Merge tag 'for-linus-4.5-2' of git://git.code.sf.net/p/openipmi/linux-ipmi
Pull IPMI fix from Corey Minyard:
"Fix a compile error on IPMI when ACPI is disabled"
* tag 'for-linus-4.5-2' of git://git.code.sf.net/p/openipmi/linux-ipmi:
ipmi: put acpi.h with the other headers
diff --git a/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt b/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt
index 451fef2..10587bd 100644
--- a/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt
+++ b/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt
@@ -68,7 +68,7 @@
phy1: ethernet-phy@1 {
max-speed = <1000>;
reg = <0x1>;
- compatible = "brcm,28nm-gphy", "ethernet-phy-ieee802.3-c22";
+ compatible = "ethernet-phy-ieee802.3-c22";
};
};
};
@@ -115,7 +115,7 @@
phy0: ethernet-phy@0 {
max-speed = <1000>;
reg = <0x0>;
- compatible = "brcm,bcm53125", "ethernet-phy-ieee802.3-c22";
+ compatible = "ethernet-phy-ieee802.3-c22";
};
};
};
diff --git a/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt b/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt
index 80411b2..ecacfa4 100644
--- a/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt
+++ b/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt
@@ -4,8 +4,6 @@
- compatible: should be "hisilicon,hns-dsaf-v1" or "hisilicon,hns-dsaf-v2".
"hisilicon,hns-dsaf-v1" is for hip05.
"hisilicon,hns-dsaf-v2" is for Hi1610 and Hi1612.
-- dsa-name: dsa fabric name who provide this interface.
- should be "dsafX", X is the dsaf id.
- mode: dsa fabric mode string. only support one of dsaf modes like these:
"2port-64vf",
"6port-16rss",
@@ -26,9 +24,8 @@
Example:
-dsa: dsa@c7000000 {
+dsaf0: dsa@c7000000 {
compatible = "hisilicon,hns-dsaf-v1";
- dsa_name = "dsaf0";
mode = "6port-16rss";
interrupt-parent = <&mbigen_dsa>;
reg = <0x0 0xC0000000 0x0 0x420000
diff --git a/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt b/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt
index 41d19be..e6a9d1c 100644
--- a/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt
+++ b/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt
@@ -4,8 +4,9 @@
- compatible: "hisilicon,hns-nic-v1" or "hisilicon,hns-nic-v2".
"hisilicon,hns-nic-v1" is for hip05.
"hisilicon,hns-nic-v2" is for Hi1610 and Hi1612.
-- ae-name: accelerator name who provides this interface,
- is simply a name referring to the name of name in the accelerator node.
+- ae-handle: accelerator engine handle for hns,
+ specifies a reference to the associating hardware driver node.
+ see Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt
- port-id: is the index of port provided by DSAF (the accelerator). DSAF can
connect to 8 PHYs. Port 0 to 1 are both used for adminstration purpose. They
are called debug ports.
@@ -41,7 +42,7 @@
ethernet@0{
compatible = "hisilicon,hns-nic-v1";
- ae-name = "dsaf0";
+ ae-handle = <&dsaf0>;
port-id = <0>;
local-mac-address = [a2 14 e4 4b 56 76];
};
diff --git a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
index aeea50c..d0cb869 100644
--- a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
+++ b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
@@ -6,12 +6,17 @@
- interrupts: interrupt for the device
- phy: See ethernet.txt file in the same directory.
- phy-mode: See ethernet.txt file in the same directory
-- clocks: a pointer to the reference clock for this device.
+- clocks: List of clocks for this device. At least one clock is
+ mandatory for the core clock. If several clocks are given, then the
+ clock-names property must be used to identify them.
Optional properties:
- tx-csum-limit: maximum mtu supported by port that allow TX checksum.
Value is presented in bytes. If not used, by default 1600B is set for
"marvell,armada-370-neta" and 9800B for others.
+- clock-names: List of names corresponding to clocks property; shall be
+ "core" for core clock and "bus" for the optional bus clock.
+
Example:
diff --git a/Documentation/devicetree/bindings/net/mdio-mux-gpio.txt b/Documentation/devicetree/bindings/net/mdio-mux-gpio.txt
index 7938411..694987d 100644
--- a/Documentation/devicetree/bindings/net/mdio-mux-gpio.txt
+++ b/Documentation/devicetree/bindings/net/mdio-mux-gpio.txt
@@ -38,7 +38,6 @@
phy11: ethernet-phy@1 {
reg = <1>;
- compatible = "marvell,88e1149r";
marvell,reg-init = <3 0x10 0 0x5777>,
<3 0x11 0 0x00aa>,
<3 0x12 0 0x4105>,
@@ -48,7 +47,6 @@
};
phy12: ethernet-phy@2 {
reg = <2>;
- compatible = "marvell,88e1149r";
marvell,reg-init = <3 0x10 0 0x5777>,
<3 0x11 0 0x00aa>,
<3 0x12 0 0x4105>,
@@ -58,7 +56,6 @@
};
phy13: ethernet-phy@3 {
reg = <3>;
- compatible = "marvell,88e1149r";
marvell,reg-init = <3 0x10 0 0x5777>,
<3 0x11 0 0x00aa>,
<3 0x12 0 0x4105>,
@@ -68,7 +65,6 @@
};
phy14: ethernet-phy@4 {
reg = <4>;
- compatible = "marvell,88e1149r";
marvell,reg-init = <3 0x10 0 0x5777>,
<3 0x11 0 0x00aa>,
<3 0x12 0 0x4105>,
@@ -85,7 +81,6 @@
phy21: ethernet-phy@1 {
reg = <1>;
- compatible = "marvell,88e1149r";
marvell,reg-init = <3 0x10 0 0x5777>,
<3 0x11 0 0x00aa>,
<3 0x12 0 0x4105>,
@@ -95,7 +90,6 @@
};
phy22: ethernet-phy@2 {
reg = <2>;
- compatible = "marvell,88e1149r";
marvell,reg-init = <3 0x10 0 0x5777>,
<3 0x11 0 0x00aa>,
<3 0x12 0 0x4105>,
@@ -105,7 +99,6 @@
};
phy23: ethernet-phy@3 {
reg = <3>;
- compatible = "marvell,88e1149r";
marvell,reg-init = <3 0x10 0 0x5777>,
<3 0x11 0 0x00aa>,
<3 0x12 0 0x4105>,
@@ -115,7 +108,6 @@
};
phy24: ethernet-phy@4 {
reg = <4>;
- compatible = "marvell,88e1149r";
marvell,reg-init = <3 0x10 0 0x5777>,
<3 0x11 0 0x00aa>,
<3 0x12 0 0x4105>,
diff --git a/Documentation/devicetree/bindings/net/mdio-mux.txt b/Documentation/devicetree/bindings/net/mdio-mux.txt
index f65606f..491f5bd 100644
--- a/Documentation/devicetree/bindings/net/mdio-mux.txt
+++ b/Documentation/devicetree/bindings/net/mdio-mux.txt
@@ -47,7 +47,6 @@
phy11: ethernet-phy@1 {
reg = <1>;
- compatible = "marvell,88e1149r";
marvell,reg-init = <3 0x10 0 0x5777>,
<3 0x11 0 0x00aa>,
<3 0x12 0 0x4105>,
@@ -57,7 +56,6 @@
};
phy12: ethernet-phy@2 {
reg = <2>;
- compatible = "marvell,88e1149r";
marvell,reg-init = <3 0x10 0 0x5777>,
<3 0x11 0 0x00aa>,
<3 0x12 0 0x4105>,
@@ -67,7 +65,6 @@
};
phy13: ethernet-phy@3 {
reg = <3>;
- compatible = "marvell,88e1149r";
marvell,reg-init = <3 0x10 0 0x5777>,
<3 0x11 0 0x00aa>,
<3 0x12 0 0x4105>,
@@ -77,7 +74,6 @@
};
phy14: ethernet-phy@4 {
reg = <4>;
- compatible = "marvell,88e1149r";
marvell,reg-init = <3 0x10 0 0x5777>,
<3 0x11 0 0x00aa>,
<3 0x12 0 0x4105>,
@@ -94,7 +90,6 @@
phy21: ethernet-phy@1 {
reg = <1>;
- compatible = "marvell,88e1149r";
marvell,reg-init = <3 0x10 0 0x5777>,
<3 0x11 0 0x00aa>,
<3 0x12 0 0x4105>,
@@ -104,7 +99,6 @@
};
phy22: ethernet-phy@2 {
reg = <2>;
- compatible = "marvell,88e1149r";
marvell,reg-init = <3 0x10 0 0x5777>,
<3 0x11 0 0x00aa>,
<3 0x12 0 0x4105>,
@@ -114,7 +108,6 @@
};
phy23: ethernet-phy@3 {
reg = <3>;
- compatible = "marvell,88e1149r";
marvell,reg-init = <3 0x10 0 0x5777>,
<3 0x11 0 0x00aa>,
<3 0x12 0 0x4105>,
@@ -124,7 +117,6 @@
};
phy24: ethernet-phy@4 {
reg = <4>;
- compatible = "marvell,88e1149r";
marvell,reg-init = <3 0x10 0 0x5777>,
<3 0x11 0 0x00aa>,
<3 0x12 0 0x4105>,
diff --git a/Documentation/devicetree/bindings/net/phy.txt b/Documentation/devicetree/bindings/net/phy.txt
index 525e165..bc1c3c8 100644
--- a/Documentation/devicetree/bindings/net/phy.txt
+++ b/Documentation/devicetree/bindings/net/phy.txt
@@ -17,8 +17,7 @@
"ethernet-phy-ieee802.3-c22" or "ethernet-phy-ieee802.3-c45" for
PHYs that implement IEEE802.3 clause 22 or IEEE802.3 clause 45
specifications. If neither of these are specified, the default is to
- assume clause 22. The compatible list may also contain other
- elements.
+ assume clause 22.
If the phy's identifier is known then the list may contain an entry
of the form: "ethernet-phy-idAAAA.BBBB" where
@@ -28,6 +27,9 @@
4 hex digits. This is the chip vendor OUI bits 19:24,
followed by 10 bits of a vendor specific ID.
+ The compatible list should not contain other values than those
+ listed here.
+
- max-speed: Maximum PHY supported speed (10, 100, 1000...)
- broken-turn-around: If set, indicates the PHY device does not correctly
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index ceb44a0..73b36d7 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -594,7 +594,7 @@
tcp_syn_retries - INTEGER
Number of times initial SYNs for an active TCP connection attempt
- will be retransmitted. Should not be higher than 255. Default value
+ will be retransmitted. Should not be higher than 127. Default value
is 6, which corresponds to 63seconds till the last retransmission
with the current initial RTO of 1second. With this the final timeout
for an active TCP connection attempt will happen after 127seconds.
diff --git a/MAINTAINERS b/MAINTAINERS
index 30aca4a..c245e42 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -967,6 +967,8 @@
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
F: arch/arm/mach-highbank/
+F: arch/arm/boot/dts/highbank.dts
+F: arch/arm/boot/dts/ecx-*.dts*
ARM/CAVIUM NETWORKS CNS3XXX MACHINE SUPPORT
M: Krzysztof Halasa <khalasa@piap.pl>
@@ -1042,6 +1044,7 @@
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
T: git git://git.kernel.org/pub/scm/linux/kernel/git/baohua/linux.git
S: Maintained
+F: arch/arm/boot/dts/prima2*
F: arch/arm/mach-prima2/
F: drivers/clk/sirf/
F: drivers/clocksource/timer-prima2.c
@@ -1143,6 +1146,10 @@
S: Supported
T: git git://github.com/hisilicon/linux-hisi.git
F: arch/arm/mach-hisi/
+F: arch/arm/boot/dts/hi3*
+F: arch/arm/boot/dts/hip*
+F: arch/arm/boot/dts/hisi*
+F: arch/arm64/boot/dts/hisilicon/
ARM/HP JORNADA 7XX MACHINE SUPPORT
M: Kristoffer Ericson <kristoffer.ericson@gmail.com>
@@ -1219,6 +1226,7 @@
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
F: arch/arm/mach-keystone/
+F: arch/arm/boot/dts/k2*
T: git git://git.kernel.org/pub/scm/linux/kernel/git/ssantosh/linux-keystone.git
ARM/TEXAS INSTRUMENT KEYSTONE CLOCK FRAMEWORK
@@ -1287,6 +1295,7 @@
S: Maintained
F: arch/arm/mach-berlin/
F: arch/arm/boot/dts/berlin*
+F: arch/arm64/boot/dts/marvell/berlin*
ARM/Marvell Dove/MV78xx0/Orion SOC support
@@ -1425,6 +1434,7 @@
F: arch/arm/boot/dts/qcom-*.dts
F: arch/arm/boot/dts/qcom-*.dtsi
F: arch/arm/mach-qcom/
+F: arch/arm64/boot/dts/qcom/*
F: drivers/soc/qcom/
F: drivers/tty/serial/msm_serial.h
F: drivers/tty/serial/msm_serial.c
@@ -1484,6 +1494,8 @@
L: linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
S: Maintained
F: arch/arm/boot/dts/s3c*
+F: arch/arm/boot/dts/s5p*
+F: arch/arm/boot/dts/samsung*
F: arch/arm/boot/dts/exynos*
F: arch/arm64/boot/dts/exynos/
F: arch/arm/plat-samsung/
@@ -1563,6 +1575,7 @@
F: arch/arm/mach-socfpga/
F: arch/arm/boot/dts/socfpga*
F: arch/arm/configs/socfpga_defconfig
+F: arch/arm64/boot/dts/altera/
W: http://www.rocketboards.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/dinguyen/linux.git
@@ -1716,7 +1729,7 @@
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
F: arch/arm/boot/dts/vexpress*
-F: arch/arm64/boot/dts/arm/vexpress*
+F: arch/arm64/boot/dts/arm/
F: arch/arm/mach-vexpress/
F: */*/vexpress*
F: */*/*/vexpress*
@@ -2343,6 +2356,7 @@
F: arch/arm/boot/dts/bcm113*
F: arch/arm/boot/dts/bcm216*
F: arch/arm/boot/dts/bcm281*
+F: arch/arm64/boot/dts/broadcom/
F: arch/arm/configs/bcm_defconfig
F: drivers/mmc/host/sdhci-bcm-kona.c
F: drivers/clocksource/bcm_kona_timer.c
@@ -8818,6 +8832,7 @@
T: git git://github.com/hzhuang1/linux.git
T: git git://github.com/rjarzmik/linux.git
S: Maintained
+F: arch/arm/boot/dts/pxa*
F: arch/arm/mach-pxa/
F: drivers/dma/pxa*
F: drivers/pcmcia/pxa2xx*
@@ -8847,6 +8862,7 @@
T: git git://github.com/hzhuang1/linux.git
T: git git://git.linaro.org/people/ycmiao/pxa-linux.git
S: Maintained
+F: arch/arm/boot/dts/mmp*
F: arch/arm/mach-mmp/
PXA MMCI DRIVER
@@ -10173,7 +10189,7 @@
SONICS SILICON BACKPLANE DRIVER (SSB)
M: Michael Buesch <m@bues.ch>
-L: netdev@vger.kernel.org
+L: linux-wireless@vger.kernel.org
S: Maintained
F: drivers/ssb/
F: include/linux/ssb/
@@ -10291,6 +10307,7 @@
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
W: http://www.st.com/spear
S: Maintained
+F: arch/arm/boot/dts/spear*
F: arch/arm/mach-spear/
SPEAR CLOCK FRAMEWORK SUPPORT
diff --git a/Makefile b/Makefile
index c65fe37..6c1a3c2 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
VERSION = 4
PATCHLEVEL = 5
SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
NAME = Blurry Fish Butt
# *DOCUMENTATION*
diff --git a/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi b/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi
index da7b6e6..933cba3 100644
--- a/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi
+++ b/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi
@@ -23,9 +23,8 @@
};
};
- dsa: dsa@c7000000 {
+ dsaf0: dsa@c7000000 {
compatible = "hisilicon,hns-dsaf-v1";
- dsa_name = "dsaf0";
mode = "6port-16rss";
interrupt-parent = <&mbigen_dsa>;
@@ -127,7 +126,7 @@
eth0: ethernet@0{
compatible = "hisilicon,hns-nic-v1";
- ae-name = "dsaf0";
+ ae-handle = <&dsaf0>;
port-id = <0>;
local-mac-address = [00 00 00 01 00 58];
status = "disabled";
@@ -135,14 +134,14 @@
};
eth1: ethernet@1{
compatible = "hisilicon,hns-nic-v1";
- ae-name = "dsaf0";
+ ae-handle = <&dsaf0>;
port-id = <1>;
status = "disabled";
dma-coherent;
};
eth2: ethernet@2{
compatible = "hisilicon,hns-nic-v1";
- ae-name = "dsaf0";
+ ae-handle = <&dsaf0>;
port-id = <2>;
local-mac-address = [00 00 00 01 00 5a];
status = "disabled";
@@ -150,7 +149,7 @@
};
eth3: ethernet@3{
compatible = "hisilicon,hns-nic-v1";
- ae-name = "dsaf0";
+ ae-handle = <&dsaf0>;
port-id = <3>;
local-mac-address = [00 00 00 01 00 5b];
status = "disabled";
@@ -158,7 +157,7 @@
};
eth4: ethernet@4{
compatible = "hisilicon,hns-nic-v1";
- ae-name = "dsaf0";
+ ae-handle = <&dsaf0>;
port-id = <4>;
local-mac-address = [00 00 00 01 00 5c];
status = "disabled";
@@ -166,7 +165,7 @@
};
eth5: ethernet@5{
compatible = "hisilicon,hns-nic-v1";
- ae-name = "dsaf0";
+ ae-handle = <&dsaf0>;
port-id = <5>;
local-mac-address = [00 00 00 01 00 5d];
status = "disabled";
@@ -174,7 +173,7 @@
};
eth6: ethernet@6{
compatible = "hisilicon,hns-nic-v1";
- ae-name = "dsaf0";
+ ae-handle = <&dsaf0>;
port-id = <6>;
local-mac-address = [00 00 00 01 00 5e];
status = "disabled";
@@ -182,7 +181,7 @@
};
eth7: ethernet@7{
compatible = "hisilicon,hns-nic-v1";
- ae-name = "dsaf0";
+ ae-handle = <&dsaf0>;
port-id = <7>;
local-mac-address = [00 00 00 01 00 5f];
status = "disabled";
diff --git a/arch/mips/bcm63xx/nvram.c b/arch/mips/bcm63xx/nvram.c
index 5f2bc1e..05757ae 100644
--- a/arch/mips/bcm63xx/nvram.c
+++ b/arch/mips/bcm63xx/nvram.c
@@ -19,6 +19,8 @@
#include <bcm63xx_nvram.h>
+#define BCM63XX_DEFAULT_PSI_SIZE 64
+
static struct bcm963xx_nvram nvram;
static int mac_addr_used;
@@ -85,3 +87,12 @@
return 0;
}
EXPORT_SYMBOL(bcm63xx_nvram_get_mac_address);
+
+int bcm63xx_nvram_get_psi_size(void)
+{
+ if (nvram.psi_size > 0)
+ return nvram.psi_size;
+
+ return BCM63XX_DEFAULT_PSI_SIZE;
+}
+EXPORT_SYMBOL(bcm63xx_nvram_get_psi_size);
diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h
index 4e0b6bc..348df49 100644
--- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h
+++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h
@@ -30,4 +30,6 @@
*/
int bcm63xx_nvram_get_mac_address(u8 *mac);
+int bcm63xx_nvram_get_psi_size(void);
+
#endif /* BCM63XX_NVRAM_H */
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 330e738..9af2e63 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -509,11 +509,10 @@
config X86_INTEL_MID
bool "Intel MID platform support"
- depends on X86_32
depends on X86_EXTENDED_PLATFORM
depends on X86_PLATFORM_DEVICES
depends on PCI
- depends on PCI_GOANY
+ depends on X86_64 || (PCI_GOANY && X86_32)
depends on X86_IO_APIC
select SFI
select I2C
diff --git a/arch/x86/crypto/chacha20-ssse3-x86_64.S b/arch/x86/crypto/chacha20-ssse3-x86_64.S
index 712b130..3a33124 100644
--- a/arch/x86/crypto/chacha20-ssse3-x86_64.S
+++ b/arch/x86/crypto/chacha20-ssse3-x86_64.S
@@ -157,7 +157,9 @@
# done with the slightly better performing SSSE3 byte shuffling,
# 7/12-bit word rotation uses traditional shift+OR.
- sub $0x40,%rsp
+ mov %rsp,%r11
+ sub $0x80,%rsp
+ and $~63,%rsp
# x0..15[0-3] = s0..3[0..3]
movq 0x00(%rdi),%xmm1
@@ -620,6 +622,6 @@
pxor %xmm1,%xmm15
movdqu %xmm15,0xf0(%rsi)
- add $0x40,%rsp
+ mov %r11,%rsp
ret
ENDPROC(chacha20_4block_xor_ssse3)
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 881b476..e7de5c9 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -23,11 +23,13 @@
#define __ARCH_HAS_DO_SOFTIRQ
+struct irq_desc;
+
#ifdef CONFIG_HOTPLUG_CPU
#include <linux/cpumask.h>
extern int check_irq_vectors_for_cpu_disable(void);
extern void fixup_irqs(void);
-extern void irq_force_complete_move(int);
+extern void irq_force_complete_move(struct irq_desc *desc);
#endif
#ifdef CONFIG_HAVE_KVM
@@ -37,7 +39,6 @@
extern void (*x86_platform_ipi_callback)(void);
extern void native_init_IRQ(void);
-struct irq_desc;
extern bool handle_irq(struct irq_desc *desc, struct pt_regs *regs);
extern __visible unsigned int do_IRQ(struct pt_regs *regs);
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 04c27a0..4432ab7 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -366,20 +366,18 @@
}
static inline pgprot_t pgprot_4k_2_large(pgprot_t pgprot)
{
+ pgprotval_t val = pgprot_val(pgprot);
pgprot_t new;
- unsigned long val;
- val = pgprot_val(pgprot);
pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) |
((val & _PAGE_PAT) << (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT));
return new;
}
static inline pgprot_t pgprot_large_2_4k(pgprot_t pgprot)
{
+ pgprotval_t val = pgprot_val(pgprot);
pgprot_t new;
- unsigned long val;
- val = pgprot_val(pgprot);
pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) |
((val & _PAGE_PAT_LARGE) >>
(_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT));
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index f253218..fdb0fbf 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2521,6 +2521,7 @@
{
int pin, ioapic, irq, irq_entry;
const struct cpumask *mask;
+ struct irq_desc *desc;
struct irq_data *idata;
struct irq_chip *chip;
@@ -2536,7 +2537,9 @@
if (irq < 0 || !mp_init_irq_at_boot(ioapic, irq))
continue;
- idata = irq_get_irq_data(irq);
+ desc = irq_to_desc(irq);
+ raw_spin_lock_irq(&desc->lock);
+ idata = irq_desc_get_irq_data(desc);
/*
* Honour affinities which have been set in early boot
@@ -2550,6 +2553,7 @@
/* Might be lapic_chip for irq 0 */
if (chip->irq_set_affinity)
chip->irq_set_affinity(idata, mask, false);
+ raw_spin_unlock_irq(&desc->lock);
}
}
#endif
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 908cb37..3b670df 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -31,7 +31,7 @@
struct irq_domain *x86_vector_domain;
EXPORT_SYMBOL_GPL(x86_vector_domain);
static DEFINE_RAW_SPINLOCK(vector_lock);
-static cpumask_var_t vector_cpumask;
+static cpumask_var_t vector_cpumask, vector_searchmask, searched_cpumask;
static struct irq_chip lapic_controller;
#ifdef CONFIG_X86_IO_APIC
static struct apic_chip_data *legacy_irq_data[NR_IRQS_LEGACY];
@@ -118,35 +118,47 @@
*/
static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START;
static int current_offset = VECTOR_OFFSET_START % 16;
- int cpu, err;
+ int cpu, vector;
- if (d->move_in_progress)
+ /*
+ * If there is still a move in progress or the previous move has not
+ * been cleaned up completely, tell the caller to come back later.
+ */
+ if (d->move_in_progress ||
+ cpumask_intersects(d->old_domain, cpu_online_mask))
return -EBUSY;
/* Only try and allocate irqs on cpus that are present */
- err = -ENOSPC;
cpumask_clear(d->old_domain);
+ cpumask_clear(searched_cpumask);
cpu = cpumask_first_and(mask, cpu_online_mask);
while (cpu < nr_cpu_ids) {
- int new_cpu, vector, offset;
+ int new_cpu, offset;
+ /* Get the possible target cpus for @mask/@cpu from the apic */
apic->vector_allocation_domain(cpu, vector_cpumask, mask);
+ /*
+ * Clear the offline cpus from @vector_cpumask for searching
+ * and verify whether the result overlaps with @mask. If true,
+ * then the call to apic->cpu_mask_to_apicid_and() will
+ * succeed as well. If not, no point in trying to find a
+ * vector in this mask.
+ */
+ cpumask_and(vector_searchmask, vector_cpumask, cpu_online_mask);
+ if (!cpumask_intersects(vector_searchmask, mask))
+ goto next_cpu;
+
if (cpumask_subset(vector_cpumask, d->domain)) {
- err = 0;
if (cpumask_equal(vector_cpumask, d->domain))
- break;
+ goto success;
/*
- * New cpumask using the vector is a proper subset of
- * the current in use mask. So cleanup the vector
- * allocation for the members that are not used anymore.
+ * Mark the cpus which are not longer in the mask for
+ * cleanup.
*/
- cpumask_andnot(d->old_domain, d->domain,
- vector_cpumask);
- d->move_in_progress =
- cpumask_intersects(d->old_domain, cpu_online_mask);
- cpumask_and(d->domain, d->domain, vector_cpumask);
- break;
+ cpumask_andnot(d->old_domain, d->domain, vector_cpumask);
+ vector = d->cfg.vector;
+ goto update;
}
vector = current_vector;
@@ -158,45 +170,60 @@
vector = FIRST_EXTERNAL_VECTOR + offset;
}
- if (unlikely(current_vector == vector)) {
- cpumask_or(d->old_domain, d->old_domain,
- vector_cpumask);
- cpumask_andnot(vector_cpumask, mask, d->old_domain);
- cpu = cpumask_first_and(vector_cpumask,
- cpu_online_mask);
- continue;
- }
+ /* If the search wrapped around, try the next cpu */
+ if (unlikely(current_vector == vector))
+ goto next_cpu;
if (test_bit(vector, used_vectors))
goto next;
- for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) {
+ for_each_cpu(new_cpu, vector_searchmask) {
if (!IS_ERR_OR_NULL(per_cpu(vector_irq, new_cpu)[vector]))
goto next;
}
/* Found one! */
current_vector = vector;
current_offset = offset;
- if (d->cfg.vector) {
+ /* Schedule the old vector for cleanup on all cpus */
+ if (d->cfg.vector)
cpumask_copy(d->old_domain, d->domain);
- d->move_in_progress =
- cpumask_intersects(d->old_domain, cpu_online_mask);
- }
- for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask)
+ for_each_cpu(new_cpu, vector_searchmask)
per_cpu(vector_irq, new_cpu)[vector] = irq_to_desc(irq);
- d->cfg.vector = vector;
- cpumask_copy(d->domain, vector_cpumask);
- err = 0;
- break;
- }
+ goto update;
- if (!err) {
- /* cache destination APIC IDs into cfg->dest_apicid */
- err = apic->cpu_mask_to_apicid_and(mask, d->domain,
- &d->cfg.dest_apicid);
+next_cpu:
+ /*
+ * We exclude the current @vector_cpumask from the requested
+ * @mask and try again with the next online cpu in the
+ * result. We cannot modify @mask, so we use @vector_cpumask
+ * as a temporary buffer here as it will be reassigned when
+ * calling apic->vector_allocation_domain() above.
+ */
+ cpumask_or(searched_cpumask, searched_cpumask, vector_cpumask);
+ cpumask_andnot(vector_cpumask, mask, searched_cpumask);
+ cpu = cpumask_first_and(vector_cpumask, cpu_online_mask);
+ continue;
}
+ return -ENOSPC;
- return err;
+update:
+ /*
+ * Exclude offline cpus from the cleanup mask and set the
+ * move_in_progress flag when the result is not empty.
+ */
+ cpumask_and(d->old_domain, d->old_domain, cpu_online_mask);
+ d->move_in_progress = !cpumask_empty(d->old_domain);
+ d->cfg.vector = vector;
+ cpumask_copy(d->domain, vector_cpumask);
+success:
+ /*
+ * Cache destination APIC IDs into cfg->dest_apicid. This cannot fail
+ * as we already established, that mask & d->domain & cpu_online_mask
+ * is not empty.
+ */
+ BUG_ON(apic->cpu_mask_to_apicid_and(mask, d->domain,
+ &d->cfg.dest_apicid));
+ return 0;
}
static int assign_irq_vector(int irq, struct apic_chip_data *data,
@@ -226,10 +253,8 @@
static void clear_irq_vector(int irq, struct apic_chip_data *data)
{
struct irq_desc *desc;
- unsigned long flags;
int cpu, vector;
- raw_spin_lock_irqsave(&vector_lock, flags);
BUG_ON(!data->cfg.vector);
vector = data->cfg.vector;
@@ -239,10 +264,13 @@
data->cfg.vector = 0;
cpumask_clear(data->domain);
- if (likely(!data->move_in_progress)) {
- raw_spin_unlock_irqrestore(&vector_lock, flags);
+ /*
+ * If move is in progress or the old_domain mask is not empty,
+ * i.e. the cleanup IPI has not been processed yet, we need to remove
+ * the old references to desc from all cpus vector tables.
+ */
+ if (!data->move_in_progress && cpumask_empty(data->old_domain))
return;
- }
desc = irq_to_desc(irq);
for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) {
@@ -255,7 +283,6 @@
}
}
data->move_in_progress = 0;
- raw_spin_unlock_irqrestore(&vector_lock, flags);
}
void init_irq_alloc_info(struct irq_alloc_info *info,
@@ -276,19 +303,24 @@
static void x86_vector_free_irqs(struct irq_domain *domain,
unsigned int virq, unsigned int nr_irqs)
{
+ struct apic_chip_data *apic_data;
struct irq_data *irq_data;
+ unsigned long flags;
int i;
for (i = 0; i < nr_irqs; i++) {
irq_data = irq_domain_get_irq_data(x86_vector_domain, virq + i);
if (irq_data && irq_data->chip_data) {
+ raw_spin_lock_irqsave(&vector_lock, flags);
clear_irq_vector(virq + i, irq_data->chip_data);
- free_apic_chip_data(irq_data->chip_data);
+ apic_data = irq_data->chip_data;
+ irq_domain_reset_irq_data(irq_data);
+ raw_spin_unlock_irqrestore(&vector_lock, flags);
+ free_apic_chip_data(apic_data);
#ifdef CONFIG_X86_IO_APIC
if (virq + i < nr_legacy_irqs())
legacy_irq_data[virq + i] = NULL;
#endif
- irq_domain_reset_irq_data(irq_data);
}
}
}
@@ -406,6 +438,8 @@
arch_init_htirq_domain(x86_vector_domain);
BUG_ON(!alloc_cpumask_var(&vector_cpumask, GFP_KERNEL));
+ BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL));
+ BUG_ON(!alloc_cpumask_var(&searched_cpumask, GFP_KERNEL));
return arch_early_ioapic_init();
}
@@ -494,14 +528,7 @@
return -EINVAL;
err = assign_irq_vector(irq, data, dest);
- if (err) {
- if (assign_irq_vector(irq, data,
- irq_data_get_affinity_mask(irq_data)))
- pr_err("Failed to recover vector for irq %d\n", irq);
- return err;
- }
-
- return IRQ_SET_MASK_OK;
+ return err ? err : IRQ_SET_MASK_OK;
}
static struct irq_chip lapic_controller = {
@@ -513,20 +540,12 @@
#ifdef CONFIG_SMP
static void __send_cleanup_vector(struct apic_chip_data *data)
{
- cpumask_var_t cleanup_mask;
-
- if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
- unsigned int i;
-
- for_each_cpu_and(i, data->old_domain, cpu_online_mask)
- apic->send_IPI_mask(cpumask_of(i),
- IRQ_MOVE_CLEANUP_VECTOR);
- } else {
- cpumask_and(cleanup_mask, data->old_domain, cpu_online_mask);
- apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
- free_cpumask_var(cleanup_mask);
- }
+ raw_spin_lock(&vector_lock);
+ cpumask_and(data->old_domain, data->old_domain, cpu_online_mask);
data->move_in_progress = 0;
+ if (!cpumask_empty(data->old_domain))
+ apic->send_IPI_mask(data->old_domain, IRQ_MOVE_CLEANUP_VECTOR);
+ raw_spin_unlock(&vector_lock);
}
void send_cleanup_vector(struct irq_cfg *cfg)
@@ -570,12 +589,25 @@
goto unlock;
/*
- * Check if the irq migration is in progress. If so, we
- * haven't received the cleanup request yet for this irq.
+ * Nothing to cleanup if irq migration is in progress
+ * or this cpu is not set in the cleanup mask.
*/
- if (data->move_in_progress)
+ if (data->move_in_progress ||
+ !cpumask_test_cpu(me, data->old_domain))
goto unlock;
+ /*
+ * We have two cases to handle here:
+ * 1) vector is unchanged but the target mask got reduced
+ * 2) vector and the target mask has changed
+ *
+ * #1 is obvious, but in #2 we have two vectors with the same
+ * irq descriptor: the old and the new vector. So we need to
+ * make sure that we only cleanup the old vector. The new
+ * vector has the current @vector number in the config and
+ * this cpu is part of the target mask. We better leave that
+ * one alone.
+ */
if (vector == data->cfg.vector &&
cpumask_test_cpu(me, data->domain))
goto unlock;
@@ -593,6 +625,7 @@
goto unlock;
}
__this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
+ cpumask_clear_cpu(me, data->old_domain);
unlock:
raw_spin_unlock(&desc->lock);
}
@@ -621,12 +654,48 @@
__irq_complete_move(cfg, ~get_irq_regs()->orig_ax);
}
-void irq_force_complete_move(int irq)
+/*
+ * Called with @desc->lock held and interrupts disabled.
+ */
+void irq_force_complete_move(struct irq_desc *desc)
{
- struct irq_cfg *cfg = irq_cfg(irq);
+ struct irq_data *irqdata = irq_desc_get_irq_data(desc);
+ struct apic_chip_data *data = apic_chip_data(irqdata);
+ struct irq_cfg *cfg = data ? &data->cfg : NULL;
- if (cfg)
- __irq_complete_move(cfg, cfg->vector);
+ if (!cfg)
+ return;
+
+ __irq_complete_move(cfg, cfg->vector);
+
+ /*
+ * This is tricky. If the cleanup of @data->old_domain has not been
+ * done yet, then the following setaffinity call will fail with
+ * -EBUSY. This can leave the interrupt in a stale state.
+ *
+ * The cleanup cannot make progress because we hold @desc->lock. So in
+ * case @data->old_domain is not yet cleaned up, we need to drop the
+ * lock and acquire it again. @desc cannot go away, because the
+ * hotplug code holds the sparse irq lock.
+ */
+ raw_spin_lock(&vector_lock);
+ /* Clean out all offline cpus (including ourself) first. */
+ cpumask_and(data->old_domain, data->old_domain, cpu_online_mask);
+ while (!cpumask_empty(data->old_domain)) {
+ raw_spin_unlock(&vector_lock);
+ raw_spin_unlock(&desc->lock);
+ cpu_relax();
+ raw_spin_lock(&desc->lock);
+ /*
+ * Reevaluate apic_chip_data. It might have been cleared after
+ * we dropped @desc->lock.
+ */
+ data = apic_chip_data(irqdata);
+ if (!data)
+ return;
+ raw_spin_lock(&vector_lock);
+ }
+ raw_spin_unlock(&vector_lock);
}
#endif
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index d760c6b..624db005 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -889,7 +889,10 @@
return;
}
pr_info("UV: Found %s hub\n", hub);
- map_low_mmrs();
+
+ /* We now only need to map the MMRs on UV1 */
+ if (is_uv1_hub())
+ map_low_mmrs();
m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR );
m_val = m_n_config.s.m_skt;
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index a667078..fed2ab1 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1960,7 +1960,8 @@
static int intel_alt_er(int idx, u64 config)
{
- int alt_idx;
+ int alt_idx = idx;
+
if (!(x86_pmu.flags & PMU_FL_HAS_RSP_1))
return idx;
@@ -2897,14 +2898,12 @@
return;
if (!(x86_pmu.flags & PMU_FL_NO_HT_SHARING)) {
- void **onln = &cpuc->kfree_on_online[X86_PERF_KFREE_SHARED];
-
for_each_cpu(i, topology_sibling_cpumask(cpu)) {
struct intel_shared_regs *pc;
pc = per_cpu(cpu_hw_events, i).shared_regs;
if (pc && pc->core_id == core_id) {
- *onln = cpuc->shared_regs;
+ cpuc->kfree_on_online[0] = cpuc->shared_regs;
cpuc->shared_regs = pc;
break;
}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index f97f807..3bf41d4 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -995,6 +995,9 @@
case 87: /* Knights Landing */
ret = knl_uncore_pci_init();
break;
+ case 94: /* SkyLake */
+ ret = skl_uncore_pci_init();
+ break;
default:
return 0;
}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 07aa2d6..a7086b8 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -336,6 +336,7 @@
int ivb_uncore_pci_init(void);
int hsw_uncore_pci_init(void);
int bdw_uncore_pci_init(void);
+int skl_uncore_pci_init(void);
void snb_uncore_cpu_init(void);
void nhm_uncore_cpu_init(void);
int snb_pci2phy_map_init(int devid);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
index 0b93482..2bd030d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
@@ -8,6 +8,7 @@
#define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00
#define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04
#define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604
+#define PCI_DEVICE_ID_INTEL_SKL_IMC 0x191f
/* SNB event control */
#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff
@@ -524,6 +525,14 @@
{ /* end: all zeroes */ },
};
+static const struct pci_device_id skl_uncore_pci_ids[] = {
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* end: all zeroes */ },
+};
+
static struct pci_driver snb_uncore_pci_driver = {
.name = "snb_uncore",
.id_table = snb_uncore_pci_ids,
@@ -544,6 +553,11 @@
.id_table = bdw_uncore_pci_ids,
};
+static struct pci_driver skl_uncore_pci_driver = {
+ .name = "skl_uncore",
+ .id_table = skl_uncore_pci_ids,
+};
+
struct imc_uncore_pci_dev {
__u32 pci_id;
struct pci_driver *driver;
@@ -558,6 +572,7 @@
IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core Processor */
IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core ULT Mobile Processor */
IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver), /* 5th Gen Core U */
+ IMC_DEV(SKL_IMC, &skl_uncore_pci_driver), /* 6th Gen Core */
{ /* end marker */ }
};
@@ -610,6 +625,11 @@
return imc_uncore_pci_init();
}
+int skl_uncore_pci_init(void)
+{
+ return imc_uncore_pci_init();
+}
+
/* end of Sandy Bridge uncore support */
/* Nehalem uncore support */
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index f129a9a..2c0f340 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -192,5 +192,13 @@
reserve_ebda_region();
+ switch (boot_params.hdr.hardware_subarch) {
+ case X86_SUBARCH_INTEL_MID:
+ x86_intel_mid_early_setup();
+ break;
+ default:
+ break;
+ }
+
start_kernel();
}
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index f8062aa..61521dc 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -462,7 +462,7 @@
* non intr-remapping case, we can't wait till this interrupt
* arrives at this cpu before completing the irq move.
*/
- irq_force_complete_move(irq);
+ irq_force_complete_move(desc);
if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
break_affinity = 1;
@@ -470,6 +470,15 @@
}
chip = irq_data_get_irq_chip(data);
+ /*
+ * The interrupt descriptor might have been cleaned up
+ * already, but it is not yet removed from the radix tree
+ */
+ if (!chip) {
+ raw_spin_unlock(&desc->lock);
+ continue;
+ }
+
if (!irqd_can_move_in_process_context(data) && chip->irq_mask)
chip->irq_mask(data);
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index fc6a4c8..2440814 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -33,7 +33,7 @@
pgd_t *pgd;
pgprot_t mask_set;
pgprot_t mask_clr;
- int numpages;
+ unsigned long numpages;
int flags;
unsigned long pfn;
unsigned force_split : 1;
@@ -1350,7 +1350,7 @@
* CPA operation. Either a large page has been
* preserved or a single page update happened.
*/
- BUG_ON(cpa->numpages > numpages);
+ BUG_ON(cpa->numpages > numpages || !cpa->numpages);
numpages -= cpa->numpages;
if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY))
cpa->curpage++;
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 1c7380d..2d66db8 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -8,6 +8,7 @@
#include <linux/memblock.h>
#include <linux/bootmem.h>
#include <linux/acpi.h>
+#include <linux/dmi.h>
#include <asm/efi.h>
#include <asm/uv/uv.h>
@@ -248,6 +249,16 @@
return ret;
}
+static const struct dmi_system_id sgi_uv1_dmi[] = {
+ { NULL, "SGI UV1",
+ { DMI_MATCH(DMI_PRODUCT_NAME, "Stoutland Platform"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"),
+ DMI_MATCH(DMI_BIOS_VENDOR, "SGI.COM"),
+ }
+ },
+ { } /* NULL entry stops DMI scanning */
+};
+
void __init efi_apply_memmap_quirks(void)
{
/*
@@ -260,10 +271,8 @@
efi_unmap_memmap();
}
- /*
- * UV doesn't support the new EFI pagetable mapping yet.
- */
- if (is_uv_system())
+ /* UV2+ BIOS has a fix for this issue. UV1 still needs the quirk. */
+ if (dmi_check_system(sgi_uv1_dmi))
set_bit(EFI_OLD_MEMMAP, &efi.flags);
}
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 1bbc21e..90bb997 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -138,7 +138,7 @@
intel_mid_ops = get_intel_mid_ops[__intel_mid_cpu_chip]();
else {
intel_mid_ops = get_intel_mid_ops[INTEL_MID_CPU_CHIP_PENWELL]();
- pr_info("ARCH: Unknown SoC, assuming PENWELL!\n");
+ pr_info("ARCH: Unknown SoC, assuming Penwell!\n");
}
out:
@@ -214,12 +214,10 @@
else if (strcmp("lapic_and_apbt", arg) == 0)
intel_mid_timer_options = INTEL_MID_TIMER_LAPIC_APBT;
else {
- pr_warn("X86 INTEL_MID timer option %s not recognised"
- " use x86_intel_mid_timer=apbt_only or lapic_and_apbt\n",
- arg);
+ pr_warn("X86 INTEL_MID timer option %s not recognised use x86_intel_mid_timer=apbt_only or lapic_and_apbt\n",
+ arg);
return -EINVAL;
}
return 0;
}
__setup("x86_intel_mid_timer=", setup_x86_intel_mid_timer);
-
diff --git a/arch/x86/platform/intel-quark/imr.c b/arch/x86/platform/intel-quark/imr.c
index c1bdafa..c61b6c3 100644
--- a/arch/x86/platform/intel-quark/imr.c
+++ b/arch/x86/platform/intel-quark/imr.c
@@ -220,11 +220,12 @@
if (imr_is_enabled(&imr)) {
base = imr_to_phys(imr.addr_lo);
end = imr_to_phys(imr.addr_hi) + IMR_MASK;
+ size = end - base + 1;
} else {
base = 0;
end = 0;
+ size = 0;
}
- size = end - base;
seq_printf(s, "imr%02i: base=%pa, end=%pa, size=0x%08zx "
"rmask=0x%08x, wmask=0x%08x, %s, %s\n", i,
&base, &end, size, imr.rmask, imr.wmask,
@@ -579,6 +580,7 @@
{
phys_addr_t base = virt_to_phys(&_text);
size_t size = virt_to_phys(&__end_rodata) - base;
+ unsigned long start, end;
int i;
int ret;
@@ -586,18 +588,24 @@
for (i = 0; i < idev->max_imr; i++)
imr_clear(i);
+ start = (unsigned long)_text;
+ end = (unsigned long)__end_rodata - 1;
+
/*
* Setup a locked IMR around the physical extent of the kernel
* from the beginning of the .text secton to the end of the
* .rodata section as one physically contiguous block.
+ *
+ * We don't round up @size since it is already PAGE_SIZE aligned.
+ * See vmlinux.lds.S for details.
*/
ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, true);
if (ret < 0) {
- pr_err("unable to setup IMR for kernel: (%p - %p)\n",
- &_text, &__end_rodata);
+ pr_err("unable to setup IMR for kernel: %zu KiB (%lx - %lx)\n",
+ size / 1024, start, end);
} else {
- pr_info("protecting kernel .text - .rodata: %zu KiB (%p - %p)\n",
- size / 1024, &_text, &__end_rodata);
+ pr_info("protecting kernel .text - .rodata: %zu KiB (%lx - %lx)\n",
+ size / 1024, start, end);
}
}
diff --git a/block/ioctl.c b/block/ioctl.c
index 77f5d177..d8996bb 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -434,42 +434,6 @@
return true;
}
-
-static int blkdev_daxset(struct block_device *bdev, unsigned long argp)
-{
- unsigned long arg;
- int rc = 0;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
-
- if (get_user(arg, (int __user *)(argp)))
- return -EFAULT;
- arg = !!arg;
- if (arg == !!(bdev->bd_inode->i_flags & S_DAX))
- return 0;
-
- if (arg)
- arg = S_DAX;
-
- if (arg && !blkdev_dax_capable(bdev))
- return -ENOTTY;
-
- inode_lock(bdev->bd_inode);
- if (bdev->bd_map_count == 0)
- inode_set_flags(bdev->bd_inode, arg, S_DAX);
- else
- rc = -EBUSY;
- inode_unlock(bdev->bd_inode);
- return rc;
-}
-#else
-static int blkdev_daxset(struct block_device *bdev, int arg)
-{
- if (arg)
- return -ENOTTY;
- return 0;
-}
#endif
static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode,
@@ -634,8 +598,6 @@
case BLKTRACESETUP:
case BLKTRACETEARDOWN:
return blk_trace_ioctl(bdev, cmd, argp);
- case BLKDAXSET:
- return blkdev_daxset(bdev, arg);
case BLKDAXGET:
return put_int(arg, !!(bdev->bd_inode->i_flags & S_DAX));
break;
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 746935a..fefd01b 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -16,6 +16,7 @@
#include <linux/kmod.h>
#include <linux/ctype.h>
#include <linux/genhd.h>
+#include <linux/dax.h>
#include <linux/blktrace_api.h>
#include "partitions/check.h"
@@ -550,13 +551,24 @@
return 0;
}
-unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p)
+static struct page *read_pagecache_sector(struct block_device *bdev, sector_t n)
{
struct address_space *mapping = bdev->bd_inode->i_mapping;
+
+ return read_mapping_page(mapping, (pgoff_t)(n >> (PAGE_CACHE_SHIFT-9)),
+ NULL);
+}
+
+unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p)
+{
struct page *page;
- page = read_mapping_page(mapping, (pgoff_t)(n >> (PAGE_CACHE_SHIFT-9)),
- NULL);
+ /* don't populate page cache for dax capable devices */
+ if (IS_DAX(bdev->bd_inode))
+ page = read_dax_sector(bdev, n);
+ else
+ page = read_pagecache_sector(bdev, n);
+
if (!IS_ERR(page)) {
if (PageError(page))
goto fail;
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 7240821..3be07ad 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -472,11 +472,13 @@
config CRYPTO_GHASH
tristate "GHASH digest algorithm"
select CRYPTO_GF128MUL
+ select CRYPTO_HASH
help
GHASH is message digest algorithm for GCM (Galois/Counter Mode).
config CRYPTO_POLY1305
tristate "Poly1305 authenticator algorithm"
+ select CRYPTO_HASH
help
Poly1305 authenticator algorithm, RFC7539.
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 608a756..68a5cea 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -54,7 +54,8 @@
lock_sock(sk);
if (!ctx->more) {
- err = crypto_ahash_init(&ctx->req);
+ err = af_alg_wait_for_completion(crypto_ahash_init(&ctx->req),
+ &ctx->completion);
if (err)
goto unlock;
}
@@ -125,6 +126,7 @@
} else {
if (!ctx->more) {
err = crypto_ahash_init(&ctx->req);
+ err = af_alg_wait_for_completion(err, &ctx->completion);
if (err)
goto unlock;
}
diff --git a/crypto/asymmetric_keys/pkcs7_parser.c b/crypto/asymmetric_keys/pkcs7_parser.c
index 758acab..8f3056c 100644
--- a/crypto/asymmetric_keys/pkcs7_parser.c
+++ b/crypto/asymmetric_keys/pkcs7_parser.c
@@ -547,9 +547,7 @@
struct pkcs7_signed_info *sinfo = ctx->sinfo;
if (!test_bit(sinfo_has_content_type, &sinfo->aa_set) ||
- !test_bit(sinfo_has_message_digest, &sinfo->aa_set) ||
- (ctx->msg->data_type == OID_msIndirectData &&
- !test_bit(sinfo_has_ms_opus_info, &sinfo->aa_set))) {
+ !test_bit(sinfo_has_message_digest, &sinfo->aa_set)) {
pr_warn("Missing required AuthAttr\n");
return -EBADMSG;
}
diff --git a/crypto/shash.c b/crypto/shash.c
index 88a27de..35975459 100644
--- a/crypto/shash.c
+++ b/crypto/shash.c
@@ -354,11 +354,10 @@
crt->final = shash_async_final;
crt->finup = shash_async_finup;
crt->digest = shash_async_digest;
+ crt->setkey = shash_async_setkey;
- if (alg->setkey) {
- crt->setkey = shash_async_setkey;
- crt->has_setkey = true;
- }
+ crt->has_setkey = alg->setkey != shash_no_setkey;
+
if (alg->export)
crt->export = shash_async_export;
if (alg->import)
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 73d6e5d3..f437afa 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -558,10 +558,15 @@
return ret;
ret = dev_pm_domain_attach(_dev, true);
- if (ret != -EPROBE_DEFER && drv->probe) {
- ret = drv->probe(dev);
- if (ret)
- dev_pm_domain_detach(_dev, true);
+ if (ret != -EPROBE_DEFER) {
+ if (drv->probe) {
+ ret = drv->probe(dev);
+ if (ret)
+ dev_pm_domain_detach(_dev, true);
+ } else {
+ /* don't fail if just dev_pm_domain_attach failed */
+ ret = 0;
+ }
}
if (drv->prevent_deferred_probe && ret == -EPROBE_DEFER) {
diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig
index dbf2271..ff00331 100644
--- a/drivers/char/hw_random/Kconfig
+++ b/drivers/char/hw_random/Kconfig
@@ -372,6 +372,7 @@
config HW_RANDOM_STM32
tristate "STMicroelectronics STM32 random number generator"
depends on HW_RANDOM && (ARCH_STM32 || COMPILE_TEST)
+ depends on HAS_IOMEM
help
This driver provides kernel-side support for the Random Number
Generator hardware found on STM32 microcontrollers.
