen, RTA_VIA);
@@ -737,7 +780,20 @@ static int mpls_count_nexthops(struct rtnexthop *rtnh, int len,
via_alen);
}
+ nla = nla_find(attrs, attrlen, RTA_NEWDST);
+ if (nla &&
+ nla_get_labels(nla, MAX_NEW_LABELS, &n_labels, NULL) != 0)
+ return 0;
+
+ *max_labels = max_t(u8, *max_labels, n_labels);
+
+ /* number of nexthops is tracked by a u8.
+ * Check for overflow.
+ */
+ if (nhs == 255)
+ return 0;
nhs++;
+
rtnh = rtnh_next(rtnh, &remaining);
}
@@ -746,13 +802,13 @@ static int mpls_count_nexthops(struct rtnexthop *rtnh, int len,
}
static int mpls_nh_build_multi(struct mpls_route_config *cfg,
- struct mpls_route *rt)
+ struct mpls_route *rt, u8 max_labels)
{
struct rtnexthop *rtnh = cfg->rc_mp;
struct nlattr *nla_via, *nla_newdst;
int remaining = cfg->rc_mp_len;
- int nhs = 0;
int err = 0;
+ u8 nhs = 0;
change_nexthops(rt) {
int attrlen;
@@ -779,7 +835,8 @@ static int mpls_nh_build_multi(struct mpls_route_config *cfg,
}
err = mpls_nh_build(cfg->rc_nlinfo.nl_net, rt, nh,
- rtnh->rtnh_ifindex, nla_via, nla_newdst);
+ rtnh->rtnh_ifindex, nla_via, nla_newdst,
+ max_labels);
if (err)
goto errout;
@@ -806,7 +863,8 @@ static int mpls_route_add(struct mpls_route_config *cfg)
int err = -EINVAL;
u8 max_via_alen;
unsigned index;
- int nhs;
+ u8 max_labels;
+ u8 nhs;
index = cfg->rc_label;
@@ -844,21 +902,32 @@ static int mpls_route_add(struct mpls_route_config *cfg)
goto errout;
err = -EINVAL;
- nhs = mpls_count_nexthops(cfg->rc_mp, cfg->rc_mp_len,
- cfg->rc_via_alen, &max_via_alen);
+ if (cfg->rc_mp) {
+ nhs = mpls_count_nexthops(cfg->rc_mp, cfg->rc_mp_len,
+ cfg->rc_via_alen, &max_via_alen,
+ &max_labels);
+ } else {
+ max_via_alen = cfg->rc_via_alen;
+ max_labels = cfg->rc_output_labels;
+ nhs = 1;
+ }
+
if (nhs == 0)
goto errout;
err = -ENOMEM;
- rt = mpls_rt_alloc(nhs, max_via_alen);
- if (!rt)
+ rt = mpls_rt_alloc(nhs, max_via_alen, max_labels);
+ if (IS_ERR(rt)) {
+ err = PTR_ERR(rt);
goto errout;
+ }
rt->rt_protocol = cfg->rc_protocol;
rt->rt_payload_type = cfg->rc_payload_type;
+ rt->rt_ttl_propagate = cfg->rc_ttl_propagate;
if (cfg->rc_mp)
- err = mpls_nh_build_multi(cfg, rt);
+ err = mpls_nh_build_multi(cfg, rt, max_labels);
else
err = mpls_nh_build_from_cfg(cfg, rt);
if (err)
@@ -1011,8 +1080,8 @@ static int mpls_netconf_msgsize_devconf(int type)
return size;
}
-static void mpls_netconf_notify_devconf(struct net *net, int type,
- struct mpls_dev *mdev)
+static void mpls_netconf_notify_devconf(struct net *net, int event,
+ int type, struct mpls_dev *mdev)
{
struct sk_buff *skb;
int err = -ENOBUFS;
@@ -1021,8 +1090,7 @@ static void mpls_netconf_notify_devconf(struct net *net, int type,
if (!skb)
goto errout;
- err = mpls_netconf_fill_devconf(skb, mdev, 0, 0, RTM_NEWNETCONF,
- 0, type);
+ err = mpls_netconf_fill_devconf(skb, mdev, 0, 0, event, 0, type);
if (err < 0) {
/* -EMSGSIZE implies BUG in mpls_netconf_msgsize_devconf() */
WARN_ON(err == -EMSGSIZE);
@@ -1155,9 +1223,8 @@ static int mpls_conf_proc(struct ctl_table *ctl, int write,
if (i == offsetof(struct mpls_dev, input_enabled) &&
val != oval) {
- mpls_netconf_notify_devconf(net,
- NETCONFA_INPUT,
- mdev);
+ mpls_netconf_notify_devconf(net, RTM_NEWNETCONF,
+ NETCONFA_INPUT, mdev);
}
}
@@ -1198,10 +1265,11 @@ static int mpls_dev_sysctl_register(struct net_device *dev,
snprintf(path, sizeof(path), "net/mpls/conf/%s", dev->name);
- mdev->sysctl = register_net_sysctl(dev_net(dev), path, table);
+ mdev->sysctl = register_net_sysctl(net, path, table);
if (!mdev->sysctl)
goto free;
+ mpls_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL, mdev);
return 0;
free:
@@ -1210,13 +1278,17 @@ static int mpls_dev_sysctl_register(struct net_device *dev,
return -ENOBUFS;
}
-static void mpls_dev_sysctl_unregister(struct mpls_dev *mdev)
+static void mpls_dev_sysctl_unregister(struct net_device *dev,
+ struct mpls_dev *mdev)
{
+ struct net *net = dev_net(dev);
struct ctl_table *table;
table = mdev->sysctl->ctl_table_arg;
unregister_net_sysctl_table(mdev->sysctl);
kfree(table);
+
+ mpls_netconf_notify_devconf(net, RTM_DELNETCONF, 0, mdev);
}
static struct mpls_dev *mpls_add_dev(struct net_device *dev)
@@ -1242,11 +1314,12 @@ static struct mpls_dev *mpls_add_dev(struct net_device *dev)
u64_stats_init(&mpls_stats->syncp);
}
+ mdev->dev = dev;
+
err = mpls_dev_sysctl_register(dev, mdev);
if (err)
goto free;
- mdev->dev = dev;
rcu_assign_pointer(dev->mpls_ptr, mdev);
return mdev;
@@ -1269,6 +1342,7 @@ static void mpls_ifdown(struct net_device *dev, int event)
{
struct mpls_route __rcu **platform_label;
struct net *net = dev_net(dev);
+ u8 alive, deleted;
unsigned index;
platform_label = rtnl_dereference(net->mpls.platform_label);
@@ -1278,31 +1352,49 @@ static void mpls_ifdown(struct net_device *dev, int event)
if (!rt)
continue;
+ alive = 0;
+ deleted = 0;
change_nexthops(rt) {
+ unsigned int nh_flags = nh->nh_flags;
+
if (rtnl_dereference(nh->nh_dev) != dev)
- continue;
+ goto next;
+
switch (event) {
case NETDEV_DOWN:
case NETDEV_UNREGISTER:
- nh->nh_flags |= RTNH_F_DEAD;
+ nh_flags |= RTNH_F_DEAD;
/* fall through */
case NETDEV_CHANGE:
- nh->nh_flags |= RTNH_F_LINKDOWN;
- ACCESS_ONCE(rt->rt_nhn_alive) = rt->rt_nhn_alive - 1;
+ nh_flags |= RTNH_F_LINKDOWN;
break;
}
if (event == NETDEV_UNREGISTER)
RCU_INIT_POINTER(nh->nh_dev, NULL);
+
+ if (nh->nh_flags != nh_flags)
+ WRITE_ONCE(nh->nh_flags, nh_flags);
+next:
+ if (!(nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)))
+ alive++;
+ if (!rtnl_dereference(nh->nh_dev))
+ deleted++;
} endfor_nexthops(rt);
+
+ WRITE_ONCE(rt->rt_nhn_alive, alive);
+
+ /* if there are no more nexthops, delete the route */
+ if (event == NETDEV_UNREGISTER && deleted == rt->rt_nhn)
+ mpls_route_update(net, index, NULL, NULL);
}
}
-static void mpls_ifup(struct net_device *dev, unsigned int nh_flags)
+static void mpls_ifup(struct net_device *dev, unsigned int flags)
{
struct mpls_route __rcu **platform_label;
struct net *net = dev_net(dev);
unsigned index;
- int alive;
+ u8 alive;
platform_label = rtnl_dereference(net->mpls.platform_label);
for (index = 0; index < net->mpls.platform_labels; index++) {
@@ -1313,20 +1405,22 @@ static void mpls_ifup(struct net_device *dev, unsigned int nh_flags)
alive = 0;
change_nexthops(rt) {
+ unsigned int nh_flags = nh->nh_flags;
struct net_device *nh_dev =
rtnl_dereference(nh->nh_dev);
- if (!(nh->nh_flags & nh_flags)) {
+ if (!(nh_flags & flags)) {
alive++;
continue;
}
if (nh_dev != dev)
continue;
alive++;
- nh->nh_flags &= ~nh_flags;
+ nh_flags &= ~flags;
+ WRITE_ONCE(nh->nh_flags, flags);
} endfor_nexthops(rt);
- ACCESS_ONCE(rt->rt_nhn_alive) = alive;
+ WRITE_ONCE(rt->rt_nhn_alive, alive);
}
}
@@ -1377,7 +1471,7 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
mpls_ifdown(dev, event);
mdev = mpls_dev_get(dev);
if (mdev) {
- mpls_dev_sysctl_unregister(mdev);
+ mpls_dev_sysctl_unregister(dev, mdev);
RCU_INIT_POINTER(dev->mpls_ptr, NULL);
call_rcu(&mdev->rcu, mpls_dev_destroy_rcu);
}
@@ -1387,7 +1481,7 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
if (mdev) {
int err;
- mpls_dev_sysctl_unregister(mdev);
+ mpls_dev_sysctl_unregister(dev, mdev);
err = mpls_dev_sysctl_register(dev, mdev);
if (err)
return notifier_from_errno(err);
@@ -1447,16 +1541,18 @@ int nla_put_labels(struct sk_buff *skb, int attrtype,
EXPORT_SYMBOL_GPL(nla_put_labels);
int nla_get_labels(const struct nlattr *nla,
- u32 max_labels, u8 *labels, u32 label[])
+ u8 max_labels, u8 *labels, u32 label[])
{
unsigned len = nla_len(nla);
- unsigned nla_labels;
struct mpls_shim_hdr *nla_label;
+ u8 nla_labels;
bool bos;
int i;
- /* len needs to be an even multiple of 4 (the label size) */
- if (len & 3)
+ /* len needs to be an even multiple of 4 (the label size). Number
+ * of labels is a u8 so check for overflow.
+ */
+ if (len & 3 || len / 4 > 255)
return -EINVAL;
/* Limit the number of new labels allowed */
@@ -1464,6 +1560,10 @@ int nla_get_labels(const struct nlattr *nla,
if (nla_labels > max_labels)
return -EINVAL;
+ /* when label == NULL, caller wants number of labels */
+ if (!label)
+ goto out;
+
nla_label = nla_data(nla);
bos = true;
for (i = nla_labels - 1; i >= 0; i--, bos = false) {
@@ -1487,6 +1587,7 @@ int nla_get_labels(const struct nlattr *nla,
label[i] = dec.label;
}
+out:
*labels = nla_labels;
return 0;
}
@@ -1548,7 +1649,6 @@ static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh,
err = -EINVAL;
rtm = nlmsg_data(nlh);
- memset(cfg, 0, sizeof(*cfg));
if (rtm->rtm_family != AF_MPLS)
goto errout;
@@ -1576,6 +1676,7 @@ static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh,
cfg->rc_label = LABEL_NOT_SPECIFIED;
cfg->rc_protocol = rtm->rtm_protocol;
cfg->rc_via_table = MPLS_NEIGH_TABLE_UNSPEC;
+ cfg->rc_ttl_propagate = MPLS_TTL_PROP_DEFAULT;
cfg->rc_nlflags = nlh->nlmsg_flags;
cfg->rc_nlinfo.portid = NETLINK_CB(skb).portid;
cfg->rc_nlinfo.nlh = nlh;
@@ -1622,6 +1723,17 @@ static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh,
cfg->rc_mp_len = nla_len(nla);
break;
}
+ case RTA_TTL_PROPAGATE:
+ {
+ u8 ttl_propagate = nla_get_u8(nla);
+
+ if (ttl_propagate > 1)
+ goto errout;
+ cfg->rc_ttl_propagate = ttl_propagate ?
+ MPLS_TTL_PROP_ENABLED :
+ MPLS_TTL_PROP_DISABLED;
+ break;
+ }
default:
/* Unsupported attribute */
goto errout;
@@ -1635,27 +1747,43 @@ static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh,
static int mpls_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
{
- struct mpls_route_config cfg;
+ struct mpls_route_config *cfg;
int err;
- err = rtm_to_route_config(skb, nlh, &cfg);
- if (err < 0)
- return err;
+ cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
+ if (!cfg)
+ return -ENOMEM;
- return mpls_route_del(&cfg);
+ err = rtm_to_route_config(skb, nlh, cfg);
+ if (err < 0)
+ goto out;
+
+ err = mpls_route_del(cfg);
+out:
+ kfree(cfg);
+
+ return err;
}
static int mpls_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
{
- struct mpls_route_config cfg;
+ struct mpls_route_config *cfg;
int err;
- err = rtm_to_route_config(skb, nlh, &cfg);
- if (err < 0)
- return err;
+ cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
+ if (!cfg)
+ return -ENOMEM;
- return mpls_route_add(&cfg);
+ err = rtm_to_route_config(skb, nlh, cfg);
+ if (err < 0)
+ goto out;
+
+ err = mpls_route_add(cfg);
+out:
+ kfree(cfg);
+
+ return err;
}
static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
@@ -1682,6 +1810,15 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
if (nla_put_labels(skb, RTA_DST, 1, &label))
goto nla_put_failure;
+
+ if (rt->rt_ttl_propagate != MPLS_TTL_PROP_DEFAULT) {
+ bool ttl_propagate =
+ rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED;
+
+ if (nla_put_u8(skb, RTA_TTL_PROPAGATE,
+ ttl_propagate))
+ goto nla_put_failure;
+ }
if (rt->rt_nhn == 1) {
const struct mpls_nh *nh = rt->rt_nh;
@@ -1703,21 +1840,23 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
} else {
struct rtnexthop *rtnh;
struct nlattr *mp;
- int dead = 0;
- int linkdown = 0;
+ u8 linkdown = 0;
+ u8 dead = 0;
mp = nla_nest_start(skb, RTA_MULTIPATH);
if (!mp)
goto nla_put_failure;
for_nexthops(rt) {
+ dev = rtnl_dereference(nh->nh_dev);
+ if (!dev)
+ continue;
+
rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh));
if (!rtnh)
goto nla_put_failure;
- dev = rtnl_dereference(nh->nh_dev);
- if (dev)
- rtnh->rtnh_ifindex = dev->ifindex;
+ rtnh->rtnh_ifindex = dev->ifindex;
if (nh->nh_flags & RTNH_F_LINKDOWN) {
rtnh->rtnh_flags |= RTNH_F_LINKDOWN;
linkdown++;
@@ -1792,7 +1931,8 @@ static inline size_t lfib_nlmsg_size(struct mpls_route *rt)
{
size_t payload =
NLMSG_ALIGN(sizeof(struct rtmsg))
- + nla_total_size(4); /* RTA_DST */
+ + nla_total_size(4) /* RTA_DST */
+ + nla_total_size(1); /* RTA_TTL_PROPAGATE */
if (rt->rt_nhn == 1) {
struct mpls_nh *nh = rt->rt_nh;
@@ -1808,6 +1948,8 @@ static inline size_t lfib_nlmsg_size(struct mpls_route *rt)
size_t nhsize = 0;
for_nexthops(rt) {
+ if (!rtnl_dereference(nh->nh_dev))
+ continue;
nhsize += nla_total_size(sizeof(struct rtnexthop));
/* RTA_VIA */
if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC)
@@ -1870,12 +2012,13 @@ static int resize_platform_label_table(struct net *net, size_t limit)
/* In case the predefined labels need to be populated */
if (limit > MPLS_LABEL_IPV4NULL) {
struct net_device *lo = net->loopback_dev;
- rt0 = mpls_rt_alloc(1, lo->addr_len);
- if (!rt0)
+ rt0 = mpls_rt_alloc(1, lo->addr_len, 0);
+ if (IS_ERR(rt0))
goto nort0;
RCU_INIT_POINTER(rt0->rt_nh->nh_dev, lo);
rt0->rt_protocol = RTPROT_KERNEL;
rt0->rt_payload_type = MPT_IPV4;
+ rt0->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT;
rt0->rt_nh->nh_via_table = NEIGH_LINK_TABLE;
rt0->rt_nh->nh_via_alen = lo->addr_len;
memcpy(__mpls_nh_via(rt0, rt0->rt_nh), lo->dev_addr,
@@ -1883,12 +2026,13 @@ static int resize_platform_label_table(struct net *net, size_t limit)
}
if (limit > MPLS_LABEL_IPV6NULL) {
struct net_device *lo = net->loopback_dev;
- rt2 = mpls_rt_alloc(1, lo->addr_len);
- if (!rt2)
+ rt2 = mpls_rt_alloc(1, lo->addr_len, 0);
+ if (IS_ERR(rt2))
goto nort2;
RCU_INIT_POINTER(rt2->rt_nh->nh_dev, lo);
rt2->rt_protocol = RTPROT_KERNEL;
rt2->rt_payload_type = MPT_IPV6;
+ rt2->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT;
rt2->rt_nh->nh_via_table = NEIGH_LINK_TABLE;
rt2->rt_nh->nh_via_alen = lo->addr_len;
memcpy(__mpls_nh_via(rt2, rt2->rt_nh), lo->dev_addr,
@@ -1970,6 +2114,9 @@ static int mpls_platform_labels(struct ctl_table *table, int write,
return ret;
}
+#define MPLS_NS_SYSCTL_OFFSET(field) \
+ (&((struct net *)0)->field)
+
static const struct ctl_table mpls_table[] = {
{
.procname = "platform_labels",
@@ -1978,21 +2125,47 @@ static const struct ctl_table mpls_table[] = {
.mode = 0644,
.proc_handler = mpls_platform_labels,
},
+ {
+ .procname = "ip_ttl_propagate",
+ .data = MPLS_NS_SYSCTL_OFFSET(mpls.ip_ttl_propagate),
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
+ {
+ .procname = "default_ttl",
+ .data = MPLS_NS_SYSCTL_OFFSET(mpls.default_ttl),
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
+ .extra2 = &ttl_max,
+ },
{ }
};
static int mpls_net_init(struct net *net)
{
struct ctl_table *table;
+ int i;
net->mpls.platform_labels = 0;
net->mpls.platform_label = NULL;
+ net->mpls.ip_ttl_propagate = 1;
+ net->mpls.default_ttl = 255;
table = kmemdup(mpls_table, sizeof(mpls_table), GFP_KERNEL);
if (table == NULL)
return -ENOMEM;
- table[0].data = net;
+ /* Table data contains only offsets relative to the base of
+ * the mdev at this point, so make them absolute.
+ */
+ for (i = 0; i < ARRAY_SIZE(mpls_table) - 1; i++)
+ table[i].data = (char *)net + (uintptr_t)table[i].data;
+
net->mpls.ctl = register_net_sysctl(net, "net/mpls", table);
if (net->mpls.ctl == NULL) {
kfree(table);
@@ -2028,6 +2201,7 @@ static void mpls_net_exit(struct net *net)
for (index = 0; index < platform_labels; index++) {
struct mpls_route *rt = rtnl_dereference(platform_label[index]);
RCU_INIT_POINTER(platform_label[index], NULL);
+ mpls_notify_route(net, index, rt, NULL, NULL);
mpls_rt_free(rt);
}
rtnl_unlock();
diff --git a/net/mpls/internal.h b/net/mpls/internal.h
index 76360d8..4db6a59 100644
--- a/net/mpls/internal.h
+++ b/net/mpls/internal.h
@@ -2,6 +2,11 @@
#define MPLS_INTERNAL_H
#include <net/mpls.h>
+/* put a reasonable limit on the number of labels
+ * we will accept from userspace
+ */
+#define MAX_NEW_LABELS 30
+
struct mpls_entry_decoded {
u32 label;
u8 ttl;
@@ -64,7 +69,6 @@ struct mpls_dev {
struct sk_buff;
#define LABEL_NOT_SPECIFIED (1 << 20)
-#define MAX_NEW_LABELS 2
/* This maximum ha length copied from the definition of struct neighbour */
#define VIA_ALEN_ALIGN sizeof(unsigned long)
@@ -83,11 +87,35 @@ enum mpls_payload_type {
struct mpls_nh { /* next hop label forwarding entry */
struct net_device __rcu *nh_dev;
+
+ /* nh_flags is accessed under RCU in the packet path; it is
+ * modified handling netdev events with rtnl lock held
+ */
unsigned int nh_flags;
- u32 nh_label[MAX_NEW_LABELS];
u8 nh_labels;
u8 nh_via_alen;
u8 nh_via_table;
+ u8 nh_reserved1;
+
+ u32 nh_label[0];
+};
+
+/* offset of via from beginning of mpls_nh */
+#define MPLS_NH_VIA_OFF(num_labels) \
+ ALIGN(sizeof(struct mpls_nh) + (num_labels) * sizeof(u32), \
+ VIA_ALEN_ALIGN)
+
+/* all nexthops within a route have the same size based on the
+ * max number of labels and max via length across all nexthops
+ */
+#define MPLS_NH_SIZE(num_labels, max_via_alen) \
+ (MPLS_NH_VIA_OFF((num_labels)) + \
+ ALIGN((max_via_alen), VIA_ALEN_ALIGN))
+
+enum mpls_ttl_propagation {
+ MPLS_TTL_PROP_DEFAULT,
+ MPLS_TTL_PROP_ENABLED,
+ MPLS_TTL_PROP_DISABLED,
};
/* The route, nexthops and vias are stored together in the same memory
@@ -98,16 +126,16 @@ struct mpls_nh { /* next hop label forwarding entry */
* +----------------------+
* | mpls_nh 0 |
* +----------------------+
- * | ... |
- * +----------------------+
- * | mpls_nh n-1 |
- * +----------------------+
- * | alignment padding |
+ * | alignment padding | 4 bytes for odd number of labels
* +----------------------+
* | via[rt_max_alen] 0 |
* +----------------------+
+ * | alignment padding | via's aligned on sizeof(unsigned long)
+ * +----------------------+
* | ... |
* +----------------------+
+ * | mpls_nh n-1 |
+ * +----------------------+
* | via[rt_max_alen] n-1 |
* +----------------------+
*/
@@ -116,22 +144,30 @@ struct mpls_route { /* next hop label forwarding entry */
u8 rt_protocol;
u8 rt_payload_type;
u8 rt_max_alen;
- unsigned int rt_nhn;
- unsigned int rt_nhn_alive;
+ u8 rt_ttl_propagate;
+ u8 rt_nhn;
+ /* rt_nhn_alive is accessed under RCU in the packet path; it
+ * is modified handling netdev events with rtnl lock held
+ */
+ u8 rt_nhn_alive;
+ u8 rt_nh_size;
+ u8 rt_via_offset;
+ u8 rt_reserved1;
struct mpls_nh rt_nh[0];
};
#define for_nexthops(rt) { \
- int nhsel; struct mpls_nh *nh; \
- for (nhsel = 0, nh = (rt)->rt_nh; \
+ int nhsel; struct mpls_nh *nh; u8 *__nh; \
+ for (nhsel = 0, nh = (rt)->rt_nh, __nh = (u8 *)((rt)->rt_nh); \
nhsel < (rt)->rt_nhn; \
- nh++, nhsel++)
+ __nh += rt->rt_nh_size, nh = (struct mpls_nh *)__nh, nhsel++)
#define change_nexthops(rt) { \
- int nhsel; struct mpls_nh *nh; \
- for (nhsel = 0, nh = (struct mpls_nh *)((rt)->rt_nh); \
+ int nhsel; struct mpls_nh *nh; u8 *__nh; \
+ for (nhsel = 0, nh = (struct mpls_nh *)((rt)->rt_nh), \
+ __nh = (u8 *)((rt)->rt_nh); \
nhsel < (rt)->rt_nhn; \
- nh++, nhsel++)
+ __nh += rt->rt_nh_size, nh = (struct mpls_nh *)__nh, nhsel++)
#define endfor_nexthops(rt) }
@@ -166,7 +202,7 @@ static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev)
int nla_put_labels(struct sk_buff *skb, int attrtype, u8 labels,
const u32 label[]);
-int nla_get_labels(const struct nlattr *nla, u32 max_labels, u8 *labels,
+int nla_get_labels(const struct nlattr *nla, u8 max_labels, u8 *labels,
u32 label[]);
int nla_get_via(const struct nlattr *nla, u8 *via_alen, u8 *via_table,
u8 via[]);
diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c
index e4e4424..fe00e98 100644
--- a/net/mpls/mpls_iptunnel.c
+++ b/net/mpls/mpls_iptunnel.c
@@ -29,6 +29,7 @@
static const struct nla_policy mpls_iptunnel_policy[MPLS_IPTUNNEL_MAX + 1] = {
[MPLS_IPTUNNEL_DST] = { .type = NLA_U32 },
+ [MPLS_IPTUNNEL_TTL] = { .type = NLA_U8 },
};
static unsigned int mpls_encap_size(struct mpls_iptunnel_encap *en)
@@ -49,6 +50,7 @@ static int mpls_xmit(struct sk_buff *skb)
struct rtable *rt = NULL;
struct rt6_info *rt6 = NULL;
struct mpls_dev *out_mdev;
+ struct net *net;
int err = 0;
bool bos;
int i;
@@ -56,17 +58,7 @@ static int mpls_xmit(struct sk_buff *skb)
/* Find the output device */
out_dev = dst->dev;
-
- /* Obtain the ttl */
- if (dst->ops->family == AF_INET) {
- ttl = ip_hdr(skb)->ttl;
- rt = (struct rtable *)dst;
- } else if (dst->ops->family == AF_INET6) {
- ttl = ipv6_hdr(skb)->hop_limit;
- rt6 = (struct rt6_info *)dst;
- } else {
- goto drop;
- }
+ net = dev_net(out_dev);
skb_orphan(skb);
@@ -78,6 +70,38 @@ static int mpls_xmit(struct sk_buff *skb)
tun_encap_info = mpls_lwtunnel_encap(dst->lwtstate);
+ /* Obtain the ttl using the following set of rules.
+ *
+ * LWT ttl propagation setting:
+ * - disabled => use default TTL value from LWT
+ * - enabled => use TTL value from IPv4/IPv6 header
+ * - default =>
+ * Global ttl propagation setting:
+ * - disabled => use default TTL value from global setting
+ * - enabled => use TTL value from IPv4/IPv6 header
+ */
+ if (dst->ops->family == AF_INET) {
+ if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DISABLED)
+ ttl = tun_encap_info->default_ttl;
+ else if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DEFAULT &&
+ !net->mpls.ip_ttl_propagate)
+ ttl = net->mpls.default_ttl;
+ else
+ ttl = ip_hdr(skb)->ttl;
+ rt = (struct rtable *)dst;
+ } else if (dst->ops->family == AF_INET6) {
+ if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DISABLED)
+ ttl = tun_encap_info->default_ttl;
+ else if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DEFAULT &&
+ !net->mpls.ip_ttl_propagate)
+ ttl = net->mpls.default_ttl;
+ else
+ ttl = ipv6_hdr(skb)->hop_limit;
+ rt6 = (struct rt6_info *)dst;
+ } else {
+ goto drop;
+ }
+
/* Verify the destination can hold the packet */
new_header_size = mpls_encap_size(tun_encap_info);
mtu = mpls_dev_mtu(out_dev);
@@ -140,6 +164,7 @@ static int mpls_build_state(struct nlattr *nla,
struct mpls_iptunnel_encap *tun_encap_info;
struct nlattr *tb[MPLS_IPTUNNEL_MAX + 1];
struct lwtunnel_state *newts;
+ u8 n_labels;
int ret;
ret = nla_parse_nested(tb, MPLS_IPTUNNEL_MAX, nla,
@@ -151,15 +176,32 @@ static int mpls_build_state(struct nlattr *nla,
return -EINVAL;
- newts = lwtunnel_state_alloc(sizeof(*tun_encap_info));
+ /* determine number of labels */
+ if (nla_get_labels(tb[MPLS_IPTUNNEL_DST],
+ MAX_NEW_LABELS, &n_labels, NULL))
+ return -EINVAL;
+
+ newts = lwtunnel_state_alloc(sizeof(*tun_encap_info) +
+ n_labels * sizeof(u32));
if (!newts)
return -ENOMEM;
tun_encap_info = mpls_lwtunnel_encap(newts);
- ret = nla_get_labels(tb[MPLS_IPTUNNEL_DST], MAX_NEW_LABELS,
+ ret = nla_get_labels(tb[MPLS_IPTUNNEL_DST], n_labels,
&tun_encap_info->labels, tun_encap_info->label);
if (ret)
goto errout;
+
+ tun_encap_info->ttl_propagate = MPLS_TTL_PROP_DEFAULT;
+
+ if (tb[MPLS_IPTUNNEL_TTL]) {
+ tun_encap_info->default_ttl = nla_get_u8(tb[MPLS_IPTUNNEL_TTL]);
+ /* TTL 0 implies propagate from IP header */
+ tun_encap_info->ttl_propagate = tun_encap_info->default_ttl ?
+ MPLS_TTL_PROP_DISABLED :
+ MPLS_TTL_PROP_ENABLED;
+ }
+
newts->type = LWTUNNEL_ENCAP_MPLS;
newts->flags |= LWTUNNEL_STATE_XMIT_REDIRECT;
newts->headroom = mpls_encap_size(tun_encap_info);
@@ -186,6 +228,10 @@ static int mpls_fill_encap_info(struct sk_buff *skb,
tun_encap_info->label))
goto nla_put_failure;
+ if (tun_encap_info->ttl_propagate != MPLS_TTL_PROP_DEFAULT &&
+ nla_put_u8(skb, MPLS_IPTUNNEL_TTL, tun_encap_info->default_ttl))
+ goto nla_put_failure;
+
return 0;
nla_put_failure:
@@ -195,10 +241,16 @@ static int mpls_fill_encap_info(struct sk_buff *skb,
static int mpls_encap_nlsize(struct lwtunnel_state *lwtstate)
{
struct mpls_iptunnel_encap *tun_encap_info;
+ int nlsize;
tun_encap_info = mpls_lwtunnel_encap(lwtstate);
- return nla_total_size(tun_encap_info->labels * 4);
+ nlsize = nla_total_size(tun_encap_info->labels * 4);
+
+ if (tun_encap_info->ttl_propagate != MPLS_TTL_PROP_DEFAULT)
+ nlsize += nla_total_size(1);
+
+ return nlsize;
}
static int mpls_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
@@ -207,10 +259,12 @@ static int mpls_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
struct mpls_iptunnel_encap *b_hdr = mpls_lwtunnel_encap(b);
int l;
- if (a_hdr->labels != b_hdr->labels)
+ if (a_hdr->labels != b_hdr->labels ||
+ a_hdr->ttl_propagate != b_hdr->ttl_propagate ||
+ a_hdr->default_ttl != b_hdr->default_ttl)
return 1;
- for (l = 0; l < MAX_NEW_LABELS; l++)
+ for (l = 0; l < a_hdr->labels; l++)
if (a_hdr->label[l] != b_hdr->label[l])
return 1;
return 0;
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index e6a2753..3d2ac71a 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -181,7 +181,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp)
if (!(cp->flags & IP_VS_CONN_F_HASHED)) {
cp->flags |= IP_VS_CONN_F_HASHED;
- atomic_inc(&cp->refcnt);
+ refcount_inc(&cp->refcnt);
hlist_add_head_rcu(&cp->c_list, &ip_vs_conn_tab[hash]);
ret = 1;
} else {
@@ -215,7 +215,7 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp)
if (cp->flags & IP_VS_CONN_F_HASHED) {
hlist_del_rcu(&cp->c_list);
cp->flags &= ~IP_VS_CONN_F_HASHED;
- atomic_dec(&cp->refcnt);
+ refcount_dec(&cp->refcnt);
ret = 1;
} else
ret = 0;
@@ -242,13 +242,13 @@ static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp)
if (cp->flags & IP_VS_CONN_F_HASHED) {
ret = false;
/* Decrease refcnt and unlink conn only if we are last user */
- if (atomic_cmpxchg(&cp->refcnt, 1, 0) == 1) {
+ if (refcount_dec_if_one(&cp->refcnt)) {
hlist_del_rcu(&cp->c_list);
cp->flags &= ~IP_VS_CONN_F_HASHED;
ret = true;
}
} else
- ret = atomic_read(&cp->refcnt) ? false : true;
+ ret = refcount_read(&cp->refcnt) ? false : true;
spin_unlock(&cp->lock);
ct_write_unlock_bh(hash);
@@ -475,7 +475,7 @@ static void __ip_vs_conn_put_timer(struct ip_vs_conn *cp)
void ip_vs_conn_put(struct ip_vs_conn *cp)
{
if ((cp->flags & IP_VS_CONN_F_ONE_PACKET) &&
- (atomic_read(&cp->refcnt) == 1) &&
+ (refcount_read(&cp->refcnt) == 1) &&
!timer_pending(&cp->timer))
/* expire connection immediately */
__ip_vs_conn_put_notimer(cp);
@@ -617,8 +617,8 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),
IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport),
ip_vs_fwd_tag(cp), cp->state,
- cp->flags, atomic_read(&cp->refcnt),
- atomic_read(&dest->refcnt));
+ cp->flags, refcount_read(&cp->refcnt),
+ refcount_read(&dest->refcnt));
/* Update the connection counters */
if (!(flags & IP_VS_CONN_F_TEMPLATE)) {
@@ -714,8 +714,8 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp)
IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),
IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport),
ip_vs_fwd_tag(cp), cp->state,
- cp->flags, atomic_read(&cp->refcnt),
- atomic_read(&dest->refcnt));
+ cp->flags, refcount_read(&cp->refcnt),
+ refcount_read(&dest->refcnt));
/* Update the connection counters */
if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) {
@@ -863,10 +863,10 @@ static void ip_vs_conn_expire(unsigned long data)
expire_later:
IP_VS_DBG(7, "delayed: conn->refcnt=%d conn->n_control=%d\n",
- atomic_read(&cp->refcnt),
+ refcount_read(&cp->refcnt),
atomic_read(&cp->n_control));
- atomic_inc(&cp->refcnt);
+ refcount_inc(&cp->refcnt);
cp->timeout = 60*HZ;
if (ipvs->sync_state & IP_VS_STATE_MASTER)
@@ -941,7 +941,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af,
* it in the table, so that other thread run ip_vs_random_dropentry
* but cannot drop this entry.
*/
- atomic_set(&cp->refcnt, 1);
+ refcount_set(&cp->refcnt, 1);
cp->control = NULL;
atomic_set(&cp->n_control, 0);
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index db40050..b4a746d 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -542,7 +542,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport),
IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),
IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport),
- cp->flags, atomic_read(&cp->refcnt));
+ cp->flags, refcount_read(&cp->refcnt));
ip_vs_conn_stats(cp, svc);
return cp;
@@ -1193,7 +1193,7 @@ struct ip_vs_conn *ip_vs_new_conn_out(struct ip_vs_service *svc,
IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport),
IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),
IP_VS_DBG_ADDR(cp->af, &cp->daddr), ntohs(cp->dport),
- cp->flags, atomic_read(&cp->refcnt));
+ cp->flags, refcount_read(&cp->refcnt));
LeaveFunction(12);
return cp;
}
@@ -2231,8 +2231,6 @@ static int __net_init __ip_vs_init(struct net *net)
if (ip_vs_sync_net_init(ipvs) < 0)
goto sync_fail;
- printk(KERN_INFO "IPVS: Creating netns size=%zu id=%d\n",
- sizeof(struct netns_ipvs), ipvs->gen);
return 0;
/*
* Error handling
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 5aeb0dd..541aa76 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -699,7 +699,7 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, int dest_af,
dest->vfwmark,
IP_VS_DBG_ADDR(dest->af, &dest->addr),
ntohs(dest->port),
- atomic_read(&dest->refcnt));
+ refcount_read(&dest->refcnt));
if (dest->af == dest_af &&
ip_vs_addr_equal(dest_af, &dest->addr, daddr) &&
dest->port == dport &&
@@ -934,7 +934,7 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
atomic_set(&dest->activeconns, 0);
atomic_set(&dest->inactconns, 0);
atomic_set(&dest->persistconns, 0);
- atomic_set(&dest->refcnt, 1);
+ refcount_set(&dest->refcnt, 1);
INIT_HLIST_NODE(&dest->d_list);
spin_lock_init(&dest->dst_lock);
@@ -998,7 +998,7 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
IP_VS_DBG_BUF(3, "Get destination %s:%u from trash, "
"dest->refcnt=%d, service %u/%s:%u\n",
IP_VS_DBG_ADDR(udest->af, &daddr), ntohs(dport),
- atomic_read(&dest->refcnt),
+ refcount_read(&dest->refcnt),
dest->vfwmark,
IP_VS_DBG_ADDR(svc->af, &dest->vaddr),
ntohs(dest->vport));
@@ -1074,7 +1074,7 @@ static void __ip_vs_del_dest(struct netns_ipvs *ipvs, struct ip_vs_dest *dest,
spin_lock_bh(&ipvs->dest_trash_lock);
IP_VS_DBG_BUF(3, "Moving dest %s:%u into trash, dest->refcnt=%d\n",
IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port),
- atomic_read(&dest->refcnt));
+ refcount_read(&dest->refcnt));
if (list_empty(&ipvs->dest_trash) && !cleanup)
mod_timer(&ipvs->dest_trash_timer,
jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1));
@@ -1157,7 +1157,7 @@ static void ip_vs_dest_trash_expire(unsigned long data)
spin_lock(&ipvs->dest_trash_lock);
list_for_each_entry_safe(dest, next, &ipvs->dest_trash, t_list) {
- if (atomic_read(&dest->refcnt) > 1)
+ if (refcount_read(&dest->refcnt) > 1)
continue;
if (dest->idle_start) {
if (time_before(now, dest->idle_start +
@@ -1545,7 +1545,7 @@ ip_vs_forget_dev(struct ip_vs_dest *dest, struct net_device *dev)
dev->name,
IP_VS_DBG_ADDR(dest->af, &dest->addr),
ntohs(dest->port),
- atomic_read(&dest->refcnt));
+ refcount_read(&dest->refcnt));
__ip_vs_dst_cache_reset(dest);
}
spin_unlock_bh(&dest->dst_lock);
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index 5824927..b6aa4a9 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -448,7 +448,7 @@ __ip_vs_lblc_schedule(struct ip_vs_service *svc)
IP_VS_DBG_ADDR(least->af, &least->addr),
ntohs(least->port),
atomic_read(&least->activeconns),
- atomic_read(&least->refcnt),
+ refcount_read(&least->refcnt),
atomic_read(&least->weight), loh);
return least;
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index 703f118..c13ff57 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -204,7 +204,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set)
IP_VS_DBG_ADDR(least->af, &least->addr),
ntohs(least->port),
atomic_read(&least->activeconns),
- atomic_read(&least->refcnt),
+ refcount_read(&least->refcnt),
atomic_read(&least->weight), loh);
return least;
}
@@ -249,7 +249,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set)
__func__,
IP_VS_DBG_ADDR(most->af, &most->addr), ntohs(most->port),
atomic_read(&most->activeconns),
- atomic_read(&most->refcnt),
+ refcount_read(&most->refcnt),
atomic_read(&most->weight), moh);
return most;
}
@@ -612,7 +612,7 @@ __ip_vs_lblcr_schedule(struct ip_vs_service *svc)
IP_VS_DBG_ADDR(least->af, &least->addr),
ntohs(least->port),
atomic_read(&least->activeconns),
- atomic_read(&least->refcnt),
+ refcount_read(&least->refcnt),
atomic_read(&least->weight), loh);
return least;
diff --git a/net/netfilter/ipvs/ip_vs_nq.c b/net/netfilter/ipvs/ip_vs_nq.c
index a8b6340..7d9d4ac 100644
--- a/net/netfilter/ipvs/ip_vs_nq.c
+++ b/net/netfilter/ipvs/ip_vs_nq.c
@@ -110,7 +110,7 @@ ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
IP_VS_DBG_ADDR(least->af, &least->addr),
ntohs(least->port),
atomic_read(&least->activeconns),
- atomic_read(&least->refcnt),
+ refcount_read(&least->refcnt),
atomic_read(&least->weight), loh);
return least;
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index d952d67..56f8e4b 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -447,7 +447,7 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
ntohs(cp->cport),
sctp_state_name(cp->state),
sctp_state_name(next_state),
- atomic_read(&cp->refcnt));
+ refcount_read(&cp->refcnt));
if (dest) {
if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
(next_state != IP_VS_SCTP_S_ESTABLISHED)) {
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 5117bcb..12dc8d5 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -557,7 +557,7 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
ntohs(cp->cport),
tcp_state_name(cp->state),
tcp_state_name(new_state),
- atomic_read(&cp->refcnt));
+ refcount_read(&cp->refcnt));
if (dest) {
if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
diff --git a/net/netfilter/ipvs/ip_vs_rr.c b/net/netfilter/ipvs/ip_vs_rr.c
index 58bacfc..ee0530d1 100644
--- a/net/netfilter/ipvs/ip_vs_rr.c
+++ b/net/netfilter/ipvs/ip_vs_rr.c
@@ -97,7 +97,7 @@ ip_vs_rr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
"activeconns %d refcnt %d weight %d\n",
IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port),
atomic_read(&dest->activeconns),
- atomic_read(&dest->refcnt), atomic_read(&dest->weight));
+ refcount_read(&dest->refcnt), atomic_read(&dest->weight));
return dest;
}
diff --git a/net/netfilter/ipvs/ip_vs_sed.c b/net/netfilter/ipvs/ip_vs_sed.c
index f8e2d00..ab23cf2 100644
--- a/net/netfilter/ipvs/ip_vs_sed.c
+++ b/net/netfilter/ipvs/ip_vs_sed.c
@@ -111,7 +111,7 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
IP_VS_DBG_ADDR(least->af, &least->addr),
ntohs(least->port),
atomic_read(&least->activeconns),
- atomic_read(&least->refcnt),
+ refcount_read(&least->refcnt),
atomic_read(&least->weight), loh);
return least;
diff --git a/net/netfilter/ipvs/ip_vs_wlc.c b/net/netfilter/ipvs/ip_vs_wlc.c
index 6b366fd..6add39e 100644
--- a/net/netfilter/ipvs/ip_vs_wlc.c
+++ b/net/netfilter/ipvs/ip_vs_wlc.c
@@ -83,7 +83,7 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
IP_VS_DBG_ADDR(least->af, &least->addr),
ntohs(least->port),
atomic_read(&least->activeconns),
- atomic_read(&least->refcnt),
+ refcount_read(&least->refcnt),
atomic_read(&least->weight), loh);
return least;
diff --git a/net/netfilter/ipvs/ip_vs_wrr.c b/net/netfilter/ipvs/ip_vs_wrr.c
index 17e6d44..62258dd 100644
--- a/net/netfilter/ipvs/ip_vs_wrr.c
+++ b/net/netfilter/ipvs/ip_vs_wrr.c
@@ -218,7 +218,7 @@ ip_vs_wrr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
"activeconns %d refcnt %d weight %d\n",
IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port),
atomic_read(&dest->activeconns),
- atomic_read(&dest->refcnt),
+ refcount_read(&dest->refcnt),
atomic_read(&dest->weight));
mark->cl = dest;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 071b97f..3d621b8 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -181,7 +181,11 @@ EXPORT_SYMBOL_GPL(nf_conntrack_htable_size);
unsigned int nf_conntrack_max __read_mostly;
seqcount_t nf_conntrack_generation __read_mostly;
-DEFINE_PER_CPU(struct nf_conn, nf_conntrack_untracked);
+/* nf_conn must be 8 bytes aligned, as the 3 LSB bits are used
+ * for the nfctinfo. We cheat by (ab)using the PER CPU cache line
+ * alignment to enforce this.
+ */
+DEFINE_PER_CPU_ALIGNED(struct nf_conn, nf_conntrack_untracked);
EXPORT_PER_CPU_SYMBOL(nf_conntrack_untracked);
static unsigned int nf_conntrack_hash_rnd __read_mostly;
@@ -1129,7 +1133,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_free);
/* Allocate a new conntrack: we return -ENOMEM if classification
failed due to stress. Otherwise it really is unclassifiable. */
-static struct nf_conntrack_tuple_hash *
+static noinline struct nf_conntrack_tuple_hash *
init_conntrack(struct net *net, struct nf_conn *tmpl,
const struct nf_conntrack_tuple *tuple,
struct nf_conntrack_l3proto *l3proto,
@@ -1237,21 +1241,20 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
return &ct->tuplehash[IP_CT_DIR_ORIGINAL];
}
-/* On success, returns conntrack ptr, sets skb->_nfct | ctinfo */
-static inline struct nf_conn *
+/* On success, returns 0, sets skb->_nfct | ctinfo */
+static int
resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
struct sk_buff *skb,
unsigned int dataoff,
u_int16_t l3num,
u_int8_t protonum,
struct nf_conntrack_l3proto *l3proto,
- struct nf_conntrack_l4proto *l4proto,
- int *set_reply,
- enum ip_conntrack_info *ctinfo)
+ struct nf_conntrack_l4proto *l4proto)
{
const struct nf_conntrack_zone *zone;
struct nf_conntrack_tuple tuple;
struct nf_conntrack_tuple_hash *h;
+ enum ip_conntrack_info ctinfo;
struct nf_conntrack_zone tmp;
struct nf_conn *ct;
u32 hash;
@@ -1260,7 +1263,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
dataoff, l3num, protonum, net, &tuple, l3proto,
l4proto)) {
pr_debug("Can't get tuple\n");
- return NULL;
+ return 0;
}
/* look for tuple match */
@@ -1271,33 +1274,30 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
h = init_conntrack(net, tmpl, &tuple, l3proto, l4proto,
skb, dataoff, hash);
if (!h)
- return NULL;
+ return 0;
if (IS_ERR(h))
- return (void *)h;
+ return PTR_ERR(h);
}
ct = nf_ct_tuplehash_to_ctrack(h);
/* It exists; we have (non-exclusive) reference. */
if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) {
- *ctinfo = IP_CT_ESTABLISHED_REPLY;
- /* Please set reply bit if this packet OK */
- *set_reply = 1;
+ ctinfo = IP_CT_ESTABLISHED_REPLY;
} else {
/* Once we've had two way comms, always ESTABLISHED. */
if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
pr_debug("normal packet for %p\n", ct);
- *ctinfo = IP_CT_ESTABLISHED;
+ ctinfo = IP_CT_ESTABLISHED;
} else if (test_bit(IPS_EXPECTED_BIT, &ct->status)) {
pr_debug("related packet for %p\n", ct);
- *ctinfo = IP_CT_RELATED;
+ ctinfo = IP_CT_RELATED;
} else {
pr_debug("new packet for %p\n", ct);
- *ctinfo = IP_CT_NEW;
+ ctinfo = IP_CT_NEW;
}
- *set_reply = 0;
}
- nf_ct_set(skb, ct, *ctinfo);
- return ct;
+ nf_ct_set(skb, ct, ctinfo);
+ return 0;
}
unsigned int
@@ -1311,7 +1311,6 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
unsigned int *timeouts;
unsigned int dataoff;
u_int8_t protonum;
- int set_reply = 0;
int ret;
tmpl = nf_ct_get(skb, &ctinfo);
@@ -1354,23 +1353,22 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
goto out;
}
repeat:
- ct = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum,
- l3proto, l4proto, &set_reply, &ctinfo);
- if (!ct) {
- /* Not valid part of a connection */
- NF_CT_STAT_INC_ATOMIC(net, invalid);
- ret = NF_ACCEPT;
- goto out;
- }
-
- if (IS_ERR(ct)) {
+ ret = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum,
+ l3proto, l4proto);
+ if (ret < 0) {
/* Too stressed to deal. */
NF_CT_STAT_INC_ATOMIC(net, drop);
ret = NF_DROP;
goto out;
}
- NF_CT_ASSERT(skb_nfct(skb));
+ ct = nf_ct_get(skb, &ctinfo);
+ if (!ct) {
+ /* Not valid part of a connection */
+ NF_CT_STAT_INC_ATOMIC(net, invalid);
+ ret = NF_ACCEPT;
+ goto out;
+ }
/* Decide what timeout policy we want to apply to this flow. */
timeouts = nf_ct_timeout_lookup(net, ct, l4proto);
@@ -1395,7 +1393,8 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
goto out;
}
- if (set_reply && !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status))
+ if (ctinfo == IP_CT_ESTABLISHED_REPLY &&
+ !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status))
nf_conntrack_event_cache(IPCT_REPLY, ct);
out:
if (tmpl)
diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c
index da9df2d..22fc321 100644
--- a/net/netfilter/nf_conntrack_ecache.c
+++ b/net/netfilter/nf_conntrack_ecache.c
@@ -290,6 +290,7 @@ void nf_conntrack_unregister_notifier(struct net *net,
BUG_ON(notify != new);
RCU_INIT_POINTER(net->ct.nf_conntrack_event_cb, NULL);
mutex_unlock(&nf_ct_ecache_mutex);
+ /* synchronize_rcu() is called from ctnetlink_exit. */
}
EXPORT_SYMBOL_GPL(nf_conntrack_unregister_notifier);
@@ -326,6 +327,7 @@ void nf_ct_expect_unregister_notifier(struct net *net,
BUG_ON(notify != new);
RCU_INIT_POINTER(net->ct.nf_expect_event_cb, NULL);
mutex_unlock(&nf_ct_ecache_mutex);
+ /* synchronize_rcu() is called from ctnetlink_exit. */
}
EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier);
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 4b2e1fb..cb29e59 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -133,7 +133,7 @@ nf_ct_expect_find_get(struct net *net,
rcu_read_lock();
i = __nf_ct_expect_find(net, zone, tuple);
- if (i && !atomic_inc_not_zero(&i->use))
+ if (i && !refcount_inc_not_zero(&i->use))
i = NULL;
rcu_read_unlock();
@@ -186,7 +186,7 @@ nf_ct_find_expectation(struct net *net,
return NULL;
if (exp->flags & NF_CT_EXPECT_PERMANENT) {
- atomic_inc(&exp->use);
+ refcount_inc(&exp->use);
return exp;
} else if (del_timer(&exp->timeout)) {
nf_ct_unlink_expect(exp);
@@ -275,7 +275,7 @@ struct nf_conntrack_expect *nf_ct_expect_alloc(struct nf_conn *me)
return NULL;
new->master = me;
- atomic_set(&new->use, 1);
+ refcount_set(&new->use, 1);
return new;
}
EXPORT_SYMBOL_GPL(nf_ct_expect_alloc);
@@ -348,7 +348,7 @@ static void nf_ct_expect_free_rcu(struct rcu_head *head)
void nf_ct_expect_put(struct nf_conntrack_expect *exp)
{
- if (atomic_dec_and_test(&exp->use))
+ if (refcount_dec_and_test(&exp->use))
call_rcu(&exp->rcu, nf_ct_expect_free_rcu);
}
EXPORT_SYMBOL_GPL(nf_ct_expect_put);
@@ -361,7 +361,7 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp)
unsigned int h = nf_ct_expect_dst_hash(net, &exp->tuple);
/* two references : one for hash insert, one for the timer */
- atomic_add(2, &exp->use);
+ refcount_add(2, &exp->use);
hlist_add_head(&exp->lnode, &master_help->expectations);
master_help->expecting[exp->class]++;
diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c
index 02bcf00..008299b 100644
--- a/net/netfilter/nf_conntrack_extend.c
+++ b/net/netfilter/nf_conntrack_extend.c
@@ -53,7 +53,11 @@ nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id,
rcu_read_lock();
t = rcu_dereference(nf_ct_ext_types[id]);
- BUG_ON(t == NULL);
+ if (!t) {
+ rcu_read_unlock();
+ return NULL;
+ }
+
off = ALIGN(sizeof(struct nf_ct_ext), t->align);
len = off + t->len + var_alloc_len;
alloc_size = t->alloc_size + var_alloc_len;
@@ -88,7 +92,10 @@ void *__nf_ct_ext_add_length(struct nf_conn *ct, enum nf_ct_ext_id id,
rcu_read_lock();
t = rcu_dereference(nf_ct_ext_types[id]);
- BUG_ON(t == NULL);
+ if (!t) {
+ rcu_read_unlock();
+ return NULL;
+ }
newoff = ALIGN(old->len, t->align);
newlen = newoff + t->len + var_alloc_len;
@@ -175,6 +182,6 @@ void nf_ct_extend_unregister(struct nf_ct_ext_type *type)
RCU_INIT_POINTER(nf_ct_ext_types[type->id], NULL);
update_alloc_size(type);
mutex_unlock(&nf_ct_ext_type_mutex);
- rcu_barrier(); /* Wait for completion of call_rcu()'s */
+ synchronize_rcu();
}
EXPORT_SYMBOL_GPL(nf_ct_extend_unregister);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 6806b5e..ecdc324 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -2693,7 +2693,7 @@ ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
cb->nlh->nlmsg_seq,
IPCTNL_MSG_EXP_NEW,
exp) < 0) {
- if (!atomic_inc_not_zero(&exp->use))
+ if (!refcount_inc_not_zero(&exp->use))
continue;
cb->args[1] = (unsigned long)exp;
goto out;
@@ -2739,7 +2739,7 @@ ctnetlink_exp_ct_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
cb->nlh->nlmsg_seq,
IPCTNL_MSG_EXP_NEW,
exp) < 0) {
- if (!atomic_inc_not_zero(&exp->use))
+ if (!refcount_inc_not_zero(&exp->use))
continue;
cb->args[1] = (unsigned long)exp;
goto out;
@@ -3442,6 +3442,7 @@ static void __exit ctnetlink_exit(void)
#ifdef CONFIG_NETFILTER_NETLINK_GLUE_CT
RCU_INIT_POINTER(nfnl_ct_hook, NULL);
#endif
+ synchronize_rcu();
}
module_init(ctnetlink_init);
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 94b14c5..82802e4 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -903,6 +903,8 @@ static void __exit nf_nat_cleanup(void)
#ifdef CONFIG_XFRM
RCU_INIT_POINTER(nf_nat_decode_session_hook, NULL);
#endif
+ synchronize_rcu();
+
for (i = 0; i < NFPROTO_NUMPROTO; i++)
kfree(nf_nat_l4protos[i]);
diff --git a/net/netfilter/nf_nat_proto_sctp.c b/net/netfilter/nf_nat_proto_sctp.c
index 31d3586..804e8a0 100644
--- a/net/netfilter/nf_nat_proto_sctp.c
+++ b/net/netfilter/nf_nat_proto_sctp.c
@@ -33,8 +33,16 @@ sctp_manip_pkt(struct sk_buff *skb,
enum nf_nat_manip_type maniptype)
{
sctp_sctphdr_t *hdr;
+ int hdrsize = 8;
- if (!skb_make_writable(skb, hdroff + sizeof(*hdr)))
+ /* This could be an inner header returned in imcp packet; in such
+ * cases we cannot update the checksum field since it is outside
+ * of the 8 bytes of transport layer headers we are guaranteed.
+ */
+ if (skb->len >= hdroff + sizeof(*hdr))
+ hdrsize = sizeof(*hdr);
+
+ if (!skb_make_writable(skb, hdroff + hdrsize))
return false;
hdr = (struct sctphdr *)(skb->data + hdroff);
@@ -47,6 +55,9 @@ sctp_manip_pkt(struct sk_buff *skb,
hdr->dest = tuple->dst.u.sctp.port;
}
+ if (hdrsize < sizeof(*hdr))
+ return true;
+
if (skb->ip_summed != CHECKSUM_PARTIAL) {
hdr->checksum = sctp_compute_cksum(skb, hdroff);
skb->ip_summed = CHECKSUM_NONE;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 5e0ccfd..2d822d2 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1772,8 +1772,19 @@ static int nf_tables_newexpr(const struct nft_ctx *ctx,
goto err1;
}
+ if (ops->validate) {
+ const struct nft_data *data = NULL;
+
+ err = ops->validate(ctx, expr, &data);
+ if (err < 0)
+ goto err2;
+ }
+
return 0;
+err2:
+ if (ops->destroy)
+ ops->destroy(ctx, expr);
err1:
expr->ops = NULL;
return err;
@@ -2523,8 +2534,8 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net,
return 0;
}
-struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
- const struct nlattr *nla, u8 genmask)
+static struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
+ const struct nlattr *nla, u8 genmask)
{
struct nft_set *set;
@@ -2538,11 +2549,10 @@ struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
}
return ERR_PTR(-ENOENT);
}
-EXPORT_SYMBOL_GPL(nf_tables_set_lookup);
-struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
- const struct nlattr *nla,
- u8 genmask)
+static struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
+ const struct nlattr *nla,
+ u8 genmask)
{
struct nft_trans *trans;
u32 id = ntohl(nla_get_be32(nla));
@@ -2557,7 +2567,25 @@ struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
}
return ERR_PTR(-ENOENT);
}
-EXPORT_SYMBOL_GPL(nf_tables_set_lookup_byid);
+
+struct nft_set *nft_set_lookup(const struct net *net,
+ const struct nft_table *table,
+ const struct nlattr *nla_set_name,
+ const struct nlattr *nla_set_id,
+ u8 genmask)
+{
+ struct nft_set *set;
+
+ set = nf_tables_set_lookup(table, nla_set_name, genmask);
+ if (IS_ERR(set)) {
+ if (!nla_set_id)
+ return set;
+
+ set = nf_tables_set_lookup_byid(net, nla_set_id, genmask);
+ }
+ return set;
+}
+EXPORT_SYMBOL_GPL(nft_set_lookup);
static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set,
const char *name)
@@ -3145,7 +3173,6 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
iter.count = 0;
iter.err = 0;
iter.fn = nf_tables_bind_check_setelem;
- iter.flush = false;
set->ops->walk(ctx, set, &iter);
if (iter.err < 0)
@@ -3399,7 +3426,6 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
args.iter.count = 0;
args.iter.err = 0;
args.iter.fn = nf_tables_dump_setelem;
- args.iter.flush = false;
set->ops->walk(&ctx, set, &args.iter);
nla_nest_end(skb, nest);
@@ -3963,7 +3989,6 @@ static int nf_tables_delsetelem(struct net *net, struct sock *nlsk,
struct nft_set_iter iter = {
.genmask = genmask,
.fn = nft_flush_set,
- .flush = true,
};
set->ops->walk(&ctx, set, &iter);
@@ -4067,7 +4092,8 @@ static const struct nla_policy nft_obj_policy[NFTA_OBJ_MAX + 1] = {
[NFTA_OBJ_DATA] = { .type = NLA_NESTED },
};
-static struct nft_object *nft_obj_init(const struct nft_object_type *type,
+static struct nft_object *nft_obj_init(const struct nft_ctx *ctx,
+ const struct nft_object_type *type,
const struct nlattr *attr)
{
struct nlattr *tb[type->maxattr + 1];
@@ -4087,7 +4113,7 @@ static struct nft_object *nft_obj_init(const struct nft_object_type *type,
if (obj == NULL)
goto err1;
- err = type->init((const struct nlattr * const *)tb, obj);
+ err = type->init(ctx, (const struct nlattr * const *)tb, obj);
if (err < 0)
goto err2;
@@ -4195,7 +4221,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
if (IS_ERR(type))
return PTR_ERR(type);
- obj = nft_obj_init(type, nla[NFTA_OBJ_DATA]);
+ obj = nft_obj_init(&ctx, type, nla[NFTA_OBJ_DATA]);
if (IS_ERR(obj)) {
err = PTR_ERR(obj);
goto err1;
@@ -5114,7 +5140,6 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
iter.count = 0;
iter.err = 0;
iter.fn = nf_tables_loop_check_setelem;
- iter.flush = false;
set->ops->walk(ctx, set, &iter);
if (iter.err < 0)
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index d44d89b..c86da17 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -11,6 +11,7 @@
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/atomic.h>
+#include <linux/refcount.h>
#include <linux/netlink.h>
#include <linux/rculist.h>
#include <linux/slab.h>
@@ -32,7 +33,7 @@ struct nf_acct {
atomic64_t bytes;
unsigned long flags;
struct list_head head;
- atomic_t refcnt;
+ refcount_t refcnt;
char name[NFACCT_NAME_MAX];
struct rcu_head rcu_head;
char data[0];
@@ -123,7 +124,7 @@ static int nfnl_acct_new(struct net *net, struct sock *nfnl,
atomic64_set(&nfacct->pkts,
be64_to_cpu(nla_get_be64(tb[NFACCT_PKTS])));
}
- atomic_set(&nfacct->refcnt, 1);
+ refcount_set(&nfacct->refcnt, 1);
list_add_tail_rcu(&nfacct->head, &net->nfnl_acct_list);
return 0;
}
@@ -166,7 +167,7 @@ nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
NFACCT_PAD) ||
nla_put_be64(skb, NFACCT_BYTES, cpu_to_be64(bytes),
NFACCT_PAD) ||
- nla_put_be32(skb, NFACCT_USE, htonl(atomic_read(&acct->refcnt))))
+ nla_put_be32(skb, NFACCT_USE, htonl(refcount_read(&acct->refcnt))))
goto nla_put_failure;
if (acct->flags & NFACCT_F_QUOTA) {
u64 *quota = (u64 *)acct->data;
@@ -329,7 +330,7 @@ static int nfnl_acct_try_del(struct nf_acct *cur)
/* We want to avoid races with nfnl_acct_put. So only when the current
* refcnt is 1, we decrease it to 0.