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 56777f0..33db740 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -30,6 +30,8 @@
config DIGICOLOR_TIMER
bool "Digicolor timer driver" if COMPILE_TEST
depends on GENERIC_CLOCKEVENTS
+ select CLKSRC_MMIO
+ depends on HAS_IOMEM
help
Enables the support for the digicolor timer driver.
@@ -55,6 +57,7 @@
bool "Armada 370 and XP timer driver" if COMPILE_TEST
depends on ARM
select CLKSRC_OF
+ select CLKSRC_MMIO
help
Enables the support for the Armada 370 and XP timer driver.
@@ -76,6 +79,7 @@
config SUN4I_TIMER
bool "Sun4i timer driver" if COMPILE_TEST
depends on GENERIC_CLOCKEVENTS
+ depends on HAS_IOMEM
select CLKSRC_MMIO
help
Enables support for the Sun4i timer.
@@ -89,6 +93,7 @@
config TEGRA_TIMER
bool "Tegra timer driver" if COMPILE_TEST
+ select CLKSRC_MMIO
depends on ARM
help
Enables support for the Tegra driver.
@@ -96,6 +101,7 @@
config VT8500_TIMER
bool "VT8500 timer driver" if COMPILE_TEST
depends on GENERIC_CLOCKEVENTS
+ depends on HAS_IOMEM
help
Enables support for the VT8500 driver.
@@ -131,6 +137,7 @@
config CLKSRC_DBX500_PRCMU
bool "Clocksource PRCMU Timer" if COMPILE_TEST
depends on GENERIC_CLOCKEVENTS
+ depends on HAS_IOMEM
help
Use the always on PRCMU Timer as clocksource
@@ -248,6 +255,7 @@
config CLKSRC_SAMSUNG_PWM
bool "PWM timer drvier for Samsung S3C, S5P" if COMPILE_TEST
depends on GENERIC_CLOCKEVENTS
+ depends on HAS_IOMEM
help
This is a new clocksource driver for the PWM timer found in
Samsung S3C, S5P and Exynos SoCs, replacing an earlier driver
@@ -257,12 +265,14 @@
config FSL_FTM_TIMER
bool "Freescale FlexTimer Module driver" if COMPILE_TEST
depends on GENERIC_CLOCKEVENTS
+ depends on HAS_IOMEM
select CLKSRC_MMIO
help
Support for Freescale FlexTimer Module (FTM) timer.
config VF_PIT_TIMER
bool
+ select CLKSRC_MMIO
help
Support for Period Interrupt Timer on Freescale Vybrid Family SoCs.
@@ -360,6 +370,7 @@
config CLKSRC_PXA
bool "Clocksource for PXA or SA-11x0 platform" if COMPILE_TEST
depends on GENERIC_CLOCKEVENTS
+ depends on HAS_IOMEM
select CLKSRC_MMIO
help
This enables OST0 support available on PXA and SA-11x0
@@ -394,6 +405,7 @@
bool "Low power clocksource found in the LPC" if COMPILE_TEST
select CLKSRC_OF if OF
depends on HAS_IOMEM
+ select CLKSRC_MMIO
help
Enable this option to use the Low Power controller timer
as clocksource.
diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c
index 6ee9140..4da2af9 100644
--- a/drivers/clocksource/tcb_clksrc.c
+++ b/drivers/clocksource/tcb_clksrc.c
@@ -98,7 +98,8 @@
__raw_writel(0xff, regs + ATMEL_TC_REG(2, IDR));
__raw_writel(ATMEL_TC_CLKDIS, regs + ATMEL_TC_REG(2, CCR));
- clk_disable(tcd->clk);
+ if (!clockevent_state_detached(d))
+ clk_disable(tcd->clk);
return 0;
}
diff --git a/drivers/crypto/atmel-aes.c b/drivers/crypto/atmel-aes.c
index 6dd3317..3eb3f12 100644
--- a/drivers/crypto/atmel-aes.c
+++ b/drivers/crypto/atmel-aes.c
@@ -400,7 +400,7 @@
{
int err;
- err = clk_prepare_enable(dd->iclk);
+ err = clk_enable(dd->iclk);
if (err)
return err;
@@ -430,7 +430,7 @@
dev_info(dd->dev, "version: 0x%x\n", dd->hw_version);
- clk_disable_unprepare(dd->iclk);
+ clk_disable(dd->iclk);
return 0;
}
@@ -448,7 +448,7 @@
static inline int atmel_aes_complete(struct atmel_aes_dev *dd, int err)
{
- clk_disable_unprepare(dd->iclk);
+ clk_disable(dd->iclk);
dd->flags &= ~AES_FLAGS_BUSY;
if (dd->is_async)
@@ -2091,10 +2091,14 @@
goto res_err;
}
- err = atmel_aes_hw_version_init(aes_dd);
+ err = clk_prepare(aes_dd->iclk);
if (err)
goto res_err;
+ err = atmel_aes_hw_version_init(aes_dd);
+ if (err)
+ goto iclk_unprepare;
+
atmel_aes_get_cap(aes_dd);
err = atmel_aes_buff_init(aes_dd);
@@ -2127,6 +2131,8 @@
err_aes_dma:
atmel_aes_buff_cleanup(aes_dd);
err_aes_buff:
+iclk_unprepare:
+ clk_unprepare(aes_dd->iclk);
res_err:
tasklet_kill(&aes_dd->done_task);
tasklet_kill(&aes_dd->queue_task);
@@ -2155,6 +2161,8 @@
atmel_aes_dma_cleanup(aes_dd);
atmel_aes_buff_cleanup(aes_dd);
+ clk_unprepare(aes_dd->iclk);
+
return 0;
}
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index 8abb4bc..69d4a13 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -534,8 +534,8 @@
* long pointers in master configuration register
*/
clrsetbits_32(&ctrl->mcr, MCFGR_AWCACHE_MASK, MCFGR_AWCACHE_CACH |
- MCFGR_WDENABLE | (sizeof(dma_addr_t) == sizeof(u64) ?
- MCFGR_LONG_PTR : 0));
+ MCFGR_AWCACHE_BUFF | MCFGR_WDENABLE |
+ (sizeof(dma_addr_t) == sizeof(u64) ? MCFGR_LONG_PTR : 0));
/*
* Read the Compile Time paramters and SCFGR to determine
diff --git a/drivers/iio/imu/adis_buffer.c b/drivers/iio/imu/adis_buffer.c
index cb32b59..36607d5 100644
--- a/drivers/iio/imu/adis_buffer.c
+++ b/drivers/iio/imu/adis_buffer.c
@@ -43,7 +43,7 @@
return -ENOMEM;
rx = adis->buffer;
- tx = rx + indio_dev->scan_bytes;
+ tx = rx + scan_count;
spi_message_init(&adis->msg);
diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c
index 9fe33fc..cf34681 100644
--- a/drivers/net/dsa/mv88e6xxx.c
+++ b/drivers/net/dsa/mv88e6xxx.c
@@ -1532,7 +1532,7 @@
/* no PVID with ranges, otherwise it's a bug */
if (pvid)
- err = _mv88e6xxx_port_pvid_set(ds, port, vid);
+ err = _mv88e6xxx_port_pvid_set(ds, port, vlan->vid_end);
unlock:
mutex_unlock(&ps->smi_mutex);
@@ -2163,7 +2163,8 @@
* database, and allow every port to egress frames on all other ports.
*/
reg = BIT(ps->num_ports) - 1; /* all ports */
- ret = _mv88e6xxx_port_vlan_map_set(ds, port, reg & ~port);
+ reg &= ~BIT(port); /* except itself */
+ ret = _mv88e6xxx_port_vlan_map_set(ds, port, reg);
if (ret)
goto abort;
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
index a4799c1..5eb9b20 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
@@ -628,6 +628,7 @@
int ret;
ring = pdata->rx_ring;
+ irq_set_status_flags(ring->irq, IRQ_DISABLE_UNLAZY);
ret = devm_request_irq(dev, ring->irq, xgene_enet_rx_irq,
IRQF_SHARED, ring->irq_name, ring);
if (ret)
@@ -635,6 +636,7 @@
if (pdata->cq_cnt) {
ring = pdata->tx_ring->cp_ring;
+ irq_set_status_flags(ring->irq, IRQ_DISABLE_UNLAZY);
ret = devm_request_irq(dev, ring->irq, xgene_enet_rx_irq,
IRQF_SHARED, ring->irq_name, ring);
if (ret) {
@@ -649,15 +651,19 @@
static void xgene_enet_free_irq(struct net_device *ndev)
{
struct xgene_enet_pdata *pdata;
+ struct xgene_enet_desc_ring *ring;
struct device *dev;
pdata = netdev_priv(ndev);
dev = ndev_to_dev(ndev);
- devm_free_irq(dev, pdata->rx_ring->irq, pdata->rx_ring);
+ ring = pdata->rx_ring;
+ irq_clear_status_flags(ring->irq, IRQ_DISABLE_UNLAZY);
+ devm_free_irq(dev, ring->irq, ring);
if (pdata->cq_cnt) {
- devm_free_irq(dev, pdata->tx_ring->cp_ring->irq,
- pdata->tx_ring->cp_ring);
+ ring = pdata->tx_ring->cp_ring;
+ irq_clear_status_flags(ring->irq, IRQ_DISABLE_UNLAZY);
+ devm_free_irq(dev, ring->irq, ring);
}
}
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h
index 70d5b62..248dfc4 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h
@@ -25,6 +25,7 @@
#include <linux/acpi.h>
#include <linux/clk.h>
#include <linux/efi.h>
+#include <linux/irq.h>
#include <linux/io.h>
#include <linux/of_platform.h>
#include <linux/of_net.h>
diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c
index ecc4a33..f71ab26 100644
--- a/drivers/net/ethernet/aurora/nb8800.c
+++ b/drivers/net/ethernet/aurora/nb8800.c
@@ -302,7 +302,7 @@
nb8800_tx_done(dev);
again:
- while (work < budget) {
+ do {
struct nb8800_rx_buf *rxb;
unsigned int len;
@@ -330,7 +330,7 @@
rxd->report = 0;
last = next;
work++;
- }
+ } while (work < budget);
if (work) {
priv->rx_descs[last].desc.config |= DESC_EOC;
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index 8550df1..19f7cd0 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -151,8 +151,11 @@
config BGMAC
tristate "BCMA bus GBit core support"
- depends on BCMA_HOST_SOC && HAS_DMA && (BCM47XX || ARCH_BCM_5301X)
+ depends on BCMA && BCMA_HOST_SOC
+ depends on HAS_DMA
+ depends on BCM47XX || ARCH_BCM_5301X || COMPILE_TEST
select PHYLIB
+ select FIXED_PHY
---help---
This driver supports GBit MAC and BCM4706 GBit MAC cores on BCMA bus.
They can be found on BCM47xx SoCs and provide gigabit ethernet.
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index df835f5..5dc89e5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1490,10 +1490,11 @@
last = tx_buf->nr_frags;
j += 2;
- for (k = 0; k < last; k++, j = NEXT_TX(j)) {
+ for (k = 0; k < last; k++, j++) {
+ int ring_idx = j & bp->tx_ring_mask;
skb_frag_t *frag = &skb_shinfo(skb)->frags[k];
- tx_buf = &txr->tx_buf_ring[j];
+ tx_buf = &txr->tx_buf_ring[ring_idx];
dma_unmap_page(
&pdev->dev,
dma_unmap_addr(tx_buf, mapping),
@@ -3406,7 +3407,7 @@
struct hwrm_ring_free_output *resp = bp->hwrm_cmd_resp_addr;
u16 error_code;
- bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_FREE, -1, -1);
+ bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_FREE, cmpl_ring_id, -1);
req.ring_type = ring_type;
req.ring_id = cpu_to_le16(ring->fw_ring_id);
@@ -4819,8 +4820,6 @@
stats->multicast += le64_to_cpu(hw_stats->rx_mcast_pkts);
- stats->rx_dropped += le64_to_cpu(hw_stats->rx_drop_pkts);
-
stats->tx_dropped += le64_to_cpu(hw_stats->tx_drop_pkts);
}
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 0d77596..457c3bc 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -401,7 +401,7 @@
* Ethernet MAC ISRs
*/
if (priv->internal_phy)
- priv->mii_bus->irq[phydev->mdio.addr] = PHY_IGNORE_INTERRUPT;
+ priv->phydev->irq = PHY_IGNORE_INTERRUPT;
return 0;
}
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 9293675..49eea89 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -12016,7 +12016,7 @@
int ret;
u32 offset, len, b_offset, odd_len;
u8 *buf;
- __be32 start, end;
+ __be32 start = 0, end;
if (tg3_flag(tp, NO_NVRAM) ||
eeprom->magic != TG3_EEPROM_MAGIC)
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index 9d9984a..50c9410 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -2823,7 +2823,7 @@
struct device_node *np = pdev->dev.of_node;
struct device_node *phy_node;
const struct macb_config *macb_config = NULL;
- struct clk *pclk, *hclk, *tx_clk;
+ struct clk *pclk, *hclk = NULL, *tx_clk = NULL;
unsigned int queue_mask, num_queues;
struct macb_platform_data *pdata;
bool native_io;
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index b895044..8727655 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -1526,7 +1526,6 @@
struct timespec64 *ts)
{
u64 ns;
- u32 remainder;
unsigned long flags;
struct lio *lio = container_of(ptp, struct lio, ptp_info);
struct octeon_device *oct = (struct octeon_device *)lio->oct_dev;
@@ -1536,8 +1535,7 @@
ns += lio->ptp_adjust;
spin_unlock_irqrestore(&lio->ptp_lock, flags);
- ts->tv_sec = div_u64_rem(ns, 1000000000ULL, &remainder);
- ts->tv_nsec = remainder;
+ *ts = ns_to_timespec64(ns);
return 0;
}
diff --git a/drivers/net/ethernet/ezchip/Kconfig b/drivers/net/ethernet/ezchip/Kconfig
index 48ecbc8..b423ad3 100644
--- a/drivers/net/ethernet/ezchip/Kconfig
+++ b/drivers/net/ethernet/ezchip/Kconfig
@@ -18,6 +18,7 @@
config EZCHIP_NPS_MANAGEMENT_ENET
tristate "EZchip NPS management enet support"
depends on OF_IRQ && OF_NET
+ depends on HAS_IOMEM
---help---
Simple LAN device for debug or management purposes.
Device supports interrupts for RX and TX(completion).
diff --git a/drivers/net/ethernet/freescale/Makefile b/drivers/net/ethernet/freescale/Makefile
index 4097c58..cbe21dc 100644
--- a/drivers/net/ethernet/freescale/Makefile
+++ b/drivers/net/ethernet/freescale/Makefile
@@ -4,6 +4,9 @@
obj-$(CONFIG_FEC) += fec.o
fec-objs :=fec_main.o fec_ptp.o
+CFLAGS_fec_main.o := -D__CHECK_ENDIAN__
+CFLAGS_fec_ptp.o := -D__CHECK_ENDIAN__
+
obj-$(CONFIG_FEC_MPC52xx) += fec_mpc52xx.o
ifeq ($(CONFIG_FEC_MPC52xx_MDIO),y)
obj-$(CONFIG_FEC_MPC52xx) += fec_mpc52xx_phy.o
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 99d33e2..2106d72 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -19,8 +19,7 @@
#include <linux/timecounter.h>
#if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \
- defined(CONFIG_M520x) || defined(CONFIG_M532x) || \
- defined(CONFIG_ARCH_MXC) || defined(CONFIG_SOC_IMX28)
+ defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM)
/*
* Just figures, Motorola would have to change the offsets for
* registers in the same peripheral device on different models
@@ -190,28 +189,45 @@
/*
* Define the buffer descriptor structure.
+ *
+ * Evidently, ARM SoCs have the FEC block generated in a
+ * little endian mode so adjust endianness accordingly.
*/
-#if defined(CONFIG_ARCH_MXC) || defined(CONFIG_SOC_IMX28)
+#if defined(CONFIG_ARM)
+#define fec32_to_cpu le32_to_cpu
+#define fec16_to_cpu le16_to_cpu
+#define cpu_to_fec32 cpu_to_le32
+#define cpu_to_fec16 cpu_to_le16
+#define __fec32 __le32
+#define __fec16 __le16
+
struct bufdesc {
- unsigned short cbd_datlen; /* Data length */
- unsigned short cbd_sc; /* Control and status info */
- unsigned long cbd_bufaddr; /* Buffer address */
+ __fec16 cbd_datlen; /* Data length */
+ __fec16 cbd_sc; /* Control and status info */
+ __fec32 cbd_bufaddr; /* Buffer address */
};
#else
+#define fec32_to_cpu be32_to_cpu
+#define fec16_to_cpu be16_to_cpu
+#define cpu_to_fec32 cpu_to_be32
+#define cpu_to_fec16 cpu_to_be16
+#define __fec32 __be32
+#define __fec16 __be16
+
struct bufdesc {
- unsigned short cbd_sc; /* Control and status info */
- unsigned short cbd_datlen; /* Data length */
- unsigned long cbd_bufaddr; /* Buffer address */
+ __fec16 cbd_sc; /* Control and status info */
+ __fec16 cbd_datlen; /* Data length */
+ __fec32 cbd_bufaddr; /* Buffer address */
};
#endif
struct bufdesc_ex {
struct bufdesc desc;
- unsigned long cbd_esc;
- unsigned long cbd_prot;
- unsigned long cbd_bdu;
- unsigned long ts;
- unsigned short res0[4];
+ __fec32 cbd_esc;
+ __fec32 cbd_prot;
+ __fec32 cbd_bdu;
+ __fec32 ts;
+ __fec16 res0[4];
};
/*
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 502da6f..41c81f6 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -332,11 +332,13 @@
bdp = txq->tx_bd_base;
do {
- pr_info("%3u %c%c 0x%04x 0x%08lx %4u %p\n",
+ pr_info("%3u %c%c 0x%04x 0x%08x %4u %p\n",
index,
bdp == txq->cur_tx ? 'S' : ' ',
bdp == txq->dirty_tx ? 'H' : ' ',
- bdp->cbd_sc, bdp->cbd_bufaddr, bdp->cbd_datlen,
+ fec16_to_cpu(bdp->cbd_sc),
+ fec32_to_cpu(bdp->cbd_bufaddr),
+ fec16_to_cpu(bdp->cbd_datlen),
txq->tx_skbuff[index]);
bdp = fec_enet_get_nextdesc(bdp, fep, 0);
index++;
@@ -389,7 +391,7 @@
bdp = fec_enet_get_nextdesc(bdp, fep, queue);
ebdp = (struct bufdesc_ex *)bdp;
- status = bdp->cbd_sc;
+ status = fec16_to_cpu(bdp->cbd_sc);
status &= ~BD_ENET_TX_STATS;
status |= (BD_ENET_TX_TC | BD_ENET_TX_READY);
frag_len = skb_shinfo(skb)->frags[frag].size;
@@ -411,7 +413,7 @@
if (skb->ip_summed == CHECKSUM_PARTIAL)
estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS;
ebdp->cbd_bdu = 0;
- ebdp->cbd_esc = estatus;
+ ebdp->cbd_esc = cpu_to_fec32(estatus);
}
bufaddr = page_address(this_frag->page.p) + this_frag->page_offset;
@@ -435,9 +437,9 @@
goto dma_mapping_error;
}
- bdp->cbd_bufaddr = addr;
- bdp->cbd_datlen = frag_len;
- bdp->cbd_sc = status;
+ bdp->cbd_bufaddr = cpu_to_fec32(addr);
+ bdp->cbd_datlen = cpu_to_fec16(frag_len);
+ bdp->cbd_sc = cpu_to_fec16(status);
}
return bdp;
@@ -445,8 +447,8 @@
bdp = txq->cur_tx;
for (i = 0; i < frag; i++) {
bdp = fec_enet_get_nextdesc(bdp, fep, queue);
- dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr,
- bdp->cbd_datlen, DMA_TO_DEVICE);
+ dma_unmap_single(&fep->pdev->dev, fec32_to_cpu(bdp->cbd_bufaddr),
+ fec16_to_cpu(bdp->cbd_datlen), DMA_TO_DEVICE);
}
return ERR_PTR(-ENOMEM);
}
@@ -483,7 +485,7 @@
/* Fill in a Tx ring entry */
bdp = txq->cur_tx;
last_bdp = bdp;
- status = bdp->cbd_sc;
+ status = fec16_to_cpu(bdp->cbd_sc);
status &= ~BD_ENET_TX_STATS;
/* Set buffer length and buffer pointer */
@@ -539,21 +541,21 @@
estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS;
ebdp->cbd_bdu = 0;
- ebdp->cbd_esc = estatus;
+ ebdp->cbd_esc = cpu_to_fec32(estatus);
}
index = fec_enet_get_bd_index(txq->tx_bd_base, last_bdp, fep);
/* Save skb pointer */
txq->tx_skbuff[index] = skb;
- bdp->cbd_datlen = buflen;
- bdp->cbd_bufaddr = addr;
+ bdp->cbd_datlen = cpu_to_fec16(buflen);
+ bdp->cbd_bufaddr = cpu_to_fec32(addr);
/* Send it on its way. Tell FEC it's ready, interrupt when done,
* it's the last BD of the frame, and to put the CRC on the end.
*/
status |= (BD_ENET_TX_READY | BD_ENET_TX_TC);
- bdp->cbd_sc = status;
+ bdp->cbd_sc = cpu_to_fec16(status);
/* If this was the last BD in the ring, start at the beginning again. */
bdp = fec_enet_get_nextdesc(last_bdp, fep, queue);
@@ -585,7 +587,7 @@
unsigned int estatus = 0;
dma_addr_t addr;
- status = bdp->cbd_sc;
+ status = fec16_to_cpu(bdp->cbd_sc);
status &= ~BD_ENET_TX_STATS;
status |= (BD_ENET_TX_TC | BD_ENET_TX_READY);
@@ -607,8 +609,8 @@
return NETDEV_TX_BUSY;
}
- bdp->cbd_datlen = size;
- bdp->cbd_bufaddr = addr;
+ bdp->cbd_datlen = cpu_to_fec16(size);
+ bdp->cbd_bufaddr = cpu_to_fec32(addr);
if (fep->bufdesc_ex) {
if (fep->quirks & FEC_QUIRK_HAS_AVB)
@@ -616,7 +618,7 @@
if (skb->ip_summed == CHECKSUM_PARTIAL)
estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS;
ebdp->cbd_bdu = 0;
- ebdp->cbd_esc = estatus;
+ ebdp->cbd_esc = cpu_to_fec32(estatus);
}
/* Handle the last BD specially */
@@ -625,10 +627,10 @@
if (is_last) {
status |= BD_ENET_TX_INTR;
if (fep->bufdesc_ex)
- ebdp->cbd_esc |= BD_ENET_TX_INT;
+ ebdp->cbd_esc |= cpu_to_fec32(BD_ENET_TX_INT);
}
- bdp->cbd_sc = status;
+ bdp->cbd_sc = cpu_to_fec16(status);
return 0;
}
@@ -647,7 +649,7 @@
unsigned short status;
unsigned int estatus = 0;
- status = bdp->cbd_sc;
+ status = fec16_to_cpu(bdp->cbd_sc);
status &= ~BD_ENET_TX_STATS;
status |= (BD_ENET_TX_TC | BD_ENET_TX_READY);
@@ -671,8 +673,8 @@
}
}
- bdp->cbd_bufaddr = dmabuf;
- bdp->cbd_datlen = hdr_len;
+ bdp->cbd_bufaddr = cpu_to_fec32(dmabuf);
+ bdp->cbd_datlen = cpu_to_fec16(hdr_len);
if (fep->bufdesc_ex) {
if (fep->quirks & FEC_QUIRK_HAS_AVB)
@@ -680,10 +682,10 @@
if (skb->ip_summed == CHECKSUM_PARTIAL)
estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS;
ebdp->cbd_bdu = 0;
- ebdp->cbd_esc = estatus;
+ ebdp->cbd_esc = cpu_to_fec32(estatus);
}
- bdp->cbd_sc = status;
+ bdp->cbd_sc = cpu_to_fec16(status);
return 0;
}
@@ -823,15 +825,15 @@
/* Initialize the BD for every fragment in the page. */
if (bdp->cbd_bufaddr)
- bdp->cbd_sc = BD_ENET_RX_EMPTY;
+ bdp->cbd_sc = cpu_to_fec16(BD_ENET_RX_EMPTY);
else
- bdp->cbd_sc = 0;
+ bdp->cbd_sc = cpu_to_fec16(0);
bdp = fec_enet_get_nextdesc(bdp, fep, q);
}
/* Set the last buffer to wrap */
bdp = fec_enet_get_prevdesc(bdp, fep, q);
- bdp->cbd_sc |= BD_SC_WRAP;
+ bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP);
rxq->cur_rx = rxq->rx_bd_base;
}
@@ -844,18 +846,18 @@
for (i = 0; i < txq->tx_ring_size; i++) {
/* Initialize the BD for every fragment in the page. */
- bdp->cbd_sc = 0;
+ bdp->cbd_sc = cpu_to_fec16(0);
if (txq->tx_skbuff[i]) {
dev_kfree_skb_any(txq->tx_skbuff[i]);
txq->tx_skbuff[i] = NULL;
}
- bdp->cbd_bufaddr = 0;
+ bdp->cbd_bufaddr = cpu_to_fec32(0);
bdp = fec_enet_get_nextdesc(bdp, fep, q);
}
/* Set the last buffer to wrap */
bdp = fec_enet_get_prevdesc(bdp, fep, q);
- bdp->cbd_sc |= BD_SC_WRAP;
+ bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP);
txq->dirty_tx = bdp;
}
}
@@ -947,8 +949,10 @@
*/
if (fep->quirks & FEC_QUIRK_ENET_MAC) {
memcpy(&temp_mac, ndev->dev_addr, ETH_ALEN);
- writel(cpu_to_be32(temp_mac[0]), fep->hwp + FEC_ADDR_LOW);
- writel(cpu_to_be32(temp_mac[1]), fep->hwp + FEC_ADDR_HIGH);
+ writel((__force u32)cpu_to_be32(temp_mac[0]),
+ fep->hwp + FEC_ADDR_LOW);
+ writel((__force u32)cpu_to_be32(temp_mac[1]),
+ fep->hwp + FEC_ADDR_HIGH);
}
/* Clear any outstanding interrupt. */
@@ -1222,7 +1226,7 @@
while (bdp != READ_ONCE(txq->cur_tx)) {
/* Order the load of cur_tx and cbd_sc */
rmb();
- status = READ_ONCE(bdp->cbd_sc);
+ status = fec16_to_cpu(READ_ONCE(bdp->cbd_sc));
if (status & BD_ENET_TX_READY)
break;
@@ -1230,10 +1234,12 @@
skb = txq->tx_skbuff[index];
txq->tx_skbuff[index] = NULL;
- if (!IS_TSO_HEADER(txq, bdp->cbd_bufaddr))
- dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr,
- bdp->cbd_datlen, DMA_TO_DEVICE);
- bdp->cbd_bufaddr = 0;
+ if (!IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr)))
+ dma_unmap_single(&fep->pdev->dev,
+ fec32_to_cpu(bdp->cbd_bufaddr),
+ fec16_to_cpu(bdp->cbd_datlen),
+ DMA_TO_DEVICE);
+ bdp->cbd_bufaddr = cpu_to_fec32(0);
if (!skb) {
bdp = fec_enet_get_nextdesc(bdp, fep, queue_id);
continue;
@@ -1264,7 +1270,7 @@
struct skb_shared_hwtstamps shhwtstamps;
struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
- fec_enet_hwtstamp(fep, ebdp->ts, &shhwtstamps);
+ fec_enet_hwtstamp(fep, fec32_to_cpu(ebdp->ts), &shhwtstamps);
skb_tstamp_tx(skb, &shhwtstamps);
}
@@ -1324,10 +1330,8 @@
if (off)
skb_reserve(skb, fep->rx_align + 1 - off);
- bdp->cbd_bufaddr = dma_map_single(&fep->pdev->dev, skb->data,
- FEC_ENET_RX_FRSIZE - fep->rx_align,
- DMA_FROM_DEVICE);
- if (dma_mapping_error(&fep->pdev->dev, bdp->cbd_bufaddr)) {
+ bdp->cbd_bufaddr = cpu_to_fec32(dma_map_single(&fep->pdev->dev, skb->data, FEC_ENET_RX_FRSIZE - fep->rx_align, DMA_FROM_DEVICE));
+ if (dma_mapping_error(&fep->pdev->dev, fec32_to_cpu(bdp->cbd_bufaddr))) {
if (net_ratelimit())
netdev_err(ndev, "Rx DMA memory map failed\n");
return -ENOMEM;
@@ -1349,7 +1353,8 @@
if (!new_skb)
return false;
- dma_sync_single_for_cpu(&fep->pdev->dev, bdp->cbd_bufaddr,
+ dma_sync_single_for_cpu(&fep->pdev->dev,
+ fec32_to_cpu(bdp->cbd_bufaddr),
FEC_ENET_RX_FRSIZE - fep->rx_align,
DMA_FROM_DEVICE);
if (!swap)
@@ -1396,7 +1401,7 @@
*/
bdp = rxq->cur_rx;
- while (!((status = bdp->cbd_sc) & BD_ENET_RX_EMPTY)) {
+ while (!((status = fec16_to_cpu(bdp->cbd_sc)) & BD_ENET_RX_EMPTY)) {
if (pkt_received >= budget)
break;
@@ -1438,7 +1443,7 @@
/* Process the incoming frame. */
ndev->stats.rx_packets++;
- pkt_len = bdp->cbd_datlen;
+ pkt_len = fec16_to_cpu(bdp->cbd_datlen);
ndev->stats.rx_bytes += pkt_len;
index = fec_enet_get_bd_index(rxq->rx_bd_base, bdp, fep);
@@ -1456,7 +1461,8 @@
ndev->stats.rx_dropped++;
goto rx_processing_done;
}
- dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr,
+ dma_unmap_single(&fep->pdev->dev,
+ fec32_to_cpu(bdp->cbd_bufaddr),
FEC_ENET_RX_FRSIZE - fep->rx_align,
DMA_FROM_DEVICE);
}
@@ -1475,7 +1481,8 @@
/* If this is a VLAN packet remove the VLAN Tag */
vlan_packet_rcvd = false;
if ((ndev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
- fep->bufdesc_ex && (ebdp->cbd_esc & BD_ENET_RX_VLAN)) {
+ fep->bufdesc_ex &&
+ (ebdp->cbd_esc & cpu_to_fec32(BD_ENET_RX_VLAN))) {
/* Push and remove the vlan tag */
struct vlan_hdr *vlan_header =
(struct vlan_hdr *) (data + ETH_HLEN);
@@ -1491,12 +1498,12 @@
/* Get receive timestamp from the skb */
if (fep->hwts_rx_en && fep->bufdesc_ex)
- fec_enet_hwtstamp(fep, ebdp->ts,
+ fec_enet_hwtstamp(fep, fec32_to_cpu(ebdp->ts),
skb_hwtstamps(skb));
if (fep->bufdesc_ex &&
(fep->csum_flags & FLAG_RX_CSUM_ENABLED)) {
- if (!(ebdp->cbd_esc & FLAG_RX_CSUM_ERROR)) {
+ if (!(ebdp->cbd_esc & cpu_to_fec32(FLAG_RX_CSUM_ERROR))) {
/* don't check it */
skb->ip_summed = CHECKSUM_UNNECESSARY;
} else {
@@ -1513,7 +1520,8 @@
napi_gro_receive(&fep->napi, skb);
if (is_copybreak) {
- dma_sync_single_for_device(&fep->pdev->dev, bdp->cbd_bufaddr,
+ dma_sync_single_for_device(&fep->pdev->dev,
+ fec32_to_cpu(bdp->cbd_bufaddr),
FEC_ENET_RX_FRSIZE - fep->rx_align,
DMA_FROM_DEVICE);
} else {
@@ -1527,12 +1535,12 @@
/* Mark the buffer empty */
status |= BD_ENET_RX_EMPTY;
- bdp->cbd_sc = status;
+ bdp->cbd_sc = cpu_to_fec16(status);
if (fep->bufdesc_ex) {
struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
- ebdp->cbd_esc = BD_ENET_RX_INT;
+ ebdp->cbd_esc = cpu_to_fec32(BD_ENET_RX_INT);
ebdp->cbd_prot = 0;
ebdp->cbd_bdu = 0;
}
@@ -2145,8 +2153,7 @@
/* List of registers that can be safety be read to dump them with ethtool */
#if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \
- defined(CONFIG_M520x) || defined(CONFIG_M532x) || \
- defined(CONFIG_ARCH_MXC) || defined(CONFIG_SOC_IMX28)
+ defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM)
static u32 fec_enet_register_offset[] = {
FEC_IEVENT, FEC_IMASK, FEC_R_DES_ACTIVE_0, FEC_X_DES_ACTIVE_0,
FEC_ECNTRL, FEC_MII_DATA, FEC_MII_SPEED, FEC_MIB_CTRLSTAT, FEC_R_CNTRL,
@@ -2662,7 +2669,7 @@
rxq->rx_skbuff[i] = NULL;
if (skb) {
dma_unmap_single(&fep->pdev->dev,
- bdp->cbd_bufaddr,
+ fec32_to_cpu(bdp->cbd_bufaddr),
FEC_ENET_RX_FRSIZE - fep->rx_align,
DMA_FROM_DEVICE);
dev_kfree_skb(skb);
@@ -2777,11 +2784,11 @@
}
rxq->rx_skbuff[i] = skb;
- bdp->cbd_sc = BD_ENET_RX_EMPTY;
+ bdp->cbd_sc = cpu_to_fec16(BD_ENET_RX_EMPTY);
if (fep->bufdesc_ex) {
struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
- ebdp->cbd_esc = BD_ENET_RX_INT;
+ ebdp->cbd_esc = cpu_to_fec32(BD_ENET_RX_INT);
}
bdp = fec_enet_get_nextdesc(bdp, fep, queue);
@@ -2789,7 +2796,7 @@
/* Set the last buffer to wrap. */
bdp = fec_enet_get_prevdesc(bdp, fep, queue);
- bdp->cbd_sc |= BD_SC_WRAP;
+ bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP);
return 0;
err_alloc:
@@ -2812,12 +2819,12 @@
if (!txq->tx_bounce[i])
goto err_alloc;
- bdp->cbd_sc = 0;
- bdp->cbd_bufaddr = 0;
+ bdp->cbd_sc = cpu_to_fec16(0);
+ bdp->cbd_bufaddr = cpu_to_fec32(0);
if (fep->bufdesc_ex) {
struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
- ebdp->cbd_esc = BD_ENET_TX_INT;
+ ebdp->cbd_esc = cpu_to_fec32(BD_ENET_TX_INT);
}
bdp = fec_enet_get_nextdesc(bdp, fep, queue);
@@ -2825,7 +2832,7 @@
/* Set the last buffer to wrap. */
bdp = fec_enet_get_prevdesc(bdp, fep, queue);
- bdp->cbd_sc |= BD_SC_WRAP;
+ bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP);
return 0;
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
index 52e0091..1ba359f 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
@@ -552,7 +552,7 @@
cbd_t __iomem *prev_bd;
cbd_t __iomem *last_tx_bd;
- last_tx_bd = fep->tx_bd_base + ((fpi->tx_ring - 1) * sizeof(cbd_t));
+ last_tx_bd = fep->tx_bd_base + (fpi->tx_ring - 1);
/* get the current bd held in TBPTR and scan back from this point */
recheck_bd = curr_tbptr = (cbd_t __iomem *)
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c
index b364529..3bfe36f 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.c
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.c
@@ -95,21 +95,17 @@
static int __ae_match(struct device *dev, const void *data)
{
struct hnae_ae_dev *hdev = cls_to_ae_dev(dev);
- const char *ae_id = data;
- if (!strncmp(ae_id, hdev->name, AE_NAME_SIZE))
- return 1;
-
- return 0;
+ return hdev->dev->of_node == data;
}
-static struct hnae_ae_dev *find_ae(const char *ae_id)
+static struct hnae_ae_dev *find_ae(const struct device_node *ae_node)
{
struct device *dev;
- WARN_ON(!ae_id);
+ WARN_ON(!ae_node);
- dev = class_find_device(hnae_class, NULL, ae_id, __ae_match);
+ dev = class_find_device(hnae_class, NULL, ae_node, __ae_match);
return dev ? cls_to_ae_dev(dev) : NULL;
}
@@ -316,7 +312,8 @@
* return handle ptr or ERR_PTR
*/
struct hnae_handle *hnae_get_handle(struct device *owner_dev,
- const char *ae_id, u32 port_id,
+ const struct device_node *ae_node,
+ u32 port_id,
struct hnae_buf_ops *bops)
{
struct hnae_ae_dev *dev;
@@ -324,7 +321,7 @@
int i, j;
int ret;
- dev = find_ae(ae_id);
+ dev = find_ae(ae_node);
if (!dev)
return ERR_PTR(-ENODEV);
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h
index 6ca94dc..1cbcb9f 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.h
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.h
@@ -524,8 +524,11 @@
#define ring_to_dev(ring) ((ring)->q->dev->dev)
-struct hnae_handle *hnae_get_handle(struct device *owner_dev, const char *ae_id,
- u32 port_id, struct hnae_buf_ops *bops);
+struct hnae_handle *hnae_get_handle(struct device *owner_dev,
+ const struct device_node *ae_node,
+ u32 port_id,
+ struct hnae_buf_ops *bops);
+
void hnae_put_handle(struct hnae_handle *handle);
int hnae_ae_register(struct hnae_ae_dev *dev, struct module *owner);
void hnae_ae_unregister(struct hnae_ae_dev *dev);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
index 522b264..a0070d0 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
@@ -847,6 +847,7 @@
int hns_dsaf_ae_init(struct dsaf_device *dsaf_dev)
{
struct hnae_ae_dev *ae_dev = &dsaf_dev->ae_dev;
+ static atomic_t id = ATOMIC_INIT(-1);
switch (dsaf_dev->dsaf_ver) {
case AE_VERSION_1:
@@ -858,6 +859,9 @@
default:
break;
}
+
+ snprintf(ae_dev->name, AE_NAME_SIZE, "%s%d", DSAF_DEVICE_NAME,
+ (int)atomic_inc_return(&id));
ae_dev->ops = &hns_dsaf_ops;
ae_dev->dev = dsaf_dev->dev;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
index 1c33bd0..9439f04 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
@@ -35,7 +35,7 @@
int ret, i;
u32 desc_num;
u32 buf_size;
- const char *name, *mode_str;
+ const char *mode_str;
struct device_node *np = dsaf_dev->dev->of_node;
if (of_device_is_compatible(np, "hisilicon,hns-dsaf-v1"))
@@ -43,14 +43,6 @@
else
dsaf_dev->dsaf_ver = AE_VERSION_2;
- ret = of_property_read_string(np, "dsa_name", &name);
- if (ret) {
- dev_err(dsaf_dev->dev, "get dsaf name fail, ret=%d!\n", ret);
- return ret;
- }
- strncpy(dsaf_dev->ae_dev.name, name, AE_NAME_SIZE);
- dsaf_dev->ae_dev.name[AE_NAME_SIZE - 1] = '\0';
-
ret = of_property_read_string(np, "mode", &mode_str);
if (ret) {
dev_err(dsaf_dev->dev, "get dsaf mode fail, ret=%d!\n", ret);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
index 31c312f..40205b9 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
@@ -18,6 +18,7 @@
#define DSAF_DRV_NAME "hns_dsaf"
#define DSAF_MOD_VERSION "v1.0"
+#define DSAF_DEVICE_NAME "dsaf"
#define HNS_DSAF_DEBUG_NW_REG_OFFSET 0x100000
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 0e30846..3f77ff7 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -1802,7 +1802,7 @@
int ret;
h = hnae_get_handle(&priv->netdev->dev,
- priv->ae_name, priv->port_id, NULL);
+ priv->ae_node, priv->port_id, NULL);
if (IS_ERR_OR_NULL(h)) {
ret = PTR_ERR(h);
dev_dbg(priv->dev, "has not handle, register notifier!\n");
@@ -1880,13 +1880,16 @@
else
priv->enet_ver = AE_VERSION_2;
- ret = of_property_read_string(node, "ae-name", &priv->ae_name);
- if (ret)
- goto out_read_string_fail;
+ priv->ae_node = (void *)of_parse_phandle(node, "ae-handle", 0);
+ if (IS_ERR_OR_NULL(priv->ae_node)) {
+ ret = PTR_ERR(priv->ae_node);
+ dev_err(dev, "not find ae-handle\n");
+ goto out_read_prop_fail;
+ }
ret = of_property_read_u32(node, "port-id", &priv->port_id);
if (ret)
- goto out_read_string_fail;
+ goto out_read_prop_fail;
hns_init_mac_addr(ndev);
@@ -1945,7 +1948,7 @@
out_notify_fail:
(void)cancel_work_sync(&priv->service_task);
-out_read_string_fail:
+out_read_prop_fail:
free_netdev(ndev);
return ret;
}
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.h b/drivers/net/ethernet/hisilicon/hns/hns_enet.h
index 4b75270..c68ab3d 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.h
@@ -51,7 +51,7 @@
};
struct hns_nic_priv {
- const char *ae_name;
+ const struct device_node *ae_node;
u32 enet_ver;
u32 port_id;
int phy_mode;
diff --git a/drivers/net/ethernet/hp/hp100.c b/drivers/net/ethernet/hp/hp100.c
index 1d5c3e1..3daf2d4 100644
--- a/drivers/net/ethernet/hp/hp100.c
+++ b/drivers/net/ethernet/hp/hp100.c
@@ -194,7 +194,6 @@
};
#endif
-#ifdef CONFIG_EISA
static struct eisa_device_id hp100_eisa_tbl[] = {
{ "HWPF180" }, /* HP J2577 rev A */
{ "HWP1920" }, /* HP 27248B */
@@ -205,9 +204,7 @@
{ "" } /* Mandatory final entry ! */
};
MODULE_DEVICE_TABLE(eisa, hp100_eisa_tbl);
-#endif
-#ifdef CONFIG_PCI
static const struct pci_device_id hp100_pci_tbl[] = {
{PCI_VENDOR_ID_HP, PCI_DEVICE_ID_HP_J2585A, PCI_ANY_ID, PCI_ANY_ID,},
{PCI_VENDOR_ID_HP, PCI_DEVICE_ID_HP_J2585B, PCI_ANY_ID, PCI_ANY_ID,},
@@ -219,7 +216,6 @@
{} /* Terminating entry */
};
MODULE_DEVICE_TABLE(pci, hp100_pci_tbl);
-#endif
static int hp100_rx_ratio = HP100_DEFAULT_RX_RATIO;
static int hp100_priority_tx = HP100_DEFAULT_PRIORITY_TX;
@@ -2842,7 +2838,6 @@
free_netdev(d);
}
-#ifdef CONFIG_EISA
static int hp100_eisa_probe(struct device *gendev)
{
struct net_device *dev = alloc_etherdev(sizeof(struct hp100_private));
@@ -2884,9 +2879,7 @@
.remove = hp100_eisa_remove,
}
};
-#endif
-#ifdef CONFIG_PCI
static int hp100_pci_probe(struct pci_dev *pdev,
const struct pci_device_id *ent)
{
@@ -2955,7 +2948,6 @@
.probe = hp100_pci_probe,
.remove = hp100_pci_remove,
};
-#endif
/*
* module section
@@ -3032,23 +3024,17 @@
err = hp100_isa_init();
if (err && err != -ENODEV)
goto out;
-#ifdef CONFIG_EISA
err = eisa_driver_register(&hp100_eisa_driver);
if (err && err != -ENODEV)
goto out2;
-#endif
-#ifdef CONFIG_PCI
err = pci_register_driver(&hp100_pci_driver);
if (err && err != -ENODEV)
goto out3;
-#endif
out:
return err;
out3:
-#ifdef CONFIG_EISA
eisa_driver_unregister (&hp100_eisa_driver);
out2:
-#endif
hp100_isa_cleanup();
goto out;
}
@@ -3057,12 +3043,8 @@
static void __exit hp100_module_exit(void)
{
hp100_isa_cleanup();
-#ifdef CONFIG_EISA
eisa_driver_unregister (&hp100_eisa_driver);
-#endif
-#ifdef CONFIG_PCI
pci_unregister_driver (&hp100_pci_driver);
-#endif
}
module_init(hp100_module_init)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index bb4612c..8f3b53e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -7117,9 +7117,7 @@
i40e_watchdog_subtask(pf);
i40e_fdir_reinit_subtask(pf);
i40e_sync_filters_subtask(pf);
-#if IS_ENABLED(CONFIG_VXLAN) || IS_ENABLED(CONFIG_GENEVE)
i40e_sync_udp_filters_subtask(pf);
-#endif
i40e_clean_adminq_subtask(pf);
i40e_service_event_complete(pf);
@@ -8515,6 +8513,8 @@
}
#endif
+
+#if IS_ENABLED(CONFIG_VXLAN)
/**
* i40e_add_vxlan_port - Get notifications about VXLAN ports that come up
* @netdev: This physical port's netdev
@@ -8524,7 +8524,6 @@
static void i40e_add_vxlan_port(struct net_device *netdev,
sa_family_t sa_family, __be16 port)
{
-#if IS_ENABLED(CONFIG_VXLAN)
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
struct i40e_pf *pf = vsi->back;
@@ -8557,7 +8556,6 @@
pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_VXLAN;
pf->pending_udp_bitmap |= BIT_ULL(next_idx);
pf->flags |= I40E_FLAG_UDP_FILTER_SYNC;
-#endif
}
/**
@@ -8569,7 +8567,6 @@
static void i40e_del_vxlan_port(struct net_device *netdev,
sa_family_t sa_family, __be16 port)
{
-#if IS_ENABLED(CONFIG_VXLAN)
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
struct i40e_pf *pf = vsi->back;
@@ -8592,9 +8589,10 @@
netdev_warn(netdev, "vxlan port %d was not found, not deleting\n",
ntohs(port));
}
-#endif
}
+#endif
+#if IS_ENABLED(CONFIG_GENEVE)
/**
* i40e_add_geneve_port - Get notifications about GENEVE ports that come up
* @netdev: This physical port's netdev
@@ -8604,7 +8602,6 @@
static void i40e_add_geneve_port(struct net_device *netdev,
sa_family_t sa_family, __be16 port)
{
-#if IS_ENABLED(CONFIG_GENEVE)
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
struct i40e_pf *pf = vsi->back;
@@ -8639,7 +8636,6 @@
pf->flags |= I40E_FLAG_UDP_FILTER_SYNC;
dev_info(&pf->pdev->dev, "adding geneve port %d\n", ntohs(port));
-#endif
}
/**
@@ -8651,7 +8647,6 @@
static void i40e_del_geneve_port(struct net_device *netdev,
sa_family_t sa_family, __be16 port)
{
-#if IS_ENABLED(CONFIG_GENEVE)
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
struct i40e_pf *pf = vsi->back;
@@ -8677,8 +8672,8 @@
netdev_warn(netdev, "geneve port %d was not found, not deleting\n",
ntohs(port));
}
-#endif
}
+#endif
static int i40e_get_phys_port_id(struct net_device *netdev,
struct netdev_phys_item_id *ppid)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 720516b0..47bd8b3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2313,8 +2313,8 @@
struct iphdr *this_ip_hdr;
u32 network_hdr_len;
u8 l4_hdr = 0;
- struct udphdr *oudph;
- struct iphdr *oiph;
+ struct udphdr *oudph = NULL;
+ struct iphdr *oiph = NULL;
u32 l4_tunnel = 0;
if (skb->encapsulation) {
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index a0c0383..5583118 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -762,10 +762,10 @@
if (length <= 8 && (uintptr_t)data & 0x7) {
/* Copy unaligned small data fragment to TSO header data area */
- memcpy(txq->tso_hdrs + txq->tx_curr_desc * TSO_HEADER_SIZE,
+ memcpy(txq->tso_hdrs + tx_index * TSO_HEADER_SIZE,
data, length);
desc->buf_ptr = txq->tso_hdrs_dma
- + txq->tx_curr_desc * TSO_HEADER_SIZE;
+ + tx_index * TSO_HEADER_SIZE;
} else {
/* Alignment is okay, map buffer and hand off to hardware */
txq->tx_desc_mapping[tx_index] = DESC_DMA_MAP_SINGLE;
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index fabc8df..662c2ee 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -11,28 +11,28 @@
* warranty of any kind, whether express or implied.
*/
-#include <linux/kernel.h>
-#include <linux/netdevice.h>
+#include <linux/clk.h>
+#include <linux/cpu.h>
#include <linux/etherdevice.h>
-#include <linux/platform_device.h>
-#include <linux/skbuff.h>
+#include <linux/if_vlan.h>
#include <linux/inetdevice.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
#include <linux/mbus.h>
#include <linux/module.h>
-#include <linux/interrupt.h>
-#include <linux/if_vlan.h>
-#include <net/ip.h>
-#include <net/ipv6.h>
-#include <linux/io.h>
-#include <net/tso.h>
+#include <linux/netdevice.h>
#include <linux/of.h>
+#include <linux/of_address.h>
#include <linux/of_irq.h>
#include <linux/of_mdio.h>
#include <linux/of_net.h>
-#include <linux/of_address.h>
#include <linux/phy.h>
-#include <linux/clk.h>
-#include <linux/cpu.h>
+#include <linux/platform_device.h>
+#include <linux/skbuff.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/tso.h>
/* Registers */
#define MVNETA_RXQ_CONFIG_REG(q) (0x1400 + ((q) << 2))
@@ -373,6 +373,8 @@
/* Core clock */
struct clk *clk;
+ /* AXI clock */
+ struct clk *clk_bus;
u8 mcast_count[256];
u16 tx_ring_size;
u16 rx_ring_size;
@@ -3242,26 +3244,25 @@
const struct mvneta_statistic *s;
void __iomem *base = pp->base;
u32 high, low, val;
+ u64 val64;
int i;
for (i = 0, s = mvneta_statistics;
s < mvneta_statistics + ARRAY_SIZE(mvneta_statistics);
s++, i++) {
- val = 0;
-
switch (s->type) {
case T_REG_32:
val = readl_relaxed(base + s->offset);
+ pp->ethtool_stats[i] += val;
break;
case T_REG_64:
/* Docs say to read low 32-bit then high */
low = readl_relaxed(base + s->offset);
high = readl_relaxed(base + s->offset + 4);
- val = (u64)high << 32 | low;
+ val64 = (u64)high << 32 | low;
+ pp->ethtool_stats[i] += val64;
break;
}
-
- pp->ethtool_stats[i] += val;
}
}
@@ -3605,7 +3606,9 @@
pp->indir[0] = rxq_def;
- pp->clk = devm_clk_get(&pdev->dev, NULL);
+ pp->clk = devm_clk_get(&pdev->dev, "core");
+ if (IS_ERR(pp->clk))
+ pp->clk = devm_clk_get(&pdev->dev, NULL);
if (IS_ERR(pp->clk)) {
err = PTR_ERR(pp->clk);
goto err_put_phy_node;
@@ -3613,6 +3616,10 @@
clk_prepare_enable(pp->clk);
+ pp->clk_bus = devm_clk_get(&pdev->dev, "bus");
+ if (!IS_ERR(pp->clk_bus))
+ clk_prepare_enable(pp->clk_bus);
+
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
pp->base = devm_ioremap_resource(&pdev->dev, res);
if (IS_ERR(pp->base)) {
@@ -3724,6 +3731,7 @@
err_free_ports:
free_percpu(pp->ports);
err_clk:
+ clk_disable_unprepare(pp->clk_bus);
clk_disable_unprepare(pp->clk);
err_put_phy_node:
of_node_put(phy_node);
@@ -3741,6 +3749,7 @@
struct mvneta_port *pp = netdev_priv(dev);
unregister_netdev(dev);
+ clk_disable_unprepare(pp->clk_bus);
clk_disable_unprepare(pp->clk);
free_percpu(pp->ports);
free_percpu(pp->stats);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 0c52372..bb77e22 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -1044,6 +1044,92 @@
mlxsw_reg_sftr_port_mask_set(payload, port, 1);
}
+/* SFDF - Switch Filtering DB Flush
+ * --------------------------------
+ * The switch filtering DB flush register is used to flush the FDB.
+ * Note that FDB notifications are flushed as well.
+ */
+#define MLXSW_REG_SFDF_ID 0x2013
+#define MLXSW_REG_SFDF_LEN 0x14
+
+static const struct mlxsw_reg_info mlxsw_reg_sfdf = {
+ .id = MLXSW_REG_SFDF_ID,
+ .len = MLXSW_REG_SFDF_LEN,
+};
+
+/* reg_sfdf_swid
+ * Switch partition ID.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, sfdf, swid, 0x00, 24, 8);
+
+enum mlxsw_reg_sfdf_flush_type {
+ MLXSW_REG_SFDF_FLUSH_PER_SWID,
+ MLXSW_REG_SFDF_FLUSH_PER_FID,
+ MLXSW_REG_SFDF_FLUSH_PER_PORT,
+ MLXSW_REG_SFDF_FLUSH_PER_PORT_AND_FID,
+ MLXSW_REG_SFDF_FLUSH_PER_LAG,
+ MLXSW_REG_SFDF_FLUSH_PER_LAG_AND_FID,
+};
+
+/* reg_sfdf_flush_type
+ * Flush type.
+ * 0 - All SWID dynamic entries are flushed.
+ * 1 - All FID dynamic entries are flushed.
+ * 2 - All dynamic entries pointing to port are flushed.
+ * 3 - All FID dynamic entries pointing to port are flushed.
+ * 4 - All dynamic entries pointing to LAG are flushed.
+ * 5 - All FID dynamic entries pointing to LAG are flushed.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, sfdf, flush_type, 0x04, 28, 4);
+
+/* reg_sfdf_flush_static
+ * Static.
+ * 0 - Flush only dynamic entries.
+ * 1 - Flush both dynamic and static entries.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, sfdf, flush_static, 0x04, 24, 1);
+
+static inline void mlxsw_reg_sfdf_pack(char *payload,
+ enum mlxsw_reg_sfdf_flush_type type)
+{
+ MLXSW_REG_ZERO(sfdf, payload);
+ mlxsw_reg_sfdf_flush_type_set(payload, type);
+ mlxsw_reg_sfdf_flush_static_set(payload, true);
+}
+
+/* reg_sfdf_fid
+ * FID to flush.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, sfdf, fid, 0x0C, 0, 16);
+
+/* reg_sfdf_system_port
+ * Port to flush.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, sfdf, system_port, 0x0C, 0, 16);
+
+/* reg_sfdf_port_fid_system_port
+ * Port to flush, pointed to by FID.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, sfdf, port_fid_system_port, 0x08, 0, 16);
+
+/* reg_sfdf_lag_id
+ * LAG ID to flush.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, sfdf, lag_id, 0x0C, 0, 10);
+
+/* reg_sfdf_lag_fid_lag_id
+ * LAG ID to flush, pointed to by FID.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, sfdf, lag_fid_lag_id, 0x08, 0, 10);
+
/* SLDR - Switch LAG Descriptor Register
* -----------------------------------------
* The switch LAG descriptor register is populated by LAG descriptors.
@@ -1701,20 +1787,20 @@
* Module number.
* Access: RW
*/
-MLXSW_ITEM32_INDEXED(reg, pmlp, module, 0x04, 0, 8, 0x04, 0, false);
+MLXSW_ITEM32_INDEXED(reg, pmlp, module, 0x04, 0, 8, 0x04, 0x00, false);
/* reg_pmlp_tx_lane
* Tx Lane. When rxtx field is cleared, this field is used for Rx as well.
* Access: RW
*/
-MLXSW_ITEM32_INDEXED(reg, pmlp, tx_lane, 0x04, 16, 2, 0x04, 16, false);
+MLXSW_ITEM32_INDEXED(reg, pmlp, tx_lane, 0x04, 16, 2, 0x04, 0x00, false);
/* reg_pmlp_rx_lane
* Rx Lane. When rxtx field is cleared, this field is ignored and Rx lane is
* equal to Tx lane.
* Access: RW
*/
-MLXSW_ITEM32_INDEXED(reg, pmlp, rx_lane, 0x04, 24, 2, 0x04, 24, false);
+MLXSW_ITEM32_INDEXED(reg, pmlp, rx_lane, 0x04, 24, 2, 0x04, 0x00, false);
static inline void mlxsw_reg_pmlp_pack(char *payload, u8 local_port)
{
@@ -3121,6 +3207,8 @@
return "SFGC";
case MLXSW_REG_SFTR_ID:
return "SFTR";
+ case MLXSW_REG_SFDF_ID:
+ return "SFDF";
case MLXSW_REG_SLDR_ID:
return "SLDR";
case MLXSW_REG_SLCR_ID:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index ce6845d..217856b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1979,6 +1979,115 @@
.profile = &mlxsw_sp_config_profile,
};
+static int
+mlxsw_sp_port_fdb_flush_by_port(const struct mlxsw_sp_port *mlxsw_sp_port)
+{
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+ char sfdf_pl[MLXSW_REG_SFDF_LEN];
+
+ mlxsw_reg_sfdf_pack(sfdf_pl, MLXSW_REG_SFDF_FLUSH_PER_PORT);
+ mlxsw_reg_sfdf_system_port_set(sfdf_pl, mlxsw_sp_port->local_port);
+
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl);
+}
+
+static int
+mlxsw_sp_port_fdb_flush_by_port_fid(const struct mlxsw_sp_port *mlxsw_sp_port,
+ u16 fid)
+{
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+ char sfdf_pl[MLXSW_REG_SFDF_LEN];
+
+ mlxsw_reg_sfdf_pack(sfdf_pl, MLXSW_REG_SFDF_FLUSH_PER_PORT_AND_FID);
+ mlxsw_reg_sfdf_fid_set(sfdf_pl, fid);
+ mlxsw_reg_sfdf_port_fid_system_port_set(sfdf_pl,
+ mlxsw_sp_port->local_port);
+
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl);
+}
+
+static int
+mlxsw_sp_port_fdb_flush_by_lag_id(const struct mlxsw_sp_port *mlxsw_sp_port)
+{
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+ char sfdf_pl[MLXSW_REG_SFDF_LEN];
+
+ mlxsw_reg_sfdf_pack(sfdf_pl, MLXSW_REG_SFDF_FLUSH_PER_LAG);
+ mlxsw_reg_sfdf_lag_id_set(sfdf_pl, mlxsw_sp_port->lag_id);
+
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl);
+}
+
+static int
+mlxsw_sp_port_fdb_flush_by_lag_id_fid(const struct mlxsw_sp_port *mlxsw_sp_port,
+ u16 fid)
+{
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+ char sfdf_pl[MLXSW_REG_SFDF_LEN];
+
+ mlxsw_reg_sfdf_pack(sfdf_pl, MLXSW_REG_SFDF_FLUSH_PER_LAG_AND_FID);
+ mlxsw_reg_sfdf_fid_set(sfdf_pl, fid);
+ mlxsw_reg_sfdf_lag_fid_lag_id_set(sfdf_pl, mlxsw_sp_port->lag_id);
+
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl);
+}
+
+static int
+__mlxsw_sp_port_fdb_flush(const struct mlxsw_sp_port *mlxsw_sp_port)
+{
+ int err, last_err = 0;
+ u16 vid;
+
+ for (vid = 1; vid < VLAN_N_VID - 1; vid++) {
+ err = mlxsw_sp_port_fdb_flush_by_port_fid(mlxsw_sp_port, vid);
+ if (err)
+ last_err = err;
+ }
+
+ return last_err;
+}
+
+static int
+__mlxsw_sp_port_fdb_flush_lagged(const struct mlxsw_sp_port *mlxsw_sp_port)
+{
+ int err, last_err = 0;
+ u16 vid;
+
+ for (vid = 1; vid < VLAN_N_VID - 1; vid++) {
+ err = mlxsw_sp_port_fdb_flush_by_lag_id_fid(mlxsw_sp_port, vid);
+ if (err)
+ last_err = err;
+ }
+
+ return last_err;
+}
+
+static int mlxsw_sp_port_fdb_flush(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+ if (!list_empty(&mlxsw_sp_port->vports_list))
+ if (mlxsw_sp_port->lagged)
+ return __mlxsw_sp_port_fdb_flush_lagged(mlxsw_sp_port);
+ else
+ return __mlxsw_sp_port_fdb_flush(mlxsw_sp_port);
+ else
+ if (mlxsw_sp_port->lagged)
+ return mlxsw_sp_port_fdb_flush_by_lag_id(mlxsw_sp_port);
+ else
+ return mlxsw_sp_port_fdb_flush_by_port(mlxsw_sp_port);
+}
+
+static int mlxsw_sp_vport_fdb_flush(struct mlxsw_sp_port *mlxsw_sp_vport)
+{
+ u16 vfid = mlxsw_sp_vport_vfid_get(mlxsw_sp_vport);
+ u16 fid = mlxsw_sp_vfid_to_fid(vfid);
+
+ if (mlxsw_sp_vport->lagged)
+ return mlxsw_sp_port_fdb_flush_by_lag_id_fid(mlxsw_sp_vport,
+ fid);
+ else
+ return mlxsw_sp_port_fdb_flush_by_port_fid(mlxsw_sp_vport, fid);
+}
+
static bool mlxsw_sp_port_dev_check(const struct net_device *dev)
{
return dev->netdev_ops == &mlxsw_sp_port_netdev_ops;
@@ -2006,10 +2115,14 @@
return 0;
}
-static int mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port)
+static int mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port,
+ bool flush_fdb)
{
struct net_device *dev = mlxsw_sp_port->dev;
+ if (flush_fdb && mlxsw_sp_port_fdb_flush(mlxsw_sp_port))
+ netdev_err(mlxsw_sp_port->dev, "Failed to flush FDB\n");
+
mlxsw_sp_port->learning = 0;
mlxsw_sp_port->learning_sync = 0;
mlxsw_sp_port->uc_flood = 0;
@@ -2200,10 +2313,15 @@
return err;
}
+static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport,
+ struct net_device *br_dev,
+ bool flush_fdb);
+
static int mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port,
struct net_device *lag_dev)
{
struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+ struct mlxsw_sp_port *mlxsw_sp_vport;
struct mlxsw_sp_upper *lag;
u16 lag_id = mlxsw_sp_port->lag_id;
int err;
@@ -2220,7 +2338,32 @@
if (err)
return err;
+ /* In case we leave a LAG device that has bridges built on top,
+ * then their teardown sequence is never issued and we need to
+ * invoke the necessary cleanup routines ourselves.
+ */
+ list_for_each_entry(mlxsw_sp_vport, &mlxsw_sp_port->vports_list,
+ vport.list) {
+ struct net_device *br_dev;
+
+ if (!mlxsw_sp_vport->bridged)
+ continue;
+
+ br_dev = mlxsw_sp_vport_br_get(mlxsw_sp_vport);
+ mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport, br_dev, false);
+ }
+
+ if (mlxsw_sp_port->bridged) {
+ mlxsw_sp_port_active_vlans_del(mlxsw_sp_port);
+ mlxsw_sp_port_bridge_leave(mlxsw_sp_port, false);
+
+ if (lag->ref_count == 1)
+ mlxsw_sp_master_bridge_dec(mlxsw_sp, NULL);
+ }
+
if (lag->ref_count == 1) {
+ if (mlxsw_sp_port_fdb_flush_by_lag_id(mlxsw_sp_port))
+ netdev_err(mlxsw_sp_port->dev, "Failed to flush FDB\n");
err = mlxsw_sp_lag_destroy(mlxsw_sp, lag_id);
if (err)
return err;
@@ -2272,9 +2415,6 @@
return mlxsw_sp_port_lag_tx_en_set(mlxsw_sp_port, info->tx_enabled);
}
-static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport,
- struct net_device *br_dev);
-
static int mlxsw_sp_port_vlan_link(struct mlxsw_sp_port *mlxsw_sp_port,
struct net_device *vlan_dev)
{
@@ -2312,7 +2452,7 @@
struct net_device *br_dev;
br_dev = mlxsw_sp_vport_br_get(mlxsw_sp_vport);
- mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport, br_dev);
+ mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport, br_dev, true);
}
mlxsw_sp_vport->dev = mlxsw_sp_port->dev;
@@ -2374,7 +2514,8 @@
}
mlxsw_sp_master_bridge_inc(mlxsw_sp, upper_dev);
} else {
- err = mlxsw_sp_port_bridge_leave(mlxsw_sp_port);
+ err = mlxsw_sp_port_bridge_leave(mlxsw_sp_port,
+ true);
mlxsw_sp_master_bridge_dec(mlxsw_sp, upper_dev);
if (err) {
netdev_err(dev, "Failed to leave bridge\n");
@@ -2541,7 +2682,8 @@
}
static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport,
- struct net_device *br_dev)
+ struct net_device *br_dev,
+ bool flush_fdb)
{
struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
u16 vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport);
@@ -2604,6 +2746,9 @@
goto err_vport_flood_set;
}
+ if (flush_fdb && mlxsw_sp_vport_fdb_flush(mlxsw_sp_vport))
+ netdev_err(dev, "Failed to flush FDB\n");
+
/* Switch between the vFIDs and destroy the old one if needed. */
new_vfid->nr_vports++;
mlxsw_sp_vport->vport.vfid = new_vfid;
@@ -2777,7 +2922,7 @@
if (!mlxsw_sp_vport)
return NOTIFY_DONE;
err = mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport,
- upper_dev);
+ upper_dev, true);
if (err) {
netdev_err(dev, "Failed to leave bridge\n");
return NOTIFY_BAD;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index a23dc61..7f42eb1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -120,7 +120,6 @@
} fdb_notify;
#define MLXSW_SP_DEFAULT_AGEING_TIME 300
u32 ageing_time;
- struct mutex fdb_lock; /* Make sure FDB sessions are atomic. */
struct mlxsw_sp_upper master_bridge;
struct mlxsw_sp_upper lags[MLXSW_SP_LAG_MAX];
};
@@ -254,5 +253,6 @@
__be16 __always_unused proto, u16 vid);
int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 vfid,
bool set, bool only_uc);
+void mlxsw_sp_port_active_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port);
#endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 45479ef..e492ca2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -45,6 +45,7 @@
#include <linux/if_bridge.h>
#include <linux/workqueue.h>
#include <linux/jiffies.h>
+#include <linux/rtnetlink.h>
#include <net/switchdev.h>
#include "spectrum.h"
@@ -124,14 +125,14 @@
int err;
switch (state) {
- case BR_STATE_DISABLED: /* fall-through */
case BR_STATE_FORWARDING:
spms_state = MLXSW_REG_SPMS_STATE_FORWARDING;
break;
- case BR_STATE_LISTENING: /* fall-through */
case BR_STATE_LEARNING:
spms_state = MLXSW_REG_SPMS_STATE_LEARNING;
break;
+ case BR_STATE_LISTENING: /* fall-through */
+ case BR_STATE_DISABLED: /* fall-through */
case BR_STATE_BLOCKING:
spms_state = MLXSW_REG_SPMS_STATE_DISCARDING;
break;
@@ -936,6 +937,14 @@
vlan->vid_begin, vlan->vid_end, false);
}
+void mlxsw_sp_port_active_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+ u16 vid;
+
+ for_each_set_bit(vid, mlxsw_sp_port->active_vlans, VLAN_N_VID)
+ __mlxsw_sp_port_vlans_del(mlxsw_sp_port, vid, vid, false);
+}
+
static int
mlxsw_sp_port_fdb_static_del(struct mlxsw_sp_port *mlxsw_sp_port,
const struct switchdev_obj_port_fdb *fdb)
@@ -1040,10 +1049,12 @@
static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port,
struct switchdev_obj_port_fdb *fdb,
- switchdev_obj_dump_cb_t *cb)
+ switchdev_obj_dump_cb_t *cb,
+ struct net_device *orig_dev)
{
struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
- u16 vport_vid = 0, vport_fid = 0;
+ struct mlxsw_sp_port *tmp;
+ u16 vport_fid = 0;
char *sfd_pl;
char mac[ETH_ALEN];
u16 fid;
@@ -1058,13 +1069,11 @@
if (!sfd_pl)
return -ENOMEM;
- mutex_lock(&mlxsw_sp_port->mlxsw_sp->fdb_lock);
if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) {
u16 tmp;
tmp = mlxsw_sp_vport_vfid_get(mlxsw_sp_port);
vport_fid = mlxsw_sp_vfid_to_fid(tmp);
- vport_vid = mlxsw_sp_vport_vid_get(mlxsw_sp_port);
}
mlxsw_reg_sfd_pack(sfd_pl, MLXSW_REG_SFD_OP_QUERY_DUMP, 0);
@@ -1088,12 +1097,13 @@
mlxsw_reg_sfd_uc_unpack(sfd_pl, i, mac, &fid,
&local_port);
if (local_port == mlxsw_sp_port->local_port) {
- if (vport_fid && vport_fid != fid)
- continue;
- else if (vport_fid)
- fdb->vid = vport_vid;
- else
+ if (vport_fid && vport_fid == fid)
+ fdb->vid = 0;
+ else if (!vport_fid &&
+ !mlxsw_sp_fid_is_vfid(fid))
fdb->vid = fid;
+ else
+ continue;
ether_addr_copy(fdb->addr, mac);
fdb->ndm_state = NUD_REACHABLE;
err = cb(&fdb->obj);
@@ -1104,14 +1114,22 @@
case MLXSW_REG_SFD_REC_TYPE_UNICAST_LAG:
mlxsw_reg_sfd_uc_lag_unpack(sfd_pl, i,
mac, &fid, &lag_id);
- if (mlxsw_sp_port ==
- mlxsw_sp_lag_rep_port(mlxsw_sp, lag_id)) {
- if (vport_fid && vport_fid != fid)
+ tmp = mlxsw_sp_lag_rep_port(mlxsw_sp, lag_id);
+ if (tmp && tmp->local_port ==
+ mlxsw_sp_port->local_port) {
+ /* LAG records can only point to LAG
+ * devices or VLAN devices on top.
+ */
+ if (!netif_is_lag_master(orig_dev) &&
+ !is_vlan_dev(orig_dev))
continue;
- else if (vport_fid)
- fdb->vid = vport_vid;
- else
+ if (vport_fid && vport_fid == fid)
+ fdb->vid = 0;
+ else if (!vport_fid &&
+ !mlxsw_sp_fid_is_vfid(fid))
fdb->vid = fid;
+ else
+ continue;
ether_addr_copy(fdb->addr, mac);
fdb->ndm_state = NUD_REACHABLE;
err = cb(&fdb->obj);
@@ -1124,7 +1142,6 @@
} while (num_rec == MLXSW_REG_SFD_REC_MAX_COUNT);
out:
- mutex_unlock(&mlxsw_sp_port->mlxsw_sp->fdb_lock);
kfree(sfd_pl);
return stored_err ? stored_err : err;
}
@@ -1176,7 +1193,8 @@
break;
case SWITCHDEV_OBJ_ID_PORT_FDB:
err = mlxsw_sp_port_fdb_dump(mlxsw_sp_port,
- SWITCHDEV_OBJ_PORT_FDB(obj), cb);
+ SWITCHDEV_OBJ_PORT_FDB(obj), cb,
+ obj->orig_dev);
break;
default:
err = -EOPNOTSUPP;
@@ -1194,14 +1212,14 @@
.switchdev_port_obj_dump = mlxsw_sp_port_obj_dump,
};
-static void mlxsw_sp_fdb_call_notifiers(bool learning, bool learning_sync,
- bool adding, char *mac, u16 vid,
+static void mlxsw_sp_fdb_call_notifiers(bool learning_sync, bool adding,
+ char *mac, u16 vid,
struct net_device *dev)
{
struct switchdev_notifier_fdb_info info;
unsigned long notifier_type;
- if (learning && learning_sync) {
+ if (learning_sync) {
info.addr = mac;
info.vid = vid;
notifier_type = adding ? SWITCHDEV_FDB_ADD : SWITCHDEV_FDB_DEL;
@@ -1237,7 +1255,7 @@
netdev_err(mlxsw_sp_port->dev, "Failed to find a matching vPort following FDB notification\n");
goto just_remove;
}
- vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport);
+ vid = 0;
/* Override the physical port with the vPort. */
mlxsw_sp_port = mlxsw_sp_vport;
} else {
@@ -1257,8 +1275,7 @@
if (!do_notification)
return;
- mlxsw_sp_fdb_call_notifiers(mlxsw_sp_port->learning,
- mlxsw_sp_port->learning_sync,
+ mlxsw_sp_fdb_call_notifiers(mlxsw_sp_port->learning_sync,
adding, mac, vid, mlxsw_sp_port->dev);
return;
@@ -1273,6 +1290,7 @@
bool adding)
{
struct mlxsw_sp_port *mlxsw_sp_port;
+ struct net_device *dev;
char mac[ETH_ALEN];
u16 lag_vid = 0;
u16 lag_id;
@@ -1298,11 +1316,13 @@
goto just_remove;
}
- vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport);
- lag_vid = vid;
+ lag_vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport);
+ dev = mlxsw_sp_vport->dev;
+ vid = 0;
/* Override the physical port with the vPort. */
mlxsw_sp_port = mlxsw_sp_vport;
} else {
+ dev = mlxsw_sp_lag_get(mlxsw_sp, lag_id)->dev;
vid = fid;
}
@@ -1319,10 +1339,8 @@
if (!do_notification)
return;
- mlxsw_sp_fdb_call_notifiers(mlxsw_sp_port->learning,
- mlxsw_sp_port->learning_sync,
- adding, mac, vid,
- mlxsw_sp_lag_get(mlxsw_sp, lag_id)->dev);
+ mlxsw_sp_fdb_call_notifiers(mlxsw_sp_port->learning_sync, adding, mac,
+ vid, dev);
return;
just_remove:
@@ -1374,7 +1392,7 @@
mlxsw_sp = container_of(work, struct mlxsw_sp, fdb_notify.dw.work);
- mutex_lock(&mlxsw_sp->fdb_lock);
+ rtnl_lock();
do {
mlxsw_reg_sfn_pack(sfn_pl);
err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(sfn), sfn_pl);
@@ -1387,7 +1405,7 @@
mlxsw_sp_fdb_notify_rec_process(mlxsw_sp, sfn_pl, i);
} while (num_rec);
- mutex_unlock(&mlxsw_sp->fdb_lock);
+ rtnl_unlock();
kfree(sfn_pl);
mlxsw_sp_fdb_notify_work_schedule(mlxsw_sp);
@@ -1402,7 +1420,6 @@
dev_err(mlxsw_sp->bus_info->dev, "Failed to set default ageing time\n");
return err;
}
- mutex_init(&mlxsw_sp->fdb_lock);
INIT_DELAYED_WORK(&mlxsw_sp->fdb_notify.dw, mlxsw_sp_fdb_notify_work);
mlxsw_sp->fdb_notify.interval = MLXSW_SP_DEFAULT_LEARNING_INTERVAL;
mlxsw_sp_fdb_notify_work_schedule(mlxsw_sp);
diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c
index a10c928..00cfd95 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.c
+++ b/drivers/net/ethernet/moxa/moxart_ether.c
@@ -28,6 +28,16 @@
#include "moxart_ether.h"
+static inline void moxart_desc_write(u32 data, u32 *desc)
+{
+ *desc = cpu_to_le32(data);
+}
+
+static inline u32 moxart_desc_read(u32 *desc)
+{
+ return le32_to_cpu(*desc);
+}
+
static inline void moxart_emac_write(struct net_device *ndev,
unsigned int reg, unsigned long value)
{
@@ -112,7 +122,7 @@
static void moxart_mac_setup_desc_ring(struct net_device *ndev)
{
struct moxart_mac_priv_t *priv = netdev_priv(ndev);
- void __iomem *desc;
+ void *desc;
int i;
for (i = 0; i < TX_DESC_NUM; i++) {
@@ -121,7 +131,7 @@
priv->tx_buf[i] = priv->tx_buf_base + priv->tx_buf_size * i;
}
- writel(TX_DESC1_END, desc + TX_REG_OFFSET_DESC1);
+ moxart_desc_write(TX_DESC1_END, desc + TX_REG_OFFSET_DESC1);
priv->tx_head = 0;
priv->tx_tail = 0;
@@ -129,8 +139,8 @@
for (i = 0; i < RX_DESC_NUM; i++) {
desc = priv->rx_desc_base + i * RX_REG_DESC_SIZE;
memset(desc, 0, RX_REG_DESC_SIZE);
- writel(RX_DESC0_DMA_OWN, desc + RX_REG_OFFSET_DESC0);
- writel(RX_BUF_SIZE & RX_DESC1_BUF_SIZE_MASK,
+ moxart_desc_write(RX_DESC0_DMA_OWN, desc + RX_REG_OFFSET_DESC0);
+ moxart_desc_write(RX_BUF_SIZE & RX_DESC1_BUF_SIZE_MASK,
desc + RX_REG_OFFSET_DESC1);
priv->rx_buf[i] = priv->rx_buf_base + priv->rx_buf_size * i;
@@ -141,12 +151,12 @@
if (dma_mapping_error(&ndev->dev, priv->rx_mapping[i]))
netdev_err(ndev, "DMA mapping error\n");
- writel(priv->rx_mapping[i],
+ moxart_desc_write(priv->rx_mapping[i],
desc + RX_REG_OFFSET_DESC2 + RX_DESC2_ADDRESS_PHYS);
- writel(priv->rx_buf[i],
+ moxart_desc_write((uintptr_t)priv->rx_buf[i],
desc + RX_REG_OFFSET_DESC2 + RX_DESC2_ADDRESS_VIRT);
}
- writel(RX_DESC1_END, desc + RX_REG_OFFSET_DESC1);
+ moxart_desc_write(RX_DESC1_END, desc + RX_REG_OFFSET_DESC1);
priv->rx_head = 0;
@@ -201,14 +211,15 @@
napi);
struct net_device *ndev = priv->ndev;
struct sk_buff *skb;
- void __iomem *desc;
+ void *desc;
unsigned int desc0, len;
int rx_head = priv->rx_head;
int rx = 0;
while (rx < budget) {
desc = priv->rx_desc_base + (RX_REG_DESC_SIZE * rx_head);
- desc0 = readl(desc + RX_REG_OFFSET_DESC0);
+ desc0 = moxart_desc_read(desc + RX_REG_OFFSET_DESC0);
+ rmb(); /* ensure desc0 is up to date */
if (desc0 & RX_DESC0_DMA_OWN)
break;
@@ -250,7 +261,8 @@
priv->stats.multicast++;
rx_next:
- writel(RX_DESC0_DMA_OWN, desc + RX_REG_OFFSET_DESC0);
+ wmb(); /* prevent setting ownership back too early */
+ moxart_desc_write(RX_DESC0_DMA_OWN, desc + RX_REG_OFFSET_DESC0);
rx_head = RX_NEXT(rx_head);
priv->rx_head = rx_head;
@@ -310,7 +322,7 @@
static int moxart_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
{
struct moxart_mac_priv_t *priv = netdev_priv(ndev);
- void __iomem *desc;
+ void *desc;
unsigned int len;
unsigned int tx_head = priv->tx_head;
u32 txdes1;
@@ -319,11 +331,12 @@
desc = priv->tx_desc_base + (TX_REG_DESC_SIZE * tx_head);
spin_lock_irq(&priv->txlock);
- if (readl(desc + TX_REG_OFFSET_DESC0) & TX_DESC0_DMA_OWN) {
+ 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++;
goto out_unlock;
}
+ rmb(); /* ensure data is only read that had TX_DESC0_DMA_OWN cleared */
len = skb->len > TX_BUF_SIZE ? TX_BUF_SIZE : skb->len;
@@ -337,9 +350,9 @@
priv->tx_len[tx_head] = len;
priv->tx_skb[tx_head] = skb;
- writel(priv->tx_mapping[tx_head],
+ moxart_desc_write(priv->tx_mapping[tx_head],
desc + TX_REG_OFFSET_DESC2 + TX_DESC2_ADDRESS_PHYS);
- writel(skb->data,
+ moxart_desc_write((uintptr_t)skb->data,
desc + TX_REG_OFFSET_DESC2 + TX_DESC2_ADDRESS_VIRT);
if (skb->len < ETH_ZLEN) {
@@ -354,8 +367,9 @@
txdes1 = TX_DESC1_LTS | TX_DESC1_FTS | (len & TX_DESC1_BUF_SIZE_MASK);
if (tx_head == TX_DESC_NUM_MASK)
txdes1 |= TX_DESC1_END;
- writel(txdes1, desc + TX_REG_OFFSET_DESC1);
- writel(TX_DESC0_DMA_OWN, desc + TX_REG_OFFSET_DESC0);
+ moxart_desc_write(txdes1, desc + TX_REG_OFFSET_DESC1);
+ wmb(); /* flush descriptor before transferring ownership */
+ moxart_desc_write(TX_DESC0_DMA_OWN, desc + TX_REG_OFFSET_DESC0);
/* start to send packet */
writel(0xffffffff, priv->base + REG_TX_POLL_DEMAND);
diff --git a/drivers/net/ethernet/moxa/moxart_ether.h b/drivers/net/ethernet/moxa/moxart_ether.h
index 2be9280..93a9563 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.h
+++ b/drivers/net/ethernet/moxa/moxart_ether.h
@@ -300,7 +300,7 @@
dma_addr_t rx_base;
dma_addr_t rx_mapping[RX_DESC_NUM];
- void __iomem *rx_desc_base;
+ void *rx_desc_base;
unsigned char *rx_buf_base;
unsigned char *rx_buf[RX_DESC_NUM];
unsigned int rx_head;
@@ -308,7 +308,7 @@
dma_addr_t tx_base;
dma_addr_t tx_mapping[TX_DESC_NUM];
- void __iomem *tx_desc_base;
+ void *tx_desc_base;
unsigned char *tx_buf_base;
unsigned char *tx_buf[RX_DESC_NUM];
unsigned int tx_head;
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c
index 50d5604..e0993eb 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-main.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c
@@ -2223,8 +2223,6 @@
return IRQ_NONE;
}
-#ifdef CONFIG_PCI_MSI
-
static irqreturn_t vxge_tx_msix_handle(int irq, void *dev_id)
{
struct vxge_fifo *fifo = (struct vxge_fifo *)dev_id;
@@ -2442,16 +2440,13 @@
if (vdev->config.intr_type == MSI_X)
pci_disable_msix(vdev->pdev);
}
-#endif
static void vxge_rem_isr(struct vxgedev *vdev)
{
-#ifdef CONFIG_PCI_MSI
- if (vdev->config.intr_type == MSI_X) {
+ if (IS_ENABLED(CONFIG_PCI_MSI) &&
+ vdev->config.intr_type == MSI_X) {
vxge_rem_msix_isr(vdev);
- } else
-#endif
- if (vdev->config.intr_type == INTA) {
+ } else if (vdev->config.intr_type == INTA) {
synchronize_irq(vdev->pdev->irq);
free_irq(vdev->pdev->irq, vdev);
}
@@ -2460,11 +2455,10 @@
static int vxge_add_isr(struct vxgedev *vdev)
{
int ret = 0;
-#ifdef CONFIG_PCI_MSI
int vp_idx = 0, intr_idx = 0, intr_cnt = 0, msix_idx = 0, irq_req = 0;
int pci_fun = PCI_FUNC(vdev->pdev->devfn);
- if (vdev->config.intr_type == MSI_X)
+ if (IS_ENABLED(CONFIG_PCI_MSI) && vdev->config.intr_type == MSI_X)
ret = vxge_enable_msix(vdev);
if (ret) {
@@ -2475,7 +2469,7 @@
vdev->config.intr_type = INTA;
}
- if (vdev->config.intr_type == MSI_X) {
+ if (IS_ENABLED(CONFIG_PCI_MSI) && vdev->config.intr_type == MSI_X) {
for (intr_idx = 0;
intr_idx < (vdev->no_of_vpath *
VXGE_HW_VPATH_MSIX_ACTIVE); intr_idx++) {
@@ -2576,9 +2570,8 @@
vdev->vxge_entries[intr_cnt].in_use = 1;
vdev->vxge_entries[intr_cnt].arg = &vdev->vpaths[0];
}
-INTA_MODE:
-#endif
+INTA_MODE:
if (vdev->config.intr_type == INTA) {
snprintf(vdev->desc[0], VXGE_INTR_STRLEN,
"%s:vxge:INTA", vdev->ndev->name);
@@ -3889,12 +3882,12 @@
if (max_mac_vpath > VXGE_MAX_MAC_ADDR_COUNT)
max_mac_vpath = VXGE_MAX_MAC_ADDR_COUNT;
-#ifndef CONFIG_PCI_MSI
- vxge_debug_init(VXGE_ERR,
- "%s: This Kernel does not support "
- "MSI-X. Defaulting to INTA", VXGE_DRIVER_NAME);
- *intr_type = INTA;
-#endif
+ if (!IS_ENABLED(CONFIG_PCI_MSI)) {
+ vxge_debug_init(VXGE_ERR,
+ "%s: This Kernel does not support "
+ "MSI-X. Defaulting to INTA", VXGE_DRIVER_NAME);
+ *intr_type = INTA;
+ }
/* Configure whether MSI-X or IRQL. */
switch (*intr_type) {
diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c
index a4ab71d..166a7fc 100644
--- a/drivers/net/ethernet/rocker/rocker.c
+++ b/drivers/net/ethernet/rocker/rocker.c
@@ -3531,12 +3531,14 @@
info.addr = lw->addr;
info.vid = lw->vid;
+ rtnl_lock();
if (learned && removing)
call_switchdev_notifiers(SWITCHDEV_FDB_DEL,
lw->rocker_port->dev, &info.info);
else if (learned && !removing)
call_switchdev_notifiers(SWITCHDEV_FDB_ADD,
lw->rocker_port->dev, &info.info);
+ rtnl_unlock();
rocker_port_kfree(lw->trans, work);
}
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index cc106d8..23fa298 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -389,17 +389,27 @@
if (vio_version_after_eq(&port->vio, 1, 8)) {
struct vio_net_dext *dext = vio_net_ext(desc);
+ skb_reset_network_header(skb);
+
if (dext->flags & VNET_PKT_HCK_IPV4_HDRCKSUM) {
if (skb->protocol == ETH_P_IP) {
- struct iphdr *iph = (struct iphdr *)skb->data;
+ struct iphdr *iph = ip_hdr(skb);
iph->check = 0;
ip_send_check(iph);
}
}
if ((dext->flags & VNET_PKT_HCK_FULLCKSUM) &&
- skb->ip_summed == CHECKSUM_NONE)
- vnet_fullcsum(skb);
+ skb->ip_summed == CHECKSUM_NONE) {
+ if (skb->protocol == htons(ETH_P_IP)) {
+ struct iphdr *iph = ip_hdr(skb);
+ int ihl = iph->ihl * 4;
+
+ skb_reset_transport_header(skb);
+ skb_set_transport_header(skb, ihl);
+ vnet_fullcsum(skb);
+ }
+ }
if (dext->flags & VNET_PKT_HCK_IPV4_HDRCKSUM_OK) {
skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum_level = 0;
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c
index 657b65b..18bf3a8 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.c
+++ b/drivers/net/ethernet/ti/davinci_cpdma.c
@@ -82,7 +82,7 @@
struct cpdma_desc_pool {
phys_addr_t phys;
- u32 hw_addr;
+ dma_addr_t hw_addr;
void __iomem *iomap; /* ioremap map */
void *cpumap; /* dma_alloc map */
int desc_size, mem_size;
@@ -152,7 +152,7 @@
* abstract out these details
*/
static struct cpdma_desc_pool *
-cpdma_desc_pool_create(struct device *dev, u32 phys, u32 hw_addr,
+cpdma_desc_pool_create(struct device *dev, u32 phys, dma_addr_t hw_addr,
int size, int align)
{
int bitmap_size;
@@ -176,13 +176,13 @@
if (phys) {
pool->phys = phys;
- pool->iomap = ioremap(phys, size);
+ pool->iomap = ioremap(phys, size); /* should be memremap? */
pool->hw_addr = hw_addr;
} else {
- pool->cpumap = dma_alloc_coherent(dev, size, &pool->phys,
+ pool->cpumap = dma_alloc_coherent(dev, size, &pool->hw_addr,
GFP_KERNEL);
- pool->iomap = pool->cpumap;
- pool->hw_addr = pool->phys;
+ pool->iomap = (void __iomem __force *)pool->cpumap;
+ pool->phys = pool->hw_addr; /* assumes no IOMMU, don't use this value */
}
if (pool->iomap)
diff --git a/drivers/net/fddi/defxx.c b/drivers/net/fddi/defxx.c
index 7f975a2..b0de8ec 100644
--- a/drivers/net/fddi/defxx.c
+++ b/drivers/net/fddi/defxx.c
@@ -533,8 +533,8 @@
const char *print_name = dev_name(bdev);
struct net_device *dev;
DFX_board_t *bp; /* board pointer */
- resource_size_t bar_start[3]; /* pointers to ports */
- resource_size_t bar_len[3]; /* resource length */
+ resource_size_t bar_start[3] = {0}; /* pointers to ports */
+ resource_size_t bar_len[3] = {0}; /* resource length */
int alloc_size; /* total buffer size used */
struct resource *region;
int err = 0;
@@ -3697,8 +3697,8 @@
int dfx_bus_pci = dev_is_pci(bdev);
int dfx_bus_tc = DFX_BUS_TC(bdev);
int dfx_use_mmio = DFX_MMIO || dfx_bus_tc;
- resource_size_t bar_start[3]; /* pointers to ports */
- resource_size_t bar_len[3]; /* resource lengths */
+ resource_size_t bar_start[3] = {0}; /* pointers to ports */
+ resource_size_t bar_len[3] = {0}; /* resource lengths */
int alloc_size; /* total buffer size used */
unregister_netdev(dev);
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 7456569..0b14ac3 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -980,9 +980,9 @@
opts = ip_tunnel_info_opts(info);
if (key->tun_flags & TUNNEL_CSUM)
- flags |= GENEVE_F_UDP_CSUM;
+ flags &= ~GENEVE_F_UDP_ZERO_CSUM6_TX;
else
- flags &= ~GENEVE_F_UDP_CSUM;
+ flags |= GENEVE_F_UDP_ZERO_CSUM6_TX;
err = geneve6_build_skb(dst, skb, key->tun_flags, vni,
info->options_len, opts,
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index f4130af..fcb92c0 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -624,6 +624,7 @@
#define RNDIS_PKT_ALIGN_DEFAULT 8
struct multi_send_data {
+ struct sk_buff *skb; /* skb containing the pkt */
struct hv_netvsc_packet *pkt; /* netvsc pkt pending */
u32 count; /* counter of batched packets */
};
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 059fc52..ec313fc 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -841,6 +841,18 @@
return ret;
}
+/* Move packet out of multi send data (msd), and clear msd */
+static inline void move_pkt_msd(struct hv_netvsc_packet **msd_send,
+ struct sk_buff **msd_skb,
+ struct multi_send_data *msdp)
+{
+ *msd_skb = msdp->skb;
+ *msd_send = msdp->pkt;
+ msdp->skb = NULL;
+ msdp->pkt = NULL;
+ msdp->count = 0;
+}
+
int netvsc_send(struct hv_device *device,
struct hv_netvsc_packet *packet,
struct rndis_message *rndis_msg,
@@ -855,6 +867,7 @@
unsigned int section_index = NETVSC_INVALID_INDEX;
struct multi_send_data *msdp;
struct hv_netvsc_packet *msd_send = NULL, *cur_send = NULL;
+ struct sk_buff *msd_skb = NULL;
bool try_batch;
bool xmit_more = (skb != NULL) ? skb->xmit_more : false;
@@ -897,10 +910,8 @@
net_device->send_section_size) {
section_index = netvsc_get_next_send_section(net_device);
if (section_index != NETVSC_INVALID_INDEX) {
- msd_send = msdp->pkt;
- msdp->pkt = NULL;
- msdp->count = 0;
- msd_len = 0;
+ move_pkt_msd(&msd_send, &msd_skb, msdp);
+ msd_len = 0;
}
}
@@ -919,31 +930,31 @@
packet->total_data_buflen += msd_len;
}
- if (msdp->pkt)
- dev_kfree_skb_any(skb);
+ if (msdp->skb)
+ dev_kfree_skb_any(msdp->skb);
if (xmit_more && !packet->cp_partial) {
+ msdp->skb = skb;
msdp->pkt = packet;
msdp->count++;
} else {
cur_send = packet;
+ msdp->skb = NULL;
msdp->pkt = NULL;
msdp->count = 0;
}
} else {
- msd_send = msdp->pkt;
- msdp->pkt = NULL;
- msdp->count = 0;
+ move_pkt_msd(&msd_send, &msd_skb, msdp);
cur_send = packet;
}
if (msd_send) {
- m_ret = netvsc_send_pkt(msd_send, net_device, pb, skb);
+ m_ret = netvsc_send_pkt(msd_send, net_device, NULL, msd_skb);
if (m_ret != 0) {
netvsc_free_send_slot(net_device,
msd_send->send_buf_index);
- dev_kfree_skb_any(skb);
+ dev_kfree_skb_any(msd_skb);
}
}
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 1c8db9a..1d3a665 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -196,65 +196,6 @@
return ppi;
}
-union sub_key {
- u64 k;
- struct {
- u8 pad[3];
- u8 kb;
- u32 ka;
- };
-};
-
-/* Toeplitz hash function
- * data: network byte order
- * return: host byte order
- */
-static u32 comp_hash(u8 *key, int klen, void *data, int dlen)
-{
- union sub_key subk;
- int k_next = 4;
- u8 dt;
- int i, j;
- u32 ret = 0;
-
- subk.k = 0;
- subk.ka = ntohl(*(u32 *)key);
-
- for (i = 0; i < dlen; i++) {
- subk.kb = key[k_next];
- k_next = (k_next + 1) % klen;
- dt = ((u8 *)data)[i];
- for (j = 0; j < 8; j++) {
- if (dt & 0x80)
- ret ^= subk.ka;
- dt <<= 1;
- subk.k <<= 1;
- }
- }
-
- return ret;
-}
-
-static bool netvsc_set_hash(u32 *hash, struct sk_buff *skb)
-{
- struct flow_keys flow;
- int data_len;
-
- if (!skb_flow_dissect_flow_keys(skb, &flow, 0) ||
- !(flow.basic.n_proto == htons(ETH_P_IP) ||
- flow.basic.n_proto == htons(ETH_P_IPV6)))
- return false;
-
- if (flow.basic.ip_proto == IPPROTO_TCP)
- data_len = 12;
- else
- data_len = 8;
-
- *hash = comp_hash(netvsc_hash_key, HASH_KEYLEN, &flow, data_len);
-
- return true;
-}
-
static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
void *accel_priv, select_queue_fallback_t fallback)
{
@@ -267,11 +208,9 @@
if (nvsc_dev == NULL || ndev->real_num_tx_queues <= 1)
return 0;
- if (netvsc_set_hash(&hash, skb)) {
- q_idx = nvsc_dev->send_table[hash % VRSS_SEND_TAB_SIZE] %
- ndev->real_num_tx_queues;
- skb_set_hash(skb, hash, PKT_HASH_TYPE_L3);
- }
+ hash = skb_get_hash(skb);
+ q_idx = nvsc_dev->send_table[hash % VRSS_SEND_TAB_SIZE] %
+ ndev->real_num_tx_queues;
if (!nvsc_dev->chn_table[q_idx])
q_idx = 0;
diff --git a/drivers/net/irda/bfin_sir.h b/drivers/net/irda/bfin_sir.h
index 29cbde8..d47cf14 100644
--- a/drivers/net/irda/bfin_sir.h
+++ b/drivers/net/irda/bfin_sir.h
@@ -82,9 +82,6 @@
#define DRIVER_NAME "bfin_sir"
-#define port_membase(port) (((struct bfin_sir_port *)(port))->membase)
-#define get_lsr_cache(port) (((struct bfin_sir_port *)(port))->lsr)
-#define put_lsr_cache(port, v) (((struct bfin_sir_port *)(port))->lsr = (v))
#include <asm/bfin_serial.h>
static const unsigned short per[][4] = {
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 6a57a00..94e6888 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1323,6 +1323,7 @@
list_add_tail_rcu(&vlan->list, &port->vlans);
netif_stacked_transfer_operstate(lowerdev, dev);
+ linkwatch_fire_event(dev);
return 0;
@@ -1522,6 +1523,7 @@
port = macvlan_port_get_rtnl(dev);
switch (event) {
+ case NETDEV_UP:
case NETDEV_CHANGE:
list_for_each_entry(vlan, &port->vlans, list)
netif_stacked_transfer_operstate(vlan->lowerdev,
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 60994a8..f0a77020 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -186,6 +186,7 @@
config MDIO_OCTEON
tristate "Support for MDIO buses on Octeon and ThunderX SOCs"
depends on 64BIT
+ depends on HAS_IOMEM
help
This module provides a driver for the Octeon and ThunderX MDIO
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 180f699..7a240fc 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -846,6 +846,11 @@
struct skb_shared_hwtstamps *shhwtstamps = NULL;
struct sk_buff *skb;
unsigned long flags;
+ u8 overflow;
+
+ overflow = (phy_rxts->ns_hi >> 14) & 0x3;
+ if (overflow)
+ pr_debug("rx timestamp queue overflow, count %d\n", overflow);
spin_lock_irqsave(&dp83640->rx_lock, flags);
@@ -888,6 +893,7 @@
struct skb_shared_hwtstamps shhwtstamps;
struct sk_buff *skb;
u64 ns;
+ u8 overflow;
/* We must already have the skb that triggered this. */
@@ -897,6 +903,17 @@
pr_debug("have timestamp but tx_queue empty\n");
return;
}
+
+ overflow = (phy_txts->ns_hi >> 14) & 0x3;
+ if (overflow) {
+ pr_debug("tx timestamp queue overflow, count %d\n", overflow);
+ while (skb) {
+ skb_complete_tx_timestamp(skb, NULL);
+ skb = skb_dequeue(&dp83640->tx_queue);
+ }
+ return;
+ }
+
ns = phy2txts(phy_txts);
memset(&shhwtstamps, 0, sizeof(shhwtstamps));
shhwtstamps.hwtstamp = ns_to_ktime(ns);
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 8763bb2..5590b9c 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -692,25 +692,29 @@
struct phy_device *phydev =
container_of(work, struct phy_device, phy_queue);
- if (phydev->drv->did_interrupt &&
- !phydev->drv->did_interrupt(phydev))
- goto ignore;
+ if (phy_interrupt_is_valid(phydev)) {
+ if (phydev->drv->did_interrupt &&
+ !phydev->drv->did_interrupt(phydev))
+ goto ignore;
- if (phy_disable_interrupts(phydev))
- goto phy_err;
+ if (phy_disable_interrupts(phydev))
+ goto phy_err;
+ }
mutex_lock(&phydev->lock);
if ((PHY_RUNNING == phydev->state) || (PHY_NOLINK == phydev->state))
phydev->state = PHY_CHANGELINK;
mutex_unlock(&phydev->lock);
- atomic_dec(&phydev->irq_disable);
- enable_irq(phydev->irq);
+ if (phy_interrupt_is_valid(phydev)) {
+ atomic_dec(&phydev->irq_disable);
+ enable_irq(phydev->irq);
- /* Reenable interrupts */
- if (PHY_HALTED != phydev->state &&
- phy_config_interrupt(phydev, PHY_INTERRUPT_ENABLED))
- goto irq_enable_err;
+ /* Reenable interrupts */
+ if (PHY_HALTED != phydev->state &&
+ phy_config_interrupt(phydev, PHY_INTERRUPT_ENABLED))
+ goto irq_enable_err;
+ }
/* reschedule state queue work to run as soon as possible */
cancel_delayed_work_sync(&phydev->state_queue);
@@ -905,10 +909,10 @@
phydev->adjust_link(phydev->attached_dev);
break;
case PHY_RUNNING:
- /* Only register a CHANGE if we are polling or ignoring
- * interrupts and link changed since latest checking.
+ /* Only register a CHANGE if we are polling and link changed
+ * since latest checking.