*/
- if (atomic_cmpxchg(&cur->refcnt, 1, 0) == 1) {
+ if (refcount_dec_if_one(&cur->refcnt)) {
/* We are protected by nfnl mutex. */
list_del_rcu(&cur->head);
kfree_rcu(cur, rcu_head);
@@ -413,7 +414,7 @@ struct nf_acct *nfnl_acct_find_get(struct net *net, const char *acct_name)
if (!try_module_get(THIS_MODULE))
goto err;
- if (!atomic_inc_not_zero(&cur->refcnt)) {
+ if (!refcount_inc_not_zero(&cur->refcnt)) {
module_put(THIS_MODULE);
goto err;
}
@@ -429,7 +430,7 @@ EXPORT_SYMBOL_GPL(nfnl_acct_find_get);
void nfnl_acct_put(struct nf_acct *acct)
{
- if (atomic_dec_and_test(&acct->refcnt))
+ if (refcount_dec_and_test(&acct->refcnt))
kfree_rcu(acct, rcu_head);
module_put(THIS_MODULE);
@@ -502,7 +503,7 @@ static void __net_exit nfnl_acct_net_exit(struct net *net)
list_for_each_entry_safe(cur, tmp, &net->nfnl_acct_list, head) {
list_del_rcu(&cur->head);
- if (atomic_dec_and_test(&cur->refcnt))
+ if (refcount_dec_and_test(&cur->refcnt))
kfree_rcu(cur, rcu_head);
}
}
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index de87823..d455581 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -32,6 +32,13 @@ MODULE_LICENSE("GPL");
MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
MODULE_DESCRIPTION("nfnl_cthelper: User-space connection tracking helpers");
+struct nfnl_cthelper {
+ struct list_head list;
+ struct nf_conntrack_helper helper;
+};
+
+static LIST_HEAD(nfnl_cthelper_list);
+
static int
nfnl_userspace_cthelper(struct sk_buff *skb, unsigned int protoff,
struct nf_conn *ct, enum ip_conntrack_info ctinfo)
@@ -161,6 +168,7 @@ nfnl_cthelper_parse_expect_policy(struct nf_conntrack_helper *helper,
int i, ret;
struct nf_conntrack_expect_policy *expect_policy;
struct nlattr *tb[NFCTH_POLICY_SET_MAX+1];
+ unsigned int class_max;
ret = nla_parse_nested(tb, NFCTH_POLICY_SET_MAX, attr,
nfnl_cthelper_expect_policy_set);
@@ -170,19 +178,18 @@ nfnl_cthelper_parse_expect_policy(struct nf_conntrack_helper *helper,
if (!tb[NFCTH_POLICY_SET_NUM])
return -EINVAL;
- helper->expect_class_max =
- ntohl(nla_get_be32(tb[NFCTH_POLICY_SET_NUM]));
-
- if (helper->expect_class_max != 0 &&
- helper->expect_class_max > NF_CT_MAX_EXPECT_CLASSES)
+ class_max = ntohl(nla_get_be32(tb[NFCTH_POLICY_SET_NUM]));
+ if (class_max == 0)
+ return -EINVAL;
+ if (class_max > NF_CT_MAX_EXPECT_CLASSES)
return -EOVERFLOW;
expect_policy = kzalloc(sizeof(struct nf_conntrack_expect_policy) *
- helper->expect_class_max, GFP_KERNEL);
+ class_max, GFP_KERNEL);
if (expect_policy == NULL)
return -ENOMEM;
- for (i=0; i<helper->expect_class_max; i++) {
+ for (i = 0; i < class_max; i++) {
if (!tb[NFCTH_POLICY_SET+i])
goto err;
@@ -191,6 +198,8 @@ nfnl_cthelper_parse_expect_policy(struct nf_conntrack_helper *helper,
if (ret < 0)
goto err;
}
+
+ helper->expect_class_max = class_max - 1;
helper->expect_policy = expect_policy;
return 0;
err:
@@ -203,18 +212,20 @@ nfnl_cthelper_create(const struct nlattr * const tb[],
struct nf_conntrack_tuple *tuple)
{
struct nf_conntrack_helper *helper;
+ struct nfnl_cthelper *nfcth;
int ret;
if (!tb[NFCTH_TUPLE] || !tb[NFCTH_POLICY] || !tb[NFCTH_PRIV_DATA_LEN])
return -EINVAL;
- helper = kzalloc(sizeof(struct nf_conntrack_helper), GFP_KERNEL);
- if (helper == NULL)
+ nfcth = kzalloc(sizeof(*nfcth), GFP_KERNEL);
+ if (nfcth == NULL)
return -ENOMEM;
+ helper = &nfcth->helper;
ret = nfnl_cthelper_parse_expect_policy(helper, tb[NFCTH_POLICY]);
if (ret < 0)
- goto err;
+ goto err1;
strncpy(helper->name, nla_data(tb[NFCTH_NAME]), NF_CT_HELPER_NAME_LEN);
helper->data_len = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN]));
@@ -245,12 +256,98 @@ nfnl_cthelper_create(const struct nlattr * const tb[],
ret = nf_conntrack_helper_register(helper);
if (ret < 0)
- goto err;
+ goto err2;
+
+ list_add_tail(&nfcth->list, &nfnl_cthelper_list);
+ return 0;
+err2:
+ kfree(helper->expect_policy);
+err1:
+ kfree(nfcth);
+ return ret;
+}
+
+static int
+nfnl_cthelper_update_policy_one(const struct nf_conntrack_expect_policy *policy,
+ struct nf_conntrack_expect_policy *new_policy,
+ const struct nlattr *attr)
+{
+ struct nlattr *tb[NFCTH_POLICY_MAX + 1];
+ int err;
+
+ err = nla_parse_nested(tb, NFCTH_POLICY_MAX, attr,
+ nfnl_cthelper_expect_pol);
+ if (err < 0)
+ return err;
+
+ if (!tb[NFCTH_POLICY_NAME] ||
+ !tb[NFCTH_POLICY_EXPECT_MAX] ||
+ !tb[NFCTH_POLICY_EXPECT_TIMEOUT])
+ return -EINVAL;
+
+ if (nla_strcmp(tb[NFCTH_POLICY_NAME], policy->name))
+ return -EBUSY;
+
+ new_policy->max_expected =
+ ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX]));
+ new_policy->timeout =
+ ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_TIMEOUT]));
return 0;
-err:
- kfree(helper);
- return ret;
+}
+
+static int nfnl_cthelper_update_policy_all(struct nlattr *tb[],
+ struct nf_conntrack_helper *helper)
+{
+ struct nf_conntrack_expect_policy new_policy[helper->expect_class_max + 1];
+ struct nf_conntrack_expect_policy *policy;
+ int i, err;
+
+ /* Check first that all policy attributes are well-formed, so we don't
+ * leave things in inconsistent state on errors.
+ */
+ for (i = 0; i < helper->expect_class_max + 1; i++) {
+
+ if (!tb[NFCTH_POLICY_SET + i])
+ return -EINVAL;
+
+ err = nfnl_cthelper_update_policy_one(&helper->expect_policy[i],
+ &new_policy[i],
+ tb[NFCTH_POLICY_SET + i]);
+ if (err < 0)
+ return err;
+ }
+ /* Now we can safely update them. */
+ for (i = 0; i < helper->expect_class_max + 1; i++) {
+ policy = (struct nf_conntrack_expect_policy *)
+ &helper->expect_policy[i];
+ policy->max_expected = new_policy->max_expected;
+ policy->timeout = new_policy->timeout;
+ }
+
+ return 0;
+}
+
+static int nfnl_cthelper_update_policy(struct nf_conntrack_helper *helper,
+ const struct nlattr *attr)
+{
+ struct nlattr *tb[NFCTH_POLICY_SET_MAX + 1];
+ unsigned int class_max;
+ int err;
+
+ err = nla_parse_nested(tb, NFCTH_POLICY_SET_MAX, attr,
+ nfnl_cthelper_expect_policy_set);
+ if (err < 0)
+ return err;
+
+ if (!tb[NFCTH_POLICY_SET_NUM])
+ return -EINVAL;
+
+ class_max = ntohl(nla_get_be32(tb[NFCTH_POLICY_SET_NUM]));
+ if (helper->expect_class_max + 1 != class_max)
+ return -EBUSY;
+
+ return nfnl_cthelper_update_policy_all(tb, helper);
}
static int
@@ -263,8 +360,7 @@ nfnl_cthelper_update(const struct nlattr * const tb[],
return -EBUSY;
if (tb[NFCTH_POLICY]) {
- ret = nfnl_cthelper_parse_expect_policy(helper,
- tb[NFCTH_POLICY]);
+ ret = nfnl_cthelper_update_policy(helper, tb[NFCTH_POLICY]);
if (ret < 0)
return ret;
}
@@ -293,7 +389,8 @@ static int nfnl_cthelper_new(struct net *net, struct sock *nfnl,
const char *helper_name;
struct nf_conntrack_helper *cur, *helper = NULL;
struct nf_conntrack_tuple tuple;
- int ret = 0, i;
+ struct nfnl_cthelper *nlcth;
+ int ret = 0;
if (!tb[NFCTH_NAME] || !tb[NFCTH_TUPLE])
return -EINVAL;
@@ -304,31 +401,22 @@ static int nfnl_cthelper_new(struct net *net, struct sock *nfnl,
if (ret < 0)
return ret;
- rcu_read_lock();
- for (i = 0; i < nf_ct_helper_hsize && !helper; i++) {
- hlist_for_each_entry_rcu(cur, &nf_ct_helper_hash[i], hnode) {
+ list_for_each_entry(nlcth, &nfnl_cthelper_list, list) {
+ cur = &nlcth->helper;
- /* skip non-userspace conntrack helpers. */
- if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
- continue;
+ if (strncmp(cur->name, helper_name, NF_CT_HELPER_NAME_LEN))
+ continue;
- if (strncmp(cur->name, helper_name,
- NF_CT_HELPER_NAME_LEN) != 0)
- continue;
+ if ((tuple.src.l3num != cur->tuple.src.l3num ||
+ tuple.dst.protonum != cur->tuple.dst.protonum))
+ continue;
- if ((tuple.src.l3num != cur->tuple.src.l3num ||
- tuple.dst.protonum != cur->tuple.dst.protonum))
- continue;
+ if (nlh->nlmsg_flags & NLM_F_EXCL)
+ return -EEXIST;
- if (nlh->nlmsg_flags & NLM_F_EXCL) {
- ret = -EEXIST;
- goto err;
- }
- helper = cur;
- break;
- }
+ helper = cur;
+ break;
}
- rcu_read_unlock();
if (helper == NULL)
ret = nfnl_cthelper_create(tb, &tuple);
@@ -336,9 +424,6 @@ static int nfnl_cthelper_new(struct net *net, struct sock *nfnl,
ret = nfnl_cthelper_update(tb, helper);
return ret;
-err:
- rcu_read_unlock();
- return ret;
}
static int
@@ -377,10 +462,10 @@ nfnl_cthelper_dump_policy(struct sk_buff *skb,
goto nla_put_failure;
if (nla_put_be32(skb, NFCTH_POLICY_SET_NUM,
- htonl(helper->expect_class_max)))
+ htonl(helper->expect_class_max + 1)))
goto nla_put_failure;
- for (i=0; i<helper->expect_class_max; i++) {
+ for (i = 0; i < helper->expect_class_max + 1; i++) {
nest_parms2 = nla_nest_start(skb,
(NFCTH_POLICY_SET+i) | NLA_F_NESTED);
if (nest_parms2 == NULL)
@@ -502,11 +587,12 @@ static int nfnl_cthelper_get(struct net *net, struct sock *nfnl,
struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const tb[])
{
- int ret = -ENOENT, i;
+ int ret = -ENOENT;
struct nf_conntrack_helper *cur;
struct sk_buff *skb2;
char *helper_name = NULL;
struct nf_conntrack_tuple tuple;
+ struct nfnl_cthelper *nlcth;
bool tuple_set = false;
if (nlh->nlmsg_flags & NLM_F_DUMP) {
@@ -527,45 +613,39 @@ static int nfnl_cthelper_get(struct net *net, struct sock *nfnl,
tuple_set = true;
}
- for (i = 0; i < nf_ct_helper_hsize; i++) {
- hlist_for_each_entry_rcu(cur, &nf_ct_helper_hash[i], hnode) {
+ list_for_each_entry(nlcth, &nfnl_cthelper_list, list) {
+ cur = &nlcth->helper;
+ if (helper_name &&
+ strncmp(cur->name, helper_name, NF_CT_HELPER_NAME_LEN))
+ continue;
- /* skip non-userspace conntrack helpers. */
- if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
- continue;
+ if (tuple_set &&
+ (tuple.src.l3num != cur->tuple.src.l3num ||
+ tuple.dst.protonum != cur->tuple.dst.protonum))
+ continue;
- if (helper_name && strncmp(cur->name, helper_name,
- NF_CT_HELPER_NAME_LEN) != 0) {
- continue;
- }
- if (tuple_set &&
- (tuple.src.l3num != cur->tuple.src.l3num ||
- tuple.dst.protonum != cur->tuple.dst.protonum))
- continue;
-
- skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (skb2 == NULL) {
- ret = -ENOMEM;
- break;
- }
-
- ret = nfnl_cthelper_fill_info(skb2, NETLINK_CB(skb).portid,
- nlh->nlmsg_seq,
- NFNL_MSG_TYPE(nlh->nlmsg_type),
- NFNL_MSG_CTHELPER_NEW, cur);
- if (ret <= 0) {
- kfree_skb(skb2);
- break;
- }
-
- ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).portid,
- MSG_DONTWAIT);
- if (ret > 0)
- ret = 0;
-
- /* this avoids a loop in nfnetlink. */
- return ret == -EAGAIN ? -ENOBUFS : ret;
+ skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (skb2 == NULL) {
+ ret = -ENOMEM;
+ break;
}
+
+ ret = nfnl_cthelper_fill_info(skb2, NETLINK_CB(skb).portid,
+ nlh->nlmsg_seq,
+ NFNL_MSG_TYPE(nlh->nlmsg_type),
+ NFNL_MSG_CTHELPER_NEW, cur);
+ if (ret <= 0) {
+ kfree_skb(skb2);
+ break;
+ }
+
+ ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).portid,
+ MSG_DONTWAIT);
+ if (ret > 0)
+ ret = 0;
+
+ /* this avoids a loop in nfnetlink. */
+ return ret == -EAGAIN ? -ENOBUFS : ret;
}
return ret;
}
@@ -576,10 +656,10 @@ static int nfnl_cthelper_del(struct net *net, struct sock *nfnl,
{
char *helper_name = NULL;
struct nf_conntrack_helper *cur;
- struct hlist_node *tmp;
struct nf_conntrack_tuple tuple;
bool tuple_set = false, found = false;
- int i, j = 0, ret;
+ struct nfnl_cthelper *nlcth, *n;
+ int j = 0, ret;
if (tb[NFCTH_NAME])
helper_name = nla_data(tb[NFCTH_NAME]);
@@ -592,28 +672,27 @@ static int nfnl_cthelper_del(struct net *net, struct sock *nfnl,
tuple_set = true;
}
- for (i = 0; i < nf_ct_helper_hsize; i++) {
- hlist_for_each_entry_safe(cur, tmp, &nf_ct_helper_hash[i],
- hnode) {
- /* skip non-userspace conntrack helpers. */
- if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
- continue;
+ list_for_each_entry_safe(nlcth, n, &nfnl_cthelper_list, list) {
+ cur = &nlcth->helper;
+ j++;
- j++;
+ if (helper_name &&
+ strncmp(cur->name, helper_name, NF_CT_HELPER_NAME_LEN))
+ continue;
- if (helper_name && strncmp(cur->name, helper_name,
- NF_CT_HELPER_NAME_LEN) != 0) {
- continue;
- }
- if (tuple_set &&
- (tuple.src.l3num != cur->tuple.src.l3num ||
- tuple.dst.protonum != cur->tuple.dst.protonum))
- continue;
+ if (tuple_set &&
+ (tuple.src.l3num != cur->tuple.src.l3num ||
+ tuple.dst.protonum != cur->tuple.dst.protonum))
+ continue;
- found = true;
- nf_conntrack_helper_unregister(cur);
- }
+ found = true;
+ nf_conntrack_helper_unregister(cur);
+ kfree(cur->expect_policy);
+
+ list_del(&nlcth->list);
+ kfree(nlcth);
}
+
/* Make sure we return success if we flush and there is no helpers */
return (found || j == 0) ? 0 : -ENOENT;
}
@@ -662,20 +741,16 @@ static int __init nfnl_cthelper_init(void)
static void __exit nfnl_cthelper_exit(void)
{
struct nf_conntrack_helper *cur;
- struct hlist_node *tmp;
- int i;
+ struct nfnl_cthelper *nlcth, *n;
nfnetlink_subsys_unregister(&nfnl_cthelper_subsys);
- for (i=0; i<nf_ct_helper_hsize; i++) {
- hlist_for_each_entry_safe(cur, tmp, &nf_ct_helper_hash[i],
- hnode) {
- /* skip non-userspace conntrack helpers. */
- if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
- continue;
+ list_for_each_entry_safe(nlcth, n, &nfnl_cthelper_list, list) {
+ cur = &nlcth->helper;
- nf_conntrack_helper_unregister(cur);
- }
+ nf_conntrack_helper_unregister(cur);
+ kfree(cur->expect_policy);
+ kfree(nlcth);
}
}
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index 139e086..57c2cdf 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -138,7 +138,7 @@ static int cttimeout_new_timeout(struct net *net, struct sock *ctnl,
strcpy(timeout->name, nla_data(cda[CTA_TIMEOUT_NAME]));
timeout->l3num = l3num;
timeout->l4proto = l4proto;
- atomic_set(&timeout->refcnt, 1);
+ refcount_set(&timeout->refcnt, 1);
list_add_tail_rcu(&timeout->head, &net->nfct_timeout_list);
return 0;
@@ -172,7 +172,7 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
nla_put_be16(skb, CTA_TIMEOUT_L3PROTO, htons(timeout->l3num)) ||
nla_put_u8(skb, CTA_TIMEOUT_L4PROTO, timeout->l4proto->l4proto) ||
nla_put_be32(skb, CTA_TIMEOUT_USE,
- htonl(atomic_read(&timeout->refcnt))))
+ htonl(refcount_read(&timeout->refcnt))))
goto nla_put_failure;
if (likely(l4proto->ctnl_timeout.obj_to_nlattr)) {
@@ -339,7 +339,7 @@ static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout)
/* We want to avoid races with ctnl_timeout_put. So only when the
* current refcnt is 1, we decrease it to 0.
*/
- if (atomic_cmpxchg(&timeout->refcnt, 1, 0) == 1) {
+ if (refcount_dec_if_one(&timeout->refcnt)) {
/* We are protected by nfnl mutex. */
list_del_rcu(&timeout->head);
nf_ct_l4proto_put(timeout->l4proto);
@@ -536,7 +536,7 @@ ctnl_timeout_find_get(struct net *net, const char *name)
if (!try_module_get(THIS_MODULE))
goto err;
- if (!atomic_inc_not_zero(&timeout->refcnt)) {
+ if (!refcount_inc_not_zero(&timeout->refcnt)) {
module_put(THIS_MODULE);
goto err;
}
@@ -550,7 +550,7 @@ ctnl_timeout_find_get(struct net *net, const char *name)
static void ctnl_timeout_put(struct ctnl_timeout *timeout)
{
- if (atomic_dec_and_test(&timeout->refcnt))
+ if (refcount_dec_and_test(&timeout->refcnt))
kfree_rcu(timeout, rcu_head);
module_put(THIS_MODULE);
@@ -601,7 +601,7 @@ static void __net_exit cttimeout_net_exit(struct net *net)
list_del_rcu(&cur->head);
nf_ct_l4proto_put(cur->l4proto);
- if (atomic_dec_and_test(&cur->refcnt))
+ if (refcount_dec_and_test(&cur->refcnt))
kfree_rcu(cur, rcu_head);
}
}
@@ -646,8 +646,8 @@ static void __exit cttimeout_exit(void)
#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
RCU_INIT_POINTER(nf_ct_timeout_find_get_hook, NULL);
RCU_INIT_POINTER(nf_ct_timeout_put_hook, NULL);
+ synchronize_rcu();
#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
- rcu_barrier();
}
module_init(cttimeout_init);
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 08247bf..ecd857b 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -40,6 +40,8 @@
#include <net/netfilter/nfnetlink_log.h>
#include <linux/atomic.h>
+#include <linux/refcount.h>
+
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
#include "../bridge/br_private.h"
@@ -57,7 +59,7 @@
struct nfulnl_instance {
struct hlist_node hlist; /* global list of instances */
spinlock_t lock;
- atomic_t use; /* use count */
+ refcount_t use; /* use count */
unsigned int qlen; /* number of nlmsgs in skb */
struct sk_buff *skb; /* pre-allocatd skb */
@@ -115,7 +117,7 @@ __instance_lookup(struct nfnl_log_net *log, u_int16_t group_num)
static inline void
instance_get(struct nfulnl_instance *inst)
{
- atomic_inc(&inst->use);
+ refcount_inc(&inst->use);
}
static struct nfulnl_instance *
@@ -125,7 +127,7 @@ instance_lookup_get(struct nfnl_log_net *log, u_int16_t group_num)
rcu_read_lock_bh();
inst = __instance_lookup(log, group_num);
- if (inst && !atomic_inc_not_zero(&inst->use))
+ if (inst && !refcount_inc_not_zero(&inst->use))
inst = NULL;
rcu_read_unlock_bh();
@@ -145,7 +147,7 @@ static void nfulnl_instance_free_rcu(struct rcu_head *head)
static void
instance_put(struct nfulnl_instance *inst)
{
- if (inst && atomic_dec_and_test(&inst->use))
+ if (inst && refcount_dec_and_test(&inst->use))
call_rcu_bh(&inst->rcu, nfulnl_instance_free_rcu);
}
@@ -180,7 +182,7 @@ instance_create(struct net *net, u_int16_t group_num,
INIT_HLIST_NODE(&inst->hlist);
spin_lock_init(&inst->lock);
/* needs to be two, since we _put() after creation */
- atomic_set(&inst->use, 2);
+ refcount_set(&inst->use, 2);
setup_timer(&inst->timer, nfulnl_timer, (unsigned long)inst);
@@ -1031,7 +1033,7 @@ static int seq_show(struct seq_file *s, void *v)
inst->group_num,
inst->peer_portid, inst->qlen,
inst->copy_mode, inst->copy_range,
- inst->flushtimeout, atomic_read(&inst->use));
+ inst->flushtimeout, refcount_read(&inst->use));
return 0;
}
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 3ee0b8a..933509e 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -443,7 +443,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
skb = alloc_skb(size, GFP_ATOMIC);
if (!skb) {
skb_tx_error(entskb);
- return NULL;
+ goto nlmsg_failure;
}
nlh = nlmsg_put(skb, 0, 0,
@@ -452,7 +452,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
if (!nlh) {
skb_tx_error(entskb);
kfree_skb(skb);
- return NULL;
+ goto nlmsg_failure;
}
nfmsg = nlmsg_data(nlh);
nfmsg->nfgen_family = entry->state.pf;
@@ -598,12 +598,17 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
}
nlh->nlmsg_len = skb->len;
+ if (seclen)
+ security_release_secctx(secdata, seclen);
return skb;
nla_put_failure:
skb_tx_error(entskb);
kfree_skb(skb);
net_err_ratelimited("nf_queue: error creating packet message\n");
+nlmsg_failure:
+ if (seclen)
+ security_release_secctx(secdata, seclen);
return NULL;
}
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index c21e7eb..fab6bf3 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -230,10 +230,6 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
union nft_entry e = {};
int ret;
- ret = nft_compat_chain_validate_dependency(target->table, ctx->chain);
- if (ret < 0)
- goto err;
-
target_compat_from_user(target, nla_data(tb[NFTA_TARGET_INFO]), info);
if (ctx->nla[NFTA_RULE_COMPAT]) {
@@ -419,10 +415,6 @@ nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
union nft_entry e = {};
int ret;
- ret = nft_compat_chain_validate_dependency(match->table, ctx->chain);
- if (ret < 0)
- goto err;
-
match_compat_from_user(match, nla_data(tb[NFTA_MATCH_INFO]), info);
if (ctx->nla[NFTA_RULE_COMPAT]) {
diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c
index 7f84222..67a710e 100644
--- a/net/netfilter/nft_counter.c
+++ b/net/netfilter/nft_counter.c
@@ -82,7 +82,8 @@ static int nft_counter_do_init(const struct nlattr * const tb[],
return 0;
}
-static int nft_counter_obj_init(const struct nlattr * const tb[],
+static int nft_counter_obj_init(const struct nft_ctx *ctx,
+ const struct nlattr * const tb[],
struct nft_object *obj)
{
struct nft_counter_percpu_priv *priv = nft_obj_data(obj);
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index bf548a7..640fe5a 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -32,6 +32,12 @@ struct nft_ct {
};
};
+struct nft_ct_helper_obj {
+ struct nf_conntrack_helper *helper4;
+ struct nf_conntrack_helper *helper6;
+ u8 l4proto;
+};
+
#ifdef CONFIG_NF_CONNTRACK_ZONES
static DEFINE_PER_CPU(struct nf_conn *, nft_ct_pcpu_template);
static unsigned int nft_ct_pcpu_template_refcnt __read_mostly;
@@ -83,7 +89,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr,
switch (priv->key) {
case NFT_CT_DIRECTION:
- *dest = CTINFO2DIR(ctinfo);
+ nft_reg_store8(dest, CTINFO2DIR(ctinfo));
return;
case NFT_CT_STATUS:
*dest = ct->status;
@@ -151,20 +157,22 @@ static void nft_ct_get_eval(const struct nft_expr *expr,
return;
}
case NFT_CT_L3PROTOCOL:
- *dest = nf_ct_l3num(ct);
+ nft_reg_store8(dest, nf_ct_l3num(ct));
return;
case NFT_CT_PROTOCOL:
- *dest = nf_ct_protonum(ct);
+ nft_reg_store8(dest, nf_ct_protonum(ct));
return;
#ifdef CONFIG_NF_CONNTRACK_ZONES
case NFT_CT_ZONE: {
const struct nf_conntrack_zone *zone = nf_ct_zone(ct);
+ u16 zoneid;
if (priv->dir < IP_CT_DIR_MAX)
- *dest = nf_ct_zone_id(zone, priv->dir);
+ zoneid = nf_ct_zone_id(zone, priv->dir);
else
- *dest = zone->id;
+ zoneid = zone->id;
+ nft_reg_store16(dest, zoneid);
return;
}
#endif
@@ -183,10 +191,10 @@ static void nft_ct_get_eval(const struct nft_expr *expr,
nf_ct_l3num(ct) == NFPROTO_IPV4 ? 4 : 16);
return;
case NFT_CT_PROTO_SRC:
- *dest = (__force __u16)tuple->src.u.all;
+ nft_reg_store16(dest, (__force u16)tuple->src.u.all);
return;
case NFT_CT_PROTO_DST:
- *dest = (__force __u16)tuple->dst.u.all;
+ nft_reg_store16(dest, (__force u16)tuple->dst.u.all);
return;
default:
break;
@@ -205,7 +213,7 @@ static void nft_ct_set_zone_eval(const struct nft_expr *expr,
const struct nft_ct *priv = nft_expr_priv(expr);
struct sk_buff *skb = pkt->skb;
enum ip_conntrack_info ctinfo;
- u16 value = regs->data[priv->sreg];
+ u16 value = nft_reg_load16(®s->data[priv->sreg]);
struct nf_conn *ct;
ct = nf_ct_get(skb, &ctinfo);
@@ -542,7 +550,8 @@ static int nft_ct_set_init(const struct nft_ctx *ctx,
case IP_CT_DIR_REPLY:
break;
default:
- return -EINVAL;
+ err = -EINVAL;
+ goto err1;
}
}
@@ -730,6 +739,162 @@ static struct nft_expr_type nft_notrack_type __read_mostly = {
.owner = THIS_MODULE,
};
+static int nft_ct_helper_obj_init(const struct nft_ctx *ctx,
+ const struct nlattr * const tb[],
+ struct nft_object *obj)
+{
+ struct nft_ct_helper_obj *priv = nft_obj_data(obj);
+ struct nf_conntrack_helper *help4, *help6;
+ char name[NF_CT_HELPER_NAME_LEN];
+ int family = ctx->afi->family;
+
+ if (!tb[NFTA_CT_HELPER_NAME] || !tb[NFTA_CT_HELPER_L4PROTO])
+ return -EINVAL;
+
+ priv->l4proto = nla_get_u8(tb[NFTA_CT_HELPER_L4PROTO]);
+ if (!priv->l4proto)
+ return -ENOENT;
+
+ nla_strlcpy(name, tb[NFTA_CT_HELPER_NAME], sizeof(name));
+
+ if (tb[NFTA_CT_HELPER_L3PROTO])
+ family = ntohs(nla_get_be16(tb[NFTA_CT_HELPER_L3PROTO]));
+
+ help4 = NULL;
+ help6 = NULL;
+
+ switch (family) {
+ case NFPROTO_IPV4:
+ if (ctx->afi->family == NFPROTO_IPV6)
+ return -EINVAL;
+
+ help4 = nf_conntrack_helper_try_module_get(name, family,
+ priv->l4proto);
+ break;
+ case NFPROTO_IPV6:
+ if (ctx->afi->family == NFPROTO_IPV4)
+ return -EINVAL;
+
+ help6 = nf_conntrack_helper_try_module_get(name, family,
+ priv->l4proto);
+ break;
+ case NFPROTO_NETDEV: /* fallthrough */
+ case NFPROTO_BRIDGE: /* same */
+ case NFPROTO_INET:
+ help4 = nf_conntrack_helper_try_module_get(name, NFPROTO_IPV4,
+ priv->l4proto);
+ help6 = nf_conntrack_helper_try_module_get(name, NFPROTO_IPV6,
+ priv->l4proto);
+ break;
+ default:
+ return -EAFNOSUPPORT;
+ }
+
+ /* && is intentional; only error if INET found neither ipv4 or ipv6 */
+ if (!help4 && !help6)
+ return -ENOENT;
+
+ priv->helper4 = help4;
+ priv->helper6 = help6;
+
+ return 0;
+}
+
+static void nft_ct_helper_obj_destroy(struct nft_object *obj)
+{
+ struct nft_ct_helper_obj *priv = nft_obj_data(obj);
+
+ if (priv->helper4)
+ module_put(priv->helper4->me);
+ if (priv->helper6)
+ module_put(priv->helper6->me);
+}
+
+static void nft_ct_helper_obj_eval(struct nft_object *obj,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_ct_helper_obj *priv = nft_obj_data(obj);
+ struct nf_conn *ct = (struct nf_conn *)skb_nfct(pkt->skb);
+ struct nf_conntrack_helper *to_assign = NULL;
+ struct nf_conn_help *help;
+
+ if (!ct ||
+ nf_ct_is_confirmed(ct) ||
+ nf_ct_is_template(ct) ||
+ priv->l4proto != nf_ct_protonum(ct))
+ return;
+
+ switch (nf_ct_l3num(ct)) {
+ case NFPROTO_IPV4:
+ to_assign = priv->helper4;
+ break;
+ case NFPROTO_IPV6:
+ to_assign = priv->helper6;
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ return;
+ }
+
+ if (!to_assign)
+ return;
+
+ if (test_bit(IPS_HELPER_BIT, &ct->status))
+ return;
+
+ help = nf_ct_helper_ext_add(ct, to_assign, GFP_ATOMIC);
+ if (help) {
+ rcu_assign_pointer(help->helper, to_assign);
+ set_bit(IPS_HELPER_BIT, &ct->status);
+ }
+}
+
+static int nft_ct_helper_obj_dump(struct sk_buff *skb,
+ struct nft_object *obj, bool reset)
+{
+ const struct nft_ct_helper_obj *priv = nft_obj_data(obj);
+ const struct nf_conntrack_helper *helper = priv->helper4;
+ u16 family;
+
+ if (nla_put_string(skb, NFTA_CT_HELPER_NAME, helper->name))
+ return -1;
+
+ if (nla_put_u8(skb, NFTA_CT_HELPER_L4PROTO, priv->l4proto))
+ return -1;
+
+ if (priv->helper4 && priv->helper6)
+ family = NFPROTO_INET;
+ else if (priv->helper6)
+ family = NFPROTO_IPV6;
+ else
+ family = NFPROTO_IPV4;
+
+ if (nla_put_be16(skb, NFTA_CT_HELPER_L3PROTO, htons(family)))
+ return -1;
+
+ return 0;
+}
+
+static const struct nla_policy nft_ct_helper_policy[NFTA_CT_HELPER_MAX + 1] = {
+ [NFTA_CT_HELPER_NAME] = { .type = NLA_STRING,
+ .len = NF_CT_HELPER_NAME_LEN - 1 },
+ [NFTA_CT_HELPER_L3PROTO] = { .type = NLA_U16 },
+ [NFTA_CT_HELPER_L4PROTO] = { .type = NLA_U8 },
+};
+
+static struct nft_object_type nft_ct_helper_obj __read_mostly = {
+ .type = NFT_OBJECT_CT_HELPER,
+ .size = sizeof(struct nft_ct_helper_obj),
+ .maxattr = NFTA_CT_HELPER_MAX,
+ .policy = nft_ct_helper_policy,
+ .eval = nft_ct_helper_obj_eval,
+ .init = nft_ct_helper_obj_init,
+ .destroy = nft_ct_helper_obj_destroy,
+ .dump = nft_ct_helper_obj_dump,
+ .owner = THIS_MODULE,
+};
+
static int __init nft_ct_module_init(void)
{
int err;
@@ -744,7 +909,14 @@ static int __init nft_ct_module_init(void)
if (err < 0)
goto err1;
+ err = nft_register_obj(&nft_ct_helper_obj);
+ if (err < 0)
+ goto err2;
+
return 0;
+
+err2:
+ nft_unregister_expr(&nft_notrack_type);
err1:
nft_unregister_expr(&nft_ct_type);
return err;
@@ -752,6 +924,7 @@ static int __init nft_ct_module_init(void)
static void __exit nft_ct_module_exit(void)
{
+ nft_unregister_obj(&nft_ct_helper_obj);
nft_unregister_expr(&nft_notrack_type);
nft_unregister_expr(&nft_ct_type);
}
@@ -763,3 +936,4 @@ MODULE_LICENSE("GPL");
MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
MODULE_ALIAS_NFT_EXPR("ct");
MODULE_ALIAS_NFT_EXPR("notrack");
+MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_CT_HELPER);
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 049ad2d..3948da3 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -133,16 +133,10 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
priv->invert = true;
}
- set = nf_tables_set_lookup(ctx->table, tb[NFTA_DYNSET_SET_NAME],
- genmask);
- if (IS_ERR(set)) {
- if (tb[NFTA_DYNSET_SET_ID])
- set = nf_tables_set_lookup_byid(ctx->net,
- tb[NFTA_DYNSET_SET_ID],
- genmask);
- if (IS_ERR(set))
- return PTR_ERR(set);
- }
+ set = nft_set_lookup(ctx->net, ctx->table, tb[NFTA_DYNSET_SET_NAME],
+ tb[NFTA_DYNSET_SET_ID], genmask);
+ if (IS_ERR(set))
+ return PTR_ERR(set);
if (set->ops->update == NULL)
return -EOPNOTSUPP;
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index c308920..d212a85 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -98,14 +98,21 @@ static void nft_exthdr_tcp_eval(const struct nft_expr *expr,
goto err;
offset = i + priv->offset;
- dest[priv->len / NFT_REG32_SIZE] = 0;
- memcpy(dest, opt + offset, priv->len);
+ if (priv->flags & NFT_EXTHDR_F_PRESENT) {
+ *dest = 1;
+ } else {
+ dest[priv->len / NFT_REG32_SIZE] = 0;
+ memcpy(dest, opt + offset, priv->len);
+ }
return;
}
err:
- regs->verdict.code = NFT_BREAK;
+ if (priv->flags & NFT_EXTHDR_F_PRESENT)
+ *dest = 0;
+ else
+ regs->verdict.code = NFT_BREAK;
}
static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = {
diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c
index 29a4906..21df8cc 100644
--- a/net/netfilter/nft_fib.c
+++ b/net/netfilter/nft_fib.c
@@ -24,7 +24,8 @@ const struct nla_policy nft_fib_policy[NFTA_FIB_MAX + 1] = {
EXPORT_SYMBOL(nft_fib_policy);
#define NFTA_FIB_F_ALL (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR | \
- NFTA_FIB_F_MARK | NFTA_FIB_F_IIF | NFTA_FIB_F_OIF)
+ NFTA_FIB_F_MARK | NFTA_FIB_F_IIF | NFTA_FIB_F_OIF | \
+ NFTA_FIB_F_PRESENT)
int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
const struct nft_data **data)
@@ -112,7 +113,7 @@ int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
if (err < 0)
return err;
- return nft_fib_validate(ctx, expr, NULL);
+ return 0;
}
EXPORT_SYMBOL_GPL(nft_fib_init);
@@ -133,19 +134,22 @@ int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr)
}
EXPORT_SYMBOL_GPL(nft_fib_dump);
-void nft_fib_store_result(void *reg, enum nft_fib_result r,
+void nft_fib_store_result(void *reg, const struct nft_fib *priv,
const struct nft_pktinfo *pkt, int index)
{
struct net_device *dev;
u32 *dreg = reg;
- switch (r) {
+ switch (priv->result) {
case NFT_FIB_RESULT_OIF:
- *dreg = index;
+ *dreg = (priv->flags & NFTA_FIB_F_PRESENT) ? !!index : index;
break;
case NFT_FIB_RESULT_OIFNAME:
dev = dev_get_by_index_rcu(nft_net(pkt), index);
- strncpy(reg, dev ? dev->name : "", IFNAMSIZ);
+ if (priv->flags & NFTA_FIB_F_PRESENT)
+ *dreg = !!dev;
+ else
+ strncpy(reg, dev ? dev->name : "", IFNAMSIZ);
break;
default:
WARN_ON_ONCE(1);
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index eb2721a..a6a4633 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -17,7 +17,7 @@
#include <net/netfilter/nf_tables_core.h>
#include <linux/jhash.h>
-struct nft_hash {
+struct nft_jhash {
enum nft_registers sreg:8;
enum nft_registers dreg:8;
u8 len;
@@ -26,11 +26,11 @@ struct nft_hash {
u32 offset;
};
-static void nft_hash_eval(const struct nft_expr *expr,
- struct nft_regs *regs,
- const struct nft_pktinfo *pkt)
+static void nft_jhash_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
{
- struct nft_hash *priv = nft_expr_priv(expr);
+ struct nft_jhash *priv = nft_expr_priv(expr);
const void *data = ®s->data[priv->sreg];
u32 h;
@@ -38,6 +38,25 @@ static void nft_hash_eval(const struct nft_expr *expr,
regs->data[priv->dreg] = h + priv->offset;
}
+struct nft_symhash {
+ enum nft_registers dreg:8;
+ u32 modulus;
+ u32 offset;
+};
+
+static void nft_symhash_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ struct nft_symhash *priv = nft_expr_priv(expr);
+ struct sk_buff *skb = pkt->skb;
+ u32 h;
+
+ h = reciprocal_scale(__skb_get_hash_symmetric(skb), priv->modulus);
+
+ regs->data[priv->dreg] = h + priv->offset;
+}
+
static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = {
[NFTA_HASH_SREG] = { .type = NLA_U32 },
[NFTA_HASH_DREG] = { .type = NLA_U32 },
@@ -45,13 +64,14 @@ static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = {
[NFTA_HASH_MODULUS] = { .type = NLA_U32 },
[NFTA_HASH_SEED] = { .type = NLA_U32 },
[NFTA_HASH_OFFSET] = { .type = NLA_U32 },
+ [NFTA_HASH_TYPE] = { .type = NLA_U32 },
};
-static int nft_hash_init(const struct nft_ctx *ctx,
- const struct nft_expr *expr,
- const struct nlattr * const tb[])
+static int nft_jhash_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
{
- struct nft_hash *priv = nft_expr_priv(expr);
+ struct nft_jhash *priv = nft_expr_priv(expr);
u32 len;
int err;
@@ -92,10 +112,36 @@ static int nft_hash_init(const struct nft_ctx *ctx,
NFT_DATA_VALUE, sizeof(u32));
}
-static int nft_hash_dump(struct sk_buff *skb,
- const struct nft_expr *expr)
+static int nft_symhash_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
{
- const struct nft_hash *priv = nft_expr_priv(expr);
+ struct nft_symhash *priv = nft_expr_priv(expr);
+
+ if (!tb[NFTA_HASH_DREG] ||
+ !tb[NFTA_HASH_MODULUS])
+ return -EINVAL;
+
+ if (tb[NFTA_HASH_OFFSET])
+ priv->offset = ntohl(nla_get_be32(tb[NFTA_HASH_OFFSET]));
+
+ priv->dreg = nft_parse_register(tb[NFTA_HASH_DREG]);
+
+ priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS]));
+ if (priv->modulus <= 1)
+ return -ERANGE;
+
+ if (priv->offset + priv->modulus - 1 < priv->offset)
+ return -EOVERFLOW;
+
+ return nft_validate_register_store(ctx, priv->dreg, NULL,
+ NFT_DATA_VALUE, sizeof(u32));
+}
+
+static int nft_jhash_dump(struct sk_buff *skb,
+ const struct nft_expr *expr)
+{
+ const struct nft_jhash *priv = nft_expr_priv(expr);
if (nft_dump_register(skb, NFTA_HASH_SREG, priv->sreg))
goto nla_put_failure;
@@ -110,6 +156,28 @@ static int nft_hash_dump(struct sk_buff *skb,
if (priv->offset != 0)
if (nla_put_be32(skb, NFTA_HASH_OFFSET, htonl(priv->offset)))
goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_HASH_TYPE, htonl(NFT_HASH_JENKINS)))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static int nft_symhash_dump(struct sk_buff *skb,
+ const struct nft_expr *expr)
+{
+ const struct nft_symhash *priv = nft_expr_priv(expr);
+
+ if (nft_dump_register(skb, NFTA_HASH_DREG, priv->dreg))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_HASH_MODULUS, htonl(priv->modulus)))
+ goto nla_put_failure;
+ if (priv->offset != 0)
+ if (nla_put_be32(skb, NFTA_HASH_OFFSET, htonl(priv->offset)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_HASH_TYPE, htonl(NFT_HASH_SYM)))
+ goto nla_put_failure;
return 0;
nla_put_failure:
@@ -117,17 +185,46 @@ static int nft_hash_dump(struct sk_buff *skb,
}
static struct nft_expr_type nft_hash_type;
-static const struct nft_expr_ops nft_hash_ops = {
+static const struct nft_expr_ops nft_jhash_ops = {
.type = &nft_hash_type,
- .size = NFT_EXPR_SIZE(sizeof(struct nft_hash)),
- .eval = nft_hash_eval,
- .init = nft_hash_init,
- .dump = nft_hash_dump,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_jhash)),
+ .eval = nft_jhash_eval,
+ .init = nft_jhash_init,
+ .dump = nft_jhash_dump,
};
+static const struct nft_expr_ops nft_symhash_ops = {
+ .type = &nft_hash_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_symhash)),
+ .eval = nft_symhash_eval,
+ .init = nft_symhash_init,
+ .dump = nft_symhash_dump,
+};
+
+static const struct nft_expr_ops *
+nft_hash_select_ops(const struct nft_ctx *ctx,
+ const struct nlattr * const tb[])
+{
+ u32 type;
+
+ if (!tb[NFTA_HASH_TYPE])
+ return &nft_jhash_ops;
+
+ type = ntohl(nla_get_be32(tb[NFTA_HASH_TYPE]));
+ switch (type) {
+ case NFT_HASH_SYM:
+ return &nft_symhash_ops;
+ case NFT_HASH_JENKINS:
+ return &nft_jhash_ops;
+ default:
+ break;
+ }
+ return ERR_PTR(-EOPNOTSUPP);
+}
+
static struct nft_expr_type nft_hash_type __read_mostly = {
.name = "hash",
- .ops = &nft_hash_ops,
+ .select_ops = &nft_hash_select_ops,
.policy = nft_hash_policy,
.maxattr = NFTA_HASH_MAX,
.owner = THIS_MODULE,
diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c
index c6baf41..18dd57a 100644
--- a/net/netfilter/nft_limit.c
+++ b/net/netfilter/nft_limit.c
@@ -17,9 +17,8 @@
#include <linux/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables.h>
-static DEFINE_SPINLOCK(limit_lock);
-
struct nft_limit {
+ spinlock_t lock;
u64 last;
u64 tokens;
u64 tokens_max;
@@ -34,7 +33,7 @@ static inline bool nft_limit_eval(struct nft_limit *limit, u64 cost)
u64 now, tokens;
s64 delta;
- spin_lock_bh(&limit_lock);
+ spin_lock_bh(&limit->lock);
now = ktime_get_ns();
tokens = limit->tokens + now - limit->last;
if (tokens > limit->tokens_max)
@@ -44,11 +43,11 @@ static inline bool nft_limit_eval(struct nft_limit *limit, u64 cost)
delta = tokens - cost;
if (delta >= 0) {
limit->tokens = delta;
- spin_unlock_bh(&limit_lock);
+ spin_unlock_bh(&limit->lock);
return limit->invert;
}
limit->tokens = tokens;
- spin_unlock_bh(&limit_lock);
+ spin_unlock_bh(&limit->lock);
return !limit->invert;
}
@@ -86,6 +85,7 @@ static int nft_limit_init(struct nft_limit *limit,
limit->invert = true;
}
limit->last = ktime_get_ns();
+ spin_lock_init(&limit->lock);
return 0;
}
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index e21aea7..475570e 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -71,16 +71,10 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
tb[NFTA_LOOKUP_SREG] == NULL)
return -EINVAL;
- set = nf_tables_set_lookup(ctx->table, tb[NFTA_LOOKUP_SET], genmask);
- if (IS_ERR(set)) {
- if (tb[NFTA_LOOKUP_SET_ID]) {
- set = nf_tables_set_lookup_byid(ctx->net,
- tb[NFTA_LOOKUP_SET_ID],
- genmask);
- }
- if (IS_ERR(set))
- return PTR_ERR(set);
- }
+ set = nft_set_lookup(ctx->net, ctx->table, tb[NFTA_LOOKUP_SET],
+ tb[NFTA_LOOKUP_SET_ID], genmask);
+ if (IS_ERR(set))
+ return PTR_ERR(set);
if (set->flags & NFT_SET_EVAL)
return -EOPNOTSUPP;
diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c
index 11ce016..6ac03d4 100644
--- a/net/netfilter/nft_masq.c
+++ b/net/netfilter/nft_masq.c
@@ -46,10 +46,6 @@ int nft_masq_init(const struct nft_ctx *ctx,
struct nft_masq *priv = nft_expr_priv(expr);
int err;
- err = nft_masq_validate(ctx, expr, NULL);
- if (err)
- return err;
-
if (tb[NFTA_MASQ_FLAGS]) {
priv->flags = ntohl(nla_get_be32(tb[NFTA_MASQ_FLAGS]));
if (priv->flags & ~NF_NAT_RANGE_MASK)
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index e1f5ca9..9563ce3 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -45,16 +45,15 @@ void nft_meta_get_eval(const struct nft_expr *expr,
*dest = skb->len;
break;
case NFT_META_PROTOCOL:
- *dest = 0;
- *(__be16 *)dest = skb->protocol;
+ nft_reg_store16(dest, (__force u16)skb->protocol);
break;
case NFT_META_NFPROTO:
- *dest = nft_pf(pkt);
+ nft_reg_store8(dest, nft_pf(pkt));
break;
case NFT_META_L4PROTO:
if (!pkt->tprot_set)
goto err;
- *dest = pkt->tprot;
+ nft_reg_store8(dest, pkt->tprot);
break;
case NFT_META_PRIORITY:
*dest = skb->priority;
@@ -85,14 +84,12 @@ void nft_meta_get_eval(const struct nft_expr *expr,
case NFT_META_IIFTYPE:
if (in == NULL)
goto err;
- *dest = 0;
- *(u16 *)dest = in->type;
+ nft_reg_store16(dest, in->type);
break;
case NFT_META_OIFTYPE:
if (out == NULL)
goto err;
- *dest = 0;
- *(u16 *)dest = out->type;
+ nft_reg_store16(dest, out->type);
break;
case NFT_META_SKUID:
sk = skb_to_full_sk(skb);
@@ -142,19 +139,19 @@ void nft_meta_get_eval(const struct nft_expr *expr,
#endif
case NFT_META_PKTTYPE:
if (skb->pkt_type != PACKET_LOOPBACK) {
- *dest = skb->pkt_type;
+ nft_reg_store8(dest, skb->pkt_type);
break;
}
switch (nft_pf(pkt)) {
case NFPROTO_IPV4:
if (ipv4_is_multicast(ip_hdr(skb)->daddr))
- *dest = PACKET_MULTICAST;
+ nft_reg_store8(dest, PACKET_MULTICAST);
else
- *dest = PACKET_BROADCAST;
+ nft_reg_store8(dest, PACKET_BROADCAST);
break;
case NFPROTO_IPV6:
- *dest = PACKET_MULTICAST;
+ nft_reg_store8(dest, PACKET_MULTICAST);
break;
case NFPROTO_NETDEV:
switch (skb->protocol) {
@@ -168,14 +165,14 @@ void nft_meta_get_eval(const struct nft_expr *expr,
goto err;
if (ipv4_is_multicast(iph->daddr))
- *dest = PACKET_MULTICAST;
+ nft_reg_store8(dest, PACKET_MULTICAST);
else
- *dest = PACKET_BROADCAST;
+ nft_reg_store8(dest, PACKET_BROADCAST);
break;
}
case htons(ETH_P_IPV6):
- *dest = PACKET_MULTICAST;
+ nft_reg_store8(dest, PACKET_MULTICAST);
break;
default:
WARN_ON_ONCE(1);
@@ -230,7 +227,9 @@ void nft_meta_set_eval(const struct nft_expr *expr,
{
const struct nft_meta *meta = nft_expr_priv(expr);
struct sk_buff *skb = pkt->skb;
- u32 value = regs->data[meta->sreg];
+ u32 *sreg = ®s->data[meta->sreg];
+ u32 value = *sreg;
+ u8 pkt_type;
switch (meta->key) {
case NFT_META_MARK:
@@ -240,9 +239,12 @@ void nft_meta_set_eval(const struct nft_expr *expr,
skb->priority = value;
break;
case NFT_META_PKTTYPE:
- if (skb->pkt_type != value &&
- skb_pkt_type_ok(value) && skb_pkt_type_ok(skb->pkt_type))
- skb->pkt_type = value;
+ pkt_type = nft_reg_load8(sreg);
+
+ if (skb->pkt_type != pkt_type &&
+ skb_pkt_type_ok(pkt_type) &&
+ skb_pkt_type_ok(skb->pkt_type))
+ skb->pkt_type = pkt_type;
break;
case NFT_META_NFTRACE:
skb->nf_trace = !!value;
@@ -370,10 +372,6 @@ int nft_meta_set_init(const struct nft_ctx *ctx,
return -EOPNOTSUPP;
}
- err = nft_meta_set_validate(ctx, expr, NULL);
- if (err < 0)
- return err;
-
priv->sreg = nft_parse_register(tb[NFTA_META_SREG]);
err = nft_validate_register_load(priv->sreg, len);
if (err < 0)
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index 19a7bf3..ed548d0 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -65,10 +65,10 @@ static void nft_nat_eval(const struct nft_expr *expr,
}
if (priv->sreg_proto_min) {
- range.min_proto.all =
- *(__be16 *)®s->data[priv->sreg_proto_min];
- range.max_proto.all =
- *(__be16 *)®s->data[priv->sreg_proto_max];
+ range.min_proto.all = (__force __be16)nft_reg_load16(
+ ®s->data[priv->sreg_proto_min]);
+ range.max_proto.all = (__force __be16)nft_reg_load16(
+ ®s->data[priv->sreg_proto_max]);
range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
}
@@ -138,10 +138,6 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
return -EINVAL;
}
- err = nft_nat_validate(ctx, expr, NULL);
- if (err < 0)
- return err;
-
if (tb[NFTA_NAT_FAMILY] == NULL)
return -EINVAL;
diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c
index 1ae8c49..1dd428f 100644
--- a/net/netfilter/nft_objref.c
+++ b/net/netfilter/nft_objref.c
@@ -116,16 +116,10 @@ static int nft_objref_map_init(const struct nft_ctx *ctx,
struct nft_set *set;
int err;
- set = nf_tables_set_lookup(ctx->table, tb[NFTA_OBJREF_SET_NAME], genmask);
- if (IS_ERR(set)) {
- if (tb[NFTA_OBJREF_SET_ID]) {
- set = nf_tables_set_lookup_byid(ctx->net,
- tb[NFTA_OBJREF_SET_ID],
- genmask);
- }
- if (IS_ERR(set))
- return PTR_ERR(set);
- }
+ set = nft_set_lookup(ctx->net, ctx->table, tb[NFTA_OBJREF_SET_NAME],
+ tb[NFTA_OBJREF_SET_ID], genmask);
+ if (IS_ERR(set))
+ return PTR_ERR(set);
if (!(set->flags & NFT_SET_OBJECT))
return -EINVAL;
diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c
index 2d6fe35..25e3315 100644
--- a/net/netfilter/nft_quota.c
+++ b/net/netfilter/nft_quota.c
@@ -99,7 +99,8 @@ static int nft_quota_do_init(const struct nlattr * const tb[],
return 0;
}
-static int nft_quota_obj_init(const struct nlattr * const tb[],
+static int nft_quota_obj_init(const struct nft_ctx *ctx,
+ const struct nlattr * const tb[],
struct nft_object *obj)
{
struct nft_quota *priv = nft_obj_data(obj);
diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c
index 40dcd05..1e66538 100644
--- a/net/netfilter/nft_redir.c
+++ b/net/netfilter/nft_redir.c
@@ -47,10 +47,6 @@ int nft_redir_init(const struct nft_ctx *ctx,
unsigned int plen;
int err;
- err = nft_redir_validate(ctx, expr, NULL);
- if (err < 0)
- return err;
-
plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all);
if (tb[NFTA_REDIR_REG_PROTO_MIN]) {
priv->sreg_proto_min =
diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c
index c64de3f7..29f5bd2 100644
--- a/net/netfilter/nft_reject.c
+++ b/net/netfilter/nft_reject.c
@@ -42,11 +42,6 @@ int nft_reject_init(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
{
struct nft_reject *priv = nft_expr_priv(expr);
- int err;
-
- err = nft_reject_validate(ctx, expr, NULL);
- if (err < 0)
- return err;
if (tb[NFTA_REJECT_TYPE] == NULL)
return -EINVAL;
diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c
index 9e90a02..5a7fb5f 100644
--- a/net/netfilter/nft_reject_inet.c
+++ b/net/netfilter/nft_reject_inet.c
@@ -66,11 +66,7 @@ static int nft_reject_inet_init(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
{
struct nft_reject *priv = nft_expr_priv(expr);
- int icmp_code, err;
-
- err = nft_reject_validate(ctx, expr, NULL);
- if (err < 0)
- return err;
+ int icmp_code;
if (tb[NFTA_REJECT_TYPE] == NULL)
return -EINVAL;
diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c
index 152d226..8ebbc29 100644
--- a/net/netfilter/nft_set_bitmap.c
+++ b/net/netfilter/nft_set_bitmap.c
@@ -15,6 +15,11 @@
#include <linux/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables.h>
+struct nft_bitmap_elem {
+ struct list_head head;
+ struct nft_set_ext ext;
+};
+
/* This bitmap uses two bits to represent one element. These two bits determine
* the element state in the current and the future generation.
*
@@ -41,13 +46,22 @@
* restore its previous state.
*/
struct nft_bitmap {
- u16 bitmap_size;
- u8 bitmap[];
+ struct list_head list;
+ u16 bitmap_size;
+ u8 bitmap[];
};
-static inline void nft_bitmap_location(u32 key, u32 *idx, u32 *off)
+static inline void nft_bitmap_location(const struct nft_set *set,
+ const void *key,
+ u32 *idx, u32 *off)
{
- u32 k = (key << 1);
+ u32 k;
+
+ if (set->klen == 2)
+ k = *(u16 *)key;
+ else
+ k = *(u8 *)key;
+ k <<= 1;
*idx = k / BITS_PER_BYTE;
*off = k % BITS_PER_BYTE;
@@ -69,26 +83,48 @@ static bool nft_bitmap_lookup(const struct net *net, const struct nft_set *set,
u8 genmask = nft_genmask_cur(net);
u32 idx, off;
- nft_bitmap_location(*key, &idx, &off);
+ nft_bitmap_location(set, key, &idx, &off);
return nft_bitmap_active(priv->bitmap, idx, off, genmask);
}
+static struct nft_bitmap_elem *
+nft_bitmap_elem_find(const struct nft_set *set, struct nft_bitmap_elem *this,
+ u8 genmask)
+{
+ const struct nft_bitmap *priv = nft_set_priv(set);
+ struct nft_bitmap_elem *be;
+
+ list_for_each_entry_rcu(be, &priv->list, head) {
+ if (memcmp(nft_set_ext_key(&be->ext),
+ nft_set_ext_key(&this->ext), set->klen) ||
+ !nft_set_elem_active(&be->ext, genmask))
+ continue;
+
+ return be;
+ }
+ return NULL;
+}
+
static int nft_bitmap_insert(const struct net *net, const struct nft_set *set,
const struct nft_set_elem *elem,
- struct nft_set_ext **_ext)
+ struct nft_set_ext **ext)
{
struct nft_bitmap *priv = nft_set_priv(set);
- struct nft_set_ext *ext = elem->priv;
+ struct nft_bitmap_elem *new = elem->priv, *be;
u8 genmask = nft_genmask_next(net);
u32 idx, off;
- nft_bitmap_location(nft_set_ext_key(ext)->data[0], &idx, &off);
- if (nft_bitmap_active(priv->bitmap, idx, off, genmask))
+ be = nft_bitmap_elem_find(set, new, genmask);
+ if (be) {
+ *ext = &be->ext;
return -EEXIST;
+ }
+ nft_bitmap_location(set, nft_set_ext_key(&new->ext), &idx, &off);
/* Enter 01 state. */
priv->bitmap[idx] |= (genmask << off);
+ list_add_tail_rcu(&new->head, &priv->list);
return 0;
}
@@ -98,13 +134,14 @@ static void nft_bitmap_remove(const struct net *net,
const struct nft_set_elem *elem)
{
struct nft_bitmap *priv = nft_set_priv(set);
- struct nft_set_ext *ext = elem->priv;
+ struct nft_bitmap_elem *be = elem->priv;
u8 genmask = nft_genmask_next(net);
u32 idx, off;
- nft_bitmap_location(nft_set_ext_key(ext)->data[0], &idx, &off);
+ nft_bitmap_location(set, nft_set_ext_key(&be->ext), &idx, &off);
/* Enter 00 state. */
priv->bitmap[idx] &= ~(genmask << off);
+ list_del_rcu(&be->head);
}
static void nft_bitmap_activate(const struct net *net,
@@ -112,74 +149,52 @@ static void nft_bitmap_activate(const struct net *net,
const struct nft_set_elem *elem)
{
struct nft_bitmap *priv = nft_set_priv(set);
- struct nft_set_ext *ext = elem->priv;
+ struct nft_bitmap_elem *be = elem->priv;
u8 genmask = nft_genmask_next(net);
u32 idx, off;
- nft_bitmap_location(nft_set_ext_key(ext)->data[0], &idx, &off);
+ nft_bitmap_location(set, nft_set_ext_key(&be->ext), &idx, &off);
/* Enter 11 state. */
priv->bitmap[idx] |= (genmask << off);
+ nft_set_elem_change_active(net, set, &be->ext);
}
static bool nft_bitmap_flush(const struct net *net,
- const struct nft_set *set, void *ext)
+ const struct nft_set *set, void *_be)
{
struct nft_bitmap *priv = nft_set_priv(set);
u8 genmask = nft_genmask_next(net);
+ struct nft_bitmap_elem *be = _be;
u32 idx, off;
- nft_bitmap_location(nft_set_ext_key(ext)->data[0], &idx, &off);
+ nft_bitmap_location(set, nft_set_ext_key(&be->ext), &idx, &off);
/* Enter 10 state, similar to deactivation. */
priv->bitmap[idx] &= ~(genmask << off);
+ nft_set_elem_change_active(net, set, &be->ext);
return true;
}
-static struct nft_set_ext *nft_bitmap_ext_alloc(const struct nft_set *set,
- const struct nft_set_elem *elem)
-{
- struct nft_set_ext_tmpl tmpl;
- struct nft_set_ext *ext;
-
- nft_set_ext_prepare(&tmpl);
- nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen);
-
- ext = kzalloc(tmpl.len, GFP_KERNEL);
- if (!ext)
- return NULL;
-
- nft_set_ext_init(ext, &tmpl);
- memcpy(nft_set_ext_key(ext), elem->key.val.data, set->klen);
-
- return ext;
-}
-
static void *nft_bitmap_deactivate(const struct net *net,
const struct nft_set *set,
const struct nft_set_elem *elem)
{
struct nft_bitmap *priv = nft_set_priv(set);
+ struct nft_bitmap_elem *this = elem->priv, *be;
u8 genmask = nft_genmask_next(net);
- struct nft_set_ext *ext;
- u32 idx, off, key = 0;
+ u32 idx, off;
- memcpy(&key, elem->key.val.data, set->klen);
- nft_bitmap_location(key, &idx, &off);
+ nft_bitmap_location(set, elem->key.val.data, &idx, &off);
- if (!nft_bitmap_active(priv->bitmap, idx, off, genmask))
- return NULL;
-
- /* We have no real set extension since this is a bitmap, allocate this
- * dummy object that is released from the commit/abort path.
- */
- ext = nft_bitmap_ext_alloc(set, elem);
- if (!ext)
+ be = nft_bitmap_elem_find(set, this, genmask);
+ if (!be)
return NULL;
/* Enter 10 state. */
priv->bitmap[idx] &= ~(genmask << off);
+ nft_set_elem_change_active(net, set, &be->ext);
- return ext;
+ return be;
}
static void nft_bitmap_walk(const struct nft_ctx *ctx,
@@ -187,47 +202,23 @@ static void nft_bitmap_walk(const struct nft_ctx *ctx,
struct nft_set_iter *iter)
{
const struct nft_bitmap *priv = nft_set_priv(set);
- struct nft_set_ext_tmpl tmpl;
+ struct nft_bitmap_elem *be;
struct nft_set_elem elem;
- struct nft_set_ext *ext;
- int idx, off;
- u16 key;
- nft_set_ext_prepare(&tmpl);
- nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen);
+ list_for_each_entry_rcu(be, &priv->list, head) {
+ if (iter->count < iter->skip)
+ goto cont;
+ if (!nft_set_elem_active(&be->ext, iter->genmask))
+ goto cont;
- for (idx = 0; idx < priv->bitmap_size; idx++) {
- for (off = 0; off < BITS_PER_BYTE; off += 2) {
- if (iter->count < iter->skip)
- goto cont;
+ elem.priv = be;
- if (!nft_bitmap_active(priv->bitmap, idx, off,
- iter->genmask))
- goto cont;
+ iter->err = iter->fn(ctx, set, iter, &elem);
- ext = kzalloc(tmpl.len, GFP_KERNEL);
- if (!ext) {
- iter->err = -ENOMEM;
- return;
- }
- nft_set_ext_init(ext, &tmpl);
- key = ((idx * BITS_PER_BYTE) + off) >> 1;
- memcpy(nft_set_ext_key(ext), &key, set->klen);
-
- elem.priv = ext;
- iter->err = iter->fn(ctx, set, iter, &elem);
-
- /* On set flush, this dummy extension object is released
- * from the commit/abort path.