*/
- if (!phy_interrupt_is_valid(phydev)) {
+ if (phydev->irq == PHY_POLL) {
old_link = phydev->link;
err = phy_read_status(phydev);
if (err)
@@ -1000,15 +1004,21 @@
phy_state_to_str(old_state),
phy_state_to_str(phydev->state));
- queue_delayed_work(system_power_efficient_wq, &phydev->state_queue,
- PHY_STATE_TIME * HZ);
+ /* Only re-schedule a PHY state machine change if we are polling the
+ * PHY, if PHY_IGNORE_INTERRUPT is set, then we will be moving
+ * between states from phy_mac_interrupt()
+ */
+ if (phydev->irq == PHY_POLL)
+ queue_delayed_work(system_power_efficient_wq, &phydev->state_queue,
+ PHY_STATE_TIME * HZ);
}
void phy_mac_interrupt(struct phy_device *phydev, int new_link)
{
- cancel_work_sync(&phydev->phy_queue);
phydev->link = new_link;
- schedule_work(&phydev->phy_queue);
+
+ /* Trigger a state machine change */
+ queue_work(system_power_efficient_wq, &phydev->phy_queue);
}
EXPORT_SYMBOL(phy_mac_interrupt);
diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index e485f26..2e21e93 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -24,6 +24,10 @@
#include <linux/netdevice.h>
#include <linux/smscphy.h>
+struct smsc_phy_priv {
+ bool energy_enable;
+};
+
static int smsc_phy_config_intr(struct phy_device *phydev)
{
int rc = phy_write (phydev, MII_LAN83C185_IM,
@@ -43,19 +47,14 @@
static int smsc_phy_config_init(struct phy_device *phydev)
{
- int __maybe_unused len;
- struct device *dev __maybe_unused = &phydev->mdio.dev;
- struct device_node *of_node __maybe_unused = dev->of_node;
+ struct smsc_phy_priv *priv = phydev->priv;
+
int rc = phy_read(phydev, MII_LAN83C185_CTRL_STATUS);
- int enable_energy = 1;
if (rc < 0)
return rc;
- if (of_find_property(of_node, "smsc,disable-energy-detect", &len))
- enable_energy = 0;
-
- if (enable_energy) {
+ if (priv->energy_enable) {
/* Enable energy detect mode for this SMSC Transceivers */
rc = phy_write(phydev, MII_LAN83C185_CTRL_STATUS,
rc | MII_LAN83C185_EDPWRDOWN);
@@ -110,10 +109,13 @@
*/
static int lan87xx_read_status(struct phy_device *phydev)
{
- int err = genphy_read_status(phydev);
- int i;
+ struct smsc_phy_priv *priv = phydev->priv;
- if (!phydev->link) {
+ int err = genphy_read_status(phydev);
+
+ if (!phydev->link && priv->energy_enable) {
+ int i;
+
/* Disable EDPD to wake up PHY */
int rc = phy_read(phydev, MII_LAN83C185_CTRL_STATUS);
if (rc < 0)
@@ -149,6 +151,26 @@
return err;
}
+static int smsc_phy_probe(struct phy_device *phydev)
+{
+ struct device *dev = &phydev->mdio.dev;
+ struct device_node *of_node = dev->of_node;
+ struct smsc_phy_priv *priv;
+
+ priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+ if (!priv)
+ return -ENOMEM;
+
+ priv->energy_enable = true;
+
+ if (of_property_read_bool(of_node, "smsc,disable-energy-detect"))
+ priv->energy_enable = false;
+
+ phydev->priv = priv;
+
+ return 0;
+}
+
static struct phy_driver smsc_phy_driver[] = {
{
.phy_id = 0x0007c0a0, /* OUI=0x00800f, Model#=0x0a */
@@ -159,6 +181,8 @@
| SUPPORTED_Asym_Pause),
.flags = PHY_HAS_INTERRUPT | PHY_HAS_MAGICANEG,
+ .probe = smsc_phy_probe,
+
/* basic functions */
.config_aneg = genphy_config_aneg,
.read_status = genphy_read_status,
@@ -180,6 +204,8 @@
| SUPPORTED_Asym_Pause),
.flags = PHY_HAS_INTERRUPT | PHY_HAS_MAGICANEG,
+ .probe = smsc_phy_probe,
+
/* basic functions */
.config_aneg = genphy_config_aneg,
.read_status = genphy_read_status,
@@ -201,6 +227,8 @@
| SUPPORTED_Asym_Pause),
.flags = PHY_HAS_INTERRUPT | PHY_HAS_MAGICANEG,
+ .probe = smsc_phy_probe,
+
/* basic functions */
.config_aneg = genphy_config_aneg,
.read_status = lan87xx_read_status,
@@ -222,6 +250,8 @@
| SUPPORTED_Asym_Pause),
.flags = PHY_HAS_INTERRUPT | PHY_HAS_MAGICANEG,
+ .probe = smsc_phy_probe,
+
/* basic functions */
.config_aneg = genphy_config_aneg,
.read_status = genphy_read_status,
@@ -242,6 +272,8 @@
| SUPPORTED_Asym_Pause),
.flags = PHY_HAS_INTERRUPT | PHY_HAS_MAGICANEG,
+ .probe = smsc_phy_probe,
+
/* basic functions */
.config_aneg = genphy_config_aneg,
.read_status = lan87xx_read_status,
@@ -263,6 +295,8 @@
| SUPPORTED_Asym_Pause),
.flags = PHY_HAS_INTERRUPT | PHY_HAS_MAGICANEG,
+ .probe = smsc_phy_probe,
+
/* basic functions */
.config_aneg = genphy_config_aneg,
.read_status = lan87xx_read_status,
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 90868ca..ae0905e 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -129,24 +129,27 @@
return i < MAX_CALLID;
}
-static int add_chan(struct pppox_sock *sock)
+static int add_chan(struct pppox_sock *sock,
+ struct pptp_addr *sa)
{
static int call_id;
spin_lock(&chan_lock);
- if (!sock->proto.pptp.src_addr.call_id) {
+ if (!sa->call_id) {
call_id = find_next_zero_bit(callid_bitmap, MAX_CALLID, call_id + 1);
if (call_id == MAX_CALLID) {
call_id = find_next_zero_bit(callid_bitmap, MAX_CALLID, 1);
if (call_id == MAX_CALLID)
goto out_err;
}
- sock->proto.pptp.src_addr.call_id = call_id;
- } else if (test_bit(sock->proto.pptp.src_addr.call_id, callid_bitmap))
+ sa->call_id = call_id;
+ } else if (test_bit(sa->call_id, callid_bitmap)) {
goto out_err;
+ }
- set_bit(sock->proto.pptp.src_addr.call_id, callid_bitmap);
- rcu_assign_pointer(callid_sock[sock->proto.pptp.src_addr.call_id], sock);
+ sock->proto.pptp.src_addr = *sa;
+ set_bit(sa->call_id, callid_bitmap);
+ rcu_assign_pointer(callid_sock[sa->call_id], sock);
spin_unlock(&chan_lock);
return 0;
@@ -416,7 +419,6 @@
struct sock *sk = sock->sk;
struct sockaddr_pppox *sp = (struct sockaddr_pppox *) uservaddr;
struct pppox_sock *po = pppox_sk(sk);
- struct pptp_opt *opt = &po->proto.pptp;
int error = 0;
if (sockaddr_len < sizeof(struct sockaddr_pppox))
@@ -424,10 +426,22 @@
lock_sock(sk);
- opt->src_addr = sp->sa_addr.pptp;
- if (add_chan(po))
- error = -EBUSY;
+ if (sk->sk_state & PPPOX_DEAD) {
+ error = -EALREADY;
+ goto out;
+ }
+ if (sk->sk_state & PPPOX_BOUND) {
+ error = -EBUSY;
+ goto out;
+ }
+
+ if (add_chan(po, &sp->sa_addr.pptp))
+ error = -EBUSY;
+ else
+ sk->sk_state |= PPPOX_BOUND;
+
+out:
release_sock(sk);
return error;
}
@@ -498,7 +512,7 @@
}
opt->dst_addr = sp->sa_addr.pptp;
- sk->sk_state = PPPOX_CONNECTED;
+ sk->sk_state |= PPPOX_CONNECTED;
end:
release_sock(sk);
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 2ed5333..1c299b8 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -36,7 +36,7 @@
#define DRIVER_AUTHOR "WOOJUNG HUH <woojung.huh@microchip.com>"
#define DRIVER_DESC "LAN78XX USB 3.0 Gigabit Ethernet Devices"
#define DRIVER_NAME "lan78xx"
-#define DRIVER_VERSION "1.0.1"
+#define DRIVER_VERSION "1.0.2"
#define TX_TIMEOUT_JIFFIES (5 * HZ)
#define THROTTLE_JIFFIES (HZ / 8)
@@ -462,32 +462,53 @@
u32 length, u8 *data)
{
u32 val;
+ u32 saved;
int i, ret;
+ int retval;
- ret = lan78xx_eeprom_confirm_not_busy(dev);
- if (ret)
- return ret;
+ /* depends on chip, some EEPROM pins are muxed with LED function.
+ * disable & restore LED function to access EEPROM.
+ */
+ ret = lan78xx_read_reg(dev, HW_CFG, &val);
+ saved = val;
+ if ((dev->devid & ID_REV_CHIP_ID_MASK_) == 0x78000000) {
+ val &= ~(HW_CFG_LED1_EN_ | HW_CFG_LED0_EN_);
+ ret = lan78xx_write_reg(dev, HW_CFG, val);
+ }
+
+ retval = lan78xx_eeprom_confirm_not_busy(dev);
+ if (retval)
+ return retval;
for (i = 0; i < length; i++) {
val = E2P_CMD_EPC_BUSY_ | E2P_CMD_EPC_CMD_READ_;
val |= (offset & E2P_CMD_EPC_ADDR_MASK_);
ret = lan78xx_write_reg(dev, E2P_CMD, val);
- if (unlikely(ret < 0))
- return -EIO;
+ if (unlikely(ret < 0)) {
+ retval = -EIO;
+ goto exit;
+ }
- ret = lan78xx_wait_eeprom(dev);
- if (ret < 0)
- return ret;
+ retval = lan78xx_wait_eeprom(dev);
+ if (retval < 0)
+ goto exit;
ret = lan78xx_read_reg(dev, E2P_DATA, &val);
- if (unlikely(ret < 0))
- return -EIO;
+ if (unlikely(ret < 0)) {
+ retval = -EIO;
+ goto exit;
+ }
data[i] = val & 0xFF;
offset++;
}
- return 0;
+ retval = 0;
+exit:
+ if ((dev->devid & ID_REV_CHIP_ID_MASK_) == 0x78000000)
+ ret = lan78xx_write_reg(dev, HW_CFG, saved);
+
+ return retval;
}
static int lan78xx_read_eeprom(struct lan78xx_net *dev, u32 offset,
@@ -509,44 +530,67 @@
u32 length, u8 *data)
{
u32 val;
+ u32 saved;
int i, ret;
+ int retval;
- ret = lan78xx_eeprom_confirm_not_busy(dev);
- if (ret)
- return ret;
+ /* depends on chip, some EEPROM pins are muxed with LED function.
+ * disable & restore LED function to access EEPROM.
+ */
+ ret = lan78xx_read_reg(dev, HW_CFG, &val);
+ saved = val;
+ if ((dev->devid & ID_REV_CHIP_ID_MASK_) == 0x78000000) {
+ val &= ~(HW_CFG_LED1_EN_ | HW_CFG_LED0_EN_);
+ ret = lan78xx_write_reg(dev, HW_CFG, val);
+ }
+
+ retval = lan78xx_eeprom_confirm_not_busy(dev);
+ if (retval)
+ goto exit;
/* Issue write/erase enable command */
val = E2P_CMD_EPC_BUSY_ | E2P_CMD_EPC_CMD_EWEN_;
ret = lan78xx_write_reg(dev, E2P_CMD, val);
- if (unlikely(ret < 0))
- return -EIO;
+ if (unlikely(ret < 0)) {
+ retval = -EIO;
+ goto exit;
+ }
- ret = lan78xx_wait_eeprom(dev);
- if (ret < 0)
- return ret;
+ retval = lan78xx_wait_eeprom(dev);
+ if (retval < 0)
+ goto exit;
for (i = 0; i < length; i++) {
/* Fill data register */
val = data[i];
ret = lan78xx_write_reg(dev, E2P_DATA, val);
- if (ret < 0)
- return ret;
+ if (ret < 0) {
+ retval = -EIO;
+ goto exit;
+ }
/* Send "write" command */
val = E2P_CMD_EPC_BUSY_ | E2P_CMD_EPC_CMD_WRITE_;
val |= (offset & E2P_CMD_EPC_ADDR_MASK_);
ret = lan78xx_write_reg(dev, E2P_CMD, val);
- if (ret < 0)
- return ret;
+ if (ret < 0) {
+ retval = -EIO;
+ goto exit;
+ }
- ret = lan78xx_wait_eeprom(dev);
- if (ret < 0)
- return ret;
+ retval = lan78xx_wait_eeprom(dev);
+ if (retval < 0)
+ goto exit;
offset++;
}
- return 0;
+ retval = 0;
+exit:
+ if ((dev->devid & ID_REV_CHIP_ID_MASK_) == 0x78000000)
+ ret = lan78xx_write_reg(dev, HW_CFG, saved);
+
+ return retval;
}
static int lan78xx_read_raw_otp(struct lan78xx_net *dev, u32 offset,
@@ -904,7 +948,6 @@
if (!phydev->link && dev->link_on) {
dev->link_on = false;
- netif_carrier_off(dev->net);
/* reset MAC */
ret = lan78xx_read_reg(dev, MAC_CR, &buf);
@@ -914,6 +957,8 @@
ret = lan78xx_write_reg(dev, MAC_CR, buf);
if (unlikely(ret < 0))
return -EIO;
+
+ phy_mac_interrupt(phydev, 0);
} else if (phydev->link && !dev->link_on) {
dev->link_on = true;
@@ -953,7 +998,7 @@
ethtool_cmd_speed(&ecmd), ecmd.duplex, ladv, radv);
ret = lan78xx_update_flowcontrol(dev, ecmd.duplex, ladv, radv);
- netif_carrier_on(dev->net);
+ phy_mac_interrupt(phydev, 1);
}
return ret;
@@ -1495,7 +1540,6 @@
static int lan78xx_mdio_init(struct lan78xx_net *dev)
{
int ret;
- int i;
dev->mdiobus = mdiobus_alloc();
if (!dev->mdiobus) {
@@ -1511,10 +1555,6 @@
snprintf(dev->mdiobus->id, MII_BUS_ID_SIZE, "usb-%03d:%03d",
dev->udev->bus->busnum, dev->udev->devnum);
- /* handle our own interrupt */
- for (i = 0; i < PHY_MAX_ADDR; i++)
- dev->mdiobus->irq[i] = PHY_IGNORE_INTERRUPT;
-
switch (dev->devid & ID_REV_CHIP_ID_MASK_) {
case 0x78000000:
case 0x78500000:
@@ -1558,6 +1598,16 @@
return -EIO;
}
+ /* Enable PHY interrupts.
+ * We handle our own interrupt
+ */
+ ret = phy_read(phydev, LAN88XX_INT_STS);
+ ret = phy_write(phydev, LAN88XX_INT_MASK,
+ LAN88XX_INT_MASK_MDINTPIN_EN_ |
+ LAN88XX_INT_MASK_LINK_CHANGE_);
+
+ phydev->irq = PHY_IGNORE_INTERRUPT;
+
ret = phy_connect_direct(dev->net, phydev,
lan78xx_link_status_change,
PHY_INTERFACE_MODE_GMII);
@@ -1580,14 +1630,6 @@
SUPPORTED_Pause | SUPPORTED_Asym_Pause);
genphy_config_aneg(phydev);
- /* Workaround to enable PHY interrupt.
- * phy_start_interrupts() is API for requesting and enabling
- * PHY interrupt. However, USB-to-Ethernet device can't use
- * request_irq() called in phy_start_interrupts().
- * Set PHY to PHY_HALTED and call phy_start()
- * to make a call to phy_enable_interrupts()
- */
- phy_stop(phydev);
phy_start(phydev);
netif_dbg(dev, ifup, dev->net, "phy initialised successfully");
@@ -2221,7 +2263,9 @@
if (skb2) {
skb_queue_tail(&dev->txq_pend, skb2);
- if (skb_queue_len(&dev->txq_pend) > 10)
+ /* throttle TX patch at slower than SUPER SPEED USB */
+ if ((dev->udev->speed < USB_SPEED_SUPER) &&
+ (skb_queue_len(&dev->txq_pend) > 10))
netif_stop_queue(net);
} else {
netif_dbg(dev, tx_err, dev->net,
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 2d88c79..6543918 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -73,7 +73,7 @@
static int vxlan_net_id;
static struct rtnl_link_ops vxlan_link_ops;
-static const u8 all_zeros_mac[ETH_ALEN];
+static const u8 all_zeros_mac[ETH_ALEN + 2];
static int vxlan_sock_add(struct vxlan_dev *vxlan);
@@ -1985,11 +1985,6 @@
vxlan->cfg.port_max, true);
if (info) {
- if (info->key.tun_flags & TUNNEL_CSUM)
- flags |= VXLAN_F_UDP_CSUM;
- else
- flags &= ~VXLAN_F_UDP_CSUM;
-
ttl = info->key.ttl;
tos = info->key.tos;
@@ -2004,8 +1999,15 @@
goto drop;
sk = vxlan->vn4_sock->sock->sk;
- if (info && (info->key.tun_flags & TUNNEL_DONT_FRAGMENT))
- df = htons(IP_DF);
+ if (info) {
+ if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT)
+ df = htons(IP_DF);
+
+ if (info->key.tun_flags & TUNNEL_CSUM)
+ flags |= VXLAN_F_UDP_CSUM;
+ else
+ flags &= ~VXLAN_F_UDP_CSUM;
+ }
memset(&fl4, 0, sizeof(fl4));
fl4.flowi4_oif = rdst ? rdst->remote_ifindex : 0;
@@ -2101,6 +2103,13 @@
return;
}
+ if (info) {
+ if (info->key.tun_flags & TUNNEL_CSUM)
+ flags &= ~VXLAN_F_UDP_ZERO_CSUM6_TX;
+ else
+ flags |= VXLAN_F_UDP_ZERO_CSUM6_TX;
+ }
+
ttl = ttl ? : ip6_dst_hoplimit(ndst);
err = vxlan6_xmit_skb(ndst, sk, skb, dev, &saddr, &dst->sin6.sin6_addr,
0, ttl, src_port, dst_port, htonl(vni << 8), md,
diff --git a/drivers/net/wireless/ath/ath9k/eeprom.c b/drivers/net/wireless/ath/ath9k/eeprom.c
index a7afdee..73fb423 100644
--- a/drivers/net/wireless/ath/ath9k/eeprom.c
+++ b/drivers/net/wireless/ath/ath9k/eeprom.c
@@ -150,18 +150,18 @@
return -EIO;
}
- if (magic == AR5416_EEPROM_MAGIC) {
- *swap_needed = false;
- } else if (swab16(magic) == AR5416_EEPROM_MAGIC) {
+ *swap_needed = false;
+ if (swab16(magic) == AR5416_EEPROM_MAGIC) {
if (ah->ah_flags & AH_NO_EEP_SWAP) {
ath_info(common,
"Ignoring endianness difference in EEPROM magic bytes.\n");
-
- *swap_needed = false;
} else {
*swap_needed = true;
}
- } else {
+ } else if (magic != AR5416_EEPROM_MAGIC) {
+ if (ath9k_hw_use_flash(ah))
+ return 0;
+
ath_err(common,
"Invalid EEPROM Magic (0x%04x).\n", magic);
return -EINVAL;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
index 5363739..b98db8a 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
@@ -879,11 +879,24 @@
return 0;
}
-static void brcmf_sdiod_sgtable_alloc(struct brcmf_sdio_dev *sdiodev)
+void brcmf_sdiod_sgtable_alloc(struct brcmf_sdio_dev *sdiodev)
{
+ struct sdio_func *func;
+ struct mmc_host *host;
+ uint max_blocks;
uint nents;
int err;
+ func = sdiodev->func[2];
+ host = func->card->host;
+ sdiodev->sg_support = host->max_segs > 1;
+ max_blocks = min_t(uint, host->max_blk_count, 511u);
+ sdiodev->max_request_size = min_t(uint, host->max_req_size,
+ max_blocks * func->cur_blksize);
+ sdiodev->max_segment_count = min_t(uint, host->max_segs,
+ SG_MAX_SINGLE_ALLOC);
+ sdiodev->max_segment_size = host->max_seg_size;
+
if (!sdiodev->sg_support)
return;
@@ -1021,9 +1034,6 @@
static int brcmf_sdiod_probe(struct brcmf_sdio_dev *sdiodev)
{
- struct sdio_func *func;
- struct mmc_host *host;
- uint max_blocks;
int ret = 0;
sdiodev->num_funcs = 2;
@@ -1054,26 +1064,6 @@
goto out;
}
- /*
- * determine host related variables after brcmf_sdiod_probe()
- * as func->cur_blksize is properly set and F2 init has been
- * completed successfully.
- */
- func = sdiodev->func[2];
- host = func->card->host;
- sdiodev->sg_support = host->max_segs > 1;
- max_blocks = min_t(uint, host->max_blk_count, 511u);
- sdiodev->max_request_size = min_t(uint, host->max_req_size,
- max_blocks * func->cur_blksize);
- sdiodev->max_segment_count = min_t(uint, host->max_segs,
- SG_MAX_SINGLE_ALLOC);
- sdiodev->max_segment_size = host->max_seg_size;
-
- /* allocate scatter-gather table. sg support
- * will be disabled upon allocation failure.
- */
- brcmf_sdiod_sgtable_alloc(sdiodev);
-
ret = brcmf_sdiod_freezer_attach(sdiodev);
if (ret)
goto out;
@@ -1084,7 +1074,7 @@
ret = -ENODEV;
goto out;
}
- brcmf_sdiod_host_fixup(host);
+ brcmf_sdiod_host_fixup(sdiodev->func[2]->card->host);
out:
if (ret)
brcmf_sdiod_remove(sdiodev);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
index 4265b50..cfee477 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
@@ -17,6 +17,7 @@
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/netdevice.h>
+#include <linux/module.h>
#include <brcmu_wifi.h>
#include <brcmu_utils.h>
#include "core.h"
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index dd66143..a14d9d9d 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -4114,6 +4114,11 @@
goto fail;
}
+ /* allocate scatter-gather table. sg support
+ * will be disabled upon allocation failure.
+ */
+ brcmf_sdiod_sgtable_alloc(bus->sdiodev);
+
/* Query the F2 block size, set roundup accordingly */
bus->blocksize = bus->sdiodev->func[2]->cur_blksize;
bus->roundup = min(max_roundup, bus->blocksize);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
index 5ec7a6d..23f2231 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
@@ -342,6 +342,7 @@
/* Issue an abort to the specified function */
int brcmf_sdiod_abort(struct brcmf_sdio_dev *sdiodev, uint fn);
+void brcmf_sdiod_sgtable_alloc(struct brcmf_sdio_dev *sdiodev);
void brcmf_sdiod_change_state(struct brcmf_sdio_dev *sdiodev,
enum brcmf_sdiod_state state);
#ifdef CONFIG_PM_SLEEP
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-7000.c b/drivers/net/wireless/intel/iwlwifi/iwl-7000.c
index e60cf14..fa41a5e 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-7000.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-7000.c
@@ -74,16 +74,19 @@
#define IWL7260_UCODE_API_MAX 17
#define IWL7265_UCODE_API_MAX 17
#define IWL7265D_UCODE_API_MAX 20
+#define IWL3168_UCODE_API_MAX 20
/* Oldest version we won't warn about */
#define IWL7260_UCODE_API_OK 13
#define IWL7265_UCODE_API_OK 13
#define IWL7265D_UCODE_API_OK 13
+#define IWL3168_UCODE_API_OK 20
/* Lowest firmware API version supported */
#define IWL7260_UCODE_API_MIN 13
#define IWL7265_UCODE_API_MIN 13
#define IWL7265D_UCODE_API_MIN 13
+#define IWL3168_UCODE_API_MIN 20
/* NVM versions */
#define IWL7260_NVM_VERSION 0x0a1d
@@ -92,6 +95,8 @@
#define IWL3160_TX_POWER_VERSION 0xffff /* meaningless */
#define IWL3165_NVM_VERSION 0x709
#define IWL3165_TX_POWER_VERSION 0xffff /* meaningless */
+#define IWL3168_NVM_VERSION 0xd01
+#define IWL3168_TX_POWER_VERSION 0xffff /* meaningless */
#define IWL7265_NVM_VERSION 0x0a1d
#define IWL7265_TX_POWER_VERSION 0xffff /* meaningless */
#define IWL7265D_NVM_VERSION 0x0c11
@@ -109,6 +114,9 @@
#define IWL3160_FW_PRE "iwlwifi-3160-"
#define IWL3160_MODULE_FIRMWARE(api) IWL3160_FW_PRE __stringify(api) ".ucode"
+#define IWL3168_FW_PRE "iwlwifi-3168-"
+#define IWL3168_MODULE_FIRMWARE(api) IWL3168_FW_PRE __stringify(api) ".ucode"
+
#define IWL7265_FW_PRE "iwlwifi-7265-"
#define IWL7265_MODULE_FIRMWARE(api) IWL7265_FW_PRE __stringify(api) ".ucode"
@@ -180,6 +188,12 @@
.ucode_api_ok = IWL7265_UCODE_API_OK, \
.ucode_api_min = IWL7265_UCODE_API_MIN
+#define IWL_DEVICE_3008 \
+ IWL_DEVICE_7000_COMMON, \
+ .ucode_api_max = IWL3168_UCODE_API_MAX, \
+ .ucode_api_ok = IWL3168_UCODE_API_OK, \
+ .ucode_api_min = IWL3168_UCODE_API_MIN
+
#define IWL_DEVICE_7005D \
IWL_DEVICE_7000_COMMON, \
.ucode_api_max = IWL7265D_UCODE_API_MAX, \
@@ -299,11 +313,11 @@
const struct iwl_cfg iwl3168_2ac_cfg = {
.name = "Intel(R) Dual Band Wireless AC 3168",
- .fw_name_pre = IWL7265D_FW_PRE,
- IWL_DEVICE_7000,
+ .fw_name_pre = IWL3168_FW_PRE,
+ IWL_DEVICE_3008,
.ht_params = &iwl7000_ht_params,
- .nvm_ver = IWL3165_NVM_VERSION,
- .nvm_calib_ver = IWL3165_TX_POWER_VERSION,
+ .nvm_ver = IWL3168_NVM_VERSION,
+ .nvm_calib_ver = IWL3168_TX_POWER_VERSION,
.pwr_tx_backoffs = iwl7265_pwr_tx_backoffs,
.dccm_len = IWL7265_DCCM_LEN,
};
@@ -376,5 +390,6 @@
MODULE_FIRMWARE(IWL7260_MODULE_FIRMWARE(IWL7260_UCODE_API_OK));
MODULE_FIRMWARE(IWL3160_MODULE_FIRMWARE(IWL7260_UCODE_API_OK));
+MODULE_FIRMWARE(IWL3168_MODULE_FIRMWARE(IWL3168_UCODE_API_OK));
MODULE_FIRMWARE(IWL7265_MODULE_FIRMWARE(IWL7265_UCODE_API_OK));
MODULE_FIRMWARE(IWL7265D_MODULE_FIRMWARE(IWL7265D_UCODE_API_OK));
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-tx.h b/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-tx.h
index 0036d18..ba3f0bb 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-tx.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-tx.h
@@ -510,6 +510,9 @@
* @scd_ssn: the index of the last contiguously sent packet
* @txed: number of Txed frames in this batch
* @txed_2_done: number of Acked frames in this batch
+ * @reduced_txp: power reduced according to TPC. This is the actual value and
+ * not a copy from the LQ command. Thus, if not the first rate was used
+ * for Tx-ing then this value will be set to 0 by FW.
*/
struct iwl_mvm_ba_notif {
__le32 sta_addr_lo32;
@@ -524,7 +527,8 @@
__le16 scd_ssn;
u8 txed;
u8 txed_2_done;
- __le16 reserved1;
+ u8 reduced_txp;
+ u8 reserved1;
} __packed;
/*
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
index 7bb6fd0..94caa88 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
@@ -2,6 +2,7 @@
*
* Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
+ * Copyright(c) 2016 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
@@ -724,14 +725,28 @@
return 0;
}
-static int rs_collect_tx_data(struct iwl_mvm *mvm,
- struct iwl_lq_sta *lq_sta,
- struct iwl_scale_tbl_info *tbl,
- int scale_index, int attempts, int successes,
- u8 reduced_txp)
+static int rs_collect_tpc_data(struct iwl_mvm *mvm,
+ struct iwl_lq_sta *lq_sta,
+ struct iwl_scale_tbl_info *tbl,
+ int scale_index, int attempts, int successes,
+ u8 reduced_txp)
{
struct iwl_rate_scale_data *window = NULL;
- int ret;
+
+ if (WARN_ON_ONCE(reduced_txp > TPC_MAX_REDUCTION))
+ return -EINVAL;
+
+ window = &tbl->tpc_win[reduced_txp];
+ return _rs_collect_tx_data(mvm, tbl, scale_index, attempts, successes,
+ window);
+}
+
+static int rs_collect_tlc_data(struct iwl_mvm *mvm,
+ struct iwl_lq_sta *lq_sta,
+ struct iwl_scale_tbl_info *tbl,
+ int scale_index, int attempts, int successes)
+{
+ struct iwl_rate_scale_data *window = NULL;
if (scale_index < 0 || scale_index >= IWL_RATE_COUNT)
return -EINVAL;
@@ -745,16 +760,6 @@
/* Select window for current tx bit rate */
window = &(tbl->win[scale_index]);
-
- ret = _rs_collect_tx_data(mvm, tbl, scale_index, attempts, successes,
- window);
- if (ret)
- return ret;
-
- if (WARN_ON_ONCE(reduced_txp > TPC_MAX_REDUCTION))
- return -EINVAL;
-
- window = &tbl->tpc_win[reduced_txp];
return _rs_collect_tx_data(mvm, tbl, scale_index, attempts, successes,
window);
}
@@ -1301,17 +1306,30 @@
* first index into rate scale table.
*/
if (info->flags & IEEE80211_TX_STAT_AMPDU) {
- /* ampdu_ack_len = 0 marks no BA was received. In this case
- * treat it as a single frame loss as we don't want the success
- * ratio to dip too quickly because a BA wasn't received
+ rs_collect_tpc_data(mvm, lq_sta, curr_tbl, lq_rate.index,
+ info->status.ampdu_len,
+ info->status.ampdu_ack_len,
+ reduced_txp);
+
+ /* ampdu_ack_len = 0 marks no BA was received. For TLC, treat
+ * it as a single frame loss as we don't want the success ratio
+ * to dip too quickly because a BA wasn't received.
+ * For TPC, there's no need for this optimisation since we want
+ * to recover very quickly from a bad power reduction and,
+ * therefore we'd like the success ratio to get an immediate hit
+ * when failing to get a BA, so we'd switch back to a lower or
+ * zero power reduction. When FW transmits agg with a rate
+ * different from the initial rate, it will not use reduced txp
+ * and will send BA notification twice (one empty with reduced
+ * txp equal to the value from LQ and one with reduced txp 0).
+ * We need to update counters for each txp level accordingly.
*/
if (info->status.ampdu_ack_len == 0)
info->status.ampdu_len = 1;
- rs_collect_tx_data(mvm, lq_sta, curr_tbl, lq_rate.index,
- info->status.ampdu_len,
- info->status.ampdu_ack_len,
- reduced_txp);
+ rs_collect_tlc_data(mvm, lq_sta, curr_tbl, lq_rate.index,
+ info->status.ampdu_len,
+ info->status.ampdu_ack_len);
/* Update success/fail counts if not searching for new mode */
if (lq_sta->rs_state == RS_STATE_STAY_IN_COLUMN) {
@@ -1344,9 +1362,13 @@
else
continue;
- rs_collect_tx_data(mvm, lq_sta, tmp_tbl, lq_rate.index,
- 1, i < retries ? 0 : legacy_success,
- reduced_txp);
+ rs_collect_tpc_data(mvm, lq_sta, tmp_tbl,
+ lq_rate.index, 1,
+ i < retries ? 0 : legacy_success,
+ reduced_txp);
+ rs_collect_tlc_data(mvm, lq_sta, tmp_tbl,
+ lq_rate.index, 1,
+ i < retries ? 0 : legacy_success);
}
/* Update success/fail counts if not searching for new mode */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index 8bf48a7..0914ec2 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -1029,7 +1029,6 @@
struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
mvmsta->tid_data[tid].rate_n_flags =
le32_to_cpu(tx_resp->initial_rate);
- mvmsta->tid_data[tid].reduced_tpc = tx_resp->reduced_tpc;
mvmsta->tid_data[tid].tx_time =
le16_to_cpu(tx_resp->wireless_media_time);
}
@@ -1060,7 +1059,7 @@
/* TODO: not accounted if the whole A-MPDU failed */
info->status.tx_time = tid_data->tx_time;
info->status.status_driver_data[0] =
- (void *)(uintptr_t)tid_data->reduced_tpc;
+ (void *)(uintptr_t)ba_notif->reduced_txp;
info->status.status_driver_data[1] =
(void *)(uintptr_t)tid_data->rate_n_flags;
}
@@ -1133,6 +1132,8 @@
scd_flow, ba_resp_scd_ssn, ba_notif->txed,
ba_notif->txed_2_done);
+ IWL_DEBUG_TX_REPLY(mvm, "reduced txp from ba notif %d\n",
+ ba_notif->reduced_txp);
tid_data->next_reclaimed = ba_resp_scd_ssn;
iwl_mvm_check_ratid_empty(mvm, sta, tid);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 6261a68..00335ea 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -378,7 +378,10 @@
{IWL_PCI_DEVICE(0x3165, 0x8110, iwl3165_2ac_cfg)},
/* 3168 Series */
+ {IWL_PCI_DEVICE(0x24FB, 0x2010, iwl3168_2ac_cfg)},
{IWL_PCI_DEVICE(0x24FB, 0x2110, iwl3168_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x24FB, 0x2050, iwl3168_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x24FB, 0x2150, iwl3168_2ac_cfg)},
{IWL_PCI_DEVICE(0x24FB, 0x0000, iwl3168_2ac_cfg)},
/* 7265 Series */
@@ -475,6 +478,7 @@
{IWL_PCI_DEVICE(0x24F3, 0x0000, iwl8265_2ac_cfg)},
{IWL_PCI_DEVICE(0x24FD, 0x0010, iwl8265_2ac_cfg)},
{IWL_PCI_DEVICE(0x24FD, 0x8010, iwl8265_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x24FD, 0x0810, iwl8265_2ac_cfg)},
/* 9000 Series */
{IWL_PCI_DEVICE(0x9DF0, 0x2A10, iwl5165_2ac_cfg)},
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index c32889a..a28414c 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -991,7 +991,8 @@
goto nla_put_failure;
}
- if (nla_put(skb, HWSIM_ATTR_ADDR_TRANSMITTER, ETH_ALEN, hdr->addr2))
+ if (nla_put(skb, HWSIM_ATTR_ADDR_TRANSMITTER,
+ ETH_ALEN, data->addresses[1].addr))
goto nla_put_failure;
/* We get the skb->data */
@@ -2736,7 +2737,7 @@
spin_lock_bh(&hwsim_radio_lock);
list_for_each_entry(data, &hwsim_radios, list) {
- if (mac80211_hwsim_addr_match(data, addr)) {
+ if (memcmp(data->addresses[1].addr, addr, ETH_ALEN) == 0) {
_found = true;
break;
}
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2400pci.c b/drivers/net/wireless/ralink/rt2x00/rt2400pci.c
index 9a3966c..155f343 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2400pci.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2400pci.c
@@ -273,8 +273,10 @@
!(filter_flags & FIF_PLCPFAIL));
rt2x00_set_field32(®, RXCSR0_DROP_CONTROL,
!(filter_flags & FIF_CONTROL));
- rt2x00_set_field32(®, RXCSR0_DROP_NOT_TO_ME, 1);
+ rt2x00_set_field32(®, RXCSR0_DROP_NOT_TO_ME,
+ !test_bit(CONFIG_MONITORING, &rt2x00dev->flags));
rt2x00_set_field32(®, RXCSR0_DROP_TODS,
+ !test_bit(CONFIG_MONITORING, &rt2x00dev->flags) &&
!rt2x00dev->intf_ap_count);
rt2x00_set_field32(®, RXCSR0_DROP_VERSION_ERROR, 1);
rt2x00mmio_register_write(rt2x00dev, RXCSR0, reg);
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2500pci.c b/drivers/net/wireless/ralink/rt2x00/rt2500pci.c
index 1a6740b..2553cdd 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2500pci.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2500pci.c
@@ -274,8 +274,10 @@
!(filter_flags & FIF_PLCPFAIL));
rt2x00_set_field32(®, RXCSR0_DROP_CONTROL,
!(filter_flags & FIF_CONTROL));
- rt2x00_set_field32(®, RXCSR0_DROP_NOT_TO_ME, 1);
+ rt2x00_set_field32(®, RXCSR0_DROP_NOT_TO_ME,
+ !test_bit(CONFIG_MONITORING, &rt2x00dev->flags));
rt2x00_set_field32(®, RXCSR0_DROP_TODS,
+ !test_bit(CONFIG_MONITORING, &rt2x00dev->flags) &&
!rt2x00dev->intf_ap_count);
rt2x00_set_field32(®, RXCSR0_DROP_VERSION_ERROR, 1);
rt2x00_set_field32(®, RXCSR0_DROP_MCAST,
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2500usb.c b/drivers/net/wireless/ralink/rt2x00/rt2500usb.c
index d26018f..2d64611 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2500usb.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2500usb.c
@@ -437,8 +437,10 @@
!(filter_flags & FIF_PLCPFAIL));
rt2x00_set_field16(®, TXRX_CSR2_DROP_CONTROL,
!(filter_flags & FIF_CONTROL));
- rt2x00_set_field16(®, TXRX_CSR2_DROP_NOT_TO_ME, 1);
+ rt2x00_set_field16(®, TXRX_CSR2_DROP_NOT_TO_ME,
+ !test_bit(CONFIG_MONITORING, &rt2x00dev->flags));
rt2x00_set_field16(®, TXRX_CSR2_DROP_TODS,
+ !test_bit(CONFIG_MONITORING, &rt2x00dev->flags) &&
!rt2x00dev->intf_ap_count);
rt2x00_set_field16(®, TXRX_CSR2_DROP_VERSION_ERROR, 1);
rt2x00_set_field16(®, TXRX_CSR2_DROP_MULTICAST,
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
index 9733b31..a26afca 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
@@ -1490,7 +1490,8 @@
!(filter_flags & FIF_FCSFAIL));
rt2x00_set_field32(®, RX_FILTER_CFG_DROP_PHY_ERROR,
!(filter_flags & FIF_PLCPFAIL));
- rt2x00_set_field32(®, RX_FILTER_CFG_DROP_NOT_TO_ME, 1);
+ rt2x00_set_field32(®, RX_FILTER_CFG_DROP_NOT_TO_ME,
+ !test_bit(CONFIG_MONITORING, &rt2x00dev->flags));
rt2x00_set_field32(®, RX_FILTER_CFG_DROP_NOT_MY_BSSD, 0);
rt2x00_set_field32(®, RX_FILTER_CFG_DROP_VER_ERROR, 1);
rt2x00_set_field32(®, RX_FILTER_CFG_DROP_MULTICAST,
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00.h b/drivers/net/wireless/ralink/rt2x00/rt2x00.h
index 3282ddb..2642714 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00.h
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00.h
@@ -669,6 +669,7 @@
CONFIG_POWERSAVING,
CONFIG_HT_DISABLED,
CONFIG_QOS_DISABLED,
+ CONFIG_MONITORING,
/*
* Mark we currently are sequentially reading TX_STA_FIFO register
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00config.c b/drivers/net/wireless/ralink/rt2x00/rt2x00config.c
index 7e8bb11..6a1f508 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00config.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00config.c
@@ -277,6 +277,11 @@
else
clear_bit(CONFIG_POWERSAVING, &rt2x00dev->flags);
+ if (conf->flags & IEEE80211_CONF_MONITOR)
+ set_bit(CONFIG_MONITORING, &rt2x00dev->flags);
+ else
+ clear_bit(CONFIG_MONITORING, &rt2x00dev->flags);
+
rt2x00dev->curr_band = conf->chandef.chan->band;
rt2x00dev->curr_freq = conf->chandef.chan->center_freq;
rt2x00dev->tx_power = conf->power_level;
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c
index 3c26ee6..13da95a 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c
@@ -385,11 +385,6 @@
*total_flags |= FIF_PSPOLL;
}
- /*
- * Check if there is any work left for us.
- */
- if (rt2x00dev->packet_filter == *total_flags)
- return;
rt2x00dev->packet_filter = *total_flags;
rt2x00dev->ops->lib->config_filter(rt2x00dev, *total_flags);
diff --git a/drivers/net/wireless/ralink/rt2x00/rt61pci.c b/drivers/net/wireless/ralink/rt2x00/rt61pci.c
index c0e730e..24a3436 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt61pci.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt61pci.c
@@ -530,8 +530,10 @@
!(filter_flags & FIF_PLCPFAIL));
rt2x00_set_field32(®, TXRX_CSR0_DROP_CONTROL,
!(filter_flags & (FIF_CONTROL | FIF_PSPOLL)));
- rt2x00_set_field32(®, TXRX_CSR0_DROP_NOT_TO_ME, 1);
+ rt2x00_set_field32(®, TXRX_CSR0_DROP_NOT_TO_ME,
+ !test_bit(CONFIG_MONITORING, &rt2x00dev->flags));
rt2x00_set_field32(®, TXRX_CSR0_DROP_TO_DS,
+ !test_bit(CONFIG_MONITORING, &rt2x00dev->flags) &&
!rt2x00dev->intf_ap_count);
rt2x00_set_field32(®, TXRX_CSR0_DROP_VERSION_ERROR, 1);
rt2x00_set_field32(®, TXRX_CSR0_DROP_MULTICAST,
diff --git a/drivers/net/wireless/ralink/rt2x00/rt73usb.c b/drivers/net/wireless/ralink/rt2x00/rt73usb.c
index 7081e13..7bbc869 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt73usb.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt73usb.c
@@ -480,8 +480,10 @@
!(filter_flags & FIF_PLCPFAIL));
rt2x00_set_field32(®, TXRX_CSR0_DROP_CONTROL,
!(filter_flags & (FIF_CONTROL | FIF_PSPOLL)));
- rt2x00_set_field32(®, TXRX_CSR0_DROP_NOT_TO_ME, 1);
+ rt2x00_set_field32(®, TXRX_CSR0_DROP_NOT_TO_ME,
+ !test_bit(CONFIG_MONITORING, &rt2x00dev->flags));
rt2x00_set_field32(®, TXRX_CSR0_DROP_TO_DS,
+ !test_bit(CONFIG_MONITORING, &rt2x00dev->flags) &&
!rt2x00dev->intf_ap_count);
rt2x00_set_field32(®, TXRX_CSR0_DROP_VERSION_ERROR, 1);
rt2x00_set_field32(®, TXRX_CSR0_DROP_MULTICAST,
diff --git a/drivers/net/wireless/realtek/rtlwifi/regd.c b/drivers/net/wireless/realtek/rtlwifi/regd.c
index a62bf0a..5be3411 100644
--- a/drivers/net/wireless/realtek/rtlwifi/regd.c
+++ b/drivers/net/wireless/realtek/rtlwifi/regd.c
@@ -351,7 +351,6 @@
case COUNTRY_CODE_SPAIN:
case COUNTRY_CODE_FRANCE:
case COUNTRY_CODE_ISRAEL:
- case COUNTRY_CODE_WORLD_WIDE_13:
return &rtl_regdom_12_13;
case COUNTRY_CODE_MKK:
case COUNTRY_CODE_MKK1:
@@ -360,6 +359,7 @@
return &rtl_regdom_14_60_64;
case COUNTRY_CODE_GLOBAL_DOMAIN:
return &rtl_regdom_14;
+ case COUNTRY_CODE_WORLD_WIDE_13:
case COUNTRY_CODE_WORLD_WIDE_13_5G_ALL:
return &rtl_regdom_12_13_5g_all;
default:
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index d6abf19..96ccd4e 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -364,6 +364,7 @@
RING_IDX cons, prod;
unsigned short id;
struct sk_buff *skb;
+ bool more_to_do;
BUG_ON(!netif_carrier_ok(queue->info->netdev));
@@ -398,18 +399,8 @@
queue->tx.rsp_cons = prod;
- /*
- * Set a new event, then check for race with update of tx_cons.
- * Note that it is essential to schedule a callback, no matter
- * how few buffers are pending. Even if there is space in the
- * transmit ring, higher layers may be blocked because too much
- * data is outstanding: in such cases notification from Xen is
- * likely to be the only kick that we'll get.
- */
- queue->tx.sring->rsp_event =
- prod + ((queue->tx.sring->req_prod - prod) >> 1) + 1;
- mb(); /* update shared area */
- } while ((cons == prod) && (prod != queue->tx.sring->rsp_prod));
+ RING_FINAL_CHECK_FOR_RESPONSES(&queue->tx, more_to_do);
+ } while (more_to_do);
xennet_maybe_wake_tx(queue);
}
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index 8ebfcaa..9edf7eb 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -1277,10 +1277,12 @@
device_lock(dev);
claim = ndns->claim;
- if (pmem_should_map_pages(dev) || (claim && is_nd_pfn(claim)))
- mode = "memory";
- else if (claim && is_nd_btt(claim))
+ if (claim && is_nd_btt(claim))
mode = "safe";
+ else if (claim && is_nd_pfn(claim))
+ mode = "memory";
+ else if (!claim && pmem_should_map_pages(dev))
+ mode = "memory";
else
mode = "raw";
rc = sprintf(buf, "%s\n", mode);
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index 0cc9048b..ae81a2f 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -301,10 +301,8 @@
switch (le32_to_cpu(pfn_sb->mode)) {
case PFN_MODE_RAM:
- break;
case PFN_MODE_PMEM:
- /* TODO: allocate from PMEM support */
- return -ENOTTY;
+ break;
default:
return -ENXIO;
}
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index 86829f8..5648317 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -143,11 +143,31 @@
}
EXPORT_SYMBOL(of_mdio_parse_addr);
+/* The following is a list of PHY compatible strings which appear in
+ * some DTBs. The compatible string is never matched against a PHY
+ * driver, so is pointless. We only expect devices which are not PHYs
+ * to have a compatible string, so they can be matched to an MDIO
+ * driver. Encourage users to upgrade their DT blobs to remove these.