- */
- if (!iter->flush)
- kfree(ext);
-
- if (iter->err < 0)
- return;
+ if (iter->err < 0)
+ return;
cont:
- iter->count++;
- }
+ iter->count++;
}
}
@@ -258,6 +249,7 @@ static int nft_bitmap_init(const struct nft_set *set,
{
struct nft_bitmap *priv = nft_set_priv(set);
+ INIT_LIST_HEAD(&priv->list);
priv->bitmap_size = nft_bitmap_size(set->klen);
return 0;
@@ -283,6 +275,7 @@ static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features,
static struct nft_set_ops nft_bitmap_ops __read_mostly = {
.privsize = nft_bitmap_privsize,
+ .elemsize = offsetof(struct nft_bitmap_elem, ext),
.estimate = nft_bitmap_estimate,
.init = nft_bitmap_init,
.destroy = nft_bitmap_destroy,
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 78dfbf9..e97e2fb 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -18,9 +18,8 @@
#include <linux/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables.h>
-static DEFINE_SPINLOCK(nft_rbtree_lock);
-
struct nft_rbtree {
+ rwlock_t lock;
struct rb_root root;
};
@@ -44,14 +43,14 @@ static bool nft_rbtree_equal(const struct nft_set *set, const void *this,
static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
const u32 *key, const struct nft_set_ext **ext)
{
- const struct nft_rbtree *priv = nft_set_priv(set);
+ struct nft_rbtree *priv = nft_set_priv(set);
const struct nft_rbtree_elem *rbe, *interval = NULL;
u8 genmask = nft_genmask_cur(net);
const struct rb_node *parent;
const void *this;
int d;
- spin_lock_bh(&nft_rbtree_lock);
+ read_lock_bh(&priv->lock);
parent = priv->root.rb_node;
while (parent != NULL) {
rbe = rb_entry(parent, struct nft_rbtree_elem, node);
@@ -75,7 +74,7 @@ static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
}
if (nft_rbtree_interval_end(rbe))
goto out;
- spin_unlock_bh(&nft_rbtree_lock);
+ read_unlock_bh(&priv->lock);
*ext = &rbe->ext;
return true;
@@ -85,12 +84,12 @@ static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
if (set->flags & NFT_SET_INTERVAL && interval != NULL &&
nft_set_elem_active(&interval->ext, genmask) &&
!nft_rbtree_interval_end(interval)) {
- spin_unlock_bh(&nft_rbtree_lock);
+ read_unlock_bh(&priv->lock);
*ext = &interval->ext;
return true;
}
out:
- spin_unlock_bh(&nft_rbtree_lock);
+ read_unlock_bh(&priv->lock);
return false;
}
@@ -140,12 +139,13 @@ static int nft_rbtree_insert(const struct net *net, const struct nft_set *set,
const struct nft_set_elem *elem,
struct nft_set_ext **ext)
{
+ struct nft_rbtree *priv = nft_set_priv(set);
struct nft_rbtree_elem *rbe = elem->priv;
int err;
- spin_lock_bh(&nft_rbtree_lock);
+ write_lock_bh(&priv->lock);
err = __nft_rbtree_insert(net, set, rbe, ext);
- spin_unlock_bh(&nft_rbtree_lock);
+ write_unlock_bh(&priv->lock);
return err;
}
@@ -157,9 +157,9 @@ static void nft_rbtree_remove(const struct net *net,
struct nft_rbtree *priv = nft_set_priv(set);
struct nft_rbtree_elem *rbe = elem->priv;
- spin_lock_bh(&nft_rbtree_lock);
+ write_lock_bh(&priv->lock);
rb_erase(&rbe->node, &priv->root);
- spin_unlock_bh(&nft_rbtree_lock);
+ write_unlock_bh(&priv->lock);
}
static void nft_rbtree_activate(const struct net *net,
@@ -224,12 +224,12 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
struct nft_set *set,
struct nft_set_iter *iter)
{
- const struct nft_rbtree *priv = nft_set_priv(set);
+ struct nft_rbtree *priv = nft_set_priv(set);
struct nft_rbtree_elem *rbe;
struct nft_set_elem elem;
struct rb_node *node;
- spin_lock_bh(&nft_rbtree_lock);
+ read_lock_bh(&priv->lock);
for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) {
rbe = rb_entry(node, struct nft_rbtree_elem, node);
@@ -242,13 +242,13 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
iter->err = iter->fn(ctx, set, iter, &elem);
if (iter->err < 0) {
- spin_unlock_bh(&nft_rbtree_lock);
+ read_unlock_bh(&priv->lock);
return;
}
cont:
iter->count++;
}
- spin_unlock_bh(&nft_rbtree_lock);
+ read_unlock_bh(&priv->lock);
}
static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[])
@@ -262,6 +262,7 @@ static int nft_rbtree_init(const struct nft_set *set,
{
struct nft_rbtree *priv = nft_set_priv(set);
+ rwlock_init(&priv->lock);
priv->root = RB_ROOT;
return 0;
}
diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c
index dab962d..d27b5f1 100644
--- a/net/netfilter/xt_limit.c
+++ b/net/netfilter/xt_limit.c
@@ -18,6 +18,7 @@
#include <linux/netfilter/xt_limit.h>
struct xt_limit_priv {
+ spinlock_t lock;
unsigned long prev;
uint32_t credit;
};
@@ -32,8 +33,6 @@ MODULE_ALIAS("ip6t_limit");
* see net/sched/sch_tbf.c in the linux source tree
*/
-static DEFINE_SPINLOCK(limit_lock);
-
/* Rusty: This is my (non-mathematically-inclined) understanding of
this algorithm. The `average rate' in jiffies becomes your initial
amount of credit `credit' and the most credit you can ever have
@@ -72,7 +71,7 @@ limit_mt(const struct sk_buff *skb, struct xt_action_param *par)
struct xt_limit_priv *priv = r->master;
unsigned long now = jiffies;
- spin_lock_bh(&limit_lock);
+ spin_lock_bh(&priv->lock);
priv->credit += (now - xchg(&priv->prev, now)) * CREDITS_PER_JIFFY;
if (priv->credit > r->credit_cap)
priv->credit = r->credit_cap;
@@ -80,11 +79,11 @@ limit_mt(const struct sk_buff *skb, struct xt_action_param *par)
if (priv->credit >= r->cost) {
/* We're not limited. */
priv->credit -= r->cost;
- spin_unlock_bh(&limit_lock);
+ spin_unlock_bh(&priv->lock);
return true;
}
- spin_unlock_bh(&limit_lock);
+ spin_unlock_bh(&priv->lock);
return false;
}
@@ -126,6 +125,8 @@ static int limit_mt_check(const struct xt_mtchk_param *par)
r->credit_cap = priv->credit; /* Credits full. */
r->cost = user2credits(r->avg);
}
+ spin_lock_init(&priv->lock);
+
return 0;
}
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 7b73c7c..fc23244 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -78,14 +78,6 @@ struct listeners {
/* state bits */
#define NETLINK_S_CONGESTED 0x0
-/* flags */
-#define NETLINK_F_KERNEL_SOCKET 0x1
-#define NETLINK_F_RECV_PKTINFO 0x2
-#define NETLINK_F_BROADCAST_SEND_ERROR 0x4
-#define NETLINK_F_RECV_NO_ENOBUFS 0x8
-#define NETLINK_F_LISTEN_ALL_NSID 0x10
-#define NETLINK_F_CAP_ACK 0x20
-
static inline int netlink_is_kernel(struct sock *sk)
{
return nlk_sk(sk)->flags & NETLINK_F_KERNEL_SOCKET;
@@ -96,6 +88,44 @@ EXPORT_SYMBOL_GPL(nl_table);
static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait);
+static struct lock_class_key nlk_cb_mutex_keys[MAX_LINKS];
+
+static const char *const nlk_cb_mutex_key_strings[MAX_LINKS + 1] = {
+ "nlk_cb_mutex-ROUTE",
+ "nlk_cb_mutex-1",
+ "nlk_cb_mutex-USERSOCK",
+ "nlk_cb_mutex-FIREWALL",
+ "nlk_cb_mutex-SOCK_DIAG",
+ "nlk_cb_mutex-NFLOG",
+ "nlk_cb_mutex-XFRM",
+ "nlk_cb_mutex-SELINUX",
+ "nlk_cb_mutex-ISCSI",
+ "nlk_cb_mutex-AUDIT",
+ "nlk_cb_mutex-FIB_LOOKUP",
+ "nlk_cb_mutex-CONNECTOR",
+ "nlk_cb_mutex-NETFILTER",
+ "nlk_cb_mutex-IP6_FW",
+ "nlk_cb_mutex-DNRTMSG",
+ "nlk_cb_mutex-KOBJECT_UEVENT",
+ "nlk_cb_mutex-GENERIC",
+ "nlk_cb_mutex-17",
+ "nlk_cb_mutex-SCSITRANSPORT",
+ "nlk_cb_mutex-ECRYPTFS",
+ "nlk_cb_mutex-RDMA",
+ "nlk_cb_mutex-CRYPTO",
+ "nlk_cb_mutex-SMC",
+ "nlk_cb_mutex-23",
+ "nlk_cb_mutex-24",
+ "nlk_cb_mutex-25",
+ "nlk_cb_mutex-26",
+ "nlk_cb_mutex-27",
+ "nlk_cb_mutex-28",
+ "nlk_cb_mutex-29",
+ "nlk_cb_mutex-30",
+ "nlk_cb_mutex-31",
+ "nlk_cb_mutex-MAX_LINKS"
+};
+
static int netlink_dump(struct sock *sk);
static void netlink_skb_destructor(struct sk_buff *skb);
@@ -585,6 +615,9 @@ static int __netlink_create(struct net *net, struct socket *sock,
} else {
nlk->cb_mutex = &nlk->cb_def_mutex;
mutex_init(nlk->cb_mutex);
+ lockdep_set_class_and_name(nlk->cb_mutex,
+ nlk_cb_mutex_keys + protocol,
+ nlk_cb_mutex_key_strings[protocol]);
}
init_waitqueue_head(&nlk->wait);
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index 4fdb383..f792f8d 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -6,6 +6,14 @@
#include <linux/workqueue.h>
#include <net/sock.h>
+/* flags */
+#define NETLINK_F_KERNEL_SOCKET 0x1
+#define NETLINK_F_RECV_PKTINFO 0x2
+#define NETLINK_F_BROADCAST_SEND_ERROR 0x4
+#define NETLINK_F_RECV_NO_ENOBUFS 0x8
+#define NETLINK_F_LISTEN_ALL_NSID 0x10
+#define NETLINK_F_CAP_ACK 0x20
+
#define NLGRPSZ(x) (ALIGN(x, sizeof(unsigned long) * 8) / 8)
#define NLGRPLONGS(x) (NLGRPSZ(x)/sizeof(unsigned long))
diff --git a/net/netlink/diag.c b/net/netlink/diag.c
index a554624..8faa20b 100644
--- a/net/netlink/diag.c
+++ b/net/netlink/diag.c
@@ -19,6 +19,27 @@ static int sk_diag_dump_groups(struct sock *sk, struct sk_buff *nlskb)
nlk->groups);
}
+static int sk_diag_put_flags(struct sock *sk, struct sk_buff *skb)
+{
+ struct netlink_sock *nlk = nlk_sk(sk);
+ u32 flags = 0;
+
+ if (nlk->cb_running)
+ flags |= NDIAG_FLAG_CB_RUNNING;
+ if (nlk->flags & NETLINK_F_RECV_PKTINFO)
+ flags |= NDIAG_FLAG_PKTINFO;
+ if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR)
+ flags |= NDIAG_FLAG_BROADCAST_ERROR;
+ if (nlk->flags & NETLINK_F_RECV_NO_ENOBUFS)
+ flags |= NDIAG_FLAG_NO_ENOBUFS;
+ if (nlk->flags & NETLINK_F_LISTEN_ALL_NSID)
+ flags |= NDIAG_FLAG_LISTEN_ALL_NSID;
+ if (nlk->flags & NETLINK_F_CAP_ACK)
+ flags |= NDIAG_FLAG_CAP_ACK;
+
+ return nla_put_u32(skb, NETLINK_DIAG_FLAGS, flags);
+}
+
static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
struct netlink_diag_req *req,
u32 portid, u32 seq, u32 flags, int sk_ino)
@@ -52,6 +73,10 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
sock_diag_put_meminfo(sk, skb, NETLINK_DIAG_MEMINFO))
goto out_nlmsg_trim;
+ if ((req->ndiag_show & NDIAG_SHOW_FLAGS) &&
+ sk_diag_put_flags(sk, skb))
+ goto out_nlmsg_trim;
+
nlmsg_end(skb, nlh);
return 0;
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index fb6e10f..92e0981 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -783,8 +783,10 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb)
if (ctrl_fill_info(rt, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
- skb, CTRL_CMD_NEWFAMILY) < 0)
+ skb, CTRL_CMD_NEWFAMILY) < 0) {
+ n--;
break;
+ }
}
cb->args[0] = n;
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 4bbf452..ebf16f7 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -765,7 +765,8 @@ static int nr_connect(struct socket *sock, struct sockaddr *uaddr,
return err;
}
-static int nr_accept(struct socket *sock, struct socket *newsock, int flags)
+static int nr_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sk_buff *skb;
struct sock *newsk;
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 879885b..2ffb18e 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -441,7 +441,7 @@ struct sock *nfc_llcp_accept_dequeue(struct sock *parent,
}
static int llcp_sock_accept(struct socket *sock, struct socket *newsock,
- int flags)
+ int flags, bool kern)
{
DECLARE_WAITQUEUE(wait, current);
struct sock *sk = sock->sk, *new_sk;
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index c82301c..e461067 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2007-2014 Nicira, Inc.
+ * Copyright (c) 2007-2017 Nicira, Inc.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
@@ -44,13 +44,10 @@
#include "conntrack.h"
#include "vport.h"
-static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
- struct sw_flow_key *key,
- const struct nlattr *attr, int len);
-
struct deferred_action {
struct sk_buff *skb;
const struct nlattr *actions;
+ int actions_len;
/* Store pkt_key clone when creating deferred action. */
struct sw_flow_key pkt_key;
@@ -82,14 +79,31 @@ struct action_fifo {
struct deferred_action fifo[DEFERRED_ACTION_FIFO_SIZE];
};
-struct recirc_keys {
+struct action_flow_keys {
struct sw_flow_key key[OVS_DEFERRED_ACTION_THRESHOLD];
};
static struct action_fifo __percpu *action_fifos;
-static struct recirc_keys __percpu *recirc_keys;
+static struct action_flow_keys __percpu *flow_keys;
static DEFINE_PER_CPU(int, exec_actions_level);
+/* Make a clone of the 'key', using the pre-allocated percpu 'flow_keys'
+ * space. Return NULL if out of key spaces.
+ */
+static struct sw_flow_key *clone_key(const struct sw_flow_key *key_)
+{
+ struct action_flow_keys *keys = this_cpu_ptr(flow_keys);
+ int level = this_cpu_read(exec_actions_level);
+ struct sw_flow_key *key = NULL;
+
+ if (level <= OVS_DEFERRED_ACTION_THRESHOLD) {
+ key = &keys->key[level - 1];
+ *key = *key_;
+ }
+
+ return key;
+}
+
static void action_fifo_init(struct action_fifo *fifo)
{
fifo->head = 0;
@@ -119,8 +133,9 @@ static struct deferred_action *action_fifo_put(struct action_fifo *fifo)
/* Return true if fifo is not full */
static struct deferred_action *add_deferred_actions(struct sk_buff *skb,
- const struct sw_flow_key *key,
- const struct nlattr *attr)
+ const struct sw_flow_key *key,
+ const struct nlattr *actions,
+ const int actions_len)
{
struct action_fifo *fifo;
struct deferred_action *da;
@@ -129,7 +144,8 @@ static struct deferred_action *add_deferred_actions(struct sk_buff *skb,
da = action_fifo_put(fifo);
if (da) {
da->skb = skb;
- da->actions = attr;
+ da->actions = actions;
+ da->actions_len = actions_len;
da->pkt_key = *key;
}
@@ -146,6 +162,12 @@ static bool is_flow_key_valid(const struct sw_flow_key *key)
return !(key->mac_proto & SW_FLOW_KEY_INVALID);
}
+static int clone_execute(struct datapath *dp, struct sk_buff *skb,
+ struct sw_flow_key *key,
+ u32 recirc_id,
+ const struct nlattr *actions, int len,
+ bool last, bool clone_flow_key);
+
static void update_ethertype(struct sk_buff *skb, struct ethhdr *hdr,
__be16 ethertype)
{
@@ -908,72 +930,35 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
return ovs_dp_upcall(dp, skb, key, &upcall, cutlen);
}
+/* When 'last' is true, sample() should always consume the 'skb'.
+ * Otherwise, sample() should keep 'skb' intact regardless what
+ * actions are executed within sample().
+ */
static int sample(struct datapath *dp, struct sk_buff *skb,
struct sw_flow_key *key, const struct nlattr *attr,
- const struct nlattr *actions, int actions_len)
+ bool last)
{
- const struct nlattr *acts_list = NULL;
- const struct nlattr *a;
- int rem;
- u32 cutlen = 0;
+ struct nlattr *actions;
+ struct nlattr *sample_arg;
+ int rem = nla_len(attr);
+ const struct sample_arg *arg;
+ bool clone_flow_key;
- for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
- a = nla_next(a, &rem)) {
- u32 probability;
+ /* The first action is always 'OVS_SAMPLE_ATTR_ARG'. */
+ sample_arg = nla_data(attr);
+ arg = nla_data(sample_arg);
+ actions = nla_next(sample_arg, &rem);
- switch (nla_type(a)) {
- case OVS_SAMPLE_ATTR_PROBABILITY:
- probability = nla_get_u32(a);
- if (!probability || prandom_u32() > probability)
- return 0;
- break;
-
- case OVS_SAMPLE_ATTR_ACTIONS:
- acts_list = a;
- break;
- }
- }
-
- rem = nla_len(acts_list);
- a = nla_data(acts_list);
-
- /* Actions list is empty, do nothing */
- if (unlikely(!rem))
+ if ((arg->probability != U32_MAX) &&
+ (!arg->probability || prandom_u32() > arg->probability)) {
+ if (last)
+ consume_skb(skb);
return 0;
-
- /* The only known usage of sample action is having a single user-space
- * action, or having a truncate action followed by a single user-space
- * action. Treat this usage as a special case.
- * The output_userspace() should clone the skb to be sent to the
- * user space. This skb will be consumed by its caller.
- */
- if (unlikely(nla_type(a) == OVS_ACTION_ATTR_TRUNC)) {
- struct ovs_action_trunc *trunc = nla_data(a);
-
- if (skb->len > trunc->max_len)
- cutlen = skb->len - trunc->max_len;
-
- a = nla_next(a, &rem);
}
- if (likely(nla_type(a) == OVS_ACTION_ATTR_USERSPACE &&
- nla_is_last(a, rem)))
- return output_userspace(dp, skb, key, a, actions,
- actions_len, cutlen);
-
- skb = skb_clone(skb, GFP_ATOMIC);
- if (!skb)
- /* Skip the sample action when out of memory. */
- return 0;
-
- if (!add_deferred_actions(skb, key, a)) {
- if (net_ratelimit())
- pr_warn("%s: deferred actions limit reached, dropping sample action\n",
- ovs_dp_name(dp));
-
- kfree_skb(skb);
- }
- return 0;
+ clone_flow_key = !arg->exec;
+ return clone_execute(dp, skb, key, 0, actions, rem, last,
+ clone_flow_key);
}
static void execute_hash(struct sk_buff *skb, struct sw_flow_key *key,
@@ -1084,10 +1069,9 @@ static int execute_masked_set_action(struct sk_buff *skb,
static int execute_recirc(struct datapath *dp, struct sk_buff *skb,
struct sw_flow_key *key,
- const struct nlattr *a, int rem)
+ const struct nlattr *a, bool last)
{
- struct deferred_action *da;
- int level;
+ u32 recirc_id;
if (!is_flow_key_valid(key)) {
int err;
@@ -1098,43 +1082,8 @@ static int execute_recirc(struct datapath *dp, struct sk_buff *skb,
}
BUG_ON(!is_flow_key_valid(key));
- if (!nla_is_last(a, rem)) {
- /* Recirc action is the not the last action
- * of the action list, need to clone the skb.
- */
- skb = skb_clone(skb, GFP_ATOMIC);
-
- /* Skip the recirc action when out of memory, but
- * continue on with the rest of the action list.
- */
- if (!skb)
- return 0;
- }
-
- level = this_cpu_read(exec_actions_level);
- if (level <= OVS_DEFERRED_ACTION_THRESHOLD) {
- struct recirc_keys *rks = this_cpu_ptr(recirc_keys);
- struct sw_flow_key *recirc_key = &rks->key[level - 1];
-
- *recirc_key = *key;
- recirc_key->recirc_id = nla_get_u32(a);
- ovs_dp_process_packet(skb, recirc_key);
-
- return 0;
- }
-
- da = add_deferred_actions(skb, key, NULL);
- if (da) {
- da->pkt_key.recirc_id = nla_get_u32(a);
- } else {
- kfree_skb(skb);
-
- if (net_ratelimit())
- pr_warn("%s: deferred action limit reached, drop recirc action\n",
- ovs_dp_name(dp));
- }
-
- return 0;
+ recirc_id = nla_get_u32(a);
+ return clone_execute(dp, skb, key, recirc_id, NULL, 0, last, true);
}
/* Execute a list of actions against 'skb'. */
@@ -1206,9 +1155,11 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
err = pop_vlan(skb, key);
break;
- case OVS_ACTION_ATTR_RECIRC:
- err = execute_recirc(dp, skb, key, a, rem);
- if (nla_is_last(a, rem)) {
+ case OVS_ACTION_ATTR_RECIRC: {
+ bool last = nla_is_last(a, rem);
+
+ err = execute_recirc(dp, skb, key, a, last);
+ if (last) {
/* If this is the last action, the skb has
* been consumed or freed.
* Return immediately.
@@ -1216,6 +1167,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
return err;
}
break;
+ }
case OVS_ACTION_ATTR_SET:
err = execute_set_action(skb, key, nla_data(a));
@@ -1226,9 +1178,15 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
err = execute_masked_set_action(skb, key, nla_data(a));
break;
- case OVS_ACTION_ATTR_SAMPLE:
- err = sample(dp, skb, key, a, attr, len);
+ case OVS_ACTION_ATTR_SAMPLE: {
+ bool last = nla_is_last(a, rem);
+
+ err = sample(dp, skb, key, a, last);
+ if (last)
+ return err;
+
break;
+ }
case OVS_ACTION_ATTR_CT:
if (!is_flow_key_valid(key)) {
@@ -1264,6 +1222,79 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
return 0;
}
+/* Execute the actions on the clone of the packet. The effect of the
+ * execution does not affect the original 'skb' nor the original 'key'.
+ *
+ * The execution may be deferred in case the actions can not be executed
+ * immediately.
+ */
+static int clone_execute(struct datapath *dp, struct sk_buff *skb,
+ struct sw_flow_key *key, u32 recirc_id,
+ const struct nlattr *actions, int len,
+ bool last, bool clone_flow_key)
+{
+ struct deferred_action *da;
+ struct sw_flow_key *clone;
+
+ skb = last ? skb : skb_clone(skb, GFP_ATOMIC);
+ if (!skb) {
+ /* Out of memory, skip this action.
+ */
+ return 0;
+ }
+
+ /* When clone_flow_key is false, the 'key' will not be change
+ * by the actions, then the 'key' can be used directly.
+ * Otherwise, try to clone key from the next recursion level of
+ * 'flow_keys'. If clone is successful, execute the actions
+ * without deferring.
+ */
+ clone = clone_flow_key ? clone_key(key) : key;
+ if (clone) {
+ int err = 0;
+
+ if (actions) { /* Sample action */
+ if (clone_flow_key)
+ __this_cpu_inc(exec_actions_level);
+
+ err = do_execute_actions(dp, skb, clone,
+ actions, len);
+
+ if (clone_flow_key)
+ __this_cpu_dec(exec_actions_level);
+ } else { /* Recirc action */
+ clone->recirc_id = recirc_id;
+ ovs_dp_process_packet(skb, clone);
+ }
+ return err;
+ }
+
+ /* Out of 'flow_keys' space. Defer actions */
+ da = add_deferred_actions(skb, key, actions, len);
+ if (da) {
+ if (!actions) { /* Recirc action */
+ key = &da->pkt_key;
+ key->recirc_id = recirc_id;
+ }
+ } else {
+ /* Out of per CPU action FIFO space. Drop the 'skb' and
+ * log an error.
+ */
+ kfree_skb(skb);
+
+ if (net_ratelimit()) {
+ if (actions) { /* Sample action */
+ pr_warn("%s: deferred action limit reached, drop sample action\n",
+ ovs_dp_name(dp));
+ } else { /* Recirc action */
+ pr_warn("%s: deferred action limit reached, drop recirc action\n",
+ ovs_dp_name(dp));
+ }
+ }
+ }
+ return 0;
+}
+
static void process_deferred_actions(struct datapath *dp)
{
struct action_fifo *fifo = this_cpu_ptr(action_fifos);
@@ -1278,10 +1309,10 @@ static void process_deferred_actions(struct datapath *dp)
struct sk_buff *skb = da->skb;
struct sw_flow_key *key = &da->pkt_key;
const struct nlattr *actions = da->actions;
+ int actions_len = da->actions_len;
if (actions)
- do_execute_actions(dp, skb, key, actions,
- nla_len(actions));
+ do_execute_actions(dp, skb, key, actions, actions_len);
else
ovs_dp_process_packet(skb, key);
} while (!action_fifo_is_empty(fifo));
@@ -1323,8 +1354,8 @@ int action_fifos_init(void)
if (!action_fifos)
return -ENOMEM;
- recirc_keys = alloc_percpu(struct recirc_keys);
- if (!recirc_keys) {
+ flow_keys = alloc_percpu(struct action_flow_keys);
+ if (!flow_keys) {
free_percpu(action_fifos);
return -ENOMEM;
}
@@ -1335,5 +1366,5 @@ int action_fifos_init(void)
void action_fifos_exit(void)
{
free_percpu(action_fifos);
- free_percpu(recirc_keys);
+ free_percpu(flow_keys);
}
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index e0a8777..7b2c2fc 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -643,8 +643,8 @@ static bool skb_nfct_cached(struct net *net,
*/
if (nf_ct_is_confirmed(ct))
nf_ct_delete(ct, 0, 0);
- else
- nf_conntrack_put(&ct->ct_general);
+
+ nf_conntrack_put(&ct->ct_general);
nf_ct_set(skb, NULL, 0);
return false;
}
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 1c6e937..da931bd 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -34,8 +34,6 @@
#define DP_MAX_PORTS USHRT_MAX
#define DP_VPORT_HASH_BUCKETS 1024
-#define SAMPLE_ACTION_DEPTH 3
-
/**
* struct dp_stats_percpu - per-cpu packet processing statistics for a given
* datapath.
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 9d4bb8e..3f76cb7 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -527,7 +527,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
/* Link layer. */
clear_vlan(key);
- if (key->mac_proto == MAC_PROTO_NONE) {
+ if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) {
if (unlikely(eth_type_vlan(skb->protocol)))
return -EINVAL;
@@ -745,7 +745,13 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key)
{
- return key_extract(skb, key);
+ int res;
+
+ res = key_extract(skb, key);
+ if (!res)
+ key->mac_proto &= ~SW_FLOW_KEY_INVALID;
+
+ return res;
}
static int key_extract_mac_proto(struct sk_buff *skb)
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 6f5fa50..df82b81 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2007-2014 Nicira, Inc.
+ * Copyright (c) 2007-2017 Nicira, Inc.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
@@ -59,6 +59,39 @@ struct ovs_len_tbl {
#define OVS_ATTR_NESTED -1
#define OVS_ATTR_VARIABLE -2
+static bool actions_may_change_flow(const struct nlattr *actions)
+{
+ struct nlattr *nla;
+ int rem;
+
+ nla_for_each_nested(nla, actions, rem) {
+ u16 action = nla_type(nla);
+
+ switch (action) {
+ case OVS_ACTION_ATTR_OUTPUT:
+ case OVS_ACTION_ATTR_RECIRC:
+ case OVS_ACTION_ATTR_TRUNC:
+ case OVS_ACTION_ATTR_USERSPACE:
+ break;
+
+ case OVS_ACTION_ATTR_CT:
+ case OVS_ACTION_ATTR_HASH:
+ case OVS_ACTION_ATTR_POP_ETH:
+ case OVS_ACTION_ATTR_POP_MPLS:
+ case OVS_ACTION_ATTR_POP_VLAN:
+ case OVS_ACTION_ATTR_PUSH_ETH:
+ case OVS_ACTION_ATTR_PUSH_MPLS:
+ case OVS_ACTION_ATTR_PUSH_VLAN:
+ case OVS_ACTION_ATTR_SAMPLE:
+ case OVS_ACTION_ATTR_SET:
+ case OVS_ACTION_ATTR_SET_MASKED:
+ default:
+ return true;
+ }
+ }
+ return false;
+}
+
static void update_range(struct sw_flow_match *match,
size_t offset, size_t size, bool is_mask)
{
@@ -604,7 +637,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr,
ipv4 = true;
break;
case OVS_TUNNEL_KEY_ATTR_IPV6_SRC:
- SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst,
+ SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.src,
nla_get_in6_addr(a), is_mask);
ipv6 = true;
break;
@@ -665,6 +698,8 @@ static int ip_tun_from_nlattr(const struct nlattr *attr,
tun_flags |= TUNNEL_VXLAN_OPT;
opts_type = type;
break;
+ case OVS_TUNNEL_KEY_ATTR_PAD:
+ break;
default:
OVS_NLERR(log, "Unknown IP tunnel attribute %d",
type);
@@ -2021,18 +2056,20 @@ static inline void add_nested_action_end(struct sw_flow_actions *sfa,
static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
const struct sw_flow_key *key,
- int depth, struct sw_flow_actions **sfa,
+ struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci, bool log);
static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
- const struct sw_flow_key *key, int depth,
+ const struct sw_flow_key *key,
struct sw_flow_actions **sfa,
- __be16 eth_type, __be16 vlan_tci, bool log)
+ __be16 eth_type, __be16 vlan_tci,
+ bool log, bool last)
{
const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
const struct nlattr *probability, *actions;
const struct nlattr *a;
- int rem, start, err, st_acts;
+ int rem, start, err;
+ struct sample_arg arg;
memset(attrs, 0, sizeof(attrs));
nla_for_each_nested(a, attr, rem) {
@@ -2056,20 +2093,32 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SAMPLE, log);
if (start < 0)
return start;
- err = ovs_nla_add_action(sfa, OVS_SAMPLE_ATTR_PROBABILITY,
- nla_data(probability), sizeof(u32), log);
+
+ /* When both skb and flow may be changed, put the sample
+ * into a deferred fifo. On the other hand, if only skb
+ * may be modified, the actions can be executed in place.
+ *
+ * Do this analysis at the flow installation time.
+ * Set 'clone_action->exec' to true if the actions can be
+ * executed without being deferred.
+ *
+ * If the sample is the last action, it can always be excuted
+ * rather than deferred.
+ */
+ arg.exec = last || !actions_may_change_flow(actions);
+ arg.probability = nla_get_u32(probability);
+
+ err = ovs_nla_add_action(sfa, OVS_SAMPLE_ATTR_ARG, &arg, sizeof(arg),
+ log);
if (err)
return err;
- st_acts = add_nested_action_start(sfa, OVS_SAMPLE_ATTR_ACTIONS, log);
- if (st_acts < 0)
- return st_acts;
- err = __ovs_nla_copy_actions(net, actions, key, depth + 1, sfa,
+ err = __ovs_nla_copy_actions(net, actions, key, sfa,
eth_type, vlan_tci, log);
+
if (err)
return err;
- add_nested_action_end(*sfa, st_acts);
add_nested_action_end(*sfa, start);
return 0;
@@ -2406,16 +2455,13 @@ static int copy_action(const struct nlattr *from,
static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
const struct sw_flow_key *key,
- int depth, struct sw_flow_actions **sfa,
+ struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci, bool log)
{
u8 mac_proto = ovs_key_mac_proto(key);
const struct nlattr *a;
int rem, err;
- if (depth >= SAMPLE_ACTION_DEPTH)
- return -EOVERFLOW;
-
nla_for_each_nested(a, attr, rem) {
/* Expected argument lengths, (u32)-1 for variable length. */
static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = {
@@ -2553,13 +2599,17 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
return err;
break;
- case OVS_ACTION_ATTR_SAMPLE:
- err = validate_and_copy_sample(net, a, key, depth, sfa,
- eth_type, vlan_tci, log);
+ case OVS_ACTION_ATTR_SAMPLE: {
+ bool last = nla_is_last(a, rem);
+
+ err = validate_and_copy_sample(net, a, key, sfa,
+ eth_type, vlan_tci,
+ log, last);
if (err)
return err;
skip_copy = true;
break;
+ }
case OVS_ACTION_ATTR_CT:
err = ovs_ct_copy_action(net, a, key, sfa, log);
@@ -2613,7 +2663,7 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
return PTR_ERR(*sfa);
(*sfa)->orig_len = nla_len(attr);
- err = __ovs_nla_copy_actions(net, attr, key, 0, sfa, key->eth.type,
+ err = __ovs_nla_copy_actions(net, attr, key, sfa, key->eth.type,
key->eth.vlan.tci, log);
if (err)
ovs_nla_free_flow_actions(*sfa);
@@ -2621,39 +2671,44 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
return err;
}
-static int sample_action_to_attr(const struct nlattr *attr, struct sk_buff *skb)
+static int sample_action_to_attr(const struct nlattr *attr,
+ struct sk_buff *skb)
{
- const struct nlattr *a;
- struct nlattr *start;
- int err = 0, rem;
+ struct nlattr *start, *ac_start = NULL, *sample_arg;
+ int err = 0, rem = nla_len(attr);
+ const struct sample_arg *arg;
+ struct nlattr *actions;
start = nla_nest_start(skb, OVS_ACTION_ATTR_SAMPLE);
if (!start)
return -EMSGSIZE;
- nla_for_each_nested(a, attr, rem) {
- int type = nla_type(a);
- struct nlattr *st_sample;
+ sample_arg = nla_data(attr);
+ arg = nla_data(sample_arg);
+ actions = nla_next(sample_arg, &rem);
- switch (type) {
- case OVS_SAMPLE_ATTR_PROBABILITY:
- if (nla_put(skb, OVS_SAMPLE_ATTR_PROBABILITY,
- sizeof(u32), nla_data(a)))
- return -EMSGSIZE;
- break;
- case OVS_SAMPLE_ATTR_ACTIONS:
- st_sample = nla_nest_start(skb, OVS_SAMPLE_ATTR_ACTIONS);
- if (!st_sample)
- return -EMSGSIZE;
- err = ovs_nla_put_actions(nla_data(a), nla_len(a), skb);
- if (err)
- return err;
- nla_nest_end(skb, st_sample);
- break;
- }
+ if (nla_put_u32(skb, OVS_SAMPLE_ATTR_PROBABILITY, arg->probability)) {
+ err = -EMSGSIZE;
+ goto out;
}
- nla_nest_end(skb, start);
+ ac_start = nla_nest_start(skb, OVS_SAMPLE_ATTR_ACTIONS);
+ if (!ac_start) {
+ err = -EMSGSIZE;
+ goto out;
+ }
+
+ err = ovs_nla_put_actions(actions, rem, skb);
+
+out:
+ if (err) {
+ nla_nest_cancel(skb, ac_start);
+ nla_nest_cancel(skb, start);
+ } else {
+ nla_nest_end(skb, ac_start);
+ nla_nest_end(skb, start);
+ }
+
return err;
}
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index a0dbe7c..8489bef 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3665,6 +3665,8 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
return -EBUSY;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
+ if (val > INT_MAX)
+ return -EINVAL;
po->tp_reserve = val;
return 0;
}
@@ -4193,8 +4195,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
if (unlikely(!PAGE_ALIGNED(req->tp_block_size)))
goto out;
if (po->tp_version >= TPACKET_V3 &&
- (int)(req->tp_block_size -
- BLK_PLUS_PRIV(req_u->req3.tp_sizeof_priv)) <= 0)
+ req->tp_block_size <=
+ BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv))
goto out;
if (unlikely(req->tp_frame_size < po->tp_hdrlen +
po->tp_reserve))
@@ -4205,6 +4207,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
rb->frames_per_block = req->tp_block_size / req->tp_frame_size;
if (unlikely(rb->frames_per_block == 0))
goto out;
+ if (unlikely(req->tp_block_size > UINT_MAX / req->tp_block_nr))
+ goto out;
if (unlikely((rb->frames_per_block * req->tp_block_nr) !=
req->tp_frame_nr))
goto out;
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 222bedc..e815379 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -772,7 +772,8 @@ static void pep_sock_close(struct sock *sk, long timeout)
sock_put(sk);
}
-static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp)
+static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp,
+ bool kern)
{
struct pep_sock *pn = pep_sk(sk), *newpn;
struct sock *newsk = NULL;
@@ -846,7 +847,8 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp)
}
/* Create a new to-be-accepted sock */
- newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot, 0);
+ newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot,
+ kern);
if (!newsk) {
pep_reject_conn(sk, skb, PN_PIPE_ERR_OVERLOAD, GFP_KERNEL);
err = -ENOBUFS;
diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index a6c8da3..64634e3 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -305,7 +305,7 @@ static int pn_socket_connect(struct socket *sock, struct sockaddr *addr,
}
static int pn_socket_accept(struct socket *sock, struct socket *newsock,
- int flags)
+ int flags, bool kern)
{
struct sock *sk = sock->sk;
struct sock *newsk;
@@ -314,7 +314,7 @@ static int pn_socket_accept(struct socket *sock, struct socket *newsock,
if (unlikely(sk->sk_state != TCP_LISTEN))
return -EINVAL;
- newsk = sk->sk_prot->accept(sk, flags, &err);
+ newsk = sk->sk_prot->accept(sk, flags, &err, kern);
if (!newsk)
return err;
diff --git a/net/qrtr/Kconfig b/net/qrtr/Kconfig
index b83c680..326fd97 100644
--- a/net/qrtr/Kconfig
+++ b/net/qrtr/Kconfig
@@ -16,7 +16,7 @@
config QRTR_SMD
tristate "SMD IPC Router channels"
- depends on QCOM_SMD || (COMPILE_TEST && QCOM_SMD=n)
+ depends on RPMSG || (COMPILE_TEST && RPMSG=n)
---help---
Say Y here to support SMD based ipcrouter channels. SMD is the
most common transport for IPC Router.
diff --git a/net/qrtr/smd.c b/net/qrtr/smd.c
index 0d11132..50615d5 100644
--- a/net/qrtr/smd.c
+++ b/net/qrtr/smd.c
@@ -14,21 +14,21 @@
#include <linux/module.h>
#include <linux/skbuff.h>
-#include <linux/soc/qcom/smd.h>
+#include <linux/rpmsg.h>
#include "qrtr.h"
struct qrtr_smd_dev {
struct qrtr_endpoint ep;
- struct qcom_smd_channel *channel;
+ struct rpmsg_endpoint *channel;
struct device *dev;
};
/* from smd to qrtr */
-static int qcom_smd_qrtr_callback(struct qcom_smd_channel *channel,
- const void *data, size_t len)
+static int qcom_smd_qrtr_callback(struct rpmsg_device *rpdev,
+ void *data, int len, void *priv, u32 addr)
{
- struct qrtr_smd_dev *qdev = qcom_smd_get_drvdata(channel);
+ struct qrtr_smd_dev *qdev = dev_get_drvdata(&rpdev->dev);
int rc;
if (!qdev)
@@ -54,7 +54,7 @@ static int qcom_smd_qrtr_send(struct qrtr_endpoint *ep, struct sk_buff *skb)
if (rc)
goto out;
- rc = qcom_smd_send(qdev->channel, skb->data, skb->len);
+ rc = rpmsg_send(qdev->channel, skb->data, skb->len);
out:
if (rc)
@@ -64,57 +64,55 @@ static int qcom_smd_qrtr_send(struct qrtr_endpoint *ep, struct sk_buff *skb)
return rc;
}
-static int qcom_smd_qrtr_probe(struct qcom_smd_device *sdev)
+static int qcom_smd_qrtr_probe(struct rpmsg_device *rpdev)
{
struct qrtr_smd_dev *qdev;
int rc;
- qdev = devm_kzalloc(&sdev->dev, sizeof(*qdev), GFP_KERNEL);
+ qdev = devm_kzalloc(&rpdev->dev, sizeof(*qdev), GFP_KERNEL);
if (!qdev)
return -ENOMEM;
- qdev->channel = sdev->channel;
- qdev->dev = &sdev->dev;
+ qdev->channel = rpdev->ept;
+ qdev->dev = &rpdev->dev;
qdev->ep.xmit = qcom_smd_qrtr_send;
rc = qrtr_endpoint_register(&qdev->ep, QRTR_EP_NID_AUTO);
if (rc)
return rc;
- qcom_smd_set_drvdata(sdev->channel, qdev);
- dev_set_drvdata(&sdev->dev, qdev);
+ dev_set_drvdata(&rpdev->dev, qdev);
- dev_dbg(&sdev->dev, "Qualcomm SMD QRTR driver probed\n");
+ dev_dbg(&rpdev->dev, "Qualcomm SMD QRTR driver probed\n");
return 0;
}
-static void qcom_smd_qrtr_remove(struct qcom_smd_device *sdev)
+static void qcom_smd_qrtr_remove(struct rpmsg_device *rpdev)
{
- struct qrtr_smd_dev *qdev = dev_get_drvdata(&sdev->dev);
+ struct qrtr_smd_dev *qdev = dev_get_drvdata(&rpdev->dev);
qrtr_endpoint_unregister(&qdev->ep);
- dev_set_drvdata(&sdev->dev, NULL);
+ dev_set_drvdata(&rpdev->dev, NULL);
}
-static const struct qcom_smd_id qcom_smd_qrtr_smd_match[] = {
+static const struct rpmsg_device_id qcom_smd_qrtr_smd_match[] = {
{ "IPCRTR" },
{}
};
-static struct qcom_smd_driver qcom_smd_qrtr_driver = {
+static struct rpmsg_driver qcom_smd_qrtr_driver = {
.probe = qcom_smd_qrtr_probe,
.remove = qcom_smd_qrtr_remove,
.callback = qcom_smd_qrtr_callback,
- .smd_match_table = qcom_smd_qrtr_smd_match,
- .driver = {
+ .id_table = qcom_smd_qrtr_smd_match,
+ .drv = {
.name = "qcom_smd_qrtr",
- .owner = THIS_MODULE,
},
};
-module_qcom_smd_driver(qcom_smd_qrtr_driver);
+module_rpmsg_driver(qcom_smd_qrtr_driver);
MODULE_DESCRIPTION("Qualcomm IPC-Router SMD interface driver");
MODULE_LICENSE("GPL v2");
diff --git a/net/rds/connection.c b/net/rds/connection.c
index 0e04dcc..6a5ebde 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -333,11 +333,19 @@ void rds_conn_shutdown(struct rds_conn_path *cp)
rds_conn_path_reset(cp);
if (!rds_conn_path_transition(cp, RDS_CONN_DISCONNECTING,
+ RDS_CONN_DOWN) &&
+ !rds_conn_path_transition(cp, RDS_CONN_ERROR,
RDS_CONN_DOWN)) {
/* This can happen - eg when we're in the middle of tearing
* down the connection, and someone unloads the rds module.
- * Quite reproduceable with loopback connections.
+ * Quite reproducible with loopback connections.
* Mostly harmless.
+ *
+ * Note that this also happens with rds-tcp because
+ * we could have triggered rds_conn_path_drop in irq
+ * mode from rds_tcp_state change on the receipt of
+ * a FIN, thus we need to recheck for RDS_CONN_ERROR
+ * here.
*/
rds_conn_path_error(cp, "%s: failed to transition "
"to state DOWN, current state "
@@ -429,6 +437,7 @@ void rds_conn_destroy(struct rds_connection *conn)
*/
rds_cong_remove_conn(conn);
+ put_net(conn->c_net);
kmem_cache_free(rds_conn_slab, conn);
spin_lock_irqsave(&rds_conn_lock, flags);
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index ce3775a..80fb6f6 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -442,7 +442,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
ic->i_send_cq = NULL;
ibdev_put_vector(rds_ibdev, ic->i_scq_vector);
rdsdebug("ib_create_cq send failed: %d\n", ret);
- goto out;
+ goto rds_ibdev_out;
}
ic->i_rcq_vector = ibdev_get_unused_vector(rds_ibdev);
@@ -456,19 +456,19 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
ic->i_recv_cq = NULL;
ibdev_put_vector(rds_ibdev, ic->i_rcq_vector);
rdsdebug("ib_create_cq recv failed: %d\n", ret);
- goto out;
+ goto send_cq_out;
}
ret = ib_req_notify_cq(ic->i_send_cq, IB_CQ_NEXT_COMP);
if (ret) {
rdsdebug("ib_req_notify_cq send failed: %d\n", ret);
- goto out;
+ goto recv_cq_out;
}
ret = ib_req_notify_cq(ic->i_recv_cq, IB_CQ_SOLICITED);
if (ret) {
rdsdebug("ib_req_notify_cq recv failed: %d\n", ret);
- goto out;
+ goto recv_cq_out;
}
/* XXX negotiate max send/recv with remote? */
@@ -494,7 +494,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
ret = rdma_create_qp(ic->i_cm_id, ic->i_pd, &attr);
if (ret) {
rdsdebug("rdma_create_qp failed: %d\n", ret);
- goto out;
+ goto recv_cq_out;
}
ic->i_send_hdrs = ib_dma_alloc_coherent(dev,
@@ -504,7 +504,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
if (!ic->i_send_hdrs) {
ret = -ENOMEM;
rdsdebug("ib_dma_alloc_coherent send failed\n");
- goto out;
+ goto qp_out;
}
ic->i_recv_hdrs = ib_dma_alloc_coherent(dev,
@@ -514,7 +514,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
if (!ic->i_recv_hdrs) {
ret = -ENOMEM;
rdsdebug("ib_dma_alloc_coherent recv failed\n");
- goto out;
+ goto send_hdrs_dma_out;
}
ic->i_ack = ib_dma_alloc_coherent(dev, sizeof(struct rds_header),
@@ -522,7 +522,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
if (!ic->i_ack) {
ret = -ENOMEM;
rdsdebug("ib_dma_alloc_coherent ack failed\n");
- goto out;
+ goto recv_hdrs_dma_out;
}
ic->i_sends = vzalloc_node(ic->i_send_ring.w_nr * sizeof(struct rds_ib_send_work),
@@ -530,7 +530,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
if (!ic->i_sends) {
ret = -ENOMEM;
rdsdebug("send allocation failed\n");
- goto out;
+ goto ack_dma_out;
}
ic->i_recvs = vzalloc_node(ic->i_recv_ring.w_nr * sizeof(struct rds_ib_recv_work),
@@ -538,7 +538,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
if (!ic->i_recvs) {
ret = -ENOMEM;
rdsdebug("recv allocation failed\n");
- goto out;
+ goto sends_out;
}
rds_ib_recv_init_ack(ic);
@@ -546,8 +546,33 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
rdsdebug("conn %p pd %p cq %p %p\n", conn, ic->i_pd,
ic->i_send_cq, ic->i_recv_cq);
-out:
+ return ret;
+
+sends_out:
+ vfree(ic->i_sends);
+ack_dma_out:
+ ib_dma_free_coherent(dev, sizeof(struct rds_header),
+ ic->i_ack, ic->i_ack_dma);
+recv_hdrs_dma_out:
+ ib_dma_free_coherent(dev, ic->i_recv_ring.w_nr *
+ sizeof(struct rds_header),
+ ic->i_recv_hdrs, ic->i_recv_hdrs_dma);
+send_hdrs_dma_out:
+ ib_dma_free_coherent(dev, ic->i_send_ring.w_nr *
+ sizeof(struct rds_header),
+ ic->i_send_hdrs, ic->i_send_hdrs_dma);
+qp_out:
+ rdma_destroy_qp(ic->i_cm_id);
+recv_cq_out:
+ if (!ib_destroy_cq(ic->i_recv_cq))
+ ic->i_recv_cq = NULL;
+send_cq_out:
+ if (!ib_destroy_cq(ic->i_send_cq))
+ ic->i_send_cq = NULL;
+rds_ibdev_out:
+ rds_ib_remove_conn(rds_ibdev, conn);
rds_ib_dev_put(rds_ibdev);
+
return ret;
}
@@ -677,9 +702,8 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
event->param.conn.initiator_depth);
/* rdma_accept() calls rdma_reject() internally if it fails */
- err = rdma_accept(cm_id, &conn_param);
- if (err)
- rds_ib_conn_error(conn, "rdma_accept failed (%d)\n", err);
+ if (rdma_accept(cm_id, &conn_param))
+ rds_ib_conn_error(conn, "rdma_accept failed\n");
out:
if (conn)
diff --git a/net/rds/ib_fmr.c b/net/rds/ib_fmr.c
index 4fe8f4f..86ef907 100644
--- a/net/rds/ib_fmr.c
+++ b/net/rds/ib_fmr.c
@@ -78,17 +78,15 @@ struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev, int npages)
return ibmr;
out_no_cigar:
- if (ibmr) {
- if (fmr->fmr)
- ib_dealloc_fmr(fmr->fmr);
- kfree(ibmr);
- }
+ kfree(ibmr);
atomic_dec(&pool->item_count);
+
return ERR_PTR(err);
}
-int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, struct rds_ib_mr *ibmr,
- struct scatterlist *sg, unsigned int nents)
+static int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev,
+ struct rds_ib_mr *ibmr, struct scatterlist *sg,
+ unsigned int nents)
{
struct ib_device *dev = rds_ibdev->dev;
struct rds_ib_fmr *fmr = &ibmr->u.fmr;
@@ -114,29 +112,39 @@ int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, struct rds_ib_mr *ibmr,
u64 dma_addr = ib_sg_dma_address(dev, &scat[i]);
if (dma_addr & ~PAGE_MASK) {
- if (i > 0)
+ if (i > 0) {
+ ib_dma_unmap_sg(dev, sg, nents,
+ DMA_BIDIRECTIONAL);
return -EINVAL;
- else
+ } else {
++page_cnt;
+ }
}
if ((dma_addr + dma_len) & ~PAGE_MASK) {
- if (i < sg_dma_len - 1)
+ if (i < sg_dma_len - 1) {
+ ib_dma_unmap_sg(dev, sg, nents,
+ DMA_BIDIRECTIONAL);
return -EINVAL;
- else
+ } else {
++page_cnt;
+ }
}
len += dma_len;
}
page_cnt += len >> PAGE_SHIFT;
- if (page_cnt > ibmr->pool->fmr_attr.max_pages)
+ if (page_cnt > ibmr->pool->fmr_attr.max_pages) {
+ ib_dma_unmap_sg(dev, sg, nents, DMA_BIDIRECTIONAL);
return -EINVAL;
+ }
dma_pages = kmalloc_node(sizeof(u64) * page_cnt, GFP_ATOMIC,
rdsibdev_to_node(rds_ibdev));
- if (!dma_pages)
+ if (!dma_pages) {
+ ib_dma_unmap_sg(dev, sg, nents, DMA_BIDIRECTIONAL);
return -ENOMEM;
+ }
page_cnt = 0;
for (i = 0; i < sg_dma_len; ++i) {
@@ -149,8 +157,10 @@ int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, struct rds_ib_mr *ibmr,
}
ret = ib_map_phys_fmr(fmr->fmr, dma_pages, page_cnt, io_addr);
- if (ret)
+ if (ret) {
+ ib_dma_unmap_sg(dev, sg, nents, DMA_BIDIRECTIONAL);
goto out;
+ }
/* Success - we successfully remapped the MR, so we can
* safely tear down the old mapping.
diff --git a/net/rds/ib_mr.h b/net/rds/ib_mr.h
index 5d6e98a..0ea4ab0 100644
--- a/net/rds/ib_mr.h
+++ b/net/rds/ib_mr.h
@@ -125,8 +125,6 @@ void rds_ib_mr_exit(void);
void __rds_ib_teardown_mr(struct rds_ib_mr *);
void rds_ib_teardown_mr(struct rds_ib_mr *);
struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *, int);
-int rds_ib_map_fmr(struct rds_ib_device *, struct rds_ib_mr *,
- struct scatterlist *, unsigned int);
struct rds_ib_mr *rds_ib_reuse_mr(struct rds_ib_mr_pool *);
int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *, int, struct rds_ib_mr **);
struct rds_ib_mr *rds_ib_reg_fmr(struct rds_ib_device *, struct scatterlist *,
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 39518ef..82d38cc 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -147,7 +147,7 @@ struct rds_connection {
/* Protocol version */
unsigned int c_version;
- possible_net_t c_net;
+ struct net *c_net;
struct list_head c_map_item;
unsigned long c_map_queued;
@@ -162,13 +162,13 @@ struct rds_connection {
static inline
struct net *rds_conn_net(struct rds_connection *conn)
{
- return read_pnet(&conn->c_net);
+ return conn->c_net;
}
static inline
void rds_conn_net_set(struct rds_connection *conn, struct net *net)
{
- write_pnet(&conn->c_net, net);
+ conn->c_net = get_net(net);
}
#define RDS_FLAG_CONG_BITMAP 0x01
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index a973d3b..2256900 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -484,9 +484,10 @@ static void __net_exit rds_tcp_exit_net(struct net *net)
* we do need to clean up the listen socket here.
*/
if (rtn->rds_tcp_listen_sock) {
- rds_tcp_listen_stop(rtn->rds_tcp_listen_sock);
+ struct socket *lsock = rtn->rds_tcp_listen_sock;
+
rtn->rds_tcp_listen_sock = NULL;
- flush_work(&rtn->rds_tcp_accept_w);
+ rds_tcp_listen_stop(lsock, &rtn->rds_tcp_accept_w);
}
}
@@ -523,13 +524,13 @@ static void rds_tcp_kill_sock(struct net *net)
struct rds_tcp_connection *tc, *_tc;
LIST_HEAD(tmp_list);
struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
+ struct socket *lsock = rtn->rds_tcp_listen_sock;
- rds_tcp_listen_stop(rtn->rds_tcp_listen_sock);
rtn->rds_tcp_listen_sock = NULL;
- flush_work(&rtn->rds_tcp_accept_w);
+ rds_tcp_listen_stop(lsock, &rtn->rds_tcp_accept_w);
spin_lock_irq(&rds_tcp_conn_lock);
list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) {
- struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net);
+ struct net *c_net = tc->t_cpath->cp_conn->c_net;
if (net != c_net || !tc->t_sock)
continue;
@@ -546,8 +547,12 @@ static void rds_tcp_kill_sock(struct net *net)
void *rds_tcp_listen_sock_def_readable(struct net *net)
{
struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
+ struct socket *lsock = rtn->rds_tcp_listen_sock;
- return rtn->rds_tcp_listen_sock->sk->sk_user_data;
+ if (!lsock)
+ return NULL;
+
+ return lsock->sk->sk_user_data;
}
static int rds_tcp_dev_event(struct notifier_block *this,
@@ -584,7 +589,7 @@ static void rds_tcp_sysctl_reset(struct net *net)
spin_lock_irq(&rds_tcp_conn_lock);
list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) {
- struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net);
+ struct net *c_net = tc->t_cpath->cp_conn->c_net;
if (net != c_net || !tc->t_sock)
continue;
@@ -638,19 +643,19 @@ static int rds_tcp_init(void)
goto out;
}
- ret = register_netdevice_notifier(&rds_tcp_dev_notifier);
- if (ret) {
- pr_warn("could not register rds_tcp_dev_notifier\n");
+ ret = rds_tcp_recv_init();
+ if (ret)
goto out_slab;
- }
ret = register_pernet_subsys(&rds_tcp_net_ops);
if (ret)
- goto out_notifier;
+ goto out_recv;
- ret = rds_tcp_recv_init();
- if (ret)
+ ret = register_netdevice_notifier(&rds_tcp_dev_notifier);
+ if (ret) {
+ pr_warn("could not register rds_tcp_dev_notifier\n");
goto out_pernet;
+ }
rds_trans_register(&rds_tcp_transport);
@@ -660,9 +665,8 @@ static int rds_tcp_init(void)
out_pernet:
unregister_pernet_subsys(&rds_tcp_net_ops);
-out_notifier:
- if (unregister_netdevice_notifier(&rds_tcp_dev_notifier))
- pr_warn("could not unregister rds_tcp_dev_notifier\n");
+out_recv:
+ rds_tcp_recv_exit();
out_slab:
kmem_cache_destroy(rds_tcp_conn_slab);
out:
diff --git a/net/rds/tcp.h b/net/rds/tcp.h
index 9a1cc89..56ea662 100644
--- a/net/rds/tcp.h
+++ b/net/rds/tcp.h
@@ -66,7 +66,7 @@ void rds_tcp_state_change(struct sock *sk);
/* tcp_listen.c */
struct socket *rds_tcp_listen_init(struct net *);
-void rds_tcp_listen_stop(struct socket *);
+void rds_tcp_listen_stop(struct socket *sock, struct work_struct *acceptor);
void rds_tcp_listen_data_ready(struct sock *sk);
int rds_tcp_accept_one(struct socket *sock);
int rds_tcp_keepalive(struct socket *sock);
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 67d0929..5076788 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -133,7 +133,7 @@ int rds_tcp_accept_one(struct socket *sock)
new_sock->type = sock->type;
new_sock->ops = sock->ops;
- ret = sock->ops->accept(sock, new_sock, O_NONBLOCK);
+ ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, true);
if (ret < 0)
goto out;
@@ -223,6 +223,9 @@ void rds_tcp_listen_data_ready(struct sock *sk)
* before it has been accepted and the accepter has set up their
* data_ready.. we only want to queue listen work for our listening
* socket
+ *
+ * (*ready)() may be null if we are racing with netns delete, and
+ * the listen socket is being torn down.
*/
if (sk->sk_state == TCP_LISTEN)
rds_tcp_accept_work(sk);
@@ -231,7 +234,8 @@ void rds_tcp_listen_data_ready(struct sock *sk)
out:
read_unlock_bh(&sk->sk_callback_lock);
- ready(sk);
+ if (ready)
+ ready(sk);
}
struct socket *rds_tcp_listen_init(struct net *net)
@@ -271,7 +275,7 @@ struct socket *rds_tcp_listen_init(struct net *net)
return NULL;
}
-void rds_tcp_listen_stop(struct socket *sock)
+void rds_tcp_listen_stop(struct socket *sock, struct work_struct *acceptor)
{
struct sock *sk;
@@ -292,5 +296,6 @@ void rds_tcp_listen_stop(struct socket *sock)
/* wait for accepts to stop and close the socket */
flush_workqueue(rds_wq);
+ flush_work(acceptor);
sock_release(sock);
}
diff --git a/net/rds/threads.c b/net/rds/threads.c
index e36e333..3e447d05 100644
--- a/net/rds/threads.c
+++ b/net/rds/threads.c
@@ -156,7 +156,7 @@ void rds_connect_worker(struct work_struct *work)
struct rds_connection *conn = cp->cp_conn;
int ret;
- if (cp->cp_index > 1 && cp->cp_conn->c_laddr > cp->cp_conn->c_faddr)
+ if (cp->cp_index > 0 && cp->cp_conn->c_laddr > cp->cp_conn->c_faddr)
return;
clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags);
ret = rds_conn_path_transition(cp, RDS_CONN_DOWN, RDS_CONN_CONNECTING);
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index b8a1df2..4a97292 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -871,7 +871,8 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le
return err;
}
-static int rose_accept(struct socket *sock, struct socket *newsock, int flags)
+static int rose_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sk_buff *skb;
struct sock *newsk;
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 26a7b1d..7486926 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -740,6 +740,25 @@ static inline bool rxrpc_abort_call(const char *why, struct rxrpc_call *call,
}
/*
+ * Abort a call due to a protocol error.
+ */
+static inline bool __rxrpc_abort_eproto(struct rxrpc_call *call,
+ struct sk_buff *skb,
+ const char *eproto_why,
+ const char *why,
+ u32 abort_code)
+{
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+ trace_rxrpc_rx_eproto(call, sp->hdr.serial, eproto_why);
+ return rxrpc_abort_call(why, call, sp->hdr.seq, abort_code, -EPROTO);
+}
+
+#define rxrpc_abort_eproto(call, skb, eproto_why, abort_why, abort_code) \
+ __rxrpc_abort_eproto((call), (skb), tracepoint_string(eproto_why), \
+ (abort_why), (abort_code))
+
+/*
* conn_client.c
*/
extern unsigned int rxrpc_max_client_connections;
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 0ed181f..1752fcf 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -413,11 +413,11 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
case RXRPC_CONN_REMOTELY_ABORTED:
rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED,
- conn->remote_abort, ECONNABORTED);
+ conn->remote_abort, -ECONNABORTED);
break;
case RXRPC_CONN_LOCALLY_ABORTED:
rxrpc_abort_call("CON", call, sp->hdr.seq,
- conn->local_abort, ECONNABORTED);
+ conn->local_abort, -ECONNABORTED);
break;
default:
BUG();
@@ -600,7 +600,7 @@ int rxrpc_reject_call(struct rxrpc_sock *rx)
write_lock_bh(&call->state_lock);
switch (call->state) {
case RXRPC_CALL_SERVER_ACCEPTING:
- __rxrpc_abort_call("REJ", call, 1, RX_USER_ABORT, ECONNABORTED);
+ __rxrpc_abort_call("REJ", call, 1, RX_USER_ABORT, -ECONNABORTED);
abort = true;
/* fall through */
case RXRPC_CALL_COMPLETE:
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index 97a17ad..7a77844 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -386,7 +386,7 @@ void rxrpc_process_call(struct work_struct *work)
now = ktime_get_real();
if (ktime_before(call->expire_at, now)) {
- rxrpc_abort_call("EXP", call, 0, RX_CALL_TIMEOUT, ETIME);
+ rxrpc_abort_call("EXP", call, 0, RX_CALL_TIMEOUT, -ETIME);
set_bit(RXRPC_CALL_EV_ABORT, &call->events);
goto recheck_state;
}
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index d79cd36..47f7f42 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -486,7 +486,7 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx)
call = list_entry(rx->to_be_accepted.next,
struct rxrpc_call, accept_link);
list_del(&call->accept_link);
- rxrpc_abort_call("SKR", call, 0, RX_CALL_DEAD, ECONNRESET);
+ rxrpc_abort_call("SKR", call, 0, RX_CALL_DEAD, -ECONNRESET);
rxrpc_put_call(call, rxrpc_call_put);
}
@@ -494,7 +494,7 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx)
call = list_entry(rx->sock_calls.next,
struct rxrpc_call, sock_link);
rxrpc_get_call(call, rxrpc_call_got);
- rxrpc_abort_call("SKT", call, 0, RX_CALL_DEAD, ECONNRESET);
+ rxrpc_abort_call("SKT", call, 0, RX_CALL_DEAD, -ECONNRESET);
rxrpc_send_abort_packet(call);
rxrpc_release_call(rx, call);
rxrpc_put_call(call, rxrpc_call_put);
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index c3be03e8..e8dea0d 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -550,6 +550,7 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn,
call->cid = conn->proto.cid | channel;
call->call_id = call_id;
+ trace_rxrpc_connect_call(call);
_net("CONNECT call %08x:%08x as call %d on conn %d",
call->cid, call->call_id, call->debug_id, conn->debug_id);
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 3f9d8d7..46babcf 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -168,7 +168,7 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn,
* generate a connection-level abort
*/
static int rxrpc_abort_connection(struct rxrpc_connection *conn,
- u32 error, u32 abort_code)
+ int error, u32 abort_code)
{
struct rxrpc_wire_header whdr;
struct msghdr msg;
@@ -275,16 +275,23 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
rxrpc_conn_retransmit_call(conn, skb);
return 0;
+ case RXRPC_PACKET_TYPE_BUSY:
+ /* Just ignore BUSY packets for now. */
+ return 0;
+
case RXRPC_PACKET_TYPE_ABORT:
if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
- &wtmp, sizeof(wtmp)) < 0)
+ &wtmp, sizeof(wtmp)) < 0) {
+ trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
+ tracepoint_string("bad_abort"));
return -EPROTO;
+ }
abort_code = ntohl(wtmp);
_proto("Rx ABORT %%%u { ac=%d }", sp->hdr.serial, abort_code);
conn->state = RXRPC_CONN_REMOTELY_ABORTED;
rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED,
- abort_code, ECONNABORTED);
+ abort_code, -ECONNABORTED);
return -ECONNABORTED;
case RXRPC_PACKET_TYPE_CHALLENGE:
@@ -323,7 +330,8 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
return 0;
default:
- _leave(" = -EPROTO [%u]", sp->hdr.type);
+ trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
+ tracepoint_string("bad_conn_pkt"));
return -EPROTO;
}
}
@@ -366,7 +374,7 @@ static void rxrpc_secure_connection(struct rxrpc_connection *conn)
abort:
_debug("abort %d, %d", ret, abort_code);
- rxrpc_abort_connection(conn, -ret, abort_code);
+ rxrpc_abort_connection(conn, ret, abort_code);
_leave(" [aborted]");
}
@@ -415,9 +423,8 @@ void rxrpc_process_connection(struct work_struct *work)
goto out;
protocol_error:
- if (rxrpc_abort_connection(conn, -ret, abort_code) < 0)
+ if (rxrpc_abort_connection(conn, ret, abort_code) < 0)
goto requeue_and_leave;
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
- _leave(" [EPROTO]");
goto out;
}
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 9f4cfa2..45dba73 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -30,7 +30,7 @@
static void rxrpc_proto_abort(const char *why,
struct rxrpc_call *call, rxrpc_seq_t seq)
{
- if (rxrpc_abort_call(why, call, seq, RX_PROTOCOL_ERROR, EBADMSG)) {
+ if (rxrpc_abort_call(why, call, seq, RX_PROTOCOL_ERROR, -EBADMSG)) {
set_bit(RXRPC_CALL_EV_ABORT, &call->events);
rxrpc_queue_call(call);
}
@@ -420,6 +420,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb,
u16 skew)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+ enum rxrpc_call_state state;
unsigned int offset = sizeof(struct rxrpc_wire_header);
unsigned int ix;
rxrpc_serial_t serial = sp->hdr.serial, ack_serial = 0;
@@ -434,14 +435,15 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb,
_proto("Rx DATA %%%u { #%u f=%02x }",
sp->hdr.serial, seq, sp->hdr.flags);
- if (call->state >= RXRPC_CALL_COMPLETE)
+ state = READ_ONCE(call->state);
+ if (state >= RXRPC_CALL_COMPLETE)
return;
/* Received data implicitly ACKs all of the request packets we sent
* when we're acting as a client.
*/
- if ((call->state == RXRPC_CALL_CLIENT_SEND_REQUEST ||
- call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY) &&
+ if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST ||
+ state == RXRPC_CALL_CLIENT_AWAIT_REPLY) &&
!rxrpc_receiving_reply(call))
return;
@@ -650,6 +652,7 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rxrpc_peer *peer;
unsigned int mtu;
+ bool wake = false;
u32 rwind = ntohl(ackinfo->rwind);
_proto("Rx ACK %%%u Info { rx=%u max=%u rwin=%u jm=%u }",
@@ -657,9 +660,16 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU),
rwind, ntohl(ackinfo->jumbo_max));
- if (rwind > RXRPC_RXTX_BUFF_SIZE - 1)
- rwind = RXRPC_RXTX_BUFF_SIZE - 1;
- call->tx_winsize = rwind;
+ if (call->tx_winsize != rwind) {
+ if (rwind > RXRPC_RXTX_BUFF_SIZE - 1)
+ rwind = RXRPC_RXTX_BUFF_SIZE - 1;
+ if (rwind > call->tx_winsize)
+ wake = true;
+ trace_rxrpc_rx_rwind_change(call, sp->hdr.serial,
+ ntohl(ackinfo->rwind), wake);
+ call->tx_winsize = rwind;
+ }
+
if (call->cong_ssthresh > rwind)
call->cong_ssthresh = rwind;
@@ -673,6 +683,9 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
spin_unlock_bh(&peer->lock);
_net("Net MTU %u (maxdata %u)", peer->mtu, peer->maxdata);
}
+
+ if (wake)
+ wake_up(&call->waitq);
}
/*
@@ -799,7 +812,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
return rxrpc_proto_abort("AK0", call, 0);
/* Ignore ACKs unless we are or have just been transmitting. */
- switch (call->state) {
+ switch (READ_ONCE(call->state)) {
case RXRPC_CALL_CLIENT_SEND_REQUEST:
case RXRPC_CALL_CLIENT_AWAIT_REPLY:
case RXRPC_CALL_SERVER_SEND_REPLY:
@@ -866,7 +879,7 @@ static void rxrpc_input_ackall(struct rxrpc_call *call, struct sk_buff *skb)
}
/*
- * Process an ABORT packet.
+ * Process an ABORT packet directed at a call.
*/
static void rxrpc_input_abort(struct rxrpc_call *call, struct sk_buff *skb)
{
@@ -881,10 +894,12 @@ static void rxrpc_input_abort(struct rxrpc_call *call, struct sk_buff *skb)
&wtmp, sizeof(wtmp)) >= 0)
abort_code = ntohl(wtmp);
+ trace_rxrpc_rx_abort(call, sp->hdr.serial, abort_code);
+
_proto("Rx ABORT %%%u { %x }", sp->hdr.serial, abort_code);
if (rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED,
- abort_code, ECONNABORTED))
+ abort_code, -ECONNABORTED))
rxrpc_notify_socket(call);
}
@@ -940,14 +955,14 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call,
static void rxrpc_input_implicit_end_call(struct rxrpc_connection *conn,
struct rxrpc_call *call)
{
- switch (call->state) {
+ switch (READ_ONCE(call->state)) {
case RXRPC_CALL_SERVER_AWAIT_ACK:
rxrpc_call_completed(call);
break;
case RXRPC_CALL_COMPLETE:
break;
default:
- if (rxrpc_abort_call("IMP", call, 0, RX_CALL_DEAD, ESHUTDOWN)) {
+ if (rxrpc_abort_call("IMP", call, 0, RX_CALL_DEAD, -ESHUTDOWN)) {
set_bit(RXRPC_CALL_EV_ABORT, &call->events);
rxrpc_queue_call(call);
}
@@ -1006,8 +1021,11 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb)
struct rxrpc_wire_header whdr;
/* dig out the RxRPC connection details */
- if (skb_copy_bits(skb, 0, &whdr, sizeof(whdr)) < 0)
+ if (skb_copy_bits(skb, 0, &whdr, sizeof(whdr)) < 0) {
+ trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
+ tracepoint_string("bad_hdr"));
return -EBADMSG;
+ }
memset(sp, 0, sizeof(*sp));
sp->hdr.epoch = ntohl(whdr.epoch);
diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c
index 7d4375e..af276f1 100644
--- a/net/rxrpc/insecure.c
+++ b/net/rxrpc/insecure.c
@@ -46,7 +46,10 @@ static int none_respond_to_challenge(struct rxrpc_connection *conn,
struct sk_buff *skb,
u32 *_abort_code)
{
- *_abort_code = RX_PROTOCOL_ERROR;
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+ trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
+ tracepoint_string("chall_none"));
return -EPROTO;
}
@@ -54,7 +57,10 @@ static int none_verify_response(struct rxrpc_connection *conn,
struct sk_buff *skb,
u32 *_abort_code)
{
- *_abort_code = RX_PROTOCOL_ERROR;
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+ trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
+ tracepoint_string("resp_none"));
return -EPROTO;
}
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index bf13b84..1ed9c0c 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -296,7 +296,7 @@ void rxrpc_peer_error_distributor(struct work_struct *work)
hlist_del_init(&call->error_link);
rxrpc_see_call(call);
- if (rxrpc_set_call_completion(call, compl, 0, error))
+ if (rxrpc_set_call_completion(call, compl, 0, -error))
rxrpc_notify_socket(call);
}
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 6491ca4..f9caf3b 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -83,11 +83,11 @@ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg)
ret = put_cmsg(msg, SOL_RXRPC, RXRPC_ABORT, 4, &tmp);
break;
case RXRPC_CALL_NETWORK_ERROR:
- tmp = call->error;
+ tmp = -call->error;
ret = put_cmsg(msg, SOL_RXRPC, RXRPC_NET_ERROR, 4, &tmp);
break;
case RXRPC_CALL_LOCAL_ERROR:
- tmp = call->error;
+ tmp = -call->error;
ret = put_cmsg(msg, SOL_RXRPC, RXRPC_LOCAL_ERROR, 4, &tmp);
break;
default:
@@ -527,7 +527,7 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
msg->msg_namelen = len;
}
- switch (call->state) {
+ switch (READ_ONCE(call->state)) {
case RXRPC_CALL_SERVER_ACCEPTING:
ret = rxrpc_recvmsg_new_call(rx, call, msg, flags);
break;
@@ -640,7 +640,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
mutex_lock(&call->user_mutex);
- switch (call->state) {
+ switch (READ_ONCE(call->state)) {
case RXRPC_CALL_CLIENT_RECV_REPLY:
case RXRPC_CALL_SERVER_RECV_REQUEST:
case RXRPC_CALL_SERVER_ACK_REQUEST:
@@ -682,14 +682,16 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
return ret;
short_data:
+ trace_rxrpc_rx_eproto(call, 0, tracepoint_string("short_data"));
ret = -EBADMSG;
goto out;
excess_data:
+ trace_rxrpc_rx_eproto(call, 0, tracepoint_string("excess_data"));
ret = -EMSGSIZE;
goto out;
call_complete:
*_abort = call->abort_code;
- ret = -call->error;
+ ret = call->error;
if (call->completion == RXRPC_CALL_SUCCEEDED) {
ret = 1;
if (size > 0)
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index 4374e7b..1bb9b2c 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -148,15 +148,13 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call,
u32 data_size,
void *sechdr)
{
- struct rxrpc_skb_priv *sp;
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher);
struct rxkad_level1_hdr hdr;
struct rxrpc_crypt iv;
struct scatterlist sg;
u16 check;
- sp = rxrpc_skb(skb);
-
_enter("");
check = sp->hdr.seq ^ call->call_id;
@@ -323,6 +321,7 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb,
struct rxrpc_crypt iv;
struct scatterlist sg[16];
struct sk_buff *trailer;
+ bool aborted;
u32 data_size, buf;
u16 check;
int nsg;
@@ -330,7 +329,8 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb,
_enter("");
if (len < 8) {
- rxrpc_abort_call("V1H", call, seq, RXKADSEALEDINCON, EPROTO);
+ aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_hdr", "V1H",
+ RXKADSEALEDINCON);
goto protocol_error;
}
@@ -355,7 +355,8 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb,
/* Extract the decrypted packet length */
if (skb_copy_bits(skb, offset, &sechdr, sizeof(sechdr)) < 0) {
- rxrpc_abort_call("XV1", call, seq, RXKADDATALEN, EPROTO);
+ aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_len", "XV1",
+ RXKADDATALEN);
goto protocol_error;
}
offset += sizeof(sechdr);
@@ -368,12 +369,14 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb,
check ^= seq ^ call->call_id;
check &= 0xffff;
if (check != 0) {
- rxrpc_abort_call("V1C", call, seq, RXKADSEALEDINCON, EPROTO);
+ aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_check", "V1C",
+ RXKADSEALEDINCON);
goto protocol_error;
}
if (data_size > len) {
- rxrpc_abort_call("V1L", call, seq, RXKADDATALEN, EPROTO);
+ aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_datalen", "V1L",
+ RXKADDATALEN);
goto protocol_error;
}
@@ -381,8 +384,8 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb,
return 0;
protocol_error:
- rxrpc_send_abort_packet(call);
- _leave(" = -EPROTO");
+ if (aborted)
+ rxrpc_send_abort_packet(call);
return -EPROTO;
nomem:
@@ -403,6 +406,7 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb,
struct rxrpc_crypt iv;
struct scatterlist _sg[4], *sg;
struct sk_buff *trailer;
+ bool aborted;
u32 data_size, buf;
u16 check;
int nsg;
@@ -410,7 +414,8 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb,
_enter(",{%d}", skb->len);
if (len < 8) {
- rxrpc_abort_call("V2H", call, seq, RXKADSEALEDINCON, EPROTO);
+ aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_hdr", "V2H",
+ RXKADSEALEDINCON);
goto protocol_error;
}
@@ -445,7 +450,8 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb,
/* Extract the decrypted packet length */
if (skb_copy_bits(skb, offset, &sechdr, sizeof(sechdr)) < 0) {
- rxrpc_abort_call("XV2", call, seq, RXKADDATALEN, EPROTO);
+ aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_len", "XV2",
+ RXKADDATALEN);
goto protocol_error;
}
offset += sizeof(sechdr);
@@ -458,12 +464,14 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb,
check ^= seq ^ call->call_id;
check &= 0xffff;
if (check != 0) {
- rxrpc_abort_call("V2C", call, seq, RXKADSEALEDINCON, EPROTO);
+ aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_check", "V2C",
+ RXKADSEALEDINCON);
goto protocol_error;
}
if (data_size > len) {
- rxrpc_abort_call("V2L", call, seq, RXKADDATALEN, EPROTO);
+ aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_datalen", "V2L",
+ RXKADDATALEN);
goto protocol_error;
}
@@ -471,8 +479,8 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb,
return 0;
protocol_error:
- rxrpc_send_abort_packet(call);
- _leave(" = -EPROTO");
+ if (aborted)
+ rxrpc_send_abort_packet(call);
return -EPROTO;
nomem:
@@ -491,6 +499,7 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb,
SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher);
struct rxrpc_crypt iv;
struct scatterlist sg;
+ bool aborted;
u16 cksum;
u32 x, y;
@@ -522,10 +531,9 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb,
cksum = 1; /* zero checksums are not permitted */
if (cksum != expected_cksum) {
- rxrpc_abort_call("VCK", call, seq, RXKADSEALEDINCON, EPROTO);
- rxrpc_send_abort_packet(call);
- _leave(" = -EPROTO [csum failed]");
- return -EPROTO;
+ aborted = rxrpc_abort_eproto(call, skb, "rxkad_csum", "VCK",
+ RXKADSEALEDINCON);
+ goto protocol_error;
}
switch (call->conn->params.security_level) {
@@ -538,6 +546,11 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb,
default:
return -ENOANO;
}
+
+protocol_error:
+ if (aborted)
+ rxrpc_send_abort_packet(call);
+ return -EPROTO;
}
/*
@@ -754,22 +767,23 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn,
struct rxkad_response resp
__attribute__((aligned(8))); /* must be aligned for crypto */
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+ const char *eproto;
u32 version, nonce, min_level, abort_code;
int ret;
_enter("{%d,%x}", conn->debug_id, key_serial(conn->params.key));
- if (!conn->params.key) {
- _leave(" = -EPROTO [no key]");
- return -EPROTO;
- }
+ eproto = tracepoint_string("chall_no_key");
+ abort_code = RX_PROTOCOL_ERROR;
+ if (!conn->params.key)
+ goto protocol_error;
+ abort_code = RXKADEXPIRED;
ret = key_validate(conn->params.key);
- if (ret < 0) {
- *_abort_code = RXKADEXPIRED;
- return ret;
- }
+ if (ret < 0)
+ goto other_error;
+ eproto = tracepoint_string("chall_short");
abort_code = RXKADPACKETSHORT;
if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
&challenge, sizeof(challenge)) < 0)
@@ -782,13 +796,15 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn,
_proto("Rx CHALLENGE %%%u { v=%u n=%u ml=%u }",
sp->hdr.serial, version, nonce, min_level);
+ eproto = tracepoint_string("chall_ver");
abort_code = RXKADINCONSISTENCY;
if (version != RXKAD_VERSION)
goto protocol_error;
abort_code = RXKADLEVELFAIL;
+ ret = -EACCES;
if (conn->params.security_level < min_level)
- goto protocol_error;
+ goto other_error;
token = conn->params.key->payload.data[0];
@@ -815,28 +831,34 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn,
return rxkad_send_response(conn, &sp->hdr, &resp, token->kad);
protocol_error:
+ trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto);
+ ret = -EPROTO;
+other_error:
*_abort_code = abort_code;
- _leave(" = -EPROTO [%d]", abort_code);
- return -EPROTO;
+ return ret;
}
/*
* decrypt the kerberos IV ticket in the response
*/
static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
+ struct sk_buff *skb,
void *ticket, size_t ticket_len,
struct rxrpc_crypt *_session_key,
time_t *_expiry,
u32 *_abort_code)
{
struct skcipher_request *req;
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rxrpc_crypt iv, key;
struct scatterlist sg[1];
struct in_addr addr;
unsigned int life;
+ const char *eproto;
time_t issue, now;
bool little_endian;
int ret;
+ u32 abort_code;
u8 *p, *q, *name, *end;
_enter("{%d},{%x}", conn->debug_id, key_serial(conn->server_key));
@@ -847,11 +869,11 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
if (ret < 0) {
switch (ret) {
case -EKEYEXPIRED:
- *_abort_code = RXKADEXPIRED;
- goto error;
+ abort_code = RXKADEXPIRED;
+ goto other_error;
default:
- *_abort_code = RXKADNOAUTH;
- goto error;
+ abort_code = RXKADNOAUTH;
+ goto other_error;
}
}
@@ -860,13 +882,11 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
memcpy(&iv, &conn->server_key->payload.data[2], sizeof(iv));
+ ret = -ENOMEM;
req = skcipher_request_alloc(conn->server_key->payload.data[0],
GFP_NOFS);
- if (!req) {
- *_abort_code = RXKADNOAUTH;
- ret = -ENOMEM;
- goto error;
- }
+ if (!req)
+ goto temporary_error;
sg_init_one(&sg[0], ticket, ticket_len);
skcipher_request_set_callback(req, 0, NULL, NULL);
@@ -877,11 +897,12 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
p = ticket;
end = p + ticket_len;
-#define Z(size) \
+#define Z(field) \
({ \
u8 *__str = p; \
+ eproto = tracepoint_string("rxkad_bad_"#field); \
q = memchr(p, 0, end - p); \
- if (!q || q - p > (size)) \
+ if (!q || q - p > (field##_SZ)) \
goto bad_ticket; \
for (; p < q; p++) \
if (!isprint(*p)) \
@@ -896,17 +917,18 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
p++;
/* extract the authentication name */
- name = Z(ANAME_SZ);
+ name = Z(ANAME);
_debug("KIV ANAME: %s", name);
/* extract the principal's instance */
- name = Z(INST_SZ);
+ name = Z(INST);
_debug("KIV INST : %s", name);
/* extract the principal's authentication domain */
- name = Z(REALM_SZ);
+ name = Z(REALM);
_debug("KIV REALM: %s", name);
+ eproto = tracepoint_string("rxkad_bad_len");
if (end - p < 4 + 8 + 4 + 2)
goto bad_ticket;
@@ -941,36 +963,37 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
/* check the ticket is in date */
if (issue > now) {
- *_abort_code = RXKADNOAUTH;
+ abort_code = RXKADNOAUTH;
ret = -EKEYREJECTED;
- goto error;
+ goto other_error;
}
if (issue < now - life) {
- *_abort_code = RXKADEXPIRED;
+ abort_code = RXKADEXPIRED;
ret = -EKEYEXPIRED;
- goto error;
+ goto other_error;
}
*_expiry = issue + life;
/* get the service name */
- name = Z(SNAME_SZ);
+ name = Z(SNAME);
_debug("KIV SNAME: %s", name);
/* get the service instance name */
- name = Z(INST_SZ);
+ name = Z(INST);
_debug("KIV SINST: %s", name);
-
- ret = 0;
-error:
- _leave(" = %d", ret);
- return ret;
+ return 0;
bad_ticket:
- *_abort_code = RXKADBADTICKET;
- ret = -EBADMSG;
- goto error;
+ trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto);
+ abort_code = RXKADBADTICKET;
+ ret = -EPROTO;
+other_error:
+ *_abort_code = abort_code;
+ return ret;
+temporary_error:
+ return ret;
}
/*
@@ -1020,6 +1043,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
__attribute__((aligned(8))); /* must be aligned for crypto */
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rxrpc_crypt session_key;
+ const char *eproto;
time_t expiry;
void *ticket;
u32 abort_code, version, kvno, ticket_len, level;
@@ -1028,6 +1052,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
_enter("{%d,%x}", conn->debug_id, key_serial(conn->server_key));
+ eproto = tracepoint_string("rxkad_rsp_short");
abort_code = RXKADPACKETSHORT;
if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
&response, sizeof(response)) < 0)
@@ -1041,40 +1066,43 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
_proto("Rx RESPONSE %%%u { v=%u kv=%u tl=%u }",
sp->hdr.serial, version, kvno, ticket_len);
+ eproto = tracepoint_string("rxkad_rsp_ver");
abort_code = RXKADINCONSISTENCY;
if (version != RXKAD_VERSION)
goto protocol_error;
+ eproto = tracepoint_string("rxkad_rsp_tktlen");
abort_code = RXKADTICKETLEN;
if (ticket_len < 4 || ticket_len > MAXKRB5TICKETLEN)
goto protocol_error;
+ eproto = tracepoint_string("rxkad_rsp_unkkey");
abort_code = RXKADUNKNOWNKEY;
if (kvno >= RXKAD_TKT_TYPE_KERBEROS_V5)
goto protocol_error;
/* extract the kerberos ticket and decrypt and decode it */
+ ret = -ENOMEM;
ticket = kmalloc(ticket_len, GFP_NOFS);
if (!ticket)
- return -ENOMEM;
+ goto temporary_error;
+ eproto = tracepoint_string("rxkad_tkt_short");
abort_code = RXKADPACKETSHORT;
if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
ticket, ticket_len) < 0)
goto protocol_error_free;
- ret = rxkad_decrypt_ticket(conn, ticket, ticket_len, &session_key,
- &expiry, &abort_code);
- if (ret < 0) {
- *_abort_code = abort_code;
- kfree(ticket);
- return ret;
- }
+ ret = rxkad_decrypt_ticket(conn, skb, ticket, ticket_len, &session_key,
+ &expiry, _abort_code);
+ if (ret < 0)
+ goto temporary_error_free;
/* use the session key from inside the ticket to decrypt the
* response */
rxkad_decrypt_response(conn, &response, &session_key);
+ eproto = tracepoint_string("rxkad_rsp_param");
abort_code = RXKADSEALEDINCON;
if (ntohl(response.encrypted.epoch) != conn->proto.epoch)
goto protocol_error_free;
@@ -1085,6 +1113,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
csum = response.encrypted.checksum;
response.encrypted.checksum = 0;
rxkad_calc_response_checksum(&response);
+ eproto = tracepoint_string("rxkad_rsp_csum");
if (response.encrypted.checksum != csum)
goto protocol_error_free;
@@ -1093,11 +1122,15 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
struct rxrpc_call *call;
u32 call_id = ntohl(response.encrypted.call_id[i]);
+ eproto = tracepoint_string("rxkad_rsp_callid");
if (call_id > INT_MAX)
goto protocol_error_unlock;
+ eproto = tracepoint_string("rxkad_rsp_callctr");
if (call_id < conn->channels[i].call_counter)
goto protocol_error_unlock;
+
+ eproto = tracepoint_string("rxkad_rsp_callst");
if (call_id > conn->channels[i].call_counter) {
call = rcu_dereference_protected(
conn->channels[i].call,
@@ -1109,10 +1142,12 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
}
spin_unlock(&conn->channel_lock);
+ eproto = tracepoint_string("rxkad_rsp_seq");
abort_code = RXKADOUTOFSEQUENCE;
if (ntohl(response.encrypted.inc_nonce) != conn->security_nonce + 1)
goto protocol_error_free;
+ eproto = tracepoint_string("rxkad_rsp_level");
abort_code = RXKADLEVELFAIL;
level = ntohl(response.encrypted.level);
if (level > RXRPC_SECURITY_ENCRYPT)
@@ -1123,10 +1158,8 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
* this the connection security can be handled in exactly the same way
* as for a client connection */
ret = rxrpc_get_server_data_key(conn, &session_key, expiry, kvno);
- if (ret < 0) {
- kfree(ticket);
- return ret;
- }
+ if (ret < 0)
+ goto temporary_error_free;
kfree(ticket);
_leave(" = 0");
@@ -1137,9 +1170,18 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
protocol_error_free:
kfree(ticket);
protocol_error:
+ trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto);
*_abort_code = abort_code;
- _leave(" = -EPROTO [%d]", abort_code);
return -EPROTO;
+
+temporary_error_free:
+ kfree(ticket);
+temporary_error:
+ /* Ignore the response packet if we got a temporary error such as
+ * ENOMEM. We just want to send the challenge again. Note that we
+ * also come out this way if the ticket decryption fails.
+ */
+ return ret;
}
/*
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index bc2d3dc..96ffa5d 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -488,6 +488,7 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
__releases(&rx->sk.sk_lock.slock)
{
+ enum rxrpc_call_state state;
enum rxrpc_command cmd;
struct rxrpc_call *call;
unsigned long user_call_ID = 0;
@@ -526,13 +527,17 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
return PTR_ERR(call);
/* ... and we have the call lock. */
} else {
- ret = -EBUSY;
- if (call->state == RXRPC_CALL_UNINITIALISED ||
- call->state == RXRPC_CALL_CLIENT_AWAIT_CONN ||
- call->state == RXRPC_CALL_SERVER_PREALLOC ||
- call->state == RXRPC_CALL_SERVER_SECURING ||
- call->state == RXRPC_CALL_SERVER_ACCEPTING)
+ switch (READ_ONCE(call->state)) {
+ case RXRPC_CALL_UNINITIALISED:
+ case RXRPC_CALL_CLIENT_AWAIT_CONN:
+ case RXRPC_CALL_SERVER_PREALLOC:
+ case RXRPC_CALL_SERVER_SECURING:
+ case RXRPC_CALL_SERVER_ACCEPTING:
+ ret = -EBUSY;
goto error_release_sock;
+ default:
+ break;
+ }
ret = mutex_lock_interruptible(&call->user_mutex);
release_sock(&rx->sk);
@@ -542,25 +547,26 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
}
}
+ state = READ_ONCE(call->state);
_debug("CALL %d USR %lx ST %d on CONN %p",
- call->debug_id, call->user_call_ID, call->state, call->conn);
+ call->debug_id, call->user_call_ID, state, call->conn);
- if (call->state >= RXRPC_CALL_COMPLETE) {
+ if (state >= RXRPC_CALL_COMPLETE) {
/* it's too late for this call */
ret = -ESHUTDOWN;
} else if (cmd == RXRPC_CMD_SEND_ABORT) {
ret = 0;
- if (rxrpc_abort_call("CMD", call, 0, abort_code, ECONNABORTED))
+ if (rxrpc_abort_call("CMD", call, 0, abort_code, -ECONNABORTED))
ret = rxrpc_send_abort_packet(call);
} else if (cmd != RXRPC_CMD_SEND_DATA) {
ret = -EINVAL;
} else if (rxrpc_is_client_call(call) &&
- call->state != RXRPC_CALL_CLIENT_SEND_REQUEST) {
+ state != RXRPC_CALL_CLIENT_SEND_REQUEST) {
/* request phase complete for this client call */
ret = -EPROTO;
} else if (rxrpc_is_service_call(call) &&
- call->state != RXRPC_CALL_SERVER_ACK_REQUEST &&
- call->state != RXRPC_CALL_SERVER_SEND_REPLY) {
+ state != RXRPC_CALL_SERVER_ACK_REQUEST &&
+ state != RXRPC_CALL_SERVER_SEND_REPLY) {
/* Reply phase not begun or not complete for service call. */
ret = -EPROTO;
} else {
@@ -605,14 +611,22 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
_debug("CALL %d USR %lx ST %d on CONN %p",
call->debug_id, call->user_call_ID, call->state, call->conn);
- if (call->state >= RXRPC_CALL_COMPLETE) {
- ret = -ESHUTDOWN; /* it's too late for this call */
- } else if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST &&
- call->state != RXRPC_CALL_SERVER_ACK_REQUEST &&
- call->state != RXRPC_CALL_SERVER_SEND_REPLY) {
- ret = -EPROTO; /* request phase complete for this client call */
- } else {
+ switch (READ_ONCE(call->state)) {
+ case RXRPC_CALL_CLIENT_SEND_REQUEST:
+ case RXRPC_CALL_SERVER_ACK_REQUEST:
+ case RXRPC_CALL_SERVER_SEND_REPLY:
ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len);
+ break;
+ case RXRPC_CALL_COMPLETE:
+ read_lock_bh(&call->state_lock);
+ ret = -call->error;
+ read_unlock_bh(&call->state_lock);
+ break;
+ default:
+ /* Request phase complete for this client call */
+ trace_rxrpc_rx_eproto(call, 0, tracepoint_string("late_send"));
+ ret = -EPROTO;
+ break;
}
mutex_unlock(&call->user_mutex);
@@ -629,20 +643,24 @@ EXPORT_SYMBOL(rxrpc_kernel_send_data);
* @error: Local error value
* @why: 3-char string indicating why.
*
- * Allow a kernel service to abort a call, if it's still in an abortable state.
+ * Allow a kernel service to abort a call, if it's still in an abortable state
+ * and return true if the call was aborted, false if it was already complete.
*/
-void rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call,
+bool rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call,
u32 abort_code, int error, const char *why)
{
+ bool aborted;
+
_enter("{%d},%d,%d,%s", call->debug_id, abort_code, error, why);
mutex_lock(&call->user_mutex);
- if (rxrpc_abort_call(why, call, 0, abort_code, error))
+ aborted = rxrpc_abort_call(why, call, 0, abort_code, error);
+ if (aborted)
rxrpc_send_abort_packet(call);
mutex_unlock(&call->user_mutex);
- _leave("");
+ return aborted;
}
EXPORT_SYMBOL(rxrpc_kernel_abort_call);
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index ab80629..f9bb43c 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -113,6 +113,9 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
if (ret < 0)
return ret;
+ if (!tb[TCA_CONNMARK_PARMS])
+ return -EINVAL;
+
parm = nla_data(tb[TCA_CONNMARK_PARMS]);
if (!tcf_hash_check(tn, parm->index, a, bind)) {
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index e978ccd4..6c319a4 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -181,6 +181,9 @@ static int tcf_csum_ipv4_tcp(struct sk_buff *skb, unsigned int ihl,
struct tcphdr *tcph;
const struct iphdr *iph;
+ if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
+ return 1;
+
tcph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*tcph));
if (tcph == NULL)
return 0;
@@ -202,6 +205,9 @@ static int tcf_csum_ipv6_tcp(struct sk_buff *skb, unsigned int ihl,
struct tcphdr *tcph;
const struct ipv6hdr *ip6h;
+ if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
+ return 1;
+
tcph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*tcph));
if (tcph == NULL)
return 0;
@@ -225,6 +231,9 @@ static int tcf_csum_ipv4_udp(struct sk_buff *skb, unsigned int ihl,
const struct iphdr *iph;
u16 ul;
+ if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+ return 1;
+
/*
* Support both UDP and UDPLITE checksum algorithms, Don't use
* udph->len to get the real length without any protocol check,
@@ -278,6 +287,9 @@ static int tcf_csum_ipv6_udp(struct sk_buff *skb, unsigned int ihl,
const struct ipv6hdr *ip6h;
u16 ul;
+ if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+ return 1;
+
/*
* Support both UDP and UDPLITE checksum algorithms, Don't use
* udph->len to get the real length without any protocol check,
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 71e7ff22..c75ea5c 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -603,8 +603,8 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind,
return -1;
}
-int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife,
- u16 metaid, u16 mlen, void *mdata)
+static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife,
+ u16 metaid, u16 mlen, void *mdata)
{
struct tcf_meta_info *e;
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 3b7074e..c736627 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -228,7 +228,6 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a,
return skb->len;
nla_put_failure:
- rcu_read_unlock();
nlmsg_trim(skb, b);
return -1;
}
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 3d6b928..ca193af 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -508,9 +508,8 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
get_random_bytes(&fnew->hashrnd, 4);
}
- fnew->perturb_timer.function = flow_perturbation;
- fnew->perturb_timer.data = (unsigned long)fnew;
- init_timer_deferrable(&fnew->perturb_timer);
+ setup_deferrable_timer(&fnew->perturb_timer, flow_perturbation,
+ (unsigned long)fnew);
tcf_exts_change(tp, &fnew->exts, &e);
tcf_em_tree_change(tp, &fnew->ematches, &t);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index bcf49cd..62567bf 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -274,7 +274,7 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
return NULL;
}
-void qdisc_hash_add(struct Qdisc *q)
+void qdisc_hash_add(struct Qdisc *q, bool invisible)
{
if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) {
struct Qdisc *root = qdisc_dev(q)->qdisc;
@@ -282,6 +282,8 @@ void qdisc_hash_add(struct Qdisc *q)
WARN_ON_ONCE(root == &noop_qdisc);
ASSERT_RTNL();
hash_add_rcu(qdisc_dev(q)->qdisc_hash, &q->hash, q->handle);
+ if (invisible)
+ q->flags |= TCQ_F_INVISIBLE;
}
}
EXPORT_SYMBOL(qdisc_hash_add);
@@ -1003,7 +1005,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev,
goto err_out4;
}
- qdisc_hash_add(sch);
+ qdisc_hash_add(sch, false);
return sch;
}
@@ -1401,9 +1403,14 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
return -1;
}
-static bool tc_qdisc_dump_ignore(struct Qdisc *q)
+static bool tc_qdisc_dump_ignore(struct Qdisc *q, bool dump_invisible)
{
- return (q->flags & TCQ_F_BUILTIN) ? true : false;
+ if (q->flags & TCQ_F_BUILTIN)
+ return true;
+ if ((q->flags & TCQ_F_INVISIBLE) && !dump_invisible)
+ return true;
+
+ return false;
}
static int qdisc_notify(struct net *net, struct sk_buff *oskb,
@@ -1417,12 +1424,12 @@ static int qdisc_notify(struct net *net, struct sk_buff *oskb,
if (!skb)
return -ENOBUFS;
- if (old && !tc_qdisc_dump_ignore(old)) {
+ if (old && !tc_qdisc_dump_ignore(old, false)) {
if (tc_fill_qdisc(skb, old, clid, portid, n->nlmsg_seq,
0, RTM_DELQDISC) < 0)
goto err_out;
}
- if (new && !tc_qdisc_dump_ignore(new)) {
+ if (new && !tc_qdisc_dump_ignore(new, false)) {
if (tc_fill_qdisc(skb, new, clid, portid, n->nlmsg_seq,
old ? NLM_F_REPLACE : 0, RTM_NEWQDISC) < 0)
goto err_out;
@@ -1439,7 +1446,8 @@ static int qdisc_notify(struct net *net, struct sk_buff *oskb,
static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb,
struct netlink_callback *cb,
- int *q_idx_p, int s_q_idx, bool recur)
+ int *q_idx_p, int s_q_idx, bool recur,
+ bool dump_invisible)
{
int ret = 0, q_idx = *q_idx_p;
struct Qdisc *q;
@@ -1452,7 +1460,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb,
if (q_idx < s_q_idx) {
q_idx++;
} else {
- if (!tc_qdisc_dump_ignore(q) &&
+ if (!tc_qdisc_dump_ignore(q, dump_invisible) &&
tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
RTM_NEWQDISC) <= 0)
@@ -1474,7 +1482,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb,
q_idx++;
continue;
}
- if (!tc_qdisc_dump_ignore(q) &&
+ if (!tc_qdisc_dump_ignore(q, dump_invisible) &&
tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
RTM_NEWQDISC) <= 0)
@@ -1496,12 +1504,21 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb)
int idx, q_idx;
int s_idx, s_q_idx;
struct net_device *dev;
+ const struct nlmsghdr *nlh = cb->nlh;
+ struct tcmsg *tcm = nlmsg_data(nlh);
+ struct nlattr *tca[TCA_MAX + 1];
+ int err;
s_idx = cb->args[0];
s_q_idx = q_idx = cb->args[1];
idx = 0;
ASSERT_RTNL();
+
+ err = nlmsg_parse(nlh, sizeof(*tcm), tca, TCA_MAX, NULL);
+ if (err < 0)
+ return err;
+
for_each_netdev(net, dev) {
struct netdev_queue *dev_queue;
@@ -1512,13 +1529,14 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb)
q_idx = 0;
if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx,
- true) < 0)
+ true, tca[TCA_DUMP_INVISIBLE]) < 0)
goto done;
dev_queue = dev_ingress_queue(dev);
if (dev_queue &&
tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb,
- &q_idx, s_q_idx, false) < 0)
+ &q_idx, s_q_idx, false,
+ tca[TCA_DUMP_INVISIBLE]) < 0)
goto done;
cont:
@@ -1762,7 +1780,7 @@ static int tc_dump_tclass_qdisc(struct Qdisc *q, struct sk_buff *skb,
{
struct qdisc_dump_args arg;
- if (tc_qdisc_dump_ignore(q) ||
+ if (tc_qdisc_dump_ignore(q, false) ||
*t_p < s_t || !q->ops->cl_ops ||
(tcm->tcm_parent &&
TC_H_MAJ(tcm->tcm_parent) != q->handle)) {
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index d6ca18dc..cf93e5f 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1161,6 +1161,8 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt)
sch->handle);
if (!q->link.q)
q->link.q = &noop_qdisc;
+ else
+ qdisc_hash_add(q->link.q, true);
q->link.priority = TC_CBQ_MAXPRIO - 1;
q->link.priority2 = TC_CBQ_MAXPRIO - 1;
@@ -1600,6 +1602,9 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
cl->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid);
if (!cl->q)
cl->q = &noop_qdisc;
+ else
+ qdisc_hash_add(cl->q, true);
+
cl->common.classid = classid;
cl->tparent = parent;
cl->qdisc = sch;
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index 3b86a97..593183a 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -58,7 +58,6 @@ struct choke_sched_data {
/* Variables */
struct red_vars vars;
- struct tcf_proto __rcu *filter_list;
struct {
u32 prob_drop; /* Early probability drops */
u32 prob_mark; /* Early probability marks */
@@ -152,11 +151,6 @@ static inline void choke_set_classid(struct sk_buff *skb, u16 classid)
choke_skb_cb(skb)->classid = classid;
}
-static u16 choke_get_classid(const struct sk_buff *skb)
-{
- return choke_skb_cb(skb)->classid;
-}
-
/*
* Compare flow of two packets
* Returns true only if source and destination address and port match.
@@ -188,40 +182,6 @@ static bool choke_match_flow(struct sk_buff *skb1,
}
/*
- * Classify flow using either:
- * 1. pre-existing classification result in skb
- * 2. fast internal classification
- * 3. use TC filter based classification
- */
-static bool choke_classify(struct sk_buff *skb,
- struct Qdisc *sch, int *qerr)
-
-{
- struct choke_sched_data *q = qdisc_priv(sch);
- struct tcf_result res;
- struct tcf_proto *fl;
- int result;
-
- fl = rcu_dereference_bh(q->filter_list);
- result = tc_classify(skb, fl, &res, false);
- if (result >= 0) {
-#ifdef CONFIG_NET_CLS_ACT
- switch (result) {
- case TC_ACT_STOLEN:
- case TC_ACT_QUEUED:
- *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
- case TC_ACT_SHOT:
- return false;
- }
-#endif
- choke_set_classid(skb, TC_H_MIN(res.classid));
- return true;
- }
-
- return false;
-}
-
-/*
* Select a packet at random from queue
* HACK: since queue can have holes from previous deletion; retry several
* times to find a random skb but then just give up and return the head
@@ -257,25 +217,15 @@ static bool choke_match_random(const struct choke_sched_data *q,
return false;
oskb = choke_peek_random(q, pidx);
- if (rcu_access_pointer(q->filter_list))
- return choke_get_classid(nskb) == choke_get_classid(oskb);
-
return choke_match_flow(oskb, nskb);
}
static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct sk_buff **to_free)
{
- int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
struct choke_sched_data *q = qdisc_priv(sch);
const struct red_parms *p = &q->parms;
- if (rcu_access_pointer(q->filter_list)) {
- /* If using external classifiers, get result and record it. */
- if (!choke_classify(skb, sch, &ret))
- goto other_drop; /* Packet was eaten by filter */
- }
-
choke_skb_cb(skb)->keys_valid = 0;
/* Compute average queue usage (see RED) */
q->vars.qavg = red_calc_qavg(p, &q->vars, sch->q.qlen);
@@ -339,12 +289,6 @@ static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch,
congestion_drop:
qdisc_drop(skb, sch, to_free);
return NET_XMIT_CN;
-
-other_drop:
- if (ret & __NET_XMIT_BYPASS)
- qdisc_qstats_drop(sch);
- __qdisc_drop(skb, to_free);
- return ret;
}
static struct sk_buff *choke_dequeue(struct Qdisc *sch)
@@ -538,7 +482,6 @@ static void choke_destroy(struct Qdisc *sch)
{
struct choke_sched_data *q = qdisc_priv(sch);
- tcf_destroy_chain(&q->filter_list);
choke_free(q->tab);
}
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index bb4cbdf..9fe67e2 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -117,6 +117,8 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
&pfifo_qdisc_ops, classid);
if (cl->qdisc == NULL)
cl->qdisc = &noop_qdisc;
+ else
+ qdisc_hash_add(cl->qdisc, true);
if (tca[TCA_RATE]) {
err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est,
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 802ac7c..cfa1f2c 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -201,9 +201,13 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch,
pr_debug("%s(skb %p,sch %p,[qdisc %p])\n", __func__, skb, sch, p);
if (p->set_tc_index) {
+ int wlen = skb_network_offset(skb);
+
switch (tc_skb_protocol(skb)) {
case htons(ETH_P_IP):
- if (skb_cow_head(skb, sizeof(struct iphdr)))
+ wlen += sizeof(struct iphdr);
+ if (!pskb_may_pull(skb, wlen) ||
+ skb_try_make_writable(skb, wlen))
goto drop;
skb->tc_index = ipv4_get_dsfield(ip_hdr(skb))
@@ -211,7 +215,9 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch,
break;
case htons(ETH_P_IPV6):
- if (skb_cow_head(skb, sizeof(struct ipv6hdr)))
+ wlen += sizeof(struct ipv6hdr);
+ if (!pskb_may_pull(skb, wlen) ||
+ skb_try_make_writable(skb, wlen))
goto drop;
skb->tc_index = ipv6_get_dsfield(ipv6_hdr(skb))
@@ -368,6 +374,8 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt)
p->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle);
if (p->q == NULL)
p->q = &noop_qdisc;
+ else
+ qdisc_hash_add(p->q, true);
pr_debug("%s: qdisc %p\n", __func__, p->q);
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 9f3a884..097bbe9 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -288,7 +288,6 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch)
struct fq_codel_flow *flow;
struct list_head *head;
u32 prev_drop_count, prev_ecn_mark;
- unsigned int prev_backlog;
begin:
head = &q->new_flows;
@@ -307,7 +306,6 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch)
prev_drop_count = q->cstats.drop_count;
prev_ecn_mark = q->cstats.ecn_mark;
- prev_backlog = sch->qstats.backlog;
skb = codel_dequeue(sch, &sch->qstats.backlog, &q->cparams,
&flow->cvars, &q->cstats, qdisc_pkt_len,
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index b052b27..3e64d23 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -795,7 +795,7 @@ static void attach_default_qdiscs(struct net_device *dev)
}
#ifdef CONFIG_NET_SCHED
if (dev->qdisc)
- qdisc_hash_add(dev->qdisc);
+ qdisc_hash_add(dev->qdisc, false);
#endif
}
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 3ffaa6f..0198c6c 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1066,6 +1066,8 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
&pfifo_qdisc_ops, classid);
if (cl->qdisc == NULL)
cl->qdisc = &noop_qdisc;
+ else
+ qdisc_hash_add(cl->qdisc, true);
INIT_LIST_HEAD(&cl->children);
cl->vt_tree = RB_ROOT;
cl->cf_tree = RB_ROOT;
@@ -1425,6 +1427,8 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt)
sch->handle);
if (q->root.qdisc == NULL)
q->root.qdisc = &noop_qdisc;
+ else
+ qdisc_hash_add(q->root.qdisc, true);
INIT_LIST_HEAD(&q->root.children);
q->root.vt_tree = RB_ROOT;
q->root.cf_tree = RB_ROOT;
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 4cd5fb1..95867033 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1460,6 +1460,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
qdisc_class_hash_insert(&q->clhash, &cl->common);
if (parent)
parent->children++;
+ if (cl->un.leaf.q != &noop_qdisc)
+ qdisc_hash_add(cl->un.leaf.q, true);
} else {
if (tca[TCA_RATE]) {
err = gen_replace_estimator(&cl->bstats, NULL,
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index 20b7f16..cadfdd4 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -84,7 +84,7 @@ static void mq_attach(struct Qdisc *sch)
qdisc_destroy(old);
#ifdef CONFIG_NET_SCHED
if (ntx < dev->real_num_tx_queues)
- qdisc_hash_add(qdisc);
+ qdisc_hash_add(qdisc, false);
#endif
}
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 9226834..0a4cf27 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -21,14 +21,13 @@
struct mqprio_sched {
struct Qdisc **qdiscs;
- int hw_owned;
+ int hw_offload;
};
static void mqprio_destroy(struct Qdisc *sch)
{
struct net_device *dev = qdisc_dev(sch);
struct mqprio_sched *priv = qdisc_priv(sch);
- struct tc_to_netdev tc = {.type = TC_SETUP_MQPRIO};
unsigned int ntx;
if (priv->qdiscs) {
@@ -39,10 +38,15 @@ static void mqprio_destroy(struct Qdisc *sch)
kfree(priv->qdiscs);
}
- if (priv->hw_owned && dev->netdev_ops->ndo_setup_tc)
+ if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) {
+ struct tc_mqprio_qopt offload = { 0 };
+ struct tc_to_netdev tc = { .type = TC_SETUP_MQPRIO,
+ { .mqprio = &offload } };
+
dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0, &tc);
- else
+ } else {
netdev_set_num_tc(dev, 0);
+ }
}
static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt)
@@ -59,15 +63,20 @@ static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt)
return -EINVAL;
}
- /* net_device does not support requested operation */
- if (qopt->hw && !dev->netdev_ops->ndo_setup_tc)
- return -EINVAL;
+ /* Limit qopt->hw to maximum supported offload value. Drivers have
+ * the option of overriding this later if they don't support the a
+ * given offload type.
+ */
+ if (qopt->hw > TC_MQPRIO_HW_OFFLOAD_MAX)
+ qopt->hw = TC_MQPRIO_HW_OFFLOAD_MAX;
- /* if hw owned qcount and qoffset are taken from LLD so
- * no reason to verify them here
+ /* If hardware offload is requested we will leave it to the device
+ * to either populate the queue counts itself or to validate the
+ * provided queue counts. If ndo_setup_tc is not present then
+ * hardware doesn't support offload and we should return an error.
*/
if (qopt->hw)
- return 0;
+ return dev->netdev_ops->ndo_setup_tc ? 0 : -EINVAL;
for (i = 0; i < qopt->num_tc; i++) {
unsigned int last = qopt->offset[i] + qopt->count[i];
@@ -139,13 +148,15 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
* supplied and verified mapping
*/
if (qopt->hw) {
- struct tc_to_netdev tc = {.type = TC_SETUP_MQPRIO,
- { .tc = qopt->num_tc }};
+ struct tc_mqprio_qopt offload = *qopt;
+ struct tc_to_netdev tc = { .type = TC_SETUP_MQPRIO,
+ { .mqprio = &offload } };
- priv->hw_owned = 1;
err = dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0, &tc);
if (err)
return err;
+
+ priv->hw_offload = offload.hw;
} else {
netdev_set_num_tc(dev, qopt->num_tc);
for (i = 0; i < qopt->num_tc; i++)
@@ -175,7 +186,7 @@ static void mqprio_attach(struct Qdisc *sch)
if (old)
qdisc_destroy(old);
if (ntx < dev->real_num_tx_queues)
- qdisc_hash_add(qdisc);
+ qdisc_hash_add(qdisc, false);
}
kfree(priv->qdiscs);
priv->qdiscs = NULL;
@@ -243,7 +254,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
opt.num_tc = netdev_get_num_tc(dev);
memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map));
- opt.hw = priv->hw_owned;
+ opt.hw = priv->hw_offload;
for (i = 0; i < netdev_get_num_tc(dev); i++) {
opt.count[i] = dev->tc_to_txq[i].count;
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index e7839a0..43a3a10 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -217,6 +217,8 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt)
sch_tree_lock(sch);
old = q->queues[i];
q->queues[i] = child;
+ if (child != &noop_qdisc)
+ qdisc_hash_add(child, true);
if (old != &noop_qdisc) {
qdisc_tree_reduce_backlog(old,
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index c8bb62a..94b4928 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -462,7 +462,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
/* If a delay is expected, orphan the skb. (orphaning usually takes
* place at TX completion time, so _before_ the link transit delay)
*/
- if (q->latency || q->jitter)
+ if (q->latency || q->jitter || q->rate)
skb_orphan_partial(skb);
/*
@@ -530,21 +530,31 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
now = psched_get_time();
if (q->rate) {
- struct sk_buff *last;
+ struct netem_skb_cb *last = NULL;
- if (sch->q.qlen)
- last = sch->q.tail;
- else
- last = netem_rb_to_skb(rb_last(&q->t_root));
+ if (sch->q.tail)
+ last = netem_skb_cb(sch->q.tail);
+ if (q->t_root.rb_node) {
+ struct sk_buff *t_skb;
+ struct netem_skb_cb *t_last;
+
+ t_skb = netem_rb_to_skb(rb_last(&q->t_root));
+ t_last = netem_skb_cb(t_skb);
+ if (!last ||
+ t_last->time_to_send > last->time_to_send) {
+ last = t_last;
+ }
+ }
+
if (last) {
/*
* Last packet in queue is reference point (now),
* calculate this time bonus and subtract
* from delay.
*/
- delay -= netem_skb_cb(last)->time_to_send - now;
+ delay -= last->time_to_send - now;
delay = max_t(psched_tdiff_t, 0, delay);
- now = netem_skb_cb(last)->time_to_send;
+ now = last->time_to_send;
}
delay += packet_len_2_sched_time(qdisc_pkt_len(skb), q);
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index d4d7db2..92c2e6d 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -192,8 +192,11 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
qdisc_destroy(child);
}
- for (i = oldbands; i < q->bands; i++)
+ for (i = oldbands; i < q->bands; i++) {
q->queues[i] = queues[i];
+ if (q->queues[i] != &noop_qdisc)
+ qdisc_hash_add(q->queues[i], true);
+ }
sch_tree_unlock(sch);
return 0;
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index f9e712c..6c85f3e 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -494,6 +494,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
goto destroy_class;
}
+ if (cl->qdisc != &noop_qdisc)
+ qdisc_hash_add(cl->qdisc, true);
sch_tree_lock(sch);
qdisc_class_hash_insert(&q->clhash, &cl->common);
sch_tree_unlock(sch);
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 249b2a1..799ea6d 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -191,6 +191,8 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt)
return PTR_ERR(child);
}
+ if (child != &noop_qdisc)
+ qdisc_hash_add(child, true);
sch_tree_lock(sch);
q->flags = ctl->flags;
q->limit = ctl->limit;
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index fe6963d..ae862f172 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -513,6 +513,8 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt)
if (IS_ERR(child))
return PTR_ERR(child);
+ if (child != &noop_qdisc)
+ qdisc_hash_add(child, true);
sch_tree_lock(sch);
qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 42e8c86..b00e02c 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -714,9 +714,8 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt)
struct sfq_sched_data *q = qdisc_priv(sch);
int i;
- q->perturb_timer.function = sfq_perturbation;
- q->perturb_timer.data = (unsigned long)sch;
- init_timer_deferrable(&q->perturb_timer);
+ setup_deferrable_timer(&q->perturb_timer, sfq_perturbation,
+ (unsigned long)sch);
for (i = 0; i < SFQ_MAX_DEPTH + 1; i++) {
q->dep[i].next = i + SFQ_MAX_FLOWS;
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 303355c..9850126 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -396,6 +396,8 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
q->qdisc->qstats.backlog);
qdisc_destroy(q->qdisc);
q->qdisc = child;
+ if (child != &noop_qdisc)
+ qdisc_hash_add(child, true);
}
q->limit = qopt->limit;
if (tb[TCA_TBF_PBURST])
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 2a6835b..a9708da 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -71,9 +71,8 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
{
struct net *net = sock_net(sk);
struct sctp_sock *sp;
- int i;
sctp_paramhdr_t *p;
- int err;
+ int i;
/* Retrieve the SCTP per socket area. */
sp = sctp_sk((struct sock *)sk);
@@ -247,6 +246,9 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
if (!sctp_ulpq_init(&asoc->ulpq, asoc))
goto fail_init;
+ if (sctp_stream_new(asoc, gfp))
+ goto fail_init;
+
/* Assume that peer would support both address types unless we are
* told otherwise.
*/
@@ -264,9 +266,8 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
/* AUTH related initializations */
INIT_LIST_HEAD(&asoc->endpoint_shared_keys);
- err = sctp_auth_asoc_copy_shkeys(ep, asoc, gfp);
- if (err)
- goto fail_init;
+ if (sctp_auth_asoc_copy_shkeys(ep, asoc, gfp))
+ goto stream_free;
asoc->active_key_id = ep->active_key_id;
asoc->prsctp_enable = ep->prsctp_enable;
@@ -289,6 +290,8 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
return asoc;
+stream_free:
+ sctp_stream_free(asoc->stream);
fail_init:
sock_put(asoc->base.sk);
sctp_endpoint_put(asoc->ep);
@@ -1409,7 +1412,7 @@ sctp_assoc_choose_alter_transport(struct sctp_association *asoc,
/* Update the association's pmtu and frag_point by going through all the
* transports. This routine is called when a transport's PMTU has changed.
*/
-void sctp_assoc_sync_pmtu(struct sock *sk, struct sctp_association *asoc)
+void sctp_assoc_sync_pmtu(struct sctp_association *asoc)
{
struct sctp_transport *t;
__u32 pmtu = 0;
@@ -1421,8 +1424,8 @@ void sctp_assoc_sync_pmtu(struct sock *sk, struct sctp_association *asoc)
list_for_each_entry(t, &asoc->peer.transport_addr_list,
transports) {
if (t->pmtu_pending && t->dst) {
- sctp_transport_update_pmtu(sk, t,
- SCTP_TRUNC4(dst_mtu(t->dst)));
+ sctp_transport_update_pmtu(
+ t, SCTP_TRUNC4(dst_mtu(t->dst)));
t->pmtu_pending = 0;
}
if (!pmtu || (t->pathmtu < pmtu))
diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c
index e3621cb..697721a 100644
--- a/net/sctp/chunk.c
+++ b/net/sctp/chunk.c
@@ -306,14 +306,24 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk)
if (SCTP_PR_TTL_ENABLED(chunk->sinfo.sinfo_flags) &&
time_after(jiffies, chunk->msg->expires_at)) {
- if (chunk->sent_count)
+ struct sctp_stream_out *streamout =
+ &chunk->asoc->stream->out[chunk->sinfo.sinfo_stream];
+
+ if (chunk->sent_count) {
chunk->asoc->abandoned_sent[SCTP_PR_INDEX(TTL)]++;
- else
+ streamout->abandoned_sent[SCTP_PR_INDEX(TTL)]++;
+ } else {
chunk->asoc->abandoned_unsent[SCTP_PR_INDEX(TTL)]++;
+ streamout->abandoned_unsent[SCTP_PR_INDEX(TTL)]++;
+ }
return 1;
} else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) &&
chunk->sent_count > chunk->sinfo.sinfo_timetolive) {
+ struct sctp_stream_out *streamout =
+ &chunk->asoc->stream->out[chunk->sinfo.sinfo_stream];
+
chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++;
+ streamout->abandoned_sent[SCTP_PR_INDEX(RTX)]++;
return 1;
} else if (!SCTP_PR_POLICY(chunk->sinfo.sinfo_flags) &&
chunk->msg->expires_at &&
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 2a28ab2..0e06a27 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -401,10 +401,10 @@ void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc,
if (t->param_flags & SPP_PMTUD_ENABLE) {
/* Update transports view of the MTU */
- sctp_transport_update_pmtu(sk, t, pmtu);
+ sctp_transport_update_pmtu(t, pmtu);
/* Update association pmtu. */
- sctp_assoc_sync_pmtu(sk, asoc);
+ sctp_assoc_sync_pmtu(asoc);
}
/* Retransmit with the new pmtu setting.
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 063baac..961ee59 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -640,14 +640,15 @@ static sctp_scope_t sctp_v6_scope(union sctp_addr *addr)
/* Create and initialize a new sk for the socket to be returned by accept(). */
static struct sock *sctp_v6_create_accept_sk(struct sock *sk,
- struct sctp_association *asoc)
+ struct sctp_association *asoc,
+ bool kern)
{
struct sock *newsk;
struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
struct sctp6_sock *newsctp6sk;
struct ipv6_txoptions *opt;
- newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, 0);
+ newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, kern);
if (!newsk)
goto out;
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 71ce6b9..1409a87 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -86,43 +86,53 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag,
{
struct sctp_transport *tp = packet->transport;
struct sctp_association *asoc = tp->asoc;
+ struct sock *sk;
pr_debug("%s: packet:%p vtag:0x%x\n", __func__, packet, vtag);
-
packet->vtag = vtag;
- if (asoc && tp->dst) {
- struct sock *sk = asoc->base.sk;
+ /* do the following jobs only once for a flush schedule */
+ if (!sctp_packet_empty(packet))
+ return;
- rcu_read_lock();
- if (__sk_dst_get(sk) != tp->dst) {
- dst_hold(tp->dst);
- sk_setup_caps(sk, tp->dst);
- }
+ /* set packet max_size with pathmtu */
+ packet->max_size = tp->pathmtu;
+ if (!asoc)
+ return;
- if (sk_can_gso(sk)) {
- struct net_device *dev = tp->dst->dev;
-
- packet->max_size = dev->gso_max_size;
- } else {
- packet->max_size = asoc->pathmtu;
- }
- rcu_read_unlock();
-
- } else {
- packet->max_size = tp->pathmtu;
+ /* update dst or transport pathmtu if in need */
+ sk = asoc->base.sk;
+ if (!sctp_transport_dst_check(tp)) {
+ sctp_transport_route(tp, NULL, sctp_sk(sk));
+ if (asoc->param_flags & SPP_PMTUD_ENABLE)
+ sctp_assoc_sync_pmtu(asoc);
+ } else if (!sctp_transport_pmtu_check(tp)) {
+ if (asoc->param_flags & SPP_PMTUD_ENABLE)
+ sctp_assoc_sync_pmtu(asoc);
}
- if (ecn_capable && sctp_packet_empty(packet)) {
- struct sctp_chunk *chunk;
+ /* If there a is a prepend chunk stick it on the list before
+ * any other chunks get appended.
+ */
+ if (ecn_capable) {
+ struct sctp_chunk *chunk = sctp_get_ecne_prepend(asoc);
- /* If there a is a prepend chunk stick it on the list before
- * any other chunks get appended.