+ */
+static const struct of_device_id whitelist_phys[] = {
+ { .compatible = "brcm,40nm-ephy" },
+ { .compatible = "marvell,88E1111", },
+ { .compatible = "marvell,88e1116", },
+ { .compatible = "marvell,88e1118", },
+ { .compatible = "marvell,88e1149r", },
+ { .compatible = "marvell,88e1310", },
+ { .compatible = "marvell,88E1510", },
+ { .compatible = "marvell,88E1514", },
+ { .compatible = "moxa,moxart-rtl8201cp", },
+ {}
+};
+
/*
* Return true if the child node is for a phy. It must either:
* o Compatible string of "ethernet-phy-idX.X"
* o Compatible string of "ethernet-phy-ieee802.3-c45"
* o Compatible string of "ethernet-phy-ieee802.3-c22"
+ * o In the white list above (and issue a warning)
* o No compatibility string
*
* A device which is not a phy is expected to have a compatible string
@@ -166,6 +186,13 @@
if (of_device_is_compatible(child, "ethernet-phy-ieee802.3-c22"))
return true;
+ if (of_match_node(whitelist_phys, child)) {
+ pr_warn(FW_WARN
+ "%s: Whitelisted compatible string. Please remove\n",
+ child->full_name);
+ return true;
+ }
+
if (!of_find_property(child, "compatible", NULL))
return true;
@@ -256,11 +283,19 @@
struct phy_device *of_phy_find_device(struct device_node *phy_np)
{
struct device *d;
+ struct mdio_device *mdiodev;
+
if (!phy_np)
return NULL;
d = bus_find_device(&mdio_bus_type, NULL, phy_np, of_phy_match);
- return d ? to_phy_device(d) : NULL;
+ if (d) {
+ mdiodev = to_mdio_device(d);
+ if (mdiodev->flags & MDIO_DEVICE_FLAG_PHY)
+ return to_phy_device(d);
+ }
+
+ return NULL;
}
EXPORT_SYMBOL(of_phy_find_device);
diff --git a/drivers/ptp/ptp_ixp46x.c b/drivers/ptp/ptp_ixp46x.c
index 934c139..ee4f183 100644
--- a/drivers/ptp/ptp_ixp46x.c
+++ b/drivers/ptp/ptp_ixp46x.c
@@ -178,7 +178,6 @@
static int ptp_ixp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
{
u64 ns;
- u32 remainder;
unsigned long flags;
struct ixp_clock *ixp_clock = container_of(ptp, struct ixp_clock, caps);
struct ixp46x_ts_regs *regs = ixp_clock->regs;
@@ -189,8 +188,7 @@
spin_unlock_irqrestore(®ister_lock, flags);
- ts->tv_sec = div_u64_rem(ns, 1000000000, &remainder);
- ts->tv_nsec = remainder;
+ *ts = ns_to_timespec64(ns);
return 0;
}
@@ -202,8 +200,7 @@
struct ixp_clock *ixp_clock = container_of(ptp, struct ixp_clock, caps);
struct ixp46x_ts_regs *regs = ixp_clock->regs;
- ns = ts->tv_sec * 1000000000ULL;
- ns += ts->tv_nsec;
+ ns = timespec64_to_ns(ts);
spin_lock_irqsave(®ister_lock, flags);
diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c
index cde5ff7..d1a7507 100644
--- a/drivers/ssb/main.c
+++ b/drivers/ssb/main.c
@@ -613,9 +613,10 @@
return err;
}
-static int ssb_bus_register(struct ssb_bus *bus,
- ssb_invariants_func_t get_invariants,
- unsigned long baseaddr)
+static int __maybe_unused
+ssb_bus_register(struct ssb_bus *bus,
+ ssb_invariants_func_t get_invariants,
+ unsigned long baseaddr)
{
int err;
diff --git a/drivers/staging/panel/panel.c b/drivers/staging/panel/panel.c
index 79ac192..70b8f4f 100644
--- a/drivers/staging/panel/panel.c
+++ b/drivers/staging/panel/panel.c
@@ -825,8 +825,7 @@
lcd_send_serial(0x1F); /* R/W=W, RS=0 */
lcd_send_serial(cmd & 0x0F);
lcd_send_serial((cmd >> 4) & 0x0F);
- /* the shortest command takes at least 40 us */
- usleep_range(40, 100);
+ udelay(40); /* the shortest command takes at least 40 us */
spin_unlock_irq(&pprt_lock);
}
@@ -837,8 +836,7 @@
lcd_send_serial(0x5F); /* R/W=W, RS=1 */
lcd_send_serial(data & 0x0F);
lcd_send_serial((data >> 4) & 0x0F);
- /* the shortest data takes at least 40 us */
- usleep_range(40, 100);
+ udelay(40); /* the shortest data takes at least 40 us */
spin_unlock_irq(&pprt_lock);
}
@@ -848,20 +846,19 @@
spin_lock_irq(&pprt_lock);
/* present the data to the data port */
w_dtr(pprt, cmd);
- /* maintain the data during 20 us before the strobe */
- usleep_range(20, 100);
+ udelay(20); /* maintain the data during 20 us before the strobe */
bits.e = BIT_SET;
bits.rs = BIT_CLR;
bits.rw = BIT_CLR;
set_ctrl_bits();
- usleep_range(40, 100); /* maintain the strobe during 40 us */
+ udelay(40); /* maintain the strobe during 40 us */
bits.e = BIT_CLR;
set_ctrl_bits();
- usleep_range(120, 500); /* the shortest command takes at least 120 us */
+ udelay(120); /* the shortest command takes at least 120 us */
spin_unlock_irq(&pprt_lock);
}
@@ -871,20 +868,19 @@
spin_lock_irq(&pprt_lock);
/* present the data to the data port */
w_dtr(pprt, data);
- /* maintain the data during 20 us before the strobe */
- usleep_range(20, 100);
+ udelay(20); /* maintain the data during 20 us before the strobe */
bits.e = BIT_SET;
bits.rs = BIT_SET;
bits.rw = BIT_CLR;
set_ctrl_bits();
- usleep_range(40, 100); /* maintain the strobe during 40 us */
+ udelay(40); /* maintain the strobe during 40 us */
bits.e = BIT_CLR;
set_ctrl_bits();
- usleep_range(45, 100); /* the shortest data takes at least 45 us */
+ udelay(45); /* the shortest data takes at least 45 us */
spin_unlock_irq(&pprt_lock);
}
@@ -894,7 +890,7 @@
spin_lock_irq(&pprt_lock);
/* present the data to the control port */
w_ctr(pprt, cmd);
- usleep_range(60, 120);
+ udelay(60);
spin_unlock_irq(&pprt_lock);
}
@@ -904,7 +900,7 @@
spin_lock_irq(&pprt_lock);
/* present the data to the data port */
w_dtr(pprt, data);
- usleep_range(60, 120);
+ udelay(60);
spin_unlock_irq(&pprt_lock);
}
@@ -947,7 +943,7 @@
lcd_send_serial(0x5F); /* R/W=W, RS=1 */
lcd_send_serial(' ' & 0x0F);
lcd_send_serial((' ' >> 4) & 0x0F);
- usleep_range(40, 100); /* the shortest data takes at least 40 us */
+ udelay(40); /* the shortest data takes at least 40 us */
}
spin_unlock_irq(&pprt_lock);
@@ -971,7 +967,7 @@
w_dtr(pprt, ' ');
/* maintain the data during 20 us before the strobe */
- usleep_range(20, 100);
+ udelay(20);
bits.e = BIT_SET;
bits.rs = BIT_SET;
@@ -979,13 +975,13 @@
set_ctrl_bits();
/* maintain the strobe during 40 us */
- usleep_range(40, 100);
+ udelay(40);
bits.e = BIT_CLR;
set_ctrl_bits();
/* the shortest data takes at least 45 us */
- usleep_range(45, 100);
+ udelay(45);
}
spin_unlock_irq(&pprt_lock);
@@ -1007,7 +1003,7 @@
for (pos = 0; pos < lcd.height * lcd.hwidth; pos++) {
/* present the data to the data port */
w_dtr(pprt, ' ');
- usleep_range(60, 120);
+ udelay(60);
}
spin_unlock_irq(&pprt_lock);
diff --git a/drivers/staging/speakup/main.c b/drivers/staging/speakup/main.c
index 63c59bc..30cf973 100644
--- a/drivers/staging/speakup/main.c
+++ b/drivers/staging/speakup/main.c
@@ -264,8 +264,9 @@
.notifier_call = vt_notifier_call,
};
-static unsigned char get_attributes(u16 *pos)
+static unsigned char get_attributes(struct vc_data *vc, u16 *pos)
{
+ pos = screen_pos(vc, pos - (u16 *)vc->vc_origin, 1);
return (u_char) (scr_readw(pos) >> 8);
}
@@ -275,7 +276,7 @@
spk_y = spk_cy = vc->vc_y;
spk_pos = spk_cp = vc->vc_pos;
spk_old_attr = spk_attr;
- spk_attr = get_attributes((u_short *) spk_pos);
+ spk_attr = get_attributes(vc, (u_short *)spk_pos);
}
static void bleep(u_short val)
@@ -469,8 +470,12 @@
u16 ch = ' ';
if (vc && pos) {
- u16 w = scr_readw(pos);
- u16 c = w & 0xff;
+ u16 w;
+ u16 c;
+
+ pos = screen_pos(vc, pos - (u16 *)vc->vc_origin, 1);
+ w = scr_readw(pos);
+ c = w & 0xff;
if (w & vc->vc_hi_font_mask)
c |= 0x100;
@@ -746,7 +751,7 @@
u_char tmp2;
spk_old_attr = spk_attr;
- spk_attr = get_attributes((u_short *) spk_pos);
+ spk_attr = get_attributes(vc, (u_short *)spk_pos);
for (i = 0; i < vc->vc_cols; i++) {
buf[i] = (u_char) get_char(vc, (u_short *) tmp, &tmp2);
tmp += 2;
@@ -811,7 +816,7 @@
u_short saved_punc_mask = spk_punc_mask;
spk_old_attr = spk_attr;
- spk_attr = get_attributes((u_short *) from);
+ spk_attr = get_attributes(vc, (u_short *)from);
while (from < to) {
buf[i++] = (char)get_char(vc, (u_short *) from, &tmp);
from += 2;
@@ -886,7 +891,7 @@
sentmarks[bn][0] = &sentbuf[bn][0];
i = 0;
spk_old_attr = spk_attr;
- spk_attr = get_attributes((u_short *) start);
+ spk_attr = get_attributes(vc, (u_short *)start);
while (start < end) {
sentbuf[bn][i] = (char)get_char(vc, (u_short *) start, &tmp);
@@ -1585,7 +1590,7 @@
u16 *ptr;
for (ptr = start; ptr < end; ptr++) {
- ch = get_attributes(ptr);
+ ch = get_attributes(vc, ptr);
bg = (ch & 0x70) >> 4;
speakup_console[vc_num]->ht.bgcount[bg]++;
}
diff --git a/drivers/staging/speakup/selection.c b/drivers/staging/speakup/selection.c
index aa5ab6c..41ef099 100644
--- a/drivers/staging/speakup/selection.c
+++ b/drivers/staging/speakup/selection.c
@@ -142,7 +142,9 @@
struct tty_ldisc *ld;
DECLARE_WAITQUEUE(wait, current);
- ld = tty_ldisc_ref_wait(tty);
+ ld = tty_ldisc_ref(tty);
+ if (!ld)
+ goto tty_unref;
tty_buffer_lock_exclusive(&vc->port);
add_wait_queue(&vc->paste_wait, &wait);
@@ -162,6 +164,7 @@
tty_buffer_unlock_exclusive(&vc->port);
tty_ldisc_deref(ld);
+tty_unref:
tty_kref_put(tty);
}
diff --git a/drivers/staging/speakup/serialio.c b/drivers/staging/speakup/serialio.c
index 3b5835b..a5bbb33 100644
--- a/drivers/staging/speakup/serialio.c
+++ b/drivers/staging/speakup/serialio.c
@@ -6,6 +6,11 @@
#include "spk_priv.h"
#include "serialio.h"
+#include <linux/serial_core.h>
+/* WARNING: Do not change this to <linux/serial.h> without testing that
+ * SERIAL_PORT_DFNS does get defined to the appropriate value. */
+#include <asm/serial.h>
+
#ifndef SERIAL_PORT_DFNS
#define SERIAL_PORT_DFNS
#endif
@@ -23,9 +28,15 @@
int baud = 9600, quot = 0;
unsigned int cval = 0;
int cflag = CREAD | HUPCL | CLOCAL | B9600 | CS8;
- const struct old_serial_port *ser = rs_table + index;
+ const struct old_serial_port *ser;
int err;
+ if (index >= ARRAY_SIZE(rs_table)) {
+ pr_info("no port info for ttyS%d\n", index);
+ return NULL;
+ }
+ ser = rs_table + index;
+
/* Divisor, bytesize and parity */
quot = ser->baud_base / baud;
cval = cflag & (CSIZE | CSTOPB);
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index d9a5fc2..b280abaa 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -269,16 +269,13 @@
static void n_tty_check_unthrottle(struct tty_struct *tty)
{
- if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
- tty->link->ldisc->ops->write_wakeup == n_tty_write_wakeup) {
+ if (tty->driver->type == TTY_DRIVER_TYPE_PTY) {
if (chars_in_buffer(tty) > TTY_THRESHOLD_UNTHROTTLE)
return;
if (!tty->count)
return;
n_tty_kick_worker(tty);
- n_tty_write_wakeup(tty->link);
- if (waitqueue_active(&tty->link->write_wait))
- wake_up_interruptible_poll(&tty->link->write_wait, POLLOUT);
+ tty_wakeup(tty->link);
return;
}
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 4097f3f6..e71ec78 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -1379,6 +1379,9 @@
#define PCI_DEVICE_ID_INTEL_BSW_UART1 0x228a
#define PCI_DEVICE_ID_INTEL_BSW_UART2 0x228c
+#define PCI_DEVICE_ID_INTEL_BDW_UART1 0x9ce3
+#define PCI_DEVICE_ID_INTEL_BDW_UART2 0x9ce4
+
#define BYT_PRV_CLK 0x800
#define BYT_PRV_CLK_EN (1 << 0)
#define BYT_PRV_CLK_M_VAL_SHIFT 1
@@ -1461,11 +1464,13 @@
switch (pdev->device) {
case PCI_DEVICE_ID_INTEL_BYT_UART1:
case PCI_DEVICE_ID_INTEL_BSW_UART1:
+ case PCI_DEVICE_ID_INTEL_BDW_UART1:
rx_param->src_id = 3;
tx_param->dst_id = 2;
break;
case PCI_DEVICE_ID_INTEL_BYT_UART2:
case PCI_DEVICE_ID_INTEL_BSW_UART2:
+ case PCI_DEVICE_ID_INTEL_BDW_UART2:
rx_param->src_id = 5;
tx_param->dst_id = 4;
break;
@@ -2062,6 +2067,20 @@
.subdevice = PCI_ANY_ID,
.setup = byt_serial_setup,
},
+ {
+ .vendor = PCI_VENDOR_ID_INTEL,
+ .device = PCI_DEVICE_ID_INTEL_BDW_UART1,
+ .subvendor = PCI_ANY_ID,
+ .subdevice = PCI_ANY_ID,
+ .setup = byt_serial_setup,
+ },
+ {
+ .vendor = PCI_VENDOR_ID_INTEL,
+ .device = PCI_DEVICE_ID_INTEL_BDW_UART2,
+ .subvendor = PCI_ANY_ID,
+ .subdevice = PCI_ANY_ID,
+ .setup = byt_serial_setup,
+ },
/*
* ITE
*/
@@ -5506,6 +5525,16 @@
PCI_CLASS_COMMUNICATION_SERIAL << 8, 0xff0000,
pbn_byt },
+ /* Intel Broadwell */
+ { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_UART1,
+ PCI_ANY_ID, PCI_ANY_ID,
+ PCI_CLASS_COMMUNICATION_SERIAL << 8, 0xff0000,
+ pbn_byt },
+ { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_UART2,
+ PCI_ANY_ID, PCI_ANY_ID,
+ PCI_CLASS_COMMUNICATION_SERIAL << 8, 0xff0000,
+ pbn_byt },
+
/*
* Intel Quark x1000
*/
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 892c923..5cec01c 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -1463,13 +1463,13 @@
{
struct tty_driver *driver = tty->driver;
- if (!tty->count)
- return -EIO;
-
if (driver->type == TTY_DRIVER_TYPE_PTY &&
driver->subtype == PTY_TYPE_MASTER)
return -EIO;
+ if (!tty->count)
+ return -EAGAIN;
+
if (test_bit(TTY_EXCLUSIVE, &tty->flags) && !capable(CAP_SYS_ADMIN))
return -EBUSY;
@@ -2065,7 +2065,12 @@
if (tty) {
mutex_unlock(&tty_mutex);
- tty_lock(tty);
+ retval = tty_lock_interruptible(tty);
+ if (retval) {
+ if (retval == -EINTR)
+ retval = -ERESTARTSYS;
+ goto err_unref;
+ }
/* safe to drop the kref from tty_driver_lookup_tty() */
tty_kref_put(tty);
retval = tty_reopen(tty);
@@ -2083,7 +2088,11 @@
if (IS_ERR(tty)) {
retval = PTR_ERR(tty);
- goto err_file;
+ if (retval != -EAGAIN || signal_pending(current))
+ goto err_file;
+ tty_free_file(filp);
+ schedule();
+ goto retry_open;
}
tty_add_file(tty, filp);
@@ -2152,6 +2161,7 @@
return 0;
err_unlock:
mutex_unlock(&tty_mutex);
+err_unref:
/* after locks to avoid deadlock */
if (!IS_ERR_OR_NULL(driver))
tty_driver_kref_put(driver);
@@ -2649,6 +2659,28 @@
}
/**
+ * tiocgetd - get line discipline
+ * @tty: tty device
+ * @p: pointer to user data
+ *
+ * Retrieves the line discipline id directly from the ldisc.
+ *
+ * Locking: waits for ldisc reference (in case the line discipline
+ * is changing or the tty is being hungup)
+ */
+
+static int tiocgetd(struct tty_struct *tty, int __user *p)
+{
+ struct tty_ldisc *ld;
+ int ret;
+
+ ld = tty_ldisc_ref_wait(tty);
+ ret = put_user(ld->ops->num, p);
+ tty_ldisc_deref(ld);
+ return ret;
+}
+
+/**
* send_break - performed time break
* @tty: device to break on
* @duration: timeout in mS
@@ -2874,7 +2906,7 @@
case TIOCGSID:
return tiocgsid(tty, real_tty, p);
case TIOCGETD:
- return put_user(tty->ldisc->ops->num, (int __user *)p);
+ return tiocgetd(tty, p);
case TIOCSETD:
return tiocsetd(tty, p);
case TIOCVHANGUP:
diff --git a/drivers/tty/tty_mutex.c b/drivers/tty/tty_mutex.c
index 77703a39..d2f3c4c 100644
--- a/drivers/tty/tty_mutex.c
+++ b/drivers/tty/tty_mutex.c
@@ -19,6 +19,14 @@
}
EXPORT_SYMBOL(tty_lock);
+int tty_lock_interruptible(struct tty_struct *tty)
+{
+ if (WARN(tty->magic != TTY_MAGIC, "L Bad %p\n", tty))
+ return -EIO;
+ tty_kref_get(tty);
+ return mutex_lock_interruptible(&tty->legacy_mutex);
+}
+
void __lockfunc tty_unlock(struct tty_struct *tty)
{
if (WARN(tty->magic != TTY_MAGIC, "U Bad %p\n", tty))
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index e7cbc44..bd51bdd 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -4250,6 +4250,7 @@
{
return screenpos(vc, 2 * w_offset, viewed);
}
+EXPORT_SYMBOL_GPL(screen_pos);
void getconsxy(struct vc_data *vc, unsigned char *p)
{
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 26ca4f9..fa4e239 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -428,7 +428,8 @@
set_bit(rb->index, &acm->read_urbs_free);
dev_dbg(&acm->data->dev, "%s - non-zero urb status: %d\n",
__func__, status);
- return;
+ if ((status != -ENOENT) || (urb->actual_length == 0))
+ return;
}
usb_mark_last_busy(acm->dev);
@@ -1404,6 +1405,8 @@
usb_sndbulkpipe(usb_dev, epwrite->bEndpointAddress),
NULL, acm->writesize, acm_write_bulk, snd);
snd->urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
+ if (quirks & SEND_ZERO_PACKET)
+ snd->urb->transfer_flags |= URB_ZERO_PACKET;
snd->instance = acm;
}
@@ -1838,6 +1841,11 @@
},
#endif
+ /*Samsung phone in firmware update mode */
+ { USB_DEVICE(0x04e8, 0x685d),
+ .driver_info = IGNORE_DEVICE,
+ },
+
/* Exclude Infineon Flash Loader utility */
{ USB_DEVICE(0x058b, 0x0041),
.driver_info = IGNORE_DEVICE,
@@ -1861,6 +1869,10 @@
{ USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ACM,
USB_CDC_ACM_PROTO_AT_CDMA) },
+ { USB_DEVICE(0x1519, 0x0452), /* Intel 7260 modem */
+ .driver_info = SEND_ZERO_PACKET,
+ },
+
{ }
};
diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h
index dd9af38..ccfaba9 100644
--- a/drivers/usb/class/cdc-acm.h
+++ b/drivers/usb/class/cdc-acm.h
@@ -134,3 +134,4 @@
#define IGNORE_DEVICE BIT(5)
#define QUIRK_CONTROL_LINE_STATE BIT(6)
#define CLEAR_HALT_CONDITIONS BIT(7)
+#define SEND_ZERO_PACKET BIT(8)
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 51b43691..350dcd9 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -5401,7 +5401,6 @@
}
bos = udev->bos;
- udev->bos = NULL;
for (i = 0; i < SET_CONFIG_TRIES; ++i) {
@@ -5494,8 +5493,11 @@
usb_set_usb2_hardware_lpm(udev, 1);
usb_unlocked_enable_lpm(udev);
usb_enable_ltm(udev);
- usb_release_bos_descriptor(udev);
- udev->bos = bos;
+ /* release the new BOS descriptor allocated by hub_port_init() */
+ if (udev->bos != bos) {
+ usb_release_bos_descriptor(udev);
+ udev->bos = bos;
+ }
return 0;
re_enumerate:
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 9b90ad7..987813b 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -99,6 +99,7 @@
{ USB_DEVICE(0x10C4, 0x81AC) }, /* MSD Dash Hawk */
{ USB_DEVICE(0x10C4, 0x81AD) }, /* INSYS USB Modem */
{ USB_DEVICE(0x10C4, 0x81C8) }, /* Lipowsky Industrie Elektronik GmbH, Baby-JTAG */
+ { USB_DEVICE(0x10C4, 0x81D7) }, /* IAI Corp. RCB-CV-USB USB to RS485 Adaptor */
{ USB_DEVICE(0x10C4, 0x81E2) }, /* Lipowsky Industrie Elektronik GmbH, Baby-LIN */
{ USB_DEVICE(0x10C4, 0x81E7) }, /* Aerocomm Radio */
{ USB_DEVICE(0x10C4, 0x81E8) }, /* Zephyr Bioharness */
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index a5a0376..8c660ae 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -824,6 +824,7 @@
{ USB_DEVICE(FTDI_VID, FTDI_TURTELIZER_PID),
.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
{ USB_DEVICE(RATOC_VENDOR_ID, RATOC_PRODUCT_ID_USB60F) },
+ { USB_DEVICE(RATOC_VENDOR_ID, RATOC_PRODUCT_ID_SCU18) },
{ USB_DEVICE(FTDI_VID, FTDI_REU_TINY_PID) },
/* Papouch devices based on FTDI chip */
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index 67c6d44..a84df25 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -615,6 +615,7 @@
*/
#define RATOC_VENDOR_ID 0x0584
#define RATOC_PRODUCT_ID_USB60F 0xb020
+#define RATOC_PRODUCT_ID_SCU18 0xb03a
/*
* Infineon Technologies
diff --git a/drivers/usb/serial/mxu11x0.c b/drivers/usb/serial/mxu11x0.c
index e3c3f57c..6196073 100644
--- a/drivers/usb/serial/mxu11x0.c
+++ b/drivers/usb/serial/mxu11x0.c
@@ -368,6 +368,16 @@
return 0;
}
+static int mxu1_port_remove(struct usb_serial_port *port)
+{
+ struct mxu1_port *mxport;
+
+ mxport = usb_get_serial_port_data(port);
+ kfree(mxport);
+
+ return 0;
+}
+
static int mxu1_startup(struct usb_serial *serial)
{
struct mxu1_device *mxdev;
@@ -427,6 +437,14 @@
return err;
}
+static void mxu1_release(struct usb_serial *serial)
+{
+ struct mxu1_device *mxdev;
+
+ mxdev = usb_get_serial_data(serial);
+ kfree(mxdev);
+}
+
static int mxu1_write_byte(struct usb_serial_port *port, u32 addr,
u8 mask, u8 byte)
{
@@ -957,7 +975,9 @@
.id_table = mxu1_idtable,
.num_ports = 1,
.port_probe = mxu1_port_probe,
+ .port_remove = mxu1_port_remove,
.attach = mxu1_startup,
+ .release = mxu1_release,
.open = mxu1_open,
.close = mxu1_close,
.ioctl = mxu1_ioctl,
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index f228060..db86e51 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -268,6 +268,8 @@
#define TELIT_PRODUCT_CC864_SINGLE 0x1006
#define TELIT_PRODUCT_DE910_DUAL 0x1010
#define TELIT_PRODUCT_UE910_V2 0x1012
+#define TELIT_PRODUCT_LE922_USBCFG0 0x1042
+#define TELIT_PRODUCT_LE922_USBCFG3 0x1043
#define TELIT_PRODUCT_LE920 0x1200
#define TELIT_PRODUCT_LE910 0x1201
@@ -615,6 +617,16 @@
.reserved = BIT(1) | BIT(5),
};
+static const struct option_blacklist_info telit_le922_blacklist_usbcfg0 = {
+ .sendsetup = BIT(2),
+ .reserved = BIT(0) | BIT(1) | BIT(3),
+};
+
+static const struct option_blacklist_info telit_le922_blacklist_usbcfg3 = {
+ .sendsetup = BIT(0),
+ .reserved = BIT(1) | BIT(2) | BIT(3),
+};
+
static const struct usb_device_id option_ids[] = {
{ USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) },
{ USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_RICOLA) },
@@ -1160,6 +1172,10 @@
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_CC864_SINGLE) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_DE910_DUAL) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UE910_V2) },
+ { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG0),
+ .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 },
+ { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG3),
+ .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910),
.driver_info = (kernel_ulong_t)&telit_le910_blacklist },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920),
@@ -1679,7 +1695,7 @@
{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_EU3_P) },
{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PH8),
.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
- { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX) },
+ { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX, 0xff) },
{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PLXX),
.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_HC28_MDM) },
diff --git a/drivers/usb/serial/visor.c b/drivers/usb/serial/visor.c
index 60afb39..337a0be 100644
--- a/drivers/usb/serial/visor.c
+++ b/drivers/usb/serial/visor.c
@@ -544,6 +544,11 @@
(serial->num_interrupt_in == 0))
return 0;
+ if (serial->num_bulk_in < 2 || serial->num_interrupt_in < 2) {
+ dev_err(&serial->interface->dev, "missing endpoints\n");
+ return -ENODEV;
+ }
+
/*
* It appears that Treos and Kyoceras want to use the
* 1st bulk in endpoint to communicate with the 2nd bulk out endpoint,
@@ -597,8 +602,10 @@
*/
/* some sanity check */
- if (serial->num_ports < 2)
- return -1;
+ if (serial->num_bulk_out < 2) {
+ dev_err(&serial->interface->dev, "missing bulk out endpoints\n");
+ return -ENODEV;
+ }
/* port 0 now uses the modified endpoint Address */
port = serial->port[0];
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 7b9cd49..afb4374 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1736,37 +1736,13 @@
return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL);
}
-static void blkdev_vm_open(struct vm_area_struct *vma)
-{
- struct inode *bd_inode = bdev_file_inode(vma->vm_file);
- struct block_device *bdev = I_BDEV(bd_inode);
-
- inode_lock(bd_inode);
- bdev->bd_map_count++;
- inode_unlock(bd_inode);
-}
-
-static void blkdev_vm_close(struct vm_area_struct *vma)
-{
- struct inode *bd_inode = bdev_file_inode(vma->vm_file);
- struct block_device *bdev = I_BDEV(bd_inode);
-
- inode_lock(bd_inode);
- bdev->bd_map_count--;
- inode_unlock(bd_inode);
-}
-
static const struct vm_operations_struct blkdev_dax_vm_ops = {
- .open = blkdev_vm_open,
- .close = blkdev_vm_close,
.fault = blkdev_dax_fault,
.pmd_fault = blkdev_dax_pmd_fault,
.pfn_mkwrite = blkdev_dax_fault,
};
static const struct vm_operations_struct blkdev_default_vm_ops = {
- .open = blkdev_vm_open,
- .close = blkdev_vm_close,
.fault = filemap_fault,
.map_pages = filemap_map_pages,
};
@@ -1774,18 +1750,14 @@
static int blkdev_mmap(struct file *file, struct vm_area_struct *vma)
{
struct inode *bd_inode = bdev_file_inode(file);
- struct block_device *bdev = I_BDEV(bd_inode);
file_accessed(file);
- inode_lock(bd_inode);
- bdev->bd_map_count++;
if (IS_DAX(bd_inode)) {
vma->vm_ops = &blkdev_dax_vm_ops;
vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
} else {
vma->vm_ops = &blkdev_default_vm_ops;
}
- inode_unlock(bd_inode);
return 0;
}
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index a5b8eb6..6402eaf 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -1261,6 +1261,9 @@
COMPATIBLE_IOCTL(HCIINQUIRY)
COMPATIBLE_IOCTL(HCIUARTSETPROTO)
COMPATIBLE_IOCTL(HCIUARTGETPROTO)
+COMPATIBLE_IOCTL(HCIUARTGETDEVICE)
+COMPATIBLE_IOCTL(HCIUARTSETFLAGS)
+COMPATIBLE_IOCTL(HCIUARTGETFLAGS)
COMPATIBLE_IOCTL(RFCOMMCREATEDEV)
COMPATIBLE_IOCTL(RFCOMMRELEASEDEV)
COMPATIBLE_IOCTL(RFCOMMGETDEVLIST)
diff --git a/fs/dax.c b/fs/dax.c
index 4fd6b0c..e0e9358 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -58,6 +58,26 @@
blk_queue_exit(bdev->bd_queue);
}
+struct page *read_dax_sector(struct block_device *bdev, sector_t n)
+{
+ struct page *page = alloc_pages(GFP_KERNEL, 0);
+ struct blk_dax_ctl dax = {
+ .size = PAGE_SIZE,
+ .sector = n & ~((((int) PAGE_SIZE) / 512) - 1),
+ };
+ long rc;
+
+ if (!page)
+ return ERR_PTR(-ENOMEM);
+
+ rc = dax_map_atomic(bdev, &dax);
+ if (rc < 0)
+ return ERR_PTR(rc);
+ memcpy_from_pmem(page_address(page), dax.addr, PAGE_SIZE);
+ dax_unmap_atomic(bdev, &dax);
+ return page;
+}
+
/*
* dax_clear_blocks() is called from within transaction context from XFS,
* and hence this means the stack from this point must follow GFP_NOFS
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 5bcd92d..0cb1abd 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1215,7 +1215,7 @@
hdr->pgio_mirror_idx + 1,
&hdr->pgio_mirror_idx))
goto out_eagain;
- set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+ set_bit(NFS_LAYOUT_RETURN_REQUESTED,
&hdr->lseg->pls_layout->plh_flags);
pnfs_read_resend_pnfs(hdr);
return task->tk_status;
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index 29898a9..eb37046 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -412,7 +412,7 @@
OP_ILLEGAL, GFP_NOIO);
if (!fail_return) {
if (ff_layout_has_available_ds(lseg))
- set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+ set_bit(NFS_LAYOUT_RETURN_REQUESTED,
&lseg->pls_layout->plh_flags);
else
pnfs_error_mark_layout_for_return(ino, lseg);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index a3592cc..482b6e9 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -52,9 +52,7 @@
*/
static LIST_HEAD(pnfs_modules_tbl);
-static int
-pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, const nfs4_stateid *stateid,
- enum pnfs_iomode iomode, bool sync);
+static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo);
/* Return the registered pnfs layout driver module matching given id */
static struct pnfs_layoutdriver_type *
@@ -243,6 +241,8 @@
{
struct inode *inode = lo->plh_inode;
+ pnfs_layoutreturn_before_put_layout_hdr(lo);
+
if (atomic_dec_and_lock(&lo->plh_refcount, &inode->i_lock)) {
if (!list_empty(&lo->plh_segs))
WARN_ONCE(1, "NFS: BUG unfreed layout segments.\n");
@@ -345,58 +345,6 @@
rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq);
}
-/* Return true if layoutreturn is needed */
-static bool
-pnfs_layout_need_return(struct pnfs_layout_hdr *lo,
- struct pnfs_layout_segment *lseg)
-{
- struct pnfs_layout_segment *s;
-
- if (!test_and_clear_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))
- return false;
-
- list_for_each_entry(s, &lo->plh_segs, pls_list)
- if (s != lseg && test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags))
- return false;
-
- return true;
-}
-
-static bool
-pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo)
-{
- if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
- return false;
- lo->plh_return_iomode = 0;
- pnfs_get_layout_hdr(lo);
- clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags);
- return true;
-}
-
-static void pnfs_layoutreturn_before_put_lseg(struct pnfs_layout_segment *lseg,
- struct pnfs_layout_hdr *lo, struct inode *inode)
-{
- lo = lseg->pls_layout;
- inode = lo->plh_inode;
-
- spin_lock(&inode->i_lock);
- if (pnfs_layout_need_return(lo, lseg)) {
- nfs4_stateid stateid;
- enum pnfs_iomode iomode;
- bool send;
-
- nfs4_stateid_copy(&stateid, &lo->plh_stateid);
- iomode = lo->plh_return_iomode;
- send = pnfs_prepare_layoutreturn(lo);
- spin_unlock(&inode->i_lock);
- if (send) {
- /* Send an async layoutreturn so we dont deadlock */
- pnfs_send_layoutreturn(lo, &stateid, iomode, false);
- }
- } else
- spin_unlock(&inode->i_lock);
-}
-
void
pnfs_put_lseg(struct pnfs_layout_segment *lseg)
{
@@ -410,15 +358,8 @@
atomic_read(&lseg->pls_refcount),
test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
- /* Handle the case where refcount != 1 */
- if (atomic_add_unless(&lseg->pls_refcount, -1, 1))
- return;
-
lo = lseg->pls_layout;
inode = lo->plh_inode;
- /* Do we need a layoutreturn? */
- if (test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))
- pnfs_layoutreturn_before_put_lseg(lseg, lo, inode);
if (atomic_dec_and_lock(&lseg->pls_refcount, &inode->i_lock)) {
if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags)) {
@@ -937,6 +878,17 @@
rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq);
}
+static bool
+pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo)
+{
+ if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
+ return false;
+ lo->plh_return_iomode = 0;
+ pnfs_get_layout_hdr(lo);
+ clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
+ return true;
+}
+
static int
pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, const nfs4_stateid *stateid,
enum pnfs_iomode iomode, bool sync)
@@ -971,6 +923,48 @@
return status;
}
+/* Return true if layoutreturn is needed */
+static bool
+pnfs_layout_need_return(struct pnfs_layout_hdr *lo)
+{
+ struct pnfs_layout_segment *s;
+
+ if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags))
+ return false;
+
+ /* Defer layoutreturn until all lsegs are done */
+ list_for_each_entry(s, &lo->plh_segs, pls_list) {
+ if (test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags))
+ return false;
+ }
+
+ return true;
+}
+
+static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo)
+{
+ struct inode *inode= lo->plh_inode;
+
+ if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags))
+ return;
+ spin_lock(&inode->i_lock);
+ if (pnfs_layout_need_return(lo)) {
+ nfs4_stateid stateid;
+ enum pnfs_iomode iomode;
+ bool send;
+
+ nfs4_stateid_copy(&stateid, &lo->plh_stateid);
+ iomode = lo->plh_return_iomode;
+ send = pnfs_prepare_layoutreturn(lo);
+ spin_unlock(&inode->i_lock);
+ if (send) {
+ /* Send an async layoutreturn so we dont deadlock */
+ pnfs_send_layoutreturn(lo, &stateid, iomode, false);
+ }
+ } else
+ spin_unlock(&inode->i_lock);
+}
+
/*
* Initiates a LAYOUTRETURN(FILE), and removes the pnfs_layout_hdr
* when the layout segment list is empty.
@@ -1091,7 +1085,7 @@
nfs4_stateid_copy(&stateid, &lo->plh_stateid);
/* always send layoutreturn if being marked so */
- if (test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+ if (test_and_clear_bit(NFS_LAYOUT_RETURN_REQUESTED,
&lo->plh_flags))
layoutreturn = pnfs_prepare_layoutreturn(lo);
@@ -1772,7 +1766,7 @@
pnfs_set_plh_return_iomode(lo, return_range->iomode);
if (!mark_lseg_invalid(lseg, tmp_list))
remaining++;
- set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+ set_bit(NFS_LAYOUT_RETURN_REQUESTED,
&lo->plh_flags);
}
return remaining;
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 9f4e2a4..1ac1db5 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -94,8 +94,8 @@
NFS_LAYOUT_RO_FAILED = 0, /* get ro layout failed stop trying */
NFS_LAYOUT_RW_FAILED, /* get rw layout failed stop trying */
NFS_LAYOUT_BULK_RECALL, /* bulk recall affecting layout */
- NFS_LAYOUT_RETURN, /* Return this layout ASAP */
- NFS_LAYOUT_RETURN_BEFORE_CLOSE, /* Return this layout before close */
+ NFS_LAYOUT_RETURN, /* layoutreturn in progress */
+ NFS_LAYOUT_RETURN_REQUESTED, /* Return this layout ASAP */
NFS_LAYOUT_INVALID_STID, /* layout stateid id is invalid */
NFS_LAYOUT_FIRST_LAYOUTGET, /* Serialize first layoutget */
};
diff --git a/fs/timerfd.c b/fs/timerfd.c
index b94fa6c..053818d 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -153,7 +153,7 @@
if (isalarm(ctx))
remaining = alarm_expires_remaining(&ctx->t.alarm);
else
- remaining = hrtimer_expires_remaining(&ctx->t.tmr);
+ remaining = hrtimer_expires_remaining_adjusted(&ctx->t.tmr);
return remaining.tv64 < 0 ? ktime_set(0, 0): remaining;
}
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 8204c3d..818e450 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -14,6 +14,17 @@
dax_iodone_t);
int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
dax_iodone_t);
+
+#ifdef CONFIG_FS_DAX
+struct page *read_dax_sector(struct block_device *bdev, sector_t n);
+#else
+static inline struct page *read_dax_sector(struct block_device *bdev,
+ sector_t n)
+{
+ return ERR_PTR(-ENXIO);
+}
+#endif
+
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
unsigned int flags, get_block_t, dax_iodone_t);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 1a20462..ae68100 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -484,9 +484,6 @@
int bd_fsfreeze_count;
/* Mutex for freeze */
struct mutex bd_fsfreeze_mutex;
-#ifdef CONFIG_FS_DAX
- int bd_map_count;
-#endif
};
/*
@@ -2907,7 +2904,7 @@
static inline bool io_is_direct(struct file *filp)
{
- return (filp->f_flags & O_DIRECT) || IS_DAX(file_inode(filp));
+ return (filp->f_flags & O_DIRECT) || IS_DAX(filp->f_mapping->host);
}
static inline int iocb_flags(struct file *file)
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 76dd4f0..2ead22d 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -87,7 +87,8 @@
* @function: timer expiry callback function
* @base: pointer to the timer base (per cpu and per clock)
* @state: state information (See bit values above)
- * @start_pid: timer statistics field to store the pid of the task which
+ * @is_rel: Set if the timer was armed relative
+ * @start_pid: timer statistics field to store the pid of the task which
* started the timer
* @start_site: timer statistics field to store the site where the timer
* was started
@@ -101,7 +102,8 @@
ktime_t _softexpires;
enum hrtimer_restart (*function)(struct hrtimer *);
struct hrtimer_clock_base *base;
- unsigned long state;
+ u8 state;
+ u8 is_rel;
#ifdef CONFIG_TIMER_STATS
int start_pid;
void *start_site;
@@ -321,6 +323,27 @@
#endif
+static inline ktime_t
+__hrtimer_expires_remaining_adjusted(const struct hrtimer *timer, ktime_t now)
+{
+ ktime_t rem = ktime_sub(timer->node.expires, now);
+
+ /*
+ * Adjust relative timers for the extra we added in
+ * hrtimer_start_range_ns() to prevent short timeouts.
+ */
+ if (IS_ENABLED(CONFIG_TIME_LOW_RES) && timer->is_rel)
+ rem.tv64 -= hrtimer_resolution;
+ return rem;
+}
+
+static inline ktime_t
+hrtimer_expires_remaining_adjusted(const struct hrtimer *timer)
+{
+ return __hrtimer_expires_remaining_adjusted(timer,
+ timer->base->get_time());
+}
+
extern void clock_was_set(void);
#ifdef CONFIG_TIMERFD
extern void timerfd_clock_was_set(void);
@@ -390,7 +413,12 @@
}
/* Query timers: */
-extern ktime_t hrtimer_get_remaining(const struct hrtimer *timer);
+extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust);
+
+static inline ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
+{
+ return __hrtimer_get_remaining(timer, false);
+}
extern u64 hrtimer_get_next_event(void);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5ac140d..289c231 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -512,7 +512,6 @@
clear_bit(NAPI_STATE_NPSVC, &n->state);
}
-#ifdef CONFIG_SMP
/**
* napi_synchronize - wait until NAPI is not running
* @n: napi context
@@ -523,12 +522,12 @@
*/
static inline void napi_synchronize(const struct napi_struct *n)
{
- while (test_bit(NAPI_STATE_SCHED, &n->state))
- msleep(1);
+ if (IS_ENABLED(CONFIG_SMP))
+ while (test_bit(NAPI_STATE_SCHED, &n->state))
+ msleep(1);
+ else
+ barrier();
}
-#else
-# define napi_synchronize(n) barrier()
-#endif
enum netdev_queue_state_t {
__QUEUE_STATE_DRV_XOFF,
diff --git a/include/linux/of.h b/include/linux/of.h
index dd10626..dc6e396 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -929,7 +929,7 @@
return num;
}
-#ifdef CONFIG_OF
+#if defined(CONFIG_OF) && !defined(MODULE)
#define _OF_DECLARE(table, name, compat, fn, fn_type) \
static const struct of_device_id __of_table_##name \
__used __section(__##table##_of_table) \
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f9828a4..b35a61a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -634,9 +634,6 @@
int nr_cgroups; /* cgroup evts */
void *task_ctx_data; /* pmu specific data */
struct rcu_head rcu_head;
-
- struct delayed_work orphans_remove;
- bool orphans_remove_sched;
};
/*
@@ -729,7 +726,7 @@
extern void perf_event_exit_task(struct task_struct *child);
extern void perf_event_free_task(struct task_struct *task);
extern void perf_event_delayed_put(struct task_struct *task);
-extern struct perf_event *perf_event_get(unsigned int fd);
+extern struct file *perf_event_get(unsigned int fd);
extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event);
extern void perf_event_print_debug(void);
extern void perf_pmu_disable(struct pmu *pmu);
@@ -1044,7 +1041,7 @@
extern u64 perf_swevent_set_period(struct perf_event *event);
extern void perf_event_enable(struct perf_event *event);
extern void perf_event_disable(struct perf_event *event);
-extern int __perf_event_disable(void *info);
+extern void perf_event_disable_local(struct perf_event *event);
extern void perf_event_task_tick(void);
#else /* !CONFIG_PERF_EVENTS: */
static inline void *
@@ -1070,7 +1067,7 @@
static inline void perf_event_exit_task(struct task_struct *child) { }
static inline void perf_event_free_task(struct task_struct *task) { }
static inline void perf_event_delayed_put(struct task_struct *task) { }
-static inline struct perf_event *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); }
+static inline struct file *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); }
static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event)
{
return ERR_PTR(-EINVAL);
diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h
index 0703b53..37448ab 100644
--- a/include/linux/pfn_t.h
+++ b/include/linux/pfn_t.h
@@ -29,7 +29,7 @@
return __pfn_to_pfn_t(pfn, 0);
}
-extern pfn_t phys_to_pfn_t(dma_addr_t addr, unsigned long flags);
+extern pfn_t phys_to_pfn_t(phys_addr_t addr, unsigned long flags);
static inline bool pfn_t_has_page(pfn_t pfn)
{
@@ -48,7 +48,7 @@
return NULL;
}
-static inline dma_addr_t pfn_t_to_phys(pfn_t pfn)
+static inline phys_addr_t pfn_t_to_phys(pfn_t pfn)
{
return PFN_PHYS(pfn_t_to_pfn(pfn));
}
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 2fd8708..d9fb4b0 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -649,6 +649,7 @@
/* tty_mutex.c */
/* functions for preparation of BKL removal */
extern void __lockfunc tty_lock(struct tty_struct *tty);
+extern int tty_lock_interruptible(struct tty_struct *tty);
extern void __lockfunc tty_unlock(struct tty_struct *tty);
extern void __lockfunc tty_lock_slave(struct tty_struct *tty);
extern void __lockfunc tty_unlock_slave(struct tty_struct *tty);
diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 5289929..5ee3c68 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -252,6 +252,12 @@
#define L2CAP_PSM_3DSP 0x0021
#define L2CAP_PSM_IPSP 0x0023 /* 6LoWPAN */
+#define L2CAP_PSM_DYN_START 0x1001
+#define L2CAP_PSM_DYN_END 0xffff
+#define L2CAP_PSM_AUTO_END 0x10ff
+#define L2CAP_PSM_LE_DYN_START 0x0080
+#define L2CAP_PSM_LE_DYN_END 0x00ff
+
/* channel identifier */
#define L2CAP_CID_SIGNALING 0x0001
#define L2CAP_CID_CONN_LESS 0x0002
diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h
index 6816f0f..30a56ab 100644
--- a/include/net/dst_metadata.h
+++ b/include/net/dst_metadata.h
@@ -44,6 +44,24 @@
return dst && !(dst->flags & DST_METADATA);
}
+static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a,
+ const struct sk_buff *skb_b)
+{
+ const struct metadata_dst *a, *b;
+
+ if (!(skb_a->_skb_refdst | skb_b->_skb_refdst))
+ return 0;
+
+ a = (const struct metadata_dst *) skb_dst(skb_a);
+ b = (const struct metadata_dst *) skb_dst(skb_b);
+
+ if (!a != !b || a->u.tun_info.options_len != b->u.tun_info.options_len)
+ return 1;
+
+ return memcmp(&a->u.tun_info, &b->u.tun_info,
+ sizeof(a->u.tun_info) + a->u.tun_info.options_len);
+}
+
struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags);
struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags);
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 877f682..295d291 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -64,8 +64,16 @@
void ip6_route_input(struct sk_buff *skb);
-struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk,
- struct flowi6 *fl6);
+struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
+ struct flowi6 *fl6, int flags);
+
+static inline struct dst_entry *ip6_route_output(struct net *net,
+ const struct sock *sk,
+ struct flowi6 *fl6)
+{
+ return ip6_route_output_flags(net, sk, fl6, 0);
+}
+
struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6,
int flags);
diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index 788ef58..62e17d1 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -79,12 +79,10 @@
const struct nf_conntrack_l3proto *l3proto,
const struct nf_conntrack_l4proto *proto);
-#ifdef CONFIG_LOCKDEP
-# define CONNTRACK_LOCKS 8
-#else
-# define CONNTRACK_LOCKS 1024
-#endif
+#define CONNTRACK_LOCKS 1024
+
extern spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS];
+void nf_conntrack_lock(spinlock_t *lock);
extern spinlock_t nf_conntrack_expect_lock;
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 20e7212..205630b 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -756,7 +756,6 @@
/* Reference counting. */
atomic_t refcnt;
- __u32 dead:1,
/* RTO-Pending : A flag used to track if one of the DATA
* chunks sent to this address is currently being
* used to compute a RTT. If this flag is 0,
@@ -766,7 +765,7 @@
* calculation completes (i.e. the DATA chunk
* is SACK'd) clear this flag.
*/
- rto_pending:1,
+ __u32 rto_pending:1,
/*
* hb_sent : a flag that signals that we have a pending
@@ -955,7 +954,7 @@
void sctp_transport_pmtu(struct sctp_transport *, struct sock *sk);
void sctp_transport_free(struct sctp_transport *);
void sctp_transport_reset_timers(struct sctp_transport *);
-void sctp_transport_hold(struct sctp_transport *);
+int sctp_transport_hold(struct sctp_transport *);
void sctp_transport_put(struct sctp_transport *);
void sctp_transport_update_rto(struct sctp_transport *, __u32);
void sctp_transport_raise_cwnd(struct sctp_transport *, __u32, __u32);
diff --git a/include/net/sock.h b/include/net/sock.h
index b9e7b3d..f5ea148 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1036,18 +1036,6 @@
#ifdef SOCK_REFCNT_DEBUG
atomic_t socks;
#endif
-#ifdef CONFIG_MEMCG_KMEM
- /*
- * cgroup specific init/deinit functions. Called once for all
- * protocols that implement it, from cgroups populate function.
- * This function has to setup any files the protocol want to
- * appear in the kmem cgroup filesystem.
- */
- int (*init_cgroup)(struct mem_cgroup *memcg,
- struct cgroup_subsys *ss);
- void (*destroy_cgroup)(struct mem_cgroup *memcg);
- struct cg_proto *(*proto_cgroup)(struct mem_cgroup *memcg);
-#endif
int (*diag_destroy)(struct sock *sk, int err);
};
diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h
index 7dda3d7..aecd303 100644
--- a/include/net/sock_reuseport.h
+++ b/include/net/sock_reuseport.h
@@ -16,7 +16,7 @@
};
extern int reuseport_alloc(struct sock *sk);
-extern int reuseport_add_sock(struct sock *sk, const struct sock *sk2);
+extern int reuseport_add_sock(struct sock *sk, struct sock *sk2);
extern void reuseport_detach_sock(struct sock *sk);
extern struct sock *reuseport_select_sock(struct sock *sk,
u32 hash,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 8ea1997..f6f8f03 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -216,7 +216,7 @@
/* TCP thin-stream limits */
#define TCP_THIN_LINEAR_RETRIES 6 /* After 6 linear retries, do exp. backoff */
-/* TCP initial congestion window as per draft-hkchu-tcpm-initcwnd-01 */
+/* TCP initial congestion window as per rfc6928 */
#define TCP_INIT_CWND 10
/* Bit Flags for sysctl_tcp_fastopen */
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 41e0433..149bec8 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -222,7 +222,6 @@
#define BLKSECDISCARD _IO(0x12,125)
#define BLKROTATIONAL _IO(0x12,126)
#define BLKZEROOUT _IO(0x12,127)
-#define BLKDAXSET _IO(0x12,128)
#define BLKDAXGET _IO(0x12,129)
#define BMAP_IOCTL 1 /* obsolete - kept for compatibility */
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index b0799bc..89ebbc4 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -291,10 +291,13 @@
{
struct perf_event *event;
const struct perf_event_attr *attr;
+ struct file *file;
- event = perf_event_get(fd);
- if (IS_ERR(event))
- return event;
+ file = perf_event_get(fd);
+ if (IS_ERR(file))
+ return file;
+
+ event = file->private_data;
attr = perf_event_attrs(event);
if (IS_ERR(attr))
@@ -304,24 +307,22 @@
goto err;
if (attr->type == PERF_TYPE_RAW)
- return event;
+ return file;
if (attr->type == PERF_TYPE_HARDWARE)
- return event;
+ return file;
if (attr->type == PERF_TYPE_SOFTWARE &&
attr->config == PERF_COUNT_SW_BPF_OUTPUT)
- return event;
+ return file;
err:
- perf_event_release_kernel(event);
+ fput(file);
return ERR_PTR(-EINVAL);
}
static void perf_event_fd_array_put_ptr(void *ptr)
{
- struct perf_event *event = ptr;
-
- perf_event_release_kernel(event);
+ fput((struct file *)ptr);
}
static const struct bpf_map_ops perf_event_array_ops = {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 06ae52e..5946460 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -49,8 +49,6 @@
#include <asm/irq_regs.h>
-static struct workqueue_struct *perf_wq;
-
typedef int (*remote_function_f)(void *);
struct remote_function_call {
@@ -126,44 +124,181 @@
return data.ret;
}
-static void event_function_call(struct perf_event *event,
- int (*active)(void *),
- void (*inactive)(void *),
- void *data)
+static inline struct perf_cpu_context *
+__get_cpu_context(struct perf_event_context *ctx)
+{
+ return this_cpu_ptr(ctx->pmu->pmu_cpu_context);
+}
+
+static void perf_ctx_lock(struct perf_cpu_context *cpuctx,
+ struct perf_event_context *ctx)
+{
+ raw_spin_lock(&cpuctx->ctx.lock);
+ if (ctx)
+ raw_spin_lock(&ctx->lock);
+}
+
+static void perf_ctx_unlock(struct perf_cpu_context *cpuctx,
+ struct perf_event_context *ctx)
+{
+ if (ctx)
+ raw_spin_unlock(&ctx->lock);
+ raw_spin_unlock(&cpuctx->ctx.lock);
+}
+
+#define TASK_TOMBSTONE ((void *)-1L)
+
+static bool is_kernel_event(struct perf_event *event)
+{
+ return READ_ONCE(event->owner) == TASK_TOMBSTONE;
+}
+
+/*
+ * On task ctx scheduling...
+ *
+ * When !ctx->nr_events a task context will not be scheduled. This means
+ * we can disable the scheduler hooks (for performance) without leaving
+ * pending task ctx state.
+ *
+ * This however results in two special cases:
+ *
+ * - removing the last event from a task ctx; this is relatively straight
+ * forward and is done in __perf_remove_from_context.
+ *
+ * - adding the first event to a task ctx; this is tricky because we cannot
+ * rely on ctx->is_active and therefore cannot use event_function_call().
+ * See perf_install_in_context().
+ *
+ * This is because we need a ctx->lock serialized variable (ctx->is_active)
+ * to reliably determine if a particular task/context is scheduled in. The
+ * task_curr() use in task_function_call() is racy in that a remote context
+ * switch is not a single atomic operation.
+ *
+ * As is, the situation is 'safe' because we set rq->curr before we do the
+ * actual context switch. This means that task_curr() will fail early, but
+ * we'll continue spinning on ctx->is_active until we've passed
+ * perf_event_task_sched_out().
+ *
+ * Without this ctx->lock serialized variable we could have race where we find
+ * the task (and hence the context) would not be active while in fact they are.
+ *
+ * If ctx->nr_events, then ctx->is_active and cpuctx->task_ctx are set.
+ */
+
+typedef void (*event_f)(struct perf_event *, struct perf_cpu_context *,
+ struct perf_event_context *, void *);
+
+struct event_function_struct {
+ struct perf_event *event;
+ event_f func;
+ void *data;
+};
+
+static int event_function(void *info)
+{
+ struct event_function_struct *efs = info;
+ struct perf_event *event = efs->event;
+ struct perf_event_context *ctx = event->ctx;
+ struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+ struct perf_event_context *task_ctx = cpuctx->task_ctx;
+ int ret = 0;
+
+ WARN_ON_ONCE(!irqs_disabled());
+
+ perf_ctx_lock(cpuctx, task_ctx);
+ /*
+ * Since we do the IPI call without holding ctx->lock things can have
+ * changed, double check we hit the task we set out to hit.
+ */
+ if (ctx->task) {
+ if (ctx->task != current) {
+ ret = -EAGAIN;
+ goto unlock;
+ }
+
+ /*
+ * We only use event_function_call() on established contexts,
+ * and event_function() is only ever called when active (or
+ * rather, we'll have bailed in task_function_call() or the
+ * above ctx->task != current test), therefore we must have
+ * ctx->is_active here.
+ */
+ WARN_ON_ONCE(!ctx->is_active);
+ /*
+ * And since we have ctx->is_active, cpuctx->task_ctx must
+ * match.
+ */
+ WARN_ON_ONCE(task_ctx != ctx);
+ } else {
+ WARN_ON_ONCE(&cpuctx->ctx != ctx);
+ }
+
+ efs->func(event, cpuctx, ctx, efs->data);
+unlock:
+ perf_ctx_unlock(cpuctx, task_ctx);
+
+ return ret;
+}
+
+static void event_function_local(struct perf_event *event, event_f func, void *data)
+{
+ struct event_function_struct efs = {
+ .event = event,
+ .func = func,
+ .data = data,
+ };
+
+ int ret = event_function(&efs);
+ WARN_ON_ONCE(ret);
+}
+
+static void event_function_call(struct perf_event *event, event_f func, void *data)
{
struct perf_event_context *ctx = event->ctx;
- struct task_struct *task = ctx->task;
+ struct task_struct *task = READ_ONCE(ctx->task); /* verified in event_function */
+ struct event_function_struct efs = {
+ .event = event,
+ .func = func,
+ .data = data,
+ };
+
+ if (!event->parent) {
+ /*
+ * If this is a !child event, we must hold ctx::mutex to
+ * stabilize the the event->ctx relation. See
+ * perf_event_ctx_lock().
+ */
+ lockdep_assert_held(&ctx->mutex);
+ }
if (!task) {
- cpu_function_call(event->cpu, active, data);
+ cpu_function_call(event->cpu, event_function, &efs);
return;
}
again:
- if (!task_function_call(task, active, data))
+ if (task == TASK_TOMBSTONE)
+ return;
+
+ if (!task_function_call(task, event_function, &efs))
return;
raw_spin_lock_irq(&ctx->lock);
- if (ctx->is_active) {
- /*
- * Reload the task pointer, it might have been changed by
- * a concurrent perf_event_context_sched_out().
- */
- task = ctx->task;
- raw_spin_unlock_irq(&ctx->lock);
- goto again;
+ /*
+ * Reload the task pointer, it might have been changed by
+ * a concurrent perf_event_context_sched_out().
+ */
+ task = ctx->task;
+ if (task != TASK_TOMBSTONE) {
+ if (ctx->is_active) {
+ raw_spin_unlock_irq(&ctx->lock);
+ goto again;
+ }
+ func(event, NULL, ctx, data);
}
- inactive(data);
raw_spin_unlock_irq(&ctx->lock);
}
-#define EVENT_OWNER_KERNEL ((void *) -1)
-
-static bool is_kernel_event(struct perf_event *event)
-{
- return event->owner == EVENT_OWNER_KERNEL;
-}
-
#define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
PERF_FLAG_FD_OUTPUT |\
PERF_FLAG_PID_CGROUP |\
@@ -368,28 +503,6 @@
return event->clock();
}
-static inline struct perf_cpu_context *
-__get_cpu_context(struct perf_event_context *ctx)
-{
- return this_cpu_ptr(ctx->pmu->pmu_cpu_context);
-}
-
-static void perf_ctx_lock(struct perf_cpu_context *cpuctx,
- struct perf_event_context *ctx)
-{
- raw_spin_lock(&cpuctx->ctx.lock);
- if (ctx)
- raw_spin_lock(&ctx->lock);
-}
-
-static void perf_ctx_unlock(struct perf_cpu_context *cpuctx,
- struct perf_event_context *ctx)
-{
- if (ctx)
- raw_spin_unlock(&ctx->lock);
- raw_spin_unlock(&cpuctx->ctx.lock);
-}
-
#ifdef CONFIG_CGROUP_PERF
static inline bool
@@ -579,13 +692,7 @@
* we are holding the rcu lock
*/
cgrp1 = perf_cgroup_from_task(task, NULL);
-
- /*
- * next is NULL when called from perf_event_enable_on_exec()
- * that will systematically cause a cgroup_switch()
- */
- if (next)
- cgrp2 = perf_cgroup_from_task(next, NULL);
+ cgrp2 = perf_cgroup_from_task(next, NULL);
/*
* only schedule out current cgroup events if we know
@@ -611,8 +718,6 @@
* we are holding the rcu lock
*/
cgrp1 = perf_cgroup_from_task(task, NULL);
-
- /* prev can never be NULL */
cgrp2 = perf_cgroup_from_task(prev, NULL);
/*
@@ -917,7 +1022,7 @@
if (atomic_dec_and_test(&ctx->refcount)) {
if (ctx->parent_ctx)
put_ctx(ctx->parent_ctx);
- if (ctx->task)
+ if (ctx->task && ctx->task != TASK_TOMBSTONE)
put_task_struct(ctx->task);
call_rcu(&ctx->rcu_head, free_ctx);
}
@@ -934,9 +1039,8 @@
* perf_event_context::mutex nests and those are:
*
* - perf_event_exit_task_context() [ child , 0 ]
- * __perf_event_exit_task()
- * sync_child_event()
- * put_event() [ parent, 1 ]
+ * perf_event_exit_event()
+ * put_event() [ parent, 1 ]
*
* - perf_event_init_context() [ parent, 0 ]
* inherit_task_group()
@@ -979,8 +1083,8 @@
* Lock order:
* task_struct::perf_event_mutex
* perf_event_context::mutex
- * perf_event_context::lock
* perf_event::child_mutex;
+ * perf_event_context::lock
* perf_event::mmap_mutex
* mmap_sem
*/
@@ -1078,6 +1182,7 @@
/*
* Get the perf_event_context for a task and lock it.
+ *
* This has to cope with with the fact that until it is locked,
* the context could get moved to another task.
*/
@@ -1118,9 +1223,12 @@
goto retry;
}
- if (!atomic_inc_not_zero(&ctx->refcount)) {
+ if (ctx->task == TASK_TOMBSTONE ||
+ !atomic_inc_not_zero(&ctx->refcount)) {
raw_spin_unlock(&ctx->lock);
ctx = NULL;
+ } else {
+ WARN_ON_ONCE(ctx->task != task);
}
}
rcu_read_unlock();
@@ -1246,6 +1354,8 @@
static void
list_add_event(struct perf_event *event, struct perf_event_context *ctx)
{
+ lockdep_assert_held(&ctx->lock);
+
WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT);
event->attach_state |= PERF_ATTACH_CONTEXT;
@@ -1448,11 +1558,14 @@
if (is_cgroup_event(event)) {
ctx->nr_cgroups--;
+ /*
+ * Because cgroup events are always per-cpu events, this will
+ * always be called from the right CPU.
+ */
cpuctx = __get_cpu_context(ctx);
/*
- * if there are no more cgroup events
- * then cler cgrp to avoid stale pointer
- * in update_cgrp_time_from_cpuctx()
+ * If there are no more cgroup events then clear cgrp to avoid
+ * stale pointer in update_cgrp_time_from_cpuctx().
*/
if (!ctx->nr_cgroups)
cpuctx->cgrp = NULL;
@@ -1530,45 +1643,11 @@
perf_event__header_size(tmp);
}
-/*
- * User event without the task.
- */
static bool is_orphaned_event(struct perf_event *event)
{
- return event && !is_kernel_event(event) && !event->owner;
+ return event->state == PERF_EVENT_STATE_EXIT;
}
-/*
- * Event has a parent but parent's task finished and it's
- * alive only because of children holding refference.
- */
-static bool is_orphaned_child(struct perf_event *event)
-{
- return is_orphaned_event(event->parent);
-}
-
-static void orphans_remove_work(struct work_struct *work);
-
-static void schedule_orphans_remove(struct perf_event_context *ctx)
-{
- if (!ctx->task || ctx->orphans_remove_sched || !perf_wq)
- return;
-
- if (queue_delayed_work(perf_wq, &ctx->orphans_remove, 1)) {
- get_ctx(ctx);
- ctx->orphans_remove_sched = true;
- }
-}
-
-static int __init perf_workqueue_init(void)
-{
- perf_wq = create_singlethread_workqueue("perf");
- WARN(!perf_wq, "failed to create perf workqueue\n");
- return perf_wq ? 0 : -1;
-}
-
-core_initcall(perf_workqueue_init);
-
static inline int pmu_filter_match(struct perf_event *event)
{
struct pmu *pmu = event->pmu;
@@ -1629,9 +1708,6 @@
if (event->attr.exclusive || !cpuctx->active_oncpu)
cpuctx->exclusive = 0;
- if (is_orphaned_child(event))
- schedule_orphans_remove(ctx);
-
perf_pmu_enable(event->pmu);
}
@@ -1655,21 +1731,8 @@
cpuctx->exclusive = 0;
}
-struct remove_event {
- struct perf_event *event;
- bool detach_group;
-};
-
-static void ___perf_remove_from_context(void *info)
-{
- struct remove_event *re = info;
- struct perf_event *event = re->event;
- struct perf_event_context *ctx = event->ctx;
-
- if (re->detach_group)
- perf_group_detach(event);
- list_del_event(event, ctx);
-}
+#define DETACH_GROUP 0x01UL
+#define DETACH_STATE 0x02UL
/*
* Cross CPU call to remove a performance event
@@ -1677,33 +1740,33 @@
* We disable the event on the hardware level first. After that we
* remove it from the context list.
*/
-static int __perf_remove_from_context(void *info)
+static void
+__perf_remove_from_context(struct perf_event *event,
+ struct perf_cpu_context *cpuctx,
+ struct perf_event_context *ctx,
+ void *info)
{
- struct remove_event *re = info;
- struct perf_event *event = re->event;
- struct perf_event_context *ctx = event->ctx;
- struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+ unsigned long flags = (unsigned long)info;
- raw_spin_lock(&ctx->lock);
event_sched_out(event, cpuctx, ctx);
- if (re->detach_group)
+ if (flags & DETACH_GROUP)
perf_group_detach(event);
list_del_event(event, ctx);
- if (!ctx->nr_events && cpuctx->task_ctx == ctx) {
- ctx->is_active = 0;
- cpuctx->task_ctx = NULL;
- }
- raw_spin_unlock(&ctx->lock);
+ if (flags & DETACH_STATE)
+ event->state = PERF_EVENT_STATE_EXIT;
- return 0;
+ if (!ctx->nr_events && ctx->is_active) {
+ ctx->is_active = 0;
+ if (ctx->task) {
+ WARN_ON_ONCE(cpuctx->task_ctx != ctx);
+ cpuctx->task_ctx = NULL;
+ }
+ }
}
/*
* Remove the event from a task's (or a CPU's) list of events.
*
- * CPU events are removed with a smp call. For task events we only
- * call when the task is on a CPU.
- *
* If event->ctx is a cloned context, callers must make sure that
* every task struct that event->ctx->task could possibly point to
* remains valid. This is OK when called from perf_release since
@@ -1711,73 +1774,32 @@
* When called from perf_event_exit_task, it's OK because the
* context has been detached from its task.
*/
-static void perf_remove_from_context(struct perf_event *event, bool detach_group)
+static void perf_remove_from_context(struct perf_event *event, unsigned long flags)
{
- struct perf_event_context *ctx = event->ctx;
- struct remove_event re = {
- .event = event,
- .detach_group = detach_group,
- };
+ lockdep_assert_held(&event->ctx->mutex);
- lockdep_assert_held(&ctx->mutex);
-
- event_function_call(event, __perf_remove_from_context,
- ___perf_remove_from_context, &re);
+ event_function_call(event, __perf_remove_from_context, (void *)flags);
}
/*
* Cross CPU call to disable a performance event
*/
-int __perf_event_disable(void *info)
+static void __perf_event_disable(struct perf_event *event,
+ struct perf_cpu_context *cpuctx,
+ struct perf_event_context *ctx,
+ void *info)
{
- struct perf_event *event = info;
- struct perf_event_context *ctx = event->ctx;
- struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+ if (event->state < PERF_EVENT_STATE_INACTIVE)
+ return;
- /*
- * If this is a per-task event, need to check whether this
- * event's task is the current task on this cpu.
- *
- * Can trigger due to concurrent perf_event_context_sched_out()
- * flipping contexts around.
- */
- if (ctx->task && cpuctx->task_ctx != ctx)
- return -EINVAL;
-
- raw_spin_lock(&ctx->lock);
-
- /*
- * If the event is on, turn it off.
- * If it is in error state, leave it in error state.
- */
- if (event->state >= PERF_EVENT_STATE_INACTIVE) {
- update_context_time(ctx);
- update_cgrp_time_from_event(event);
- update_group_times(event);
- if (event == event->group_leader)
- group_sched_out(event, cpuctx, ctx);
- else
- event_sched_out(event, cpuctx, ctx);
- event->state = PERF_EVENT_STATE_OFF;
- }
-
- raw_spin_unlock(&ctx->lock);
-
- return 0;
-}
-
-void ___perf_event_disable(void *info)
-{
- struct perf_event *event = info;
-
- /*
- * Since we have the lock this context can't be scheduled
- * in, so we can change the state safely.
- */
- if (event->state == PERF_EVENT_STATE_INACTIVE) {
- update_group_times(event);
- event->state = PERF_EVENT_STATE_OFF;
- }
+ update_context_time(ctx);
+ update_cgrp_time_from_event(event);
+ update_group_times(event);
+ if (event == event->group_leader)
+ group_sched_out(event, cpuctx, ctx);
+ else
+ event_sched_out(event, cpuctx, ctx);
+ event->state = PERF_EVENT_STATE_OFF;
}
/*
@@ -1788,7 +1810,8 @@
* remains valid. This condition is satisifed when called through
* perf_event_for_each_child or perf_event_for_each because they
* hold the top-level event's child_mutex, so any descendant that
- * goes to exit will block in sync_child_event.
+ * goes to exit will block in perf_event_exit_event().
+ *
* When called from perf_pending_event it's OK because event->ctx
* is the current context on this CPU and preemption is disabled,
* hence we can't get into perf_event_task_sched_out for this context.
@@ -1804,8 +1827,12 @@
}
raw_spin_unlock_irq(&ctx->lock);
- event_function_call(event, __perf_event_disable,
- ___perf_event_disable, event);
+ event_function_call(event, __perf_event_disable, NULL);
+}
+
+void perf_event_disable_local(struct perf_event *event)
+{
+ event_function_local(event, __perf_event_disable, NULL);
}
/*
@@ -1918,9 +1945,6 @@
if (event->attr.exclusive)
cpuctx->exclusive = 1;
- if (is_orphaned_child(event))
- schedule_orphans_remove(ctx);
-
out:
perf_pmu_enable(event->pmu);
@@ -2039,7 +2063,8 @@
event->tstamp_stopped = tstamp;
}
-static void task_ctx_sched_out(struct perf_event_context *ctx);
+static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
+ struct perf_event_context *ctx);
static void
ctx_sched_in(struct perf_event_context *ctx,
struct perf_cpu_context *cpuctx,
@@ -2058,16 +2083,15 @@
ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task);
}
-static void ___perf_install_in_context(void *info)
+static void ctx_resched(struct perf_cpu_context *cpuctx,
+ struct perf_event_context *task_ctx)
{
- struct perf_event *event = info;
- struct perf_event_context *ctx = event->ctx;
-
- /*
- * Since the task isn't running, its safe to add the event, us holding
- * the ctx->lock ensures the task won't get scheduled in.
- */
- add_event_to_ctx(event, ctx);
+ perf_pmu_disable(cpuctx->ctx.pmu);
+ if (task_ctx)
+ task_ctx_sched_out(cpuctx, task_ctx);
+ cpu_ctx_sched_out(cpuctx, EVENT_ALL);
+ perf_event_sched_in(cpuctx, task_ctx, current);
+ perf_pmu_enable(cpuctx->ctx.pmu);
}
/*
@@ -2077,55 +2101,31 @@
*/
static int __perf_install_in_context(void *info)
{
- struct perf_event *event = info;
- struct perf_event_context *ctx = event->ctx;
+ struct perf_event_context *ctx = info;
struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
struct perf_event_context *task_ctx = cpuctx->task_ctx;
- struct task_struct *task = current;
- perf_ctx_lock(cpuctx, task_ctx);
- perf_pmu_disable(cpuctx->ctx.pmu);
-
- /*
- * If there was an active task_ctx schedule it out.
- */
- if (task_ctx)
- task_ctx_sched_out(task_ctx);
-
- /*
- * If the context we're installing events in is not the
- * active task_ctx, flip them.
- */
- if (ctx->task && task_ctx != ctx) {
- if (task_ctx)
- raw_spin_unlock(&task_ctx->lock);
+ raw_spin_lock(&cpuctx->ctx.lock);
+ if (ctx->task) {
raw_spin_lock(&ctx->lock);
+ /*
+ * If we hit the 'wrong' task, we've since scheduled and
+ * everything should be sorted, nothing to do!
+ */
task_ctx = ctx;
+ if (ctx->task != current)
+ goto unlock;
+
+ /*
+ * If task_ctx is set, it had better be to us.
+ */
+ WARN_ON_ONCE(cpuctx->task_ctx != ctx && cpuctx->task_ctx);
+ } else if (task_ctx) {
+ raw_spin_lock(&task_ctx->lock);
}
- if (task_ctx) {
- cpuctx->task_ctx = task_ctx;
- task = task_ctx->task;
- }
-
- cpu_ctx_sched_out(cpuctx, EVENT_ALL);
-
- update_context_time(ctx);
- /*
- * update cgrp time only if current cgrp
- * matches event->cgrp. Must be done before
- * calling add_event_to_ctx()
- */
- update_cgrp_time_from_event(event);
-
- add_event_to_ctx(event, ctx);
-
- /*
- * Schedule everything back in
- */
- perf_event_sched_in(cpuctx, task_ctx, task);
-
- perf_pmu_enable(cpuctx->ctx.pmu);
+ ctx_resched(cpuctx, task_ctx);
+unlock:
perf_ctx_unlock(cpuctx, task_ctx);
return 0;
@@ -2133,27 +2133,54 @@
/*
* Attach a performance event to a context
- *
- * First we add the event to the list with the hardware enable bit
- * in event->hw_config cleared.
- *
- * If the event is attached to a task which is on a CPU we use a smp
- * call to enable it in the task context. The task might have been
- * scheduled away, but we check this in the smp call again.
*/
static void
perf_install_in_context(struct perf_event_context *ctx,
struct perf_event *event,
int cpu)
{
+ struct task_struct *task = NULL;
+
lockdep_assert_held(&ctx->mutex);
event->ctx = ctx;
if (event->cpu != -1)
event->cpu = cpu;
- event_function_call(event, __perf_install_in_context,
- ___perf_install_in_context, event);
+ /*
+ * Installing events is tricky because we cannot rely on ctx->is_active
+ * to be set in case this is the nr_events 0 -> 1 transition.
+ *
+ * So what we do is we add the event to the list here, which will allow
+ * a future context switch to DTRT and then send a racy IPI. If the IPI
+ * fails to hit the right task, this means a context switch must have
+ * happened and that will have taken care of business.
+ */
+ raw_spin_lock_irq(&ctx->lock);
+ task = ctx->task;
+ /*
+ * Worse, we cannot even rely on the ctx actually existing anymore. If
+ * between find_get_context() and perf_install_in_context() the task
+ * went through perf_event_exit_task() its dead and we should not be
+ * adding new events.
+ */
+ if (task == TASK_TOMBSTONE) {
+ raw_spin_unlock_irq(&ctx->lock);
+ return;
+ }
+ update_context_time(ctx);
+ /*
+ * Update cgrp time only if current cgrp matches event->cgrp.
+ * Must be done before calling add_event_to_ctx().
+ */
+ update_cgrp_time_from_event(event);
+ add_event_to_ctx(event, ctx);
+ raw_spin_unlock_irq(&ctx->lock);
+
+ if (task)
+ task_function_call(task, __perf_install_in_context, ctx);
+ else
+ cpu_function_call(cpu, __perf_install_in_context, ctx);
}
/*
@@ -2180,43 +2207,30 @@
/*
* Cross CPU call to enable a performance event
*/
-static int __perf_event_enable(void *info)
+static void __perf_event_enable(struct perf_event *event,
+ struct perf_cpu_context *cpuctx,
+ struct perf_event_context *ctx,
+ void *info)
{
- struct perf_event *event = info;
- struct perf_event_context *ctx = event->ctx;
struct perf_event *leader = event->group_leader;
- struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
- int err;
+ struct perf_event_context *task_ctx;
- /*
- * There's a time window between 'ctx->is_active' check
- * in perf_event_enable function and this place having:
- * - IRQs on
- * - ctx->lock unlocked
- *
- * where the task could be killed and 'ctx' deactivated
- * by perf_event_exit_task.
- */
- if (!ctx->is_active)
- return -EINVAL;
+ if (event->state >= PERF_EVENT_STATE_INACTIVE ||
+ event->state <= PERF_EVENT_STATE_ERROR)
+ return;
- raw_spin_lock(&ctx->lock);
update_context_time(ctx);
-
- if (event->state >= PERF_EVENT_STATE_INACTIVE)
- goto unlock;
-
- /*
- * set current task's cgroup time reference point
- */
- perf_cgroup_set_timestamp(current, ctx);
-
__perf_event_mark_enabled(event);
+ if (!ctx->is_active)
+ return;
+
if (!event_filter_match(event)) {
- if (is_cgroup_event(event))
+ if (is_cgroup_event(event)) {
+ perf_cgroup_set_timestamp(current, ctx); // XXX ?
perf_cgroup_defer_enabled(event);
- goto unlock;
+ }
+ return;
}
/*
@@ -2224,41 +2238,13 @@
* then don't put it on unless the group is on.
*/
if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE)
- goto unlock;
+ return;
- if (!group_can_go_on(event, cpuctx, 1)) {
- err = -EEXIST;
- } else {
- if (event == leader)
- err = group_sched_in(event, cpuctx, ctx);
- else
- err = event_sched_in(event, cpuctx, ctx);
- }
+ task_ctx = cpuctx->task_ctx;
+ if (ctx->task)
+ WARN_ON_ONCE(task_ctx != ctx);
- if (err) {
- /*
- * If this event can't go on and it's part of a
- * group, then the whole group has to come off.
- */
- if (leader != event) {
- group_sched_out(leader, cpuctx, ctx);
- perf_mux_hrtimer_restart(cpuctx);
- }
- if (leader->attr.pinned) {
- update_group_times(leader);
- leader->state = PERF_EVENT_STATE_ERROR;
- }
- }
-
-unlock:
- raw_spin_unlock(&ctx->lock);
-
- return 0;
-}
-
-void ___perf_event_enable(void *info)
-{
- __perf_event_mark_enabled((struct perf_event *)info);
+ ctx_resched(cpuctx, task_ctx);
}
/*
@@ -2275,7 +2261,8 @@
struct perf_event_context *ctx = event->ctx;
raw_spin_lock_irq(&ctx->lock);
- if (event->state >= PERF_EVENT_STATE_INACTIVE) {
+ if (event->state >= PERF_EVENT_STATE_INACTIVE ||
+ event->state < PERF_EVENT_STATE_ERROR) {
raw_spin_unlock_irq(&ctx->lock);
return;
}
@@ -2291,8 +2278,7 @@
event->state = PERF_EVENT_STATE_OFF;
raw_spin_unlock_irq(&ctx->lock);
- event_function_call(event, __perf_event_enable,
- ___perf_event_enable, event);
+ event_function_call(event, __perf_event_enable, NULL);
}
/*
@@ -2342,12 +2328,27 @@
struct perf_cpu_context *cpuctx,
enum event_type_t event_type)
{
- struct perf_event *event;
int is_active = ctx->is_active;
+ struct perf_event *event;
+
+ lockdep_assert_held(&ctx->lock);
+
+ if (likely(!ctx->nr_events)) {
+ /*
+ * See __perf_remove_from_context().
+ */
+ WARN_ON_ONCE(ctx->is_active);
+ if (ctx->task)
+ WARN_ON_ONCE(cpuctx->task_ctx);
+ return;
+ }
ctx->is_active &= ~event_type;
- if (likely(!ctx->nr_events))
- return;
+ if (ctx->task) {
+ WARN_ON_ONCE(cpuctx->task_ctx != ctx);
+ if (!ctx->is_active)
+ cpuctx->task_ctx = NULL;
+ }
update_context_time(ctx);
update_cgrp_time_from_cpuctx(cpuctx);
@@ -2518,17 +2519,21 @@
raw_spin_lock(&ctx->lock);
raw_spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING);
if (context_equiv(ctx, next_ctx)) {
- /*
- * XXX do we need a memory barrier of sorts
- * wrt to rcu_dereference() of perf_event_ctxp
- */
- task->perf_event_ctxp[ctxn] = next_ctx;
- next->perf_event_ctxp[ctxn] = ctx;
- ctx->task = next;
- next_ctx->task = task;
+ WRITE_ONCE(ctx->task, next);
+ WRITE_ONCE(next_ctx->task, task);
swap(ctx->task_ctx_data, next_ctx->task_ctx_data);
+ /*
+ * RCU_INIT_POINTER here is safe because we've not
+ * modified the ctx and the above modification of
+ * ctx->task and ctx->task_ctx_data are immaterial
+ * since those values are always verified under
+ * ctx->lock which we're now holding.
+ */
+ RCU_INIT_POINTER(task->perf_event_ctxp[ctxn], next_ctx);
+ RCU_INIT_POINTER(next->perf_event_ctxp[ctxn], ctx);
+
do_switch = 0;
perf_event_sync_stat(ctx, next_ctx);
@@ -2541,8 +2546,7 @@
if (do_switch) {
raw_spin_lock(&ctx->lock);
- ctx_sched_out(ctx, cpuctx, EVENT_ALL);
- cpuctx->task_ctx = NULL;
+ task_ctx_sched_out(cpuctx, ctx);
raw_spin_unlock(&ctx->lock);
}
}
@@ -2637,10 +2641,9 @@
perf_cgroup_sched_out(task, next);
}
-static void task_ctx_sched_out(struct perf_event_context *ctx)
+static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
+ struct perf_event_context *ctx)
{
- struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
-
if (!cpuctx->task_ctx)
return;
@@ -2648,7 +2651,6 @@
return;
ctx_sched_out(ctx, cpuctx, EVENT_ALL);
- cpuctx->task_ctx = NULL;
}
/*
@@ -2725,13 +2727,22 @@
enum event_type_t event_type,
struct task_struct *task)
{
- u64 now;
int is_active = ctx->is_active;
+ u64 now;
- ctx->is_active |= event_type;
+ lockdep_assert_held(&ctx->lock);
+
if (likely(!ctx->nr_events))
return;
+ ctx->is_active |= event_type;
+ if (ctx->task) {
+ if (!is_active)
+ cpuctx->task_ctx = ctx;
+ else
+ WARN_ON_ONCE(cpuctx->task_ctx != ctx);
+ }
+
now = perf_clock();
ctx->timestamp = now;
perf_cgroup_set_timestamp(task, ctx);
@@ -2773,12 +2784,7 @@
* cpu flexible, task flexible.
*/
cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
-
- if (ctx->nr_events)
- cpuctx->task_ctx = ctx;
-
- perf_event_sched_in(cpuctx, cpuctx->task_ctx, task);
-
+ perf_event_sched_in(cpuctx, ctx, task);
perf_pmu_enable(ctx->pmu);
perf_ctx_unlock(cpuctx, ctx);
}
@@ -2800,6 +2806,16 @@
struct perf_event_context *ctx;
int ctxn;
+ /*
+ * If cgroup events exist on this CPU, then we need to check if we have
+ * to switch in PMU state; cgroup event are system-wide mode only.
+ *
+ * Since cgroup events are CPU events, we must schedule these in before
+ * we schedule in the task events.
+ */
+ if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
+ perf_cgroup_sched_in(prev, task);
+
for_each_task_context_nr(ctxn) {
ctx = task->perf_event_ctxp[ctxn];
if (likely(!ctx))
@@ -2807,13 +2823,6 @@
perf_event_context_sched_in(ctx, task);
}
- /*
- * if cgroup events exist on this CPU, then we need
- * to check if we have to switch in PMU state.
- * cgroup event are system-wide mode only
- */
- if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
- perf_cgroup_sched_in(prev, task);
if (atomic_read(&nr_switch_events))
perf_event_switch(task, prev, true);
@@ -3099,46 +3108,30 @@
static void perf_event_enable_on_exec(int ctxn)
{
struct perf_event_context *ctx, *clone_ctx = NULL;
+ struct perf_cpu_context *cpuctx;
struct perf_event *event;
unsigned long flags;
int enabled = 0;
- int ret;
local_irq_save(flags);
ctx = current->perf_event_ctxp[ctxn];
if (!ctx || !ctx->nr_events)
goto out;
- /*
- * We must ctxsw out cgroup events to avoid conflict
- * when invoking perf_task_event_sched_in() later on
- * in this function. Otherwise we end up trying to
- * ctxswin cgroup events which are already scheduled
- * in.
- */
- perf_cgroup_sched_out(current, NULL);
-
- raw_spin_lock(&ctx->lock);
- task_ctx_sched_out(ctx);
-
- list_for_each_entry(event, &ctx->event_list, event_entry) {
- ret = event_enable_on_exec(event, ctx);
- if (ret)
- enabled = 1;
- }
+ cpuctx = __get_cpu_context(ctx);
+ perf_ctx_lock(cpuctx, ctx);
+ list_for_each_entry(event, &ctx->event_list, event_entry)
+ enabled |= event_enable_on_exec(event, ctx);
/*
- * Unclone this context if we enabled any event.
+ * Unclone and reschedule this context if we enabled any event.
*/
- if (enabled)
+ if (enabled) {
clone_ctx = unclone_ctx(ctx);
+ ctx_resched(cpuctx, ctx);
+ }
+ perf_ctx_unlock(cpuctx, ctx);
- raw_spin_unlock(&ctx->lock);
-
- /*
- * Also calls ctxswin for cgroup events, if any:
- */
- perf_event_context_sched_in(ctx, ctx->task);
out:
local_irq_restore(flags);
@@ -3334,7 +3327,6 @@
INIT_LIST_HEAD(&ctx->flexible_groups);
INIT_LIST_HEAD(&ctx->event_list);
atomic_set(&ctx->refcount, 1);
- INIT_DELAYED_WORK(&ctx->orphans_remove, orphans_remove_work);
}
static struct perf_event_context *
@@ -3521,11 +3513,13 @@
static void unaccount_event(struct perf_event *event)
{
+ bool dec = false;
+
if (event->parent)
return;
if (event->attach_state & PERF_ATTACH_TASK)
- static_key_slow_dec_deferred(&perf_sched_events);
+ dec = true;
if (event->attr.mmap || event->attr.mmap_data)
atomic_dec(&nr_mmap_events);
if (event->attr.comm)
@@ -3535,12 +3529,15 @@
if (event->attr.freq)
atomic_dec(&nr_freq_events);
if (event->attr.context_switch) {
- static_key_slow_dec_deferred(&perf_sched_events);
+ dec = true;
atomic_dec(&nr_switch_events);
}
if (is_cgroup_event(event))
- static_key_slow_dec_deferred(&perf_sched_events);
+ dec = true;
if (has_branch_stack(event))
+ dec = true;
+
+ if (dec)
static_key_slow_dec_deferred(&perf_sched_events);
unaccount_event_cpu(event, event->cpu);
@@ -3556,7 +3553,7 @@
* 3) two matching events on the same context.
*
* The former two cases are handled in the allocation path (perf_event_alloc(),
- * __free_event()), the latter -- before the first perf_install_in_context().
+ * _free_event()), the latter -- before the first perf_install_in_context().
*/
static int exclusive_event_init(struct perf_event *event)
{
@@ -3631,29 +3628,6 @@
return true;
}
-static void __free_event(struct perf_event *event)
-{
- if (!event->parent) {
- if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
- put_callchain_buffers();
- }
-
- perf_event_free_bpf_prog(event);
-
- if (event->destroy)
- event->destroy(event);
-
- if (event->ctx)
- put_ctx(event->ctx);
-
- if (event->pmu) {
- exclusive_event_destroy(event);
- module_put(event->pmu->module);
- }
-
- call_rcu(&event->rcu_head, free_event_rcu);
-}
-
static void _free_event(struct perf_event *event)
{
irq_work_sync(&event->pending);
@@ -3675,7 +3649,25 @@
if (is_cgroup_event(event))
perf_detach_cgroup(event);
- __free_event(event);
+ if (!event->parent) {
+ if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
+ put_callchain_buffers();
+ }
+
+ perf_event_free_bpf_prog(event);
+
+ if (event->destroy)
+ event->destroy(event);
+
+ if (event->ctx)
+ put_ctx(event->ctx);
+
+ if (event->pmu) {
+ exclusive_event_destroy(event);
+ module_put(event->pmu->module);
+ }
+
+ call_rcu(&event->rcu_head, free_event_rcu);
}
/*
@@ -3702,14 +3694,13 @@
struct task_struct *owner;
rcu_read_lock();
- owner = ACCESS_ONCE(event->owner);
/*
- * Matches the smp_wmb() in perf_event_exit_task(). If we observe
- * !owner it means the list deletion is complete and we can indeed
- * free this event, otherwise we need to serialize on
+ * Matches the smp_store_release() in perf_event_exit_task(). If we
+ * observe !owner it means the list deletion is complete and we can
+ * indeed free this event, otherwise we need to serialize on
* owner->perf_event_mutex.
*/
- smp_read_barrier_depends();
+ owner = lockless_dereference(event->owner);
if (owner) {
/*
* Since delayed_put_task_struct() also drops the last
@@ -3737,8 +3728,10 @@
* ensured they're done, and we can proceed with freeing the
* event.
*/
- if (event->owner)
+ if (event->owner) {
list_del_init(&event->owner_entry);
+ smp_store_release(&event->owner, NULL);
+ }
mutex_unlock(&owner->perf_event_mutex);
put_task_struct(owner);
}
@@ -3746,36 +3739,98 @@
static void put_event(struct perf_event *event)
{
- struct perf_event_context *ctx;
-
if (!atomic_long_dec_and_test(&event->refcount))
return;
- if (!is_kernel_event(event))
- perf_remove_from_owner(event);
-
- /*
- * There are two ways this annotation is useful:
- *
- * 1) there is a lock recursion from perf_event_exit_task
- * see the comment there.
- *
- * 2) there is a lock-inversion with mmap_sem through
- * perf_read_group(), which takes faults while
- * holding ctx->mutex, however this is called after
- * the last filedesc died, so there is no possibility
- * to trigger the AB-BA case.
- */
- ctx = perf_event_ctx_lock_nested(event, SINGLE_DEPTH_NESTING);
- WARN_ON_ONCE(ctx->parent_ctx);
- perf_remove_from_context(event, true);
- perf_event_ctx_unlock(event, ctx);
-
_free_event(event);
}
+/*
+ * Kill an event dead; while event:refcount will preserve the event
+ * object, it will not preserve its functionality. Once the last 'user'
+ * gives up the object, we'll destroy the thing.
+ */
int perf_event_release_kernel(struct perf_event *event)
{
+ struct perf_event_context *ctx;
+ struct perf_event *child, *tmp;
+
+ if (!is_kernel_event(event))
+ perf_remove_from_owner(event);
+
+ ctx = perf_event_ctx_lock(event);
+ WARN_ON_ONCE(ctx->parent_ctx);
+ perf_remove_from_context(event, DETACH_GROUP | DETACH_STATE);
+ perf_event_ctx_unlock(event, ctx);
+
+ /*
+ * At this point we must have event->state == PERF_EVENT_STATE_EXIT,
+ * either from the above perf_remove_from_context() or through
+ * perf_event_exit_event().
+ *
+ * Therefore, anybody acquiring event->child_mutex after the below
+ * loop _must_ also see this, most importantly inherit_event() which
+ * will avoid placing more children on the list.
+ *
+ * Thus this guarantees that we will in fact observe and kill _ALL_
+ * child events.
+ */
+ WARN_ON_ONCE(event->state != PERF_EVENT_STATE_EXIT);
+
+again:
+ mutex_lock(&event->child_mutex);
+ list_for_each_entry(child, &event->child_list, child_list) {
+
+ /*
+ * Cannot change, child events are not migrated, see the
+ * comment with perf_event_ctx_lock_nested().
+ */
+ ctx = lockless_dereference(child->ctx);
+ /*
+ * Since child_mutex nests inside ctx::mutex, we must jump
+ * through hoops. We start by grabbing a reference on the ctx.
+ *
+ * Since the event cannot get freed while we hold the
+ * child_mutex, the context must also exist and have a !0
+ * reference count.
+ */
+ get_ctx(ctx);
+
+ /*
+ * Now that we have a ctx ref, we can drop child_mutex, and
+ * acquire ctx::mutex without fear of it going away. Then we
+ * can re-acquire child_mutex.
+ */
+ mutex_unlock(&event->child_mutex);
+ mutex_lock(&ctx->mutex);
+ mutex_lock(&event->child_mutex);
+
+ /*
+ * Now that we hold ctx::mutex and child_mutex, revalidate our
+ * state, if child is still the first entry, it didn't get freed
+ * and we can continue doing so.
+ */
+ tmp = list_first_entry_or_null(&event->child_list,
+ struct perf_event, child_list);
+ if (tmp == child) {
+ perf_remove_from_context(child, DETACH_GROUP);
+ list_del(&child->child_list);
+ free_event(child);
+ /*
+ * This matches the refcount bump in inherit_event();
+ * this can't be the last reference.
+ */
+ put_event(event);
+ }
+
+ mutex_unlock(&event->child_mutex);
+ mutex_unlock(&ctx->mutex);
+ put_ctx(ctx);
+ goto again;
+ }
+ mutex_unlock(&event->child_mutex);
+
+ /* Must be the last reference */
put_event(event);
return 0;
}
@@ -3786,46 +3841,10 @@
*/
static int perf_release(struct inode *inode, struct file *file)
{
- put_event(file->private_data);
+ perf_event_release_kernel(file->private_data);
return 0;
}
-/*
- * Remove all orphanes events from the context.
- */
-static void orphans_remove_work(struct work_struct *work)
-{
- struct perf_event_context *ctx;
- struct perf_event *event, *tmp;
-
- ctx = container_of(work, struct perf_event_context,
- orphans_remove.work);
-
- mutex_lock(&ctx->mutex);
- list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry) {
- struct perf_event *parent_event = event->parent;
-
- if (!is_orphaned_child(event))
- continue;
-
- perf_remove_from_context(event, true);
-
- mutex_lock(&parent_event->child_mutex);
- list_del_init(&event->child_list);
- mutex_unlock(&parent_event->child_mutex);
-
- free_event(event);
- put_event(parent_event);
- }
-
- raw_spin_lock_irq(&ctx->lock);
- ctx->orphans_remove_sched = false;
- raw_spin_unlock_irq(&ctx->lock);
- mutex_unlock(&ctx->mutex);
-
- put_ctx(ctx);
-}
-
u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running)
{
struct perf_event *child;
@@ -4054,7 +4073,7 @@
/*
* Holding the top-level event's child_mutex means that any
* descendant process that has inherited this event will block
- * in sync_child_event if it goes to exit, thus satisfying the
+ * in perf_event_exit_event() if it goes to exit, thus satisfying the
* task existence requirements of perf_event_enable/disable.
*/
static void perf_event_for_each_child(struct perf_event *event,
@@ -4086,36 +4105,14 @@
perf_event_for_each_child(sibling, func);
}
-struct period_event {
- struct perf_event *event;
- u64 value;
-};
-
-static void ___perf_event_period(void *info)
+static void __perf_event_period(struct perf_event *event,
+ struct perf_cpu_context *cpuctx,
+ struct perf_event_context *ctx,
+ void *info)
{
- struct period_event *pe = info;
- struct perf_event *event = pe->event;
- u64 value = pe->value;
-
- if (event->attr.freq) {
- event->attr.sample_freq = value;
- } else {
- event->attr.sample_period = value;
- event->hw.sample_period = value;
- }
-
- local64_set(&event->hw.period_left, 0);
-}
-
-static int __perf_event_period(void *info)
-{
- struct period_event *pe = info;
- struct perf_event *event = pe->event;
- struct perf_event_context *ctx = event->ctx;
- u64 value = pe->value;
+ u64 value = *((u64 *)info);
bool active;
- raw_spin_lock(&ctx->lock);
if (event->attr.freq) {
event->attr.sample_freq = value;
} else {
@@ -4135,14 +4132,10 @@
event->pmu->start(event, PERF_EF_RELOAD);
perf_pmu_enable(ctx->pmu);
}
- raw_spin_unlock(&ctx->lock);
-
- return 0;
}
static int perf_event_period(struct perf_event *event, u64 __user *arg)
{
- struct period_event pe = { .event = event, };
u64 value;
if (!is_sampling_event(event))
@@ -4157,10 +4150,7 @@
if (event->attr.freq && value > sysctl_perf_event_sample_rate)
return -EINVAL;
- pe.value = value;
-
- event_function_call(event, __perf_event_period,
- ___perf_event_period, &pe);
+ event_function_call(event, __perf_event_period, &value);
return 0;
}
@@ -4932,7 +4922,7 @@
if (event->pending_disable) {
event->pending_disable = 0;
- __perf_event_disable(event);
+ perf_event_disable_local(event);
}
if (event->pending_wakeup) {
@@ -7753,11 +7743,13 @@
static void account_event(struct perf_event *event)
{
+ bool inc = false;
+
if (event->parent)
return;
if (event->attach_state & PERF_ATTACH_TASK)
- static_key_slow_inc(&perf_sched_events.key);
+ inc = true;
if (event->attr.mmap || event->attr.mmap_data)
atomic_inc(&nr_mmap_events);
if (event->attr.comm)
@@ -7770,11 +7762,14 @@
}
if (event->attr.context_switch) {
atomic_inc(&nr_switch_events);
- static_key_slow_inc(&perf_sched_events.key);
+ inc = true;
}
if (has_branch_stack(event))
- static_key_slow_inc(&perf_sched_events.key);
+ inc = true;
if (is_cgroup_event(event))
+ inc = true;
+
+ if (inc)
static_key_slow_inc(&perf_sched_events.key);
account_event_cpu(event, event->cpu);
@@ -8422,11 +8417,11 @@
* See perf_event_ctx_lock() for comments on the details
* of swizzling perf_event::ctx.
*/
- perf_remove_from_context(group_leader, false);
+ perf_remove_from_context(group_leader, 0);
list_for_each_entry(sibling, &group_leader->sibling_list,
group_entry) {
- perf_remove_from_context(sibling, false);
+ perf_remove_from_context(sibling, 0);
put_ctx(gctx);
}
@@ -8479,6 +8474,8 @@
perf_event__header_size(event);
perf_event__id_header_size(event);
+ event->owner = current;
+
perf_install_in_context(ctx, event, event->cpu);
perf_unpin_context(ctx);
@@ -8488,8 +8485,6 @@
put_online_cpus();
- event->owner = current;
-
mutex_lock(¤t->perf_event_mutex);
list_add_tail(&event->owner_entry, ¤t->perf_event_list);
mutex_unlock(¤t->perf_event_mutex);
@@ -8556,7 +8551,7 @@
}
/* Mark owner so we could distinguish it from user events. */
- event->owner = EVENT_OWNER_KERNEL;
+ event->owner = TASK_TOMBSTONE;
account_event(event);
@@ -8606,7 +8601,7 @@
mutex_lock_double(&src_ctx->mutex, &dst_ctx->mutex);
list_for_each_entry_safe(event, tmp, &src_ctx->event_list,
event_entry) {
- perf_remove_from_context(event, false);
+ perf_remove_from_context(event, 0);
unaccount_event_cpu(event, src_cpu);
put_ctx(src_ctx);
list_add(&event->migrate_entry, &events);
@@ -8673,33 +8668,15 @@
&parent_event->child_total_time_enabled);
atomic64_add(child_event->total_time_running,
&parent_event->child_total_time_running);
-
- /*
- * Remove this event from the parent's list
- */
- WARN_ON_ONCE(parent_event->ctx->parent_ctx);
- mutex_lock(&parent_event->child_mutex);
- list_del_init(&child_event->child_list);
- mutex_unlock(&parent_event->child_mutex);
-
- /*
- * Make sure user/parent get notified, that we just
- * lost one event.
- */
- perf_event_wakeup(parent_event);
-
- /*
- * Release the parent event, if this was the last
- * reference to it.
- */
- put_event(parent_event);
}
static void
-__perf_event_exit_task(struct perf_event *child_event,
- struct perf_event_context *child_ctx,
- struct task_struct *child)
+perf_event_exit_event(struct perf_event *child_event,
+ struct perf_event_context *child_ctx,
+ struct task_struct *child)
{
+ struct perf_event *parent_event = child_event->parent;
+
/*
* Do not destroy the 'original' grouping; because of the context
* switch optimization the original events could've ended up in a
@@ -8712,57 +8689,86 @@
* Do destroy all inherited groups, we don't care about those
* and being thorough is better.
*/
- perf_remove_from_context(child_event, !!child_event->parent);
+ raw_spin_lock_irq(&child_ctx->lock);
+ WARN_ON_ONCE(child_ctx->is_active);
+
+ if (parent_event)
+ perf_group_detach(child_event);
+ list_del_event(child_event, child_ctx);
+ child_event->state = PERF_EVENT_STATE_EXIT; /* see perf_event_release_kernel() */
+ raw_spin_unlock_irq(&child_ctx->lock);
/*
- * It can happen that the parent exits first, and has events
- * that are still around due to the child reference. These
- * events need to be zapped.
+ * Parent events are governed by their filedesc, retain them.
*/
- if (child_event->parent) {
- sync_child_event(child_event, child);
- free_event(child_event);
- } else {
- child_event->state = PERF_EVENT_STATE_EXIT;
+ if (!parent_event) {
perf_event_wakeup(child_event);
+ return;
}
+ /*
+ * Child events can be cleaned up.
+ */
+
+ sync_child_event(child_event, child);
+
+ /*
+ * Remove this event from the parent's list
+ */
+ WARN_ON_ONCE(parent_event->ctx->parent_ctx);
+ mutex_lock(&parent_event->child_mutex);
+ list_del_init(&child_event->child_list);
+ mutex_unlock(&parent_event->child_mutex);
+
+ /*
+ * Kick perf_poll() for is_event_hup().
+ */
+ perf_event_wakeup(parent_event);
+ free_event(child_event);
+ put_event(parent_event);
}
static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
{
- struct perf_event *child_event, *next;
struct perf_event_context *child_ctx, *clone_ctx = NULL;
- unsigned long flags;
+ struct perf_event *child_event, *next;
- if (likely(!child->perf_event_ctxp[ctxn]))
+ WARN_ON_ONCE(child != current);
+
+ child_ctx = perf_pin_task_context(child, ctxn);
+ if (!child_ctx)
return;
- local_irq_save(flags);
/*
- * We can't reschedule here because interrupts are disabled,
- * and either child is current or it is a task that can't be
- * scheduled, so we are now safe from rescheduling changing
- * our context.
+ * In order to reduce the amount of tricky in ctx tear-down, we hold
+ * ctx::mutex over the entire thing. This serializes against almost
+ * everything that wants to access the ctx.
+ *
+ * The exception is sys_perf_event_open() /
+ * perf_event_create_kernel_count() which does find_get_context()
+ * without ctx::mutex (it cannot because of the move_group double mutex
+ * lock thing). See the comments in perf_install_in_context().
*/
- child_ctx = rcu_dereference_raw(child->perf_event_ctxp[ctxn]);
+ mutex_lock(&child_ctx->mutex);
/*
- * Take the context lock here so that if find_get_context is
- * reading child->perf_event_ctxp, we wait until it has
- * incremented the context's refcount before we do put_ctx below.
+ * In a single ctx::lock section, de-schedule the events and detach the
+ * context from the task such that we cannot ever get it scheduled back
+ * in.
*/
- raw_spin_lock(&child_ctx->lock);
- task_ctx_sched_out(child_ctx);
- child->perf_event_ctxp[ctxn] = NULL;
+ raw_spin_lock_irq(&child_ctx->lock);
+ task_ctx_sched_out(__get_cpu_context(child_ctx), child_ctx);
/*
- * If this context is a clone; unclone it so it can't get
- * swapped to another process while we're removing all
- * the events from it.
+ * Now that the context is inactive, destroy the task <-> ctx relation
+ * and mark the context dead.
*/
+ RCU_INIT_POINTER(child->perf_event_ctxp[ctxn], NULL);
+ put_ctx(child_ctx); /* cannot be last */
+ WRITE_ONCE(child_ctx->task, TASK_TOMBSTONE);
+ put_task_struct(current); /* cannot be last */
+
clone_ctx = unclone_ctx(child_ctx);
- update_context_time(child_ctx);
- raw_spin_unlock_irqrestore(&child_ctx->lock, flags);
+ raw_spin_unlock_irq(&child_ctx->lock);
if (clone_ctx)
put_ctx(clone_ctx);
@@ -8774,20 +8780,8 @@
*/
perf_event_task(child, child_ctx, 0);
- /*
- * We can recurse on the same lock type through:
- *
- * __perf_event_exit_task()
- * sync_child_event()
- * put_event()
- * mutex_lock(&ctx->mutex)
- *
- * But since its the parent context it won't be the same instance.
- */
- mutex_lock(&child_ctx->mutex);
-
list_for_each_entry_safe(child_event, next, &child_ctx->event_list, event_entry)
- __perf_event_exit_task(child_event, child_ctx, child);
+ perf_event_exit_event(child_event, child_ctx, child);
mutex_unlock(&child_ctx->mutex);
@@ -8812,8 +8806,7 @@
* the owner, closes a race against perf_release() where
* we need to serialize on the owner->perf_event_mutex.
*/
- smp_wmb();
- event->owner = NULL;
+ smp_store_release(&event->owner, NULL);
}
mutex_unlock(&child->perf_event_mutex);
@@ -8896,21 +8889,20 @@
WARN_ON_ONCE(task->perf_event_ctxp[ctxn]);
}
-struct perf_event *perf_event_get(unsigned int fd)
+struct file *perf_event_get(unsigned int fd)
{
- int err;
- struct fd f;
- struct perf_event *event;
+ struct file *file;
- err = perf_fget_light(fd, &f);
- if (err)
- return ERR_PTR(err);
+ file = fget_raw(fd);
+ if (!file)
+ return ERR_PTR(-EBADF);
- event = f.file->private_data;
- atomic_long_inc(&event->refcount);
- fdput(f);
+ if (file->f_op != &perf_fops) {
+ fput(file);
+ return ERR_PTR(-EBADF);
+ }
- return event;
+ return file;
}
const struct perf_event_attr *perf_event_attrs(struct perf_event *event)
@@ -8953,8 +8945,16 @@
if (IS_ERR(child_event))
return child_event;
+ /*
+ * is_orphaned_event() and list_add_tail(&parent_event->child_list)
+ * must be under the same lock in order to serialize against
+ * perf_event_release_kernel(), such that either we must observe
+ * is_orphaned_event() or they will observe us on the child_list.