- */
- chunk = sctp_get_ecne_prepend(asoc);
if (chunk)
sctp_packet_append_chunk(packet, chunk);
}
+
+ if (!tp->dst)
+ return;
+
+ /* set packet max_size with gso_max_size if gso is enabled*/
+ rcu_read_lock();
+ if (__sk_dst_get(sk) != tp->dst) {
+ dst_hold(tp->dst);
+ sk_setup_caps(sk, tp->dst);
+ }
+ packet->max_size = sk_can_gso(sk) ? tp->dst->dev->gso_max_size
+ : asoc->pathmtu;
+ rcu_read_unlock();
}
/* Initialize the packet structure. */
@@ -546,7 +556,6 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
struct sctp_association *asoc = tp->asoc;
struct sctp_chunk *chunk, *tmp;
int pkt_count, gso = 0;
- int confirm;
struct dst_entry *dst;
struct sk_buff *head;
struct sctphdr *sh;
@@ -583,12 +592,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
sh->vtag = htonl(packet->vtag);
sh->checksum = 0;
- /* update dst if in need */
- if (!sctp_transport_dst_check(tp)) {
- sctp_transport_route(tp, NULL, sctp_sk(sk));
- if (asoc && asoc->param_flags & SPP_PMTUD_ENABLE)
- sctp_assoc_sync_pmtu(sk, asoc);
- }
+ /* drop packet if no dst */
dst = dst_clone(tp->dst);
if (!dst) {
IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
@@ -625,13 +629,13 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
asoc->peer.last_sent_to = tp;
}
head->ignore_df = packet->ipfragok;
- confirm = tp->dst_pending_confirm;
- if (confirm)
+ if (tp->dst_pending_confirm)
skb_set_dst_pending_confirm(head, 1);
/* neighbour should be confirmed on successful transmission or
* positive error
*/
- if (tp->af_specific->sctp_xmit(head, tp) >= 0 && confirm)
+ if (tp->af_specific->sctp_xmit(head, tp) >= 0 &&
+ tp->dst_pending_confirm)
tp->dst_pending_confirm = 0;
out:
@@ -705,7 +709,7 @@ static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet,
*/
if ((sctp_sk(asoc->base.sk)->nodelay || inflight == 0) &&
- !chunk->msg->force_delay)
+ !asoc->force_delay)
/* Nothing unacked */
return SCTP_XMIT_OK;
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index db352e5..fe4c3d46 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -353,6 +353,8 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc,
struct sctp_chunk *chk, *temp;
list_for_each_entry_safe(chk, temp, queue, transmitted_list) {
+ struct sctp_stream_out *streamout;
+
if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) ||
chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)
continue;
@@ -361,8 +363,10 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc,
sctp_insert_list(&asoc->outqueue.abandoned,
&chk->transmitted_list);
+ streamout = &asoc->stream->out[chk->sinfo.sinfo_stream];
asoc->sent_cnt_removable--;
asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++;
+ streamout->abandoned_sent[SCTP_PR_INDEX(PRIO)]++;
if (!chk->tsn_gap_acked) {
if (chk->transport)
@@ -382,19 +386,26 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc,
}
static int sctp_prsctp_prune_unsent(struct sctp_association *asoc,
- struct sctp_sndrcvinfo *sinfo,
- struct list_head *queue, int msg_len)
+ struct sctp_sndrcvinfo *sinfo, int msg_len)
{
+ struct sctp_outq *q = &asoc->outqueue;
struct sctp_chunk *chk, *temp;
- list_for_each_entry_safe(chk, temp, queue, list) {
+ list_for_each_entry_safe(chk, temp, &q->out_chunk_list, list) {
if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) ||
chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)
continue;
list_del_init(&chk->list);
+ q->out_qlen -= chk->skb->len;
asoc->sent_cnt_removable--;
asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++;
+ if (chk->sinfo.sinfo_stream < asoc->stream->outcnt) {
+ struct sctp_stream_out *streamout =
+ &asoc->stream->out[chk->sinfo.sinfo_stream];
+
+ streamout->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++;
+ }
msg_len -= SCTP_DATA_SNDSIZE(chk) +
sizeof(struct sk_buff) +
@@ -431,9 +442,7 @@ void sctp_prsctp_prune(struct sctp_association *asoc,
return;
}
- sctp_prsctp_prune_unsent(asoc, sinfo,
- &asoc->outqueue.out_chunk_list,
- msg_len);
+ sctp_prsctp_prune_unsent(asoc, sinfo, msg_len);
}
/* Mark all the eligible packets on a transport for retransmission. */
@@ -1027,8 +1036,7 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
/* RFC 2960 6.5 Every DATA chunk MUST carry a valid
* stream identifier.
*/
- if (chunk->sinfo.sinfo_stream >=
- asoc->c.sinit_num_ostreams) {
+ if (chunk->sinfo.sinfo_stream >= asoc->stream->outcnt) {
/* Mark as failed send. */
sctp_chunk_fail(chunk, SCTP_ERROR_INV_STRM);
diff --git a/net/sctp/proc.c b/net/sctp/proc.c
index 206377f..a0b29d4 100644
--- a/net/sctp/proc.c
+++ b/net/sctp/proc.c
@@ -361,8 +361,8 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v)
sctp_seq_dump_remote_addrs(seq, assoc);
seq_printf(seq, "\t%8lu %5d %5d %4d %4d %4d %8d "
"%8d %8d %8d %8d",
- assoc->hbinterval, assoc->c.sinit_max_instreams,
- assoc->c.sinit_num_ostreams, assoc->max_retrans,
+ assoc->hbinterval, assoc->stream->incnt,
+ assoc->stream->outcnt, assoc->max_retrans,
assoc->init_retries, assoc->shutdown_retries,
assoc->rtx_data_chunks,
atomic_read(&sk->sk_wmem_alloc),
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 1b6d457..989a900 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -575,10 +575,11 @@ static int sctp_v4_is_ce(const struct sk_buff *skb)
/* Create and initialize a new sk for the socket returned by accept(). */
static struct sock *sctp_v4_create_accept_sk(struct sock *sk,
- struct sctp_association *asoc)
+ struct sctp_association *asoc,
+ bool kern)
{
struct sock *newsk = sk_alloc(sock_net(sk), PF_INET, GFP_KERNEL,
- sk->sk_prot, 0);
+ sk->sk_prot, kern);
struct inet_sock *newinet;
if (!newsk)
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 969a30c..118faff 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -2460,15 +2460,10 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk,
* association.
*/
if (!asoc->temp) {
- int error;
-
- asoc->stream = sctp_stream_new(asoc->c.sinit_max_instreams,
- asoc->c.sinit_num_ostreams, gfp);
- if (!asoc->stream)
+ if (sctp_stream_init(asoc, gfp))
goto clean_up;
- error = sctp_assoc_set_id(asoc, gfp);
- if (error)
+ if (sctp_assoc_set_id(asoc, gfp))
goto clean_up;
}
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index e03bb1a..4f5e6cf 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -3872,9 +3872,18 @@ sctp_disposition_t sctp_sf_do_reconf(struct net *net,
else if (param.p->type == SCTP_PARAM_RESET_IN_REQUEST)
reply = sctp_process_strreset_inreq(
(struct sctp_association *)asoc, param, &ev);
- /* More handles for other types will be added here, by now it
- * just ignores other types.
- */
+ else if (param.p->type == SCTP_PARAM_RESET_TSN_REQUEST)
+ reply = sctp_process_strreset_tsnreq(
+ (struct sctp_association *)asoc, param, &ev);
+ else if (param.p->type == SCTP_PARAM_RESET_ADD_OUT_STREAMS)
+ reply = sctp_process_strreset_addstrm_out(
+ (struct sctp_association *)asoc, param, &ev);
+ else if (param.p->type == SCTP_PARAM_RESET_ADD_IN_STREAMS)
+ reply = sctp_process_strreset_addstrm_in(
+ (struct sctp_association *)asoc, param, &ev);
+ else if (param.p->type == SCTP_PARAM_RESET_RESPONSE)
+ reply = sctp_process_strreset_resp(
+ (struct sctp_association *)asoc, param, &ev);
if (ev)
sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP,
@@ -3946,7 +3955,7 @@ sctp_disposition_t sctp_sf_eat_fwd_tsn(struct net *net,
/* Silently discard the chunk if stream-id is not valid */
sctp_walk_fwdtsn(skip, chunk) {
- if (ntohs(skip->stream) >= asoc->c.sinit_max_instreams)
+ if (ntohs(skip->stream) >= asoc->stream->incnt)
goto discard_noforce;
}
@@ -4017,7 +4026,7 @@ sctp_disposition_t sctp_sf_eat_fwd_tsn_fast(
/* Silently discard the chunk if stream-id is not valid */
sctp_walk_fwdtsn(skip, chunk) {
- if (ntohs(skip->stream) >= asoc->c.sinit_max_instreams)
+ if (ntohs(skip->stream) >= asoc->stream->incnt)
goto gen_shutdown;
}
@@ -6353,7 +6362,7 @@ static int sctp_eat_data(const struct sctp_association *asoc,
* and discard the DATA chunk.
*/
sid = ntohs(data_hdr->stream);
- if (sid >= asoc->c.sinit_max_instreams) {
+ if (sid >= asoc->stream->incnt) {
/* Mark tsn as received even though we drop it */
sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_TSN, SCTP_U32(tsn));
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 6f0a9be..8e56df8 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1907,7 +1907,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
}
if (asoc->pmtu_pending)
- sctp_assoc_pending_pmtu(sk, asoc);
+ sctp_assoc_pending_pmtu(asoc);
/* If fragmentation is disabled and the message length exceeds the
* association fragmentation point, return EMSGSIZE. The I-D
@@ -1920,7 +1920,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
}
/* Check for invalid stream. */
- if (sinfo->sinfo_stream >= asoc->c.sinit_num_ostreams) {
+ if (sinfo->sinfo_stream >= asoc->stream->outcnt) {
err = -EINVAL;
goto out_free;
}
@@ -1965,7 +1965,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
err = PTR_ERR(datamsg);
goto out_free;
}
- datamsg->force_delay = !!(msg->msg_flags & MSG_MORE);
+ asoc->force_delay = !!(msg->msg_flags & MSG_MORE);
/* Now send the (possibly) fragmented message. */
list_for_each_entry(chunk, &datamsg->chunks, frag_list) {
@@ -2435,7 +2435,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params,
if ((params->spp_flags & SPP_PMTUD_DISABLE) && params->spp_pathmtu) {
if (trans) {
trans->pathmtu = params->spp_pathmtu;
- sctp_assoc_sync_pmtu(sctp_opt2sk(sp), asoc);
+ sctp_assoc_sync_pmtu(asoc);
} else if (asoc) {
asoc->pathmtu = params->spp_pathmtu;
} else {
@@ -2451,7 +2451,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params,
(trans->param_flags & ~SPP_PMTUD) | pmtud_change;
if (update) {
sctp_transport_pmtu(trans, sctp_opt2sk(sp));
- sctp_assoc_sync_pmtu(sctp_opt2sk(sp), asoc);
+ sctp_assoc_sync_pmtu(asoc);
}
} else if (asoc) {
asoc->param_flags =
@@ -3758,6 +3758,39 @@ static int sctp_setsockopt_default_prinfo(struct sock *sk,
return retval;
}
+static int sctp_setsockopt_reconfig_supported(struct sock *sk,
+ char __user *optval,
+ unsigned int optlen)
+{
+ struct sctp_assoc_value params;
+ struct sctp_association *asoc;
+ int retval = -EINVAL;
+
+ if (optlen != sizeof(params))
+ goto out;
+
+ if (copy_from_user(¶ms, optval, optlen)) {
+ retval = -EFAULT;
+ goto out;
+ }
+
+ asoc = sctp_id2assoc(sk, params.assoc_id);
+ if (asoc) {
+ asoc->reconf_enable = !!params.assoc_value;
+ } else if (!params.assoc_id) {
+ struct sctp_sock *sp = sctp_sk(sk);
+
+ sp->ep->reconf_enable = !!params.assoc_value;
+ } else {
+ goto out;
+ }
+
+ retval = 0;
+
+out:
+ return retval;
+}
+
static int sctp_setsockopt_enable_strreset(struct sock *sk,
char __user *optval,
unsigned int optlen)
@@ -4038,6 +4071,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
case SCTP_DEFAULT_PRINFO:
retval = sctp_setsockopt_default_prinfo(sk, optval, optlen);
break;
+ case SCTP_RECONFIG_SUPPORTED:
+ retval = sctp_setsockopt_reconfig_supported(sk, optval, optlen);
+ break;
case SCTP_ENABLE_STREAM_RESET:
retval = sctp_setsockopt_enable_strreset(sk, optval, optlen);
break;
@@ -4116,7 +4152,7 @@ static int sctp_disconnect(struct sock *sk, int flags)
* descriptor will be returned from accept() to represent the newly
* formed association.
*/
-static struct sock *sctp_accept(struct sock *sk, int flags, int *err)
+static struct sock *sctp_accept(struct sock *sk, int flags, int *err, bool kern)
{
struct sctp_sock *sp;
struct sctp_endpoint *ep;
@@ -4151,7 +4187,7 @@ static struct sock *sctp_accept(struct sock *sk, int flags, int *err)
*/
asoc = list_entry(ep->asocs.next, struct sctp_association, asocs);
- newsk = sp->pf->create_accept_sk(sk, asoc);
+ newsk = sp->pf->create_accept_sk(sk, asoc, kern);
if (!newsk) {
error = -ENOMEM;
goto out;
@@ -4461,8 +4497,8 @@ int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc,
info->sctpi_rwnd = asoc->a_rwnd;
info->sctpi_unackdata = asoc->unack_data;
info->sctpi_penddata = sctp_tsnmap_pending(&asoc->peer.tsn_map);
- info->sctpi_instrms = asoc->c.sinit_max_instreams;
- info->sctpi_outstrms = asoc->c.sinit_num_ostreams;
+ info->sctpi_instrms = asoc->stream->incnt;
+ info->sctpi_outstrms = asoc->stream->outcnt;
list_for_each(pos, &asoc->base.inqueue.in_chunk_list)
info->sctpi_inqueue++;
list_for_each(pos, &asoc->outqueue.out_chunk_list)
@@ -4691,8 +4727,8 @@ static int sctp_getsockopt_sctp_status(struct sock *sk, int len,
status.sstat_unackdata = asoc->unack_data;
status.sstat_penddata = sctp_tsnmap_pending(&asoc->peer.tsn_map);
- status.sstat_instrms = asoc->c.sinit_max_instreams;
- status.sstat_outstrms = asoc->c.sinit_num_ostreams;
+ status.sstat_instrms = asoc->stream->incnt;
+ status.sstat_outstrms = asoc->stream->outcnt;
status.sstat_fragmentation_point = asoc->frag_point;
status.sstat_primary.spinfo_assoc_id = sctp_assoc2id(transport->asoc);
memcpy(&status.sstat_primary.spinfo_address, &transport->ipaddr,
@@ -6540,6 +6576,102 @@ static int sctp_getsockopt_pr_assocstatus(struct sock *sk, int len,
return retval;
}
+static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len,
+ char __user *optval,
+ int __user *optlen)
+{
+ struct sctp_stream_out *streamout;
+ struct sctp_association *asoc;
+ struct sctp_prstatus params;
+ int retval = -EINVAL;
+ int policy;
+
+ if (len < sizeof(params))
+ goto out;
+
+ len = sizeof(params);
+ if (copy_from_user(¶ms, optval, len)) {
+ retval = -EFAULT;
+ goto out;
+ }
+
+ policy = params.sprstat_policy;
+ if (policy & ~SCTP_PR_SCTP_MASK)
+ goto out;
+
+ asoc = sctp_id2assoc(sk, params.sprstat_assoc_id);
+ if (!asoc || params.sprstat_sid >= asoc->stream->outcnt)
+ goto out;
+
+ streamout = &asoc->stream->out[params.sprstat_sid];
+ if (policy == SCTP_PR_SCTP_NONE) {
+ params.sprstat_abandoned_unsent = 0;
+ params.sprstat_abandoned_sent = 0;
+ for (policy = 0; policy <= SCTP_PR_INDEX(MAX); policy++) {
+ params.sprstat_abandoned_unsent +=
+ streamout->abandoned_unsent[policy];
+ params.sprstat_abandoned_sent +=
+ streamout->abandoned_sent[policy];
+ }
+ } else {
+ params.sprstat_abandoned_unsent =
+ streamout->abandoned_unsent[__SCTP_PR_INDEX(policy)];
+ params.sprstat_abandoned_sent =
+ streamout->abandoned_sent[__SCTP_PR_INDEX(policy)];
+ }
+
+ if (put_user(len, optlen) || copy_to_user(optval, ¶ms, len)) {
+ retval = -EFAULT;
+ goto out;
+ }
+
+ retval = 0;
+
+out:
+ return retval;
+}
+
+static int sctp_getsockopt_reconfig_supported(struct sock *sk, int len,
+ char __user *optval,
+ int __user *optlen)
+{
+ struct sctp_assoc_value params;
+ struct sctp_association *asoc;
+ int retval = -EFAULT;
+
+ if (len < sizeof(params)) {
+ retval = -EINVAL;
+ goto out;
+ }
+
+ len = sizeof(params);
+ if (copy_from_user(¶ms, optval, len))
+ goto out;
+
+ asoc = sctp_id2assoc(sk, params.assoc_id);
+ if (asoc) {
+ params.assoc_value = asoc->reconf_enable;
+ } else if (!params.assoc_id) {
+ struct sctp_sock *sp = sctp_sk(sk);
+
+ params.assoc_value = sp->ep->reconf_enable;
+ } else {
+ retval = -EINVAL;
+ goto out;
+ }
+
+ if (put_user(len, optlen))
+ goto out;
+
+ if (copy_to_user(optval, ¶ms, len))
+ goto out;
+
+ retval = 0;
+
+out:
+ return retval;
+}
+
static int sctp_getsockopt_enable_strreset(struct sock *sk, int len,
char __user *optval,
int __user *optlen)
@@ -6748,6 +6880,14 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
retval = sctp_getsockopt_pr_assocstatus(sk, len, optval,
optlen);
break;
+ case SCTP_PR_STREAM_STATUS:
+ retval = sctp_getsockopt_pr_streamstatus(sk, len, optval,
+ optlen);
+ break;
+ case SCTP_RECONFIG_SUPPORTED:
+ retval = sctp_getsockopt_reconfig_supported(sk, len, optval,
+ optlen);
+ break;
case SCTP_ENABLE_STREAM_RESET:
retval = sctp_getsockopt_enable_strreset(sk, len, optval,
optlen);
@@ -7437,9 +7577,12 @@ struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags,
if (sk->sk_shutdown & RCV_SHUTDOWN)
break;
- if (sk_can_busy_loop(sk) &&
- sk_busy_loop(sk, noblock))
- continue;
+ if (sk_can_busy_loop(sk)) {
+ sk_busy_loop(sk, noblock);
+
+ if (!skb_queue_empty(&sk->sk_receive_queue))
+ continue;
+ }
/* User doesn't want to wait. */
error = -EAGAIN;
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 1c6cc04..eff6008 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -35,33 +35,60 @@
#include <net/sctp/sctp.h>
#include <net/sctp/sm.h>
-struct sctp_stream *sctp_stream_new(__u16 incnt, __u16 outcnt, gfp_t gfp)
+int sctp_stream_new(struct sctp_association *asoc, gfp_t gfp)
{
struct sctp_stream *stream;
int i;
stream = kzalloc(sizeof(*stream), gfp);
if (!stream)
- return NULL;
+ return -ENOMEM;
- stream->outcnt = outcnt;
+ stream->outcnt = asoc->c.sinit_num_ostreams;
stream->out = kcalloc(stream->outcnt, sizeof(*stream->out), gfp);
if (!stream->out) {
kfree(stream);
- return NULL;
+ return -ENOMEM;
}
for (i = 0; i < stream->outcnt; i++)
stream->out[i].state = SCTP_STREAM_OPEN;
- stream->incnt = incnt;
+ asoc->stream = stream;
+
+ return 0;
+}
+
+int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp)
+{
+ struct sctp_stream *stream = asoc->stream;
+ int i;
+
+ /* Initial stream->out size may be very big, so free it and alloc
+ * a new one with new outcnt to save memory.
+ */
+ kfree(stream->out);
+ stream->outcnt = asoc->c.sinit_num_ostreams;
+ stream->out = kcalloc(stream->outcnt, sizeof(*stream->out), gfp);
+ if (!stream->out)
+ goto nomem;
+
+ for (i = 0; i < stream->outcnt; i++)
+ stream->out[i].state = SCTP_STREAM_OPEN;
+
+ stream->incnt = asoc->c.sinit_max_instreams;
stream->in = kcalloc(stream->incnt, sizeof(*stream->in), gfp);
if (!stream->in) {
kfree(stream->out);
- kfree(stream);
- return NULL;
+ goto nomem;
}
- return stream;
+ return 0;
+
+nomem:
+ asoc->stream = NULL;
+ kfree(stream);
+
+ return -ENOMEM;
}
void sctp_stream_free(struct sctp_stream *stream)
@@ -267,18 +294,6 @@ int sctp_send_add_streams(struct sctp_association *asoc,
stream->out = streamout;
}
- if (in) {
- struct sctp_stream_in *streamin;
-
- streamin = krealloc(stream->in, incnt * sizeof(*streamin),
- GFP_KERNEL);
- if (!streamin)
- goto out;
-
- memset(streamin + stream->incnt, 0, in * sizeof(*streamin));
- stream->in = streamin;
- }
-
chunk = sctp_make_strreset_addstrm(asoc, out, in);
if (!chunk)
goto out;
@@ -303,13 +318,14 @@ int sctp_send_add_streams(struct sctp_association *asoc,
}
static sctp_paramhdr_t *sctp_chunk_lookup_strreset_param(
- struct sctp_association *asoc, __u32 resp_seq)
+ struct sctp_association *asoc, __u32 resp_seq,
+ __be16 type)
{
struct sctp_chunk *chunk = asoc->strreset_chunk;
struct sctp_reconf_chunk *hdr;
union sctp_params param;
- if (ntohl(resp_seq) != asoc->strreset_outseq || !chunk)
+ if (!chunk)
return NULL;
hdr = (struct sctp_reconf_chunk *)chunk->chunk_hdr;
@@ -320,7 +336,8 @@ static sctp_paramhdr_t *sctp_chunk_lookup_strreset_param(
*/
struct sctp_strreset_tsnreq *req = param.v;
- if (req->request_seq == resp_seq)
+ if ((!resp_seq || req->request_seq == resp_seq) &&
+ (!type || type == req->param_hdr.type))
return param.v;
}
@@ -361,13 +378,9 @@ struct sctp_chunk *sctp_process_strreset_outreq(
goto out;
if (asoc->strreset_chunk) {
- sctp_paramhdr_t *param_hdr;
- struct sctp_transport *t;
-
- param_hdr = sctp_chunk_lookup_strreset_param(
- asoc, outreq->response_seq);
- if (!param_hdr || param_hdr->type !=
- SCTP_PARAM_RESET_IN_REQUEST) {
+ if (!sctp_chunk_lookup_strreset_param(
+ asoc, outreq->response_seq,
+ SCTP_PARAM_RESET_IN_REQUEST)) {
/* same process with outstanding isn't 0 */
result = SCTP_STRRESET_ERR_IN_PROGRESS;
goto out;
@@ -377,6 +390,8 @@ struct sctp_chunk *sctp_process_strreset_outreq(
asoc->strreset_outseq++;
if (!asoc->strreset_outstanding) {
+ struct sctp_transport *t;
+
t = asoc->strreset_chunk->transport;
if (del_timer(&t->reconf_timer))
sctp_transport_put(t);
@@ -477,3 +492,367 @@ struct sctp_chunk *sctp_process_strreset_inreq(
return chunk;
}
+
+struct sctp_chunk *sctp_process_strreset_tsnreq(
+ struct sctp_association *asoc,
+ union sctp_params param,
+ struct sctp_ulpevent **evp)
+{
+ __u32 init_tsn = 0, next_tsn = 0, max_tsn_seen;
+ struct sctp_strreset_tsnreq *tsnreq = param.v;
+ struct sctp_stream *stream = asoc->stream;
+ __u32 result = SCTP_STRRESET_DENIED;
+ __u32 request_seq;
+ __u16 i;
+
+ request_seq = ntohl(tsnreq->request_seq);
+ if (request_seq > asoc->strreset_inseq) {
+ result = SCTP_STRRESET_ERR_BAD_SEQNO;
+ goto out;
+ } else if (request_seq == asoc->strreset_inseq) {
+ asoc->strreset_inseq++;
+ }
+
+ if (!(asoc->strreset_enable & SCTP_ENABLE_RESET_ASSOC_REQ))
+ goto out;
+
+ if (asoc->strreset_outstanding) {
+ result = SCTP_STRRESET_ERR_IN_PROGRESS;
+ goto out;
+ }
+
+ /* G3: The same processing as though a SACK chunk with no gap report
+ * and a cumulative TSN ACK of the Sender's Next TSN minus 1 were
+ * received MUST be performed.
+ */
+ max_tsn_seen = sctp_tsnmap_get_max_tsn_seen(&asoc->peer.tsn_map);
+ sctp_ulpq_reasm_flushtsn(&asoc->ulpq, max_tsn_seen);
+ sctp_ulpq_abort_pd(&asoc->ulpq, GFP_ATOMIC);
+
+ /* G1: Compute an appropriate value for the Receiver's Next TSN -- the
+ * TSN that the peer should use to send the next DATA chunk. The
+ * value SHOULD be the smallest TSN not acknowledged by the
+ * receiver of the request plus 2^31.
+ */
+ init_tsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map) + (1 << 31);
+ sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL,
+ init_tsn, GFP_ATOMIC);
+
+ /* G4: The same processing as though a FWD-TSN chunk (as defined in
+ * [RFC3758]) with all streams affected and a new cumulative TSN
+ * ACK of the Receiver's Next TSN minus 1 were received MUST be
+ * performed.
+ */
+ sctp_outq_free(&asoc->outqueue);
+
+ /* G2: Compute an appropriate value for the local endpoint's next TSN,
+ * i.e., the next TSN assigned by the receiver of the SSN/TSN reset
+ * chunk. The value SHOULD be the highest TSN sent by the receiver
+ * of the request plus 1.
+ */
+ next_tsn = asoc->next_tsn;
+ asoc->ctsn_ack_point = next_tsn - 1;
+ asoc->adv_peer_ack_point = asoc->ctsn_ack_point;
+
+ /* G5: The next expected and outgoing SSNs MUST be reset to 0 for all
+ * incoming and outgoing streams.
+ */
+ for (i = 0; i < stream->outcnt; i++)
+ stream->out[i].ssn = 0;
+ for (i = 0; i < stream->incnt; i++)
+ stream->in[i].ssn = 0;
+
+ result = SCTP_STRRESET_PERFORMED;
+
+ *evp = sctp_ulpevent_make_assoc_reset_event(asoc, 0, init_tsn,
+ next_tsn, GFP_ATOMIC);
+
+out:
+ return sctp_make_strreset_tsnresp(asoc, result, request_seq,
+ next_tsn, init_tsn);
+}
+
+struct sctp_chunk *sctp_process_strreset_addstrm_out(
+ struct sctp_association *asoc,
+ union sctp_params param,
+ struct sctp_ulpevent **evp)
+{
+ struct sctp_strreset_addstrm *addstrm = param.v;
+ struct sctp_stream *stream = asoc->stream;
+ __u32 result = SCTP_STRRESET_DENIED;
+ struct sctp_stream_in *streamin;
+ __u32 request_seq, incnt;
+ __u16 in;
+
+ request_seq = ntohl(addstrm->request_seq);
+ if (request_seq > asoc->strreset_inseq) {
+ result = SCTP_STRRESET_ERR_BAD_SEQNO;
+ goto out;
+ } else if (request_seq == asoc->strreset_inseq) {
+ asoc->strreset_inseq++;
+ }
+
+ if (!(asoc->strreset_enable & SCTP_ENABLE_CHANGE_ASSOC_REQ))
+ goto out;
+
+ if (asoc->strreset_chunk) {
+ if (!sctp_chunk_lookup_strreset_param(
+ asoc, 0, SCTP_PARAM_RESET_ADD_IN_STREAMS)) {
+ /* same process with outstanding isn't 0 */
+ result = SCTP_STRRESET_ERR_IN_PROGRESS;
+ goto out;
+ }
+
+ asoc->strreset_outstanding--;
+ asoc->strreset_outseq++;
+
+ if (!asoc->strreset_outstanding) {
+ struct sctp_transport *t;
+
+ t = asoc->strreset_chunk->transport;
+ if (del_timer(&t->reconf_timer))
+ sctp_transport_put(t);
+
+ sctp_chunk_put(asoc->strreset_chunk);
+ asoc->strreset_chunk = NULL;
+ }
+ }
+
+ in = ntohs(addstrm->number_of_streams);
+ incnt = stream->incnt + in;
+ if (!in || incnt > SCTP_MAX_STREAM)
+ goto out;
+
+ streamin = krealloc(stream->in, incnt * sizeof(*streamin),
+ GFP_ATOMIC);
+ if (!streamin)
+ goto out;
+
+ memset(streamin + stream->incnt, 0, in * sizeof(*streamin));
+ stream->in = streamin;
+ stream->incnt = incnt;
+
+ result = SCTP_STRRESET_PERFORMED;
+
+ *evp = sctp_ulpevent_make_stream_change_event(asoc,
+ 0, ntohs(addstrm->number_of_streams), 0, GFP_ATOMIC);
+
+out:
+ return sctp_make_strreset_resp(asoc, result, request_seq);
+}
+
+struct sctp_chunk *sctp_process_strreset_addstrm_in(
+ struct sctp_association *asoc,
+ union sctp_params param,
+ struct sctp_ulpevent **evp)
+{
+ struct sctp_strreset_addstrm *addstrm = param.v;
+ struct sctp_stream *stream = asoc->stream;
+ __u32 result = SCTP_STRRESET_DENIED;
+ struct sctp_stream_out *streamout;
+ struct sctp_chunk *chunk = NULL;
+ __u32 request_seq, outcnt;
+ __u16 out;
+
+ request_seq = ntohl(addstrm->request_seq);
+ if (request_seq > asoc->strreset_inseq) {
+ result = SCTP_STRRESET_ERR_BAD_SEQNO;
+ goto out;
+ } else if (request_seq == asoc->strreset_inseq) {
+ asoc->strreset_inseq++;
+ }
+
+ if (!(asoc->strreset_enable & SCTP_ENABLE_CHANGE_ASSOC_REQ))
+ goto out;
+
+ if (asoc->strreset_outstanding) {
+ result = SCTP_STRRESET_ERR_IN_PROGRESS;
+ goto out;
+ }
+
+ out = ntohs(addstrm->number_of_streams);
+ outcnt = stream->outcnt + out;
+ if (!out || outcnt > SCTP_MAX_STREAM)
+ goto out;
+
+ streamout = krealloc(stream->out, outcnt * sizeof(*streamout),
+ GFP_ATOMIC);
+ if (!streamout)
+ goto out;
+
+ memset(streamout + stream->outcnt, 0, out * sizeof(*streamout));
+ stream->out = streamout;
+
+ chunk = sctp_make_strreset_addstrm(asoc, out, 0);
+ if (!chunk)
+ goto out;
+
+ asoc->strreset_chunk = chunk;
+ asoc->strreset_outstanding = 1;
+ sctp_chunk_hold(asoc->strreset_chunk);
+
+ stream->outcnt = outcnt;
+
+ *evp = sctp_ulpevent_make_stream_change_event(asoc,
+ 0, 0, ntohs(addstrm->number_of_streams), GFP_ATOMIC);
+
+out:
+ if (!chunk)
+ chunk = sctp_make_strreset_resp(asoc, result, request_seq);
+
+ return chunk;
+}
+
+struct sctp_chunk *sctp_process_strreset_resp(
+ struct sctp_association *asoc,
+ union sctp_params param,
+ struct sctp_ulpevent **evp)
+{
+ struct sctp_strreset_resp *resp = param.v;
+ struct sctp_stream *stream = asoc->stream;
+ struct sctp_transport *t;
+ __u16 i, nums, flags = 0;
+ sctp_paramhdr_t *req;
+ __u32 result;
+
+ req = sctp_chunk_lookup_strreset_param(asoc, resp->response_seq, 0);
+ if (!req)
+ return NULL;
+
+ result = ntohl(resp->result);
+ if (result != SCTP_STRRESET_PERFORMED) {
+ /* if in progress, do nothing but retransmit */
+ if (result == SCTP_STRRESET_IN_PROGRESS)
+ return NULL;
+ else if (result == SCTP_STRRESET_DENIED)
+ flags = SCTP_STREAM_RESET_DENIED;
+ else
+ flags = SCTP_STREAM_RESET_FAILED;
+ }
+
+ if (req->type == SCTP_PARAM_RESET_OUT_REQUEST) {
+ struct sctp_strreset_outreq *outreq;
+ __u16 *str_p = NULL;
+
+ outreq = (struct sctp_strreset_outreq *)req;
+ nums = (ntohs(outreq->param_hdr.length) - sizeof(*outreq)) / 2;
+
+ if (result == SCTP_STRRESET_PERFORMED) {
+ if (nums) {
+ str_p = outreq->list_of_streams;
+ for (i = 0; i < nums; i++)
+ stream->out[ntohs(str_p[i])].ssn = 0;
+ } else {
+ for (i = 0; i < stream->outcnt; i++)
+ stream->out[i].ssn = 0;
+ }
+
+ flags = SCTP_STREAM_RESET_OUTGOING_SSN;
+ }
+
+ for (i = 0; i < stream->outcnt; i++)
+ stream->out[i].state = SCTP_STREAM_OPEN;
+
+ *evp = sctp_ulpevent_make_stream_reset_event(asoc, flags,
+ nums, str_p, GFP_ATOMIC);
+ } else if (req->type == SCTP_PARAM_RESET_IN_REQUEST) {
+ struct sctp_strreset_inreq *inreq;
+ __u16 *str_p = NULL;
+
+ /* if the result is performed, it's impossible for inreq */
+ if (result == SCTP_STRRESET_PERFORMED)
+ return NULL;
+
+ inreq = (struct sctp_strreset_inreq *)req;
+ nums = (ntohs(inreq->param_hdr.length) - sizeof(*inreq)) / 2;
+
+ str_p = inreq->list_of_streams;
+ *evp = sctp_ulpevent_make_stream_reset_event(asoc, flags,
+ nums, str_p, GFP_ATOMIC);
+ } else if (req->type == SCTP_PARAM_RESET_TSN_REQUEST) {
+ struct sctp_strreset_resptsn *resptsn;
+ __u32 stsn, rtsn;
+
+ /* check for resptsn, as sctp_verify_reconf didn't do it*/
+ if (ntohs(param.p->length) != sizeof(*resptsn))
+ return NULL;
+
+ resptsn = (struct sctp_strreset_resptsn *)resp;
+ stsn = ntohl(resptsn->senders_next_tsn);
+ rtsn = ntohl(resptsn->receivers_next_tsn);
+
+ if (result == SCTP_STRRESET_PERFORMED) {
+ __u32 mtsn = sctp_tsnmap_get_max_tsn_seen(
+ &asoc->peer.tsn_map);
+
+ sctp_ulpq_reasm_flushtsn(&asoc->ulpq, mtsn);
+ sctp_ulpq_abort_pd(&asoc->ulpq, GFP_ATOMIC);
+
+ sctp_tsnmap_init(&asoc->peer.tsn_map,
+ SCTP_TSN_MAP_INITIAL,
+ stsn, GFP_ATOMIC);
+
+ sctp_outq_free(&asoc->outqueue);
+
+ asoc->next_tsn = rtsn;
+ asoc->ctsn_ack_point = asoc->next_tsn - 1;
+ asoc->adv_peer_ack_point = asoc->ctsn_ack_point;
+
+ for (i = 0; i < stream->outcnt; i++)
+ stream->out[i].ssn = 0;
+ for (i = 0; i < stream->incnt; i++)
+ stream->in[i].ssn = 0;
+ }
+
+ for (i = 0; i < stream->outcnt; i++)
+ stream->out[i].state = SCTP_STREAM_OPEN;
+
+ *evp = sctp_ulpevent_make_assoc_reset_event(asoc, flags,
+ stsn, rtsn, GFP_ATOMIC);
+ } else if (req->type == SCTP_PARAM_RESET_ADD_OUT_STREAMS) {
+ struct sctp_strreset_addstrm *addstrm;
+ __u16 number;
+
+ addstrm = (struct sctp_strreset_addstrm *)req;
+ nums = ntohs(addstrm->number_of_streams);
+ number = stream->outcnt - nums;
+
+ if (result == SCTP_STRRESET_PERFORMED)
+ for (i = number; i < stream->outcnt; i++)
+ stream->out[i].state = SCTP_STREAM_OPEN;
+ else
+ stream->outcnt = number;
+
+ *evp = sctp_ulpevent_make_stream_change_event(asoc, flags,
+ 0, nums, GFP_ATOMIC);
+ } else if (req->type == SCTP_PARAM_RESET_ADD_IN_STREAMS) {
+ struct sctp_strreset_addstrm *addstrm;
+
+ /* if the result is performed, it's impossible for addstrm in
+ * request.
+ */
+ if (result == SCTP_STRRESET_PERFORMED)
+ return NULL;
+
+ addstrm = (struct sctp_strreset_addstrm *)req;
+ nums = ntohs(addstrm->number_of_streams);
+
+ *evp = sctp_ulpevent_make_stream_change_event(asoc, flags,
+ nums, 0, GFP_ATOMIC);
+ }
+
+ asoc->strreset_outstanding--;
+ asoc->strreset_outseq++;
+
+ /* remove everything for this reconf request */
+ if (!asoc->strreset_outstanding) {
+ t = asoc->strreset_chunk->transport;
+ if (del_timer(&t->reconf_timer))
+ sctp_transport_put(t);
+
+ sctp_chunk_put(asoc->strreset_chunk);
+ asoc->strreset_chunk = NULL;
+ }
+
+ return NULL;
+}
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index daf8554..0e732f6 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -275,6 +275,13 @@ static struct ctl_table sctp_net_table[] = {
.proc_handler = proc_dointvec,
},
{
+ .procname = "reconf_enable",
+ .data = &init_net.sctp.reconf_enable,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "auth_enable",
.data = &init_net.sctp.auth_enable,
.maxlen = sizeof(int),
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 3379668..721eeeb 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -251,14 +251,13 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk)
transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT;
}
-void sctp_transport_update_pmtu(struct sock *sk, struct sctp_transport *t, u32 pmtu)
+void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)
{
- struct dst_entry *dst;
+ struct dst_entry *dst = sctp_transport_dst_check(t);
if (unlikely(pmtu < SCTP_DEFAULT_MINSEGMENT)) {
pr_warn("%s: Reported pmtu %d too low, using default minimum of %d\n",
- __func__, pmtu,
- SCTP_DEFAULT_MINSEGMENT);
+ __func__, pmtu, SCTP_DEFAULT_MINSEGMENT);
/* Use default minimum segment size and disable
* pmtu discovery on this transport.
*/
@@ -267,17 +266,13 @@ void sctp_transport_update_pmtu(struct sock *sk, struct sctp_transport *t, u32 p
t->pathmtu = pmtu;
}
- dst = sctp_transport_dst_check(t);
- if (!dst)
- t->af_specific->get_dst(t, &t->saddr, &t->fl, sk);
-
if (dst) {
- dst->ops->update_pmtu(dst, sk, NULL, pmtu);
-
+ dst->ops->update_pmtu(dst, t->asoc->base.sk, NULL, pmtu);
dst = sctp_transport_dst_check(t);
- if (!dst)
- t->af_specific->get_dst(t, &t->saddr, &t->fl, sk);
}
+
+ if (!dst)
+ t->af_specific->get_dst(t, &t->saddr, &t->fl, t->asoc->base.sk);
}
/* Caches the dst entry and source address for a transport's destination
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index c8881bc5..ec2b3e0 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -883,6 +883,62 @@ struct sctp_ulpevent *sctp_ulpevent_make_stream_reset_event(
return event;
}
+struct sctp_ulpevent *sctp_ulpevent_make_assoc_reset_event(
+ const struct sctp_association *asoc, __u16 flags, __u32 local_tsn,
+ __u32 remote_tsn, gfp_t gfp)
+{
+ struct sctp_assoc_reset_event *areset;
+ struct sctp_ulpevent *event;
+ struct sk_buff *skb;
+
+ event = sctp_ulpevent_new(sizeof(struct sctp_assoc_reset_event),
+ MSG_NOTIFICATION, gfp);
+ if (!event)
+ return NULL;
+
+ skb = sctp_event2skb(event);
+ areset = (struct sctp_assoc_reset_event *)
+ skb_put(skb, sizeof(struct sctp_assoc_reset_event));
+
+ areset->assocreset_type = SCTP_ASSOC_RESET_EVENT;
+ areset->assocreset_flags = flags;
+ areset->assocreset_length = sizeof(struct sctp_assoc_reset_event);
+ sctp_ulpevent_set_owner(event, asoc);
+ areset->assocreset_assoc_id = sctp_assoc2id(asoc);
+ areset->assocreset_local_tsn = local_tsn;
+ areset->assocreset_remote_tsn = remote_tsn;
+
+ return event;
+}
+
+struct sctp_ulpevent *sctp_ulpevent_make_stream_change_event(
+ const struct sctp_association *asoc, __u16 flags,
+ __u32 strchange_instrms, __u32 strchange_outstrms, gfp_t gfp)
+{
+ struct sctp_stream_change_event *schange;
+ struct sctp_ulpevent *event;
+ struct sk_buff *skb;
+
+ event = sctp_ulpevent_new(sizeof(struct sctp_stream_change_event),
+ MSG_NOTIFICATION, gfp);
+ if (!event)
+ return NULL;
+
+ skb = sctp_event2skb(event);
+ schange = (struct sctp_stream_change_event *)
+ skb_put(skb, sizeof(struct sctp_stream_change_event));
+
+ schange->strchange_type = SCTP_STREAM_CHANGE_EVENT;
+ schange->strchange_flags = flags;
+ schange->strchange_length = sizeof(struct sctp_stream_change_event);
+ sctp_ulpevent_set_owner(event, asoc);
+ schange->strchange_assoc_id = sctp_assoc2id(asoc);
+ schange->strchange_instrms = strchange_instrms;
+ schange->strchange_outstrms = strchange_outstrms;
+
+ return event;
+}
+
/* Return the notification type, assuming this is a notification
* event.
*/
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 85837ab..0938037 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -944,7 +944,7 @@ static int smc_listen(struct socket *sock, int backlog)
}
static int smc_accept(struct socket *sock, struct socket *new_sock,
- int flags)
+ int flags, bool kern)
{
struct sock *sk = sock->sk, *nsk;
DECLARE_WAITQUEUE(wait, current);
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
index a95f74b..7e1f0e2 100644
--- a/net/smc/smc_ib.h
+++ b/net/smc/smc_ib.h
@@ -11,6 +11,7 @@
#ifndef _SMC_IB_H
#define _SMC_IB_H
+#include <linux/interrupt.h>
#include <linux/if_ether.h>
#include <rdma/ib_verbs.h>
diff --git a/net/socket.c b/net/socket.c
index 2c1e867..eea9970 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -652,6 +652,16 @@ int kernel_sendmsg(struct socket *sock, struct msghdr *msg,
}
EXPORT_SYMBOL(kernel_sendmsg);
+static bool skb_is_err_queue(const struct sk_buff *skb)
+{
+ /* pkt_type of skbs enqueued on the error queue are set to
+ * PACKET_OUTGOING in skb_set_err_queue(). This is only safe to do
+ * in recvmsg, since skbs received on a local socket will never
+ * have a pkt_type of PACKET_OUTGOING.
+ */
+ return skb->pkt_type == PACKET_OUTGOING;
+}
+
/*
* called from sock_recv_timestamp() if sock_flag(sk, SOCK_RCVTSTAMP)
*/
@@ -695,7 +705,8 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
put_cmsg(msg, SOL_SOCKET,
SCM_TIMESTAMPING, sizeof(tss), &tss);
- if (skb->len && (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS))
+ if (skb_is_err_queue(skb) && skb->len &&
+ SKB_EXT_ERR(skb)->opt_stats)
put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_OPT_STATS,
skb->len, skb->data);
}
@@ -1506,7 +1517,7 @@ SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
if (err)
goto out_fd;
- err = sock->ops->accept(sock, newsock, sock->file->f_flags);
+ err = sock->ops->accept(sock, newsock, sock->file->f_flags, false);
if (err < 0)
goto out_fd;
@@ -1731,6 +1742,7 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size,
/* We assume all kernel code knows the size of sockaddr_storage */
msg.msg_namelen = 0;
msg.msg_iocb = NULL;
+ msg.msg_flags = 0;
if (sock->file->f_flags & O_NONBLOCK)
flags |= MSG_DONTWAIT;
err = sock_recvmsg(sock, &msg, flags);
@@ -3238,7 +3250,7 @@ int kernel_accept(struct socket *sock, struct socket **newsock, int flags)
if (err < 0)
goto done;
- err = sock->ops->accept(sock, *newsock, flags);
+ err = sock->ops->accept(sock, *newsock, flags, true);
if (err < 0) {
sock_release(*newsock);
*newsock = NULL;
@@ -3344,3 +3356,49 @@ int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how)
return sock->ops->shutdown(sock, how);
}
EXPORT_SYMBOL(kernel_sock_shutdown);
+
+/* This routine returns the IP overhead imposed by a socket i.e.
+ * the length of the underlying IP header, depending on whether
+ * this is an IPv4 or IPv6 socket and the length from IP options turned
+ * on at the socket.
+ */
+u32 kernel_sock_ip_overhead(struct sock *sk)
+{
+ struct inet_sock *inet;
+ struct ip_options_rcu *opt;
+ u32 overhead = 0;
+ bool owned_by_user;
+#if IS_ENABLED(CONFIG_IPV6)
+ struct ipv6_pinfo *np;
+ struct ipv6_txoptions *optv6 = NULL;
+#endif /* IS_ENABLED(CONFIG_IPV6) */
+
+ if (!sk)
+ return overhead;
+
+ owned_by_user = sock_owned_by_user(sk);
+ switch (sk->sk_family) {
+ case AF_INET:
+ inet = inet_sk(sk);
+ overhead += sizeof(struct iphdr);
+ opt = rcu_dereference_protected(inet->inet_opt,
+ owned_by_user);
+ if (opt)
+ overhead += opt->opt.optlen;
+ return overhead;
+#if IS_ENABLED(CONFIG_IPV6)
+ case AF_INET6:
+ np = inet6_sk(sk);
+ overhead += sizeof(struct ipv6hdr);
+ if (np)
+ optv6 = rcu_dereference_protected(np->opt,
+ owned_by_user);
+ if (optv6)
+ overhead += (optv6->opt_flen + optv6->opt_nflen);
+ return overhead;
+#endif /* IS_ENABLED(CONFIG_IPV6) */
+ default: /* Returns 0 overhead if the socket is not ipv4 or ipv6 */
+ return overhead;
+ }
+}
+EXPORT_SYMBOL(kernel_sock_ip_overhead);
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 8931e33..2b720fa 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1635,6 +1635,7 @@ static struct svc_xprt *svc_bc_create_socket(struct svc_serv *serv,
xprt = &svsk->sk_xprt;
svc_xprt_init(net, &svc_tcp_bc_class, xprt, serv);
+ set_bit(XPT_CONG_CTRL, &svsk->sk_xprt.xpt_flags);
serv->sv_bc_xprt = xprt;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index c13a5c3..fc8f14c 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -127,6 +127,7 @@ static struct svc_xprt *svc_rdma_bc_create(struct svc_serv *serv,
xprt = &cma_xprt->sc_xprt;
svc_xprt_init(net, &svc_rdma_bc_class, xprt, serv);
+ set_bit(XPT_CONG_CTRL, &xprt->xpt_flags);
serv->sv_bc_xprt = xprt;
dprintk("svcrdma: %s(%p)\n", __func__, xprt);
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 81cd31a..3b332b3 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -503,7 +503,8 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
struct ib_cq *sendcq, *recvcq;
int rc;
- max_sge = min(ia->ri_device->attrs.max_sge, RPCRDMA_MAX_SEND_SGES);
+ max_sge = min_t(unsigned int, ia->ri_device->attrs.max_sge,
+ RPCRDMA_MAX_SEND_SGES);
if (max_sge < RPCRDMA_MIN_SEND_SGES) {
pr_warn("rpcrdma: HCA provides only %d send SGEs\n", max_sge);
return -ENOMEM;
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 9be6592..bd0aac8 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -416,6 +416,7 @@ static void tipc_nameseq_subscribe(struct name_seq *nseq,
tipc_subscrp_convert_seq(&s->evt.s.seq, s->swap, &ns);
+ tipc_subscrp_get(s);
list_add(&s->nameseq_list, &nseq->subscriptions);
if (!sseq)
@@ -787,6 +788,7 @@ void tipc_nametbl_unsubscribe(struct tipc_subscription *s)
if (seq != NULL) {
spin_lock_bh(&seq->lock);
list_del_init(&s->nameseq_list);
+ tipc_subscrp_put(s);
if (!seq->first_free && list_empty(&seq->subscriptions)) {
hlist_del_init_rcu(&seq->ns_list);
kfree(seq->sseqs);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 43e4045..15f6ce7b 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -115,7 +115,8 @@ static void tipc_data_ready(struct sock *sk);
static void tipc_write_space(struct sock *sk);
static void tipc_sock_destruct(struct sock *sk);
static int tipc_release(struct socket *sock);
-static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags);
+static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
+ bool kern);
static void tipc_sk_timeout(unsigned long data);
static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
struct tipc_name_seq const *seq);
@@ -2029,7 +2030,8 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo)
*
* Returns 0 on success, errno otherwise
*/
-static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
+static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
+ bool kern)
{
struct sock *new_sk, *sk = sock->sk;
struct sk_buff *buf;
@@ -2051,7 +2053,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
buf = skb_peek(&sk->sk_receive_queue);
- res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, 0);
+ res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, kern);
if (res)
goto exit;
security_sk_clone(sock->sk, new_sock->sk);
@@ -2509,6 +2511,28 @@ static int tipc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
}
}
+static int tipc_socketpair(struct socket *sock1, struct socket *sock2)
+{
+ struct tipc_sock *tsk2 = tipc_sk(sock2->sk);
+ struct tipc_sock *tsk1 = tipc_sk(sock1->sk);
+ u32 onode = tipc_own_addr(sock_net(sock1->sk));
+
+ tsk1->peer.family = AF_TIPC;
+ tsk1->peer.addrtype = TIPC_ADDR_ID;
+ tsk1->peer.scope = TIPC_NODE_SCOPE;
+ tsk1->peer.addr.id.ref = tsk2->portid;
+ tsk1->peer.addr.id.node = onode;
+ tsk2->peer.family = AF_TIPC;
+ tsk2->peer.addrtype = TIPC_ADDR_ID;
+ tsk2->peer.scope = TIPC_NODE_SCOPE;
+ tsk2->peer.addr.id.ref = tsk1->portid;
+ tsk2->peer.addr.id.node = onode;
+
+ tipc_sk_finish_conn(tsk1, tsk2->portid, onode);
+ tipc_sk_finish_conn(tsk2, tsk1->portid, onode);
+ return 0;
+}
+
/* Protocol switches for the various types of TIPC sockets */
static const struct proto_ops msg_ops = {
@@ -2517,7 +2541,7 @@ static const struct proto_ops msg_ops = {
.release = tipc_release,
.bind = tipc_bind,
.connect = tipc_connect,
- .socketpair = sock_no_socketpair,
+ .socketpair = tipc_socketpair,
.accept = sock_no_accept,
.getname = tipc_getname,
.poll = tipc_poll,
@@ -2538,7 +2562,7 @@ static const struct proto_ops packet_ops = {
.release = tipc_release,
.bind = tipc_bind,
.connect = tipc_connect,
- .socketpair = sock_no_socketpair,
+ .socketpair = tipc_socketpair,
.accept = tipc_accept,
.getname = tipc_getname,
.poll = tipc_poll,
@@ -2559,7 +2583,7 @@ static const struct proto_ops stream_ops = {
.release = tipc_release,
.bind = tipc_bind,
.connect = tipc_connect,
- .socketpair = sock_no_socketpair,
+ .socketpair = tipc_socketpair,
.accept = tipc_accept,
.getname = tipc_getname,
.poll = tipc_poll,
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index 9d94e65..0bf91cd 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -54,8 +54,6 @@ struct tipc_subscriber {
static void tipc_subscrp_delete(struct tipc_subscription *sub);
static void tipc_subscrb_put(struct tipc_subscriber *subscriber);
-static void tipc_subscrp_put(struct tipc_subscription *subscription);
-static void tipc_subscrp_get(struct tipc_subscription *subscription);
/**
* htohl - convert value to endianness used by destination
@@ -125,7 +123,6 @@ void tipc_subscrp_report_overlap(struct tipc_subscription *sub, u32 found_lower,
{
struct tipc_name_seq seq;
- tipc_subscrp_get(sub);
tipc_subscrp_convert_seq(&sub->evt.s.seq, sub->swap, &seq);
if (!tipc_subscrp_check_overlap(&seq, found_lower, found_upper))
return;
@@ -135,12 +132,17 @@ void tipc_subscrp_report_overlap(struct tipc_subscription *sub, u32 found_lower,
tipc_subscrp_send_event(sub, found_lower, found_upper, event, port_ref,
node);
- tipc_subscrp_put(sub);
}
static void tipc_subscrp_timeout(unsigned long data)
{
struct tipc_subscription *sub = (struct tipc_subscription *)data;
+ struct tipc_subscriber *subscriber = sub->subscriber;
+
+ spin_lock_bh(&subscriber->lock);
+ tipc_nametbl_unsubscribe(sub);
+ list_del(&sub->subscrp_list);
+ spin_unlock_bh(&subscriber->lock);
/* Notify subscriber of timeout */
tipc_subscrp_send_event(sub, sub->evt.s.seq.lower, sub->evt.s.seq.upper,
@@ -172,21 +174,17 @@ static void tipc_subscrp_kref_release(struct kref *kref)
struct tipc_net *tn = net_generic(sub->net, tipc_net_id);
struct tipc_subscriber *subscriber = sub->subscriber;
- spin_lock_bh(&subscriber->lock);
- tipc_nametbl_unsubscribe(sub);
- list_del(&sub->subscrp_list);
atomic_dec(&tn->subscription_count);
- spin_unlock_bh(&subscriber->lock);
kfree(sub);
tipc_subscrb_put(subscriber);
}
-static void tipc_subscrp_put(struct tipc_subscription *subscription)
+void tipc_subscrp_put(struct tipc_subscription *subscription)
{
kref_put(&subscription->kref, tipc_subscrp_kref_release);
}
-static void tipc_subscrp_get(struct tipc_subscription *subscription)
+void tipc_subscrp_get(struct tipc_subscription *subscription)
{
kref_get(&subscription->kref);
}
@@ -205,11 +203,9 @@ static void tipc_subscrb_subscrp_delete(struct tipc_subscriber *subscriber,
if (s && memcmp(s, &sub->evt.s, sizeof(struct tipc_subscr)))
continue;
- tipc_subscrp_get(sub);
- spin_unlock_bh(&subscriber->lock);
+ tipc_nametbl_unsubscribe(sub);
+ list_del(&sub->subscrp_list);
tipc_subscrp_delete(sub);
- tipc_subscrp_put(sub);
- spin_lock_bh(&subscriber->lock);
if (s)
break;
diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h
index ffdc214..ee52957 100644
--- a/net/tipc/subscr.h
+++ b/net/tipc/subscr.h
@@ -78,4 +78,7 @@ u32 tipc_subscrp_convert_seq_type(u32 type, int swap);
int tipc_topsrv_start(struct net *net);
void tipc_topsrv_stop(struct net *net);
+void tipc_subscrp_put(struct tipc_subscription *subscription);
+void tipc_subscrp_get(struct tipc_subscription *subscription);
+
#endif
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index ee37b39..6a7fe76 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -636,7 +636,7 @@ static int unix_bind(struct socket *, struct sockaddr *, int);
static int unix_stream_connect(struct socket *, struct sockaddr *,
int addr_len, int flags);
static int unix_socketpair(struct socket *, struct socket *);
-static int unix_accept(struct socket *, struct socket *, int);
+static int unix_accept(struct socket *, struct socket *, int, bool);
static int unix_getname(struct socket *, struct sockaddr *, int *, int);
static unsigned int unix_poll(struct file *, struct socket *, poll_table *);
static unsigned int unix_dgram_poll(struct file *, struct socket *,
@@ -996,7 +996,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
unsigned int hash;
struct unix_address *addr;
struct hlist_head *list;
- struct path path = { NULL, NULL };
+ struct path path = { };
err = -EINVAL;
if (sunaddr->sun_family != AF_UNIX)
@@ -1402,7 +1402,8 @@ static void unix_sock_inherit_flags(const struct socket *old,
set_bit(SOCK_PASSSEC, &new->flags);
}
-static int unix_accept(struct socket *sock, struct socket *newsock, int flags)
+static int unix_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sock *sk = sock->sk;
struct sock *tsk;
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 6a0d485..c36757e7 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -146,6 +146,7 @@ void unix_notinflight(struct user_struct *user, struct file *fp)
if (s) {
struct unix_sock *u = unix_sk(s);
+ BUG_ON(!atomic_long_read(&u->inflight));
BUG_ON(list_empty(&u->link));
if (atomic_long_dec_and_test(&u->inflight))
@@ -341,6 +342,14 @@ void unix_gc(void)
}
list_del(&cursor);
+ /* Now gc_candidates contains only garbage. Restore original
+ * inflight counters for these as well, and remove the skbuffs
+ * which are creating the cycle(s).
+ */
+ skb_queue_head_init(&hitlist);
+ list_for_each_entry(u, &gc_candidates, link)
+ scan_children(&u->sk, inc_inflight, &hitlist);
+
/* not_cycle_list contains those sockets which do not make up a
* cycle. Restore these to the inflight list.
*/
@@ -350,14 +359,6 @@ void unix_gc(void)
list_move_tail(&u->link, &gc_inflight_list);
}
- /* Now gc_candidates contains only garbage. Restore original
- * inflight counters for these as well, and remove the skbuffs
- * which are creating the cycle(s).
- */
- skb_queue_head_init(&hitlist);
- list_for_each_entry(u, &gc_candidates, link)
- scan_children(&u->sk, inc_inflight, &hitlist);
-
spin_unlock(&unix_gc_lock);
/* Here we are. Hitlist is filled. Die. */
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 9192ead..6f7f675 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1102,10 +1102,19 @@ static const struct proto_ops vsock_dgram_ops = {
.sendpage = sock_no_sendpage,
};
+static int vsock_transport_cancel_pkt(struct vsock_sock *vsk)
+{
+ if (!transport->cancel_pkt)
+ return -EOPNOTSUPP;
+
+ return transport->cancel_pkt(vsk);
+}
+
static void vsock_connect_timeout(struct work_struct *work)
{
struct sock *sk;
struct vsock_sock *vsk;
+ int cancel = 0;
vsk = container_of(work, struct vsock_sock, dwork.work);
sk = sk_vsock(vsk);
@@ -1116,8 +1125,11 @@ static void vsock_connect_timeout(struct work_struct *work)
sk->sk_state = SS_UNCONNECTED;
sk->sk_err = ETIMEDOUT;
sk->sk_error_report(sk);
+ cancel = 1;
}
release_sock(sk);
+ if (cancel)
+ vsock_transport_cancel_pkt(vsk);
sock_put(sk);
}
@@ -1224,11 +1236,13 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
err = sock_intr_errno(timeout);
sk->sk_state = SS_UNCONNECTED;
sock->state = SS_UNCONNECTED;
+ vsock_transport_cancel_pkt(vsk);
goto out_wait;
} else if (timeout == 0) {
err = -ETIMEDOUT;
sk->sk_state = SS_UNCONNECTED;
sock->state = SS_UNCONNECTED;
+ vsock_transport_cancel_pkt(vsk);
goto out_wait;
}
@@ -1250,7 +1264,8 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
return err;
}
-static int vsock_accept(struct socket *sock, struct socket *newsock, int flags)
+static int vsock_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sock *listener;
int err;
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 9d24c0e..68675a1 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -213,6 +213,47 @@ virtio_transport_send_pkt(struct virtio_vsock_pkt *pkt)
return len;
}
+static int
+virtio_transport_cancel_pkt(struct vsock_sock *vsk)
+{
+ struct virtio_vsock *vsock;
+ struct virtio_vsock_pkt *pkt, *n;
+ int cnt = 0;
+ LIST_HEAD(freeme);
+
+ vsock = virtio_vsock_get();
+ if (!vsock) {
+ return -ENODEV;
+ }
+
+ spin_lock_bh(&vsock->send_pkt_list_lock);
+ list_for_each_entry_safe(pkt, n, &vsock->send_pkt_list, list) {
+ if (pkt->vsk != vsk)
+ continue;
+ list_move(&pkt->list, &freeme);
+ }
+ spin_unlock_bh(&vsock->send_pkt_list_lock);
+
+ list_for_each_entry_safe(pkt, n, &freeme, list) {
+ if (pkt->reply)
+ cnt++;
+ list_del(&pkt->list);
+ virtio_transport_free_pkt(pkt);
+ }
+
+ if (cnt) {
+ struct virtqueue *rx_vq = vsock->vqs[VSOCK_VQ_RX];
+ int new_cnt;
+
+ new_cnt = atomic_sub_return(cnt, &vsock->queued_replies);
+ if (new_cnt + cnt >= virtqueue_get_vring_size(rx_vq) &&
+ new_cnt < virtqueue_get_vring_size(rx_vq))
+ queue_work(virtio_vsock_workqueue, &vsock->rx_work);
+ }
+
+ return 0;
+}
+
static void virtio_vsock_rx_fill(struct virtio_vsock *vsock)
{
int buf_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE;
@@ -462,6 +503,7 @@ static struct virtio_transport virtio_transport = {
.release = virtio_transport_release,
.connect = virtio_transport_connect,
.shutdown = virtio_transport_shutdown,
+ .cancel_pkt = virtio_transport_cancel_pkt,
.dgram_bind = virtio_transport_dgram_bind,
.dgram_dequeue = virtio_transport_dgram_dequeue,
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 8d592a4..af087b4 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -58,6 +58,7 @@ virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info,
pkt->len = len;
pkt->hdr.len = cpu_to_le32(len);
pkt->reply = info->reply;
+ pkt->vsk = info->vsk;
if (info->msg && len > 0) {
pkt->buf = kmalloc(len, GFP_KERNEL);
@@ -180,6 +181,7 @@ static int virtio_transport_send_credit_update(struct vsock_sock *vsk,
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_CREDIT_UPDATE,
.type = type,
+ .vsk = vsk,
};
return virtio_transport_send_pkt_info(vsk, &info);
@@ -519,6 +521,7 @@ int virtio_transport_connect(struct vsock_sock *vsk)
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_REQUEST,
.type = VIRTIO_VSOCK_TYPE_STREAM,
+ .vsk = vsk,
};
return virtio_transport_send_pkt_info(vsk, &info);
@@ -534,6 +537,7 @@ int virtio_transport_shutdown(struct vsock_sock *vsk, int mode)
VIRTIO_VSOCK_SHUTDOWN_RCV : 0) |
(mode & SEND_SHUTDOWN ?