+ */
+ mutex_lock(&parent_event->child_mutex);
if (is_orphaned_event(parent_event) ||
!atomic_long_inc_not_zero(&parent_event->refcount)) {
+ mutex_unlock(&parent_event->child_mutex);
free_event(child_event);
return NULL;
}
@@ -9002,8 +9002,6 @@
/*
* Link this into the parent event's child list
*/
- WARN_ON_ONCE(parent_event->ctx->parent_ctx);
- mutex_lock(&parent_event->child_mutex);
list_add_tail(&child_event->child_list, &parent_event->child_list);
mutex_unlock(&parent_event->child_mutex);
@@ -9221,13 +9219,14 @@
#if defined CONFIG_HOTPLUG_CPU || defined CONFIG_KEXEC_CORE
static void __perf_event_exit_context(void *__info)
{
- struct remove_event re = { .detach_group = true };
struct perf_event_context *ctx = __info;
+ struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+ struct perf_event *event;
- rcu_read_lock();
- list_for_each_entry_rcu(re.event, &ctx->event_list, event_entry)
- __perf_remove_from_context(&re);
- rcu_read_unlock();
+ raw_spin_lock(&ctx->lock);
+ list_for_each_entry(event, &ctx->event_list, event_entry)
+ __perf_remove_from_context(event, cpuctx, ctx, (void *)DETACH_GROUP);
+ raw_spin_unlock(&ctx->lock);
}
static void perf_event_exit_cpu_context(int cpu)
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 92ce5f4..3f8cb1e 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -444,7 +444,7 @@
* current task.
*/
if (irqs_disabled() && bp->ctx && bp->ctx->task == current)
- __perf_event_disable(bp);
+ perf_event_disable_local(bp);
else
perf_event_disable(bp);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index adfdc05..1faad2cf 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -459,6 +459,25 @@
__free_page(page);
}
+static void __rb_free_aux(struct ring_buffer *rb)
+{
+ int pg;
+
+ if (rb->aux_priv) {
+ rb->free_aux(rb->aux_priv);
+ rb->free_aux = NULL;
+ rb->aux_priv = NULL;
+ }
+
+ if (rb->aux_nr_pages) {
+ for (pg = 0; pg < rb->aux_nr_pages; pg++)
+ rb_free_aux_page(rb, pg);
+
+ kfree(rb->aux_pages);
+ rb->aux_nr_pages = 0;
+ }
+}
+
int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
pgoff_t pgoff, int nr_pages, long watermark, int flags)
{
@@ -547,30 +566,11 @@
if (!ret)
rb->aux_pgoff = pgoff;
else
- rb_free_aux(rb);
+ __rb_free_aux(rb);
return ret;
}
-static void __rb_free_aux(struct ring_buffer *rb)
-{
- int pg;
-
- if (rb->aux_priv) {
- rb->free_aux(rb->aux_priv);
- rb->free_aux = NULL;
- rb->aux_priv = NULL;
- }
-
- if (rb->aux_nr_pages) {
- for (pg = 0; pg < rb->aux_nr_pages; pg++)
- rb_free_aux_page(rb, pg);
-
- kfree(rb->aux_pages);
- rb->aux_nr_pages = 0;
- }
-}
-
void rb_free_aux(struct ring_buffer *rb)
{
if (atomic_dec_and_test(&rb->aux_refcount))
diff --git a/kernel/futex.c b/kernel/futex.c
index 0773f2b..5d6ce64 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1191,7 +1191,7 @@
if (pi_state->owner != current)
return -EINVAL;
- raw_spin_lock(&pi_state->pi_mutex.wait_lock);
+ raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
/*
@@ -1217,22 +1217,22 @@
else if (curval != uval)
ret = -EINVAL;
if (ret) {
- raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
+ raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
return ret;
}
- raw_spin_lock_irq(&pi_state->owner->pi_lock);
+ raw_spin_lock(&pi_state->owner->pi_lock);
WARN_ON(list_empty(&pi_state->list));
list_del_init(&pi_state->list);
- raw_spin_unlock_irq(&pi_state->owner->pi_lock);
+ raw_spin_unlock(&pi_state->owner->pi_lock);
- raw_spin_lock_irq(&new_owner->pi_lock);
+ raw_spin_lock(&new_owner->pi_lock);
WARN_ON(!list_empty(&pi_state->list));
list_add(&pi_state->list, &new_owner->pi_state_list);
pi_state->owner = new_owner;
- raw_spin_unlock_irq(&new_owner->pi_lock);
+ raw_spin_unlock(&new_owner->pi_lock);
- raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
+ raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
@@ -2127,11 +2127,11 @@
* we returned due to timeout or signal without taking the
* rt_mutex. Too late.
*/
- raw_spin_lock(&q->pi_state->pi_mutex.wait_lock);
+ raw_spin_lock_irq(&q->pi_state->pi_mutex.wait_lock);
owner = rt_mutex_owner(&q->pi_state->pi_mutex);
if (!owner)
owner = rt_mutex_next_owner(&q->pi_state->pi_mutex);
- raw_spin_unlock(&q->pi_state->pi_mutex.wait_lock);
+ raw_spin_unlock_irq(&q->pi_state->pi_mutex.wait_lock);
ret = fixup_pi_state_owner(uaddr, q, owner);
goto out;
}
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 8251e75..3e74660 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -99,13 +99,14 @@
* 2) Drop lock->wait_lock
* 3) Try to unlock the lock with cmpxchg
*/
-static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock,
+ unsigned long flags)
__releases(lock->wait_lock)
{
struct task_struct *owner = rt_mutex_owner(lock);
clear_rt_mutex_waiters(lock);
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
/*
* If a new waiter comes in between the unlock and the cmpxchg
* we have two situations:
@@ -147,11 +148,12 @@
/*
* Simple slow path only version: lock->owner is protected by lock->wait_lock.
*/
-static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock,
+ unsigned long flags)
__releases(lock->wait_lock)
{
lock->owner = NULL;
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
return true;
}
#endif
@@ -433,7 +435,6 @@
int ret = 0, depth = 0;
struct rt_mutex *lock;
bool detect_deadlock;
- unsigned long flags;
bool requeue = true;
detect_deadlock = rt_mutex_cond_detect_deadlock(orig_waiter, chwalk);
@@ -476,7 +477,7 @@
/*
* [1] Task cannot go away as we did a get_task() before !
*/
- raw_spin_lock_irqsave(&task->pi_lock, flags);
+ raw_spin_lock_irq(&task->pi_lock);
/*
* [2] Get the waiter on which @task is blocked on.
@@ -560,7 +561,7 @@
* operations.
*/
if (!raw_spin_trylock(&lock->wait_lock)) {
- raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ raw_spin_unlock_irq(&task->pi_lock);
cpu_relax();
goto retry;
}
@@ -591,7 +592,7 @@
/*
* No requeue[7] here. Just release @task [8]
*/
- raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ raw_spin_unlock(&task->pi_lock);
put_task_struct(task);
/*
@@ -599,14 +600,14 @@
* If there is no owner of the lock, end of chain.
*/
if (!rt_mutex_owner(lock)) {
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irq(&lock->wait_lock);
return 0;
}
/* [10] Grab the next task, i.e. owner of @lock */
task = rt_mutex_owner(lock);
get_task_struct(task);
- raw_spin_lock_irqsave(&task->pi_lock, flags);
+ raw_spin_lock(&task->pi_lock);
/*
* No requeue [11] here. We just do deadlock detection.
@@ -621,8 +622,8 @@
top_waiter = rt_mutex_top_waiter(lock);
/* [13] Drop locks */
- raw_spin_unlock_irqrestore(&task->pi_lock, flags);
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock(&task->pi_lock);
+ raw_spin_unlock_irq(&lock->wait_lock);
/* If owner is not blocked, end of chain. */
if (!next_lock)
@@ -643,7 +644,7 @@
rt_mutex_enqueue(lock, waiter);
/* [8] Release the task */
- raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ raw_spin_unlock(&task->pi_lock);
put_task_struct(task);
/*
@@ -661,14 +662,14 @@
*/
if (prerequeue_top_waiter != rt_mutex_top_waiter(lock))
wake_up_process(rt_mutex_top_waiter(lock)->task);
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irq(&lock->wait_lock);
return 0;
}
/* [10] Grab the next task, i.e. the owner of @lock */
task = rt_mutex_owner(lock);
get_task_struct(task);
- raw_spin_lock_irqsave(&task->pi_lock, flags);
+ raw_spin_lock(&task->pi_lock);
/* [11] requeue the pi waiters if necessary */
if (waiter == rt_mutex_top_waiter(lock)) {
@@ -722,8 +723,8 @@
top_waiter = rt_mutex_top_waiter(lock);
/* [13] Drop the locks */
- raw_spin_unlock_irqrestore(&task->pi_lock, flags);
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock(&task->pi_lock);
+ raw_spin_unlock_irq(&lock->wait_lock);
/*
* Make the actual exit decisions [12], based on the stored
@@ -746,7 +747,7 @@
goto again;
out_unlock_pi:
- raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ raw_spin_unlock_irq(&task->pi_lock);
out_put_task:
put_task_struct(task);
@@ -756,7 +757,7 @@
/*
* Try to take an rt-mutex
*
- * Must be called with lock->wait_lock held.
+ * Must be called with lock->wait_lock held and interrupts disabled
*
* @lock: The lock to be acquired.
* @task: The task which wants to acquire the lock
@@ -766,8 +767,6 @@
static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
struct rt_mutex_waiter *waiter)
{
- unsigned long flags;
-
/*
* Before testing whether we can acquire @lock, we set the
* RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all
@@ -852,7 +851,7 @@
* case, but conditionals are more expensive than a redundant
* store.
*/
- raw_spin_lock_irqsave(&task->pi_lock, flags);
+ raw_spin_lock(&task->pi_lock);
task->pi_blocked_on = NULL;
/*
* Finish the lock acquisition. @task is the new owner. If
@@ -861,7 +860,7 @@
*/
if (rt_mutex_has_waiters(lock))
rt_mutex_enqueue_pi(task, rt_mutex_top_waiter(lock));
- raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ raw_spin_unlock(&task->pi_lock);
takeit:
/* We got the lock. */
@@ -883,7 +882,7 @@
*
* Prepare waiter and propagate pi chain
*
- * This must be called with lock->wait_lock held.
+ * This must be called with lock->wait_lock held and interrupts disabled
*/
static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
struct rt_mutex_waiter *waiter,
@@ -894,7 +893,6 @@
struct rt_mutex_waiter *top_waiter = waiter;
struct rt_mutex *next_lock;
int chain_walk = 0, res;
- unsigned long flags;
/*
* Early deadlock detection. We really don't want the task to
@@ -908,7 +906,7 @@
if (owner == task)
return -EDEADLK;
- raw_spin_lock_irqsave(&task->pi_lock, flags);
+ raw_spin_lock(&task->pi_lock);
__rt_mutex_adjust_prio(task);
waiter->task = task;
waiter->lock = lock;
@@ -921,12 +919,12 @@
task->pi_blocked_on = waiter;
- raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ raw_spin_unlock(&task->pi_lock);
if (!owner)
return 0;
- raw_spin_lock_irqsave(&owner->pi_lock, flags);
+ raw_spin_lock(&owner->pi_lock);
if (waiter == rt_mutex_top_waiter(lock)) {
rt_mutex_dequeue_pi(owner, top_waiter);
rt_mutex_enqueue_pi(owner, waiter);
@@ -941,7 +939,7 @@
/* Store the lock on which owner is blocked or NULL */
next_lock = task_blocked_on_lock(owner);
- raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
+ raw_spin_unlock(&owner->pi_lock);
/*
* Even if full deadlock detection is on, if the owner is not
* blocked itself, we can avoid finding this out in the chain
@@ -957,12 +955,12 @@
*/
get_task_struct(owner);
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irq(&lock->wait_lock);
res = rt_mutex_adjust_prio_chain(owner, chwalk, lock,
next_lock, waiter, task);
- raw_spin_lock(&lock->wait_lock);
+ raw_spin_lock_irq(&lock->wait_lock);
return res;
}
@@ -971,15 +969,14 @@
* Remove the top waiter from the current tasks pi waiter tree and
* queue it up.
*
- * Called with lock->wait_lock held.
+ * Called with lock->wait_lock held and interrupts disabled.
*/
static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
struct rt_mutex *lock)
{
struct rt_mutex_waiter *waiter;
- unsigned long flags;
- raw_spin_lock_irqsave(¤t->pi_lock, flags);
+ raw_spin_lock(¤t->pi_lock);
waiter = rt_mutex_top_waiter(lock);
@@ -1001,7 +998,7 @@
*/
lock->owner = (void *) RT_MUTEX_HAS_WAITERS;
- raw_spin_unlock_irqrestore(¤t->pi_lock, flags);
+ raw_spin_unlock(¤t->pi_lock);
wake_q_add(wake_q, waiter->task);
}
@@ -1009,7 +1006,7 @@
/*
* Remove a waiter from a lock and give up
*
- * Must be called with lock->wait_lock held and
+ * Must be called with lock->wait_lock held and interrupts disabled. I must
* have just failed to try_to_take_rt_mutex().
*/
static void remove_waiter(struct rt_mutex *lock,
@@ -1018,12 +1015,11 @@
bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock));
struct task_struct *owner = rt_mutex_owner(lock);
struct rt_mutex *next_lock;
- unsigned long flags;
- raw_spin_lock_irqsave(¤t->pi_lock, flags);
+ raw_spin_lock(¤t->pi_lock);
rt_mutex_dequeue(lock, waiter);
current->pi_blocked_on = NULL;
- raw_spin_unlock_irqrestore(¤t->pi_lock, flags);
+ raw_spin_unlock(¤t->pi_lock);
/*
* Only update priority if the waiter was the highest priority
@@ -1032,7 +1028,7 @@
if (!owner || !is_top_waiter)
return;
- raw_spin_lock_irqsave(&owner->pi_lock, flags);
+ raw_spin_lock(&owner->pi_lock);
rt_mutex_dequeue_pi(owner, waiter);
@@ -1044,7 +1040,7 @@
/* Store the lock on which owner is blocked or NULL */
next_lock = task_blocked_on_lock(owner);
- raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
+ raw_spin_unlock(&owner->pi_lock);
/*
* Don't walk the chain, if the owner task is not blocked
@@ -1056,12 +1052,12 @@
/* gets dropped in rt_mutex_adjust_prio_chain()! */
get_task_struct(owner);
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irq(&lock->wait_lock);
rt_mutex_adjust_prio_chain(owner, RT_MUTEX_MIN_CHAINWALK, lock,
next_lock, NULL, current);
- raw_spin_lock(&lock->wait_lock);
+ raw_spin_lock_irq(&lock->wait_lock);
}
/*
@@ -1097,11 +1093,11 @@
* __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop
* @lock: the rt_mutex to take
* @state: the state the task should block in (TASK_INTERRUPTIBLE
- * or TASK_UNINTERRUPTIBLE)
+ * or TASK_UNINTERRUPTIBLE)
* @timeout: the pre-initialized and started timer, or NULL for none
* @waiter: the pre-initialized rt_mutex_waiter
*
- * lock->wait_lock must be held by the caller.
+ * Must be called with lock->wait_lock held and interrupts disabled
*/
static int __sched
__rt_mutex_slowlock(struct rt_mutex *lock, int state,
@@ -1129,13 +1125,13 @@
break;
}
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irq(&lock->wait_lock);
debug_rt_mutex_print_deadlock(waiter);
schedule();
- raw_spin_lock(&lock->wait_lock);
+ raw_spin_lock_irq(&lock->wait_lock);
set_current_state(state);
}
@@ -1172,17 +1168,26 @@
enum rtmutex_chainwalk chwalk)
{
struct rt_mutex_waiter waiter;
+ unsigned long flags;
int ret = 0;
debug_rt_mutex_init_waiter(&waiter);
RB_CLEAR_NODE(&waiter.pi_tree_entry);
RB_CLEAR_NODE(&waiter.tree_entry);
- raw_spin_lock(&lock->wait_lock);
+ /*
+ * Technically we could use raw_spin_[un]lock_irq() here, but this can
+ * be called in early boot if the cmpxchg() fast path is disabled
+ * (debug, no architecture support). In this case we will acquire the
+ * rtmutex with lock->wait_lock held. But we cannot unconditionally
+ * enable interrupts in that early boot case. So we need to use the
+ * irqsave/restore variants.
+ */
+ raw_spin_lock_irqsave(&lock->wait_lock, flags);
/* Try to acquire the lock again: */
if (try_to_take_rt_mutex(lock, current, NULL)) {
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
return 0;
}
@@ -1211,7 +1216,7 @@
*/
fixup_rt_mutex_waiters(lock);
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
/* Remove pending timer: */
if (unlikely(timeout))
@@ -1227,6 +1232,7 @@
*/
static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
{
+ unsigned long flags;
int ret;
/*
@@ -1238,10 +1244,10 @@
return 0;
/*
- * The mutex has currently no owner. Lock the wait lock and
- * try to acquire the lock.
+ * The mutex has currently no owner. Lock the wait lock and try to
+ * acquire the lock. We use irqsave here to support early boot calls.
*/
- raw_spin_lock(&lock->wait_lock);
+ raw_spin_lock_irqsave(&lock->wait_lock, flags);
ret = try_to_take_rt_mutex(lock, current, NULL);
@@ -1251,7 +1257,7 @@
*/
fixup_rt_mutex_waiters(lock);
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
return ret;
}
@@ -1263,7 +1269,10 @@
static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
struct wake_q_head *wake_q)
{
- raw_spin_lock(&lock->wait_lock);
+ unsigned long flags;
+
+ /* irqsave required to support early boot calls */
+ raw_spin_lock_irqsave(&lock->wait_lock, flags);
debug_rt_mutex_unlock(lock);
@@ -1302,10 +1311,10 @@
*/
while (!rt_mutex_has_waiters(lock)) {
/* Drops lock->wait_lock ! */
- if (unlock_rt_mutex_safe(lock) == true)
+ if (unlock_rt_mutex_safe(lock, flags) == true)
return false;
/* Relock the rtmutex and try again */
- raw_spin_lock(&lock->wait_lock);
+ raw_spin_lock_irqsave(&lock->wait_lock, flags);
}
/*
@@ -1316,7 +1325,7 @@
*/
mark_wakeup_next_waiter(wake_q, lock);
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
/* check PI boosting */
return true;
@@ -1596,10 +1605,10 @@
{
int ret;
- raw_spin_lock(&lock->wait_lock);
+ raw_spin_lock_irq(&lock->wait_lock);
if (try_to_take_rt_mutex(lock, task, NULL)) {
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irq(&lock->wait_lock);
return 1;
}
@@ -1620,7 +1629,7 @@
if (unlikely(ret))
remove_waiter(lock, waiter);
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irq(&lock->wait_lock);
debug_rt_mutex_print_deadlock(waiter);
@@ -1668,7 +1677,7 @@
{
int ret;
- raw_spin_lock(&lock->wait_lock);
+ raw_spin_lock_irq(&lock->wait_lock);
set_current_state(TASK_INTERRUPTIBLE);
@@ -1684,7 +1693,7 @@
*/
fixup_rt_mutex_waiters(lock);
- raw_spin_unlock(&lock->wait_lock);
+ raw_spin_unlock_irq(&lock->wait_lock);
return ret;
}
diff --git a/kernel/memremap.c b/kernel/memremap.c
index e517a16..70ee377 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -150,7 +150,7 @@
}
EXPORT_SYMBOL(devm_memunmap);
-pfn_t phys_to_pfn_t(dma_addr_t addr, unsigned long flags)
+pfn_t phys_to_pfn_t(phys_addr_t addr, unsigned long flags)
{
return __pfn_to_pfn_t(addr >> PAGE_SHIFT, flags);
}
@@ -183,7 +183,11 @@
static void pgmap_radix_release(struct resource *res)
{
- resource_size_t key;
+ resource_size_t key, align_start, align_size, align_end;
+
+ align_start = res->start & ~(SECTION_SIZE - 1);
+ align_size = ALIGN(resource_size(res), SECTION_SIZE);
+ align_end = align_start + align_size - 1;
mutex_lock(&pgmap_lock);
for (key = res->start; key <= res->end; key += SECTION_SIZE)
@@ -226,12 +230,11 @@
percpu_ref_put(pgmap->ref);
}
- pgmap_radix_release(res);
-
/* pages are dead and unused, undo the arch mapping */
align_start = res->start & ~(SECTION_SIZE - 1);
align_size = ALIGN(resource_size(res), SECTION_SIZE);
arch_remove_memory(align_start, align_size);
+ pgmap_radix_release(res);
dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc,
"%s: failed to free all reserved pages\n", __func__);
}
@@ -267,7 +270,7 @@
{
int is_ram = region_intersects(res->start, resource_size(res),
"System RAM");
- resource_size_t key, align_start, align_size;
+ resource_size_t key, align_start, align_size, align_end;
struct dev_pagemap *pgmap;
struct page_map *page_map;
unsigned long pfn;
@@ -309,7 +312,10 @@
mutex_lock(&pgmap_lock);
error = 0;
- for (key = res->start; key <= res->end; key += SECTION_SIZE) {
+ align_start = res->start & ~(SECTION_SIZE - 1);
+ align_size = ALIGN(resource_size(res), SECTION_SIZE);
+ align_end = align_start + align_size - 1;
+ for (key = align_start; key <= align_end; key += SECTION_SIZE) {
struct dev_pagemap *dup;
rcu_read_lock();
@@ -336,8 +342,6 @@
if (nid < 0)
nid = numa_mem_id();
- align_start = res->start & ~(SECTION_SIZE - 1);
- align_size = ALIGN(resource_size(res), SECTION_SIZE);
error = arch_add_memory(nid, align_start, align_size, true);
if (error)
goto err_add_memory;
diff --git a/kernel/pid.c b/kernel/pid.c
index f4ad91b..4d73a83 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -588,7 +588,7 @@
void __init pidmap_init(void)
{
- /* Veryify no one has done anything silly */
+ /* Verify no one has done anything silly: */
BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_HASH_ADDING);
/* bump default and minimum pid_max based on number of cpus */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 63d3a24..9503d59 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6840,7 +6840,7 @@
sched_domains_numa_masks[i][j] = mask;
- for (k = 0; k < nr_node_ids; k++) {
+ for_each_node(k) {
if (node_distance(j, k) > sched_domains_numa_distance[i])
continue;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1926606..56b7d4b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1220,8 +1220,6 @@
{
if (env->best_task)
put_task_struct(env->best_task);
- if (p)
- get_task_struct(p);
env->best_task = p;
env->best_imp = imp;
@@ -1289,20 +1287,30 @@
long imp = env->p->numa_group ? groupimp : taskimp;
long moveimp = imp;
int dist = env->dist;
+ bool assigned = false;
rcu_read_lock();
raw_spin_lock_irq(&dst_rq->lock);
cur = dst_rq->curr;
/*
- * No need to move the exiting task, and this ensures that ->curr
- * wasn't reaped and thus get_task_struct() in task_numa_assign()
- * is safe under RCU read lock.
- * Note that rcu_read_lock() itself can't protect from the final
- * put_task_struct() after the last schedule().
+ * No need to move the exiting task or idle task.
*/
if ((cur->flags & PF_EXITING) || is_idle_task(cur))
cur = NULL;
+ else {
+ /*
+ * The task_struct must be protected here to protect the
+ * p->numa_faults access in the task_weight since the
+ * numa_faults could already be freed in the following path:
+ * finish_task_switch()
+ * --> put_task_struct()
+ * --> __put_task_struct()
+ * --> task_numa_free()
+ */
+ get_task_struct(cur);
+ }
+
raw_spin_unlock_irq(&dst_rq->lock);
/*
@@ -1386,6 +1394,7 @@
*/
if (!load_too_imbalanced(src_load, dst_load, env)) {
imp = moveimp - 1;
+ put_task_struct(cur);
cur = NULL;
goto assign;
}
@@ -1411,9 +1420,16 @@
env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu);
assign:
+ assigned = true;
task_numa_assign(env, cur, imp);
unlock:
rcu_read_unlock();
+ /*
+ * The dst_rq->curr isn't assigned. The protection for task_struct is
+ * finished.
+ */
+ if (cur && !assigned)
+ put_task_struct(cur);
}
static void task_numa_find_cpu(struct task_numa_env *env,
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 435b885..fa909f9 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -897,10 +897,10 @@
*/
static void __remove_hrtimer(struct hrtimer *timer,
struct hrtimer_clock_base *base,
- unsigned long newstate, int reprogram)
+ u8 newstate, int reprogram)
{
struct hrtimer_cpu_base *cpu_base = base->cpu_base;
- unsigned int state = timer->state;
+ u8 state = timer->state;
timer->state = newstate;
if (!(state & HRTIMER_STATE_ENQUEUED))
@@ -930,7 +930,7 @@
remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart)
{
if (hrtimer_is_queued(timer)) {
- unsigned long state = timer->state;
+ u8 state = timer->state;
int reprogram;
/*
@@ -954,6 +954,22 @@
return 0;
}
+static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim,
+ const enum hrtimer_mode mode)
+{
+#ifdef CONFIG_TIME_LOW_RES
+ /*
+ * CONFIG_TIME_LOW_RES indicates that the system has no way to return
+ * granular time values. For relative timers we add hrtimer_resolution
+ * (i.e. one jiffie) to prevent short timeouts.
+ */
+ timer->is_rel = mode & HRTIMER_MODE_REL;
+ if (timer->is_rel)
+ tim = ktime_add_safe(tim, ktime_set(0, hrtimer_resolution));
+#endif
+ return tim;
+}
+
/**
* hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
* @timer: the timer to be added
@@ -974,19 +990,10 @@
/* Remove an active timer from the queue: */
remove_hrtimer(timer, base, true);
- if (mode & HRTIMER_MODE_REL) {
+ if (mode & HRTIMER_MODE_REL)
tim = ktime_add_safe(tim, base->get_time());
- /*
- * CONFIG_TIME_LOW_RES is a temporary way for architectures
- * to signal that they simply return xtime in
- * do_gettimeoffset(). In this case we want to round up by
- * resolution when starting a relative timer, to avoid short
- * timeouts. This will go away with the GTOD framework.
- */
-#ifdef CONFIG_TIME_LOW_RES
- tim = ktime_add_safe(tim, ktime_set(0, hrtimer_resolution));
-#endif
- }
+
+ tim = hrtimer_update_lowres(timer, tim, mode);
hrtimer_set_expires_range_ns(timer, tim, delta_ns);
@@ -1074,19 +1081,23 @@
/**
* hrtimer_get_remaining - get remaining time for the timer
* @timer: the timer to read
+ * @adjust: adjust relative timers when CONFIG_TIME_LOW_RES=y
*/
-ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
+ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust)
{
unsigned long flags;
ktime_t rem;
lock_hrtimer_base(timer, &flags);
- rem = hrtimer_expires_remaining(timer);
+ if (IS_ENABLED(CONFIG_TIME_LOW_RES) && adjust)
+ rem = hrtimer_expires_remaining_adjusted(timer);
+ else
+ rem = hrtimer_expires_remaining(timer);
unlock_hrtimer_base(timer, &flags);
return rem;
}
-EXPORT_SYMBOL_GPL(hrtimer_get_remaining);
+EXPORT_SYMBOL_GPL(__hrtimer_get_remaining);
#ifdef CONFIG_NO_HZ_COMMON
/**
@@ -1220,6 +1231,14 @@
fn = timer->function;
/*
+ * Clear the 'is relative' flag for the TIME_LOW_RES case. If the
+ * timer is restarted with a period then it becomes an absolute
+ * timer. If its not restarted it does not matter.
+ */
+ if (IS_ENABLED(CONFIG_TIME_LOW_RES))
+ timer->is_rel = false;
+
+ /*
* Because we run timers from hardirq context, there is no chance
* they get migrated to another cpu, therefore its safe to unlock
* the timer base.
diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c
index 8d262b4..1d5c720 100644
--- a/kernel/time/itimer.c
+++ b/kernel/time/itimer.c
@@ -26,7 +26,7 @@
*/
static struct timeval itimer_get_remtime(struct hrtimer *timer)
{
- ktime_t rem = hrtimer_get_remaining(timer);
+ ktime_t rem = __hrtimer_get_remaining(timer, true);
/*
* Racy but safe: if the itimer expires after the above
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 36f2ca0..6df8927 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -685,8 +685,18 @@
if (!capable(CAP_SYS_TIME))
return -EPERM;
- if (!timeval_inject_offset_valid(&txc->time))
- return -EINVAL;
+ if (txc->modes & ADJ_NANO) {
+ struct timespec ts;
+
+ ts.tv_sec = txc->time.tv_sec;
+ ts.tv_nsec = txc->time.tv_usec;
+ if (!timespec_inject_offset_valid(&ts))
+ return -EINVAL;
+
+ } else {
+ if (!timeval_inject_offset_valid(&txc->time))
+ return -EINVAL;
+ }
}
/*
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 31d11ac..f2826c3 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -760,7 +760,7 @@
(timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE))
timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv);
- remaining = ktime_sub(hrtimer_get_expires(timer), now);
+ remaining = __hrtimer_expires_remaining_adjusted(timer, now);
/* Return 0 only, when the timer is expired and not pending */
if (remaining.tv64 <= 0) {
/*
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 9d7a053..0b17424 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -36,16 +36,17 @@
*/
static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);
-/*
- * The time, when the last jiffy update happened. Protected by jiffies_lock.
- */
-static ktime_t last_jiffies_update;
-
struct tick_sched *tick_get_tick_sched(int cpu)
{
return &per_cpu(tick_cpu_sched, cpu);
}
+#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
+/*
+ * The time, when the last jiffy update happened. Protected by jiffies_lock.
+ */
+static ktime_t last_jiffies_update;
+
/*
* Must be called with interrupts disabled !
*/
@@ -151,6 +152,7 @@
update_process_times(user_mode(regs));
profile_tick(CPU_PROFILING);
}
+#endif
#ifdef CONFIG_NO_HZ_FULL
cpumask_var_t tick_nohz_full_mask;
@@ -993,9 +995,9 @@
/* Get the next period */
next = tick_init_jiffy_update();
- hrtimer_forward_now(&ts->sched_timer, tick_period);
hrtimer_set_expires(&ts->sched_timer, next);
- tick_program_event(next, 1);
+ hrtimer_forward_now(&ts->sched_timer, tick_period);
+ tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
tick_nohz_activate(ts, NOHZ_MODE_LOWRES);
}
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index f75e35b..ba7d8b2 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -69,7 +69,7 @@
print_name_offset(m, taddr);
SEQ_printf(m, ", ");
print_name_offset(m, timer->function);
- SEQ_printf(m, ", S:%02lx", timer->state);
+ SEQ_printf(m, ", S:%02x", timer->state);
#ifdef CONFIG_TIMER_STATS
SEQ_printf(m, ", ");
print_name_offset(m, timer->start_site);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 45dd798..326a75e 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -191,14 +191,17 @@
struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
struct bpf_array *array = container_of(map, struct bpf_array, map);
struct perf_event *event;
+ struct file *file;
if (unlikely(index >= array->map.max_entries))
return -E2BIG;
- event = (struct perf_event *)array->ptrs[index];
- if (!event)
+ file = (struct file *)array->ptrs[index];
+ if (unlikely(!file))
return -ENOENT;
+ event = file->private_data;
+
/* make sure event is local and doesn't have pmu::count */
if (event->oncpu != smp_processor_id() ||
event->pmu->count)
@@ -228,6 +231,7 @@
void *data = (void *) (long) r4;
struct perf_sample_data sample_data;
struct perf_event *event;
+ struct file *file;
struct perf_raw_record raw = {
.size = size,
.data = data,
@@ -236,10 +240,12 @@
if (unlikely(index >= array->map.max_entries))
return -E2BIG;
- event = (struct perf_event *)array->ptrs[index];
- if (unlikely(!event))
+ file = (struct file *)array->ptrs[index];
+ if (unlikely(!file))
return -ENOENT;
+ event = file->private_data;
+
if (unlikely(event->attr.type != PERF_TYPE_SOFTWARE ||
event->attr.config != PERF_COUNT_SW_BPF_OUTPUT))
return -EINVAL;
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index dda9e67..202df6c 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -126,6 +126,13 @@
}
/*
+ * Some archs may not have the passed in ip in the dump.
+ * If that happens, we need to show everything.
+ */
+ if (i == stack_trace_max.nr_entries)
+ i = 0;
+
+ /*
* Now find where in the stack these are.
*/
x = 0;
diff --git a/mm/gup.c b/mm/gup.c
index b64a361..7bf19ff 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -430,10 +430,8 @@
* Anon pages in shared mappings are surprising: now
* just reject it.
*/
- if (!is_cow_mapping(vm_flags)) {
- WARN_ON_ONCE(vm_flags & VM_MAYWRITE);
+ if (!is_cow_mapping(vm_flags))
return -EFAULT;
- }
}
} else if (!(vm_flags & VM_READ)) {
if (!(gup_flags & FOLL_FORCE))
diff --git a/mm/memory.c b/mm/memory.c
index 30991f8..635451a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1591,10 +1591,15 @@
* than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP
* without pte special, it would there be refcounted as a normal page.
*/
- if (!HAVE_PTE_SPECIAL && pfn_t_valid(pfn)) {
+ if (!HAVE_PTE_SPECIAL && !pfn_t_devmap(pfn) && pfn_t_valid(pfn)) {
struct page *page;
- page = pfn_t_to_page(pfn);
+ /*
+ * At this point we are committed to insert_page()
+ * regardless of whether the caller specified flags that
+ * result in pfn_t_has_page() == false.
+ */
+ page = pfn_to_page(pfn_t_to_pfn(pfn));
return insert_page(vma, addr, page, vma->vm_page_prot);
}
return insert_pfn(vma, addr, pfn, vma->vm_page_prot);
@@ -2232,11 +2237,6 @@
page_cache_get(old_page);
- /*
- * Only catch write-faults on shared writable pages,
- * read-only shared pages can get COWed by
- * get_user_pages(.write=1, .force=1).
- */
if (vma->vm_ops && vma->vm_ops->page_mkwrite) {
int tmp;
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index d040365..8a4cc2f 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -307,6 +307,9 @@
/* check that it's our buffer */
if (lowpan_is_ipv6(*skb_network_header(skb))) {
+ /* Pull off the 1-byte of 6lowpan header. */
+ skb_pull(skb, 1);
+
/* Copy the packet so that the IPv6 header is
* properly aligned.
*/
@@ -317,6 +320,7 @@
local_skb->protocol = htons(ETH_P_IPV6);
local_skb->pkt_type = PACKET_HOST;
+ local_skb->dev = dev;
skb_set_transport_header(local_skb, sizeof(struct ipv6hdr));
@@ -335,6 +339,8 @@
if (!local_skb)
goto drop;
+ local_skb->dev = dev;
+
ret = iphc_decompress(local_skb, dev, chan);
if (ret < 0) {
kfree_skb(local_skb);
@@ -343,7 +349,6 @@
local_skb->protocol = htons(ETH_P_IPV6);
local_skb->pkt_type = PACKET_HOST;
- local_skb->dev = dev;
if (give_skb_to_upper(local_skb, dev)
!= NET_RX_SUCCESS) {
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index 41b5f38..c78ee2d 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -688,21 +688,29 @@
* command to remove it from the controller.
*/
list_for_each_entry(b, &hdev->le_white_list, list) {
- struct hci_cp_le_del_from_white_list cp;
+ /* If the device is neither in pend_le_conns nor
+ * pend_le_reports then remove it from the whitelist.
+ */
+ if (!hci_pend_le_action_lookup(&hdev->pend_le_conns,
+ &b->bdaddr, b->bdaddr_type) &&
+ !hci_pend_le_action_lookup(&hdev->pend_le_reports,
+ &b->bdaddr, b->bdaddr_type)) {
+ struct hci_cp_le_del_from_white_list cp;
- if (hci_pend_le_action_lookup(&hdev->pend_le_conns,
- &b->bdaddr, b->bdaddr_type) ||
- hci_pend_le_action_lookup(&hdev->pend_le_reports,
- &b->bdaddr, b->bdaddr_type)) {
- white_list_entries++;
+ cp.bdaddr_type = b->bdaddr_type;
+ bacpy(&cp.bdaddr, &b->bdaddr);
+
+ hci_req_add(req, HCI_OP_LE_DEL_FROM_WHITE_LIST,
+ sizeof(cp), &cp);
continue;
}
- cp.bdaddr_type = b->bdaddr_type;
- bacpy(&cp.bdaddr, &b->bdaddr);
+ if (hci_find_irk_by_addr(hdev, &b->bdaddr, b->bdaddr_type)) {
+ /* White list can not be used with RPAs */
+ return 0x00;
+ }
- hci_req_add(req, HCI_OP_LE_DEL_FROM_WHITE_LIST,
- sizeof(cp), &cp);
+ white_list_entries++;
}
/* Since all no longer valid white list entries have been
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 39a5149..eb4f5f2 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -197,10 +197,20 @@
chan->sport = psm;
err = 0;
} else {
- u16 p;
+ u16 p, start, end, incr;
+
+ if (chan->src_type == BDADDR_BREDR) {
+ start = L2CAP_PSM_DYN_START;
+ end = L2CAP_PSM_AUTO_END;
+ incr = 2;
+ } else {
+ start = L2CAP_PSM_LE_DYN_START;
+ end = L2CAP_PSM_LE_DYN_END;
+ incr = 1;
+ }
err = -EINVAL;
- for (p = 0x1001; p < 0x1100; p += 2)
+ for (p = start; p <= end; p += incr)
if (!__l2cap_global_chan_by_addr(cpu_to_le16(p), src)) {
chan->psm = cpu_to_le16(p);
chan->sport = cpu_to_le16(p);
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 1bb5515..e4cae72 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -58,7 +58,7 @@
return -EINVAL;
/* Restrict usage of well-known PSMs */
- if (psm < 0x1001 && !capable(CAP_NET_BIND_SERVICE))
+ if (psm < L2CAP_PSM_DYN_START && !capable(CAP_NET_BIND_SERVICE))
return -EACCES;
return 0;
@@ -67,11 +67,11 @@
static int l2cap_validate_le_psm(u16 psm)
{
/* Valid LE_PSM ranges are defined only until 0x00ff */
- if (psm > 0x00ff)
+ if (psm > L2CAP_PSM_LE_DYN_END)
return -EINVAL;
/* Restrict fixed, SIG assigned PSM values to CAP_NET_BIND_SERVICE */
- if (psm <= 0x007f && !capable(CAP_NET_BIND_SERVICE))
+ if (psm < L2CAP_PSM_LE_DYN_START && !capable(CAP_NET_BIND_SERVICE))
return -EACCES;
return 0;
@@ -125,6 +125,9 @@
goto done;
}
+ bacpy(&chan->src, &la.l2_bdaddr);
+ chan->src_type = la.l2_bdaddr_type;
+
if (la.l2_cid)
err = l2cap_add_scid(chan, __le16_to_cpu(la.l2_cid));
else
@@ -156,9 +159,6 @@
break;
}
- bacpy(&chan->src, &la.l2_bdaddr);
- chan->src_type = la.l2_bdaddr_type;
-
if (chan->psm && bdaddr_type_is_le(chan->src_type))
chan->mode = L2CAP_MODE_LE_FLOWCTL;
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index ffed8a1..4b175df 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -1072,22 +1072,6 @@
hcon->dst_type = smp->remote_irk->addr_type;
queue_work(hdev->workqueue, &conn->id_addr_update_work);
}
-
- /* When receiving an indentity resolving key for
- * a remote device that does not use a resolvable
- * private address, just remove the key so that
- * it is possible to use the controller white
- * list for scanning.
- *
- * Userspace will have been told to not store
- * this key at this point. So it is safe to
- * just remove it.
- */
- if (!bacmp(&smp->remote_irk->rpa, BDADDR_ANY)) {
- list_del_rcu(&smp->remote_irk->list);
- kfree_rcu(smp->remote_irk, rcu);
- smp->remote_irk = NULL;
- }
}
if (smp->csrk) {
diff --git a/net/bridge/br.c b/net/bridge/br.c
index a1abe49..3addc05 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -121,6 +121,7 @@
.notifier_call = br_device_event
};
+/* called with RTNL */
static int br_switchdev_event(struct notifier_block *unused,
unsigned long event, void *ptr)
{
@@ -130,7 +131,6 @@
struct switchdev_notifier_fdb_info *fdb_info;
int err = NOTIFY_DONE;
- rtnl_lock();
p = br_port_get_rtnl(dev);
if (!p)
goto out;
@@ -155,7 +155,6 @@
}
out:
- rtnl_unlock();
return err;
}
diff --git a/net/core/dev.c b/net/core/dev.c
index cc9e365..8cba3d8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4351,6 +4351,7 @@
diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
diffs |= p->vlan_tci ^ skb->vlan_tci;
+ diffs |= skb_metadata_dst_cmp(p, skb);
if (maclen == ETH_HLEN)
diffs |= compare_ether_header(skb_mac_header(p),
skb_mac_header(skb));
@@ -4548,10 +4549,12 @@
break;
case GRO_MERGED_FREE:
- if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD)
+ if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) {
+ skb_dst_drop(skb);
kmem_cache_free(skbuff_head_cache, skb);
- else
+ } else {
__kfree_skb(skb);
+ }
break;
case GRO_HELD:
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index 1df98c5..e92b759 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -93,10 +93,17 @@
* @sk2: Socket belonging to the existing reuseport group.
* May return ENOMEM and not add socket to group under memory pressure.
*/
-int reuseport_add_sock(struct sock *sk, const struct sock *sk2)
+int reuseport_add_sock(struct sock *sk, struct sock *sk2)
{
struct sock_reuseport *reuse;
+ if (!rcu_access_pointer(sk2->sk_reuseport_cb)) {
+ int err = reuseport_alloc(sk2);
+
+ if (err)
+ return err;
+ }
+
spin_lock_bh(&reuseport_lock);
reuse = rcu_dereference_protected(sk2->sk_reuseport_cb,
lockdep_is_held(&reuseport_lock)),
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index c229205..7758247 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -353,6 +353,7 @@
select CRYPTO_CBC
select CRYPTO_SHA1
select CRYPTO_DES
+ select CRYPTO_ECHAINIV
---help---
Support for IPsec ESP.
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 7aea0cc..d07fc07 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1394,9 +1394,10 @@
struct fib_info *fi = fa->fa_info;
int nhsel, err;
- if ((index >= (1ul << fa->fa_slen)) &&
- ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen != KEYLENGTH)))
- continue;
+ if ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen < KEYLENGTH)) {
+ if (index >= (1ul << fa->fa_slen))
+ continue;
+ }
if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
continue;
if (fi->fib_dead)
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 8bb8e7a..6029157 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -361,13 +361,20 @@
req->id.idiag_dport, req->id.idiag_src[0],
req->id.idiag_sport, req->id.idiag_if);
#if IS_ENABLED(CONFIG_IPV6)
- else if (req->sdiag_family == AF_INET6)
- sk = inet6_lookup(net, hashinfo,
- (struct in6_addr *)req->id.idiag_dst,
- req->id.idiag_dport,
- (struct in6_addr *)req->id.idiag_src,
- req->id.idiag_sport,
- req->id.idiag_if);
+ else if (req->sdiag_family == AF_INET6) {
+ if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) &&
+ ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src))
+ sk = inet_lookup(net, hashinfo, req->id.idiag_dst[3],
+ req->id.idiag_dport, req->id.idiag_src[3],
+ req->id.idiag_sport, req->id.idiag_if);
+ else
+ sk = inet6_lookup(net, hashinfo,
+ (struct in6_addr *)req->id.idiag_dst,
+ req->id.idiag_dport,
+ (struct in6_addr *)req->id.idiag_src,
+ req->id.idiag_sport,
+ req->id.idiag_if);
+ }
#endif
else
return ERR_PTR(-EINVAL);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 3f00810..187c6fc 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -661,6 +661,7 @@
struct ipq *qp;
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS);
+ skb_orphan(skb);
/* Lookup (or create) queue header */
qp = ip_find(net, ip_hdr(skb), user, vif);
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index b1209b6..d77eb0c 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -316,7 +316,10 @@
const struct iphdr *iph = ip_hdr(skb);
struct rtable *rt;
- if (sysctl_ip_early_demux && !skb_dst(skb) && !skb->sk) {
+ if (sysctl_ip_early_demux &&
+ !skb_dst(skb) &&
+ !skb->sk &&
+ !ip_is_fragment(iph)) {
const struct net_protocol *ipprot;
int protocol = iph->protocol;
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 67f7c9d..2ed9dd2 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -143,7 +143,11 @@
/* Persistent data: */
+#ifdef IPCONFIG_DYNAMIC
static int ic_proto_used; /* Protocol used, if any */
+#else
+#define ic_proto_used 0
+#endif
static __be32 ic_nameservers[CONF_NAMESERVERS_MAX]; /* DNS Server IP addresses */
static u8 ic_domain[64]; /* DNS (not NIS) domain name */
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 6fb869f6..a04dee5 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -27,8 +27,6 @@
{
int err;
- skb_orphan(skb);
-
local_bh_disable();
err = ip_defrag(net, skb, user);
local_bh_enable();
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index fd17eec..19746b3 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -279,6 +279,7 @@
#include <asm/uaccess.h>
#include <asm/ioctls.h>
+#include <asm/unaligned.h>
#include <net/busy_poll.h>
int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
@@ -2638,6 +2639,7 @@
const struct inet_connection_sock *icsk = inet_csk(sk);
u32 now = tcp_time_stamp;
unsigned int start;
+ u64 rate64;
u32 rate;
memset(info, 0, sizeof(*info));
@@ -2703,15 +2705,17 @@
info->tcpi_total_retrans = tp->total_retrans;
rate = READ_ONCE(sk->sk_pacing_rate);
- info->tcpi_pacing_rate = rate != ~0U ? rate : ~0ULL;
+ rate64 = rate != ~0U ? rate : ~0ULL;
+ put_unaligned(rate64, &info->tcpi_pacing_rate);
rate = READ_ONCE(sk->sk_max_pacing_rate);
- info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL;
+ rate64 = rate != ~0U ? rate : ~0ULL;
+ put_unaligned(rate64, &info->tcpi_max_pacing_rate);
do {
start = u64_stats_fetch_begin_irq(&tp->syncp);
- info->tcpi_bytes_acked = tp->bytes_acked;
- info->tcpi_bytes_received = tp->bytes_received;
+ put_unaligned(tp->bytes_acked, &info->tcpi_bytes_acked);
+ put_unaligned(tp->bytes_received, &info->tcpi_bytes_received);
} while (u64_stats_fetch_retry_irq(&tp->syncp, start));
info->tcpi_segs_out = tp->segs_out;
info->tcpi_segs_in = tp->segs_in;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 0003d40..1c2a734 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2164,8 +2164,7 @@
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
- int cnt, oldcnt;
- int err;
+ int cnt, oldcnt, lost;
unsigned int mss;
/* Use SACK to deduce losses of new sequences sent during recovery */
const u32 loss_high = tcp_is_sack(tp) ? tp->snd_nxt : tp->high_seq;
@@ -2205,9 +2204,10 @@
break;
mss = tcp_skb_mss(skb);
- err = tcp_fragment(sk, skb, (packets - oldcnt) * mss,
- mss, GFP_ATOMIC);
- if (err < 0)
+ /* If needed, chop off the prefix to mark as lost. */
+ lost = (packets - oldcnt) * mss;
+ if (lost < skb->len &&
+ tcp_fragment(sk, skb, lost, mss, GFP_ATOMIC) < 0)
break;
cnt = packets;
}
@@ -2366,8 +2366,6 @@
tp->snd_ssthresh = tp->prior_ssthresh;
tcp_ecn_withdraw_cwr(tp);
}
- } else {
- tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh);
}
tp->snd_cwnd_stamp = tcp_time_stamp;
tp->undo_marker = 0;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5ced3e4..a4d5237 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -707,7 +707,8 @@
outside socket context is ugly, certainly. What can I do?
*/
-static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
+static void tcp_v4_send_ack(struct net *net,
+ struct sk_buff *skb, u32 seq, u32 ack,
u32 win, u32 tsval, u32 tsecr, int oif,
struct tcp_md5sig_key *key,
int reply_flags, u8 tos)
@@ -722,7 +723,6 @@
];
} rep;
struct ip_reply_arg arg;
- struct net *net = dev_net(skb_dst(skb)->dev);
memset(&rep.th, 0, sizeof(struct tcphdr));
memset(&arg, 0, sizeof(arg));
@@ -784,7 +784,8 @@
struct inet_timewait_sock *tw = inet_twsk(sk);
struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
- tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
+ tcp_v4_send_ack(sock_net(sk), skb,
+ tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
tcp_time_stamp + tcptw->tw_ts_offset,
tcptw->tw_ts_recent,
@@ -803,8 +804,10 @@
/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
* sk->sk_state == TCP_SYN_RECV -> for Fast Open.
*/
- tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ?
- tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
+ u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 :
+ tcp_sk(sk)->snd_nxt;
+
+ tcp_v4_send_ack(sock_net(sk), skb, seq,
tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd,
tcp_time_stamp,
req->ts_recent,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index dc45b53..be0b218 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -499,6 +499,7 @@
struct sock *sk, *result;
struct hlist_nulls_node *node;
int score, badness, matches = 0, reuseport = 0;
+ bool select_ok = true;
u32 hash = 0;
begin:
@@ -512,14 +513,18 @@
badness = score;
reuseport = sk->sk_reuseport;
if (reuseport) {
- struct sock *sk2;
hash = udp_ehashfn(net, daddr, hnum,
saddr, sport);
- sk2 = reuseport_select_sock(sk, hash, skb,
- sizeof(struct udphdr));
- if (sk2) {
- result = sk2;
- goto found;
+ if (select_ok) {
+ struct sock *sk2;
+
+ sk2 = reuseport_select_sock(sk, hash, skb,
+ sizeof(struct udphdr));
+ if (sk2) {
+ result = sk2;
+ select_ok = false;
+ goto found;
+ }
}
matches = 1;
}
@@ -563,6 +568,7 @@
unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask);
struct udp_hslot *hslot2, *hslot = &udptable->hash[slot];
int score, badness, matches = 0, reuseport = 0;
+ bool select_ok = true;
u32 hash = 0;
rcu_read_lock();
@@ -601,14 +607,18 @@
badness = score;
reuseport = sk->sk_reuseport;
if (reuseport) {
- struct sock *sk2;
hash = udp_ehashfn(net, daddr, hnum,
saddr, sport);
- sk2 = reuseport_select_sock(sk, hash, skb,
+ if (select_ok) {
+ struct sock *sk2;
+
+ sk2 = reuseport_select_sock(sk, hash, skb,
sizeof(struct udphdr));
- if (sk2) {
- result = sk2;
- goto found;
+ if (sk2) {
+ result = sk2;
+ select_ok = false;
+ goto found;
+ }
}
matches = 1;
}
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index bb7dabe..40c8975 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -69,6 +69,7 @@
select CRYPTO_CBC
select CRYPTO_SHA1
select CRYPTO_DES
+ select CRYPTO_ECHAINIV
---help---
Support for IPsec ESP.