VIRTIO_VSOCK_SHUTDOWN_SEND : 0),
+ .vsk = vsk,
};
return virtio_transport_send_pkt_info(vsk, &info);
@@ -560,6 +564,7 @@ virtio_transport_stream_enqueue(struct vsock_sock *vsk,
.type = VIRTIO_VSOCK_TYPE_STREAM,
.msg = msg,
.pkt_len = len,
+ .vsk = vsk,
};
return virtio_transport_send_pkt_info(vsk, &info);
@@ -581,6 +586,7 @@ static int virtio_transport_reset(struct vsock_sock *vsk,
.op = VIRTIO_VSOCK_OP_RST,
.type = VIRTIO_VSOCK_TYPE_STREAM,
.reply = !!pkt,
+ .vsk = vsk,
};
/* Send RST only if the original pkt is not a RST pkt */
@@ -826,6 +832,7 @@ virtio_transport_send_response(struct vsock_sock *vsk,
.remote_cid = le64_to_cpu(pkt->hdr.src_cid),
.remote_port = le32_to_cpu(pkt->hdr.src_port),
.reply = true,
+ .vsk = vsk,
};
return virtio_transport_send_pkt_info(vsk, &info);
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index 4be4fbb..10ae782 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -96,31 +96,23 @@ static int PROTOCOL_OVERRIDE = -1;
static s32 vmci_transport_error_to_vsock_error(s32 vmci_error)
{
- int err;
-
switch (vmci_error) {
case VMCI_ERROR_NO_MEM:
- err = ENOMEM;
- break;
+ return -ENOMEM;
case VMCI_ERROR_DUPLICATE_ENTRY:
case VMCI_ERROR_ALREADY_EXISTS:
- err = EADDRINUSE;
- break;
+ return -EADDRINUSE;
case VMCI_ERROR_NO_ACCESS:
- err = EPERM;
- break;
+ return -EPERM;
case VMCI_ERROR_NO_RESOURCES:
- err = ENOBUFS;
- break;
+ return -ENOBUFS;
case VMCI_ERROR_INVALID_RESOURCE:
- err = EHOSTUNREACH;
- break;
+ return -EHOSTUNREACH;
case VMCI_ERROR_INVALID_ARGS:
default:
- err = EINVAL;
+ break;
}
-
- return err > 0 ? -err : err;
+ return -EINVAL;
}
static u32 vmci_transport_peer_rid(u32 peer_cid)
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d7f8be4..2312dc2 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -545,22 +545,18 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb,
{
int err;
- rtnl_lock();
-
if (!cb->args[0]) {
err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize,
genl_family_attrbuf(&nl80211_fam),
nl80211_fam.maxattr, nl80211_policy);
if (err)
- goto out_unlock;
+ return err;
*wdev = __cfg80211_wdev_from_attrs(
sock_net(skb->sk),
genl_family_attrbuf(&nl80211_fam));
- if (IS_ERR(*wdev)) {
- err = PTR_ERR(*wdev);
- goto out_unlock;
- }
+ if (IS_ERR(*wdev))
+ return PTR_ERR(*wdev);
*rdev = wiphy_to_rdev((*wdev)->wiphy);
/* 0 is the first index - add 1 to parse only once */
cb->args[0] = (*rdev)->wiphy_idx + 1;
@@ -570,10 +566,8 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb,
struct wiphy *wiphy = wiphy_idx_to_wiphy(cb->args[0] - 1);
struct wireless_dev *tmp;
- if (!wiphy) {
- err = -ENODEV;
- goto out_unlock;
- }
+ if (!wiphy)
+ return -ENODEV;
*rdev = wiphy_to_rdev(wiphy);
*wdev = NULL;
@@ -584,21 +578,11 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb,
}
}
- if (!*wdev) {
- err = -ENODEV;
- goto out_unlock;
- }
+ if (!*wdev)
+ return -ENODEV;
}
return 0;
- out_unlock:
- rtnl_unlock();
- return err;
-}
-
-static void nl80211_finish_wdev_dump(struct cfg80211_registered_device *rdev)
-{
- rtnl_unlock();
}
/* IE validation */
@@ -2608,17 +2592,17 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback *
int filter_wiphy = -1;
struct cfg80211_registered_device *rdev;
struct wireless_dev *wdev;
+ int ret;
rtnl_lock();
if (!cb->args[2]) {
struct nl80211_dump_wiphy_state state = {
.filter_wiphy = -1,
};
- int ret;
ret = nl80211_dump_wiphy_parse(skb, cb, &state);
if (ret)
- return ret;
+ goto out_unlock;
filter_wiphy = state.filter_wiphy;
@@ -2663,12 +2647,14 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback *
wp_idx++;
}
out:
- rtnl_unlock();
-
cb->args[0] = wp_idx;
cb->args[1] = if_idx;
- return skb->len;
+ ret = skb->len;
+ out_unlock:
+ rtnl_unlock();
+
+ return ret;
}
static int nl80211_get_interface(struct sk_buff *skb, struct genl_info *info)
@@ -4452,9 +4438,10 @@ static int nl80211_dump_station(struct sk_buff *skb,
int sta_idx = cb->args[2];
int err;
+ rtnl_lock();
err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
if (err)
- return err;
+ goto out_err;
if (!wdev->netdev) {
err = -EINVAL;
@@ -4489,7 +4476,7 @@ static int nl80211_dump_station(struct sk_buff *skb,
cb->args[2] = sta_idx;
err = skb->len;
out_err:
- nl80211_finish_wdev_dump(rdev);
+ rtnl_unlock();
return err;
}
@@ -5275,9 +5262,10 @@ static int nl80211_dump_mpath(struct sk_buff *skb,
int path_idx = cb->args[2];
int err;
+ rtnl_lock();
err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
if (err)
- return err;
+ goto out_err;
if (!rdev->ops->dump_mpath) {
err = -EOPNOTSUPP;
@@ -5310,7 +5298,7 @@ static int nl80211_dump_mpath(struct sk_buff *skb,
cb->args[2] = path_idx;
err = skb->len;
out_err:
- nl80211_finish_wdev_dump(rdev);
+ rtnl_unlock();
return err;
}
@@ -5470,9 +5458,10 @@ static int nl80211_dump_mpp(struct sk_buff *skb,
int path_idx = cb->args[2];
int err;
+ rtnl_lock();
err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
if (err)
- return err;
+ goto out_err;
if (!rdev->ops->dump_mpp) {
err = -EOPNOTSUPP;
@@ -5505,7 +5494,7 @@ static int nl80211_dump_mpp(struct sk_buff *skb,
cb->args[2] = path_idx;
err = skb->len;
out_err:
- nl80211_finish_wdev_dump(rdev);
+ rtnl_unlock();
return err;
}
@@ -7674,9 +7663,12 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb)
int start = cb->args[2], idx = 0;
int err;
+ rtnl_lock();
err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
- if (err)
+ if (err) {
+ rtnl_unlock();
return err;
+ }
wdev_lock(wdev);
spin_lock_bh(&rdev->bss_lock);
@@ -7699,7 +7691,7 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb)
wdev_unlock(wdev);
cb->args[2] = idx;
- nl80211_finish_wdev_dump(rdev);
+ rtnl_unlock();
return skb->len;
}
@@ -7784,9 +7776,10 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb)
int res;
bool radio_stats;
+ rtnl_lock();
res = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
if (res)
- return res;
+ goto out_err;
/* prepare_wdev_dump parsed the attributes */
radio_stats = attrbuf[NL80211_ATTR_SURVEY_RADIO_STATS];
@@ -7827,7 +7820,7 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb)
cb->args[2] = survey_idx;
res = skb->len;
out_err:
- nl80211_finish_wdev_dump(rdev);
+ rtnl_unlock();
return res;
}
@@ -11508,17 +11501,13 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb,
void *data = NULL;
unsigned int data_len = 0;
- rtnl_lock();
-
if (cb->args[0]) {
/* subtract the 1 again here */
struct wiphy *wiphy = wiphy_idx_to_wiphy(cb->args[0] - 1);
struct wireless_dev *tmp;
- if (!wiphy) {
- err = -ENODEV;
- goto out_unlock;
- }
+ if (!wiphy)
+ return -ENODEV;
*rdev = wiphy_to_rdev(wiphy);
*wdev = NULL;
@@ -11538,23 +11527,19 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb,
err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize,
attrbuf, nl80211_fam.maxattr, nl80211_policy);
if (err)
- goto out_unlock;
+ return err;
if (!attrbuf[NL80211_ATTR_VENDOR_ID] ||
- !attrbuf[NL80211_ATTR_VENDOR_SUBCMD]) {
- err = -EINVAL;
- goto out_unlock;
- }
+ !attrbuf[NL80211_ATTR_VENDOR_SUBCMD])
+ return -EINVAL;
*wdev = __cfg80211_wdev_from_attrs(sock_net(skb->sk), attrbuf);
if (IS_ERR(*wdev))
*wdev = NULL;
*rdev = __cfg80211_rdev_from_attrs(sock_net(skb->sk), attrbuf);
- if (IS_ERR(*rdev)) {
- err = PTR_ERR(*rdev);
- goto out_unlock;
- }
+ if (IS_ERR(*rdev))
+ return PTR_ERR(*rdev);
vid = nla_get_u32(attrbuf[NL80211_ATTR_VENDOR_ID]);
subcmd = nla_get_u32(attrbuf[NL80211_ATTR_VENDOR_SUBCMD]);
@@ -11567,19 +11552,15 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb,
if (vcmd->info.vendor_id != vid || vcmd->info.subcmd != subcmd)
continue;
- if (!vcmd->dumpit) {
- err = -EOPNOTSUPP;
- goto out_unlock;
- }
+ if (!vcmd->dumpit)
+ return -EOPNOTSUPP;
vcmd_idx = i;
break;
}
- if (vcmd_idx < 0) {
- err = -EOPNOTSUPP;
- goto out_unlock;
- }
+ if (vcmd_idx < 0)
+ return -EOPNOTSUPP;
if (attrbuf[NL80211_ATTR_VENDOR_DATA]) {
data = nla_data(attrbuf[NL80211_ATTR_VENDOR_DATA]);
@@ -11596,9 +11577,6 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb,
/* keep rtnl locked in successful case */
return 0;
- out_unlock:
- rtnl_unlock();
- return err;
}
static int nl80211_vendor_cmd_dump(struct sk_buff *skb,
@@ -11613,9 +11591,10 @@ static int nl80211_vendor_cmd_dump(struct sk_buff *skb,
int err;
struct nlattr *vendor_data;
+ rtnl_lock();
err = nl80211_prepare_vendor_dump(skb, cb, &rdev, &wdev);
if (err)
- return err;
+ goto out;
vcmd_idx = cb->args[2];
data = (void *)cb->args[3];
@@ -11624,15 +11603,21 @@ static int nl80211_vendor_cmd_dump(struct sk_buff *skb,
if (vcmd->flags & (WIPHY_VENDOR_CMD_NEED_WDEV |
WIPHY_VENDOR_CMD_NEED_NETDEV)) {
- if (!wdev)
- return -EINVAL;
+ if (!wdev) {
+ err = -EINVAL;
+ goto out;
+ }
if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_NETDEV &&
- !wdev->netdev)
- return -EINVAL;
+ !wdev->netdev) {
+ err = -EINVAL;
+ goto out;
+ }
if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_RUNNING) {
- if (!wdev_running(wdev))
- return -ENETDOWN;
+ if (!wdev_running(wdev)) {
+ err = -ENETDOWN;
+ goto out;
+ }
}
}
diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c
index 16b6b59..570a2b6 100644
--- a/net/wireless/sysfs.c
+++ b/net/wireless/sysfs.c
@@ -132,12 +132,10 @@ static int wiphy_resume(struct device *dev)
/* Age scan results with time spent in suspend */
cfg80211_bss_age(rdev, get_seconds() - rdev->suspend_at);
- if (rdev->ops->resume) {
- rtnl_lock();
- if (rdev->wiphy.registered)
- ret = rdev_resume(rdev);
- rtnl_unlock();
- }
+ rtnl_lock();
+ if (rdev->wiphy.registered && rdev->ops->resume)
+ ret = rdev_resume(rdev);
+ rtnl_unlock();
return ret;
}
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index fd28a49..8b911c2 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -852,7 +852,8 @@ static int x25_wait_for_data(struct sock *sk, long timeout)
return rc;
}
-static int x25_accept(struct socket *sock, struct socket *newsock, int flags)
+static int x25_accept(struct socket *sock, struct socket *newsock, int flags,
+ bool kern)
{
struct sock *sk = sock->sk;
struct sock *newsk;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 0806dcc..236cbbc 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1243,7 +1243,7 @@ static inline int policy_to_flow_dir(int dir)
}
static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
- const struct flowi *fl)
+ const struct flowi *fl, u16 family)
{
struct xfrm_policy *pol;
@@ -1251,8 +1251,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
again:
pol = rcu_dereference(sk->sk_policy[dir]);
if (pol != NULL) {
- bool match = xfrm_selector_match(&pol->selector, fl,
- sk->sk_family);
+ bool match = xfrm_selector_match(&pol->selector, fl, family);
int err = 0;
if (match) {
@@ -2239,7 +2238,7 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
sk = sk_const_to_full_sk(sk);
if (sk && sk->sk_policy[XFRM_POLICY_OUT]) {
num_pols = 1;
- pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl);
+ pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family);
err = xfrm_expand_policies(fl, family, pols,
&num_pols, &num_xfrms);
if (err < 0)
@@ -2518,7 +2517,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
pol = NULL;
sk = sk_to_full_sk(sk);
if (sk && sk->sk_policy[dir]) {
- pol = xfrm_sk_policy_lookup(sk, dir, &fl);
+ pol = xfrm_sk_policy_lookup(sk, dir, &fl, family);
if (IS_ERR(pol)) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);
return 0;
@@ -3069,6 +3068,11 @@ static int __net_init xfrm_net_init(struct net *net)
{
int rv;
+ /* Initialize the per-net locks here */
+ spin_lock_init(&net->xfrm.xfrm_state_lock);
+ spin_lock_init(&net->xfrm.xfrm_policy_lock);
+ mutex_init(&net->xfrm.xfrm_cfg_mutex);
+
rv = xfrm_statistics_init(net);
if (rv < 0)
goto out_statistics;
@@ -3085,11 +3089,6 @@ static int __net_init xfrm_net_init(struct net *net)
if (rv < 0)
goto out;
- /* Initialize the per-net locks here */
- spin_lock_init(&net->xfrm.xfrm_state_lock);
- spin_lock_init(&net->xfrm.xfrm_policy_lock);
- mutex_init(&net->xfrm.xfrm_cfg_mutex);
-
return 0;
out:
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 9705c27..40a8aa3 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -412,7 +412,14 @@ static inline int xfrm_replay_verify_len(struct xfrm_replay_state_esn *replay_es
up = nla_data(rp);
ulen = xfrm_replay_state_esn_len(up);
- if (nla_len(rp) < ulen || xfrm_replay_state_esn_len(replay_esn) != ulen)
+ /* Check the overall length and the internal bitmap length to avoid
+ * potential overflow. */
+ if (nla_len(rp) < ulen ||
+ xfrm_replay_state_esn_len(replay_esn) != ulen ||
+ replay_esn->bmp_len != up->bmp_len)
+ return -EINVAL;
+
+ if (up->replay_window > up->bmp_len * sizeof(__u32) * 8)
return -EINVAL;
return 0;
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 09e9d53..d42b495 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -34,6 +34,8 @@
hostprogs-y += tc_l2_redirect
hostprogs-y += lwt_len_hist
hostprogs-y += xdp_tx_iptunnel
+hostprogs-y += test_map_in_map
+hostprogs-y += per_socket_stats_example
# Libbpf dependencies
LIBBPF := ../../tools/lib/bpf/bpf.o
@@ -72,6 +74,8 @@
tc_l2_redirect-objs := bpf_load.o $(LIBBPF) tc_l2_redirect_user.o
lwt_len_hist-objs := bpf_load.o $(LIBBPF) lwt_len_hist_user.o
xdp_tx_iptunnel-objs := bpf_load.o $(LIBBPF) xdp_tx_iptunnel_user.o
+test_map_in_map-objs := bpf_load.o $(LIBBPF) test_map_in_map_user.o
+per_socket_stats_example-objs := $(LIBBPF) cookie_uid_helper_example.o
# Tell kbuild to always build the programs
always := $(hostprogs-y)
@@ -105,6 +109,8 @@
always += sampleip_kern.o
always += lwt_len_hist_kern.o
always += xdp_tx_iptunnel_kern.o
+always += test_map_in_map_kern.o
+always += cookie_uid_helper_example.o
HOSTCFLAGS += -I$(objtree)/usr/include
HOSTCFLAGS += -I$(srctree)/tools/lib/
@@ -139,6 +145,7 @@
HOSTLOADLIBES_tc_l2_redirect += -l elf
HOSTLOADLIBES_lwt_len_hist += -l elf
HOSTLOADLIBES_xdp_tx_iptunnel += -lelf
+HOSTLOADLIBES_test_map_in_map += -lelf
# Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
# make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h
index faaffe2..52de9d8 100644
--- a/samples/bpf/bpf_helpers.h
+++ b/samples/bpf/bpf_helpers.h
@@ -80,6 +80,7 @@ struct bpf_map_def {
unsigned int value_size;
unsigned int max_entries;
unsigned int map_flags;
+ unsigned int inner_map_idx;
};
static int (*bpf_skb_load_bytes)(void *ctx, int off, void *to, int len) =
diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index b86ee54..dcdce12 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -43,6 +43,7 @@ struct bpf_map_def {
unsigned int value_size;
unsigned int max_entries;
unsigned int map_flags;
+ unsigned int inner_map_idx;
};
static int populate_prog_array(const char *event, int prog_fd)
@@ -198,11 +199,22 @@ static int load_maps(struct bpf_map_def *maps, int len)
for (i = 0; i < len / sizeof(struct bpf_map_def); i++) {
- map_fd[i] = bpf_create_map(maps[i].type,
- maps[i].key_size,
- maps[i].value_size,
- maps[i].max_entries,
- maps[i].map_flags);
+ if (maps[i].type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
+ maps[i].type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+ int inner_map_fd = map_fd[maps[i].inner_map_idx];
+
+ map_fd[i] = bpf_create_map_in_map(maps[i].type,
+ maps[i].key_size,
+ inner_map_fd,
+ maps[i].max_entries,
+ maps[i].map_flags);
+ } else {
+ map_fd[i] = bpf_create_map(maps[i].type,
+ maps[i].key_size,
+ maps[i].value_size,
+ maps[i].max_entries,
+ maps[i].map_flags);
+ }
if (map_fd[i] < 0) {
printf("failed to create a map: %d %s\n",
errno, strerror(errno));
diff --git a/samples/bpf/cookie_uid_helper_example.c b/samples/bpf/cookie_uid_helper_example.c
new file mode 100644
index 0000000..ad5afed
--- /dev/null
+++ b/samples/bpf/cookie_uid_helper_example.c
@@ -0,0 +1,321 @@
+/* This test is a demo of using get_socket_uid and get_socket_cookie
+ * helper function to do per socket based network traffic monitoring.
+ * It requires iptables version higher then 1.6.1. to load pinned eBPF
+ * program into the xt_bpf match.
+ *
+ * TEST:
+ * ./run_cookie_uid_helper_example.sh -option
+ * option:
+ * -t: do traffic monitoring test, the program will continuously
+ * print out network traffic happens after program started A sample
+ * output is shown below:
+ *
+ * cookie: 877, uid: 0x3e8, Pakcet Count: 20, Bytes Count: 11058
+ * cookie: 132, uid: 0x0, Pakcet Count: 2, Bytes Count: 286
+ * cookie: 812, uid: 0x3e8, Pakcet Count: 3, Bytes Count: 1726
+ * cookie: 802, uid: 0x3e8, Pakcet Count: 2, Bytes Count: 104
+ * cookie: 877, uid: 0x3e8, Pakcet Count: 20, Bytes Count: 11058
+ * cookie: 831, uid: 0x3e8, Pakcet Count: 2, Bytes Count: 104
+ * cookie: 0, uid: 0x0, Pakcet Count: 6, Bytes Count: 712
+ * cookie: 880, uid: 0xfffe, Pakcet Count: 1, Bytes Count: 70
+ *
+ * -s: do getsockopt SO_COOKIE test, the program will set up a pair of
+ * UDP sockets and send packets between them. And read out the traffic data
+ * directly from the ebpf map based on the socket cookie.
+ *
+ * Clean up: if using shell script, the script file will delete the iptables
+ * rule and unmount the bpf program when exit. Else the iptables rule need
+ * to be deleted by hand, see run_cookie_uid_helper_example.sh for detail.
+ */
+
+#define _GNU_SOURCE
+
+#define offsetof(type, member) __builtin_offsetof(type, member)
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <limits.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <net/if.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <bpf/bpf.h>
+#include "libbpf.h"
+
+#define PORT 8888
+
+struct stats {
+ uint32_t uid;
+ uint64_t packets;
+ uint64_t bytes;
+};
+
+static int map_fd, prog_fd;
+
+static bool test_finish;
+
+static void maps_create(void)
+{
+ map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(uint32_t),
+ sizeof(struct stats), 100, 0);
+ if (map_fd < 0)
+ error(1, errno, "map create failed!\n");
+}
+
+static void prog_load(void)
+{
+ static char log_buf[1 << 16];
+
+ struct bpf_insn prog[] = {
+ /*
+ * Save sk_buff for future usage. value stored in R6 to R10 will
+ * not be reset after a bpf helper function call.
+ */
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ /*
+ * pc1: BPF_FUNC_get_socket_cookie takes one parameter,
+ * R1: sk_buff
+ */
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_socket_cookie),
+ /* pc2-4: save &socketCookie to r7 for future usage*/
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ /*
+ * pc5-8: set up the registers for BPF_FUNC_map_lookup_elem,
+ * it takes two parameters (R1: map_fd, R2: &socket_cookie)
+ */
+ BPF_LD_MAP_FD(BPF_REG_1, map_fd),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ /*
+ * pc9. if r0 != 0x0, go to pc+14, since we have the cookie
+ * stored already
+ * Otherwise do pc10-22 to setup a new data entry.
+ */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 14),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_socket_uid),
+ /*
+ * Place a struct stats in the R10 stack and sequentially
+ * place the member value into the memory. Packets value
+ * is set by directly place a IMM value 1 into the stack.
+ */
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0,
+ -32 + offsetof(struct stats, uid)),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10,
+ -32 + offsetof(struct stats, packets), 1),
+ /*
+ * __sk_buff is a special struct used for eBPF program to
+ * directly access some sk_buff field.
+ */
+ BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+ offsetof(struct __sk_buff, len)),
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1,
+ -32 + offsetof(struct stats, bytes)),
+ /*
+ * add new map entry using BPF_FUNC_map_update_elem, it takes
+ * 4 parameters (R1: map_fd, R2: &socket_cookie, R3: &stats,
+ * R4: flags)
+ */
+ BPF_LD_MAP_FD(BPF_REG_1, map_fd),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+ BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -32),
+ BPF_MOV64_IMM(BPF_REG_4, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_update_elem),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 5),
+ /*
+ * pc24-30 update the packet info to a exist data entry, it can
+ * be done by directly write to pointers instead of using
+ * BPF_FUNC_map_update_elem helper function
+ */
+ BPF_MOV64_REG(BPF_REG_9, BPF_REG_0),
+ BPF_MOV64_IMM(BPF_REG_1, 1),
+ BPF_STX_XADD(BPF_DW, BPF_REG_9, BPF_REG_1,
+ offsetof(struct stats, packets)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+ offsetof(struct __sk_buff, len)),
+ BPF_STX_XADD(BPF_DW, BPF_REG_9, BPF_REG_1,
+ offsetof(struct stats, bytes)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6,
+ offsetof(struct __sk_buff, len)),
+ BPF_EXIT_INSN(),
+ };
+ prog_fd = bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, prog,
+ ARRAY_SIZE(prog), "GPL", 0,
+ log_buf, sizeof(log_buf));
+ if (prog_fd < 0)
+ error(1, errno, "failed to load prog\n%s\n", log_buf);
+}
+
+static void prog_attach_iptables(char *file)
+{
+ int ret;
+ char rules[100];
+
+ if (bpf_obj_pin(prog_fd, file))
+ error(1, errno, "bpf_obj_pin");
+ if (strlen(file) > 50) {
+ printf("file path too long: %s\n", file);
+ exit(1);
+ }
+ sprintf(rules, "iptables -A OUTPUT -m bpf --object-pinned %s -j ACCEPT",
+ file);
+ ret = system(rules);
+ if (ret < 0) {
+ printf("iptables rule update failed: %d/n", WEXITSTATUS(ret));
+ exit(1);
+ }
+}
+
+static void print_table(void)
+{
+ struct stats curEntry;
+ uint32_t curN = UINT32_MAX;
+ uint32_t nextN;
+ int res;
+
+ while (bpf_map_get_next_key(map_fd, &curN, &nextN) > -1) {
+ curN = nextN;
+ res = bpf_map_lookup_elem(map_fd, &curN, &curEntry);
+ if (res < 0) {
+ error(1, errno, "fail to get entry value of Key: %u\n",
+ curN);
+ } else {
+ printf("cookie: %u, uid: 0x%x, Packet Count: %lu,"
+ " Bytes Count: %lu\n", curN, curEntry.uid,
+ curEntry.packets, curEntry.bytes);
+ }
+ }
+}
+
+static void udp_client(void)
+{
+ struct sockaddr_in si_other = {0};
+ struct sockaddr_in si_me = {0};
+ struct stats dataEntry;
+ int s_rcv, s_send, i, recv_len;
+ char message = 'a';
+ char buf;
+ uint64_t cookie;
+ int res;
+ socklen_t cookie_len = sizeof(cookie);
+ socklen_t slen = sizeof(si_other);
+
+ s_rcv = socket(PF_INET, SOCK_DGRAM, 0);
+ if (s_rcv < 0)
+ error(1, errno, "rcv socket creat failed!\n");
+ si_other.sin_family = AF_INET;
+ si_other.sin_port = htons(PORT);
+ if (inet_aton("127.0.0.1", &si_other.sin_addr) == 0)
+ error(1, errno, "inet_aton\n");
+ if (bind(s_rcv, (struct sockaddr *)&si_other, sizeof(si_other)) == -1)
+ error(1, errno, "bind\n");
+ s_send = socket(PF_INET, SOCK_DGRAM, 0);
+ if (s_send < 0)
+ error(1, errno, "send socket creat failed!\n");
+ res = getsockopt(s_send, SOL_SOCKET, SO_COOKIE, &cookie, &cookie_len);
+ if (res < 0)
+ printf("get cookie failed: %s\n", strerror(errno));
+ res = bpf_map_lookup_elem(map_fd, &cookie, &dataEntry);
+ if (res != -1)
+ error(1, errno, "socket stat found while flow not active\n");
+ for (i = 0; i < 10; i++) {
+ res = sendto(s_send, &message, sizeof(message), 0,
+ (struct sockaddr *)&si_other, slen);
+ if (res == -1)
+ error(1, errno, "send\n");
+ if (res != sizeof(message))
+ error(1, 0, "%uB != %luB\n", res, sizeof(message));
+ recv_len = recvfrom(s_rcv, &buf, sizeof(buf), 0,
+ (struct sockaddr *)&si_me, &slen);
+ if (recv_len < 0)
+ error(1, errno, "revieve\n");
+ res = memcmp(&(si_other.sin_addr), &(si_me.sin_addr),
+ sizeof(si_me.sin_addr));
+ if (res != 0)
+ error(1, EFAULT, "sender addr error: %d\n", res);
+ printf("Message received: %c\n", buf);
+ res = bpf_map_lookup_elem(map_fd, &cookie, &dataEntry);
+ if (res < 0)
+ error(1, errno, "lookup sk stat failed, cookie: %lu\n",
+ cookie);
+ printf("cookie: %lu, uid: 0x%x, Packet Count: %lu,"
+ " Bytes Count: %lu\n\n", cookie, dataEntry.uid,
+ dataEntry.packets, dataEntry.bytes);
+ }
+ close(s_send);
+ close(s_rcv);
+}
+
+static int usage(void)
+{
+ printf("Usage: ./run_cookie_uid_helper_example.sh"
+ " bpfObjName -option\n"
+ " -t traffic monitor test\n"
+ " -s getsockopt cookie test\n");
+ return 1;
+}
+
+void finish(int ret)
+{
+ test_finish = true;
+}
+
+int main(int argc, char *argv[])
+{
+ int opt;
+ bool cfg_test_traffic = false;
+ bool cfg_test_cookie = false;
+
+ if (argc != 3)
+ return usage();
+ while ((opt = getopt(argc, argv, "ts")) != -1) {
+ switch (opt) {
+ case 't':
+ cfg_test_traffic = true;
+ break;
+ case 's':
+ cfg_test_cookie = true;
+ break;
+
+ default:
+ printf("unknown option %c\n", opt);
+ usage();
+ return -1;
+ }
+ }
+ maps_create();
+ prog_load();
+ prog_attach_iptables(argv[2]);
+ if (cfg_test_traffic) {
+ if (signal(SIGINT, finish) == SIG_ERR)
+ error(1, errno, "register handler failed");
+ while (!test_finish) {
+ print_table();
+ printf("\n");
+ sleep(1);
+ };
+ } else if (cfg_test_cookie) {
+ udp_client();
+ }
+ close(prog_fd);
+ close(map_fd);
+ return 0;
+}
diff --git a/samples/bpf/libbpf.h b/samples/bpf/libbpf.h
index 3705fba..8ab36a0 100644
--- a/samples/bpf/libbpf.h
+++ b/samples/bpf/libbpf.h
@@ -135,6 +135,16 @@ struct bpf_insn;
.off = OFF, \
.imm = 0 })
+/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */
+
+#define BPF_STX_XADD(SIZE, DST, SRC, OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = OFF, \
+ .imm = 0 })
+
/* Memory store, *(uint *) (dst_reg + off16) = imm32 */
#define BPF_ST_MEM(SIZE, DST, OFF, IMM) \
diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test_kern.c
index a91872a..9da2a34 100644
--- a/samples/bpf/map_perf_test_kern.c
+++ b/samples/bpf/map_perf_test_kern.c
@@ -65,6 +65,13 @@ struct bpf_map_def SEC("maps") lpm_trie_map_alloc = {
.map_flags = BPF_F_NO_PREALLOC,
};
+struct bpf_map_def SEC("maps") array_map = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(long),
+ .max_entries = MAX_ENTRIES,
+};
+
SEC("kprobe/sys_getuid")
int stress_hmap(struct pt_regs *ctx)
{
@@ -165,5 +172,31 @@ int stress_lpm_trie_map_alloc(struct pt_regs *ctx)
return 0;
}
+SEC("kprobe/sys_getpgid")
+int stress_hash_map_lookup(struct pt_regs *ctx)
+{
+ u32 key = 1, i;
+ long *value;
+
+#pragma clang loop unroll(full)
+ for (i = 0; i < 64; ++i)
+ value = bpf_map_lookup_elem(&hash_map, &key);
+
+ return 0;
+}
+
+SEC("kprobe/sys_getpgrp")
+int stress_array_map_lookup(struct pt_regs *ctx)
+{
+ u32 key = 1, i;
+ long *value;
+
+#pragma clang loop unroll(full)
+ for (i = 0; i < 64; ++i)
+ value = bpf_map_lookup_elem(&array_map, &key);
+
+ return 0;
+}
+
char _license[] SEC("license") = "GPL";
u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c
index 680260a..e29ff31 100644
--- a/samples/bpf/map_perf_test_user.c
+++ b/samples/bpf/map_perf_test_user.c
@@ -38,6 +38,8 @@ static __u64 time_get_ns(void)
#define LRU_HASH_PREALLOC (1 << 4)
#define PERCPU_LRU_HASH_PREALLOC (1 << 5)
#define LPM_KMALLOC (1 << 6)
+#define HASH_LOOKUP (1 << 7)
+#define ARRAY_LOOKUP (1 << 8)
static int test_flags = ~0;
@@ -125,6 +127,30 @@ static void test_lpm_kmalloc(int cpu)
cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
}
+static void test_hash_lookup(int cpu)
+{
+ __u64 start_time;
+ int i;
+
+ start_time = time_get_ns();
+ for (i = 0; i < MAX_CNT; i++)
+ syscall(__NR_getpgid, 0);
+ printf("%d:hash_lookup %lld lookups per sec\n",
+ cpu, MAX_CNT * 1000000000ll * 64 / (time_get_ns() - start_time));
+}
+
+static void test_array_lookup(int cpu)
+{
+ __u64 start_time;
+ int i;
+
+ start_time = time_get_ns();
+ for (i = 0; i < MAX_CNT; i++)
+ syscall(__NR_getpgrp, 0);
+ printf("%d:array_lookup %lld lookups per sec\n",
+ cpu, MAX_CNT * 1000000000ll * 64 / (time_get_ns() - start_time));
+}
+
static void loop(int cpu)
{
cpu_set_t cpuset;
@@ -153,6 +179,12 @@ static void loop(int cpu)
if (test_flags & LPM_KMALLOC)
test_lpm_kmalloc(cpu);
+
+ if (test_flags & HASH_LOOKUP)
+ test_hash_lookup(cpu);
+
+ if (test_flags & ARRAY_LOOKUP)
+ test_array_lookup(cpu);
}
static void run_perf_test(int tasks)
diff --git a/samples/bpf/run_cookie_uid_helper_example.sh b/samples/bpf/run_cookie_uid_helper_example.sh
new file mode 100755
index 0000000..f898cfa
--- /dev/null
+++ b/samples/bpf/run_cookie_uid_helper_example.sh
@@ -0,0 +1,14 @@
+#!/bin/bash
+local_dir="$(pwd)"
+root_dir=$local_dir/../..
+mnt_dir=$(mktemp -d --tmp)
+
+on_exit() {
+ iptables -D OUTPUT -m bpf --object-pinned ${mnt_dir}/bpf_prog -j ACCEPT
+ umount ${mnt_dir}
+ rm -r ${mnt_dir}
+}
+
+trap on_exit EXIT
+mount -t bpf bpf ${mnt_dir}
+./per_socket_stats_example ${mnt_dir}/bpf_prog $1
diff --git a/samples/bpf/test_map_in_map_kern.c b/samples/bpf/test_map_in_map_kern.c
new file mode 100644
index 0000000..42c44d0
--- /dev/null
+++ b/samples/bpf/test_map_in_map_kern.c
@@ -0,0 +1,173 @@
+/*
+ * Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#define KBUILD_MODNAME "foo"
+#include <linux/ptrace.h>
+#include <linux/version.h>
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/in6.h>
+#include "bpf_helpers.h"
+
+#define MAX_NR_PORTS 65536
+
+/* map #0 */
+struct bpf_map_def SEC("maps") port_a = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(int),
+ .max_entries = MAX_NR_PORTS,
+};
+
+/* map #1 */
+struct bpf_map_def SEC("maps") port_h = {
+ .type = BPF_MAP_TYPE_HASH,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(int),
+ .max_entries = 1,
+};
+
+/* map #2 */
+struct bpf_map_def SEC("maps") reg_result_h = {
+ .type = BPF_MAP_TYPE_HASH,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(int),
+ .max_entries = 1,
+};
+
+/* map #3 */
+struct bpf_map_def SEC("maps") inline_result_h = {
+ .type = BPF_MAP_TYPE_HASH,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(int),
+ .max_entries = 1,
+};
+
+/* map #4 */ /* Test case #0 */
+struct bpf_map_def SEC("maps") a_of_port_a = {
+ .type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
+ .key_size = sizeof(u32),
+ .inner_map_idx = 0, /* map_fd[0] is port_a */
+ .max_entries = MAX_NR_PORTS,
+};
+
+/* map #5 */ /* Test case #1 */
+struct bpf_map_def SEC("maps") h_of_port_a = {
+ .type = BPF_MAP_TYPE_HASH_OF_MAPS,
+ .key_size = sizeof(u32),
+ .inner_map_idx = 0, /* map_fd[0] is port_a */
+ .max_entries = 1,
+};
+
+/* map #6 */ /* Test case #2 */
+struct bpf_map_def SEC("maps") h_of_port_h = {
+ .type = BPF_MAP_TYPE_HASH_OF_MAPS,
+ .key_size = sizeof(u32),
+ .inner_map_idx = 1, /* map_fd[1] is port_h */
+ .max_entries = 1,
+};
+
+static __always_inline int do_reg_lookup(void *inner_map, u32 port)
+{
+ int *result;
+
+ result = bpf_map_lookup_elem(inner_map, &port);
+ return result ? *result : -ENOENT;
+}
+
+static __always_inline int do_inline_array_lookup(void *inner_map, u32 port)
+{
+ int *result;
+
+ if (inner_map != &port_a)
+ return -EINVAL;
+
+ result = bpf_map_lookup_elem(&port_a, &port);
+ return result ? *result : -ENOENT;
+}
+
+static __always_inline int do_inline_hash_lookup(void *inner_map, u32 port)
+{
+ int *result;
+
+ if (inner_map != &port_h)
+ return -EINVAL;
+
+ result = bpf_map_lookup_elem(&port_h, &port);
+ return result ? *result : -ENOENT;
+}
+
+SEC("kprobe/sys_connect")
+int trace_sys_connect(struct pt_regs *ctx)
+{
+ struct sockaddr_in6 *in6;
+ u16 test_case, port, dst6[8];
+ int addrlen, ret, inline_ret, ret_key = 0;
+ u32 port_key;
+ void *outer_map, *inner_map;
+ bool inline_hash = false;
+
+ in6 = (struct sockaddr_in6 *)PT_REGS_PARM2(ctx);
+ addrlen = (int)PT_REGS_PARM3(ctx);
+
+ if (addrlen != sizeof(*in6))
+ return 0;
+
+ ret = bpf_probe_read(dst6, sizeof(dst6), &in6->sin6_addr);
+ if (ret) {
+ inline_ret = ret;
+ goto done;
+ }
+
+ if (dst6[0] != 0xdead || dst6[1] != 0xbeef)
+ return 0;
+
+ test_case = dst6[7];
+
+ ret = bpf_probe_read(&port, sizeof(port), &in6->sin6_port);
+ if (ret) {
+ inline_ret = ret;
+ goto done;
+ }
+
+ port_key = port;
+
+ ret = -ENOENT;
+ if (test_case == 0) {
+ outer_map = &a_of_port_a;
+ } else if (test_case == 1) {
+ outer_map = &h_of_port_a;
+ } else if (test_case == 2) {
+ outer_map = &h_of_port_h;
+ } else {
+ ret = __LINE__;
+ inline_ret = ret;
+ goto done;
+ }
+
+ inner_map = bpf_map_lookup_elem(outer_map, &port_key);
+ if (!inner_map) {
+ ret = __LINE__;
+ inline_ret = ret;
+ goto done;
+ }
+
+ ret = do_reg_lookup(inner_map, port_key);
+
+ if (test_case == 0 || test_case == 1)
+ inline_ret = do_inline_array_lookup(inner_map, port_key);
+ else
+ inline_ret = do_inline_hash_lookup(inner_map, port_key);
+
+done:
+ bpf_map_update_elem(®_result_h, &ret_key, &ret, BPF_ANY);
+ bpf_map_update_elem(&inline_result_h, &ret_key, &inline_ret, BPF_ANY);
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/test_map_in_map_user.c b/samples/bpf/test_map_in_map_user.c
new file mode 100644
index 0000000..f62fdc2
--- /dev/null
+++ b/samples/bpf/test_map_in_map_user.c
@@ -0,0 +1,116 @@
+/*
+ * Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <sys/resource.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
+#include <stdint.h>
+#include <assert.h>
+#include <errno.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+
+#define PORT_A (map_fd[0])
+#define PORT_H (map_fd[1])
+#define REG_RESULT_H (map_fd[2])
+#define INLINE_RESULT_H (map_fd[3])
+#define A_OF_PORT_A (map_fd[4]) /* Test case #0 */
+#define H_OF_PORT_A (map_fd[5]) /* Test case #1 */
+#define H_OF_PORT_H (map_fd[6]) /* Test case #2 */
+
+static const char * const test_names[] = {
+ "Array of Array",
+ "Hash of Array",
+ "Hash of Hash",
+};
+
+#define NR_TESTS (sizeof(test_names) / sizeof(*test_names))
+
+static void populate_map(uint32_t port_key, int magic_result)
+{
+ int ret;
+
+ ret = bpf_map_update_elem(PORT_A, &port_key, &magic_result, BPF_ANY);
+ assert(!ret);
+
+ ret = bpf_map_update_elem(PORT_H, &port_key, &magic_result,
+ BPF_NOEXIST);
+ assert(!ret);
+
+ ret = bpf_map_update_elem(A_OF_PORT_A, &port_key, &PORT_A, BPF_ANY);
+ assert(!ret);
+
+ ret = bpf_map_update_elem(H_OF_PORT_A, &port_key, &PORT_A, BPF_NOEXIST);
+ assert(!ret);
+
+ ret = bpf_map_update_elem(H_OF_PORT_H, &port_key, &PORT_H, BPF_NOEXIST);
+ assert(!ret);
+}
+
+static void test_map_in_map(void)
+{
+ struct sockaddr_in6 in6 = { .sin6_family = AF_INET6 };
+ uint32_t result_key = 0, port_key;
+ int result, inline_result;
+ int magic_result = 0xfaceb00c;
+ int ret;
+ int i;
+
+ port_key = rand() & 0x00FF;
+ populate_map(port_key, magic_result);
+
+ in6.sin6_addr.s6_addr16[0] = 0xdead;
+ in6.sin6_addr.s6_addr16[1] = 0xbeef;
+ in6.sin6_port = port_key;
+
+ for (i = 0; i < NR_TESTS; i++) {
+ printf("%s: ", test_names[i]);
+
+ in6.sin6_addr.s6_addr16[7] = i;
+ ret = connect(-1, (struct sockaddr *)&in6, sizeof(in6));
+ assert(ret == -1 && errno == EBADF);
+
+ ret = bpf_map_lookup_elem(REG_RESULT_H, &result_key, &result);
+ assert(!ret);
+
+ ret = bpf_map_lookup_elem(INLINE_RESULT_H, &result_key,
+ &inline_result);
+ assert(!ret);
+
+ if (result != magic_result || inline_result != magic_result) {
+ printf("Error. result:%d inline_result:%d\n",
+ result, inline_result);
+ exit(1);
+ }
+
+ bpf_map_delete_elem(REG_RESULT_H, &result_key);
+ bpf_map_delete_elem(INLINE_RESULT_H, &result_key);
+
+ printf("Pass\n");
+ }
+}
+
+int main(int argc, char **argv)
+{
+ struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+ char filename[256];
+
+ assert(!setrlimit(RLIMIT_MEMLOCK, &r));
+
+ snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+ if (load_bpf_file(filename)) {
+ printf("%s", bpf_log_buf);
+ return 1;
+ }
+
+ test_map_in_map();
+
+ return 0;
+}
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index d6ca649..afe3fd3 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -148,6 +148,10 @@
# Usage: EXTRA_CFLAGS += $(call cc-ifversion, -lt, 0402, -O1)
cc-ifversion = $(shell [ $(cc-version) $(1) $(2) ] && echo $(3) || echo $(4))
+# cc-if-fullversion
+# Usage: EXTRA_CFLAGS += $(call cc-if-fullversion, -lt, 040502, -O1)
+cc-if-fullversion = $(shell [ $(cc-fullversion) $(1) $(2) ] && echo $(3) || echo $(4))
+
# cc-ldoption
# Usage: ldflags += $(call cc-ldoption, -Wl$(comma)--hash-style=both)
cc-ldoption = $(call try-run,\
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 0a07f90..7234e61 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -155,7 +155,7 @@
# $(call addtree,-I$(obj)) locates .h files in srctree, from generated .c files
# and locates generated .h files
# FIXME: Replace both with specific CFLAGS* statements in the makefiles
-__c_flags = $(if $(obj),-I$(srctree)/$(src) -I$(obj)) \
+__c_flags = $(if $(obj),$(call addtree,-I$(src)) -I$(obj)) \
$(call flags,_c_flags)
__a_flags = $(call flags,_a_flags)
__cpp_flags = $(call flags,_cpp_flags)
diff --git a/scripts/gcc-plugins/sancov_plugin.c b/scripts/gcc-plugins/sancov_plugin.c
index 9b0b5cb..0f98634 100644
--- a/scripts/gcc-plugins/sancov_plugin.c
+++ b/scripts/gcc-plugins/sancov_plugin.c
@@ -133,7 +133,7 @@ __visible int plugin_init(struct plugin_name_args *plugin_info, struct plugin_gc
#if BUILDING_GCC_VERSION < 6000
register_callback(plugin_name, PLUGIN_START_UNIT, &sancov_start_unit, NULL);
register_callback(plugin_name, PLUGIN_REGISTER_GGC_ROOTS, NULL, (void *)>_ggc_r_gt_sancov);
- register_callback(plugin_name, PLUGIN_PASS_MANAGER_SETUP, NULL, &sancov_plugin_pass_info);
+ register_callback(plugin_name, PLUGIN_PASS_MANAGER_SETUP, NULL, &sancov_pass_info);
#endif
return 0;
diff --git a/scripts/kconfig/gconf.c b/scripts/kconfig/gconf.c
index 26d208b..cfddddb 100644
--- a/scripts/kconfig/gconf.c
+++ b/scripts/kconfig/gconf.c
@@ -914,7 +914,7 @@ on_treeview2_button_press_event(GtkWidget * widget,
current = menu;
display_tree_part();
gtk_widget_set_sensitive(back_btn, TRUE);
- } else if ((col == COL_OPTION)) {
+ } else if (col == COL_OPTION) {
toggle_sym_value(menu);
gtk_tree_view_expand_row(view, path, TRUE);
}
diff --git a/scripts/module-common.lds b/scripts/module-common.lds
index cf7e52e..9b6e246 100644
--- a/scripts/module-common.lds
+++ b/scripts/module-common.lds
@@ -22,4 +22,6 @@
. = ALIGN(8);
.init_array 0 : { *(SORT(.init_array.*)) *(.init_array) }
+
+ __jump_table 0 : ALIGN(8) { KEEP(*(__jump_table)) }
}
diff --git a/scripts/spelling.txt b/scripts/spelling.txt
index 0458b03..0545f5a 100644
--- a/scripts/spelling.txt
+++ b/scripts/spelling.txt
@@ -372,6 +372,8 @@
disapear||disappear
disapeared||disappeared
disappared||disappeared
+disble||disable
+disbled||disabled
disconnet||disconnect
discontinous||discontinuous
dispertion||dispersion
@@ -732,6 +734,7 @@
overaall||overall
overhread||overhead
overlaping||overlapping
+overide||override
overrided||overridden
overriden||overridden
overun||overrun
diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c
index 2ca9cde..8e67bb4 100644
--- a/security/selinux/nlmsgtab.c
+++ b/security/selinux/nlmsgtab.c
@@ -69,6 +69,7 @@ static struct nlmsg_perm nlmsg_route_perms[] =
{ RTM_GETDCB, NETLINK_ROUTE_SOCKET__NLMSG_READ },
{ RTM_SETDCB, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
{ RTM_NEWNETCONF, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+ { RTM_DELNETCONF, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
{ RTM_GETNETCONF, NETLINK_ROUTE_SOCKET__NLMSG_READ },
{ RTM_NEWMDB, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
{ RTM_DELMDB, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index 4c93520..f3b1d7f 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -1832,6 +1832,7 @@ static int snd_seq_ioctl_set_client_pool(struct snd_seq_client *client,
info->output_pool != client->pool->size)) {
if (snd_seq_write_pool_allocated(client)) {
/* remove all existing cells */
+ snd_seq_pool_mark_closing(client->pool);
snd_seq_queue_client_leave_cells(client->number);
snd_seq_pool_done(client->pool);
}
diff --git a/sound/core/seq/seq_fifo.c b/sound/core/seq/seq_fifo.c
index 448efd4..01c4cfe 100644
--- a/sound/core/seq/seq_fifo.c
+++ b/sound/core/seq/seq_fifo.c
@@ -72,6 +72,9 @@ void snd_seq_fifo_delete(struct snd_seq_fifo **fifo)
return;
*fifo = NULL;
+ if (f->pool)
+ snd_seq_pool_mark_closing(f->pool);
+
snd_seq_fifo_clear(f);
/* wake up clients if any */
@@ -264,6 +267,10 @@ int snd_seq_fifo_resize(struct snd_seq_fifo *f, int poolsize)
/* NOTE: overflow flag is not cleared */
spin_unlock_irqrestore(&f->lock, flags);
+ /* close the old pool and wait until all users are gone */
+ snd_seq_pool_mark_closing(oldpool);
+ snd_use_lock_sync(&f->use_lock);
+
/* release cells in old pool */
for (cell = oldhead; cell; cell = next) {
next = cell->next;
diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c
index 1a1acf3..d4c61ec 100644
--- a/sound/core/seq/seq_memory.c
+++ b/sound/core/seq/seq_memory.c
@@ -415,6 +415,18 @@ int snd_seq_pool_init(struct snd_seq_pool *pool)
return 0;
}
+/* refuse the further insertion to the pool */
+void snd_seq_pool_mark_closing(struct snd_seq_pool *pool)
+{
+ unsigned long flags;
+
+ if (snd_BUG_ON(!pool))
+ return;
+ spin_lock_irqsave(&pool->lock, flags);
+ pool->closing = 1;
+ spin_unlock_irqrestore(&pool->lock, flags);
+}
+
/* remove events */
int snd_seq_pool_done(struct snd_seq_pool *pool)
{
@@ -425,10 +437,6 @@ int snd_seq_pool_done(struct snd_seq_pool *pool)
return -EINVAL;
/* wait for closing all threads */
- spin_lock_irqsave(&pool->lock, flags);
- pool->closing = 1;
- spin_unlock_irqrestore(&pool->lock, flags);
-
if (waitqueue_active(&pool->output_sleep))
wake_up(&pool->output_sleep);
@@ -485,6 +493,7 @@ int snd_seq_pool_delete(struct snd_seq_pool **ppool)
*ppool = NULL;
if (pool == NULL)
return 0;
+ snd_seq_pool_mark_closing(pool);
snd_seq_pool_done(pool);
kfree(pool);
return 0;
diff --git a/sound/core/seq/seq_memory.h b/sound/core/seq/seq_memory.h
index 4a2ec77..32f959c 100644
--- a/sound/core/seq/seq_memory.h
+++ b/sound/core/seq/seq_memory.h
@@ -84,6 +84,7 @@ static inline int snd_seq_total_cells(struct snd_seq_pool *pool)
int snd_seq_pool_init(struct snd_seq_pool *pool);
/* done pool - free events */
+void snd_seq_pool_mark_closing(struct snd_seq_pool *pool);
int snd_seq_pool_done(struct snd_seq_pool *pool);
/* create pool */
diff --git a/sound/pci/ctxfi/cthw20k1.c b/sound/pci/ctxfi/cthw20k1.c
index ab4cdab..79edd88 100644
--- a/sound/pci/ctxfi/cthw20k1.c
+++ b/sound/pci/ctxfi/cthw20k1.c
@@ -1905,7 +1905,7 @@ static int hw_card_start(struct hw *hw)
return err;
/* Set DMA transfer mask */
- if (dma_set_mask(&pci->dev, DMA_BIT_MASK(dma_bits))) {
+ if (!dma_set_mask(&pci->dev, DMA_BIT_MASK(dma_bits))) {
dma_set_coherent_mask(&pci->dev, DMA_BIT_MASK(dma_bits));
} else {
dma_set_mask(&pci->dev, DMA_BIT_MASK(32));
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index c15c51b..69266b8 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -261,6 +261,7 @@ enum {
CXT_FIXUP_HP_530,
CXT_FIXUP_CAP_MIX_AMP_5047,
CXT_FIXUP_MUTE_LED_EAPD,
+ CXT_FIXUP_HP_DOCK,
CXT_FIXUP_HP_SPECTRE,
CXT_FIXUP_HP_GATE_MIC,
};
@@ -778,6 +779,14 @@ static const struct hda_fixup cxt_fixups[] = {
.type = HDA_FIXUP_FUNC,
.v.func = cxt_fixup_mute_led_eapd,
},
+ [CXT_FIXUP_HP_DOCK] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x16, 0x21011020 }, /* line-out */
+ { 0x18, 0x2181103f }, /* line-in */
+ { }
+ }
+ },
[CXT_FIXUP_HP_SPECTRE] = {
.type = HDA_FIXUP_PINS,
.v.pins = (const struct hda_pintbl[]) {
@@ -839,6 +848,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = {
SND_PCI_QUIRK(0x1025, 0x0543, "Acer Aspire One 522", CXT_FIXUP_STEREO_DMIC),
SND_PCI_QUIRK(0x1025, 0x054c, "Acer Aspire 3830TG", CXT_FIXUP_ASPIRE_DMIC),
SND_PCI_QUIRK(0x1025, 0x054f, "Acer Aspire 4830T", CXT_FIXUP_ASPIRE_DMIC),
+ SND_PCI_QUIRK(0x103c, 0x8079, "HP EliteBook 840 G3", CXT_FIXUP_HP_DOCK),
SND_PCI_QUIRK(0x103c, 0x8174, "HP Spectre x360", CXT_FIXUP_HP_SPECTRE),
SND_PCI_QUIRK(0x103c, 0x8115, "HP Z1 Gen3", CXT_FIXUP_HP_GATE_MIC),
SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN),
@@ -871,6 +881,7 @@ static const struct hda_model_fixup cxt5066_fixup_models[] = {
{ .id = CXT_PINCFG_LEMOTE_A1205, .name = "lemote-a1205" },
{ .id = CXT_FIXUP_OLPC_XO, .name = "olpc-xo" },
{ .id = CXT_FIXUP_MUTE_LED_EAPD, .name = "mute-led-eapd" },
+ { .id = CXT_FIXUP_HP_DOCK, .name = "hp-dock" },
{}
};
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 4e11222..299835d 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4847,6 +4847,7 @@ enum {
ALC286_FIXUP_HP_GPIO_LED,
ALC280_FIXUP_HP_GPIO2_MIC_HOTKEY,
ALC280_FIXUP_HP_DOCK_PINS,
+ ALC269_FIXUP_HP_DOCK_GPIO_MIC1_LED,
ALC280_FIXUP_HP_9480M,
ALC288_FIXUP_DELL_HEADSET_MODE,
ALC288_FIXUP_DELL1_MIC_NO_PRESENCE,
@@ -4857,6 +4858,7 @@ enum {
ALC292_FIXUP_DISABLE_AAMIX,
ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK,
ALC298_FIXUP_DELL1_MIC_NO_PRESENCE,
+ ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE,
ALC275_FIXUP_DELL_XPS,
ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE,
ALC293_FIXUP_LENOVO_SPK_NOISE,
@@ -5388,6 +5390,16 @@ static const struct hda_fixup alc269_fixups[] = {
.chained = true,
.chain_id = ALC280_FIXUP_HP_GPIO4
},
+ [ALC269_FIXUP_HP_DOCK_GPIO_MIC1_LED] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x1b, 0x21011020 }, /* line-out */
+ { 0x18, 0x2181103f }, /* line-in */
+ { },
+ },
+ .chained = true,
+ .chain_id = ALC269_FIXUP_HP_GPIO_MIC1_LED
+ },
[ALC280_FIXUP_HP_9480M] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc280_fixup_hp_9480m,
@@ -5459,6 +5471,15 @@ static const struct hda_fixup alc269_fixups[] = {
.chained = true,
.chain_id = ALC269_FIXUP_HEADSET_MODE
},
+ [ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x18, 0x01a1913c }, /* use as headset mic, without its own jack detect */
+ { }
+ },
+ .chained = true,
+ .chain_id = ALC269_FIXUP_HEADSET_MODE
+ },
[ALC275_FIXUP_DELL_XPS] = {
.type = HDA_FIXUP_VERBS,
.v.verbs = (const struct hda_verb[]) {
@@ -5531,7 +5552,7 @@ static const struct hda_fixup alc269_fixups[] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc298_fixup_speaker_volume,
.chained = true,
- .chain_id = ALC298_FIXUP_DELL1_MIC_NO_PRESENCE,
+ .chain_id = ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE,
},
[ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER] = {
.type = HDA_FIXUP_PINS,
@@ -5647,7 +5668,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x2256, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
SND_PCI_QUIRK(0x103c, 0x2257, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
SND_PCI_QUIRK(0x103c, 0x2259, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
- SND_PCI_QUIRK(0x103c, 0x225a, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
+ SND_PCI_QUIRK(0x103c, 0x225a, "HP", ALC269_FIXUP_HP_DOCK_GPIO_MIC1_LED),
SND_PCI_QUIRK(0x103c, 0x2260, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
SND_PCI_QUIRK(0x103c, 0x2263, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
SND_PCI_QUIRK(0x103c, 0x2264, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
@@ -5816,6 +5837,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
{.id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC, .name = "headset-mode-no-hp-mic"},
{.id = ALC269_FIXUP_LENOVO_DOCK, .name = "lenovo-dock"},
{.id = ALC269_FIXUP_HP_GPIO_LED, .name = "hp-gpio-led"},
+ {.id = ALC269_FIXUP_HP_DOCK_GPIO_MIC1_LED, .name = "hp-dock-gpio-mic1-led"},
{.id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "dell-headset-multi"},
{.id = ALC269_FIXUP_DELL2_MIC_NO_PRESENCE, .name = "dell-headset-dock"},
{.id = ALC283_FIXUP_CHROME_BOOK, .name = "alc283-dac-wcaps"},
@@ -6090,6 +6112,8 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
ALC295_STANDARD_PINS,
{0x17, 0x21014040},
{0x18, 0x21a19050}),
+ SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+ ALC295_STANDARD_PINS),
SND_HDA_PIN_QUIRK(0x10ec0298, 0x1028, "Dell", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE,
ALC298_STANDARD_PINS,
{0x17, 0x90170110}),
diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index ec1067a..08b1399 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -89,7 +89,7 @@ static void acp_reg_write(u32 val, void __iomem *acp_mmio, u32 reg)
writel(val, acp_mmio + (reg * 4));
}
-/* Configure a given dma channel parameters - enable/disble,
+/* Configure a given dma channel parameters - enable/disable,
* number of descriptors, priority
*/
static void config_acp_dma_channel(void __iomem *acp_mmio, u8 ch_num,
diff --git a/sound/soc/atmel/atmel-classd.c b/sound/soc/atmel/atmel-classd.c
index 89ac5f5..7ae46c2 100644
--- a/sound/soc/atmel/atmel-classd.c
+++ b/sound/soc/atmel/atmel-classd.c
@@ -349,7 +349,7 @@ static int atmel_classd_codec_dai_digital_mute(struct snd_soc_dai *codec_dai,
}
#define CLASSD_ACLK_RATE_11M2896_MPY_8 (112896 * 100 * 8)
-#define CLASSD_ACLK_RATE_12M288_MPY_8 (12228 * 1000 * 8)
+#define CLASSD_ACLK_RATE_12M288_MPY_8 (12288 * 1000 * 8)
static struct {
int rate;
diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index 78fca8a..fd272a4 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -1534,21 +1534,20 @@ static void hdac_hdmi_eld_notify_cb(void *aptr, int port, int pipe)
pin->mst_capable = false;
/* if not MST, default is port[0] */
hport = &pin->ports[0];
- goto out;
} else {
for (i = 0; i < pin->num_ports; i++) {
pin->mst_capable = true;
if (pin->ports[i].id == pipe) {
hport = &pin->ports[i];
- goto out;
+ break;
}
}
}
+
+ if (hport)
+ hdac_hdmi_present_sense(pin, hport);
}
-out:
- if (pin && hport)
- hdac_hdmi_present_sense(pin, hport);
}
static struct i915_audio_component_audio_ops aops = {
@@ -1998,7 +1997,7 @@ static int hdac_hdmi_dev_remove(struct hdac_ext_device *edev)
struct hdac_hdmi_pin *pin, *pin_next;
struct hdac_hdmi_cvt *cvt, *cvt_next;
struct hdac_hdmi_pcm *pcm, *pcm_next;
- struct hdac_hdmi_port *port;
+ struct hdac_hdmi_port *port, *port_next;
int i;
snd_soc_unregister_codec(&edev->hdac.dev);
@@ -2008,8 +2007,9 @@ static int hdac_hdmi_dev_remove(struct hdac_ext_device *edev)
if (list_empty(&pcm->port_list))
continue;
- list_for_each_entry(port, &pcm->port_list, head)
- port = NULL;
+ list_for_each_entry_safe(port, port_next,
+ &pcm->port_list, head)
+ list_del(&port->head);
list_del(&pcm->head);
kfree(pcm);
diff --git a/sound/soc/codecs/rt5665.c b/sound/soc/codecs/rt5665.c
index 324461e..476135e 100644
--- a/sound/soc/codecs/rt5665.c
+++ b/sound/soc/codecs/rt5665.c
@@ -1241,7 +1241,7 @@ static irqreturn_t rt5665_irq(int irq, void *data)
static void rt5665_jd_check_handler(struct work_struct *work)
{
struct rt5665_priv *rt5665 = container_of(work, struct rt5665_priv,
- calibrate_work.work);
+ jd_check_work.work);
if (snd_soc_read(rt5665->codec, RT5665_AJD1_CTRL) & 0x0010) {
/* jack out */
@@ -2252,7 +2252,7 @@ static const char * const rt5665_if2_1_adc_in_src[] = {
static const SOC_ENUM_SINGLE_DECL(
rt5665_if2_1_adc_in_enum, RT5665_DIG_INF2_DATA,
- RT5665_IF3_ADC_IN_SFT, rt5665_if2_1_adc_in_src);
+ RT5665_IF2_1_ADC_IN_SFT, rt5665_if2_1_adc_in_src);
static const struct snd_kcontrol_new rt5665_if2_1_adc_in_mux =
SOC_DAPM_ENUM("IF2_1 ADC IN Source", rt5665_if2_1_adc_in_enum);
@@ -3178,6 +3178,9 @@ static const struct snd_soc_dapm_route rt5665_dapm_routes[] = {
{"DAC Mono Right Filter", NULL, "DAC Mono R ASRC", is_using_asrc},
{"DAC Stereo1 Filter", NULL, "DAC STO1 ASRC", is_using_asrc},
{"DAC Stereo2 Filter", NULL, "DAC STO2 ASRC", is_using_asrc},
+ {"I2S1 ASRC", NULL, "CLKDET"},
+ {"I2S2 ASRC", NULL, "CLKDET"},
+ {"I2S3 ASRC", NULL, "CLKDET"},
/*Vref*/
{"Mic Det Power", NULL, "Vref2"},
@@ -3912,6 +3915,7 @@ static const struct snd_soc_dapm_route rt5665_dapm_routes[] = {
{"Mono MIX", "MONOVOL Switch", "MONOVOL"},
{"Mono Amp", NULL, "Mono MIX"},
{"Mono Amp", NULL, "Vref2"},
+ {"Mono Amp", NULL, "Vref3"},
{"Mono Amp", NULL, "CLKDET SYS"},
{"Mono Amp", NULL, "CLKDET MONO"},
{"Mono Playback", "Switch", "Mono Amp"},
@@ -4798,7 +4802,7 @@ static int rt5665_i2c_probe(struct i2c_client *i2c,
/* Enhance performance*/
regmap_update_bits(rt5665->regmap, RT5665_PWR_ANLG_1,
RT5665_HP_DRIVER_MASK | RT5665_LDO1_DVO_MASK,
- RT5665_HP_DRIVER_5X | RT5665_LDO1_DVO_09);
+ RT5665_HP_DRIVER_5X | RT5665_LDO1_DVO_12);
INIT_DELAYED_WORK(&rt5665->jack_detect_work,
rt5665_jack_detect_handler);
diff --git a/sound/soc/codecs/rt5665.h b/sound/soc/codecs/rt5665.h
index 12f7080..a30f5e6 100644
--- a/sound/soc/codecs/rt5665.h
+++ b/sound/soc/codecs/rt5665.h
@@ -1106,7 +1106,7 @@
#define RT5665_HP_DRIVER_MASK (0x3 << 2)
#define RT5665_HP_DRIVER_1X (0x0 << 2)
#define RT5665_HP_DRIVER_3X (0x1 << 2)
-#define RT5665_HP_DRIVER_5X (0x2 << 2)
+#define RT5665_HP_DRIVER_5X (0x3 << 2)
#define RT5665_LDO1_DVO_MASK (0x3)
#define RT5665_LDO1_DVO_09 (0x0)
#define RT5665_LDO1_DVO_10 (0x1)
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index d151224..bbdb72f 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -899,7 +899,10 @@ static int wm_coeff_put(struct snd_kcontrol *kctl,
mutex_lock(&ctl->dsp->pwr_lock);
- memcpy(ctl->cache, p, ctl->len);
+ if (ctl->flags & WMFW_CTL_FLAG_VOLATILE)
+ ret = -EPERM;
+ else
+ memcpy(ctl->cache, p, ctl->len);
ctl->set = 1;
if (ctl->enabled && ctl->dsp->running)
@@ -926,6 +929,8 @@ static int wm_coeff_tlv_put(struct snd_kcontrol *kctl,
ctl->set = 1;
if (ctl->enabled && ctl->dsp->running)
ret = wm_coeff_write_control(ctl, ctl->cache, size);
+ else if (ctl->flags & WMFW_CTL_FLAG_VOLATILE)
+ ret = -EPERM;
}
mutex_unlock(&ctl->dsp->pwr_lock);
@@ -947,7 +952,7 @@ static int wm_coeff_put_acked(struct snd_kcontrol *kctl,
mutex_lock(&ctl->dsp->pwr_lock);
- if (ctl->enabled)
+ if (ctl->enabled && ctl->dsp->running)
ret = wm_coeff_write_acked_control(ctl, val);
else
ret = -EPERM;
diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c
index 4924575..343b291 100644
--- a/sound/soc/generic/simple-card-utils.c
+++ b/sound/soc/generic/simple-card-utils.c
@@ -115,6 +115,7 @@ int asoc_simple_card_parse_clk(struct device *dev,
clk = devm_get_clk_from_child(dev, node, NULL);
if (!IS_ERR(clk)) {
simple_dai->sysclk = clk_get_rate(clk);
+ simple_dai->clk = clk;
} else if (!of_property_read_u32(node, "system-clock-frequency", &val)) {
simple_dai->sysclk = val;
} else {
diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c
index ed58b5b..2dbfb1b 100644
--- a/sound/soc/intel/skylake/skl-topology.c
+++ b/sound/soc/intel/skylake/skl-topology.c
@@ -512,7 +512,7 @@ static int skl_tplg_set_module_init_data(struct snd_soc_dapm_widget *w)
if (bc->set_params != SKL_PARAM_INIT)
continue;
- mconfig->formats_config.caps = (u32 *)&bc->params;
+ mconfig->formats_config.caps = (u32 *)bc->params;
mconfig->formats_config.caps_size = bc->size;
break;
diff --git a/sound/soc/mediatek/Kconfig b/sound/soc/mediatek/Kconfig
index 05cf809..d7013bd 100644
--- a/sound/soc/mediatek/Kconfig
+++ b/sound/soc/mediatek/Kconfig
@@ -13,7 +13,7 @@
config SND_SOC_MT2701_CS42448
tristate "ASoc Audio driver for MT2701 with CS42448 codec"
- depends on SND_SOC_MT2701
+ depends on SND_SOC_MT2701 && I2C
select SND_SOC_CS42XX8_I2C
select SND_SOC_BT_SCO
help
diff --git a/sound/soc/sh/rcar/cmd.c b/sound/soc/sh/rcar/cmd.c
index abb5eaa..7d92a24 100644
--- a/sound/soc/sh/rcar/cmd.c
+++ b/sound/soc/sh/rcar/cmd.c
@@ -31,23 +31,24 @@ static int rsnd_cmd_init(struct rsnd_mod *mod,
struct rsnd_mod *mix = rsnd_io_to_mod_mix(io);
struct device *dev = rsnd_priv_to_dev(priv);
u32 data;
+ u32 path[] = {
+ [1] = 1 << 0,
+ [5] = 1 << 8,
+ [6] = 1 << 12,
+ [9] = 1 << 15,
+ };
if (!mix && !dvc)
return 0;
+ if (ARRAY_SIZE(path) < rsnd_mod_id(mod) + 1)
+ return -ENXIO;
+
if (mix) {
struct rsnd_dai *rdai;
struct rsnd_mod *src;
struct rsnd_dai_stream *tio;
int i;
- u32 path[] = {
- [0] = 0,
- [1] = 1 << 0,
- [2] = 0,
- [3] = 0,
- [4] = 0,
- [5] = 1 << 8
- };
/*
* it is assuming that integrater is well understanding about
@@ -70,16 +71,19 @@ static int rsnd_cmd_init(struct rsnd_mod *mod,
} else {
struct rsnd_mod *src = rsnd_io_to_mod_src(io);
- u32 path[] = {
- [0] = 0x30000,
- [1] = 0x30001,
- [2] = 0x40000,
- [3] = 0x10000,
- [4] = 0x20000,
- [5] = 0x40100
+ u8 cmd_case[] = {
+ [0] = 0x3,
+ [1] = 0x3,
+ [2] = 0x4,
+ [3] = 0x1,
+ [4] = 0x2,
+ [5] = 0x4,
+ [6] = 0x1,
+ [9] = 0x2,
};
- data = path[rsnd_mod_id(src)];
+ data = path[rsnd_mod_id(src)] |
+ cmd_case[rsnd_mod_id(src)] << 16;
}
dev_dbg(dev, "ctu/mix path = 0x%08x", data);
diff --git a/sound/soc/sh/rcar/dma.c b/sound/soc/sh/rcar/dma.c
index 1f405c8..241cb3b 100644
--- a/sound/soc/sh/rcar/dma.c
+++ b/sound/soc/sh/rcar/dma.c
@@ -454,6 +454,20 @@ static u32 rsnd_dmapp_read(struct rsnd_dma *dma, u32 reg)
return ioread32(rsnd_dmapp_addr(dmac, dma, reg));
}
+static void rsnd_dmapp_bset(struct rsnd_dma *dma, u32 data, u32 mask, u32 reg)
+{
+ struct rsnd_mod *mod = rsnd_mod_get(dma);
+ struct rsnd_priv *priv = rsnd_mod_to_priv(mod);
+ struct rsnd_dma_ctrl *dmac = rsnd_priv_to_dmac(priv);
+ void __iomem *addr = rsnd_dmapp_addr(dmac, dma, reg);
+ u32 val = ioread32(addr);
+
+ val &= ~mask;
+ val |= (data & mask);
+
+ iowrite32(val, addr);
+}
+
static int rsnd_dmapp_stop(struct rsnd_mod *mod,
struct rsnd_dai_stream *io,
struct rsnd_priv *priv)
@@ -461,10 +475,10 @@ static int rsnd_dmapp_stop(struct rsnd_mod *mod,
struct rsnd_dma *dma = rsnd_mod_to_dma(mod);
int i;
- rsnd_dmapp_write(dma, 0, PDMACHCR);
+ rsnd_dmapp_bset(dma, 0, PDMACHCR_DE, PDMACHCR);
for (i = 0; i < 1024; i++) {
- if (0 == rsnd_dmapp_read(dma, PDMACHCR))
+ if (0 == (rsnd_dmapp_read(dma, PDMACHCR) & PDMACHCR_DE))
return 0;
udelay(1);
}
diff --git a/sound/soc/sh/rcar/ssiu.c b/sound/soc/sh/rcar/ssiu.c
index 4e817c8..14fafda 100644
--- a/sound/soc/sh/rcar/ssiu.c
+++ b/sound/soc/sh/rcar/ssiu.c
@@ -64,7 +64,11 @@ static int rsnd_ssiu_init(struct rsnd_mod *mod,
mask1 = (1 << 4) | (1 << 20); /* mask sync bit */
mask2 = (1 << 4); /* mask sync bit */
val1 = val2 = 0;
- if (rsnd_ssi_is_pin_sharing(io)) {
+ if (id == 8) {
+ /*
+ * SSI8 pin is sharing with SSI7, nothing to do.
+ */
+ } else if (rsnd_ssi_is_pin_sharing(io)) {
int shift = -1;
switch (id) {
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 6dca408..2722bb0 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -3326,7 +3326,10 @@ static int snd_soc_platform_drv_pcm_new(struct snd_soc_pcm_runtime *rtd)
{
struct snd_soc_platform *platform = rtd->platform;
- return platform->driver->pcm_new(rtd);
+ if (platform->driver->pcm_new)
+ return platform->driver->pcm_new(rtd);
+ else
+ return 0;
}
static void snd_soc_platform_drv_pcm_free(struct snd_pcm *pcm)
@@ -3334,7 +3337,8 @@ static void snd_soc_platform_drv_pcm_free(struct snd_pcm *pcm)
struct snd_soc_pcm_runtime *rtd = pcm->private_data;
struct snd_soc_platform *platform = rtd->platform;
- platform->driver->pcm_free(pcm);
+ if (platform->driver->pcm_free)
+ platform->driver->pcm_free(pcm);
}
/**
diff --git a/sound/soc/sti/uniperif_reader.c b/sound/soc/sti/uniperif_reader.c
index 5992c6a..93a8df6 100644
--- a/sound/soc/sti/uniperif_reader.c
+++ b/sound/soc/sti/uniperif_reader.c
@@ -349,6 +349,8 @@ static int uni_reader_startup(struct snd_pcm_substream *substream,
struct uniperif *reader = priv->dai_data.uni;
int ret;
+ reader->substream = substream;
+
if (!UNIPERIF_TYPE_IS_TDM(reader))
return 0;
@@ -378,6 +380,7 @@ static void uni_reader_shutdown(struct snd_pcm_substream *substream,
/* Stop the reader */
uni_reader_stop(reader);
}
+ reader->substream = NULL;
}
static const struct snd_soc_dai_ops uni_reader_dai_ops = {
diff --git a/sound/soc/sunxi/sun8i-codec.c b/sound/soc/sunxi/sun8i-codec.c
index b92bdc8..7527ba2 100644
--- a/sound/soc/sunxi/sun8i-codec.c
+++ b/sound/soc/sunxi/sun8i-codec.c
@@ -259,25 +259,20 @@ static int sun8i_codec_hw_params(struct snd_pcm_substream *substream,
return 0;
}
-static const struct snd_kcontrol_new sun8i_output_left_mixer_controls[] = {
- SOC_DAPM_SINGLE("LSlot 0", SUN8I_DAC_MXR_SRC,
- SUN8I_DAC_MXR_SRC_DACL_MXR_SRC_AIF1DA0L, 1, 0),
- SOC_DAPM_SINGLE("LSlot 1", SUN8I_DAC_MXR_SRC,
- SUN8I_DAC_MXR_SRC_DACL_MXR_SRC_AIF1DA1L, 1, 0),
- SOC_DAPM_SINGLE("DACL", SUN8I_DAC_MXR_SRC,
- SUN8I_DAC_MXR_SRC_DACL_MXR_SRC_AIF2DACL, 1, 0),
- SOC_DAPM_SINGLE("ADCL", SUN8I_DAC_MXR_SRC,
- SUN8I_DAC_MXR_SRC_DACL_MXR_SRC_ADCL, 1, 0),
-};
-
-static const struct snd_kcontrol_new sun8i_output_right_mixer_controls[] = {
- SOC_DAPM_SINGLE("RSlot 0", SUN8I_DAC_MXR_SRC,
+static const struct snd_kcontrol_new sun8i_dac_mixer_controls[] = {
+ SOC_DAPM_DOUBLE("AIF1 Slot 0 Digital DAC Playback Switch",
+ SUN8I_DAC_MXR_SRC,
+ SUN8I_DAC_MXR_SRC_DACL_MXR_SRC_AIF1DA0L,
SUN8I_DAC_MXR_SRC_DACR_MXR_SRC_AIF1DA0R, 1, 0),
- SOC_DAPM_SINGLE("RSlot 1", SUN8I_DAC_MXR_SRC,
+ SOC_DAPM_DOUBLE("AIF1 Slot 1 Digital DAC Playback Switch",
+ SUN8I_DAC_MXR_SRC,
+ SUN8I_DAC_MXR_SRC_DACL_MXR_SRC_AIF1DA1L,
SUN8I_DAC_MXR_SRC_DACR_MXR_SRC_AIF1DA1R, 1, 0),
- SOC_DAPM_SINGLE("DACR", SUN8I_DAC_MXR_SRC,
+ SOC_DAPM_DOUBLE("AIF2 Digital DAC Playback Switch", SUN8I_DAC_MXR_SRC,
+ SUN8I_DAC_MXR_SRC_DACL_MXR_SRC_AIF2DACL,
SUN8I_DAC_MXR_SRC_DACR_MXR_SRC_AIF2DACR, 1, 0),
- SOC_DAPM_SINGLE("ADCR", SUN8I_DAC_MXR_SRC,
+ SOC_DAPM_DOUBLE("ADC Digital DAC Playback Switch", SUN8I_DAC_MXR_SRC,
+ SUN8I_DAC_MXR_SRC_DACL_MXR_SRC_ADCL,
SUN8I_DAC_MXR_SRC_DACR_MXR_SRC_ADCR, 1, 0),
};
@@ -286,19 +281,21 @@ static const struct snd_soc_dapm_widget sun8i_codec_dapm_widgets[] = {
SND_SOC_DAPM_SUPPLY("DAC", SUN8I_DAC_DIG_CTRL, SUN8I_DAC_DIG_CTRL_ENDA,
0, NULL, 0),
- /* Analog DAC */
- SND_SOC_DAPM_DAC("Digital Left DAC", "Playback", SUN8I_AIF1_DACDAT_CTRL,
- SUN8I_AIF1_DACDAT_CTRL_AIF1_DA0L_ENA, 0),
- SND_SOC_DAPM_DAC("Digital Right DAC", "Playback", SUN8I_AIF1_DACDAT_CTRL,
- SUN8I_AIF1_DACDAT_CTRL_AIF1_DA0R_ENA, 0),
+ /* Analog DAC AIF */
+ SND_SOC_DAPM_AIF_IN("AIF1 Slot 0 Left", "Playback", 0,
+ SUN8I_AIF1_DACDAT_CTRL,
+ SUN8I_AIF1_DACDAT_CTRL_AIF1_DA0L_ENA, 0),
+ SND_SOC_DAPM_AIF_IN("AIF1 Slot 0 Right", "Playback", 0,
+ SUN8I_AIF1_DACDAT_CTRL,
+ SUN8I_AIF1_DACDAT_CTRL_AIF1_DA0R_ENA, 0),
/* DAC Mixers */
- SND_SOC_DAPM_MIXER("Left DAC Mixer", SND_SOC_NOPM, 0, 0,
- sun8i_output_left_mixer_controls,
- ARRAY_SIZE(sun8i_output_left_mixer_controls)),
- SND_SOC_DAPM_MIXER("Right DAC Mixer", SND_SOC_NOPM, 0, 0,
- sun8i_output_right_mixer_controls,
- ARRAY_SIZE(sun8i_output_right_mixer_controls)),
+ SND_SOC_DAPM_MIXER("Left Digital DAC Mixer", SND_SOC_NOPM, 0, 0,
+ sun8i_dac_mixer_controls,
+ ARRAY_SIZE(sun8i_dac_mixer_controls)),
+ SND_SOC_DAPM_MIXER("Right Digital DAC Mixer", SND_SOC_NOPM, 0, 0,
+ sun8i_dac_mixer_controls,
+ ARRAY_SIZE(sun8i_dac_mixer_controls)),
/* Clocks */
SND_SOC_DAPM_SUPPLY("MODCLK AFI1", SUN8I_MOD_CLK_ENA,
@@ -321,8 +318,6 @@ static const struct snd_soc_dapm_widget sun8i_codec_dapm_widgets[] = {
SUN8I_MOD_RST_CTL_AIF1, 0, NULL, 0),
SND_SOC_DAPM_SUPPLY("RST DAC", SUN8I_MOD_RST_CTL,
SUN8I_MOD_RST_CTL_DAC, 0, NULL, 0),
-
- SND_SOC_DAPM_OUTPUT("HP"),
};
static const struct snd_soc_dapm_route sun8i_codec_dapm_routes[] = {
@@ -338,16 +333,14 @@ static const struct snd_soc_dapm_route sun8i_codec_dapm_routes[] = {
{ "DAC", NULL, "MODCLK DAC" },
/* DAC Routes */
- { "Digital Left DAC", NULL, "DAC" },
- { "Digital Right DAC", NULL, "DAC" },
+ { "AIF1 Slot 0 Right", NULL, "DAC" },
+ { "AIF1 Slot 0 Left", NULL, "DAC" },
/* DAC Mixer Routes */
- { "Left DAC Mixer", "LSlot 0", "Digital Left DAC"},
- { "Right DAC Mixer", "RSlot 0", "Digital Right DAC"},
-
- /* End of route : HP out */
- { "HP", NULL, "Left DAC Mixer" },
- { "HP", NULL, "Right DAC Mixer" },
+ { "Left Digital DAC Mixer", "AIF1 Slot 0 Digital DAC Playback Switch",
+ "AIF1 Slot 0 Left"},
+ { "Right Digital DAC Mixer", "AIF1 Slot 0 Digital DAC Playback Switch",
+ "AIF1 Slot 0 Right"},
};
static struct snd_soc_dai_ops sun8i_codec_dai_ops = {
diff --git a/sound/x86/Kconfig b/sound/x86/Kconfig
index 84c8f8fc..8adf4d1 100644
--- a/sound/x86/Kconfig
+++ b/sound/x86/Kconfig
@@ -1,6 +1,7 @@
menuconfig SND_X86
- tristate "X86 sound devices"
+ bool "X86 sound devices"
depends on X86
+ default y
---help---
X86 sound devices that don't fall under SoC or PCI categories
diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h
index 122153b..390d7c9 100644
--- a/tools/include/linux/filter.h
+++ b/tools/include/linux/filter.h
@@ -168,6 +168,16 @@
.off = OFF, \
.imm = 0 })
+/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */
+
+#define BPF_STX_XADD(SIZE, DST, SRC, OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = OFF, \
+ .imm = 0 })
+
/* Memory store, *(uint *) (dst_reg + off16) = imm32 */
#define BPF_ST_MEM(SIZE, DST, OFF, IMM) \
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0539a0c..a1d9538 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -81,6 +81,7 @@ enum bpf_cmd {
BPF_OBJ_GET,
BPF_PROG_ATTACH,
BPF_PROG_DETACH,
+ BPF_PROG_TEST_RUN,
};
enum bpf_map_type {
@@ -96,6 +97,8 @@ enum bpf_map_type {
BPF_MAP_TYPE_LRU_HASH,
BPF_MAP_TYPE_LRU_PERCPU_HASH,
BPF_MAP_TYPE_LPM_TRIE,
+ BPF_MAP_TYPE_ARRAY_OF_MAPS,
+ BPF_MAP_TYPE_HASH_OF_MAPS,
};
enum bpf_prog_type {
@@ -152,6 +155,7 @@ union bpf_attr {
__u32 value_size; /* size of value in bytes */
__u32 max_entries; /* max number of entries in a map */
__u32 map_flags; /* prealloc or not */
+ __u32 inner_map_fd; /* fd pointing to the inner map */
};
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -186,6 +190,17 @@ union bpf_attr {
__u32 attach_type;
__u32 attach_flags;
};
+
+ struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
+ __u32 prog_fd;
+ __u32 retval;
+ __u32 data_size_in;
+ __u32 data_size_out;
+ __aligned_u64 data_in;
+ __aligned_u64 data_out;
+ __u32 repeat;
+ __u32 duration;
+ } test;
} __attribute__((aligned(8)));
/* BPF helper function descriptions:
@@ -456,6 +471,18 @@ union bpf_attr {
* Return:
* > 0 length of the string including the trailing NUL on success
* < 0 error
+ *
+ * u64 bpf_bpf_get_socket_cookie(skb)
+ * Get the cookie for the socket stored inside sk_buff.
+ * @skb: pointer to skb
+ * Return: 8 Bytes non-decreasing number on success or 0 if the socket
+ * field is missing inside sk_buff
+ *
+ * u32 bpf_get_socket_uid(skb)
+ * Get the owner uid of the socket stored inside sk_buff.
+ * @skb: pointer to skb
+ * Return: uid of the socket owner on success or 0 if the socket pointer
+ * inside sk_buff is NULL
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -503,7 +530,9 @@ union bpf_attr {
FN(get_numa_node_id), \
FN(skb_change_head), \
FN(xdp_adjust_head), \
- FN(probe_read_str),
+ FN(probe_read_str), \
+ FN(get_socket_cookie), \
+ FN(get_socket_uid),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
diff --git a/tools/include/uapi/linux/bpf_perf_event.h b/tools/include/uapi/linux/bpf_perf_event.h
new file mode 100644
index 0000000..0674272
--- /dev/null
+++ b/tools/include/uapi/linux/bpf_perf_event.h
@@ -0,0 +1,18 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef _UAPI__LINUX_BPF_PERF_EVENT_H__
+#define _UAPI__LINUX_BPF_PERF_EVENT_H__
+
+#include <linux/types.h>
+#include <linux/ptrace.h>
+
+struct bpf_perf_event_data {
+ struct pt_regs regs;
+ __u64 sample_period;
+};
+
+#endif /* _UAPI__LINUX_BPF_PERF_EVENT_H__ */
diff --git a/tools/lguest/lguest.c b/tools/lguest/lguest.c
index 11c8d9b..5d19fdf 100644
--- a/tools/lguest/lguest.c
+++ b/tools/lguest/lguest.c
@@ -1387,7 +1387,7 @@ static bool pci_data_iowrite(u16 port, u32 mask, u32 val)
/* Allow writing to any other BAR, or expansion ROM */
iowrite(portoff, val, mask, &d->config_words[reg]);
return true;
- /* We let them overide latency timer and cacheline size */
+ /* We let them override latency timer and cacheline size */
} else if (&d->config_words[reg] == (void *)&d->config.cacheline_size) {
/* Only let them change the first two fields. */
if (mask == 0xFFFFFFFF)
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index e2efddf..1f5300e 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -132,7 +132,7 @@
Q = @
endif
-# Disable command line variables (CFLAGS) overide from top
+# Disable command line variables (CFLAGS) override from top
# level Makefile (perf), otherwise build Makefile will get
# the same command line setup.
MAKEOVERRIDES=
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 207c2ee..f84c398 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -69,6 +69,23 @@ int bpf_create_map(enum bpf_map_type map_type, int key_size,
return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
}
+int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size,
+ int inner_map_fd, int max_entries, __u32 map_flags)
+{
+ union bpf_attr attr;
+
+ memset(&attr, '\0', sizeof(attr));
+
+ attr.map_type = map_type;
+ attr.key_size = key_size;
+ attr.value_size = 4;
+ attr.inner_map_fd = inner_map_fd;
+ attr.max_entries = max_entries;
+ attr.map_flags = map_flags;
+
+ return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+}
+
int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
size_t insns_cnt, const char *license,
__u32 kern_version, char *log_buf, size_t log_buf_sz)
@@ -192,3 +209,27 @@ int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
}
+
+int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
+ void *data_out, __u32 *size_out, __u32 *retval,
+ __u32 *duration)
+{
+ union bpf_attr attr;
+ int ret;
+
+ bzero(&attr, sizeof(attr));
+ attr.test.prog_fd = prog_fd;
+ attr.test.data_in = ptr_to_u64(data);
+ attr.test.data_out = ptr_to_u64(data_out);
+ attr.test.data_size_in = size;
+ attr.test.repeat = repeat;
+
+ ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr));
+ if (size_out)
+ *size_out = attr.test.data_size_out;
+ if (retval)
+ *retval = attr.test.retval;
+ if (duration)
+ *duration = attr.test.duration;
+ return ret;
+}
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 09c3dca..edb4dae 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -26,6 +26,8 @@
int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
int max_entries, __u32 map_flags);
+int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size,
+ int inner_map_fd, int max_entries, __u32 map_flags);
/* Recommend log buffer size */
#define BPF_LOG_BUF_SIZE 65536
@@ -45,6 +47,8 @@ int bpf_obj_get(const char *pathname);
int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type,
unsigned int flags);
int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
-
+int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
+ void *data_out, __u32 *size_out, __u32 *retval,
+ __u32 *duration);
#endif
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index ac6eb86..1a2c07e 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1618,8 +1618,7 @@ int bpf_program__nth_fd(struct bpf_program *prog, int n)
return fd;
}
-static void bpf_program__set_type(struct bpf_program *prog,
- enum bpf_prog_type type)
+void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type)
{
prog->type = type;
}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index b30394f..32c7252 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -25,6 +25,7 @@
#include <stdint.h>
#include <stdbool.h>
#include <sys/types.h> // for size_t
+#include <linux/bpf.h>
enum libbpf_errno {
__LIBBPF_ERRNO__START = 4000,
@@ -185,6 +186,7 @@ int bpf_program__set_sched_cls(struct bpf_program *prog);
int bpf_program__set_sched_act(struct bpf_program *prog);
int bpf_program__set_xdp(struct bpf_program *prog);
int bpf_program__set_perf_event(struct bpf_program *prog);
+void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type);
bool bpf_program__is_socket_filter(struct bpf_program *prog);
bool bpf_program__is_tracepoint(struct bpf_program *prog);
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 47076b1..9b8555e 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -135,7 +135,7 @@
Q = @
endif
-# Disable command line variables (CFLAGS) overide from top
+# Disable command line variables (CFLAGS) override from top
# level Makefile (perf), otherwise build Makefile will get
# the same command line setup.
MAKEOVERRIDES=
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 6634280..0c03538 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -140,7 +140,7 @@ struct pevent_plugin_option {
* struct pevent_plugin_option PEVENT_PLUGIN_OPTIONS[] = {
* {
* .name = "option-name",
- * .plugin_alias = "overide-file-name", (optional)
+ * .plugin_alias = "override-file-name", (optional)
* .description = "description of option to show users",
* },
* {
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index 4cfdbb5..066086d 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -805,11 +805,20 @@ static struct rela *find_switch_table(struct objtool_file *file,
insn->jump_dest->offset > orig_insn->offset))
break;
+ /* look for a relocation which references .rodata */
text_rela = find_rela_by_dest_range(insn->sec, insn->offset,
insn->len);
- if (text_rela && text_rela->sym == file->rodata->sym)
- return find_rela_by_dest(file->rodata,
- text_rela->addend);
+ if (!text_rela || text_rela->sym != file->rodata->sym)
+ continue;
+
+ /*
+ * Make sure the .rodata address isn't associated with a
+ * symbol. gcc jump tables are anonymous data.
+ */
+ if (find_symbol_containing(file->rodata, text_rela->addend))
+ continue;
+
+ return find_rela_by_dest(file->rodata, text_rela->addend);
}
return NULL;
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 0d7983a..d897702 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -85,6 +85,18 @@ struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset)
return NULL;
}
+struct symbol *find_symbol_containing(struct section *sec, unsigned long offset)
+{
+ struct symbol *sym;
+
+ list_for_each_entry(sym, &sec->symbol_list, list)
+ if (sym->type != STT_SECTION &&
+ offset >= sym->offset && offset < sym->offset + sym->len)
+ return sym;
+
+ return NULL;
+}
+
struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,
unsigned int len)
{
diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h
index aa1ff65..731973e 100644
--- a/tools/objtool/elf.h
+++ b/tools/objtool/elf.h
@@ -79,6 +79,7 @@ struct elf {
struct elf *elf_open(const char *name);
struct section *find_section_by_name(struct elf *elf, const char *name);
struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset);
+struct symbol *find_symbol_containing(struct section *sec, unsigned long offset);
struct rela *find_rela_by_dest(struct section *sec, unsigned long offset);
struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,
unsigned int len);
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
index 7913363..4f3c758 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
@@ -31,7 +31,7 @@
#error Instruction buffer size too small
#endif
-/* Based on branch_type() from perf_event_intel_lbr.c */
+/* Based on branch_type() from arch/x86/events/intel/lbr.c */
static void intel_pt_insn_decoder(struct insn *insn,
struct intel_pt_insn *intel_pt_insn)
{
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 70e389b..9b4d8ba 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -202,7 +202,7 @@ void symbols__fixup_end(struct rb_root *symbols)
/* Last entry */
if (curr->end == curr->start)
- curr->end = roundup(curr->start, 4096);
+ curr->end = roundup(curr->start, 4096) + 4096;
}
void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index 6e4eb2f..0c8b61f 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -1880,6 +1880,7 @@
sub wait_for_input
{
my ($fp, $time) = @_;
+ my $start_time;
my $rin;
my $rout;
my $nr;
@@ -1895,17 +1896,22 @@
vec($rin, fileno($fp), 1) = 1;
vec($rin, fileno(\*STDIN), 1) = 1;
+ $start_time = time;
+
while (1) {
$nr = select($rout=$rin, undef, undef, $time);
- if ($nr <= 0) {
- return undef;
- }
+ last if ($nr <= 0);
# copy data from stdin to the console
if (vec($rout, fileno(\*STDIN), 1) == 1) {
- sysread(\*STDIN, $buf, 1000);
- syswrite($fp, $buf, 1000);
+ $nr = sysread(\*STDIN, $buf, 1000);
+ syswrite($fp, $buf, $nr) if ($nr > 0);
+ }
+
+ # The timeout is based on time waiting for the fp data
+ if (vec($rout, fileno($fp), 1) != 1) {
+ last if (defined($time) && (time - $start_time > $time));
next;
}
@@ -1917,12 +1923,11 @@
last if ($ch eq "\n");
}
- if (!length($line)) {
- return undef;
- }
+ last if (!length($line));
return $line;
}
+ return undef;
}
sub reboot_to {
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index f11315b..6a9480c 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -1,6 +1,7 @@
CFLAGS += -I. -I../../include -g -O2 -Wall -D_LGPL_SOURCE -fsanitize=address
-LDFLAGS += -lpthread -lurcu
+LDFLAGS += -fsanitize=address
+LDLIBS+= -lpthread -lurcu
TARGETS = main idr-test multiorder
CORE_OFILES := radix-tree.o idr.o linux.o test.o find_bit.o
OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \
@@ -10,23 +11,25 @@
SHIFT=3
endif
+ifeq ($(BUILD), 32)
+ CFLAGS += -m32
+ LDFLAGS += -m32
+endif
+
targets: mapshift $(TARGETS)
main: $(OFILES)
- $(CC) $(CFLAGS) $(LDFLAGS) $^ -o main
idr-test: idr-test.o $(CORE_OFILES)
- $(CC) $(CFLAGS) $(LDFLAGS) $^ -o idr-test
multiorder: multiorder.o $(CORE_OFILES)
- $(CC) $(CFLAGS) $(LDFLAGS) $^ -o multiorder
clean:
$(RM) $(TARGETS) *.o radix-tree.c idr.c generated/map-shift.h
vpath %.c ../../lib
-$(OFILES): *.h */*.h generated/map-shift.h \
+$(OFILES): Makefile *.h */*.h generated/map-shift.h \
../../include/linux/*.h \
../../include/asm/*.h \
../../../include/linux/radix-tree.h \
@@ -41,7 +44,7 @@
.PHONY: mapshift
mapshift:
- @if ! grep -qw $(SHIFT) generated/map-shift.h; then \
+ @if ! grep -qws $(SHIFT) generated/map-shift.h; then \
echo "#define RADIX_TREE_MAP_SHIFT $(SHIFT)" > \
generated/map-shift.h; \
fi
diff --git a/tools/testing/radix-tree/benchmark.c b/tools/testing/radix-tree/benchmark.c
index 9b09ddf..99c40f3 100644
--- a/tools/testing/radix-tree/benchmark.c
+++ b/tools/testing/radix-tree/benchmark.c
@@ -17,6 +17,9 @@
#include <time.h>
#include "test.h"
+#define for_each_index(i, base, order) \
+ for (i = base; i < base + (1 << order); i++)
+
#define NSEC_PER_SEC 1000000000L
static long long benchmark_iter(struct radix_tree_root *root, bool tagged)
@@ -57,27 +60,176 @@ static long long benchmark_iter(struct radix_tree_root *root, bool tagged)
return nsec;
}
+static void benchmark_insert(struct radix_tree_root *root,
+ unsigned long size, unsigned long step, int order)
+{
+ struct timespec start, finish;
+ unsigned long index;
+ long long nsec;
+
+ clock_gettime(CLOCK_MONOTONIC, &start);
+
+ for (index = 0 ; index < size ; index += step)
+ item_insert_order(root, index, order);
+
+ clock_gettime(CLOCK_MONOTONIC, &finish);
+
+ nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+ (finish.tv_nsec - start.tv_nsec);
+
+ printv(2, "Size: %8ld, step: %8ld, order: %d, insertion: %15lld ns\n",
+ size, step, order, nsec);
+}
+
+static void benchmark_tagging(struct radix_tree_root *root,
+ unsigned long size, unsigned long step, int order)
+{
+ struct timespec start, finish;
+ unsigned long index;
+ long long nsec;
+
+ clock_gettime(CLOCK_MONOTONIC, &start);
+
+ for (index = 0 ; index < size ; index += step)
+ radix_tree_tag_set(root, index, 0);
+
+ clock_gettime(CLOCK_MONOTONIC, &finish);
+
+ nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+ (finish.tv_nsec - start.tv_nsec);
+
+ printv(2, "Size: %8ld, step: %8ld, order: %d, tagging: %17lld ns\n",
+ size, step, order, nsec);
+}
+
+static void benchmark_delete(struct radix_tree_root *root,
+ unsigned long size, unsigned long step, int order)
+{
+ struct timespec start, finish;
+ unsigned long index, i;
+ long long nsec;
+
+ clock_gettime(CLOCK_MONOTONIC, &start);
+
+ for (index = 0 ; index < size ; index += step)
+ for_each_index(i, index, order)
+ item_delete(root, i);
+
+ clock_gettime(CLOCK_MONOTONIC, &finish);
+
+ nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+ (finish.tv_nsec - start.tv_nsec);
+
+ printv(2, "Size: %8ld, step: %8ld, order: %d, deletion: %16lld ns\n",
+ size, step, order, nsec);
+}
+
static void benchmark_size(unsigned long size, unsigned long step, int order)
{
RADIX_TREE(tree, GFP_KERNEL);
long long normal, tagged;
- unsigned long index;
- for (index = 0 ; index < size ; index += step) {
- item_insert_order(&tree, index, order);
- radix_tree_tag_set(&tree, index, 0);
- }
+ benchmark_insert(&tree, size, step, order);
+ benchmark_tagging(&tree, size, step, order);
tagged = benchmark_iter(&tree, true);
normal = benchmark_iter(&tree, false);
- printv(2, "Size %ld, step %6ld, order %d tagged %10lld ns, normal %10lld ns\n",
- size, step, order, tagged, normal);
+ printv(2, "Size: %8ld, step: %8ld, order: %d, tagged iteration: %8lld ns\n",
+ size, step, order, tagged);
+ printv(2, "Size: %8ld, step: %8ld, order: %d, normal iteration: %8lld ns\n",
+ size, step, order, normal);
+
+ benchmark_delete(&tree, size, step, order);
item_kill_tree(&tree);
rcu_barrier();
}
+static long long __benchmark_split(unsigned long index,
+ int old_order, int new_order)
+{
+ struct timespec start, finish;
+ long long nsec;
+ RADIX_TREE(tree, GFP_ATOMIC);
+
+ item_insert_order(&tree, index, old_order);
+
+ clock_gettime(CLOCK_MONOTONIC, &start);
+ radix_tree_split(&tree, index, new_order);
+ clock_gettime(CLOCK_MONOTONIC, &finish);
+ nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+ (finish.tv_nsec - start.tv_nsec);
+
+ item_kill_tree(&tree);
+
+ return nsec;
+
+}
+
+static void benchmark_split(unsigned long size, unsigned long step)
+{
+ int i, j, idx;
+ long long nsec = 0;
+
+
+ for (idx = 0; idx < size; idx += step) {
+ for (i = 3; i < 11; i++) {
+ for (j = 0; j < i; j++) {
+ nsec += __benchmark_split(idx, i, j);
+ }
+ }
+ }
+
+ printv(2, "Size %8ld, step %8ld, split time %10lld ns\n",
+ size, step, nsec);
+
+}
+
+static long long __benchmark_join(unsigned long index,
+ unsigned order1, unsigned order2)
+{
+ unsigned long loc;
+ struct timespec start, finish;
+ long long nsec;
+ void *item, *item2 = item_create(index + 1, order1);
+ RADIX_TREE(tree, GFP_KERNEL);
+
+ item_insert_order(&tree, index, order2);
+ item = radix_tree_lookup(&tree, index);
+
+ clock_gettime(CLOCK_MONOTONIC, &start);
+ radix_tree_join(&tree, index + 1, order1, item2);
+ clock_gettime(CLOCK_MONOTONIC, &finish);
+ nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+ (finish.tv_nsec - start.tv_nsec);
+
+ loc = find_item(&tree, item);
+ if (loc == -1)
+ free(item);
+
+ item_kill_tree(&tree);
+
+ return nsec;
+}
+
+static void benchmark_join(unsigned long step)
+{
+ int i, j, idx;
+ long long nsec = 0;
+
+ for (idx = 0; idx < 1 << 10; idx += step) {
+ for (i = 1; i < 15; i++) {
+ for (j = 0; j < i; j++) {
+ nsec += __benchmark_join(idx, i, j);
+ }
+ }
+ }
+
+ printv(2, "Size %8d, step %8ld, join time %10lld ns\n",
+ 1 << 10, step, nsec);
+}
+
void benchmark(void)
{
unsigned long size[] = {1 << 10, 1 << 20, 0};
@@ -95,4 +247,11 @@ void benchmark(void)
for (c = 0; size[c]; c++)
for (s = 0; step[s]; s++)
benchmark_size(size[c], step[s] << 9, 9);
+
+ for (c = 0; size[c]; c++)
+ for (s = 0; step[s]; s++)
+ benchmark_split(size[c], step[s]);
+
+ for (s = 0; step[s]; s++)
+ benchmark_join(step[s]);
}
diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index a26098c..30cd0b2 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -153,6 +153,30 @@ void idr_nowait_test(void)
idr_destroy(&idr);
}
+void idr_get_next_test(void)
+{
+ unsigned long i;
+ int nextid;
+ DEFINE_IDR(idr);
+
+ int indices[] = {4, 7, 9, 15, 65, 128, 1000, 99999, 0};
+
+ for(i = 0; indices[i]; i++) {
+ struct item *item = item_create(indices[i], 0);
+ assert(idr_alloc(&idr, item, indices[i], indices[i+1],
+ GFP_KERNEL) == indices[i]);
+ }
+
+ for(i = 0, nextid = 0; indices[i]; i++) {
+ idr_get_next(&idr, &nextid);
+ assert(nextid == indices[i]);
+ nextid++;
+ }
+
+ idr_for_each(&idr, item_idr_free, &idr);
+ idr_destroy(&idr);
+}
+
void idr_checks(void)
{
unsigned long i;
@@ -202,6 +226,7 @@ void idr_checks(void)
idr_alloc_test();
idr_null_test();
idr_nowait_test();
+ idr_get_next_test();
}
/*
@@ -338,7 +363,7 @@ void ida_check_random(void)
{
DEFINE_IDA(ida);
DECLARE_BITMAP(bitmap, 2048);
- int id;
+ int id, err;
unsigned int i;
time_t s = time(NULL);
@@ -352,8 +377,11 @@ void ida_check_random(void)
ida_remove(&ida, bit);
} else {
__set_bit(bit, bitmap);
- ida_pre_get(&ida, GFP_KERNEL);
- assert(!ida_get_new_above(&ida, bit, &id));
+ do {
+ ida_pre_get(&ida, GFP_KERNEL);
+ err = ida_get_new_above(&ida, bit, &id);
+ } while (err == -ENOMEM);
+ assert(!err);
assert(id == bit);
}
}
@@ -362,6 +390,24 @@ void ida_check_random(void)
goto repeat;
}
+void ida_simple_get_remove_test(void)
+{
+ DEFINE_IDA(ida);
+ unsigned long i;
+
+ for (i = 0; i < 10000; i++) {
+ assert(ida_simple_get(&ida, 0, 20000, GFP_KERNEL) == i);
+ }
+ assert(ida_simple_get(&ida, 5, 30, GFP_KERNEL) < 0);
+
+ for (i = 0; i < 10000; i++) {
+ ida_simple_remove(&ida, i);
+ }
+ assert(ida_is_empty(&ida));
+
+ ida_destroy(&ida);
+}
+
void ida_checks(void)
{
DEFINE_IDA(ida);
@@ -428,15 +474,41 @@ void ida_checks(void)
ida_check_max();
ida_check_conv();
ida_check_random();
+ ida_simple_get_remove_test();
radix_tree_cpu_dead(1);
}
+static void *ida_random_fn(void *arg)
+{
+ rcu_register_thread();
+ ida_check_random();
+ rcu_unregister_thread();
+ return NULL;
+}
+
+void ida_thread_tests(void)
+{
+ pthread_t threads[10];
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(threads); i++)
+ if (pthread_create(&threads[i], NULL, ida_random_fn, NULL)) {
+ perror("creating ida thread");
+ exit(1);
+ }
+
+ while (i--)
+ pthread_join(threads[i], NULL);
+}
+
int __weak main(void)
{
radix_tree_init();
idr_checks();
ida_checks();
+ ida_thread_tests();
+ radix_tree_cpu_dead(1);
rcu_barrier();
if (nr_allocated)
printf("nr_allocated = %d\n", nr_allocated);
diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c
index b829127..bc9a784 100644
--- a/tools/testing/radix-tree/main.c
+++ b/tools/testing/radix-tree/main.c
@@ -368,6 +368,7 @@ int main(int argc, char **argv)
iteration_test(0, 10 + 90 * long_run);
iteration_test(7, 10 + 90 * long_run);
single_thread_tests(long_run);
+ ida_thread_tests();
/* Free any remaining preallocated nodes */
radix_tree_cpu_dead(0);
diff --git a/tools/testing/radix-tree/tag_check.c b/tools/testing/radix-tree/tag_check.c
index d4ff009..36dcf7d 100644
--- a/tools/testing/radix-tree/tag_check.c
+++ b/tools/testing/radix-tree/tag_check.c
@@ -330,6 +330,34 @@ static void single_check(void)
item_kill_tree(&tree);
}
+void radix_tree_clear_tags_test(void)
+{
+ unsigned long index;
+ struct radix_tree_node *node;
+ struct radix_tree_iter iter;
+ void **slot;
+
+ RADIX_TREE(tree, GFP_KERNEL);
+
+ item_insert(&tree, 0);
+ item_tag_set(&tree, 0, 0);
+ __radix_tree_lookup(&tree, 0, &node, &slot);
+ radix_tree_clear_tags(&tree, node, slot);
+ assert(item_tag_get(&tree, 0, 0) == 0);
+
+ for (index = 0; index < 1000; index++) {
+ item_insert(&tree, index);
+ item_tag_set(&tree, index, 0);
+ }
+
+ radix_tree_for_each_slot(slot, &tree, &iter, 0) {
+ radix_tree_clear_tags(&tree, iter.node, slot);
+ assert(item_tag_get(&tree, iter.index, 0) == 0);
+ }
+
+ item_kill_tree(&tree);
+}
+
void tag_check(void)
{
single_check();
@@ -347,4 +375,5 @@ void tag_check(void)
thrash_tags();
rcu_barrier();
printv(2, "after thrash_tags: %d allocated\n", nr_allocated);
+ radix_tree_clear_tags_test();
}
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index b30e11d..0f8220c 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -36,6 +36,7 @@ void iteration_test(unsigned order, unsigned duration);
void benchmark(void);
void idr_checks(void);
void ida_checks(void);
+void ida_thread_tests(void);
struct item *
item_tag_set(struct radix_tree_root *root, unsigned long index, int tag);
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 4b49826..d8d94b9 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -1,20 +1,39 @@
LIBDIR := ../../../lib
-BPFOBJ := $(LIBDIR)/bpf/bpf.o
+BPFDIR := $(LIBDIR)/bpf
+APIDIR := ../../../include/uapi
+GENDIR := ../../../../include/generated
+GENHDR := $(GENDIR)/autoconf.h
-CFLAGS += -Wall -O2 -lcap -I../../../include/uapi -I$(LIBDIR)
+ifneq ($(wildcard $(GENHDR)),)
+ GENFLAGS := -DHAVE_GENHDR
+endif
-TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map
+CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include
+LDLIBS += -lcap -lelf
+
+TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs
+
+TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o
TEST_PROGS := test_kmod.sh
-.PHONY: all clean force
+include ../lib.mk
+
+BPFOBJ := $(OUTPUT)/libbpf.a
+
+$(TEST_GEN_PROGS): $(BPFOBJ)
+
+.PHONY: force
# force a rebuild of BPFOBJ when its dependencies are updated
force:
$(BPFOBJ): force
- $(MAKE) -C $(dir $(BPFOBJ))
+ $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/
-$(test_objs): $(BPFOBJ)
+CLANG ?= clang
-include ../lib.mk
+%.o: %.c
+ $(CLANG) -I../../../include/uapi -I../../../../samples/bpf/ \
+ -D__x86_64__ -Wno-compare-distinct-pointer-types \
+ -O2 -target bpf -c $< -o $@
diff --git a/tools/testing/selftests/bpf/test_iptunnel_common.h b/tools/testing/selftests/bpf/test_iptunnel_common.h
new file mode 100644
index 0000000..e4cd252
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_iptunnel_common.h
@@ -0,0 +1,37 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef _TEST_IPTNL_COMMON_H
+#define _TEST_IPTNL_COMMON_H
+
+#include <linux/types.h>
+
+#define MAX_IPTNL_ENTRIES 256U
+
+struct vip {
+ union {
+ __u32 v6[4];
+ __u32 v4;
+ } daddr;
+ __u16 dport;
+ __u16 family;
+ __u8 protocol;
+};
+
+struct iptnl_info {
+ union {
+ __u32 v6[4];
+ __u32 v4;
+ } saddr;
+ union {
+ __u32 v6[4];
+ __u32 v4;
+ } daddr;
+ __u16 family;
+ __u8 dmac[6];
+};
+
+#endif
diff --git a/tools/testing/selftests/bpf/test_l4lb.c b/tools/testing/selftests/bpf/test_l4lb.c
new file mode 100644
index 0000000..368bfe8
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_l4lb.c
@@ -0,0 +1,474 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <stddef.h>
+#include <stdbool.h>
+#include <string.h>
+#include <linux/pkt_cls.h>
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include "bpf_helpers.h"
+#include "test_iptunnel_common.h"
+
+#define htons __builtin_bswap16
+#define ntohs __builtin_bswap16
+int _version SEC("version") = 1;
+
+static inline __u32 rol32(__u32 word, unsigned int shift)
+{
+ return (word << shift) | (word >> ((-shift) & 31));
+}
+
+/* copy paste of jhash from kernel sources to make sure llvm
+ * can compile it into valid sequence of bpf instructions
+ */
+#define __jhash_mix(a, b, c) \
+{ \
+ a -= c; a ^= rol32(c, 4); c += b; \
+ b -= a; b ^= rol32(a, 6); a += c; \
+ c -= b; c ^= rol32(b, 8); b += a; \
+ a -= c; a ^= rol32(c, 16); c += b; \
+ b -= a; b ^= rol32(a, 19); a += c; \
+ c -= b; c ^= rol32(b, 4); b += a; \
+}
+
+#define __jhash_final(a, b, c) \
+{ \
+ c ^= b; c -= rol32(b, 14); \
+ a ^= c; a -= rol32(c, 11); \
+ b ^= a; b -= rol32(a, 25); \
+ c ^= b; c -= rol32(b, 16); \
+ a ^= c; a -= rol32(c, 4); \
+ b ^= a; b -= rol32(a, 14); \
+ c ^= b; c -= rol32(b, 24); \
+}
+
+#define JHASH_INITVAL 0xdeadbeef
+
+typedef unsigned int u32;
+
+static inline u32 jhash(const void *key, u32 length, u32 initval)
+{
+ u32 a, b, c;
+ const unsigned char *k = key;
+
+ a = b = c = JHASH_INITVAL + length + initval;
+
+ while (length > 12) {
+ a += *(u32 *)(k);
+ b += *(u32 *)(k + 4);
+ c += *(u32 *)(k + 8);
+ __jhash_mix(a, b, c);
+ length -= 12;
+ k += 12;
+ }
+ switch (length) {
+ case 12: c += (u32)k[11]<<24;
+ case 11: c += (u32)k[10]<<16;
+ case 10: c += (u32)k[9]<<8;
+ case 9: c += k[8];
+ case 8: b += (u32)k[7]<<24;
+ case 7: b += (u32)k[6]<<16;
+ case 6: b += (u32)k[5]<<8;
+ case 5: b += k[4];
+ case 4: a += (u32)k[3]<<24;
+ case 3: a += (u32)k[2]<<16;
+ case 2: a += (u32)k[1]<<8;
+ case 1: a += k[0];
+ __jhash_final(a, b, c);
+ case 0: /* Nothing left to add */
+ break;
+ }
+
+ return c;
+}
+
+static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval)
+{
+ a += initval;
+ b += initval;
+ c += initval;
+ __jhash_final(a, b, c);
+ return c;
+}
+
+static inline u32 jhash_2words(u32 a, u32 b, u32 initval)
+{
+ return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2));
+}
+
+#define PCKT_FRAGMENTED 65343
+#define IPV4_HDR_LEN_NO_OPT 20
+#define IPV4_PLUS_ICMP_HDR 28
+#define IPV6_PLUS_ICMP_HDR 48
+#define RING_SIZE 2
+#define MAX_VIPS 12
+#define MAX_REALS 5
+#define CTL_MAP_SIZE 16
+#define CH_RINGS_SIZE (MAX_VIPS * RING_SIZE)
+#define F_IPV6 (1 << 0)
+#define F_HASH_NO_SRC_PORT (1 << 0)
+#define F_ICMP (1 << 0)
+#define F_SYN_SET (1 << 1)
+
+struct packet_description {
+ union {
+ __be32 src;
+ __be32 srcv6[4];
+ };
+ union {
+ __be32 dst;
+ __be32 dstv6[4];
+ };
+ union {
+ __u32 ports;
+ __u16 port16[2];
+ };
+ __u8 proto;
+ __u8 flags;
+};
+
+struct ctl_value {
+ union {
+ __u64 value;
+ __u32 ifindex;
+ __u8 mac[6];
+ };
+};
+
+struct vip_meta {
+ __u32 flags;
+ __u32 vip_num;
+};
+
+struct real_definition {
+ union {
+ __be32 dst;
+ __be32 dstv6[4];
+ };
+ __u8 flags;
+};
+
+struct vip_stats {
+ __u64 bytes;
+ __u64 pkts;
+};
+
+struct eth_hdr {
+ unsigned char eth_dest[ETH_ALEN];
+ unsigned char eth_source[ETH_ALEN];
+ unsigned short eth_proto;
+};
+
+struct bpf_map_def SEC("maps") vip_map = {
+ .type = BPF_MAP_TYPE_HASH,
+ .key_size = sizeof(struct vip),
+ .value_size = sizeof(struct vip_meta),
+ .max_entries = MAX_VIPS,
+};
+
+struct bpf_map_def SEC("maps") ch_rings = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(__u32),
+ .max_entries = CH_RINGS_SIZE,
+};
+
+struct bpf_map_def SEC("maps") reals = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(struct real_definition),
+ .max_entries = MAX_REALS,
+};
+
+struct bpf_map_def SEC("maps") stats = {
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(struct vip_stats),
+ .max_entries = MAX_VIPS,
+};
+
+struct bpf_map_def SEC("maps") ctl_array = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(struct ctl_value),
+ .max_entries = CTL_MAP_SIZE,
+};
+
+static __always_inline __u32 get_packet_hash(struct packet_description *pckt,
+ bool ipv6)
+{
+ if (ipv6)
+ return jhash_2words(jhash(pckt->srcv6, 16, MAX_VIPS),
+ pckt->ports, CH_RINGS_SIZE);
+ else
+ return jhash_2words(pckt->src, pckt->ports, CH_RINGS_SIZE);
+}
+
+static __always_inline bool get_packet_dst(struct real_definition **real,
+ struct packet_description *pckt,
+ struct vip_meta *vip_info,
+ bool is_ipv6)
+{
+ __u32 hash = get_packet_hash(pckt, is_ipv6) % RING_SIZE;
+ __u32 key = RING_SIZE * vip_info->vip_num + hash;
+ __u32 *real_pos;
+
+ real_pos = bpf_map_lookup_elem(&ch_rings, &key);
+ if (!real_pos)
+ return false;
+ key = *real_pos;
+ *real = bpf_map_lookup_elem(&reals, &key);
+ if (!(*real))
+ return false;
+ return true;
+}
+
+static __always_inline int parse_icmpv6(void *data, void *data_end, __u64 off,
+ struct packet_description *pckt)
+{
+ struct icmp6hdr *icmp_hdr;
+ struct ipv6hdr *ip6h;
+
+ icmp_hdr = data + off;
+ if (icmp_hdr + 1 > data_end)
+ return TC_ACT_SHOT;
+ if (icmp_hdr->icmp6_type != ICMPV6_PKT_TOOBIG)
+ return TC_ACT_OK;
+ off += sizeof(struct icmp6hdr);
+ ip6h = data + off;
+ if (ip6h + 1 > data_end)
+ return TC_ACT_SHOT;
+ pckt->proto = ip6h->nexthdr;
+ pckt->flags |= F_ICMP;
+ memcpy(pckt->srcv6, ip6h->daddr.s6_addr32, 16);
+ memcpy(pckt->dstv6, ip6h->saddr.s6_addr32, 16);
+ return TC_ACT_UNSPEC;
+}
+
+static __always_inline int parse_icmp(void *data, void *data_end, __u64 off,
+ struct packet_description *pckt)
+{
+ struct icmphdr *icmp_hdr;
+ struct iphdr *iph;
+
+ icmp_hdr = data + off;
+ if (icmp_hdr + 1 > data_end)
+ return TC_ACT_SHOT;
+ if (icmp_hdr->type != ICMP_DEST_UNREACH ||
+ icmp_hdr->code != ICMP_FRAG_NEEDED)
+ return TC_ACT_OK;
+ off += sizeof(struct icmphdr);
+ iph = data + off;
+ if (iph + 1 > data_end)
+ return TC_ACT_SHOT;
+ if (iph->ihl != 5)
+ return TC_ACT_SHOT;
+ pckt->proto = iph->protocol;
+ pckt->flags |= F_ICMP;
+ pckt->src = iph->daddr;
+ pckt->dst = iph->saddr;
+ return TC_ACT_UNSPEC;
+}
+
+static __always_inline bool parse_udp(void *data, __u64 off, void *data_end,
+ struct packet_description *pckt)
+{
+ struct udphdr *udp;
+ udp = data + off;
+
+ if (udp + 1 > data_end)
+ return false;
+
+ if (!(pckt->flags & F_ICMP)) {
+ pckt->port16[0] = udp->source;
+ pckt->port16[1] = udp->dest;
+ } else {
+ pckt->port16[0] = udp->dest;
+ pckt->port16[1] = udp->source;
+ }
+ return true;
+}
+
+static __always_inline bool parse_tcp(void *data, __u64 off, void *data_end,
+ struct packet_description *pckt)
+{
+ struct tcphdr *tcp;
+
+ tcp = data + off;
+ if (tcp + 1 > data_end)
+ return false;
+
+ if (tcp->syn)
+ pckt->flags |= F_SYN_SET;
+
+ if (!(pckt->flags & F_ICMP)) {
+ pckt->port16[0] = tcp->source;
+ pckt->port16[1] = tcp->dest;
+ } else {
+ pckt->port16[0] = tcp->dest;
+ pckt->port16[1] = tcp->source;
+ }
+ return true;
+}
+
+static __always_inline int process_packet(void *data, __u64 off, void *data_end,
+ bool is_ipv6, struct __sk_buff *skb)
+{
+ void *pkt_start = (void *)(long)skb->data;
+ struct packet_description pckt = {};
+ struct eth_hdr *eth = pkt_start;
+ struct bpf_tunnel_key tkey = {};
+ struct vip_stats *data_stats;
+ struct real_definition *dst;
+ struct vip_meta *vip_info;
+ struct ctl_value *cval;
+ __u32 v4_intf_pos = 1;
+ __u32 v6_intf_pos = 2;
+ struct ipv6hdr *ip6h;
+ struct vip vip = {};
+ struct iphdr *iph;
+ int tun_flag = 0;
+ __u16 pkt_bytes;
+ __u64 iph_len;
+ __u32 ifindex;
+ __u8 protocol;
+ __u32 vip_num;
+ int action;
+
+ tkey.tunnel_ttl = 64;
+ if (is_ipv6) {
+ ip6h = data + off;
+ if (ip6h + 1 > data_end)
+ return TC_ACT_SHOT;
+
+ iph_len = sizeof(struct ipv6hdr);
+ protocol = ip6h->nexthdr;
+ pckt.proto = protocol;
+ pkt_bytes = ntohs(ip6h->payload_len);
+ off += iph_len;
+ if (protocol == IPPROTO_FRAGMENT) {
+ return TC_ACT_SHOT;
+ } else if (protocol == IPPROTO_ICMPV6) {
+ action = parse_icmpv6(data, data_end, off, &pckt);
+ if (action >= 0)
+ return action;
+ off += IPV6_PLUS_ICMP_HDR;
+ } else {
+ memcpy(pckt.srcv6, ip6h->saddr.s6_addr32, 16);
+ memcpy(pckt.dstv6, ip6h->daddr.s6_addr32, 16);
+ }
+ } else {
+ iph = data + off;
+ if (iph + 1 > data_end)
+ return TC_ACT_SHOT;
+ if (iph->ihl != 5)
+ return TC_ACT_SHOT;
+
+ protocol = iph->protocol;
+ pckt.proto = protocol;
+ pkt_bytes = ntohs(iph->tot_len);
+ off += IPV4_HDR_LEN_NO_OPT;
+
+ if (iph->frag_off & PCKT_FRAGMENTED)
+ return TC_ACT_SHOT;
+ if (protocol == IPPROTO_ICMP) {
+ action = parse_icmp(data, data_end, off, &pckt);
+ if (action >= 0)
+ return action;
+ off += IPV4_PLUS_ICMP_HDR;
+ } else {
+ pckt.src = iph->saddr;
+ pckt.dst = iph->daddr;
+ }
+ }
+ protocol = pckt.proto;
+
+ if (protocol == IPPROTO_TCP) {
+ if (!parse_tcp(data, off, data_end, &pckt))
+ return TC_ACT_SHOT;
+ } else if (protocol == IPPROTO_UDP) {
+ if (!parse_udp(data, off, data_end, &pckt))
+ return TC_ACT_SHOT;
+ } else {
+ return TC_ACT_SHOT;
+ }
+
+ if (is_ipv6)
+ memcpy(vip.daddr.v6, pckt.dstv6, 16);
+ else
+ vip.daddr.v4 = pckt.dst;
+
+ vip.dport = pckt.port16[1];
+ vip.protocol = pckt.proto;
+ vip_info = bpf_map_lookup_elem(&vip_map, &vip);
+ if (!vip_info) {
+ vip.dport = 0;
+ vip_info = bpf_map_lookup_elem(&vip_map, &vip);
+ if (!vip_info)
+ return TC_ACT_SHOT;
+ pckt.port16[1] = 0;
+ }
+
+ if (vip_info->flags & F_HASH_NO_SRC_PORT)
+ pckt.port16[0] = 0;
+
+ if (!get_packet_dst(&dst, &pckt, vip_info, is_ipv6))
+ return TC_ACT_SHOT;
+
+ if (dst->flags & F_IPV6) {
+ cval = bpf_map_lookup_elem(&ctl_array, &v6_intf_pos);
+ if (!cval)
+ return TC_ACT_SHOT;
+ ifindex = cval->ifindex;
+ memcpy(tkey.remote_ipv6, dst->dstv6, 16);
+ tun_flag = BPF_F_TUNINFO_IPV6;
+ } else {
+ cval = bpf_map_lookup_elem(&ctl_array, &v4_intf_pos);
+ if (!cval)
+ return TC_ACT_SHOT;
+ ifindex = cval->ifindex;
+ tkey.remote_ipv4 = dst->dst;
+ }
+ vip_num = vip_info->vip_num;
+ data_stats = bpf_map_lookup_elem(&stats, &vip_num);
+ if (!data_stats)
+ return TC_ACT_SHOT;
+ data_stats->pkts++;
+ data_stats->bytes += pkt_bytes;
+ bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), tun_flag);
+ *(u32 *)eth->eth_dest = tkey.remote_ipv4;
+ return bpf_redirect(ifindex, 0);
+}
+
+SEC("l4lb-demo")
+int balancer_ingress(struct __sk_buff *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct eth_hdr *eth = data;
+ __u32 eth_proto;
+ __u32 nh_off;
+
+ nh_off = sizeof(struct eth_hdr);
+ if (data + nh_off > data_end)
+ return TC_ACT_SHOT;
+ eth_proto = eth->eth_proto;
+ if (eth_proto == htons(ETH_P_IP))
+ return process_packet(data, nh_off, data_end, false, ctx);
+ else if (eth_proto == htons(ETH_P_IPV6))
+ return process_packet(data, nh_off, data_end, true, ctx);
+ else
+ return TC_ACT_SHOT;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index cada17a..a0aa200 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -80,8 +80,9 @@ static void test_hashmap(int task, void *data)
assert(bpf_map_update_elem(fd, &key, &value, BPF_EXIST) == 0);
key = 2;
assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0);
- key = 1;
- assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0);
+ key = 3;
+ assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 &&
+ errno == E2BIG);
/* Check that key = 0 doesn't exist. */
key = 0;
@@ -110,6 +111,24 @@ static void test_hashmap(int task, void *data)
close(fd);
}
+static void test_hashmap_sizes(int task, void *data)
+{
+ int fd, i, j;
+
+ for (i = 1; i <= 512; i <<= 1)
+ for (j = 1; j <= 1 << 18; j <<= 1) {
+ fd = bpf_create_map(BPF_MAP_TYPE_HASH, i, j,
+ 2, map_flags);
+ if (fd < 0) {
+ printf("Failed to create hashmap key=%d value=%d '%s'\n",
+ i, j, strerror(errno));
+ exit(1);
+ }
+ close(fd);
+ usleep(10); /* give kernel time to destroy */
+ }
+}
+
static void test_hashmap_percpu(int task, void *data)
{
unsigned int nr_cpus = bpf_num_possible_cpus();
@@ -317,7 +336,10 @@ static void test_arraymap_percpu(int task, void *data)
static void test_arraymap_percpu_many_keys(void)
{
unsigned int nr_cpus = bpf_num_possible_cpus();
- unsigned int nr_keys = 20000;
+ /* nr_keys is not too large otherwise the test stresses percpu
+ * allocator more than anything else
+ */
+ unsigned int nr_keys = 2000;
long values[nr_cpus];
int key, fd, i;
@@ -419,6 +441,7 @@ static void test_map_stress(void)
{
run_parallel(100, test_hashmap, NULL);
run_parallel(100, test_hashmap_percpu, NULL);
+ run_parallel(100, test_hashmap_sizes, NULL);
run_parallel(100, test_arraymap, NULL);
run_parallel(100, test_arraymap_percpu, NULL);
diff --git a/tools/testing/selftests/bpf/test_pkt_access.c b/tools/testing/selftests/bpf/test_pkt_access.c
new file mode 100644
index 0000000..fd1e083
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_pkt_access.c
@@ -0,0 +1,64 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/tcp.h>
+#include <linux/pkt_cls.h>
+#include "bpf_helpers.h"
+
+#define _htons __builtin_bswap16
+#define barrier() __asm__ __volatile__("": : :"memory")
+int _version SEC("version") = 1;
+
+SEC("test1")
+int process(struct __sk_buff *skb)
+{
+ void *data_end = (void *)(long)skb->data_end;
+ void *data = (void *)(long)skb->data;
+ struct ethhdr *eth = (struct ethhdr *)(data);
+ struct tcphdr *tcp = NULL;
+ __u8 proto = 255;
+ __u64 ihl_len;
+
+ if (eth + 1 > data_end)
+ return TC_ACT_SHOT;
+
+ if (eth->h_proto == _htons(ETH_P_IP)) {
+ struct iphdr *iph = (struct iphdr *)(eth + 1);
+
+ if (iph + 1 > data_end)
+ return TC_ACT_SHOT;
+ ihl_len = iph->ihl * 4;
+ proto = iph->protocol;
+ tcp = (struct tcphdr *)((void *)(iph) + ihl_len);
+ } else if (eth->h_proto == _htons(ETH_P_IPV6)) {
+ struct ipv6hdr *ip6h = (struct ipv6hdr *)(eth + 1);
+
+ if (ip6h + 1 > data_end)
+ return TC_ACT_SHOT;
+ ihl_len = sizeof(*ip6h);
+ proto = ip6h->nexthdr;
+ tcp = (struct tcphdr *)((void *)(ip6h) + ihl_len);
+ }
+
+ if (tcp) {
+ if (((void *)(tcp) + 20) > data_end || proto != 6)
+ return TC_ACT_SHOT;
+ barrier(); /* to force ordering of checks */
+ if (((void *)(tcp) + 18) > data_end)
+ return TC_ACT_SHOT;
+ if (tcp->urg_ptr == 123)
+ return TC_ACT_OK;
+ }
+
+ return TC_ACT_UNSPEC;
+}
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
new file mode 100644
index 0000000..5275d4a
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -0,0 +1,284 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <stdio.h>
+#include <unistd.h>
+#include <errno.h>
+#include <string.h>
+#include <assert.h>
+#include <stdlib.h>
+
+#include <linux/types.h>
+typedef __u16 __sum16;
+#include <arpa/inet.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+
+#include <sys/wait.h>
+#include <sys/resource.h>
+
+#include <linux/bpf.h>
+#include <linux/err.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "test_iptunnel_common.h"
+#include "bpf_util.h"
+
+#define _htons __builtin_bswap16
+
+static int error_cnt, pass_cnt;
+
+#define MAGIC_BYTES 123
+
+/* ipv4 test vector */
+static struct {
+ struct ethhdr eth;
+ struct iphdr iph;
+ struct tcphdr tcp;
+} __packed pkt_v4 = {
+ .eth.h_proto = _htons(ETH_P_IP),
+ .iph.ihl = 5,
+ .iph.protocol = 6,
+ .iph.tot_len = _htons(MAGIC_BYTES),
+ .tcp.urg_ptr = 123,
+};
+
+/* ipv6 test vector */
+static struct {
+ struct ethhdr eth;
+ struct ipv6hdr iph;
+ struct tcphdr tcp;
+} __packed pkt_v6 = {
+ .eth.h_proto = _htons(ETH_P_IPV6),
+ .iph.nexthdr = 6,
+ .iph.payload_len = _htons(MAGIC_BYTES),
+ .tcp.urg_ptr = 123,
+};
+
+#define CHECK(condition, tag, format...) ({ \
+ int __ret = !!(condition); \
+ if (__ret) { \
+ error_cnt++; \
+ printf("%s:FAIL:%s ", __func__, tag); \
+ printf(format); \
+ } else { \
+ pass_cnt++; \
+ printf("%s:PASS:%s %d nsec\n", __func__, tag, duration);\
+ } \
+})
+
+static int bpf_prog_load(const char *file, enum bpf_prog_type type,
+ struct bpf_object **pobj, int *prog_fd)
+{
+ struct bpf_program *prog;
+ struct bpf_object *obj;
+ int err;
+
+ obj = bpf_object__open(file);
+ if (IS_ERR(obj)) {
+ error_cnt++;
+ return -ENOENT;
+ }
+
+ prog = bpf_program__next(NULL, obj);
+ if (!prog) {
+ bpf_object__close(obj);
+ error_cnt++;
+ return -ENOENT;
+ }
+
+ bpf_program__set_type(prog, type);
+ err = bpf_object__load(obj);
+ if (err) {
+ bpf_object__close(obj);
+ error_cnt++;
+ return -EINVAL;
+ }
+
+ *pobj = obj;
+ *prog_fd = bpf_program__fd(prog);
+ return 0;
+}
+
+static int bpf_find_map(const char *test, struct bpf_object *obj,
+ const char *name)
+{
+ struct bpf_map *map;
+
+ map = bpf_object__find_map_by_name(obj, name);
+ if (!map) {
+ printf("%s:FAIL:map '%s' not found\n", test, name);
+ error_cnt++;
+ return -1;
+ }
+ return bpf_map__fd(map);
+}
+
+static void test_pkt_access(void)
+{
+ const char *file = "./test_pkt_access.o";
+ struct bpf_object *obj;
+ __u32 duration, retval;
+ int err, prog_fd;
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd);
+ if (err)
+ return;
+
+ err = bpf_prog_test_run(prog_fd, 100000, &pkt_v4, sizeof(pkt_v4),
+ NULL, NULL, &retval, &duration);
+ CHECK(err || errno || retval, "ipv4",
+ "err %d errno %d retval %d duration %d\n",
+ err, errno, retval, duration);
+
+ err = bpf_prog_test_run(prog_fd, 100000, &pkt_v6, sizeof(pkt_v6),
+ NULL, NULL, &retval, &duration);
+ CHECK(err || errno || retval, "ipv6",
+ "err %d errno %d retval %d duration %d\n",
+ err, errno, retval, duration);
+ bpf_object__close(obj);
+}
+
+static void test_xdp(void)
+{
+ struct vip key4 = {.protocol = 6, .family = AF_INET};
+ struct vip key6 = {.protocol = 6, .family = AF_INET6};
+ struct iptnl_info value4 = {.family = AF_INET};
+ struct iptnl_info value6 = {.family = AF_INET6};
+ const char *file = "./test_xdp.o";
+ struct bpf_object *obj;
+ char buf[128];
+ struct ipv6hdr *iph6 = (void *)buf + sizeof(struct ethhdr);
+ struct iphdr *iph = (void *)buf + sizeof(struct ethhdr);
+ __u32 duration, retval, size;
+ int err, prog_fd, map_fd;
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
+ if (err)
+ return;
+
+ map_fd = bpf_find_map(__func__, obj, "vip2tnl");
+ if (map_fd < 0)
+ goto out;
+ bpf_map_update_elem(map_fd, &key4, &value4, 0);
+ bpf_map_update_elem(map_fd, &key6, &value6, 0);
+
+ err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+ buf, &size, &retval, &duration);
+
+ CHECK(err || errno || retval != XDP_TX || size != 74 ||
+ iph->protocol != IPPROTO_IPIP, "ipv4",
+ "err %d errno %d retval %d size %d\n",
+ err, errno, retval, size);
+
+ err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6),
+ buf, &size, &retval, &duration);
+ CHECK(err || errno || retval != XDP_TX || size != 114 ||
+ iph6->nexthdr != IPPROTO_IPV6, "ipv6",
+ "err %d errno %d retval %d size %d\n",
+ err, errno, retval, size);
+out:
+ bpf_object__close(obj);
+}
+
+#define MAGIC_VAL 0x1234
+#define NUM_ITER 100000
+#define VIP_NUM 5
+
+static void test_l4lb(void)
+{
+ unsigned int nr_cpus = bpf_num_possible_cpus();
+ const char *file = "./test_l4lb.o";
+ struct vip key = {.protocol = 6};
+ struct vip_meta {
+ __u32 flags;
+ __u32 vip_num;
+ } value = {.vip_num = VIP_NUM};
+ __u32 stats_key = VIP_NUM;
+ struct vip_stats {
+ __u64 bytes;
+ __u64 pkts;
+ } stats[nr_cpus];
+ struct real_definition {
+ union {
+ __be32 dst;
+ __be32 dstv6[4];
+ };
+ __u8 flags;
+ } real_def = {.dst = MAGIC_VAL};
+ __u32 ch_key = 11, real_num = 3;
+ __u32 duration, retval, size;
+ int err, i, prog_fd, map_fd;
+ __u64 bytes = 0, pkts = 0;
+ struct bpf_object *obj;
+ char buf[128];
+ u32 *magic = (u32 *)buf;
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd);
+ if (err)
+ return;
+
+ map_fd = bpf_find_map(__func__, obj, "vip_map");
+ if (map_fd < 0)
+ goto out;
+ bpf_map_update_elem(map_fd, &key, &value, 0);
+
+ map_fd = bpf_find_map(__func__, obj, "ch_rings");
+ if (map_fd < 0)
+ goto out;
+ bpf_map_update_elem(map_fd, &ch_key, &real_num, 0);
+
+ map_fd = bpf_find_map(__func__, obj, "reals");
+ if (map_fd < 0)
+ goto out;
+ bpf_map_update_elem(map_fd, &real_num, &real_def, 0);
+
+ err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v4, sizeof(pkt_v4),
+ buf, &size, &retval, &duration);
+ CHECK(err || errno || retval != 7/*TC_ACT_REDIRECT*/ || size != 54 ||
+ *magic != MAGIC_VAL, "ipv4",
+ "err %d errno %d retval %d size %d magic %x\n",
+ err, errno, retval, size, *magic);
+
+ err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v6, sizeof(pkt_v6),
+ buf, &size, &retval, &duration);
+ CHECK(err || errno || retval != 7/*TC_ACT_REDIRECT*/ || size != 74 ||
+ *magic != MAGIC_VAL, "ipv6",
+ "err %d errno %d retval %d size %d magic %x\n",
+ err, errno, retval, size, *magic);
+
+ map_fd = bpf_find_map(__func__, obj, "stats");
+ if (map_fd < 0)
+ goto out;
+ bpf_map_lookup_elem(map_fd, &stats_key, stats);
+ for (i = 0; i < nr_cpus; i++) {
+ bytes += stats[i].bytes;
+ pkts += stats[i].pkts;
+ }
+ if (bytes != MAGIC_BYTES * NUM_ITER * 2 || pkts != NUM_ITER * 2) {
+ error_cnt++;
+ printf("test_l4lb:FAIL:stats %lld %lld\n", bytes, pkts);
+ }
+out:
+ bpf_object__close(obj);
+}
+
+int main(void)
+{
+ struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY };
+
+ setrlimit(RLIMIT_MEMLOCK, &rinf);
+
+ test_pkt_access();
+ test_xdp();
+ test_l4lb();
+
+ printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt);
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index e1f5b9e..6178b65 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -8,6 +8,8 @@
* License as published by the Free Software Foundation.