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 517c55b..4281621 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -162,6 +162,9 @@
fl6.fl6_dport = inet->inet_dport;
fl6.fl6_sport = inet->inet_sport;
+ if (!fl6.flowi6_oif)
+ fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
+
if (!fl6.flowi6_oif && (addr_type&IPV6_ADDR_MULTICAST))
fl6.flowi6_oif = np->mcast_oif;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 23de98f..a163102 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -909,6 +909,7 @@
struct rt6_info *rt;
#endif
int err;
+ int flags = 0;
/* The correct way to handle this would be to do
* ip6_route_get_saddr, and then ip6_route_output; however,
@@ -940,10 +941,13 @@
dst_release(*dst);
*dst = NULL;
}
+
+ if (fl6->flowi6_oif)
+ flags |= RT6_LOOKUP_F_IFACE;
}
if (!*dst)
- *dst = ip6_route_output(net, sk, fl6);
+ *dst = ip6_route_output_flags(net, sk, fl6, flags);
err = (*dst)->error;
if (err)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 3c8834b..ed44663 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1183,11 +1183,10 @@
return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags);
}
-struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk,
- struct flowi6 *fl6)
+struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
+ struct flowi6 *fl6, int flags)
{
struct dst_entry *dst;
- int flags = 0;
bool any_src;
dst = l3mdev_rt6_dst_by_oif(net, fl6);
@@ -1208,7 +1207,7 @@
return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_output);
}
-EXPORT_SYMBOL(ip6_route_output);
+EXPORT_SYMBOL_GPL(ip6_route_output_flags);
struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig)
{
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index e794ef6..2066d1c 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -201,14 +201,14 @@
if ((__force u16)t->parms.i_flags & SIT_ISATAP)
dev->priv_flags |= IFF_ISATAP;
+ dev->rtnl_link_ops = &sit_link_ops;
+
err = register_netdevice(dev);
if (err < 0)
goto out;
ipip6_tunnel_clone_6rd(dev, sitn);
- dev->rtnl_link_ops = &sit_link_ops;
-
dev_hold(dev);
ipip6_tunnel_link(sitn, t);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 5d2c2af..22e28a4 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -257,6 +257,7 @@
struct sock *sk, *result;
struct hlist_nulls_node *node;
int score, badness, matches = 0, reuseport = 0;
+ bool select_ok = true;
u32 hash = 0;
begin:
@@ -270,14 +271,18 @@
badness = score;
reuseport = sk->sk_reuseport;
if (reuseport) {
- struct sock *sk2;
hash = udp6_ehashfn(net, daddr, hnum,
saddr, sport);
- sk2 = reuseport_select_sock(sk, hash, skb,
- sizeof(struct udphdr));
- if (sk2) {
- result = sk2;
- goto found;
+ if (select_ok) {
+ struct sock *sk2;
+
+ sk2 = reuseport_select_sock(sk, hash, skb,
+ sizeof(struct udphdr));
+ if (sk2) {
+ result = sk2;
+ select_ok = false;
+ goto found;
+ }
}
matches = 1;
}
@@ -321,6 +326,7 @@
unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask);
struct udp_hslot *hslot2, *hslot = &udptable->hash[slot];
int score, badness, matches = 0, reuseport = 0;
+ bool select_ok = true;
u32 hash = 0;
rcu_read_lock();
@@ -358,14 +364,18 @@
badness = score;
reuseport = sk->sk_reuseport;
if (reuseport) {
- struct sock *sk2;
hash = udp6_ehashfn(net, daddr, hnum,
saddr, sport);
- sk2 = reuseport_select_sock(sk, hash, skb,
+ if (select_ok) {
+ struct sock *sk2;
+
+ sk2 = reuseport_select_sock(sk, hash, skb,
sizeof(struct udphdr));
- if (sk2) {
- result = sk2;
- goto found;
+ if (sk2) {
+ result = sk2;
+ select_ok = false;
+ goto found;
+ }
}
matches = 1;
}
diff --git a/net/irda/ircomm/ircomm_param.c b/net/irda/ircomm/ircomm_param.c
index 3c4caa6..5728e76 100644
--- a/net/irda/ircomm/ircomm_param.c
+++ b/net/irda/ircomm/ircomm_param.c
@@ -134,11 +134,10 @@
return -1;
}
skb_put(skb, count);
+ pr_debug("%s(), skb->len=%d\n", __func__, skb->len);
spin_unlock_irqrestore(&self->spinlock, flags);
- pr_debug("%s(), skb->len=%d\n", __func__ , skb->len);
-
if (flush) {
/* ircomm_tty_do_softint will take care of the rest */
schedule_work(&self->tqueue);
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index ef50a94..fc3598a 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -708,6 +708,9 @@
if (!addr || addr->sa_family != AF_IUCV)
return -EINVAL;
+ if (addr_len < sizeof(struct sockaddr_iucv))
+ return -EINVAL;
+
lock_sock(sk);
if (sk->sk_state != IUCV_OPEN) {
err = -EBADFD;
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index f7fc0e0..978d3bc 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -1733,7 +1733,6 @@
if (sdata->vif.type != NL80211_IFTYPE_ADHOC)
continue;
sdata->u.ibss.last_scan_completed = jiffies;
- ieee80211_queue_work(&local->hw, &sdata->work);
}
mutex_unlock(&local->iflist_mtx);
}
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 6bcf0fa..8190bf2 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -248,6 +248,7 @@
/* wait for scan work complete */
flush_workqueue(local->workqueue);
+ flush_work(&local->sched_scan_stopped_work);
WARN(test_bit(SCAN_HW_SCANNING, &local->scanning),
"%s called with hardware scan in progress\n", __func__);
@@ -256,6 +257,11 @@
list_for_each_entry(sdata, &local->interfaces, list)
flush_delayed_work(&sdata->dec_tailroom_needed_wk);
ieee80211_scan_cancel(local);
+
+ /* make sure any new ROC will consider local->in_reconfig */
+ flush_delayed_work(&local->roc_work);
+ flush_work(&local->hw_roc_done);
+
ieee80211_reconfig(local);
rtnl_unlock();
}
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index fa28500..6f85b6a 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -1370,17 +1370,6 @@
sdata_unlock(sdata);
}
-void ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local)
-{
- struct ieee80211_sub_if_data *sdata;
-
- rcu_read_lock();
- list_for_each_entry_rcu(sdata, &local->interfaces, list)
- if (ieee80211_vif_is_mesh(&sdata->vif) &&
- ieee80211_sdata_running(sdata))
- ieee80211_queue_work(&local->hw, &sdata->work);
- rcu_read_unlock();
-}
void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata)
{
diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h
index a159634..4a8019f 100644
--- a/net/mac80211/mesh.h
+++ b/net/mac80211/mesh.h
@@ -362,14 +362,10 @@
return sdata->u.mesh.mesh_pp_id == IEEE80211_PATH_PROTOCOL_HWMP;
}
-void ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local);
-
void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata);
void mesh_sync_adjust_tbtt(struct ieee80211_sub_if_data *sdata);
void ieee80211s_stop(void);
#else
-static inline void
-ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local) {}
static inline bool mesh_path_sel_is_hwmp(struct ieee80211_sub_if_data *sdata)
{ return false; }
static inline void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata)
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 1c342e2..bfbb1ac 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -4005,8 +4005,6 @@
if (!ieee80211_hw_check(&sdata->local->hw, CONNECTION_MONITOR))
ieee80211_queue_work(&sdata->local->hw,
&sdata->u.mgd.monitor_work);
- /* and do all the other regular work too */
- ieee80211_queue_work(&sdata->local->hw, &sdata->work);
}
}
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index 8b2f4ea..55a9c5b 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -252,14 +252,11 @@
static void ieee80211_handle_roc_started(struct ieee80211_roc_work *roc,
unsigned long start_time)
{
- struct ieee80211_local *local = roc->sdata->local;
-
if (WARN_ON(roc->notified))
return;
roc->start_time = start_time;
roc->started = true;
- roc->hw_begun = true;
if (roc->mgmt_tx_cookie) {
if (!WARN_ON(!roc->frame)) {
@@ -274,9 +271,6 @@
}
roc->notified = true;
-
- if (!local->ops->remain_on_channel)
- ieee80211_recalc_sw_work(local, start_time);
}
static void ieee80211_hw_roc_start(struct work_struct *work)
@@ -291,6 +285,7 @@
if (!roc->started)
break;
+ roc->hw_begun = true;
ieee80211_handle_roc_started(roc, local->hw_roc_start_time);
}
@@ -413,6 +408,10 @@
return;
}
+ /* defer roc if driver is not started (i.e. during reconfig) */
+ if (local->in_reconfig)
+ return;
+
roc = list_first_entry(&local->roc_list, struct ieee80211_roc_work,
list);
@@ -534,8 +533,10 @@
* begin, otherwise they'll both be marked properly by the work
* struct that runs once the driver notifies us of the beginning
*/
- if (cur_roc->hw_begun)
+ if (cur_roc->hw_begun) {
+ new_roc->hw_begun = true;
ieee80211_handle_roc_started(new_roc, now);
+ }
return true;
}
@@ -658,6 +659,7 @@
queued = true;
roc->on_channel = tmp->on_channel;
ieee80211_handle_roc_started(roc, now);
+ ieee80211_recalc_sw_work(local, now);
break;
}
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index a413e52..ae980ce 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -314,6 +314,7 @@
bool was_scanning = local->scanning;
struct cfg80211_scan_request *scan_req;
struct ieee80211_sub_if_data *scan_sdata;
+ struct ieee80211_sub_if_data *sdata;
lockdep_assert_held(&local->mtx);
@@ -373,7 +374,16 @@
ieee80211_mlme_notify_scan_completed(local);
ieee80211_ibss_notify_scan_completed(local);
- ieee80211_mesh_notify_scan_completed(local);
+
+ /* Requeue all the work that might have been ignored while
+ * the scan was in progress; if there was none this will
+ * just be a no-op for the particular interface.
+ */
+ list_for_each_entry_rcu(sdata, &local->interfaces, list) {
+ if (ieee80211_sdata_running(sdata))
+ ieee80211_queue_work(&sdata->local->hw, &sdata->work);
+ }
+
if (was_scanning)
ieee80211_start_next_roc(local);
}
@@ -1213,6 +1223,14 @@
trace_api_sched_scan_stopped(local);
+ /*
+ * this shouldn't really happen, so for simplicity
+ * simply ignore it, and let mac80211 reconfigure
+ * the sched scan later on.
+ */
+ if (local->in_reconfig)
+ return;
+
schedule_work(&local->sched_scan_stopped_work);
}
EXPORT_SYMBOL(ieee80211_sched_scan_stopped);
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 4402ad5..a4a4f89 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -1453,7 +1453,7 @@
more_data = ieee80211_sta_ps_more_data(sta, ignored_acs, reason, driver_release_tids);
- if (reason == IEEE80211_FRAME_RELEASE_PSPOLL)
+ if (driver_release_tids && reason == IEEE80211_FRAME_RELEASE_PSPOLL)
driver_release_tids =
BIT(find_highest_prio_tid(driver_release_tids));
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 5bad05e..6101deb 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -51,6 +51,11 @@
struct ieee80211_hdr *hdr = (void *)skb->data;
int ac;
+ if (info->flags & IEEE80211_TX_CTL_NO_PS_BUFFER) {
+ ieee80211_free_txskb(&local->hw, skb);
+ return;
+ }
+
/*
* This skb 'survived' a round-trip through the driver, and
* hopefully the driver didn't mangle it too badly. However,
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 3943d4b..58f58bd 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -2043,16 +2043,26 @@
*/
if (sched_scan_req->n_scan_plans > 1 ||
__ieee80211_request_sched_scan_start(sched_scan_sdata,
- sched_scan_req))
+ sched_scan_req)) {
+ RCU_INIT_POINTER(local->sched_scan_sdata, NULL);
+ RCU_INIT_POINTER(local->sched_scan_req, NULL);
sched_scan_stopped = true;
+ }
mutex_unlock(&local->mtx);
if (sched_scan_stopped)
cfg80211_sched_scan_stopped_rtnl(local->hw.wiphy);
wake_up:
- local->in_reconfig = false;
- barrier();
+ if (local->in_reconfig) {
+ local->in_reconfig = false;
+ barrier();
+
+ /* Restart deferred ROCs */
+ mutex_lock(&local->mtx);
+ ieee80211_start_next_roc(local);
+ mutex_unlock(&local->mtx);
+ }
if (local->monitors == local->open_count && local->monitors > 0)
ieee80211_add_virtual_monitor(local);
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index 43d8c98..f0f688d 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -164,8 +164,6 @@
};
struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
- if (e.cidr == 0)
- return -EINVAL;
if (adt == IPSET_TEST)
e.cidr = HOST_MASK;
@@ -377,8 +375,6 @@
};
struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
- if (e.cidr == 0)
- return -EINVAL;
if (adt == IPSET_TEST)
e.cidr = HOST_MASK;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 3cb3cb8..58882de 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -66,6 +66,21 @@
__cacheline_aligned_in_smp DEFINE_SPINLOCK(nf_conntrack_expect_lock);
EXPORT_SYMBOL_GPL(nf_conntrack_expect_lock);
+static __read_mostly spinlock_t nf_conntrack_locks_all_lock;
+static __read_mostly bool nf_conntrack_locks_all;
+
+void nf_conntrack_lock(spinlock_t *lock) __acquires(lock)
+{
+ spin_lock(lock);
+ while (unlikely(nf_conntrack_locks_all)) {
+ spin_unlock(lock);
+ spin_lock(&nf_conntrack_locks_all_lock);
+ spin_unlock(&nf_conntrack_locks_all_lock);
+ spin_lock(lock);
+ }
+}
+EXPORT_SYMBOL_GPL(nf_conntrack_lock);
+
static void nf_conntrack_double_unlock(unsigned int h1, unsigned int h2)
{
h1 %= CONNTRACK_LOCKS;
@@ -82,12 +97,12 @@
h1 %= CONNTRACK_LOCKS;
h2 %= CONNTRACK_LOCKS;
if (h1 <= h2) {
- spin_lock(&nf_conntrack_locks[h1]);
+ nf_conntrack_lock(&nf_conntrack_locks[h1]);
if (h1 != h2)
spin_lock_nested(&nf_conntrack_locks[h2],
SINGLE_DEPTH_NESTING);
} else {
- spin_lock(&nf_conntrack_locks[h2]);
+ nf_conntrack_lock(&nf_conntrack_locks[h2]);
spin_lock_nested(&nf_conntrack_locks[h1],
SINGLE_DEPTH_NESTING);
}
@@ -102,16 +117,19 @@
{
int i;
- for (i = 0; i < CONNTRACK_LOCKS; i++)
- spin_lock_nested(&nf_conntrack_locks[i], i);
+ spin_lock(&nf_conntrack_locks_all_lock);
+ nf_conntrack_locks_all = true;
+
+ for (i = 0; i < CONNTRACK_LOCKS; i++) {
+ spin_lock(&nf_conntrack_locks[i]);
+ spin_unlock(&nf_conntrack_locks[i]);
+ }
}
static void nf_conntrack_all_unlock(void)
{
- int i;
-
- for (i = 0; i < CONNTRACK_LOCKS; i++)
- spin_unlock(&nf_conntrack_locks[i]);
+ nf_conntrack_locks_all = false;
+ spin_unlock(&nf_conntrack_locks_all_lock);
}
unsigned int nf_conntrack_htable_size __read_mostly;
@@ -757,7 +775,7 @@
hash = hash_bucket(_hash, net);
for (; i < net->ct.htable_size; i++) {
lockp = &nf_conntrack_locks[hash % CONNTRACK_LOCKS];
- spin_lock(lockp);
+ nf_conntrack_lock(lockp);
if (read_seqcount_retry(&net->ct.generation, sequence)) {
spin_unlock(lockp);
goto restart;
@@ -1382,7 +1400,7 @@
for (; *bucket < net->ct.htable_size; (*bucket)++) {
lockp = &nf_conntrack_locks[*bucket % CONNTRACK_LOCKS];
local_bh_disable();
- spin_lock(lockp);
+ nf_conntrack_lock(lockp);
if (*bucket < net->ct.htable_size) {
hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) {
if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index bd9d315..3b40ec5 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -425,7 +425,7 @@
}
local_bh_disable();
for (i = 0; i < net->ct.htable_size; i++) {
- spin_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);
+ nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);
if (i < net->ct.htable_size) {
hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode)
unhelp(h, me);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index dbb1bb3..355e855 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -840,7 +840,7 @@
for (; cb->args[0] < net->ct.htable_size; cb->args[0]++) {
restart:
lockp = &nf_conntrack_locks[cb->args[0] % CONNTRACK_LOCKS];
- spin_lock(lockp);
+ nf_conntrack_lock(lockp);
if (cb->args[0] >= net->ct.htable_size) {
spin_unlock(lockp);
goto out;
diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c
index b6605e0..5eefe4a 100644
--- a/net/netfilter/nf_tables_netdev.c
+++ b/net/netfilter/nf_tables_netdev.c
@@ -224,12 +224,12 @@
nft_register_chain_type(&nft_filter_chain_netdev);
ret = register_pernet_subsys(&nf_tables_netdev_net_ops);
- if (ret < 0)
+ if (ret < 0) {
nft_unregister_chain_type(&nft_filter_chain_netdev);
-
+ return ret;
+ }
register_netdevice_notifier(&nf_tables_netdev_notifier);
-
- return ret;
+ return 0;
}
static void __exit nf_tables_netdev_exit(void)
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index 5d010f2..94837d2 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -307,12 +307,12 @@
local_bh_disable();
for (i = 0; i < net->ct.htable_size; i++) {
- spin_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);
+ nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);
if (i < net->ct.htable_size) {
hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode)
untimeout(h, timeout);
}
- spin_unlock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);
+ nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);
}
local_bh_enable();
}
diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c
index 383c171..b78c28b 100644
--- a/net/netfilter/nft_byteorder.c
+++ b/net/netfilter/nft_byteorder.c
@@ -46,16 +46,14 @@
switch (priv->op) {
case NFT_BYTEORDER_NTOH:
for (i = 0; i < priv->len / 8; i++) {
- src64 = get_unaligned_be64(&src[i]);
- src64 = be64_to_cpu((__force __be64)src64);
+ src64 = get_unaligned((u64 *)&src[i]);
put_unaligned_be64(src64, &dst[i]);
}
break;
case NFT_BYTEORDER_HTON:
for (i = 0; i < priv->len / 8; i++) {
src64 = get_unaligned_be64(&src[i]);
- src64 = (__force u64)cpu_to_be64(src64);
- put_unaligned_be64(src64, &dst[i]);
+ put_unaligned(src64, (u64 *)&dst[i]);
}
break;
}
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index a0eb216..d4a4619 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -127,6 +127,7 @@
NF_CT_LABELS_MAX_SIZE - size);
return;
}
+#endif
case NFT_CT_BYTES: /* fallthrough */
case NFT_CT_PKTS: {
const struct nf_conn_acct *acct = nf_conn_acct_find(ct);
@@ -138,7 +139,6 @@
memcpy(dest, &count, sizeof(count));
return;
}
-#endif
default:
break;
}
diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c
index b7c43de..e118397 100644
--- a/net/netfilter/xt_TCPMSS.c
+++ b/net/netfilter/xt_TCPMSS.c
@@ -228,7 +228,7 @@
{
struct ipv6hdr *ipv6h = ipv6_hdr(skb);
u8 nexthdr;
- __be16 frag_off;
+ __be16 frag_off, oldlen, newlen;
int tcphoff;
int ret;
@@ -244,7 +244,12 @@
return NF_DROP;
if (ret > 0) {
ipv6h = ipv6_hdr(skb);
- ipv6h->payload_len = htons(ntohs(ipv6h->payload_len) + ret);
+ oldlen = ipv6h->payload_len;
+ newlen = htons(ntohs(oldlen) + ret);
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
+ skb->csum = csum_add(csum_sub(skb->csum, oldlen),
+ newlen);
+ ipv6h->payload_len = newlen;
}
return XT_CONTINUE;
}
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 81dc1bb..f1ffb34 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2831,7 +2831,8 @@
* reasonable static buffer based on the expected largest dump of a
* single netdev. The outcome is MSG_TRUNC error.
*/
- skb_reserve(skb, skb_tailroom(skb) - alloc_size);
+ if (!netlink_rx_is_mmaped(sk))
+ skb_reserve(skb, skb_tailroom(skb) - alloc_size);
netlink_skb_set_owner_r(skb, sk);
len = cb->dump(skb, cb);
diff --git a/net/rfkill/core.c b/net/rfkill/core.c
index f53bf3b6..cf5b69a 100644
--- a/net/rfkill/core.c
+++ b/net/rfkill/core.c
@@ -1095,17 +1095,6 @@
return res;
}
-static bool rfkill_readable(struct rfkill_data *data)
-{
- bool r;
-
- mutex_lock(&data->mtx);
- r = !list_empty(&data->events);
- mutex_unlock(&data->mtx);
-
- return r;
-}
-
static ssize_t rfkill_fop_read(struct file *file, char __user *buf,
size_t count, loff_t *pos)
{
@@ -1122,8 +1111,11 @@
goto out;
}
mutex_unlock(&data->mtx);
+ /* since we re-check and it just compares pointers,
+ * using !list_empty() without locking isn't a problem
+ */
ret = wait_event_interruptible(data->read_wait,
- rfkill_readable(data));
+ !list_empty(&data->events));
mutex_lock(&data->mtx);
if (ret)
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index f26bdea..a1cd778 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -403,6 +403,8 @@
if (len <= cl->deficit) {
cl->deficit -= len;
skb = qdisc_dequeue_peeked(cl->qdisc);
+ if (unlikely(skb == NULL))
+ goto out;
if (cl->qdisc->q.qlen == 0)
list_del(&cl->alist);
diff --git a/net/sctp/input.c b/net/sctp/input.c
index bf61dfb..49d2cc7 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -935,15 +935,22 @@
struct sctp_transport **pt)
{
struct sctp_transport *t;
+ struct sctp_association *asoc = NULL;
+ rcu_read_lock();
t = sctp_addrs_lookup_transport(net, local, peer);
- if (!t || t->dead)
- return NULL;
+ if (!t || !sctp_transport_hold(t))
+ goto out;
- sctp_association_hold(t->asoc);
+ asoc = t->asoc;
+ sctp_association_hold(asoc);
*pt = t;
- return t->asoc;
+ sctp_transport_put(t);
+
+out:
+ rcu_read_unlock();
+ return asoc;
}
/* Look up an association. protected by RCU read lock */
@@ -955,9 +962,7 @@
{
struct sctp_association *asoc;
- rcu_read_lock();
asoc = __sctp_lookup_association(net, laddr, paddr, transportp);
- rcu_read_unlock();
return asoc;
}
diff --git a/net/sctp/proc.c b/net/sctp/proc.c
index 684c5b3..ded7d93 100644
--- a/net/sctp/proc.c
+++ b/net/sctp/proc.c
@@ -165,8 +165,6 @@
list_for_each_entry_rcu(transport, &assoc->peer.transport_addr_list,
transports) {
addr = &transport->ipaddr;
- if (transport->dead)
- continue;
af = sctp_get_af_specific(addr->sa.sa_family);
if (af->cmp_addr(addr, primary)) {
@@ -380,6 +378,8 @@
}
transport = (struct sctp_transport *)v;
+ if (!sctp_transport_hold(transport))
+ return 0;
assoc = transport->asoc;
epb = &assoc->base;
sk = epb->sk;
@@ -412,6 +412,8 @@
sk->sk_rcvbuf);
seq_printf(seq, "\n");
+ sctp_transport_put(transport);
+
return 0;
}
@@ -489,12 +491,12 @@
}
tsp = (struct sctp_transport *)v;
+ if (!sctp_transport_hold(tsp))
+ return 0;
assoc = tsp->asoc;
list_for_each_entry_rcu(tsp, &assoc->peer.transport_addr_list,
transports) {
- if (tsp->dead)
- continue;
/*
* The remote address (ADDR)
*/
@@ -544,6 +546,8 @@
seq_printf(seq, "\n");
}
+ sctp_transport_put(tsp);
+
return 0;
}
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 2e21384..b5327bb 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -259,12 +259,6 @@
goto out_unlock;
}
- /* Is this transport really dead and just waiting around for
- * the timer to let go of the reference?
- */
- if (transport->dead)
- goto out_unlock;
-
/* Run through the state machine. */
error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT,
SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_T3_RTX),
@@ -380,12 +374,6 @@
goto out_unlock;
}
- /* Is this structure just waiting around for us to actually
- * get destroyed?
- */
- if (transport->dead)
- goto out_unlock;
-
error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT,
SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_HEARTBEAT),
asoc->state, asoc->ep, asoc,
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 9bb80ec..5ca2ebf 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -6636,6 +6636,7 @@
if (cmsgs->srinfo->sinfo_flags &
~(SCTP_UNORDERED | SCTP_ADDR_OVER |
+ SCTP_SACK_IMMEDIATELY |
SCTP_ABORT | SCTP_EOF))
return -EINVAL;
break;
@@ -6659,6 +6660,7 @@
if (cmsgs->sinfo->snd_flags &
~(SCTP_UNORDERED | SCTP_ADDR_OVER |
+ SCTP_SACK_IMMEDIATELY |
SCTP_ABORT | SCTP_EOF))
return -EINVAL;
break;
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index aab9e3f..a431c14 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -132,8 +132,6 @@
*/
void sctp_transport_free(struct sctp_transport *transport)
{
- transport->dead = 1;
-
/* Try to delete the heartbeat timer. */
if (del_timer(&transport->hb_timer))
sctp_transport_put(transport);
@@ -169,7 +167,7 @@
*/
static void sctp_transport_destroy(struct sctp_transport *transport)
{
- if (unlikely(!transport->dead)) {
+ if (unlikely(atomic_read(&transport->refcnt))) {
WARN(1, "Attempt to destroy undead transport %p!\n", transport);
return;
}
@@ -296,9 +294,9 @@
}
/* Hold a reference to a transport. */
-void sctp_transport_hold(struct sctp_transport *transport)
+int sctp_transport_hold(struct sctp_transport *transport)
{
- atomic_inc(&transport->refcnt);
+ return atomic_add_unless(&transport->refcnt, 1, 0);
}
/* Release a reference to a transport and clean up
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index ebc661d..47f7da5 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -20,6 +20,7 @@
#include <linux/list.h>
#include <linux/workqueue.h>
#include <linux/if_vlan.h>
+#include <linux/rtnetlink.h>
#include <net/ip_fib.h>
#include <net/switchdev.h>
@@ -567,7 +568,6 @@
}
EXPORT_SYMBOL_GPL(switchdev_port_obj_dump);
-static DEFINE_MUTEX(switchdev_mutex);
static RAW_NOTIFIER_HEAD(switchdev_notif_chain);
/**
@@ -582,9 +582,9 @@
{
int err;
- mutex_lock(&switchdev_mutex);
+ rtnl_lock();
err = raw_notifier_chain_register(&switchdev_notif_chain, nb);
- mutex_unlock(&switchdev_mutex);
+ rtnl_unlock();
return err;
}
EXPORT_SYMBOL_GPL(register_switchdev_notifier);
@@ -600,9 +600,9 @@
{
int err;
- mutex_lock(&switchdev_mutex);
+ rtnl_lock();
err = raw_notifier_chain_unregister(&switchdev_notif_chain, nb);
- mutex_unlock(&switchdev_mutex);
+ rtnl_unlock();
return err;
}
EXPORT_SYMBOL_GPL(unregister_switchdev_notifier);
@@ -616,16 +616,17 @@
* Call all network notifier blocks. This should be called by driver
* when it needs to propagate hardware event.
* Return values are same as for atomic_notifier_call_chain().
+ * rtnl_lock must be held.
*/
int call_switchdev_notifiers(unsigned long val, struct net_device *dev,
struct switchdev_notifier_info *info)
{
int err;
+ ASSERT_RTNL();
+
info->dev = dev;
- mutex_lock(&switchdev_mutex);
err = raw_notifier_call_chain(&switchdev_notif_chain, val, info);
- mutex_unlock(&switchdev_mutex);
return err;
}
EXPORT_SYMBOL_GPL(call_switchdev_notifiers);
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index 350cca3..69ee2ee 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -289,15 +289,14 @@
struct sockaddr_tipc *addr, void *usr_data,
void *buf, size_t len)
{
- struct tipc_subscriber *subscriber = usr_data;
+ struct tipc_subscriber *subscrb = usr_data;
struct tipc_subscription *sub = NULL;
struct tipc_net *tn = net_generic(net, tipc_net_id);
- tipc_subscrp_create(net, (struct tipc_subscr *)buf, subscriber, &sub);
- if (sub)
- tipc_nametbl_subscribe(sub);
- else
- tipc_conn_terminate(tn->topsrv, subscriber->conid);
+ if (tipc_subscrp_create(net, (struct tipc_subscr *)buf, subscrb, &sub))
+ return tipc_conn_terminate(tn->topsrv, subscrb->conid);
+
+ tipc_nametbl_subscribe(sub);
}
/* Handle one request to establish a new subscriber */
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index c5bf5ef..49d5093 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2339,6 +2339,7 @@
if (signal_pending(current)) {
err = sock_intr_errno(timeo);
+ scm_destroy(&scm);
goto out;
}
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 3b0ce1c..547ceec 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -231,20 +231,22 @@
/* IEEE 802.11b/g, channels 1..11 */
REG_RULE(2412-10, 2462+10, 40, 6, 20, 0),
/* IEEE 802.11b/g, channels 12..13. */
- REG_RULE(2467-10, 2472+10, 40, 6, 20,
- NL80211_RRF_NO_IR),
+ REG_RULE(2467-10, 2472+10, 20, 6, 20,
+ NL80211_RRF_NO_IR | NL80211_RRF_AUTO_BW),
/* IEEE 802.11 channel 14 - Only JP enables
* this and for 802.11b only */
REG_RULE(2484-10, 2484+10, 20, 6, 20,
NL80211_RRF_NO_IR |
NL80211_RRF_NO_OFDM),
/* IEEE 802.11a, channel 36..48 */
- REG_RULE(5180-10, 5240+10, 160, 6, 20,
- NL80211_RRF_NO_IR),
+ REG_RULE(5180-10, 5240+10, 80, 6, 20,
+ NL80211_RRF_NO_IR |
+ NL80211_RRF_AUTO_BW),
/* IEEE 802.11a, channel 52..64 - DFS required */
- REG_RULE(5260-10, 5320+10, 160, 6, 20,
+ REG_RULE(5260-10, 5320+10, 80, 6, 20,
NL80211_RRF_NO_IR |
+ NL80211_RRF_AUTO_BW |
NL80211_RRF_DFS),
/* IEEE 802.11a, channel 100..144 - DFS required */
@@ -2745,7 +2747,7 @@
const struct ieee80211_power_rule *power_rule = NULL;
char bw[32], cac_time[32];
- pr_info(" (start_freq - end_freq @ bandwidth), (max_antenna_gain, max_eirp), (dfs_cac_time)\n");
+ pr_debug(" (start_freq - end_freq @ bandwidth), (max_antenna_gain, max_eirp), (dfs_cac_time)\n");
for (i = 0; i < rd->n_reg_rules; i++) {
reg_rule = &rd->reg_rules[i];
@@ -2772,7 +2774,7 @@
* in certain regions
*/
if (power_rule->max_antenna_gain)
- pr_info(" (%d KHz - %d KHz @ %s), (%d mBi, %d mBm), (%s)\n",
+ pr_debug(" (%d KHz - %d KHz @ %s), (%d mBi, %d mBm), (%s)\n",
freq_range->start_freq_khz,
freq_range->end_freq_khz,
bw,
@@ -2780,7 +2782,7 @@
power_rule->max_eirp,
cac_time);
else
- pr_info(" (%d KHz - %d KHz @ %s), (N/A, %d mBm), (%s)\n",
+ pr_debug(" (%d KHz - %d KHz @ %s), (N/A, %d mBm), (%s)\n",
freq_range->start_freq_khz,
freq_range->end_freq_khz,
bw,
@@ -2813,35 +2815,35 @@
struct cfg80211_registered_device *rdev;
rdev = cfg80211_rdev_by_wiphy_idx(lr->wiphy_idx);
if (rdev) {
- pr_info("Current regulatory domain updated by AP to: %c%c\n",
+ pr_debug("Current regulatory domain updated by AP to: %c%c\n",
rdev->country_ie_alpha2[0],
rdev->country_ie_alpha2[1]);
} else
- pr_info("Current regulatory domain intersected:\n");
+ pr_debug("Current regulatory domain intersected:\n");
} else
- pr_info("Current regulatory domain intersected:\n");
+ pr_debug("Current regulatory domain intersected:\n");
} else if (is_world_regdom(rd->alpha2)) {
- pr_info("World regulatory domain updated:\n");
+ pr_debug("World regulatory domain updated:\n");
} else {
if (is_unknown_alpha2(rd->alpha2))
- pr_info("Regulatory domain changed to driver built-in settings (unknown country)\n");
+ pr_debug("Regulatory domain changed to driver built-in settings (unknown country)\n");
else {
if (reg_request_cell_base(lr))
- pr_info("Regulatory domain changed to country: %c%c by Cell Station\n",
+ pr_debug("Regulatory domain changed to country: %c%c by Cell Station\n",
rd->alpha2[0], rd->alpha2[1]);
else
- pr_info("Regulatory domain changed to country: %c%c\n",
+ pr_debug("Regulatory domain changed to country: %c%c\n",
rd->alpha2[0], rd->alpha2[1]);
}
}
- pr_info(" DFS Master region: %s", reg_dfs_region_str(rd->dfs_region));
+ pr_debug(" DFS Master region: %s", reg_dfs_region_str(rd->dfs_region));
print_rd_rules(rd);
}
static void print_regdomain_info(const struct ieee80211_regdomain *rd)
{
- pr_info("Regulatory domain: %c%c\n", rd->alpha2[0], rd->alpha2[1]);
+ pr_debug("Regulatory domain: %c%c\n", rd->alpha2[0], rd->alpha2[1]);
print_rd_rules(rd);
}
@@ -2862,7 +2864,8 @@
return -EALREADY;
if (!is_valid_rd(rd)) {
- pr_err("Invalid regulatory domain detected:\n");
+ pr_err("Invalid regulatory domain detected: %c%c\n",
+ rd->alpha2[0], rd->alpha2[1]);
print_regdomain_info(rd);
return -EINVAL;
}
@@ -2898,7 +2901,8 @@
return -EALREADY;
if (!is_valid_rd(rd)) {
- pr_err("Invalid regulatory domain detected:\n");
+ pr_err("Invalid regulatory domain detected: %c%c\n",
+ rd->alpha2[0], rd->alpha2[1]);
print_regdomain_info(rd);
return -EINVAL;
}
@@ -2956,7 +2960,8 @@
*/
if (!is_valid_rd(rd)) {
- pr_err("Invalid regulatory domain detected:\n");
+ pr_err("Invalid regulatory domain detected: %c%c\n",
+ rd->alpha2[0], rd->alpha2[1]);
print_regdomain_info(rd);
return -EINVAL;
}
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 0a22407..5d34815 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -77,6 +77,9 @@
# Define NO_AUXTRACE if you do not want AUX area tracing support
#
# Define NO_LIBBPF if you do not want BPF support
+#
+# Define FEATURES_DUMP to provide features detection dump file
+# and bypass the feature detection
# As per kernel Makefile, avoid funny character set dependencies
unexport LC_ALL
@@ -166,6 +169,15 @@
include config/Makefile
endif
+# The FEATURE_DUMP_EXPORT holds location of the actual
+# FEATURE_DUMP file to be used to bypass feature detection
+# (for bpf or any other subproject)
+ifeq ($(FEATURES_DUMP),)
+FEATURE_DUMP_EXPORT := $(realpath $(OUTPUT)FEATURE-DUMP)
+else
+FEATURE_DUMP_EXPORT := $(FEATURES_DUMP)
+endif
+
export prefix bindir sharedir sysconfdir DESTDIR
# sparse is architecture-neutral, which means that we need to tell it
@@ -436,7 +448,7 @@
$(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null
$(LIBBPF): fixdep FORCE
- $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(realpath $(OUTPUT)FEATURE-DUMP)
+ $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(FEATURE_DUMP_EXPORT)
$(LIBBPF)-clean:
$(call QUIET_CLEAN, libbpf)
@@ -611,6 +623,17 @@
$(python-clean)
#
+# To provide FEATURE-DUMP into $(FEATURE_DUMP_COPY)
+# file if defined, with no further action.
+feature-dump:
+ifdef FEATURE_DUMP_COPY
+ @cp $(OUTPUT)FEATURE-DUMP $(FEATURE_DUMP_COPY)
+ @echo "FEATURE-DUMP file copied into $(FEATURE_DUMP_COPY)"
+else
+ @echo "FEATURE-DUMP file available in $(OUTPUT)FEATURE-DUMP"
+endif
+
+#
# Trick: if ../../.git does not exist - we are building out of tree for example,
# then force version regeneration:
#
diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c
index 3e89ba8..7f064eb 100644
--- a/tools/perf/arch/x86/tests/intel-cqm.c
+++ b/tools/perf/arch/x86/tests/intel-cqm.c
@@ -17,7 +17,7 @@
if (pid)
return pid;
- while(1);
+ while(1)
sleep(5);
return 0;
}
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index e5959c1..511141b 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -181,7 +181,11 @@
EXTLIBS = -lpthread -lrt -lm -ldl
+ifeq ($(FEATURES_DUMP),)
include $(srctree)/tools/build/Makefile.feature
+else
+include $(FEATURES_DUMP)
+endif
ifeq ($(feature-stackprotector-all), 1)
CFLAGS += -fstack-protector-all
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index df38dec..f918015 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -5,7 +5,7 @@
# no target specified, trigger the whole suite
all:
@echo "Testing Makefile"; $(MAKE) -sf tests/make MK=Makefile
- @echo "Testing Makefile.perf"; $(MAKE) -sf tests/make MK=Makefile.perf
+ @echo "Testing Makefile.perf"; $(MAKE) -sf tests/make MK=Makefile.perf SET_PARALLEL=1 SET_O=1
else
# run only specific test over 'Makefile'
%:
@@ -13,6 +13,26 @@
endif
else
PERF := .
+PERF_O := $(PERF)
+O_OPT :=
+
+ifneq ($(O),)
+ FULL_O := $(shell readlink -f $(O) || echo $(O))
+ PERF_O := $(FULL_O)
+ ifeq ($(SET_O),1)
+ O_OPT := 'O=$(FULL_O)'
+ endif
+ K_O_OPT := 'O=$(FULL_O)'
+endif
+
+PARALLEL_OPT=
+ifeq ($(SET_PARALLEL),1)
+ cores := $(shell (getconf _NPROCESSORS_ONLN || egrep -c '^processor|^CPU[0-9]' /proc/cpuinfo) 2>/dev/null)
+ ifeq ($(cores),0)
+ cores := 1
+ endif
+ PARALLEL_OPT="-j$(cores)"
+endif
# As per kernel Makefile, avoid funny character set dependencies
unexport LC_ALL
@@ -156,11 +176,11 @@
test_make_help_O := $(test_ok)
test_make_doc_O := $(test_ok)
-test_make_python_perf_so := test -f $(PERF)/python/perf.so
+test_make_python_perf_so := test -f $(PERF_O)/python/perf.so
-test_make_perf_o := test -f $(PERF)/perf.o
-test_make_util_map_o := test -f $(PERF)/util/map.o
-test_make_util_pmu_bison_o := test -f $(PERF)/util/pmu-bison.o
+test_make_perf_o := test -f $(PERF_O)/perf.o
+test_make_util_map_o := test -f $(PERF_O)/util/map.o
+test_make_util_pmu_bison_o := test -f $(PERF_O)/util/pmu-bison.o
define test_dest_files
for file in $(1); do \
@@ -227,7 +247,7 @@
test_make_util_map_o_O := test -f $$TMP_O/util/map.o
test_make_util_pmu_bison_o_O := test -f $$TMP_O/util/pmu-bison.o
-test_default = test -x $(PERF)/perf
+test_default = test -x $(PERF_O)/perf
test = $(if $(test_$1),$(test_$1),$(test_default))
test_default_O = test -x $$TMP_O/perf
@@ -247,12 +267,12 @@
MAKEFLAGS := --no-print-directory
-clean := @(cd $(PERF); make -s -f $(MK) clean >/dev/null)
+clean := @(cd $(PERF); make -s -f $(MK) $(O_OPT) clean >/dev/null)
$(run):
$(call clean)
@TMP_DEST=$$(mktemp -d); \
- cmd="cd $(PERF) && make -f $(MK) DESTDIR=$$TMP_DEST $($@)"; \
+ cmd="cd $(PERF) && make -f $(MK) $(PARALLEL_OPT) $(O_OPT) DESTDIR=$$TMP_DEST $($@)"; \
echo "- $@: $$cmd" && echo $$cmd > $@ && \
( eval $$cmd ) >> $@ 2>&1; \
echo " test: $(call test,$@)" >> $@ 2>&1; \
@@ -263,7 +283,7 @@
$(call clean)
@TMP_O=$$(mktemp -d); \
TMP_DEST=$$(mktemp -d); \
- cmd="cd $(PERF) && make -f $(MK) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \
+ cmd="cd $(PERF) && make -f $(MK) $(PARALLEL_OPT) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \
echo "- $@: $$cmd" && echo $$cmd > $@ && \
( eval $$cmd ) >> $@ 2>&1 && \
echo " test: $(call test_O,$@)" >> $@ 2>&1; \
@@ -276,17 +296,22 @@
( eval $$cmd ) >> $@ 2>&1 && \
rm -f $@
+KERNEL_O := ../..
+ifneq ($(O),)
+ KERNEL_O := $(O)
+endif
+
make_kernelsrc:
- @echo "- make -C <kernelsrc> tools/perf"
+ @echo "- make -C <kernelsrc> $(PARALLEL_OPT) $(K_O_OPT) tools/perf"
$(call clean); \
- (make -C ../.. tools/perf) > $@ 2>&1 && \
- test -x perf && rm -f $@ || (cat $@ ; false)
+ (make -C ../.. $(PARALLEL_OPT) $(K_O_OPT) tools/perf) > $@ 2>&1 && \
+ test -x $(KERNEL_O)/tools/perf/perf && rm -f $@ || (cat $@ ; false)
make_kernelsrc_tools:
- @echo "- make -C <kernelsrc>/tools perf"
+ @echo "- make -C <kernelsrc>/tools $(PARALLEL_OPT) $(K_O_OPT) perf"
$(call clean); \
- (make -C ../../tools perf) > $@ 2>&1 && \
- test -x perf && rm -f $@ || (cat $@ ; false)
+ (make -C ../../tools $(PARALLEL_OPT) $(K_O_OPT) perf) > $@ 2>&1 && \
+ test -x $(KERNEL_O)/tools/perf/perf && rm -f $@ || (cat $@ ; false)
all: $(run) $(run_O) tarpkg make_kernelsrc make_kernelsrc_tools
@echo OK
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index d4d7cc2..718bd46 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -755,11 +755,11 @@
nd = browser->curr_hot;
break;
case K_UNTAB:
- if (nd != NULL)
+ if (nd != NULL) {
nd = rb_next(nd);
if (nd == NULL)
nd = rb_first(&browser->entries);
- else
+ } else
nd = browser->curr_hot;
break;
case K_F1:
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index c226303..68a7612 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -131,6 +131,8 @@
symlen = unresolved_col_width + 4 + 2;
hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,
symlen);
+ hists__new_col_len(hists, HISTC_MEM_DCACHELINE,
+ symlen);
}
if (h->mem_info->iaddr.sym) {
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index d5636ba..40b7a0d 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1149,7 +1149,7 @@
machine = machines__find(machines, pid);
if (!machine)
- machine = machines__find(machines, DEFAULT_GUEST_KERNEL_ID);
+ machine = machines__findnew(machines, DEFAULT_GUEST_KERNEL_ID);
return machine;
}
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 2f901d1..2b58edc 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -310,7 +310,6 @@
int i, ret;
aggr->val = aggr->ena = aggr->run = 0;
- init_stats(ps->res_stats);
if (counter->per_pkg)
zero_per_pkg(counter);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 3b2de6e..ab02209 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1466,7 +1466,7 @@
* Read the build id if possible. This is required for
* DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work
*/
- if (filename__read_build_id(dso->name, build_id, BUILD_ID_SIZE) > 0)
+ if (filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0)
dso__set_build_id(dso, build_id);
/*
diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c
index 7ec7df9..0c1a7e6 100644
--- a/tools/testing/nvdimm/test/iomap.c
+++ b/tools/testing/nvdimm/test/iomap.c
@@ -113,7 +113,7 @@
}
EXPORT_SYMBOL(__wrap_devm_memremap_pages);
-pfn_t __wrap_phys_to_pfn_t(dma_addr_t addr, unsigned long flags)
+pfn_t __wrap_phys_to_pfn_t(phys_addr_t addr, unsigned long flags)
{
struct nfit_test_resource *nfit_res = get_nfit_res(addr);
diff --git a/tools/testing/selftests/timers/valid-adjtimex.c b/tools/testing/selftests/timers/valid-adjtimex.c
index e86d937..60fe3c5 100644
--- a/tools/testing/selftests/timers/valid-adjtimex.c
+++ b/tools/testing/selftests/timers/valid-adjtimex.c
@@ -45,7 +45,17 @@
}
#endif
-#define NSEC_PER_SEC 1000000000L
+#define NSEC_PER_SEC 1000000000LL
+#define USEC_PER_SEC 1000000LL
+
+#define ADJ_SETOFFSET 0x0100
+
+#include <sys/syscall.h>
+static int clock_adjtime(clockid_t id, struct timex *tx)
+{
+ return syscall(__NR_clock_adjtime, id, tx);
+}
+
/* clear NTP time_status & time_state */
int clear_time_state(void)
@@ -193,10 +203,137 @@
}
+int set_offset(long long offset, int use_nano)
+{
+ struct timex tmx = {};
+ int ret;
+
+ tmx.modes = ADJ_SETOFFSET;
+ if (use_nano) {
+ tmx.modes |= ADJ_NANO;
+
+ tmx.time.tv_sec = offset / NSEC_PER_SEC;
+ tmx.time.tv_usec = offset % NSEC_PER_SEC;
+
+ if (offset < 0 && tmx.time.tv_usec) {
+ tmx.time.tv_sec -= 1;
+ tmx.time.tv_usec += NSEC_PER_SEC;
+ }
+ } else {
+ tmx.time.tv_sec = offset / USEC_PER_SEC;
+ tmx.time.tv_usec = offset % USEC_PER_SEC;
+
+ if (offset < 0 && tmx.time.tv_usec) {
+ tmx.time.tv_sec -= 1;
+ tmx.time.tv_usec += USEC_PER_SEC;
+ }
+ }
+
+ ret = clock_adjtime(CLOCK_REALTIME, &tmx);
+ if (ret < 0) {
+ printf("(sec: %ld usec: %ld) ", tmx.time.tv_sec, tmx.time.tv_usec);
+ printf("[FAIL]\n");
+ return -1;
+ }
+ return 0;
+}
+
+int set_bad_offset(long sec, long usec, int use_nano)
+{
+ struct timex tmx = {};
+ int ret;
+
+ tmx.modes = ADJ_SETOFFSET;
+ if (use_nano)
+ tmx.modes |= ADJ_NANO;
+
+ tmx.time.tv_sec = sec;
+ tmx.time.tv_usec = usec;
+ ret = clock_adjtime(CLOCK_REALTIME, &tmx);
+ if (ret >= 0) {
+ printf("Invalid (sec: %ld usec: %ld) did not fail! ", tmx.time.tv_sec, tmx.time.tv_usec);
+ printf("[FAIL]\n");
+ return -1;
+ }
+ return 0;
+}
+
+int validate_set_offset(void)
+{
+ printf("Testing ADJ_SETOFFSET... ");
+
+ /* Test valid values */
+ if (set_offset(NSEC_PER_SEC - 1, 1))
+ return -1;
+
+ if (set_offset(-NSEC_PER_SEC + 1, 1))
+ return -1;
+
+ if (set_offset(-NSEC_PER_SEC - 1, 1))
+ return -1;
+
+ if (set_offset(5 * NSEC_PER_SEC, 1))
+ return -1;
+
+ if (set_offset(-5 * NSEC_PER_SEC, 1))
+ return -1;
+
+ if (set_offset(5 * NSEC_PER_SEC + NSEC_PER_SEC / 2, 1))
+ return -1;
+
+ if (set_offset(-5 * NSEC_PER_SEC - NSEC_PER_SEC / 2, 1))
+ return -1;
+
+ if (set_offset(USEC_PER_SEC - 1, 0))
+ return -1;
+
+ if (set_offset(-USEC_PER_SEC + 1, 0))
+ return -1;
+
+ if (set_offset(-USEC_PER_SEC - 1, 0))
+ return -1;
+
+ if (set_offset(5 * USEC_PER_SEC, 0))
+ return -1;
+
+ if (set_offset(-5 * USEC_PER_SEC, 0))
+ return -1;
+
+ if (set_offset(5 * USEC_PER_SEC + USEC_PER_SEC / 2, 0))
+ return -1;
+
+ if (set_offset(-5 * USEC_PER_SEC - USEC_PER_SEC / 2, 0))
+ return -1;
+
+ /* Test invalid values */
+ if (set_bad_offset(0, -1, 1))
+ return -1;
+ if (set_bad_offset(0, -1, 0))
+ return -1;
+ if (set_bad_offset(0, 2 * NSEC_PER_SEC, 1))
+ return -1;
+ if (set_bad_offset(0, 2 * USEC_PER_SEC, 0))
+ return -1;
+ if (set_bad_offset(0, NSEC_PER_SEC, 1))
+ return -1;
+ if (set_bad_offset(0, USEC_PER_SEC, 0))
+ return -1;
+ if (set_bad_offset(0, -NSEC_PER_SEC, 1))
+ return -1;
+ if (set_bad_offset(0, -USEC_PER_SEC, 0))
+ return -1;
+
+ printf("[OK]\n");
+ return 0;
+}
+
int main(int argc, char **argv)
{
if (validate_freq())
return ksft_exit_fail();
+ if (validate_set_offset())
+ return ksft_exit_fail();
+
return ksft_exit_pass();
}