*/
+#include <asm/types.h>
+#include <linux/types.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
@@ -28,6 +30,14 @@
#include <bpf/bpf.h>
+#ifdef HAVE_GENHDR
+# include "autoconf.h"
+#else
+# if defined(__i386) || defined(__x86_64) || defined(__s390x__) || defined(__aarch64__)
+# define CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS 1
+# endif
+#endif
+
#include "../../../include/linux/filter.h"
#ifndef ARRAY_SIZE
@@ -36,6 +46,9 @@
#define MAX_INSNS 512
#define MAX_FIXUPS 8
+#define MAX_NR_MAPS 4
+
+#define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS (1 << 0)
struct bpf_test {
const char *descr;
@@ -43,6 +56,7 @@ struct bpf_test {
int fixup_map1[MAX_FIXUPS];
int fixup_map2[MAX_FIXUPS];
int fixup_prog[MAX_FIXUPS];
+ int fixup_map_in_map[MAX_FIXUPS];
const char *errstr;
const char *errstr_unpriv;
enum {
@@ -51,6 +65,7 @@ struct bpf_test {
REJECT
} result, result_unpriv;
enum bpf_prog_type prog_type;
+ uint8_t flags;
};
/* Note we want this to be 64 bit aligned so that the end of our array is
@@ -2430,6 +2445,30 @@ static struct bpf_test tests[] = {
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
},
{
+ "direct packet access: test15 (spill with xadd)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct __sk_buff, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct __sk_buff, data_end)),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+ BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 8),
+ BPF_MOV64_IMM(BPF_REG_5, 4096),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+ BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+ BPF_STX_XADD(BPF_DW, BPF_REG_4, BPF_REG_5, 0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_4, 0),
+ BPF_STX_MEM(BPF_W, BPF_REG_2, BPF_REG_5, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R2 invalid mem access 'inv'",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ },
+ {
"helper access to packet: test1, valid packet_ptr range",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
@@ -2932,6 +2971,7 @@ static struct bpf_test tests[] = {
.errstr_unpriv = "R0 pointer arithmetic prohibited",
.result_unpriv = REJECT,
.result = ACCEPT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"valid map access into an array with a variable",
@@ -2955,6 +2995,7 @@ static struct bpf_test tests[] = {
.errstr_unpriv = "R0 pointer arithmetic prohibited",
.result_unpriv = REJECT,
.result = ACCEPT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"valid map access into an array with a signed variable",
@@ -2982,6 +3023,7 @@ static struct bpf_test tests[] = {
.errstr_unpriv = "R0 pointer arithmetic prohibited",
.result_unpriv = REJECT,
.result = ACCEPT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid map access into an array with a constant",
@@ -3023,6 +3065,7 @@ static struct bpf_test tests[] = {
.errstr = "R0 min value is outside of the array range",
.result_unpriv = REJECT,
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid map access into an array with a variable",
@@ -3046,6 +3089,7 @@ static struct bpf_test tests[] = {
.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
.result_unpriv = REJECT,
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid map access into an array with no floor check",
@@ -3072,6 +3116,7 @@ static struct bpf_test tests[] = {
.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
.result_unpriv = REJECT,
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid map access into an array with a invalid max check",
@@ -3098,6 +3143,7 @@ static struct bpf_test tests[] = {
.errstr = "invalid access to map value, value_size=48 off=44 size=8",
.result_unpriv = REJECT,
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid map access into an array with a invalid max check",
@@ -3127,6 +3173,7 @@ static struct bpf_test tests[] = {
.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
.result_unpriv = REJECT,
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"multiple registers share map_lookup_elem result",
@@ -3250,6 +3297,7 @@ static struct bpf_test tests[] = {
.result = REJECT,
.errstr_unpriv = "R0 pointer arithmetic prohibited",
.result_unpriv = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"constant register |= constant should keep constant type",
@@ -3416,6 +3464,26 @@ static struct bpf_test tests[] = {
.prog_type = BPF_PROG_TYPE_LWT_XMIT,
},
{
+ "overlapping checks for direct packet access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct __sk_buff, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct __sk_buff, data_end)),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+ BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 4),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
+ BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+ BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_2, 6),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_LWT_XMIT,
+ },
+ {
"invalid access of tc_classid for LWT_IN",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
@@ -3959,7 +4027,208 @@ static struct bpf_test tests[] = {
.result_unpriv = REJECT,
},
{
- "map element value (adjusted) is preserved across register spilling",
+ "map element value or null is marked on register spilling",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -152),
+ BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_1, 0),
+ BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 42),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 leaks addr",
+ .result = ACCEPT,
+ .result_unpriv = REJECT,
+ },
+ {
+ "map element value store of cleared call register",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R1 !read_ok",
+ .errstr = "R1 !read_ok",
+ .result = REJECT,
+ .result_unpriv = REJECT,
+ },
+ {
+ "map element value with unaligned store",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 17),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 3),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 2, 43),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, -2, 44),
+ BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
+ BPF_ST_MEM(BPF_DW, BPF_REG_8, 0, 32),
+ BPF_ST_MEM(BPF_DW, BPF_REG_8, 2, 33),
+ BPF_ST_MEM(BPF_DW, BPF_REG_8, -2, 34),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_8, 5),
+ BPF_ST_MEM(BPF_DW, BPF_REG_8, 0, 22),
+ BPF_ST_MEM(BPF_DW, BPF_REG_8, 4, 23),
+ BPF_ST_MEM(BPF_DW, BPF_REG_8, -7, 24),
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_8),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 3),
+ BPF_ST_MEM(BPF_DW, BPF_REG_7, 0, 22),
+ BPF_ST_MEM(BPF_DW, BPF_REG_7, 4, 23),
+ BPF_ST_MEM(BPF_DW, BPF_REG_7, -4, 24),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 pointer arithmetic prohibited",
+ .result = ACCEPT,
+ .result_unpriv = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+ },
+ {
+ "map element value with unaligned load",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
+ BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JGE, BPF_REG_1, MAX_ENTRIES, 9),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 3),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 2),
+ BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_8, 0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_8, 2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 5),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 4),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 pointer arithmetic prohibited",
+ .result = ACCEPT,
+ .result_unpriv = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+ },
+ {
+ "map element value illegal alu op, 1",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 pointer arithmetic prohibited",
+ .errstr = "invalid mem access 'inv'",
+ .result = REJECT,
+ .result_unpriv = REJECT,
+ },
+ {
+ "map element value illegal alu op, 2",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_ALU32_IMM(BPF_ADD, BPF_REG_0, 0),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 pointer arithmetic prohibited",
+ .errstr = "invalid mem access 'inv'",
+ .result = REJECT,
+ .result_unpriv = REJECT,
+ },
+ {
+ "map element value illegal alu op, 3",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_ALU64_IMM(BPF_DIV, BPF_REG_0, 42),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 pointer arithmetic prohibited",
+ .errstr = "invalid mem access 'inv'",
+ .result = REJECT,
+ .result_unpriv = REJECT,
+ },
+ {
+ "map element value illegal alu op, 4",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_ENDIAN(BPF_FROM_BE, BPF_REG_0, 64),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 pointer arithmetic prohibited",
+ .errstr = "invalid mem access 'inv'",
+ .result = REJECT,
+ .result_unpriv = REJECT,
+ },
+ {
+ "map element value illegal alu op, 5",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+ BPF_MOV64_IMM(BPF_REG_3, 4096),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+ BPF_STX_XADD(BPF_DW, BPF_REG_2, BPF_REG_3, 0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .errstr = "R0 invalid mem access 'inv'",
+ .result = REJECT,
+ .result_unpriv = REJECT,
+ },
+ {
+ "map element value is preserved across register spilling",
.insns = {
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
@@ -3981,6 +4250,7 @@ static struct bpf_test tests[] = {
.errstr_unpriv = "R0 pointer arithmetic prohibited",
.result = ACCEPT,
.result_unpriv = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"helper access to variable memory: stack, bitwise AND + JMP, correct bounds",
@@ -4419,6 +4689,7 @@ static struct bpf_test tests[] = {
.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
.result = REJECT,
.result_unpriv = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid range check",
@@ -4450,6 +4721,76 @@ static struct bpf_test tests[] = {
.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
.result = REJECT,
.result_unpriv = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+ },
+ {
+ "map in map access",
+ .insns = {
+ BPF_ST_MEM(0, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+ BPF_ST_MEM(0, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_MOV64_REG(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_in_map = { 3 },
+ .result = ACCEPT,
+ },
+ {
+ "invalid inner map pointer",
+ .insns = {
+ BPF_ST_MEM(0, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+ BPF_ST_MEM(0, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_MOV64_REG(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_in_map = { 3 },
+ .errstr = "R1 type=inv expected=map_ptr",
+ .errstr_unpriv = "R1 pointer arithmetic prohibited",
+ .result = REJECT,
+ },
+ {
+ "forgot null checking on the inner map pointer",
+ .insns = {
+ BPF_ST_MEM(0, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_ST_MEM(0, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_MOV64_REG(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_in_map = { 3 },
+ .errstr = "R1 type=map_value_or_null expected=map_ptr",
+ .result = REJECT,
}
};
@@ -4487,55 +4828,90 @@ static int create_prog_array(void)
return fd;
}
+static int create_map_in_map(void)
+{
+ int inner_map_fd, outer_map_fd;
+
+ inner_map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(int),
+ sizeof(int), 1, 0);
+ if (inner_map_fd < 0) {
+ printf("Failed to create array '%s'!\n", strerror(errno));
+ return inner_map_fd;
+ }
+
+ outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS,
+ sizeof(int), inner_map_fd, 1, 0);
+ if (outer_map_fd < 0)
+ printf("Failed to create array of maps '%s'!\n",
+ strerror(errno));
+
+ close(inner_map_fd);
+
+ return outer_map_fd;
+}
+
static char bpf_vlog[32768];
static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
- int *fd_f1, int *fd_f2, int *fd_f3)
+ int *map_fds)
{
int *fixup_map1 = test->fixup_map1;
int *fixup_map2 = test->fixup_map2;
int *fixup_prog = test->fixup_prog;
+ int *fixup_map_in_map = test->fixup_map_in_map;
/* Allocating HTs with 1 elem is fine here, since we only test
* for verifier and not do a runtime lookup, so the only thing
* that really matters is value size in this case.
*/
if (*fixup_map1) {
- *fd_f1 = create_map(sizeof(long long), 1);
+ map_fds[0] = create_map(sizeof(long long), 1);
do {
- prog[*fixup_map1].imm = *fd_f1;
+ prog[*fixup_map1].imm = map_fds[0];
fixup_map1++;
} while (*fixup_map1);
}
if (*fixup_map2) {
- *fd_f2 = create_map(sizeof(struct test_val), 1);
+ map_fds[1] = create_map(sizeof(struct test_val), 1);
do {
- prog[*fixup_map2].imm = *fd_f2;
+ prog[*fixup_map2].imm = map_fds[1];
fixup_map2++;
} while (*fixup_map2);
}
if (*fixup_prog) {
- *fd_f3 = create_prog_array();
+ map_fds[2] = create_prog_array();
do {
- prog[*fixup_prog].imm = *fd_f3;
+ prog[*fixup_prog].imm = map_fds[2];
fixup_prog++;
} while (*fixup_prog);
}
+
+ if (*fixup_map_in_map) {
+ map_fds[3] = create_map_in_map();
+ do {
+ prog[*fixup_map_in_map].imm = map_fds[3];
+ fixup_map_in_map++;
+ } while (*fixup_map_in_map);
+ }
}
static void do_test_single(struct bpf_test *test, bool unpriv,
int *passes, int *errors)
{
+ int fd_prog, expected_ret, reject_from_alignment;
struct bpf_insn *prog = test->insns;
int prog_len = probe_filter_length(prog);
int prog_type = test->prog_type;
- int fd_f1 = -1, fd_f2 = -1, fd_f3 = -1;
- int fd_prog, expected_ret;
+ int map_fds[MAX_NR_MAPS];
const char *expected_err;
+ int i;
- do_test_fixup(test, prog, &fd_f1, &fd_f2, &fd_f3);
+ for (i = 0; i < MAX_NR_MAPS; i++)
+ map_fds[i] = -1;
+
+ do_test_fixup(test, prog, map_fds);
fd_prog = bpf_load_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
prog, prog_len, "GPL", 0, bpf_vlog,
@@ -4545,8 +4921,19 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
test->result_unpriv : test->result;
expected_err = unpriv && test->errstr_unpriv ?
test->errstr_unpriv : test->errstr;
+
+ reject_from_alignment = fd_prog < 0 &&
+ (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS) &&
+ strstr(bpf_vlog, "Unknown alignment.");
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+ if (reject_from_alignment) {
+ printf("FAIL\nFailed due to alignment despite having efficient unaligned access: '%s'!\n",
+ strerror(errno));
+ goto fail_log;
+ }
+#endif
if (expected_ret == ACCEPT) {
- if (fd_prog < 0) {
+ if (fd_prog < 0 && !reject_from_alignment) {
printf("FAIL\nFailed to load prog '%s'!\n",
strerror(errno));
goto fail_log;
@@ -4556,19 +4943,19 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
printf("FAIL\nUnexpected success to load!\n");
goto fail_log;
}
- if (!strstr(bpf_vlog, expected_err)) {
+ if (!strstr(bpf_vlog, expected_err) && !reject_from_alignment) {
printf("FAIL\nUnexpected error message!\n");
goto fail_log;
}
}
(*passes)++;
- printf("OK\n");
+ printf("OK%s\n", reject_from_alignment ?
+ " (NOTE: reject due to unknown alignment)" : "");
close_fds:
close(fd_prog);
- close(fd_f1);
- close(fd_f2);
- close(fd_f3);
+ for (i = 0; i < MAX_NR_MAPS; i++)
+ close(map_fds[i]);
sched_yield();
return;
fail_log:
@@ -4583,10 +4970,12 @@ static bool is_admin(void)
cap_flag_value_t sysadmin = CAP_CLEAR;
const cap_value_t cap_val = CAP_SYS_ADMIN;
+#ifdef CAP_IS_SUPPORTED
if (!CAP_IS_SUPPORTED(CAP_SETFCAP)) {
perror("cap_get_flag");
return false;
}
+#endif
caps = cap_get_proc();
if (!caps) {
perror("cap_get_proc");
diff --git a/tools/testing/selftests/bpf/test_xdp.c b/tools/testing/selftests/bpf/test_xdp.c
new file mode 100644
index 0000000..9a33b03
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp.c
@@ -0,0 +1,236 @@
+/* Copyright (c) 2016,2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/udp.h>
+#include <linux/tcp.h>
+#include <linux/pkt_cls.h>
+#include <sys/socket.h>
+#include "bpf_helpers.h"
+#include "test_iptunnel_common.h"
+
+#define htons __builtin_bswap16
+#define ntohs __builtin_bswap16
+int _version SEC("version") = 1;
+
+struct bpf_map_def SEC("maps") rxcnt = {
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(__u64),
+ .max_entries = 256,
+};
+
+struct bpf_map_def SEC("maps") vip2tnl = {
+ .type = BPF_MAP_TYPE_HASH,
+ .key_size = sizeof(struct vip),
+ .value_size = sizeof(struct iptnl_info),
+ .max_entries = MAX_IPTNL_ENTRIES,
+};
+
+static __always_inline void count_tx(__u32 protocol)
+{
+ __u64 *rxcnt_count;
+
+ rxcnt_count = bpf_map_lookup_elem(&rxcnt, &protocol);
+ if (rxcnt_count)
+ *rxcnt_count += 1;
+}
+
+static __always_inline int get_dport(void *trans_data, void *data_end,
+ __u8 protocol)
+{
+ struct tcphdr *th;
+ struct udphdr *uh;
+
+ switch (protocol) {
+ case IPPROTO_TCP:
+ th = (struct tcphdr *)trans_data;
+ if (th + 1 > data_end)
+ return -1;
+ return th->dest;
+ case IPPROTO_UDP:
+ uh = (struct udphdr *)trans_data;
+ if (uh + 1 > data_end)
+ return -1;
+ return uh->dest;
+ default:
+ return 0;
+ }
+}
+
+static __always_inline void set_ethhdr(struct ethhdr *new_eth,
+ const struct ethhdr *old_eth,
+ const struct iptnl_info *tnl,
+ __be16 h_proto)
+{
+ memcpy(new_eth->h_source, old_eth->h_dest, sizeof(new_eth->h_source));
+ memcpy(new_eth->h_dest, tnl->dmac, sizeof(new_eth->h_dest));
+ new_eth->h_proto = h_proto;
+}
+
+static __always_inline int handle_ipv4(struct xdp_md *xdp)
+{
+ void *data_end = (void *)(long)xdp->data_end;
+ void *data = (void *)(long)xdp->data;
+ struct iptnl_info *tnl;
+ struct ethhdr *new_eth;
+ struct ethhdr *old_eth;
+ struct iphdr *iph = data + sizeof(struct ethhdr);
+ __u16 *next_iph;
+ __u16 payload_len;
+ struct vip vip = {};
+ int dport;
+ __u32 csum = 0;
+ int i;
+
+ if (iph + 1 > data_end)
+ return XDP_DROP;
+
+ dport = get_dport(iph + 1, data_end, iph->protocol);
+ if (dport == -1)
+ return XDP_DROP;
+
+ vip.protocol = iph->protocol;
+ vip.family = AF_INET;
+ vip.daddr.v4 = iph->daddr;
+ vip.dport = dport;
+ payload_len = ntohs(iph->tot_len);
+
+ tnl = bpf_map_lookup_elem(&vip2tnl, &vip);
+ /* It only does v4-in-v4 */
+ if (!tnl || tnl->family != AF_INET)
+ return XDP_PASS;
+
+ if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct iphdr)))
+ return XDP_DROP;
+
+ data = (void *)(long)xdp->data;
+ data_end = (void *)(long)xdp->data_end;
+
+ new_eth = data;
+ iph = data + sizeof(*new_eth);
+ old_eth = data + sizeof(*iph);
+
+ if (new_eth + 1 > data_end ||
+ old_eth + 1 > data_end ||
+ iph + 1 > data_end)
+ return XDP_DROP;
+
+ set_ethhdr(new_eth, old_eth, tnl, htons(ETH_P_IP));
+
+ iph->version = 4;
+ iph->ihl = sizeof(*iph) >> 2;
+ iph->frag_off = 0;
+ iph->protocol = IPPROTO_IPIP;
+ iph->check = 0;
+ iph->tos = 0;
+ iph->tot_len = htons(payload_len + sizeof(*iph));
+ iph->daddr = tnl->daddr.v4;
+ iph->saddr = tnl->saddr.v4;
+ iph->ttl = 8;
+
+ next_iph = (__u16 *)iph;
+#pragma clang loop unroll(full)
+ for (i = 0; i < sizeof(*iph) >> 1; i++)
+ csum += *next_iph++;
+
+ iph->check = ~((csum & 0xffff) + (csum >> 16));
+
+ count_tx(vip.protocol);
+
+ return XDP_TX;
+}
+
+static __always_inline int handle_ipv6(struct xdp_md *xdp)
+{
+ void *data_end = (void *)(long)xdp->data_end;
+ void *data = (void *)(long)xdp->data;
+ struct iptnl_info *tnl;
+ struct ethhdr *new_eth;
+ struct ethhdr *old_eth;
+ struct ipv6hdr *ip6h = data + sizeof(struct ethhdr);
+ __u16 payload_len;
+ struct vip vip = {};
+ int dport;
+
+ if (ip6h + 1 > data_end)
+ return XDP_DROP;
+
+ dport = get_dport(ip6h + 1, data_end, ip6h->nexthdr);
+ if (dport == -1)
+ return XDP_DROP;
+
+ vip.protocol = ip6h->nexthdr;
+ vip.family = AF_INET6;
+ memcpy(vip.daddr.v6, ip6h->daddr.s6_addr32, sizeof(vip.daddr));
+ vip.dport = dport;
+ payload_len = ip6h->payload_len;
+
+ tnl = bpf_map_lookup_elem(&vip2tnl, &vip);
+ /* It only does v6-in-v6 */
+ if (!tnl || tnl->family != AF_INET6)
+ return XDP_PASS;
+
+ if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct ipv6hdr)))
+ return XDP_DROP;
+
+ data = (void *)(long)xdp->data;
+ data_end = (void *)(long)xdp->data_end;
+
+ new_eth = data;
+ ip6h = data + sizeof(*new_eth);
+ old_eth = data + sizeof(*ip6h);
+
+ if (new_eth + 1 > data_end || old_eth + 1 > data_end ||
+ ip6h + 1 > data_end)
+ return XDP_DROP;
+
+ set_ethhdr(new_eth, old_eth, tnl, htons(ETH_P_IPV6));
+
+ ip6h->version = 6;
+ ip6h->priority = 0;
+ memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl));
+ ip6h->payload_len = htons(ntohs(payload_len) + sizeof(*ip6h));
+ ip6h->nexthdr = IPPROTO_IPV6;
+ ip6h->hop_limit = 8;
+ memcpy(ip6h->saddr.s6_addr32, tnl->saddr.v6, sizeof(tnl->saddr.v6));
+ memcpy(ip6h->daddr.s6_addr32, tnl->daddr.v6, sizeof(tnl->daddr.v6));
+
+ count_tx(vip.protocol);
+
+ return XDP_TX;
+}
+
+SEC("xdp_tx_iptunnel")
+int _xdp_tx_iptunnel(struct xdp_md *xdp)
+{
+ void *data_end = (void *)(long)xdp->data_end;
+ void *data = (void *)(long)xdp->data;
+ struct ethhdr *eth = data;
+ __u16 h_proto;
+
+ if (eth + 1 > data_end)
+ return XDP_DROP;
+
+ h_proto = eth->h_proto;
+
+ if (h_proto == htons(ETH_P_IP))
+ return handle_ipv4(xdp);
+ else if (h_proto == htons(ETH_P_IPV6))
+
+ return handle_ipv6(xdp);
+ else
+ return XDP_DROP;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index fbfe5d0..35cbb4c 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -5,7 +5,7 @@
reuseport_bpf_numa: LDFLAGS += -lnuma
-TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh
+TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh
TEST_GEN_FILES = socket
TEST_GEN_FILES += psock_fanout psock_tpacket
TEST_GEN_FILES += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
diff --git a/tools/testing/selftests/net/netdevice.sh b/tools/testing/selftests/net/netdevice.sh
new file mode 100755
index 0000000..4e00568
--- /dev/null
+++ b/tools/testing/selftests/net/netdevice.sh
@@ -0,0 +1,200 @@
+#!/bin/sh
+#
+# This test is for checking network interface
+# For the moment it tests only ethernet interface (but wifi could be easily added)
+#
+# We assume that all network driver are loaded
+# if not they probably have failed earlier in the boot process and their logged error will be catched by another test
+#
+
+# this function will try to up the interface
+# if already up, nothing done
+# arg1: network interface name
+kci_net_start()
+{
+ netdev=$1
+
+ ip link show "$netdev" |grep -q UP
+ if [ $? -eq 0 ];then
+ echo "SKIP: $netdev: interface already up"
+ return 0
+ fi
+
+ ip link set "$netdev" up
+ if [ $? -ne 0 ];then
+ echo "FAIL: $netdev: Fail to up interface"
+ return 1
+ else
+ echo "PASS: $netdev: set interface up"
+ NETDEV_STARTED=1
+ fi
+ return 0
+}
+
+# this function will try to setup an IP and MAC address on a network interface
+# Doing nothing if the interface was already up
+# arg1: network interface name
+kci_net_setup()
+{
+ netdev=$1
+
+ # do nothing if the interface was already up
+ if [ $NETDEV_STARTED -eq 0 ];then
+ return 0
+ fi
+
+ MACADDR='02:03:04:05:06:07'
+ ip link set dev $netdev address "$MACADDR"
+ if [ $? -ne 0 ];then
+ echo "FAIL: $netdev: Cannot set MAC address"
+ else
+ ip link show $netdev |grep -q "$MACADDR"
+ if [ $? -eq 0 ];then
+ echo "PASS: $netdev: set MAC address"
+ else
+ echo "FAIL: $netdev: Cannot set MAC address"
+ fi
+ fi
+
+ #check that the interface did not already have an IP
+ ip address show "$netdev" |grep '^[[:space:]]*inet'
+ if [ $? -eq 0 ];then
+ echo "SKIP: $netdev: already have an IP"
+ return 0
+ fi
+
+ # TODO what ipaddr to set ? DHCP ?
+ echo "SKIP: $netdev: set IP address"
+ return 0
+}
+
+# test an ethtool command
+# arg1: return code for not supported (see ethtool code source)
+# arg2: summary of the command
+# arg3: command to execute
+kci_netdev_ethtool_test()
+{
+ if [ $# -le 2 ];then
+ echo "SKIP: $netdev: ethtool: invalid number of arguments"
+ return 1
+ fi
+ $3 >/dev/null
+ ret=$?
+ if [ $ret -ne 0 ];then
+ if [ $ret -eq "$1" ];then
+ echo "SKIP: $netdev: ethtool $2 not supported"
+ else
+ echo "FAIL: $netdev: ethtool $2"
+ return 1
+ fi
+ else
+ echo "PASS: $netdev: ethtool $2"
+ fi
+ return 0
+}
+
+# test ethtool commands
+# arg1: network interface name
+kci_netdev_ethtool()
+{
+ netdev=$1
+
+ #check presence of ethtool
+ ethtool --version 2>/dev/null >/dev/null
+ if [ $? -ne 0 ];then
+ echo "SKIP: ethtool not present"
+ return 1
+ fi
+
+ TMP_ETHTOOL_FEATURES="$(mktemp)"
+ if [ ! -e "$TMP_ETHTOOL_FEATURES" ];then
+ echo "SKIP: Cannot create a tmp file"
+ return 1
+ fi
+
+ ethtool -k "$netdev" > "$TMP_ETHTOOL_FEATURES"
+ if [ $? -ne 0 ];then
+ echo "FAIL: $netdev: ethtool list features"
+ rm "$TMP_ETHTOOL_FEATURES"
+ return 1
+ fi
+ echo "PASS: $netdev: ethtool list features"
+ #TODO for each non fixed features, try to turn them on/off
+ rm "$TMP_ETHTOOL_FEATURES"
+
+ kci_netdev_ethtool_test 74 'dump' "ethtool -d $netdev"
+ kci_netdev_ethtool_test 94 'stats' "ethtool -S $netdev"
+ return 0
+}
+
+# stop a netdev
+# arg1: network interface name
+kci_netdev_stop()
+{
+ netdev=$1
+
+ if [ $NETDEV_STARTED -eq 0 ];then
+ echo "SKIP: $netdev: interface kept up"
+ return 0
+ fi
+
+ ip link set "$netdev" down
+ if [ $? -ne 0 ];then
+ echo "FAIL: $netdev: stop interface"
+ return 1
+ fi
+ echo "PASS: $netdev: stop interface"
+ return 0
+}
+
+# run all test on a netdev
+# arg1: network interface name
+kci_test_netdev()
+{
+ NETDEV_STARTED=0
+ IFACE_TO_UPDOWN="$1"
+ IFACE_TO_TEST="$1"
+ #check for VLAN interface
+ MASTER_IFACE="$(echo $1 | cut -d@ -f2)"
+ if [ ! -z "$MASTER_IFACE" ];then
+ IFACE_TO_UPDOWN="$MASTER_IFACE"
+ IFACE_TO_TEST="$(echo $1 | cut -d@ -f1)"
+ fi
+
+ NETDEV_STARTED=0
+ kci_net_start "$IFACE_TO_UPDOWN"
+
+ kci_net_setup "$IFACE_TO_TEST"
+
+ kci_netdev_ethtool "$IFACE_TO_TEST"
+
+ kci_netdev_stop "$IFACE_TO_UPDOWN"
+ return 0
+}
+
+#check for needed privileges
+if [ "$(id -u)" -ne 0 ];then
+ echo "SKIP: Need root privileges"
+ exit 0
+fi
+
+ip -Version 2>/dev/null >/dev/null
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without the ip tool"
+ exit 0
+fi
+
+TMP_LIST_NETDEV="$(mktemp)"
+if [ ! -e "$TMP_LIST_NETDEV" ];then
+ echo "FAIL: Cannot create a tmp file"
+ exit 1
+fi
+
+ip link show |grep '^[0-9]' | grep -oE '[[:space:]].*eth[0-9]*:|[[:space:]].*enp[0-9]s[0-9]:' | cut -d\ -f2 | cut -d: -f1> "$TMP_LIST_NETDEV"
+while read netdev
+do
+ kci_test_netdev "$netdev"
+done < "$TMP_LIST_NETDEV"
+
+rm "$TMP_LIST_NETDEV"
+exit 0
diff --git a/tools/testing/selftests/powerpc/harness.c b/tools/testing/selftests/powerpc/harness.c
index 248a820..66d31de 100644
--- a/tools/testing/selftests/powerpc/harness.c
+++ b/tools/testing/selftests/powerpc/harness.c
@@ -114,9 +114,11 @@ int test_harness(int (test_function)(void), char *name)
rc = run_test(test_function, name);
- if (rc == MAGIC_SKIP_RETURN_VALUE)
+ if (rc == MAGIC_SKIP_RETURN_VALUE) {
test_skip(name);
- else
+ /* so that skipped test is not marked as failed */
+ rc = 0;
+ } else
test_finish(name, rc);
return rc;
diff --git a/tools/testing/selftests/powerpc/include/vsx_asm.h b/tools/testing/selftests/powerpc/include/vsx_asm.h
index d828bfb..54064ce 100644
--- a/tools/testing/selftests/powerpc/include/vsx_asm.h
+++ b/tools/testing/selftests/powerpc/include/vsx_asm.h
@@ -16,56 +16,56 @@
*/
FUNC_START(load_vsx)
li r5,0
- lxvx vs20,r5,r3
+ lxvd2x vs20,r5,r3
addi r5,r5,16
- lxvx vs21,r5,r3
+ lxvd2x vs21,r5,r3
addi r5,r5,16
- lxvx vs22,r5,r3
+ lxvd2x vs22,r5,r3
addi r5,r5,16
- lxvx vs23,r5,r3
+ lxvd2x vs23,r5,r3
addi r5,r5,16
- lxvx vs24,r5,r3
+ lxvd2x vs24,r5,r3
addi r5,r5,16
- lxvx vs25,r5,r3
+ lxvd2x vs25,r5,r3
addi r5,r5,16
- lxvx vs26,r5,r3
+ lxvd2x vs26,r5,r3
addi r5,r5,16
- lxvx vs27,r5,r3
+ lxvd2x vs27,r5,r3
addi r5,r5,16
- lxvx vs28,r5,r3
+ lxvd2x vs28,r5,r3
addi r5,r5,16
- lxvx vs29,r5,r3
+ lxvd2x vs29,r5,r3
addi r5,r5,16
- lxvx vs30,r5,r3
+ lxvd2x vs30,r5,r3
addi r5,r5,16
- lxvx vs31,r5,r3
+ lxvd2x vs31,r5,r3
blr
FUNC_END(load_vsx)
FUNC_START(store_vsx)
li r5,0
- stxvx vs20,r5,r3
+ stxvd2x vs20,r5,r3
addi r5,r5,16
- stxvx vs21,r5,r3
+ stxvd2x vs21,r5,r3
addi r5,r5,16
- stxvx vs22,r5,r3
+ stxvd2x vs22,r5,r3
addi r5,r5,16
- stxvx vs23,r5,r3
+ stxvd2x vs23,r5,r3
addi r5,r5,16
- stxvx vs24,r5,r3
+ stxvd2x vs24,r5,r3
addi r5,r5,16
- stxvx vs25,r5,r3
+ stxvd2x vs25,r5,r3
addi r5,r5,16
- stxvx vs26,r5,r3
+ stxvd2x vs26,r5,r3
addi r5,r5,16
- stxvx vs27,r5,r3
+ stxvd2x vs27,r5,r3
addi r5,r5,16
- stxvx vs28,r5,r3
+ stxvd2x vs28,r5,r3
addi r5,r5,16
- stxvx vs29,r5,r3
+ stxvd2x vs29,r5,r3
addi r5,r5,16
- stxvx vs30,r5,r3
+ stxvd2x vs30,r5,r3
addi r5,r5,16
- stxvx vs31,r5,r3
+ stxvd2x vs31,r5,r3
blr
FUNC_END(store_vsx)
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 4cff7e7..41642ba 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -1,5 +1,9 @@
# Makefile for vm selftests
+ifndef OUTPUT
+ OUTPUT := $(shell pwd)
+endif
+
CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS)
LDLIBS = -lrt
TEST_GEN_FILES = compaction_test
diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c
index 5b2b4b3..b4967d8 100644
--- a/tools/testing/selftests/x86/fsgsbase.c
+++ b/tools/testing/selftests/x86/fsgsbase.c
@@ -245,7 +245,7 @@ void do_unexpected_base(void)
long ret;
asm volatile ("int $0x80"
: "=a" (ret) : "a" (243), "b" (low_desc)
- : "flags");
+ : "r8", "r9", "r10", "r11");
memcpy(&desc, low_desc, sizeof(desc));
munmap(low_desc, sizeof(desc));
diff --git a/tools/testing/selftests/x86/ldt_gdt.c b/tools/testing/selftests/x86/ldt_gdt.c
index 4af4707..f612161 100644
--- a/tools/testing/selftests/x86/ldt_gdt.c
+++ b/tools/testing/selftests/x86/ldt_gdt.c
@@ -45,6 +45,12 @@
#define AR_DB (1 << 22)
#define AR_G (1 << 23)
+#ifdef __x86_64__
+# define INT80_CLOBBERS "r8", "r9", "r10", "r11"
+#else
+# define INT80_CLOBBERS
+#endif
+
static int nerrs;
/* Points to an array of 1024 ints, each holding its own index. */
@@ -588,7 +594,7 @@ static int invoke_set_thread_area(void)
asm volatile ("int $0x80"
: "=a" (ret), "+m" (low_user_desc) :
"a" (243), "b" (low_user_desc)
- : "flags");
+ : INT80_CLOBBERS);
return ret;
}
@@ -657,7 +663,7 @@ static void test_gdt_invalidation(void)
"+a" (eax)
: "m" (low_user_desc_clear),
[arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear)
- : "flags");
+ : INT80_CLOBBERS);
if (sel != 0) {
result = "FAIL";
@@ -688,7 +694,7 @@ static void test_gdt_invalidation(void)
"+a" (eax)
: "m" (low_user_desc_clear),
[arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear)
- : "flags");
+ : INT80_CLOBBERS);
if (sel != 0) {
result = "FAIL";
@@ -721,7 +727,7 @@ static void test_gdt_invalidation(void)
"+a" (eax)
: "m" (low_user_desc_clear),
[arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear)
- : "flags");
+ : INT80_CLOBBERS);
#ifdef __x86_64__
syscall(SYS_arch_prctl, ARCH_GET_FS, &new_base);
@@ -774,7 +780,7 @@ static void test_gdt_invalidation(void)
"+a" (eax)
: "m" (low_user_desc_clear),
[arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear)
- : "flags");
+ : INT80_CLOBBERS);
#ifdef __x86_64__
syscall(SYS_arch_prctl, ARCH_GET_GS, &new_base);
diff --git a/tools/testing/selftests/x86/ptrace_syscall.c b/tools/testing/selftests/x86/ptrace_syscall.c
index b037ce9c..eaea924 100644
--- a/tools/testing/selftests/x86/ptrace_syscall.c
+++ b/tools/testing/selftests/x86/ptrace_syscall.c
@@ -58,7 +58,8 @@ static void do_full_int80(struct syscall_args32 *args)
asm volatile ("int $0x80"
: "+a" (args->nr),
"+b" (args->arg0), "+c" (args->arg1), "+d" (args->arg2),
- "+S" (args->arg3), "+D" (args->arg4), "+r" (bp));
+ "+S" (args->arg3), "+D" (args->arg4), "+r" (bp)
+ : : "r8", "r9", "r10", "r11");
args->arg5 = bp;
#else
sys32_helper(args, int80_and_ret);
diff --git a/tools/testing/selftests/x86/single_step_syscall.c b/tools/testing/selftests/x86/single_step_syscall.c
index 50c2635..a48da95 100644
--- a/tools/testing/selftests/x86/single_step_syscall.c
+++ b/tools/testing/selftests/x86/single_step_syscall.c
@@ -56,9 +56,11 @@ static volatile sig_atomic_t sig_traps;
#ifdef __x86_64__
# define REG_IP REG_RIP
# define WIDTH "q"
+# define INT80_CLOBBERS "r8", "r9", "r10", "r11"
#else
# define REG_IP REG_EIP
# define WIDTH "l"
+# define INT80_CLOBBERS
#endif
static unsigned long get_eflags(void)
@@ -140,7 +142,8 @@ int main()
printf("[RUN]\tSet TF and check int80\n");
set_eflags(get_eflags() | X86_EFLAGS_TF);
- asm volatile ("int $0x80" : "=a" (tmp) : "a" (SYS_getpid));
+ asm volatile ("int $0x80" : "=a" (tmp) : "a" (SYS_getpid)
+ : INT80_CLOBBERS);
check_result();
/*
diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
index 571b64a..8d1da1a 100644
--- a/virt/kvm/arm/vgic/vgic-its.c
+++ b/virt/kvm/arm/vgic/vgic-its.c
@@ -360,29 +360,6 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu)
return ret;
}
-static unsigned long vgic_mmio_read_its_ctlr(struct kvm *vcpu,
- struct vgic_its *its,
- gpa_t addr, unsigned int len)
-{
- u32 reg = 0;
-
- mutex_lock(&its->cmd_lock);
- if (its->creadr == its->cwriter)
- reg |= GITS_CTLR_QUIESCENT;
- if (its->enabled)
- reg |= GITS_CTLR_ENABLE;
- mutex_unlock(&its->cmd_lock);
-
- return reg;
-}
-
-static void vgic_mmio_write_its_ctlr(struct kvm *kvm, struct vgic_its *its,
- gpa_t addr, unsigned int len,
- unsigned long val)
-{
- its->enabled = !!(val & GITS_CTLR_ENABLE);
-}
-
static unsigned long vgic_mmio_read_its_typer(struct kvm *kvm,
struct vgic_its *its,
gpa_t addr, unsigned int len)
@@ -1161,33 +1138,16 @@ static void vgic_mmio_write_its_cbaser(struct kvm *kvm, struct vgic_its *its,
#define ITS_CMD_SIZE 32
#define ITS_CMD_OFFSET(reg) ((reg) & GENMASK(19, 5))
-/*
- * By writing to CWRITER the guest announces new commands to be processed.
- * To avoid any races in the first place, we take the its_cmd lock, which
- * protects our ring buffer variables, so that there is only one user
- * per ITS handling commands at a given time.
- */
-static void vgic_mmio_write_its_cwriter(struct kvm *kvm, struct vgic_its *its,
- gpa_t addr, unsigned int len,
- unsigned long val)
+/* Must be called with the cmd_lock held. */
+static void vgic_its_process_commands(struct kvm *kvm, struct vgic_its *its)
{
gpa_t cbaser;
u64 cmd_buf[4];
- u32 reg;
- if (!its)
+ /* Commands are only processed when the ITS is enabled. */
+ if (!its->enabled)
return;
- mutex_lock(&its->cmd_lock);
-
- reg = update_64bit_reg(its->cwriter, addr & 7, len, val);
- reg = ITS_CMD_OFFSET(reg);
- if (reg >= ITS_CMD_BUFFER_SIZE(its->cbaser)) {
- mutex_unlock(&its->cmd_lock);
- return;
- }
-
- its->cwriter = reg;
cbaser = CBASER_ADDRESS(its->cbaser);
while (its->cwriter != its->creadr) {
@@ -1207,6 +1167,34 @@ static void vgic_mmio_write_its_cwriter(struct kvm *kvm, struct vgic_its *its,
if (its->creadr == ITS_CMD_BUFFER_SIZE(its->cbaser))
its->creadr = 0;
}
+}
+
+/*
+ * By writing to CWRITER the guest announces new commands to be processed.
+ * To avoid any races in the first place, we take the its_cmd lock, which
+ * protects our ring buffer variables, so that there is only one user
+ * per ITS handling commands at a given time.
+ */
+static void vgic_mmio_write_its_cwriter(struct kvm *kvm, struct vgic_its *its,
+ gpa_t addr, unsigned int len,
+ unsigned long val)
+{
+ u64 reg;
+
+ if (!its)
+ return;
+
+ mutex_lock(&its->cmd_lock);
+
+ reg = update_64bit_reg(its->cwriter, addr & 7, len, val);
+ reg = ITS_CMD_OFFSET(reg);
+ if (reg >= ITS_CMD_BUFFER_SIZE(its->cbaser)) {
+ mutex_unlock(&its->cmd_lock);
+ return;
+ }
+ its->cwriter = reg;
+
+ vgic_its_process_commands(kvm, its);
mutex_unlock(&its->cmd_lock);
}
@@ -1287,6 +1275,39 @@ static void vgic_mmio_write_its_baser(struct kvm *kvm,
*regptr = reg;
}
+static unsigned long vgic_mmio_read_its_ctlr(struct kvm *vcpu,
+ struct vgic_its *its,
+ gpa_t addr, unsigned int len)
+{
+ u32 reg = 0;
+
+ mutex_lock(&its->cmd_lock);
+ if (its->creadr == its->cwriter)
+ reg |= GITS_CTLR_QUIESCENT;
+ if (its->enabled)
+ reg |= GITS_CTLR_ENABLE;
+ mutex_unlock(&its->cmd_lock);
+
+ return reg;
+}
+
+static void vgic_mmio_write_its_ctlr(struct kvm *kvm, struct vgic_its *its,
+ gpa_t addr, unsigned int len,
+ unsigned long val)
+{
+ mutex_lock(&its->cmd_lock);
+
+ its->enabled = !!(val & GITS_CTLR_ENABLE);
+
+ /*
+ * Try to process any pending commands. This function bails out early
+ * if the ITS is disabled or no commands have been queued.
+ */
+ vgic_its_process_commands(kvm, its);
+
+ mutex_unlock(&its->cmd_lock);
+}
+
#define REGISTER_ITS_DESC(off, rd, wr, length, acc) \
{ \
.reg_offset = off, \
diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c
index 3654b4c..2a5db13 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.c
+++ b/virt/kvm/arm/vgic/vgic-mmio.c
@@ -180,21 +180,37 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu,
static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
bool new_active_state)
{
+ struct kvm_vcpu *requester_vcpu;
spin_lock(&irq->irq_lock);
+
+ /*
+ * The vcpu parameter here can mean multiple things depending on how
+ * this function is called; when handling a trap from the kernel it
+ * depends on the GIC version, and these functions are also called as
+ * part of save/restore from userspace.
+ *
+ * Therefore, we have to figure out the requester in a reliable way.
+ *
+ * When accessing VGIC state from user space, the requester_vcpu is
+ * NULL, which is fine, because we guarantee that no VCPUs are running
+ * when accessing VGIC state from user space so irq->vcpu->cpu is
+ * always -1.
+ */
+ requester_vcpu = kvm_arm_get_running_vcpu();
+
/*
* If this virtual IRQ was written into a list register, we
* have to make sure the CPU that runs the VCPU thread has
- * synced back LR state to the struct vgic_irq. We can only
- * know this for sure, when either this irq is not assigned to
- * anyone's AP list anymore, or the VCPU thread is not
- * running on any CPUs.
+ * synced back the LR state to the struct vgic_irq.
*
- * In the opposite case, we know the VCPU thread may be on its
- * way back from the guest and still has to sync back this
- * IRQ, so we release and re-acquire the spin_lock to let the
- * other thread sync back the IRQ.
+ * As long as the conditions below are true, we know the VCPU thread
+ * may be on its way back from the guest (we kicked the VCPU thread in
+ * vgic_change_active_prepare) and still has to sync back this IRQ,
+ * so we release and re-acquire the spin_lock to let the other thread
+ * sync back the IRQ.
*/
while (irq->vcpu && /* IRQ may have state in an LR somewhere */
+ irq->vcpu != requester_vcpu && /* Current thread is not the VCPU thread */
irq->vcpu->cpu != -1) /* VCPU thread is running */
cond_resched_lock(&irq->irq_lock);
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index edc6ee2..be0f4c3 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -229,10 +229,13 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu)
/*
* If we are emulating a GICv3, we do it in an non-GICv2-compatible
* way, so we force SRE to 1 to demonstrate this to the guest.
+ * Also, we don't support any form of IRQ/FIQ bypass.
* This goes with the spec allowing the value to be RAO/WI.
*/
if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
- vgic_v3->vgic_sre = ICC_SRE_EL1_SRE;
+ vgic_v3->vgic_sre = (ICC_SRE_EL1_DIB |
+ ICC_SRE_EL1_DFB |
+ ICC_SRE_EL1_SRE);
vcpu->arch.vgic_cpu.pendbaser = INITIAL_PENDBASER_VALUE;
} else {
vgic_v3->vgic_sre = 0;
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index a29786d..4d28a9d 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -870,7 +870,8 @@ kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx,
continue;
kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
- kvm->buses[bus_idx]->ioeventfd_count--;
+ if (kvm->buses[bus_idx])
+ kvm->buses[bus_idx]->ioeventfd_count--;
ioeventfd_release(p);
ret = 0;
break;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index a17d787..88257b3 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -727,8 +727,11 @@ static void kvm_destroy_vm(struct kvm *kvm)
list_del(&kvm->vm_list);
spin_unlock(&kvm_lock);
kvm_free_irq_routing(kvm);
- for (i = 0; i < KVM_NR_BUSES; i++)
- kvm_io_bus_destroy(kvm->buses[i]);
+ for (i = 0; i < KVM_NR_BUSES; i++) {
+ if (kvm->buses[i])
+ kvm_io_bus_destroy(kvm->buses[i]);
+ kvm->buses[i] = NULL;
+ }
kvm_coalesced_mmio_free(kvm);
#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm);
@@ -1062,7 +1065,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
* changes) is disallowed above, so any other attribute changes getting
* here can be skipped.
*/
- if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) {
+ if (as_id == 0 && (change == KVM_MR_CREATE || change == KVM_MR_MOVE)) {
r = kvm_iommu_map_pages(kvm, &new);
return r;
}
@@ -3474,6 +3477,8 @@ int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
};
bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+ if (!bus)
+ return -ENOMEM;
r = __kvm_io_bus_write(vcpu, bus, &range, val);
return r < 0 ? r : 0;
}
@@ -3491,6 +3496,8 @@ int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx,
};
bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+ if (!bus)
+ return -ENOMEM;
/* First try the device referenced by cookie. */
if ((cookie >= 0) && (cookie < bus->dev_count) &&
@@ -3541,6 +3548,8 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
};
bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+ if (!bus)
+ return -ENOMEM;
r = __kvm_io_bus_read(vcpu, bus, &range, val);
return r < 0 ? r : 0;
}
@@ -3553,6 +3562,9 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
struct kvm_io_bus *new_bus, *bus;
bus = kvm->buses[bus_idx];
+ if (!bus)
+ return -ENOMEM;
+
/* exclude ioeventfd which is limited by maximum fd */
if (bus->dev_count - bus->ioeventfd_count > NR_IOBUS_DEVS - 1)
return -ENOSPC;
@@ -3572,37 +3584,41 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
}
/* Caller must hold slots_lock. */
-int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
- struct kvm_io_device *dev)
+void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
+ struct kvm_io_device *dev)
{
- int i, r;
+ int i;
struct kvm_io_bus *new_bus, *bus;
bus = kvm->buses[bus_idx];
- r = -ENOENT;
+ if (!bus)
+ return;
+
for (i = 0; i < bus->dev_count; i++)
if (bus->range[i].dev == dev) {
- r = 0;
break;
}
- if (r)
- return r;
+ if (i == bus->dev_count)
+ return;
new_bus = kmalloc(sizeof(*bus) + ((bus->dev_count - 1) *
sizeof(struct kvm_io_range)), GFP_KERNEL);
- if (!new_bus)
- return -ENOMEM;
+ if (!new_bus) {
+ pr_err("kvm: failed to shrink bus, removing it completely\n");
+ goto broken;
+ }
memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range));
new_bus->dev_count--;
memcpy(new_bus->range + i, bus->range + i + 1,
(new_bus->dev_count - i) * sizeof(struct kvm_io_range));
+broken:
rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
synchronize_srcu_expedited(&kvm->srcu);
kfree(bus);
- return r;
+ return;
}
struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
@@ -3615,6 +3631,8 @@ struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
srcu_idx = srcu_read_lock(&kvm->srcu);
bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
+ if (!bus)
+ goto out_unlock;
dev_idx = kvm_io_bus_get_first_dev(bus, addr, 1);
if (dev_idx < 0)